diff options
1425 files changed, 17240 insertions, 9765 deletions
@@ -391,6 +391,10 @@ Uwe Kleine-König <ukleinek@strlen.de> Uwe Kleine-König <ukl@pengutronix.de> Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com> Valdis Kletnieks <Valdis.Kletnieks@vt.edu> +Vasily Averin <vasily.averin@linux.dev> <vvs@virtuozzo.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@openvz.org> +Vasily Averin <vasily.averin@linux.dev> <vvs@parallels.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@sw.ru> Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com> Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com> Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> diff --git a/Documentation/ABI/testing/sysfs-class-firmware-attributes b/Documentation/ABI/testing/sysfs-class-firmware-attributes index 05820365f1ec..4cdba3477176 100644 --- a/Documentation/ABI/testing/sysfs-class-firmware-attributes +++ b/Documentation/ABI/testing/sysfs-class-firmware-attributes @@ -116,7 +116,7 @@ Description: <value>[ForceIf:<attribute>=<value>] <value>[ForceIfNot:<attribute>=<value>] - For example: + For example:: LegacyOrom/dell_value_modifier has value: Disabled[ForceIf:SecureBoot=Enabled] @@ -212,7 +212,7 @@ Description: the next boot. Lenovo specific class extensions - ------------------------------ + -------------------------------- On Lenovo systems the following additional settings are available: @@ -246,9 +246,7 @@ Description: that is being referenced (e.g hdd0, hdd1 etc) This attribute defaults to device 0. - certificate: - signature: - save_signature: + certificate, signature, save_signature: These attributes are used for certificate based authentication. This is used in conjunction with a signing server as an alternative to password based authentication. @@ -257,22 +255,27 @@ Description: The attributes can be displayed to check the stored value. Some usage examples: - Installing a certificate to enable feature: - echo <supervisor password > authentication/Admin/current_password - echo <signed certificate> > authentication/Admin/certificate - Updating the installed certificate: - echo <signature> > authentication/Admin/signature - echo <signed certificate> > authentication/Admin/certificate + Installing a certificate to enable feature:: + + echo "supervisor password" > authentication/Admin/current_password + echo "signed certificate" > authentication/Admin/certificate + + Updating the installed certificate:: + + echo "signature" > authentication/Admin/signature + echo "signed certificate" > authentication/Admin/certificate - Removing the installed certificate: - echo <signature> > authentication/Admin/signature - echo '' > authentication/Admin/certificate + Removing the installed certificate:: - Changing a BIOS setting: - echo <signature> > authentication/Admin/signature - echo <save signature> > authentication/Admin/save_signature - echo Enable > attribute/PasswordBeep/current_value + echo "signature" > authentication/Admin/signature + echo "" > authentication/Admin/certificate + + Changing a BIOS setting:: + + echo "signature" > authentication/Admin/signature + echo "save signature" > authentication/Admin/save_signature + echo Enable > attribute/PasswordBeep/current_value You cannot enable certificate authentication if a supervisor password has not been set. @@ -288,9 +291,10 @@ Description: certificate_to_password: Write only attribute used to switch from certificate based authentication back to password based. - Usage: - echo <signature> > authentication/Admin/signature - echo <password> > authentication/Admin/certificate_to_password + Usage:: + + echo "signature" > authentication/Admin/signature + echo "password" > authentication/Admin/certificate_to_password What: /sys/class/firmware-attributes/*/attributes/pending_reboot @@ -345,7 +349,7 @@ Description: # echo "factory" > /sys/class/firmware-attributes/*/device/attributes/reset_bios # cat /sys/class/firmware-attributes/*/device/attributes/reset_bios - # builtinsafe lastknowngood [factory] custom + builtinsafe lastknowngood [factory] custom Note that any changes to this attribute requires a reboot for changes to take effect. diff --git a/Documentation/ABI/testing/sysfs-driver-intel_sdsi b/Documentation/ABI/testing/sysfs-driver-intel_sdsi index ab122125ff9a..96b92c105ec4 100644 --- a/Documentation/ABI/testing/sysfs-driver-intel_sdsi +++ b/Documentation/ABI/testing/sysfs-driver-intel_sdsi @@ -13,17 +13,19 @@ Description: Should the operation fail, one of the following error codes may be returned: + ========== ===== Error Code Cause - ---------- ----- - EIO General mailbox failure. Log may indicate cause. - EBUSY Mailbox is owned by another agent. - EPERM SDSI capability is not enabled in hardware. - EPROTO Failure in mailbox protocol detected by driver. + ========== ===== + EIO General mailbox failure. Log may indicate cause. + EBUSY Mailbox is owned by another agent. + EPERM SDSI capability is not enabled in hardware. + EPROTO Failure in mailbox protocol detected by driver. See log for details. - EOVERFLOW For provision commands, the size of the data + EOVERFLOW For provision commands, the size of the data exceeds what may be written. - ESPIPE Seeking is not allowed. - ETIMEDOUT Failure to complete mailbox transaction in time. + ESPIPE Seeking is not allowed. + ETIMEDOUT Failure to complete mailbox transaction in time. + ========== ===== What: /sys/bus/auxiliary/devices/intel_vsec.sdsi.X/guid Date: Feb 2022 diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs index 05482374a741..bb4681a01811 100644 --- a/Documentation/ABI/testing/sysfs-fs-erofs +++ b/Documentation/ABI/testing/sysfs-fs-erofs @@ -9,8 +9,9 @@ Description: Shows all enabled kernel features. What: /sys/fs/erofs/<disk>/sync_decompress Date: November 2021 Contact: "Huang Jianan" <huangjianan@oppo.com> -Description: Control strategy of sync decompression +Description: Control strategy of sync decompression: + - 0 (default, auto): enable for readpage, and enable for - readahead on atomic contexts only, + readahead on atomic contexts only. - 1 (force on): enable for readpage and readahead. - 2 (force off): disable for all situations. diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index 749ae970c319..04ba83e1965f 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -290,6 +290,8 @@ infrastructure: +------------------------------+---------+---------+ | RPRES | [7-4] | y | +------------------------------+---------+---------+ + | WFXT | [3-0] | y | + +------------------------------+---------+---------+ Appendix I: Example diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst index a8f30963e550..3d116fb536c5 100644 --- a/Documentation/arm64/elf_hwcaps.rst +++ b/Documentation/arm64/elf_hwcaps.rst @@ -264,6 +264,43 @@ HWCAP2_MTE3 Functionality implied by ID_AA64PFR1_EL1.MTE == 0b0011, as described by Documentation/arm64/memory-tagging-extension.rst. +HWCAP2_SME + + Functionality implied by ID_AA64PFR1_EL1.SME == 0b0001, as described + by Documentation/arm64/sme.rst. + +HWCAP2_SME_I16I64 + + Functionality implied by ID_AA64SMFR0_EL1.I16I64 == 0b1111. + +HWCAP2_SME_F64F64 + + Functionality implied by ID_AA64SMFR0_EL1.F64F64 == 0b1. + +HWCAP2_SME_I8I32 + + Functionality implied by ID_AA64SMFR0_EL1.I8I32 == 0b1111. + +HWCAP2_SME_F16F32 + + Functionality implied by ID_AA64SMFR0_EL1.F16F32 == 0b1. + +HWCAP2_SME_B16F32 + + Functionality implied by ID_AA64SMFR0_EL1.B16F32 == 0b1. + +HWCAP2_SME_F32F32 + + Functionality implied by ID_AA64SMFR0_EL1.F32F32 == 0b1. + +HWCAP2_SME_FA64 + + Functionality implied by ID_AA64SMFR0_EL1.FA64 == 0b1. + +HWCAP2_WFXT + + Functionality implied by ID_AA64ISAR2_EL1.WFXT == 0b0010. + 4. Unused AT_HWCAP bits ----------------------- diff --git a/Documentation/arm64/index.rst b/Documentation/arm64/index.rst index 4f840bac083e..ae21f8118830 100644 --- a/Documentation/arm64/index.rst +++ b/Documentation/arm64/index.rst @@ -21,6 +21,7 @@ ARM64 Architecture perf pointer-authentication silicon-errata + sme sve tagged-address-abi tagged-pointers diff --git a/Documentation/arm64/memory-tagging-extension.rst b/Documentation/arm64/memory-tagging-extension.rst index dd27f78d7608..dbae47bba25e 100644 --- a/Documentation/arm64/memory-tagging-extension.rst +++ b/Documentation/arm64/memory-tagging-extension.rst @@ -228,10 +228,10 @@ Core dump support ----------------- The allocation tags for user memory mapped with ``PROT_MTE`` are dumped -in the core file as additional ``PT_ARM_MEMTAG_MTE`` segments. The +in the core file as additional ``PT_AARCH64_MEMTAG_MTE`` segments. The program header for such segment is defined as: -:``p_type``: ``PT_ARM_MEMTAG_MTE`` +:``p_type``: ``PT_AARCH64_MEMTAG_MTE`` :``p_flags``: 0 :``p_offset``: segment file offset :``p_vaddr``: segment virtual address, same as the corresponding diff --git a/Documentation/arm64/sme.rst b/Documentation/arm64/sme.rst new file mode 100644 index 000000000000..8ba677b87e90 --- /dev/null +++ b/Documentation/arm64/sme.rst @@ -0,0 +1,428 @@ +=================================================== +Scalable Matrix Extension support for AArch64 Linux +=================================================== + +This document outlines briefly the interface provided to userspace by Linux in +order to support use of the ARM Scalable Matrix Extension (SME). + +This is an outline of the most important features and issues only and not +intended to be exhaustive. It should be read in conjunction with the SVE +documentation in sve.rst which provides details on the Streaming SVE mode +included in SME. + +This document does not aim to describe the SME architecture or programmer's +model. To aid understanding, a minimal description of relevant programmer's +model features for SME is included in Appendix A. + + +1. General +----------- + +* PSTATE.SM, PSTATE.ZA, the streaming mode vector length, the ZA + register state and TPIDR2_EL0 are tracked per thread. + +* The presence of SME is reported to userspace via HWCAP2_SME in the aux vector + AT_HWCAP2 entry. Presence of this flag implies the presence of the SME + instructions and registers, and the Linux-specific system interfaces + described in this document. SME is reported in /proc/cpuinfo as "sme". + +* Support for the execution of SME instructions in userspace can also be + detected by reading the CPU ID register ID_AA64PFR1_EL1 using an MRS + instruction, and checking that the value of the SME field is nonzero. [3] + + It does not guarantee the presence of the system interfaces described in the + following sections: software that needs to verify that those interfaces are + present must check for HWCAP2_SME instead. + +* There are a number of optional SME features, presence of these is reported + through AT_HWCAP2 through: + + HWCAP2_SME_I16I64 + HWCAP2_SME_F64F64 + HWCAP2_SME_I8I32 + HWCAP2_SME_F16F32 + HWCAP2_SME_B16F32 + HWCAP2_SME_F32F32 + HWCAP2_SME_FA64 + + This list may be extended over time as the SME architecture evolves. + + These extensions are also reported via the CPU ID register ID_AA64SMFR0_EL1, + which userspace can read using an MRS instruction. See elf_hwcaps.txt and + cpu-feature-registers.txt for details. + +* Debuggers should restrict themselves to interacting with the target via the + NT_ARM_SVE, NT_ARM_SSVE and NT_ARM_ZA regsets. The recommended way + of detecting support for these regsets is to connect to a target process + first and then attempt a + + ptrace(PTRACE_GETREGSET, pid, NT_ARM_<regset>, &iov). + +* Whenever ZA register values are exchanged in memory between userspace and + the kernel, the register value is encoded in memory as a series of horizontal + vectors from 0 to VL/8-1 stored in the same endianness invariant format as is + used for SVE vectors. + +* On thread creation TPIDR2_EL0 is preserved unless CLONE_SETTLS is specified, + in which case it is set to 0. + +2. Vector lengths +------------------ + +SME defines a second vector length similar to the SVE vector length which is +controls the size of the streaming mode SVE vectors and the ZA matrix array. +The ZA matrix is square with each side having as many bytes as a streaming +mode SVE vector. + + +3. Sharing of streaming and non-streaming mode SVE state +--------------------------------------------------------- + +It is implementation defined which if any parts of the SVE state are shared +between streaming and non-streaming modes. When switching between modes +via software interfaces such as ptrace if no register content is provided as +part of switching no state will be assumed to be shared and everything will +be zeroed. + + +4. System call behaviour +------------------------- + +* On syscall PSTATE.ZA is preserved, if PSTATE.ZA==1 then the contents of the + ZA matrix are preserved. + +* On syscall PSTATE.SM will be cleared and the SVE registers will be handled + as per the standard SVE ABI. + +* Neither the SVE registers nor ZA are used to pass arguments to or receive + results from any syscall. + +* On process creation (eg, clone()) the newly created process will have + PSTATE.SM cleared. + +* All other SME state of a thread, including the currently configured vector + length, the state of the PR_SME_VL_INHERIT flag, and the deferred vector + length (if any), is preserved across all syscalls, subject to the specific + exceptions for execve() described in section 6. + + +5. Signal handling +------------------- + +* Signal handlers are invoked with streaming mode and ZA disabled. + +* A new signal frame record za_context encodes the ZA register contents on + signal delivery. [1] + +* The signal frame record for ZA always contains basic metadata, in particular + the thread's vector length (in za_context.vl). + +* The ZA matrix may or may not be included in the record, depending on + the value of PSTATE.ZA. The registers are present if and only if: + za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + in which case PSTATE.ZA == 1. + +* If matrix data is present, the remainder of the record has a vl-dependent + size and layout. Macros ZA_SIG_* are defined [1] to facilitate access to + them. + +* The matrix is stored as a series of horizontal vectors in the same format as + is used for SVE vectors. + +* If the ZA context is too big to fit in sigcontext.__reserved[], then extra + space is allocated on the stack, an extra_context record is written in + __reserved[] referencing this space. za_context is then written in the + extra space. Refer to [1] for further details about this mechanism. + + +5. Signal return +----------------- + +When returning from a signal handler: + +* If there is no za_context record in the signal frame, or if the record is + present but contains no register data as described in the previous section, + then ZA is disabled. + +* If za_context is present in the signal frame and contains matrix data then + PSTATE.ZA is set to 1 and ZA is populated with the specified data. + +* The vector length cannot be changed via signal return. If za_context.vl in + the signal frame does not match the current vector length, the signal return + attempt is treated as illegal, resulting in a forced SIGSEGV. + + +6. prctl extensions +-------------------- + +Some new prctl() calls are added to allow programs to manage the SME vector +length: + +prctl(PR_SME_SET_VL, unsigned long arg) + + Sets the vector length of the calling thread and related flags, where + arg == vl | flags. Other threads of the calling process are unaffected. + + vl is the desired vector length, where sve_vl_valid(vl) must be true. + + flags: + + PR_SME_VL_INHERIT + + Inherit the current vector length across execve(). Otherwise, the + vector length is reset to the system default at execve(). (See + Section 9.) + + PR_SME_SET_VL_ONEXEC + + Defer the requested vector length change until the next execve() + performed by this thread. + + The effect is equivalent to implicit execution of the following + call immediately after the next execve() (if any) by the thread: + + prctl(PR_SME_SET_VL, arg & ~PR_SME_SET_VL_ONEXEC) + + This allows launching of a new program with a different vector + length, while avoiding runtime side effects in the caller. + + Without PR_SME_SET_VL_ONEXEC, the requested change takes effect + immediately. + + + Return value: a nonnegative on success, or a negative value on error: + EINVAL: SME not supported, invalid vector length requested, or + invalid flags. + + + On success: + + * Either the calling thread's vector length or the deferred vector length + to be applied at the next execve() by the thread (dependent on whether + PR_SME_SET_VL_ONEXEC is present in arg), is set to the largest value + supported by the system that is less than or equal to vl. If vl == + SVE_VL_MAX, the value set will be the largest value supported by the + system. + + * Any previously outstanding deferred vector length change in the calling + thread is cancelled. + + * The returned value describes the resulting configuration, encoded as for + PR_SME_GET_VL. The vector length reported in this value is the new + current vector length for this thread if PR_SME_SET_VL_ONEXEC was not + present in arg; otherwise, the reported vector length is the deferred + vector length that will be applied at the next execve() by the calling + thread. + + * Changing the vector length causes all of ZA, P0..P15, FFR and all bits of + Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become + unspecified, including both streaming and non-streaming SVE state. + Calling PR_SME_SET_VL with vl equal to the thread's current vector + length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + does not constitute a change to the vector length for this purpose. + + * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared. + Calling PR_SME_SET_VL with vl equal to the thread's current vector + length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + does not constitute a change to the vector length for this purpose. + + +prctl(PR_SME_GET_VL) + + Gets the vector length of the calling thread. + + The following flag may be OR-ed into the result: + + PR_SME_VL_INHERIT + + Vector length will be inherited across execve(). + + There is no way to determine whether there is an outstanding deferred + vector length change (which would only normally be the case between a + fork() or vfork() and the corresponding execve() in typical use). + + To extract the vector length from the result, bitwise and it with + PR_SME_VL_LEN_MASK. + + Return value: a nonnegative value on success, or a negative value on error: + EINVAL: SME not supported. + + +7. ptrace extensions +--------------------- + +* A new regset NT_ARM_SSVE is defined for access to streaming mode SVE + state via PTRACE_GETREGSET and PTRACE_SETREGSET, this is documented in + sve.rst. + +* A new regset NT_ARM_ZA is defined for ZA state for access to ZA state via + PTRACE_GETREGSET and PTRACE_SETREGSET. + + Refer to [2] for definitions. + +The regset data starts with struct user_za_header, containing: + + size + + Size of the complete regset, in bytes. + This depends on vl and possibly on other things in the future. + + If a call to PTRACE_GETREGSET requests less data than the value of + size, the caller can allocate a larger buffer and retry in order to + read the complete regset. + + max_size + + Maximum size in bytes that the regset can grow to for the target + thread. The regset won't grow bigger than this even if the target + thread changes its vector length etc. + + vl + + Target thread's current streaming vector length, in bytes. + + max_vl + + Maximum possible streaming vector length for the target thread. + + flags + + Zero or more of the following flags, which have the same + meaning and behaviour as the corresponding PR_SET_VL_* flags: + + SME_PT_VL_INHERIT + + SME_PT_VL_ONEXEC (SETREGSET only). + +* The effects of changing the vector length and/or flags are equivalent to + those documented for PR_SME_SET_VL. + + The caller must make a further GETREGSET call if it needs to know what VL is + actually set by SETREGSET, unless is it known in advance that the requested + VL is supported. + +* The size and layout of the payload depends on the header fields. The + SME_PT_ZA_*() macros are provided to facilitate access to the data. + +* In either case, for SETREGSET it is permissible to omit the payload, in which + case the vector length and flags are changed and PSTATE.ZA is set to 0 + (along with any consequences of those changes). If a payload is provided + then PSTATE.ZA will be set to 1. + +* For SETREGSET, if the requested VL is not supported, the effect will be the + same as if the payload were omitted, except that an EIO error is reported. + No attempt is made to translate the payload data to the correct layout + for the vector length actually set. It is up to the caller to translate the + payload layout for the actual VL and retry. + +* The effect of writing a partial, incomplete payload is unspecified. + + +8. ELF coredump extensions +--------------------------- + +* NT_ARM_SSVE notes will be added to each coredump for + each thread of the dumped process. The contents will be equivalent to the + data that would have been read if a PTRACE_GETREGSET of the corresponding + type were executed for each thread when the coredump was generated. + +* A NT_ARM_ZA note will be added to each coredump for each thread of the + dumped process. The contents will be equivalent to the data that would have + been read if a PTRACE_GETREGSET of NT_ARM_ZA were executed for each thread + when the coredump was generated. + + +9. System runtime configuration +-------------------------------- + +* To mitigate the ABI impact of expansion of the signal frame, a policy + mechanism is provided for administrators, distro maintainers and developers + to set the default vector length for userspace processes: + +/proc/sys/abi/sme_default_vector_length + + Writing the text representation of an integer to this file sets the system + default vector length to the specified value, unless the value is greater + than the maximum vector length supported by the system in which case the + default vector length is set to that maximum. + + The result can be determined by reopening the file and reading its + contents. + + At boot, the default vector length is initially set to 32 or the maximum + supported vector length, whichever is smaller and supported. This + determines the initial vector length of the init process (PID 1). + + Reading this file returns the current system default vector length. + +* At every execve() call, the new vector length of the new process is set to + the system default vector length, unless + + * PR_SME_VL_INHERIT (or equivalently SME_PT_VL_INHERIT) is set for the + calling thread, or + + * a deferred vector length change is pending, established via the + PR_SME_SET_VL_ONEXEC flag (or SME_PT_VL_ONEXEC). + +* Modifying the system default vector length does not affect the vector length + of any existing process or thread that does not make an execve() call. + + +Appendix A. SME programmer's model (informative) +================================================= + +This section provides a minimal description of the additions made by SVE to the +ARMv8-A programmer's model that are relevant to this document. + +Note: This section is for information only and not intended to be complete or +to replace any architectural specification. + +A.1. Registers +--------------- + +In A64 state, SME adds the following: + +* A new mode, streaming mode, in which a subset of the normal FPSIMD and SVE + features are available. When supported EL0 software may enter and leave + streaming mode at any time. + + For best system performance it is strongly encouraged for software to enable + streaming mode only when it is actively being used. + +* A new vector length controlling the size of ZA and the Z registers when in + streaming mode, separately to the vector length used for SVE when not in + streaming mode. There is no requirement that either the currently selected + vector length or the set of vector lengths supported for the two modes in + a given system have any relationship. The streaming mode vector length + is referred to as SVL. + +* A new ZA matrix register. This is a square matrix of SVLxSVL bits. Most + operations on ZA require that streaming mode be enabled but ZA can be + enabled without streaming mode in order to load, save and retain data. + + For best system performance it is strongly encouraged for software to enable + ZA only when it is actively being used. + +* Two new 1 bit fields in PSTATE which may be controlled via the SMSTART and + SMSTOP instructions or by access to the SVCR system register: + + * PSTATE.ZA, if this is 1 then the ZA matrix is accessible and has valid + data while if it is 0 then ZA can not be accessed. When PSTATE.ZA is + changed from 0 to 1 all bits in ZA are cleared. + + * PSTATE.SM, if this is 1 then the PE is in streaming mode. When the value + of PSTATE.SM is changed then it is implementation defined if the subset + of the floating point register bits valid in both modes may be retained. + Any other bits will be cleared. + + +References +========== + +[1] arch/arm64/include/uapi/asm/sigcontext.h + AArch64 Linux signal ABI definitions + +[2] arch/arm64/include/uapi/asm/ptrace.h + AArch64 Linux ptrace ABI definitions + +[3] Documentation/arm64/cpu-feature-registers.rst diff --git a/Documentation/arm64/sve.rst b/Documentation/arm64/sve.rst index 9d9a4de5bc34..93c2c2990584 100644 --- a/Documentation/arm64/sve.rst +++ b/Documentation/arm64/sve.rst @@ -7,7 +7,9 @@ Author: Dave Martin <Dave.Martin@arm.com> Date: 4 August 2017 This document outlines briefly the interface provided to userspace by Linux in -order to support use of the ARM Scalable Vector Extension (SVE). +order to support use of the ARM Scalable Vector Extension (SVE), including +interactions with Streaming SVE mode added by the Scalable Matrix Extension +(SME). This is an outline of the most important features and issues only and not intended to be exhaustive. @@ -23,6 +25,10 @@ model features for SVE is included in Appendix A. * SVE registers Z0..Z31, P0..P15 and FFR and the current vector length VL, are tracked per-thread. +* In streaming mode FFR is not accessible unless HWCAP2_SME_FA64 is present + in the system, when it is not supported and these interfaces are used to + access streaming mode FFR is read and written as zero. + * The presence of SVE is reported to userspace via HWCAP_SVE in the aux vector AT_HWCAP entry. Presence of this flag implies the presence of the SVE instructions and registers, and the Linux-specific system interfaces @@ -53,10 +59,19 @@ model features for SVE is included in Appendix A. which userspace can read using an MRS instruction. See elf_hwcaps.txt and cpu-feature-registers.txt for details. +* On hardware that supports the SME extensions, HWCAP2_SME will also be + reported in the AT_HWCAP2 aux vector entry. Among other things SME adds + streaming mode which provides a subset of the SVE feature set using a + separate SME vector length and the same Z/V registers. See sme.rst + for more details. + * Debuggers should restrict themselves to interacting with the target via the NT_ARM_SVE regset. The recommended way of detecting support for this regset is to connect to a target process first and then attempt a - ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov). + ptrace(PTRACE_GETREGSET, pid, NT_ARM_SVE, &iov). Note that when SME is + present and streaming SVE mode is in use the FPSIMD subset of registers + will be read via NT_ARM_SVE and NT_ARM_SVE writes will exit streaming mode + in the target. * Whenever SVE scalable register values (Zn, Pn, FFR) are exchanged in memory between userspace and the kernel, the register value is encoded in memory in @@ -126,6 +141,11 @@ the SVE instruction set architecture. are only present in fpsimd_context. For convenience, the content of V0..V31 is duplicated between sve_context and fpsimd_context. +* The record contains a flag field which includes a flag SVE_SIG_FLAG_SM which + if set indicates that the thread is in streaming mode and the vector length + and register data (if present) describe the streaming SVE data and vector + length. + * The signal frame record for SVE always contains basic metadata, in particular the thread's vector length (in sve_context.vl). @@ -170,6 +190,11 @@ When returning from a signal handler: the signal frame does not match the current vector length, the signal return attempt is treated as illegal, resulting in a forced SIGSEGV. +* It is permitted to enter or leave streaming mode by setting or clearing + the SVE_SIG_FLAG_SM flag but applications should take care to ensure that + when doing so sve_context.vl and any register data are appropriate for the + vector length in the new mode. + 6. prctl extensions -------------------- @@ -265,8 +290,14 @@ prctl(PR_SVE_GET_VL) 7. ptrace extensions --------------------- -* A new regset NT_ARM_SVE is defined for use with PTRACE_GETREGSET and - PTRACE_SETREGSET. +* New regsets NT_ARM_SVE and NT_ARM_SSVE are defined for use with + PTRACE_GETREGSET and PTRACE_SETREGSET. NT_ARM_SSVE describes the + streaming mode SVE registers and NT_ARM_SVE describes the + non-streaming mode SVE registers. + + In this description a register set is referred to as being "live" when + the target is in the appropriate streaming or non-streaming mode and is + using data beyond the subset shared with the FPSIMD Vn registers. Refer to [2] for definitions. @@ -297,7 +328,7 @@ The regset data starts with struct user_sve_header, containing: flags - either + at most one of SVE_PT_REGS_FPSIMD @@ -331,6 +362,10 @@ The regset data starts with struct user_sve_header, containing: SVE_PT_VL_ONEXEC (SETREGSET only). + If neither FPSIMD nor SVE flags are provided then no register + payload is available, this is only possible when SME is implemented. + + * The effects of changing the vector length and/or flags are equivalent to those documented for PR_SVE_SET_VL. @@ -346,6 +381,13 @@ The regset data starts with struct user_sve_header, containing: case only the vector length and flags are changed (along with any consequences of those changes). +* In systems supporting SME when in streaming mode a GETREGSET for + NT_REG_SVE will return only the user_sve_header with no register data, + similarly a GETREGSET for NT_REG_SSVE will not return any register data + when not in streaming mode. + +* A GETREGSET for NT_ARM_SSVE will never return SVE_PT_REGS_FPSIMD. + * For SETREGSET, if an SVE_PT_REGS_SVE payload is present and the requested VL is not supported, the effect will be the same as if the payload were omitted, except that an EIO error is reported. No @@ -355,17 +397,25 @@ The regset data starts with struct user_sve_header, containing: unspecified. It is up to the caller to translate the payload layout for the actual VL and retry. +* Where SME is implemented it is not possible to GETREGSET the register + state for normal SVE when in streaming mode, nor the streaming mode + register state when in normal mode, regardless of the implementation defined + behaviour of the hardware for sharing data between the two modes. + +* Any SETREGSET of NT_ARM_SVE will exit streaming mode if the target was in + streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode + if the target was not in streaming mode. + * The effect of writing a partial, incomplete payload is unspecified. 8. ELF coredump extensions --------------------------- -* A NT_ARM_SVE note will be added to each coredump for each thread of the - dumped process. The contents will be equivalent to the data that would have - been read if a PTRACE_GETREGSET of NT_ARM_SVE were executed for each thread - when the coredump was generated. - +* NT_ARM_SVE and NT_ARM_SSVE notes will be added to each coredump for + each thread of the dumped process. The contents will be equivalent to the + data that would have been read if a PTRACE_GETREGSET of the corresponding + type were executed for each thread when the coredump was generated. 9. System runtime configuration -------------------------------- diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index ad168d16968f..867a4bba6bf6 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -41,13 +41,18 @@ or ``VFAT_FS``. To run ``FAT_KUNIT_TEST``, the ``.kunitconfig`` has: CONFIG_MSDOS_FS=y CONFIG_FAT_KUNIT_TEST=y -1. A good starting point for the ``.kunitconfig``, is the KUnit default - config. Run the command: +1. A good starting point for the ``.kunitconfig`` is the KUnit default config. + You can generate it by running: .. code-block:: bash cd $PATH_TO_LINUX_REPO - cp tools/testing/kunit/configs/default.config .kunitconfig + tools/testing/kunit/kunit.py config + cat .kunit/.kunitconfig + +.. note :: + ``.kunitconfig`` lives in the ``--build_dir`` used by kunit.py, which is + ``.kunit`` by default. .. note :: You may want to remove CONFIG_KUNIT_ALL_TESTS from the ``.kunitconfig`` as diff --git a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml index 0afec83cc723..564ae6aaccf7 100644 --- a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml +++ b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-pmc.yaml @@ -14,7 +14,6 @@ properties: compatible: enum: - nvidia,tegra20-pmc - - nvidia,tegra20-pmc - nvidia,tegra30-pmc - nvidia,tegra114-pmc - nvidia,tegra124-pmc diff --git a/Documentation/devicetree/bindings/bus/ti-sysc.yaml b/Documentation/devicetree/bindings/bus/ti-sysc.yaml index bd40213302da..fced4082b047 100644 --- a/Documentation/devicetree/bindings/bus/ti-sysc.yaml +++ b/Documentation/devicetree/bindings/bus/ti-sysc.yaml @@ -35,7 +35,6 @@ properties: - items: - enum: - ti,sysc-omap2 - - ti,sysc-omap2 - ti,sysc-omap4 - ti,sysc-omap4-simple - ti,sysc-omap2-timer diff --git a/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml b/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml index 0c15afa2214c..016a4f378b9b 100644 --- a/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml +++ b/Documentation/devicetree/bindings/clock/microchip,mpfs.yaml @@ -22,7 +22,16 @@ properties: const: microchip,mpfs-clkcfg reg: - maxItems: 1 + items: + - description: | + clock config registers: + These registers contain enable, reset & divider tables for the, cpu, + axi, ahb and rtc/mtimer reference clocks as well as enable and reset + for the peripheral clocks. + - description: | + mss pll dri registers: + Block of registers responsible for dynamic reconfiguration of the mss + pll clocks: maxItems: 1 @@ -51,7 +60,7 @@ examples: #size-cells = <2>; clkcfg: clock-controller@20002000 { compatible = "microchip,mpfs-clkcfg"; - reg = <0x0 0x20002000 0x0 0x1000>; + reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>; clocks = <&ref>; #clock-cells = <1>; }; diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml index f14f1d39da36..d819dfaafff9 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-audss-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC Audio SubSystem clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml index 4e8062860986..0589a63e273a 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml index 64d027dbe3b2..c98eff64f2b5 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos-ext-clock.yaml @@ -8,7 +8,7 @@ title: Samsung SoC external/osc/XXTI/XusbXTI clock maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml index 1ed64add4355..b644bbd0df38 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos4412-isp-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos4412 SoC ISP clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml index a3fac5c6809d..b05f83533e3d 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5260-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5260 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml index 032862e9f55b..b737c9d35a1c 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5410-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5410 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml index edd1b4ac4334..3f9326e09f79 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos5433-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos5433 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml index 599baf0b7231..c137c6744ef9 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos7-clock.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos7 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml index 7e5a9cac2fd2..5073e569a47f 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos7885-clock.yaml @@ -9,7 +9,7 @@ title: Samsung Exynos7885 SoC clock controller maintainers: - Dávid Virág <virag.david003@gmail.com> - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml index 80ba60838f2b..aa11815ad3a3 100644 --- a/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,exynos850-clock.yaml @@ -9,7 +9,7 @@ title: Samsung Exynos850 SoC clock controller maintainers: - Sam Protsenko <semen.protsenko@linaro.org> - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml index 1410c51e0e7d..9248bfc16d48 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2M and S5M family clock generator block maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml index ae8f8fc93233..2659854ea1c0 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s5pv210-audss-clock.yaml @@ -8,7 +8,7 @@ title: Samsung S5Pv210 SoC Audio SubSystem clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml b/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml index dcb29a2d1159..67a33665cf00 100644 --- a/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml +++ b/Documentation/devicetree/bindings/clock/samsung,s5pv210-clock.yaml @@ -8,7 +8,7 @@ title: Samsung S5P6442/S5PC110/S5PV210 SoC clock controller maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml index d318fccf78f1..2bdd05af6079 100644 --- a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml +++ b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-nocp.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos NoC (Network on Chip) Probe maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung Exynos542x SoC has a NoC (Network on Chip) Probe for NoC bus. diff --git a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml index c9a8cb5fd555..e300df4b47f3 100644 --- a/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml +++ b/Documentation/devicetree/bindings/devfreq/event/samsung,exynos-ppmu.yaml @@ -8,7 +8,7 @@ title: Samsung Exynos SoC PPMU (Platform Performance Monitoring Unit) maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung Exynos SoC has PPMU (Platform Performance Monitoring Unit) for diff --git a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml index 62c3bd4cb28d..7257fd0ae4da 100644 --- a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml +++ b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml @@ -51,7 +51,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml index 5216c27fc0ad..a412a1da950f 100644 --- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml +++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml @@ -39,7 +39,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml b/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml index d31483a78eab..6fb7e321f011 100644 --- a/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml +++ b/Documentation/devicetree/bindings/display/msm/dpu-qcm2290.yaml @@ -160,7 +160,7 @@ examples: mdss: mdss@5e00000 { #address-cells = <1>; #size-cells = <1>; - compatible = "qcom,qcm2290-mdss", "qcom,mdss"; + compatible = "qcom,qcm2290-mdss"; reg = <0x05e00000 0x1000>; reg-names = "mdss"; power-domains = <&dispcc MDSS_GDSC>; @@ -180,7 +180,7 @@ examples: <&apps_smmu 0x421 0x0>; ranges; - mdss_mdp: mdp@5e01000 { + mdss_mdp: display-controller@5e01000 { compatible = "qcom,qcm2290-dpu"; reg = <0x05e01000 0x8f000>, <0x05eb0000 0x2008>; diff --git a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml index f29789994b18..c2df8d28aaf5 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml @@ -83,6 +83,8 @@ properties: required: - compatible - reg + - width-mm + - height-mm - panel-timing unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/display/panel/panel-timing.yaml b/Documentation/devicetree/bindings/display/panel/panel-timing.yaml index 9bf592dc3033..7749de95ee40 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-timing.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-timing.yaml @@ -71,78 +71,72 @@ properties: hfront-porch: description: Horizontal front porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels hback-porch: description: Horizontal back porch timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels hsync-len: description: Horizontal sync length panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of pixels - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of pixels vfront-porch: description: Vertical front porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines vback-porch: description: Vertical back porch panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines vsync-len: description: Vertical sync length panel timing + $ref: /schemas/types.yaml#/definitions/uint32-array oneOf: - - $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 + - maxItems: 1 items: description: typical number of lines - - $ref: /schemas/types.yaml#/definitions/uint32-array - minItems: 3 + - minItems: 3 maxItems: 3 items: description: min, typ, max number of lines diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml index f998a3a5b71f..919734c05c0b 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi-ddc.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml index cb8e735ce3bd..63379fae3636 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-hdmi.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml index ba40284ac66f..00e325a19cb1 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos-mixer.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: Samsung Exynos SoC Mixer is responsible for mixing and blending multiple data diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml index 6f796835ea03..7c37470bd329 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-decon.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | DECON (Display and Enhancement Controller) is the Display Controller for the diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml index 01fccb138ebd..c5c6239c28d0 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos5433-mic.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | MIC (Mobile Image Compressor) resides between DECON and MIPI DSI. MIPI DSI is diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml index afa137d47922..320eedc61a5b 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,exynos7-decon.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | DECON (Display and Enhancement Controller) is the Display Controller for the diff --git a/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml b/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml index 9cf5f120d516..c62ea9d22843 100644 --- a/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml +++ b/Documentation/devicetree/bindings/display/samsung/samsung,fimd.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml index e614fe3187bb..d09d79d7406a 100644 --- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml +++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml @@ -29,6 +29,7 @@ properties: interrupts: description: Interrupt lines for each GPI instance + minItems: 1 maxItems: 13 "#dma-cells": diff --git a/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml b/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml index f9ffe3d6f957..128960545640 100644 --- a/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/extcon/maxim,max77843.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77843 MicroUSB and Companion Power Management IC Extcon maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB @@ -25,7 +25,7 @@ properties: $ref: /schemas/connector/usb-connector.yaml# ports: - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/properties/ports description: Any connector to the data bus of this controller should be modelled using the OF graph bindings specified diff --git a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml index 4d6bfae0653c..85f8d4764740 100644 --- a/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml +++ b/Documentation/devicetree/bindings/gpu/arm,mali-bifrost.yaml @@ -20,6 +20,7 @@ properties: - mediatek,mt8183-mali - realtek,rtd1619-mali - renesas,r9a07g044-mali + - renesas,r9a07g054-mali - rockchip,px30-mali - rockchip,rk3568-mali - const: arm,mali-bifrost # Mali Bifrost GPU model/revision is fully discoverable @@ -109,7 +110,9 @@ allOf: properties: compatible: contains: - const: renesas,r9a07g044-mali + enum: + - renesas,r9a07g044-mali + - renesas,r9a07g054-mali then: properties: interrupts: diff --git a/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml b/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml index 4b5851c326f7..b1a4c235376e 100644 --- a/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml +++ b/Documentation/devicetree/bindings/hwmon/lltc,ltc4151.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LTC4151 High Voltage I2C Current and Voltage Monitor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml b/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml index c42051f8a191..028d6e570131 100644 --- a/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml +++ b/Documentation/devicetree/bindings/hwmon/microchip,mcp3021.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip MCP3021 A/D converter maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml b/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml index 4669217d01e1..80df7182ea28 100644 --- a/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml +++ b/Documentation/devicetree/bindings/hwmon/sensirion,sht15.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Sensirion SHT15 humidity and temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml index d3eff4fac107..c5a889e3e27b 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp102.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TMP102 temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml index eda55bbc172d..dcbc6fbc3b48 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp108.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TMP108 temperature sensor maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml index 801ca9ba7d34..e7493e25a7d2 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp464.yaml @@ -58,9 +58,8 @@ patternProperties: The value (two's complement) to be programmed in the channel specific N correction register. For remote channels only. $ref: /schemas/types.yaml#/definitions/int32 - items: - minimum: -128 - maximum: 127 + minimum: -128 + maximum: 127 required: - reg diff --git a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml index 19874e8b73b9..3e52a0db6c41 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-exynos5.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung's High Speed I2C controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Samsung's High Speed I2C controller is used to interface with I2C devices diff --git a/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml b/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml index 84051b0129c2..c26230518957 100644 --- a/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/samsung,s3c2410-i2c.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC I2C Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml index cf711082ad7d..666414a9c0de 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7476.yaml @@ -98,6 +98,7 @@ allOf: - ti,adc121s - ti,ads7866 - ti,ads7868 + then: required: - vcc-supply # Devices with a vref diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml index 7c260f209687..92f9472a77ae 100644 --- a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml @@ -108,9 +108,7 @@ patternProperties: - [1-5]: order 1 to 5. For audio purpose it is recommended to use order 3 to 5. $ref: /schemas/types.yaml#/definitions/uint32 - items: - minimum: 0 - maximum: 5 + maximum: 5 "#io-channel-cells": const: 1 @@ -174,7 +172,7 @@ patternProperties: contains: const: st,stm32-dfsdm-adc - - then: + then: properties: st,adc-channels: minItems: 1 @@ -206,7 +204,7 @@ patternProperties: contains: const: st,stm32-dfsdm-dmic - - then: + then: properties: st,adc-channels: maxItems: 1 @@ -254,7 +252,7 @@ allOf: contains: const: st,stm32h7-dfsdm - - then: + then: patternProperties: "^filter@[0-9]+$": properties: @@ -269,7 +267,7 @@ allOf: contains: const: st,stm32mp1-dfsdm - - then: + then: patternProperties: "^filter@[0-9]+$": properties: diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml index 0d8fb56f4b09..65f86f26947c 100644 --- a/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5360.yaml @@ -59,9 +59,9 @@ allOf: contains: enum: - adi,ad5371 - then: - required: - - vref2-supply + then: + required: + - vref2-supply examples: - | diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml index 89853b482513..8a676fef8c1d 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml @@ -93,48 +93,48 @@ allOf: - qcom,sdm660-gnoc - qcom,sdm660-snoc - then: - properties: - clock-names: - items: - - const: bus - - const: bus_a - - clocks: - items: - - description: Bus Clock - - description: Bus A Clock - - # Child node's properties - patternProperties: - '^interconnect-[a-z0-9]+$': - type: object - description: - snoc-mm is a child of snoc, sharing snoc's register address space. - - properties: - compatible: - enum: - - qcom,msm8939-snoc-mm - - '#interconnect-cells': - const: 1 - - clock-names: - items: - - const: bus - - const: bus_a - - clocks: - items: - - description: Bus Clock - - description: Bus A Clock - - required: - - compatible - - '#interconnect-cells' - - clock-names - - clocks + then: + properties: + clock-names: + items: + - const: bus + - const: bus_a + + clocks: + items: + - description: Bus Clock + - description: Bus A Clock + + # Child node's properties + patternProperties: + '^interconnect-[a-z0-9]+$': + type: object + description: + snoc-mm is a child of snoc, sharing snoc's register address space. + + properties: + compatible: + enum: + - qcom,msm8939-snoc-mm + + '#interconnect-cells': + const: 1 + + clock-names: + items: + - const: bus + - const: bus_a + + clocks: + items: + - description: Bus Clock + - description: Bus A Clock + + required: + - compatible + - '#interconnect-cells' + - clock-names + - clocks - if: properties: diff --git a/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml b/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml index 372ccbfae771..5a583bf3dbc1 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/mrvl,intc.yaml @@ -7,10 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell MMP/Orion Interrupt controller bindings maintainers: - - Thomas Gleixner <tglx@linutronix.de> - - Jason Cooper <jason@lakedaemon.net> - - Marc Zyngier <maz@kernel.org> - - Rob Herring <robh+dt@kernel.org> + - Andrew Lunn <andrew@lunn.ch> + - Gregory Clement <gregory.clement@bootlin.com> allOf: - if: diff --git a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml index d631b7589d50..72456a07dac9 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Interrupt Combiner Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | Samsung's Exynos4 architecture includes a interrupt combiner controller which diff --git a/Documentation/devicetree/bindings/leds/maxim,max77693.yaml b/Documentation/devicetree/bindings/leds/maxim,max77693.yaml index 86a0005cf156..e27f57bb52ae 100644 --- a/Documentation/devicetree/bindings/leds/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/leds/maxim,max77693.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77693 MicroUSB and Companion Power Management IC LEDs maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/media/coda.yaml b/Documentation/devicetree/bindings/media/coda.yaml index 36781ee4617f..c9d5adbc8c4a 100644 --- a/Documentation/devicetree/bindings/media/coda.yaml +++ b/Documentation/devicetree/bindings/media/coda.yaml @@ -65,7 +65,6 @@ properties: iram: $ref: /schemas/types.yaml#/definitions/phandle description: phandle pointing to the SRAM device node - maxItems: 1 required: - compatible diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml index 9b179bb44dfb..aa55ca65d6ed 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml @@ -63,13 +63,11 @@ properties: mediatek,vpu: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to vpu. mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to scp. diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml index e7b65a91c92c..deb5b657a2d5 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml @@ -55,13 +55,11 @@ properties: mediatek,vpu: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to vpu. mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: Describes point to scp. @@ -106,7 +104,6 @@ allOf: enum: - mediatek,mt8173-vcodec-enc - mediatek,mt8192-vcodec-enc - - mediatek,mt8173-vcodec-enc then: properties: diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml index 7687be0f50aa..c73bf2352aca 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-subdev-decoder.yaml @@ -61,7 +61,6 @@ properties: mediatek,scp: $ref: /schemas/types.yaml#/definitions/phandle - maxItems: 1 description: | The node of system control processor (SCP), using the remoteproc & rpmsg framework. diff --git a/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml b/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml index 769f13250047..08cbdcddfead 100644 --- a/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: DDR PHY Front End (DPFE) for Broadcom STB maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Markus Mayer <mmayer@broadcom.com> properties: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml index f3e62ee07126..1daa66592477 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2-timings.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR2 SDRAM AC timing parameters for a given speed-bin maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml index dd2141cad866..9d78f140609b 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR2 SDRAM compliant to JEDEC JESD209-2 maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml index 97c3e988af5f..5c6512c1e1e3 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3-timings.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR3 SDRAM AC timing parameters for a given speed-bin maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml index c542f32c39fa..48908a19473c 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ddr/jedec,lpddr3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: LPDDR3 SDRAM compliant to JEDEC JESD209-3 maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml b/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml index 14a6bc8f421f..9249624c4fa0 100644 --- a/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/marvell,mvebu-sdram-controller.yaml @@ -8,7 +8,7 @@ title: Marvell MVEBU SDRAM controller maintainers: - Jan Luebbe <jlu@pengutronix.de> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml b/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml index 9566b3421f03..0c511ab906bf 100644 --- a/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/qca,ath79-ddr-controller.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Atheros AR7xxx/AR9xxx DDR controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The DDR controller of the AR7xxx and AR9xxx families provides an interface to diff --git a/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml b/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml index 2b18cef99511..514b2c5f8858 100644 --- a/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: H8/300 bus controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Yoshinori Sato <ysato@users.sourceforge.jp> properties: diff --git a/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml b/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml index f152243f6b18..098348b2b815 100644 --- a/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/samsung,exynos5422-dmc.yaml @@ -9,7 +9,7 @@ title: | Controller device maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Lukasz Luba <lukasz.luba@arm.com> description: | diff --git a/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml b/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml index fb7ae38a9c86..f46e95704f53 100644 --- a/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/synopsys,ddrc-ecc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Synopsys IntelliDDR Multi Protocol memory controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Manish Narani <manish.narani@xilinx.com> - Michal Simek <michal.simek@xilinx.com> @@ -24,9 +24,9 @@ description: | properties: compatible: enum: + - snps,ddrc-3.80a - xlnx,zynq-ddrc-a05 - xlnx,zynqmp-ddrc-2.40a - - snps,ddrc-3.80a interrupts: maxItems: 1 @@ -43,7 +43,9 @@ allOf: properties: compatible: contains: - const: xlnx,zynqmp-ddrc-2.40a + enum: + - snps,ddrc-3.80a + - xlnx,zynqmp-ddrc-2.40a then: required: - interrupts diff --git a/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml b/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml index 9ed51185ff99..382ddab60fbd 100644 --- a/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/ti,da8xx-ddrctl.yaml @@ -8,7 +8,7 @@ title: Texas Instruments da8xx DDR2/mDDR memory controller maintainers: - Bartosz Golaszewski <bgolaszewski@baylibre.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | Documentation: diff --git a/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt b/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt index 692300117c64..9d837535637b 100644 --- a/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt +++ b/Documentation/devicetree/bindings/mfd/atmel-flexcom.txt @@ -54,7 +54,7 @@ flexcom@f8034000 { clock-names = "spi_clk"; atmel,fifo-size = <32>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at25f512b"; reg = <0>; spi-max-frequency = <20000000>; diff --git a/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml b/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml index 27870b8760a6..52edd1bf549f 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml index 859655a789c3..d027aabe453b 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77686.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77686 Power Management IC maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77686 Power Management diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml index 906101197e11..1b06a77ec798 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77693.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77693 MicroUSB and Companion Power Management IC maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml index baa1346ac5d5..ad2013900b03 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77802.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77802 Power Management IC maintainers: - Javier Martinez Canillas <javier@dowhile0.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77802 Power Management diff --git a/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml b/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml index 61a0f9dcb983..f30f96bbff43 100644 --- a/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/mfd/maxim,max77843.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77843 MicroUSB and Companion Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB diff --git a/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml b/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml index bae55c98961c..f7bb67d10eff 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,exynos5433-lpass.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Low Power Audio Subsystem (LPASS) maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml b/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml index 017befdf8adb..055dfc337c2f 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s2mpa01.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPA01 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml index 771b3f16da96..5ff6546c72b7 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS11/13/14/15 and S2MPU02 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml b/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml index 5531718abdf0..10c7b408f33a 100644 --- a/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml +++ b/Documentation/devicetree/bindings/mfd/samsung,s5m8767.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5M8767 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml index ce64b3498378..f3f4d5b02744 100644 --- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml @@ -197,6 +197,8 @@ allOf: - nvidia,tegra30-sdhci - nvidia,tegra114-sdhci - nvidia,tegra124-sdhci + then: + properties: clocks: items: - description: module clock diff --git a/Documentation/devicetree/bindings/net/dsa/realtek.yaml b/Documentation/devicetree/bindings/net/dsa/realtek.yaml index 8756060895a8..99ee4b5b9346 100644 --- a/Documentation/devicetree/bindings/net/dsa/realtek.yaml +++ b/Documentation/devicetree/bindings/net/dsa/realtek.yaml @@ -27,32 +27,25 @@ description: The realtek-mdio driver is an MDIO driver and it must be inserted inside an MDIO node. + The compatible string is only used to identify which (silicon) family the + switch belongs to. Roughly speaking, a family is any set of Realtek switches + whose chip identification register(s) have a common location and semantics. + The different models in a given family can be automatically disambiguated by + parsing the chip identification register(s) according to the given family, + avoiding the need for a unique compatible string for each model. + properties: compatible: enum: - realtek,rtl8365mb - - realtek,rtl8366 - realtek,rtl8366rb - - realtek,rtl8366s - - realtek,rtl8367 - - realtek,rtl8367b - - realtek,rtl8367rb - - realtek,rtl8367s - - realtek,rtl8368s - - realtek,rtl8369 - - realtek,rtl8370 description: | - realtek,rtl8365mb: 4+1 ports - realtek,rtl8366: 5+1 ports - realtek,rtl8366rb: 5+1 ports - realtek,rtl8366s: 5+1 ports - realtek,rtl8367: - realtek,rtl8367b: - realtek,rtl8367rb: 5+2 ports - realtek,rtl8367s: 5+2 ports - realtek,rtl8368s: 8 ports - realtek,rtl8369: 8+1 ports - realtek,rtl8370: 8+2 ports + realtek,rtl8365mb: + Use with models RTL8363NB, RTL8363NB-VB, RTL8363SC, RTL8363SC-VB, + RTL8364NB, RTL8364NB-VB, RTL8365MB, RTL8366SC, RTL8367RB-VB, RTL8367S, + RTL8367SB, RTL8370MB, RTL8310SR + realtek,rtl8366rb: + Use with models RTL8366RB, RTL8366S mdc-gpios: description: GPIO line for the MDC clock line. @@ -335,7 +328,7 @@ examples: #size-cells = <0>; switch@29 { - compatible = "realtek,rtl8367s"; + compatible = "realtek,rtl8365mb"; reg = <29>; reset-gpios = <&gpio2 20 GPIO_ACTIVE_LOW>; diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 817794e56227..4f15463611f8 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -106,6 +106,12 @@ properties: phy-mode: $ref: "#/properties/phy-connection-type" + pcs-handle: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Specifies a reference to a node representing a PCS PHY device on a MDIO + bus to link with an external PHY (phy-handle) if exists. + phy-handle: $ref: /schemas/types.yaml#/definitions/phandle description: diff --git a/Documentation/devicetree/bindings/net/micrel.txt b/Documentation/devicetree/bindings/net/micrel.txt index c5ab62c39133..8d157f0295a5 100644 --- a/Documentation/devicetree/bindings/net/micrel.txt +++ b/Documentation/devicetree/bindings/net/micrel.txt @@ -45,20 +45,3 @@ Optional properties: In fiber mode, auto-negotiation is disabled and the PHY can only work in 100base-fx (full and half duplex) modes. - - - lan8814,ignore-ts: If present the PHY will not support timestamping. - - This option acts as check whether Timestamping is supported by - hardware or not. LAN8814 phy support hardware tmestamping. - - - lan8814,latency_rx_10: Configures Latency value of phy in ingress at 10 Mbps. - - - lan8814,latency_tx_10: Configures Latency value of phy in egress at 10 Mbps. - - - lan8814,latency_rx_100: Configures Latency value of phy in ingress at 100 Mbps. - - - lan8814,latency_tx_100: Configures Latency value of phy in egress at 100 Mbps. - - - lan8814,latency_rx_1000: Configures Latency value of phy in ingress at 1000 Mbps. - - - lan8814,latency_tx_1000: Configures Latency value of phy in egress at 1000 Mbps. diff --git a/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml b/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml index 15a45db3899a..1bcaf6ba822c 100644 --- a/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/marvell,nci.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell International Ltd. NCI NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml index 7465aea2e1c0..e381a3c14836 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml @@ -8,7 +8,7 @@ title: NXP Semiconductors NCI NFC controller maintainers: - Charles Gorand <charles.gorand@effinnov.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml index d8ba5a18db98..0509e0166345 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,pn532.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP Semiconductors PN532 NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml b/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml index d520414de463..18b3a7d819df 100644 --- a/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml +++ b/Documentation/devicetree/bindings/net/nfc/nxp,pn544.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP Semiconductors PN544 NFC Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml b/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml index a6a1bc788d29..ef1155038a2f 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st-nci.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics ST NCI NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml b/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml index 4356eacde8aa..8a7274357b46 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st21nfca.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics SAS ST21NFCA NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml b/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml index d3bca376039e..963d9531a856 100644 --- a/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml +++ b/Documentation/devicetree/bindings/net/nfc/st,st95hf.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics ST95HF NFC controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml index 40da2ac98978..404c8df99364 100644 --- a/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml +++ b/Documentation/devicetree/bindings/net/nfc/ti,trf7970a.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Texas Instruments TRF7970A RFID/NFC/15693 Transceiver maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Mark Greer <mgreer@animalcreek.com> properties: diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 2d5248f5b919..36c85eb3dc0d 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -53,20 +53,18 @@ properties: - allwinner,sun8i-r40-gmac - allwinner,sun8i-v3s-emac - allwinner,sun50i-a64-emac - - loongson,ls2k-dwmac - - loongson,ls7a-dwmac - amlogic,meson6-dwmac - amlogic,meson8b-dwmac - amlogic,meson8m2-dwmac - amlogic,meson-gxbb-dwmac - amlogic,meson-axg-dwmac - - loongson,ls2k-dwmac - - loongson,ls7a-dwmac - ingenic,jz4775-mac - ingenic,x1000-mac - ingenic,x1600-mac - ingenic,x1830-mac - ingenic,x2000-mac + - loongson,ls2k-dwmac + - loongson,ls7a-dwmac - rockchip,px30-gmac - rockchip,rk3128-gmac - rockchip,rk3228-gmac diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml index e602761f7b14..b0ebcef6801c 100644 --- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml +++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml @@ -13,9 +13,6 @@ description: | This describes the devicetree bindings for AVE ethernet controller implemented on Socionext UniPhier SoCs. -allOf: - - $ref: ethernet-controller.yaml# - properties: compatible: enum: @@ -44,25 +41,13 @@ properties: minItems: 1 maxItems: 4 - clock-names: - oneOf: - - items: # for Pro4 - - const: gio - - const: ether - - const: ether-gb - - const: ether-phy - - const: ether # for others + clock-names: true resets: minItems: 1 maxItems: 2 - reset-names: - oneOf: - - items: # for Pro4 - - const: gio - - const: ether - - const: ether # for others + reset-names: true socionext,syscon-phy-mode: $ref: /schemas/types.yaml#/definitions/phandle-array @@ -78,6 +63,42 @@ properties: $ref: mdio.yaml# unevaluatedProperties: false +allOf: + - $ref: ethernet-controller.yaml# + - if: + properties: + compatible: + contains: + const: socionext,uniphier-pro4-ave4 + then: + properties: + clocks: + minItems: 4 + maxItems: 4 + clock-names: + items: + - const: gio + - const: ether + - const: ether-gb + - const: ether-phy + resets: + minItems: 2 + maxItems: 2 + reset-names: + items: + - const: gio + - const: ether + else: + properties: + clocks: + maxItems: 1 + clock-names: + const: ether + resets: + maxItems: 1 + reset-names: + const: ether + required: - compatible - reg @@ -90,7 +111,7 @@ required: - reset-names - mdio -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml b/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml index dbfca5ee9139..6f44f9516c36 100644 --- a/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml +++ b/Documentation/devicetree/bindings/net/ti,davinci-mdio.yaml @@ -56,6 +56,7 @@ if: compatible: contains: const: ti,davinci_mdio +then: required: - bus_freq diff --git a/Documentation/devicetree/bindings/net/xilinx_axienet.txt b/Documentation/devicetree/bindings/net/xilinx_axienet.txt index b8e4894bc634..1aa4c6006cd0 100644 --- a/Documentation/devicetree/bindings/net/xilinx_axienet.txt +++ b/Documentation/devicetree/bindings/net/xilinx_axienet.txt @@ -26,7 +26,8 @@ Required properties: specified, the TX/RX DMA interrupts should be on that node instead, and only the Ethernet core interrupt is optionally specified here. -- phy-handle : Should point to the external phy device. +- phy-handle : Should point to the external phy device if exists. Pointing + this to the PCS/PMA PHY is deprecated and should be avoided. See ethernet.txt file in the same directory. - xlnx,rxmem : Set to allocated memory buffer for Rx/Tx in the hardware @@ -68,6 +69,11 @@ Optional properties: required through the core's MDIO interface (i.e. always, unless the PHY is accessed through a different bus). + - pcs-handle: Phandle to the internal PCS/PMA PHY in SGMII or 1000Base-X + modes, where "pcs-handle" should be used to point + to the PCS/PMA PHY, and "phy-handle" should point to an + external PHY if exists. + Example: axi_ethernet_eth: ethernet@40c00000 { compatible = "xlnx,axi-ethernet-1.00.a"; diff --git a/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml b/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml index dfde0eaf66e1..d61585c96e31 100644 --- a/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml +++ b/Documentation/devicetree/bindings/phy/nvidia,tegra20-usb-phy.yaml @@ -275,17 +275,17 @@ allOf: - nvidia,hssquelch-level - nvidia,hsdiscon-level - else: - properties: - clocks: - maxItems: 4 + else: + properties: + clocks: + maxItems: 4 - clock-names: - items: - - const: reg - - const: pll_u - - const: timer - - const: utmi-pads + clock-names: + items: + - const: reg + - const: pll_u + - const: timer + - const: utmi-pads - if: properties: diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml index e23e5590eaa3..0655e485b260 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-hs-phy.yaml @@ -14,24 +14,24 @@ if: compatible: contains: const: qcom,usb-hs-phy-apq8064 - then: - properties: - resets: - maxItems: 1 +then: + properties: + resets: + maxItems: 1 - reset-names: - const: por + reset-names: + const: por - else: - properties: - resets: - minItems: 2 - maxItems: 2 +else: + properties: + resets: + minItems: 2 + maxItems: 2 - reset-names: - items: - - const: phy - - const: por + reset-names: + items: + - const: phy + - const: por properties: compatible: @@ -92,6 +92,8 @@ additionalProperties: false examples: - | otg: usb-controller { + #reset-cells = <1>; + ulpi { phy { compatible = "qcom,usb-hs-phy-msm8974", "qcom,usb-hs-phy"; diff --git a/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml index 838c6d480ce6..b03b2f00cc5b 100644 --- a/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,dp-video-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC DisplayPort PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml index c61574e10b2a..3e5f035de2e9 100644 --- a/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,exynos-hdmi-phy.yaml @@ -11,7 +11,7 @@ maintainers: - Joonyoung Shim <jy0922.shim@samsung.com> - Seung-Woo Kim <sw0312.kim@samsung.com> - Kyungmin Park <kyungmin.park@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml index 62b39bb46585..8751e559484f 100644 --- a/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,exynos5250-sata-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos5250 SoC SATA PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml index 54aa056b224d..415440aaad89 100644 --- a/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,mipi-video-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5P/Exynos SoC MIPI CSIS/DSIM DPHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml index 056e270a4e88..d9f22a801cbf 100644 --- a/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,usb2-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5P/Exynos SoC USB 2.0 PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml index f83f0f8135b9..5ba55f9f20cc 100644 --- a/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,usb3-drd-phy.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 3.0 DRD PHY USB 2.0 PHY maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Marek Szyprowski <m.szyprowski@samsung.com> - Sylwester Nawrocki <s.nawrocki@samsung.com> diff --git a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml index 8a90d8273767..6bd42e43cdab 100644 --- a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml +++ b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml @@ -48,13 +48,12 @@ properties: Name of one pin group to configure. enum: [ aif1, aif2, aif3, aif4, mif1, mif2, mif3, pdmspk1, pdmspk2, dmic4, dmic5, dmic6, gpio1, gpio2, gpio3, - gpio4, gpio5, gpio6, gpio7, gpio7, gpio8, gpio9, + gpio4, gpio5, gpio6, gpio7, gpio8, gpio9, gpio10, gpio11, gpio12, gpio13, gpio14, gpio15, - gpio16, gpio17, gpio17, gpio18, gpio19, gpio20, - gpio21, gpio22, gpio23, gpio24, gpio25, gpio26, - gpio27, gpio27, gpio28, gpio29, gpio30, gpio31, - gpio32, gpio33, gpio34, gpio35, gpio36, gpio37, - gpio37, gpio38, gpio39 ] + gpio16, gpio17, gpio18, gpio19, gpio20, gpio21, + gpio22, gpio23, gpio24, gpio25, gpio26, gpio27, + gpio28, gpio29, gpio30, gpio31, gpio32, gpio33, + gpio34, gpio35, gpio36, gpio37, gpio38, gpio39 ] function: description: diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml index f73348c54748..8cf3c47ab86b 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-gpio-bank.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - gpio bank maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml index c71939ac8b63..9869d4dceddb 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-pins-cfg.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - pins configuration maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml index a822f70f5702..1de91a51234d 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl-wakeup-interrupt.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller - wake-up interrupt controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml index 989e48c051cf..3a65c66ca71d 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC pin controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> - Tomasz Figa <tomasz.figa@gmail.com> diff --git a/Documentation/devicetree/bindings/power/renesas,apmu.yaml b/Documentation/devicetree/bindings/power/renesas,apmu.yaml index 4d293b2b2f84..d77fc88050c8 100644 --- a/Documentation/devicetree/bindings/power/renesas,apmu.yaml +++ b/Documentation/devicetree/bindings/power/renesas,apmu.yaml @@ -36,7 +36,8 @@ properties: cpus: $ref: /schemas/types.yaml#/definitions/phandle-array items: - maxItems: 1 + minItems: 1 + maxItems: 4 description: | Array of phandles pointing to CPU cores, which should match the order of CPU cores used by the WUPCR and PSTR registers in the Advanced Power diff --git a/Documentation/devicetree/bindings/power/supply/bq2415x.yaml b/Documentation/devicetree/bindings/power/supply/bq2415x.yaml index f8461f06e6f4..118cf484cc69 100644 --- a/Documentation/devicetree/bindings/power/supply/bq2415x.yaml +++ b/Documentation/devicetree/bindings/power/supply/bq2415x.yaml @@ -17,7 +17,6 @@ properties: compatible: enum: - ti,bq24150 - - ti,bq24150 - ti,bq24150a - ti,bq24151 - ti,bq24151a diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml index 3978b48299de..4d3a1d09036f 100644 --- a/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC Charger maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml index a21dc1a8890f..f5fd53debbc8 100644 --- a/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77693 MicroUSB and Companion Power Management IC Charger maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml index 9b131c6facbc..84eeaef179a5 100644 --- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml @@ -18,23 +18,23 @@ description: allOf: - $ref: "regulator.yaml#" - -if: - properties: - compatible: - contains: - const: regulator-fixed-clock - required: - - clocks -else: - if: - properties: - compatible: - contains: - const: regulator-fixed-domain - required: - - power-domains - - required-opps + - if: + properties: + compatible: + contains: + const: regulator-fixed-clock + then: + required: + - clocks + - if: + properties: + compatible: + contains: + const: regulator-fixed-domain + then: + required: + - power-domains + - required-opps properties: compatible: diff --git a/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml b/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml index 16f01886a601..285dc7122977 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max14577.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX14577/MAX77836 MicroUSB and Companion Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX14577/MAX77836 MicroUSB diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml index bb64b679f765..0e7cd4b3ace0 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77686.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77686 Power Management IC regulators maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77686 Power Management diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml index 20d8559bdc2b..945a539749e8 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77693.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77693 MicroUSB and Companion Power Management IC regulators maintainers: - Chanwoo Choi <cw00.choi@samsung.com> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77693 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml index f2b4dd15a0f3..236348c4710c 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77802.yaml @@ -8,7 +8,7 @@ title: Maxim MAX77802 Power Management IC regulators maintainers: - Javier Martinez Canillas <javier@dowhile0.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77802 Power Management diff --git a/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml b/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml index a963025e96c1..9695e7242882 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max77843.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX77843 MicroUSB and Companion Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for Maxim MAX77843 MicroUSB Integrated diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml index e4e8c58f6046..3ff0d7d980e9 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8952.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8952 voltage regulator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> allOf: - $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml index 5898dcf10f06..b92eef68c19f 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8973.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8973/MAX77621 voltage regulator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> allOf: - $ref: regulator.yaml# diff --git a/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml b/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml index d5a44ca3df04..4321f061a7f6 100644 --- a/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml +++ b/Documentation/devicetree/bindings/regulator/maxim,max8997.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim MAX8997 Power Management IC maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | The Maxim MAX8997 is a Power Management IC which includes voltage and current diff --git a/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml b/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml index 28725c5467fc..edb411be0390 100644 --- a/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/richtek,rt5190a-regulator.yaml @@ -58,7 +58,7 @@ properties: type: object $ref: regulator.yaml# description: | - regulator description for buck1 and buck4. + regulator description for buck1 to buck4, and ldo. properties: regulator-allowed-modes: diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml index 0627dec513da..0f9eb317ba9a 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mpa01.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPA01 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml index e3b780715f44..f1c50dcd0b04 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps11.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS11 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml index 579d77aefc3f..53b105a4ead1 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps13.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS13 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml index fdea290b3e94..01f9d4e236e9 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS14 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml index b3a883c94628..9576c2df45a6 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps15.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPS15 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml index 0ded6953e3b6..39b652c3c3c4 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mpu02.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S2MPU02 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml index 3c1617b66861..172631ca3c25 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S5M8767 Power Management IC regulators maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | This is a part of device tree bindings for S2M and S5M family of Power diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml b/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml index 2424de733ee4..d99a729d2710 100644 --- a/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml +++ b/Documentation/devicetree/bindings/remoteproc/qcom,sc7280-wpss-pil.yaml @@ -104,8 +104,7 @@ properties: qcom,smem-state-names: $ref: /schemas/types.yaml#/definitions/string description: The names of the state bits used for SMP2P output - items: - - const: stop + const: stop glink-edge: type: object @@ -130,7 +129,6 @@ properties: qcom,remote-pid: $ref: /schemas/types.yaml#/definitions/uint32 description: ID of the shared memory used by GLINK for communication with WPSS - maxItems: 1 required: - interrupts diff --git a/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml b/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml index b0c41ab1a746..cdfcf32c53fa 100644 --- a/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml +++ b/Documentation/devicetree/bindings/reset/hisilicon,hi3660-reset.yaml @@ -24,6 +24,11 @@ properties: - const: hisilicon,hi3670-reset - const: hisilicon,hi3660-reset + hisi,rst-syscon: + deprecated: true + description: phandle of the reset's syscon, use hisilicon,rst-syscon instead + $ref: /schemas/types.yaml#/definitions/phandle + hisilicon,rst-syscon: description: phandle of the reset's syscon. $ref: /schemas/types.yaml#/definitions/phandle diff --git a/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml b/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml index 377a7d242323..6566804ec567 100644 --- a/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml +++ b/Documentation/devicetree/bindings/reset/socionext,uniphier-reset.yaml @@ -55,6 +55,9 @@ properties: "#reset-cells": const: 1 + resets: + maxItems: 1 + additionalProperties: false required: diff --git a/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml b/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml index a50c34d5d199..765d9f9edd6e 100644 --- a/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml +++ b/Documentation/devicetree/bindings/rng/samsung,exynos5250-trng.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC True Random Number Generator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Łukasz Stelmach <l.stelmach@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml b/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml index 84bf518a5549..4754174e9849 100644 --- a/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml +++ b/Documentation/devicetree/bindings/rng/timeriomem_rng.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TimerIO Random Number Generator maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml b/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml index a2e984ea3553..500c62becd6b 100644 --- a/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/microchip,mfps-rtc.yaml @@ -31,11 +31,19 @@ properties: to that of the RTC's count register. clocks: - maxItems: 1 + items: + - description: | + AHB clock + - description: | + Reference clock: divided by the prescaler to create a time-based + strobe (typically 1 Hz) for the calendar counter. By default, the rtc + on the PolarFire SoC shares it's reference with MTIMER so this will + be a 1 MHz clock. clock-names: items: - const: rtc + - const: rtcref required: - compatible @@ -48,11 +56,12 @@ additionalProperties: false examples: - | + #include "dt-bindings/clock/microchip,mpfs-clock.h" rtc@20124000 { compatible = "microchip,mpfs-rtc"; reg = <0x20124000 0x1000>; - clocks = <&clkcfg 21>; - clock-names = "rtc"; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; interrupts = <80>, <81>; }; ... diff --git a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml index a98ed66d092e..0cabb773c397 100644 --- a/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml +++ b/Documentation/devicetree/bindings/soc/samsung/exynos-usi.yaml @@ -8,7 +8,7 @@ title: Samsung's Exynos USI (Universal Serial Interface) binding maintainers: - Sam Protsenko <semen.protsenko@linaro.org> - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | USI IP-core provides selectable serial protocol (UART, SPI or High-Speed I2C). diff --git a/Documentation/devicetree/bindings/sound/samsung,arndale.yaml b/Documentation/devicetree/bindings/sound/samsung,arndale.yaml index cea2bf3544f0..9bc4585bb6e5 100644 --- a/Documentation/devicetree/bindings/sound/samsung,arndale.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,arndale.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Insignal Arndale boards audio complex maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml b/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml index cb51af90435e..ac151d3c1d77 100644 --- a/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,smdk5250.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung SMDK5250 audio complex with WM8994 codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,snow.yaml b/Documentation/devicetree/bindings/sound/samsung,snow.yaml index 0c3b3302b842..51a83d3c7274 100644 --- a/Documentation/devicetree/bindings/sound/samsung,snow.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,snow.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Google Snow audio complex with MAX9809x codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/samsung,tm2.yaml b/Documentation/devicetree/bindings/sound/samsung,tm2.yaml index 74712d6f3ef4..491e08019c04 100644 --- a/Documentation/devicetree/bindings/sound/samsung,tm2.yaml +++ b/Documentation/devicetree/bindings/sound/samsung,tm2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos5433 TM2(E) audio complex with WM5110 codec maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> - Sylwester Nawrocki <s.nawrocki@samsung.com> properties: diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml index b3dbcba33e41..fe2e15504ebc 100644 --- a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml +++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml @@ -136,8 +136,7 @@ allOf: compatible: contains: const: st,stm32f4-sai - - - then: + then: properties: clocks: items: @@ -148,8 +147,7 @@ allOf: items: - const: x8k - const: x11k - - - else: + else: properties: clocks: items: diff --git a/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml b/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml index b104899205f6..5de710adfa63 100644 --- a/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml +++ b/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml @@ -124,7 +124,6 @@ properties: description: | Override the default TX fifo size. Unit is words. Ignored if 0. $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 default: 64 renesas,rx-fifo-size: @@ -132,7 +131,6 @@ properties: description: | Override the default RX fifo size. Unit is words. Ignored if 0. $ref: /schemas/types.yaml#/definitions/uint32 - maxItems: 1 default: 64 required: diff --git a/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml index f0db3fb3d688..25b1b6c12d4d 100644 --- a/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml +++ b/Documentation/devicetree/bindings/spi/samsung,spi-peripheral-props.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Peripheral-specific properties for Samsung S3C/S5P/Exynos SoC SPI controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: See spi-peripheral-props.yaml for more info. diff --git a/Documentation/devicetree/bindings/spi/samsung,spi.yaml b/Documentation/devicetree/bindings/spi/samsung,spi.yaml index bf9a76d931d2..a50f24f9359d 100644 --- a/Documentation/devicetree/bindings/spi/samsung,spi.yaml +++ b/Documentation/devicetree/bindings/spi/samsung,spi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung S3C/S5P/Exynos SoC SPI controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: All the SPI controller nodes should be represented in the aliases node using diff --git a/Documentation/devicetree/bindings/sram/sram.yaml b/Documentation/devicetree/bindings/sram/sram.yaml index 668a9a41a775..993430be355b 100644 --- a/Documentation/devicetree/bindings/sram/sram.yaml +++ b/Documentation/devicetree/bindings/sram/sram.yaml @@ -136,14 +136,14 @@ required: - reg if: - properties: - compatible: - contains: - enum: - - qcom,rpm-msg-ram - - rockchip,rk3288-pmu-sram - -else: + not: + properties: + compatible: + contains: + enum: + - qcom,rpm-msg-ram + - rockchip,rk3288-pmu-sram +then: required: - "#address-cells" - "#size-cells" diff --git a/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml b/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml index 17129f75d962..1344df708e2d 100644 --- a/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/samsung,exynos-thermal.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC Thermal Management Unit (TMU) maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> description: | For multi-instance tmu each instance should have an alias correctly numbered diff --git a/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml b/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml index 22b91a27d776..6b9a3bcb3926 100644 --- a/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/samsung,exynos-dwc3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 3.0 DWC3 Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml b/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml index fbf07d6e707a..9c92defbba01 100644 --- a/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml +++ b/Documentation/devicetree/bindings/usb/samsung,exynos-usb2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Samsung Exynos SoC USB 2.0 EHCI/OHCI Controller maintainers: - - Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> + - Krzysztof Kozlowski <krzk@kernel.org> properties: compatible: @@ -62,6 +62,7 @@ required: - interrupts - phys - phy-names + - reg allOf: - if: diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 55006678394a..36a76cbe9095 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -185,6 +185,12 @@ DMA Fence Chain .. kernel-doc:: include/linux/dma-fence-chain.h :internal: +DMA Fence unwrap +~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/linux/dma-fence-unwrap.h + :internal: + DMA Fence uABI/Sync File ~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/filesystems/caching/backend-api.rst b/Documentation/filesystems/caching/backend-api.rst index be793c49a772..d7507becf674 100644 --- a/Documentation/filesystems/caching/backend-api.rst +++ b/Documentation/filesystems/caching/backend-api.rst @@ -73,7 +73,7 @@ busy. If successful, the cache backend can then start setting up the cache. In the event that the initialisation fails, the cache backend should call:: - void fscache_relinquish_cookie(struct fscache_cache *cache); + void fscache_relinquish_cache(struct fscache_cache *cache); to reset and discard the cookie. @@ -110,9 +110,9 @@ to withdraw them, calling:: on the cookie that each object belongs to. This schedules the specified cookie for withdrawal. This gets offloaded to a workqueue. The cache backend can -test for completion by calling:: +wait for completion by calling:: - bool fscache_are_objects_withdrawn(struct fscache_cookie *cache); + void fscache_wait_for_objects(struct fscache_cache *cache); Once all the cookies are withdrawn, a cache backend can withdraw all the volumes, calling:: @@ -125,7 +125,7 @@ outstanding accesses on the volume to complete before returning. When the the cache is completely withdrawn, fscache should be notified by calling:: - void fscache_cache_relinquish(struct fscache_cache *cache); + void fscache_relinquish_cache(struct fscache_cache *cache); to clear fields in the cookie and discard the caller's ref on it. diff --git a/Documentation/filesystems/caching/netfs-api.rst b/Documentation/filesystems/caching/netfs-api.rst index 5066113acad5..7308d76a29dc 100644 --- a/Documentation/filesystems/caching/netfs-api.rst +++ b/Documentation/filesystems/caching/netfs-api.rst @@ -404,22 +404,21 @@ schedule a write of that region:: And if an error occurs before that point is reached, the marks can be removed by calling:: - void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, + void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) -In both of these functions, the cookie representing the cache object to be -written to and a pointer to the mapping to which the source pages are attached -are passed in; start and len indicate the size of the region that's going to be -written (it doesn't have to align to page boundaries necessarily, but it does -have to align to DIO boundaries on the backing filesystem). The caching -parameter indicates if caching should be skipped, and if false, the functions -do nothing. - -The write function takes some additional parameters: i_size indicates the size -of the netfs file and term_func indicates an optional completion function, to -which term_func_priv will be passed, along with the error or amount written. +In these functions, a pointer to the mapping to which the source pages are +attached is passed in and start and len indicate the size of the region that's +going to be written (it doesn't have to align to page boundaries necessarily, +but it does have to align to DIO boundaries on the backing filesystem). The +caching parameter indicates if caching should be skipped, and if false, the +functions do nothing. + +The write function takes some additional parameters: the cookie representing +the cache object to be written to, i_size indicates the size of the netfs file +and term_func indicates an optional completion function, to which +term_func_priv will be passed, along with the error or amount written. Note that the write function will always run asynchronously and will unmark all the pages upon completion before calling term_func. diff --git a/Documentation/filesystems/ext4/attributes.rst b/Documentation/filesystems/ext4/attributes.rst index 54386a010a8d..871d2da7a0a9 100644 --- a/Documentation/filesystems/ext4/attributes.rst +++ b/Documentation/filesystems/ext4/attributes.rst @@ -76,7 +76,7 @@ The beginning of an extended attribute block is in - Checksum of the extended attribute block. * - 0x14 - \_\_u32 - - h\_reserved[2] + - h\_reserved[3] - Zero. The checksum is calculated against the FS UUID, the 64-bit block number diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst index 4a2426f0485a..ad8dc8c040a2 100644 --- a/Documentation/filesystems/f2fs.rst +++ b/Documentation/filesystems/f2fs.rst @@ -235,12 +235,6 @@ offgrpjquota Turn off group journalled quota. offprjjquota Turn off project journalled quota. quota Enable plain user disk quota accounting. noquota Disable all plain disk quota option. -whint_mode=%s Control which write hints are passed down to block - layer. This supports "off", "user-based", and - "fs-based". In "off" mode (default), f2fs does not pass - down hints. In "user-based" mode, f2fs tries to pass - down hints given by users. And in "fs-based" mode, f2fs - passes down hints with its policy. alloc_mode=%s Adjust block allocation policy, which supports "reuse" and "default". fsync_mode=%s Control the policy of fsync. Currently supports "posix", @@ -751,70 +745,6 @@ In order to identify whether the data in the victim segment are valid or not, F2FS manages a bitmap. Each bit represents the validity of a block, and the bitmap is composed of a bit stream covering whole blocks in main area. -Write-hint Policy ------------------ - -1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. - -2) whint_mode=user-based. F2FS tries to pass down hints given by -users. - -===================== ======================== =================== -User F2FS Block -===================== ======================== =================== -N/A META WRITE_LIFE_NOT_SET -N/A HOT_NODE " -N/A WARM_NODE " -N/A COLD_NODE " -ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME -extension list " " - --- buffered io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " " -WRITE_LIFE_MEDIUM " " -WRITE_LIFE_LONG " " - --- direct io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " WRITE_LIFE_NONE -WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM -WRITE_LIFE_LONG " WRITE_LIFE_LONG -===================== ======================== =================== - -3) whint_mode=fs-based. F2FS passes down hints with its policy. - -===================== ======================== =================== -User F2FS Block -===================== ======================== =================== -N/A META WRITE_LIFE_MEDIUM; -N/A HOT_NODE WRITE_LIFE_NOT_SET -N/A WARM_NODE " -N/A COLD_NODE WRITE_LIFE_NONE -ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME -extension list " " - --- buffered io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG -WRITE_LIFE_NONE " " -WRITE_LIFE_MEDIUM " " -WRITE_LIFE_LONG " " - --- direct io -WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME -WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT -WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET -WRITE_LIFE_NONE " WRITE_LIFE_NONE -WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM -WRITE_LIFE_LONG " WRITE_LIFE_LONG -===================== ======================== =================== - Fallocate(2) Policy ------------------- diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 525e6842dd33..43be3782e5df 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -894,7 +894,7 @@ xmit_hash_policy Uses XOR of hardware MAC addresses and packet type ID field to generate the hash. The formula is - hash = source MAC XOR destination MAC XOR packet type ID + hash = source MAC[5] XOR destination MAC[5] XOR packet type ID slave number = hash modulo slave count This algorithm will place all traffic to a particular @@ -910,7 +910,7 @@ xmit_hash_policy Uses XOR of hardware MAC addresses and IP addresses to generate the hash. The formula is - hash = source MAC XOR destination MAC XOR packet type ID + hash = source MAC[5] XOR destination MAC[5] XOR packet type ID hash = hash XOR source IP XOR destination IP hash = hash XOR (hash RSHIFT 16) hash = hash XOR (hash RSHIFT 8) diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 89bb4fa4c362..ddc1dd039337 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -10,21 +10,21 @@ in joining the effort. Design principles ================= -The Distributed Switch Architecture is a subsystem which was primarily designed -to support Marvell Ethernet switches (MV88E6xxx, a.k.a Linkstreet product line) -using Linux, but has since evolved to support other vendors as well. +The Distributed Switch Architecture subsystem was primarily designed to +support Marvell Ethernet switches (MV88E6xxx, a.k.a. Link Street product +line) using Linux, but has since evolved to support other vendors as well. The original philosophy behind this design was to be able to use unmodified Linux tools such as bridge, iproute2, ifconfig to work transparently whether they configured/queried a switch port network device or a regular network device. -An Ethernet switch is typically comprised of multiple front-panel ports, and one -or more CPU or management port. The DSA subsystem currently relies on the +An Ethernet switch typically comprises multiple front-panel ports and one +or more CPU or management ports. The DSA subsystem currently relies on the presence of a management port connected to an Ethernet controller capable of receiving Ethernet frames from the switch. This is a very common setup for all kinds of Ethernet switches found in Small Home and Office products: routers, -gateways, or even top-of-the rack switches. This host Ethernet controller will +gateways, or even top-of-rack switches. This host Ethernet controller will be later referred to as "master" and "cpu" in DSA terminology and code. The D in DSA stands for Distributed, because the subsystem has been designed @@ -33,14 +33,14 @@ using upstream and downstream Ethernet links between switches. These specific ports are referred to as "dsa" ports in DSA terminology and code. A collection of multiple switches connected to each other is called a "switch tree". -For each front-panel port, DSA will create specialized network devices which are +For each front-panel port, DSA creates specialized network devices which are used as controlling and data-flowing endpoints for use by the Linux networking stack. These specialized network interfaces are referred to as "slave" network interfaces in DSA terminology and code. The ideal case for using DSA is when an Ethernet switch supports a "switch tag" which is a hardware feature making the switch insert a specific tag for each -Ethernet frames it received to/from specific ports to help the management +Ethernet frame it receives to/from specific ports to help the management interface figure out: - what port is this frame coming from @@ -125,7 +125,7 @@ other switches from the same fabric, and in this case, the outermost switch ports must decapsulate the packet. Note that in certain cases, it might be the case that the tagging format used -by a leaf switch (not connected directly to the CPU) to not be the same as what +by a leaf switch (not connected directly to the CPU) is not the same as what the network stack sees. This can be seen with Marvell switch trees, where the CPU port can be configured to use either the DSA or the Ethertype DSA (EDSA) format, but the DSA links are configured to use the shorter (without Ethertype) @@ -270,21 +270,21 @@ These interfaces are specialized in order to: to/from specific switch ports - query the switch for ethtool operations: statistics, link state, Wake-on-LAN, register dumps... -- external/internal PHY management: link, auto-negotiation etc. +- manage external/internal PHY: link, auto-negotiation, etc. These slave network devices have custom net_device_ops and ethtool_ops function pointers which allow DSA to introduce a level of layering between the networking -stack/ethtool, and the switch driver implementation. +stack/ethtool and the switch driver implementation. Upon frame transmission from these slave network devices, DSA will look up which -switch tagging protocol is currently registered with these network devices, and +switch tagging protocol is currently registered with these network devices and invoke a specific transmit routine which takes care of adding the relevant switch tag in the Ethernet frames. These frames are then queued for transmission using the master network device -``ndo_start_xmit()`` function, since they contain the appropriate switch tag, the +``ndo_start_xmit()`` function. Since they contain the appropriate switch tag, the Ethernet switch will be able to process these incoming frames from the -management interface and delivers these frames to the physical switch port. +management interface and deliver them to the physical switch port. Graphical representation ------------------------ @@ -330,9 +330,9 @@ MDIO reads/writes towards specific PHY addresses. In most MDIO-connected switches, these functions would utilize direct or indirect PHY addressing mode to return standard MII registers from the switch builtin PHYs, allowing the PHY library and/or to return link status, link partner pages, auto-negotiation -results etc.. +results, etc. -For Ethernet switches which have both external and internal MDIO busses, the +For Ethernet switches which have both external and internal MDIO buses, the slave MII bus can be utilized to mux/demux MDIO reads and writes towards either internal or external MDIO devices this switch might be connected to: internal PHYs, external PHYs, or even external switches. @@ -349,7 +349,7 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as table indication (when cascading switches) - ``dsa_platform_data``: platform device configuration data which can reference - a collection of dsa_chip_data structure if multiples switches are cascaded, + a collection of dsa_chip_data structures if multiple switches are cascaded, the master network device this switch tree is attached to needs to be referenced @@ -426,7 +426,7 @@ logic basically looks like this: "phy-handle" property, if found, this PHY device is created and registered using ``of_phy_connect()`` -- if Device Tree is used, and the PHY device is "fixed", that is, conforms to +- if Device Tree is used and the PHY device is "fixed", that is, conforms to the definition of a non-MDIO managed PHY as defined in ``Documentation/devicetree/bindings/net/fixed-link.txt``, the PHY is registered and connected transparently using the special fixed MDIO bus driver @@ -481,7 +481,7 @@ Device Tree DSA features a standardized binding which is documented in ``Documentation/devicetree/bindings/net/dsa/dsa.txt``. PHY/MDIO library helper functions such as ``of_get_phy_mode()``, ``of_phy_connect()`` are also used to query -per-port PHY specific details: interface connection, MDIO bus location etc.. +per-port PHY specific details: interface connection, MDIO bus location, etc. Driver development ================== @@ -509,7 +509,7 @@ Switch configuration - ``setup``: setup function for the switch, this function is responsible for setting up the ``dsa_switch_ops`` private structure with all it needs: register maps, - interrupts, mutexes, locks etc.. This function is also expected to properly + interrupts, mutexes, locks, etc. This function is also expected to properly configure the switch to separate all network interfaces from each other, that is, they should be isolated by the switch hardware itself, typically by creating a Port-based VLAN ID for each port and allowing only the CPU port and the @@ -526,13 +526,13 @@ PHY devices and link management - ``get_phy_flags``: Some switches are interfaced to various kinds of Ethernet PHYs, if the PHY library PHY driver needs to know about information it cannot obtain on its own (e.g.: coming from switch memory mapped registers), this function - should return a 32-bits bitmask of "flags", that is private between the switch + should return a 32-bit bitmask of "flags" that is private between the switch driver and the Ethernet PHY driver in ``drivers/net/phy/\*``. - ``phy_read``: Function invoked by the DSA slave MDIO bus when attempting to read the switch port MDIO registers. If unavailable, return 0xffff for each read. For builtin switch Ethernet PHYs, this function should allow reading the link - status, auto-negotiation results, link partner pages etc.. + status, auto-negotiation results, link partner pages, etc. - ``phy_write``: Function invoked by the DSA slave MDIO bus when attempting to write to the switch port MDIO registers. If unavailable return a negative error @@ -554,7 +554,7 @@ Ethtool operations ------------------ - ``get_strings``: ethtool function used to query the driver's strings, will - typically return statistics strings, private flags strings etc. + typically return statistics strings, private flags strings, etc. - ``get_ethtool_stats``: ethtool function used to query per-port statistics and return their values. DSA overlays slave network devices general statistics: @@ -564,7 +564,7 @@ Ethtool operations - ``get_sset_count``: ethtool function used to query the number of statistics items - ``get_wol``: ethtool function used to obtain Wake-on-LAN settings per-port, this - function may, for certain implementations also query the master network device + function may for certain implementations also query the master network device Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN - ``set_wol``: ethtool function used to configure Wake-on-LAN settings per-port, @@ -607,14 +607,14 @@ Power management in a fully active state - ``port_enable``: function invoked by the DSA slave network device ndo_open - function when a port is administratively brought up, this function should be - fully enabling a given switch port. DSA takes care of marking the port with + function when a port is administratively brought up, this function should + fully enable a given switch port. DSA takes care of marking the port with ``BR_STATE_BLOCKING`` if the port is a bridge member, or ``BR_STATE_FORWARDING`` if it was not, and propagating these changes down to the hardware - ``port_disable``: function invoked by the DSA slave network device ndo_close - function when a port is administratively brought down, this function should be - fully disabling a given switch port. DSA takes care of marking the port with + function when a port is administratively brought down, this function should + fully disable a given switch port. DSA takes care of marking the port with ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is disabled while being a bridge member @@ -622,12 +622,12 @@ Bridge layer ------------ - ``port_bridge_join``: bridge layer function invoked when a given switch port is - added to a bridge, this function should be doing the necessary at the switch - level to permit the joining port from being added to the relevant logical + added to a bridge, this function should do what's necessary at the switch + level to permit the joining port to be added to the relevant logical domain for it to ingress/egress traffic with other members of the bridge. - ``port_bridge_leave``: bridge layer function invoked when a given switch port is - removed from a bridge, this function should be doing the necessary at the + removed from a bridge, this function should do what's necessary at the switch level to deny the leaving port from ingress/egress traffic from the remaining bridge members. When the port leaves the bridge, it should be aged out at the switch hardware for the switch to (re) learn MAC addresses behind @@ -663,7 +663,7 @@ Bridge layer point for drivers that need to configure the hardware for enabling this feature. -- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoken when a driver +- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoked when a driver leaves a bridge port which had the TX forwarding offload feature enabled. Bridge VLAN filtering diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index b0024aa7b051..66828293d9cb 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -267,6 +267,13 @@ ipfrag_max_dist - INTEGER from different IP datagrams, which could result in data corruption. Default: 64 +bc_forwarding - INTEGER + bc_forwarding enables the feature described in rfc1812#section-5.3.5.2 + and rfc2644. It allows the router to forward directed broadcast. + To enable this feature, the 'all' entry and the input interface entry + should be set to 1. + Default: 0 + INET peer storage ================= diff --git a/Documentation/security/siphash.rst b/Documentation/security/siphash.rst index bd9363025fcb..a10380cb78e5 100644 --- a/Documentation/security/siphash.rst +++ b/Documentation/security/siphash.rst @@ -121,26 +121,36 @@ even scarier, uses an easily brute-forcable 64-bit key (with a 32-bit output) instead of SipHash's 128-bit key. However, this may appeal to some high-performance `jhash` users. -Danger! - -Do not ever use HalfSipHash except for as a hashtable key function, and only -then when you can be absolutely certain that the outputs will never be -transmitted out of the kernel. This is only remotely useful over `jhash` as a -means of mitigating hashtable flooding denial of service attacks. - -Generating a HalfSipHash key -============================ +HalfSipHash support is provided through the "hsiphash" family of functions. + +.. warning:: + Do not ever use the hsiphash functions except for as a hashtable key + function, and only then when you can be absolutely certain that the outputs + will never be transmitted out of the kernel. This is only remotely useful + over `jhash` as a means of mitigating hashtable flooding denial of service + attacks. + +On 64-bit kernels, the hsiphash functions actually implement SipHash-1-3, a +reduced-round variant of SipHash, instead of HalfSipHash-1-3. This is because in +64-bit code, SipHash-1-3 is no slower than HalfSipHash-1-3, and can be faster. +Note, this does *not* mean that in 64-bit kernels the hsiphash functions are the +same as the siphash ones, or that they are secure; the hsiphash functions still +use a less secure reduced-round algorithm and truncate their outputs to 32 +bits. + +Generating a hsiphash key +========================= Keys should always be generated from a cryptographically secure source of -random numbers, either using get_random_bytes or get_random_once: +random numbers, either using get_random_bytes or get_random_once:: -hsiphash_key_t key; -get_random_bytes(&key, sizeof(key)); + hsiphash_key_t key; + get_random_bytes(&key, sizeof(key)); If you're not deriving your key from here, you're doing it wrong. -Using the HalfSipHash functions -=============================== +Using the hsiphash functions +============================ There are two variants of the function, one that takes a list of integers, and one that takes a buffer:: @@ -183,7 +193,7 @@ You may then iterate like usual over the returned hash bucket. Performance =========== -HalfSipHash is roughly 3 times slower than JenkinsHash. For many replacements, -this will not be a problem, as the hashtable lookup isn't the bottleneck. And -in general, this is probably a good sacrifice to make for the security and DoS -resistance of HalfSipHash. +hsiphash() is roughly 3 times slower than jhash(). For many replacements, this +will not be a problem, as the hashtable lookup isn't the bottleneck. And in +general, this is probably a good sacrifice to make for the security and DoS +resistance of hsiphash(). diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 0c1b9f139e4a..f9016fbb6b20 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1486,14 +1486,43 @@ Possible values are: [s390] KVM_MP_STATE_LOAD the vcpu is in a special load/startup state [s390] + KVM_MP_STATE_SUSPENDED the vcpu is in a suspend state and is waiting + for a wakeup event [arm64] ========================== =============================================== On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. -For arm64/riscv: -^^^^^^^^^^^^^^^^ +For arm64: +^^^^^^^^^^ + +If a vCPU is in the KVM_MP_STATE_SUSPENDED state, KVM will emulate the +architectural execution of a WFI instruction. + +If a wakeup event is recognized, KVM will exit to userspace with a +KVM_SYSTEM_EVENT exit, where the event type is KVM_SYSTEM_EVENT_WAKEUP. If +userspace wants to honor the wakeup, it must set the vCPU's MP state to +KVM_MP_STATE_RUNNABLE. If it does not, KVM will continue to await a wakeup +event in subsequent calls to KVM_RUN. + +.. warning:: + + If userspace intends to keep the vCPU in a SUSPENDED state, it is + strongly recommended that userspace take action to suppress the + wakeup event (such as masking an interrupt). Otherwise, subsequent + calls to KVM_RUN will immediately exit with a KVM_SYSTEM_EVENT_WAKEUP + event and inadvertently waste CPU cycles. + + Additionally, if userspace takes action to suppress a wakeup event, + it is strongly recommended that it also restores the vCPU to its + original state when the vCPU is made RUNNABLE again. For example, + if userspace masked a pending interrupt to suppress the wakeup, + the interrupt should be unmasked before returning control to the + guest. + +For riscv: +^^^^^^^^^^ The only states that are valid are KVM_MP_STATE_STOPPED and KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not. @@ -2614,6 +2643,24 @@ EINVAL. After the vcpu's SVE configuration is finalized, further attempts to write this register will fail with EPERM. +arm64 bitmap feature firmware pseudo-registers have the following bit pattern:: + + 0x6030 0000 0016 <regno:16> + +The bitmap feature firmware registers exposes the hypercall services that +are available for userspace to configure. The set bits corresponds to the +services that are available for the guests to access. By default, KVM +sets all the supported bits during VM initialization. The userspace can +discover the available services via KVM_GET_ONE_REG, and write back the +bitmap corresponding to the features that it wishes guests to see via +KVM_SET_ONE_REG. + +Note: These registers are immutable once any of the vCPUs of the VM has +run at least once. A KVM_SET_ONE_REG in such a scenario will return +a -EBUSY to userspace. + +(See Documentation/virt/kvm/arm/hypercalls.rst for more details.) + MIPS registers are mapped using the lower 32 bits. The upper 16 of that is the register group type: @@ -6088,7 +6135,9 @@ should put the acknowledged interrupt vector into the 'epr' field. #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 - #define KVM_SYSTEM_EVENT_SEV_TERM 4 + #define KVM_SYSTEM_EVENT_WAKEUP 4 + #define KVM_SYSTEM_EVENT_SUSPEND 5 + #define KVM_SYSTEM_EVENT_SEV_TERM 6 __u32 type; __u32 ndata; __u64 data[16]; @@ -6115,6 +6164,37 @@ Valid values for 'type' are: reset/shutdown of the VM. - KVM_SYSTEM_EVENT_SEV_TERM -- an AMD SEV guest requested termination. The guest physical address of the guest's GHCB is stored in `data[0]`. + - KVM_SYSTEM_EVENT_WAKEUP -- the exiting vCPU is in a suspended state and + KVM has recognized a wakeup event. Userspace may honor this event by + marking the exiting vCPU as runnable, or deny it and call KVM_RUN again. + - KVM_SYSTEM_EVENT_SUSPEND -- the guest has requested a suspension of + the VM. + +For arm/arm64: +-------------- + + KVM_SYSTEM_EVENT_SUSPEND exits are enabled with the + KVM_CAP_ARM_SYSTEM_SUSPEND VM capability. If a guest invokes the PSCI + SYSTEM_SUSPEND function, KVM will exit to userspace with this event + type. + + It is the sole responsibility of userspace to implement the PSCI + SYSTEM_SUSPEND call according to ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND". + KVM does not change the vCPU's state before exiting to userspace, so + the call parameters are left in-place in the vCPU registers. + + Userspace is _required_ to take action for such an exit. It must + either: + + - Honor the guest request to suspend the VM. Userspace can request + in-kernel emulation of suspension by setting the calling vCPU's + state to KVM_MP_STATE_SUSPENDED. Userspace must configure the vCPU's + state according to the parameters passed to the PSCI function when + the calling vCPU is resumed. See ARM DEN0022D.b 5.19.1 "Intended use" + for details on the function parameters. + + - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2 + "Caller responsibilities" for possible return values. If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain architecture specific information for the system-level event. Only @@ -7858,6 +7938,16 @@ At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting this capability will disable PMU virtualization for that VM. Usermode should adjust CPUID leaf 0xA to reflect that the PMU is disabled. +8.36 KVM_CAP_ARM_SYSTEM_SUSPEND +------------------------------- + +:Capability: KVM_CAP_ARM_SYSTEM_SUSPEND +:Architectures: arm64 +:Type: vm + +When enabled, KVM will exit to userspace with KVM_EXIT_SYSTEM_EVENT of +type KVM_SYSTEM_EVENT_SUSPEND to process the guest suspend request. + 9. Known KVM API problems ========================= diff --git a/Documentation/virt/kvm/arm/hypercalls.rst b/Documentation/virt/kvm/arm/hypercalls.rst new file mode 100644 index 000000000000..3e23084644ba --- /dev/null +++ b/Documentation/virt/kvm/arm/hypercalls.rst @@ -0,0 +1,138 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================= +ARM Hypercall Interface +======================= + +KVM handles the hypercall services as requested by the guests. New hypercall +services are regularly made available by the ARM specification or by KVM (as +vendor services) if they make sense from a virtualization point of view. + +This means that a guest booted on two different versions of KVM can observe +two different "firmware" revisions. This could cause issues if a given guest +is tied to a particular version of a hypercall service, or if a migration +causes a different version to be exposed out of the blue to an unsuspecting +guest. + +In order to remedy this situation, KVM exposes a set of "firmware +pseudo-registers" that can be manipulated using the GET/SET_ONE_REG +interface. These registers can be saved/restored by userspace, and set +to a convenient value as required. + +The following registers are defined: + +* KVM_REG_ARM_PSCI_VERSION: + + KVM implements the PSCI (Power State Coordination Interface) + specification in order to provide services such as CPU on/off, reset + and power-off to the guest. + + - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set + (and thus has already been initialized) + - Returns the current PSCI version on GET_ONE_REG (defaulting to the + highest PSCI version implemented by KVM and compatible with v0.2) + - Allows any PSCI version implemented by KVM and compatible with + v0.2 to be set with SET_ONE_REG + - Affects the whole VM (even if the register view is per-vcpu) + +* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + Holds the state of the firmware support to mitigate CVE-2017-5715, as + offered by KVM to the guest via a HVC call. The workaround is described + under SMCCC_ARCH_WORKAROUND_1 in [1]. + + Accepted values are: + + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: + KVM does not offer + firmware support for the workaround. The mitigation status for the + guest is unknown. + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: + The workaround HVC call is + available to the guest and required for the mitigation. + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: + The workaround HVC call + is available to the guest, but it is not needed on this VCPU. + +* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + Holds the state of the firmware support to mitigate CVE-2018-3639, as + offered by KVM to the guest via a HVC call. The workaround is described + under SMCCC_ARCH_WORKAROUND_2 in [1]_. + + Accepted values are: + + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: + A workaround is not + available. KVM does not offer firmware support for the workaround. + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: + The workaround state is + unknown. KVM does not offer firmware support for the workaround. + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: + The workaround is available, + and can be disabled by a vCPU. If + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED is set, it is active for + this vCPU. + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: + The workaround is always active on this vCPU or it is not needed. + + +Bitmap Feature Firmware Registers +--------------------------------- + +Contrary to the above registers, the following registers exposes the +hypercall services in the form of a feature-bitmap to the userspace. This +bitmap is translated to the services that are available to the guest. +There is a register defined per service call owner and can be accessed via +GET/SET_ONE_REG interface. + +By default, these registers are set with the upper limit of the features +that are supported. This way userspace can discover all the usable +hypercall services via GET_ONE_REG. The user-space can write-back the +desired bitmap back via SET_ONE_REG. The features for the registers that +are untouched, probably because userspace isn't aware of them, will be +exposed as is to the guest. + +Note that KVM will not allow the userspace to configure the registers +anymore once any of the vCPUs has run at least once. Instead, it will +return a -EBUSY. + +The pseudo-firmware bitmap register are as follows: + +* KVM_REG_ARM_STD_BMAP: + Controls the bitmap of the ARM Standard Secure Service Calls. + + The following bits are accepted: + + Bit-0: KVM_REG_ARM_STD_BIT_TRNG_V1_0: + The bit represents the services offered under v1.0 of ARM True Random + Number Generator (TRNG) specification, ARM DEN0098. + +* KVM_REG_ARM_STD_HYP_BMAP: + Controls the bitmap of the ARM Standard Hypervisor Service Calls. + + The following bits are accepted: + + Bit-0: KVM_REG_ARM_STD_HYP_BIT_PV_TIME: + The bit represents the Paravirtualized Time service as represented by + ARM DEN0057A. + +* KVM_REG_ARM_VENDOR_HYP_BMAP: + Controls the bitmap of the Vendor specific Hypervisor Service Calls. + + The following bits are accepted: + + Bit-0: KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT + The bit represents the ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID + and ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID function-ids. + + Bit-1: KVM_REG_ARM_VENDOR_HYP_BIT_PTP: + The bit represents the Precision Time Protocol KVM service. + +Errors: + + ======= ============================================================= + -ENOENT Unknown register accessed. + -EBUSY Attempt a 'write' to the register after the VM has started. + -EINVAL Invalid bitmap written to the register. + ======= ============================================================= + +.. [1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf diff --git a/Documentation/virt/kvm/arm/index.rst b/Documentation/virt/kvm/arm/index.rst index 78a9b670aafe..e84848432158 100644 --- a/Documentation/virt/kvm/arm/index.rst +++ b/Documentation/virt/kvm/arm/index.rst @@ -8,6 +8,6 @@ ARM :maxdepth: 2 hyp-abi - psci + hypercalls pvtime ptp_kvm diff --git a/Documentation/virt/kvm/arm/psci.rst b/Documentation/virt/kvm/arm/psci.rst deleted file mode 100644 index d52c2e83b5b8..000000000000 --- a/Documentation/virt/kvm/arm/psci.rst +++ /dev/null @@ -1,77 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 - -========================================= -Power State Coordination Interface (PSCI) -========================================= - -KVM implements the PSCI (Power State Coordination Interface) -specification in order to provide services such as CPU on/off, reset -and power-off to the guest. - -The PSCI specification is regularly updated to provide new features, -and KVM implements these updates if they make sense from a virtualization -point of view. - -This means that a guest booted on two different versions of KVM can -observe two different "firmware" revisions. This could cause issues if -a given guest is tied to a particular PSCI revision (unlikely), or if -a migration causes a different PSCI version to be exposed out of the -blue to an unsuspecting guest. - -In order to remedy this situation, KVM exposes a set of "firmware -pseudo-registers" that can be manipulated using the GET/SET_ONE_REG -interface. These registers can be saved/restored by userspace, and set -to a convenient value if required. - -The following register is defined: - -* KVM_REG_ARM_PSCI_VERSION: - - - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set - (and thus has already been initialized) - - Returns the current PSCI version on GET_ONE_REG (defaulting to the - highest PSCI version implemented by KVM and compatible with v0.2) - - Allows any PSCI version implemented by KVM and compatible with - v0.2 to be set with SET_ONE_REG - - Affects the whole VM (even if the register view is per-vcpu) - -* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - Holds the state of the firmware support to mitigate CVE-2017-5715, as - offered by KVM to the guest via a HVC call. The workaround is described - under SMCCC_ARCH_WORKAROUND_1 in [1]. - - Accepted values are: - - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: - KVM does not offer - firmware support for the workaround. The mitigation status for the - guest is unknown. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: - The workaround HVC call is - available to the guest and required for the mitigation. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: - The workaround HVC call - is available to the guest, but it is not needed on this VCPU. - -* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - Holds the state of the firmware support to mitigate CVE-2018-3639, as - offered by KVM to the guest via a HVC call. The workaround is described - under SMCCC_ARCH_WORKAROUND_2 in [1]_. - - Accepted values are: - - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: - A workaround is not - available. KVM does not offer firmware support for the workaround. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: - The workaround state is - unknown. KVM does not offer firmware support for the workaround. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: - The workaround is available, - and can be disabled by a vCPU. If - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED is set, it is active for - this vCPU. - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: - The workaround is always active on this vCPU or it is not needed. - -.. [1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf diff --git a/Documentation/vm/page_owner.rst b/Documentation/vm/page_owner.rst index 65204d7f004f..7e0c3f574e78 100644 --- a/Documentation/vm/page_owner.rst +++ b/Documentation/vm/page_owner.rst @@ -110,7 +110,7 @@ Usage If you want to sort by the page nums of buf, use the ``-m`` parameter. The detailed parameters are: - fundamental function: + fundamental function:: Sort: -a Sort by memory allocation time. @@ -122,7 +122,7 @@ Usage -s Sort by stack trace. -t Sort by times (default). - additional function: + additional function:: Cull: --cull <rules> @@ -153,6 +153,7 @@ Usage STANDARD FORMAT SPECIFIERS ========================== +:: KEY LONG DESCRIPTION p pid process ID diff --git a/MAINTAINERS b/MAINTAINERS index fd768d43e048..edc96cdb85e8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -201,6 +201,7 @@ F: include/net/ieee80211_radiotap.h F: include/net/iw_handler.h F: include/net/wext.h F: include/uapi/linux/nl80211.h +F: include/uapi/linux/wireless.h F: net/wireless/ 8169 10/100/1000 GIGABIT ETHERNET DRIVER @@ -2636,13 +2637,14 @@ F: sound/soc/rockchip/ N: rockchip ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org S: Maintained C: irc://irc.libera.chat/linux-exynos Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ +B: mailto:linux-samsung-soc@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux.git F: Documentation/arm/samsung/ F: Documentation/devicetree/bindings/arm/samsung/ @@ -3742,7 +3744,7 @@ F: include/linux/platform_data/b53.h BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE M: Nicolas Saenz Julienne <nsaenz@kernel.org> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -3757,7 +3759,7 @@ BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained T: git git://github.com/broadcom/mach-bcm F: arch/arm/mach-bcm/ @@ -3777,7 +3779,7 @@ F: arch/mips/include/asm/mach-bcm47xx/* BROADCOM BCM4908 ETHERNET DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml @@ -3786,7 +3788,7 @@ F: drivers/net/ethernet/broadcom/unimac.h BROADCOM BCM4908 PINMUX DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-gpio@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pinctrl/brcm,bcm4908-pinctrl.yaml @@ -3796,7 +3798,7 @@ BROADCOM BCM5301X ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Hauke Mehrtens <hauke@hauke-m.de> M: Rafał Miłecki <zajec5@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/bcm470* @@ -3807,7 +3809,7 @@ F: arch/arm/mach-bcm/bcm_5301x.c BROADCOM BCM53573 ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: Rafał Miłecki <rafal@milecki.pl> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/boot/dts/bcm47189* @@ -3815,7 +3817,7 @@ F: arch/arm/boot/dts/bcm53573* BROADCOM BCM63XX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3829,7 +3831,7 @@ F: drivers/usb/gadget/udc/bcm63xx_udc.* BROADCOM BCM7XXX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3847,21 +3849,21 @@ N: bcm7120 BROADCOM BDC DRIVER M: Al Cooper <alcooperx@gmail.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained F: Documentation/devicetree/bindings/usb/brcm,bdc.yaml F: drivers/usb/gadget/udc/bdc/ BROADCOM BMIPS CPUFREQ DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: drivers/cpufreq/bmips-cpufreq.c BROADCOM BMIPS MIPS ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mips@vger.kernel.org S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -3912,7 +3914,9 @@ BROADCOM BNXT_EN 50 GIGABIT ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> L: netdev@vger.kernel.org S: Supported +F: drivers/firmware/broadcom/tee_bnxt_fw.c F: drivers/net/ethernet/broadcom/bnxt/ +F: include/linux/firmware/broadcom/tee_bnxt_fw.h BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER M: Arend van Spriel <aspriel@gmail.com> @@ -3927,53 +3931,53 @@ F: drivers/net/wireless/broadcom/brcm80211/ BROADCOM BRCMSTB GPIO DRIVER M: Doug Berger <opendmb@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.yaml F: drivers/gpio/gpio-brcmstb.c BROADCOM BRCMSTB I2C DRIVER M: Kamal Dasu <kdasu.kdev@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-i2c@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Supported F: Documentation/devicetree/bindings/i2c/brcm,brcmstb-i2c.yaml F: drivers/i2c/busses/i2c-brcmstb.c BROADCOM BRCMSTB UART DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-serial@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml F: drivers/tty/serial/8250/8250_bcm7271.c BROADCOM BRCMSTB USB EHCI DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/usb/brcm,bcm7445-ehci.yaml F: drivers/usb/host/ehci-brcm.* BROADCOM BRCMSTB USB PIN MAP DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-usb@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: Documentation/devicetree/bindings/usb/brcm,usb-pinmap.yaml F: drivers/usb/misc/brcmstb-usb-pinmap.c BROADCOM BRCMSTB USB2 and USB3 PHY DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-kernel@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/phy/broadcom/phy-brcm-usb* BROADCOM ETHERNET PHY DRIVERS M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/net/broadcom-bcm87xx.txt @@ -3984,7 +3988,7 @@ F: include/linux/brcmphy.h BROADCOM GENET ETHERNET DRIVER M: Doug Berger <opendmb@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml @@ -3998,7 +4002,7 @@ F: include/linux/platform_data/mdio-bcm-unimac.h BROADCOM IPROC ARM ARCHITECTURE M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -4026,7 +4030,7 @@ N: stingray BROADCOM IPROC GBIT ETHERNET DRIVER M: Rafał Miłecki <rafal@milecki.pl> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/brcm,amac.yaml @@ -4035,7 +4039,7 @@ F: drivers/net/ethernet/broadcom/unimac.h BROADCOM KONA GPIO DRIVER M: Ray Jui <rjui@broadcom.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: Documentation/devicetree/bindings/gpio/brcm,kona-gpio.txt F: drivers/gpio/gpio-bcm-kona.c @@ -4068,7 +4072,7 @@ F: drivers/firmware/broadcom/* BROADCOM PMB (POWER MANAGEMENT BUS) DRIVER M: Rafał Miłecki <rafal@milecki.pl> M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained T: git git://github.com/broadcom/stblinux.git @@ -4084,7 +4088,7 @@ F: include/linux/bcma/ BROADCOM SPI DRIVER M: Kamal Dasu <kdasu.kdev@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Maintained F: Documentation/devicetree/bindings/spi/brcm,spi-bcm-qspi.yaml F: drivers/spi/spi-bcm-qspi.* @@ -4093,7 +4097,7 @@ F: drivers/spi/spi-iproc-qspi.c BROADCOM STB AVS CPUFREQ DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt @@ -4101,7 +4105,7 @@ F: drivers/cpufreq/brcmstb* BROADCOM STB AVS TMON DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/thermal/brcm,avs-tmon.yaml @@ -4109,7 +4113,7 @@ F: drivers/thermal/broadcom/brcmstb* BROADCOM STB DPFE DRIVER M: Markus Mayer <mmayer@broadcom.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/memory-controllers/brcm,dpfe-cpu.yaml @@ -4118,8 +4122,8 @@ F: drivers/memory/brcmstb_dpfe.c BROADCOM STB NAND FLASH DRIVER M: Brian Norris <computersforpeace@gmail.com> M: Kamal Dasu <kdasu.kdev@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mtd@lists.infradead.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/mtd/nand/raw/brcmnand/ F: include/linux/platform_data/brcmnand.h @@ -4128,7 +4132,7 @@ BROADCOM STB PCIE DRIVER M: Jim Quinlan <jim2101024@gmail.com> M: Nicolas Saenz Julienne <nsaenz@kernel.org> M: Florian Fainelli <f.fainelli@gmail.com> -M: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml @@ -4136,7 +4140,7 @@ F: drivers/pci/controller/pcie-brcmstb.c BROADCOM SYSTEMPORT ETHERNET DRIVER M: Florian Fainelli <f.fainelli@gmail.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/bcmsysport.* @@ -4153,7 +4157,7 @@ F: drivers/net/ethernet/broadcom/tg3.* BROADCOM VK DRIVER M: Scott Branden <scott.branden@broadcom.com> -L: bcm-kernel-feedback-list@broadcom.com +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> S: Supported F: drivers/misc/bcm-vk/ F: include/uapi/linux/misc/bcm_vk.h @@ -4791,6 +4795,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor <nathan@kernel.org> M: Nick Desaulniers <ndesaulniers@google.com> +R: Tom Rix <trix@redhat.com> L: llvm@lists.linux.dev S: Supported W: https://clangbuiltlinux.github.io/ @@ -5715,7 +5720,7 @@ W: http://lanana.org/docs/device-list/index.html DEVICE RESOURCE MANAGEMENT HELPERS M: Hans de Goede <hdegoede@redhat.com> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Maintained F: include/linux/devm-helpers.h @@ -8675,7 +8680,6 @@ F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h HFI1 DRIVER -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported @@ -9336,14 +9340,12 @@ F: drivers/pci/hotplug/rpaphp* IBM Power SRIOV Virtual NIC Device Driver M: Dany Madden <drt@linux.ibm.com> -M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmvnic.* IBM Power Virtual Accelerator Switchboard -M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> L: linuxppc-dev@lists.ozlabs.org S: Supported F: arch/powerpc/include/asm/vas.h @@ -9598,6 +9600,7 @@ F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM M: Jason Gunthorpe <jgg@nvidia.com> +M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/linux-rdma/rdma-core @@ -10237,8 +10240,6 @@ F: drivers/net/ethernet/sgi/ioc3-eth.c IOMAP FILESYSTEM LIBRARY M: Christoph Hellwig <hch@infradead.org> M: Darrick J. Wong <djwong@kernel.org> -M: linux-xfs@vger.kernel.org -M: linux-fsdevel@vger.kernel.org L: linux-xfs@vger.kernel.org L: linux-fsdevel@vger.kernel.org S: Supported @@ -10369,6 +10370,7 @@ F: include/linux/isapnp.h ISCSI M: Lee Duncan <lduncan@suse.com> M: Chris Leech <cleech@redhat.com> +M: Mike Christie <michael.christie@oracle.com> L: open-iscsi@googlegroups.com L: linux-scsi@vger.kernel.org S: Maintained @@ -10546,6 +10548,7 @@ M: Andrey Ryabinin <ryabinin.a.a@gmail.com> R: Alexander Potapenko <glider@google.com> R: Andrey Konovalov <andreyknvl@gmail.com> R: Dmitry Vyukov <dvyukov@google.com> +R: Vincenzo Frascino <vincenzo.frascino@arm.com> L: kasan-dev@googlegroups.com S: Maintained F: Documentation/dev-tools/kasan.rst @@ -11208,7 +11211,7 @@ F: scripts/spdxcheck.py LINEAR RANGES HELPERS M: Mark Brown <broonie@kernel.org> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: lib/linear_ranges.c F: lib/test_linear_ranges.c F: include/linux/linear_range.h @@ -11905,7 +11908,7 @@ F: drivers/iio/proximity/mb1232.c MAXIM MAX17040 FAMILY FUEL GAUGE DRIVERS R: Iskren Chernev <iskren.chernev@gmail.com> -R: Krzysztof Kozlowski <krzk@kernel.org> +R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Matheus Castello <matheus@castello.eng.br> L: linux-pm@vger.kernel.org @@ -11915,7 +11918,7 @@ F: drivers/power/supply/max17040_battery.c MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS R: Hans de Goede <hdegoede@redhat.com> -R: Krzysztof Kozlowski <krzk@kernel.org> +R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm> R: Purism Kernel Team <kernel@puri.sm> @@ -11967,10 +11970,11 @@ F: Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml F: drivers/power/supply/max77976_charger.c MAXIM MUIC CHARGER DRIVERS FOR EXYNOS BASED BOARDS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-pm@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/power/supply/maxim,max14577.yaml F: Documentation/devicetree/bindings/power/supply/maxim,max77693.yaml F: drivers/power/supply/max14577_charger.c @@ -11978,10 +11982,11 @@ F: drivers/power/supply/max77693_charger.c MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS M: Chanwoo Choi <cw00.choi@samsung.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/*/maxim,max14577.yaml F: Documentation/devicetree/bindings/*/maxim,max77686.yaml F: Documentation/devicetree/bindings/*/maxim,max77693.yaml @@ -12401,7 +12406,7 @@ F: drivers/mmc/host/mtk-sd.c MEDIATEK MT76 WIRELESS LAN DRIVER M: Felix Fietkau <nbd@nbd.name> -M: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com> +M: Lorenzo Bianconi <lorenzo@kernel.org> M: Ryder Lee <ryder.lee@mediatek.com> R: Shayne Chen <shayne.chen@mediatek.com> R: Sean Wang <sean.wang@mediatek.com> @@ -12672,9 +12677,10 @@ F: mm/memblock.c F: tools/testing/memblock/ MEMORY CONTROLLER DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-kernel@vger.kernel.org S: Maintained +B: mailto:krzysztof.kozlowski@linaro.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux-mem-ctrl.git F: Documentation/devicetree/bindings/memory-controllers/ F: drivers/memory/ @@ -13623,6 +13629,7 @@ F: net/core/drop_monitor.c NETWORKING DRIVERS M: "David S. Miller" <davem@davemloft.net> +M: Eric Dumazet <edumazet@google.com> M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org @@ -13670,6 +13677,7 @@ F: tools/testing/selftests/drivers/net/dsa/ NETWORKING [GENERAL] M: "David S. Miller" <davem@davemloft.net> +M: Eric Dumazet <edumazet@google.com> M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org @@ -13816,10 +13824,11 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-nfc@lists.01.org (subscribers-only) L: netdev@vger.kernel.org S: Maintained +B: mailto:linux-nfc@lists.01.org F: Documentation/devicetree/bindings/net/nfc/ F: drivers/nfc/ F: include/linux/platform_data/nfcmrvl.h @@ -14133,7 +14142,7 @@ F: Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml F: drivers/regulator/pf8x00-regulator.c NXP PTN5150A CC LOGIC AND EXTCON DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/extcon/extcon-ptn5150.yaml @@ -14656,7 +14665,6 @@ F: drivers/rtc/rtc-optee.c OPA-VNIC DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/ulp/opa_vnic @@ -14687,7 +14695,7 @@ F: scripts/dtc/ OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS M: Rob Herring <robh+dt@kernel.org> -M: Krzysztof Kozlowski <krzk+dt@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org> L: devicetree@vger.kernel.org S: Maintained C: irc://irc.libera.chat/devicetree @@ -15599,7 +15607,7 @@ F: drivers/pinctrl/renesas/ PIN CONTROLLER - SAMSUNG M: Tomasz Figa <tomasz.figa@gmail.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -15607,6 +15615,7 @@ L: linux-samsung-soc@vger.kernel.org S: Maintained C: irc://irc.libera.chat/linux-exynos Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ +B: mailto:linux-samsung-soc@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/samsung.git F: Documentation/devicetree/bindings/pinctrl/samsung,pinctrl*yaml F: drivers/pinctrl/samsung/ @@ -16098,7 +16107,6 @@ F: include/uapi/linux/qemu_fw_cfg.h QIB DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/hw/qib/ @@ -16616,7 +16624,6 @@ F: drivers/net/ethernet/rdc/r6040.c RDMAVT - RDMA verbs software M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/sw/rdmavt @@ -17011,8 +17018,7 @@ S: Odd Fixes F: drivers/tty/serial/rp2.* ROHM BD99954 CHARGER IC -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/power/supply/bd99954-charger.c F: drivers/power/supply/bd99954-charger.h @@ -17035,8 +17041,7 @@ F: drivers/regulator/bd9571mwv-regulator.c F: include/linux/mfd/bd9571mwv.h ROHM POWER MANAGEMENT IC DEVICE DRIVERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/clk/clk-bd718x7.c F: drivers/gpio/gpio-bd71815.c @@ -17278,7 +17283,7 @@ W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/scsi/zfcp_* S3C ADC BATTERY DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-samsung-soc@vger.kernel.org S: Odd Fixes F: drivers/power/supply/s3c_adc_battery.c @@ -17323,15 +17328,16 @@ F: Documentation/admin-guide/LSM/SafeSetID.rst F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -17366,11 +17372,12 @@ S: Maintained F: drivers/platform/x86/samsung-laptop.c SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Supported +B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/clock/samsung,s2mps11.yaml F: Documentation/devicetree/bindings/mfd/samsung,s2m*.yaml F: Documentation/devicetree/bindings/mfd/samsung,s5m*.yaml @@ -17392,7 +17399,7 @@ F: drivers/media/platform/samsung/s3c-camif/ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Krzysztof Opasiak <k.opasiak@samsung.com> L: linux-nfc@lists.01.org (subscribers-only) S: Maintained @@ -17414,7 +17421,7 @@ S: Supported F: drivers/media/i2c/s5k5baf.c SAMSUNG S5P Security SubSystem (SSS) DRIVER -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Vladimir Zapolskiy <vz@mleia.com> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17449,7 +17456,7 @@ F: include/linux/clk/samsung.h F: include/linux/platform_data/clk-s3c2410.h SAMSUNG SPI DRIVERS -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Andi Shyti <andi@etezian.org> L: linux-spi@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17467,7 +17474,7 @@ F: drivers/net/ethernet/samsung/sxgbe/ SAMSUNG THERMAL DRIVER M: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> -M: Krzysztof Kozlowski <krzk@kernel.org> +M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> L: linux-pm@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -17651,8 +17658,8 @@ K: \bTIF_SECCOMP\b SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) Broadcom BRCMSTB DRIVER M: Al Cooper <alcooperx@gmail.com> +R: Broadcom Kernel Team <bcm-kernel-feedback-list@broadcom.com> L: linux-mmc@vger.kernel.org -L: bcm-kernel-feedback-list@broadcom.com S: Maintained F: drivers/mmc/host/sdhci-brcmstb* @@ -21118,7 +21125,7 @@ F: include/linux/regulator/ K: regulator_get_optional VOLTAGE AND CURRENT REGULATOR IRQ HELPERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: drivers/regulator/irq_helpers.c VRF @@ -21231,10 +21238,8 @@ S: Maintained F: drivers/hid/hid-wiimote* WILOCITY WIL6210 WIRELESS DRIVER -M: Maya Erez <merez@codeaurora.org> L: linux-wireless@vger.kernel.org -L: wil6210@qti.qualcomm.com -S: Supported +S: Orphan W: https://wireless.wiki.kernel.org/en/users/Drivers/wil6210 F: drivers/net/wireless/ath/wil6210/ @@ -21438,6 +21443,15 @@ F: arch/x86/include/asm/uv/ F: arch/x86/kernel/apic/x2apic_uv_x.c F: arch/x86/platform/uv/ +X86 STACK UNWINDING +M: Josh Poimboeuf <jpoimboe@redhat.com> +M: Peter Zijlstra <peterz@infradead.org> +S: Supported +F: arch/x86/include/asm/unwind*.h +F: arch/x86/kernel/dumpstack.c +F: arch/x86/kernel/stacktrace.c +F: arch/x86/kernel/unwind_*.c + X86 VDSO M: Andy Lutomirski <luto@kernel.org> L: linux-kernel@vger.kernel.org @@ -21600,7 +21614,6 @@ F: drivers/xen/*swiotlb* XFS FILESYSTEM C: irc://irc.oftc.net/xfs M: Darrick J. Wong <djwong@kernel.org> -M: linux-xfs@vger.kernel.org L: linux-xfs@vger.kernel.org S: Supported W: http://xfs.org/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc5 NAME = Superb Owl # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 29b0167c088b..31c4fdc4a4ba 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -854,10 +854,8 @@ config HAVE_ARCH_HUGE_VMAP # # Archs that select this would be capable of PMD-sized vmaps (i.e., -# arch_vmap_pmd_supported() returns true), and they must make no assumptions -# that vmalloc memory is mapped with PAGE_SIZE ptes. The VM_NO_HUGE_VMAP flag -# can be used to prohibit arch-specific allocations from using hugepages to -# help with this (e.g., modules may require it). +# arch_vmap_pmd_supported() returns true). The VM_ALLOW_HUGE_VMAP flag +# must be used to enable allocations to use hugepages. # config HAVE_ARCH_HUGE_VMALLOC depends on HAVE_ARCH_HUGE_VMAP diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index dcaa44e408ac..f48ba03e9b5e 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -275,7 +275,7 @@ cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>, <&creg_gpio 1 GPIO_ACTIVE_LOW>; - spi-flash@0 { + flash@0 { compatible = "sst26wf016b", "jedec,spi-nor"; reg = <0>; #address-cells = <1>; diff --git a/arch/arc/include/asm/atomic-llsc.h b/arch/arc/include/asm/atomic-llsc.h index 088d348781c1..1b0ffaeee16d 100644 --- a/arch/arc/include/asm/atomic-llsc.h +++ b/arch/arc/include/asm/atomic-llsc.h @@ -5,7 +5,7 @@ #define arch_atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#define ATOMIC_OP(op, c_op, asm_op) \ +#define ATOMIC_OP(op, asm_op) \ static inline void arch_atomic_##op(int i, atomic_t *v) \ { \ unsigned int val; \ @@ -21,7 +21,7 @@ static inline void arch_atomic_##op(int i, atomic_t *v) \ : "cc"); \ } \ -#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ +#define ATOMIC_OP_RETURN(op, asm_op) \ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ { \ unsigned int val; \ @@ -42,7 +42,7 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \ #define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed #define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed -#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ +#define ATOMIC_FETCH_OP(op, asm_op) \ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ { \ unsigned int val, orig; \ @@ -69,23 +69,23 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ #define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed #define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_OP_RETURN(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_OP_RETURN(op, asm_op) \ + ATOMIC_FETCH_OP(op, asm_op) -ATOMIC_OPS(add, +=, add) -ATOMIC_OPS(sub, -=, sub) +ATOMIC_OPS(add, add) +ATOMIC_OPS(sub, sub) #undef ATOMIC_OPS -#define ATOMIC_OPS(op, c_op, asm_op) \ - ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_FETCH_OP(op, c_op, asm_op) +#define ATOMIC_OPS(op, asm_op) \ + ATOMIC_OP(op, asm_op) \ + ATOMIC_FETCH_OP(op, asm_op) -ATOMIC_OPS(and, &=, and) -ATOMIC_OPS(andnot, &= ~, bic) -ATOMIC_OPS(or, |=, or) -ATOMIC_OPS(xor, ^=, xor) +ATOMIC_OPS(and, and) +ATOMIC_OPS(andnot, bic) +ATOMIC_OPS(or, or) +ATOMIC_OPS(xor, xor) #define arch_atomic_andnot arch_atomic_andnot diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h index 7848348719b2..64ca25d199be 100644 --- a/arch/arc/include/asm/pgtable-levels.h +++ b/arch/arc/include/asm/pgtable-levels.h @@ -98,9 +98,6 @@ /* * 1st level paging: pgd */ -#define pgd_index(addr) ((addr) >> PGDIR_SHIFT) -#define pgd_offset(mm, addr) (((mm)->pgd) + pgd_index(addr)) -#define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pgd_ERROR(e) \ pr_crit("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) diff --git a/arch/arc/kernel/disasm.c b/arch/arc/kernel/disasm.c index 03f8b1be0c3a..1e1db51b6941 100644 --- a/arch/arc/kernel/disasm.c +++ b/arch/arc/kernel/disasm.c @@ -366,7 +366,7 @@ void __kprobes disasm_instr(unsigned long addr, struct disasm_state *state, case op_SP: /* LD_S|LDB_S b,[sp,u7], ST_S|STB_S b,[sp,u7] */ /* note: we are ignoring possibility of: * ADD_S, SUB_S, PUSH_S, POP_S as these should not - * cause unaliged exception anyway */ + * cause unaligned exception anyway */ state->write = BITS(state->words[0], 6, 6); state->zz = BITS(state->words[0], 5, 5); if (state->zz) @@ -503,7 +503,6 @@ int __kprobes disasm_next_pc(unsigned long pc, struct pt_regs *regs, { struct disasm_state instr; - memset(&instr, 0, sizeof(struct disasm_state)); disasm_instr(pc, &instr, 0, regs, cregs); *next_pc = pc + instr.instr_len; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index dd77a0c8f740..66ba549b520f 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -196,6 +196,7 @@ tracesys_exit: st r0, [sp, PT_r0] ; sys call return value in pt_regs ;POST Sys Call Ptrace Hook + mov r0, sp ; pt_regs needed bl @syscall_trace_exit b ret_from_exception ; NOT ret_from_system_call at is saves r0 which ; we'd done before calling post hook above diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index f748483628f2..3c1590c27fae 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -319,7 +319,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) regs->ret = (unsigned long)ksig->ka.sa.sa_handler; /* - * handler returns using sigreturn stub provided already by userpsace + * handler returns using sigreturn stub provided already by userspace * If not, nuke the process right away */ if(!(ksig->ka.sa.sa_flags & SA_RESTORER)) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 78e6d069b1c1..d947473f1e6d 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -35,7 +35,7 @@ EXPORT_SYMBOL_GPL(smp_atomic_ops_lock); struct plat_smp_ops __weak plat_smp_ops; -/* XXX: per cpu ? Only needed once in early seconday boot */ +/* XXX: per cpu ? Only needed once in early secondary boot */ struct task_struct *secondary_idle_tsk; /* Called from start_kernel */ @@ -274,7 +274,7 @@ static void ipi_send_msg_one(int cpu, enum ipi_msg_type msg) * and read back old value */ do { - new = old = READ_ONCE(*ipi_data_ptr); + new = old = *ipi_data_ptr; new |= 1U << msg; } while (cmpxchg(ipi_data_ptr, old, new) != old); diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index d63ebd81f1c6..99a9b92ed98d 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -237,7 +237,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, if (state.fault) goto fault; - /* clear any remanants of delay slot */ + /* clear any remnants of delay slot */ if (delay_mode(regs)) { regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 8aa1231865d1..5446967ea98d 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -401,7 +401,7 @@ static inline void __before_dc_op(const int op) { if (op == OP_FLUSH_N_INV) { /* Dcache provides 2 cmd: FLUSH or INV - * INV inturn has sub-modes: DISCARD or FLUSH-BEFORE + * INV in turn has sub-modes: DISCARD or FLUSH-BEFORE * flush-n-inv is achieved by INV cmd but with IM=1 * So toggle INV sub-mode depending on op request and default */ diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index c9629cb5ccd1..7da42a5b959c 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -263,6 +263,8 @@ compatible = "ti,am3359-tscadc"; reg = <0x0 0x1000>; interrupts = <16>; + clocks = <&adc_tsc_fck>; + clock-names = "fck"; status = "disabled"; dmas = <&edma 53 0>, <&edma 57 0>; dma-names = "fifo0", "fifo1"; diff --git a/arch/arm/boot/dts/am3517-evm.dts b/arch/arm/boot/dts/am3517-evm.dts index 0d2fac98ce7d..c8b80f156ec9 100644 --- a/arch/arm/boot/dts/am3517-evm.dts +++ b/arch/arm/boot/dts/am3517-evm.dts @@ -161,6 +161,8 @@ /* HS USB Host PHY on PORT 1 */ hsusb1_phy: hsusb1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb1_rst_pins>; compatible = "usb-nop-xceiv"; reset-gpios = <&gpio2 25 GPIO_ACTIVE_LOW>; /* gpio_57 */ #phy-cells = <0>; @@ -168,7 +170,9 @@ }; &davinci_emac { - status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <ðernet_pins>; + status = "okay"; }; &davinci_mdio { @@ -193,6 +197,8 @@ }; &i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; clock-frequency = <400000>; /* User DIP swithes [1:8] / User LEDS [1:2] */ tca6416: gpio@21 { @@ -205,6 +211,8 @@ }; &i2c3 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; clock-frequency = <400000>; }; @@ -223,6 +231,8 @@ }; &usbhshost { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb1_pins>; port1-mode = "ehci-phy"; }; @@ -231,8 +241,35 @@ }; &omap3_pmx_core { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb1_rst_pins>; + + ethernet_pins: pinmux_ethernet_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21fe, PIN_INPUT | MUX_MODE0) /* rmii_mdio_data */ + OMAP3_CORE1_IOPAD(0x2200, MUX_MODE0) /* rmii_mdio_clk */ + OMAP3_CORE1_IOPAD(0x2202, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_rxd0 */ + OMAP3_CORE1_IOPAD(0x2204, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_rxd1 */ + OMAP3_CORE1_IOPAD(0x2206, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_crs_dv */ + OMAP3_CORE1_IOPAD(0x2208, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_rxer */ + OMAP3_CORE1_IOPAD(0x220a, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_txd0 */ + OMAP3_CORE1_IOPAD(0x220c, PIN_OUTPUT_PULLDOWN | MUX_MODE0) /* rmii_txd1 */ + OMAP3_CORE1_IOPAD(0x220e, PIN_OUTPUT_PULLDOWN |MUX_MODE0) /* rmii_txen */ + OMAP3_CORE1_IOPAD(0x2210, PIN_INPUT_PULLDOWN | MUX_MODE0) /* rmii_50mhz_clk */ + >; + }; + + i2c2_pins: pinmux_i2c2_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_scl */ + OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c2_sda */ + >; + }; + + i2c3_pins: pinmux_i2c3_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_scl */ + OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c3_sda */ + >; + }; leds_pins: pinmux_leds_pins { pinctrl-single,pins = < @@ -300,8 +337,6 @@ }; &omap3_pmx_core2 { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb1_pins>; hsusb1_pins: pinmux_hsusb1_pins { pinctrl-single,pins = < diff --git a/arch/arm/boot/dts/am3517-som.dtsi b/arch/arm/boot/dts/am3517-som.dtsi index 8b669e2eafec..f7b680f6c48a 100644 --- a/arch/arm/boot/dts/am3517-som.dtsi +++ b/arch/arm/boot/dts/am3517-som.dtsi @@ -69,6 +69,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <400000>; s35390a: s35390a@30 { @@ -179,6 +181,13 @@ &omap3_pmx_core { + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT_PULLUP | MUX_MODE0) /* i2c1_sda */ + >; + }; + wl12xx_buffer_pins: pinmux_wl12xx_buffer_pins { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2156, PIN_OUTPUT | MUX_MODE4) /* mmc1_dat7.gpio_129 */ diff --git a/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi b/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi index c1c8650dafce..3542ad8a243e 100644 --- a/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi +++ b/arch/arm/boot/dts/at91-dvk_su60_somc.dtsi @@ -44,7 +44,7 @@ status = "okay"; /* spi0.0: 4M Flash Macronix MX25R4035FM1IL0 */ - spi-flash@0 { + flash@0 { compatible = "mxicy,mx25u4035", "jedec,spi-nor"; spi-max-frequency = <33000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-q5xr5.dts b/arch/arm/boot/dts/at91-q5xr5.dts index 47a00062f01f..9cf60b6f695c 100644 --- a/arch/arm/boot/dts/at91-q5xr5.dts +++ b/arch/arm/boot/dts/at91-q5xr5.dts @@ -125,7 +125,7 @@ cs-gpios = <&pioA 3 GPIO_ACTIVE_HIGH>, <&pioC 11 GPIO_ACTIVE_LOW>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "jedec,spi-nor"; spi-max-frequency = <20000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sam9_l9260.dts b/arch/arm/boot/dts/at91-sam9_l9260.dts index 1e2a28c2f365..2fb51b9aca2a 100644 --- a/arch/arm/boot/dts/at91-sam9_l9260.dts +++ b/arch/arm/boot/dts/at91-sam9_l9260.dts @@ -101,7 +101,7 @@ nand0: nand@40000000 { nand-bus-width = <8>; nand-ecc-mode = "soft"; - nand-on-flash-bbt = <1>; + nand-on-flash-bbt; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi index 21c86171e462..ba621783acdb 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi @@ -214,7 +214,7 @@ pinctrl-0 = <&pinctrl_qspi1_default>; status = "disabled"; - qspi1_flash: spi_flash@0 { + qspi1_flash: flash@0 { #address-cells = <1>; #size-cells = <1>; compatible = "jedec,spi-nor"; diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts index c145c4e5ef58..5e8755f22784 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1_ek.dts @@ -191,7 +191,7 @@ &qspi1 { status = "okay"; - qspi1_flash: spi_flash@0 { + qspi1_flash: flash@0 { status = "okay"; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts index 9bf2ec0ba3e2..cdfe891f9a9e 100644 --- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts @@ -137,7 +137,7 @@ pinctrl-0 = <&pinctrl_spi0_default>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; reg = <0>; spi-max-frequency = <50000000>; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index d72c042f2850..a49c2966b41e 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -57,8 +57,8 @@ }; spi0: spi@f0004000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi0_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi0_cs>; cs-gpios = <&pioD 13 0>, <0>, <0>, <&pioD 16 0>; status = "okay"; }; @@ -171,8 +171,8 @@ }; spi1: spi@f8008000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi1_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi1_cs>; cs-gpios = <&pioC 25 0>; status = "okay"; }; diff --git a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi index 710cb72bda5a..fd1086f52b40 100644 --- a/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi +++ b/arch/arm/boot/dts/at91-sama5d4_ma5d4.dtsi @@ -49,7 +49,7 @@ cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index d241c24f0d83..e519d2747936 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -81,8 +81,8 @@ }; spi1: spi@fc018000 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_spi0_cs>; + pinctrl-names = "default", "cs"; + pinctrl-1 = <&pinctrl_spi1_cs>; cs-gpios = <&pioB 21 0>; status = "okay"; }; @@ -140,7 +140,7 @@ atmel,pins = <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; }; - pinctrl_spi0_cs: spi0_cs_default { + pinctrl_spi1_cs: spi1_cs_default { atmel,pins = <AT91_PIOB 21 AT91_PERIPH_GPIO AT91_PINCTRL_NONE>; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index fe432b6b7e95..7017f626f362 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -65,7 +65,7 @@ spi0: spi@f8010000 { cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts index 08685a10eda1..d83f76a6cd6a 100644 --- a/arch/arm/boot/dts/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/at91-sama7g5ek.dts @@ -495,7 +495,7 @@ pinctrl_flx3_default: flx3_default { pinmux = <PIN_PD16__FLEXCOM3_IO0>, <PIN_PD17__FLEXCOM3_IO1>; - bias-disable; + bias-pull-up; }; pinctrl_flx4_default: flx4_default { @@ -655,7 +655,7 @@ <PIN_PB21__QSPI0_INT>; bias-disable; slew-rate = <0>; - atmel,drive-strength = <ATMEL_PIO_DRVSTR_HI>; + atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>; }; pinctrl_sdmmc0_default: sdmmc0_default { diff --git a/arch/arm/boot/dts/at91-vinco.dts b/arch/arm/boot/dts/at91-vinco.dts index a51a3372afa1..ebeaa6ab500e 100644 --- a/arch/arm/boot/dts/at91-vinco.dts +++ b/arch/arm/boot/dts/at91-vinco.dts @@ -59,7 +59,7 @@ spi0: spi@f8010000 { cs-gpios = <&pioC 3 0>, <0>, <0>, <0>; status = "okay"; - m25p80@0 { + flash@0 { compatible = "n25q32b", "jedec,spi-nor"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts index e1ef4e44e663..4624a6f076f8 100644 --- a/arch/arm/boot/dts/at91rm9200ek.dts +++ b/arch/arm/boot/dts/at91rm9200ek.dts @@ -73,7 +73,7 @@ spi0: spi@fffe0000 { status = "okay"; cs-gpios = <&pioA 3 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <15000000>; reg = <0>; @@ -94,7 +94,7 @@ status = "okay"; }; - nor_flash@10000000 { + flash@10000000 { compatible = "cfi-flash"; reg = <0x10000000 0x800000>; linux,mtd-name = "physmap-flash.0"; diff --git a/arch/arm/boot/dts/at91sam9260ek.dts b/arch/arm/boot/dts/at91sam9260ek.dts index ce96345d28a3..6381088ba24f 100644 --- a/arch/arm/boot/dts/at91sam9260ek.dts +++ b/arch/arm/boot/dts/at91sam9260ek.dts @@ -92,7 +92,7 @@ spi0: spi@fffc8000 { cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; - mtd_dataflash@1 { + flash@1 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <1>; diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts index beed819609e8..8f11c0b7d76d 100644 --- a/arch/arm/boot/dts/at91sam9261ek.dts +++ b/arch/arm/boot/dts/at91sam9261ek.dts @@ -145,7 +145,7 @@ cs-gpios = <&pioA 3 0>, <0>, <&pioA 28 0>, <0>; status = "okay"; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; reg = <0>; spi-max-frequency = <15000000>; diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts index 71f60576761a..42e734020235 100644 --- a/arch/arm/boot/dts/at91sam9263ek.dts +++ b/arch/arm/boot/dts/at91sam9263ek.dts @@ -95,7 +95,7 @@ spi0: spi@fffa4000 { status = "okay"; cs-gpios = <&pioA 5 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi index 87bb39060e8b..85c17dd1c8d5 100644 --- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi +++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi @@ -110,7 +110,7 @@ spi0: spi@fffc8000 { cs-gpios = <0>, <&pioC 11 0>, <0>, <0>; - mtd_dataflash@1 { + flash@1 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <50000000>; reg = <1>; @@ -214,11 +214,23 @@ 24c512@50 { compatible = "atmel,24c512"; reg = <0x50>; + vcc-supply = <®_3v3>; }; wm8731: wm8731@1b { compatible = "wm8731"; reg = <0x1b>; + + /* PCK0 at 12MHz */ + clocks = <&pmc PMC_TYPE_SYSTEM 8>; + clock-names = "mclk"; + assigned-clocks = <&pmc PMC_TYPE_SYSTEM 8>; + assigned-clock-rates = <12000000>; + + HPVDD-supply = <&vcc_dac>; + AVDD-supply = <&vcc_dac>; + DCVDD-supply = <®_3v3>; + DBVDD-supply = <®_3v3>; }; }; @@ -254,4 +266,35 @@ atmel,ssc-controller = <&ssc0>; atmel,audio-codec = <&wm8731>; }; + + reg_5v: fixedregulator0 { + compatible = "regulator-fixed"; + regulator-name = "5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + reg_3v3: fixedregulator1 { + compatible = "regulator-fixed"; + regulator-name = "3V3"; + vin-supply = <®_5v>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_1v: fixedregulator2 { + compatible = "regulator-fixed"; + regulator-name = "1V"; + vin-supply = <®_5v>; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + }; + + vcc_dac: fixedregulator3 { + compatible = "regulator-fixed"; + regulator-name = "VCC_DAC"; + vin-supply = <®_3v3>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; }; diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts index b6256a20fbc7..e5db198a87a8 100644 --- a/arch/arm/boot/dts/at91sam9m10g45ek.dts +++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts @@ -167,7 +167,7 @@ spi0: spi@fffa4000{ status = "okay"; cs-gpios = <&pioB 3 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <13000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index 2bc4e6e0a923..c905d7bfc771 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -119,7 +119,7 @@ spi0: spi@f0000000 { status = "okay"; cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts index 62981b39c815..d74b8d9d84aa 100644 --- a/arch/arm/boot/dts/at91sam9rlek.dts +++ b/arch/arm/boot/dts/at91sam9rlek.dts @@ -180,7 +180,7 @@ spi0: spi@fffcc000 { status = "okay"; cs-gpios = <&pioA 28 0>, <0>, <0>, <0>; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; spi-max-frequency = <15000000>; reg = <0>; diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi index 6d1264de6060..5f4eaa618ab4 100644 --- a/arch/arm/boot/dts/at91sam9x5ek.dtsi +++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi @@ -125,7 +125,7 @@ cs-gpios = <&pioA 14 0>, <0>, <0>, <0>; status = "disabled"; /* conflicts with mmc1 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts index 87c517d65f62..e9aecac4f5b5 100644 --- a/arch/arm/boot/dts/da850-evm.dts +++ b/arch/arm/boot/dts/da850-evm.dts @@ -278,7 +278,7 @@ status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&spi1_pins &spi1_cs0_pin>; - flash: m25p80@0 { + flash: flash@0 { #address-cells = <1>; #size-cells = <1>; compatible = "jedec,spi-nor"; diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts index 5126e2d72ed7..778796c10af8 100644 --- a/arch/arm/boot/dts/dm8168-evm.dts +++ b/arch/arm/boot/dts/dm8168-evm.dts @@ -177,7 +177,7 @@ pinctrl-names = "default"; pinctrl-0 = <&mcspi1_pins>; - m25p80@0 { + flash@0 { compatible = "w25x32"; spi-max-frequency = <48000000>; reg = <0>; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index 0a11bacffc1f..5733e3a4ea8e 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -4188,11 +4188,11 @@ reg = <0x1d0010 0x4>; reg-names = "sysc"; ti,sysc-midle = <SYSC_IDLE_FORCE>, - <SYSC_IDLE_NO>, - <SYSC_IDLE_SMART>; + <SYSC_IDLE_NO>; ti,sysc-sidle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>; + power-domains = <&prm_vpe>; clocks = <&vpe_clkctrl DRA7_VPE_VPE_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/imx28-ts4600.dts b/arch/arm/boot/dts/imx28-ts4600.dts index 097ec35c62d8..0d58da1c0cc5 100644 --- a/arch/arm/boot/dts/imx28-ts4600.dts +++ b/arch/arm/boot/dts/imx28-ts4600.dts @@ -26,7 +26,7 @@ pinctrl-0 = <&mmc0_4bit_pins_a &mmc0_sck_cfg &en_sd_pwr>; - broken-cd = <1>; + broken-cd; bus-width = <4>; vmmc-supply = <®_vddio_sd0>; status = "okay"; diff --git a/arch/arm/boot/dts/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/imx6qdl-apalis.dtsi index ed2739e39085..bd763bae596b 100644 --- a/arch/arm/boot/dts/imx6qdl-apalis.dtsi +++ b/arch/arm/boot/dts/imx6qdl-apalis.dtsi @@ -286,6 +286,8 @@ codec: sgtl5000@a { compatible = "fsl,sgtl5000"; reg = <0x0a>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_sgtl5000>; clocks = <&clks IMX6QDL_CLK_CKO>; VDDA-supply = <®_module_3v3_audio>; VDDIO-supply = <®_module_3v3>; @@ -517,8 +519,6 @@ MX6QDL_PAD_DISP0_DAT21__AUD4_TXD 0x130b0 MX6QDL_PAD_DISP0_DAT22__AUD4_TXFS 0x130b0 MX6QDL_PAD_DISP0_DAT23__AUD4_RXD 0x130b0 - /* SGTL5000 sys_mclk */ - MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0 >; }; @@ -811,6 +811,12 @@ >; }; + pinctrl_sgtl5000: sgtl5000grp { + fsl,pins = < + MX6QDL_PAD_GPIO_5__CCM_CLKO1 0x130b0 + >; + }; + pinctrl_spdif: spdifgrp { fsl,pins = < MX6QDL_PAD_GPIO_16__SPDIF_IN 0x1b0b0 diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi index 563bf9d44fe0..0b90c3f59f89 100644 --- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi @@ -154,112 +154,112 @@ regulators { bcore1 { regulator-name = "bcore1"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bcore2 { regulator-name = "bcore2"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bpro { regulator-name = "bpro"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bperi { regulator-name = "bperi"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bmem { regulator-name = "bmem"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo2 { regulator-name = "ldo2"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <1800000>; }; ldo3 { regulator-name = "ldo3"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo4 { regulator-name = "ldo4"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo5 { regulator-name = "ldo5"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo6 { regulator-name = "ldo6"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo7 { regulator-name = "ldo7"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo8 { regulator-name = "ldo8"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo9 { regulator-name = "ldo9"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo10 { regulator-name = "ldo10"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; ldo11 { regulator-name = "ldo11"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <300000>; regulator-max-microvolt = <3300000>; }; bio { regulator-name = "bio"; - regulator-always-on = <1>; + regulator-always-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; diff --git a/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi b/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi index 7cda6944501d..205e4d462702 100644 --- a/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi +++ b/arch/arm/boot/dts/imx6ul-phytec-segin-peb-av-02.dtsi @@ -72,8 +72,8 @@ st,settling = <2>; st,fraction-z = <7>; st,i-drive = <1>; - touchscreen-inverted-x = <1>; - touchscreen-inverted-y = <1>; + touchscreen-inverted-x; + touchscreen-inverted-y; }; }; }; diff --git a/arch/arm/boot/dts/imx6ull-colibri.dtsi b/arch/arm/boot/dts/imx6ull-colibri.dtsi index 7f35a06dff95..951a2a6c5a65 100644 --- a/arch/arm/boot/dts/imx6ull-colibri.dtsi +++ b/arch/arm/boot/dts/imx6ull-colibri.dtsi @@ -37,7 +37,7 @@ reg_sd1_vmmc: regulator-sd1-vmmc { compatible = "regulator-gpio"; - gpio = <&gpio5 9 GPIO_ACTIVE_HIGH>; + gpios = <&gpio5 9 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_snvs_reg_sd>; regulator-always-on; diff --git a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts index 2a0a98fe67f0..3240c67e0c39 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-35xx-devkit.dts @@ -11,3 +11,18 @@ model = "LogicPD Zoom OMAP35xx SOM-LV Development Kit"; compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3430", "ti,omap3"; }; + +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + OMAP3430_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ + OMAP3430_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ + OMAP3430_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ + OMAP3430_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ + OMAP3430_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ + OMAP3430_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts index a604d92221a4..c757f0d7781c 100644 --- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts @@ -11,3 +11,18 @@ model = "LogicPD Zoom DM3730 SOM-LV Development Kit"; compatible = "logicpd,dm3730-som-lv-devkit", "ti,omap3630", "ti,omap3"; }; + +&omap3_pmx_core2 { + pinctrl-names = "default"; + pinctrl-0 = <&hsusb2_2_pins>; + hsusb2_2_pins: pinmux_hsusb2_2_pins { + pinctrl-single,pins = < + OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ + OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ + OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ + OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ + OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ + OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ + >; + }; +}; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index b56524cc7fe2..55b619c99e24 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -265,21 +265,6 @@ }; }; -&omap3_pmx_core2 { - pinctrl-names = "default"; - pinctrl-0 = <&hsusb2_2_pins>; - hsusb2_2_pins: pinmux_hsusb2_2_pins { - pinctrl-single,pins = < - OMAP3630_CORE2_IOPAD(0x25f0, PIN_OUTPUT | MUX_MODE3) /* etk_d10.hsusb2_clk */ - OMAP3630_CORE2_IOPAD(0x25f2, PIN_OUTPUT | MUX_MODE3) /* etk_d11.hsusb2_stp */ - OMAP3630_CORE2_IOPAD(0x25f4, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d12.hsusb2_dir */ - OMAP3630_CORE2_IOPAD(0x25f6, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d13.hsusb2_nxt */ - OMAP3630_CORE2_IOPAD(0x25f8, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d14.hsusb2_data0 */ - OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT_PULLDOWN | MUX_MODE3) /* etk_d15.hsusb2_data1 */ - >; - }; -}; - &uart2 { interrupts-extended = <&intc 73 &omap3_pmx_core OMAP3_UART2_RX>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi index b4664ab00256..d3da8b1b473b 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi @@ -118,8 +118,8 @@ gpmc,device-width = <2>; gpmc,wait-pin = <0>; gpmc,burst-length = <4>; - gpmc,cycle2cycle-samecsen = <1>; - gpmc,cycle2cycle-diffcsen = <1>; + gpmc,cycle2cycle-samecsen; + gpmc,cycle2cycle-diffcsen; gpmc,cs-on-ns = <0>; gpmc,cs-rd-off-ns = <45>; gpmc,cs-wr-off-ns = <45>; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index 7e3d8147e2c1..0365f06165e9 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -31,6 +31,8 @@ aliases { display0 = &lcd; display1 = &tv0; + /delete-property/ mmc2; + /delete-property/ mmc3; }; ldo_3v3: fixedregulator { diff --git a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi index cbe42c4153a0..b4d286a6fab1 100644 --- a/arch/arm/boot/dts/qcom-apq8064-pins.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064-pins.dtsi @@ -76,7 +76,7 @@ pinconf { pins = "gpio20", "gpio21"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -116,7 +116,7 @@ pinconf { pins = "gpio24", "gpio25"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -141,7 +141,7 @@ pinconf { pins = "gpio8", "gpio9"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -166,7 +166,7 @@ pinconf { pins = "gpio12", "gpio13"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -229,7 +229,7 @@ pinconf { pins = "gpio16", "gpio17"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; @@ -282,7 +282,7 @@ pinconf { pins = "gpio84", "gpio85"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm/boot/dts/qcom-ipq8064.dtsi b/arch/arm/boot/dts/qcom-ipq8064.dtsi index 996f4458d9fc..8cb04aa8ed2f 100644 --- a/arch/arm/boot/dts/qcom-ipq8064.dtsi +++ b/arch/arm/boot/dts/qcom-ipq8064.dtsi @@ -972,7 +972,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -996,7 +996,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -1020,7 +1020,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; @@ -1044,7 +1044,7 @@ snps,axi-config = <&stmmac_axi_setup>; snps,pbl = <32>; - snps,aal = <1>; + snps,aal; qcom,nss-common = <&nss_common>; qcom,qsgmii-csr = <&qsgmii_csr>; diff --git a/arch/arm/boot/dts/sama5d3xmb.dtsi b/arch/arm/boot/dts/sama5d3xmb.dtsi index a499de8a7a64..3652c9e24124 100644 --- a/arch/arm/boot/dts/sama5d3xmb.dtsi +++ b/arch/arm/boot/dts/sama5d3xmb.dtsi @@ -26,7 +26,7 @@ spi0: spi@f0004000 { dmas = <0>, <0>; /* Do not use DMA for spi0 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi index fa9e5e2a745d..5d9e97fecf83 100644 --- a/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi +++ b/arch/arm/boot/dts/sama5d3xmb_cmp.dtsi @@ -25,7 +25,7 @@ spi0: spi@f0004000 { dmas = <0>, <0>; /* Do not use DMA for spi0 */ - m25p80@0 { + flash@0 { compatible = "atmel,at25df321a"; spi-max-frequency = <50000000>; reg = <0>; diff --git a/arch/arm/boot/dts/sama7g5.dtsi b/arch/arm/boot/dts/sama7g5.dtsi index 4decd3a91a76..f691c8f08d04 100644 --- a/arch/arm/boot/dts/sama7g5.dtsi +++ b/arch/arm/boot/dts/sama7g5.dtsi @@ -601,9 +601,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 39>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(7)>, - <&dma0 AT91_XDMAC_DT_PERID(8)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(8)>, + <&dma0 AT91_XDMAC_DT_PERID(7)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; @@ -786,9 +786,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 46>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(21)>, - <&dma0 AT91_XDMAC_DT_PERID(22)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(22)>, + <&dma0 AT91_XDMAC_DT_PERID(21)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; @@ -810,9 +810,9 @@ #size-cells = <0>; clocks = <&pmc PMC_TYPE_PERIPHERAL 47>; atmel,fifo-size = <32>; - dmas = <&dma0 AT91_XDMAC_DT_PERID(23)>, - <&dma0 AT91_XDMAC_DT_PERID(24)>; - dma-names = "rx", "tx"; + dmas = <&dma0 AT91_XDMAC_DT_PERID(24)>, + <&dma0 AT91_XDMAC_DT_PERID(23)>; + dma-names = "tx", "rx"; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts index 4cbadcb41084..ddd1cf4d0554 100644 --- a/arch/arm/boot/dts/spear1310-evb.dts +++ b/arch/arm/boot/dts/spear1310-evb.dts @@ -379,7 +379,7 @@ }; }; - m25p80@1 { + flash@1 { compatible = "st,m25p80"; reg = <1>; spi-max-frequency = <12000000>; diff --git a/arch/arm/boot/dts/spear1340-evb.dts b/arch/arm/boot/dts/spear1340-evb.dts index fd194ebeedc9..3a51a41eb5e4 100644 --- a/arch/arm/boot/dts/spear1340-evb.dts +++ b/arch/arm/boot/dts/spear1340-evb.dts @@ -439,7 +439,7 @@ cs-gpios = <&gpiopinctrl 80 0>, <&gpiopinctrl 24 0>, <&gpiopinctrl 85 0>; - m25p80@0 { + flash@0 { compatible = "m25p80"; reg = <0>; spi-max-frequency = <12000000>; diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index 33ae5e0590df..ac53ee3c496b 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -398,7 +398,7 @@ #size-cells = <0>; status = "okay"; - flash0: is25lp016d@0 { + flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <133000000>; diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts index e222d2d2cb44..d142dd30e16b 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts @@ -262,7 +262,7 @@ #size-cells = <0>; status = "okay"; - flash0: mx66l51235l@0 { + flash0: flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-rx-bus-width = <4>; @@ -271,7 +271,7 @@ #size-cells = <1>; }; - flash1: mx66l51235l@1 { + flash1: flash@1 { compatible = "jedec,spi-nor"; reg = <1>; spi-rx-bus-width = <4>; diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts index 8a0cfbfd0c45..b6cb9cdf8197 100644 --- a/arch/arm/boot/dts/usb_a9263.dts +++ b/arch/arm/boot/dts/usb_a9263.dts @@ -60,7 +60,7 @@ spi0: spi@fffa4000 { cs-gpios = <&pioB 15 GPIO_ACTIVE_HIGH>; status = "okay"; - mtd_dataflash@0 { + flash@0 { compatible = "atmel,at45", "atmel,dataflash"; reg = <0>; spi-max-frequency = <15000000>; diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig index a7acfee11ffc..a80bc8a43091 100644 --- a/arch/arm/configs/gemini_defconfig +++ b/arch/arm/configs/gemini_defconfig @@ -49,11 +49,13 @@ CONFIG_ATA=y CONFIG_PATA_FTIDE010=y CONFIG_NETDEVICES=y CONFIG_TUN=y +CONFIG_NET_DSA_REALTEK=y CONFIG_NET_DSA_REALTEK_SMI=y +CONFIG_NET_DSA_REALTEK_RTL8366RB=y CONFIG_GEMINI_ETHERNET=y +CONFIG_MARVELL_PHY=y CONFIG_MDIO_BITBANG=y CONFIG_MDIO_GPIO=y -CONFIG_MARVELL_PHY=y CONFIG_INPUT_EVDEV=y CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set @@ -66,6 +68,7 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_I2C_GPIO=y CONFIG_SPI=y CONFIG_SPI_GPIO=y +CONFIG_SENSORS_DRIVETEMP=y CONFIG_SENSORS_GPIO_FAN=y CONFIG_SENSORS_LM75=y CONFIG_THERMAL=y diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig deleted file mode 100644 index 015b7ef237de..000000000000 --- a/arch/arm/configs/imote2_defconfig +++ /dev/null @@ -1,365 +0,0 @@ -# CONFIG_LOCALVERSION_AUTO is not set -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_SYSFS_DEPRECATED_V2=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_RD_BZIP2=y -CONFIG_RD_LZMA=y -CONFIG_EXPERT=y -# CONFIG_COMPAT_BRK is not set -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_MODVERSIONS=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_ARCH_PXA=y -CONFIG_MACH_INTELMOTE2=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT=y -CONFIG_AEABI=y -CONFIG_ZBOOT_ROM_TEXT=0x0 -CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="root=/dev/mtdblock2 rootfstype=jffs2 console=ttyS2,115200 mem=32M" -CONFIG_KEXEC=y -CONFIG_FPE_NWFPE=y -CONFIG_BINFMT_AOUT=m -CONFIG_BINFMT_MISC=m -CONFIG_PM=y -CONFIG_APM_EMULATION=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_IP_PNP_RARP=y -CONFIG_SYN_COOKIES=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_DIAG is not set -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_IPV6_MIP6=m -CONFIG_IPV6_TUNNEL=m -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_SUBTREES=y -CONFIG_NETFILTER=y -CONFIG_NETFILTER_NETLINK_QUEUE=m -CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_SCTP=y -CONFIG_NF_CT_PROTO_UDPLITE=y -CONFIG_NF_CONNTRACK_AMANDA=m -CONFIG_NF_CONNTRACK_FTP=m -CONFIG_NF_CONNTRACK_H323=m -CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_NETBIOS_NS=m -CONFIG_NF_CONNTRACK_PPTP=m -CONFIG_NF_CONNTRACK_SANE=m -CONFIG_NF_CONNTRACK_SIP=m -CONFIG_NF_CONNTRACK_TFTP=m -CONFIG_NF_CT_NETLINK=m -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m -CONFIG_NETFILTER_XT_TARGET_LED=m -CONFIG_NETFILTER_XT_TARGET_MARK=m -CONFIG_NETFILTER_XT_TARGET_NFLOG=m -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_COMMENT=m -CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m -CONFIG_NETFILTER_XT_MATCH_CONNMARK=m -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -CONFIG_NETFILTER_XT_MATCH_DCCP=m -CONFIG_NETFILTER_XT_MATCH_DSCP=m -CONFIG_NETFILTER_XT_MATCH_ESP=m -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m -CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_LENGTH=m -CONFIG_NETFILTER_XT_MATCH_LIMIT=m -CONFIG_NETFILTER_XT_MATCH_MAC=m -CONFIG_NETFILTER_XT_MATCH_MARK=m -CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -CONFIG_NETFILTER_XT_MATCH_POLICY=m -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m -CONFIG_NETFILTER_XT_MATCH_QUOTA=m -CONFIG_NETFILTER_XT_MATCH_REALM=m -CONFIG_NETFILTER_XT_MATCH_SCTP=m -CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NETFILTER_XT_MATCH_STATISTIC=m -CONFIG_NETFILTER_XT_MATCH_STRING=m -CONFIG_NETFILTER_XT_MATCH_TCPMSS=m -CONFIG_NETFILTER_XT_MATCH_TIME=m -CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_ADDRTYPE=m -CONFIG_IP_NF_MATCH_AH=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_LOG=m -CONFIG_NF_NAT=m -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_TARGET_NETMAP=m -CONFIG_IP_NF_TARGET_REDIRECT=m -CONFIG_NF_NAT_SNMP_BASIC=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_TTL=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_AH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_MH=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_TARGET_HL=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_REJECT=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_RAW=m -CONFIG_BRIDGE=m -# CONFIG_BRIDGE_IGMP_SNOOPING is not set -CONFIG_IEEE802154=y -# CONFIG_WIRELESS is not set -CONFIG_DEVTMPFS=y -CONFIG_DEVTMPFS_MOUNT=y -CONFIG_FW_LOADER=m -CONFIG_CONNECTOR=m -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_AFS_PARTS=y -CONFIG_MTD_AR7_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_ADV_OPTIONS=y -CONFIG_MTD_CFI_GEOMETRY=y -# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_4 is not set -# CONFIG_MTD_CFI_I2 is not set -CONFIG_MTD_OTP=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PXA2XX=y -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_NETDEVICES=y -CONFIG_DUMMY=y -# CONFIG_WLAN is not set -CONFIG_PPP=m -CONFIG_PPP_MULTILINK=y -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPP_BSDCOMP=m -# CONFIG_INPUT_MOUSEDEV is not set -CONFIG_INPUT_EVDEV=y -# CONFIG_KEYBOARD_ATKBD is not set -CONFIG_KEYBOARD_GPIO=y -CONFIG_KEYBOARD_PXA27x=y -# CONFIG_INPUT_MOUSE is not set -CONFIG_INPUT_TOUCHSCREEN=y -CONFIG_INPUT_MISC=y -CONFIG_INPUT_UINPUT=y -# CONFIG_SERIO is not set -CONFIG_SERIAL_PXA=y -CONFIG_SERIAL_PXA_CONSOLE=y -CONFIG_LEGACY_PTY_COUNT=8 -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_PXA=y -CONFIG_SPI=y -CONFIG_SPI_PXA2XX=y -CONFIG_GPIO_SYSFS=y -CONFIG_POWER_SUPPLY=y -# CONFIG_HWMON is not set -CONFIG_PMIC_DA903X=y -CONFIG_REGULATOR=y -CONFIG_REGULATOR_DEBUG=y -CONFIG_REGULATOR_DA903X=y -CONFIG_MEDIA_SUPPORT=y -CONFIG_VIDEO_DEV=y -CONFIG_MEDIA_TUNER_CUSTOMISE=y -# CONFIG_MEDIA_TUNER_SIMPLE is not set -# CONFIG_MEDIA_TUNER_TDA8290 is not set -# CONFIG_MEDIA_TUNER_TDA827X is not set -# CONFIG_MEDIA_TUNER_TDA18271 is not set -# CONFIG_MEDIA_TUNER_TDA9887 is not set -# CONFIG_MEDIA_TUNER_TEA5761 is not set -# CONFIG_MEDIA_TUNER_TEA5767 is not set -# CONFIG_MEDIA_TUNER_MT20XX is not set -# CONFIG_MEDIA_TUNER_MT2060 is not set -# CONFIG_MEDIA_TUNER_MT2266 is not set -# CONFIG_MEDIA_TUNER_MT2131 is not set -# CONFIG_MEDIA_TUNER_QT1010 is not set -# CONFIG_MEDIA_TUNER_XC2028 is not set -# CONFIG_MEDIA_TUNER_XC5000 is not set -# CONFIG_MEDIA_TUNER_MXL5005S is not set -# CONFIG_MEDIA_TUNER_MXL5007T is not set -# CONFIG_MEDIA_TUNER_MC44S803 is not set -# CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set -CONFIG_VIDEO_PXA27x=y -# CONFIG_V4L_USB_DRIVERS is not set -# CONFIG_RADIO_ADAPTERS is not set -CONFIG_FB=y -CONFIG_FB_PXA=y -CONFIG_FB_PXA_OVERLAY=y -CONFIG_FB_PXA_PARAMETERS=y -# CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_BACKLIGHT_CLASS_DEVICE=y -# CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_FONTS=y -CONFIG_FONT_MINI_4x6=y -CONFIG_SOUND=y -CONFIG_SND=y -CONFIG_SND_MIXER_OSS=y -CONFIG_SND_PCM_OSS=y -# CONFIG_SND_DRIVERS is not set -# CONFIG_SND_ARM is not set -# CONFIG_SND_SPI is not set -# CONFIG_SND_USB is not set -CONFIG_SND_SOC=y -CONFIG_SND_PXA2XX_SOC=y -# CONFIG_USB_HID is not set -CONFIG_USB=y -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_GADGET=y -CONFIG_USB_PXA27X=y -CONFIG_USB_ETH=m -# CONFIG_USB_ETH_RNDIS is not set -CONFIG_MMC=y -CONFIG_SDIO_UART=m -CONFIG_MMC_PXA=y -CONFIG_MMC_SPI=y -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=y -CONFIG_LEDS_LP3944=y -CONFIG_LEDS_TRIGGERS=y -CONFIG_LEDS_TRIGGER_TIMER=y -CONFIG_LEDS_TRIGGER_HEARTBEAT=y -CONFIG_LEDS_TRIGGER_BACKLIGHT=y -CONFIG_LEDS_TRIGGER_GPIO=y -CONFIG_LEDS_TRIGGER_DEFAULT_ON=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_PXA=y -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=m -CONFIG_AUTOFS4_FS=y -CONFIG_FUSE_FS=m -CONFIG_CUSE=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y -CONFIG_JFFS2_FS_WBUF_VERIFY=y -CONFIG_JFFS2_SUMMARY=y -CONFIG_JFFS2_FS_XATTR=y -CONFIG_JFFS2_COMPRESSION_OPTIONS=y -CONFIG_JFFS2_LZO=y -CONFIG_JFFS2_RUBIN=y -CONFIG_CRAMFS=m -CONFIG_SQUASHFS=m -CONFIG_ROMFS_FS=m -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V3_ACL=y -CONFIG_NFSD=m -CONFIG_NFSD_V3_ACL=y -CONFIG_SMB_FS=m -CONFIG_CIFS=m -CONFIG_CIFS_STATS=y -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m -CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y -# CONFIG_SCHED_DEBUG is not set -CONFIG_DEBUG_RT_MUTEXES=y -CONFIG_PROVE_LOCKING=y -# CONFIG_FTRACE is not set -CONFIG_DEBUG_USER=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_XTS=m -CONFIG_CRYPTO_XCBC=m -CONFIG_CRYPTO_VMAC=m -CONFIG_CRYPTO_GHASH=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_AES=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_FCRYPT=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SEED=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set -CONFIG_CRC16=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 6e0c8c19b35c..d6a6811f0539 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -673,6 +673,7 @@ CONFIG_VIDEO_STI_DELTA=m CONFIG_VIDEO_RENESAS_FDP1=m CONFIG_VIDEO_RENESAS_JPU=m CONFIG_VIDEO_RENESAS_VSP1=m +CONFIG_VIDEO_TEGRA_VDE=m CONFIG_V4L_TEST_DRIVERS=y CONFIG_VIDEO_VIVID=m CONFIG_VIDEO_ADV7180=m diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig index 289d022acc4b..c209722399d7 100644 --- a/arch/arm/configs/tegra_defconfig +++ b/arch/arm/configs/tegra_defconfig @@ -286,7 +286,8 @@ CONFIG_SERIO_NVEC_PS2=y CONFIG_NVEC_POWER=y CONFIG_NVEC_PAZ00=y CONFIG_STAGING_MEDIA=y -CONFIG_TEGRA_VDE=y +CONFIG_V4L_MEM2MEM_DRIVERS=y +CONFIG_VIDEO_TEGRA_VDE=y CONFIG_CHROME_PLATFORMS=y CONFIG_CROS_EC=y CONFIG_CROS_EC_I2C=m diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index 3b30913d7d8d..a352207a64d7 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -20,7 +20,6 @@ CONFIG_VFP=y CONFIG_NEON=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set CONFIG_PARTITION_ADVANCED=y CONFIG_CMA=y CONFIG_NET=y @@ -41,6 +40,8 @@ CONFIG_MAC80211_LEDS=y CONFIG_CAIF=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y +CONFIG_GNSS=y +CONFIG_GNSS_SIRF_SERIAL=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_NETDEVICES=y @@ -83,6 +84,8 @@ CONFIG_SPI_GPIO=y CONFIG_SPI_PL022=y CONFIG_GPIO_STMPE=y CONFIG_GPIO_TC3589X=y +CONFIG_BATTERY_SAMSUNG_SDI=y +CONFIG_AB8500_BM=y CONFIG_SENSORS_IIO_HWMON=y CONFIG_SENSORS_NTC_THERMISTOR=y CONFIG_THERMAL=y @@ -98,10 +101,13 @@ CONFIG_VIDEO_V4L2_SUBDEV_API=y CONFIG_V4L2_FLASH_LED_CLASS=y CONFIG_DRM=y CONFIG_DRM_PANEL_NOVATEK_NT35510=y +CONFIG_DRM_PANEL_NOVATEK_NT35560=y +CONFIG_DRM_PANEL_SAMSUNG_DB7430=y CONFIG_DRM_PANEL_SAMSUNG_S6D16D0=y +CONFIG_DRM_PANEL_SAMSUNG_S6D27A1=y CONFIG_DRM_PANEL_SAMSUNG_S6E63M0=y CONFIG_DRM_PANEL_SAMSUNG_S6E63M0_DSI=y -CONFIG_DRM_PANEL_SONY_ACX424AKP=y +CONFIG_DRM_PANEL_WIDECHIPS_WS2401=y CONFIG_DRM_LIMA=y CONFIG_DRM_MCDE=y CONFIG_FB=y @@ -129,6 +135,7 @@ CONFIG_LEDS_LM3530=y CONFIG_LEDS_GPIO=y CONFIG_LEDS_LP55XX_COMMON=y CONFIG_LEDS_LP5521=y +CONFIG_LEDS_REGULATOR=y CONFIG_LEDS_RT8515=y CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_RTC_CLASS=y @@ -144,17 +151,22 @@ CONFIG_IIO_SW_TRIGGER=y CONFIG_BMA180=y CONFIG_BMC150_ACCEL=y CONFIG_IIO_ST_ACCEL_3AXIS=y +# CONFIG_IIO_ST_ACCEL_SPI_3AXIS is not set CONFIG_IIO_RESCALE=y CONFIG_MPU3050_I2C=y CONFIG_IIO_ST_GYRO_3AXIS=y +# CONFIG_IIO_ST_GYRO_SPI_3AXIS is not set CONFIG_INV_MPU6050_I2C=y CONFIG_BH1780=y CONFIG_GP2AP002=y +CONFIG_TSL2772=y CONFIG_AK8974=y CONFIG_IIO_ST_MAGN_3AXIS=y +# CONFIG_IIO_ST_MAGN_SPI_3AXIS is not set CONFIG_YAMAHA_YAS530=y CONFIG_IIO_HRTIMER_TRIGGER=y CONFIG_IIO_ST_PRESS=y +# CONFIG_IIO_ST_PRESS_SPI is not set CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -173,10 +185,9 @@ CONFIG_CRYPTO_DEV_UX500_CRYP=y CONFIG_CRYPTO_DEV_UX500_HASH=y CONFIG_CRYPTO_DEV_UX500_DEBUG=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y # CONFIG_SCHED_DEBUG is not set # CONFIG_FTRACE is not set CONFIG_DEBUG_USER=y diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index 428012687a80..7f7f6bae21c2 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -1101,11 +1101,13 @@ static int __init da850_evm_config_emac(void) int ret; u32 val; struct davinci_soc_info *soc_info = &davinci_soc_info; - u8 rmii_en = soc_info->emac_pdata->rmii_en; + u8 rmii_en; if (!machine_is_davinci_da850_evm()) return 0; + rmii_en = soc_info->emac_pdata->rmii_en; + cfg_chip3_base = DA8XX_SYSCFG0_VIRT(DA8XX_CFGCHIP3_REG); val = __raw_readl(cfg_chip3_base); diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index cc75087134d3..4fa6ea5461b7 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -148,8 +148,10 @@ static struct clk_hw *ep93xx_clk_register_gate(const char *name, psc->lock = &clk_lock; clk = clk_register(NULL, &psc->hw); - if (IS_ERR(clk)) + if (IS_ERR(clk)) { kfree(psc); + return ERR_CAST(clk); + } return &psc->hw; } @@ -207,7 +209,7 @@ static int ep93xx_mux_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { unsigned long rate = req->rate; - struct clk *best_parent = 0; + struct clk *best_parent = NULL; unsigned long __parent_rate; unsigned long best_rate = 0, actual_rate, mclk_rate; unsigned long best_parent_rate; diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index f7d993628cb7..a9c1efcf7c9c 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -17,7 +17,6 @@ menuconfig ARCH_EXYNOS select EXYNOS_PMU select EXYNOS_SROM select EXYNOS_PM_DOMAINS if PM_GENERIC_DOMAINS - select GPIOLIB select HAVE_ARM_ARCH_TIMER if ARCH_EXYNOS5 select HAVE_ARM_SCU if SMP select PINCTRL diff --git a/arch/arm/mach-iop32x/cp6.c b/arch/arm/mach-iop32x/cp6.c index 2882674a1c39..7135a0ac9949 100644 --- a/arch/arm/mach-iop32x/cp6.c +++ b/arch/arm/mach-iop32x/cp6.c @@ -7,6 +7,8 @@ #include <asm/traps.h> #include <asm/ptrace.h> +#include "iop3xx.h" + void iop_enable_cp6(void) { u32 temp; diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c index 5c3845730dbf..0b80f8bcd304 100644 --- a/arch/arm/mach-omap2/omap4-common.c +++ b/arch/arm/mach-omap2/omap4-common.c @@ -314,10 +314,12 @@ void __init omap_gic_of_init(void) np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-gic"); gic_dist_base_addr = of_iomap(np, 0); + of_node_put(np); WARN_ON(!gic_dist_base_addr); np = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-twd-timer"); twd_base = of_iomap(np, 0); + of_node_put(np); WARN_ON(!twd_base); skip_errata_init: diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 1da11bdb1dfb..6e6985e756af 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -122,13 +122,13 @@ static inline bool cluster_is_a15(u32 cluster) } /** - * ve_spc_global_wakeup_irq() + * ve_spc_global_wakeup_irq() - sets/clears global wakeup IRQs + * + * @set: if true, global wake-up IRQs are set, if false they are cleared * * Function to set/clear global wakeup IRQs. Not protected by locking since * it might be used in code paths where normal cacheable locks are not * working. Locking must be provided by the caller to ensure atomicity. - * - * @set: if true, global wake-up IRQs are set, if false they are cleared */ void ve_spc_global_wakeup_irq(bool set) { @@ -145,15 +145,15 @@ void ve_spc_global_wakeup_irq(bool set) } /** - * ve_spc_cpu_wakeup_irq() - * - * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since - * it might be used in code paths where normal cacheable locks are not - * working. Locking must be provided by the caller to ensure atomicity. + * ve_spc_cpu_wakeup_irq() - sets/clears per-CPU wake-up IRQs * * @cluster: mpidr[15:8] bitfield describing cluster affinity level * @cpu: mpidr[7:0] bitfield describing cpu affinity level * @set: if true, wake-up IRQs are set, if false they are cleared + * + * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since + * it might be used in code paths where normal cacheable locks are not + * working. Locking must be provided by the caller to ensure atomicity. */ void ve_spc_cpu_wakeup_irq(u32 cluster, u32 cpu, bool set) { @@ -200,14 +200,14 @@ void ve_spc_set_resume_addr(u32 cluster, u32 cpu, u32 addr) } /** - * ve_spc_powerdown() + * ve_spc_powerdown() - enables/disables cluster powerdown + * + * @cluster: mpidr[15:8] bitfield describing cluster affinity level + * @enable: if true enables powerdown, if false disables it * * Function to enable/disable cluster powerdown. Not protected by locking * since it might be used in code paths where normal cacheable locks are not * working. Locking must be provided by the caller to ensure atomicity. - * - * @cluster: mpidr[15:8] bitfield describing cluster affinity level - * @enable: if true enables powerdown, if false disables it */ void ve_spc_powerdown(u32 cluster, bool enable) { @@ -228,7 +228,7 @@ static u32 standbywfi_cpu_mask(u32 cpu, u32 cluster) } /** - * ve_spc_cpu_in_wfi(u32 cpu, u32 cluster) + * ve_spc_cpu_in_wfi() - Checks if the specified CPU is in WFI or not * * @cpu: mpidr[7:0] bitfield describing CPU affinity level within cluster * @cluster: mpidr[15:8] bitfield describing cluster affinity level @@ -580,7 +580,7 @@ static int __init ve_spc_clk_init(void) } cluster = topology_physical_package_id(cpu_dev->id); - if (init_opp_table[cluster]) + if (cluster < 0 || init_opp_table[cluster]) continue; if (ve_init_opp_table(cpu_dev)) diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index ec5b082f3de6..07eb69f9e7df 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -337,12 +337,15 @@ int __init arch_xen_unpopulated_init(struct resource **res) if (!nr_reg) { pr_err("No extended regions are found\n"); + of_node_put(np); return -EINVAL; } regs = kcalloc(nr_reg, sizeof(*regs), GFP_KERNEL); - if (!regs) + if (!regs) { + of_node_put(np); return -ENOMEM; + } /* * Create resource from extended regions provided by the hypervisor to be @@ -403,8 +406,8 @@ int __init arch_xen_unpopulated_init(struct resource **res) *res = &xen_resource; err: + of_node_put(np); kfree(regs); - return rc; } #endif @@ -424,8 +427,10 @@ static void __init xen_dt_guest_init(void) if (of_address_to_resource(xen_node, GRANT_TABLE_INDEX, &res)) { pr_err("Xen grant table region is not found\n"); + of_node_put(xen_node); return; } + of_node_put(xen_node); xen_grant_frames = res.start; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 57c4c995965f..0dbae092c9b9 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -175,8 +175,6 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_REGS \ - if $(cc-option,-fpatchable-function-entry=2) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_REGS select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -228,6 +226,17 @@ config ARM64 help ARM 64-bit (AArch64) Linux support. +config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS + def_bool CC_IS_CLANG + # https://github.com/ClangBuiltLinux/linux/issues/1507 + depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) + select HAVE_DYNAMIC_FTRACE_WITH_REGS + +config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS + def_bool CC_IS_GCC + depends on $(cc-option,-fpatchable-function-entry=2) + select HAVE_DYNAMIC_FTRACE_WITH_REGS + config 64BIT def_bool y @@ -678,7 +687,7 @@ config ARM64_ERRATUM_2051678 default y help This options adds the workaround for ARM Cortex-A510 erratum ARM64_ERRATUM_2051678. - Affected Coretex-A510 might not respect the ordering rules for + Affected Cortex-A510 might not respect the ordering rules for hardware update of the page table's dirty bit. The workaround is to not enable the feature on affected CPUs. @@ -1939,6 +1948,17 @@ config ARM64_SVE booting the kernel. If unsure and you are not observing these symptoms, you should assume that it is safe to say Y. +config ARM64_SME + bool "ARM Scalable Matrix Extension support" + default y + depends on ARM64_SVE + help + The Scalable Matrix Extension (SME) is an extension to the AArch64 + execution state which utilises a substantial subset of the SVE + instruction set, together with the addition of new architectural + register state capable of holding two dimensional matrix tiles to + enable various matrix operations. + config ARM64_MODULE_PLTS bool "Use PLTs to allow module memory to spill over into vmalloc area" depends on MODULES diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi index d61f43052a34..8e9ad1e51d66 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-a311d.dtsi @@ -11,26 +11,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <761000>; @@ -71,26 +51,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi index 1e5d0ee5d541..44c23c984034 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-s922x.dtsi @@ -11,26 +11,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <731000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <731000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <731000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <731000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <731000>; @@ -76,26 +56,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <751000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <751000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <751000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <667000000>; - opp-microvolt = <751000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <771000>; diff --git a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi index bf9ae1e1016b..480afa2cc61f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-s4.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-s4.dtsi @@ -13,28 +13,28 @@ cpu0: cpu@0 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x0>; enable-method = "psci"; }; cpu1: cpu@1 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x1>; enable-method = "psci"; }; cpu2: cpu@2 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x2>; enable-method = "psci"; }; cpu3: cpu@3 { device_type = "cpu"; - compatible = "arm,cortex-a35","arm,armv8"; + compatible = "arm,cortex-a35"; reg = <0x0 0x3>; enable-method = "psci"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts index 5751c48620ed..cadba194b149 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-bananapi-m5.dts @@ -437,6 +437,7 @@ "", "eMMC_RST#", /* BOOT_12 */ "eMMC_DS", /* BOOT_13 */ + "", "", /* GPIOC */ "SD_D0_B", /* GPIOC_0 */ "SD_D1_B", /* GPIOC_1 */ diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi index 3c07a89bfd27..80737731af3f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi @@ -95,26 +95,6 @@ compatible = "operating-points-v2"; opp-shared; - opp-100000000 { - opp-hz = /bits/ 64 <100000000>; - opp-microvolt = <730000>; - }; - - opp-250000000 { - opp-hz = /bits/ 64 <250000000>; - opp-microvolt = <730000>; - }; - - opp-500000000 { - opp-hz = /bits/ 64 <500000000>; - opp-microvolt = <730000>; - }; - - opp-667000000 { - opp-hz = /bits/ 64 <666666666>; - opp-microvolt = <750000>; - }; - opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; opp-microvolt = <770000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi index 1dc9d187601c..a0bd540f27d3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-var-som.dtsi @@ -89,12 +89,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi index 73addc0b8e57..cce55c3c5df0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw71xx.dtsi @@ -146,12 +146,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; status = "okay"; }; @@ -215,7 +217,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi index 1e7badb2a82e..f61e4847fa49 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx.dtsi @@ -211,12 +211,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; vbus-supply = <®_usb_otg2_vbus>; status = "okay"; }; @@ -309,7 +311,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi index 426483ec1f88..023619648966 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi @@ -238,12 +238,14 @@ &usbotg1 { dr_mode = "otg"; + over-current-active-low; vbus-supply = <®_usb_otg1_vbus>; status = "okay"; }; &usbotg2 { dr_mode = "host"; + disable-over-current; vbus-supply = <®_usb_otg2_vbus>; status = "okay"; }; @@ -358,7 +360,7 @@ fsl,pins = < MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0xd6 - MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0xd6 + MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0xd6 MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0xd6 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index 7dfee715a2c4..d8ce217c6016 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -59,6 +59,10 @@ interrupts = <3 IRQ_TYPE_LEVEL_LOW>; rohm,reset-snvs-powered; + #clock-cells = <0>; + clocks = <&osc_32k 0>; + clock-output-names = "clk-32k-out"; + regulators { buck1_reg: BUCK1 { regulator-name = "buck1"; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index b16c7caf34c1..87b5e23c766f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -70,12 +70,12 @@ pendown-gpio = <&gpio1 3 GPIO_ACTIVE_LOW>; ti,x-min = /bits/ 16 <125>; - touchscreen-size-x = /bits/ 16 <4008>; + touchscreen-size-x = <4008>; ti,y-min = /bits/ 16 <282>; - touchscreen-size-y = /bits/ 16 <3864>; + touchscreen-size-y = <3864>; ti,x-plate-ohms = /bits/ 16 <180>; - touchscreen-max-pressure = /bits/ 16 <255>; - touchscreen-average-samples = /bits/ 16 <10>; + touchscreen-max-pressure = <255>; + touchscreen-average-samples = <10>; ti,debounce-tol = /bits/ 16 <3>; ti,debounce-rep = /bits/ 16 <1>; ti,settle-delay-usec = /bits/ 16 <150>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 99f0f5026674..5c0ca2490561 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -293,7 +293,7 @@ ranges; sai2: sai@30020000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30020000 0x10000>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI2_IPG>, @@ -307,7 +307,7 @@ }; sai3: sai@30030000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30030000 0x10000>; interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI3_IPG>, @@ -321,7 +321,7 @@ }; sai5: sai@30050000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30050000 0x10000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI5_IPG>, @@ -337,7 +337,7 @@ }; sai6: sai@30060000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x30060000 0x10000>; interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI6_IPG>, @@ -394,7 +394,7 @@ }; sai7: sai@300b0000 { - compatible = "fsl,imx8mm-sai", "fsl,imx8mq-sai"; + compatible = "fsl,imx8mn-sai", "fsl,imx8mq-sai"; reg = <0x300b0000 0x10000>; interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SAI7_IPG>, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi index 38ffcd145b33..899e8e7dbc24 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi @@ -253,7 +253,7 @@ #address-cells = <1>; #size-cells = <1>; spi-max-frequency = <84000000>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm.dtsi b/arch/arm64/boot/dts/freescale/imx8qm.dtsi index be8c76a0554c..4f767012f1f5 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm.dtsi @@ -196,7 +196,7 @@ }; clk: clock-controller { - compatible = "fsl,imx8qxp-clk", "fsl,scu-clk"; + compatible = "fsl,imx8qm-clk", "fsl,scu-clk"; #clock-cells = <2>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index f0f81c23c16f..b9a48cfd760f 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -1249,14 +1249,14 @@ pins = "gpio47", "gpio48"; function = "blsp_i2c3"; drive-strength = <16>; - bias-disable = <0>; + bias-disable; }; blsp1_i2c3_sleep: blsp1-i2c2-sleep { pins = "gpio47", "gpio48"; function = "gpio"; drive-strength = <2>; - bias-disable = <0>; + bias-disable; }; blsp2_uart3_4pins_default: blsp2-uart2-4pins { diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi index e90f99ef5323..e47c74e513af 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-pompom.dtsi @@ -33,7 +33,7 @@ ap_h1_spi: &spi0 {}; }; &alc5682 { - realtek,dmic-clk-driving-high = "true"; + realtek,dmic-clk-driving-high; }; &cpu6_alert0 { diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index 1084d5ce9ac7..07b729f9fec5 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -630,7 +630,7 @@ pins = "gpio6", "gpio25", "gpio26"; function = "gpio"; drive-strength = <8>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts index 8553c8bf79bd..103cc40816fd 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts @@ -563,7 +563,7 @@ config { pins = "gpio6", "gpio11"; drive-strength = <8>; - bias-disable = <0>; + bias-disable; }; }; diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 62217be36217..9f3e2c3d2ca0 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -16,7 +16,11 @@ #define sev() asm volatile("sev" : : : "memory") #define wfe() asm volatile("wfe" : : : "memory") +#define wfet(val) asm volatile("msr s0_3_c1_c0_0, %0" \ + : : "r" (val) : "memory") #define wfi() asm volatile("wfi" : : : "memory") +#define wfit(val) asm volatile("msr s0_3_c1_c0_1, %0" \ + : : "r" (val) : "memory") #define isb() asm volatile("isb" : : : "memory") #define dmb(opt) asm volatile("dmb " #opt : : : "memory") diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index a58e366f0b07..115cdec1ae87 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -58,11 +58,15 @@ struct cpuinfo_arm64 { u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; u64 reg_id_aa64zfr0; + u64 reg_id_aa64smfr0; struct cpuinfo_32bit aarch32; /* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */ u64 reg_zcr; + + /* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */ + u64 reg_smcr; }; DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data); diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index c62e7e5e2f0c..14a8f3d93add 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -622,6 +622,13 @@ static inline bool id_aa64pfr0_sve(u64 pfr0) return val > 0; } +static inline bool id_aa64pfr1_sme(u64 pfr1) +{ + u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_SME_SHIFT); + + return val > 0; +} + static inline bool id_aa64pfr1_mte(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_MTE_SHIFT); @@ -759,6 +766,23 @@ static __always_inline bool system_supports_sve(void) cpus_have_const_cap(ARM64_SVE); } +static __always_inline bool system_supports_sme(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME); +} + +static __always_inline bool system_supports_fa64(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME_FA64); +} + +static __always_inline bool system_supports_tpidr2(void) +{ + return system_supports_sme(); +} + static __always_inline bool system_supports_cnp(void) { return IS_ENABLED(CONFIG_ARM64_CNP) && diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 232b439cbaf3..60647bdc0b09 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -117,6 +118,10 @@ #define APPLE_CPU_PART_M1_ICESTORM 0x022 #define APPLE_CPU_PART_M1_FIRESTORM 0x023 +#define APPLE_CPU_PART_M1_ICESTORM_PRO 0x024 +#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025 +#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 +#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) @@ -130,6 +135,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) @@ -162,6 +168,10 @@ #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM) #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM) +#define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO) +#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) +#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) +#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 7f3c87f7a0ce..fabdbde0fe02 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -107,7 +107,7 @@ isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm @@ -143,6 +143,50 @@ .Lskip_sve_\@: .endm +/* SME register access and priority mapping */ +.macro __init_el2_nvhe_sme + mrs x1, id_aa64pfr1_el1 + ubfx x1, x1, #ID_AA64PFR1_SME_SHIFT, #4 + cbz x1, .Lskip_sme_\@ + + bic x0, x0, #CPTR_EL2_TSM // Also disable SME traps + msr cptr_el2, x0 // Disable copro. traps to EL2 + isb + + mrs x1, sctlr_el2 + orr x1, x1, #SCTLR_ELx_ENTP2 // Disable TPIDR2 traps + msr sctlr_el2, x1 + isb + + mov x1, #0 // SMCR controls + + mrs_s x2, SYS_ID_AA64SMFR0_EL1 + ubfx x2, x2, #ID_AA64SMFR0_FA64_SHIFT, #1 // Full FP in SM? + cbz x2, .Lskip_sme_fa64_\@ + + orr x1, x1, SMCR_ELx_FA64_MASK +.Lskip_sme_fa64_\@: + + orr x1, x1, #SMCR_ELx_LEN_MASK // Enable full SME vector + msr_s SYS_SMCR_EL2, x1 // length for EL1. + + mrs_s x1, SYS_SMIDR_EL1 // Priority mapping supported? + ubfx x1, x1, #SYS_SMIDR_EL1_SMPS_SHIFT, #1 + cbz x1, .Lskip_sme_\@ + + msr_s SYS_SMPRIMAP_EL2, xzr // Make all priorities equal + + mrs x1, id_aa64mmfr1_el1 // HCRX_EL2 present? + ubfx x1, x1, #ID_AA64MMFR1_HCX_SHIFT, #4 + cbz x1, .Lskip_sme_\@ + + mrs_s x1, SYS_HCRX_EL2 + orr x1, x1, #HCRX_EL2_SMPME_MASK // Enable priority mapping + msr_s SYS_HCRX_EL2, x1 + +.Lskip_sme_\@: +.endm + /* Disable any fine grained traps */ .macro __init_el2_fgt mrs x1, id_aa64mmfr0_el1 @@ -153,15 +197,26 @@ mrs x1, id_aa64dfr0_el1 ubfx x1, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4 cmp x1, #3 - b.lt .Lset_fgt_\@ + b.lt .Lset_debug_fgt_\@ /* Disable PMSNEVFR_EL1 read and write traps */ orr x0, x0, #(1 << 62) -.Lset_fgt_\@: +.Lset_debug_fgt_\@: msr_s SYS_HDFGRTR_EL2, x0 msr_s SYS_HDFGWTR_EL2, x0 - msr_s SYS_HFGRTR_EL2, xzr - msr_s SYS_HFGWTR_EL2, xzr + + mov x0, xzr + mrs x1, id_aa64pfr1_el1 + ubfx x1, x1, #ID_AA64PFR1_SME_SHIFT, #4 + cbz x1, .Lset_fgt_\@ + + /* Disable nVHE traps of TPIDR2 and SMPRI */ + orr x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK + orr x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK + +.Lset_fgt_\@: + msr_s SYS_HFGRTR_EL2, x0 + msr_s SYS_HFGWTR_EL2, x0 msr_s SYS_HFGITR_EL2, xzr mrs x1, id_aa64pfr0_el1 // AMU traps UNDEF without AMU @@ -196,6 +251,7 @@ __init_el2_nvhe_idregs __init_el2_nvhe_cptr __init_el2_nvhe_sve + __init_el2_nvhe_sme __init_el2_fgt __init_el2_nvhe_prepare_eret .endm diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index d52a0b269ee8..0bc9941b412e 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -37,7 +37,8 @@ #define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ /* Unallocated EC: 0x1B */ #define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */ -/* Unallocated EC: 0x1D - 0x1E */ +#define ESR_ELx_EC_SME (0x1D) +/* Unallocated EC: 0x1E */ #define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ #define ESR_ELx_EC_IABT_LOW (0x20) #define ESR_ELx_EC_IABT_CUR (0x21) @@ -75,6 +76,7 @@ #define ESR_ELx_IL_SHIFT (25) #define ESR_ELx_IL (UL(1) << ESR_ELx_IL_SHIFT) #define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1) +#define ESR_ELx_ISS(esr) ((esr) & ESR_ELx_ISS_MASK) /* ISS field definitions shared by different classes */ #define ESR_ELx_WNR_SHIFT (6) @@ -133,7 +135,10 @@ #define ESR_ELx_CV (UL(1) << 24) #define ESR_ELx_COND_SHIFT (20) #define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT) -#define ESR_ELx_WFx_ISS_TI (UL(1) << 0) +#define ESR_ELx_WFx_ISS_RN (UL(0x1F) << 5) +#define ESR_ELx_WFx_ISS_RV (UL(1) << 2) +#define ESR_ELx_WFx_ISS_TI (UL(3) << 0) +#define ESR_ELx_WFx_ISS_WFxT (UL(2) << 0) #define ESR_ELx_WFx_ISS_WFI (UL(0) << 0) #define ESR_ELx_WFx_ISS_WFE (UL(1) << 0) #define ESR_ELx_xVC_IMM_MASK ((1UL << 16) - 1) @@ -146,7 +151,8 @@ #define DISR_EL1_ESR_MASK (ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC) /* ESR value templates for specific events */ -#define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | ESR_ELx_WFx_ISS_TI) +#define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | \ + (ESR_ELx_WFx_ISS_TI & ~ESR_ELx_WFx_ISS_WFxT)) #define ESR_ELx_WFx_WFI_VAL ((ESR_ELx_EC_WFx << ESR_ELx_EC_SHIFT) | \ ESR_ELx_WFx_ISS_WFI) @@ -327,6 +333,15 @@ #define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ (ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\ ESR_ELx_CP15_32_ISS_DIR_READ) +/* + * ISS values for SME traps + */ + +#define ESR_ELx_SME_ISS_SME_DISABLED 0 +#define ESR_ELx_SME_ISS_ILL 1 +#define ESR_ELx_SME_ISS_SM_DISABLED 2 +#define ESR_ELx_SME_ISS_ZA_DISABLED 3 + #ifndef __ASSEMBLY__ #include <asm/types.h> diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 339477dca551..2add7f33b7c2 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -64,6 +64,7 @@ void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, struct pt_regs *regs); void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs); void do_sve_acc(unsigned int esr, struct pt_regs *regs); +void do_sme_acc(unsigned int esr, struct pt_regs *regs); void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs); void do_sysinstr(unsigned int esr, struct pt_regs *regs); void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index cb24385e3632..5afcd0709aae 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -46,11 +46,23 @@ extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, - void *sve_state, unsigned int sve_vl); + void *sve_state, unsigned int sve_vl, + void *za_state, unsigned int sme_vl, + u64 *svcr); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); +static inline bool thread_sm_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK); +} + +static inline bool thread_za_enabled(struct thread_struct *thread) +{ + return system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_ZA_MASK); +} + /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100 @@ -62,7 +74,14 @@ static inline size_t sve_ffr_offset(int vl) static inline void *sve_pffr(struct thread_struct *thread) { - return (char *)thread->sve_state + sve_ffr_offset(thread_get_sve_vl(thread)); + unsigned int vl; + + if (system_supports_sme() && thread_sm_enabled(thread)) + vl = thread_get_sme_vl(thread); + else + vl = thread_get_sve_vl(thread); + + return (char *)thread->sve_state + sve_ffr_offset(vl); } extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); @@ -71,11 +90,17 @@ extern void sve_load_state(void const *state, u32 const *pfpsr, extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); +extern void sme_set_vq(unsigned long vq_minus_1); +extern void za_save_state(void *state); +extern void za_load_state(void const *state); struct arm64_cpu_capabilities; extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused); extern u64 read_zcr_features(void); +extern u64 read_smcr_features(void); /* * Helpers to translate bit indices in sve_vq_map to VQ values (and @@ -119,6 +144,7 @@ struct vl_info { extern void sve_alloc(struct task_struct *task); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_to_sve(struct task_struct *task); +extern void fpsimd_force_sync_to_sve(struct task_struct *task); extern void sve_sync_to_fpsimd(struct task_struct *task); extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); @@ -171,6 +197,12 @@ static inline void write_vl(enum vec_type type, u64 val) write_sysreg_s(tmp | val, SYS_ZCR_EL1); break; #endif +#ifdef CONFIG_ARM64_SME + case ARM64_VEC_SME: + tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK; + write_sysreg_s(tmp | val, SYS_SMCR_EL1); + break; +#endif default: WARN_ON_ONCE(1); break; @@ -208,6 +240,8 @@ static inline bool sve_vq_available(unsigned int vq) return vq_available(ARM64_VEC_SVE, vq); } +size_t sve_state_size(struct task_struct const *task); + #else /* ! CONFIG_ARM64_SVE */ static inline void sve_alloc(struct task_struct *task) { } @@ -247,8 +281,93 @@ static inline void vec_update_vq_map(enum vec_type t) { } static inline int vec_verify_vq_map(enum vec_type t) { return 0; } static inline void sve_setup(void) { } +static inline size_t sve_state_size(struct task_struct const *task) +{ + return 0; +} + #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static inline void sme_user_disable(void) +{ + sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0); +} + +static inline void sme_user_enable(void) +{ + sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN); +} + +static inline void sme_smstart_sm(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr")); +} + +static inline void sme_smstop_sm(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr")); +} + +static inline void sme_smstop(void) +{ + asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr")); +} + +extern void __init sme_setup(void); + +static inline int sme_max_vl(void) +{ + return vec_max_vl(ARM64_VEC_SME); +} + +static inline int sme_max_virtualisable_vl(void) +{ + return vec_max_virtualisable_vl(ARM64_VEC_SME); +} + +extern void sme_alloc(struct task_struct *task); +extern unsigned int sme_get_vl(void); +extern int sme_set_current_vl(unsigned long arg); +extern int sme_get_current_vl(void); + +/* + * Return how many bytes of memory are required to store the full SME + * specific state (currently just ZA) for task, given task's currently + * configured vector length. + */ +static inline size_t za_state_size(struct task_struct const *task) +{ + unsigned int vl = task_get_sme_vl(task); + + return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); +} + +#else + +static inline void sme_user_disable(void) { BUILD_BUG(); } +static inline void sme_user_enable(void) { BUILD_BUG(); } + +static inline void sme_smstart_sm(void) { } +static inline void sme_smstop_sm(void) { } +static inline void sme_smstop(void) { } + +static inline void sme_alloc(struct task_struct *task) { } +static inline void sme_setup(void) { } +static inline unsigned int sme_get_vl(void) { return 0; } +static inline int sme_max_vl(void) { return 0; } +static inline int sme_max_virtualisable_vl(void) { return 0; } +static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } +static inline int sme_get_current_vl(void) { return -EINVAL; } + +static inline size_t za_state_size(struct task_struct const *task) +{ + return 0; +} + +#endif /* ! CONFIG_ARM64_SME */ + /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index 2509d7dde55a..5e0910cf4832 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -93,6 +93,12 @@ .endif .endm +.macro _sme_check_wv v + .if (\v) < 12 || (\v) > 15 + .error "Bad vector select register \v." + .endif +.endm + /* SVE instruction encodings for non-SVE-capable assemblers */ /* (pre binutils 2.28, all kernel capable clang versions support SVE) */ @@ -174,6 +180,54 @@ | (\np) .endm +/* SME instruction encodings for non-SME-capable assemblers */ +/* (pre binutils 2.38/LLVM 13) */ + +/* RDSVL X\nx, #\imm */ +.macro _sme_rdsvl nx, imm + _check_general_reg \nx + _check_num (\imm), -0x20, 0x1f + .inst 0x04bf5800 \ + | (\nx) \ + | (((\imm) & 0x3f) << 5) +.endm + +/* + * STR (vector from ZA array): + * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_str_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1200000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * LDR (vector to ZA array): + * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL] + */ +.macro _sme_ldr_zav nw, nxbase, offset=0 + _sme_check_wv \nw + _check_general_reg \nxbase + _check_num (\offset), -0x100, 0xff + .inst 0xe1000000 \ + | (((\nw) & 3) << 13) \ + | ((\nxbase) << 5) \ + | ((\offset) & 7) +.endm + +/* + * Zero the entire ZA array + * ZERO ZA + */ +.macro zero_za + .inst 0xc00800ff +.endm + .macro __for from:req, to:req .if (\from) == (\to) _for__body %\from @@ -208,6 +262,17 @@ 921: .endm +/* Update SMCR_EL1.LEN with the new VQ */ +.macro sme_load_vq xvqminus1, xtmp, xtmp2 + mrs_s \xtmp, SYS_SMCR_EL1 + bic \xtmp2, \xtmp, SMCR_ELx_LEN_MASK + orr \xtmp2, \xtmp2, \xvqminus1 + cmp \xtmp2, \xtmp + b.eq 921f + msr_s SYS_SMCR_EL1, \xtmp2 //self-synchronising +921: +.endm + /* Preserve the first 128-bits of Znz and zero the rest. */ .macro _sve_flush_z nz _sve_check_zreg \nz @@ -254,3 +319,25 @@ ldr w\nxtmp, [\xpfpsr, #4] msr fpcr, x\nxtmp .endm + +.macro sme_save_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_str_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm + +.macro sme_load_za nxbase, xvl, nw + mov w\nw, #0 + +423: + _sme_ldr_zav \nw, \nxbase + add x\nxbase, x\nxbase, \xvl + add x\nw, x\nw, #1 + cmp \xvl, x\nw + bne 423b +.endm diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 8db5ec0089db..aa443d8f8cfb 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -109,6 +109,15 @@ #define KERNEL_HWCAP_AFP __khwcap2_feature(AFP) #define KERNEL_HWCAP_RPRES __khwcap2_feature(RPRES) #define KERNEL_HWCAP_MTE3 __khwcap2_feature(MTE3) +#define KERNEL_HWCAP_SME __khwcap2_feature(SME) +#define KERNEL_HWCAP_SME_I16I64 __khwcap2_feature(SME_I16I64) +#define KERNEL_HWCAP_SME_F64F64 __khwcap2_feature(SME_F64F64) +#define KERNEL_HWCAP_SME_I8I32 __khwcap2_feature(SME_I8I32) +#define KERNEL_HWCAP_SME_F16F32 __khwcap2_feature(SME_F16F32) +#define KERNEL_HWCAP_SME_B16F32 __khwcap2_feature(SME_B16F32) +#define KERNEL_HWCAP_SME_F32F32 __khwcap2_feature(SME_F32F32) +#define KERNEL_HWCAP_SME_FA64 __khwcap2_feature(SME_FA64) +#define KERNEL_HWCAP_WFXT __khwcap2_feature(WFXT) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 1767ded83888..8aa8492dafc0 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -80,11 +80,12 @@ * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate * PTW: Take a stage2 fault if a stage1 walk steps in device memory + * TID3: Trap EL1 reads of group 3 ID registers */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_BSU_IS | HCR_FB | HCR_TACR | \ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ - HCR_FMO | HCR_IMO | HCR_PTW ) + HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 ) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA) #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) @@ -279,6 +280,7 @@ #define CPTR_EL2_TCPAC (1U << 31) #define CPTR_EL2_TAM (1 << 30) #define CPTR_EL2_TTA (1 << 20) +#define CPTR_EL2_TSM (1 << 12) #define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) #define CPTR_EL2_TZ (1 << 8) #define CPTR_NVHE_EL2_RES1 0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index d5b0386ef765..2e277f2ed671 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -169,6 +169,7 @@ struct kvm_nvhe_init_params { unsigned long tcr_el2; unsigned long tpidr_el2; unsigned long stack_hyp_va; + unsigned long stack_pa; phys_addr_t pgd_pa; unsigned long hcr_el2; unsigned long vttbr; diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 7496deab025a..07812680fcaf 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -40,6 +40,7 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu); void kvm_inject_vabt(struct kvm_vcpu *vcpu); void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr); +void kvm_inject_size_fault(struct kvm_vcpu *vcpu); void kvm_vcpu_wfi(struct kvm_vcpu *vcpu); @@ -86,13 +87,6 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) if (vcpu_el1_is_32bit(vcpu)) vcpu->arch.hcr_el2 &= ~HCR_RW; - else - /* - * TID3: trap feature register accesses that we virtualise. - * For now this is conditional, since no AArch32 feature regs - * are currently virtualised. - */ - vcpu->arch.hcr_el2 |= HCR_TID3; if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) || vcpu_el1_is_32bit(vcpu)) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 27ebb2929e0c..78e718a1b23d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -46,6 +46,7 @@ #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) #define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) #define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5) +#define KVM_REQ_SUSPEND KVM_ARCH_REQ(6) #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) @@ -101,6 +102,19 @@ struct kvm_s2_mmu { struct kvm_arch_memory_slot { }; +/** + * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests + * + * @std_bmap: Bitmap of standard secure service calls + * @std_hyp_bmap: Bitmap of standard hypervisor service calls + * @vendor_hyp_bmap: Bitmap of vendor specific hypervisor service calls + */ +struct kvm_smccc_features { + unsigned long std_bmap; + unsigned long std_hyp_bmap; + unsigned long vendor_hyp_bmap; +}; + struct kvm_arch { struct kvm_s2_mmu mmu; @@ -133,6 +147,8 @@ struct kvm_arch { */ #define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED 3 #define KVM_ARCH_FLAG_EL1_32BIT 4 + /* PSCI SYSTEM_SUSPEND enabled for the guest */ +#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 5 unsigned long flags; @@ -147,6 +163,9 @@ struct kvm_arch { u8 pfr0_csv2; u8 pfr0_csv3; + + /* Hypercall features firmware registers' descriptor */ + struct kvm_smccc_features smccc_feat; }; struct kvm_vcpu_fault_info { @@ -251,14 +270,8 @@ struct kvm_cpu_context { struct kvm_vcpu *__hyp_running_vcpu; }; -struct kvm_pmu_events { - u32 events_host; - u32 events_guest; -}; - struct kvm_host_data { struct kvm_cpu_context host_ctxt; - struct kvm_pmu_events pmu_events; }; struct kvm_host_psci_config { @@ -292,8 +305,11 @@ struct vcpu_reset_state { struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; + + /* Guest floating point state */ void *sve_state; unsigned int sve_max_vl; + u64 svcr; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; @@ -362,8 +378,8 @@ struct kvm_vcpu_arch { u32 mdscr_el1; } guest_debug_preserved; - /* vcpu power-off state */ - bool power_off; + /* vcpu power state */ + struct kvm_mp_state mp_state; /* Don't run the guest (internal implementation need) */ bool pause; @@ -448,6 +464,8 @@ struct kvm_vcpu_arch { #define KVM_ARM64_DEBUG_STATE_SAVE_TRBE (1 << 13) /* Save TRBE context if active */ #define KVM_ARM64_FP_FOREIGN_FPSTATE (1 << 14) #define KVM_ARM64_ON_UNSUPPORTED_CPU (1 << 15) /* Physical CPU not in supported_cpus */ +#define KVM_ARM64_HOST_SME_ENABLED (1 << 16) /* SME enabled for EL0 */ +#define KVM_ARM64_WFIT (1 << 17) /* WFIT instruction trapped */ #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ @@ -680,10 +698,11 @@ int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); int kvm_handle_cp15_32(struct kvm_vcpu *vcpu); int kvm_handle_cp15_64(struct kvm_vcpu *vcpu); int kvm_handle_sys_reg(struct kvm_vcpu *vcpu); +int kvm_handle_cp10_id(struct kvm_vcpu *vcpu); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); -void kvm_sys_reg_table_init(void); +int kvm_sys_reg_table_init(void); /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); @@ -792,9 +811,6 @@ void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u32 clr); - -void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu); -void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); #else static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u32 clr) {} @@ -826,8 +842,6 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); #define kvm_has_mte(kvm) \ (system_supports_mte() && \ test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags)) -#define kvm_vcpu_has_pmu(vcpu) \ - (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM @@ -838,4 +852,7 @@ void __init kvm_hyp_reserve(void); static inline void kvm_hyp_reserve(void) { } #endif +void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu); +bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu); + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 74735a864eee..b208da3bebec 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -154,6 +154,9 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) int kvm_share_hyp(void *from, void *to); void kvm_unshare_hyp(void *from, void *to); int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot); +int __create_hyp_mappings(unsigned long start, unsigned long size, + unsigned long phys, enum kvm_pgtable_prot prot); +int hyp_alloc_private_va_range(size_t size, unsigned long *haddr); int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, void __iomem **haddr); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 94e147e5456c..dff2b483ea50 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -535,7 +535,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) -#define pmd_leaf(pmd) pmd_sect(pmd) +#define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) @@ -625,7 +625,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) -#define pud_leaf(pud) pud_sect(pud) +#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) static inline void set_pud(pud_t *pudp, pud_t pud) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 73e38d9a540c..1d2ca4870b84 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -118,6 +118,7 @@ struct debug_info { enum vec_type { ARM64_VEC_SVE = 0, + ARM64_VEC_SME, ARM64_VEC_MAX, }; @@ -153,6 +154,7 @@ struct thread_struct { unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ + void *za_state; /* ZA register, if any */ unsigned int vl[ARM64_VEC_MAX]; /* vector length */ unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */ unsigned long fault_address; /* fault info */ @@ -168,6 +170,8 @@ struct thread_struct { u64 mte_ctrl; #endif u64 sctlr_user; + u64 svcr; + u64 tpidr2_el0; }; static inline unsigned int thread_get_vl(struct thread_struct *thread, @@ -181,6 +185,19 @@ static inline unsigned int thread_get_sve_vl(struct thread_struct *thread) return thread_get_vl(thread, ARM64_VEC_SVE); } +static inline unsigned int thread_get_sme_vl(struct thread_struct *thread) +{ + return thread_get_vl(thread, ARM64_VEC_SME); +} + +static inline unsigned int thread_get_cur_vl(struct thread_struct *thread) +{ + if (system_supports_sme() && (thread->svcr & SYS_SVCR_EL0_SM_MASK)) + return thread_get_sme_vl(thread); + else + return thread_get_sve_vl(thread); +} + unsigned int task_get_vl(const struct task_struct *task, enum vec_type type); void task_set_vl(struct task_struct *task, enum vec_type type, unsigned long vl); @@ -194,6 +211,11 @@ static inline unsigned int task_get_sve_vl(const struct task_struct *task) return task_get_vl(task, ARM64_VEC_SVE); } +static inline unsigned int task_get_sme_vl(const struct task_struct *task) +{ + return task_get_vl(task, ARM64_VEC_SME); +} + static inline void task_set_sve_vl(struct task_struct *task, unsigned long vl) { task_set_vl(task, ARM64_VEC_SVE, vl); @@ -354,9 +376,11 @@ extern void __init minsigstksz_setup(void); */ #include <asm/fpsimd.h> -/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */ +/* Userspace interface for PR_S[MV]E_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() +#define SME_SET_VL(arg) sme_set_current_vl(arg) +#define SME_GET_VL() sme_get_current_vl() /* PR_PAC_RESET_KEYS prctl */ #define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index fbf5f8bb9055..bebfdd27296a 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -118,6 +118,10 @@ * System registers, organised loosely by encoding but grouped together * where the architected name contains an index. e.g. ID_MMFR<n>_EL1. */ +#define SYS_SVCR_SMSTOP_SM_EL0 sys_reg(0, 3, 4, 2, 3) +#define SYS_SVCR_SMSTART_SM_EL0 sys_reg(0, 3, 4, 3, 3) +#define SYS_SVCR_SMSTOP_SMZA_EL0 sys_reg(0, 3, 4, 6, 3) + #define SYS_OSDTRRX_EL1 sys_reg(2, 0, 0, 0, 2) #define SYS_MDCCINT_EL1 sys_reg(2, 0, 0, 2, 0) #define SYS_MDSCR_EL1 sys_reg(2, 0, 0, 2, 2) @@ -181,6 +185,7 @@ #define SYS_ID_AA64PFR0_EL1 sys_reg(3, 0, 0, 4, 0) #define SYS_ID_AA64PFR1_EL1 sys_reg(3, 0, 0, 4, 1) #define SYS_ID_AA64ZFR0_EL1 sys_reg(3, 0, 0, 4, 4) +#define SYS_ID_AA64SMFR0_EL1 sys_reg(3, 0, 0, 4, 5) #define SYS_ID_AA64DFR0_EL1 sys_reg(3, 0, 0, 5, 0) #define SYS_ID_AA64DFR1_EL1 sys_reg(3, 0, 0, 5, 1) @@ -204,6 +209,8 @@ #define SYS_ZCR_EL1 sys_reg(3, 0, 1, 2, 0) #define SYS_TRFCR_EL1 sys_reg(3, 0, 1, 2, 1) +#define SYS_SMPRI_EL1 sys_reg(3, 0, 1, 2, 4) +#define SYS_SMCR_EL1 sys_reg(3, 0, 1, 2, 6) #define SYS_TTBR0_EL1 sys_reg(3, 0, 2, 0, 0) #define SYS_TTBR1_EL1 sys_reg(3, 0, 2, 0, 1) @@ -396,6 +403,8 @@ #define TRBIDR_ALIGN_MASK GENMASK(3, 0) #define TRBIDR_ALIGN_SHIFT 0 +#define SMPRI_EL1_PRIORITY_MASK 0xf + #define SYS_PMINTENSET_EL1 sys_reg(3, 0, 9, 14, 1) #define SYS_PMINTENCLR_EL1 sys_reg(3, 0, 9, 14, 2) @@ -451,8 +460,13 @@ #define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) #define SYS_CLIDR_EL1 sys_reg(3, 1, 0, 0, 1) #define SYS_GMID_EL1 sys_reg(3, 1, 0, 0, 4) +#define SYS_SMIDR_EL1 sys_reg(3, 1, 0, 0, 6) #define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7) +#define SYS_SMIDR_EL1_IMPLEMENTER_SHIFT 24 +#define SYS_SMIDR_EL1_SMPS_SHIFT 15 +#define SYS_SMIDR_EL1_AFFINITY_SHIFT 0 + #define SYS_CSSELR_EL1 sys_reg(3, 2, 0, 0, 0) #define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1) @@ -461,6 +475,10 @@ #define SYS_RNDR_EL0 sys_reg(3, 3, 2, 4, 0) #define SYS_RNDRRS_EL0 sys_reg(3, 3, 2, 4, 1) +#define SYS_SVCR_EL0 sys_reg(3, 3, 4, 2, 2) +#define SYS_SVCR_EL0_ZA_MASK 2 +#define SYS_SVCR_EL0_SM_MASK 1 + #define SYS_PMCR_EL0 sys_reg(3, 3, 9, 12, 0) #define SYS_PMCNTENSET_EL0 sys_reg(3, 3, 9, 12, 1) #define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2) @@ -477,6 +495,7 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +#define SYS_TPIDR2_EL0 sys_reg(3, 3, 13, 0, 5) #define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7) @@ -546,6 +565,9 @@ #define SYS_HFGITR_EL2 sys_reg(3, 4, 1, 1, 6) #define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0) #define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) +#define SYS_HCRX_EL2 sys_reg(3, 4, 1, 2, 2) +#define SYS_SMPRIMAP_EL2 sys_reg(3, 4, 1, 2, 5) +#define SYS_SMCR_EL2 sys_reg(3, 4, 1, 2, 6) #define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0) #define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4) #define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5) @@ -605,6 +627,7 @@ #define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0) #define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2) #define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0) +#define SYS_SMCR_EL12 sys_reg(3, 5, 1, 2, 6) #define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0) #define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1) #define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2) @@ -628,6 +651,7 @@ #define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2) /* Common SCTLR_ELx flags. */ +#define SCTLR_ELx_ENTP2 (BIT(60)) #define SCTLR_ELx_DSSBS (BIT(44)) #define SCTLR_ELx_ATA (BIT(43)) @@ -836,6 +860,7 @@ #define ID_AA64PFR0_ELx_32BIT_64BIT 0x2 /* id_aa64pfr1 */ +#define ID_AA64PFR1_SME_SHIFT 24 #define ID_AA64PFR1_MPAMFRAC_SHIFT 16 #define ID_AA64PFR1_RASFRAC_SHIFT 12 #define ID_AA64PFR1_MTE_SHIFT 8 @@ -846,6 +871,7 @@ #define ID_AA64PFR1_SSBS_PSTATE_ONLY 1 #define ID_AA64PFR1_SSBS_PSTATE_INSNS 2 #define ID_AA64PFR1_BT_BTI 0x1 +#define ID_AA64PFR1_SME 1 #define ID_AA64PFR1_MTE_NI 0x0 #define ID_AA64PFR1_MTE_EL0 0x1 @@ -874,6 +900,23 @@ #define ID_AA64ZFR0_AES_PMULL 0x2 #define ID_AA64ZFR0_SVEVER_SVE2 0x1 +/* id_aa64smfr0 */ +#define ID_AA64SMFR0_FA64_SHIFT 63 +#define ID_AA64SMFR0_I16I64_SHIFT 52 +#define ID_AA64SMFR0_F64F64_SHIFT 48 +#define ID_AA64SMFR0_I8I32_SHIFT 36 +#define ID_AA64SMFR0_F16F32_SHIFT 35 +#define ID_AA64SMFR0_B16F32_SHIFT 34 +#define ID_AA64SMFR0_F32F32_SHIFT 32 + +#define ID_AA64SMFR0_FA64 0x1 +#define ID_AA64SMFR0_I16I64 0x4 +#define ID_AA64SMFR0_F64F64 0x1 +#define ID_AA64SMFR0_I8I32 0x4 +#define ID_AA64SMFR0_F16F32 0x1 +#define ID_AA64SMFR0_B16F32 0x1 +#define ID_AA64SMFR0_F32F32 0x1 + /* id_aa64mmfr0 */ #define ID_AA64MMFR0_ECV_SHIFT 60 #define ID_AA64MMFR0_FGT_SHIFT 56 @@ -926,6 +969,7 @@ /* id_aa64mmfr1 */ #define ID_AA64MMFR1_ECBHB_SHIFT 60 +#define ID_AA64MMFR1_HCX_SHIFT 40 #define ID_AA64MMFR1_AFP_SHIFT 44 #define ID_AA64MMFR1_ETS_SHIFT 36 #define ID_AA64MMFR1_TWED_SHIFT 32 @@ -1119,9 +1163,24 @@ #define ZCR_ELx_LEN_SIZE 9 #define ZCR_ELx_LEN_MASK 0x1ff +#define SMCR_ELx_FA64_SHIFT 31 +#define SMCR_ELx_FA64_MASK (1 << SMCR_ELx_FA64_SHIFT) + +/* + * The SMCR_ELx_LEN_* definitions intentionally include bits [8:4] which + * are reserved by the SME architecture for future expansion of the LEN + * field, with compatible semantics. + */ +#define SMCR_ELx_LEN_SHIFT 0 +#define SMCR_ELx_LEN_SIZE 9 +#define SMCR_ELx_LEN_MASK 0x1ff + #define CPACR_EL1_FPEN_EL1EN (BIT(20)) /* enable EL1 access */ #define CPACR_EL1_FPEN_EL0EN (BIT(21)) /* enable EL0 access, if EL1EN set */ +#define CPACR_EL1_SMEN_EL1EN (BIT(24)) /* enable EL1 access */ +#define CPACR_EL1_SMEN_EL0EN (BIT(25)) /* enable EL0 access, if EL1EN set */ + #define CPACR_EL1_ZEN_EL1EN (BIT(16)) /* enable EL1 access */ #define CPACR_EL1_ZEN_EL0EN (BIT(17)) /* enable EL0 access, if EL1EN set */ @@ -1170,6 +1229,8 @@ #define TRFCR_ELx_ExTRE BIT(1) #define TRFCR_ELx_E0TRE BIT(0) +/* HCRX_EL2 definitions */ +#define HCRX_EL2_SMPME_MASK (1 << 5) /* GIC Hypervisor interface registers */ /* ICH_MISR_EL2 bit definitions */ @@ -1233,6 +1294,12 @@ #define ICH_VTR_TDS_SHIFT 19 #define ICH_VTR_TDS_MASK (1 << ICH_VTR_TDS_SHIFT) +/* HFG[WR]TR_EL2 bit definitions */ +#define HFGxTR_EL2_nTPIDR2_EL0_SHIFT 55 +#define HFGxTR_EL2_nTPIDR2_EL0_MASK BIT_MASK(HFGxTR_EL2_nTPIDR2_EL0_SHIFT) +#define HFGxTR_EL2_nSMPRI_EL1_SHIFT 54 +#define HFGxTR_EL2_nSMPRI_EL1_MASK BIT_MASK(HFGxTR_EL2_nSMPRI_EL1_SHIFT) + #define ARM64_FEATURE_FIELD_BITS 4 /* Create a mask for the feature bits of the specified feature. */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index e1317b7c4525..848739c15de8 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -82,6 +82,8 @@ int arch_dup_task_struct(struct task_struct *dst, #define TIF_SVE_VL_INHERIT 24 /* Inherit SVE vl_onexec across exec */ #define TIF_SSBD 25 /* Wants SSB mitigation */ #define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ +#define TIF_SME 27 /* SME in use */ +#define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 99cb5d383048..4bb2cc8ac446 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -79,5 +79,14 @@ #define HWCAP2_AFP (1 << 20) #define HWCAP2_RPRES (1 << 21) #define HWCAP2_MTE3 (1 << 22) +#define HWCAP2_SME (1 << 23) +#define HWCAP2_SME_I16I64 (1 << 24) +#define HWCAP2_SME_F64F64 (1 << 25) +#define HWCAP2_SME_I8I32 (1 << 26) +#define HWCAP2_SME_F16F32 (1 << 27) +#define HWCAP2_SME_B16F32 (1 << 28) +#define HWCAP2_SME_F32F32 (1 << 29) +#define HWCAP2_SME_FA64 (1 << 30) +#define HWCAP2_WFXT (1UL << 31) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index c1b6ddc02d2f..d4722b08f0d4 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -332,6 +332,40 @@ struct kvm_arm_copy_mte_tags { #define KVM_ARM64_SVE_VLS_WORDS \ ((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1) +/* Bitmap feature firmware registers */ +#define KVM_REG_ARM_FW_FEAT_BMAP (0x0016 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_FEAT_BMAP_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW_FEAT_BMAP | \ + ((r) & 0xffff)) + +#define KVM_REG_ARM_STD_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(0) + +enum { + KVM_REG_ARM_STD_BIT_TRNG_V1_0 = 0, +#ifdef __KERNEL__ + KVM_REG_ARM_STD_BMAP_BIT_COUNT, +#endif +}; + +#define KVM_REG_ARM_STD_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(1) + +enum { + KVM_REG_ARM_STD_HYP_BIT_PV_TIME = 0, +#ifdef __KERNEL__ + KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT, +#endif +}; + +#define KVM_REG_ARM_VENDOR_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(2) + +enum { + KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT = 0, + KVM_REG_ARM_VENDOR_HYP_BIT_PTP = 1, +#ifdef __KERNEL__ + KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT, +#endif +}; + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 758ae984ff97..7fa2f7036aa7 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -109,7 +109,7 @@ struct user_hwdebug_state { } dbg_regs[16]; }; -/* SVE/FP/SIMD state (NT_ARM_SVE) */ +/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */ struct user_sve_header { __u32 size; /* total meaningful regset content in bytes */ @@ -220,6 +220,7 @@ struct user_sve_header { (SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \ SVE_PT_SVE_PREGS_OFFSET(vq)) +/* For streaming mode SVE (SSVE) FFR must be read and written as zero */ #define SVE_PT_SVE_FFR_OFFSET(vq) \ (SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq)) @@ -240,10 +241,12 @@ struct user_sve_header { - SVE_PT_SVE_OFFSET + (__SVE_VQ_BYTES - 1)) \ / __SVE_VQ_BYTES * __SVE_VQ_BYTES) -#define SVE_PT_SIZE(vq, flags) \ - (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ - SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ - : SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags)) +#define SVE_PT_SIZE(vq, flags) \ + (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ + SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ + : ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ? \ + SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \ + : SVE_PT_REGS_OFFSET))) /* pointer authentication masks (NT_ARM_PAC_MASK) */ @@ -265,6 +268,62 @@ struct user_pac_generic_keys { __uint128_t apgakey; }; +/* ZA state (NT_ARM_ZA) */ + +struct user_za_header { + __u32 size; /* total meaningful regset content in bytes */ + __u32 max_size; /* maxmium possible size for this thread */ + __u16 vl; /* current vector length */ + __u16 max_vl; /* maximum possible vector length */ + __u16 flags; + __u16 __reserved; +}; + +/* + * Common ZA_PT_* flags: + * These must be kept in sync with prctl interface in <linux/prctl.h> + */ +#define ZA_PT_VL_INHERIT ((1 << 17) /* PR_SME_VL_INHERIT */ >> 16) +#define ZA_PT_VL_ONEXEC ((1 << 18) /* PR_SME_SET_VL_ONEXEC */ >> 16) + + +/* + * The remainder of the ZA state follows struct user_za_header. The + * total size of the ZA state (including header) depends on the + * metadata in the header: ZA_PT_SIZE(vq, flags) gives the total size + * of the state in bytes, including the header. + * + * Refer to <asm/sigcontext.h> for details of how to pass the correct + * "vq" argument to these macros. + */ + +/* Offset from the start of struct user_za_header to the register data */ +#define ZA_PT_ZA_OFFSET \ + ((sizeof(struct user_za_header) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +/* + * The payload starts at offset ZA_PT_ZA_OFFSET, and is of size + * ZA_PT_ZA_SIZE(vq, flags). + * + * The ZA array is stored as a sequence of horizontal vectors ZAV of SVL/8 + * bytes each, starting from vector 0. + * + * Additional data might be appended in the future. + * + * The ZA matrix is represented in memory in an endianness-invariant layout + * which differs from the layout used for the FPSIMD V-registers on big-endian + * systems: see sigcontext.h for more explanation. + */ + +#define ZA_PT_ZAV_OFFSET(vq, n) \ + (ZA_PT_ZA_OFFSET + ((vq * __SVE_VQ_BYTES) * n)) + +#define ZA_PT_ZA_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_PT_SIZE(vq) \ + (ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq)) + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 0c796c795dbe..4aaf31e3bf16 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -134,6 +134,17 @@ struct extra_context { struct sve_context { struct _aarch64_ctx head; __u16 vl; + __u16 flags; + __u16 __reserved[2]; +}; + +#define SVE_SIG_FLAG_SM 0x1 /* Context describes streaming mode */ + +#define ZA_MAGIC 0x54366345 + +struct za_context { + struct _aarch64_ctx head; + __u16 vl; __u16 __reserved[3]; }; @@ -186,9 +197,16 @@ struct sve_context { * sve_context.vl must equal the thread's current vector length when * doing a sigreturn. * + * On systems with support for SME the SVE register state may reflect either + * streaming or non-streaming mode. In streaming mode the streaming mode + * vector length will be used and the flag SVE_SIG_FLAG_SM will be set in + * the flags field. It is permitted to enter or leave streaming mode in + * a signal return, applications should take care to ensure that any difference + * in vector length between the two modes is handled, including any resizing + * and movement of context blocks. * - * Note: for all these macros, the "vq" argument denotes the SVE - * vector length in quadwords (i.e., units of 128 bits). + * Note: for all these macros, the "vq" argument denotes the vector length + * in quadwords (i.e., units of 128 bits). * * The correct way to obtain vq is to use sve_vq_from_vl(vl). The * result is valid if and only if sve_vl_valid(vl) is true. This is @@ -249,4 +267,37 @@ struct sve_context { #define SVE_SIG_CONTEXT_SIZE(vq) \ (SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq)) +/* + * If the ZA register is enabled for the thread at signal delivery then, + * za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * and the register data may be accessed using the ZA_SIG_*() macros. + * + * If za_context.head.size < ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * then ZA was not enabled and no register data was included in which case + * ZA register was not enabled for the thread and no register data + * the ZA_SIG_*() macros should not be used except for this check. + * + * The same convention applies when returning from a signal: a caller + * will need to remove or resize the za_context block if it wants to + * enable the ZA register when it was previously non-live or vice-versa. + * This may require the caller to allocate fresh memory and/or move other + * context blocks in the signal frame. + * + * Changing the vector length during signal return is not permitted: + * za_context.vl must equal the thread's current SME vector length when + * doing a sigreturn. + */ + +#define ZA_SIG_REGS_OFFSET \ + ((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \ + (SVE_SIG_ZREG_SIZE(vq) * n)) + +#define ZA_SIG_CONTEXT_SIZE(vq) \ + (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) + #endif /* _UAPI__ASM_SIGCONTEXT_H */ diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 3fb79b76e9d9..7bbf5104b7b7 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -42,7 +42,7 @@ bool alternative_is_applied(u16 cpufeature) /* * Check if the target PC is within an alternative block. */ -static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) +static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); return !(pc >= replptr && pc <= (replptr + alt->alt_len)); @@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) -static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) +static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) { u32 insn; @@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp return insn; } -static void patch_alternative(struct alt_instr *alt, +static noinstr void patch_alternative(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { __le32 *replptr; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d72c4b4d389c..78ed5fc762eb 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -237,6 +237,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_GPA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_RPRES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_WFXT_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -261,6 +262,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SME_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE), @@ -293,6 +296,24 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_FA64_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I16I64_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F64F64_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_I8I32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F16F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_B16F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_F32F32_SHIFT, 1, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0), @@ -561,6 +582,12 @@ static const struct arm64_ftr_bits ftr_zcr[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_smcr[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, + SMCR_ELx_LEN_SHIFT, SMCR_ELx_LEN_SIZE, 0), /* LEN */ + ARM64_FTR_END, +}; + /* * Common ftr bits for a 32bit register with all hidden, strict * attributes, with 4bit feature fields and a default safe value of @@ -645,6 +672,7 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1, &id_aa64pfr1_override), ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0), + ARM64_FTR_REG(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), @@ -666,6 +694,7 @@ static const struct __ftr_reg_entry { /* Op1 = 0, CRn = 1, CRm = 2 */ ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr), + ARM64_FTR_REG(SYS_SMCR_EL1, ftr_smcr), /* Op1 = 1, CRn = 0, CRm = 0 */ ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid), @@ -960,6 +989,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0); + init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) init_32bit_cpu_features(&info->aarch32); @@ -969,6 +999,12 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) vec_init_vq_map(ARM64_VEC_SVE); } + if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + init_cpu_ftr_reg(SYS_SMCR_EL1, info->reg_smcr); + if (IS_ENABLED(CONFIG_ARM64_SME)) + vec_init_vq_map(ARM64_VEC_SME); + } + if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid); @@ -1195,6 +1231,9 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu, info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu, + info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0); + if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) { taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu, info->reg_zcr, boot->reg_zcr); @@ -1205,6 +1244,16 @@ void update_cpu_features(int cpu, vec_update_vq_map(ARM64_VEC_SVE); } + if (id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + taint |= check_update_ftr_reg(SYS_SMCR_EL1, cpu, + info->reg_smcr, boot->reg_smcr); + + /* Probe vector lengths, unless we already gave up on SME */ + if (id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1)) && + !system_capabilities_finalized()) + vec_update_vq_map(ARM64_VEC_SME); + } + /* * The kernel uses the LDGM/STGM instructions and the number of tags * they read/write depends on the GMID_EL1.BS field. Check that the @@ -1288,6 +1337,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64PFR0_EL1); read_sysreg_case(SYS_ID_AA64PFR1_EL1); read_sysreg_case(SYS_ID_AA64ZFR0_EL1); + read_sysreg_case(SYS_ID_AA64SMFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR0_EL1); @@ -2442,6 +2492,44 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .min_field_value = 1, }, +#ifdef CONFIG_ARM64_SME + { + .desc = "Scalable Matrix Extension", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_SME, + .sys_reg = SYS_ID_AA64PFR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64PFR1_SME_SHIFT, + .field_width = 4, + .min_field_value = ID_AA64PFR1_SME, + .matches = has_cpuid_feature, + .cpu_enable = sme_kernel_enable, + }, + /* FA64 should be sorted after the base SME capability */ + { + .desc = "FA64", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_SME_FA64, + .sys_reg = SYS_ID_AA64SMFR0_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64SMFR0_FA64_SHIFT, + .field_width = 1, + .min_field_value = ID_AA64SMFR0_FA64, + .matches = has_cpuid_feature, + .cpu_enable = fa64_kernel_enable, + }, +#endif /* CONFIG_ARM64_SME */ + { + .desc = "WFx with timeout", + .capability = ARM64_HAS_WFXT, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64ISAR2_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64ISAR2_WFXT_SHIFT, + .field_width = 4, + .matches = has_cpuid_feature, + .min_field_value = ID_AA64ISAR2_WFXT_SUPPORTED, + }, {}, }; @@ -2575,6 +2663,17 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV), HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP), HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES), + HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_WFXT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_WFXT_SUPPORTED, CAP_HWCAP, KERNEL_HWCAP_WFXT), +#ifdef CONFIG_ARM64_SME + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SME, CAP_HWCAP, KERNEL_HWCAP_SME), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_FA64, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I16I64, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F64F64, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_I8I32, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F16F32, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_B16F32, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_F32F32, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), +#endif /* CONFIG_ARM64_SME */ {}, }; @@ -2872,6 +2971,23 @@ static void verify_sve_features(void) /* Add checks on other ZCR bits here if necessary */ } +static void verify_sme_features(void) +{ + u64 safe_smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1); + u64 smcr = read_smcr_features(); + + unsigned int safe_len = safe_smcr & SMCR_ELx_LEN_MASK; + unsigned int len = smcr & SMCR_ELx_LEN_MASK; + + if (len < safe_len || vec_verify_vq_map(ARM64_VEC_SME)) { + pr_crit("CPU%d: SME: vector length support mismatch\n", + smp_processor_id()); + cpu_die_early(); + } + + /* Add checks on other SMCR bits here if necessary */ +} + static void verify_hyp_capabilities(void) { u64 safe_mmfr1, mmfr0, mmfr1; @@ -2924,6 +3040,9 @@ static void verify_local_cpu_capabilities(void) if (system_supports_sve()) verify_sve_features(); + if (system_supports_sme()) + verify_sme_features(); + if (is_hyp_mode_available()) verify_hyp_capabilities(); } @@ -3041,6 +3160,7 @@ void __init setup_cpu_features(void) pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); sve_setup(); + sme_setup(); minsigstksz_setup(); /* Advertise that we have computed the system capabilities */ diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 330b92ea863a..8eff0a34ffd4 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -98,6 +98,15 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_AFP] = "afp", [KERNEL_HWCAP_RPRES] = "rpres", [KERNEL_HWCAP_MTE3] = "mte3", + [KERNEL_HWCAP_SME] = "sme", + [KERNEL_HWCAP_SME_I16I64] = "smei16i64", + [KERNEL_HWCAP_SME_F64F64] = "smef64f64", + [KERNEL_HWCAP_SME_I8I32] = "smei8i32", + [KERNEL_HWCAP_SME_F16F32] = "smef16f32", + [KERNEL_HWCAP_SME_B16F32] = "smeb16f32", + [KERNEL_HWCAP_SME_F32F32] = "smef32f32", + [KERNEL_HWCAP_SME_FA64] = "smefa64", + [KERNEL_HWCAP_WFXT] = "wfxt", }; #ifdef CONFIG_COMPAT @@ -401,6 +410,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1); info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1); info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1); + info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1); if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) info->reg_gmid = read_cpuid(GMID_EL1); @@ -412,6 +422,10 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) id_aa64pfr0_sve(info->reg_id_aa64pfr0)) info->reg_zcr = read_zcr_features(); + if (IS_ENABLED(CONFIG_ARM64_SME) && + id_aa64pfr1_sme(info->reg_id_aa64pfr1)) + info->reg_smcr = read_smcr_features(); + cpuinfo_detect_icache_policy(info); } diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 3ed39c61a510..98d67444a5b6 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,16 +8,9 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#ifndef VMA_ITERATOR -#define VMA_ITERATOR(name, mm, addr) \ - struct mm_struct *name = mm -#define for_each_vma(vmi, vma) \ - for (vma = vmi->mmap; vma; vma = vma->vm_next) -#endif - -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(tsk, vma) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ + for (vma = tsk->mm->mmap; vma; vma = vma->vm_next) \ if (vma->vm_flags & VM_MTE) static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) @@ -32,10 +25,11 @@ static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) static int mte_dump_tag_range(struct coredump_params *cprm, unsigned long start, unsigned long end) { + int ret = 1; unsigned long addr; + void *tags = NULL; for (addr = start; addr < end; addr += PAGE_SIZE) { - char tags[MTE_PAGE_TAG_STORAGE]; struct page *page = get_dump_page(addr); /* @@ -59,22 +53,36 @@ static int mte_dump_tag_range(struct coredump_params *cprm, continue; } + if (!tags) { + tags = mte_allocate_tag_storage(); + if (!tags) { + put_page(page); + ret = 0; + break; + } + } + mte_save_page_tags(page_address(page), tags); put_page(page); - if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) - return 0; + if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { + mte_free_tag_storage(tags); + ret = 0; + break; + } } - return 1; + if (tags) + mte_free_tag_storage(tags); + + return ret; } Elf_Half elf_core_extra_phdrs(void) { struct vm_area_struct *vma; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) vma_count++; return vma_count; @@ -83,12 +91,11 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { struct elf_phdr phdr; - phdr.p_type = PT_ARM_MEMTAG_MTE; + phdr.p_type = PT_AARCH64_MEMTAG_MTE; phdr.p_offset = offset; phdr.p_vaddr = vma->vm_start; phdr.p_paddr = 0; @@ -109,9 +116,8 @@ size_t elf_core_extra_data_size(void) { struct vm_area_struct *vma; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) data_size += mte_vma_tag_dump_size(vma); return data_size; @@ -120,9 +126,8 @@ size_t elf_core_extra_data_size(void) int elf_core_write_extra_data(struct coredump_params *cprm) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { if (vma->vm_flags & VM_DONTDUMP) continue; diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 878c65aa7206..29139e9a1517 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -537,6 +537,14 @@ static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr) exit_to_user_mode(regs); } +static void noinstr el0_sme_acc(struct pt_regs *regs, unsigned long esr) +{ + enter_from_user_mode(regs); + local_daif_restore(DAIF_PROCCTX); + do_sme_acc(esr, regs); + exit_to_user_mode(regs); +} + static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) { enter_from_user_mode(regs); @@ -645,6 +653,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_SVE: el0_sve_acc(regs, esr); break; + case ESR_ELx_EC_SME: + el0_sme_acc(regs, esr); + break; case ESR_ELx_EC_FP_EXC64: el0_fpsimd_exc(regs, esr); break; diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S index dc242e269f9a..229436f33df5 100644 --- a/arch/arm64/kernel/entry-fpsimd.S +++ b/arch/arm64/kernel/entry-fpsimd.S @@ -86,3 +86,39 @@ SYM_FUNC_START(sve_flush_live) SYM_FUNC_END(sve_flush_live) #endif /* CONFIG_ARM64_SVE */ + +#ifdef CONFIG_ARM64_SME + +SYM_FUNC_START(sme_get_vl) + _sme_rdsvl 0, 1 + ret +SYM_FUNC_END(sme_get_vl) + +SYM_FUNC_START(sme_set_vq) + sme_load_vq x0, x1, x2 + ret +SYM_FUNC_END(sme_set_vq) + +/* + * Save the SME state + * + * x0 - pointer to buffer for state + */ +SYM_FUNC_START(za_save_state) + _sme_rdsvl 1, 1 // x1 = VL/8 + sme_save_za 0, x1, 12 + ret +SYM_FUNC_END(za_save_state) + +/* + * Load the SME state + * + * x0 - pointer to buffer for state + */ +SYM_FUNC_START(za_load_state) + _sme_rdsvl 1, 1 // x1 = VL/8 + sme_load_za 0, x1, 12 + ret +SYM_FUNC_END(za_load_state) + +#endif /* CONFIG_ARM64_SME */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 47af76e53221..64431bc62472 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -121,7 +121,10 @@ struct fpsimd_last_state_struct { struct user_fpsimd_state *st; void *sve_state; + void *za_state; + u64 *svcr; unsigned int sve_vl; + unsigned int sme_vl; }; static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); @@ -136,6 +139,12 @@ __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = { .max_virtualisable_vl = SVE_VL_MIN, }, #endif +#ifdef CONFIG_ARM64_SME + [ARM64_VEC_SME] = { + .type = ARM64_VEC_SME, + .name = "SME", + }, +#endif }; static unsigned int vec_vl_inherit_flag(enum vec_type type) @@ -143,6 +152,8 @@ static unsigned int vec_vl_inherit_flag(enum vec_type type) switch (type) { case ARM64_VEC_SVE: return TIF_SVE_VL_INHERIT; + case ARM64_VEC_SME: + return TIF_SME_VL_INHERIT; default: WARN_ON_ONCE(1); return 0; @@ -186,6 +197,26 @@ extern void __percpu *efi_sve_state; #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int get_sme_default_vl(void) +{ + return get_default_vl(ARM64_VEC_SME); +} + +static void set_sme_default_vl(int val) +{ + set_default_vl(ARM64_VEC_SME, val); +} + +static void sme_free(struct task_struct *); + +#else + +static inline void sme_free(struct task_struct *t) { } + +#endif + DEFINE_PER_CPU(bool, fpsimd_context_busy); EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy); @@ -279,16 +310,27 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, } /* + * TIF_SME controls whether a task can use SME without trapping while + * in userspace, when TIF_SME is set then we must have storage + * alocated in sve_state and za_state to store the contents of both ZA + * and the SVE registers for both streaming and non-streaming modes. + * + * If both SVCR.ZA and SVCR.SM are disabled then at any point we + * may disable TIF_SME and reenable traps. + */ + + +/* * TIF_SVE controls whether a task can use SVE without trapping while - * in userspace, and also the way a task's FPSIMD/SVE state is stored - * in thread_struct. + * in userspace, and also (together with TIF_SME) the way a task's + * FPSIMD/SVE state is stored in thread_struct. * * The kernel uses this flag to track whether a user task is actively * using SVE, and therefore whether full SVE register state needs to * be tracked. If not, the cheaper FPSIMD context handling code can * be used instead of the more costly SVE equivalents. * - * * TIF_SVE set: + * * TIF_SVE or SVCR.SM set: * * The task can execute SVE instructions while in userspace without * trapping to the kernel. @@ -296,7 +338,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the * corresponding Zn), P0-P15 and FFR are encoded in in * task->thread.sve_state, formatted appropriately for vector - * length task->thread.sve_vl. + * length task->thread.sve_vl or, if SVCR.SM is set, + * task->thread.sme_vl. * * task->thread.sve_state must point to a valid buffer at least * sve_state_size(task) bytes in size. @@ -334,16 +377,44 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, */ static void task_fpsimd_load(void) { + bool restore_sve_regs = false; + bool restore_ffr; + WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); + /* Check if we should restore SVE first */ if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); + restore_sve_regs = true; + restore_ffr = true; + } + + /* Restore SME, override SVE register configuration if needed */ + if (system_supports_sme()) { + unsigned long sme_vl = task_get_sme_vl(current); + + /* Ensure VL is set up for restoring data */ + if (test_thread_flag(TIF_SME)) + sme_set_vq(sve_vq_from_vl(sme_vl) - 1); + + write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0); + + if (thread_za_enabled(¤t->thread)) + za_load_state(current->thread.za_state); + + if (thread_sm_enabled(¤t->thread)) { + restore_sve_regs = true; + restore_ffr = system_supports_fa64(); + } + } + + if (restore_sve_regs) sve_load_state(sve_pffr(¤t->thread), - ¤t->thread.uw.fpsimd_state.fpsr, true); - } else { + ¤t->thread.uw.fpsimd_state.fpsr, + restore_ffr); + else fpsimd_load_state(¤t->thread.uw.fpsimd_state); - } } /* @@ -361,6 +432,9 @@ static void fpsimd_save(void) struct fpsimd_last_state_struct const *last = this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ + bool save_sve_regs = false; + bool save_ffr; + unsigned int vl; WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); @@ -368,9 +442,32 @@ static void fpsimd_save(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; - if (IS_ENABLED(CONFIG_ARM64_SVE) && - test_thread_flag(TIF_SVE)) { - if (WARN_ON(sve_get_vl() != last->sve_vl)) { + if (test_thread_flag(TIF_SVE)) { + save_sve_regs = true; + save_ffr = true; + vl = last->sve_vl; + } + + if (system_supports_sme()) { + u64 *svcr = last->svcr; + *svcr = read_sysreg_s(SYS_SVCR_EL0); + + *svcr = read_sysreg_s(SYS_SVCR_EL0); + + if (*svcr & SYS_SVCR_EL0_ZA_MASK) + za_save_state(last->za_state); + + /* If we are in streaming mode override regular SVE. */ + if (*svcr & SYS_SVCR_EL0_SM_MASK) { + save_sve_regs = true; + save_ffr = system_supports_fa64(); + vl = last->sme_vl; + } + } + + if (IS_ENABLED(CONFIG_ARM64_SVE) && save_sve_regs) { + /* Get the configured VL from RDVL, will account for SM */ + if (WARN_ON(sve_get_vl() != vl)) { /* * Can't save the user regs, so current would * re-enter user with corrupt state. @@ -381,8 +478,8 @@ static void fpsimd_save(void) } sve_save_state((char *)last->sve_state + - sve_ffr_offset(last->sve_vl), - &last->st->fpsr, true); + sve_ffr_offset(vl), + &last->st->fpsr, save_ffr); } else { fpsimd_save_state(last->st); } @@ -409,6 +506,8 @@ static unsigned int find_supported_vector_length(enum vec_type type, if (vl > max_vl) vl = max_vl; + if (vl < info->min_vl) + vl = info->min_vl; bit = find_next_bit(info->vq_map, SVE_VQ_MAX, __vq_to_bit(sve_vq_from_vl(vl))); @@ -467,6 +566,30 @@ static int __init sve_sysctl_init(void) static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ +#if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) +static struct ctl_table sme_default_vl_table[] = { + { + .procname = "sme_default_vector_length", + .mode = 0644, + .proc_handler = vec_proc_do_default_vl, + .extra1 = &vl_info[ARM64_VEC_SME], + }, + { } +}; + +static int __init sme_sysctl_init(void) +{ + if (system_supports_sme()) + if (!register_sysctl("abi", sme_default_vl_table)) + return -EINVAL; + + return 0; +} + +#else /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ +static int __init sme_sysctl_init(void) { return 0; } +#endif /* ! (CONFIG_ARM64_SME && CONFIG_SYSCTL) */ + #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) @@ -520,7 +643,7 @@ static void fpsimd_to_sve(struct task_struct *task) if (!system_supports_sve()) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); __fpsimd_to_sve(sst, fst, vq); } @@ -537,7 +660,7 @@ static void fpsimd_to_sve(struct task_struct *task) */ static void sve_to_fpsimd(struct task_struct *task) { - unsigned int vq; + unsigned int vq, vl; void const *sst = task->thread.sve_state; struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state; unsigned int i; @@ -546,7 +669,8 @@ static void sve_to_fpsimd(struct task_struct *task) if (!system_supports_sve()) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vl = thread_get_cur_vl(&task->thread); + vq = sve_vq_from_vl(vl); for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); @@ -559,9 +683,16 @@ static void sve_to_fpsimd(struct task_struct *task) * Return how many bytes of memory are required to store the full SVE * state for task, given task's currently configured vector length. */ -static size_t sve_state_size(struct task_struct const *task) +size_t sve_state_size(struct task_struct const *task) { - return SVE_SIG_REGS_SIZE(sve_vq_from_vl(task_get_sve_vl(task))); + unsigned int vl = 0; + + if (system_supports_sve()) + vl = task_get_sve_vl(task); + if (system_supports_sme()) + vl = max(vl, task_get_sme_vl(task)); + + return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)); } /* @@ -588,6 +719,19 @@ void sve_alloc(struct task_struct *task) /* + * Force the FPSIMD state shared with SVE to be updated in the SVE state + * even if the SVE state is the current active state. + * + * This should only be called by ptrace. task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + */ +void fpsimd_force_sync_to_sve(struct task_struct *task) +{ + fpsimd_to_sve(task); +} + +/* * Ensure that task->thread.sve_state is up to date with respect to * the user task, irrespective of when SVE is in use or not. * @@ -597,7 +741,8 @@ void sve_alloc(struct task_struct *task) */ void fpsimd_sync_to_sve(struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SVE)) + if (!test_tsk_thread_flag(task, TIF_SVE) && + !thread_sm_enabled(&task->thread)) fpsimd_to_sve(task); } @@ -611,7 +756,8 @@ void fpsimd_sync_to_sve(struct task_struct *task) */ void sve_sync_to_fpsimd(struct task_struct *task) { - if (test_tsk_thread_flag(task, TIF_SVE)) + if (test_tsk_thread_flag(task, TIF_SVE) || + thread_sm_enabled(&task->thread)) sve_to_fpsimd(task); } @@ -636,7 +782,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) if (!test_tsk_thread_flag(task, TIF_SVE)) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); __fpsimd_to_sve(sst, fst, vq); @@ -680,8 +826,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, /* * To ensure the FPSIMD bits of the SVE vector registers are preserved, * write any live register state back to task_struct, and convert to a - * regular FPSIMD thread. Since the vector length can only be changed - * with a syscall we can't be in streaming mode while reconfiguring. + * regular FPSIMD thread. */ if (task == current) { get_cpu_fpsimd_context(); @@ -690,17 +835,26 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, } fpsimd_flush_task_state(task); - if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) + if (test_and_clear_tsk_thread_flag(task, TIF_SVE) || + thread_sm_enabled(&task->thread)) sve_to_fpsimd(task); + if (system_supports_sme() && type == ARM64_VEC_SME) { + task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK | + SYS_SVCR_EL0_ZA_MASK); + clear_thread_flag(TIF_SME); + } + if (task == current) put_cpu_fpsimd_context(); /* - * Force reallocation of task SVE state to the correct size - * on next use: + * Force reallocation of task SVE and SME state to the correct + * size on next use: */ sve_free(task); + if (system_supports_sme() && type == ARM64_VEC_SME) + sme_free(task); task_set_vl(task, type, vl); @@ -761,6 +915,36 @@ int sve_get_current_vl(void) return vec_prctl_status(ARM64_VEC_SVE, 0); } +#ifdef CONFIG_ARM64_SME +/* PR_SME_SET_VL */ +int sme_set_current_vl(unsigned long arg) +{ + unsigned long vl, flags; + int ret; + + vl = arg & PR_SME_VL_LEN_MASK; + flags = arg & ~vl; + + if (!system_supports_sme() || is_compat_task()) + return -EINVAL; + + ret = vec_set_vector_length(current, ARM64_VEC_SME, vl, flags); + if (ret) + return ret; + + return vec_prctl_status(ARM64_VEC_SME, flags); +} + +/* PR_SME_GET_VL */ +int sme_get_current_vl(void) +{ + if (!system_supports_sme() || is_compat_task()) + return -EINVAL; + + return vec_prctl_status(ARM64_VEC_SME, 0); +} +#endif /* CONFIG_ARM64_SME */ + static void vec_probe_vqs(struct vl_info *info, DECLARE_BITMAP(map, SVE_VQ_MAX)) { @@ -770,7 +954,23 @@ static void vec_probe_vqs(struct vl_info *info, for (vq = SVE_VQ_MAX; vq >= SVE_VQ_MIN; --vq) { write_vl(info->type, vq - 1); /* self-syncing */ - vl = sve_get_vl(); + + switch (info->type) { + case ARM64_VEC_SVE: + vl = sve_get_vl(); + break; + case ARM64_VEC_SME: + vl = sme_get_vl(); + break; + default: + vl = 0; + break; + } + + /* Minimum VL identified? */ + if (sve_vq_from_vl(vl) > vq) + break; + vq = sve_vq_from_vl(vl); /* skip intervening lengths */ set_bit(__vq_to_bit(vq), map); } @@ -856,21 +1056,25 @@ int vec_verify_vq_map(enum vec_type type) static void __init sve_efi_setup(void) { - struct vl_info *info = &vl_info[ARM64_VEC_SVE]; + int max_vl = 0; + int i; if (!IS_ENABLED(CONFIG_EFI)) return; + for (i = 0; i < ARRAY_SIZE(vl_info); i++) + max_vl = max(vl_info[i].max_vl, max_vl); + /* * alloc_percpu() warns and prints a backtrace if this goes wrong. * This is evidence of a crippled system and we are returning void, * so no attempt is made to handle this situation here. */ - if (!sve_vl_valid(info->max_vl)) + if (!sve_vl_valid(max_vl)) goto fail; efi_sve_state = __alloc_percpu( - SVE_SIG_REGS_SIZE(sve_vq_from_vl(info->max_vl)), SVE_VQ_BYTES); + SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES); if (!efi_sve_state) goto fail; @@ -989,10 +1193,172 @@ void __init sve_setup(void) void fpsimd_release_task(struct task_struct *dead_task) { __sve_free(dead_task); + sme_free(dead_task); } #endif /* CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +/* + * Ensure that task->thread.za_state is allocated and sufficiently large. + * + * This function should be used only in preparation for replacing + * task->thread.za_state with new data. The memory is always zeroed + * here to prevent stale data from showing through: this is done in + * the interest of testability and predictability, the architecture + * guarantees that when ZA is enabled it will be zeroed. + */ +void sme_alloc(struct task_struct *task) +{ + if (task->thread.za_state) { + memset(task->thread.za_state, 0, za_state_size(task)); + return; + } + + /* This could potentially be up to 64K. */ + task->thread.za_state = + kzalloc(za_state_size(task), GFP_KERNEL); +} + +static void sme_free(struct task_struct *task) +{ + kfree(task->thread.za_state); + task->thread.za_state = NULL; +} + +void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +{ + /* Set priority for all PEs to architecturally defined minimum */ + write_sysreg_s(read_sysreg_s(SYS_SMPRI_EL1) & ~SMPRI_EL1_PRIORITY_MASK, + SYS_SMPRI_EL1); + + /* Allow SME in kernel */ + write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); + isb(); + + /* Allow EL0 to access TPIDR2 */ + write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); + isb(); +} + +/* + * This must be called after sme_kernel_enable(), we rely on the + * feature table being sorted to ensure this. + */ +void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +{ + /* Allow use of FA64 */ + write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_FA64_MASK, + SYS_SMCR_EL1); +} + +/* + * Read the pseudo-SMCR used by cpufeatures to identify the supported + * vector length. + * + * Use only if SME is present. + * This function clobbers the SME vector length. + */ +u64 read_smcr_features(void) +{ + u64 smcr; + unsigned int vq_max; + + sme_kernel_enable(NULL); + sme_smstart_sm(); + + /* + * Set the maximum possible VL. + */ + write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK, + SYS_SMCR_EL1); + + smcr = read_sysreg_s(SYS_SMCR_EL1); + smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */ + vq_max = sve_vq_from_vl(sve_get_vl()); + smcr |= vq_max - 1; /* set LEN field to maximum effective value */ + + sme_smstop_sm(); + + return smcr; +} + +void __init sme_setup(void) +{ + struct vl_info *info = &vl_info[ARM64_VEC_SME]; + u64 smcr; + int min_bit; + + if (!system_supports_sme()) + return; + + /* + * SME doesn't require any particular vector length be + * supported but it does require at least one. We should have + * disabled the feature entirely while bringing up CPUs but + * let's double check here. + */ + WARN_ON(bitmap_empty(info->vq_map, SVE_VQ_MAX)); + + min_bit = find_last_bit(info->vq_map, SVE_VQ_MAX); + info->min_vl = sve_vl_from_vq(__bit_to_vq(min_bit)); + + smcr = read_sanitised_ftr_reg(SYS_SMCR_EL1); + info->max_vl = sve_vl_from_vq((smcr & SMCR_ELx_LEN_MASK) + 1); + + /* + * Sanity-check that the max VL we determined through CPU features + * corresponds properly to sme_vq_map. If not, do our best: + */ + if (WARN_ON(info->max_vl != find_supported_vector_length(ARM64_VEC_SME, + info->max_vl))) + info->max_vl = find_supported_vector_length(ARM64_VEC_SME, + info->max_vl); + + WARN_ON(info->min_vl > info->max_vl); + + /* + * For the default VL, pick the maximum supported value <= 32 + * (256 bits) if there is one since this is guaranteed not to + * grow the signal frame when in streaming mode, otherwise the + * minimum available VL will be used. + */ + set_sme_default_vl(find_supported_vector_length(ARM64_VEC_SME, 32)); + + pr_info("SME: minimum available vector length %u bytes per vector\n", + info->min_vl); + pr_info("SME: maximum available vector length %u bytes per vector\n", + info->max_vl); + pr_info("SME: default vector length %u bytes per vector\n", + get_sme_default_vl()); +} + +#endif /* CONFIG_ARM64_SME */ + +static void sve_init_regs(void) +{ + /* + * Convert the FPSIMD state to SVE, zeroing all the state that + * is not shared with FPSIMD. If (as is likely) the current + * state is live in the registers then do this there and + * update our metadata for the current task including + * disabling the trap, otherwise update our in-memory copy. + * We are guaranteed to not be in streaming mode, we can only + * take a SVE trap when not in streaming mode and we can't be + * in streaming mode when taking a SME trap. + */ + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { + unsigned long vq_minus_one = + sve_vq_from_vl(task_get_sve_vl(current)) - 1; + sve_set_vq(vq_minus_one); + sve_flush_live(true, vq_minus_one); + fpsimd_bind_task_to_cpu(); + } else { + fpsimd_to_sve(current); + } +} + /* * Trapped SVE access * @@ -1024,22 +1390,77 @@ void do_sve_acc(unsigned int esr, struct pt_regs *regs) WARN_ON(1); /* SVE access shouldn't have trapped */ /* - * Convert the FPSIMD state to SVE, zeroing all the state that - * is not shared with FPSIMD. If (as is likely) the current - * state is live in the registers then do this there and - * update our metadata for the current task including - * disabling the trap, otherwise update our in-memory copy. + * Even if the task can have used streaming mode we can only + * generate SVE access traps in normal SVE mode and + * transitioning out of streaming mode may discard any + * streaming mode state. Always clear the high bits to avoid + * any potential errors tracking what is properly initialised. */ + sve_init_regs(); + + put_cpu_fpsimd_context(); +} + +/* + * Trapped SME access + * + * Storage is allocated for the full SVE and SME state, the current + * FPSIMD register contents are migrated to SVE if SVE is not already + * active, and the access trap is disabled. + * + * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state() + * would have disabled the SME access trap for userspace during + * ret_to_user, making an SVE access trap impossible in that case. + */ +void do_sme_acc(unsigned int esr, struct pt_regs *regs) +{ + /* Even if we chose not to use SME, the hardware could still trap: */ + if (unlikely(!system_supports_sme()) || WARN_ON(is_compat_task())) { + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); + return; + } + + /* + * If this not a trap due to SME being disabled then something + * is being used in the wrong mode, report as SIGILL. + */ + if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) { + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); + return; + } + + sve_alloc(current); + sme_alloc(current); + if (!current->thread.sve_state || !current->thread.za_state) { + force_sig(SIGKILL); + return; + } + + get_cpu_fpsimd_context(); + + /* With TIF_SME userspace shouldn't generate any traps */ + if (test_and_set_thread_flag(TIF_SME)) + WARN_ON(1); + if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { unsigned long vq_minus_one = - sve_vq_from_vl(task_get_sve_vl(current)) - 1; - sve_set_vq(vq_minus_one); - sve_flush_live(true, vq_minus_one); + sve_vq_from_vl(task_get_sme_vl(current)) - 1; + sme_set_vq(vq_minus_one); + fpsimd_bind_task_to_cpu(); - } else { - fpsimd_to_sve(current); } + /* + * If SVE was not already active initialise the SVE registers, + * any non-shared state between the streaming and regular SVE + * registers is architecturally guaranteed to be zeroed when + * we enter streaming mode. We do not need to initialize ZA + * since ZA must be disabled at this point and enabling ZA is + * architecturally defined to zero ZA. + */ + if (system_supports_sve() && !test_thread_flag(TIF_SVE)) + sve_init_regs(); + put_cpu_fpsimd_context(); } @@ -1156,6 +1577,13 @@ void fpsimd_flush_thread(void) fpsimd_flush_thread_vl(ARM64_VEC_SVE); } + if (system_supports_sme()) { + clear_thread_flag(TIF_SME); + sme_free(current); + fpsimd_flush_thread_vl(ARM64_VEC_SME); + current->thread.svcr = 0; + } + put_cpu_fpsimd_context(); } @@ -1198,22 +1626,34 @@ static void fpsimd_bind_task_to_cpu(void) WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; + last->za_state = current->thread.za_state; last->sve_vl = task_get_sve_vl(current); + last->sme_vl = task_get_sme_vl(current); + last->svcr = ¤t->thread.svcr; current->thread.fpsimd_cpu = smp_processor_id(); + /* + * Toggle SVE and SME trapping for userspace if needed, these + * are serialsied by ret_to_user(). + */ + if (system_supports_sme()) { + if (test_thread_flag(TIF_SME)) + sme_user_enable(); + else + sme_user_disable(); + } + if (system_supports_sve()) { - /* Toggle SVE trapping for userspace if needed */ if (test_thread_flag(TIF_SVE)) sve_user_enable(); else sve_user_disable(); - - /* Serialised by exception return to user */ } } void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, - unsigned int sve_vl) + unsigned int sve_vl, void *za_state, + unsigned int sme_vl, u64 *svcr) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); @@ -1222,8 +1662,11 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, WARN_ON(!in_softirq() && !irqs_disabled()); last->st = st; + last->svcr = svcr; last->sve_state = sve_state; + last->za_state = za_state; last->sve_vl = sve_vl; + last->sme_vl = sme_vl; } /* @@ -1320,6 +1763,15 @@ static void fpsimd_flush_cpu_state(void) { WARN_ON(!system_supports_fpsimd()); __this_cpu_write(fpsimd_last_state.st, NULL); + + /* + * Leaving streaming mode enabled will cause issues for any kernel + * NEON and leaving streaming mode or ZA enabled may increase power + * consumption. + */ + if (system_supports_sme()) + sme_smstop(); + set_thread_flag(TIF_FOREIGN_FPSTATE); } @@ -1397,6 +1849,7 @@ EXPORT_SYMBOL(kernel_neon_end); static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state); static DEFINE_PER_CPU(bool, efi_fpsimd_state_used); static DEFINE_PER_CPU(bool, efi_sve_state_used); +static DEFINE_PER_CPU(bool, efi_sm_state); /* * EFI runtime services support functions @@ -1431,12 +1884,28 @@ void __efi_fpsimd_begin(void) */ if (system_supports_sve() && likely(efi_sve_state)) { char *sve_state = this_cpu_ptr(efi_sve_state); + bool ffr = true; + u64 svcr; __this_cpu_write(efi_sve_state_used, true); + if (system_supports_sme()) { + svcr = read_sysreg_s(SYS_SVCR_EL0); + + if (!system_supports_fa64()) + ffr = svcr & SYS_SVCR_EL0_SM_MASK; + + __this_cpu_write(efi_sm_state, ffr); + } + sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, - true); + ffr); + + if (system_supports_sme()) + sysreg_clear_set_s(SYS_SVCR_EL0, + SYS_SVCR_EL0_SM_MASK, 0); + } else { fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state)); } @@ -1459,11 +1928,26 @@ void __efi_fpsimd_end(void) if (system_supports_sve() && likely(__this_cpu_read(efi_sve_state_used))) { char const *sve_state = this_cpu_ptr(efi_sve_state); + bool ffr = true; + + /* + * Restore streaming mode; EFI calls are + * normal function calls so should not return in + * streaming mode. + */ + if (system_supports_sme()) { + if (__this_cpu_read(efi_sm_state)) { + sysreg_clear_set_s(SYS_SVCR_EL0, + 0, + SYS_SVCR_EL0_SM_MASK); + if (!system_supports_fa64()) + ffr = efi_sm_state; + } + } - sve_set_vq(sve_vq_from_vl(sve_get_vl()) - 1); sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()), &this_cpu_ptr(&efi_fpsimd_state)->fpsr, - true); + ffr); __this_cpu_write(efi_sve_state_used, false); } else { @@ -1538,6 +2022,13 @@ static int __init fpsimd_init(void) if (!cpu_have_named_feature(ASIMD)) pr_notice("Advanced SIMD is not implemented\n"); - return sve_sysctl_init(); + + if (cpu_have_named_feature(SME) && !cpu_have_named_feature(SVE)) + pr_notice("SME is implemented but not SVE\n"); + + sve_sysctl_init(); + sme_sysctl_init(); + + return 0; } core_initcall(fpsimd_init); diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 712e97c03e54..cd868084e724 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -701,7 +701,7 @@ NOKPROBE_SYMBOL(breakpoint_handler); * addresses. There is no straight-forward way, short of disassembling the * offending instruction, to map that address back to the watchpoint. This * function computes the distance of the memory access from the watchpoint as a - * heuristic for the likelyhood that a given access triggered the watchpoint. + * heuristic for the likelihood that a given access triggered the watchpoint. * * See Section D2.10.5 "Determining the memory location that caused a Watchpoint * exception" of ARMv8 Architecture Reference Manual for details. diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index e53493d8b208..a3d0494f25a9 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -220,7 +220,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, * increasing the section's alignment so that the * resulting address of this instruction is guaranteed * to equal the offset in that particular bit (as well - * as all less signficant bits). This ensures that the + * as all less significant bits). This ensures that the * address modulo 4 KB != 0xfff8 or 0xfffc (which would * have all ones in bits [11:3]) */ diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 771f543464e0..33e0fabc0b79 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) int i, ret = 0; struct aarch64_insn_patch *pp = arg; - /* The first CPU becomes master */ - if (atomic_inc_return(&pp->cpu_count) == 1) { + /* The last CPU becomes master */ + if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) { for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 7fa97df55e3a..9734c9fb1a32 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -250,6 +250,8 @@ void show_regs(struct pt_regs *regs) static void tls_thread_flush(void) { write_sysreg(0, tpidr_el0); + if (system_supports_tpidr2()) + write_sysreg_s(0, SYS_TPIDR2_EL0); if (is_compat_task()) { current->thread.uw.tp_value = 0; @@ -298,16 +300,42 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) /* * Detach src's sve_state (if any) from dst so that it does not - * get erroneously used or freed prematurely. dst's sve_state + * get erroneously used or freed prematurely. dst's copies * will be allocated on demand later on if dst uses SVE. * For consistency, also clear TIF_SVE here: this could be done * later in copy_process(), but to avoid tripping up future - * maintainers it is best not to leave TIF_SVE and sve_state in + * maintainers it is best not to leave TIF flags and buffers in * an inconsistent state, even temporarily. */ dst->thread.sve_state = NULL; clear_tsk_thread_flag(dst, TIF_SVE); + /* + * In the unlikely event that we create a new thread with ZA + * enabled we should retain the ZA state so duplicate it here. + * This may be shortly freed if we exec() or if CLONE_SETTLS + * but it's simpler to do it here. To avoid confusing the rest + * of the code ensure that we have a sve_state allocated + * whenever za_state is allocated. + */ + if (thread_za_enabled(&src->thread)) { + dst->thread.sve_state = kzalloc(sve_state_size(src), + GFP_KERNEL); + if (!dst->thread.sve_state) + return -ENOMEM; + dst->thread.za_state = kmemdup(src->thread.za_state, + za_state_size(src), + GFP_KERNEL); + if (!dst->thread.za_state) { + kfree(dst->thread.sve_state); + dst->thread.sve_state = NULL; + return -ENOMEM; + } + } else { + dst->thread.za_state = NULL; + clear_tsk_thread_flag(dst, TIF_SME); + } + /* clear any pending asynchronous tag fault raised by the parent */ clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT); @@ -343,6 +371,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, * out-of-sync with the saved value. */ *task_user_tls(p) = read_sysreg(tpidr_el0); + if (system_supports_tpidr2()) + p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); if (stack_start) { if (is_compat_thread(task_thread_info(p))) @@ -353,10 +383,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, /* * If a TLS pointer was passed to clone, use it for the new - * thread. + * thread. We also reset TPIDR2 if it's in use. */ - if (clone_flags & CLONE_SETTLS) + if (clone_flags & CLONE_SETTLS) { p->thread.uw.tp_value = tls; + p->thread.tpidr2_el0 = 0; + } } else { /* * A kthread has no context to ERET to, so ensure any buggy @@ -387,6 +419,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, void tls_preserve_current_state(void) { *task_user_tls(current) = read_sysreg(tpidr_el0); + if (system_supports_tpidr2() && !is_compat_task()) + current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); } static void tls_thread_switch(struct task_struct *next) @@ -399,6 +433,8 @@ static void tls_thread_switch(struct task_struct *next) write_sysreg(0, tpidrro_el0); write_sysreg(*task_user_tls(next), tpidr_el0); + if (system_supports_tpidr2()) + write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0); } /* diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 5777929d35bf..40be3a7c2c53 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope) if (scope == SCOPE_LOCAL_CPU) { static const struct midr_range spectre_bhb_k32_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 230a47b9189e..47d8a7472171 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -713,21 +713,51 @@ static int system_call_set(struct task_struct *target, #ifdef CONFIG_ARM64_SVE static void sve_init_header_from_task(struct user_sve_header *header, - struct task_struct *target) + struct task_struct *target, + enum vec_type type) { unsigned int vq; + bool active; + bool fpsimd_only; + enum vec_type task_type; memset(header, 0, sizeof(*header)); - header->flags = test_tsk_thread_flag(target, TIF_SVE) ? - SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD; - if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) - header->flags |= SVE_PT_VL_INHERIT; + /* Check if the requested registers are active for the task */ + if (thread_sm_enabled(&target->thread)) + task_type = ARM64_VEC_SME; + else + task_type = ARM64_VEC_SVE; + active = (task_type == type); + + switch (type) { + case ARM64_VEC_SVE: + if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE); + break; + case ARM64_VEC_SME: + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = false; + break; + default: + WARN_ON_ONCE(1); + return; + } - header->vl = task_get_sve_vl(target); + if (active) { + if (fpsimd_only) { + header->flags |= SVE_PT_REGS_FPSIMD; + } else { + header->flags |= SVE_PT_REGS_SVE; + } + } + + header->vl = task_get_vl(target, type); vq = sve_vq_from_vl(header->vl); - header->max_vl = sve_max_vl(); + header->max_vl = vec_max_vl(type); header->size = SVE_PT_SIZE(vq, header->flags); header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), SVE_PT_REGS_SVE); @@ -738,19 +768,17 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header) return ALIGN(header->size, SVE_VQ_BYTES); } -static int sve_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) +static int sve_get_common(struct task_struct *target, + const struct user_regset *regset, + struct membuf to, + enum vec_type type) { struct user_sve_header header; unsigned int vq; unsigned long start, end; - if (!system_supports_sve()) - return -EINVAL; - /* Header */ - sve_init_header_from_task(&header, target); + sve_init_header_from_task(&header, target, type); vq = sve_vq_from_vl(header.vl); membuf_write(&to, &header, sizeof(header)); @@ -758,49 +786,61 @@ static int sve_get(struct task_struct *target, if (target == current) fpsimd_preserve_current_state(); - /* Registers: FPSIMD-only case */ - BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); - if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + + switch ((header.flags & SVE_PT_REGS_MASK)) { + case SVE_PT_REGS_FPSIMD: return __fpr_get(target, regset, to); - /* Otherwise: full SVE case */ + case SVE_PT_REGS_SVE: + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + membuf_write(&to, target->thread.sve_state, end - start); - BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); - start = SVE_PT_SVE_OFFSET; - end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); - membuf_write(&to, target->thread.sve_state, end - start); + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + membuf_zero(&to, end - start); - start = end; - end = SVE_PT_SVE_FPSR_OFFSET(vq); - membuf_zero(&to, end - start); + /* + * Copy fpsr, and fpcr which must follow contiguously in + * struct fpsimd_state: + */ + start = end; + end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; + membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, + end - start); - /* - * Copy fpsr, and fpcr which must follow contiguously in - * struct fpsimd_state: - */ - start = end; - end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; - membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start); + start = end; + end = sve_size_from_header(&header); + return membuf_zero(&to, end - start); - start = end; - end = sve_size_from_header(&header); - return membuf_zero(&to, end - start); + default: + return 0; + } } -static int sve_set(struct task_struct *target, +static int sve_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + struct membuf to) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SVE); +} + +static int sve_set_common(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf, + enum vec_type type) { int ret; struct user_sve_header header; unsigned int vq; unsigned long start, end; - if (!system_supports_sve()) - return -EINVAL; - /* Header */ if (count < sizeof(header)) return -EINVAL; @@ -813,13 +853,37 @@ static int sve_set(struct task_struct *target, * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for us: */ - ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl, + ret = vec_set_vector_length(target, type, header.vl, ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); if (ret) goto out; /* Actual VL set may be less than the user asked for: */ - vq = sve_vq_from_vl(task_get_sve_vl(target)); + vq = sve_vq_from_vl(task_get_vl(target, type)); + + /* Enter/exit streaming mode */ + if (system_supports_sme()) { + u64 old_svcr = target->thread.svcr; + + switch (type) { + case ARM64_VEC_SVE: + target->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK; + break; + case ARM64_VEC_SME: + target->thread.svcr |= SYS_SVCR_EL0_SM_MASK; + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + + /* + * If we switched then invalidate any existing SVE + * state and ensure there's storage. + */ + if (target->thread.svcr != old_svcr) + sve_alloc(target); + } /* Registers: FPSIMD-only case */ @@ -828,10 +892,15 @@ static int sve_set(struct task_struct *target, ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, SVE_PT_FPSIMD_OFFSET); clear_tsk_thread_flag(target, TIF_SVE); + if (type == ARM64_VEC_SME) + fpsimd_force_sync_to_sve(target); goto out; } - /* Otherwise: full SVE case */ + /* + * Otherwise: no registers or full SVE case. For backwards + * compatibility reasons we treat empty flags as SVE registers. + */ /* * If setting a different VL from the requested VL and there is @@ -852,8 +921,9 @@ static int sve_set(struct task_struct *target, /* * Ensure target->thread.sve_state is up to date with target's - * FPSIMD regs, so that a short copyin leaves trailing registers - * unmodified. + * FPSIMD regs, so that a short copyin leaves trailing + * registers unmodified. Always enable SVE even if going into + * streaming mode. */ fpsimd_sync_to_sve(target); set_tsk_thread_flag(target, TIF_SVE); @@ -889,8 +959,181 @@ out: return ret; } +static int sve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SVE); +} + #endif /* CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int ssve_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SME); +} + +static int ssve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SME); +} + +static int za_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + memset(&header, 0, sizeof(header)); + + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header.flags |= ZA_PT_VL_INHERIT; + + header.vl = task_get_sme_vl(target); + vq = sve_vq_from_vl(header.vl); + header.max_vl = sme_max_vl(); + header.max_size = ZA_PT_SIZE(vq); + + /* If ZA is not active there is only the header */ + if (thread_za_enabled(&target->thread)) + header.size = ZA_PT_SIZE(vq); + else + header.size = ZA_PT_ZA_OFFSET; + + membuf_write(&to, &header, sizeof(header)); + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + end = ZA_PT_ZA_OFFSET; + + if (target == current) + fpsimd_preserve_current_state(); + + /* Any register data to include? */ + if (thread_za_enabled(&target->thread)) { + start = end; + end = ZA_PT_SIZE(vq); + membuf_write(&to, target->thread.za_state, end - start); + } + + /* Zero any trailing padding */ + start = end; + end = ALIGN(header.size, SVE_VQ_BYTES); + return membuf_zero(&to, end - start); +} + +static int za_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + if (count < sizeof(header)) + return -EINVAL; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, + 0, sizeof(header)); + if (ret) + goto out; + + /* + * All current ZA_PT_* flags are consumed by + * vec_set_vector_length(), which will also validate them for + * us: + */ + ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl, + ((unsigned long)header.flags) << 16); + if (ret) + goto out; + + /* Actual VL set may be less than the user asked for: */ + vq = sve_vq_from_vl(task_get_sme_vl(target)); + + /* Ensure there is some SVE storage for streaming mode */ + if (!target->thread.sve_state) { + sve_alloc(target); + if (!target->thread.sve_state) { + clear_thread_flag(TIF_SME); + ret = -ENOMEM; + goto out; + } + } + + /* Allocate/reinit ZA storage */ + sme_alloc(target); + if (!target->thread.za_state) { + ret = -ENOMEM; + clear_tsk_thread_flag(target, TIF_SME); + goto out; + } + + /* If there is no data then disable ZA */ + if (!count) { + target->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + goto out; + } + + /* + * If setting a different VL from the requested VL and there is + * register data, the data layout will be wrong: don't even + * try to set the registers in this case. + */ + if (vq != sve_vq_from_vl(header.vl)) { + ret = -EIO; + goto out; + } + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + start = ZA_PT_ZA_OFFSET; + end = ZA_PT_SIZE(vq); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + target->thread.za_state, + start, end); + if (ret) + goto out; + + /* Mark ZA as active and let userspace use it */ + set_tsk_thread_flag(target, TIF_SME); + target->thread.svcr |= SYS_SVCR_EL0_ZA_MASK; + +out: + fpsimd_flush_task_state(target); + return ret; +} + +#endif /* CONFIG_ARM64_SME */ + #ifdef CONFIG_ARM64_PTR_AUTH static int pac_mask_get(struct task_struct *target, const struct user_regset *regset, @@ -1108,6 +1351,10 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif +#ifdef CONFIG_ARM64_SVE + REGSET_SSVE, + REGSET_ZA, +#endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, REGSET_PAC_ENABLED_KEYS, @@ -1188,6 +1435,25 @@ static const struct user_regset aarch64_regsets[] = { .set = sve_set, }, #endif +#ifdef CONFIG_ARM64_SME + [REGSET_SSVE] = { /* Streaming mode SVE */ + .core_note_type = NT_ARM_SSVE, + .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE), + SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = ssve_get, + .set = ssve_set, + }, + [REGSET_ZA] = { /* SME ZA */ + .core_note_type = NT_ARM_ZA, + .n = DIV_ROUND_UP(ZA_PT_ZA_SIZE(SVE_VQ_MAX), SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = za_get, + .set = za_set, + }, +#endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { .core_note_type = NT_ARM_PAC_MASK, diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 4a4122ef6f39..2295948d97fd 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -56,6 +56,7 @@ struct rt_sigframe_user_layout { unsigned long fpsimd_offset; unsigned long esr_offset; unsigned long sve_offset; + unsigned long za_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -218,6 +219,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx) struct user_ctxs { struct fpsimd_context __user *fpsimd; struct sve_context __user *sve; + struct za_context __user *za; }; #ifdef CONFIG_ARM64_SVE @@ -226,11 +228,17 @@ static int preserve_sve_context(struct sve_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + u16 flags = 0; unsigned int vl = task_get_sve_vl(current); unsigned int vq = 0; - if (test_thread_flag(TIF_SVE)) + if (thread_sm_enabled(¤t->thread)) { + vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); + flags |= SVE_SIG_FLAG_SM; + } else if (test_thread_flag(TIF_SVE)) { + vq = sve_vq_from_vl(vl); + } memset(reserved, 0, sizeof(reserved)); @@ -238,6 +246,7 @@ static int preserve_sve_context(struct sve_context __user *ctx) __put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16), &ctx->head.size, err); __put_user_error(vl, &ctx->vl, err); + __put_user_error(flags, &ctx->flags, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); @@ -258,18 +267,28 @@ static int preserve_sve_context(struct sve_context __user *ctx) static int restore_sve_fpsimd_context(struct user_ctxs *user) { int err; - unsigned int vq; + unsigned int vl, vq; struct user_fpsimd_state fpsimd; struct sve_context sve; if (__copy_from_user(&sve, user->sve, sizeof(sve))) return -EFAULT; - if (sve.vl != task_get_sve_vl(current)) + if (sve.flags & SVE_SIG_FLAG_SM) { + if (!system_supports_sme()) + return -EINVAL; + + vl = task_get_sme_vl(current); + } else { + vl = task_get_sve_vl(current); + } + + if (sve.vl != vl) return -EINVAL; if (sve.head.size <= sizeof(*user->sve)) { clear_thread_flag(TIF_SVE); + current->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK; goto fpsimd_only; } @@ -301,7 +320,10 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (err) return -EFAULT; - set_thread_flag(TIF_SVE); + if (sve.flags & SVE_SIG_FLAG_SM) + current->thread.svcr |= SYS_SVCR_EL0_SM_MASK; + else + set_thread_flag(TIF_SVE); fpsimd_only: /* copy the FP and status/control registers */ @@ -326,6 +348,101 @@ extern int restore_sve_fpsimd_context(struct user_ctxs *user); #endif /* ! CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int preserve_za_context(struct za_context __user *ctx) +{ + int err = 0; + u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + unsigned int vl = task_get_sme_vl(current); + unsigned int vq; + + if (thread_za_enabled(¤t->thread)) + vq = sve_vq_from_vl(vl); + else + vq = 0; + + memset(reserved, 0, sizeof(reserved)); + + __put_user_error(ZA_MAGIC, &ctx->head.magic, err); + __put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16), + &ctx->head.size, err); + __put_user_error(vl, &ctx->vl, err); + BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); + err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); + + if (vq) { + /* + * This assumes that the ZA state has already been saved to + * the task struct by calling the function + * fpsimd_signal_preserve_current_state(). + */ + err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET, + current->thread.za_state, + ZA_SIG_REGS_SIZE(vq)); + } + + return err ? -EFAULT : 0; +} + +static int restore_za_context(struct user_ctxs __user *user) +{ + int err; + unsigned int vq; + struct za_context za; + + if (__copy_from_user(&za, user->za, sizeof(za))) + return -EFAULT; + + if (za.vl != task_get_sme_vl(current)) + return -EINVAL; + + if (za.head.size <= sizeof(*user->za)) { + current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + return 0; + } + + vq = sve_vq_from_vl(za.vl); + + if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq)) + return -EINVAL; + + /* + * Careful: we are about __copy_from_user() directly into + * thread.za_state with preemption enabled, so protection is + * needed to prevent a racing context switch from writing stale + * registers back over the new data. + */ + + fpsimd_flush_task_state(current); + /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ + + sme_alloc(current); + if (!current->thread.za_state) { + current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + clear_thread_flag(TIF_SME); + return -ENOMEM; + } + + err = __copy_from_user(current->thread.za_state, + (char __user const *)user->za + + ZA_SIG_REGS_OFFSET, + ZA_SIG_REGS_SIZE(vq)); + if (err) + return -EFAULT; + + set_thread_flag(TIF_SME); + current->thread.svcr |= SYS_SVCR_EL0_ZA_MASK; + + return 0; +} +#else /* ! CONFIG_ARM64_SME */ + +/* Turn any non-optimised out attempts to use these into a link error: */ +extern int preserve_za_context(void __user *ctx); +extern int restore_za_context(struct user_ctxs *user); + +#endif /* ! CONFIG_ARM64_SME */ static int parse_user_sigframe(struct user_ctxs *user, struct rt_sigframe __user *sf) @@ -340,6 +457,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->fpsimd = NULL; user->sve = NULL; + user->za = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -393,7 +511,7 @@ static int parse_user_sigframe(struct user_ctxs *user, break; case SVE_MAGIC: - if (!system_supports_sve()) + if (!system_supports_sve() && !system_supports_sme()) goto invalid; if (user->sve) @@ -405,6 +523,19 @@ static int parse_user_sigframe(struct user_ctxs *user, user->sve = (struct sve_context __user *)head; break; + case ZA_MAGIC: + if (!system_supports_sme()) + goto invalid; + + if (user->za) + goto invalid; + + if (size < sizeof(*user->za)) + goto invalid; + + user->za = (struct za_context __user *)head; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -528,6 +659,9 @@ static int restore_sigframe(struct pt_regs *regs, } } + if (err == 0 && system_supports_sme() && user.za) + err = restore_za_context(&user); + return err; } @@ -594,11 +728,12 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, if (system_supports_sve()) { unsigned int vq = 0; - if (add_all || test_thread_flag(TIF_SVE)) { - int vl = sve_max_vl(); + if (add_all || test_thread_flag(TIF_SVE) || + thread_sm_enabled(¤t->thread)) { + int vl = max(sve_max_vl(), sme_max_vl()); if (!add_all) - vl = task_get_sve_vl(current); + vl = thread_get_cur_vl(¤t->thread); vq = sve_vq_from_vl(vl); } @@ -609,6 +744,24 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } + if (system_supports_sme()) { + unsigned int vl; + unsigned int vq = 0; + + if (add_all) + vl = sme_max_vl(); + else + vl = task_get_sme_vl(current); + + if (thread_za_enabled(¤t->thread)) + vq = sve_vq_from_vl(vl); + + err = sigframe_alloc(user, &user->za_offset, + ZA_SIG_CONTEXT_SIZE(vq)); + if (err) + return err; + } + return sigframe_alloc_end(user); } @@ -649,13 +802,21 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); } - /* Scalable Vector Extension state, if present */ - if (system_supports_sve() && err == 0 && user->sve_offset) { + /* Scalable Vector Extension state (including streaming), if present */ + if ((system_supports_sve() || system_supports_sme()) && + err == 0 && user->sve_offset) { struct sve_context __user *sve_ctx = apply_user_offset(user, user->sve_offset); err |= preserve_sve_context(sve_ctx); } + /* ZA state if present */ + if (system_supports_sme() && err == 0 && user->za_offset) { + struct za_context __user *za_ctx = + apply_user_offset(user, user->za_offset); + err |= preserve_za_context(za_ctx); + } + if (err == 0 && user->extra_offset) { char __user *sfp = (char __user *)user->sigframe; char __user *userp = @@ -759,6 +920,13 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, /* TCO (Tag Check Override) always cleared for signal handlers */ regs->pstate &= ~PSR_TCO_BIT; + /* Signal handlers are invoked with ZA and streaming mode disabled */ + if (system_supports_sme()) { + current->thread.svcr &= ~(SYS_SVCR_EL0_ZA_MASK | + SYS_SVCR_EL0_SM_MASK); + sme_smstop(); + } + if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 27df5c1e6baa..3b46041f2b97 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void) * Log the CPU info before it is marked online and might get read. */ cpuinfo_store_cpu(); + store_cpu_topology(cpu); /* * Enable GIC and timers. @@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void) ipi_setup(cpu); - store_cpu_topology(cpu); numa_add_cpu(cpu); /* diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 19ee7c33769d..2b0887e58a7c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -140,7 +140,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully - * renabled if it was enabled when core started shutdown. + * reenabled if it was enabled when core started shutdown. */ local_daif_restore(flags); diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index c938603b3ba0..92c69e5ac269 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -158,11 +158,36 @@ trace_exit: syscall_trace_exit(regs); } -static inline void sve_user_discard(void) +/* + * As per the ABI exit SME streaming mode and clear the SVE state not + * shared with FPSIMD on syscall entry. + */ +static inline void fp_user_discard(void) { + /* + * If SME is active then exit streaming mode. If ZA is active + * then flush the SVE registers but leave userspace access to + * both SVE and SME enabled, otherwise disable SME for the + * task and fall through to disabling SVE too. This means + * that after a syscall we never have any streaming mode + * register state to track, if this changes the KVM code will + * need updating. + */ + if (system_supports_sme() && test_thread_flag(TIF_SME)) { + u64 svcr = read_sysreg_s(SYS_SVCR_EL0); + + if (svcr & SYS_SVCR_EL0_SM_MASK) + sme_smstop_sm(); + } + if (!system_supports_sve()) return; + /* + * If SME is not active then disable SVE, the registers will + * be cleared when userspace next attempts to access them and + * we do not need to track the SVE register state until then. + */ clear_thread_flag(TIF_SVE); /* @@ -177,7 +202,7 @@ static inline void sve_user_discard(void) void do_el0_svc(struct pt_regs *regs) { - sve_user_discard(); + fp_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 0529fd57567e..6751621e5bea 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -821,6 +821,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_SVE] = "SVE", [ESR_ELx_EC_ERET] = "ERET/ERETAA/ERETAB", [ESR_ELx_EC_FPAC] = "FPAC", + [ESR_ELx_EC_SME] = "SME", [ESR_ELx_EC_IMP_DEF] = "EL3 IMP DEF", [ESR_ELx_EC_IABT_LOW] = "IABT (lower EL)", [ESR_ELx_EC_IABT_CUR] = "IABT (current EL)", diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 261644b1a6bb..aa127ae9f675 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_KVM) += hyp/ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ inject_fault.o va_layout.o handle_exit.o \ guest.o debug.o reset.o sys_regs.o \ - vgic-sys-reg-v3.o fpsimd.o pmu.o pkvm.o \ + vgic-sys-reg-v3.o fpsimd.o pkvm.o \ arch_timer.o trng.o vmid.o \ vgic/vgic.o vgic/vgic-init.o \ vgic/vgic-irqfd.o vgic/vgic-v2.o \ @@ -22,7 +22,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \ vgic/vgic-its.o vgic/vgic-debug.o -kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o +kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o pmu.o always-y := hyp_constants.h hyp-constants.s diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 6e542e2eae32..4e39ace073af 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -208,18 +208,16 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) +static u64 kvm_counter_compute_delta(struct arch_timer_context *timer_ctx, + u64 val) { - u64 cval, now; - - cval = timer_get_cval(timer_ctx); - now = kvm_phys_timer_read() - timer_get_offset(timer_ctx); + u64 now = kvm_phys_timer_read() - timer_get_offset(timer_ctx); - if (now < cval) { + if (now < val) { u64 ns; ns = cyclecounter_cyc2ns(timecounter->cc, - cval - now, + val - now, timecounter->mask, &timecounter->frac); return ns; @@ -228,6 +226,11 @@ static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) return 0; } +static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) +{ + return kvm_counter_compute_delta(timer_ctx, timer_get_cval(timer_ctx)); +} + static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) { WARN_ON(timer_ctx && timer_ctx->loaded); @@ -236,6 +239,20 @@ static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) (ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE); } +static bool vcpu_has_wfit_active(struct kvm_vcpu *vcpu) +{ + return (cpus_have_final_cap(ARM64_HAS_WFXT) && + (vcpu->arch.flags & KVM_ARM64_WFIT)); +} + +static u64 wfit_delay_ns(struct kvm_vcpu *vcpu) +{ + struct arch_timer_context *ctx = vcpu_vtimer(vcpu); + u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); + + return kvm_counter_compute_delta(ctx, val); +} + /* * Returns the earliest expiration time in ns among guest timers. * Note that it will return 0 if none of timers can fire. @@ -253,6 +270,9 @@ static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu) min_delta = min(min_delta, kvm_timer_compute_delta(ctx)); } + if (vcpu_has_wfit_active(vcpu)) + min_delta = min(min_delta, wfit_delay_ns(vcpu)); + /* If none of timers can fire, then return 0 */ if (min_delta == ULLONG_MAX) return 0; @@ -350,15 +370,9 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) return cval <= now; } -bool kvm_timer_is_pending(struct kvm_vcpu *vcpu) +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - struct timer_map map; - - get_timer_map(vcpu, &map); - - return kvm_timer_should_fire(map.direct_vtimer) || - kvm_timer_should_fire(map.direct_ptimer) || - kvm_timer_should_fire(map.emul_ptimer); + return vcpu_has_wfit_active(vcpu) && wfit_delay_ns(vcpu) == 0; } /* @@ -484,7 +498,8 @@ static void kvm_timer_blocking(struct kvm_vcpu *vcpu) */ if (!kvm_timer_irq_can_fire(map.direct_vtimer) && !kvm_timer_irq_can_fire(map.direct_ptimer) && - !kvm_timer_irq_can_fire(map.emul_ptimer)) + !kvm_timer_irq_can_fire(map.emul_ptimer) && + !vcpu_has_wfit_active(vcpu)) return; /* diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 7fceb855fa71..807b2853b02a 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -97,6 +97,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, } mutex_unlock(&kvm->lock); break; + case KVM_CAP_ARM_SYSTEM_SUSPEND: + r = 0; + set_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags); + break; default: r = -EINVAL; break; @@ -156,6 +160,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->max_vcpus = kvm_arm_default_max_vcpus(); set_default_spectre(kvm); + kvm_arm_init_hypercalls(kvm); return ret; out_free_stage2_pgd: @@ -210,6 +215,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: + case KVM_CAP_ARM_SYSTEM_SUSPEND: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -356,11 +362,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_arm_vcpu_destroy(vcpu); } -int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) -{ - return kvm_timer_is_pending(vcpu); -} - void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { @@ -432,20 +433,34 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->cpu = -1; } -static void vcpu_power_off(struct kvm_vcpu *vcpu) +void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) { - vcpu->arch.power_off = true; + vcpu->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; kvm_make_request(KVM_REQ_SLEEP, vcpu); kvm_vcpu_kick(vcpu); } +bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mp_state.mp_state == KVM_MP_STATE_STOPPED; +} + +static void kvm_arm_vcpu_suspend(struct kvm_vcpu *vcpu) +{ + vcpu->arch.mp_state.mp_state = KVM_MP_STATE_SUSPENDED; + kvm_make_request(KVM_REQ_SUSPEND, vcpu); + kvm_vcpu_kick(vcpu); +} + +static bool kvm_arm_vcpu_suspended(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mp_state.mp_state == KVM_MP_STATE_SUSPENDED; +} + int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - if (vcpu->arch.power_off) - mp_state->mp_state = KVM_MP_STATE_STOPPED; - else - mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + *mp_state = vcpu->arch.mp_state; return 0; } @@ -457,10 +472,13 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: - vcpu->arch.power_off = false; + vcpu->arch.mp_state = *mp_state; break; case KVM_MP_STATE_STOPPED: - vcpu_power_off(vcpu); + kvm_arm_vcpu_power_off(vcpu); + break; + case KVM_MP_STATE_SUSPENDED: + kvm_arm_vcpu_suspend(vcpu); break; default: ret = -EINVAL; @@ -480,7 +498,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v) { bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF); return ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) - && !v->arch.power_off && !v->arch.pause); + && !kvm_arm_vcpu_stopped(v) && !v->arch.pause); } bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) @@ -592,15 +610,15 @@ void kvm_arm_resume_guest(struct kvm *kvm) } } -static void vcpu_req_sleep(struct kvm_vcpu *vcpu) +static void kvm_vcpu_sleep(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); rcuwait_wait_event(wait, - (!vcpu->arch.power_off) &&(!vcpu->arch.pause), + (!kvm_arm_vcpu_stopped(vcpu)) && (!vcpu->arch.pause), TASK_INTERRUPTIBLE); - if (vcpu->arch.power_off || vcpu->arch.pause) { + if (kvm_arm_vcpu_stopped(vcpu) || vcpu->arch.pause) { /* Awaken to handle a signal, request we sleep again later. */ kvm_make_request(KVM_REQ_SLEEP, vcpu); } @@ -639,6 +657,7 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) preempt_enable(); kvm_vcpu_halt(vcpu); + vcpu->arch.flags &= ~KVM_ARM64_WFIT; kvm_clear_request(KVM_REQ_UNHALT, vcpu); preempt_disable(); @@ -646,11 +665,53 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) preempt_enable(); } -static void check_vcpu_requests(struct kvm_vcpu *vcpu) +static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu) +{ + if (!kvm_arm_vcpu_suspended(vcpu)) + return 1; + + kvm_vcpu_wfi(vcpu); + + /* + * The suspend state is sticky; we do not leave it until userspace + * explicitly marks the vCPU as runnable. Request that we suspend again + * later. + */ + kvm_make_request(KVM_REQ_SUSPEND, vcpu); + + /* + * Check to make sure the vCPU is actually runnable. If so, exit to + * userspace informing it of the wakeup condition. + */ + if (kvm_arch_vcpu_runnable(vcpu)) { + memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_WAKEUP; + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + return 0; + } + + /* + * Otherwise, we were unblocked to process a different event, such as a + * pending signal. Return 1 and allow kvm_arch_vcpu_ioctl_run() to + * process the event. + */ + return 1; +} + +/** + * check_vcpu_requests - check and handle pending vCPU requests + * @vcpu: the VCPU pointer + * + * Return: 1 if we should enter the guest + * 0 if we should exit to userspace + * < 0 if we should exit to userspace, where the return value indicates + * an error + */ +static int check_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) - vcpu_req_sleep(vcpu); + kvm_vcpu_sleep(vcpu); if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) kvm_reset_vcpu(vcpu); @@ -675,7 +736,12 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu)) kvm_pmu_handle_pmcr(vcpu, __vcpu_sys_reg(vcpu, PMCR_EL0)); + + if (kvm_check_request(KVM_REQ_SUSPEND, vcpu)) + return kvm_vcpu_suspend(vcpu); } + + return 1; } static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu) @@ -791,7 +857,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (!ret) ret = 1; - check_vcpu_requests(vcpu); + if (ret > 0) + ret = check_vcpu_requests(vcpu); /* * Preparing the interrupts to be injected also @@ -815,6 +882,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_vgic_flush_hwstate(vcpu); + kvm_pmu_update_vcpu_events(vcpu); + /* * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. @@ -1124,9 +1193,9 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, * Handle the "start in power-off" case. */ if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) - vcpu_power_off(vcpu); + kvm_arm_vcpu_power_off(vcpu); else - vcpu->arch.power_off = false; + vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE; return 0; } @@ -1483,7 +1552,6 @@ static void cpu_prepare_hyp_mode(int cpu) tcr |= (idmap_t0sz & GENMASK(TCR_TxSZ_WIDTH - 1, 0)) << TCR_T0SZ_OFFSET; params->tcr_el2 = tcr; - params->stack_hyp_va = kern_hyp_va(per_cpu(kvm_arm_hyp_stack_page, cpu) + PAGE_SIZE); params->pgd_pa = kvm_mmu_get_httbr(); if (is_protected_kvm_enabled()) params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS; @@ -1761,8 +1829,6 @@ static int init_subsystems(void) kvm_register_perf_callbacks(NULL); - kvm_sys_reg_table_init(); - out: if (err || !is_protected_kvm_enabled()) on_each_cpu(_kvm_arch_hardware_disable, NULL, 1); @@ -1933,14 +1999,46 @@ static int init_hyp_mode(void) * Map the Hyp stack pages */ for_each_possible_cpu(cpu) { + struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu); - err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE, - PAGE_HYP); + unsigned long hyp_addr; + + /* + * Allocate a contiguous HYP private VA range for the stack + * and guard page. The allocation is also aligned based on + * the order of its size. + */ + err = hyp_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr); + if (err) { + kvm_err("Cannot allocate hyp stack guard page\n"); + goto out_err; + } + /* + * Since the stack grows downwards, map the stack to the page + * at the higher address and leave the lower guard page + * unbacked. + * + * Any valid stack address now has the PAGE_SHIFT bit as 1 + * and addresses corresponding to the guard page have the + * PAGE_SHIFT bit as 0 - this is used for overflow detection. + */ + err = __create_hyp_mappings(hyp_addr + PAGE_SIZE, PAGE_SIZE, + __pa(stack_page), PAGE_HYP); if (err) { kvm_err("Cannot map hyp stack\n"); goto out_err; } + + /* + * Save the stack PA in nvhe_init_params. This will be needed + * to recreate the stack mapping in protected nVHE mode. + * __hyp_pa() won't do the right thing there, since the stack + * has been mapped in the flexible private VA space. + */ + params->stack_pa = __pa(stack_page); + + params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE); } for_each_possible_cpu(cpu) { @@ -2089,6 +2187,12 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + err = kvm_sys_reg_table_init(); + if (err) { + kvm_info("Error initializing system register tables"); + return err; + } + in_hyp_mode = is_kernel_in_hyp_mode(); if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) || diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 397fdac75cb1..441edb9c398c 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -82,6 +82,26 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; + + /* + * We don't currently support SME guests but if we leave + * things in streaming mode then when the guest starts running + * FPSIMD or SVE code it may generate SME traps so as a + * special case if we are in streaming mode we force the host + * state to be saved now and exit streaming mode so that we + * don't have to handle any SME traps for valid guest + * operations. Do this for ZA as well for now for simplicity. + */ + if (system_supports_sme()) { + if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) + vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED; + + if (read_sysreg_s(SYS_SVCR_EL0) & + (SYS_SVCR_EL0_SM_MASK | SYS_SVCR_EL0_ZA_MASK)) { + vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; + fpsimd_save_and_flush_cpu_state(); + } + } } /* @@ -109,9 +129,14 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!irqs_disabled()); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { + /* + * Currently we do not support SME guests so SVCR is + * always 0 and we just need a variable to point to. + */ fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs, vcpu->arch.sve_state, - vcpu->arch.sve_max_vl); + vcpu->arch.sve_max_vl, + NULL, 0, &vcpu->arch.svcr); clear_thread_flag(TIF_FOREIGN_FPSTATE); update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu)); @@ -130,6 +155,22 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); + /* + * If we have VHE then the Hyp code will reset CPACR_EL1 to + * CPACR_EL1_DEFAULT and we need to reenable SME. + */ + if (has_vhe() && system_supports_sme()) { + /* Also restore EL0 state seen on entry */ + if (vcpu->arch.flags & KVM_ARM64_HOST_SME_ENABLED) + sysreg_clear_set(CPACR_EL1, 0, + CPACR_EL1_SMEN_EL0EN | + CPACR_EL1_SMEN_EL1EN); + else + sysreg_clear_set(CPACR_EL1, + CPACR_EL1_SMEN_EL0EN, + CPACR_EL1_SMEN_EL1EN); + } + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { if (vcpu_has_sve(vcpu)) { __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 7e15b03fbdf8..8c607199cad1 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -18,7 +18,7 @@ #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/fs.h> -#include <kvm/arm_psci.h> +#include <kvm/arm_hypercalls.h> #include <asm/cputype.h> #include <linux/uaccess.h> #include <asm/fpsimd.h> @@ -756,7 +756,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) switch (reg->id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: return get_core_reg(vcpu, reg); - case KVM_REG_ARM_FW: return kvm_arm_get_fw_reg(vcpu, reg); + case KVM_REG_ARM_FW: + case KVM_REG_ARM_FW_FEAT_BMAP: + return kvm_arm_get_fw_reg(vcpu, reg); case KVM_REG_ARM64_SVE: return get_sve_reg(vcpu, reg); } @@ -774,7 +776,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) switch (reg->id & KVM_REG_ARM_COPROC_MASK) { case KVM_REG_ARM_CORE: return set_core_reg(vcpu, reg); - case KVM_REG_ARM_FW: return kvm_arm_set_fw_reg(vcpu, reg); + case KVM_REG_ARM_FW: + case KVM_REG_ARM_FW_FEAT_BMAP: + return kvm_arm_set_fw_reg(vcpu, reg); case KVM_REG_ARM64_SVE: return set_sve_reg(vcpu, reg); } diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 97fe14aab1a3..2ebebd3efaee 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -80,24 +80,51 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu) * * @vcpu: the vcpu pointer * - * WFE: Yield the CPU and come back to this vcpu when the scheduler + * WFE[T]: Yield the CPU and come back to this vcpu when the scheduler * decides to. * WFI: Simply call kvm_vcpu_halt(), which will halt execution of * world-switches and schedule other host processes until there is an * incoming IRQ or FIQ to the VM. + * WFIT: Same as WFI, with a timed wakeup implemented as a background timer + * + * WF{I,E}T can immediately return if the deadline has already expired. */ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE) { + u64 esr = kvm_vcpu_get_esr(vcpu); + + if (esr & ESR_ELx_WFx_ISS_WFE) { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true); vcpu->stat.wfe_exit_stat++; - kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu)); } else { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false); vcpu->stat.wfi_exit_stat++; - kvm_vcpu_wfi(vcpu); } + if (esr & ESR_ELx_WFx_ISS_WFxT) { + if (esr & ESR_ELx_WFx_ISS_RV) { + u64 val, now; + + now = kvm_arm_timer_get_reg(vcpu, KVM_REG_ARM_TIMER_CNT); + val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); + + if (now >= val) + goto out; + } else { + /* Treat WFxT as WFx if RN is invalid */ + esr &= ~ESR_ELx_WFx_ISS_WFxT; + } + } + + if (esr & ESR_ELx_WFx_ISS_WFE) { + kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu)); + } else { + if (esr & ESR_ELx_WFx_ISS_WFxT) + vcpu->arch.flags |= KVM_ARM64_WFIT; + + kvm_vcpu_wfi(vcpu); + } +out: kvm_incr_pc(vcpu); return 1; @@ -167,6 +194,7 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_CP15_64] = kvm_handle_cp15_64, [ESR_ELx_EC_CP14_MR] = kvm_handle_cp14_32, [ESR_ELx_EC_CP14_LS] = kvm_handle_cp14_load_store, + [ESR_ELx_EC_CP10_ID] = kvm_handle_cp10_id, [ESR_ELx_EC_CP14_64] = kvm_handle_cp14_64, [ESR_ELx_EC_HVC32] = handle_hvc, [ESR_ELx_EC_SMC32] = handle_smc, @@ -295,13 +323,8 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr_in_kimg = __phys_to_kimg(elr_phys); u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr_virt; u64 mode = spsr & PSR_MODE_MASK; + u64 panic_addr = elr_virt + hyp_offset; - /* - * The nVHE hyp symbols are not included by kallsyms to avoid issues - * with aliasing. That means that the symbols cannot be printed with the - * "%pS" format specifier, so fall back to the vmlinux address if - * there's no better option. - */ if (mode != PSR_MODE_EL2t && mode != PSR_MODE_EL2h) { kvm_err("Invalid host exception to nVHE hyp!\n"); } else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 && @@ -321,9 +344,11 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, if (file) kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line); else - kvm_err("nVHE hyp BUG at: %016llx!\n", elr_virt + hyp_offset); + kvm_err("nVHE hyp BUG at: [<%016llx>] %pB!\n", panic_addr, + (void *)panic_addr); } else { - kvm_err("nVHE hyp panic at: %016llx!\n", elr_virt + hyp_offset); + kvm_err("nVHE hyp panic at: [<%016llx>] %pB!\n", panic_addr, + (void *)panic_addr); } /* diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h index 2d08510c6cc1..42d8eb9bfe72 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/mm.h +++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h @@ -19,8 +19,10 @@ int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back); int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot); int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot); int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot); -unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size, - enum kvm_pgtable_prot prot); +int __pkvm_create_private_mapping(phys_addr_t phys, size_t size, + enum kvm_pgtable_prot prot, + unsigned long *haddr); +int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr); static inline void hyp_vmemmap_range(phys_addr_t phys, unsigned long size, unsigned long *start, unsigned long *end) diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index 3d613e721a75..ea6a397b64a6 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -80,7 +80,7 @@ SYM_FUNC_START(__hyp_do_panic) mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ PSR_MODE_EL1h) msr spsr_el2, lr - ldr lr, =nvhe_hyp_panic_handler + adr_l lr, nvhe_hyp_panic_handler hyp_kimg_va lr, x6 msr elr_el2, lr @@ -125,13 +125,11 @@ alternative_else_nop_endif add sp, sp, #16 /* * Compute the idmap address of __kvm_handle_stub_hvc and - * jump there. Since we use kimage_voffset, do not use the - * HYP VA for __kvm_handle_stub_hvc, but the kernel VA instead - * (by loading it from the constant pool). + * jump there. * * Preserve x0-x4, which may contain stub parameters. */ - ldr x5, =__kvm_handle_stub_hvc + adr_l x5, __kvm_handle_stub_hvc hyp_pa x5, x6 br x5 SYM_FUNC_END(__host_hvc) @@ -153,6 +151,18 @@ SYM_FUNC_END(__host_hvc) .macro invalid_host_el2_vect .align 7 + + /* + * Test whether the SP has overflowed, without corrupting a GPR. + * nVHE hypervisor stacks are aligned so that the PAGE_SHIFT bit + * of SP should always be 1. + */ + add sp, sp, x0 // sp' = sp + x0 + sub x0, sp, x0 // x0' = sp' - x0 = (sp + x0) - x0 = sp + tbz x0, #PAGE_SHIFT, .L__hyp_sp_overflow\@ + sub x0, sp, x0 // x0'' = sp' - x0' = (sp + x0) - sp = x0 + sub sp, sp, x0 // sp'' = sp' - x0 = (sp + x0) - x0 = sp + /* If a guest is loaded, panic out of it. */ stp x0, x1, [sp, #-16]! get_loaded_vcpu x0, x1 @@ -165,6 +175,18 @@ SYM_FUNC_END(__host_hvc) * been partially clobbered by __host_enter. */ b hyp_panic + +.L__hyp_sp_overflow\@: + /* + * Reset SP to the top of the stack, to allow handling the hyp_panic. + * This corrupts the stack but is ok, since we won't be attempting + * any unwinding here. + */ + ldr_this_cpu x0, kvm_init_params + NVHE_INIT_STACK_HYP_VA, x1 + mov sp, x0 + + b hyp_panic_bad_stack + ASM_BUG() .endm .macro invalid_host_el1_vect @@ -198,15 +220,15 @@ SYM_CODE_START(__kvm_hyp_host_vector) invalid_host_el2_vect // FIQ EL2h invalid_host_el2_vect // Error EL2h - host_el1_sync_vect // Synchronous 64-bit EL1 - invalid_host_el1_vect // IRQ 64-bit EL1 - invalid_host_el1_vect // FIQ 64-bit EL1 - invalid_host_el1_vect // Error 64-bit EL1 + host_el1_sync_vect // Synchronous 64-bit EL1/EL0 + invalid_host_el1_vect // IRQ 64-bit EL1/EL0 + invalid_host_el1_vect // FIQ 64-bit EL1/EL0 + invalid_host_el1_vect // Error 64-bit EL1/EL0 - invalid_host_el1_vect // Synchronous 32-bit EL1 - invalid_host_el1_vect // IRQ 32-bit EL1 - invalid_host_el1_vect // FIQ 32-bit EL1 - invalid_host_el1_vect // Error 32-bit EL1 + host_el1_sync_vect // Synchronous 32-bit EL1/EL0 + invalid_host_el1_vect // IRQ 32-bit EL1/EL0 + invalid_host_el1_vect // FIQ 32-bit EL1/EL0 + invalid_host_el1_vect // Error 32-bit EL1/EL0 SYM_CODE_END(__kvm_hyp_host_vector) /* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 5e2197db0d32..3cea4b6ac23e 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -160,7 +160,23 @@ static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ct DECLARE_REG(size_t, size, host_ctxt, 2); DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3); - cpu_reg(host_ctxt, 1) = __pkvm_create_private_mapping(phys, size, prot); + /* + * __pkvm_create_private_mapping() populates a pointer with the + * hypervisor start address of the allocation. + * + * However, handle___pkvm_create_private_mapping() hypercall crosses the + * EL1/EL2 boundary so the pointer would not be valid in this context. + * + * Instead pass the allocation address as the return value (or return + * ERR_PTR() on failure). + */ + unsigned long haddr; + int err = __pkvm_create_private_mapping(phys, size, prot, &haddr); + + if (err) + haddr = (unsigned long)ERR_PTR(err); + + cpu_reg(host_ctxt, 1) = haddr; } static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt) diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index cdbe8e246418..96193cb31a39 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -37,36 +37,60 @@ static int __pkvm_create_mappings(unsigned long start, unsigned long size, return err; } -unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size, - enum kvm_pgtable_prot prot) +/** + * pkvm_alloc_private_va_range - Allocates a private VA range. + * @size: The size of the VA range to reserve. + * @haddr: The hypervisor virtual start address of the allocation. + * + * The private virtual address (VA) range is allocated above __io_map_base + * and aligned based on the order of @size. + * + * Return: 0 on success or negative error code on failure. + */ +int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr) { - unsigned long addr; - int err; + unsigned long base, addr; + int ret = 0; hyp_spin_lock(&pkvm_pgd_lock); - size = PAGE_ALIGN(size + offset_in_page(phys)); - addr = __io_map_base; - __io_map_base += size; + /* Align the allocation based on the order of its size */ + addr = ALIGN(__io_map_base, PAGE_SIZE << get_order(size)); - /* Are we overflowing on the vmemmap ? */ - if (__io_map_base > __hyp_vmemmap) { - __io_map_base -= size; - addr = (unsigned long)ERR_PTR(-ENOMEM); - goto out; - } + /* The allocated size is always a multiple of PAGE_SIZE */ + base = addr + PAGE_ALIGN(size); - err = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, size, phys, prot); - if (err) { - addr = (unsigned long)ERR_PTR(err); - goto out; + /* Are we overflowing on the vmemmap ? */ + if (!addr || base > __hyp_vmemmap) + ret = -ENOMEM; + else { + __io_map_base = base; + *haddr = addr; } - addr = addr + offset_in_page(phys); -out: hyp_spin_unlock(&pkvm_pgd_lock); - return addr; + return ret; +} + +int __pkvm_create_private_mapping(phys_addr_t phys, size_t size, + enum kvm_pgtable_prot prot, + unsigned long *haddr) +{ + unsigned long addr; + int err; + + size = PAGE_ALIGN(size + offset_in_page(phys)); + err = pkvm_alloc_private_va_range(size, &addr); + if (err) + return err; + + err = __pkvm_create_mappings(addr, size, phys, prot); + if (err) + return err; + + *haddr = addr + offset_in_page(phys); + return err; } int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot) @@ -146,7 +170,8 @@ int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot) int hyp_map_vectors(void) { phys_addr_t phys; - void *bp_base; + unsigned long bp_base; + int ret; if (!kvm_system_needs_idmapped_vectors()) { __hyp_bp_vect_base = __bp_harden_hyp_vecs; @@ -154,13 +179,12 @@ int hyp_map_vectors(void) } phys = __hyp_pa(__bp_harden_hyp_vecs); - bp_base = (void *)__pkvm_create_private_mapping(phys, - __BP_HARDEN_HYP_VECS_SZ, - PAGE_HYP_EXEC); - if (IS_ERR_OR_NULL(bp_base)) - return PTR_ERR(bp_base); + ret = __pkvm_create_private_mapping(phys, __BP_HARDEN_HYP_VECS_SZ, + PAGE_HYP_EXEC, &bp_base); + if (ret) + return ret; - __hyp_bp_vect_base = bp_base; + __hyp_bp_vect_base = (void *)bp_base; return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 27af337f9fea..e8d4ea2fcfa0 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -99,17 +99,42 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, return ret; for (i = 0; i < hyp_nr_cpus; i++) { + struct kvm_nvhe_init_params *params = per_cpu_ptr(&kvm_init_params, i); + unsigned long hyp_addr; + start = (void *)kern_hyp_va(per_cpu_base[i]); end = start + PAGE_ALIGN(hyp_percpu_size); ret = pkvm_create_mappings(start, end, PAGE_HYP); if (ret) return ret; - end = (void *)per_cpu_ptr(&kvm_init_params, i)->stack_hyp_va; - start = end - PAGE_SIZE; - ret = pkvm_create_mappings(start, end, PAGE_HYP); + /* + * Allocate a contiguous HYP private VA range for the stack + * and guard page. The allocation is also aligned based on + * the order of its size. + */ + ret = pkvm_alloc_private_va_range(PAGE_SIZE * 2, &hyp_addr); + if (ret) + return ret; + + /* + * Since the stack grows downwards, map the stack to the page + * at the higher address and leave the lower guard page + * unbacked. + * + * Any valid stack address now has the PAGE_SHIFT bit as 1 + * and addresses corresponding to the guard page have the + * PAGE_SHIFT bit as 0 - this is used for overflow detection. + */ + hyp_spin_lock(&pkvm_pgd_lock); + ret = kvm_pgtable_hyp_map(&pkvm_pgtable, hyp_addr + PAGE_SIZE, + PAGE_SIZE, params->stack_pa, PAGE_HYP); + hyp_spin_unlock(&pkvm_pgd_lock); if (ret) return ret; + + /* Update stack_hyp_va to end of the stack's private VA range */ + params->stack_hyp_va = hyp_addr + (2 * PAGE_SIZE); } /* diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6410d21d8695..6db801db8f27 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -47,10 +47,24 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val |= CPTR_EL2_TFP | CPTR_EL2_TZ; __activate_traps_fpsimd32(vcpu); } + if (cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; write_sysreg(val, cptr_el2); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); + if (cpus_have_final_cap(ARM64_SME)) { + val = read_sysreg_s(SYS_HFGRTR_EL2); + val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK); + write_sysreg_s(val, SYS_HFGRTR_EL2); + + val = read_sysreg_s(SYS_HFGWTR_EL2); + val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK); + write_sysreg_s(val, SYS_HFGWTR_EL2); + } + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; @@ -94,9 +108,25 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); + if (cpus_have_final_cap(ARM64_SME)) { + u64 val; + + val = read_sysreg_s(SYS_HFGRTR_EL2); + val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK; + write_sysreg_s(val, SYS_HFGRTR_EL2); + + val = read_sysreg_s(SYS_HFGWTR_EL2); + val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | + HFGxTR_EL2_nSMPRI_EL1_MASK; + write_sysreg_s(val, SYS_HFGWTR_EL2); + } + cptr = CPTR_EL2_DEFAULT; if (vcpu_has_sve(vcpu) && (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)) cptr |= CPTR_EL2_TZ; + if (cpus_have_final_cap(ARM64_SME)) + cptr &= ~CPTR_EL2_TSM; write_sysreg(cptr, cptr_el2); write_sysreg(__kvm_hyp_host_vector, vbar_el2); @@ -120,16 +150,13 @@ static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) } } -/** +/* * Disable host events, enable guest events */ -static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt) +#ifdef CONFIG_HW_PERF_EVENTS +static bool __pmu_switch_to_guest(struct kvm_vcpu *vcpu) { - struct kvm_host_data *host; - struct kvm_pmu_events *pmu; - - host = container_of(host_ctxt, struct kvm_host_data, host_ctxt); - pmu = &host->pmu_events; + struct kvm_pmu_events *pmu = &vcpu->arch.pmu.events; if (pmu->events_host) write_sysreg(pmu->events_host, pmcntenclr_el0); @@ -140,16 +167,12 @@ static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt) return (pmu->events_host || pmu->events_guest); } -/** +/* * Disable guest events, enable host events */ -static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) +static void __pmu_switch_to_host(struct kvm_vcpu *vcpu) { - struct kvm_host_data *host; - struct kvm_pmu_events *pmu; - - host = container_of(host_ctxt, struct kvm_host_data, host_ctxt); - pmu = &host->pmu_events; + struct kvm_pmu_events *pmu = &vcpu->arch.pmu.events; if (pmu->events_guest) write_sysreg(pmu->events_guest, pmcntenclr_el0); @@ -157,8 +180,12 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) if (pmu->events_host) write_sysreg(pmu->events_host, pmcntenset_el0); } +#else +#define __pmu_switch_to_guest(v) ({ false; }) +#define __pmu_switch_to_host(v) do {} while (0) +#endif -/** +/* * Handler for protected VM MSR, MRS or System instruction execution in AArch64. * * Returns true if the hypervisor has handled the exit, and control should go @@ -175,23 +202,6 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_handle_pvm_sysreg(vcpu, exit_code)); } -/** - * Handler for protected floating-point and Advanced SIMD accesses. - * - * Returns true if the hypervisor has handled the exit, and control should go - * back to the guest, or false if it hasn't. - */ -static bool kvm_handle_pvm_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) -{ - /* Linux guests assume support for floating-point and Advanced SIMD. */ - BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP), - PVM_ID_AA64PFR0_ALLOW)); - BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD), - PVM_ID_AA64PFR0_ALLOW)); - - return kvm_hyp_handle_fpsimd(vcpu, exit_code); -} - static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, @@ -207,7 +217,7 @@ static const exit_handler_fn pvm_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_SYS64] = kvm_handle_pvm_sys64, [ESR_ELx_EC_SVE] = kvm_handle_pvm_restricted, - [ESR_ELx_EC_FP_ASIMD] = kvm_handle_pvm_fpsimd, + [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd, [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, @@ -274,7 +284,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) host_ctxt->__hyp_running_vcpu = vcpu; guest_ctxt = &vcpu->arch.ctxt; - pmu_switch_needed = __pmu_switch_to_guest(host_ctxt); + pmu_switch_needed = __pmu_switch_to_guest(vcpu); __sysreg_save_state_nvhe(host_ctxt); /* @@ -336,7 +346,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) __debug_restore_host_buffers_nvhe(vcpu); if (pmu_switch_needed) - __pmu_switch_to_host(host_ctxt); + __pmu_switch_to_host(vcpu); /* Returning to host will clear PSR.I, remask PMR if needed */ if (system_uses_irq_prio_masking()) @@ -347,7 +357,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) return exit_code; } -void __noreturn hyp_panic(void) +asmlinkage void __noreturn hyp_panic(void) { u64 spsr = read_sysreg_el2(SYS_SPSR); u64 elr = read_sysreg_el2(SYS_ELR); @@ -369,6 +379,11 @@ void __noreturn hyp_panic(void) unreachable(); } +asmlinkage void __noreturn hyp_panic_bad_stack(void) +{ + hyp_panic(); +} + asmlinkage void kvm_unexpected_el2_exception(void) { return __kvm_unexpected_el2_exception(); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 33f5181af330..3f5d7bd171c5 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -90,9 +90,6 @@ static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) u64 set_mask = 0; u64 allow_mask = PVM_ID_AA64PFR0_ALLOW; - if (!vcpu_has_sve(vcpu)) - allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_SVE); - set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val, PVM_ID_AA64PFR0_RESTRICT_UNSIGNED); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 262dfe03134d..969f20daf97a 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -41,7 +41,8 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; - val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN); + val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN | + CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN); /* * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to @@ -62,6 +63,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); } + if (cpus_have_final_cap(ARM64_SME)) + write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2, + sctlr_el2); + write_sysreg(val, cpacr_el1); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); @@ -83,6 +88,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); + if (cpus_have_final_cap(ARM64_SME)) + write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2, + sctlr_el2); + write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); if (!arm64_kernel_unmapped_at_el0()) diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 202b8c455724..c9f401fa01a9 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -9,6 +9,13 @@ #include <kvm/arm_hypercalls.h> #include <kvm/arm_psci.h> +#define KVM_ARM_SMCCC_STD_FEATURES \ + GENMASK(KVM_REG_ARM_STD_BMAP_BIT_COUNT - 1, 0) +#define KVM_ARM_SMCCC_STD_HYP_FEATURES \ + GENMASK(KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT - 1, 0) +#define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES \ + GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT - 1, 0) + static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) { struct system_time_snapshot systime_snapshot; @@ -58,13 +65,73 @@ static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) val[3] = lower_32_bits(cycles); } +static bool kvm_hvc_call_default_allowed(u32 func_id) +{ + switch (func_id) { + /* + * List of function-ids that are not gated with the bitmapped + * feature firmware registers, and are to be allowed for + * servicing the call by default. + */ + case ARM_SMCCC_VERSION_FUNC_ID: + case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: + return true; + default: + /* PSCI 0.2 and up is in the 0:0x1f range */ + if (ARM_SMCCC_OWNER_NUM(func_id) == ARM_SMCCC_OWNER_STANDARD && + ARM_SMCCC_FUNC_NUM(func_id) <= 0x1f) + return true; + + /* + * KVM's PSCI 0.1 doesn't comply with SMCCC, and has + * its own function-id base and range + */ + if (func_id >= KVM_PSCI_FN(0) && func_id <= KVM_PSCI_FN(3)) + return true; + + return false; + } +} + +static bool kvm_hvc_call_allowed(struct kvm_vcpu *vcpu, u32 func_id) +{ + struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; + + switch (func_id) { + case ARM_SMCCC_TRNG_VERSION: + case ARM_SMCCC_TRNG_FEATURES: + case ARM_SMCCC_TRNG_GET_UUID: + case ARM_SMCCC_TRNG_RND32: + case ARM_SMCCC_TRNG_RND64: + return test_bit(KVM_REG_ARM_STD_BIT_TRNG_V1_0, + &smccc_feat->std_bmap); + case ARM_SMCCC_HV_PV_TIME_FEATURES: + case ARM_SMCCC_HV_PV_TIME_ST: + return test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, + &smccc_feat->std_hyp_bmap); + case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: + case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: + return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT, + &smccc_feat->vendor_hyp_bmap); + case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: + return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_PTP, + &smccc_feat->vendor_hyp_bmap); + default: + return kvm_hvc_call_default_allowed(func_id); + } +} + int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) { + struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; u32 func_id = smccc_get_function(vcpu); u64 val[4] = {SMCCC_RET_NOT_SUPPORTED}; u32 feature; gpa_t gpa; + if (!kvm_hvc_call_allowed(vcpu, func_id)) + goto out; + switch (func_id) { case ARM_SMCCC_VERSION_FUNC_ID: val[0] = ARM_SMCCC_VERSION_1_1; @@ -120,7 +187,9 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) } break; case ARM_SMCCC_HV_PV_TIME_FEATURES: - val[0] = SMCCC_RET_SUCCESS; + if (test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, + &smccc_feat->std_hyp_bmap)) + val[0] = SMCCC_RET_SUCCESS; break; } break; @@ -139,8 +208,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) val[3] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3; break; case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: - val[0] = BIT(ARM_SMCCC_KVM_FUNC_FEATURES); - val[0] |= BIT(ARM_SMCCC_KVM_FUNC_PTP); + val[0] = smccc_feat->vendor_hyp_bmap; break; case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: kvm_ptp_get_time(vcpu, val); @@ -155,6 +223,259 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) return kvm_psci_call(vcpu); } +out: smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]); return 1; } + +static const u64 kvm_arm_fw_reg_ids[] = { + KVM_REG_ARM_PSCI_VERSION, + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, + KVM_REG_ARM_STD_BMAP, + KVM_REG_ARM_STD_HYP_BMAP, + KVM_REG_ARM_VENDOR_HYP_BMAP, +}; + +void kvm_arm_init_hypercalls(struct kvm *kvm) +{ + struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; + + smccc_feat->std_bmap = KVM_ARM_SMCCC_STD_FEATURES; + smccc_feat->std_hyp_bmap = KVM_ARM_SMCCC_STD_HYP_FEATURES; + smccc_feat->vendor_hyp_bmap = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; +} + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) +{ + return ARRAY_SIZE(kvm_arm_fw_reg_ids); +} + +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(kvm_arm_fw_reg_ids); i++) { + if (put_user(kvm_arm_fw_reg_ids[i], uindices++)) + return -EFAULT; + } + + return 0; +} + +#define KVM_REG_FEATURE_LEVEL_MASK GENMASK(3, 0) + +/* + * Convert the workaround level into an easy-to-compare number, where higher + * values mean better protection. + */ +static int get_kernel_wa_level(u64 regid) +{ + switch (regid) { + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + switch (arm64_get_spectre_v2_state()) { + case SPECTRE_VULNERABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; + case SPECTRE_MITIGATED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL; + case SPECTRE_UNAFFECTED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED; + } + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + switch (arm64_get_spectre_v4_state()) { + case SPECTRE_MITIGATED: + /* + * As for the hypercall discovery, we pretend we + * don't have any FW mitigation if SSBS is there at + * all times. + */ + if (cpus_have_final_cap(ARM64_SSBS)) + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + fallthrough; + case SPECTRE_UNAFFECTED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; + case SPECTRE_VULNERABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + } + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: + switch (arm64_get_spectre_bhb_state()) { + case SPECTRE_VULNERABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; + case SPECTRE_MITIGATED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; + case SPECTRE_UNAFFECTED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; + } + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; + } + + return -EINVAL; +} + +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + + switch (reg->id) { + case KVM_REG_ARM_PSCI_VERSION: + val = kvm_psci_version(vcpu); + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: + val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; + break; + case KVM_REG_ARM_STD_BMAP: + val = READ_ONCE(smccc_feat->std_bmap); + break; + case KVM_REG_ARM_STD_HYP_BMAP: + val = READ_ONCE(smccc_feat->std_hyp_bmap); + break; + case KVM_REG_ARM_VENDOR_HYP_BMAP: + val = READ_ONCE(smccc_feat->vendor_hyp_bmap); + break; + default: + return -ENOENT; + } + + if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) +{ + int ret = 0; + struct kvm *kvm = vcpu->kvm; + struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; + unsigned long *fw_reg_bmap, fw_reg_features; + + switch (reg_id) { + case KVM_REG_ARM_STD_BMAP: + fw_reg_bmap = &smccc_feat->std_bmap; + fw_reg_features = KVM_ARM_SMCCC_STD_FEATURES; + break; + case KVM_REG_ARM_STD_HYP_BMAP: + fw_reg_bmap = &smccc_feat->std_hyp_bmap; + fw_reg_features = KVM_ARM_SMCCC_STD_HYP_FEATURES; + break; + case KVM_REG_ARM_VENDOR_HYP_BMAP: + fw_reg_bmap = &smccc_feat->vendor_hyp_bmap; + fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; + break; + default: + return -ENOENT; + } + + /* Check for unsupported bit */ + if (val & ~fw_reg_features) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags) && + val != *fw_reg_bmap) { + ret = -EBUSY; + goto out; + } + + WRITE_ONCE(*fw_reg_bmap, val); +out: + mutex_unlock(&kvm->lock); + return ret; +} + +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + int wa_level; + + if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + switch (reg->id) { + case KVM_REG_ARM_PSCI_VERSION: + { + bool wants_02; + + wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features); + + switch (val) { + case KVM_ARM_PSCI_0_1: + if (wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + case KVM_ARM_PSCI_0_2: + case KVM_ARM_PSCI_1_0: + case KVM_ARM_PSCI_1_1: + if (!wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + } + break; + } + + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: + if (val & ~KVM_REG_FEATURE_LEVEL_MASK) + return -EINVAL; + + if (get_kernel_wa_level(reg->id) < val) + return -EINVAL; + + return 0; + + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + if (val & ~(KVM_REG_FEATURE_LEVEL_MASK | + KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED)) + return -EINVAL; + + /* The enabled bit must not be set unless the level is AVAIL. */ + if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) && + (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL) + return -EINVAL; + + /* + * Map all the possible incoming states to the only two we + * really want to deal with. + */ + switch (val & KVM_REG_FEATURE_LEVEL_MASK) { + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: + wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: + wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; + break; + default: + return -EINVAL; + } + + /* + * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the + * other way around. + */ + if (get_kernel_wa_level(reg->id) < wa_level) + return -EINVAL; + + return 0; + case KVM_REG_ARM_STD_BMAP: + case KVM_REG_ARM_STD_HYP_BMAP: + case KVM_REG_ARM_VENDOR_HYP_BMAP: + return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val); + default: + return -ENOENT; + } + + return -EINVAL; +} diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index b47df73e98d7..ba20405d2dc2 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -145,6 +145,34 @@ void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr) inject_abt64(vcpu, true, addr); } +void kvm_inject_size_fault(struct kvm_vcpu *vcpu) +{ + unsigned long addr, esr; + + addr = kvm_vcpu_get_fault_ipa(vcpu); + addr |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + + if (kvm_vcpu_trap_is_iabt(vcpu)) + kvm_inject_pabt(vcpu, addr); + else + kvm_inject_dabt(vcpu, addr); + + /* + * If AArch64 or LPAE, set FSC to 0 to indicate an Address + * Size Fault at level 0, as if exceeding PARange. + * + * Non-LPAE guests will only get the external abort, as there + * is no way to to describe the ASF. + */ + if (vcpu_el1_is_32bit(vcpu) && + !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) + return; + + esr = vcpu_read_sys_reg(vcpu, ESR_EL1); + esr &= ~GENMASK_ULL(5, 0); + vcpu_write_sys_reg(vcpu, esr, ESR_EL1); +} + /** * kvm_inject_undefined - inject an undefined instruction into the guest * @vcpu: The vCPU in which to inject the exception diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 53ae2c0640bc..f5651a05b6a8 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -258,8 +258,8 @@ static bool kvm_host_owns_hyp_mappings(void) return true; } -static int __create_hyp_mappings(unsigned long start, unsigned long size, - unsigned long phys, enum kvm_pgtable_prot prot) +int __create_hyp_mappings(unsigned long start, unsigned long size, + unsigned long phys, enum kvm_pgtable_prot prot) { int err; @@ -457,23 +457,22 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot) return 0; } -static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, - unsigned long *haddr, - enum kvm_pgtable_prot prot) + +/** + * hyp_alloc_private_va_range - Allocates a private VA range. + * @size: The size of the VA range to reserve. + * @haddr: The hypervisor virtual start address of the allocation. + * + * The private virtual address (VA) range is allocated below io_map_base + * and aligned based on the order of @size. + * + * Return: 0 on success or negative error code on failure. + */ +int hyp_alloc_private_va_range(size_t size, unsigned long *haddr) { unsigned long base; int ret = 0; - if (!kvm_host_owns_hyp_mappings()) { - base = kvm_call_hyp_nvhe(__pkvm_create_private_mapping, - phys_addr, size, prot); - if (IS_ERR_OR_NULL((void *)base)) - return PTR_ERR((void *)base); - *haddr = base; - - return 0; - } - mutex_lock(&kvm_hyp_pgd_mutex); /* @@ -484,8 +483,10 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, * * The allocated size is always a multiple of PAGE_SIZE. */ - size = PAGE_ALIGN(size + offset_in_page(phys_addr)); - base = io_map_base - size; + base = io_map_base - PAGE_ALIGN(size); + + /* Align the allocation based on the order of its size */ + base = ALIGN_DOWN(base, PAGE_SIZE << get_order(size)); /* * Verify that BIT(VA_BITS - 1) hasn't been flipped by @@ -495,19 +496,40 @@ static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, if ((base ^ io_map_base) & BIT(VA_BITS - 1)) ret = -ENOMEM; else - io_map_base = base; + *haddr = io_map_base = base; mutex_unlock(&kvm_hyp_pgd_mutex); + return ret; +} + +static int __create_hyp_private_mapping(phys_addr_t phys_addr, size_t size, + unsigned long *haddr, + enum kvm_pgtable_prot prot) +{ + unsigned long addr; + int ret = 0; + + if (!kvm_host_owns_hyp_mappings()) { + addr = kvm_call_hyp_nvhe(__pkvm_create_private_mapping, + phys_addr, size, prot); + if (IS_ERR_VALUE(addr)) + return addr; + *haddr = addr; + + return 0; + } + + size = PAGE_ALIGN(size + offset_in_page(phys_addr)); + ret = hyp_alloc_private_va_range(size, &addr); if (ret) - goto out; + return ret; - ret = __create_hyp_mappings(base, size, phys_addr, prot); + ret = __create_hyp_mappings(addr, size, phys_addr, prot); if (ret) - goto out; + return ret; - *haddr = base + offset_in_page(phys_addr); -out: + *haddr = addr + offset_in_page(phys_addr); return ret; } @@ -1337,6 +1359,25 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); + if (fault_status == FSC_FAULT) { + /* Beyond sanitised PARange (which is the IPA limit) */ + if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { + kvm_inject_size_fault(vcpu); + return 1; + } + + /* Falls between the IPA range and the PARange? */ + if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) { + fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0); + + if (is_iabt) + kvm_inject_pabt(vcpu, fault_ipa); + else + kvm_inject_dabt(vcpu, fault_ipa); + return 1; + } + } + /* Synchronous External Abort? */ if (kvm_vcpu_abt_issea(vcpu)) { /* diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 78fdc443adc7..11c43bed5f97 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -177,6 +177,9 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc = &pmu->pmc[select_idx]; + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + counter = kvm_pmu_get_pair_counter_value(vcpu, pmc); if (kvm_pmu_pmc_is_chained(pmc) && @@ -198,6 +201,9 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { u64 reg; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + reg = (select_idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx; __vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx); @@ -322,6 +328,9 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val) return; @@ -357,7 +366,7 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; struct kvm_pmc *pmc; - if (!val) + if (!kvm_vcpu_has_pmu(vcpu) || !val) return; for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) { @@ -527,6 +536,9 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val) struct kvm_pmu *pmu = &vcpu->arch.pmu; int i; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) return; @@ -576,6 +588,9 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) { int i; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + if (val & ARMV8_PMU_PMCR_E) { kvm_pmu_enable_counter_mask(vcpu, __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); @@ -739,6 +754,9 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, { u64 reg, mask; + if (!kvm_vcpu_has_pmu(vcpu)) + return; + mask = ARMV8_PMU_EVTYPE_MASK; mask &= ~ARMV8_PMU_EVTYPE_EVENT; mask |= kvm_pmu_event_mask(vcpu->kvm); @@ -756,8 +774,7 @@ void kvm_host_pmu_init(struct arm_pmu *pmu) { struct arm_pmu_entry *entry; - if (pmu->pmuver == 0 || pmu->pmuver == ID_AA64DFR0_PMUVER_IMP_DEF || - is_protected_kvm_enabled()) + if (pmu->pmuver == 0 || pmu->pmuver == ID_AA64DFR0_PMUVER_IMP_DEF) return; mutex_lock(&arm_pmus_lock); @@ -827,6 +844,9 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) u64 val, mask = 0; int base, i, nr_events; + if (!kvm_vcpu_has_pmu(vcpu)) + return 0; + if (!pmceid1) { val = read_sysreg(pmceid0_el0); base = 0; diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index 03a6c1f4a09a..7887133d15f0 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -5,7 +5,8 @@ */ #include <linux/kvm_host.h> #include <linux/perf_event.h> -#include <asm/kvm_hyp.h> + +static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events); /* * Given the perf event attributes and system type, determine @@ -25,21 +26,26 @@ static bool kvm_pmu_switch_needed(struct perf_event_attr *attr) return (attr->exclude_host != attr->exclude_guest); } +struct kvm_pmu_events *kvm_get_pmu_events(void) +{ + return this_cpu_ptr(&kvm_pmu_events); +} + /* * Add events to track that we may want to switch at guest entry/exit * time. */ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) { - struct kvm_host_data *ctx = this_cpu_ptr_hyp_sym(kvm_host_data); + struct kvm_pmu_events *pmu = kvm_get_pmu_events(); - if (!kvm_arm_support_pmu_v3() || !ctx || !kvm_pmu_switch_needed(attr)) + if (!kvm_arm_support_pmu_v3() || !pmu || !kvm_pmu_switch_needed(attr)) return; if (!attr->exclude_host) - ctx->pmu_events.events_host |= set; + pmu->events_host |= set; if (!attr->exclude_guest) - ctx->pmu_events.events_guest |= set; + pmu->events_guest |= set; } /* @@ -47,13 +53,13 @@ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) */ void kvm_clr_pmu_events(u32 clr) { - struct kvm_host_data *ctx = this_cpu_ptr_hyp_sym(kvm_host_data); + struct kvm_pmu_events *pmu = kvm_get_pmu_events(); - if (!kvm_arm_support_pmu_v3() || !ctx) + if (!kvm_arm_support_pmu_v3() || !pmu) return; - ctx->pmu_events.events_host &= ~clr; - ctx->pmu_events.events_guest &= ~clr; + pmu->events_host &= ~clr; + pmu->events_guest &= ~clr; } #define PMEVTYPER_READ_CASE(idx) \ @@ -169,16 +175,16 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events) */ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) { - struct kvm_host_data *host; + struct kvm_pmu_events *pmu; u32 events_guest, events_host; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return; preempt_disable(); - host = this_cpu_ptr_hyp_sym(kvm_host_data); - events_guest = host->pmu_events.events_guest; - events_host = host->pmu_events.events_host; + pmu = kvm_get_pmu_events(); + events_guest = pmu->events_guest; + events_host = pmu->events_host; kvm_vcpu_pmu_enable_el0(events_guest); kvm_vcpu_pmu_disable_el0(events_host); @@ -190,15 +196,15 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) */ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) { - struct kvm_host_data *host; + struct kvm_pmu_events *pmu; u32 events_guest, events_host; if (!kvm_arm_support_pmu_v3() || !has_vhe()) return; - host = this_cpu_ptr_hyp_sym(kvm_host_data); - events_guest = host->pmu_events.events_guest; - events_host = host->pmu_events.events_host; + pmu = kvm_get_pmu_events(); + events_guest = pmu->events_guest; + events_host = pmu->events_host; kvm_vcpu_pmu_enable_el0(events_host); kvm_vcpu_pmu_disable_el0(events_guest); diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 708d80e8e60d..7fbc4c1b9df0 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -51,13 +51,6 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) return PSCI_RET_SUCCESS; } -static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu) -{ - vcpu->arch.power_off = true; - kvm_make_request(KVM_REQ_SLEEP, vcpu); - kvm_vcpu_kick(vcpu); -} - static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu, unsigned long affinity) { @@ -83,7 +76,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) */ if (!vcpu) return PSCI_RET_INVALID_PARAMS; - if (!vcpu->arch.power_off) { + if (!kvm_arm_vcpu_stopped(vcpu)) { if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1) return PSCI_RET_ALREADY_ON; else @@ -107,12 +100,12 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); /* - * Make sure the reset request is observed if the change to - * power_off is observed. + * Make sure the reset request is observed if the RUNNABLE mp_state is + * observed. */ smp_wmb(); - vcpu->arch.power_off = false; + vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE; kvm_vcpu_wake_up(vcpu); return PSCI_RET_SUCCESS; @@ -150,7 +143,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) mpidr = kvm_vcpu_get_mpidr_aff(tmp); if ((mpidr & target_affinity_mask) == target_affinity) { matching_cpus++; - if (!tmp->arch.power_off) + if (!kvm_arm_vcpu_stopped(tmp)) return PSCI_0_2_AFFINITY_LEVEL_ON; } } @@ -176,7 +169,7 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags) * re-initialized. */ kvm_for_each_vcpu(i, tmp, vcpu->kvm) - tmp->arch.power_off = true; + tmp->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); @@ -202,6 +195,15 @@ static void kvm_psci_system_reset2(struct kvm_vcpu *vcpu) KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2); } +static void kvm_psci_system_suspend(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + + memset(&run->system_event, 0, sizeof(vcpu->run->system_event)); + run->system_event.type = KVM_SYSTEM_EVENT_SUSPEND; + run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) { int i; @@ -245,7 +247,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) val = kvm_psci_vcpu_suspend(vcpu); break; case PSCI_0_2_FN_CPU_OFF: - kvm_psci_vcpu_off(vcpu); + kvm_arm_vcpu_power_off(vcpu); val = PSCI_RET_SUCCESS; break; case PSCI_0_2_FN_CPU_ON: @@ -305,9 +307,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) { + unsigned long val = PSCI_RET_NOT_SUPPORTED; u32 psci_fn = smccc_get_function(vcpu); + struct kvm *kvm = vcpu->kvm; u32 arg; - unsigned long val; int ret = 1; switch(psci_fn) { @@ -320,6 +323,8 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) if (val) break; + val = PSCI_RET_NOT_SUPPORTED; + switch(arg) { case PSCI_0_2_FN_PSCI_VERSION: case PSCI_0_2_FN_CPU_SUSPEND: @@ -336,18 +341,32 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) case ARM_SMCCC_VERSION_FUNC_ID: val = 0; break; + case PSCI_1_0_FN_SYSTEM_SUSPEND: + case PSCI_1_0_FN64_SYSTEM_SUSPEND: + if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) + val = 0; + break; case PSCI_1_1_FN_SYSTEM_RESET2: case PSCI_1_1_FN64_SYSTEM_RESET2: - if (minor >= 1) { + if (minor >= 1) val = 0; - break; - } - fallthrough; - default: - val = PSCI_RET_NOT_SUPPORTED; break; } break; + case PSCI_1_0_FN_SYSTEM_SUSPEND: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; + case PSCI_1_0_FN64_SYSTEM_SUSPEND: + /* + * Return directly to userspace without changing the vCPU's + * registers. Userspace depends on reading the SMCCC parameters + * to implement SYSTEM_SUSPEND. + */ + if (test_bit(KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED, &kvm->arch.flags)) { + kvm_psci_system_suspend(vcpu); + return 0; + } + break; case PSCI_1_1_FN_SYSTEM_RESET2: kvm_psci_narrow_to_32bit(vcpu); fallthrough; @@ -365,7 +384,7 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) val = PSCI_RET_INVALID_PARAMS; break; } - fallthrough; + break; default: return kvm_psci_0_2_call(vcpu); } @@ -382,7 +401,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) switch (psci_fn) { case KVM_PSCI_FN_CPU_OFF: - kvm_psci_vcpu_off(vcpu); + kvm_arm_vcpu_power_off(vcpu); val = PSCI_RET_SUCCESS; break; case KVM_PSCI_FN_CPU_ON: @@ -437,186 +456,3 @@ int kvm_psci_call(struct kvm_vcpu *vcpu) return -EINVAL; } } - -int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) -{ - return 4; /* PSCI version and three workaround registers */ -} - -int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices++)) - return -EFAULT; - - if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, uindices++)) - return -EFAULT; - - if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++)) - return -EFAULT; - - if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, uindices++)) - return -EFAULT; - - return 0; -} - -#define KVM_REG_FEATURE_LEVEL_WIDTH 4 -#define KVM_REG_FEATURE_LEVEL_MASK (BIT(KVM_REG_FEATURE_LEVEL_WIDTH) - 1) - -/* - * Convert the workaround level into an easy-to-compare number, where higher - * values mean better protection. - */ -static int get_kernel_wa_level(u64 regid) -{ - switch (regid) { - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - switch (arm64_get_spectre_v2_state()) { - case SPECTRE_VULNERABLE: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; - case SPECTRE_MITIGATED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL; - case SPECTRE_UNAFFECTED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED; - } - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - switch (arm64_get_spectre_v4_state()) { - case SPECTRE_MITIGATED: - /* - * As for the hypercall discovery, we pretend we - * don't have any FW mitigation if SSBS is there at - * all times. - */ - if (cpus_have_final_cap(ARM64_SSBS)) - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; - fallthrough; - case SPECTRE_UNAFFECTED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; - case SPECTRE_VULNERABLE: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; - } - break; - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: - switch (arm64_get_spectre_bhb_state()) { - case SPECTRE_VULNERABLE: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; - case SPECTRE_MITIGATED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; - case SPECTRE_UNAFFECTED: - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; - } - return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; - } - - return -EINVAL; -} - -int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - void __user *uaddr = (void __user *)(long)reg->addr; - u64 val; - - switch (reg->id) { - case KVM_REG_ARM_PSCI_VERSION: - val = kvm_psci_version(vcpu); - break; - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: - val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; - break; - default: - return -ENOENT; - } - - if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) - return -EFAULT; - - return 0; -} - -int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) -{ - void __user *uaddr = (void __user *)(long)reg->addr; - u64 val; - int wa_level; - - if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) - return -EFAULT; - - switch (reg->id) { - case KVM_REG_ARM_PSCI_VERSION: - { - bool wants_02; - - wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features); - - switch (val) { - case KVM_ARM_PSCI_0_1: - if (wants_02) - return -EINVAL; - vcpu->kvm->arch.psci_version = val; - return 0; - case KVM_ARM_PSCI_0_2: - case KVM_ARM_PSCI_1_0: - case KVM_ARM_PSCI_1_1: - if (!wants_02) - return -EINVAL; - vcpu->kvm->arch.psci_version = val; - return 0; - } - break; - } - - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: - if (val & ~KVM_REG_FEATURE_LEVEL_MASK) - return -EINVAL; - - if (get_kernel_wa_level(reg->id) < val) - return -EINVAL; - - return 0; - - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: - if (val & ~(KVM_REG_FEATURE_LEVEL_MASK | - KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED)) - return -EINVAL; - - /* The enabled bit must not be set unless the level is AVAIL. */ - if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) && - (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL) - return -EINVAL; - - /* - * Map all the possible incoming states to the only two we - * really want to deal with. - */ - switch (val & KVM_REG_FEATURE_LEVEL_MASK) { - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: - wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; - break; - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: - case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: - wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; - break; - default: - return -EINVAL; - } - - /* - * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the - * other way around. - */ - if (get_kernel_wa_level(reg->id) < wa_level) - return -EINVAL; - - return 0; - default: - return -ENOENT; - } - - return -EINVAL; -} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7b45c040cc27..d77be152cbd5 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1132,6 +1132,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, case SYS_ID_AA64PFR1_EL1: if (!kvm_has_mte(vcpu->kvm)) val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE); + + val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_SME); break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu)) @@ -1144,6 +1146,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, if (!vcpu_has_ptrauth(vcpu)) val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_APA3) | ARM64_FEATURE_MASK(ID_AA64ISAR2_GPA3)); + if (!cpus_have_final_cap(ARM64_HAS_WFXT)) + val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_WFXT); break; case SYS_ID_AA64DFR0_EL1: /* Limit debug to ARMv8.0 */ @@ -1553,7 +1557,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_UNALLOCATED(4,2), ID_UNALLOCATED(4,3), ID_SANITISED(ID_AA64ZFR0_EL1), - ID_UNALLOCATED(4,5), + ID_HIDDEN(ID_AA64SMFR0_EL1), ID_UNALLOCATED(4,6), ID_UNALLOCATED(4,7), @@ -1596,6 +1600,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TRFCR_EL1), undef_access }, + { SYS_DESC(SYS_SMPRI_EL1), undef_access }, + { SYS_DESC(SYS_SMCR_EL1), undef_access }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, { SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 }, { SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 }, @@ -1678,8 +1684,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, { SYS_DESC(SYS_CLIDR_EL1), access_clidr }, + { SYS_DESC(SYS_SMIDR_EL1), undef_access }, { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, + { SYS_DESC(SYS_SVCR_EL0), undef_access }, { PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr, .reg = PMCR_EL0 }, @@ -1719,6 +1727,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, + { SYS_DESC(SYS_TPIDR2_EL0), undef_access }, { SYS_DESC(SYS_SCXTNUM_EL0), undef_access }, @@ -2014,20 +2023,22 @@ static const struct sys_reg_desc cp14_64_regs[] = { { Op1( 0), CRm( 2), .access = trap_raz_wi }, }; +#define CP15_PMU_SYS_REG(_map, _Op1, _CRn, _CRm, _Op2) \ + AA32(_map), \ + Op1(_Op1), CRn(_CRn), CRm(_CRm), Op2(_Op2), \ + .visibility = pmu_visibility + /* Macro to expand the PMEVCNTRn register */ #define PMU_PMEVCNTR(n) \ - /* PMEVCNTRn */ \ - { Op1(0), CRn(0b1110), \ - CRm((0b1000 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)), \ - access_pmu_evcntr } + { CP15_PMU_SYS_REG(DIRECT, 0, 0b1110, \ + (0b1000 | (((n) >> 3) & 0x3)), ((n) & 0x7)), \ + .access = access_pmu_evcntr } /* Macro to expand the PMEVTYPERn register */ #define PMU_PMEVTYPER(n) \ - /* PMEVTYPERn */ \ - { Op1(0), CRn(0b1110), \ - CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)), \ - access_pmu_evtyper } - + { CP15_PMU_SYS_REG(DIRECT, 0, 0b1110, \ + (0b1100 | (((n) >> 3) & 0x3)), ((n) & 0x7)), \ + .access = access_pmu_evtyper } /* * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding, * depending on the way they are accessed (as a 32bit or a 64bit @@ -2067,25 +2078,25 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw }, /* PMU */ - { Op1( 0), CRn( 9), CRm(12), Op2( 0), access_pmcr }, - { Op1( 0), CRn( 9), CRm(12), Op2( 1), access_pmcnten }, - { Op1( 0), CRn( 9), CRm(12), Op2( 2), access_pmcnten }, - { Op1( 0), CRn( 9), CRm(12), Op2( 3), access_pmovs }, - { Op1( 0), CRn( 9), CRm(12), Op2( 4), access_pmswinc }, - { Op1( 0), CRn( 9), CRm(12), Op2( 5), access_pmselr }, - { AA32(LO), Op1( 0), CRn( 9), CRm(12), Op2( 6), access_pmceid }, - { AA32(LO), Op1( 0), CRn( 9), CRm(12), Op2( 7), access_pmceid }, - { Op1( 0), CRn( 9), CRm(13), Op2( 0), access_pmu_evcntr }, - { Op1( 0), CRn( 9), CRm(13), Op2( 1), access_pmu_evtyper }, - { Op1( 0), CRn( 9), CRm(13), Op2( 2), access_pmu_evcntr }, - { Op1( 0), CRn( 9), CRm(14), Op2( 0), access_pmuserenr }, - { Op1( 0), CRn( 9), CRm(14), Op2( 1), access_pminten }, - { Op1( 0), CRn( 9), CRm(14), Op2( 2), access_pminten }, - { Op1( 0), CRn( 9), CRm(14), Op2( 3), access_pmovs }, - { AA32(HI), Op1( 0), CRn( 9), CRm(14), Op2( 4), access_pmceid }, - { AA32(HI), Op1( 0), CRn( 9), CRm(14), Op2( 5), access_pmceid }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 0), .access = access_pmcr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 1), .access = access_pmcnten }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 2), .access = access_pmcnten }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 3), .access = access_pmovs }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 4), .access = access_pmswinc }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 12, 5), .access = access_pmselr }, + { CP15_PMU_SYS_REG(LO, 0, 9, 12, 6), .access = access_pmceid }, + { CP15_PMU_SYS_REG(LO, 0, 9, 12, 7), .access = access_pmceid }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 0), .access = access_pmu_evcntr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 1), .access = access_pmu_evtyper }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 13, 2), .access = access_pmu_evcntr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 0), .access = access_pmuserenr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 1), .access = access_pminten }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 2), .access = access_pminten }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 3), .access = access_pmovs }, + { CP15_PMU_SYS_REG(HI, 0, 9, 14, 4), .access = access_pmceid }, + { CP15_PMU_SYS_REG(HI, 0, 9, 14, 5), .access = access_pmceid }, /* PMMIR */ - { Op1( 0), CRn( 9), CRm(14), Op2( 6), trap_raz_wi }, + { CP15_PMU_SYS_REG(DIRECT, 0, 9, 14, 6), .access = trap_raz_wi }, /* PRRR/MAIR0 */ { AA32(LO), Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, MAIR_EL1 }, @@ -2170,7 +2181,7 @@ static const struct sys_reg_desc cp15_regs[] = { PMU_PMEVTYPER(29), PMU_PMEVTYPER(30), /* PMCCFILTR */ - { Op1(0), CRn(14), CRm(15), Op2(7), access_pmu_evtyper }, + { CP15_PMU_SYS_REG(DIRECT, 0, 14, 15, 7), .access = access_pmu_evtyper }, { Op1(1), CRn( 0), CRm( 0), Op2(0), access_ccsidr }, { Op1(1), CRn( 0), CRm( 0), Op2(1), access_clidr }, @@ -2179,7 +2190,7 @@ static const struct sys_reg_desc cp15_regs[] = { static const struct sys_reg_desc cp15_64_regs[] = { { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 }, - { Op1( 0), CRn( 0), CRm( 9), Op2( 0), access_pmu_evcntr }, + { CP15_PMU_SYS_REG(DIRECT, 0, 0, 9, 0), .access = access_pmu_evcntr }, { Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI1R */ { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR1_EL1 }, { Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */ @@ -2187,25 +2198,24 @@ static const struct sys_reg_desc cp15_64_regs[] = { { SYS_DESC(SYS_AARCH32_CNTP_CVAL), access_arch_timer }, }; -static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n, - bool is_32) +static bool check_sysreg_table(const struct sys_reg_desc *table, unsigned int n, + bool is_32) { unsigned int i; for (i = 0; i < n; i++) { if (!is_32 && table[i].reg && !table[i].reset) { - kvm_err("sys_reg table %p entry %d has lacks reset\n", - table, i); - return 1; + kvm_err("sys_reg table %pS entry %d lacks reset\n", &table[i], i); + return false; } if (i && cmp_sys_reg(&table[i-1], &table[i]) >= 0) { - kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1); - return 1; + kvm_err("sys_reg table %pS entry %d out of order\n", &table[i - 1], i - 1); + return false; } } - return 0; + return true; } int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu) @@ -2246,27 +2256,27 @@ static void perform_access(struct kvm_vcpu *vcpu, * @table: array of trap descriptors * @num: size of the trap descriptor array * - * Return 0 if the access has been handled, and -1 if not. + * Return true if the access has been handled, false if not. */ -static int emulate_cp(struct kvm_vcpu *vcpu, - struct sys_reg_params *params, - const struct sys_reg_desc *table, - size_t num) +static bool emulate_cp(struct kvm_vcpu *vcpu, + struct sys_reg_params *params, + const struct sys_reg_desc *table, + size_t num) { const struct sys_reg_desc *r; if (!table) - return -1; /* Not handled */ + return false; /* Not handled */ r = find_reg(params, table, num); if (r) { perform_access(vcpu, params, r); - return 0; + return true; } /* Not handled */ - return -1; + return false; } static void unhandled_cp_access(struct kvm_vcpu *vcpu, @@ -2304,7 +2314,7 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, size_t nr_global) { struct sys_reg_params params; - u32 esr = kvm_vcpu_get_esr(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); int Rt2 = (esr >> 10) & 0x1f; @@ -2330,7 +2340,7 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, * potential register operation in the case of a read and return * with success. */ - if (!emulate_cp(vcpu, ¶ms, global, nr_global)) { + if (emulate_cp(vcpu, ¶ms, global, nr_global)) { /* Split up the value between registers for the read side */ if (!params.is_write) { vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval)); @@ -2344,34 +2354,144 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, return 1; } +static bool emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params); + +/* + * The CP10 ID registers are architecturally mapped to AArch64 feature + * registers. Abuse that fact so we can rely on the AArch64 handler for accesses + * from AArch32. + */ +static bool kvm_esr_cp10_id_to_sys64(u64 esr, struct sys_reg_params *params) +{ + u8 reg_id = (esr >> 10) & 0xf; + bool valid; + + params->is_write = ((esr & 1) == 0); + params->Op0 = 3; + params->Op1 = 0; + params->CRn = 0; + params->CRm = 3; + + /* CP10 ID registers are read-only */ + valid = !params->is_write; + + switch (reg_id) { + /* MVFR0 */ + case 0b0111: + params->Op2 = 0; + break; + /* MVFR1 */ + case 0b0110: + params->Op2 = 1; + break; + /* MVFR2 */ + case 0b0101: + params->Op2 = 2; + break; + default: + valid = false; + } + + if (valid) + return true; + + kvm_pr_unimpl("Unhandled cp10 register %s: %u\n", + params->is_write ? "write" : "read", reg_id); + return false; +} + +/** + * kvm_handle_cp10_id() - Handles a VMRS trap on guest access to a 'Media and + * VFP Register' from AArch32. + * @vcpu: The vCPU pointer + * + * MVFR{0-2} are architecturally mapped to the AArch64 MVFR{0-2}_EL1 registers. + * Work out the correct AArch64 system register encoding and reroute to the + * AArch64 system register emulation. + */ +int kvm_handle_cp10_id(struct kvm_vcpu *vcpu) +{ + int Rt = kvm_vcpu_sys_get_rt(vcpu); + u64 esr = kvm_vcpu_get_esr(vcpu); + struct sys_reg_params params; + + /* UNDEF on any unhandled register access */ + if (!kvm_esr_cp10_id_to_sys64(esr, ¶ms)) { + kvm_inject_undefined(vcpu); + return 1; + } + + if (emulate_sys_reg(vcpu, ¶ms)) + vcpu_set_reg(vcpu, Rt, params.regval); + + return 1; +} + +/** + * kvm_emulate_cp15_id_reg() - Handles an MRC trap on a guest CP15 access where + * CRn=0, which corresponds to the AArch32 feature + * registers. + * @vcpu: the vCPU pointer + * @params: the system register access parameters. + * + * Our cp15 system register tables do not enumerate the AArch32 feature + * registers. Conveniently, our AArch64 table does, and the AArch32 system + * register encoding can be trivially remapped into the AArch64 for the feature + * registers: Append op0=3, leaving op1, CRn, CRm, and op2 the same. + * + * According to DDI0487G.b G7.3.1, paragraph "Behavior of VMSAv8-32 32-bit + * System registers with (coproc=0b1111, CRn==c0)", read accesses from this + * range are either UNKNOWN or RES0. Rerouting remains architectural as we + * treat undefined registers in this range as RAZ. + */ +static int kvm_emulate_cp15_id_reg(struct kvm_vcpu *vcpu, + struct sys_reg_params *params) +{ + int Rt = kvm_vcpu_sys_get_rt(vcpu); + + /* Treat impossible writes to RO registers as UNDEFINED */ + if (params->is_write) { + unhandled_cp_access(vcpu, params); + return 1; + } + + params->Op0 = 3; + + /* + * All registers where CRm > 3 are known to be UNKNOWN/RAZ from AArch32. + * Avoid conflicting with future expansion of AArch64 feature registers + * and simply treat them as RAZ here. + */ + if (params->CRm > 3) + params->regval = 0; + else if (!emulate_sys_reg(vcpu, params)) + return 1; + + vcpu_set_reg(vcpu, Rt, params->regval); + return 1; +} + /** * kvm_handle_cp_32 -- handles a mrc/mcr trap on a guest CP14/CP15 access * @vcpu: The VCPU pointer * @run: The kvm_run struct */ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, + struct sys_reg_params *params, const struct sys_reg_desc *global, size_t nr_global) { - struct sys_reg_params params; - u32 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); - params.CRm = (esr >> 1) & 0xf; - params.regval = vcpu_get_reg(vcpu, Rt); - params.is_write = ((esr & 1) == 0); - params.CRn = (esr >> 10) & 0xf; - params.Op0 = 0; - params.Op1 = (esr >> 14) & 0x7; - params.Op2 = (esr >> 17) & 0x7; + params->regval = vcpu_get_reg(vcpu, Rt); - if (!emulate_cp(vcpu, ¶ms, global, nr_global)) { - if (!params.is_write) - vcpu_set_reg(vcpu, Rt, params.regval); + if (emulate_cp(vcpu, params, global, nr_global)) { + if (!params->is_write) + vcpu_set_reg(vcpu, Rt, params->regval); return 1; } - unhandled_cp_access(vcpu, ¶ms); + unhandled_cp_access(vcpu, params); return 1; } @@ -2382,7 +2502,20 @@ int kvm_handle_cp15_64(struct kvm_vcpu *vcpu) int kvm_handle_cp15_32(struct kvm_vcpu *vcpu) { - return kvm_handle_cp_32(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs)); + struct sys_reg_params params; + + params = esr_cp1x_32_to_params(kvm_vcpu_get_esr(vcpu)); + + /* + * Certain AArch32 ID registers are handled by rerouting to the AArch64 + * system register table. Registers in the ID range where CRm=0 are + * excluded from this scheme as they do not trivially map into AArch64 + * system register encodings. + */ + if (params.Op1 == 0 && params.CRn == 0 && params.CRm) + return kvm_emulate_cp15_id_reg(vcpu, ¶ms); + + return kvm_handle_cp_32(vcpu, ¶ms, cp15_regs, ARRAY_SIZE(cp15_regs)); } int kvm_handle_cp14_64(struct kvm_vcpu *vcpu) @@ -2392,7 +2525,11 @@ int kvm_handle_cp14_64(struct kvm_vcpu *vcpu) int kvm_handle_cp14_32(struct kvm_vcpu *vcpu) { - return kvm_handle_cp_32(vcpu, cp14_regs, ARRAY_SIZE(cp14_regs)); + struct sys_reg_params params; + + params = esr_cp1x_32_to_params(kvm_vcpu_get_esr(vcpu)); + + return kvm_handle_cp_32(vcpu, ¶ms, cp14_regs, ARRAY_SIZE(cp14_regs)); } static bool is_imp_def_sys_reg(struct sys_reg_params *params) @@ -2401,7 +2538,14 @@ static bool is_imp_def_sys_reg(struct sys_reg_params *params) return params->Op0 == 3 && (params->CRn & 0b1011) == 0b1011; } -static int emulate_sys_reg(struct kvm_vcpu *vcpu, +/** + * emulate_sys_reg - Emulate a guest access to an AArch64 system register + * @vcpu: The VCPU pointer + * @params: Decoded system register parameters + * + * Return: true if the system register access was successful, false otherwise. + */ +static bool emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { const struct sys_reg_desc *r; @@ -2410,7 +2554,10 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, if (likely(r)) { perform_access(vcpu, params, r); - } else if (is_imp_def_sys_reg(params)) { + return true; + } + + if (is_imp_def_sys_reg(params)) { kvm_inject_undefined(vcpu); } else { print_sys_reg_msg(params, @@ -2418,7 +2565,7 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); kvm_inject_undefined(vcpu); } - return 1; + return false; } /** @@ -2446,18 +2593,18 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu) struct sys_reg_params params; unsigned long esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); - int ret; trace_kvm_handle_sys_reg(esr); params = esr_sys64_to_params(esr); params.regval = vcpu_get_reg(vcpu, Rt); - ret = emulate_sys_reg(vcpu, ¶ms); + if (!emulate_sys_reg(vcpu, ¶ms)) + return 1; if (!params.is_write) vcpu_set_reg(vcpu, Rt, params.regval); - return ret; + return 1; } /****************************************************************************** @@ -2860,18 +3007,22 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return write_demux_regids(uindices); } -void kvm_sys_reg_table_init(void) +int kvm_sys_reg_table_init(void) { + bool valid = true; unsigned int i; struct sys_reg_desc clidr; /* Make sure tables are unique and in order. */ - BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), false)); - BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs), true)); - BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs), true)); - BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), true)); - BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), true)); - BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs), false)); + valid &= check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs), false); + valid &= check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs), true); + valid &= check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs), true); + valid &= check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs), true); + valid &= check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs), true); + valid &= check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs), false); + + if (!valid) + return -EINVAL; /* We abuse the reset function to overwrite the table itself. */ for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) @@ -2894,4 +3045,6 @@ void kvm_sys_reg_table_init(void) break; /* Clear all higher bits. */ cache_levels &= (1 << (i*3))-1; + + return 0; } diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index cc0cc95a0280..aee8ea054f0d 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -35,12 +35,19 @@ struct sys_reg_params { .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) +#define esr_cp1x_32_to_params(esr) \ + ((struct sys_reg_params){ .Op1 = ((esr) >> 14) & 0x7, \ + .CRn = ((esr) >> 10) & 0xf, \ + .CRm = ((esr) >> 1) & 0xf, \ + .Op2 = ((esr) >> 17) & 0x7, \ + .is_write = !((esr) & 1) }) + struct sys_reg_desc { /* Sysreg string for debug */ const char *name; enum { - AA32_ZEROHIGH, + AA32_DIRECT, AA32_LO, AA32_HI, } aarch32_map; diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 77feafd5c0e3..f6d4f4052555 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -319,7 +319,12 @@ int vgic_init(struct kvm *kvm) vgic_debug_init(kvm); - dist->implementation_rev = 2; + /* + * If userspace didn't set the GIC implementation revision, + * default to the latest and greatest. You know want it. + */ + if (!dist->implementation_rev) + dist->implementation_rev = KVM_VGIC_IMP_REV_LATEST; dist->initialized = true; out: diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 2e13402be3bd..9d3299a70242 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -683,7 +683,7 @@ int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, if (!vcpu) return E_ITS_INT_UNMAPPED_INTERRUPT; - if (!vcpu->arch.vgic_cpu.lpis_enabled) + if (!vgic_lpis_enabled(vcpu)) return -EBUSY; vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq); @@ -894,6 +894,18 @@ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its, return update_affinity(ite->irq, vcpu); } +static bool __is_visible_gfn_locked(struct vgic_its *its, gpa_t gpa) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + int idx; + bool ret; + + idx = srcu_read_lock(&its->dev->kvm->srcu); + ret = kvm_is_visible_gfn(its->dev->kvm, gfn); + srcu_read_unlock(&its->dev->kvm->srcu, idx); + return ret; +} + /* * Check whether an ID can be stored into the corresponding guest table. * For a direct table this is pretty easy, but gets a bit nasty for @@ -908,9 +920,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, u64 indirect_ptr, type = GITS_BASER_TYPE(baser); phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser); int esz = GITS_BASER_ENTRY_SIZE(baser); - int index, idx; - gfn_t gfn; - bool ret; + int index; switch (type) { case GITS_BASER_TYPE_DEVICE: @@ -933,12 +943,11 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, return false; addr = base + id * esz; - gfn = addr >> PAGE_SHIFT; if (eaddr) *eaddr = addr; - goto out; + return __is_visible_gfn_locked(its, addr); } /* calculate and check the index into the 1st level */ @@ -964,27 +973,42 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, /* Find the address of the actual entry */ index = id % (SZ_64K / esz); indirect_ptr += index * esz; - gfn = indirect_ptr >> PAGE_SHIFT; if (eaddr) *eaddr = indirect_ptr; -out: - idx = srcu_read_lock(&its->dev->kvm->srcu); - ret = kvm_is_visible_gfn(its->dev->kvm, gfn); - srcu_read_unlock(&its->dev->kvm->srcu, idx); - return ret; + return __is_visible_gfn_locked(its, indirect_ptr); } +/* + * Check whether an event ID can be stored in the corresponding Interrupt + * Translation Table, which starts at device->itt_addr. + */ +static bool vgic_its_check_event_id(struct vgic_its *its, struct its_device *device, + u32 event_id) +{ + const struct vgic_its_abi *abi = vgic_its_get_abi(its); + int ite_esz = abi->ite_esz; + gpa_t gpa; + + /* max table size is: BIT_ULL(device->num_eventid_bits) * ite_esz */ + if (event_id >= BIT_ULL(device->num_eventid_bits)) + return false; + + gpa = device->itt_addr + event_id * ite_esz; + return __is_visible_gfn_locked(its, gpa); +} + +/* + * Add a new collection into the ITS collection table. + * Returns 0 on success, and a negative error value for generic errors. + */ static int vgic_its_alloc_collection(struct vgic_its *its, struct its_collection **colp, u32 coll_id) { struct its_collection *collection; - if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) - return E_ITS_MAPC_COLLECTION_OOR; - collection = kzalloc(sizeof(*collection), GFP_KERNEL_ACCOUNT); if (!collection) return -ENOMEM; @@ -1061,7 +1085,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, if (!device) return E_ITS_MAPTI_UNMAPPED_DEVICE; - if (event_id >= BIT_ULL(device->num_eventid_bits)) + if (!vgic_its_check_event_id(its, device, event_id)) return E_ITS_MAPTI_ID_OOR; if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI) @@ -1078,7 +1102,12 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, collection = find_collection(its, coll_id); if (!collection) { - int ret = vgic_its_alloc_collection(its, &collection, coll_id); + int ret; + + if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) + return E_ITS_MAPC_COLLECTION_OOR; + + ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; new_coll = collection; @@ -1233,6 +1262,10 @@ static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its, if (!collection) { int ret; + if (!vgic_its_check_id(its, its->baser_coll_table, + coll_id, NULL)) + return E_ITS_MAPC_COLLECTION_OOR; + ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) @@ -1272,6 +1305,11 @@ static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its, return 0; } +int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq) +{ + return update_lpi_config(kvm, irq, NULL, true); +} + /* * The INV command syncs the configuration bits from the memory table. * Must be called with the its_lock mutex held. @@ -1288,7 +1326,41 @@ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its, if (!ite) return E_ITS_INV_UNMAPPED_INTERRUPT; - return update_lpi_config(kvm, ite->irq, NULL, true); + return vgic_its_inv_lpi(kvm, ite->irq); +} + +/** + * vgic_its_invall - invalidate all LPIs targetting a given vcpu + * @vcpu: the vcpu for which the RD is targetted by an invalidation + * + * Contrary to the INVALL command, this targets a RD instead of a + * collection, and we don't need to hold the its_lock, since no ITS is + * involved here. + */ +int vgic_its_invall(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + int irq_count, i = 0; + u32 *intids; + + irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids); + if (irq_count < 0) + return irq_count; + + for (i = 0; i < irq_count; i++) { + struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; + update_lpi_config(kvm, irq, vcpu, false); + vgic_put_irq(kvm, irq); + } + + kfree(intids); + + if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm) + its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe); + + return 0; } /* @@ -1305,32 +1377,13 @@ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its, u32 coll_id = its_cmd_get_collection(its_cmd); struct its_collection *collection; struct kvm_vcpu *vcpu; - struct vgic_irq *irq; - u32 *intids; - int irq_count, i; collection = find_collection(its, coll_id); if (!its_is_collection_mapped(collection)) return E_ITS_INVALL_UNMAPPED_COLLECTION; vcpu = kvm_get_vcpu(kvm, collection->target_addr); - - irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids); - if (irq_count < 0) - return irq_count; - - for (i = 0; i < irq_count; i++) { - irq = vgic_get_irq(kvm, NULL, intids[i]); - if (!irq) - continue; - update_lpi_config(kvm, irq, vcpu, false); - vgic_put_irq(kvm, irq); - } - - kfree(intids); - - if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm) - its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe); + vgic_its_invall(vcpu); return 0; } @@ -2175,6 +2228,9 @@ static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, if (!collection) return -EINVAL; + if (!vgic_its_check_event_id(its, dev, event_id)) + return -EINVAL; + ite = vgic_its_alloc_ite(dev, collection, event_id); if (IS_ERR(ite)) return PTR_ERR(ite); @@ -2183,8 +2239,10 @@ static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, vcpu = kvm_get_vcpu(kvm, collection->target_addr); irq = vgic_add_lpi(kvm, lpi_id, vcpu); - if (IS_ERR(irq)) + if (IS_ERR(irq)) { + its_free_ite(kvm, ite); return PTR_ERR(irq); + } ite->irq = irq; return offset; @@ -2296,6 +2354,7 @@ static int vgic_its_restore_dte(struct vgic_its *its, u32 id, void *ptr, void *opaque) { struct its_device *dev; + u64 baser = its->baser_device_table; gpa_t itt_addr; u8 num_eventid_bits; u64 entry = *(u64 *)ptr; @@ -2316,6 +2375,9 @@ static int vgic_its_restore_dte(struct vgic_its *its, u32 id, /* dte entry is valid */ offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT; + if (!vgic_its_check_id(its, baser, id, NULL)) + return -EINVAL; + dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits); if (IS_ERR(dev)) return PTR_ERR(dev); @@ -2445,6 +2507,9 @@ static int vgic_its_restore_device_tables(struct vgic_its *its) if (ret > 0) ret = 0; + if (ret < 0) + vgic_its_free_device_list(its->dev->kvm, its); + return ret; } @@ -2461,6 +2526,11 @@ static int vgic_its_save_cte(struct vgic_its *its, return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz); } +/* + * Restore a collection entry into the ITS collection table. + * Return +1 on success, 0 if the entry was invalid (which should be + * interpreted as end-of-table), and a negative error value for generic errors. + */ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) { struct its_collection *collection; @@ -2487,6 +2557,10 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) collection = find_collection(its, coll_id); if (collection) return -EEXIST; + + if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) + return -EINVAL; + ret = vgic_its_alloc_collection(its, &collection, coll_id); if (ret) return ret; @@ -2566,6 +2640,9 @@ static int vgic_its_restore_collection_table(struct vgic_its *its) if (ret > 0) return 0; + if (ret < 0) + vgic_its_free_collection_list(its->dev->kvm, its); + return ret; } @@ -2597,7 +2674,10 @@ static int vgic_its_restore_tables_v0(struct vgic_its *its) if (ret) return ret; - return vgic_its_restore_device_tables(its); + ret = vgic_its_restore_device_tables(its); + if (ret) + vgic_its_free_collection_list(its->dev->kvm, its); + return ret; } static int vgic_its_commit_v0(struct vgic_its *its) diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c index 12e4c223e6b8..77a67e9d3d14 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -73,9 +73,13 @@ static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + u32 reg; + switch (addr & 0x0c) { case GIC_DIST_IIDR: - if (val != vgic_mmio_read_v2_misc(vcpu, addr, len)) + reg = vgic_mmio_read_v2_misc(vcpu, addr, len); + if ((reg ^ val) & ~GICD_IIDR_REVISION_MASK) return -EINVAL; /* @@ -87,8 +91,16 @@ static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu, * migration from old kernels to new kernels with legacy * userspace. */ - vcpu->kvm->arch.vgic.v2_groups_user_writable = true; - return 0; + reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg); + switch (reg) { + case KVM_VGIC_IMP_REV_2: + case KVM_VGIC_IMP_REV_3: + vcpu->kvm->arch.vgic.v2_groups_user_writable = true; + dist->implementation_rev = reg; + return 0; + default: + return -EINVAL; + } } vgic_mmio_write_v2_misc(vcpu, addr, len, val); diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 58e40b4874f8..f7aa7bcd6fb8 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -155,13 +155,27 @@ static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu, unsigned long val) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + u32 reg; switch (addr & 0x0c) { case GICD_TYPER2: - case GICD_IIDR: if (val != vgic_mmio_read_v3_misc(vcpu, addr, len)) return -EINVAL; return 0; + case GICD_IIDR: + reg = vgic_mmio_read_v3_misc(vcpu, addr, len); + if ((reg ^ val) & ~GICD_IIDR_REVISION_MASK) + return -EINVAL; + + reg = FIELD_GET(GICD_IIDR_REVISION_MASK, reg); + switch (reg) { + case KVM_VGIC_IMP_REV_2: + case KVM_VGIC_IMP_REV_3: + dist->implementation_rev = reg; + return 0; + default: + return -EINVAL; + } case GICD_CTLR: /* Not a GICv4.1? No HW SGIs */ if (!kvm_vgic_global_state.has_gicv4_1) @@ -221,34 +235,58 @@ static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu, vgic_put_irq(vcpu->kvm, irq); } +bool vgic_lpis_enabled(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + return atomic_read(&vgic_cpu->ctlr) == GICR_CTLR_ENABLE_LPIS; +} + static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + unsigned long val; - return vgic_cpu->lpis_enabled ? GICR_CTLR_ENABLE_LPIS : 0; -} + val = atomic_read(&vgic_cpu->ctlr); + if (vgic_get_implementation_rev(vcpu) >= KVM_VGIC_IMP_REV_3) + val |= GICR_CTLR_IR | GICR_CTLR_CES; + return val; +} static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - bool was_enabled = vgic_cpu->lpis_enabled; + u32 ctlr; if (!vgic_has_its(vcpu->kvm)) return; - vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS; + if (!(val & GICR_CTLR_ENABLE_LPIS)) { + /* + * Don't disable if RWP is set, as there already an + * ongoing disable. Funky guest... + */ + ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr, + GICR_CTLR_ENABLE_LPIS, + GICR_CTLR_RWP); + if (ctlr != GICR_CTLR_ENABLE_LPIS) + return; - if (was_enabled && !vgic_cpu->lpis_enabled) { vgic_flush_pending_lpis(vcpu); vgic_its_invalidate_cache(vcpu->kvm); - } + atomic_set_release(&vgic_cpu->ctlr, 0); + } else { + ctlr = atomic_cmpxchg_acquire(&vgic_cpu->ctlr, 0, + GICR_CTLR_ENABLE_LPIS); + if (ctlr != 0) + return; - if (!was_enabled && vgic_cpu->lpis_enabled) vgic_enable_lpis(vcpu); + } } static bool vgic_mmio_vcpu_rdist_is_last(struct kvm_vcpu *vcpu) @@ -478,11 +516,10 @@ static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu, unsigned long val) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; u64 old_propbaser, propbaser; /* Storing a value with LPIs already enabled is undefined */ - if (vgic_cpu->lpis_enabled) + if (vgic_lpis_enabled(vcpu)) return; do { @@ -513,7 +550,7 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, u64 old_pendbaser, pendbaser; /* Storing a value with LPIs already enabled is undefined */ - if (vgic_cpu->lpis_enabled) + if (vgic_lpis_enabled(vcpu)) return; do { @@ -525,6 +562,63 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, pendbaser) != old_pendbaser); } +static unsigned long vgic_mmio_read_sync(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return !!atomic_read(&vcpu->arch.vgic_cpu.syncr_busy); +} + +static void vgic_set_rdist_busy(struct kvm_vcpu *vcpu, bool busy) +{ + if (busy) { + atomic_inc(&vcpu->arch.vgic_cpu.syncr_busy); + smp_mb__after_atomic(); + } else { + smp_mb__before_atomic(); + atomic_dec(&vcpu->arch.vgic_cpu.syncr_busy); + } +} + +static void vgic_mmio_write_invlpi(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + struct vgic_irq *irq; + + /* + * If the guest wrote only to the upper 32bit part of the + * register, drop the write on the floor, as it is only for + * vPEs (which we don't support for obvious reasons). + * + * Also discard the access if LPIs are not enabled. + */ + if ((addr & 4) || !vgic_lpis_enabled(vcpu)) + return; + + vgic_set_rdist_busy(vcpu, true); + + irq = vgic_get_irq(vcpu->kvm, NULL, lower_32_bits(val)); + if (irq) { + vgic_its_inv_lpi(vcpu->kvm, irq); + vgic_put_irq(vcpu->kvm, irq); + } + + vgic_set_rdist_busy(vcpu, false); +} + +static void vgic_mmio_write_invall(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + /* See vgic_mmio_write_invlpi() for the early return rationale */ + if ((addr & 4) || !vgic_lpis_enabled(vcpu)) + return; + + vgic_set_rdist_busy(vcpu, true); + vgic_its_invall(vcpu); + vgic_set_rdist_busy(vcpu, false); +} + /* * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the * redistributors, while SPIs are covered by registers in the distributor @@ -630,6 +724,15 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER, vgic_mmio_read_pendbase, vgic_mmio_write_pendbase, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_INVLPIR, + vgic_mmio_read_raz, vgic_mmio_write_invlpi, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_INVALLR, + vgic_mmio_read_raz, vgic_mmio_write_invall, 8, + VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), + REGISTER_DESC_WITH_LENGTH(GICR_SYNCR, + vgic_mmio_read_sync, vgic_mmio_write_wi, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_IDREGS, vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48, VGIC_ACCESS_32bit), diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index b549af8b1dc2..826ff6f2a4e7 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -612,6 +612,10 @@ early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM), + MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), {}, }; diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 3fd6c86a7ef3..4c6bdd321faa 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -98,6 +98,11 @@ #define DEBUG_SPINLOCK_BUG_ON(p) #endif +static inline u32 vgic_get_implementation_rev(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.vgic.implementation_rev; +} + /* Requires the irq_lock to be held by the caller. */ static inline bool irq_is_pending(struct vgic_irq *irq) { @@ -308,6 +313,7 @@ static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size) (base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE); } +bool vgic_lpis_enabled(struct kvm_vcpu *vcpu); int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr); int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq); @@ -317,6 +323,10 @@ void vgic_lpi_translation_cache_init(struct kvm *kvm); void vgic_lpi_translation_cache_destroy(struct kvm *kvm); void vgic_its_invalidate_cache(struct kvm *kvm); +/* GICv4.1 MMIO interface */ +int vgic_its_inv_lpi(struct kvm *kvm, struct vgic_irq *irq); +int vgic_its_invall(struct kvm_vcpu *vcpu); + bool vgic_supports_direct_msis(struct kvm *kvm); int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c index 1688af0a4c97..5b7890139bc2 100644 --- a/arch/arm64/lib/delay.c +++ b/arch/arm64/lib/delay.c @@ -27,7 +27,17 @@ void __delay(unsigned long cycles) { cycles_t start = get_cycles(); - if (arch_timer_evtstrm_available()) { + if (cpus_have_const_cap(ARM64_HAS_WFXT)) { + u64 end = start + cycles; + + /* + * Start with WFIT. If an interrupt makes us resume + * early, use a WFET loop to complete the delay. + */ + wfit(end); + while ((get_cycles() - start) < cycles) + wfet(end); + } else if (arch_timer_evtstrm_available()) { const cycles_t timer_evt_period = USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8ac25f19084e..1e7b1550e2fc 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(memstart_addr); * In this scheme a comparatively quicker boot is observed. * * If ZONE_DMA configs are defined, crash kernel memory reservation - * is delayed until DMA zone memory range size initilazation performed in + * is delayed until DMA zone memory range size initialization performed in * zone_sizes_init(). The defer is necessary to steer clear of DMA zone * memory range to avoid overlap allocation. So crash kernel memory boundaries * are not known when mapping all bank memory ranges, which otherwise means @@ -81,7 +81,7 @@ EXPORT_SYMBOL(memstart_addr); * so page-granularity mappings are created for the entire memory range. * Hence a slightly slower boot is observed. * - * Note: Page-granularity mapppings are necessary for crash kernel memory + * Note: Page-granularity mappings are necessary for crash kernel memory * range for shrinking its size via /sys/kernel/kexec_crash_size interface. */ #if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32) diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 3ed418f70e3b..507b20373953 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -38,11 +38,14 @@ HAS_STAGE2_FWB HAS_SYSREG_GIC_CPUIF HAS_TLB_RANGE HAS_VIRT_HOST_EXTN +HAS_WFXT HW_DBM KVM_PROTECTED_MODE MISMATCHED_CACHE_TYPE MTE MTE_ASYMM +SME +SME_FA64 SPECTRE_V2 SPECTRE_V3A SPECTRE_V4 diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 827038a33064..4def2bd17b9b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -16,18 +16,6 @@ #include <asm/ppc-opcode.h> #include <asm/pte-walk.h> -#ifdef CONFIG_PPC_PSERIES -static inline bool kvmhv_on_pseries(void) -{ - return !cpu_has_feature(CPU_FTR_HVMODE); -} -#else -static inline bool kvmhv_on_pseries(void) -{ - return false; -} -#endif - /* * Structure for a nested guest, that is, for a guest that is managed by * one of our guests. diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c583d0c37f31..838d4cb460b7 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -586,6 +586,18 @@ static inline bool kvm_hv_mode_active(void) { return false; } #endif +#ifdef CONFIG_PPC_PSERIES +static inline bool kvmhv_on_pseries(void) +{ + return !cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool kvmhv_on_pseries(void) +{ + return false; +} +#endif + #ifdef CONFIG_KVM_XICS static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 254687258f42..f2c5c26869f1 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ + pfn_valid(virt_to_pfn(_addr)); \ +}) /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 049ca26893e6..8fa37ef5da4d 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -28,11 +28,13 @@ void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES +extern bool pseries_reloc_on_exception(void); extern bool pseries_enable_reloc_on_exc(void); extern void pseries_disable_reloc_on_exc(void); extern void pseries_big_endian_exceptions(void); void __init pseries_little_endian_exceptions(void); #else +static inline bool pseries_reloc_on_exception(void) { return false; } static inline bool pseries_enable_reloc_on_exc(void) { return false; } static inline void pseries_disable_reloc_on_exc(void) {} static inline void pseries_big_endian_exceptions(void) {} diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h index 0a0bc79bd1fa..de1018cc522b 100644 --- a/arch/powerpc/include/asm/static_call.h +++ b/arch/powerpc/include/asm/static_call.h @@ -24,5 +24,6 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") #endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 55caeee37c08..b66dd6f775a4 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -809,6 +809,10 @@ __start_interrupts: * - MSR_EE|MSR_RI is clear (no reentrant exceptions) * - Standard kernel environment is set up (stack, paca, etc) * + * KVM: + * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM + * ensures that FSCR[SCV] is disabled whenever it has to force AIL off. + * * Call convention: * * syscall register convention is in Documentation/powerpc/syscall64-abi.rst diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 40a583e9d3c7..97a76a8619fb 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -101,7 +101,7 @@ __module_alloc(unsigned long size, unsigned long start, unsigned long end, bool * too. */ return __vmalloc_node_range(size, 1, start, end, gfp, prot, - VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e547066a06aa..a96f05063bc9 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -196,6 +196,34 @@ static void __init configure_exceptions(void) /* Under a PAPR hypervisor, we need hypercalls */ if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * - PR KVM does not support AIL mode interrupts in the host + * while a PR guest is running. + * + * - SCV system call interrupt vectors are only implemented for + * AIL mode interrupts. + * + * - On pseries, AIL mode can only be enabled and disabled + * system-wide so when a PR VM is created on a pseries host, + * all CPUs of the host are set to AIL=0 mode. + * + * - Therefore host CPUs must not execute scv while a PR VM + * exists. + * + * - SCV support can not be disabled dynamically because the + * feature is advertised to host userspace. Disabling the + * facility and emulating it would be possible but is not + * implemented. + * + * - So SCV support is blanket disabled if PR KVM could possibly + * run. That is, PR support compiled in, booting on pseries + * with hash MMU. + */ + if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) { + init_task.thread.fscr &= ~FSCR_SCV; + cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV; + } + /* Enable AIL if possible */ if (!pseries_enable_reloc_on_exc()) { init_task.thread.fscr &= ~FSCR_SCV; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f5cbfe5efd25..f80cce0e3899 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -615,23 +615,22 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) return; } - /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) { - /* - * Ensure a positive value is written to the decrementer, or - * else some CPUs will continue to take decrementer exceptions. - * When the PPC_WATCHDOG (decrementer based) is configured, - * keep this at most 31 bits, which is about 4 seconds on most - * systems, which gives the watchdog a chance of catching timer - * interrupt hard lockups. - */ - if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) - set_dec(0x7fffffff); - else - set_dec(decrementer_max); + /* + * Ensure a positive value is written to the decrementer, or + * else some CPUs will continue to take decrementer exceptions. + * When the PPC_WATCHDOG (decrementer based) is configured, + * keep this at most 31 bits, which is about 4 seconds on most + * systems, which gives the watchdog a chance of catching timer + * interrupt hard lockups. + */ + if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) + set_dec(0x7fffffff); + else + set_dec(decrementer_max); + /* Conditionally hard-enable interrupts. */ + if (should_hard_irq_enable()) do_hard_irq_enable(); - } #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 18e58085447c..ddd88179110a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -112,12 +112,21 @@ config KVM_BOOK3S_64_PR guest in user mode (problem state) and emulating all privileged instructions and registers. + This is only available for hash MMU mode and only supports + guests that use hash MMU mode. + This is not as fast as using hypervisor mode, but works on machines where hypervisor mode is not available or not usable, and can emulate processors that are different from the host processor, including emulating 32-bit processors on a 64-bit host. + Selecting this option will cause the SCV facility to be + disabled when the kernel is booted on the pseries platform in + hash MMU mode (regardless of PR VMs running). When any PR VMs + are running, "AIL" mode is disabled which may slow interrupts + and system calls on the host. + config KVM_BOOK3S_HV_EXIT_TIMING bool "Detailed timing for hypervisor real-mode code" depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 05e003eb5d90..e42d1c609e47 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -414,10 +414,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) */ ld r10,HSTATE_SCRATCH0(r13) cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK - beq machine_check_common + beq .Lcall_machine_check_common cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET - beq system_reset_common + beq .Lcall_system_reset_common b . + +.Lcall_machine_check_common: + b machine_check_common + +.Lcall_system_reset_common: + b system_reset_common #endif diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index e4ce2a35483f..42851c32ff3b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -168,9 +168,10 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr, return -EINVAL; /* Read the entry from guest memory */ addr = base + (index * sizeof(rpte)); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (ret) { if (pte_ret_p) *pte_ret_p = addr; @@ -246,9 +247,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, /* Read the table to find the root of the radix tree */ ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry)); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (ret) return ret; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index d42b4b6d4a79..85cfa6328222 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -420,13 +420,19 @@ static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt, tbl[idx % TCES_PER_PAGE] = tce; } -static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_clear_tce(struct mm_struct *mm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill(mm, tbl, io_entry + i, &hpa, &dir); + } } static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm, @@ -485,6 +491,8 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm, break; } + iommu_tce_kill(tbl, io_entry, subpages); + return ret; } @@ -544,6 +552,8 @@ static long kvmppc_tce_iommu_map(struct kvm *kvm, break; } + iommu_tce_kill(tbl, io_entry, subpages); + return ret; } @@ -590,10 +600,9 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); - iommu_tce_kill(stit->tbl, entry, 1); if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry); goto unlock_exit; } } @@ -669,13 +678,13 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, */ if (get_user(tce, tces + i)) { ret = H_TOO_HARD; - goto invalidate_exit; + goto unlock_exit; } tce = be64_to_cpu(tce); if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -684,19 +693,15 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, + entry + i); + goto unlock_exit; } } kvmppc_tce_put(stt, entry + i, tce); } -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, entry, npages); - unlock_exit: srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -735,20 +740,16 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret; WARN_ON_ONCE(1); - kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry); + kvmppc_clear_tce(vcpu->kvm->mm, stt, stit->tbl, entry + i); } } for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value); -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce); diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 870b7f0c7ea5..fdeda6a9cff4 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -247,13 +247,19 @@ static void iommu_tce_kill_rm(struct iommu_table *tbl, tbl->it_ops->tce_kill(tbl, entry, pages, true); } -static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, - unsigned long entry) +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct kvmppc_spapr_tce_table *stt, + struct iommu_table *tbl, unsigned long entry) { - unsigned long hpa = 0; - enum dma_data_direction dir = DMA_NONE; + unsigned long i; + unsigned long subpages = 1ULL << (stt->page_shift - tbl->it_page_shift); + unsigned long io_entry = entry << (stt->page_shift - tbl->it_page_shift); + + for (i = 0; i < subpages; ++i) { + unsigned long hpa = 0; + enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir); + iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, io_entry + i, &hpa, &dir); + } } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -316,6 +322,8 @@ static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm, break; } + iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; } @@ -379,6 +387,8 @@ static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, break; } + iommu_tce_kill_rm(tbl, io_entry, subpages); + return ret; } @@ -420,10 +430,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt, stit->tbl, entry, ua, dir); - iommu_tce_kill_rm(stit->tbl, entry, 1); - if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry); return ret; } } @@ -561,7 +569,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, ua = 0; if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua)) { ret = H_PARAMETER; - goto invalidate_exit; + goto unlock_exit; } list_for_each_entry_lockless(stit, &stt->iommu_tables, next) { @@ -570,19 +578,15 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, iommu_tce_direction(tce)); if (ret != H_SUCCESS) { - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, - entry); - goto invalidate_exit; + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, + entry + i); + goto unlock_exit; } } kvmppc_rm_tce_put(stt, entry + i, tce); } -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, entry, npages); - unlock_exit: if (!prereg) arch_spin_unlock(&kvm->mmu_lock.rlock.raw_lock); @@ -620,20 +624,16 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, continue; if (ret == H_TOO_HARD) - goto invalidate_exit; + return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stt, stit->tbl, entry + i); } } for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift)) kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value); -invalidate_exit: - list_for_each_entry_lockless(stit, &stt->iommu_tables, next) - iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages); - return ret; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index c886557638a1..6fa518f6501d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) int cpu; struct rcuwait *waitp; + /* + * rcuwait_wake_up contains smp_mb() which orders prior stores that + * create pending work vs below loads of cpu fields. The other side + * is the barrier in vcpu run that orders setting the cpu fields vs + * testing for pending work. + */ + waitp = kvm_arch_vcpu_get_wait(vcpu); if (rcuwait_wake_up(waitp)) ++vcpu->stat.generic.halt_wakeup; @@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) break; } tvcpu->arch.prodded = 1; - smp_mb(); + smp_mb(); /* This orders prodded store vs ceded load */ if (tvcpu->arch.ceded) kvmppc_fast_vcpu_kick_hv(tvcpu); break; @@ -3766,6 +3773,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) pvc = core_info.vc[sub]; pvc->pcpu = pcpu + thr; for_each_runnable_thread(i, vcpu, pvc) { + /* + * XXX: is kvmppc_start_thread called too late here? + * It updates vcpu->cpu and vcpu->arch.thread_cpu + * which are used by kvmppc_fast_vcpu_kick_hv(), but + * kick is called after new exceptions become available + * and exceptions are checked earlier than here, by + * kvmppc_core_prepare_to_enter. + */ kvmppc_start_thread(vcpu, pvc); kvmppc_create_dtl_entry(vcpu, pvc); trace_kvm_guest_enter(vcpu); @@ -4487,6 +4502,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, if (need_resched() || !kvm->arch.mmu_ready) goto out; + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + /* + * Orders set cpu/thread_cpu vs testing for pending interrupts and + * doorbells below. The other side is when these fields are set vs + * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to + * kick a vCPU to notice the pending interrupt. + */ + smp_mb(); + if (!nested) { kvmppc_core_prepare_to_enter(vcpu); if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, @@ -4506,13 +4536,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, tb = mftb(); - vcpu->cpu = pcpu; - vcpu->arch.thread_cpu = pcpu; - vc->pcpu = pcpu; - local_paca->kvm_hstate.kvm_vcpu = vcpu; - local_paca->kvm_hstate.ptid = 0; - local_paca->kvm_hstate.fake_suspend = 0; - __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); trace_kvm_guest_enter(vcpu); @@ -4614,6 +4637,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 9d373f8963ee..c943a051c6e7 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -306,10 +306,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* copy parameters in */ hv_ptr = kvmppc_get_gpr(vcpu, 4); regs_ptr = kvmppc_get_gpr(vcpu, 5); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); err = kvmhv_read_guest_state_and_regs(vcpu, &l2_hv, &l2_regs, hv_ptr, regs_ptr); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (err) return H_PARAMETER; @@ -410,10 +410,10 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) byteswap_hv_regs(&l2_hv); byteswap_pt_regs(&l2_regs); } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); err = kvmhv_write_guest_state_and_regs(vcpu, &l2_hv, &l2_regs, hv_ptr, regs_ptr); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (err) return H_AUTHORITY; @@ -600,16 +600,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) goto not_found; /* Write what was loaded into our buffer back to the L1 guest */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto not_found; } else { /* Load the data to be stored from the L1 guest into our buf */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto not_found; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 34a801c3604a..7bf9e6ca5c2d 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -137,12 +137,15 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max; svcpu->in_use = 0; svcpu_put(svcpu); -#endif /* Disable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) & ~FSCR_SCV); + } +#endif vcpu->cpu = smp_processor_id(); #ifdef CONFIG_PPC_BOOK3S_32 @@ -165,6 +168,14 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; svcpu_put(svcpu); + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) | FSCR_SCV); + } #endif if (kvmppc_is_split_real(vcpu)) @@ -174,11 +185,6 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); kvmppc_save_tm_pr(vcpu); - /* Enable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); - vcpu->cpu = -1; } @@ -1037,6 +1043,8 @@ static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac) void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr) { + if (fscr & FSCR_SCV) + fscr &= ~FSCR_SCV; /* SCV must not be enabled */ if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) { /* TAR got dropped, drop it in shadow too */ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 1f10e7dfcdd0..dc4f51ac84bc 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -281,6 +281,22 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_set_mode(struct kvm_vcpu *vcpu) +{ + unsigned long mflags = kvmppc_get_gpr(vcpu, 4); + unsigned long resource = kvmppc_get_gpr(vcpu, 5); + + if (resource == H_SET_MODE_RESOURCE_ADDR_TRANS_MODE) { + /* KVM PR does not provide AIL!=0 to guests */ + if (mflags == 0) + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + else + kvmppc_set_gpr(vcpu, 3, H_UNSUPPORTED_FLAG_START - 63); + return EMULATE_DONE; + } + return EMULATE_FAIL; +} + #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) { @@ -384,6 +400,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_logical_ci_load(vcpu); case H_LOGICAL_CI_STORE: return kvmppc_h_pr_logical_ci_store(vcpu); + case H_SET_MODE: + return kvmppc_h_pr_set_mode(vcpu); case H_XIRR: case H_CPPR: case H_EOI: @@ -421,6 +439,7 @@ int kvmppc_hcall_impl_pr(unsigned long cmd) case H_CEDE: case H_LOGICAL_CI_LOAD: case H_LOGICAL_CI_STORE: + case H_SET_MODE: #ifdef CONFIG_KVM_XICS case H_XIRR: case H_CPPR: @@ -447,6 +466,7 @@ static unsigned int default_hcall_list[] = { H_BULK_REMOVE, H_PUT_TCE, H_CEDE, + H_SET_MODE, #ifdef CONFIG_KVM_XICS H_XIRR, H_CPPR, diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 0f847f1e5ddd..6808bda0dbc1 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -229,9 +229,9 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) */ args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM; - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args)); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) goto fail; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9772b176e406..533c4232e5ab 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -425,9 +425,9 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, return EMULATE_DONE; } - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (rc) return EMULATE_DO_MMIO; @@ -705,6 +705,23 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; #endif + case KVM_CAP_PPC_AIL_MODE_3: + r = 0; + /* + * KVM PR, POWER7, and some POWER9s don't support AIL=3 mode. + * The POWER9s can support it if the guest runs in hash mode, + * but QEMU doesn't necessarily query the capability in time. + */ + if (hv_enabled) { + if (kvmhv_on_pseries()) { + if (pseries_reloc_on_exception()) + r = 1; + } else if (cpu_has_feature(CPU_FTR_ARCH_207S) && + !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { + r = 1; + } + } + break; default: r = 0; break; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8e301cd8925b..4d221d033804 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -255,7 +255,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_pfn); kasan_late_init(); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b9b7fefbb64b..13022d734951 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1436,7 +1436,7 @@ int find_and_online_cpu_nid(int cpu) if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; - if (NODE_DATA(new_nid) == NULL) { + if (!node_online(new_nid)) { #ifdef CONFIG_MEMORY_HOTPLUG /* * Need to ensure that NODE_DATA is initialized for a node from diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index 2f46e31c7612..4f53d0b97539 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -3,11 +3,11 @@ obj-y += callchain.o callchain_$(BITS).o perf_regs.o obj-$(CONFIG_COMPAT) += callchain_32.o -obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o +obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o obj64-$(CONFIG_PPC_PERF_CTRS) += ppc970-pmu.o power5-pmu.o \ power5+-pmu.o power6-pmu.o power7-pmu.o \ isa207-common.o power8-pmu.o power9-pmu.o \ - generic-compat-pmu.o power10-pmu.o + generic-compat-pmu.o power10-pmu.o bhrb.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o obj-$(CONFIG_PPC_POWERNV) += imc-pmu.o diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index d3398100a60f..c6d51e7093cf 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -91,8 +91,8 @@ extern u64 PERF_REG_EXTENDED_MASK; /* Table of alternatives, sorted by column 0 */ static const unsigned int power10_event_alternatives[][MAX_ALT] = { - { PM_CYC_ALT, PM_CYC }, { PM_INST_CMPL_ALT, PM_INST_CMPL }, + { PM_CYC_ALT, PM_CYC }, }; static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index c9eb5232e68b..c393e837648e 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -133,11 +133,11 @@ int p9_dd22_bl_ev[] = { /* Table of alternatives, sorted by column 0 */ static const unsigned int power9_event_alternatives[][MAX_ALT] = { - { PM_INST_DISP, PM_INST_DISP_ALT }, - { PM_RUN_CYC_ALT, PM_RUN_CYC }, - { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, - { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, { PM_BR_2PATH, PM_BR_2PATH_ALT }, + { PM_INST_DISP, PM_INST_DISP_ALT }, + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, }; static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[]) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 069d7b3bb142..955ff8aa1644 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -353,6 +353,14 @@ static void pseries_lpar_idle(void) pseries_idle_epilog(); } +static bool pseries_reloc_on_exception_enabled; + +bool pseries_reloc_on_exception(void) +{ + return pseries_reloc_on_exception_enabled; +} +EXPORT_SYMBOL_GPL(pseries_reloc_on_exception); + /* * Enable relocation on during exceptions. This has partition wide scope and * may take a while to complete, if it takes longer than one second we will @@ -377,6 +385,7 @@ bool pseries_enable_reloc_on_exc(void) " on exceptions: %ld\n", rc); return false; } + pseries_reloc_on_exception_enabled = true; return true; } @@ -404,7 +413,9 @@ void pseries_disable_reloc_on_exc(void) break; mdelay(get_longbusy_msecs(rc)); } - if (rc != H_SUCCESS) + if (rc == H_SUCCESS) + pseries_reloc_on_exception_enabled = false; + else pr_warn("Warning: Failed to disable relocation on exceptions: %ld\n", rc); } diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c index 4a7fcde5afc0..909535ca513a 100644 --- a/arch/powerpc/platforms/pseries/vas-sysfs.c +++ b/arch/powerpc/platforms/pseries/vas-sysfs.c @@ -99,6 +99,7 @@ static struct attribute *vas_def_capab_attrs[] = { &nr_used_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_def_capab); static struct attribute *vas_qos_capab_attrs[] = { &nr_total_credits_attribute.attr, @@ -106,6 +107,7 @@ static struct attribute *vas_qos_capab_attrs[] = { &update_total_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_qos_capab); static ssize_t vas_type_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -154,13 +156,13 @@ static const struct sysfs_ops vas_sysfs_ops = { static struct kobj_type vas_def_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_def_capab_attrs, + .default_groups = vas_def_capab_groups, }; static struct kobj_type vas_qos_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_qos_capab_attrs, + .default_groups = vas_qos_capab_groups, }; static char *vas_caps_kobj_name(struct vas_caps_entry *centry, diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 34592d00dde8..f6ef358d8a2c 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -38,7 +38,7 @@ config SOC_VIRT select SIFIVE_PLIC select PM_GENERIC_DOMAINS if PM select PM_GENERIC_DOMAINS_OF if PM && OF - select RISCV_SBI_CPUIDLE if CPU_IDLE + select RISCV_SBI_CPUIDLE if CPU_IDLE && RISCV_SBI help This enables support for QEMU Virt Machine. diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi index 854320e17b28..ccaac3371cf9 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-fabric.dtsi @@ -7,7 +7,7 @@ reg = <0x0 0x41000000 0x0 0xF0>; microchip,sync-update-mask = /bits/ 32 <0>; #pwm-cells = <2>; - clocks = <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk3>; status = "disabled"; }; @@ -16,10 +16,22 @@ reg = <0x0 0x44000000 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; - clocks = <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk3>; interrupt-parent = <&plic>; interrupts = <122>; clock-frequency = <100000>; status = "disabled"; }; + + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; }; diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts index cd2fe80fa81a..3392153dd0f1 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts @@ -45,7 +45,7 @@ }; &refclk { - clock-frequency = <600000000>; + clock-frequency = <125000000>; }; &mmuart1 { diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index c5c9d1360de0..746c4d4e7686 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -141,7 +141,7 @@ }; }; - refclk: msspllclk { + refclk: mssrefclk { compatible = "fixed-clock"; #clock-cells = <0>; }; @@ -190,7 +190,7 @@ clkcfg: clkcfg@20002000 { compatible = "microchip,mpfs-clkcfg"; - reg = <0x0 0x20002000 0x0 0x1000>; + reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>; clocks = <&refclk>; #clock-cells = <1>; }; @@ -393,8 +393,8 @@ reg = <0x0 0x20124000 0x0 0x1000>; interrupt-parent = <&plic>; interrupts = <80>, <81>; - clocks = <&clkcfg CLK_RTC>; - clock-names = "rtc"; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; status = "disabled"; }; @@ -424,7 +424,7 @@ <0 0 0 3 &pcie_intc 2>, <0 0 0 4 &pcie_intc 3>; interrupt-map-mask = <0 0 0 7>; - clocks = <&clkcfg CLK_FIC0>, <&clkcfg CLK_FIC1>, <&clkcfg CLK_FIC3>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; clock-names = "fic0", "fic1", "fic3"; ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; msi-parent = <&pcie>; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 30e3017f22bc..0cc17db8aaba 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -101,6 +101,7 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 7e5efdc3829d..6cd9d84d3e13 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -93,6 +93,7 @@ CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 78da839657e5..cd4bbcecb0fb 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -193,9 +193,6 @@ struct kvm_vcpu_arch { /* Don't run the VCPU (blocked) */ bool pause; - - /* SRCU lock index for in-kernel run loop */ - int srcu_idx; }; static inline void kvm_arch_hardware_unsetup(void) {} diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 0b552873a577..765004b60513 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -104,7 +104,7 @@ static int patch_text_cb(void *data) struct patch_insn *patch = data; int ret = 0; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { ret = patch_text_nosync(patch->addr, &patch->insn, GET_INSN_LENGTH(patch->insn)); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 6785aef4cbd4..7461f964d20a 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -38,14 +38,16 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -#define KVM_RISCV_ISA_ALLOWED (riscv_isa_extension_mask(a) | \ - riscv_isa_extension_mask(c) | \ - riscv_isa_extension_mask(d) | \ - riscv_isa_extension_mask(f) | \ - riscv_isa_extension_mask(i) | \ - riscv_isa_extension_mask(m) | \ - riscv_isa_extension_mask(s) | \ - riscv_isa_extension_mask(u)) +#define KVM_RISCV_ISA_DISABLE_ALLOWED (riscv_isa_extension_mask(d) | \ + riscv_isa_extension_mask(f)) + +#define KVM_RISCV_ISA_DISABLE_NOT_ALLOWED (riscv_isa_extension_mask(a) | \ + riscv_isa_extension_mask(c) | \ + riscv_isa_extension_mask(i) | \ + riscv_isa_extension_mask(m)) + +#define KVM_RISCV_ISA_ALLOWED (KVM_RISCV_ISA_DISABLE_ALLOWED | \ + KVM_RISCV_ISA_DISABLE_NOT_ALLOWED) static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) { @@ -219,7 +221,8 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, switch (reg_num) { case KVM_REG_RISCV_CONFIG_REG(isa): if (!vcpu->arch.ran_atleast_once) { - vcpu->arch.isa = reg_val; + /* Ignore the disable request for these extensions */ + vcpu->arch.isa = reg_val | KVM_RISCV_ISA_DISABLE_NOT_ALLOWED; vcpu->arch.isa &= riscv_isa_extension_base(NULL); vcpu->arch.isa &= KVM_RISCV_ISA_ALLOWED; kvm_riscv_vcpu_fp_reset(vcpu); @@ -724,13 +727,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* Mark this VCPU ran at least once */ vcpu->arch.ran_atleast_once = true; - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* Process MMIO value returned from user-space */ if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run); if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } } @@ -739,13 +742,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) if (run->exit_reason == KVM_EXIT_RISCV_SBI) { ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); if (ret) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } } if (run->immediate_exit) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return -EINTR; } @@ -784,7 +787,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ vcpu->mode = IN_GUEST_MODE; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); smp_mb__after_srcu_read_unlock(); /* @@ -802,7 +805,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; local_irq_enable(); preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); continue; } @@ -846,7 +849,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) preempt_enable(); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); ret = kvm_riscv_vcpu_exit(vcpu, run, &trap); } @@ -855,7 +858,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu_put(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return ret; } diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index aa8af129e4bb..a72c15d4b42a 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -456,9 +456,9 @@ static int stage2_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu) { if (!kvm_arch_vcpu_runnable(vcpu)) { - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); - vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); } } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9535bea8688c..b0793dc0c291 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -718,6 +718,7 @@ retry: if (!check_l4) { disable_pgtable_l5(); check_l4 = true; + memset(early_pg_dir, 0, PAGE_SIZE); goto retry; } disable_pgtable_l4(); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 77b5a03de13a..e084c72104f8 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -255,6 +255,10 @@ config HAVE_MARCH_Z15_FEATURES def_bool n select HAVE_MARCH_Z14_FEATURES +config HAVE_MARCH_Z16_FEATURES + def_bool n + select HAVE_MARCH_Z15_FEATURES + choice prompt "Processor type" default MARCH_Z196 @@ -312,6 +316,14 @@ config MARCH_Z15 and 8561 series). The kernel will be slightly faster but will not work on older machines. +config MARCH_Z16 + bool "IBM z16" + select HAVE_MARCH_Z16_FEATURES + depends on $(cc-option,-march=z16) + help + Select this to enable optimizations for IBM z16 (3931 and + 3932 series). + endchoice config MARCH_Z10_TUNE @@ -332,6 +344,9 @@ config MARCH_Z14_TUNE config MARCH_Z15_TUNE def_bool TUNE_Z15 || MARCH_Z15 && TUNE_DEFAULT +config MARCH_Z16_TUNE + def_bool TUNE_Z16 || MARCH_Z16 && TUNE_DEFAULT + choice prompt "Tune code generation" default TUNE_DEFAULT @@ -372,6 +387,10 @@ config TUNE_Z15 bool "IBM z15" depends on $(cc-option,-mtune=z15) +config TUNE_Z16 + bool "IBM z16" + depends on $(cc-option,-mtune=z16) + endchoice config 64BIT diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7a65bca1e5af..e441b60b1812 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -42,6 +42,7 @@ mflags-$(CONFIG_MARCH_ZEC12) := -march=zEC12 mflags-$(CONFIG_MARCH_Z13) := -march=z13 mflags-$(CONFIG_MARCH_Z14) := -march=z14 mflags-$(CONFIG_MARCH_Z15) := -march=z15 +mflags-$(CONFIG_MARCH_Z16) := -march=z16 export CC_FLAGS_MARCH := $(mflags-y) @@ -54,6 +55,7 @@ cflags-$(CONFIG_MARCH_ZEC12_TUNE) += -mtune=zEC12 cflags-$(CONFIG_MARCH_Z13_TUNE) += -mtune=z13 cflags-$(CONFIG_MARCH_Z14_TUNE) += -mtune=z14 cflags-$(CONFIG_MARCH_Z15_TUNE) += -mtune=z15 +cflags-$(CONFIG_MARCH_Z16_TUNE) += -mtune=z16 cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 498bed9b261b..f6dfde577ce8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -499,11 +499,13 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set # CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DAVICOM is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_FUNGIBLE is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set @@ -588,13 +590,13 @@ CONFIG_MLX5_INFINIBAND=m CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_MLX5_VFIO_PCI=m CONFIG_VFIO_MDEV=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -690,6 +692,7 @@ CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y +CONFIG_HARDENED_USERCOPY=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y @@ -733,6 +736,7 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m @@ -786,7 +790,6 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y @@ -814,6 +817,7 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_KFENCE=y +CONFIG_KFENCE_DEFERRABLE=y CONFIG_KFENCE_STATIC_KEYS=y CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 61e36b999f67..706df3a4a867 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -490,11 +490,13 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set # CONFIG_NET_VENDOR_CORTINA is not set +# CONFIG_NET_VENDOR_DAVICOM is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set +# CONFIG_NET_VENDOR_FUNGIBLE is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set # CONFIG_NET_VENDOR_INTEL is not set @@ -578,13 +580,13 @@ CONFIG_MLX5_INFINIBAND=m CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_MLX5_VFIO_PCI=m CONFIG_VFIO_MDEV=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -720,6 +722,7 @@ CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_SHA3=m +CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m @@ -772,7 +775,6 @@ CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index c55c668dc3c7..a87fcc45e307 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -26,6 +26,7 @@ CONFIG_CRASH_DUMP=y # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set # CONFIG_GCC_PLUGINS is not set +# CONFIG_BLOCK_LEGACY_AUTOLOAD is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_COMPACTION is not set @@ -60,7 +61,6 @@ CONFIG_ZFCP=y # CONFIG_HID is not set # CONFIG_VIRTIO_MENU is not set # CONFIG_VHOST_MENU is not set -# CONFIG_SURFACE_PLATFORMS is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set @@ -71,10 +71,10 @@ CONFIG_LSM="yama,loadpin,safesetid,integrity" CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y # CONFIG_SYMBOLIC_ERRNAME is not set -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index eabab24b71dd..2f0a1cacdf85 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -58,7 +58,7 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, static inline bool on_thread_stack(void) { - return !(((unsigned long)(current->stack) ^ current_stack_pointer()) & ~(THREAD_SIZE - 1)); + return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); } #endif diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index eee8d96fb38e..ff1e25d515a8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -200,13 +200,7 @@ unsigned long __get_wchan(struct task_struct *p); /* Has task runtime instrumentation enabled ? */ #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb) -static __always_inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; - - asm volatile("la %0,0(15)" : "=a" (sp)); - return sp; -} +register unsigned long current_stack_pointer asm("r15"); static __always_inline unsigned short stap(void) { diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 275f4258fbd5..f8500191993d 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -46,7 +46,7 @@ struct stack_frame { }; /* - * Unlike current_stack_pointer() which simply returns current value of %r15 + * Unlike current_stack_pointer which simply contains the current value of %r15 * current_frame_address() returns function stack frame address, which matches * %r15 upon function invocation. It may differ from %r15 later if function * allocates stack for local variables or new stack frame to call other diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index b2ef014a9287..6ebf02e15c85 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -54,7 +54,7 @@ static void __do_machine_kdump(void *image) * This need to be done *after* s390_reset_system set the * prefix register of this CPU to zero */ - memcpy((void *) __LC_FPREGS_SAVE_AREA, + memcpy(absolute_pointer(__LC_FPREGS_SAVE_AREA), (void *)(prefix + __LC_FPREGS_SAVE_AREA), 512); __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 7a74ea5f7531..aa0e0e7fc773 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -283,6 +283,10 @@ static int __init setup_elf_platform(void) case 0x8562: strcpy(elf_platform, "z15"); break; + case 0x3931: + case 0x3932: + strcpy(elf_platform, "z16"); + break; } return 0; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 9b30beac904d..af96dc0549a4 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1334,11 +1334,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) hrtimer_start(&vcpu->arch.ckc_timer, sltime, HRTIMER_MODE_REL); VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_halt(vcpu); vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); hrtimer_cancel(&vcpu->arch.ckc_timer); return 0; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 156d1c25a3c1..da3dabda1a12 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4237,14 +4237,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) * We try to hold kvm->srcu during most of vcpu_run (except when run- * ning the guest), so that memslots (and other stuff) are protected */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); do { rc = vcpu_pre_run(vcpu); if (rc) break; - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * As PF_VCPU will be used in fault handler, between * guest_enter and guest_exit should be no uaccess. @@ -4281,12 +4281,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) __enable_cpu_timer_accounting(vcpu); guest_exit_irqoff(); local_irq_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); rc = vcpu_post_run(vcpu, exit_reason); } while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); return rc; } diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 7f7c0d6af2ce..cc7c9599f43e 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -137,12 +137,7 @@ static int kvm_s390_pv_alloc_vm(struct kvm *kvm) /* Allocate variable storage */ vlen = ALIGN(virt * ((npages * PAGE_SIZE) / HPAGE_SIZE), PAGE_SIZE); vlen += uv_info.guest_virt_base_stor_len; - /* - * The Create Secure Configuration Ultravisor Call does not support - * using large pages for the virtual memory area. - * This is a hardware limitation. - */ - kvm->arch.pv.stor_var = vmalloc_no_huge(vlen); + kvm->arch.pv.stor_var = vzalloc(vlen); if (!kvm->arch.pv.stor_var) goto out_err; return 0; diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index acda4b6fc851..dada78b92691 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -1091,7 +1091,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) handle_last_fault(vcpu, vsie_page); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* save current guest state of bp isolation override */ guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST); @@ -1133,7 +1133,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (!guest_bp_isolation) clear_thread_flag(TIF_ISOLATE_BP_GUEST); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (rc == -EINTR) { VCPU_EVENT(vcpu, 3, "%s", "machine check"); diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index 9bb067321ab4..5a053b393d5c 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -147,7 +147,7 @@ static __always_inline struct pt_regs fake_pt_regs(void) struct pt_regs regs; memset(®s, 0, sizeof(regs)); - regs.gprs[15] = current_stack_pointer(); + regs.gprs[15] = current_stack_pointer; asm volatile( "basr %[psw_addr],0\n" diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h index 41c6d734a474..adb6991d0455 100644 --- a/arch/sparc/include/asm/cacheflush_32.h +++ b/arch/sparc/include/asm/cacheflush_32.h @@ -35,6 +35,7 @@ #define flush_page_for_dma(addr) \ sparc32_cachetlb_ops->page_for_dma(addr) +struct page; void sparc_flush_page_to_ram(struct page *page); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b0142e01002e..4bed3abf444d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1866,7 +1866,7 @@ config X86_KERNEL_IBT code with them to make this happen. In addition to building the kernel with IBT, seal all functions that - are not indirect call targets, avoiding them ever becomming one. + are not indirect call targets, avoiding them ever becoming one. This requires LTO like objtool runs and will slow down the build. It does significantly reduce the number of ENDBR instructions in the diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4faac48ebec5..73d958522b6a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -337,6 +337,9 @@ SYM_CODE_END(ret_from_fork) call \cfunc + /* For some configurations \cfunc ends up being a noreturn. */ + REACHABLE + jmp error_return .endm diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e88791b420ee..fc7f458eb3de 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -302,7 +302,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), EVENT_EXTRA_END @@ -5536,7 +5536,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con /* Disabled fixed counters which are not in CPUID */ c->idxmsk64 &= intel_ctrl; - if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + /* + * Don't extend the pseudo-encoding to the + * generic counters + */ + if (!use_fixed_pseudo_encoding(c->code)) c->idxmsk64 |= (1ULL << num_counters) - 1; } c->idxmsk64 &= @@ -6212,6 +6216,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: /* * Alder Lake has 2 types of CPU, core and atom. * diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index c6262b154c3a..48e5db21142c 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,7 +40,7 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL + * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,49 +51,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL,SPR * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL + * ICL,TGL,RKL,ADL,RPL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL + * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, + * RPL,SPR * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL,SPR * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL + * KBL,CML,ICL,TGL,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL + * TNT,RKL,ADL,RPL * Scope: Package (physical package) * */ @@ -674,12 +675,14 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index e497da9bf427..7695dcae280e 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1828,6 +1828,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index f698a55bde81..4262351f52b6 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -79,6 +79,10 @@ #define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 #define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 #define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 +#define PCI_DEVICE_ID_INTEL_RPL_1_IMC 0xA700 +#define PCI_DEVICE_ID_INTEL_RPL_2_IMC 0xA702 +#define PCI_DEVICE_ID_INTEL_RPL_3_IMC 0xA706 +#define PCI_DEVICE_ID_INTEL_RPL_4_IMC 0xA709 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -1406,6 +1410,22 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_1_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 96c775abe31f..6d759f88315c 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -103,6 +103,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index c878fed3056f..fbcfec4dc4cc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -154,24 +154,24 @@ # define DEFINE_EXTABLE_TYPE_REG \ ".macro extable_type_reg type:req reg:req\n" \ - ".set found, 0\n" \ - ".set regnr, 0\n" \ + ".set .Lfound, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".set regnr, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".if (found != 1)\n" \ + ".if (.Lfound != 1)\n" \ ".error \"extable_type_reg: bad register argument\"\n" \ ".endif\n" \ ".endm\n" diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 4d20a293c6fd..aaf0cb0db4ae 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -78,9 +78,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ - __auto_type f = BUGFLAG_WARNING|(flags); \ + __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 7516e4199b3c..20fd0acd7d80 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -28,15 +28,13 @@ typedef u16 compat_ipc_pid_t; typedef __kernel_fsid_t compat_fsid_t; struct compat_stat { - compat_dev_t st_dev; - u16 __pad1; + u32 st_dev; compat_ino_t st_ino; compat_mode_t st_mode; compat_nlink_t st_nlink; __compat_uid_t st_uid; __compat_gid_t st_gid; - compat_dev_t st_rdev; - u16 __pad2; + u32 st_rdev; u32 st_size; u32 st_blksize; u32 st_blocks; diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 048b6d5aff50..def6ca121111 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -26,6 +26,7 @@ * _G - parts with extra graphics on * _X - regular server parts * _D - micro server parts + * _N,_P - other mobile parts * * Historical OPTDIFFs: * @@ -107,8 +108,10 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ +#define INTEL_FAM6_ALDERLAKE_N 0xBE #define INTEL_FAM6_RAPTORLAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE_P 0xBA /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index f6d91ecb8026..e9736af126b2 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -210,8 +210,6 @@ void __iomem *ioremap(resource_size_t offset, unsigned long size); extern void iounmap(volatile void __iomem *addr); #define iounmap iounmap -extern void set_iounmap_nonlazy(void); - #ifdef __KERNEL__ void memcpy_fromio(void *, const volatile void __iomem *, size_t); diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 96e4e9842dfc..da47f60a4650 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -118,6 +118,7 @@ KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) +KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) KVM_X86_OP(can_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c5fb4115176d..959d66b9be94 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1493,6 +1493,7 @@ struct kvm_x86_ops { int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + void (*guest_memory_reclaimed)(struct kvm *kvm); int (*get_msr_feature)(struct kvm_msr_entry *entry); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index d6bfdfb0f0af..0c3d3440fe27 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -131,10 +131,12 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool initrd_gone; +void microcode_bsp_resume(void); #else static inline void __init load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void reload_early_microcode(void) { } +static inline void microcode_bsp_resume(void) { } #endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index b85147d75626..d71c7e8b738d 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, /* Structs and defines for the X86 specific MSI message format */ typedef struct x86_msi_data { - u32 vector : 8, - delivery_mode : 3, - dest_mode_logical : 1, - reserved : 2, - active_low : 1, - is_level : 1; - - u32 dmar_subhandle; + union { + struct { + u32 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + reserved : 2, + active_low : 1, + is_level : 1; + }; + u32 dmar_subhandle; + }; } __attribute__ ((packed)) arch_msi_msg_data_t; #define arch_msi_msg_data x86_msi_data diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 0eb90d21049e..ee15311b6be1 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -128,9 +128,9 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ -/* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 -#define RNGDS_MITG_DIS BIT(0) +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a3c33b79fb86..13c0d63ed55e 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -38,9 +38,9 @@ #define arch_raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ - asm volatile("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ + asm ("add " __percpu_arg(1) ", %0" \ + : "=r" (tcp_ptr__) \ + : "m" (this_cpu_off), "0" (ptr)); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 58d9e4b1fa0a..b06e4c573add 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -241,6 +241,11 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + /* * We model BTS tracing as another fixed-mode PMC. * diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 40497a9020c6..407084d9fd99 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -559,10 +559,6 @@ static inline void update_page_count(int level, unsigned long pages) { } extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); - -struct mm_struct; -extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, - unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index ed4f8bb6c2d9..2d8dacd02643 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -26,6 +26,7 @@ ".align 4 \n" \ ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ STATIC_CALL_TRAMP_STR(name) ": \n" \ + ANNOTATE_NOENDBR \ insns " \n" \ ".byte 0x53, 0x43, 0x54 \n" \ ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ @@ -38,6 +39,8 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) #define ARCH_ADD_TRAMP_KEY(name) \ asm(".pushsection .static_call_tramp_key, \"a\" \n" \ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ed4417500700..e342ae4db3c4 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1855,6 +1855,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); + + tsx_ap_init(); } static __init int setup_noclflush(char *arg) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index ee6f23f7587d..2a8e584fc991 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -55,11 +55,10 @@ enum tsx_ctrl_states { extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; extern void __init tsx_init(void); -extern void tsx_enable(void); -extern void tsx_disable(void); -extern void tsx_clear_cpuid(void); +void tsx_ap_init(void); #else static inline void tsx_init(void) { } +static inline void tsx_ap_init(void) { } #endif /* CONFIG_CPU_SUP_INTEL */ extern void get_cpu_cap(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 8321c43554a1..f7a5370a9b3b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -717,13 +717,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_intel_misc_features(c); - if (tsx_ctrl_state == TSX_CTRL_ENABLE) - tsx_enable(); - else if (tsx_ctrl_state == TSX_CTRL_DISABLE) - tsx_disable(); - else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT) - tsx_clear_cpuid(); - split_lock_init(); bus_lock_init(); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index f955d25076ba..239ff5fcec6a 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -758,9 +758,9 @@ static struct subsys_interface mc_cpu_interface = { }; /** - * mc_bp_resume - Update boot CPU microcode during resume. + * microcode_bsp_resume - Update boot CPU microcode during resume. */ -static void mc_bp_resume(void) +void microcode_bsp_resume(void) { int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -772,7 +772,7 @@ static void mc_bp_resume(void) } static struct syscore_ops mc_syscore_ops = { - .resume = mc_bp_resume, + .resume = microcode_bsp_resume, }; static int mc_cpu_starting(unsigned int cpu) diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 9c7a5f049292..ec7bbac3a9f2 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -19,7 +19,7 @@ enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; -void tsx_disable(void) +static void tsx_disable(void) { u64 tsx; @@ -39,7 +39,7 @@ void tsx_disable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -void tsx_enable(void) +static void tsx_enable(void) { u64 tsx; @@ -58,7 +58,7 @@ void tsx_enable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -static bool __init tsx_ctrl_is_supported(void) +static bool tsx_ctrl_is_supported(void) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -84,7 +84,45 @@ static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) return TSX_CTRL_ENABLE; } -void tsx_clear_cpuid(void) +/* + * Disabling TSX is not a trivial business. + * + * First of all, there's a CPUID bit: X86_FEATURE_RTM_ALWAYS_ABORT + * which says that TSX is practically disabled (all transactions are + * aborted by default). When that bit is set, the kernel unconditionally + * disables TSX. + * + * In order to do that, however, it needs to dance a bit: + * + * 1. The first method to disable it is through MSR_TSX_FORCE_ABORT and + * the MSR is present only when *two* CPUID bits are set: + * + * - X86_FEATURE_RTM_ALWAYS_ABORT + * - X86_FEATURE_TSX_FORCE_ABORT + * + * 2. The second method is for CPUs which do not have the above-mentioned + * MSR: those use a different MSR - MSR_IA32_TSX_CTRL and disable TSX + * through that one. Those CPUs can also have the initially mentioned + * CPUID bit X86_FEATURE_RTM_ALWAYS_ABORT set and for those the same strategy + * applies: TSX gets disabled unconditionally. + * + * When either of the two methods are present, the kernel disables TSX and + * clears the respective RTM and HLE feature flags. + * + * An additional twist in the whole thing presents late microcode loading + * which, when done, may cause for the X86_FEATURE_RTM_ALWAYS_ABORT CPUID + * bit to be set after the update. + * + * A subsequent hotplug operation on any logical CPU except the BSP will + * cause for the supported CPUID feature bits to get re-detected and, if + * RTM and HLE get cleared all of a sudden, but, userspace did consult + * them before the update, then funny explosions will happen. Long story + * short: the kernel doesn't modify CPUID feature bits after booting. + * + * That's why, this function's call in init_intel() doesn't clear the + * feature flags. + */ +static void tsx_clear_cpuid(void) { u64 msr; @@ -97,6 +135,39 @@ void tsx_clear_cpuid(void) rdmsrl(MSR_TSX_FORCE_ABORT, msr); msr |= MSR_TFA_TSX_CPUID_CLEAR; wrmsrl(MSR_TSX_FORCE_ABORT, msr); + } else if (tsx_ctrl_is_supported()) { + rdmsrl(MSR_IA32_TSX_CTRL, msr); + msr |= TSX_CTRL_CPUID_CLEAR; + wrmsrl(MSR_IA32_TSX_CTRL, msr); + } +} + +/* + * Disable TSX development mode + * + * When the microcode released in Feb 2022 is applied, TSX will be disabled by + * default on some processors. MSR 0x122 (TSX_CTRL) and MSR 0x123 + * (IA32_MCU_OPT_CTRL) can be used to re-enable TSX for development, doing so is + * not recommended for production deployments. In particular, applying MD_CLEAR + * flows for mitigation of the Intel TSX Asynchronous Abort (TAA) transient + * execution attack may not be effective on these processors when Intel TSX is + * enabled with updated microcode. + */ +static void tsx_dev_mode_disable(void) +{ + u64 mcu_opt_ctrl; + + /* Check if RTM_ALLOW exists */ + if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() || + !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL)) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl); + + if (mcu_opt_ctrl & RTM_ALLOW) { + mcu_opt_ctrl &= ~RTM_ALLOW; + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl); + setup_force_cpu_cap(X86_FEATURE_RTM_ALWAYS_ABORT); } } @@ -105,14 +176,14 @@ void __init tsx_init(void) char arg[5] = {}; int ret; + tsx_dev_mode_disable(); + /* - * Hardware will always abort a TSX transaction if both CPUID bits - * RTM_ALWAYS_ABORT and TSX_FORCE_ABORT are set. In this case, it is - * better not to enumerate CPUID.RTM and CPUID.HLE bits. Clear them - * here. + * Hardware will always abort a TSX transaction when the CPUID bit + * RTM_ALWAYS_ABORT is set. In this case, it is better not to enumerate + * CPUID.RTM and CPUID.HLE bits. Clear them here. */ - if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT) && - boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) { + if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT)) { tsx_ctrl_state = TSX_CTRL_RTM_ALWAYS_ABORT; tsx_clear_cpuid(); setup_clear_cpu_cap(X86_FEATURE_RTM); @@ -175,3 +246,16 @@ void __init tsx_init(void) setup_force_cpu_cap(X86_FEATURE_HLE); } } + +void tsx_ap_init(void) +{ + tsx_dev_mode_disable(); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + else if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); + else if (tsx_ctrl_state == TSX_CTRL_RTM_ALWAYS_ABORT) + /* See comment over that function for more details. */ + tsx_clear_cpuid(); +} diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index a7f617a3981d..97529552dd24 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -37,7 +37,6 @@ static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, } else memcpy(buf, vaddr + offset, csize); - set_iounmap_nonlazy(); iounmap((void __iomem *)vaddr); return csize; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d0bb2b3fb305..b48ce07756ca 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -69,6 +69,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible; static int has_steal_clock = 0; +static int has_guest_poll = 0; /* * No need for any "IO delay" on KVM */ @@ -706,14 +707,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu) static int kvm_suspend(void) { + u64 val = 0; + kvm_guest_cpu_offline(false); +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) + rdmsrl(MSR_KVM_POLL_CONTROL, val); + has_guest_poll = !(val & 1); +#endif return 0; } static void kvm_resume(void) { kvm_cpu_online(raw_smp_processor_id()); + +#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL + if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll) + wrmsrl(MSR_KVM_POLL_CONTROL, 0); +#endif } static struct syscore_ops kvm_syscore_ops = { diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 531fb4cbb63f..aa72cefdd5be 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,10 +12,9 @@ enum insn_type { }; /* - * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax - * The REX.W cancels the effect of any data16. + * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ -static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 794fdef2501a..38185aedf7d1 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -339,11 +339,11 @@ static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, struct stack_info *info = &state->stack_info; void *addr = (void *)_addr; - if (!on_stack(info, addr, len) && - (get_stack_info(addr, state->task, info, &state->stack_mask))) - return false; + if (on_stack(info, addr, len)) + return true; - return true; + return !get_stack_info(addr, state->task, info, &state->stack_mask) && + on_stack(info, addr, len); } static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 732724ea5b10..0c1ba6aa0765 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1090,12 +1090,21 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) case 0x80000000: entry->eax = min(entry->eax, 0x80000021); /* - * Serializing LFENCE is reported in a multitude of ways, - * and NullSegClearsBase is not reported in CPUID on Zen2; - * help userspace by providing the CPUID leaf ourselves. + * Serializing LFENCE is reported in a multitude of ways, and + * NullSegClearsBase is not reported in CPUID on Zen2; help + * userspace by providing the CPUID leaf ourselves. + * + * However, only do it if the host has CPUID leaf 0x8000001d. + * QEMU thinks that it can query the host blindly for that + * CPUID leaf if KVM reports that it supports 0x8000001d or + * above. The processor merrily returns values from the + * highest Intel leaf which QEMU tries to use as the guest's + * 0x8000001d. Even worse, this can result in an infinite + * loop if said highest leaf has no subleaves indexed by ECX. */ - if (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) - || !static_cpu_has_bug(X86_BUG_NULL_SEG)) + if (entry->eax >= 0x8000001d && + (static_cpu_has(X86_FEATURE_LFENCE_RDTSC) + || !static_cpu_has_bug(X86_BUG_NULL_SEG))) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 2a53b6c9495c..e745f443b6a8 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -135,6 +135,15 @@ static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) return sample_period; } +static inline void pmc_update_sample_period(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event || pmc->is_paused) + return; + + perf_event_period(pmc->perf_event, + get_sample_period(pmc, pmc->counter)); +} + void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 47e8eaca1e90..136039fc6d01 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -279,6 +279,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { pmc->counter += data - pmc_read_counter(pmc); + pmc_update_sample_period(pmc); return 0; } /* MSR_EVNTSELn */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index b67ce873d5d2..94d62c9958b9 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2226,51 +2226,47 @@ int sev_cpu_init(struct svm_cpu_data *sd) * Pages used by hardware to hold guest encrypted state must be flushed before * returning them to the system. */ -static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va, - unsigned long len) +static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { + int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + /* - * If hardware enforced cache coherency for encrypted mappings of the - * same physical page is supported, nothing to do. + * Note! The address must be a kernel address, as regular page walk + * checks are performed by VM_PAGE_FLUSH, i.e. operating on a user + * address is non-deterministic and unsafe. This function deliberately + * takes a pointer to deter passing in a user address. */ - if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) - return; + unsigned long addr = (unsigned long)va; /* - * If the VM Page Flush MSR is supported, use it to flush the page - * (using the page virtual address and the guest ASID). + * If CPU enforced cache coherency for encrypted mappings of the + * same physical page is supported, use CLFLUSHOPT instead. NOTE: cache + * flush is still needed in order to work properly with DMA devices. */ - if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) { - struct kvm_sev_info *sev; - unsigned long va_start; - u64 start, stop; - - /* Align start and stop to page boundaries. */ - va_start = (unsigned long)va; - start = (u64)va_start & PAGE_MASK; - stop = PAGE_ALIGN((u64)va_start + len); - - if (start < stop) { - sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; + if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) { + clflush_cache_range(va, PAGE_SIZE); + return; + } - while (start < stop) { - wrmsrl(MSR_AMD64_VM_PAGE_FLUSH, - start | sev->asid); + /* + * VM Page Flush takes a host virtual address and a guest ASID. Fall + * back to WBINVD if this faults so as not to make any problems worse + * by leaving stale encrypted data in the cache. + */ + if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid))) + goto do_wbinvd; - start += PAGE_SIZE; - } + return; - return; - } +do_wbinvd: + wbinvd_on_all_cpus(); +} - WARN(1, "Address overflow, using WBINVD\n"); - } +void sev_guest_memory_reclaimed(struct kvm *kvm) +{ + if (!sev_guest(kvm)) + return; - /* - * Hardware should always have one of the above features, - * but if not, use WBINVD and issue a warning. - */ - WARN_ONCE(1, "Using WBINVD to flush guest memory\n"); wbinvd_on_all_cpus(); } @@ -2284,7 +2280,8 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) - sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE); + sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa); + __free_page(virt_to_page(svm->sev_es.vmsa)); if (svm->sev_es.ghcb_sa_free) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 3b49337998ec..63880b33ce37 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4709,6 +4709,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_ioctl = sev_mem_enc_ioctl, .mem_enc_register_region = sev_mem_enc_register_region, .mem_enc_unregister_region = sev_mem_enc_unregister_region, + .guest_memory_reclaimed = sev_guest_memory_reclaimed, .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 32220a1b0ea2..45a87b2a8b3c 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -642,6 +642,8 @@ int sev_mem_enc_unregister_region(struct kvm *kvm, struct kvm_enc_region *range); int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd); int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd); +void sev_guest_memory_reclaimed(struct kvm *kvm); + void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index a6688663da4d..f5cb18e00e78 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4640,6 +4640,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); } + if (vmx->nested.update_vmcs01_apicv_status) { + vmx->nested.update_vmcs01_apicv_status = false; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + if ((vm_exit_reason != -1) && (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) vmx->nested.need_vmcs12_to_shadow_sync = true; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 9db662399487..37e9eb32e3d9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -431,15 +431,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); - if (pmc->perf_event && !pmc->is_paused) - perf_event_period(pmc->perf_event, - get_sample_period(pmc, data)); + pmc_update_sample_period(pmc); return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 5fb37e75fd31..cbbcf97d9e66 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4174,6 +4174,11 @@ static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (is_guest_mode(vcpu)) { + vmx->nested.update_vmcs01_apicv_status = true; + return; + } + pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx)); if (cpu_has_secondary_exec_ctrls()) { if (kvm_vcpu_apicv_active(vcpu)) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 9c6bfcd84008..b98c7e96697a 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -183,6 +183,7 @@ struct nested_vmx { bool change_vmcs01_virtual_apic_mode; bool reload_vmcs01_apic_access_page; bool update_vmcs01_cpu_dirty_logging; + bool update_vmcs01_apicv_status; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8b62c9b7795e..bc507d6414f4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9164,7 +9164,7 @@ static void kvm_apicv_init(struct kvm *kvm) if (!enable_apicv) set_or_clear_apicv_inhibit(inhibits, - APICV_INHIBIT_REASON_ABSENT, true); + APICV_INHIBIT_REASON_DISABLE, true); } static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id) @@ -9954,6 +9954,11 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); } +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ + static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); +} + static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) @@ -10164,7 +10169,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* Store vcpu->apicv_active before vcpu->mode. */ smp_store_release(&vcpu->mode, IN_GUEST_MODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); /* * 1) We should set ->mode before checking ->requests. Please see @@ -10195,7 +10200,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) smp_wmb(); local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); r = 1; goto cancel_injection; } @@ -10313,7 +10318,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) local_irq_enable(); preempt_enable(); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); /* * Profile KVM exit RIPs: @@ -10343,7 +10348,7 @@ out: } /* Called within kvm->srcu read side. */ -static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +static inline int vcpu_block(struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10359,12 +10364,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (hv_timer) kvm_lapic_switch_to_sw_timer(vcpu); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED) kvm_vcpu_halt(vcpu); else kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (hv_timer) kvm_lapic_switch_to_hv_timer(vcpu); @@ -10406,7 +10411,6 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) static int vcpu_run(struct kvm_vcpu *vcpu) { int r; - struct kvm *kvm = vcpu->kvm; vcpu->arch.l1tf_flush_l1d = true; @@ -10414,7 +10418,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); } else { - r = vcpu_block(kvm, vcpu); + r = vcpu_block(vcpu); } if (r <= 0) @@ -10436,9 +10440,9 @@ static int vcpu_run(struct kvm_vcpu *vcpu) } if (__xfer_to_guest_mode_work_pending()) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); r = xfer_to_guest_mode_handle_work(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (r) return r; } @@ -10449,12 +10453,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { - int r; - - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - return r; + return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); } static int complete_emulated_pio(struct kvm_vcpu *vcpu) @@ -10546,7 +10545,6 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10554,7 +10552,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10566,9 +10564,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + kvm_vcpu_srcu_read_lock(vcpu); if (kvm_apic_accept_events(vcpu) < 0) { r = 0; @@ -10629,7 +10627,7 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_srcu_read_unlock(vcpu); kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); @@ -11047,6 +11045,9 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) struct kvm_vcpu *vcpu; unsigned long i; + if (!enable_apicv) + return; + down_write(&kvm->arch.apicv_update_lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -11258,8 +11259,21 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; - if (kvm_apicv_activated(vcpu->kvm)) + + /* + * Defer evaluating inhibits until the vCPU is first run, as + * this vCPU will not get notified of any changes until this + * vCPU is visible to other vCPUs (marked online and added to + * the set of vCPUs). Opportunistically mark APICv active as + * VMX in particularly is highly unlikely to have inhibits. + * Ignore the current per-VM APICv state so that vCPU creation + * is guaranteed to run with a deterministic value, the request + * will ensure the vCPU gets the correct state before VM-Entry. + */ + if (enable_apicv) { vcpu->arch.apicv_active = true; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } } else static_branch_inc(&kvm_has_noapic_vcpu); diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 8ca5ecf16dc4..9dec1b38a98f 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -53,12 +53,12 @@ SYM_FUNC_START(copy_user_generic_unrolled) ASM_STAC cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .Lcopy_user_short_string_bytes ALIGN_DESTINATION movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz .L_copy_short_string + jz copy_user_short_string 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -79,37 +79,11 @@ SYM_FUNC_START(copy_user_generic_unrolled) leaq 64(%rdi),%rdi decl %ecx jnz 1b -.L_copy_short_string: - movl %edx,%ecx - andl $7,%edx - shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movq %r8,(%rdi) - leaq 8(%rsi),%rsi - leaq 8(%rdi),%rdi - decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f - movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 21b -23: xor %eax,%eax - ASM_CLAC - RET + jmp copy_user_short_string 30: shll $6,%ecx addl %ecx,%edx - jmp 60f -40: leal (%rdx,%rcx,8),%edx - jmp 60f -50: movl %ecx,%edx -60: jmp .Lcopy_user_handle_tail /* ecx is zerorest also */ + jmp .Lcopy_user_handle_tail _ASM_EXTABLE_CPY(1b, 30b) _ASM_EXTABLE_CPY(2b, 30b) @@ -127,10 +101,6 @@ SYM_FUNC_START(copy_user_generic_unrolled) _ASM_EXTABLE_CPY(14b, 30b) _ASM_EXTABLE_CPY(15b, 30b) _ASM_EXTABLE_CPY(16b, 30b) - _ASM_EXTABLE_CPY(18b, 40b) - _ASM_EXTABLE_CPY(19b, 40b) - _ASM_EXTABLE_CPY(21b, 50b) - _ASM_EXTABLE_CPY(22b, 50b) SYM_FUNC_END(copy_user_generic_unrolled) EXPORT_SYMBOL(copy_user_generic_unrolled) @@ -191,7 +161,7 @@ EXPORT_SYMBOL(copy_user_generic_string) SYM_FUNC_START(copy_user_enhanced_fast_string) ASM_STAC /* CPUs without FSRM should avoid rep movsb for short copies */ - ALTERNATIVE "cmpl $64, %edx; jb .L_copy_short_string", "", X86_FEATURE_FSRM + ALTERNATIVE "cmpl $64, %edx; jb copy_user_short_string", "", X86_FEATURE_FSRM movl %edx,%ecx 1: rep movsb xorl %eax,%eax @@ -244,6 +214,53 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) SYM_CODE_END(.Lcopy_user_handle_tail) /* + * Finish memcpy of less than 64 bytes. #AC should already be set. + * + * Input: + * rdi destination + * rsi source + * rdx count (< 64) + * + * Output: + * eax uncopied bytes or 0 if successful. + */ +SYM_CODE_START_LOCAL(copy_user_short_string) + movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz .Lcopy_user_short_string_bytes +18: movq (%rsi),%r8 +19: movq %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz 18b +.Lcopy_user_short_string_bytes: + andl %edx,%edx + jz 23f + movl %edx,%ecx +21: movb (%rsi),%al +22: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 21b +23: xor %eax,%eax + ASM_CLAC + RET + +40: leal (%rdx,%rcx,8),%edx + jmp 60f +50: movl %ecx,%edx /* ecx is zerorest also */ +60: jmp .Lcopy_user_handle_tail + + _ASM_EXTABLE_CPY(18b, 40b) + _ASM_EXTABLE_CPY(19b, 40b) + _ASM_EXTABLE_CPY(21b, 50b) + _ASM_EXTABLE_CPY(22b, 50b) +SYM_CODE_END(copy_user_short_string) + +/* * copy_user_nocache - Uncached memory copy with exception handling * This will force destination out of cache for more performance. * diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index ecb2049c1273..b7dfd60243b7 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -48,6 +48,7 @@ SYM_FUNC_START(__put_user_1) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) + ENDBR ASM_STAC 1: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -62,6 +63,7 @@ SYM_FUNC_START(__put_user_2) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL) + ENDBR ASM_STAC 2: movw %ax,(%_ASM_CX) xor %ecx,%ecx @@ -76,6 +78,7 @@ SYM_FUNC_START(__put_user_4) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL) + ENDBR ASM_STAC 3: movl %eax,(%_ASM_CX) xor %ecx,%ecx @@ -90,6 +93,7 @@ SYM_FUNC_START(__put_user_8) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL) + ENDBR ASM_STAC 4: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5f87bab4fb8d..b2b2366885a2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -31,6 +31,7 @@ .align RETPOLINE_THUNK_SIZE SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ @@ -55,7 +56,6 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) .align RETPOLINE_THUNK_SIZE SYM_CODE_START(__x86_indirect_thunk_array) - ANNOTATE_NOENDBR // apply_retpolines #define GEN(reg) THUNK reg #include <asm/GEN-for-each-reg.h> diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0402a749f3a0..0ae6cf804197 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -119,7 +119,7 @@ void __memcpy_flushcache(void *_dst, const void *_src, size_t size) /* cache copy and flush to align dest */ if (!IS_ALIGNED(dest, 8)) { - unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest); + size_t len = min_t(size_t, size, ALIGN(dest, 8) - dest); memcpy((void *) dest, (void *) source, len); clean_cache_range((void *) dest, len); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index abf5ed76e4b7..0656db33574d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -638,17 +638,6 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) } EXPORT_SYMBOL_GPL(lookup_address); -/* - * Lookup the page table entry for a virtual address in a given mm. Return a - * pointer to the entry and the level of the mapping. - */ -pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, - unsigned int *level) -{ - return lookup_address_in_pgd(pgd_offset(mm, address), address, level); -} -EXPORT_SYMBOL_GPL(lookup_address_in_mm); - static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, unsigned int *level) { diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb4d91d5365..d400b6d9d246 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -855,13 +855,11 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu) +static bool tlb_is_not_lazy(int cpu, void *data) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } -static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); @@ -890,36 +888,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, * up on the new contents of what used to be page tables, while * doing a speculative memory access. */ - if (info->freed_tables) { + if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); - } else { - /* - * Although we could have used on_each_cpu_cond_mask(), - * open-coding it has performance advantages, as it eliminates - * the need for indirect calls or retpolines. In addition, it - * allows to use a designated cpumask for evaluating the - * condition, instead of allocating one. - * - * This code works under the assumption that there are no nested - * TLB flushes, an assumption that is already made in - * flush_tlb_mm_range(). - * - * cond_cpumask is logically a stack-local variable, but it is - * more efficient to have it off the stack and not to allocate - * it on demand. Preemption is disabled and this code is - * non-reentrant. - */ - struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask); - int cpu; - - cpumask_clear(cond_cpumask); - - for_each_cpu(cpu, cpumask) { - if (tlb_is_not_lazy(cpu)) - __cpumask_set_cpu(cpu, cond_cpumask); - } - on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true); - } + else + on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + (void *)info, 1, cpumask); } void flush_tlb_multi(const struct cpumask *cpumask, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8fe35ed11fd6..16b6efacf7c6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,6 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else #endif diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9bb1e2941179..b94f727251b6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -467,7 +467,6 @@ static __init void xen_setup_pci_msi(void) else xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs; - pci_msi_ignore_mask = 1; } else if (xen_hvm_domain()) { xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs; xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs; @@ -481,6 +480,11 @@ static __init void xen_setup_pci_msi(void) * in allocating the native domain and never use it. */ x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain; + /* + * With XEN PIRQ/Eventchannels in use PCI/MSI[-X] masking is solely + * controlled by the hypervisor. + */ + pci_msi_ignore_mask = 1; } #else /* CONFIG_PCI_MSI */ diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 72c1e42d121d..7fe564eaf228 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -50,6 +50,7 @@ #define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) SYM_CODE_START_LOCAL(pvh_start_xen) + UNWIND_HINT_EMPTY cld lgdt (_pa(gdt)) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9f2b251e83c5..bb176c72891c 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -25,6 +25,7 @@ #include <asm/cpu.h> #include <asm/mmu_context.h> #include <asm/cpu_device_id.h> +#include <asm/microcode.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -40,7 +41,8 @@ static void msr_save_context(struct saved_context *ctxt) struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { - msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + if (msr->valid) + rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } @@ -261,11 +263,18 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); - msr_restore_context(ctxt); c = &cpu_data(smp_processor_id()); if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) init_ia32_feat_ctl(c); + + microcode_bsp_resume(); + + /* + * This needs to happen after the microcode has been updated upon resume + * because some of the MSRs are "emulated" in microcode. + */ + msr_restore_context(ctxt); } /* Needed by apm.c */ @@ -424,8 +433,10 @@ static int msr_build_context(const u32 *msr_id, const int num) } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + u64 dummy; + msr_array[i].info.msr_no = msr_id[j]; - msr_array[i].valid = false; + msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; @@ -500,10 +511,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c) return ret; } +static void pm_save_spec_msr(void) +{ + u32 spec_msr_id[] = { + MSR_IA32_SPEC_CTRL, + MSR_IA32_TSX_CTRL, + MSR_TSX_FORCE_ABORT, + MSR_IA32_MCU_OPT_CTRL, + MSR_AMD64_LS_CFG, + }; + + msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); + pm_save_spec_msr(); return 0; } diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index ac17196e2518..3a2cd93bf059 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -45,6 +45,7 @@ SYM_CODE_END(hypercall_page) __INIT SYM_CODE_START(startup_xen) UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR cld /* Clear .bss */ diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index 45cc0ae0af6f..c7b9f12896f2 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -29,7 +29,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lsave_cp_regs_cp##x: \ - xchal_cp##x##_store a2 a4 a5 a6 a7; \ + xchal_cp##x##_store a2 a3 a4 a5 a6; \ jx a0; \ .endif @@ -46,7 +46,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lload_cp_regs_cp##x: \ - xchal_cp##x##_load a2 a4 a5 a6 a7; \ + xchal_cp##x##_load a2 a3 a4 a5 a6; \ jx a0; \ .endif diff --git a/arch/xtensa/kernel/jump_label.c b/arch/xtensa/kernel/jump_label.c index 0dde21e0d3de..ad1841cecdfb 100644 --- a/arch/xtensa/kernel/jump_label.c +++ b/arch/xtensa/kernel/jump_label.c @@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) { struct patch *patch = data; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { local_patch_text(patch->addr, patch->data, patch->sz); atomic_inc(&patch->cpu_count); } else { diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 81d7c7e8f7e9..10b79d3c74e0 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -36,24 +36,19 @@ static void rs_poll(struct timer_list *); static struct tty_driver *serial_driver; static struct tty_port serial_port; static DEFINE_TIMER(serial_timer, rs_poll); -static DEFINE_SPINLOCK(timer_lock); static int rs_open(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock_bh(&timer_lock); return 0; } static void rs_close(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) del_timer_sync(&serial_timer); - spin_unlock_bh(&timer_lock); } @@ -73,8 +68,6 @@ static void rs_poll(struct timer_list *unused) int rd = 1; unsigned char c; - spin_lock(&timer_lock); - while (simc_poll(0)) { rd = simc_read(0, &c, 1); if (rd <= 0) @@ -87,7 +80,6 @@ static void rs_poll(struct timer_list *unused) tty_flip_buffer_push(port); if (rd) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock(&timer_lock); } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 2e0dd68a3cbe..1f62dbdc521f 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -569,7 +569,7 @@ static bool bfqq_request_over_limit(struct bfq_queue *bfqq, int limit) struct bfq_entity *entity = &bfqq->entity; struct bfq_entity *inline_entities[BFQ_LIMIT_INLINE_DEPTH]; struct bfq_entity **entities = inline_entities; - int depth, level; + int depth, level, alloc_depth = BFQ_LIMIT_INLINE_DEPTH; int class_idx = bfqq->ioprio_class - 1; struct bfq_sched_data *sched_data; unsigned long wsum; @@ -578,15 +578,21 @@ static bool bfqq_request_over_limit(struct bfq_queue *bfqq, int limit) if (!entity->on_st_or_in_serv) return false; +retry: + spin_lock_irq(&bfqd->lock); /* +1 for bfqq entity, root cgroup not included */ depth = bfqg_to_blkg(bfqq_group(bfqq))->blkcg->css.cgroup->level + 1; - if (depth > BFQ_LIMIT_INLINE_DEPTH) { + if (depth > alloc_depth) { + spin_unlock_irq(&bfqd->lock); + if (entities != inline_entities) + kfree(entities); entities = kmalloc_array(depth, sizeof(*entities), GFP_NOIO); if (!entities) return false; + alloc_depth = depth; + goto retry; } - spin_lock_irq(&bfqd->lock); sched_data = entity->sched_data; /* Gather our ancestors as we need to traverse them in reverse order */ level = 0; diff --git a/block/bio.c b/block/bio.c index cdd7b2915c53..4259125e16ab 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1598,7 +1598,7 @@ EXPORT_SYMBOL(bio_split); void bio_trim(struct bio *bio, sector_t offset, sector_t size) { if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS || - offset + size > bio->bi_iter.bi_size)) + offset + size > bio_sectors(bio))) return; size <<= 9; diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 70a0a3d680a3..9bd670999d0a 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2322,7 +2322,17 @@ static void ioc_timer_fn(struct timer_list *timer) iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); - } else { + } else if (!iocg->abs_vdebt) { + /* + * @iocg doesn't have enough to donate. Reset + * its inuse to active. + * + * Don't reset debtors as their inuse's are + * owned by debt handling. This shouldn't affect + * donation calculuation in any meaningful way + * as @iocg doesn't have a meaningful amount of + * share anyway. + */ TRACE_IOCG_PATH(inuse_shortage, iocg, &now, iocg->inuse, iocg->active, iocg->hweight_inuse, new_hwi); diff --git a/block/blk-mq.c b/block/blk-mq.c index ed3ed86f7dd2..84d749511f55 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -794,7 +794,8 @@ bool blk_update_request(struct request *req, blk_status_t error, #endif if (unlikely(error && !blk_rq_is_passthrough(req) && - !(req->rq_flags & RQF_QUIET))) { + !(req->rq_flags & RQF_QUIET)) && + !test_bit(GD_DEAD, &req->q->disk->state)) { blk_print_req_error(req, error); trace_block_rq_error(req, error, nr_bytes); } @@ -1130,14 +1131,7 @@ void blk_mq_start_request(struct request *rq) trace_block_rq_issue(rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { - u64 start_time; -#ifdef CONFIG_BLK_CGROUP - if (rq->bio) - start_time = bio_issue_time(&rq->bio->bi_issue); - else -#endif - start_time = ktime_get_ns(); - rq->io_start_time_ns = start_time; + rq->io_start_time_ns = ktime_get_ns(); rq->stats_sectors = blk_rq_sectors(rq); rq->rq_flags |= RQF_STATS; rq_qos_issue(q, rq); diff --git a/block/ioctl.c b/block/ioctl.c index 4a86340133e4..f8703db99c73 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -629,7 +629,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return compat_put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: - if (bdev_nr_sectors(bdev) > ~0UL) + if (bdev_nr_sectors(bdev) > ~(compat_ulong_t)0) return -EFBIG; return compat_put_ulong(argp, bdev_nr_sectors(bdev)); diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 32b20efff5f8..eb95e188d62b 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -96,11 +96,6 @@ static const struct dmi_system_id processor_power_dmi_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME,"L8400B series Notebook PC")}, (void *)1}, - /* T40 can not handle C3 idle state */ - { set_max_cstate, "IBM ThinkPad T40", { - DMI_MATCH(DMI_SYS_VENDOR, "IBM"), - DMI_MATCH(DMI_PRODUCT_NAME, "23737CU")}, - (void *)2}, {}, }; @@ -570,8 +565,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) { struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - if (cx->type == ACPI_STATE_C3) - ACPI_FLUSH_CPU_CACHE(); + ACPI_FLUSH_CPU_CACHE(); while (1) { @@ -796,7 +790,8 @@ static int acpi_processor_setup_cstates(struct acpi_processor *pr) if (cx->type == ACPI_STATE_C1 || cx->type == ACPI_STATE_C2 || cx->type == ACPI_STATE_C3) { state->enter_dead = acpi_idle_play_dead; - drv->safe_state_index = count; + if (cx->type != ACPI_STATE_C3) + drv->safe_state_index = count; } /* * Halt-induced C1 is not good for ->enter_s2idle, because it diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 9efbfe087de7..762b61f67e6c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -588,19 +588,6 @@ static struct acpi_device *handle_to_device(acpi_handle handle, return adev; } -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device) -{ - if (!device) - return -EINVAL; - - *device = handle_to_device(handle, NULL); - if (!*device) - return -ENODEV; - - return 0; -} -EXPORT_SYMBOL(acpi_bus_get_device); - /** * acpi_fetch_acpi_dev - Retrieve ACPI device object. * @handle: ACPI handle associated with the requested ACPI device object. diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 8351c5638880..f3b639e89dd8 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2295,6 +2295,7 @@ static int binder_do_deferred_txn_copies(struct binder_alloc *alloc, { int ret = 0; struct binder_sg_copy *sgc, *tmpsgc; + struct binder_ptr_fixup *tmppf; struct binder_ptr_fixup *pf = list_first_entry_or_null(pf_head, struct binder_ptr_fixup, node); @@ -2349,7 +2350,11 @@ static int binder_do_deferred_txn_copies(struct binder_alloc *alloc, list_del(&sgc->node); kfree(sgc); } - BUG_ON(!list_empty(pf_head)); + list_for_each_entry_safe(pf, tmppf, pf_head, node) { + BUG_ON(pf->skip_size == 0); + list_del(&pf->node); + kfree(pf); + } BUG_ON(!list_empty(sgc_head)); return ret > 0 ? -EINVAL : ret; @@ -2486,6 +2491,9 @@ static int binder_translate_fd_array(struct list_head *pf_head, struct binder_proc *proc = thread->proc; int ret; + if (fda->num_fds == 0) + return 0; + fd_buf_size = sizeof(u32) * fda->num_fds; if (fda->num_fds >= SIZE_MAX / sizeof(u32)) { binder_user_error("%d:%d got transaction with invalid number of fds (%lld)\n", diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index e5641e6c52ee..bb45a9c00514 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -115,14 +115,16 @@ config SATA_AHCI If unsure, say N. -config SATA_LPM_POLICY +config SATA_MOBILE_LPM_POLICY int "Default SATA Link Power Management policy for low power chipsets" range 0 4 default 0 depends on SATA_AHCI help Select the Default SATA Link Power Management (LPM) policy to use - for chipsets / "South Bridges" designated as supporting low power. + for chipsets / "South Bridges" supporting low-power modes. Such + chipsets are typically found on most laptops but desktops and + servers now also widely use chipsets supporting low power modes. The value set has the following meanings: 0 => Keep firmware settings diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 84456c05e845..397dfd27c90d 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1595,7 +1595,7 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, static void ahci_update_initial_lpm_policy(struct ata_port *ap, struct ahci_host_priv *hpriv) { - int policy = CONFIG_SATA_LPM_POLICY; + int policy = CONFIG_SATA_MOBILE_LPM_POLICY; /* Ignore processing for chipsets that don't use policy */ diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 6ead58c1b6e5..ad11a4c52fbe 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -236,7 +236,7 @@ enum { AHCI_HFLAG_NO_WRITE_TO_RO = (1 << 24), /* don't write to read only registers */ AHCI_HFLAG_USE_LPM_POLICY = (1 << 25), /* chipset that should use - SATA_LPM_POLICY + SATA_MOBILE_LPM_POLICY as default lpm_policy */ AHCI_HFLAG_SUSPEND_PHYS = (1 << 26), /* handle PHYs during suspend/resume */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cceedde51126..ca64837641be 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4014,6 +4014,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Samsung SSD 840 EVO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_NO_DMA_LOG | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b3be7a8f5bea..b1666adc1c3a 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1634,7 +1634,7 @@ EXPORT_SYMBOL_GPL(ata_sff_interrupt); void ata_sff_lost_interrupt(struct ata_port *ap) { - u8 status; + u8 status = 0; struct ata_queued_cmd *qc; /* Only one outstanding command per SFF channel */ diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c index 0c5a51970fbf..014ccb0f45dc 100644 --- a/drivers/ata/pata_marvell.c +++ b/drivers/ata/pata_marvell.c @@ -77,6 +77,8 @@ static int marvell_cable_detect(struct ata_port *ap) switch(ap->port_no) { case 0: + if (!ap->ioaddr.bmdma_addr) + return ATA_CBL_PATA_UNK; if (ioread8(ap->ioaddr.bmdma_addr + 1) & 1) return ATA_CBL_PATA40; return ATA_CBL_PATA80; diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index bec33d781ae0..e3263e961045 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -137,7 +137,11 @@ struct sata_dwc_device { #endif }; -#define SATA_DWC_QCMD_MAX 32 +/* + * Allow one extra special slot for commands and DMA management + * to account for libata internal commands. + */ +#define SATA_DWC_QCMD_MAX (ATA_MAX_QUEUE + 1) struct sata_dwc_device_port { struct sata_dwc_device *hsdev; diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 1d6636ebaac5..f73b836047cf 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -667,6 +667,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu) core_mask = &cpu_topology[cpu].llc_sibling; } + /* + * For systems with no shared cpu-side LLC but with clusters defined, + * extend core_mask to cluster_siblings. The sched domain builder will + * then remove MC as redundant with CLS if SCHED_CLUSTER is enabled. + */ + if (IS_ENABLED(CONFIG_SCHED_CLUSTER) && + cpumask_subset(core_mask, &cpu_topology[cpu].cluster_sibling)) + core_mask = &cpu_topology[cpu].cluster_sibling; + return core_mask; } @@ -684,7 +693,7 @@ void update_siblings_masks(unsigned int cpuid) for_each_online_cpu(cpu) { cpu_topo = &cpu_topology[cpu]; - if (cpuid_topo->llc_id == cpu_topo->llc_id) { + if (cpu_topo->llc_id != -1 && cpuid_topo->llc_id == cpu_topo->llc_id) { cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); } diff --git a/drivers/base/dd.c b/drivers/base/dd.c index af6bea56f4e2..3fc3b5940bb3 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -296,6 +296,7 @@ int driver_deferred_probe_check_state(struct device *dev) return -EPROBE_DEFER; } +EXPORT_SYMBOL_GPL(driver_deferred_probe_check_state); static void deferred_probe_timeout_work_func(struct work_struct *work) { diff --git a/drivers/base/topology.c b/drivers/base/topology.c index e9d1efcda89b..ac6ad9ab67f9 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -152,9 +152,19 @@ static struct attribute *default_attrs[] = { NULL }; +static umode_t topology_is_visible(struct kobject *kobj, + struct attribute *attr, int unused) +{ + if (attr == &dev_attr_ppin.attr && !topology_ppin(kobj_to_dev(kobj)->id)) + return 0; + + return attr->mode; +} + static const struct attribute_group topology_attr_group = { .attrs = default_attrs, .bin_attrs = bin_attrs, + .is_visible = topology_is_visible, .name = "topology" }; diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 519b6d38d4df..fdb81f2794cd 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -33,6 +33,22 @@ config BLK_DEV_FD To compile this driver as a module, choose M here: the module will be called floppy. +config BLK_DEV_FD_RAWCMD + bool "Support for raw floppy disk commands (DEPRECATED)" + depends on BLK_DEV_FD + help + If you want to use actual physical floppies and expect to do + special low-level hardware accesses to them (access and use + non-standard formats, for example), then enable this. + + Note that the code enabled by this option is rarely used and + might be unstable or insecure, and distros should not enable it. + + Note: FDRAWCMD is deprecated and will be removed from the kernel + in the near future. + + If unsure, say N. + config AMIGA_FLOPPY tristate "Amiga floppy support" depends on AMIGA diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 4b55e864a0a3..4d3efaa20b7b 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1638,22 +1638,22 @@ struct sib_info { }; void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib); -extern void notify_resource_state(struct sk_buff *, +extern int notify_resource_state(struct sk_buff *, unsigned int, struct drbd_resource *, struct resource_info *, enum drbd_notification_type); -extern void notify_device_state(struct sk_buff *, +extern int notify_device_state(struct sk_buff *, unsigned int, struct drbd_device *, struct device_info *, enum drbd_notification_type); -extern void notify_connection_state(struct sk_buff *, +extern int notify_connection_state(struct sk_buff *, unsigned int, struct drbd_connection *, struct connection_info *, enum drbd_notification_type); -extern void notify_peer_device_state(struct sk_buff *, +extern int notify_peer_device_state(struct sk_buff *, unsigned int, struct drbd_peer_device *, struct peer_device_info *, diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 9676a1d214bc..4b0b25cc916e 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2719,6 +2719,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); blk_queue_write_cache(disk->queue, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ @@ -2773,12 +2774,12 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig if (init_submitter(device)) { err = ERR_NOMEM; - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; } err = add_disk(disk); if (err) - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; /* inherit the connection state */ device->state.conn = first_connection(resource)->cstate; @@ -2792,8 +2793,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_debugfs_device_add(device); return NO_ERROR; -out_idr_remove_vol: - idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: for_each_connection(connection, resource) { peer_device = idr_remove(&connection->peer_devices, vnr); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 02030c9c4d3b..b7216c186ba4 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -4549,7 +4549,7 @@ static int nla_put_notification_header(struct sk_buff *msg, return drbd_notification_header_to_skb(msg, &nh, true); } -void notify_resource_state(struct sk_buff *skb, +int notify_resource_state(struct sk_buff *skb, unsigned int seq, struct drbd_resource *resource, struct resource_info *resource_info, @@ -4591,16 +4591,17 @@ void notify_resource_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_device_state(struct sk_buff *skb, +int notify_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_device *device, struct device_info *device_info, @@ -4640,16 +4641,17 @@ void notify_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_connection_state(struct sk_buff *skb, +int notify_connection_state(struct sk_buff *skb, unsigned int seq, struct drbd_connection *connection, struct connection_info *connection_info, @@ -4689,16 +4691,17 @@ void notify_connection_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(connection, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_peer_device_state(struct sk_buff *skb, +int notify_peer_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device *peer_device, struct peer_device_info *peer_device_info, @@ -4739,13 +4742,14 @@ void notify_peer_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(peer_device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } void notify_helper(enum drbd_notification_type type, @@ -4796,7 +4800,7 @@ fail: err, seq); } -static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) +static int notify_initial_state_done(struct sk_buff *skb, unsigned int seq) { struct drbd_genlmsghdr *dh; int err; @@ -4810,11 +4814,12 @@ static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) if (nla_put_notification_header(skb, NOTIFY_EXISTS)) goto nla_put_failure; genlmsg_end(skb, dh); - return; + return 0; nla_put_failure: nlmsg_free(skb); pr_err("Error %d sending event. Event seq:%u\n", err, seq); + return err; } static void free_state_changes(struct list_head *list) @@ -4841,6 +4846,7 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) unsigned int seq = cb->args[2]; unsigned int n; enum drbd_notification_type flags = 0; + int err = 0; /* There is no need for taking notification_mutex here: it doesn't matter if the initial state events mix with later state chage @@ -4849,32 +4855,32 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) cb->args[5]--; if (cb->args[5] == 1) { - notify_initial_state_done(skb, seq); + err = notify_initial_state_done(skb, seq); goto out; } n = cb->args[4]++; if (cb->args[4] < cb->args[3]) flags |= NOTIFY_CONTINUES; if (n < 1) { - notify_resource_state_change(skb, seq, state_change->resource, + err = notify_resource_state_change(skb, seq, state_change->resource, NOTIFY_EXISTS | flags); goto next; } n--; if (n < state_change->n_connections) { - notify_connection_state_change(skb, seq, &state_change->connections[n], + err = notify_connection_state_change(skb, seq, &state_change->connections[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_connections; if (n < state_change->n_devices) { - notify_device_state_change(skb, seq, &state_change->devices[n], + err = notify_device_state_change(skb, seq, &state_change->devices[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_devices; if (n < state_change->n_devices * state_change->n_connections) { - notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], + err = notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], NOTIFY_EXISTS | flags); goto next; } @@ -4889,7 +4895,10 @@ next: cb->args[4] = 0; } out: - return skb->len; + if (err) + return err; + else + return skb->len; } int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index b8a27818ab3f..4ee11aef6672 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -1537,7 +1537,7 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, return rv; } -void notify_resource_state_change(struct sk_buff *skb, +int notify_resource_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_resource_state_change *resource_state_change, enum drbd_notification_type type) @@ -1550,10 +1550,10 @@ void notify_resource_state_change(struct sk_buff *skb, .res_susp_fen = resource_state_change->susp_fen[NEW], }; - notify_resource_state(skb, seq, resource, &resource_info, type); + return notify_resource_state(skb, seq, resource, &resource_info, type); } -void notify_connection_state_change(struct sk_buff *skb, +int notify_connection_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_connection_state_change *connection_state_change, enum drbd_notification_type type) @@ -1564,10 +1564,10 @@ void notify_connection_state_change(struct sk_buff *skb, .conn_role = connection_state_change->peer_role[NEW], }; - notify_connection_state(skb, seq, connection, &connection_info, type); + return notify_connection_state(skb, seq, connection, &connection_info, type); } -void notify_device_state_change(struct sk_buff *skb, +int notify_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_device_state_change *device_state_change, enum drbd_notification_type type) @@ -1577,10 +1577,10 @@ void notify_device_state_change(struct sk_buff *skb, .dev_disk_state = device_state_change->disk_state[NEW], }; - notify_device_state(skb, seq, device, &device_info, type); + return notify_device_state(skb, seq, device, &device_info, type); } -void notify_peer_device_state_change(struct sk_buff *skb, +int notify_peer_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device_state_change *p, enum drbd_notification_type type) @@ -1594,7 +1594,7 @@ void notify_peer_device_state_change(struct sk_buff *skb, .peer_resync_susp_dependency = p->resync_susp_dependency[NEW], }; - notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); + return notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); } static void broadcast_state_change(struct drbd_state_change *state_change) @@ -1602,7 +1602,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change) struct drbd_resource_state_change *resource_state_change = &state_change->resource[0]; bool resource_state_has_changed; unsigned int n_device, n_connection, n_peer_device, n_peer_devices; - void (*last_func)(struct sk_buff *, unsigned int, void *, + int (*last_func)(struct sk_buff *, unsigned int, void *, enum drbd_notification_type) = NULL; void *last_arg = NULL; diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h index ba80f612d6ab..d5b0479bc9a6 100644 --- a/drivers/block/drbd/drbd_state_change.h +++ b/drivers/block/drbd/drbd_state_change.h @@ -44,19 +44,19 @@ extern struct drbd_state_change *remember_old_state(struct drbd_resource *, gfp_ extern void copy_old_to_new_state_change(struct drbd_state_change *); extern void forget_state_change(struct drbd_state_change *); -extern void notify_resource_state_change(struct sk_buff *, +extern int notify_resource_state_change(struct sk_buff *, unsigned int, struct drbd_resource_state_change *, enum drbd_notification_type type); -extern void notify_connection_state_change(struct sk_buff *, +extern int notify_connection_state_change(struct sk_buff *, unsigned int, struct drbd_connection_state_change *, enum drbd_notification_type type); -extern void notify_device_state_change(struct sk_buff *, +extern int notify_device_state_change(struct sk_buff *, unsigned int, struct drbd_device_state_change *, enum drbd_notification_type type); -extern void notify_peer_device_state_change(struct sk_buff *, +extern int notify_peer_device_state_change(struct sk_buff *, unsigned int, struct drbd_peer_device_state_change *, enum drbd_notification_type type); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 8c647532e3ce..d5b9ff9bcbb2 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2982,6 +2982,8 @@ static const char *drive_name(int type, int drive) return "(null)"; } +#ifdef CONFIG_BLK_DEV_FD_RAWCMD + /* raw commands */ static void raw_cmd_done(int flag) { @@ -3181,6 +3183,35 @@ static int raw_cmd_ioctl(int cmd, void __user *param) return ret; } +static int floppy_raw_cmd_ioctl(int type, int drive, int cmd, + void __user *param) +{ + int ret; + + pr_warn_once("Note: FDRAWCMD is deprecated and will be removed from the kernel in the near future.\n"); + + if (type) + return -EINVAL; + if (lock_fdc(drive)) + return -EINTR; + set_floppy(drive); + ret = raw_cmd_ioctl(cmd, param); + if (ret == -EINTR) + return -EINTR; + process_fd_request(); + return ret; +} + +#else /* CONFIG_BLK_DEV_FD_RAWCMD */ + +static int floppy_raw_cmd_ioctl(int type, int drive, int cmd, + void __user *param) +{ + return -EOPNOTSUPP; +} + +#endif + static int invalidate_drive(struct block_device *bdev) { /* invalidate the buffer track to force a reread */ @@ -3369,7 +3400,6 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int { int drive = (long)bdev->bd_disk->private_data; int type = ITYPE(drive_state[drive].fd_device); - int i; int ret; int size; union inparam { @@ -3520,16 +3550,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int outparam = &write_errors[drive]; break; case FDRAWCMD: - if (type) - return -EINVAL; - if (lock_fdc(drive)) - return -EINTR; - set_floppy(drive); - i = raw_cmd_ioctl(cmd, (void __user *)param); - if (i == -EINTR) - return -EINTR; - process_fd_request(); - return i; + return floppy_raw_cmd_ioctl(type, drive, cmd, (void __user *)param); case FDTWADDLE: if (lock_fdc(drive)) return -EINTR; diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 05b1120e6623..c441a4972064 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1600,7 +1600,7 @@ static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) * Only fake timeouts need to execute blk_mq_complete_request() here. */ cmd->error = BLK_STS_TIMEOUT; - if (cmd->fake_timeout) + if (cmd->fake_timeout || hctx->type == HCTX_TYPE_POLL) blk_mq_complete_request(rq); return BLK_EH_DONE; } diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c index 5e0e4393ce4d..0cfe859a4ac4 100644 --- a/drivers/bus/fsl-mc/fsl-mc-msi.c +++ b/drivers/bus/fsl-mc/fsl-mc-msi.c @@ -224,8 +224,12 @@ int fsl_mc_msi_domain_alloc_irqs(struct device *dev, unsigned int irq_count) if (error) return error; + msi_lock_descs(dev); if (msi_first_desc(dev, MSI_DESC_ALL)) - return -EINVAL; + error = -EINVAL; + msi_unlock_descs(dev); + if (error) + return error; /* * NOTE: Calling this function will trigger the invocation of the diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index 60fbd42041dd..828c66bbaa67 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -352,8 +352,7 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, pdev = of_find_device_by_node(rd->dn); if (!pdev) { - dev_err(&pdev->dev, - "Could not find platform device for '%pOF'\n", + pr_err("Could not find platform device for '%pOF'\n", rd->dn); ret = notifier_from_errno(-EINVAL); @@ -370,7 +369,7 @@ static int of_weim_notify(struct notifier_block *nb, unsigned long action, return ret; } -struct notifier_block weim_of_notifier = { +static struct notifier_block weim_of_notifier = { .notifier_call = of_weim_notify, }; #endif /* IS_ENABLED(CONFIG_OF_DYNAMIC) */ diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 9527b7d63840..541ced27d941 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -1060,6 +1060,7 @@ static int __maybe_unused mhi_pci_freeze(struct device *dev) * the intermediate restore kernel reinitializes MHI device with new * context. */ + flush_work(&mhi_pdev->recovery_work); if (test_and_clear_bit(MHI_PCI_DEV_STARTED, &mhi_pdev->status)) { mhi_power_down(mhi_cntrl, true); mhi_unprepare_after_power_down(mhi_cntrl); @@ -1085,6 +1086,7 @@ static const struct dev_pm_ops mhi_pci_pm_ops = { .resume = mhi_pci_resume, .freeze = mhi_pci_freeze, .thaw = mhi_pci_restore, + .poweroff = mhi_pci_freeze, .restore = mhi_pci_restore, #endif }; diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 4566e730ef2b..60b082fe2ed0 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -227,6 +227,8 @@ static struct sunxi_rsb_device *sunxi_rsb_device_create(struct sunxi_rsb *rsb, dev_dbg(&rdev->dev, "device %s registered\n", dev_name(&rdev->dev)); + return rdev; + err_device_add: put_device(&rdev->dev); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 54c0ee6dda30..7a1b1f9e4933 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -3232,13 +3232,27 @@ static int sysc_check_disabled_devices(struct sysc *ddata) */ static int sysc_check_active_timer(struct sysc *ddata) { + int error; + if (ddata->cap->type != TI_SYSC_OMAP2_TIMER && ddata->cap->type != TI_SYSC_OMAP4_TIMER) return 0; + /* + * Quirk for omap3 beagleboard revision A to B4 to use gpt12. + * Revision C and later are fixed with commit 23885389dbbb ("ARM: + * dts: Fix timer regression for beagleboard revision c"). This all + * can be dropped if we stop supporting old beagleboard revisions + * A to B4 at some point. + */ + if (sysc_soc->soc == SOC_3430) + error = -ENXIO; + else + error = -EBUSY; + if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) && (ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE)) - return -ENXIO; + return error; return 0; } diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 7bd10d63ddbe..2dc9da683a13 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -1365,7 +1365,6 @@ out_free: */ int cdrom_number_of_slots(struct cdrom_device_info *cdi) { - int status; int nslots = 1; struct cdrom_changer_info *info; @@ -1377,7 +1376,7 @@ int cdrom_number_of_slots(struct cdrom_device_info *cdi) if (!info) return -ENOMEM; - if ((status = cdrom_read_mech_status(cdi, info)) == 0) + if (cdrom_read_mech_status(cdi, info) == 0) nslots = info->hdr.nslots; kfree(info); diff --git a/drivers/char/random.c b/drivers/char/random.c index 1d8242969751..4c9adb4f3d5d 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -318,6 +318,13 @@ static void crng_reseed(bool force) * the resultant ChaCha state to the user, along with the second * half of the block containing 32 bytes of random data that may * be used; random_data_len may not be greater than 32. + * + * The returned ChaCha state contains within it a copy of the old + * key value, at index 4, so the state should always be zeroed out + * immediately after using in order to maintain forward secrecy. + * If the state cannot be erased in a timely manner, then it is + * safer to set the random_data parameter to &chacha_state[4] so + * that this function overwrites it before returning. */ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], u32 chacha_state[CHACHA_STATE_WORDS], @@ -437,11 +444,8 @@ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], * This shouldn't be set by functions like add_device_randomness(), * where we can't trust the buffer passed to it is guaranteed to be * unpredictable (so it might not have any entropy at all). - * - * Returns the number of bytes processed from input, which is bounded - * by CRNG_INIT_CNT_THRESH if account is true. */ -static size_t crng_pre_init_inject(const void *input, size_t len, bool account) +static void crng_pre_init_inject(const void *input, size_t len, bool account) { static int crng_init_cnt = 0; struct blake2s_state hash; @@ -452,18 +456,15 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account) spin_lock_irqsave(&base_crng.lock, flags); if (crng_init != 0) { spin_unlock_irqrestore(&base_crng.lock, flags); - return 0; + return; } - if (account) - len = min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); - blake2s_update(&hash, base_crng.key, sizeof(base_crng.key)); blake2s_update(&hash, input, len); blake2s_final(&hash, base_crng.key); if (account) { - crng_init_cnt += len; + crng_init_cnt += min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) { ++base_crng.generation; crng_init = 1; @@ -474,8 +475,6 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account) if (crng_init == 1) pr_notice("fast init done\n"); - - return len; } static void _get_random_bytes(void *buf, size_t nbytes) @@ -531,49 +530,59 @@ EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) { - bool large_request = nbytes > 256; - ssize_t ret = 0; - size_t len; + size_t len, left, ret = 0; u32 chacha_state[CHACHA_STATE_WORDS]; u8 output[CHACHA_BLOCK_SIZE]; if (!nbytes) return 0; - len = min_t(size_t, 32, nbytes); - crng_make_state(chacha_state, output, len); - - if (copy_to_user(buf, output, len)) - return -EFAULT; - nbytes -= len; - buf += len; - ret += len; - - while (nbytes) { - if (large_request && need_resched()) { - if (signal_pending(current)) - break; - schedule(); - } + /* + * Immediately overwrite the ChaCha key at index 4 with random + * bytes, in case userspace causes copy_to_user() below to sleep + * forever, so that we still retain forward secrecy in that case. + */ + crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); + /* + * However, if we're doing a read of len <= 32, we don't need to + * use chacha_state after, so we can simply return those bytes to + * the user directly. + */ + if (nbytes <= CHACHA_KEY_SIZE) { + ret = nbytes - copy_to_user(buf, &chacha_state[4], nbytes); + goto out_zero_chacha; + } + for (;;) { chacha20_block(chacha_state, output); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; len = min_t(size_t, nbytes, CHACHA_BLOCK_SIZE); - if (copy_to_user(buf, output, len)) { - ret = -EFAULT; + left = copy_to_user(buf, output, len); + if (left) { + ret += len - left; break; } - nbytes -= len; buf += len; ret += len; + nbytes -= len; + if (!nbytes) + break; + + BUILD_BUG_ON(PAGE_SIZE % CHACHA_BLOCK_SIZE != 0); + if (ret % PAGE_SIZE == 0) { + if (signal_pending(current)) + break; + cond_resched(); + } } - memzero_explicit(chacha_state, sizeof(chacha_state)); memzero_explicit(output, sizeof(output)); - return ret; +out_zero_chacha: + memzero_explicit(chacha_state, sizeof(chacha_state)); + return ret ? ret : -EFAULT; } /* @@ -1016,7 +1025,7 @@ int __init rand_initialize(void) */ void add_device_randomness(const void *buf, size_t size) { - cycles_t cycles = random_get_entropy(); + unsigned long cycles = random_get_entropy(); unsigned long flags, now = jiffies; if (crng_init == 0 && size) @@ -1047,8 +1056,7 @@ struct timer_rand_state { */ static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) { - cycles_t cycles = random_get_entropy(); - unsigned long flags, now = jiffies; + unsigned long cycles = random_get_entropy(), now = jiffies, flags; long delta, delta2, delta3; spin_lock_irqsave(&input_pool.lock, flags); @@ -1141,12 +1149,9 @@ void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy) { if (unlikely(crng_init == 0 && entropy < POOL_MIN_BITS)) { - size_t ret = crng_pre_init_inject(buffer, count, true); - mix_pool_bytes(buffer, ret); - count -= ret; - buffer += ret; - if (!count || crng_init == 0) - return; + crng_pre_init_inject(buffer, count, true); + mix_pool_bytes(buffer, count); + return; } /* @@ -1340,8 +1345,7 @@ static void mix_interrupt_randomness(struct work_struct *work) void add_interrupt_randomness(int irq) { enum { MIX_INFLIGHT = 1U << 31 }; - cycles_t cycles = random_get_entropy(); - unsigned long now = jiffies; + unsigned long cycles = random_get_entropy(), now = jiffies; struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); struct pt_regs *regs = get_irq_regs(); unsigned int new_count; @@ -1354,16 +1358,12 @@ void add_interrupt_randomness(int irq) if (cycles == 0) cycles = get_reg(fast_pool, regs); - if (sizeof(cycles) == 8) + if (sizeof(unsigned long) == 8) { irq_data.u64[0] = cycles ^ rol64(now, 32) ^ irq; - else { + irq_data.u64[1] = regs ? instruction_pointer(regs) : _RET_IP_; + } else { irq_data.u32[0] = cycles ^ irq; irq_data.u32[1] = now; - } - - if (sizeof(unsigned long) == 8) - irq_data.u64[1] = regs ? instruction_pointer(regs) : _RET_IP_; - else { irq_data.u32[2] = regs ? instruction_pointer(regs) : _RET_IP_; irq_data.u32[3] = get_reg(fast_pool, regs); } @@ -1410,7 +1410,7 @@ static void entropy_timer(struct timer_list *t) static void try_to_generate_entropy(void) { struct { - cycles_t cycles; + unsigned long cycles; struct timer_list timer; } stack; @@ -1545,6 +1545,13 @@ static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes, { static int maxwarn = 10; + /* + * Opportunistically attempt to initialize the RNG on platforms that + * have fast cycle counters, but don't (for now) require it to succeed. + */ + if (!crng_ready()) + try_to_generate_entropy(); + if (!crng_ready() && maxwarn > 0) { maxwarn--; if (__ratelimit(&urandom_warning)) diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c index aa1561b773d6..070c3b896559 100644 --- a/drivers/clk/microchip/clk-mpfs.c +++ b/drivers/clk/microchip/clk-mpfs.c @@ -11,20 +11,48 @@ #include <dt-bindings/clock/microchip,mpfs-clock.h> /* address offset of control registers */ +#define REG_MSSPLL_REF_CR 0x08u +#define REG_MSSPLL_POSTDIV_CR 0x10u +#define REG_MSSPLL_SSCG_2_CR 0x2Cu #define REG_CLOCK_CONFIG_CR 0x08u +#define REG_RTC_CLOCK_CR 0x0Cu #define REG_SUBBLK_CLOCK_CR 0x84u #define REG_SUBBLK_RESET_CR 0x88u +#define MSSPLL_FBDIV_SHIFT 0x00u +#define MSSPLL_FBDIV_WIDTH 0x0Cu +#define MSSPLL_REFDIV_SHIFT 0x08u +#define MSSPLL_REFDIV_WIDTH 0x06u +#define MSSPLL_POSTDIV_SHIFT 0x08u +#define MSSPLL_POSTDIV_WIDTH 0x07u +#define MSSPLL_FIXED_DIV 4u + struct mpfs_clock_data { void __iomem *base; + void __iomem *msspll_base; struct clk_hw_onecell_data hw_data; }; +struct mpfs_msspll_hw_clock { + void __iomem *base; + unsigned int id; + u32 reg_offset; + u32 shift; + u32 width; + u32 flags; + struct clk_hw hw; + struct clk_init_data init; +}; + +#define to_mpfs_msspll_clk(_hw) container_of(_hw, struct mpfs_msspll_hw_clock, hw) + struct mpfs_cfg_clock { const struct clk_div_table *table; unsigned int id; + u32 reg_offset; u8 shift; u8 width; + u8 flags; }; struct mpfs_cfg_hw_clock { @@ -55,7 +83,7 @@ struct mpfs_periph_hw_clock { */ static DEFINE_SPINLOCK(mpfs_clk_lock); -static const struct clk_parent_data mpfs_cfg_parent[] = { +static const struct clk_parent_data mpfs_ext_ref[] = { { .index = 0 }, }; @@ -69,6 +97,86 @@ static const struct clk_div_table mpfs_div_ahb_table[] = { { 0, 0 } }; +/* + * The only two supported reference clock frequencies for the PolarFire SoC are + * 100 and 125 MHz, as the rtc reference is required to be 1 MHz. + * It therefore only needs to have divider table entries corresponding to + * divide by 100 and 125. + */ +static const struct clk_div_table mpfs_div_rtcref_table[] = { + { 100, 100 }, { 125, 125 }, + { 0, 0 } +}; + +static unsigned long mpfs_clk_msspll_recalc_rate(struct clk_hw *hw, unsigned long prate) +{ + struct mpfs_msspll_hw_clock *msspll_hw = to_mpfs_msspll_clk(hw); + void __iomem *mult_addr = msspll_hw->base + msspll_hw->reg_offset; + void __iomem *ref_div_addr = msspll_hw->base + REG_MSSPLL_REF_CR; + void __iomem *postdiv_addr = msspll_hw->base + REG_MSSPLL_POSTDIV_CR; + u32 mult, ref_div, postdiv; + + mult = readl_relaxed(mult_addr) >> MSSPLL_FBDIV_SHIFT; + mult &= clk_div_mask(MSSPLL_FBDIV_WIDTH); + ref_div = readl_relaxed(ref_div_addr) >> MSSPLL_REFDIV_SHIFT; + ref_div &= clk_div_mask(MSSPLL_REFDIV_WIDTH); + postdiv = readl_relaxed(postdiv_addr) >> MSSPLL_POSTDIV_SHIFT; + postdiv &= clk_div_mask(MSSPLL_POSTDIV_WIDTH); + + return prate * mult / (ref_div * MSSPLL_FIXED_DIV * postdiv); +} + +static const struct clk_ops mpfs_clk_msspll_ops = { + .recalc_rate = mpfs_clk_msspll_recalc_rate, +}; + +#define CLK_PLL(_id, _name, _parent, _shift, _width, _flags, _offset) { \ + .id = _id, \ + .shift = _shift, \ + .width = _width, \ + .reg_offset = _offset, \ + .flags = _flags, \ + .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, _parent, &mpfs_clk_msspll_ops, 0), \ +} + +static struct mpfs_msspll_hw_clock mpfs_msspll_clks[] = { + CLK_PLL(CLK_MSSPLL, "clk_msspll", mpfs_ext_ref, MSSPLL_FBDIV_SHIFT, + MSSPLL_FBDIV_WIDTH, 0, REG_MSSPLL_SSCG_2_CR), +}; + +static int mpfs_clk_register_msspll(struct device *dev, struct mpfs_msspll_hw_clock *msspll_hw, + void __iomem *base) +{ + msspll_hw->base = base; + + return devm_clk_hw_register(dev, &msspll_hw->hw); +} + +static int mpfs_clk_register_mssplls(struct device *dev, struct mpfs_msspll_hw_clock *msspll_hws, + unsigned int num_clks, struct mpfs_clock_data *data) +{ + void __iomem *base = data->msspll_base; + unsigned int i; + int ret; + + for (i = 0; i < num_clks; i++) { + struct mpfs_msspll_hw_clock *msspll_hw = &msspll_hws[i]; + + ret = mpfs_clk_register_msspll(dev, msspll_hw, base); + if (ret) + return dev_err_probe(dev, ret, "failed to register msspll id: %d\n", + CLK_MSSPLL); + + data->hw_data.hws[msspll_hw->id] = &msspll_hw->hw; + } + + return 0; +} + +/* + * "CFG" clocks + */ + static unsigned long mpfs_cfg_clk_recalc_rate(struct clk_hw *hw, unsigned long prate) { struct mpfs_cfg_hw_clock *cfg_hw = to_mpfs_cfg_clk(hw); @@ -76,10 +184,10 @@ static unsigned long mpfs_cfg_clk_recalc_rate(struct clk_hw *hw, unsigned long p void __iomem *base_addr = cfg_hw->sys_base; u32 val; - val = readl_relaxed(base_addr + REG_CLOCK_CONFIG_CR) >> cfg->shift; + val = readl_relaxed(base_addr + cfg->reg_offset) >> cfg->shift; val &= clk_div_mask(cfg->width); - return prate / (1u << val); + return divider_recalc_rate(hw, prate, val, cfg->table, cfg->flags, cfg->width); } static long mpfs_cfg_clk_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) @@ -105,11 +213,10 @@ static int mpfs_cfg_clk_set_rate(struct clk_hw *hw, unsigned long rate, unsigned return divider_setting; spin_lock_irqsave(&mpfs_clk_lock, flags); - - val = readl_relaxed(base_addr + REG_CLOCK_CONFIG_CR); + val = readl_relaxed(base_addr + cfg->reg_offset); val &= ~(clk_div_mask(cfg->width) << cfg_hw->cfg.shift); val |= divider_setting << cfg->shift; - writel_relaxed(val, base_addr + REG_CLOCK_CONFIG_CR); + writel_relaxed(val, base_addr + cfg->reg_offset); spin_unlock_irqrestore(&mpfs_clk_lock, flags); @@ -122,19 +229,33 @@ static const struct clk_ops mpfs_clk_cfg_ops = { .set_rate = mpfs_cfg_clk_set_rate, }; -#define CLK_CFG(_id, _name, _parent, _shift, _width, _table, _flags) { \ - .cfg.id = _id, \ - .cfg.shift = _shift, \ - .cfg.width = _width, \ - .cfg.table = _table, \ - .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, _parent, &mpfs_clk_cfg_ops, \ - _flags), \ +#define CLK_CFG(_id, _name, _parent, _shift, _width, _table, _flags, _offset) { \ + .cfg.id = _id, \ + .cfg.shift = _shift, \ + .cfg.width = _width, \ + .cfg.table = _table, \ + .cfg.reg_offset = _offset, \ + .cfg.flags = _flags, \ + .hw.init = CLK_HW_INIT(_name, _parent, &mpfs_clk_cfg_ops, 0), \ } static struct mpfs_cfg_hw_clock mpfs_cfg_clks[] = { - CLK_CFG(CLK_CPU, "clk_cpu", mpfs_cfg_parent, 0, 2, mpfs_div_cpu_axi_table, 0), - CLK_CFG(CLK_AXI, "clk_axi", mpfs_cfg_parent, 2, 2, mpfs_div_cpu_axi_table, 0), - CLK_CFG(CLK_AHB, "clk_ahb", mpfs_cfg_parent, 4, 2, mpfs_div_ahb_table, 0), + CLK_CFG(CLK_CPU, "clk_cpu", "clk_msspll", 0, 2, mpfs_div_cpu_axi_table, 0, + REG_CLOCK_CONFIG_CR), + CLK_CFG(CLK_AXI, "clk_axi", "clk_msspll", 2, 2, mpfs_div_cpu_axi_table, 0, + REG_CLOCK_CONFIG_CR), + CLK_CFG(CLK_AHB, "clk_ahb", "clk_msspll", 4, 2, mpfs_div_ahb_table, 0, + REG_CLOCK_CONFIG_CR), + { + .cfg.id = CLK_RTCREF, + .cfg.shift = 0, + .cfg.width = 12, + .cfg.table = mpfs_div_rtcref_table, + .cfg.reg_offset = REG_RTC_CLOCK_CR, + .cfg.flags = CLK_DIVIDER_ONE_BASED, + .hw.init = + CLK_HW_INIT_PARENTS_DATA("clk_rtcref", mpfs_ext_ref, &mpfs_clk_cfg_ops, 0), + } }; static int mpfs_clk_register_cfg(struct device *dev, struct mpfs_cfg_hw_clock *cfg_hw, @@ -160,13 +281,17 @@ static int mpfs_clk_register_cfgs(struct device *dev, struct mpfs_cfg_hw_clock * return dev_err_probe(dev, ret, "failed to register clock id: %d\n", cfg_hw->cfg.id); - id = cfg_hws[i].cfg.id; + id = cfg_hw->cfg.id; data->hw_data.hws[id] = &cfg_hw->hw; } return 0; } +/* + * peripheral clocks - devices connected to axi or ahb buses. + */ + static int mpfs_periph_clk_enable(struct clk_hw *hw) { struct mpfs_periph_hw_clock *periph_hw = to_mpfs_periph_clk(hw); @@ -200,10 +325,6 @@ static void mpfs_periph_clk_disable(struct clk_hw *hw) spin_lock_irqsave(&mpfs_clk_lock, flags); - reg = readl_relaxed(base_addr + REG_SUBBLK_RESET_CR); - val = reg | (1u << periph->shift); - writel_relaxed(val, base_addr + REG_SUBBLK_RESET_CR); - reg = readl_relaxed(base_addr + REG_SUBBLK_CLOCK_CR); val = reg & ~(1u << periph->shift); writel_relaxed(val, base_addr + REG_SUBBLK_CLOCK_CR); @@ -249,8 +370,10 @@ static const struct clk_ops mpfs_periph_clk_ops = { * trap handler * - CLK_MMUART0: reserved by the hss * - CLK_DDRC: provides clock to the ddr subsystem - * - CLK_FICx: these provide clocks for sections of the fpga fabric, disabling them would - * cause the fabric to go into reset + * - CLK_FICx: these provide the processor side clocks to the "FIC" (Fabric InterConnect) + * clock domain crossers which provide the interface to the FPGA fabric. Disabling them + * causes the FPGA fabric to go into reset. + * - CLK_ATHENA: The athena clock is FIC4, which is reserved for the Athena TeraFire. */ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { @@ -258,7 +381,7 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { CLK_PERIPH(CLK_MAC0, "clk_periph_mac0", PARENT_CLK(AHB), 1, 0), CLK_PERIPH(CLK_MAC1, "clk_periph_mac1", PARENT_CLK(AHB), 2, 0), CLK_PERIPH(CLK_MMC, "clk_periph_mmc", PARENT_CLK(AHB), 3, 0), - CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(AHB), 4, 0), + CLK_PERIPH(CLK_TIMER, "clk_periph_timer", PARENT_CLK(RTCREF), 4, 0), CLK_PERIPH(CLK_MMUART0, "clk_periph_mmuart0", PARENT_CLK(AHB), 5, CLK_IS_CRITICAL), CLK_PERIPH(CLK_MMUART1, "clk_periph_mmuart1", PARENT_CLK(AHB), 6, 0), CLK_PERIPH(CLK_MMUART2, "clk_periph_mmuart2", PARENT_CLK(AHB), 7, 0), @@ -277,11 +400,11 @@ static struct mpfs_periph_hw_clock mpfs_periph_clks[] = { CLK_PERIPH(CLK_GPIO1, "clk_periph_gpio1", PARENT_CLK(AHB), 21, 0), CLK_PERIPH(CLK_GPIO2, "clk_periph_gpio2", PARENT_CLK(AHB), 22, 0), CLK_PERIPH(CLK_DDRC, "clk_periph_ddrc", PARENT_CLK(AHB), 23, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC0, "clk_periph_fic0", PARENT_CLK(AHB), 24, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC1, "clk_periph_fic1", PARENT_CLK(AHB), 25, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC2, "clk_periph_fic2", PARENT_CLK(AHB), 26, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_FIC3, "clk_periph_fic3", PARENT_CLK(AHB), 27, CLK_IS_CRITICAL), - CLK_PERIPH(CLK_ATHENA, "clk_periph_athena", PARENT_CLK(AHB), 28, 0), + CLK_PERIPH(CLK_FIC0, "clk_periph_fic0", PARENT_CLK(AXI), 24, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC1, "clk_periph_fic1", PARENT_CLK(AXI), 25, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC2, "clk_periph_fic2", PARENT_CLK(AXI), 26, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_FIC3, "clk_periph_fic3", PARENT_CLK(AXI), 27, CLK_IS_CRITICAL), + CLK_PERIPH(CLK_ATHENA, "clk_periph_athena", PARENT_CLK(AXI), 28, CLK_IS_CRITICAL), CLK_PERIPH(CLK_CFM, "clk_periph_cfm", PARENT_CLK(AHB), 29, 0), }; @@ -322,8 +445,9 @@ static int mpfs_clk_probe(struct platform_device *pdev) unsigned int num_clks; int ret; - /* CLK_RESERVED is not part of cfg_clks nor periph_clks, so add 1 */ - num_clks = ARRAY_SIZE(mpfs_cfg_clks) + ARRAY_SIZE(mpfs_periph_clks) + 1; + /* CLK_RESERVED is not part of clock arrays, so add 1 */ + num_clks = ARRAY_SIZE(mpfs_msspll_clks) + ARRAY_SIZE(mpfs_cfg_clks) + + ARRAY_SIZE(mpfs_periph_clks) + 1; clk_data = devm_kzalloc(dev, struct_size(clk_data, hw_data.hws, num_clks), GFP_KERNEL); if (!clk_data) @@ -333,8 +457,17 @@ static int mpfs_clk_probe(struct platform_device *pdev) if (IS_ERR(clk_data->base)) return PTR_ERR(clk_data->base); + clk_data->msspll_base = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(clk_data->msspll_base)) + return PTR_ERR(clk_data->msspll_base); + clk_data->hw_data.num = num_clks; + ret = mpfs_clk_register_mssplls(dev, mpfs_msspll_clks, ARRAY_SIZE(mpfs_msspll_clks), + clk_data); + if (ret) + return ret; + ret = mpfs_clk_register_cfgs(dev, mpfs_cfg_clks, ARRAY_SIZE(mpfs_cfg_clks), clk_data); if (ret) return ret; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index f675fd969c4d..e9c357309fd9 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -818,7 +818,7 @@ EXPORT_SYMBOL_GPL(clk_pixel_ops); static int clk_gfx3d_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { - struct clk_rate_request parent_req = { }; + struct clk_rate_request parent_req = { .min_rate = 0, .max_rate = ULONG_MAX }; struct clk_rcg2_gfx3d *cgfx = to_clk_rcg2_gfx3d(hw); struct clk_hw *xo, *p0, *p1, *p2; unsigned long p0_rate; diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c index 8a10bade7e0d..2f3ddc908ebd 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-rtc.c @@ -241,6 +241,7 @@ static struct clk_init_data rtc_32k_init_data = { .ops = &ccu_mux_ops, .parent_hws = rtc_32k_parents, .num_parents = ARRAY_SIZE(rtc_32k_parents), /* updated during probe */ + .flags = CLK_IS_CRITICAL, }; static struct ccu_mux rtc_32k_clk = { @@ -346,6 +347,7 @@ static const struct of_device_id sun6i_rtc_ccu_match[] = { .compatible = "allwinner,sun50i-r329-rtc", .data = &sun50i_r329_rtc_ccu_data, }, + {}, }; int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg) diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c index 542b31d6e96d..636bcf2439ef 100644 --- a/drivers/clk/sunxi/clk-sun9i-mmc.c +++ b/drivers/clk/sunxi/clk-sun9i-mmc.c @@ -109,6 +109,8 @@ static int sun9i_a80_mmc_config_clk_probe(struct platform_device *pdev) spin_lock_init(&data->lock); r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!r) + return -EINVAL; /* one clock/reset pair per word */ count = DIV_ROUND_UP((resource_size(r)), SUN9I_MMC_WIDTH); data->membase = devm_ioremap_resource(&pdev->dev, r); diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index f9d593ff4718..0253731d6d25 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -24,13 +24,17 @@ #define CLK_HW_DIV 2 #define LUT_TURBO_IND 1 +#define GT_IRQ_STATUS BIT(2) + #define HZ_PER_KHZ 1000 struct qcom_cpufreq_soc_data { u32 reg_enable; + u32 reg_domain_state; u32 reg_dcvs_ctrl; u32 reg_freq_lut; u32 reg_volt_lut; + u32 reg_intr_clr; u32 reg_current_vote; u32 reg_perf_state; u8 lut_row_size; @@ -280,37 +284,46 @@ static void qcom_get_related_cpus(int index, struct cpumask *m) } } -static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) +static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data) { - unsigned int val = readl_relaxed(data->base + data->soc_data->reg_current_vote); + unsigned int lval; + + if (data->soc_data->reg_current_vote) + lval = readl_relaxed(data->base + data->soc_data->reg_current_vote) & 0x3ff; + else + lval = readl_relaxed(data->base + data->soc_data->reg_domain_state) & 0xff; - return (val & 0x3FF) * 19200; + return lval * xo_rate; } static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data) { struct cpufreq_policy *policy = data->policy; - int cpu = cpumask_first(policy->cpus); + int cpu = cpumask_first(policy->related_cpus); struct device *dev = get_cpu_device(cpu); unsigned long freq_hz, throttled_freq; struct dev_pm_opp *opp; - unsigned int freq; /* * Get the h/w throttled frequency, normalize it using the * registered opp table and use it to calculate thermal pressure. */ - freq = qcom_lmh_get_throttle_freq(data); - freq_hz = freq * HZ_PER_KHZ; + freq_hz = qcom_lmh_get_throttle_freq(data); opp = dev_pm_opp_find_freq_floor(dev, &freq_hz); if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE) - dev_pm_opp_find_freq_ceil(dev, &freq_hz); + opp = dev_pm_opp_find_freq_ceil(dev, &freq_hz); + + if (IS_ERR(opp)) { + dev_warn(dev, "Can't find the OPP for throttling: %pe!\n", opp); + } else { + throttled_freq = freq_hz / HZ_PER_KHZ; - throttled_freq = freq_hz / HZ_PER_KHZ; + /* Update thermal pressure (the boost frequencies are accepted) */ + arch_update_thermal_pressure(policy->related_cpus, throttled_freq); - /* Update thermal pressure (the boost frequencies are accepted) */ - arch_update_thermal_pressure(policy->related_cpus, throttled_freq); + dev_pm_opp_put(opp); + } /* * In the unlikely case policy is unregistered do not enable @@ -350,6 +363,10 @@ static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data) disable_irq_nosync(c_data->throttle_irq); schedule_delayed_work(&c_data->throttle_work, 0); + if (c_data->soc_data->reg_intr_clr) + writel_relaxed(GT_IRQ_STATUS, + c_data->base + c_data->soc_data->reg_intr_clr); + return IRQ_HANDLED; } @@ -365,9 +382,11 @@ static const struct qcom_cpufreq_soc_data qcom_soc_data = { static const struct qcom_cpufreq_soc_data epss_soc_data = { .reg_enable = 0x0, + .reg_domain_state = 0x20, .reg_dcvs_ctrl = 0xb0, .reg_freq_lut = 0x100, .reg_volt_lut = 0x200, + .reg_intr_clr = 0x308, .reg_perf_state = 0x320, .lut_row_size = 4, }; @@ -417,16 +436,39 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) return 0; } -static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data) +static int qcom_cpufreq_hw_cpu_online(struct cpufreq_policy *policy) +{ + struct qcom_cpufreq_data *data = policy->driver_data; + struct platform_device *pdev = cpufreq_get_driver_data(); + int ret; + + ret = irq_set_affinity_hint(data->throttle_irq, policy->cpus); + if (ret) + dev_err(&pdev->dev, "Failed to set CPU affinity of %s[%d]\n", + data->irq_name, data->throttle_irq); + + return ret; +} + +static int qcom_cpufreq_hw_cpu_offline(struct cpufreq_policy *policy) { + struct qcom_cpufreq_data *data = policy->driver_data; + if (data->throttle_irq <= 0) - return; + return 0; mutex_lock(&data->throttle_lock); data->cancel_throttle = true; mutex_unlock(&data->throttle_lock); cancel_delayed_work_sync(&data->throttle_work); + irq_set_affinity_hint(data->throttle_irq, NULL); + + return 0; +} + +static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data) +{ free_irq(data->throttle_irq, data); } @@ -583,6 +625,8 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = { .get = qcom_cpufreq_hw_get, .init = qcom_cpufreq_hw_cpu_init, .exit = qcom_cpufreq_hw_cpu_exit, + .online = qcom_cpufreq_hw_cpu_online, + .offline = qcom_cpufreq_hw_cpu_offline, .register_em = cpufreq_register_em_with_opp, .fast_switch = qcom_cpufreq_hw_fast_switch, .name = "qcom-cpufreq-hw", diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c index 2deed8d8773f..75e1bf3a08f7 100644 --- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c +++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c @@ -98,8 +98,10 @@ static int sun50i_cpufreq_nvmem_probe(struct platform_device *pdev) return -ENOMEM; ret = sun50i_cpufreq_get_efuse(&speed); - if (ret) + if (ret) { + kfree(opp_tables); return ret; + } snprintf(name, MAX_NAME_LEN, "speed%d", speed); diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index b459eda2cd37..5c852e671992 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -22,6 +22,7 @@ #include <linux/pm_runtime.h> #include <asm/cpuidle.h> #include <asm/sbi.h> +#include <asm/smp.h> #include <asm/suspend.h> #include "dt_idle_states.h" diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 8a7267d116b7..3f2182d66829 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -436,7 +436,6 @@ static int wait_for_media_ready(struct cxl_dev_state *cxlds) for (i = mbox_ready_timeout; i; i--) { u32 temp; - int rc; rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &temp); diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 511805dbeb75..4c9eb53ba3f8 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -12,6 +12,7 @@ dmabuf_selftests-y := \ selftest.o \ st-dma-fence.o \ st-dma-fence-chain.o \ + st-dma-fence-unwrap.o \ st-dma-resv.o obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index cb1bacb5a42b..5c8a7084577b 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -159,6 +159,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence_array *array; size_t size = sizeof(*array); + WARN_ON(!num_fences || !fences); + /* Allocate the callback structures behind the array. */ size += num_fences * sizeof(struct dma_fence_array_cb); array = kzalloc(size, GFP_KERNEL); @@ -219,3 +221,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context) return true; } EXPORT_SYMBOL(dma_fence_match_context); + +struct dma_fence *dma_fence_array_first(struct dma_fence *head) +{ + struct dma_fence_array *array; + + if (!head) + return NULL; + + array = to_dma_fence_array(head); + if (!array) + return head; + + if (!array->num_fences) + return NULL; + + return array->fences[0]; +} +EXPORT_SYMBOL(dma_fence_array_first); + +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index) +{ + struct dma_fence_array *array = to_dma_fence_array(head); + + if (!array || index >= array->num_fences) + return NULL; + + return array->fences[index]; +} +EXPORT_SYMBOL(dma_fence_array_next); diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h index 97d73aaa31da..851965867d9c 100644 --- a/drivers/dma-buf/selftests.h +++ b/drivers/dma-buf/selftests.h @@ -12,4 +12,5 @@ selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ selftest(dma_fence, dma_fence) selftest(dma_fence_chain, dma_fence_chain) +selftest(dma_fence_unwrap, dma_fence_unwrap) selftest(dma_resv, dma_resv) diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c new file mode 100644 index 000000000000..039f016b57be --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-unwrap.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + */ + +#include <linux/dma-fence-unwrap.h> +#if 0 +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/random.h> +#endif + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +static inline struct mock_fence { + struct dma_fence base; + spinlock_t lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static struct dma_fence *mock_array(unsigned int num_fences, ...) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + va_list valist; + int i; + + fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); + if (!fences) + return NULL; + + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + fences[i] = va_arg(valist, typeof(*fences)); + va_end(valist); + + array = dma_fence_array_create(num_fences, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) + goto cleanup; + return &array->base; + +cleanup: + for (i = 0; i < num_fences; ++i) + dma_fence_put(fences[i]); + kfree(fences); + return NULL; +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence) +{ + struct dma_fence_chain *f; + + f = dma_fence_chain_alloc(); + if (!f) { + dma_fence_put(prev); + dma_fence_put(fence); + return NULL; + } + + dma_fence_chain_init(f, prev, fence, 1); + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain, *array; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + array = mock_array(1, f); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(chain); + return err; +} + +static int unwrap_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, array) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(array); + return 0; +} + +static int unwrap_chain(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + chain = mock_chain(f1, f2); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +static int unwrap_chain_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +int dma_fence_unwrap(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(unwrap_array), + SUBTEST(unwrap_chain), + SUBTEST(unwrap_chain_array), + }; + + return subtests(tests, NULL); +} diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 394e6e1e9686..514d213261df 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -5,6 +5,7 @@ * Copyright (C) 2012 Google, Inc. */ +#include <linux/dma-fence-unwrap.h> #include <linux/export.h> #include <linux/file.h> #include <linux/fs.h> @@ -172,20 +173,6 @@ static int sync_file_set_fence(struct sync_file *sync_file, return 0; } -static struct dma_fence **get_fences(struct sync_file *sync_file, - int *num_fences) -{ - if (dma_fence_is_array(sync_file->fence)) { - struct dma_fence_array *array = to_dma_fence_array(sync_file->fence); - - *num_fences = array->num_fences; - return array->fences; - } - - *num_fences = 1; - return &sync_file->fence; -} - static void add_fence(struct dma_fence **fences, int *i, struct dma_fence *fence) { @@ -210,86 +197,97 @@ static void add_fence(struct dma_fence **fences, static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { + struct dma_fence *a_fence, *b_fence, **fences; + struct dma_fence_unwrap a_iter, b_iter; + unsigned int index, num_fences; struct sync_file *sync_file; - struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences; - int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences; sync_file = sync_file_alloc(); if (!sync_file) return NULL; - a_fences = get_fences(a, &a_num_fences); - b_fences = get_fences(b, &b_num_fences); - if (a_num_fences > INT_MAX - b_num_fences) - goto err; + num_fences = 0; + dma_fence_unwrap_for_each(a_fence, &a_iter, a->fence) + ++num_fences; + dma_fence_unwrap_for_each(b_fence, &b_iter, b->fence) + ++num_fences; - num_fences = a_num_fences + b_num_fences; + if (num_fences > INT_MAX) + goto err_free_sync_file; fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); if (!fences) - goto err; + goto err_free_sync_file; /* - * Assume sync_file a and b are both ordered and have no - * duplicates with the same context. + * We can't guarantee that fences in both a and b are ordered, but it is + * still quite likely. * - * If a sync_file can only be created with sync_file_merge - * and sync_file_create, this is a reasonable assumption. + * So attempt to order the fences as we pass over them and merge fences + * with the same context. */ - for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { - struct dma_fence *pt_a = a_fences[i_a]; - struct dma_fence *pt_b = b_fences[i_b]; - if (pt_a->context < pt_b->context) { - add_fence(fences, &i, pt_a); + index = 0; + for (a_fence = dma_fence_unwrap_first(a->fence, &a_iter), + b_fence = dma_fence_unwrap_first(b->fence, &b_iter); + a_fence || b_fence; ) { + + if (!b_fence) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + + } else if (!a_fence) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (a_fence->context < b_fence->context) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); - i_a++; - } else if (pt_a->context > pt_b->context) { - add_fence(fences, &i, pt_b); + } else if (b_fence->context < a_fence->context) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (__dma_fence_is_later(a_fence->seqno, b_fence->seqno, + a_fence->ops)) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); - i_b++; } else { - if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno, - pt_a->ops)) - add_fence(fences, &i, pt_a); - else - add_fence(fences, &i, pt_b); - - i_a++; - i_b++; + add_fence(fences, &index, b_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); } } - for (; i_a < a_num_fences; i_a++) - add_fence(fences, &i, a_fences[i_a]); - - for (; i_b < b_num_fences; i_b++) - add_fence(fences, &i, b_fences[i_b]); - - if (i == 0) - fences[i++] = dma_fence_get(a_fences[0]); + if (index == 0) + fences[index++] = dma_fence_get_stub(); - if (num_fences > i) { - nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL); - if (!nfences) - goto err; + if (num_fences > index) { + struct dma_fence **tmp; - fences = nfences; + /* Keep going even when reducing the size failed */ + tmp = krealloc_array(fences, index, sizeof(*fences), + GFP_KERNEL); + if (tmp) + fences = tmp; } - if (sync_file_set_fence(sync_file, fences, i) < 0) - goto err; + if (sync_file_set_fence(sync_file, fences, index) < 0) + goto err_put_fences; strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; -err: - while (i) - dma_fence_put(fences[--i]); +err_put_fences: + while (index) + dma_fence_put(fences[--index]); kfree(fences); + +err_free_sync_file: fput(sync_file->file); return NULL; - } static int sync_file_release(struct inode *inode, struct file *file) @@ -398,11 +396,13 @@ static int sync_fill_fence_info(struct dma_fence *fence, static long sync_file_ioctl_fence_info(struct sync_file *sync_file, unsigned long arg) { - struct sync_file_info info; struct sync_fence_info *fence_info = NULL; - struct dma_fence **fences; + struct dma_fence_unwrap iter; + struct sync_file_info info; + unsigned int num_fences; + struct dma_fence *fence; + int ret; __u32 size; - int num_fences, ret, i; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; @@ -410,7 +410,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (info.flags || info.pad) return -EINVAL; - fences = get_fences(sync_file, &num_fences); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) + ++num_fences; /* * Passing num_fences = 0 means that userspace doesn't want to @@ -433,8 +435,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) { - int status = sync_fill_fence_info(fences[i], &fence_info[i]); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) { + int status; + + status = sync_fill_fence_info(fence, &fence_info[num_fences++]); info.status = info.status <= 0 ? info.status : status; } diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 1476156af74b..def564d1e8fa 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1453,7 +1453,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, { struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan); struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device); - struct at_xdmac_desc *desc, *_desc; + struct at_xdmac_desc *desc, *_desc, *iter; struct list_head *descs_list; enum dma_status ret; int residue, retry; @@ -1568,11 +1568,13 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, * microblock. */ descs_list = &desc->descs_list; - list_for_each_entry_safe(desc, _desc, descs_list, desc_node) { - dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg); - residue -= (desc->lld.mbr_ubc & 0xffffff) << dwidth; - if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda) + list_for_each_entry_safe(iter, _desc, descs_list, desc_node) { + dwidth = at_xdmac_get_dwidth(iter->lld.mbr_cfg); + residue -= (iter->lld.mbr_ubc & 0xffffff) << dwidth; + if ((iter->lld.mbr_nda & 0xfffffffc) == cur_nda) { + desc = iter; break; + } } residue += cur_ubc << dwidth; diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index 329fc2e57b70..33bc1e6c4cf2 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -414,14 +414,18 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) SET_CH_32(dw, chan->dir, chan->id, ch_control1, (DW_EDMA_V0_CCS | DW_EDMA_V0_LLE)); /* Linked list */ + #ifdef CONFIG_64BIT - SET_CH_64(dw, chan->dir, chan->id, llp.reg, - chunk->ll_region.paddr); + /* llp is not aligned on 64bit -> keep 32bit accesses */ + SET_CH_32(dw, chan->dir, chan->id, llp.lsb, + lower_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.msb, + upper_32_bits(chunk->ll_region.paddr)); #else /* CONFIG_64BIT */ - SET_CH_32(dw, chan->dir, chan->id, llp.lsb, - lower_32_bits(chunk->ll_region.paddr)); - SET_CH_32(dw, chan->dir, chan->id, llp.msb, - upper_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.lsb, + lower_32_bits(chunk->ll_region.paddr)); + SET_CH_32(dw, chan->dir, chan->id, llp.msb, + upper_32_bits(chunk->ll_region.paddr)); #endif /* CONFIG_64BIT */ } /* Doorbell */ diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 3061fe857d69..f652da6ab47d 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -373,7 +373,6 @@ static void idxd_wq_device_reset_cleanup(struct idxd_wq *wq) { lockdep_assert_held(&wq->wq_lock); - idxd_wq_disable_cleanup(wq); wq->size = 0; wq->group = NULL; } @@ -701,14 +700,17 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd) if (wq->state == IDXD_WQ_ENABLED) { idxd_wq_disable_cleanup(wq); - idxd_wq_device_reset_cleanup(wq); wq->state = IDXD_WQ_DISABLED; } + idxd_wq_device_reset_cleanup(wq); } } void idxd_device_clear_state(struct idxd_device *idxd) { + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return; + idxd_groups_clear_state(idxd); idxd_engines_clear_state(idxd); idxd_device_wqs_clear_state(idxd); diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c index e289fd48711a..c01db23e3333 100644 --- a/drivers/dma/idxd/submit.c +++ b/drivers/dma/idxd/submit.c @@ -150,14 +150,15 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, */ int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc) { - int rc, retries = 0; + unsigned int retries = wq->enqcmds_retries; + int rc; do { rc = enqcmds(portal, desc); if (rc == 0) break; cpu_relax(); - } while (retries++ < wq->enqcmds_retries); + } while (retries--); return rc; } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 7e19ab92b61a..dfd549685c46 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -905,6 +905,9 @@ static ssize_t wq_max_transfer_size_store(struct device *dev, struct device_attr u64 xfer_size; int rc; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + if (wq->state != IDXD_WQ_DISABLED) return -EPERM; @@ -939,6 +942,9 @@ static ssize_t wq_max_batch_size_store(struct device *dev, struct device_attribu u64 batch_size; int rc; + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + if (wq->state != IDXD_WQ_DISABLED) return -EPERM; diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 70c0aa931ddf..6196a7b3956b 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -198,12 +198,12 @@ struct sdma_script_start_addrs { s32 per_2_firi_addr; s32 mcu_2_firi_addr; s32 uart_2_per_addr; - s32 uart_2_mcu_ram_addr; + s32 uart_2_mcu_addr; s32 per_2_app_addr; s32 mcu_2_app_addr; s32 per_2_per_addr; s32 uartsh_2_per_addr; - s32 uartsh_2_mcu_ram_addr; + s32 uartsh_2_mcu_addr; s32 per_2_shp_addr; s32 mcu_2_shp_addr; s32 ata_2_mcu_addr; @@ -232,8 +232,8 @@ struct sdma_script_start_addrs { s32 mcu_2_ecspi_addr; s32 mcu_2_sai_addr; s32 sai_2_mcu_addr; - s32 uart_2_mcu_addr; - s32 uartsh_2_mcu_addr; + s32 uart_2_mcu_rom_addr; + s32 uartsh_2_mcu_rom_addr; /* End of v3 array */ s32 mcu_2_zqspi_addr; /* End of v4 array */ @@ -1796,17 +1796,17 @@ static void sdma_add_scripts(struct sdma_engine *sdma, saddr_arr[i] = addr_arr[i]; /* - * get uart_2_mcu_addr/uartsh_2_mcu_addr rom script specially because - * they are now replaced by uart_2_mcu_ram_addr/uartsh_2_mcu_ram_addr - * to be compatible with legacy freescale/nxp sdma firmware, and they - * are located in the bottom part of sdma_script_start_addrs which are - * beyond the SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1. + * For compatibility with NXP internal legacy kernel before 4.19 which + * is based on uart ram script and mainline kernel based on uart rom + * script, both uart ram/rom scripts are present in newer sdma + * firmware. Use the rom versions if they are present (V3 or newer). */ - if (addr->uart_2_mcu_addr) - sdma->script_addrs->uart_2_mcu_addr = addr->uart_2_mcu_addr; - if (addr->uartsh_2_mcu_addr) - sdma->script_addrs->uartsh_2_mcu_addr = addr->uartsh_2_mcu_addr; - + if (sdma->script_number >= SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V3) { + if (addr->uart_2_mcu_rom_addr) + sdma->script_addrs->uart_2_mcu_addr = addr->uart_2_mcu_rom_addr; + if (addr->uartsh_2_mcu_rom_addr) + sdma->script_addrs->uartsh_2_mcu_addr = addr->uartsh_2_mcu_rom_addr; + } } static void sdma_load_firmware(const struct firmware *fw, void *context) @@ -1885,7 +1885,7 @@ static int sdma_event_remap(struct sdma_engine *sdma) u32 reg, val, shift, num_map, i; int ret = 0; - if (IS_ERR(np) || IS_ERR(gpr_np)) + if (IS_ERR(np) || !gpr_np) goto out; event_remap = of_find_property(np, propname, NULL); @@ -1933,7 +1933,7 @@ static int sdma_event_remap(struct sdma_engine *sdma) } out: - if (!IS_ERR(gpr_np)) + if (gpr_np) of_node_put(gpr_np); return ret; diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index 375e7e647df6..a1517ef1f4a0 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -274,7 +274,7 @@ static int mtk_uart_apdma_alloc_chan_resources(struct dma_chan *chan) unsigned int status; int ret; - ret = pm_runtime_get_sync(mtkd->ddev.dev); + ret = pm_runtime_resume_and_get(mtkd->ddev.dev); if (ret < 0) { pm_runtime_put_noidle(chan->device->dev); return ret; @@ -288,18 +288,21 @@ static int mtk_uart_apdma_alloc_chan_resources(struct dma_chan *chan) ret = readx_poll_timeout(readl, c->base + VFF_EN, status, !status, 10, 100); if (ret) - return ret; + goto err_pm; ret = request_irq(c->irq, mtk_uart_apdma_irq_handler, IRQF_TRIGGER_NONE, KBUILD_MODNAME, chan); if (ret < 0) { dev_err(chan->device->dev, "Can't request dma IRQ\n"); - return -EINVAL; + ret = -EINVAL; + goto err_pm; } if (mtkd->support_33bits) mtk_uart_apdma_write(c, VFF_4G_SUPPORT, VFF_4G_SUPPORT_CLR_B); +err_pm: + pm_runtime_put_noidle(mtkd->ddev.dev); return ret; } diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index f05ff02c0656..40b1abeca856 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -164,6 +164,11 @@ #define ECC_STAT_CECNT_SHIFT 8 #define ECC_STAT_BITNUM_MASK 0x7F +/* ECC error count register definitions */ +#define ECC_ERRCNT_UECNT_MASK 0xFFFF0000 +#define ECC_ERRCNT_UECNT_SHIFT 16 +#define ECC_ERRCNT_CECNT_MASK 0xFFFF + /* DDR QOS Interrupt register definitions */ #define DDR_QOS_IRQ_STAT_OFST 0x20200 #define DDR_QOSUE_MASK 0x4 @@ -423,15 +428,16 @@ static int zynqmp_get_error_info(struct synps_edac_priv *priv) base = priv->baseaddr; p = &priv->stat; + regval = readl(base + ECC_ERRCNT_OFST); + p->ce_cnt = regval & ECC_ERRCNT_CECNT_MASK; + p->ue_cnt = (regval & ECC_ERRCNT_UECNT_MASK) >> ECC_ERRCNT_UECNT_SHIFT; + if (!p->ce_cnt) + goto ue_err; + regval = readl(base + ECC_STAT_OFST); if (!regval) return 1; - p->ce_cnt = (regval & ECC_STAT_CECNT_MASK) >> ECC_STAT_CECNT_SHIFT; - p->ue_cnt = (regval & ECC_STAT_UECNT_MASK) >> ECC_STAT_UECNT_SHIFT; - if (!p->ce_cnt) - goto ue_err; - p->ceinfo.bitpos = (regval & ECC_STAT_BITNUM_MASK); regval = readl(base + ECC_CEADDR0_OFST); diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c index cf6fed6dec77..45600acc0f45 100644 --- a/drivers/firmware/arm_scmi/clock.c +++ b/drivers/firmware/arm_scmi/clock.c @@ -49,7 +49,7 @@ struct scmi_msg_resp_clock_describe_rates { struct { __le32 value_low; __le32 value_high; - } rate[0]; + } rate[]; #define RATE_TO_U64(X) \ ({ \ typeof(X) x = (X); \ @@ -210,7 +210,8 @@ scmi_clock_describe_rates_get(const struct scmi_protocol_handle *ph, u32 clk_id, if (rate_discrete && rate) { clk->list.num_rates = tot_rate_cnt; - sort(rate, tot_rate_cnt, sizeof(*rate), rate_cmp_func, NULL); + sort(clk->list.rates, tot_rate_cnt, sizeof(*rate), + rate_cmp_func, NULL); } clk->rate_discrete = rate_discrete; diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 46118300a4d1..e17c6568344d 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -679,7 +679,8 @@ static void scmi_handle_response(struct scmi_chan_info *cinfo, xfer = scmi_xfer_command_acquire(cinfo, msg_hdr); if (IS_ERR(xfer)) { - scmi_clear_channel(info, cinfo); + if (MSG_XTRACT_TYPE(msg_hdr) == MSG_TYPE_DELAYED_RESP) + scmi_clear_channel(info, cinfo); return; } diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c index 734f1eeee161..8302a2b4aeeb 100644 --- a/drivers/firmware/arm_scmi/optee.c +++ b/drivers/firmware/arm_scmi/optee.c @@ -405,8 +405,8 @@ static int scmi_optee_chan_free(int id, void *p, void *data) return 0; } -static struct scmi_shared_mem *get_channel_shm(struct scmi_optee_channel *chan, - struct scmi_xfer *xfer) +static struct scmi_shared_mem __iomem * +get_channel_shm(struct scmi_optee_channel *chan, struct scmi_xfer *xfer) { if (!chan) return NULL; @@ -419,7 +419,7 @@ static int scmi_optee_send_message(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer) { struct scmi_optee_channel *channel = cinfo->transport_info; - struct scmi_shared_mem *shmem = get_channel_shm(channel, xfer); + struct scmi_shared_mem __iomem *shmem = get_channel_shm(channel, xfer); int ret; mutex_lock(&channel->mu); @@ -436,7 +436,7 @@ static void scmi_optee_fetch_response(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer) { struct scmi_optee_channel *channel = cinfo->transport_info; - struct scmi_shared_mem *shmem = get_channel_shm(channel, xfer); + struct scmi_shared_mem __iomem *shmem = get_channel_shm(channel, xfer); shmem_fetch_response(shmem, xfer); } diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index e48108e694f8..7dad6f57d970 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -955,8 +955,7 @@ static int cs_dsp_create_control(struct cs_dsp *dsp, ctl->alg_region = *alg_region; if (subname && dsp->fw_ver >= 2) { ctl->subname_len = subname_len; - ctl->subname = kmemdup(subname, - strlen(subname) + 1, GFP_KERNEL); + ctl->subname = kasprintf(GFP_KERNEL, "%.*s", subname_len, subname); if (!ctl->subname) { ret = -ENOMEM; goto err_ctl; diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 8e5d87984a48..41c31b10ae84 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -134,7 +134,7 @@ static int gpio_sim_get_multiple(struct gpio_chip *gc, struct gpio_sim_chip *chip = gpiochip_get_data(gc); mutex_lock(&chip->lock); - bitmap_copy(bits, chip->value_map, gc->ngpio); + bitmap_replace(bits, bits, chip->value_map, mask, gc->ngpio); mutex_unlock(&chip->lock); return 0; @@ -146,7 +146,7 @@ static void gpio_sim_set_multiple(struct gpio_chip *gc, struct gpio_sim_chip *chip = gpiochip_get_data(gc); mutex_lock(&chip->lock); - bitmap_copy(chip->value_map, bits, gc->ngpio); + bitmap_replace(chip->value_map, chip->value_map, bits, mask, gc->ngpio); mutex_unlock(&chip->lock); } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index a5495ad31c9c..c2523ac26fac 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -108,7 +108,7 @@ static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) * controller does not have GPIO chip registered at the moment. This is to * support probe deferral. */ -static struct gpio_desc *acpi_get_gpiod(char *path, int pin) +static struct gpio_desc *acpi_get_gpiod(char *path, unsigned int pin) { struct gpio_chip *chip; acpi_handle handle; @@ -136,7 +136,7 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) * as it is intended for use outside of the GPIO layer (in a similar fashion to * gpiod_get_index() for example) it also holds a reference to the GPIO device. */ -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label) +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label) { struct gpio_desc *gpio; int ret; @@ -317,11 +317,12 @@ static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, return desc; } -static bool acpi_gpio_in_ignore_list(const char *controller_in, int pin_in) +static bool acpi_gpio_in_ignore_list(const char *controller_in, unsigned int pin_in) { const char *controller, *pin_str; - int len, pin; + unsigned int pin; char *endp; + int len; controller = ignore_wake; while (controller) { @@ -354,13 +355,13 @@ err: static bool acpi_gpio_irq_is_wake(struct device *parent, struct acpi_resource_gpio *agpio) { - int pin = agpio->pin_table[0]; + unsigned int pin = agpio->pin_table[0]; if (agpio->wake_capable != ACPI_WAKE_CAPABLE) return false; if (acpi_gpio_in_ignore_list(dev_name(parent), pin)) { - dev_info(parent, "Ignoring wakeup on pin %d\n", pin); + dev_info(parent, "Ignoring wakeup on pin %u\n", pin); return false; } @@ -378,7 +379,8 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, struct acpi_gpio_event *event; irq_handler_t handler = NULL; struct gpio_desc *desc; - int ret, pin, irq; + unsigned int pin; + int ret, irq; if (!acpi_gpio_get_irq_resource(ares, &agpio)) return AE_OK; @@ -387,8 +389,8 @@ static acpi_status acpi_gpiochip_alloc_event(struct acpi_resource *ares, pin = agpio->pin_table[0]; if (pin <= 255) { - char ev_name[5]; - sprintf(ev_name, "_%c%02hhX", + char ev_name[8]; + sprintf(ev_name, "_%c%02X", agpio->triggering == ACPI_EDGE_SENSITIVE ? 'E' : 'L', pin); if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle))) @@ -1098,7 +1100,7 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address, length = min_t(u16, agpio->pin_table_length, pin_index + bits); for (i = pin_index; i < length; ++i) { - int pin = agpio->pin_table[i]; + unsigned int pin = agpio->pin_table[i]; struct acpi_gpio_connection *conn; struct gpio_desc *desc; bool found; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e59884cc12a7..b7694171655c 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1404,6 +1404,16 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset) { struct irq_domain *domain = gc->irq.domain; +#ifdef CONFIG_GPIOLIB_IRQCHIP + /* + * Avoid race condition with other code, which tries to lookup + * an IRQ before the irqchip has been properly registered, + * i.e. while gpiochip is still being brought up. + */ + if (!gc->irq.initialized) + return -EPROBE_DEFER; +#endif + if (!gpiochip_irqchip_irq_valid(gc, offset)) return -ENXIO; @@ -1591,6 +1601,15 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, gpiochip_set_irq_hooks(gc); + /* + * Using barrier() here to prevent compiler from reordering + * gc->irq.initialized before initialization of above + * GPIO chip irq members. + */ + barrier(); + + gc->irq.initialized = true; + acpi_gpiochip_request_interrupts(gc); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h index 5b393622f592..a0f0a17e224f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h +++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h @@ -119,6 +119,7 @@ #define CONNECTOR_OBJECT_ID_eDP 0x14 #define CONNECTOR_OBJECT_ID_MXM 0x15 #define CONNECTOR_OBJECT_ID_LVDS_eDP 0x16 +#define CONNECTOR_OBJECT_ID_USBC 0x17 /* deleted */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 970b065e9a6b..d0d0ea565e3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -128,6 +128,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs goto free_chunk; } + mutex_lock(&p->ctx->lock); + /* skip guilty context job */ if (atomic_read(&p->ctx->guilty) == 1) { ret = -ECANCELED; @@ -709,6 +711,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, dma_fence_put(parser->fence); if (parser->ctx) { + mutex_unlock(&parser->ctx->lock); amdgpu_ctx_put(parser->ctx); } if (parser->bo_list) @@ -1157,6 +1160,9 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev, { int i, r; + /* TODO: Investigate why we still need the context lock */ + mutex_unlock(&p->ctx->lock); + for (i = 0; i < p->nchunks; ++i) { struct amdgpu_cs_chunk *chunk; @@ -1167,32 +1173,34 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev, case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES: r = amdgpu_cs_process_fence_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_IN: r = amdgpu_cs_process_syncobj_in_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_OUT: r = amdgpu_cs_process_syncobj_out_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT: r = amdgpu_cs_process_syncobj_timeline_in_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL: r = amdgpu_cs_process_syncobj_timeline_out_dep(p, chunk); if (r) - return r; + goto out; break; } } - return 0; +out: + mutex_lock(&p->ctx->lock); + return r; } static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p) @@ -1368,6 +1376,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) goto out; r = amdgpu_cs_submit(&parser, cs); + out: amdgpu_cs_parser_fini(&parser, r, reserved_buffers); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 5981c7d9bd48..8f0e6d93bb9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -237,6 +237,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, kref_init(&ctx->refcount); spin_lock_init(&ctx->ring_lock); + mutex_init(&ctx->lock); ctx->reset_counter = atomic_read(&adev->gpu_reset_counter); ctx->reset_counter_query = ctx->reset_counter; @@ -357,6 +358,7 @@ static void amdgpu_ctx_fini(struct kref *ref) drm_dev_exit(idx); } + mutex_destroy(&ctx->lock); kfree(ctx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h index d0cbfcea90f7..142f2f87d44c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h @@ -49,6 +49,7 @@ struct amdgpu_ctx { bool preamble_presented; int32_t init_priority; int32_t override_priority; + struct mutex lock; atomic_t guilty; unsigned long ras_counter_ce; unsigned long ras_counter_ue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3987ecb24ef4..49f734137f15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5733,7 +5733,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) @@ -5749,7 +5749,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bb1c025d9001..7fd0277b2805 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -680,7 +680,7 @@ MODULE_PARM_DESC(sched_policy, * Maximum number of processes that HWS can schedule concurrently. The maximum is the * number of VMIDs assigned to the HWS, which is also the default. */ -int hws_max_conc_proc = 8; +int hws_max_conc_proc = -1; module_param(hws_max_conc_proc, int, 0444); MODULE_PARM_DESC(hws_max_conc_proc, "Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))"); @@ -2323,18 +2323,23 @@ static int amdgpu_pmops_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else adev->in_s3 = true; - r = amdgpu_device_suspend(drm_dev, true); - if (r) - return r; + return amdgpu_device_suspend(drm_dev, true); +} + +static int amdgpu_pmops_suspend_noirq(struct device *dev) +{ + struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + if (!adev->in_s0ix) - r = amdgpu_asic_reset(adev); - return r; + return amdgpu_asic_reset(adev); + + return 0; } static int amdgpu_pmops_resume(struct device *dev) @@ -2390,6 +2395,71 @@ static int amdgpu_pmops_restore(struct device *dev) return amdgpu_device_resume(drm_dev, true); } +static int amdgpu_runtime_idle_check_display(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + + if (adev->mode_info.num_crtc) { + struct drm_connector *list_connector; + struct drm_connector_list_iter iter; + int ret = 0; + + /* XXX: Return busy if any displays are connected to avoid + * possible display wakeups after runtime resume due to + * hotplug events in case any displays were connected while + * the GPU was in suspend. Remove this once that is fixed. + */ + mutex_lock(&drm_dev->mode_config.mutex); + drm_connector_list_iter_begin(drm_dev, &iter); + drm_for_each_connector_iter(list_connector, &iter) { + if (list_connector->status == connector_status_connected) { + ret = -EBUSY; + break; + } + } + drm_connector_list_iter_end(&iter); + mutex_unlock(&drm_dev->mode_config.mutex); + + if (ret) + return ret; + + if (amdgpu_device_has_dc_support(adev)) { + struct drm_crtc *crtc; + + drm_for_each_crtc(crtc, drm_dev) { + drm_modeset_lock(&crtc->mutex, NULL); + if (crtc->state->active) + ret = -EBUSY; + drm_modeset_unlock(&crtc->mutex); + if (ret < 0) + break; + } + } else { + mutex_lock(&drm_dev->mode_config.mutex); + drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL); + + drm_connector_list_iter_begin(drm_dev, &iter); + drm_for_each_connector_iter(list_connector, &iter) { + if (list_connector->dpms == DRM_MODE_DPMS_ON) { + ret = -EBUSY; + break; + } + } + + drm_connector_list_iter_end(&iter); + + drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); + mutex_unlock(&drm_dev->mode_config.mutex); + } + if (ret) + return ret; + } + + return 0; +} + static int amdgpu_pmops_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -2402,6 +2472,10 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) return -EBUSY; } + ret = amdgpu_runtime_idle_check_display(dev); + if (ret) + return ret; + /* wait for all rings to drain before suspending */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; @@ -2511,41 +2585,7 @@ static int amdgpu_pmops_runtime_idle(struct device *dev) return -EBUSY; } - if (amdgpu_device_has_dc_support(adev)) { - struct drm_crtc *crtc; - - drm_for_each_crtc(crtc, drm_dev) { - drm_modeset_lock(&crtc->mutex, NULL); - if (crtc->state->active) - ret = -EBUSY; - drm_modeset_unlock(&crtc->mutex); - if (ret < 0) - break; - } - - } else { - struct drm_connector *list_connector; - struct drm_connector_list_iter iter; - - mutex_lock(&drm_dev->mode_config.mutex); - drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL); - - drm_connector_list_iter_begin(drm_dev, &iter); - drm_for_each_connector_iter(list_connector, &iter) { - if (list_connector->dpms == DRM_MODE_DPMS_ON) { - ret = -EBUSY; - break; - } - } - - drm_connector_list_iter_end(&iter); - - drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); - mutex_unlock(&drm_dev->mode_config.mutex); - } - - if (ret == -EBUSY) - DRM_DEBUG_DRIVER("failing to power off - crtc active\n"); + ret = amdgpu_runtime_idle_check_display(dev); pm_runtime_mark_last_busy(dev); pm_runtime_autosuspend(dev); @@ -2575,6 +2615,7 @@ static const struct dev_pm_ops amdgpu_pm_ops = { .prepare = amdgpu_pmops_prepare, .complete = amdgpu_pmops_complete, .suspend = amdgpu_pmops_suspend, + .suspend_noirq = amdgpu_pmops_suspend_noirq, .resume = amdgpu_pmops_resume, .freeze = amdgpu_pmops_freeze, .thaw = amdgpu_pmops_thaw, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 8fe939976224..28a736c507bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev, * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - while (queue_bit-- >= 0) { + while (--queue_bit >= 0) { if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index ca2cfb65f976..a66a0881a934 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -561,9 +561,15 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 3, 0): case IP_VERSION(9, 4, 0): case IP_VERSION(9, 4, 1): case IP_VERSION(9, 4, 2): + case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): /* * noretry = 0 will cause kfd page fault tests fail * for some ASICs, so set default to 1 for these ASICs. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 25731719c627..940752488330 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1284,6 +1284,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, */ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct dma_fence *fence = NULL; struct amdgpu_bo *abo; int r; @@ -1303,7 +1304,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); if (bo->resource->mem_type != TTM_PL_VRAM || - !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) + !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || + adev->in_suspend || adev->shutdown) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 5320bb0883d8..317d80209e95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -300,8 +300,8 @@ void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); void amdgpu_ring_commit(struct amdgpu_ring *ring); void amdgpu_ring_undo(struct amdgpu_ring *ring); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, - unsigned int ring_size, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int prio, + unsigned int max_dw, struct amdgpu_irq_src *irq_src, + unsigned int irq_type, unsigned int hw_prio, atomic_t *sched_score); void amdgpu_ring_fini(struct amdgpu_ring *ring); void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index f99093f2ebc7..a0ee828a4a97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -52,7 +52,7 @@ #define FIRMWARE_ALDEBARAN "amdgpu/aldebaran_vcn.bin" #define FIRMWARE_BEIGE_GOBY "amdgpu/beige_goby_vcn.bin" #define FIRMWARE_YELLOW_CARP "amdgpu/yellow_carp_vcn.bin" -#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2_vcn.bin" +#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN); MODULE_FIRMWARE(FIRMWARE_PICASSO); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index e2fde88aaf5e..f06fb7f882e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -159,6 +159,7 @@ #define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8) #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) #define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) +#define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -279,6 +280,11 @@ struct amdgpu_fw_shared_fw_logging { uint32_t size; }; +struct amdgpu_fw_shared_smu_interface_info { + uint8_t smu_interface_type; + uint8_t padding[3]; +}; + struct amdgpu_fw_shared { uint32_t present_flag_0; uint8_t pad[44]; @@ -287,6 +293,7 @@ struct amdgpu_fw_shared { struct amdgpu_fw_shared_multi_queue multi_queue; struct amdgpu_fw_shared_sw_ring sw_ring; struct amdgpu_fw_shared_fw_logging fw_log; + struct amdgpu_fw_shared_smu_interface_info smu_interface_info; }; struct amdgpu_vcn_fwlog { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f4c6accd3226..9426e252d8aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3293,7 +3293,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3429,7 +3429,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_6[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000042), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3454,7 +3454,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_7[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000041), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -7689,6 +7689,7 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): preempt_disable(); clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 46d4bf27ebbb..b8cfcc6b1125 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1205,6 +1205,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, /* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */ { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, + /* Apple MacBook Pro (15-inch, 2019) Radeon Pro Vega 20 4 GB */ + { 0x1002, 0x69af, 0x106b, 0x019a, 0xc0 }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 3c1d440824a7..7c956cf21bc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -814,7 +814,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev); adev->gmc.aper_size = adev->gmc.real_vram_size; } @@ -1151,6 +1151,16 @@ static int gmc_v10_0_set_clockgating_state(void *handle, int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + /* + * The issue mmhub can't disconnect from DF with MMHUB clock gating being disabled + * is a new problem observed at DF 3.0.3, however with the same suspend sequence not + * seen any issue on the DF 3.0.2 series platform. + */ + if (adev->in_s0ix && adev->ip_versions[DF_HWIP][0] > IP_VERSION(3, 0, 2)) { + dev_dbg(adev->dev, "keep mmhub clock gating being enabled for s0ix\n"); + return 0; + } + r = adev->mmhub.funcs->set_clockgating(adev, state); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 344d819b4c1b..979da6f510e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -381,8 +381,9 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU && - adev->gmc.real_vram_size > adev->gmc.aper_size) { + if ((adev->flags & AMD_IS_APU) && + adev->gmc.real_vram_size > adev->gmc.aper_size && + !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index ca9841d5669f..1932a3e4af7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -581,7 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 431742eb7811..6009fbfdcc19 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1456,7 +1456,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) */ /* check whether both host-gpu and gpu-gpu xgmi links exist */ - if ((adev->flags & AMD_IS_APU) || + if (((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) || (adev->gmc.xgmi.supported && adev->gmc.xgmi.connected_to_cpu)) { adev->gmc.aper_base = @@ -1721,7 +1721,7 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); amdgpu_gart_table_vram_free(adev); - amdgpu_bo_unref(&adev->gmc.pdb0_bo); + amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index dff54190b96c..f0fbcda76f5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include "amdgpu.h" +#include "amdgpu_cs.h" #include "amdgpu_vcn.h" #include "amdgpu_pm.h" #include "soc15.h" @@ -1900,6 +1901,75 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .set_powergating_state = vcn_v1_0_set_powergating_state, }; +/* + * It is a hardware issue that VCN can't handle a GTT TMZ buffer on + * CHIP_RAVEN series ASIC. Move such a GTT TMZ buffer to VRAM domain + * before command submission as a workaround. + */ +static int vcn_v1_0_validate_bo(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + uint64_t addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; + struct amdgpu_vm *vm = &fpriv->vm; + struct amdgpu_bo_va_mapping *mapping; + struct amdgpu_bo *bo; + int r; + + addr &= AMDGPU_GMC_HOLE_MASK; + if (addr & 0x7) { + DRM_ERROR("VCN messages must be 8 byte aligned!\n"); + return -EINVAL; + } + + mapping = amdgpu_vm_bo_lookup_mapping(vm, addr/AMDGPU_GPU_PAGE_SIZE); + if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo) + return -EINVAL; + + bo = mapping->bo_va->base.bo; + if (!(bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED)) + return 0; + + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) { + DRM_ERROR("Failed to validate the VCN message BO (%d)!\n", r); + return r; + } + + return r; +} + +static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t msg_lo = 0, msg_hi = 0; + int i, r; + + if (!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) + return 0; + + for (i = 0; i < ib->length_dw; i += 2) { + uint32_t reg = amdgpu_ib_get_value(ib, i); + uint32_t val = amdgpu_ib_get_value(ib, i + 1); + + if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + msg_lo = val; + } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + msg_hi = val; + } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + r = vcn_v1_0_validate_bo(p, job, + ((u64)msg_hi) << 32 | msg_lo); + if (r) + return r; + } + } + + return 0; +} + static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, @@ -1910,6 +1980,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .get_rptr = vcn_v1_0_dec_ring_get_rptr, .get_wptr = vcn_v1_0_dec_ring_get_wptr, .set_wptr = vcn_v1_0_dec_ring_set_wptr, + .patch_cs_in_place = vcn_v1_0_ring_patch_cs_in_place, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index c87263ed20ec..cb5f0a12333f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -219,6 +219,11 @@ static int vcn_v3_0_sw_init(void *handle) cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG; + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2)) + fw_shared->smu_interface_info.smu_interface_type = 2; + else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1)) + fw_shared->smu_interface_info.smu_interface_type = 1; if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); @@ -575,8 +580,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect); /* VCN global tiling registers */ - WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( - UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( + UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) @@ -1480,8 +1485,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 339e12c94cff..62aa6c9d5123 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -483,15 +483,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, } /* Verify module parameters regarding mapped process number*/ - if ((hws_max_conc_proc < 0) - || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) { - dev_err(kfd_device, - "hws_max_conc_proc %d must be between 0 and %d, use %d instead\n", - hws_max_conc_proc, kfd->vm_info.vmid_num_kfd, - kfd->vm_info.vmid_num_kfd); + if (hws_max_conc_proc >= 0) + kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd); + else kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd; - } else - kfd->max_proc_per_quantum = hws_max_conc_proc; /* calculate max size of mqds needed for queues */ size = max_num_of_queues_per_device * @@ -536,7 +531,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, goto kfd_doorbell_error; } - kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; + if (amdgpu_use_xgmi_p2p) + kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; kfd->noretry = kfd->adev->gmc.noretry; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index acf4f7975850..198672264492 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -130,19 +130,33 @@ void program_sh_mem_settings(struct device_queue_manager *dqm, } static void increment_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count++; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count++; + + if (q->properties.is_gws) { + dqm->gws_queue_count++; + qpd->mapped_gws_queue = true; + } } static void decrement_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count--; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count--; + + if (q->properties.is_gws) { + dqm->gws_queue_count--; + qpd->mapped_gws_queue = false; + } } /* @@ -412,7 +426,7 @@ add_queue_to_list: list_add(&q->list, &qpd->queues_list); qpd->queue_count++; if (q->properties.is_active) - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q); /* * Unconditionally increment this counter, regardless of the queue's @@ -601,13 +615,8 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, deallocate_vmid(dqm, qpd, q); } qpd->queue_count--; - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q); return retval; } @@ -700,12 +709,11 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q, * dqm->active_queue_count to determine whether a new runlist must be * uploaded. */ - if (q->properties.is_active && !prev_active) - increment_queue_count(dqm, q->properties.type); - else if (!q->properties.is_active && prev_active) - decrement_queue_count(dqm, q->properties.type); - - if (q->gws && !q->properties.is_gws) { + if (q->properties.is_active && !prev_active) { + increment_queue_count(dqm, &pdd->qpd, q); + } else if (!q->properties.is_active && prev_active) { + decrement_queue_count(dqm, &pdd->qpd, q); + } else if (q->gws && !q->properties.is_gws) { if (q->properties.is_active) { dqm->gws_queue_count++; pdd->qpd.mapped_gws_queue = true; @@ -767,11 +775,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } + decrement_queue_count(dqm, qpd, q); if (WARN_ONCE(!dqm->sched_running, "Evict when stopped\n")) continue; @@ -817,7 +821,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, continue; q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); } pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, @@ -888,11 +892,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count++; - qpd->mapped_gws_queue = true; - } + increment_queue_count(dqm, qpd, q); if (WARN_ONCE(!dqm->sched_running, "Restore when stopped\n")) continue; @@ -950,7 +950,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, continue; q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, &pdd->qpd, q); } retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1378,7 +1378,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm, dqm->total_queue_count); list_add(&kq->list, &qpd->priv_queue_list); - increment_queue_count(dqm, kq->queue->properties.type); + increment_queue_count(dqm, qpd, kq->queue); qpd->is_debug = true; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); dqm_unlock(dqm); @@ -1392,7 +1392,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, { dqm_lock(dqm); list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); /* @@ -1467,7 +1467,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, qpd->queue_count++; if (q->properties.is_active) { - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q); execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1683,15 +1683,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, list_del(&q->list); qpd->queue_count--; if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); if (retval == -ETIME) qpd->reset_wavefronts = true; - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } } /* @@ -1932,7 +1928,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, /* Clean all kernel queues */ list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) { list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; dqm->total_queue_count--; filter = KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES; @@ -1945,13 +1941,8 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) deallocate_sdma_queue(dqm, q); - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q); dqm->total_queue_count--; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index deecccebe5b6..64f4a51cc880 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -749,6 +749,8 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events) event_waiters = kmalloc_array(num_events, sizeof(struct kfd_event_waiter), GFP_KERNEL); + if (!event_waiters) + return NULL; for (i = 0; (event_waiters) && (i < num_events) ; i++) { init_wait(&event_waiters[i].wait); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 9967a73d5b0f..8f58fc491b28 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1103,7 +1103,7 @@ struct kfd_criu_queue_priv_data { uint32_t priority; uint32_t q_percent; uint32_t doorbell_id; - uint32_t is_gws; + uint32_t gws; uint32_t sdma_id; uint32_t eop_ring_buffer_size; uint32_t ctx_save_restore_area_size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 6eca9509f2e3..4f58e671d39b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -636,6 +636,8 @@ static int criu_checkpoint_queue(struct kfd_process_device *pdd, q_data->ctx_save_restore_area_size = q->properties.ctx_save_restore_area_size; + q_data->gws = !!q->gws; + ret = pqm_checkpoint_mqd(&pdd->process->pqm, q->properties.queue_id, mqd, ctl_stack); if (ret) { pr_err("Failed checkpoint queue_mqd (%d)\n", ret); @@ -743,7 +745,6 @@ static void set_queue_properties_from_criu(struct queue_properties *qp, struct kfd_criu_queue_priv_data *q_data) { qp->is_interop = false; - qp->is_gws = q_data->is_gws; qp->queue_percent = q_data->q_percent; qp->priority = q_data->priority; qp->queue_address = q_data->q_address; @@ -826,12 +827,15 @@ int kfd_criu_restore_queue(struct kfd_process *p, NULL); if (ret) { pr_err("Failed to create new queue err:%d\n", ret); - ret = -EINVAL; + goto exit; } + if (q_data->gws) + ret = pqm_set_gws(&p->pqm, q_data->q_id, pdd->dev->gws); + exit: if (ret) - pr_err("Failed to create queue (%d)\n", ret); + pr_err("Failed to restore queue (%d)\n", ret); else pr_debug("Queue id %d was restored successfully\n", queue_id); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index e4beebb1c80a..f2e1d506ba21 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -247,15 +247,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) return ret; } - ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, - O_RDWR); - if (ret < 0) { - kfifo_free(&client->fifo); - kfree(client); - return ret; - } - *fd = ret; - init_waitqueue_head(&client->wait_queue); spin_lock_init(&client->lock); client->events = 0; @@ -265,5 +256,20 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) list_add_rcu(&client->list, &dev->smi_clients); spin_unlock(&dev->smi_lock); + ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, + O_RDWR); + if (ret < 0) { + spin_lock(&dev->smi_lock); + list_del_rcu(&client->list); + spin_unlock(&dev->smi_lock); + + synchronize_rcu(); + + kfifo_free(&client->fifo); + kfree(client); + return ret; + } + *fd = ret; + return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b30656959fd8..62139ff35476 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2714,7 +2714,8 @@ static int dm_resume(void *handle) * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->mst_port) + if (aconnector->dc_link && + aconnector->dc_link->type == dc_connection_mst_branch) continue; mutex_lock(&aconnector->hpd_lock); @@ -3972,7 +3973,7 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap max - min); } -static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, +static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, int bl_idx, u32 user_brightness) { @@ -4003,7 +4004,8 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx); } - return rc ? 0 : 1; + if (rc) + dm->actual_brightness[bl_idx] = user_brightness; } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -9947,7 +9949,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) /* restore the backlight level */ for (i = 0; i < dm->num_of_edps; i++) { if (dm->backlight_dev[i] && - (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i])) + (dm->actual_brightness[i] != dm->brightness[i])) amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]); } #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 6a908d736d6a..7e44b0429448 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -540,6 +540,12 @@ struct amdgpu_display_manager { * cached backlight values. */ u32 brightness[AMDGPU_DM_MAX_NUM_EDP]; + /** + * @actual_brightness: + * + * last successfully applied backlight values. + */ + u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP]; }; enum dsc_clock_force_state { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c index dfba6138f538..26feefbb8990 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c @@ -374,7 +374,7 @@ void dce_clock_read_ss_info(struct clk_mgr_internal *clk_mgr_dce) clk_mgr_dce->dprefclk_ss_percentage = info.spread_spectrum_percentage; } - if (clk_mgr_dce->base.ctx->dc->debug.ignore_dpref_ss) + if (clk_mgr_dce->base.ctx->dc->config.ignore_dpref_ss) clk_mgr_dce->dprefclk_ss_percentage = 0; } } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index edda572dc570..8be4c1970628 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -436,57 +436,84 @@ static void dcn315_clk_mgr_helper_populate_bw_params( struct integrated_info *bios_info, const DpmClocks_315_t *clock_table) { - int i, j; + int i; struct clk_bw_params *bw_params = clk_mgr->base.bw_params; - uint32_t max_dispclk = 0, max_dppclk = 0; - - j = -1; - - ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL); - - /* Find lowest DPM, FCLK is filled in reverse order*/ - - for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) { - if (clock_table->DfPstateTable[i].FClk != 0) { - j = i; - break; + uint32_t max_dispclk, max_dppclk, max_pstate, max_socclk, max_fclk = 0, min_pstate = 0; + struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1]; + + max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); + max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); + max_socclk = find_max_clk_value(clock_table->SocClocks, clock_table->NumSocClkLevelsEnabled); + + /* Find highest fclk pstate */ + for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) { + if (clock_table->DfPstateTable[i].FClk > max_fclk) { + max_fclk = clock_table->DfPstateTable[i].FClk; + max_pstate = i; } } - if (j == -1) { - /* clock table is all 0s, just use our own hardcode */ - ASSERT(0); - return; - } - - bw_params->clk_table.num_entries = j + 1; - - /* dispclk and dppclk can be max at any voltage, same number of levels for both */ - if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS && - clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) { - max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); - max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); - } else { - ASSERT(0); - } + /* For 315 we want to base clock table on dcfclk, need at least one entry regardless of pmfw table */ + for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) { + int j; + uint32_t min_fclk = clock_table->DfPstateTable[0].FClk; - for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) { - int temp; + for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) { + if (clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i] + && clock_table->DfPstateTable[j].FClk < min_fclk) { + min_fclk = clock_table->DfPstateTable[j].FClk; + min_pstate = j; + } + } - bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk; - bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk; - bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage; + bw_params->clk_table.entries[i].fclk_mhz = min_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i]; + bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i]; + bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; + bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; bw_params->clk_table.entries[i].wck_ratio = 1; - temp = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].dcfclk_mhz = temp; - temp = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].socclk_mhz = temp; + }; + + /* Make sure to include at least one entry and highest pstate */ + if (max_pstate != min_pstate) { + bw_params->clk_table.entries[i].fclk_mhz = max_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage( + clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[max_pstate].Voltage); + bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage( + clock_table, clock_table->SocClocks, clock_table->DfPstateTable[max_pstate].Voltage); bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; + bw_params->clk_table.entries[i].wck_ratio = 1; + i++; } + bw_params->clk_table.num_entries = i; + + /* Include highest socclk */ + if (bw_params->clk_table.entries[i-1].socclk_mhz < max_socclk) + bw_params->clk_table.entries[i-1].socclk_mhz = max_socclk; + /* Set any 0 clocks to max default setting. Not an issue for + * power since we aren't doing switching in such case anyway + */ + for (i = 0; i < bw_params->clk_table.num_entries; i++) { + if (!bw_params->clk_table.entries[i].fclk_mhz) { + bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz; + bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz; + bw_params->clk_table.entries[i].voltage = def_max.voltage; + } + if (!bw_params->clk_table.entries[i].dcfclk_mhz) + bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz) + bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz; + if (!bw_params->clk_table.entries[i].dispclk_mhz) + bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz; + if (!bw_params->clk_table.entries[i].dppclk_mhz) + bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz; + } bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 880ffea2afc6..2600313fea57 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -80,8 +80,8 @@ static const struct IP_BASE NBIO_BASE = { { { { 0x00000000, 0x00000014, 0x00000D #define VBIOSSMC_MSG_SetDppclkFreq 0x06 ///< Set DPP clock frequency in MHZ #define VBIOSSMC_MSG_SetHardMinDcfclkByFreq 0x07 ///< Set DCF clock frequency hard min in MHZ #define VBIOSSMC_MSG_SetMinDeepSleepDcfclk 0x08 ///< Set DCF clock minimum frequency in deep sleep in MHZ -#define VBIOSSMC_MSG_SetPhyclkVoltageByFreq 0x09 ///< Set display phy clock frequency in MHZ in case VMIN does not support phy frequency -#define VBIOSSMC_MSG_GetFclkFrequency 0x0A ///< Get FCLK frequency, return frequemcy in MHZ +#define VBIOSSMC_MSG_GetDtbclkFreq 0x09 ///< Get display dtb clock frequency in MHZ in case VMIN does not support phy frequency +#define VBIOSSMC_MSG_SetDtbClk 0x0A ///< Set dtb clock frequency, return frequemcy in MHZ #define VBIOSSMC_MSG_SetDisplayCount 0x0B ///< Inform PMFW of number of display connected #define VBIOSSMC_MSG_EnableTmdp48MHzRefclkPwrDown 0x0C ///< To ask PMFW turn off TMDP 48MHz refclk during display off to save power #define VBIOSSMC_MSG_UpdatePmeRestore 0x0D ///< To ask PMFW to write into Azalia for PME wake up event @@ -324,15 +324,26 @@ int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr) return (dprefclk_get_mhz * 1000); } -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr) +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr) { int fclk_get_mhz = -1; if (clk_mgr->smu_present) { fclk_get_mhz = dcn315_smu_send_msg_with_param( clk_mgr, - VBIOSSMC_MSG_GetFclkFrequency, + VBIOSSMC_MSG_GetDtbclkFreq, 0); } return (fclk_get_mhz * 1000); } + +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable) +{ + if (!clk_mgr->smu_present) + return; + + dcn315_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_SetDtbClk, + enable); +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h index 66fa42f8dd18..5aa3275ac7d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h @@ -37,6 +37,7 @@ #define NUM_SOC_VOLTAGE_LEVELS 4 #define NUM_DF_PSTATE_LEVELS 4 + typedef struct { uint16_t MinClock; // This is either DCFCLK or SOCCLK (in MHz) uint16_t MaxClock; // This is either DCFCLK or SOCCLK (in MHz) @@ -124,5 +125,6 @@ void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); void dcn315_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz); void dcn315_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr); int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr); -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr); +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr); +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable); #endif /* DAL_DC_315_SMU_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 702d00ce7da4..3121dd2d2a91 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -686,8 +686,8 @@ void dcn316_clk_mgr_construct( clk_mgr->base.base.dprefclk_khz = dcn316_smu_get_dpref_clk(&clk_mgr->base); clk_mgr->base.dccg->ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz; dce_clock_read_ss_info(&clk_mgr->base); - clk_mgr->base.dccg->ref_dtbclk_khz = - dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz); + /*clk_mgr->base.dccg->ref_dtbclk_khz = + dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz);*/ clk_mgr->base.base.bw_params = &dcn316_bw_params; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f6e19efea756..c436db416708 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2389,6 +2389,8 @@ static enum surface_update_type check_update_surfaces_for_stream( if (stream_update->mst_bw_update) su_flags->bits.mst_bw = 1; + if (stream_update->crtc_timing_adjust && dc_extended_blank_supported(dc)) + su_flags->bits.crtc_timing_adjust = 1; if (su_flags->raw != 0) overall_type = UPDATE_TYPE_FULL; @@ -2650,6 +2652,9 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->vrr_infopacket) stream->vrr_infopacket = *update->vrr_infopacket; + if (update->crtc_timing_adjust) + stream->adjust = *update->crtc_timing_adjust; + if (update->dpms_off) stream->dpms_off = *update->dpms_off; @@ -4051,3 +4056,17 @@ void dc_notify_vsync_int_state(struct dc *dc, struct dc_stream_state *stream, bo if (pipe->stream_res.abm && pipe->stream_res.abm->funcs->set_abm_pause) pipe->stream_res.abm->funcs->set_abm_pause(pipe->stream_res.abm, !enable, i, pipe->stream_res.tg->inst); } +/* + * dc_extended_blank_supported: Decide whether extended blank is supported + * + * Extended blank is a freesync optimization feature to be enabled in the future. + * During the extra vblank period gained from freesync, we have the ability to enter z9/z10. + * + * @param [in] dc: Current DC state + * @return: Indicate whether extended blank is supported (true or false) + */ +bool dc_extended_blank_supported(struct dc *dc) +{ + return dc->debug.extended_blank_optimization && !dc->debug.disable_z10 + && dc->caps.zstate_support && dc->caps.is_apu; +} diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index cb87dd643180..bbaa5abdf888 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -983,8 +983,7 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, destrictive = false; } } - } else if (dc_is_hdmi_signal(link->local_sink->sink_signal)) - destrictive = true; + } return destrictive; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 351081f574cb..22dabe596dfc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5216,6 +5216,62 @@ static void retrieve_cable_id(struct dc_link *link) &link->dpcd_caps.cable_id, &usbc_cable_id); } +/* DPRX may take some time to respond to AUX messages after HPD asserted. + * If AUX read unsuccessful, try to wake unresponsive DPRX by toggling DPCD SET_POWER (0x600). + */ +static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout_ms) +{ + enum dc_status status = DC_ERROR_UNEXPECTED; + uint8_t dpcd_data = 0; + uint64_t start_ts = 0; + uint64_t current_ts = 0; + uint64_t time_taken_ms = 0; + enum dc_connection_type type = dc_connection_none; + + status = core_link_read_dpcd( + link, + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, + &dpcd_data, + sizeof(dpcd_data)); + + if (status != DC_OK) { + DC_LOG_WARNING("%s: Read DPCD LTTPR_CAP failed - try to toggle DPCD SET_POWER for %lld ms.", + __func__, + timeout_ms); + start_ts = dm_get_timestamp(link->ctx); + + do { + if (!dc_link_detect_sink(link, &type) || type == dc_connection_none) + break; + + dpcd_data = DP_SET_POWER_D3; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + dpcd_data = DP_SET_POWER_D0; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + current_ts = dm_get_timestamp(link->ctx); + time_taken_ms = div_u64(dm_get_elapse_time_in_ns(link->ctx, current_ts, start_ts), 1000000); + } while (status != DC_OK && time_taken_ms < timeout_ms); + + DC_LOG_WARNING("%s: DPCD SET_POWER %s after %lld ms%s", + __func__, + (status == DC_OK) ? "succeeded" : "failed", + time_taken_ms, + (type == dc_connection_none) ? ". Unplugged." : "."); + } + + return status; +} + static bool retrieve_link_cap(struct dc_link *link) { /* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16, @@ -5251,6 +5307,15 @@ static bool retrieve_link_cap(struct dc_link *link) dc_link_aux_try_to_configure_timeout(link->ddc, LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); + /* Try to ensure AUX channel active before proceeding. */ + if (link->dc->debug.aux_wake_wa.bits.enable_wa) { + uint64_t timeout_ms = link->dc->debug.aux_wake_wa.bits.timeout_ms; + + if (link->dc->debug.aux_wake_wa.bits.use_default_timeout) + timeout_ms = LINK_AUX_WAKE_TIMEOUT_MS; + status = wa_try_to_wake_dprx(link, timeout_ms); + } + is_lttpr_present = dp_retrieve_lttpr_cap(link); /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7af153434e9e..d251c3f3a714 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1685,8 +1685,8 @@ bool dc_is_stream_unchanged( if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) return false; - // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks - if (old_stream->audio_info.mode_count != stream->audio_info.mode_count) + /*compare audio info*/ + if (memcmp(&old_stream->audio_info, &stream->audio_info, sizeof(stream->audio_info)) != 0) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4ffab7bb1098..9e79f60e6129 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -188,6 +188,7 @@ struct dc_caps { bool psp_setup_panel_mode; bool extended_aux_timeout_support; bool dmcub_support; + bool zstate_support; uint32_t num_of_internal_disp; enum dp_protocol_version max_dp_protocol_version; unsigned int mall_size_per_mem_channel; @@ -339,6 +340,7 @@ struct dc_config { bool is_asymmetric_memory; bool is_single_rank_dimm; bool use_pipe_ctx_sync_logic; + bool ignore_dpref_ss; }; enum visual_confirm { @@ -525,6 +527,22 @@ union dpia_debug_options { uint32_t raw; }; +/* AUX wake work around options + * 0: enable/disable work around + * 1: use default timeout LINK_AUX_WAKE_TIMEOUT_MS + * 15-2: reserved + * 31-16: timeout in ms + */ +union aux_wake_wa_options { + struct { + uint32_t enable_wa : 1; + uint32_t use_default_timeout : 1; + uint32_t rsvd: 14; + uint32_t timeout_ms : 16; + } bits; + uint32_t raw; +}; + struct dc_debug_data { uint32_t ltFailCount; uint32_t i2cErrorCount; @@ -703,14 +721,15 @@ struct dc_debug_options { bool enable_driver_sequence_debug; enum det_size crb_alloc_policy; int crb_alloc_policy_min_disp_count; -#if defined(CONFIG_DRM_AMD_DC_DCN) bool disable_z10; +#if defined(CONFIG_DRM_AMD_DC_DCN) bool enable_z9_disable_interface; bool enable_sw_cntl_psr; union dpia_debug_options dpia_debug; #endif bool apply_vendor_specific_lttpr_wa; - bool ignore_dpref_ss; + bool extended_blank_optimization; + union aux_wake_wa_options aux_wake_wa; uint8_t psr_power_use_phy_fsm; }; @@ -1369,6 +1388,8 @@ struct dc_sink_init_data { bool converter_disable_audio; }; +bool dc_extended_blank_supported(struct dc *dc); + struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params); /* Newer interfaces */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 99a750f561f8..c4168c11257c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -131,6 +131,7 @@ union stream_update_flags { uint32_t wb_update:1; uint32_t dsc_changed : 1; uint32_t mst_bw : 1; + uint32_t crtc_timing_adjust : 1; } bits; uint32_t raw; @@ -289,6 +290,7 @@ struct dc_stream_update { struct dc_3dlut *lut3d_func; struct test_pattern *pending_test_pattern; + struct dc_crtc_timing_adjust *crtc_timing_adjust; }; bool dc_is_stream_unchanged( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index c3e141c19a77..83fbea2df410 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1497,16 +1497,12 @@ void dcn10_init_hw(struct dc *dc) link->link_status.link_active = true; } - /* Power gate DSCs */ - if (!is_optimized_init_done) { - for (i = 0; i < res_pool->res_cap->num_dsc; i++) - if (hws->funcs.dsc_pg_control != NULL) - hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false); - } - /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -1559,8 +1555,6 @@ void dcn10_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (dc->clk_mgr->funcs->notify_wm_ranges) dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr); @@ -2056,7 +2050,7 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, { struct dc_context *dc_ctx = dc->ctx; int i, master = -1, embedded = -1; - struct dc_crtc_timing hw_crtc_timing[MAX_PIPES] = {0}; + struct dc_crtc_timing *hw_crtc_timing; uint64_t phase[MAX_PIPES]; uint64_t modulo[MAX_PIPES]; unsigned int pclk; @@ -2067,6 +2061,10 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, uint32_t dp_ref_clk_100hz = dc->res_pool->dp_clock_source->ctx->dc->clk_mgr->dprefclk_khz*10; + hw_crtc_timing = kcalloc(MAX_PIPES, sizeof(*hw_crtc_timing), GFP_KERNEL); + if (!hw_crtc_timing) + return master; + if (dc->config.vblank_alignment_dto_params && dc->res_pool->dp_clock_source->funcs->override_dp_pix_clk) { embedded_h_total = @@ -2130,6 +2128,8 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, } } + + kfree(hw_crtc_timing); return master; } @@ -2522,14 +2522,18 @@ void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) struct mpc *mpc = dc->res_pool->mpc; struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params); - if (per_pixel_alpha) - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; - else - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; - blnd_cfg.overlap_only = false; blnd_cfg.global_gain = 0xff; + if (per_pixel_alpha && pipe_ctx->plane_state->global_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN; + blnd_cfg.global_gain = pipe_ctx->plane_state->global_alpha_value; + } else if (per_pixel_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; + } else { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; + } + if (pipe_ctx->plane_state->global_alpha) blnd_cfg.global_alpha = pipe_ctx->plane_state->global_alpha_value; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index ab910deed481..b627c41713cc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1857,6 +1857,7 @@ void dcn20_optimize_bandwidth( struct dc_state *context) { struct hubbub *hubbub = dc->res_pool->hubbub; + int i; /* program dchubbub watermarks */ hubbub->funcs->program_watermarks(hubbub, @@ -1873,6 +1874,17 @@ void dcn20_optimize_bandwidth( dc->clk_mgr, context, true); + if (dc_extended_blank_supported(dc) && context->bw_ctx.bw.dcn.clk.zstate_support == DCN_ZSTATE_SUPPORT_ALLOW) { + for (i = 0; i < dc->res_pool->pipe_count; ++i) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->stream && pipe_ctx->plane_res.hubp->funcs->program_extended_blank + && pipe_ctx->stream->adjust.v_total_min == pipe_ctx->stream->adjust.v_total_max + && pipe_ctx->stream->adjust.v_total_max > pipe_ctx->stream->timing.v_total) + pipe_ctx->plane_res.hubp->funcs->program_extended_blank(pipe_ctx->plane_res.hubp, + pipe_ctx->dlg_regs.optimized_min_dst_y_next_start); + } + } /* increase compbuf size */ if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); @@ -2332,14 +2344,18 @@ void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) struct mpc *mpc = dc->res_pool->mpc; struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params); - if (per_pixel_alpha) - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; - else - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; - blnd_cfg.overlap_only = false; blnd_cfg.global_gain = 0xff; + if (per_pixel_alpha && pipe_ctx->plane_state->global_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN; + blnd_cfg.global_gain = pipe_ctx->plane_state->global_alpha_value; + } else if (per_pixel_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; + } else { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; + } + if (pipe_ctx->plane_state->global_alpha) blnd_cfg.global_alpha = pipe_ctx->plane_state->global_alpha_value; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d473708d5399..7802d603f796 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1976,7 +1976,6 @@ int dcn20_validate_apply_pipe_split_flags( /*If need split for odm but 4 way split already*/ if (split[i] == 2 && ((pipe->prev_odm_pipe && !pipe->prev_odm_pipe->prev_odm_pipe) || !pipe->next_odm_pipe)) { - ASSERT(0); /* NOT expected yet */ merge[i] = true; /* 4 -> 2 ODM */ } else if (split[i] == 0 && pipe->prev_odm_pipe) { ASSERT(0); /* NOT expected yet */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 612732656772..faab59508d82 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -644,7 +644,7 @@ static const struct dc_debug_options debug_defaults_drv = { .clock_trace = true, .disable_pplib_clock_request = true, .min_disp_clk_khz = 100000, - .pipe_split_policy = MPC_SPLIT_DYNAMIC, + .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, @@ -997,6 +997,7 @@ static struct clock_source *dcn21_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index ed0a0e5fd805..f61ec8763844 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -547,6 +547,9 @@ void dcn30_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -624,8 +627,6 @@ void dcn30_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c index 3e6d6ebd199e..51c5f3685470 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c @@ -1042,5 +1042,7 @@ void hubbub31_construct(struct dcn20_hubbub *hubbub31, hubbub31->detile_buf_size = det_size_kb * 1024; hubbub31->pixel_chunk_size = pixel_chunk_size_kb * 1024; hubbub31->crb_size_segs = config_return_buffer_size_kb / DCN31_CRB_SEGMENT_SIZE_KB; + + hubbub31->debug_test_index_pstate = 0x6; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c index 53b792b997b7..8ae6117953ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c @@ -54,6 +54,13 @@ void hubp31_soft_reset(struct hubp *hubp, bool reset) REG_UPDATE(DCHUBP_CNTL, HUBP_SOFT_RESET, reset); } +void hubp31_program_extended_blank(struct hubp *hubp, unsigned int min_dst_y_next_start_optimized) +{ + struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + + REG_SET(BLANK_OFFSET_1, 0, MIN_DST_Y_NEXT_START, min_dst_y_next_start_optimized); +} + static struct hubp_funcs dcn31_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, .hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled, @@ -80,6 +87,7 @@ static struct hubp_funcs dcn31_hubp_funcs = { .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, .hubp_in_blank = hubp1_in_blank, + .program_extended_blank = hubp31_program_extended_blank, }; bool hubp31_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 4be228680909..631d8ac63aa4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -199,6 +199,9 @@ void dcn31_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -248,8 +251,6 @@ void dcn31_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); @@ -338,20 +339,20 @@ void dcn31_enable_power_gating_plane( bool enable) { bool force_on = true; /* disable power gating */ + uint32_t org_ip_request_cntl = 0; if (enable && !hws->ctx->dc->debug.disable_hubp_power_gate) force_on = false; + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); /* DCHUBP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); /* DPP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); force_on = true; /* disable power gating */ if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) @@ -359,11 +360,11 @@ void dcn31_enable_power_gating_plane( /* DCS0/1/2/3/4/5 */ REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); + + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); } void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 8afe2130d7c5..e05527a3a8ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -124,7 +124,6 @@ static bool optc31_enable_crtc(struct timing_generator *optc) static bool optc31_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* disable otg request until end of the first line * in the vertical blank region */ @@ -138,6 +137,7 @@ static bool optc31_disable_crtc(struct timing_generator *optc) REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, 1, 100000); + optc1_clear_optc_underflow(optc); return true; } @@ -158,6 +158,9 @@ static bool optc31_immediate_disable_crtc(struct timing_generator *optc) OTG_BUSY, 0, 1, 100000); + /* clear the false state */ + optc1_clear_optc_underflow(optc); + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 89b7b6b7254a..63934ecf6be8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -2032,7 +2032,9 @@ bool dcn31_validate_bandwidth(struct dc *dc, BW_VAL_TRACE_COUNT(); + DC_FP_START(); out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); + DC_FP_END(); // Disable fast_validate to set min dcfclk in alculate_wm_and_dlg if (pipe_cnt == 0) @@ -2232,6 +2234,7 @@ static bool dcn31_resource_construct( dc->caps.extended_aux_timeout_support = true; dc->caps.dmcub_support = true; dc->caps.is_apu = true; + dc->caps.zstate_support = true; /* Color pipeline capabilities */ dc->caps.color.dpp.dcn_arch = 1; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 2f6122153bdb..f93af45aeab4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -722,8 +722,10 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc { int plane_count; int i; + unsigned int optimized_min_dst_y_next_start_us; plane_count = 0; + optimized_min_dst_y_next_start_us = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; @@ -744,11 +746,22 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; + if (dc_extended_blank_supported(dc)) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream == context->streams[0] + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min == context->res_ctx.pipe_ctx[i].stream->adjust.v_total_max + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min > context->res_ctx.pipe_ctx[i].stream->timing.v_total) { + optimized_min_dst_y_next_start_us = + context->res_ctx.pipe_ctx[i].dlg_regs.optimized_min_dst_y_next_start_us; + break; + } + } + } /* zstate only supported on PWRSEQ0 and when there's <2 planes*/ if (link->link_index != 0 || stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) + if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000) return DCN_ZSTATE_SUPPORT_ALLOW; else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; @@ -786,8 +799,6 @@ void dcn20_calculate_dlg_params( != dm_dram_clock_change_unsupported; context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; - context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); - context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) @@ -843,6 +854,7 @@ void dcn20_calculate_dlg_params( &pipes[pipe_idx].pipe); pipe_idx++; } + context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); } static void swizzle_to_dml_params( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c index e0fecf127bd5..53d760e169e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c @@ -1055,6 +1055,7 @@ static void dml_rq_dlg_get_dlg_params( float vba__refcyc_per_req_delivery_pre_l = get_refcyc_per_req_delivery_pre_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA float vba__refcyc_per_req_delivery_l = get_refcyc_per_req_delivery_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA + int blank_lines; memset(disp_dlg_regs, 0, sizeof(*disp_dlg_regs)); memset(disp_ttu_regs, 0, sizeof(*disp_ttu_regs)); @@ -1080,6 +1081,18 @@ static void dml_rq_dlg_get_dlg_params( dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start; disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start) * dml_pow(2, 2)); + blank_lines = (dst->vblank_end + dst->vtotal_min - dst->vblank_start - dst->vstartup_start - 1); + if (blank_lines < 0) + blank_lines = 0; + if (blank_lines != 0) { + disp_dlg_regs->optimized_min_dst_y_next_start_us = + ((unsigned int) blank_lines * dst->hactive) / (unsigned int) dst->pixel_rate_mhz; + disp_dlg_regs->optimized_min_dst_y_next_start = + (unsigned int)(((double) (dlg_vblank_start + blank_lines)) * dml_pow(2, 2)); + } else { + // use unoptimized value + disp_dlg_regs->optimized_min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start; + } ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int)dml_pow(2, 18)); dml_print("DML_DLG: %s: min_ttu_vblank (us) = %3.2f\n", __func__, min_ttu_vblank); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index 59f0a61c33cf..2df660cd8801 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -446,6 +446,8 @@ struct _vcs_dpi_display_dlg_regs_st { unsigned int refcyc_h_blank_end; unsigned int dlg_vblank_end; unsigned int min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start_us; unsigned int refcyc_per_htotal; unsigned int refcyc_x_after_scaler; unsigned int dst_y_after_scaler; diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index efc2339f1fa0..4385d19bc489 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -864,11 +864,11 @@ static bool setup_dsc_config( min_slices_h = inc_num_slices(dsc_common_caps.slice_caps, min_slices_h); } + is_dsc_possible = (min_slices_h <= max_slices_h); + if (pic_width % min_slices_h != 0) min_slices_h = 0; // DSC TODO: Maybe try increasing the number of slices first? - is_dsc_possible = (min_slices_h <= max_slices_h); - if (min_slices_h == 0 && max_slices_h == 0) is_dsc_possible = false; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index ab9939db8cea..44f167d2584f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -33,6 +33,7 @@ #define MAX_MTP_SLOT_COUNT 64 #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50 #define TRAINING_AUX_RD_INTERVAL 100 //us +#define LINK_AUX_WAKE_TIMEOUT_MS 1500 // Timeout when trying to wake unresponsive DPRX. struct dc_link; struct dc_stream_state; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index e45b7993c5c5..ad69d78c4ac3 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -195,6 +195,9 @@ struct hubp_funcs { void (*hubp_set_flip_int)(struct hubp *hubp); + void (*program_extended_blank)(struct hubp *hubp, + unsigned int min_dst_y_next_start_optimized); + void (*hubp_wait_pipe_read_start)(struct hubp *hubp); }; diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index b691aa45e84f..79bc207415bc 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -100,7 +100,8 @@ enum vsc_packet_revision { //PB7 = MD0 #define MASK_VTEM_MD0__VRR_EN 0x01 #define MASK_VTEM_MD0__M_CONST 0x02 -#define MASK_VTEM_MD0__RESERVED2 0x0C +#define MASK_VTEM_MD0__QMS_EN 0x04 +#define MASK_VTEM_MD0__RESERVED2 0x08 #define MASK_VTEM_MD0__FVA_FACTOR_M1 0xF0 //MD1 @@ -109,7 +110,7 @@ enum vsc_packet_revision { //MD2 #define MASK_VTEM_MD2__BASE_REFRESH_RATE_98 0x03 #define MASK_VTEM_MD2__RB 0x04 -#define MASK_VTEM_MD2__RESERVED3 0xF8 +#define MASK_VTEM_MD2__NEXT_TFR 0xF8 //MD3 #define MASK_VTEM_MD3__BASE_REFRESH_RATE_07 0xFF diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 89fbee568be4..72e7b5d40af6 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -173,6 +173,17 @@ bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev) if (!pp_funcs || !pp_funcs->get_asic_baco_capability) return false; + /* Don't use baco for reset in S3. + * This is a workaround for some platforms + * where entering BACO during suspend + * seems to cause reboots or hangs. + * This might be related to the fact that BACO controls + * power to the whole GPU including devices like audio and USB. + * Powering down/up everything may adversely affect these other + * devices. Needs more investigation. + */ + if (adev->in_s3) + return false; mutex_lock(&adev->pm.mutex); @@ -416,6 +427,7 @@ int amdgpu_dpm_read_sensor(struct amdgpu_device *adev, enum amd_pp_sensors senso void amdgpu_dpm_compute_clocks(struct amdgpu_device *adev) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; + int i; if (!adev->pm.dpm_enabled) return; @@ -423,6 +435,15 @@ void amdgpu_dpm_compute_clocks(struct amdgpu_device *adev) if (!pp_funcs->pm_compute_clocks) return; + if (adev->mode_info.num_crtc) + amdgpu_display_bandwidth_update(adev); + + for (i = 0; i < AMDGPU_MAX_RINGS; i++) { + struct amdgpu_ring *ring = adev->rings[i]; + if (ring && ring->sched.ready) + amdgpu_fence_wait_empty(ring); + } + mutex_lock(&adev->pm.mutex); pp_funcs->pm_compute_clocks(adev->powerplay.pp_handle); mutex_unlock(&adev->pm.mutex); @@ -432,6 +453,20 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable) { int ret = 0; + if (adev->family == AMDGPU_FAMILY_SI) { + mutex_lock(&adev->pm.mutex); + if (enable) { + adev->pm.dpm.uvd_active = true; + adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD; + } else { + adev->pm.dpm.uvd_active = false; + } + mutex_unlock(&adev->pm.mutex); + + amdgpu_dpm_compute_clocks(adev); + return; + } + ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable); if (ret) DRM_ERROR("Dpm %s uvd failed, ret = %d. \n", @@ -442,6 +477,21 @@ void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable) { int ret = 0; + if (adev->family == AMDGPU_FAMILY_SI) { + mutex_lock(&adev->pm.mutex); + if (enable) { + adev->pm.dpm.vce_active = true; + /* XXX select vce level based on ring/task */ + adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; + } else { + adev->pm.dpm.vce_active = false; + } + mutex_unlock(&adev->pm.mutex); + + amdgpu_dpm_compute_clocks(adev); + return; + } + ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable); if (ret) DRM_ERROR("Dpm %s vce failed, ret = %d. \n", @@ -500,6 +550,9 @@ int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size) struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_pages_num(smu, size); mutex_unlock(&adev->pm.mutex); @@ -512,6 +565,9 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_channel_flag(smu, size); mutex_unlock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index 9613c6181c17..d3fe149d8476 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -1028,16 +1028,6 @@ static int amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) void amdgpu_legacy_dpm_compute_clocks(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - int i = 0; - - if (adev->mode_info.num_crtc) - amdgpu_display_bandwidth_update(adev); - - for (i = 0; i < AMDGPU_MAX_RINGS; i++) { - struct amdgpu_ring *ring = adev->rings[i]; - if (ring && ring->sched.ready) - amdgpu_fence_wait_empty(ring); - } amdgpu_dpm_get_active_displays(adev); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index caae54487f9c..633dab14f51c 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -3892,40 +3892,6 @@ static int si_set_boot_state(struct amdgpu_device *adev) } #endif -static int si_set_powergating_by_smu(void *handle, - uint32_t block_type, - bool gate) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - switch (block_type) { - case AMD_IP_BLOCK_TYPE_UVD: - if (!gate) { - adev->pm.dpm.uvd_active = true; - adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD; - } else { - adev->pm.dpm.uvd_active = false; - } - - amdgpu_legacy_dpm_compute_clocks(handle); - break; - case AMD_IP_BLOCK_TYPE_VCE: - if (!gate) { - adev->pm.dpm.vce_active = true; - /* XXX select vce level based on ring/task */ - adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; - } else { - adev->pm.dpm.vce_active = false; - } - - amdgpu_legacy_dpm_compute_clocks(handle); - break; - default: - break; - } - return 0; -} - static int si_set_sw_state(struct amdgpu_device *adev) { return (amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_SwitchToSwState) == PPSMC_Result_OK) ? @@ -8125,7 +8091,6 @@ static const struct amd_pm_funcs si_dpm_funcs = { .print_power_state = &si_dpm_print_power_state, .debugfs_print_current_performance_level = &si_dpm_debugfs_print_current_performance_level, .force_performance_level = &si_dpm_force_performance_level, - .set_powergating_by_smu = &si_set_powergating_by_smu, .vblank_too_short = &si_dpm_vblank_too_short, .set_fan_control_mode = &si_dpm_set_fan_control_mode, .get_fan_control_mode = &si_dpm_get_fan_control_mode, diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index a2da46bf3985..71e9c6ce6b1a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1487,16 +1487,6 @@ static void pp_pm_compute_clocks(void *handle) { struct pp_hwmgr *hwmgr = handle; struct amdgpu_device *adev = hwmgr->adev; - int i = 0; - - if (adev->mode_info.num_crtc) - amdgpu_display_bandwidth_update(adev); - - for (i = 0; i < AMDGPU_MAX_RINGS; i++) { - struct amdgpu_ring *ring = adev->rings[i]; - if (ring && ring->sched.ready) - amdgpu_fence_wait_empty(ring); - } if (!amdgpu_device_has_dc_support(adev)) { amdgpu_dpm_get_active_displays(adev); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 9ddd8491ff00..ede71de2343d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -773,13 +773,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : + (data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk / 100) : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -792,11 +792,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 7bfac029e513..b81711c4ff33 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -991,7 +991,7 @@ static int smu_v13_0_5_set_performance_level(struct smu_context *smu, return -EINVAL; } - if (sclk_min && sclk_max) { + if (sclk_min && sclk_max && smu_v13_0_5_clk_dpm_is_enabled(smu, SMU_SCLK)) { ret = smu_v13_0_5_set_soft_freq_limited_range(smu, SMU_SCLK, sclk_min, diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 026e4e29a0f3..9a2cfab3a177 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -244,21 +244,6 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, if (panel) *panel = NULL; - /** - * Devices can also be child nodes when we also control that device - * through the upstream device (ie, MIPI-DCS for a MIPI-DSI device). - * - * Lookup for a child node of the given parent that isn't either port - * or ports. - */ - for_each_available_child_of_node(np, remote) { - if (of_node_name_eq(remote, "port") || - of_node_name_eq(remote, "ports")) - continue; - - goto of_find_panel_or_bridge; - } - /* * of_graph_get_remote_node() produces a noisy error message if port * node isn't found and the absence of the port is a legit case here, @@ -269,8 +254,6 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, return -ENODEV; remote = of_graph_get_remote_node(np, port, endpoint); - -of_find_panel_or_bridge: if (!remote) return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index d667657e3606..f868db8be02a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4383,13 +4383,20 @@ intel_dp_update_420(struct intel_dp *intel_dp) static void intel_dp_set_edid(struct intel_dp *intel_dp) { + struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_connector *connector = intel_dp->attached_connector; struct edid *edid; + bool vrr_capable; intel_dp_unset_edid(intel_dp); edid = intel_dp_get_edid(intel_dp); connector->detect_edid = edid; + vrr_capable = intel_vrr_is_capable(&connector->base); + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] VRR capable: %s\n", + connector->base.base.id, connector->base.name, str_yes_no(vrr_capable)); + drm_connector_set_vrr_capable_property(&connector->base, vrr_capable); + intel_dp_update_dfp(intel_dp, edid); intel_dp_update_420(intel_dp); @@ -4422,6 +4429,9 @@ intel_dp_unset_edid(struct intel_dp *intel_dp) intel_dp->dfp.ycbcr_444_to_420 = false; connector->base.ycbcr_420_allowed = false; + + drm_connector_set_vrr_capable_property(&connector->base, + false); } static int @@ -4572,14 +4582,9 @@ static int intel_dp_get_modes(struct drm_connector *connector) int num_modes = 0; edid = intel_connector->detect_edid; - if (edid) { + if (edid) num_modes = intel_connector_update_modes(connector, edid); - if (intel_vrr_is_capable(connector)) - drm_connector_set_vrr_capable_property(connector, - true); - } - /* Also add fixed mode, which may or may not be present in EDID */ if (intel_dp_is_edp(intel_attached_dp(intel_connector)) && intel_connector->panel.fixed_mode) { diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 97cf3cac0105..fb6cf30ee628 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -97,6 +97,14 @@ #define INTEL_EDP_BRIGHTNESS_OPTIMIZATION_1 0x359 +enum intel_dp_aux_backlight_modparam { + INTEL_DP_AUX_BACKLIGHT_AUTO = -1, + INTEL_DP_AUX_BACKLIGHT_OFF = 0, + INTEL_DP_AUX_BACKLIGHT_ON = 1, + INTEL_DP_AUX_BACKLIGHT_FORCE_VESA = 2, + INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL = 3, +}; + /* Intel EDP backlight callbacks */ static bool intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) @@ -126,6 +134,24 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) return false; } + /* + * If we don't have HDR static metadata there is no way to + * runtime detect used range for nits based control. For now + * do not use Intel proprietary eDP backlight control if we + * don't have this data in panel EDID. In case we find panel + * which supports only nits based control, but doesn't provide + * HDR static metadata we need to start maintaining table of + * ranges for such panels. + */ + if (i915->params.enable_dpcd_backlight != INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL && + !(connector->base.hdr_sink_metadata.hdmi_type1.metadata_type & + BIT(HDMI_STATIC_METADATA_TYPE1))) { + drm_info(&i915->drm, + "Panel is missing HDR static metadata. Possible support for Intel HDR backlight interface is not used. If your backlight controls don't work try booting with i915.enable_dpcd_backlight=%d. needs this, please file a _new_ bug report on drm/i915, see " FDO_BUG_URL " for details.\n", + INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL); + return false; + } + panel->backlight.edp.intel.sdr_uses_aux = tcon_cap[2] & INTEL_EDP_SDR_TCON_BRIGHTNESS_AUX_CAP; @@ -413,14 +439,6 @@ static const struct intel_panel_bl_funcs intel_dp_vesa_bl_funcs = { .get = intel_dp_aux_vesa_get_backlight, }; -enum intel_dp_aux_backlight_modparam { - INTEL_DP_AUX_BACKLIGHT_AUTO = -1, - INTEL_DP_AUX_BACKLIGHT_OFF = 0, - INTEL_DP_AUX_BACKLIGHT_ON = 1, - INTEL_DP_AUX_BACKLIGHT_FORCE_VESA = 2, - INTEL_DP_AUX_BACKLIGHT_FORCE_INTEL = 3, -}; - int intel_dp_aux_init_backlight_funcs(struct intel_connector *connector) { struct drm_device *dev = connector->base.dev; diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 87f4af3fd523..3e61a8936245 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -1037,7 +1037,7 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state, struct intel_plane_state *plane_state = intel_atomic_get_new_plane_state(state, plane); const struct drm_framebuffer *fb = plane_state->hw.fb; - struct intel_crtc *crtc = to_intel_crtc(plane_state->uapi.crtc); + struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc); const struct intel_crtc_state *crtc_state; struct intel_fbc *fbc = plane->fbc; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index bff8c2d73cdf..6c9e6e7f0afd 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -887,6 +887,20 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, return false; } + /* Wa_16011303918:adl-p */ + if (crtc_state->vrr.enable && + IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) { + drm_dbg_kms(&dev_priv->drm, + "PSR2 not enabled, not compatible with HW stepping + VRR\n"); + return false; + } + + if (!_compute_psr2_sdp_prior_scanline_indication(intel_dp, crtc_state)) { + drm_dbg_kms(&dev_priv->drm, + "PSR2 not enabled, PSR2 SDP indication do not fit in hblank\n"); + return false; + } + if (HAS_PSR2_SEL_FETCH(dev_priv)) { if (!intel_psr2_sel_fetch_config_valid(intel_dp, crtc_state) && !HAS_PSR_HW_TRACKING(dev_priv)) { @@ -900,12 +914,12 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, if (!crtc_state->enable_psr2_sel_fetch && IS_TGL_DISPLAY_STEP(dev_priv, STEP_A0, STEP_C0)) { drm_dbg_kms(&dev_priv->drm, "PSR2 HW tracking is not supported this Display stepping\n"); - return false; + goto unsupported; } if (!psr2_granularity_check(intel_dp, crtc_state)) { drm_dbg_kms(&dev_priv->drm, "PSR2 not enabled, SU granularity not compatible\n"); - return false; + goto unsupported; } if (!crtc_state->enable_psr2_sel_fetch && @@ -914,25 +928,15 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, "PSR2 not enabled, resolution %dx%d > max supported %dx%d\n", crtc_hdisplay, crtc_vdisplay, psr_max_h, psr_max_v); - return false; - } - - if (!_compute_psr2_sdp_prior_scanline_indication(intel_dp, crtc_state)) { - drm_dbg_kms(&dev_priv->drm, - "PSR2 not enabled, PSR2 SDP indication do not fit in hblank\n"); - return false; - } - - /* Wa_16011303918:adl-p */ - if (crtc_state->vrr.enable && - IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) { - drm_dbg_kms(&dev_priv->drm, - "PSR2 not enabled, not compatible with HW stepping + VRR\n"); - return false; + goto unsupported; } tgl_dc3co_exitline_compute_config(intel_dp, crtc_state); return true; + +unsupported: + crtc_state->enable_psr2_sel_fetch = false; + return false; } void intel_psr_compute_config(struct intel_dp *intel_dp, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index c3ea243d414d..0c5c43852e24 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -70,7 +70,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, * mmap ioctl is disallowed for all discrete platforms, * and for all platforms with GRAPHICS_VER > 12. */ - if (IS_DGFX(i915) || GRAPHICS_VER(i915) > 12) + if (IS_DGFX(i915) || GRAPHICS_VER_FULL(i915) > IP_VER(12, 0)) return -EOPNOTSUPP; if (args->flags & ~(I915_MMAP_WC)) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 3c87d77d2cf6..a9354f8f110d 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4345,12 +4345,12 @@ #define _DSPAADDR 0x70184 #define _DSPASTRIDE 0x70188 #define _DSPAPOS 0x7018C /* reserved */ -#define DISP_POS_Y_MASK REG_GENMASK(31, 0) +#define DISP_POS_Y_MASK REG_GENMASK(31, 16) #define DISP_POS_Y(y) REG_FIELD_PREP(DISP_POS_Y_MASK, (y)) #define DISP_POS_X_MASK REG_GENMASK(15, 0) #define DISP_POS_X(x) REG_FIELD_PREP(DISP_POS_X_MASK, (x)) #define _DSPASIZE 0x70190 -#define DISP_HEIGHT_MASK REG_GENMASK(31, 0) +#define DISP_HEIGHT_MASK REG_GENMASK(31, 16) #define DISP_HEIGHT(h) REG_FIELD_PREP(DISP_HEIGHT_MASK, (h)) #define DISP_WIDTH_MASK REG_GENMASK(15, 0) #define DISP_WIDTH(w) REG_FIELD_PREP(DISP_WIDTH_MASK, (w)) @@ -5152,7 +5152,7 @@ #define _SEL_FETCH_PLANE_BASE_6_A 0x70940 #define _SEL_FETCH_PLANE_BASE_7_A 0x70960 #define _SEL_FETCH_PLANE_BASE_CUR_A 0x70880 -#define _SEL_FETCH_PLANE_BASE_1_B 0x70990 +#define _SEL_FETCH_PLANE_BASE_1_B 0x71890 #define _SEL_FETCH_PLANE_BASE_A(plane) _PICK(plane, \ _SEL_FETCH_PLANE_BASE_1_A, \ diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 87428fb23d9f..a2277a0d6d06 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -222,6 +222,7 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; const struct of_device_id *match = of_match_node(dw_hdmi_imx_dt_ids, np); struct imx_hdmi *hdmi; + int ret; hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); if (!hdmi) @@ -243,10 +244,15 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) hdmi->bridge = of_drm_find_bridge(np); if (!hdmi->bridge) { dev_err(hdmi->dev, "Unable to find bridge\n"); + dw_hdmi_remove(hdmi->hdmi); return -ENODEV; } - return component_add(&pdev->dev, &dw_hdmi_imx_ops); + ret = component_add(&pdev->dev, &dw_hdmi_imx_ops); + if (ret) + dw_hdmi_remove(hdmi->hdmi); + + return ret; } static int dw_hdmi_imx_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index e5078d03020d..fb0e951248f6 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -572,6 +572,8 @@ static int imx_ldb_panel_ddc(struct device *dev, edidp = of_get_property(child, "edid", &edid_len); if (edidp) { channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL); + if (!channel->edid) + return -ENOMEM; } else if (!channel->panel) { /* fallback to display-timings node */ ret = of_get_drm_display_mode(child, diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 06cb1a59b9bc..63ba2ad84679 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -75,8 +75,10 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); - if (ret) + if (ret) { + drm_mode_destroy(connector->dev, mode); return ret; + } drm_mode_copy(mode, &imxpd->mode); mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 83c31b2ad865..ccc4fcf7a630 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1742,7 +1742,7 @@ a6xx_create_private_address_space(struct msm_gpu *gpu) return ERR_CAST(mmu); return msm_gem_address_space_create(mmu, - "gpu", 0x100000000ULL, 0x1ffffffffULL); + "gpu", 0x100000000ULL, SZ_4G); } static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 89cfd84760d7..8706bcdd1472 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -599,43 +599,91 @@ static const struct of_device_id dt_match[] = { {} }; -#ifdef CONFIG_PM -static int adreno_resume(struct device *dev) +static int adreno_runtime_resume(struct device *dev) { struct msm_gpu *gpu = dev_to_gpu(dev); return gpu->funcs->pm_resume(gpu); } -static int active_submits(struct msm_gpu *gpu) +static int adreno_runtime_suspend(struct device *dev) { - int active_submits; - mutex_lock(&gpu->active_lock); - active_submits = gpu->active_submits; - mutex_unlock(&gpu->active_lock); - return active_submits; + struct msm_gpu *gpu = dev_to_gpu(dev); + + /* + * We should be holding a runpm ref, which will prevent + * runtime suspend. In the system suspend path, we've + * already waited for active jobs to complete. + */ + WARN_ON_ONCE(gpu->active_submits); + + return gpu->funcs->pm_suspend(gpu); +} + +static void suspend_scheduler(struct msm_gpu *gpu) +{ + int i; + + /* + * Shut down the scheduler before we force suspend, so that + * suspend isn't racing with scheduler kthread feeding us + * more work. + * + * Note, we just want to park the thread, and let any jobs + * that are already on the hw queue complete normally, as + * opposed to the drm_sched_stop() path used for handling + * faulting/timed-out jobs. We can't really cancel any jobs + * already on the hw queue without racing with the GPU. + */ + for (i = 0; i < gpu->nr_rings; i++) { + struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched; + kthread_park(sched->thread); + } } -static int adreno_suspend(struct device *dev) +static void resume_scheduler(struct msm_gpu *gpu) +{ + int i; + + for (i = 0; i < gpu->nr_rings; i++) { + struct drm_gpu_scheduler *sched = &gpu->rb[i]->sched; + kthread_unpark(sched->thread); + } +} + +static int adreno_system_suspend(struct device *dev) { struct msm_gpu *gpu = dev_to_gpu(dev); - int remaining; + int remaining, ret; + + suspend_scheduler(gpu); remaining = wait_event_timeout(gpu->retire_event, - active_submits(gpu) == 0, + gpu->active_submits == 0, msecs_to_jiffies(1000)); if (remaining == 0) { dev_err(dev, "Timeout waiting for GPU to suspend\n"); - return -EBUSY; + ret = -EBUSY; + goto out; } - return gpu->funcs->pm_suspend(gpu); + ret = pm_runtime_force_suspend(dev); +out: + if (ret) + resume_scheduler(gpu); + + return ret; +} + +static int adreno_system_resume(struct device *dev) +{ + resume_scheduler(dev_to_gpu(dev)); + return pm_runtime_force_resume(dev); } -#endif static const struct dev_pm_ops adreno_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) - SET_RUNTIME_PM_OPS(adreno_suspend, adreno_resume, NULL) + SYSTEM_SLEEP_PM_OPS(adreno_system_suspend, adreno_system_resume) + RUNTIME_PM_OPS(adreno_runtime_suspend, adreno_runtime_resume, NULL) }; static struct platform_driver adreno_driver = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index c515b7cf922c..c61b5b283f08 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -54,87 +54,87 @@ struct dpu_intr_reg { * When making changes be sure to sync with dpu_hw_intr_reg */ static const struct dpu_intr_reg dpu_intr_set[] = { - { + [MDP_SSPP_TOP0_INTR] = { MDP_SSPP_TOP0_OFF+INTR_CLEAR, MDP_SSPP_TOP0_OFF+INTR_EN, MDP_SSPP_TOP0_OFF+INTR_STATUS }, - { + [MDP_SSPP_TOP0_INTR2] = { MDP_SSPP_TOP0_OFF+INTR2_CLEAR, MDP_SSPP_TOP0_OFF+INTR2_EN, MDP_SSPP_TOP0_OFF+INTR2_STATUS }, - { + [MDP_SSPP_TOP0_HIST_INTR] = { MDP_SSPP_TOP0_OFF+HIST_INTR_CLEAR, MDP_SSPP_TOP0_OFF+HIST_INTR_EN, MDP_SSPP_TOP0_OFF+HIST_INTR_STATUS }, - { + [MDP_INTF0_INTR] = { MDP_INTF_0_OFF+INTF_INTR_CLEAR, MDP_INTF_0_OFF+INTF_INTR_EN, MDP_INTF_0_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF1_INTR] = { MDP_INTF_1_OFF+INTF_INTR_CLEAR, MDP_INTF_1_OFF+INTF_INTR_EN, MDP_INTF_1_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF2_INTR] = { MDP_INTF_2_OFF+INTF_INTR_CLEAR, MDP_INTF_2_OFF+INTF_INTR_EN, MDP_INTF_2_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF3_INTR] = { MDP_INTF_3_OFF+INTF_INTR_CLEAR, MDP_INTF_3_OFF+INTF_INTR_EN, MDP_INTF_3_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF4_INTR] = { MDP_INTF_4_OFF+INTF_INTR_CLEAR, MDP_INTF_4_OFF+INTF_INTR_EN, MDP_INTF_4_OFF+INTF_INTR_STATUS }, - { + [MDP_INTF5_INTR] = { MDP_INTF_5_OFF+INTF_INTR_CLEAR, MDP_INTF_5_OFF+INTF_INTR_EN, MDP_INTF_5_OFF+INTF_INTR_STATUS }, - { + [MDP_AD4_0_INTR] = { MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF, MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF, MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF, }, - { + [MDP_AD4_1_INTR] = { MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF, MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF, MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF, }, - { + [MDP_INTF0_7xxx_INTR] = { MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_0_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF1_7xxx_INTR] = { MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_1_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF2_7xxx_INTR] = { MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_2_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF3_7xxx_INTR] = { MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_3_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF4_7xxx_INTR] = { MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_4_OFF_REV_7xxx+INTF_INTR_STATUS }, - { + [MDP_INTF5_7xxx_INTR] = { MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_CLEAR, MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_EN, MDP_INTF_5_OFF_REV_7xxx+INTF_INTR_STATUS diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c index 1ee824600995..c478d25f7825 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c @@ -98,7 +98,10 @@ static void mdp5_plane_reset(struct drm_plane *plane) __drm_atomic_helper_plane_destroy_state(plane->state); kfree(to_mdp5_plane_state(plane->state)); + plane->state = NULL; mdp5_state = kzalloc(sizeof(*mdp5_state), GFP_KERNEL); + if (!mdp5_state) + return; __drm_atomic_helper_plane_reset(plane, &mdp5_state->base); } diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index 5d2ff6791058..acfe1b31e079 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -176,6 +176,8 @@ void msm_disp_snapshot_add_block(struct msm_disp_state *disp_state, u32 len, va_list va; new_blk = kzalloc(sizeof(struct msm_disp_state_block), GFP_KERNEL); + if (!new_blk) + return; va_start(va, fmt); diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 178b774a5fbd..a42732b67349 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -580,6 +580,12 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) dp->dp_display.connector_type, state); mutex_unlock(&dp->event_mutex); + /* + * add fail safe mode outside event_mutex scope + * to avoid potiential circular lock with drm thread + */ + dp_panel_add_fail_safe_mode(dp->dp_display.connector); + /* uevent will complete connection part */ return 0; }; diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index f1418722c549..26c3653c99ec 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -151,6 +151,15 @@ static int dp_panel_update_modes(struct drm_connector *connector, return rc; } +void dp_panel_add_fail_safe_mode(struct drm_connector *connector) +{ + /* fail safe edid */ + mutex_lock(&connector->dev->mode_config.mutex); + if (drm_add_modes_noedid(connector, 640, 480)) + drm_set_preferred_mode(connector, 640, 480); + mutex_unlock(&connector->dev->mode_config.mutex); +} + int dp_panel_read_sink_caps(struct dp_panel *dp_panel, struct drm_connector *connector) { @@ -207,16 +216,7 @@ int dp_panel_read_sink_caps(struct dp_panel *dp_panel, goto end; } - /* fail safe edid */ - mutex_lock(&connector->dev->mode_config.mutex); - if (drm_add_modes_noedid(connector, 640, 480)) - drm_set_preferred_mode(connector, 640, 480); - mutex_unlock(&connector->dev->mode_config.mutex); - } else { - /* always add fail-safe mode as backup mode */ - mutex_lock(&connector->dev->mode_config.mutex); - drm_add_modes_noedid(connector, 640, 480); - mutex_unlock(&connector->dev->mode_config.mutex); + dp_panel_add_fail_safe_mode(connector); } if (panel->aux_cfg_update_done) { diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h index 9023e5bb4b8b..99739ea679a7 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.h +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -59,6 +59,7 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel); int dp_panel_deinit(struct dp_panel *dp_panel); int dp_panel_timing_cfg(struct dp_panel *dp_panel); void dp_panel_dump_regs(struct dp_panel *dp_panel); +void dp_panel_add_fail_safe_mode(struct drm_connector *connector); int dp_panel_read_sink_caps(struct dp_panel *dp_panel, struct drm_connector *connector); u32 dp_panel_get_mode_bpp(struct dp_panel *dp_panel, u32 mode_max_bpp, diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index 0c1b7dde377c..9f6af0f0fe00 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -638,7 +638,7 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id) return connector; fail: - connector->funcs->destroy(msm_dsi->connector); + connector->funcs->destroy(connector); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 02b9ae65a96a..a4f61972667b 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -926,6 +926,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, get_pid_task(aspace->pid, PIDTYPE_PID); if (task) { comm = kstrdup(task->comm, GFP_KERNEL); + put_task_struct(task); } else { comm = NULL; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c index e1772211b0a4..612310d5d481 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -216,6 +216,7 @@ gm20b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gf100_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c index 6bf7fc1bd1e3..1a6f9c3af5ec 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c @@ -23,7 +23,7 @@ */ #include "priv.h" -static void +void gp102_pmu_reset(struct nvkm_pmu *pmu) { struct nvkm_device *device = pmu->subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c index ba1583bb618b..94cfb1791af6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c @@ -83,6 +83,7 @@ gp10b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gp102_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h index bcaade758ff7..21abf31f4442 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h @@ -41,6 +41,7 @@ int gt215_pmu_send(struct nvkm_pmu *, u32[2], u32, u32, u32, u32); bool gf100_pmu_enabled(struct nvkm_pmu *); void gf100_pmu_reset(struct nvkm_pmu *); +void gp102_pmu_reset(struct nvkm_pmu *pmu); void gk110_pmu_pgob(struct nvkm_pmu *, bool); diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index a07ef26234e5..6826f4d4826a 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -612,8 +612,10 @@ static int ili9341_dbi_probe(struct spi_device *spi, struct gpio_desc *dc, int ret; vcc = devm_regulator_get_optional(dev, "vcc"); - if (IS_ERR(vcc)) + if (IS_ERR(vcc)) { dev_err(dev, "get optional vcc failed\n"); + vcc = NULL; + } dbidev = devm_drm_dev_alloc(dev, &ili9341_dbi_driver, struct mipi_dbi_dev, drm); diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index 46029c5610c8..145047e19394 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -229,7 +229,7 @@ static void rpi_touchscreen_i2c_write(struct rpi_touchscreen *ts, ret = i2c_smbus_write_byte_data(ts->i2c, reg, val); if (ret) - dev_err(&ts->dsi->dev, "I2C write failed: %d\n", ret); + dev_err(&ts->i2c->dev, "I2C write failed: %d\n", ret); } static int rpi_touchscreen_write(struct rpi_touchscreen *ts, u16 reg, u32 val) @@ -265,7 +265,7 @@ static int rpi_touchscreen_noop(struct drm_panel *panel) return 0; } -static int rpi_touchscreen_enable(struct drm_panel *panel) +static int rpi_touchscreen_prepare(struct drm_panel *panel) { struct rpi_touchscreen *ts = panel_to_ts(panel); int i; @@ -295,6 +295,13 @@ static int rpi_touchscreen_enable(struct drm_panel *panel) rpi_touchscreen_write(ts, DSI_STARTDSI, 0x01); msleep(100); + return 0; +} + +static int rpi_touchscreen_enable(struct drm_panel *panel) +{ + struct rpi_touchscreen *ts = panel_to_ts(panel); + /* Turn on the backlight. */ rpi_touchscreen_i2c_write(ts, REG_PWM, 255); @@ -349,7 +356,7 @@ static int rpi_touchscreen_get_modes(struct drm_panel *panel, static const struct drm_panel_funcs rpi_touchscreen_funcs = { .disable = rpi_touchscreen_disable, .unprepare = rpi_touchscreen_noop, - .prepare = rpi_touchscreen_noop, + .prepare = rpi_touchscreen_prepare, .enable = rpi_touchscreen_enable, .get_modes = rpi_touchscreen_get_modes, }; diff --git a/drivers/gpu/drm/radeon/radeon_sync.c b/drivers/gpu/drm/radeon/radeon_sync.c index b991ba1bcd51..f63efd8d5e52 100644 --- a/drivers/gpu/drm/radeon/radeon_sync.c +++ b/drivers/gpu/drm/radeon/radeon_sync.c @@ -96,7 +96,7 @@ int radeon_sync_resv(struct radeon_device *rdev, struct dma_fence *f; int r = 0; - dma_resv_for_each_fence(&cursor, resv, shared, f) { + dma_resv_for_each_fence(&cursor, resv, !shared, f) { fence = to_radeon_fence(f); if (fence && fence->rdev == rdev) radeon_sync_fence(sync, fence); diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.c b/drivers/gpu/drm/sun4i/sun4i_frontend.c index 56ae38389db0..462fae73eae9 100644 --- a/drivers/gpu/drm/sun4i/sun4i_frontend.c +++ b/drivers/gpu/drm/sun4i/sun4i_frontend.c @@ -222,13 +222,11 @@ void sun4i_frontend_update_buffer(struct sun4i_frontend *frontend, /* Set the physical address of the buffer in memory */ paddr = drm_fb_cma_get_gem_addr(fb, state, 0); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #0 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR0_REG, paddr); if (fb->format->num_planes > 1) { paddr = drm_fb_cma_get_gem_addr(fb, state, swap ? 2 : 1); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #1 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR1_REG, paddr); @@ -236,7 +234,6 @@ void sun4i_frontend_update_buffer(struct sun4i_frontend *frontend, if (fb->format->num_planes > 2) { paddr = drm_fb_cma_get_gem_addr(fb, state, swap ? 1 : 2); - paddr -= PHYS_OFFSET; DRM_DEBUG_DRIVER("Setting buffer #2 address to %pad\n", &paddr); regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR2_REG, paddr); diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig index de3424fed2fc..6cf2621786e6 100644 --- a/drivers/gpu/drm/vc4/Kconfig +++ b/drivers/gpu/drm/vc4/Kconfig @@ -2,6 +2,9 @@ config DRM_VC4 tristate "Broadcom VC4 Graphics" depends on ARCH_BCM || ARCH_BCM2835 || COMPILE_TEST + # Make sure not 'y' when RASPBERRYPI_FIRMWARE is 'm'. This can only + # happen when COMPILE_TEST=y, hence the added !RASPBERRYPI_FIRMWARE. + depends on RASPBERRYPI_FIRMWARE || (COMPILE_TEST && !RASPBERRYPI_FIRMWARE) depends on DRM depends on SND && SND_SOC depends on COMMON_CLK diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c index 752f921735c6..98308a17e4ed 100644 --- a/drivers/gpu/drm/vc4/vc4_dsi.c +++ b/drivers/gpu/drm/vc4/vc4_dsi.c @@ -846,7 +846,7 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder) unsigned long phy_clock; int ret; - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret) { DRM_ERROR("Failed to runtime PM enable on DSI%d\n", dsi->variant->port); return; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 31aecc46624b..04c8a378aeed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -46,6 +46,21 @@ vmw_buffer_object(struct ttm_buffer_object *bo) return container_of(bo, struct vmw_buffer_object, base); } +/** + * bo_is_vmw - check if the buffer object is a &vmw_buffer_object + * @bo: ttm buffer object to be checked + * + * Uses destroy function associated with the object to determine if this is + * a &vmw_buffer_object. + * + * Returns: + * true if the object is of &vmw_buffer_object type, false if not. + */ +static bool bo_is_vmw(struct ttm_buffer_object *bo) +{ + return bo->destroy == &vmw_bo_bo_free || + bo->destroy == &vmw_gem_destroy; +} /** * vmw_bo_pin_in_placement - Validate a buffer to placement. @@ -615,8 +630,9 @@ int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data, ret = vmw_user_bo_synccpu_grab(vbo, arg->flags); vmw_bo_unreference(&vbo); - if (unlikely(ret != 0 && ret != -ERESTARTSYS && - ret != -EBUSY)) { + if (unlikely(ret != 0)) { + if (ret == -ERESTARTSYS || ret == -EBUSY) + return -EBUSY; DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n", (unsigned int) arg->handle); return ret; @@ -798,7 +814,7 @@ int vmw_dumb_create(struct drm_file *file_priv, void vmw_bo_swap_notify(struct ttm_buffer_object *bo) { /* Is @bo embedded in a struct vmw_buffer_object? */ - if (vmw_bo_is_vmw_bo(bo)) + if (!bo_is_vmw(bo)) return; /* Kill any cached kernel maps before swapout */ @@ -822,7 +838,7 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, struct vmw_buffer_object *vbo; /* Make sure @bo is embedded in a struct vmw_buffer_object? */ - if (vmw_bo_is_vmw_bo(bo)) + if (!bo_is_vmw(bo)) return; vbo = container_of(bo, struct vmw_buffer_object, base); @@ -843,22 +859,3 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, if (mem->mem_type != VMW_PL_MOB && bo->resource->mem_type == VMW_PL_MOB) vmw_resource_unbind_list(vbo); } - -/** - * vmw_bo_is_vmw_bo - check if the buffer object is a &vmw_buffer_object - * @bo: buffer object to be checked - * - * Uses destroy function associated with the object to determine if this is - * a &vmw_buffer_object. - * - * Returns: - * true if the object is of &vmw_buffer_object type, false if not. - */ -bool vmw_bo_is_vmw_bo(struct ttm_buffer_object *bo) -{ - if (bo->destroy == &vmw_bo_bo_free || - bo->destroy == &vmw_gem_destroy) - return true; - - return false; -} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 26eb5478394a..163c00793eb1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -998,13 +998,10 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) goto out_no_fman; } - drm_vma_offset_manager_init(&dev_priv->vma_manager, - DRM_FILE_PAGE_OFFSET_START, - DRM_FILE_PAGE_OFFSET_SIZE); ret = ttm_device_init(&dev_priv->bdev, &vmw_bo_driver, dev_priv->drm.dev, dev_priv->drm.anon_inode->i_mapping, - &dev_priv->vma_manager, + dev_priv->drm.vma_offset_manager, dev_priv->map_mode == vmw_dma_alloc_coherent, false); if (unlikely(ret != 0)) { @@ -1174,7 +1171,6 @@ static void vmw_driver_unload(struct drm_device *dev) vmw_devcaps_destroy(dev_priv); vmw_vram_manager_fini(dev_priv); ttm_device_fini(&dev_priv->bdev); - drm_vma_offset_manager_destroy(&dev_priv->vma_manager); vmw_release_device_late(dev_priv); vmw_fence_manager_takedown(dev_priv->fman); if (dev_priv->capabilities & SVGA_CAP_IRQMASK) @@ -1398,7 +1394,7 @@ vmw_get_unmapped_area(struct file *file, unsigned long uaddr, struct vmw_private *dev_priv = vmw_priv(file_priv->minor->dev); return drm_get_unmapped_area(file, uaddr, len, pgoff, flags, - &dev_priv->vma_manager); + dev_priv->drm.vma_offset_manager); } static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 00e8e27e4884..ace7ca150b03 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -683,6 +683,9 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base) container_of(base, struct vmw_user_surface, prime.base); struct vmw_resource *res = &user_srf->srf.res; + if (base->shareable && res && res->backup) + drm_gem_object_put(&res->backup->base.base); + *p_base = NULL; vmw_resource_unreference(&res); } @@ -857,6 +860,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, goto out_unlock; } vmw_bo_reference(res->backup); + drm_gem_object_get(&res->backup->base.base); } tmp = vmw_resource_reference(&srf->res); @@ -1513,7 +1517,6 @@ vmw_gb_surface_define_internal(struct drm_device *dev, &res->backup); if (ret == 0) vmw_bo_reference(res->backup); - } if (unlikely(ret != 0)) { @@ -1561,6 +1564,8 @@ vmw_gb_surface_define_internal(struct drm_device *dev, drm_vma_node_offset_addr(&res->backup->base.base.vma_node); rep->buffer_size = res->backup->base.base.size; rep->buffer_handle = backup_handle; + if (user_srf->prime.base.shareable) + drm_gem_object_get(&res->backup->base.base); } else { rep->buffer_map_handle = 0; rep->buffer_size = 0; diff --git a/drivers/gpu/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c index 666223c6bec4..0a34e0ab4fe6 100644 --- a/drivers/gpu/ipu-v3/ipu-di.c +++ b/drivers/gpu/ipu-v3/ipu-di.c @@ -447,8 +447,9 @@ static void ipu_di_config_clock(struct ipu_di *di, error = rate / (sig->mode.pixelclock / 1000); - dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %d.%u%%\n", - rate, div, (signed)(error - 1000) / 10, error % 10); + dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %c%d.%d%%\n", + rate, div, error < 1000 ? '-' : '+', + abs(error - 1000) / 10, abs(error - 1000) % 10); /* Allow a 1% error */ if (error < 1010 && error >= 990) { diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 26d269ba947c..85a2142c9384 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -380,7 +380,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * execute: * * (a) In the "normal (i.e., not resuming from hibernation)" path, - * the full barrier in smp_store_mb() guarantees that the store + * the full barrier in virt_store_mb() guarantees that the store * is propagated to all CPUs before the add_channel_work work * is queued. In turn, add_channel_work is queued before the * channel's ring buffer is allocated/initialized and the @@ -392,14 +392,14 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * recv_int_page before retrieving the channel pointer from the * array of channels. * - * (b) In the "resuming from hibernation" path, the smp_store_mb() + * (b) In the "resuming from hibernation" path, the virt_store_mb() * guarantees that the store is propagated to all CPUs before * the VMBus connection is marked as ready for the resume event * (cf. check_ready_for_resume_event()). The interrupt handler * of the VMBus driver and vmbus_chan_sched() can not run before * vmbus_bus_resume() has completed execution (cf. resume_noirq). */ - smp_store_mb( + virt_store_mb( vmbus_connection.channels[channel->offermsg.child_relid], channel); } diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 439f99b8b5de..3248b48f37f6 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/kthread.h> #include <linux/completion.h> +#include <linux/count_zeros.h> #include <linux/memory_hotplug.h> #include <linux/memory.h> #include <linux/notifier.h> @@ -1130,6 +1131,7 @@ static void post_status(struct hv_dynmem_device *dm) struct dm_status status; unsigned long now = jiffies; unsigned long last_post = last_post_time; + unsigned long num_pages_avail, num_pages_committed; if (pressure_report_delay > 0) { --pressure_report_delay; @@ -1154,16 +1156,21 @@ static void post_status(struct hv_dynmem_device *dm) * num_pages_onlined) as committed to the host, otherwise it can try * asking us to balloon them out. */ - status.num_avail = si_mem_available(); - status.num_committed = vm_memory_committed() + + num_pages_avail = si_mem_available(); + num_pages_committed = vm_memory_committed() + dm->num_pages_ballooned + (dm->num_pages_added > dm->num_pages_onlined ? dm->num_pages_added - dm->num_pages_onlined : 0) + compute_balloon_floor(); - trace_balloon_status(status.num_avail, status.num_committed, + trace_balloon_status(num_pages_avail, num_pages_committed, vm_memory_committed(), dm->num_pages_ballooned, dm->num_pages_added, dm->num_pages_onlined); + + /* Convert numbers of pages into numbers of HV_HYP_PAGEs. */ + status.num_avail = num_pages_avail * NR_HV_HYP_PAGES_IN_PAGE; + status.num_committed = num_pages_committed * NR_HV_HYP_PAGES_IN_PAGE; + /* * If our transaction ID is no longer current, just don't * send the status. This can happen if we were interrupted @@ -1653,6 +1660,38 @@ static void disable_page_reporting(void) } } +static int ballooning_enabled(void) +{ + /* + * Disable ballooning if the page size is not 4k (HV_HYP_PAGE_SIZE), + * since currently it's unclear to us whether an unballoon request can + * make sure all page ranges are guest page size aligned. + */ + if (PAGE_SIZE != HV_HYP_PAGE_SIZE) { + pr_info("Ballooning disabled because page size is not 4096 bytes\n"); + return 0; + } + + return 1; +} + +static int hot_add_enabled(void) +{ + /* + * Disable hot add on ARM64, because we currently rely on + * memory_add_physaddr_to_nid() to get a node id of a hot add range, + * however ARM64's memory_add_physaddr_to_nid() always return 0 and + * DM_MEM_HOT_ADD_REQUEST doesn't have the NUMA node information for + * add_memory(). + */ + if (IS_ENABLED(CONFIG_ARM64)) { + pr_info("Memory hot add disabled on ARM64\n"); + return 0; + } + + return 1; +} + static int balloon_connect_vsp(struct hv_device *dev) { struct dm_version_request version_req; @@ -1724,8 +1763,8 @@ static int balloon_connect_vsp(struct hv_device *dev) * currently still requires the bits to be set, so we have to add code * to fail the host's hot-add and balloon up/down requests, if any. */ - cap_msg.caps.cap_bits.balloon = 1; - cap_msg.caps.cap_bits.hot_add = 1; + cap_msg.caps.cap_bits.balloon = ballooning_enabled(); + cap_msg.caps.cap_bits.hot_add = hot_add_enabled(); /* * Specify our alignment requirements as it relates diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index c1dd21d0d7ef..ae68298c0dca 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -20,6 +20,7 @@ #include <linux/panic_notifier.h> #include <linux/ptrace.h> #include <linux/slab.h> +#include <linux/dma-map-ops.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -218,6 +219,16 @@ bool hv_query_ext_cap(u64 cap_query) } EXPORT_SYMBOL_GPL(hv_query_ext_cap); +void hv_setup_dma_ops(struct device *dev, bool coherent) +{ + /* + * Hyper-V does not offer a vIOMMU in the guest + * VM, so pass 0/NULL for the IOMMU settings + */ + arch_setup_dma_ops(dev, 0, 0, NULL, coherent); +} +EXPORT_SYMBOL_GPL(hv_setup_dma_ops); + bool hv_is_hibernation_supported(void) { return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4); diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 71efacb90965..3d215d9dec43 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -439,7 +439,16 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) { u32 priv_read_loc = rbi->priv_read_index; - u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index); + u32 write_loc; + + /* + * The Hyper-V host writes the packet data, then uses + * store_release() to update the write_index. Use load_acquire() + * here to prevent loads of the packet data from being re-ordered + * before the read of the write_index and potentially getting + * stale data. + */ + write_loc = virt_load_acquire(&rbi->ring_buffer->write_index); if (write_loc >= priv_read_loc) return write_loc - priv_read_loc; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 60ee8b329f9e..14de17087864 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -77,8 +77,8 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE && hyperv_report_reg()) { @@ -100,8 +100,8 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (hyperv_report_reg()) hyperv_report_panic(regs, val, true); @@ -921,6 +921,21 @@ static int vmbus_probe(struct device *child_device) } /* + * vmbus_dma_configure -- Configure DMA coherence for VMbus device + */ +static int vmbus_dma_configure(struct device *child_device) +{ + /* + * On ARM64, propagate the DMA coherence setting from the top level + * VMbus ACPI device to the child VMbus device being added here. + * On x86/x64 coherence is assumed and these calls have no effect. + */ + hv_setup_dma_ops(child_device, + device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT); + return 0; +} + +/* * vmbus_remove - Remove a vmbus device */ static void vmbus_remove(struct device *child_device) @@ -1040,6 +1055,7 @@ static struct bus_type hv_bus = { .remove = vmbus_remove, .probe = vmbus_probe, .uevent = vmbus_uevent, + .dma_configure = vmbus_dma_configure, .dev_groups = vmbus_dev_groups, .drv_groups = vmbus_drv_groups, .bus_groups = vmbus_bus_groups, @@ -1546,14 +1562,20 @@ static int vmbus_bus_init(void) if (ret) goto err_connect; + if (hv_is_isolation_supported()) + sysctl_record_panic_msg = 0; + /* * Only register if the crash MSRs are available */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { u64 hyperv_crash_ctl; /* - * Sysctl registration is not fatal, since by default - * reporting is enabled. + * Panic message recording (sysctl_record_panic_msg) + * is enabled by default in non-isolated guests and + * disabled by default in isolated guests; the panic + * message recording won't be available in isolated + * guests should the following registration fail. */ hv_ctl_table_hdr = register_sysctl_table(hv_root_table); if (!hv_ctl_table_hdr) @@ -2097,6 +2119,10 @@ int vmbus_device_register(struct hv_device *child_device_obj) child_device_obj->device.parent = &hv_acpi_dev->dev; child_device_obj->device.release = vmbus_device_release; + child_device_obj->device.dma_parms = &child_device_obj->dma_parms; + child_device_obj->device.dma_mask = &child_device_obj->dma_mask; + dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); + /* * Register with the LDM. This will kick off the driver/device * binding...which will eventually call vmbus_match() and vmbus_probe() @@ -2122,9 +2148,6 @@ int vmbus_device_register(struct hv_device *child_device_obj) } hv_debug_add_dev_dir(child_device_obj); - child_device_obj->device.dma_parms = &child_device_obj->dma_parms; - child_device_obj->device.dma_mask = &child_device_obj->dma_mask; - dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); return 0; err_kset_unregister: @@ -2428,6 +2451,21 @@ static int vmbus_acpi_add(struct acpi_device *device) hv_acpi_dev = device; + /* + * Older versions of Hyper-V for ARM64 fail to include the _CCA + * method on the top level VMbus device in the DSDT. But devices + * are hardware coherent in all current Hyper-V use cases, so fix + * up the ACPI device to behave as if _CCA is present and indicates + * hardware coherence. + */ + ACPI_COMPANION_SET(&device->dev, device); + if (IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED) && + device_get_dma_attr(&device->dev) == DEV_DMA_NOT_SUPPORTED) { + pr_info("No ACPI _CCA found; assuming coherent device I/O\n"); + device->flags.cca_seen = true; + device->flags.coherent_dma = true; + } + result = acpi_walk_resources(device->handle, METHOD_NAME__CRS, vmbus_walk_resources, NULL); @@ -2780,10 +2818,15 @@ static void __exit vmbus_exit(void) if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { kmsg_dump_unregister(&hv_kmsg_dumper); unregister_die_notifier(&hyperv_die_block); - atomic_notifier_chain_unregister(&panic_notifier_list, - &hyperv_panic_block); } + /* + * The panic notifier is always registered, hence we should + * also unconditionally unregister it here as well. + */ + atomic_notifier_chain_unregister(&panic_notifier_list, + &hyperv_panic_block); + free_page((unsigned long)hv_panic_page); unregister_sysctl_table(hv_ctl_table_hdr); hv_ctl_table_hdr = NULL; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 27f969b3dc07..e9e2db68b9fb 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -179,6 +179,12 @@ struct imx_i2c_hwdata { unsigned int ndivs; unsigned int i2sr_clr_opcode; unsigned int i2cr_ien_opcode; + /* + * Errata ERR007805 or e7805: + * I2C: When the I2C clock speed is configured for 400 kHz, + * the SCL low period violates the I2C spec of 1.3 uS min. + */ + bool has_err007805; }; struct imx_i2c_dma { @@ -240,6 +246,16 @@ static const struct imx_i2c_hwdata imx21_i2c_hwdata = { }; +static const struct imx_i2c_hwdata imx6_i2c_hwdata = { + .devtype = IMX21_I2C, + .regshift = IMX_I2C_REGSHIFT, + .clk_div = imx_i2c_clk_div, + .ndivs = ARRAY_SIZE(imx_i2c_clk_div), + .i2sr_clr_opcode = I2SR_CLR_OPCODE_W0C, + .i2cr_ien_opcode = I2CR_IEN_OPCODE_1, + .has_err007805 = true, +}; + static struct imx_i2c_hwdata vf610_i2c_hwdata = { .devtype = VF610_I2C, .regshift = VF610_I2C_REGSHIFT, @@ -266,6 +282,16 @@ MODULE_DEVICE_TABLE(platform, imx_i2c_devtype); static const struct of_device_id i2c_imx_dt_ids[] = { { .compatible = "fsl,imx1-i2c", .data = &imx1_i2c_hwdata, }, { .compatible = "fsl,imx21-i2c", .data = &imx21_i2c_hwdata, }, + { .compatible = "fsl,imx6q-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sl-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sll-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6sx-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx6ul-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx7s-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mm-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mn-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mp-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx8mq-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,vf610-i2c", .data = &vf610_i2c_hwdata, }, { /* sentinel */ } }; @@ -551,6 +577,13 @@ static void i2c_imx_set_clk(struct imx_i2c_struct *i2c_imx, unsigned int div; int i; + if (i2c_imx->hwdata->has_err007805 && i2c_imx->bitrate > 384000) { + dev_dbg(&i2c_imx->adapter.dev, + "SoC errata ERR007805 or e7805 applies, bus frequency limited from %d Hz to 384000 Hz.\n", + i2c_imx->bitrate); + i2c_imx->bitrate = 384000; + } + /* Divider value calculation */ if (i2c_imx->cur_clk == i2c_clk_rate) return; diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index f4820fd3dc13..c0364314877e 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -145,8 +145,8 @@ #define ISMT_SPGT_SPD_MASK 0xc0000000 /* SMBus Speed mask */ #define ISMT_SPGT_SPD_80K 0x00 /* 80 kHz */ #define ISMT_SPGT_SPD_100K (0x1 << 30) /* 100 kHz */ -#define ISMT_SPGT_SPD_400K (0x2 << 30) /* 400 kHz */ -#define ISMT_SPGT_SPD_1M (0x3 << 30) /* 1 MHz */ +#define ISMT_SPGT_SPD_400K (0x2U << 30) /* 400 kHz */ +#define ISMT_SPGT_SPD_1M (0x3U << 30) /* 1 MHz */ /* MSI Control Register (MSICTL) bit definitions */ diff --git a/drivers/i2c/busses/i2c-pasemi-core.c b/drivers/i2c/busses/i2c-pasemi-core.c index 7728c8460dc0..9028ffb58cc0 100644 --- a/drivers/i2c/busses/i2c-pasemi-core.c +++ b/drivers/i2c/busses/i2c-pasemi-core.c @@ -137,6 +137,12 @@ static int pasemi_i2c_xfer_msg(struct i2c_adapter *adapter, TXFIFO_WR(smbus, msg->buf[msg->len-1] | (stop ? MTXFIFO_STOP : 0)); + + if (stop) { + err = pasemi_smb_waitready(smbus); + if (err) + goto reset_out; + } } return 0; diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index fc1dcc19f2a1..5b920f0fc7dd 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -843,10 +843,8 @@ static int geni_i2c_probe(struct platform_device *pdev) /* FIFO is disabled, so we can only use GPI DMA */ gi2c->gpi_mode = true; ret = setup_gpi_dma(gi2c); - if (ret) { - dev_err(dev, "Failed to setup GPI DMA mode:%d ret\n", ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "Failed to setup GPI DMA mode\n"); dev_dbg(dev, "Using GPI DMA mode for I2C\n"); } else { diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index cf5d049342ea..ab0adaa130da 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -557,7 +557,7 @@ static long compat_i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned lo .addr = umsg.addr, .flags = umsg.flags, .len = umsg.len, - .buf = compat_ptr(umsg.buf) + .buf = (__force __u8 *)compat_ptr(umsg.buf), }; } @@ -668,16 +668,21 @@ static int i2cdev_attach_adapter(struct device *dev, void *dummy) i2c_dev->dev.class = i2c_dev_class; i2c_dev->dev.parent = &adap->dev; i2c_dev->dev.release = i2cdev_dev_release; - dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr); + + res = dev_set_name(&i2c_dev->dev, "i2c-%d", adap->nr); + if (res) + goto err_put_i2c_dev; res = cdev_device_add(&i2c_dev->cdev, &i2c_dev->dev); - if (res) { - put_i2c_dev(i2c_dev, false); - return res; - } + if (res) + goto err_put_i2c_dev; pr_debug("adapter [%s] registered as minor %d\n", adap->name, adap->nr); return 0; + +err_put_i2c_dev: + put_i2c_dev(i2c_dev, false); + return res; } static int i2cdev_detach_adapter(struct device *dev, void *dummy) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index b7640cfe0020..47551ab73ca8 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -69,7 +69,12 @@ static unsigned int preferred_states_mask; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; static unsigned long auto_demotion_disable_flags; -static bool disable_promotion_to_c1e; + +static enum { + C1E_PROMOTION_PRESERVE, + C1E_PROMOTION_ENABLE, + C1E_PROMOTION_DISABLE +} c1e_promotion = C1E_PROMOTION_PRESERVE; struct idle_cpu { struct cpuidle_state *state_table; @@ -1398,8 +1403,6 @@ static inline void intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { } static inline bool intel_idle_off_by_default(u32 mwait_hint) { return false; } #endif /* !CONFIG_ACPI_PROCESSOR_CSTATE */ -static void c1e_promotion_enable(void); - /** * ivt_idle_state_table_update - Tune the idle states table for Ivy Town. * @@ -1578,17 +1581,14 @@ static void __init spr_idle_state_table_update(void) unsigned long long msr; /* Check if user prefers C1E over C1. */ - if (preferred_states_mask & BIT(2)) { - if (preferred_states_mask & BIT(1)) - /* Both can't be enabled, stick to the defaults. */ - return; - + if ((preferred_states_mask & BIT(2)) && + !(preferred_states_mask & BIT(1))) { + /* Disable C1 and enable C1E. */ spr_cstates[0].flags |= CPUIDLE_FLAG_UNUSABLE; spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE; /* Enable C1E using the "C1E promotion" bit. */ - c1e_promotion_enable(); - disable_promotion_to_c1e = false; + c1e_promotion = C1E_PROMOTION_ENABLE; } /* @@ -1754,7 +1754,9 @@ static int intel_idle_cpu_init(unsigned int cpu) if (auto_demotion_disable_flags) auto_demotion_disable(); - if (disable_promotion_to_c1e) + if (c1e_promotion == C1E_PROMOTION_ENABLE) + c1e_promotion_enable(); + else if (c1e_promotion == C1E_PROMOTION_DISABLE) c1e_promotion_disable(); return 0; @@ -1833,7 +1835,8 @@ static int __init intel_idle_init(void) if (icpu) { cpuidle_state_table = icpu->state_table; auto_demotion_disable_flags = icpu->auto_demotion_disable_flags; - disable_promotion_to_c1e = icpu->disable_promotion_to_c1e; + if (icpu->disable_promotion_to_c1e) + c1e_promotion = C1E_PROMOTION_DISABLE; if (icpu->use_acpi || force_use_acpi) intel_idle_acpi_cst_extract(); } else if (!intel_idle_acpi_cst_extract()) { diff --git a/drivers/iio/adc/ad7280a.c b/drivers/iio/adc/ad7280a.c index ef9d27759961..ec9acbf12b9a 100644 --- a/drivers/iio/adc/ad7280a.c +++ b/drivers/iio/adc/ad7280a.c @@ -745,7 +745,7 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_RISING: addr = AD7280A_CELL_OVERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; st->cell_threshhigh = value; @@ -753,7 +753,7 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_FALLING: addr = AD7280A_CELL_UNDERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; st->cell_threshlow = value; @@ -770,18 +770,18 @@ static int ad7280a_write_thresh(struct iio_dev *indio_dev, case IIO_EV_DIR_RISING: addr = AD7280A_AUX_ADC_OVERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; - st->aux_threshhigh = val; + st->aux_threshhigh = value; break; case IIO_EV_DIR_FALLING: addr = AD7280A_AUX_ADC_UNDERVOLTAGE_REG; ret = ad7280_write(st, AD7280A_DEVADDR_MASTER, addr, - 1, val); + 1, value); if (ret) break; - st->aux_threshlow = val; + st->aux_threshlow = value; break; default: ret = -EINVAL; diff --git a/drivers/iio/chemical/scd4x.c b/drivers/iio/chemical/scd4x.c index 20d4e7584e92..37143b5526ee 100644 --- a/drivers/iio/chemical/scd4x.c +++ b/drivers/iio/chemical/scd4x.c @@ -471,12 +471,15 @@ static ssize_t calibration_forced_value_store(struct device *dev, ret = scd4x_write_and_fetch(state, CMD_FRC, arg, &val, sizeof(val)); mutex_unlock(&state->lock); + if (ret) + return ret; + if (val == 0xff) { dev_err(dev, "forced calibration has failed"); return -EINVAL; } - return ret ?: len; + return len; } static IIO_DEVICE_ATTR_RW(calibration_auto_enable, 0); diff --git a/drivers/iio/dac/ad3552r.c b/drivers/iio/dac/ad3552r.c index 97f13c0b9631..d5ea1a1be122 100644 --- a/drivers/iio/dac/ad3552r.c +++ b/drivers/iio/dac/ad3552r.c @@ -656,7 +656,7 @@ static int ad3552r_reset(struct ad3552r_desc *dac) { struct reg_addr_pool addr; int ret; - u16 val; + int val; dac->gpio_reset = devm_gpiod_get_optional(&dac->spi->dev, "reset", GPIOD_OUT_LOW); @@ -809,10 +809,10 @@ static int ad3552r_configure_custom_gain(struct ad3552r_desc *dac, gain_child = fwnode_get_named_child_node(child, "custom-output-range-config"); - if (IS_ERR(gain_child)) { + if (!gain_child) { dev_err(dev, "mandatory custom-output-range-config property missing\n"); - return PTR_ERR(gain_child); + return -EINVAL; } dac->ch_data[ch].range_override = 1; diff --git a/drivers/iio/dac/ad5446.c b/drivers/iio/dac/ad5446.c index 14cfabacbea5..fdf824041497 100644 --- a/drivers/iio/dac/ad5446.c +++ b/drivers/iio/dac/ad5446.c @@ -178,7 +178,7 @@ static int ad5446_read_raw(struct iio_dev *indio_dev, switch (m) { case IIO_CHAN_INFO_RAW: - *val = st->cached_val; + *val = st->cached_val >> chan->scan_type.shift; return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: *val = st->vref_mv; diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index a424b7220b61..4434c1b2a322 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -522,7 +522,7 @@ static int ad5592r_alloc_channels(struct iio_dev *iio_dev) if (!ret) st->channel_modes[reg] = tmp; - fwnode_property_read_u32(child, "adi,off-state", &tmp); + ret = fwnode_property_read_u32(child, "adi,off-state", &tmp); if (!ret) st->channel_offstate[reg] = tmp; } diff --git a/drivers/iio/dac/ltc2688.c b/drivers/iio/dac/ltc2688.c index e41861d29767..2f9c384885f4 100644 --- a/drivers/iio/dac/ltc2688.c +++ b/drivers/iio/dac/ltc2688.c @@ -298,7 +298,7 @@ static int ltc2688_read_raw(struct iio_dev *indio_dev, if (ret) return ret; - *val = 16; + *val2 = 16; return IIO_VAL_FRACTIONAL_LOG2; case IIO_CHAN_INFO_CALIBBIAS: ret = regmap_read(st->regmap, diff --git a/drivers/iio/dac/ti-dac5571.c b/drivers/iio/dac/ti-dac5571.c index 4a3b8d875518..0b775f943db3 100644 --- a/drivers/iio/dac/ti-dac5571.c +++ b/drivers/iio/dac/ti-dac5571.c @@ -19,6 +19,7 @@ #include <linux/i2c.h> #include <linux/module.h> #include <linux/mod_devicetable.h> +#include <linux/property.h> #include <linux/regulator/consumer.h> enum chip_id { @@ -311,6 +312,7 @@ static int dac5571_probe(struct i2c_client *client, const struct dac5571_spec *spec; struct dac5571_data *data; struct iio_dev *indio_dev; + enum chip_id chip_id; int ret, i; indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); @@ -326,7 +328,13 @@ static int dac5571_probe(struct i2c_client *client, indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = dac5571_channels; - spec = &dac5571_spec[id->driver_data]; + if (dev_fwnode(dev)) + chip_id = (uintptr_t)device_get_match_data(dev); + else + chip_id = id->driver_data; + + spec = &dac5571_spec[chip_id]; + indio_dev->num_channels = spec->num_channels; data->spec = spec; @@ -385,15 +393,15 @@ static int dac5571_remove(struct i2c_client *i2c) } static const struct of_device_id dac5571_of_id[] = { - {.compatible = "ti,dac5571"}, - {.compatible = "ti,dac6571"}, - {.compatible = "ti,dac7571"}, - {.compatible = "ti,dac5574"}, - {.compatible = "ti,dac6574"}, - {.compatible = "ti,dac7574"}, - {.compatible = "ti,dac5573"}, - {.compatible = "ti,dac6573"}, - {.compatible = "ti,dac7573"}, + {.compatible = "ti,dac5571", .data = (void *)single_8bit}, + {.compatible = "ti,dac6571", .data = (void *)single_10bit}, + {.compatible = "ti,dac7571", .data = (void *)single_12bit}, + {.compatible = "ti,dac5574", .data = (void *)quad_8bit}, + {.compatible = "ti,dac6574", .data = (void *)quad_10bit}, + {.compatible = "ti,dac7574", .data = (void *)quad_12bit}, + {.compatible = "ti,dac5573", .data = (void *)quad_8bit}, + {.compatible = "ti,dac6573", .data = (void *)quad_10bit}, + {.compatible = "ti,dac7573", .data = (void *)quad_12bit}, {} }; MODULE_DEVICE_TABLE(of, dac5571_of_id); diff --git a/drivers/iio/filter/Kconfig b/drivers/iio/filter/Kconfig index 3ae35817ad82..a85b345ea14e 100644 --- a/drivers/iio/filter/Kconfig +++ b/drivers/iio/filter/Kconfig @@ -8,6 +8,7 @@ menu "Filters" config ADMV8818 tristate "Analog Devices ADMV8818 High-Pass and Low-Pass Filter" depends on SPI && COMMON_CLK && 64BIT + select REGMAP_SPI help Say yes here to build support for Analog Devices ADMV8818 2 GHz to 18 GHz, Digitally Tunable, High-Pass and Low-Pass Filter. diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c index 824b5124a5f5..01336105792e 100644 --- a/drivers/iio/imu/bmi160/bmi160_core.c +++ b/drivers/iio/imu/bmi160/bmi160_core.c @@ -730,7 +730,7 @@ static int bmi160_chip_init(struct bmi160_data *data, bool use_spi) ret = regmap_write(data->regmap, BMI160_REG_CMD, BMI160_CMD_SOFTRESET); if (ret) - return ret; + goto disable_regulator; usleep_range(BMI160_SOFTRESET_USLEEP, BMI160_SOFTRESET_USLEEP + 1); @@ -741,29 +741,37 @@ static int bmi160_chip_init(struct bmi160_data *data, bool use_spi) if (use_spi) { ret = regmap_read(data->regmap, BMI160_REG_DUMMY, &val); if (ret) - return ret; + goto disable_regulator; } ret = regmap_read(data->regmap, BMI160_REG_CHIP_ID, &val); if (ret) { dev_err(dev, "Error reading chip id\n"); - return ret; + goto disable_regulator; } if (val != BMI160_CHIP_ID_VAL) { dev_err(dev, "Wrong chip id, got %x expected %x\n", val, BMI160_CHIP_ID_VAL); - return -ENODEV; + ret = -ENODEV; + goto disable_regulator; } ret = bmi160_set_mode(data, BMI160_ACCEL, true); if (ret) - return ret; + goto disable_regulator; ret = bmi160_set_mode(data, BMI160_GYRO, true); if (ret) - return ret; + goto disable_accel; return 0; + +disable_accel: + bmi160_set_mode(data, BMI160_ACCEL, false); + +disable_regulator: + regulator_bulk_disable(ARRAY_SIZE(data->supplies), data->supplies); + return ret; } static int bmi160_data_rdy_trigger_set_state(struct iio_trigger *trig, diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c index 33d9afb1ba91..d4a692b838d0 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_i2c.c @@ -18,12 +18,15 @@ static int inv_icm42600_i2c_bus_setup(struct inv_icm42600_state *st) unsigned int mask, val; int ret; - /* setup interface registers */ - ret = regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG6, - INV_ICM42600_INTF_CONFIG6_MASK, - INV_ICM42600_INTF_CONFIG6_I3C_EN); - if (ret) - return ret; + /* + * setup interface registers + * This register write to REG_INTF_CONFIG6 enables a spike filter that + * is impacting the line and can prevent the I2C ACK to be seen by the + * controller. So we don't test the return value. + */ + regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG6, + INV_ICM42600_INTF_CONFIG6_MASK, + INV_ICM42600_INTF_CONFIG6_I3C_EN); ret = regmap_update_bits(st->map, INV_ICM42600_REG_INTF_CONFIG4, INV_ICM42600_INTF_CONFIG4_I3C_BUS_ONLY, 0); diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 088f748b683e..2432e697150c 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -416,6 +416,7 @@ static int ak8975_power_on(const struct ak8975_data *data) if (ret) { dev_warn(&data->client->dev, "Failed to enable specified Vid supply\n"); + regulator_disable(data->vdd); return ret; } diff --git a/drivers/iio/proximity/sx9324.c b/drivers/iio/proximity/sx9324.c index 0d9bbbb50cb4..70c37f664f6d 100644 --- a/drivers/iio/proximity/sx9324.c +++ b/drivers/iio/proximity/sx9324.c @@ -70,13 +70,17 @@ #define SX9324_REG_AFE_PH2 0x2a #define SX9324_REG_AFE_PH3 0x2b #define SX9324_REG_AFE_CTRL8 0x2c -#define SX9324_REG_AFE_CTRL8_RESFILTN_4KOHM 0x02 +#define SX9324_REG_AFE_CTRL8_RESERVED 0x10 +#define SX9324_REG_AFE_CTRL8_RESFILTIN_4KOHM 0x02 #define SX9324_REG_AFE_CTRL9 0x2d #define SX9324_REG_AFE_CTRL9_AGAIN_1 0x08 #define SX9324_REG_PROX_CTRL0 0x30 #define SX9324_REG_PROX_CTRL0_GAIN_MASK GENMASK(5, 3) -#define SX9324_REG_PROX_CTRL0_GAIN_1 0x80 +#define SX9324_REG_PROX_CTRL0_GAIN_SHIFT 3 +#define SX9324_REG_PROX_CTRL0_GAIN_RSVD 0x0 +#define SX9324_REG_PROX_CTRL0_GAIN_1 0x1 +#define SX9324_REG_PROX_CTRL0_GAIN_8 0x4 #define SX9324_REG_PROX_CTRL0_RAWFILT_MASK GENMASK(2, 0) #define SX9324_REG_PROX_CTRL0_RAWFILT_1P50 0x01 #define SX9324_REG_PROX_CTRL1 0x31 @@ -379,7 +383,14 @@ static int sx9324_read_gain(struct sx_common_data *data, if (ret) return ret; - *val = 1 << FIELD_GET(SX9324_REG_PROX_CTRL0_GAIN_MASK, regval); + regval = FIELD_GET(SX9324_REG_PROX_CTRL0_GAIN_MASK, regval); + if (regval) + regval--; + else if (regval == SX9324_REG_PROX_CTRL0_GAIN_RSVD || + regval > SX9324_REG_PROX_CTRL0_GAIN_8) + return -EINVAL; + + *val = 1 << regval; return IIO_VAL_INT; } @@ -725,8 +736,12 @@ static int sx9324_write_gain(struct sx_common_data *data, unsigned int gain, reg; int ret; - gain = ilog2(val); reg = SX9324_REG_PROX_CTRL0 + chan->channel / 2; + + gain = ilog2(val) + 1; + if (val <= 0 || gain > SX9324_REG_PROX_CTRL0_GAIN_8) + return -EINVAL; + gain = FIELD_PREP(SX9324_REG_PROX_CTRL0_GAIN_MASK, gain); mutex_lock(&data->mutex); @@ -781,12 +796,15 @@ static const struct sx_common_reg_default sx9324_default_regs[] = { { SX9324_REG_AFE_PH2, 0x1a }, { SX9324_REG_AFE_PH3, 0x16 }, - { SX9324_REG_AFE_CTRL8, SX9324_REG_AFE_CTRL8_RESFILTN_4KOHM }, + { SX9324_REG_AFE_CTRL8, SX9324_REG_AFE_CTRL8_RESERVED | + SX9324_REG_AFE_CTRL8_RESFILTIN_4KOHM }, { SX9324_REG_AFE_CTRL9, SX9324_REG_AFE_CTRL9_AGAIN_1 }, - { SX9324_REG_PROX_CTRL0, SX9324_REG_PROX_CTRL0_GAIN_1 | + { SX9324_REG_PROX_CTRL0, + SX9324_REG_PROX_CTRL0_GAIN_1 << SX9324_REG_PROX_CTRL0_GAIN_SHIFT | SX9324_REG_PROX_CTRL0_RAWFILT_1P50 }, - { SX9324_REG_PROX_CTRL1, SX9324_REG_PROX_CTRL0_GAIN_1 | + { SX9324_REG_PROX_CTRL1, + SX9324_REG_PROX_CTRL0_GAIN_1 << SX9324_REG_PROX_CTRL0_GAIN_SHIFT | SX9324_REG_PROX_CTRL0_RAWFILT_1P50 }, { SX9324_REG_PROX_CTRL2, SX9324_REG_PROX_CTRL2_AVGNEG_THRESH_16K }, { SX9324_REG_PROX_CTRL3, SX9324_REG_PROX_CTRL3_AVGDEB_2SAMPLES | diff --git a/drivers/iio/proximity/sx_common.c b/drivers/iio/proximity/sx_common.c index a7c07316a0a9..8ad814d96b7e 100644 --- a/drivers/iio/proximity/sx_common.c +++ b/drivers/iio/proximity/sx_common.c @@ -521,6 +521,7 @@ int sx_common_probe(struct i2c_client *client, return dev_err_probe(dev, ret, "error reading WHOAMI\n"); ACPI_COMPANION_SET(&indio_dev->dev, ACPI_COMPANION(dev)); + indio_dev->dev.of_node = client->dev.of_node; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = data->chip_info->iio_channels; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 35f0d5e7533d..1c107d6d03b9 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -2824,6 +2824,7 @@ static int cm_dreq_handler(struct cm_work *work) switch (cm_id_priv->id.state) { case IB_CM_REP_SENT: case IB_CM_DREQ_SENT: + case IB_CM_MRA_REP_RCVD: ib_cancel_mad(cm_id_priv->msg); break; case IB_CM_ESTABLISHED: @@ -2831,8 +2832,6 @@ static int cm_dreq_handler(struct cm_work *work) cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD) ib_cancel_mad(cm_id_priv->msg); break; - case IB_CM_MRA_REP_RCVD: - break; case IB_CM_TIMEWAIT: atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES] [CM_DREQ_COUNTER]); diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 876cc78a22cc..7333646021bb 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -80,6 +80,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) unsigned long flags; struct list_head del_list; + /* Prevent freeing of mm until we are completely finished. */ + mmgrab(handler->mn.mm); + /* Unregister first so we don't get any more notifications. */ mmu_notifier_unregister(&handler->mn, handler->mn.mm); @@ -102,6 +105,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) do_remove(handler, &del_list); + /* Now the mm may be freed. */ + mmdrop(handler->mn.mm); + kfree(handler); } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 956f8e875daa..32ef67e9a6a7 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -574,8 +574,10 @@ static void __cache_work_func(struct mlx5_cache_ent *ent) spin_lock_irq(&ent->lock); if (ent->disabled) goto out; - if (need_delay) + if (need_delay) { queue_delayed_work(cache->wq, &ent->dwork, 300 * HZ); + goto out; + } remove_cache_mr_locked(ent); queue_adjust_cache_locked(ent); } @@ -625,6 +627,7 @@ static void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { struct mlx5_cache_ent *ent = mr->cache_ent; + WRITE_ONCE(dev->cache.last_add, jiffies); spin_lock_irq(&ent->lock); list_add_tail(&mr->list, &ent->head); ent->available_mrs++; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index ae50b56e8913..8ef112f883a7 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -3190,7 +3190,11 @@ serr_no_r_lock: spin_lock_irqsave(&sqp->s_lock, flags); rvt_send_complete(sqp, wqe, send_status); if (sqp->ibqp.qp_type == IB_QPT_RC) { - int lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + int lastwqe; + + spin_lock(&sqp->r_lock); + lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + spin_unlock(&sqp->r_lock); sqp->s_flags &= ~RVT_S_BUSY; spin_unlock_irqrestore(&sqp->s_lock, flags); diff --git a/drivers/input/keyboard/cypress-sf.c b/drivers/input/keyboard/cypress-sf.c index c28996028e80..9a23eed6a4f4 100644 --- a/drivers/input/keyboard/cypress-sf.c +++ b/drivers/input/keyboard/cypress-sf.c @@ -61,6 +61,14 @@ static irqreturn_t cypress_sf_irq_handler(int irq, void *devid) return IRQ_HANDLED; } +static void cypress_sf_disable_regulators(void *arg) +{ + struct cypress_sf_data *touchkey = arg; + + regulator_bulk_disable(ARRAY_SIZE(touchkey->regulators), + touchkey->regulators); +} + static int cypress_sf_probe(struct i2c_client *client) { struct cypress_sf_data *touchkey; @@ -121,6 +129,12 @@ static int cypress_sf_probe(struct i2c_client *client) return error; } + error = devm_add_action_or_reset(&client->dev, + cypress_sf_disable_regulators, + touchkey); + if (error) + return error; + touchkey->input_dev = devm_input_allocate_device(&client->dev); if (!touchkey->input_dev) { dev_err(&client->dev, "Failed to allocate input device\n"); diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c index 43375b38ee59..8a7ce41b8c56 100644 --- a/drivers/input/keyboard/omap4-keypad.c +++ b/drivers/input/keyboard/omap4-keypad.c @@ -393,7 +393,7 @@ static int omap4_keypad_probe(struct platform_device *pdev) * revision register. */ error = pm_runtime_get_sync(dev); - if (error) { + if (error < 0) { dev_err(dev, "pm_runtime_get_sync() failed\n"); pm_runtime_put_noidle(dev); return error; diff --git a/drivers/interconnect/qcom/sc7180.c b/drivers/interconnect/qcom/sc7180.c index 12d59c36df53..5f7c0f85fa8e 100644 --- a/drivers/interconnect/qcom/sc7180.c +++ b/drivers/interconnect/qcom/sc7180.c @@ -47,7 +47,6 @@ DEFINE_QNODE(qnm_mnoc_sf, SC7180_MASTER_MNOC_SF_MEM_NOC, 1, 32, SC7180_SLAVE_GEM DEFINE_QNODE(qnm_snoc_gc, SC7180_MASTER_SNOC_GC_MEM_NOC, 1, 8, SC7180_SLAVE_LLCC); DEFINE_QNODE(qnm_snoc_sf, SC7180_MASTER_SNOC_SF_MEM_NOC, 1, 16, SC7180_SLAVE_LLCC); DEFINE_QNODE(qxm_gpu, SC7180_MASTER_GFX3D, 2, 32, SC7180_SLAVE_GEM_NOC_SNOC, SC7180_SLAVE_LLCC); -DEFINE_QNODE(ipa_core_master, SC7180_MASTER_IPA_CORE, 1, 8, SC7180_SLAVE_IPA_CORE); DEFINE_QNODE(llcc_mc, SC7180_MASTER_LLCC, 2, 4, SC7180_SLAVE_EBI1); DEFINE_QNODE(qhm_mnoc_cfg, SC7180_MASTER_CNOC_MNOC_CFG, 1, 4, SC7180_SLAVE_SERVICE_MNOC); DEFINE_QNODE(qxm_camnoc_hf0, SC7180_MASTER_CAMNOC_HF0, 2, 32, SC7180_SLAVE_MNOC_HF_MEM_NOC); @@ -129,7 +128,6 @@ DEFINE_QNODE(qhs_mdsp_ms_mpu_cfg, SC7180_SLAVE_MSS_PROC_MS_MPU_CFG, 1, 4); DEFINE_QNODE(qns_gem_noc_snoc, SC7180_SLAVE_GEM_NOC_SNOC, 1, 8, SC7180_MASTER_GEM_NOC_SNOC); DEFINE_QNODE(qns_llcc, SC7180_SLAVE_LLCC, 1, 16, SC7180_MASTER_LLCC); DEFINE_QNODE(srvc_gemnoc, SC7180_SLAVE_SERVICE_GEM_NOC, 1, 4); -DEFINE_QNODE(ipa_core_slave, SC7180_SLAVE_IPA_CORE, 1, 8); DEFINE_QNODE(ebi, SC7180_SLAVE_EBI1, 2, 4); DEFINE_QNODE(qns_mem_noc_hf, SC7180_SLAVE_MNOC_HF_MEM_NOC, 1, 32, SC7180_MASTER_MNOC_HF_MEM_NOC); DEFINE_QNODE(qns_mem_noc_sf, SC7180_SLAVE_MNOC_SF_MEM_NOC, 1, 32, SC7180_MASTER_MNOC_SF_MEM_NOC); @@ -160,7 +158,6 @@ DEFINE_QBCM(bcm_mc0, "MC0", true, &ebi); DEFINE_QBCM(bcm_sh0, "SH0", true, &qns_llcc); DEFINE_QBCM(bcm_mm0, "MM0", false, &qns_mem_noc_hf); DEFINE_QBCM(bcm_ce0, "CE0", false, &qxm_crypto); -DEFINE_QBCM(bcm_ip0, "IP0", false, &ipa_core_slave); DEFINE_QBCM(bcm_cn0, "CN0", true, &qnm_snoc, &xm_qdss_dap, &qhs_a1_noc_cfg, &qhs_a2_noc_cfg, &qhs_ahb2phy0, &qhs_aop, &qhs_aoss, &qhs_boot_rom, &qhs_camera_cfg, &qhs_camera_nrt_throttle_cfg, &qhs_camera_rt_throttle_cfg, &qhs_clk_ctl, &qhs_cpr_cx, &qhs_cpr_mx, &qhs_crypto0_cfg, &qhs_dcc_cfg, &qhs_ddrss_cfg, &qhs_display_cfg, &qhs_display_rt_throttle_cfg, &qhs_display_throttle_cfg, &qhs_glm, &qhs_gpuss_cfg, &qhs_imem_cfg, &qhs_ipa, &qhs_mnoc_cfg, &qhs_mss_cfg, &qhs_npu_cfg, &qhs_npu_dma_throttle_cfg, &qhs_npu_dsp_throttle_cfg, &qhs_pimem_cfg, &qhs_prng, &qhs_qdss_cfg, &qhs_qm_cfg, &qhs_qm_mpu_cfg, &qhs_qup0, &qhs_qup1, &qhs_security, &qhs_snoc_cfg, &qhs_tcsr, &qhs_tlmm_1, &qhs_tlmm_2, &qhs_tlmm_3, &qhs_ufs_mem_cfg, &qhs_usb3, &qhs_venus_cfg, &qhs_venus_throttle_cfg, &qhs_vsense_ctrl_cfg, &srvc_cnoc); DEFINE_QBCM(bcm_mm1, "MM1", false, &qxm_camnoc_hf0_uncomp, &qxm_camnoc_hf1_uncomp, &qxm_camnoc_sf_uncomp, &qhm_mnoc_cfg, &qxm_mdp0, &qxm_rot, &qxm_venus0, &qxm_venus_arm9); DEFINE_QBCM(bcm_sh2, "SH2", false, &acm_sys_tcu); @@ -372,22 +369,6 @@ static struct qcom_icc_desc sc7180_gem_noc = { .num_bcms = ARRAY_SIZE(gem_noc_bcms), }; -static struct qcom_icc_bcm *ipa_virt_bcms[] = { - &bcm_ip0, -}; - -static struct qcom_icc_node *ipa_virt_nodes[] = { - [MASTER_IPA_CORE] = &ipa_core_master, - [SLAVE_IPA_CORE] = &ipa_core_slave, -}; - -static struct qcom_icc_desc sc7180_ipa_virt = { - .nodes = ipa_virt_nodes, - .num_nodes = ARRAY_SIZE(ipa_virt_nodes), - .bcms = ipa_virt_bcms, - .num_bcms = ARRAY_SIZE(ipa_virt_bcms), -}; - static struct qcom_icc_bcm *mc_virt_bcms[] = { &bcm_acv, &bcm_mc0, @@ -519,8 +500,6 @@ static const struct of_device_id qnoc_of_match[] = { .data = &sc7180_dc_noc}, { .compatible = "qcom,sc7180-gem-noc", .data = &sc7180_gem_noc}, - { .compatible = "qcom,sc7180-ipa-virt", - .data = &sc7180_ipa_virt}, { .compatible = "qcom,sc7180-mc-virt", .data = &sc7180_mc_virt}, { .compatible = "qcom,sc7180-mmss-noc", diff --git a/drivers/interconnect/qcom/sdx55.c b/drivers/interconnect/qcom/sdx55.c index 03d604f84cc5..e3ac25a997b7 100644 --- a/drivers/interconnect/qcom/sdx55.c +++ b/drivers/interconnect/qcom/sdx55.c @@ -18,7 +18,6 @@ #include "icc-rpmh.h" #include "sdx55.h" -DEFINE_QNODE(ipa_core_master, SDX55_MASTER_IPA_CORE, 1, 8, SDX55_SLAVE_IPA_CORE); DEFINE_QNODE(llcc_mc, SDX55_MASTER_LLCC, 4, 4, SDX55_SLAVE_EBI_CH0); DEFINE_QNODE(acm_tcu, SDX55_MASTER_TCU_0, 1, 8, SDX55_SLAVE_LLCC, SDX55_SLAVE_MEM_NOC_SNOC, SDX55_SLAVE_MEM_NOC_PCIE_SNOC); DEFINE_QNODE(qnm_snoc_gc, SDX55_MASTER_SNOC_GC_MEM_NOC, 1, 8, SDX55_SLAVE_LLCC); @@ -40,7 +39,6 @@ DEFINE_QNODE(xm_pcie, SDX55_MASTER_PCIE, 1, 8, SDX55_SLAVE_ANOC_SNOC); DEFINE_QNODE(xm_qdss_etr, SDX55_MASTER_QDSS_ETR, 1, 8, SDX55_SLAVE_SNOC_CFG, SDX55_SLAVE_EMAC_CFG, SDX55_SLAVE_USB3, SDX55_SLAVE_AOSS, SDX55_SLAVE_SPMI_FETCHER, SDX55_SLAVE_QDSS_CFG, SDX55_SLAVE_PDM, SDX55_SLAVE_SNOC_MEM_NOC_GC, SDX55_SLAVE_TCSR, SDX55_SLAVE_CNOC_DDRSS, SDX55_SLAVE_SPMI_VGI_COEX, SDX55_SLAVE_QPIC, SDX55_SLAVE_OCIMEM, SDX55_SLAVE_IPA_CFG, SDX55_SLAVE_USB3_PHY_CFG, SDX55_SLAVE_AOP, SDX55_SLAVE_BLSP_1, SDX55_SLAVE_SDCC_1, SDX55_SLAVE_CNOC_MSS, SDX55_SLAVE_PCIE_PARF, SDX55_SLAVE_ECC_CFG, SDX55_SLAVE_AUDIO, SDX55_SLAVE_AOSS, SDX55_SLAVE_PRNG, SDX55_SLAVE_CRYPTO_0_CFG, SDX55_SLAVE_TCU, SDX55_SLAVE_CLK_CTL, SDX55_SLAVE_IMEM_CFG); DEFINE_QNODE(xm_sdc1, SDX55_MASTER_SDCC_1, 1, 8, SDX55_SLAVE_AOSS, SDX55_SLAVE_IPA_CFG, SDX55_SLAVE_ANOC_SNOC, SDX55_SLAVE_AOP, SDX55_SLAVE_AUDIO); DEFINE_QNODE(xm_usb3, SDX55_MASTER_USB3, 1, 8, SDX55_SLAVE_ANOC_SNOC); -DEFINE_QNODE(ipa_core_slave, SDX55_SLAVE_IPA_CORE, 1, 8); DEFINE_QNODE(ebi, SDX55_SLAVE_EBI_CH0, 1, 4); DEFINE_QNODE(qns_llcc, SDX55_SLAVE_LLCC, 1, 16, SDX55_SLAVE_EBI_CH0); DEFINE_QNODE(qns_memnoc_snoc, SDX55_SLAVE_MEM_NOC_SNOC, 1, 8, SDX55_MASTER_MEM_NOC_SNOC); @@ -82,7 +80,6 @@ DEFINE_QNODE(xs_sys_tcu_cfg, SDX55_SLAVE_TCU, 1, 8); DEFINE_QBCM(bcm_mc0, "MC0", true, &ebi); DEFINE_QBCM(bcm_sh0, "SH0", true, &qns_llcc); DEFINE_QBCM(bcm_ce0, "CE0", false, &qxm_crypto); -DEFINE_QBCM(bcm_ip0, "IP0", false, &ipa_core_slave); DEFINE_QBCM(bcm_pn0, "PN0", false, &qhm_snoc_cfg); DEFINE_QBCM(bcm_sh3, "SH3", false, &xm_apps_rdwr); DEFINE_QBCM(bcm_sh4, "SH4", false, &qns_memnoc_snoc, &qns_sys_pcie); @@ -219,22 +216,6 @@ static const struct qcom_icc_desc sdx55_system_noc = { .num_bcms = ARRAY_SIZE(system_noc_bcms), }; -static struct qcom_icc_bcm *ipa_virt_bcms[] = { - &bcm_ip0, -}; - -static struct qcom_icc_node *ipa_virt_nodes[] = { - [MASTER_IPA_CORE] = &ipa_core_master, - [SLAVE_IPA_CORE] = &ipa_core_slave, -}; - -static const struct qcom_icc_desc sdx55_ipa_virt = { - .nodes = ipa_virt_nodes, - .num_nodes = ARRAY_SIZE(ipa_virt_nodes), - .bcms = ipa_virt_bcms, - .num_bcms = ARRAY_SIZE(ipa_virt_bcms), -}; - static const struct of_device_id qnoc_of_match[] = { { .compatible = "qcom,sdx55-mc-virt", .data = &sdx55_mc_virt}, @@ -242,8 +223,6 @@ static const struct of_device_id qnoc_of_match[] = { .data = &sdx55_mem_noc}, { .compatible = "qcom,sdx55-system-noc", .data = &sdx55_system_noc}, - { .compatible = "qcom,sdx55-ipa-virt", - .data = &sdx55_ipa_virt}, { } }; MODULE_DEVICE_TABLE(of, qnoc_of_match); diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 4aab631ef517..d9cf2820c02e 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1661,7 +1661,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus", sizeof(phandle)); if (num_iommus < 0) - return 0; + return ERR_PTR(-ENODEV); arch_data = kcalloc(num_iommus + 1, sizeof(*arch_data), GFP_KERNEL); if (!arch_data) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 680d2fcf2686..15edb9a6fcae 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -433,6 +433,7 @@ config QCOM_PDC config QCOM_MPM tristate "QCOM MPM" depends on ARCH_QCOM + depends on MAILBOX select IRQ_DOMAIN_HIERARCHY help MSM Power Manager driver to manage and configure wakeup diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index cd772973114a..a0fc764ec9dc 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3011,18 +3011,12 @@ static int __init allocate_lpi_tables(void) return 0; } -static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +static u64 read_vpend_dirty_clear(void __iomem *vlpi_base) { u32 count = 1000000; /* 1s! */ bool clean; u64 val; - val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - val &= ~GICR_VPENDBASER_Valid; - val &= ~clr; - val |= set; - gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); - do { val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); clean = !(val & GICR_VPENDBASER_Dirty); @@ -3033,10 +3027,26 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) } } while (!clean && count); - if (unlikely(val & GICR_VPENDBASER_Dirty)) { + if (unlikely(!clean)) pr_err_ratelimited("ITS virtual pending table not cleaning\n"); + + return val; +} + +static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +{ + u64 val; + + /* Make sure we wait until the RD is done with the initial scan */ + val = read_vpend_dirty_clear(vlpi_base); + val &= ~GICR_VPENDBASER_Valid; + val &= ~clr; + val |= set; + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + val = read_vpend_dirty_clear(vlpi_base); + if (unlikely(val & GICR_VPENDBASER_Dirty)) val |= GICR_VPENDBASER_PendingLast; - } return val; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 0efe1a9a9f3b..b252d5534547 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -206,11 +206,11 @@ static inline void __iomem *gic_dist_base(struct irq_data *d) } } -static void gic_do_wait_for_rwp(void __iomem *base) +static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { u32 count = 1000000; /* 1s! */ - while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) { + while (readl_relaxed(base + GICD_CTLR) & bit) { count--; if (!count) { pr_err_ratelimited("RWP timeout, gone fishing\n"); @@ -224,13 +224,13 @@ static void gic_do_wait_for_rwp(void __iomem *base) /* Wait for completion of a distributor change */ static void gic_dist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data.dist_base); + gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP); } /* Wait for completion of a redistributor change */ static void gic_redist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data_rdist_rd_base()); + gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } #ifdef CONFIG_ARM64 @@ -1466,6 +1466,12 @@ static int gic_irq_domain_translate(struct irq_domain *d, if(fwspec->param_count != 2) return -EINVAL; + if (fwspec->param[0] < 16) { + pr_err(FW_BUG "Illegal GSI%d translation request\n", + fwspec->param[0]); + return -EINVAL; + } + *hwirq = fwspec->param[0]; *type = fwspec->param[1]; diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 58ba835bee1f..09c710ecc387 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -1123,6 +1123,12 @@ static int gic_irq_domain_translate(struct irq_domain *d, if(fwspec->param_count != 2) return -EINVAL; + if (fwspec->param[0] < 16) { + pr_err(FW_BUG "Illegal GSI%d translation request\n", + fwspec->param[0]); + return -EINVAL; + } + *hwirq = fwspec->param[0]; *type = fwspec->param[1]; diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c index eea5a753618c..d30614661eea 100644 --- a/drivers/irqchip/irq-qcom-mpm.c +++ b/drivers/irqchip/irq-qcom-mpm.c @@ -375,7 +375,7 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent) raw_spin_lock_init(&priv->lock); priv->base = devm_platform_ioremap_resource(pdev, 0); - if (!priv->base) + if (IS_ERR(priv->base)) return PTR_ERR(priv->base); for (i = 0; i < priv->reg_stride; i++) { diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index 7c2ca52ca3e4..df5347ea450b 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -771,12 +771,12 @@ static void journal_write_unlocked(struct closure *cl) bio_reset(bio, ca->bdev, REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PREFLUSH | REQ_FUA); - bch_bio_map(bio, w->data); bio->bi_iter.bi_sector = PTR_OFFSET(k, i); bio->bi_iter.bi_size = sectors << 9; bio->bi_end_io = journal_write_endio; bio->bi_private = w; + bch_bio_map(bio, w->data); trace_bcache_journal_write(bio, w->data->keys); bio_list_add(&list, bio); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index fdd0194f84dd..320fcdfef48e 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -685,7 +685,7 @@ static void do_bio_hook(struct search *s, { struct bio *bio = &s->bio.bio; - bio_init_clone(bio->bi_bdev, bio, orig_bio, GFP_NOIO); + bio_init_clone(orig_bio->bi_bdev, bio, orig_bio, GFP_NOIO); /* * bi_end_io can be set separately somewhere else, e.g. the * variants in, diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index ad2d5faa2ebb..36ae30b73a6e 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -4399,6 +4399,7 @@ try_smaller_buffer: } if (ic->internal_hash) { + size_t recalc_tags_size; ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1); if (!ic->recalc_wq ) { ti->error = "Cannot allocate workqueue"; @@ -4412,8 +4413,10 @@ try_smaller_buffer: r = -ENOMEM; goto bad; } - ic->recalc_tags = kvmalloc_array(RECALC_SECTORS >> ic->sb->log2_sectors_per_block, - ic->tag_size, GFP_KERNEL); + recalc_tags_size = (RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size; + if (crypto_shash_digestsize(ic->internal_hash) > ic->tag_size) + recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tag_size; + ic->recalc_tags = kvmalloc(recalc_tags_size, GFP_KERNEL); if (!ic->recalc_tags) { ti->error = "Cannot allocate tags for recalculating"; r = -ENOMEM; diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c index 875bca30a0dd..82f2a06153dc 100644 --- a/drivers/md/dm-ps-historical-service-time.c +++ b/drivers/md/dm-ps-historical-service-time.c @@ -27,7 +27,6 @@ #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/module.h> -#include <linux/sched/clock.h> #define DM_MSG_PREFIX "multipath historical-service-time" @@ -433,7 +432,7 @@ static struct dm_path *hst_select_path(struct path_selector *ps, { struct selector *s = ps->context; struct path_info *pi = NULL, *best = NULL; - u64 time_now = sched_clock(); + u64 time_now = ktime_get_ns(); struct dm_path *ret = NULL; unsigned long flags; @@ -474,7 +473,7 @@ static int hst_start_io(struct path_selector *ps, struct dm_path *path, static u64 path_service_time(struct path_info *pi, u64 start_time) { - u64 sched_now = ktime_get_ns(); + u64 now = ktime_get_ns(); /* if a previous disk request has finished after this IO was * sent to the hardware, pretend the submission happened @@ -483,11 +482,11 @@ static u64 path_service_time(struct path_info *pi, u64 start_time) if (time_after64(pi->last_finish, start_time)) start_time = pi->last_finish; - pi->last_finish = sched_now; - if (time_before64(sched_now, start_time)) + pi->last_finish = now; + if (time_before64(now, start_time)) return 0; - return sched_now - start_time; + return now - start_time; } static int hst_end_io(struct path_selector *ps, struct dm_path *path, diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c index c1ca9be4b79e..57daa86c19cf 100644 --- a/drivers/md/dm-zone.c +++ b/drivers/md/dm-zone.c @@ -360,16 +360,20 @@ static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno, return 0; } +struct orig_bio_details { + unsigned int op; + unsigned int nr_sectors; +}; + /* * First phase of BIO mapping for targets with zone append emulation: * check all BIO that change a zone writer pointer and change zone * append operations into regular write operations. */ static bool dm_zone_map_bio_begin(struct mapped_device *md, - struct bio *orig_bio, struct bio *clone) + unsigned int zno, struct bio *clone) { sector_t zsectors = blk_queue_zone_sectors(md->queue); - unsigned int zno = bio_zone_no(orig_bio); unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); /* @@ -384,7 +388,7 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, WRITE_ONCE(md->zwp_offset[zno], zwp_offset); } - switch (bio_op(orig_bio)) { + switch (bio_op(clone)) { case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_FINISH: return true; @@ -401,9 +405,8 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, * target zone. */ clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE | - (orig_bio->bi_opf & (~REQ_OP_MASK)); - clone->bi_iter.bi_sector = - orig_bio->bi_iter.bi_sector + zwp_offset; + (clone->bi_opf & (~REQ_OP_MASK)); + clone->bi_iter.bi_sector += zwp_offset; break; default: DMWARN_LIMIT("Invalid BIO operation"); @@ -423,11 +426,10 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md, * data written to a zone. Note that at this point, the remapped clone BIO * may already have completed, so we do not touch it. */ -static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, - struct bio *orig_bio, +static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, unsigned int zno, + struct orig_bio_details *orig_bio_details, unsigned int nr_sectors) { - unsigned int zno = bio_zone_no(orig_bio); unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); /* The clone BIO may already have been completed and failed */ @@ -435,7 +437,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, return BLK_STS_IOERR; /* Update the zone wp offset */ - switch (bio_op(orig_bio)) { + switch (orig_bio_details->op) { case REQ_OP_ZONE_RESET: WRITE_ONCE(md->zwp_offset[zno], 0); return BLK_STS_OK; @@ -452,7 +454,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, * Check that the target did not truncate the write operation * emulating a zone append. */ - if (nr_sectors != bio_sectors(orig_bio)) { + if (nr_sectors != orig_bio_details->nr_sectors) { DMWARN_LIMIT("Truncated write for zone append"); return BLK_STS_IOERR; } @@ -488,7 +490,7 @@ static inline void dm_zone_unlock(struct request_queue *q, bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED); } -static bool dm_need_zone_wp_tracking(struct bio *orig_bio) +static bool dm_need_zone_wp_tracking(struct bio *bio) { /* * Special processing is not needed for operations that do not need the @@ -496,15 +498,15 @@ static bool dm_need_zone_wp_tracking(struct bio *orig_bio) * zones and all operations that do not modify directly a sequential * zone write pointer. */ - if (op_is_flush(orig_bio->bi_opf) && !bio_sectors(orig_bio)) + if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; - switch (bio_op(orig_bio)) { + switch (bio_op(bio)) { case REQ_OP_WRITE_ZEROES: case REQ_OP_WRITE: case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_FINISH: case REQ_OP_ZONE_APPEND: - return bio_zone_is_seq(orig_bio); + return bio_zone_is_seq(bio); default: return false; } @@ -519,8 +521,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) struct dm_target *ti = tio->ti; struct mapped_device *md = io->md; struct request_queue *q = md->queue; - struct bio *orig_bio = io->orig_bio; struct bio *clone = &tio->clone; + struct orig_bio_details orig_bio_details; unsigned int zno; blk_status_t sts; int r; @@ -529,18 +531,21 @@ int dm_zone_map_bio(struct dm_target_io *tio) * IOs that do not change a zone write pointer do not need * any additional special processing. */ - if (!dm_need_zone_wp_tracking(orig_bio)) + if (!dm_need_zone_wp_tracking(clone)) return ti->type->map(ti, clone); /* Lock the target zone */ - zno = bio_zone_no(orig_bio); + zno = bio_zone_no(clone); dm_zone_lock(q, zno, clone); + orig_bio_details.nr_sectors = bio_sectors(clone); + orig_bio_details.op = bio_op(clone); + /* * Check that the bio and the target zone write pointer offset are * both valid, and if the bio is a zone append, remap it to a write. */ - if (!dm_zone_map_bio_begin(md, orig_bio, clone)) { + if (!dm_zone_map_bio_begin(md, zno, clone)) { dm_zone_unlock(q, zno, clone); return DM_MAPIO_KILL; } @@ -560,7 +565,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) * The target submitted the clone BIO. The target zone will * be unlocked on completion of the clone. */ - sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr); + sts = dm_zone_map_bio_end(md, zno, &orig_bio_details, + *tio->len_ptr); break; case DM_MAPIO_REMAPPED: /* @@ -568,7 +574,8 @@ int dm_zone_map_bio(struct dm_target_io *tio) * unlock the target zone here as the clone will not be * submitted. */ - sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr); + sts = dm_zone_map_bio_end(md, zno, &orig_bio_details, + *tio->len_ptr); if (sts != BLK_STS_OK) dm_zone_unlock(q, zno, clone); break; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 3c5fad7c4ee6..82957bd460e8 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1323,8 +1323,7 @@ static void __map_bio(struct bio *clone) } static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, - struct dm_target *ti, unsigned num_bios, - unsigned *len) + struct dm_target *ti, unsigned num_bios) { struct bio *bio; int try; @@ -1335,7 +1334,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, if (try) mutex_lock(&ci->io->md->table_devices_lock); for (bio_nr = 0; bio_nr < num_bios; bio_nr++) { - bio = alloc_tio(ci, ti, bio_nr, len, + bio = alloc_tio(ci, ti, bio_nr, NULL, try ? GFP_NOIO : GFP_NOWAIT); if (!bio) break; @@ -1363,11 +1362,11 @@ static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, break; case 1: clone = alloc_tio(ci, ti, 0, len, GFP_NOIO); - dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); __map_bio(clone); break; default: - alloc_multiple_bios(&blist, ci, ti, num_bios, len); + /* dm_accept_partial_bio() is not supported with shared tio->len_ptr */ + alloc_multiple_bios(&blist, ci, ti, num_bios); while ((clone = bio_list_pop(&blist))) { dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO); __map_bio(clone); @@ -1392,6 +1391,7 @@ static void __send_empty_flush(struct clone_info *ci) ci->bio = &flush_bio; ci->sector_count = 0; + ci->io->tio.clone.bi_iter.bi_size = 0; while ((ti = dm_table_get_target(ci->map, target_nr++))) __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL); @@ -1407,14 +1407,10 @@ static void __send_changing_extent_only(struct clone_info *ci, struct dm_target len = min_t(sector_t, ci->sector_count, max_io_len_target_boundary(ti, dm_target_offset(ti, ci->sector))); - /* - * dm_accept_partial_bio cannot be used with duplicate bios, - * so update clone_info cursor before __send_duplicate_bios(). - */ + __send_duplicate_bios(ci, ti, num_bios, &len); + ci->sector += len; ci->sector_count -= len; - - __send_duplicate_bios(ci, ti, num_bios, &len); } static bool is_abnormal_io(struct bio *bio) diff --git a/drivers/media/platform/nxp/Kconfig b/drivers/media/platform/nxp/Kconfig index 28f2bafc14d2..5afa373e534f 100644 --- a/drivers/media/platform/nxp/Kconfig +++ b/drivers/media/platform/nxp/Kconfig @@ -7,6 +7,7 @@ comment "NXP media platform drivers" config VIDEO_IMX_MIPI_CSIS tristate "NXP MIPI CSI-2 CSIS receiver found on i.MX7 and i.MX8 models" depends on ARCH_MXC || COMPILE_TEST + depends on VIDEO_DEV select MEDIA_CONTROLLER select V4L2_FWNODE select VIDEO_V4L2_SUBDEV_API diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c index 4de5e8d2b261..3d3d1062e212 100644 --- a/drivers/media/platform/rockchip/rga/rga.c +++ b/drivers/media/platform/rockchip/rga/rga.c @@ -892,7 +892,7 @@ static int rga_probe(struct platform_device *pdev) } rga->dst_mmu_pages = (unsigned int *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 3); - if (rga->dst_mmu_pages) { + if (!rga->dst_mmu_pages) { ret = -ENOMEM; goto free_src_pages; } diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c index 47029746b89e..0de587b412d4 100644 --- a/drivers/media/tuners/si2157.c +++ b/drivers/media/tuners/si2157.c @@ -77,16 +77,16 @@ err_mutex_unlock: } static const struct si2157_tuner_info si2157_tuners[] = { - { SI2141, false, 0x60, SI2141_60_FIRMWARE, SI2141_A10_FIRMWARE }, - { SI2141, false, 0x61, SI2141_61_FIRMWARE, SI2141_A10_FIRMWARE }, - { SI2146, false, 0x11, SI2146_11_FIRMWARE, NULL }, - { SI2147, false, 0x50, SI2147_50_FIRMWARE, NULL }, - { SI2148, true, 0x32, SI2148_32_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2148, true, 0x33, SI2148_33_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2157, false, 0x50, SI2157_50_FIRMWARE, SI2157_A30_FIRMWARE }, - { SI2158, false, 0x50, SI2158_50_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2158, false, 0x51, SI2158_51_FIRMWARE, SI2158_A20_FIRMWARE }, - { SI2177, false, 0x50, SI2177_50_FIRMWARE, SI2157_A30_FIRMWARE }, + { SI2141, 0x60, false, SI2141_60_FIRMWARE, SI2141_A10_FIRMWARE }, + { SI2141, 0x61, false, SI2141_61_FIRMWARE, SI2141_A10_FIRMWARE }, + { SI2146, 0x11, false, SI2146_11_FIRMWARE, NULL }, + { SI2147, 0x50, false, SI2147_50_FIRMWARE, NULL }, + { SI2148, 0x32, true, SI2148_32_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2148, 0x33, true, SI2148_33_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2157, 0x50, false, SI2157_50_FIRMWARE, SI2157_A30_FIRMWARE }, + { SI2158, 0x50, false, SI2158_50_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2158, 0x51, false, SI2158_51_FIRMWARE, SI2158_A20_FIRMWARE }, + { SI2177, 0x50, false, SI2177_50_FIRMWARE, SI2157_A30_FIRMWARE }, }; static int si2157_load_firmware(struct dvb_frontend *fe, @@ -178,7 +178,7 @@ static int si2157_find_and_load_firmware(struct dvb_frontend *fe) } } - if (!fw_name && !fw_alt_name) { + if (required && !fw_name && !fw_alt_name) { dev_err(&client->dev, "unknown chip version Si21%d-%c%c%c ROM 0x%02x\n", part_id, cmd.args[1], cmd.args[3], cmd.args[4], rom_id); diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c index c267283b01fd..e749dcb3ddea 100644 --- a/drivers/memory/atmel-ebi.c +++ b/drivers/memory/atmel-ebi.c @@ -544,20 +544,27 @@ static int atmel_ebi_probe(struct platform_device *pdev) smc_np = of_parse_phandle(dev->of_node, "atmel,smc", 0); ebi->smc.regmap = syscon_node_to_regmap(smc_np); - if (IS_ERR(ebi->smc.regmap)) - return PTR_ERR(ebi->smc.regmap); + if (IS_ERR(ebi->smc.regmap)) { + ret = PTR_ERR(ebi->smc.regmap); + goto put_node; + } ebi->smc.layout = atmel_hsmc_get_reg_layout(smc_np); - if (IS_ERR(ebi->smc.layout)) - return PTR_ERR(ebi->smc.layout); + if (IS_ERR(ebi->smc.layout)) { + ret = PTR_ERR(ebi->smc.layout); + goto put_node; + } ebi->smc.clk = of_clk_get(smc_np, 0); if (IS_ERR(ebi->smc.clk)) { - if (PTR_ERR(ebi->smc.clk) != -ENOENT) - return PTR_ERR(ebi->smc.clk); + if (PTR_ERR(ebi->smc.clk) != -ENOENT) { + ret = PTR_ERR(ebi->smc.clk); + goto put_node; + } ebi->smc.clk = NULL; } + of_node_put(smc_np); ret = clk_prepare_enable(ebi->smc.clk); if (ret) return ret; @@ -608,6 +615,10 @@ static int atmel_ebi_probe(struct platform_device *pdev) } return of_platform_populate(np, NULL, NULL, dev); + +put_node: + of_node_put(smc_np); + return ret; } static __maybe_unused int atmel_ebi_resume(struct device *dev) diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c index 2f6939da21cd..e83b61c925a4 100644 --- a/drivers/memory/fsl_ifc.c +++ b/drivers/memory/fsl_ifc.c @@ -287,8 +287,7 @@ static int fsl_ifc_ctrl_probe(struct platform_device *dev) } /* legacy dts may still use "simple-bus" compatible */ - ret = of_platform_populate(dev->dev.of_node, NULL, NULL, - &dev->dev); + ret = of_platform_default_populate(dev->dev.of_node, NULL, &dev->dev); if (ret) goto err_free_nandirq; diff --git a/drivers/memory/renesas-rpc-if.c b/drivers/memory/renesas-rpc-if.c index e4cc64f56019..019a0822bde0 100644 --- a/drivers/memory/renesas-rpc-if.c +++ b/drivers/memory/renesas-rpc-if.c @@ -164,25 +164,39 @@ static const struct regmap_access_table rpcif_volatile_table = { /* - * Custom accessor functions to ensure SMRDR0 and SMWDR0 are always accessed - * with proper width. Requires SMENR_SPIDE to be correctly set before! + * Custom accessor functions to ensure SM[RW]DR[01] are always accessed with + * proper width. Requires rpcif.xfer_size to be correctly set before! */ static int rpcif_reg_read(void *context, unsigned int reg, unsigned int *val) { struct rpcif *rpc = context; - if (reg == RPCIF_SMRDR0 || reg == RPCIF_SMWDR0) { - u32 spide = readl(rpc->base + RPCIF_SMENR) & RPCIF_SMENR_SPIDE(0xF); - - if (spide == 0x8) { + switch (reg) { + case RPCIF_SMRDR0: + case RPCIF_SMWDR0: + switch (rpc->xfer_size) { + case 1: *val = readb(rpc->base + reg); return 0; - } else if (spide == 0xC) { + + case 2: *val = readw(rpc->base + reg); return 0; - } else if (spide != 0xF) { + + case 4: + case 8: + *val = readl(rpc->base + reg); + return 0; + + default: return -EILSEQ; } + + case RPCIF_SMRDR1: + case RPCIF_SMWDR1: + if (rpc->xfer_size != 8) + return -EILSEQ; + break; } *val = readl(rpc->base + reg); @@ -193,18 +207,34 @@ static int rpcif_reg_write(void *context, unsigned int reg, unsigned int val) { struct rpcif *rpc = context; - if (reg == RPCIF_SMRDR0 || reg == RPCIF_SMWDR0) { - u32 spide = readl(rpc->base + RPCIF_SMENR) & RPCIF_SMENR_SPIDE(0xF); - - if (spide == 0x8) { + switch (reg) { + case RPCIF_SMWDR0: + switch (rpc->xfer_size) { + case 1: writeb(val, rpc->base + reg); return 0; - } else if (spide == 0xC) { + + case 2: writew(val, rpc->base + reg); return 0; - } else if (spide != 0xF) { + + case 4: + case 8: + writel(val, rpc->base + reg); + return 0; + + default: return -EILSEQ; } + + case RPCIF_SMWDR1: + if (rpc->xfer_size != 8) + return -EILSEQ; + break; + + case RPCIF_SMRDR0: + case RPCIF_SMRDR1: + return -EPERM; } writel(val, rpc->base + reg); @@ -469,6 +499,7 @@ int rpcif_manual_xfer(struct rpcif *rpc) smenr |= RPCIF_SMENR_SPIDE(rpcif_bits_set(rpc, nbytes)); regmap_write(rpc->regmap, RPCIF_SMENR, smenr); + rpc->xfer_size = nbytes; memcpy(data, rpc->buffer + pos, nbytes); if (nbytes == 8) { @@ -533,6 +564,7 @@ int rpcif_manual_xfer(struct rpcif *rpc) regmap_write(rpc->regmap, RPCIF_SMENR, smenr); regmap_write(rpc->regmap, RPCIF_SMCR, rpc->smcr | RPCIF_SMCR_SPIE); + rpc->xfer_size = nbytes; ret = wait_msg_xfer_end(rpc); if (ret) goto err_out; @@ -651,6 +683,7 @@ static int rpcif_probe(struct platform_device *pdev) struct platform_device *vdev; struct device_node *flash; const char *name; + int ret; flash = of_get_next_child(pdev->dev.of_node, NULL); if (!flash) { @@ -674,7 +707,14 @@ static int rpcif_probe(struct platform_device *pdev) return -ENOMEM; vdev->dev.parent = &pdev->dev; platform_set_drvdata(pdev, vdev); - return platform_device_add(vdev); + + ret = platform_device_add(vdev); + if (ret) { + platform_device_put(vdev); + return ret; + } + + return 0; } static int rpcif_remove(struct platform_device *pdev) diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index e90adfa57950..9b3ba2df71c7 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -6658,13 +6658,13 @@ static int mpt_summary_proc_show(struct seq_file *m, void *v) static int mpt_version_proc_show(struct seq_file *m, void *v) { u8 cb_idx; - int scsi, fc, sas, lan, ctl, targ, dmp; + int scsi, fc, sas, lan, ctl, targ; char *drvname; seq_printf(m, "%s-%s\n", "mptlinux", MPT_LINUX_VERSION_COMMON); seq_printf(m, " Fusion MPT base driver\n"); - scsi = fc = sas = lan = ctl = targ = dmp = 0; + scsi = fc = sas = lan = ctl = targ = 0; for (cb_idx = MPT_MAX_PROTOCOL_DRIVERS-1; cb_idx; cb_idx--) { drvname = NULL; if (MptCallbacks[cb_idx]) { diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 91f96abbb3f9..8d169a35cf13 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -31,6 +31,8 @@ */ #define FM25_SN_LEN 8 /* serial number length */ +#define EE_MAXADDRLEN 3 /* 24 bit addresses, up to 2 MBytes */ + struct at25_data { struct spi_eeprom chip; struct spi_device *spi; @@ -39,6 +41,7 @@ struct at25_data { struct nvmem_config nvmem_config; struct nvmem_device *nvmem; u8 sernum[FM25_SN_LEN]; + u8 command[EE_MAXADDRLEN + 1]; }; #define AT25_WREN 0x06 /* latch the write enable */ @@ -61,8 +64,6 @@ struct at25_data { #define FM25_ID_LEN 9 /* ID length */ -#define EE_MAXADDRLEN 3 /* 24 bit addresses, up to 2 MBytes */ - /* * Specs often allow 5ms for a page write, sometimes 20ms; * it's important to recover from write timeouts. @@ -78,7 +79,6 @@ static int at25_ee_read(void *priv, unsigned int offset, { struct at25_data *at25 = priv; char *buf = val; - u8 command[EE_MAXADDRLEN + 1]; u8 *cp; ssize_t status; struct spi_transfer t[2]; @@ -92,12 +92,15 @@ static int at25_ee_read(void *priv, unsigned int offset, if (unlikely(!count)) return -EINVAL; - cp = command; + cp = at25->command; instr = AT25_READ; if (at25->chip.flags & EE_INSTR_BIT3_IS_ADDR) if (offset >= BIT(at25->addrlen * 8)) instr |= AT25_INSTR_BIT3; + + mutex_lock(&at25->lock); + *cp++ = instr; /* 8/16/24-bit address is written MSB first */ @@ -116,7 +119,7 @@ static int at25_ee_read(void *priv, unsigned int offset, spi_message_init(&m); memset(t, 0, sizeof(t)); - t[0].tx_buf = command; + t[0].tx_buf = at25->command; t[0].len = at25->addrlen + 1; spi_message_add_tail(&t[0], &m); @@ -124,8 +127,6 @@ static int at25_ee_read(void *priv, unsigned int offset, t[1].len = count; spi_message_add_tail(&t[1], &m); - mutex_lock(&at25->lock); - /* * Read it all at once. * @@ -152,7 +153,7 @@ static int fm25_aux_read(struct at25_data *at25, u8 *buf, uint8_t command, spi_message_init(&m); memset(t, 0, sizeof(t)); - t[0].tx_buf = &command; + t[0].tx_buf = at25->command; t[0].len = 1; spi_message_add_tail(&t[0], &m); @@ -162,6 +163,8 @@ static int fm25_aux_read(struct at25_data *at25, u8 *buf, uint8_t command, mutex_lock(&at25->lock); + at25->command[0] = command; + status = spi_sync(at25->spi, &m); dev_dbg(&at25->spi->dev, "read %d aux bytes --> %d\n", len, status); diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index e008d82e4ba3..a13506dd8119 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -111,10 +111,10 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, if (contiguous) { if (is_power_of_2(page_size)) - paddr = (u64) (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool, - total_size, NULL, page_size); + paddr = (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool, + total_size, NULL, page_size); else - paddr = (u64) (uintptr_t) gen_pool_alloc(vm->dram_pg_pool, total_size); + paddr = gen_pool_alloc(vm->dram_pg_pool, total_size); if (!paddr) { dev_err(hdev->dev, "failed to allocate %llu contiguous pages with total size of %llu\n", @@ -150,12 +150,12 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, for (i = 0 ; i < num_pgs ; i++) { if (is_power_of_2(page_size)) phys_pg_pack->pages[i] = - (u64) gen_pool_dma_alloc_align(vm->dram_pg_pool, - page_size, NULL, - page_size); + (uintptr_t)gen_pool_dma_alloc_align(vm->dram_pg_pool, + page_size, NULL, + page_size); else - phys_pg_pack->pages[i] = (u64) gen_pool_alloc(vm->dram_pg_pool, - page_size); + phys_pg_pack->pages[i] = gen_pool_alloc(vm->dram_pg_pool, + page_size); if (!phys_pg_pack->pages[i]) { dev_err(hdev->dev, "Failed to allocate device memory (out of memory)\n"); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 4e67c1403cc9..506dc900f5c7 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -993,7 +993,7 @@ static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host, return -EEXIST; md->reset_done |= type; - err = mmc_hw_reset(host); + err = mmc_hw_reset(host->card); /* Ensure we switch back to the correct partition */ if (err) { struct mmc_blk_data *main_md = @@ -1880,6 +1880,31 @@ static inline bool mmc_blk_rq_error(struct mmc_blk_request *brq) brq->data.error || brq->cmd.resp[0] & CMD_ERRORS; } +static int mmc_spi_err_check(struct mmc_card *card) +{ + u32 status = 0; + int err; + + /* + * SPI does not have a TRAN state we have to wait on, instead the + * card is ready again when it no longer holds the line LOW. + * We still have to ensure two things here before we know the write + * was successful: + * 1. The card has not disconnected during busy and we actually read our + * own pull-up, thinking it was still connected, so ensure it + * still responds. + * 2. Check for any error bits, in particular R1_SPI_IDLE to catch a + * just reconnected card after being disconnected during busy. + */ + err = __mmc_send_status(card, &status, 0); + if (err) + return err; + /* All R1 and R2 bits of SPI are errors in our case */ + if (status) + return -EIO; + return 0; +} + static int mmc_blk_busy_cb(void *cb_data, bool *busy) { struct mmc_blk_busy_data *data = cb_data; @@ -1903,9 +1928,16 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req) struct mmc_blk_busy_data cb_data; int err; - if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ) + if (rq_data_dir(req) == READ) return 0; + if (mmc_host_is_spi(card->host)) { + err = mmc_spi_err_check(card); + if (err) + mqrq->brq.data.bytes_xfered = 0; + return err; + } + cb_data.card = card; cb_data.status = 0; err = __mmc_poll_for_busy(card->host, 0, MMC_BLK_TIMEOUT_MS, @@ -2350,6 +2382,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, struct mmc_blk_data *md; int devidx, ret; char cap_str[10]; + bool cache_enabled = false; + bool fua_enabled = false; devidx = ida_simple_get(&mmc_blk_ida, 0, max_devices, GFP_KERNEL); if (devidx < 0) { @@ -2429,13 +2463,17 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, md->flags |= MMC_BLK_CMD23; } - if (mmc_card_mmc(card) && - md->flags & MMC_BLK_CMD23 && + if (md->flags & MMC_BLK_CMD23 && ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) || card->ext_csd.rel_sectors)) { md->flags |= MMC_BLK_REL_WR; - blk_queue_write_cache(md->queue.queue, true, true); + fua_enabled = true; + cache_enabled = true; } + if (mmc_cache_enabled(card->host)) + cache_enabled = true; + + blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled); string_get_size((u64)size, 512, STRING_UNITS_2, cap_str, sizeof(cap_str)); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 368f10405e13..c6ae16d40766 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1995,7 +1995,7 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) /** * mmc_hw_reset - reset the card in hardware - * @host: MMC host to which the card is attached + * @card: card to be reset * * Hard reset the card. This function is only for upper layers, like the * block layer or card drivers. You cannot use it in host drivers (struct @@ -2003,8 +2003,9 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) * * Return: 0 on success, -errno on failure */ -int mmc_hw_reset(struct mmc_host *host) +int mmc_hw_reset(struct mmc_card *card) { + struct mmc_host *host = card->host; int ret; ret = host->bus_ops->hw_reset(host); diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index e6a2fd2c6d5c..8d9bceeff986 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -2325,10 +2325,9 @@ static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) static int mmc_test_reset(struct mmc_test_card *test) { struct mmc_card *card = test->card; - struct mmc_host *host = card->host; int err; - err = mmc_hw_reset(host); + err = mmc_hw_reset(card); if (!err) { /* * Reset will re-enable the card's command queue, but tests diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 9c13f2c31365..4566d7fc9055 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -62,8 +62,8 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, * excepted the last element which has no constraint on idmasize */ for_each_sg(data->sg, sg, data->sg_len - 1, i) { - if (!IS_ALIGNED(data->sg->offset, sizeof(u32)) || - !IS_ALIGNED(data->sg->length, SDMMC_IDMA_BURST)) { + if (!IS_ALIGNED(sg->offset, sizeof(u32)) || + !IS_ALIGNED(sg->length, SDMMC_IDMA_BURST)) { dev_err(mmc_dev(host->mmc), "unaligned scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); @@ -71,7 +71,7 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, } } - if (!IS_ALIGNED(data->sg->offset, sizeof(u32))) { + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { dev_err(mmc_dev(host->mmc), "unaligned last scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 2797a9c0f17d..ddb5ca2f559e 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -144,9 +144,9 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host, return clk_get_rate(priv->clk); if (priv->clkh) { + /* HS400 with 4TAP needs different clock settings */ bool use_4tap = priv->quirks && priv->quirks->hs400_4taps; - bool need_slow_clkh = (host->mmc->ios.timing == MMC_TIMING_UHS_SDR104) || - (host->mmc->ios.timing == MMC_TIMING_MMC_HS400); + bool need_slow_clkh = host->mmc->ios.timing == MMC_TIMING_MMC_HS400; clkh_shift = use_4tap && need_slow_clkh ? 1 : 2; ref_clk = priv->clkh; } @@ -396,10 +396,10 @@ static void renesas_sdhi_hs400_complete(struct mmc_host *mmc) SH_MOBILE_SDHI_SCC_TMPPORT2_HS400OSEL) | sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_TMPPORT2)); - /* Set the sampling clock selection range of HS400 mode */ sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_DTCNTL, SH_MOBILE_SDHI_SCC_DTCNTL_TAPEN | - 0x4 << SH_MOBILE_SDHI_SCC_DTCNTL_TAPNUM_SHIFT); + sd_scc_read32(host, priv, + SH_MOBILE_SDHI_SCC_DTCNTL)); /* Avoid bad TAP */ if (bad_taps & BIT(priv->tap_set)) { diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 666cee4c7f7c..08e838400b52 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -241,16 +241,6 @@ static void xenon_voltage_switch(struct sdhci_host *host) { /* Wait for 5ms after set 1.8V signal enable bit */ usleep_range(5000, 5500); - - /* - * For some reason the controller's Host Control2 register reports - * the bit representing 1.8V signaling as 0 when read after it was - * written as 1. Subsequent read reports 1. - * - * Since this may cause some issues, do an empty read of the Host - * Control2 register here to circumvent this. - */ - sdhci_readw(host, SDHCI_HOST_CONTROL2); } static unsigned int xenon_get_max_clock(struct sdhci_host *host) diff --git a/drivers/mtd/nand/raw/mtk_ecc.c b/drivers/mtd/nand/raw/mtk_ecc.c index e7df3dac705e..49ab3448b9b1 100644 --- a/drivers/mtd/nand/raw/mtk_ecc.c +++ b/drivers/mtd/nand/raw/mtk_ecc.c @@ -43,6 +43,7 @@ struct mtk_ecc_caps { u32 err_mask; + u32 err_shift; const u8 *ecc_strength; const u32 *ecc_regs; u8 num_ecc_strength; @@ -76,7 +77,7 @@ static const u8 ecc_strength_mt2712[] = { }; static const u8 ecc_strength_mt7622[] = { - 4, 6, 8, 10, 12, 14, 16 + 4, 6, 8, 10, 12 }; enum mtk_ecc_regs { @@ -221,7 +222,7 @@ void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats, for (i = 0; i < sectors; i++) { offset = (i >> 2) << 2; err = readl(ecc->regs + ECC_DECENUM0 + offset); - err = err >> ((i % 4) * 8); + err = err >> ((i % 4) * ecc->caps->err_shift); err &= ecc->caps->err_mask; if (err == ecc->caps->err_mask) { /* uncorrectable errors */ @@ -449,6 +450,7 @@ EXPORT_SYMBOL(mtk_ecc_get_parity_bits); static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = { .err_mask = 0x3f, + .err_shift = 8, .ecc_strength = ecc_strength_mt2701, .ecc_regs = mt2701_ecc_regs, .num_ecc_strength = 20, @@ -459,6 +461,7 @@ static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = { static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = { .err_mask = 0x7f, + .err_shift = 8, .ecc_strength = ecc_strength_mt2712, .ecc_regs = mt2712_ecc_regs, .num_ecc_strength = 23, @@ -468,10 +471,11 @@ static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = { }; static const struct mtk_ecc_caps mtk_ecc_caps_mt7622 = { - .err_mask = 0x3f, + .err_mask = 0x1f, + .err_shift = 5, .ecc_strength = ecc_strength_mt7622, .ecc_regs = mt7622_ecc_regs, - .num_ecc_strength = 7, + .num_ecc_strength = 5, .ecc_mode_shift = 4, .parity_bits = 13, .pg_irq_sel = 0, diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index 1a77542c6d67..048b255faa76 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -2651,10 +2651,23 @@ static int qcom_nand_attach_chip(struct nand_chip *chip) ecc->engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST; mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops); + /* Free the initially allocated BAM transaction for reading the ONFI params */ + if (nandc->props->is_bam) + free_bam_transaction(nandc); nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage, cwperpage); + /* Now allocate the BAM transaction based on updated max_cwperpage */ + if (nandc->props->is_bam) { + nandc->bam_txn = alloc_bam_transaction(nandc); + if (!nandc->bam_txn) { + dev_err(nandc->dev, + "failed to allocate bam transaction\n"); + return -ENOMEM; + } + } + /* * DATA_UD_BYTES varies based on whether the read/write command protects * spare data with ECC too. We protect spare data by default, so we set @@ -2955,17 +2968,6 @@ static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc, if (ret) return ret; - if (nandc->props->is_bam) { - free_bam_transaction(nandc); - nandc->bam_txn = alloc_bam_transaction(nandc); - if (!nandc->bam_txn) { - dev_err(nandc->dev, - "failed to allocate bam transaction\n"); - nand_cleanup(chip); - return -ENOMEM; - } - } - ret = mtd_device_parse_register(mtd, probes, NULL, NULL, 0); if (ret) nand_cleanup(chip); diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c index b85b9c6fcc42..a278829469d6 100644 --- a/drivers/mtd/nand/raw/sh_flctl.c +++ b/drivers/mtd/nand/raw/sh_flctl.c @@ -384,7 +384,8 @@ static int flctl_dma_fifo0_transfer(struct sh_flctl *flctl, unsigned long *buf, dma_addr_t dma_addr; dma_cookie_t cookie; uint32_t reg; - int ret; + int ret = 0; + unsigned long time_left; if (dir == DMA_FROM_DEVICE) { chan = flctl->chan_fifo0_rx; @@ -425,13 +426,14 @@ static int flctl_dma_fifo0_transfer(struct sh_flctl *flctl, unsigned long *buf, goto out; } - ret = + time_left = wait_for_completion_timeout(&flctl->dma_complete, msecs_to_jiffies(3000)); - if (ret <= 0) { + if (time_left == 0) { dmaengine_terminate_all(chan); dev_err(&flctl->pdev->dev, "wait_for_completion_timeout\n"); + ret = -ETIMEDOUT; } out: @@ -441,7 +443,7 @@ out: dma_unmap_single(chan->device->dev, dma_addr, len, dir); - /* ret > 0 is success */ + /* ret == 0 is success */ return ret; } @@ -465,7 +467,7 @@ static void read_fiforeg(struct sh_flctl *flctl, int rlen, int offset) /* initiate DMA transfer */ if (flctl->chan_fifo0_rx && rlen >= 32 && - flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_FROM_DEVICE) > 0) + !flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_FROM_DEVICE)) goto convert; /* DMA success */ /* do polling transfer */ @@ -524,7 +526,7 @@ static void write_ec_fiforeg(struct sh_flctl *flctl, int rlen, /* initiate DMA transfer */ if (flctl->chan_fifo0_tx && rlen >= 32 && - flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_TO_DEVICE) > 0) + !flctl_dma_fifo0_transfer(flctl, buf, rlen, DMA_TO_DEVICE)) return; /* DMA success */ /* do polling transfer */ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 15eddca7b4b6..38e152548126 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4027,14 +4027,19 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const v return true; } -static u32 bond_ip_hash(u32 hash, struct flow_keys *flow) +static u32 bond_ip_hash(u32 hash, struct flow_keys *flow, int xmit_policy) { hash ^= (__force u32)flow_get_u32_dst(flow) ^ (__force u32)flow_get_u32_src(flow); hash ^= (hash >> 16); hash ^= (hash >> 8); + /* discard lowest hash bit to deal with the common even ports pattern */ - return hash >> 1; + if (xmit_policy == BOND_XMIT_POLICY_LAYER34 || + xmit_policy == BOND_XMIT_POLICY_ENCAP34) + return hash >> 1; + + return hash; } /* Generate hash based on xmit policy. If @skb is given it is used to linearize @@ -4064,7 +4069,7 @@ static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const voi memcpy(&hash, &flow.ports.ports, sizeof(hash)); } - return bond_ip_hash(hash, &flow); + return bond_ip_hash(hash, &flow, bond->params.xmit_policy); } /** @@ -5259,7 +5264,7 @@ static u32 bond_sk_hash_l34(struct sock *sk) /* L4 */ memcpy(&hash, &flow.ports.ports, sizeof(hash)); /* L3 */ - return bond_ip_hash(hash, &flow); + return bond_ip_hash(hash, &flow, BOND_XMIT_POLICY_LAYER34); } static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond, diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index a416240d001b..12c15da55664 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1681,9 +1681,6 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, break; case PHY_INTERFACE_MODE_RMII: miicfg |= GSWIP_MII_CFG_MODE_RMIIM; - - /* Configure the RMII clock as output: */ - miicfg |= GSWIP_MII_CFG_RMII_CLK; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: diff --git a/drivers/net/dsa/mv88e6xxx/port_hidden.c b/drivers/net/dsa/mv88e6xxx/port_hidden.c index b49d05f0e117..7a9f9ff6dedf 100644 --- a/drivers/net/dsa/mv88e6xxx/port_hidden.c +++ b/drivers/net/dsa/mv88e6xxx/port_hidden.c @@ -40,8 +40,9 @@ int mv88e6xxx_port_hidden_wait(struct mv88e6xxx_chip *chip) { int bit = __bf_shf(MV88E6XXX_PORT_RESERVED_1A_BUSY); - return mv88e6xxx_wait_bit(chip, MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT, - MV88E6XXX_PORT_RESERVED_1A, bit, 0); + return mv88e6xxx_port_wait_bit(chip, + MV88E6XXX_PORT_RESERVED_1A_CTRL_PORT, + MV88E6XXX_PORT_RESERVED_1A, bit, 0); } int mv88e6xxx_port_hidden_read(struct mv88e6xxx_chip *chip, int block, int port, diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 413b0006e9a2..9e28219b223d 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -670,6 +670,8 @@ static int felix_change_tag_protocol(struct dsa_switch *ds, int cpu, struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); enum dsa_tag_protocol old_proto = felix->tag_proto; + bool cpu_port_active = false; + struct dsa_port *dp; int err; if (proto != DSA_TAG_PROTO_SEVILLE && @@ -677,6 +679,27 @@ static int felix_change_tag_protocol(struct dsa_switch *ds, int cpu, proto != DSA_TAG_PROTO_OCELOT_8021Q) return -EPROTONOSUPPORT; + /* We don't support multiple CPU ports, yet the DT blob may have + * multiple CPU ports defined. The first CPU port is the active one, + * the others are inactive. In this case, DSA will call + * ->change_tag_protocol() multiple times, once per CPU port. + * Since we implement the tagging protocol change towards "ocelot" or + * "seville" as effectively initializing the NPI port, what we are + * doing is effectively changing who the NPI port is to the last @cpu + * argument passed, which is an unused DSA CPU port and not the one + * that should actively pass traffic. + * Suppress DSA's calls on CPU ports that are inactive. + */ + dsa_switch_for_each_user_port(dp, ds) { + if (dp->cpu_dp->index == cpu) { + cpu_port_active = true; + break; + } + } + + if (!cpu_port_active) + return 0; + felix_del_tag_protocol(ds, cpu, old_proto); err = felix_set_tag_protocol(ds, cpu, proto); diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 8d382b27e625..52a8566071ed 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -2316,7 +2316,7 @@ static int felix_pci_probe(struct pci_dev *pdev, err = dsa_register_switch(ds); if (err) { - dev_err(&pdev->dev, "Failed to register DSA switch: %d\n", err); + dev_err_probe(&pdev->dev, err, "Failed to register DSA switch\n"); goto err_register_ds; } diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig index 1aa79735355f..060165a85fb7 100644 --- a/drivers/net/dsa/realtek/Kconfig +++ b/drivers/net/dsa/realtek/Kconfig @@ -9,34 +9,46 @@ menuconfig NET_DSA_REALTEK help Select to enable support for Realtek Ethernet switch chips. + Note that at least one interface driver must be enabled for the + subdrivers to be loaded. Moreover, an interface driver cannot achieve + anything without at least one subdriver enabled. + +if NET_DSA_REALTEK + config NET_DSA_REALTEK_MDIO - tristate "Realtek MDIO connected switch driver" - depends on NET_DSA_REALTEK + tristate "Realtek MDIO interface driver" depends on OF + depends on NET_DSA_REALTEK_RTL8365MB || NET_DSA_REALTEK_RTL8366RB + depends on NET_DSA_REALTEK_RTL8365MB || !NET_DSA_REALTEK_RTL8365MB + depends on NET_DSA_REALTEK_RTL8366RB || !NET_DSA_REALTEK_RTL8366RB help Select to enable support for registering switches configured through MDIO. config NET_DSA_REALTEK_SMI - tristate "Realtek SMI connected switch driver" - depends on NET_DSA_REALTEK + tristate "Realtek SMI interface driver" depends on OF + depends on NET_DSA_REALTEK_RTL8365MB || NET_DSA_REALTEK_RTL8366RB + depends on NET_DSA_REALTEK_RTL8365MB || !NET_DSA_REALTEK_RTL8365MB + depends on NET_DSA_REALTEK_RTL8366RB || !NET_DSA_REALTEK_RTL8366RB help Select to enable support for registering switches connected through SMI. config NET_DSA_REALTEK_RTL8365MB tristate "Realtek RTL8365MB switch subdriver" - depends on NET_DSA_REALTEK - depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + imply NET_DSA_REALTEK_SMI + imply NET_DSA_REALTEK_MDIO select NET_DSA_TAG_RTL8_4 help Select to enable support for Realtek RTL8365MB-VC and RTL8367S. config NET_DSA_REALTEK_RTL8366RB tristate "Realtek RTL8366RB switch subdriver" - depends on NET_DSA_REALTEK - depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + imply NET_DSA_REALTEK_SMI + imply NET_DSA_REALTEK_MDIO select NET_DSA_TAG_RTL4_A help - Select to enable support for Realtek RTL8366RB + Select to enable support for Realtek RTL8366RB. + +endif diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c index 31e1f100e48e..c58f49d558d2 100644 --- a/drivers/net/dsa/realtek/realtek-mdio.c +++ b/drivers/net/dsa/realtek/realtek-mdio.c @@ -267,7 +267,6 @@ static const struct of_device_id realtek_mdio_of_match[] = { #endif #if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, - { .compatible = "realtek,rtl8367s", .data = &rtl8365mb_variant, }, #endif { /* sentinel */ }, }; diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c index 2243d3da55b2..45992f79ec8d 100644 --- a/drivers/net/dsa/realtek/realtek-smi.c +++ b/drivers/net/dsa/realtek/realtek-smi.c @@ -546,20 +546,11 @@ static const struct of_device_id realtek_smi_of_match[] = { .data = &rtl8366rb_variant, }, #endif - { - /* FIXME: add support for RTL8366S and more */ - .compatible = "realtek,rtl8366s", - .data = NULL, - }, #if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, - { - .compatible = "realtek,rtl8367s", - .data = &rtl8365mb_variant, - }, #endif { /* sentinel */ }, }; diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index bd4cb9d7c35d..827993022386 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -35,15 +35,6 @@ source "drivers/net/ethernet/aquantia/Kconfig" source "drivers/net/ethernet/arc/Kconfig" source "drivers/net/ethernet/asix/Kconfig" source "drivers/net/ethernet/atheros/Kconfig" -source "drivers/net/ethernet/broadcom/Kconfig" -source "drivers/net/ethernet/brocade/Kconfig" -source "drivers/net/ethernet/cadence/Kconfig" -source "drivers/net/ethernet/calxeda/Kconfig" -source "drivers/net/ethernet/cavium/Kconfig" -source "drivers/net/ethernet/chelsio/Kconfig" -source "drivers/net/ethernet/cirrus/Kconfig" -source "drivers/net/ethernet/cisco/Kconfig" -source "drivers/net/ethernet/cortina/Kconfig" config CX_ECAT tristate "Beckhoff CX5020 EtherCAT master support" @@ -57,6 +48,14 @@ config CX_ECAT To compile this driver as a module, choose M here. The module will be called ec_bhf. +source "drivers/net/ethernet/broadcom/Kconfig" +source "drivers/net/ethernet/cadence/Kconfig" +source "drivers/net/ethernet/calxeda/Kconfig" +source "drivers/net/ethernet/cavium/Kconfig" +source "drivers/net/ethernet/chelsio/Kconfig" +source "drivers/net/ethernet/cirrus/Kconfig" +source "drivers/net/ethernet/cisco/Kconfig" +source "drivers/net/ethernet/cortina/Kconfig" source "drivers/net/ethernet/davicom/Kconfig" config DNET @@ -85,7 +84,6 @@ source "drivers/net/ethernet/huawei/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" -source "drivers/net/ethernet/microsoft/Kconfig" source "drivers/net/ethernet/xscale/Kconfig" config JME @@ -128,8 +126,9 @@ source "drivers/net/ethernet/mediatek/Kconfig" source "drivers/net/ethernet/mellanox/Kconfig" source "drivers/net/ethernet/micrel/Kconfig" source "drivers/net/ethernet/microchip/Kconfig" -source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/mscc/Kconfig" +source "drivers/net/ethernet/microsoft/Kconfig" +source "drivers/net/ethernet/moxa/Kconfig" source "drivers/net/ethernet/myricom/Kconfig" config FEALNX @@ -141,10 +140,10 @@ config FEALNX Say Y here to support the Myson MTD-800 family of PCI-based Ethernet cards. <http://www.myson.com.tw/> +source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/natsemi/Kconfig" source "drivers/net/ethernet/neterion/Kconfig" source "drivers/net/ethernet/netronome/Kconfig" -source "drivers/net/ethernet/ni/Kconfig" source "drivers/net/ethernet/8390/Kconfig" source "drivers/net/ethernet/nvidia/Kconfig" source "drivers/net/ethernet/nxp/Kconfig" @@ -164,6 +163,7 @@ source "drivers/net/ethernet/packetengines/Kconfig" source "drivers/net/ethernet/pasemi/Kconfig" source "drivers/net/ethernet/pensando/Kconfig" source "drivers/net/ethernet/qlogic/Kconfig" +source "drivers/net/ethernet/brocade/Kconfig" source "drivers/net/ethernet/qualcomm/Kconfig" source "drivers/net/ethernet/rdc/Kconfig" source "drivers/net/ethernet/realtek/Kconfig" @@ -171,10 +171,10 @@ source "drivers/net/ethernet/renesas/Kconfig" source "drivers/net/ethernet/rocker/Kconfig" source "drivers/net/ethernet/samsung/Kconfig" source "drivers/net/ethernet/seeq/Kconfig" -source "drivers/net/ethernet/sfc/Kconfig" source "drivers/net/ethernet/sgi/Kconfig" source "drivers/net/ethernet/silan/Kconfig" source "drivers/net/ethernet/sis/Kconfig" +source "drivers/net/ethernet/sfc/Kconfig" source "drivers/net/ethernet/smsc/Kconfig" source "drivers/net/ethernet/socionext/Kconfig" source "drivers/net/ethernet/stmicro/Kconfig" diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 33f1a1377588..24d715c28a35 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -486,8 +486,8 @@ int aq_nic_start(struct aq_nic_s *self) if (err < 0) goto err_exit; - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) { + for (i = 0U; self->aq_vecs > i; ++i) { + aq_vec = self->aq_vec[i]; err = aq_vec_start(aq_vec); if (err < 0) goto err_exit; @@ -517,8 +517,8 @@ int aq_nic_start(struct aq_nic_s *self) mod_timer(&self->polling_timer, jiffies + AQ_CFG_POLLING_TIMER_INTERVAL); } else { - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) { + for (i = 0U; self->aq_vecs > i; ++i) { + aq_vec = self->aq_vec[i]; err = aq_pci_func_alloc_irq(self, i, self->ndev->name, aq_vec_isr, aq_vec, aq_vec_get_affinity_mask(aq_vec)); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 797a95142d1f..3a529ee8c834 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -444,22 +444,22 @@ err_exit: static int aq_pm_freeze(struct device *dev) { - return aq_suspend_common(dev, false); + return aq_suspend_common(dev, true); } static int aq_pm_suspend_poweroff(struct device *dev) { - return aq_suspend_common(dev, true); + return aq_suspend_common(dev, false); } static int aq_pm_thaw(struct device *dev) { - return atl_resume_common(dev, false); + return atl_resume_common(dev, true); } static int aq_pm_resume_restore(struct device *dev) { - return atl_resume_common(dev, true); + return atl_resume_common(dev, false); } static const struct dev_pm_ops aq_pm_ops = { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index f4774cf051c9..6ab1f3212d24 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -43,8 +43,8 @@ static int aq_vec_poll(struct napi_struct *napi, int budget) if (!self) { err = -EINVAL; } else { - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; u64_stats_update_begin(&ring[AQ_VEC_RX_ID].stats.rx.syncp); ring[AQ_VEC_RX_ID].stats.rx.polls++; u64_stats_update_end(&ring[AQ_VEC_RX_ID].stats.rx.syncp); @@ -182,8 +182,8 @@ int aq_vec_init(struct aq_vec_s *self, const struct aq_hw_ops *aq_hw_ops, self->aq_hw_ops = aq_hw_ops; self->aq_hw = aq_hw; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; err = aq_ring_init(&ring[AQ_VEC_TX_ID], ATL_RING_TX); if (err < 0) goto err_exit; @@ -224,8 +224,8 @@ int aq_vec_start(struct aq_vec_s *self) unsigned int i = 0U; int err = 0; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; err = self->aq_hw_ops->hw_ring_tx_start(self->aq_hw, &ring[AQ_VEC_TX_ID]); if (err < 0) @@ -248,8 +248,8 @@ void aq_vec_stop(struct aq_vec_s *self) struct aq_ring_s *ring = NULL; unsigned int i = 0U; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; self->aq_hw_ops->hw_ring_tx_stop(self->aq_hw, &ring[AQ_VEC_TX_ID]); @@ -268,8 +268,8 @@ void aq_vec_deinit(struct aq_vec_s *self) if (!self) goto err_exit; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); aq_ring_rx_deinit(&ring[AQ_VEC_RX_ID]); } @@ -297,8 +297,8 @@ void aq_vec_ring_free(struct aq_vec_s *self) if (!self) goto err_exit; - for (i = 0U, ring = self->ring[0]; - self->tx_rings > i; ++i, ring = self->ring[i]) { + for (i = 0U; self->tx_rings > i; ++i) { + ring = self->ring[i]; aq_ring_free(&ring[AQ_VEC_TX_ID]); if (i < self->rx_rings) aq_ring_free(&ring[AQ_VEC_RX_ID]); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index c19b072f3a23..962253db25b8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -14153,10 +14153,6 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp) /* Stop Tx */ bnx2x_tx_disable(bp); - /* Delete all NAPI objects */ - bnx2x_del_all_napi(bp); - if (CNIC_LOADED(bp)) - bnx2x_del_all_napi_cnic(bp); netdev_reset_tc(bp->dev); del_timer_sync(&bp->timer); @@ -14261,6 +14257,11 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev) bnx2x_drain_tx_queues(bp); bnx2x_send_unload_req(bp, UNLOAD_RECOVERY); bnx2x_netif_stop(bp, 1); + bnx2x_del_all_napi(bp); + + if (CNIC_LOADED(bp)) + bnx2x_del_all_napi_cnic(bp); + bnx2x_free_irq(bp); /* Report UNLOAD_DONE to MCP */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 1c28495875cf..874fad0a5cf8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3253,6 +3253,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) } qidx = bp->tc_to_qidx[j]; ring->queue_id = bp->q_info[qidx].queue_id; + spin_lock_init(&txr->xdp_tx_lock); if (i < bp->tx_nr_rings_xdp) continue; if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1)) @@ -10338,6 +10339,12 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) if (irq_re_init) udp_tunnel_nic_reset_ntf(bp->dev); + if (bp->tx_nr_rings_xdp < num_possible_cpus()) { + if (!static_key_enabled(&bnxt_xdp_locking_key)) + static_branch_enable(&bnxt_xdp_locking_key); + } else if (static_key_enabled(&bnxt_xdp_locking_key)) { + static_branch_disable(&bnxt_xdp_locking_key); + } set_bit(BNXT_STATE_OPEN, &bp->state); bnxt_enable_int(bp); /* Enable TX queues */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 61aa3e8c5952..98453a78cbd0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -593,7 +593,8 @@ struct nqe_cn { #define BNXT_MAX_MTU 9500 #define BNXT_MAX_PAGE_MODE_MTU \ ((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \ - XDP_PACKET_HEADROOM) + XDP_PACKET_HEADROOM - \ + SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))) #define BNXT_MIN_PKT_SIZE 52 @@ -800,6 +801,8 @@ struct bnxt_tx_ring_info { u32 dev_state; struct bnxt_ring_struct tx_ring_struct; + /* Synchronize simultaneous xdp_xmit on same ring */ + spinlock_t xdp_tx_lock; }; #define BNXT_LEGACY_COAL_CMPL_PARAMS \ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 52fad0fdeacf..03b1d6c04504 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -20,6 +20,8 @@ #include "bnxt.h" #include "bnxt_xdp.h" +DEFINE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); + struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len) @@ -227,11 +229,16 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, ring = smp_processor_id() % bp->tx_nr_rings_xdp; txr = &bp->tx_ring[ring]; + if (READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING) + return -EINVAL; + + if (static_branch_unlikely(&bnxt_xdp_locking_key)) + spin_lock(&txr->xdp_tx_lock); + for (i = 0; i < num_frames; i++) { struct xdp_frame *xdp = frames[i]; - if (!txr || !bnxt_tx_avail(bp, txr) || - !(bp->bnapi[ring]->flags & BNXT_NAPI_FLAG_XDP)) + if (!bnxt_tx_avail(bp, txr)) break; mapping = dma_map_single(&pdev->dev, xdp->data, xdp->len, @@ -250,6 +257,9 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, bnxt_db_write(bp, &txr->tx_db, txr->tx_prod); } + if (static_branch_unlikely(&bnxt_xdp_locking_key)) + spin_unlock(&txr->xdp_tx_lock); + return nxmit; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h index 0df40c3beb05..067bb5e821f5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h @@ -10,6 +10,8 @@ #ifndef BNXT_XDP_H #define BNXT_XDP_H +DECLARE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); + struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 2dd79af9411b..bf1ec8fdc2ad 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -76,7 +76,7 @@ static inline void bcmgenet_writel(u32 value, void __iomem *offset) if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) __raw_writel(value, offset); else - writel(value, offset); + writel_relaxed(value, offset); } static inline u32 bcmgenet_readl(void __iomem *offset) @@ -84,7 +84,7 @@ static inline u32 bcmgenet_readl(void __iomem *offset) if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) return __raw_readl(offset); else - return readl(offset); + return readl_relaxed(offset); } static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv, @@ -2035,6 +2035,11 @@ static struct sk_buff *bcmgenet_add_tsb(struct net_device *dev, return skb; } +static void bcmgenet_hide_tsb(struct sk_buff *skb) +{ + __skb_pull(skb, sizeof(struct status_64)); +} + static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -2141,6 +2146,8 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) } GENET_CB(skb)->last_cb = tx_cb_ptr; + + bcmgenet_hide_tsb(skb); skb_tx_timestamp(skb); /* Decrement total BD count and advance our write pointer */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 800d5ced5800..e475be29845c 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1658,6 +1658,7 @@ static void macb_tx_restart(struct macb_queue *queue) unsigned int head = queue->tx_head; unsigned int tail = queue->tx_tail; struct macb *bp = queue->bp; + unsigned int head_idx, tbqp; if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(TXUBR)); @@ -1665,6 +1666,13 @@ static void macb_tx_restart(struct macb_queue *queue) if (head == tail) return; + tbqp = queue_readl(queue, TBQP) / macb_dma_desc_get_size(bp); + tbqp = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, tbqp)); + head_idx = macb_adj_dma_desc_idx(bp, macb_tx_ring_wrap(bp, head)); + + if (tbqp == head_idx) + return; + macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index d5356db7539a..caf48023f8ea 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1835,11 +1835,6 @@ static int ftgmac100_probe(struct platform_device *pdev) priv->rxdes0_edorr_mask = BIT(30); priv->txdes0_edotr_mask = BIT(30); priv->is_aspeed = true; - /* Disable ast2600 problematic HW arbitration */ - if (of_device_is_compatible(np, "aspeed,ast2600-mac")) { - iowrite32(FTGMAC100_TM_DEFAULT, - priv->base + FTGMAC100_OFFSET_TM); - } } else { priv->rxdes0_edorr_mask = BIT(15); priv->txdes0_edotr_mask = BIT(15); @@ -1911,6 +1906,11 @@ static int ftgmac100_probe(struct platform_device *pdev) err = ftgmac100_setup_clk(priv); if (err) goto err_phy_connect; + + /* Disable ast2600 problematic HW arbitration */ + if (of_device_is_compatible(np, "aspeed,ast2600-mac")) + iowrite32(FTGMAC100_TM_DEFAULT, + priv->base + FTGMAC100_OFFSET_TM); } /* Default ring sizes */ diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 763d2c7b5fb1..5750f9a56393 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -489,11 +489,15 @@ static int dpaa_get_ts_info(struct net_device *net_dev, info->phc_index = -1; fman_node = of_get_parent(mac_node); - if (fman_node) + if (fman_node) { ptp_node = of_parse_phandle(fman_node, "ptimer-handle", 0); + of_node_put(fman_node); + } - if (ptp_node) + if (ptp_node) { ptp_dev = of_find_device_by_node(ptp_node); + of_node_put(ptp_node); + } if (ptp_dev) ptp = platform_get_drvdata(ptp_dev); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c index 5f5f8c53c4a0..c8cb541572ff 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -167,7 +167,7 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) base = of_iomap(node, 0); if (!base) { err = -ENOMEM; - goto err_close; + goto err_put; } err = fsl_mc_allocate_irqs(mc_dev); @@ -210,6 +210,8 @@ err_free_mc_irq: fsl_mc_free_irqs(mc_dev); err_unmap: iounmap(base); +err_put: + of_node_put(node); err_close: dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle); err_free_mcp: diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 79afb1d7289b..9182631856d5 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -297,10 +297,6 @@ int enetc_setup_tc_txtime(struct net_device *ndev, void *type_data) if (tc < 0 || tc >= priv->num_tx_rings) return -EINVAL; - /* Do not support TXSTART and TX CSUM offload simutaniously */ - if (ndev->features & NETIF_F_CSUM_MASK) - return -EBUSY; - /* TSD and Qbv are mutually exclusive in hardware */ if (enetc_rd(&priv->si->hw, ENETC_QBV_PTGCR_OFFSET) & ENETC_QBV_TGE) return -EBUSY; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 11227f51404c..9f33ec838b52 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3731,7 +3731,7 @@ static int fec_enet_init_stop_mode(struct fec_enet_private *fep, ARRAY_SIZE(out_val)); if (ret) { dev_dbg(&fep->pdev->dev, "no stop mode property\n"); - return ret; + goto out; } fep->stop_gpr.gpr = syscon_node_to_regmap(gpr_np); diff --git a/drivers/net/ethernet/fungible/funcore/fun_dev.c b/drivers/net/ethernet/fungible/funcore/fun_dev.c index 5d7aef73df61..fb5120d90f26 100644 --- a/drivers/net/ethernet/fungible/funcore/fun_dev.c +++ b/drivers/net/ethernet/fungible/funcore/fun_dev.c @@ -586,8 +586,8 @@ static int fun_get_dev_limits(struct fun_dev *fdev) /* Calculate the max QID based on SQ/CQ/doorbell counts. * SQ/CQ doorbells alternate. */ - num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) / - (fdev->db_stride * 4); + num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) >> + (2 + NVME_CAP_STRIDE(fdev->cap_reg)); fdev->max_qid = min3(cq_count, sq_count, num_dbs / 2) - 1; fdev->kern_end_qid = fdev->max_qid + 1; return 0; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 7edf8569514c..928d934cb21a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -1065,19 +1065,23 @@ int hns_mac_init(struct dsaf_device *dsaf_dev) device_for_each_child_node(dsaf_dev->dev, child) { ret = fwnode_property_read_u32(child, "reg", &port_id); if (ret) { + fwnode_handle_put(child); dev_err(dsaf_dev->dev, "get reg fail, ret=%d!\n", ret); return ret; } if (port_id >= max_port_num) { + fwnode_handle_put(child); dev_err(dsaf_dev->dev, "reg(%u) out of range!\n", port_id); return -EINVAL; } mac_cb = devm_kzalloc(dsaf_dev->dev, sizeof(*mac_cb), GFP_KERNEL); - if (!mac_cb) + if (!mac_cb) { + fwnode_handle_put(child); return -ENOMEM; + } mac_cb->fw_port = child; mac_cb->mac_id = (u8)port_id; dsaf_dev->mac_cb[port_id] = mac_cb; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index 0c60f41fca8a..f3c9395d8351 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -75,7 +75,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, tx = %u.\n", + "failed to get tqp stat, ret = %d, rx = %u.\n", ret, i); return ret; } @@ -89,7 +89,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, ret = hclge_comm_cmd_send(hw, &desc, 1); if (ret) { dev_err(&hw->cmq.csq.pdev->dev, - "failed to get tqp stat, ret = %d, rx = %u.\n", + "failed to get tqp stat, ret = %d, tx = %u.\n", ret, i); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 44d9b560b337..93aeb615191d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -562,12 +562,12 @@ static void hns3_dbg_tx_spare_info(struct hns3_enet_ring *ring, char *buf, for (i = 0; i < ring_num; i++) { j = 0; - sprintf(result[j++], "%8u", i); - sprintf(result[j++], "%9u", ring->tx_copybreak); - sprintf(result[j++], "%3u", tx_spare->len); - sprintf(result[j++], "%3u", tx_spare->next_to_use); - sprintf(result[j++], "%3u", tx_spare->next_to_clean); - sprintf(result[j++], "%3u", tx_spare->last_to_clean); + sprintf(result[j++], "%u", i); + sprintf(result[j++], "%u", ring->tx_copybreak); + sprintf(result[j++], "%u", tx_spare->len); + sprintf(result[j++], "%u", tx_spare->next_to_use); + sprintf(result[j++], "%u", tx_spare->next_to_clean); + sprintf(result[j++], "%u", tx_spare->last_to_clean); sprintf(result[j++], "%pad", &tx_spare->dma); hns3_dbg_fill_content(content, sizeof(content), tx_spare_info_items, @@ -598,35 +598,35 @@ static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring, u32 base_add_l, base_add_h; u32 j = 0; - sprintf(result[j++], "%8u", index); + sprintf(result[j++], "%u", index); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BD_NUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BD_LEN_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_PKTNUM_RECORD_REG)); - sprintf(result[j++], "%9u", ring->rx_copybreak); + sprintf(result[j++], "%u", ring->rx_copybreak); - sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG) ? "on" : "off"); if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) - sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_EN_REG) ? "on" : "off"); else - sprintf(result[j++], "%10s", "NA"); + sprintf(result[j++], "%s", "NA"); base_add_h = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_BASEADDR_H_REG); @@ -700,36 +700,36 @@ static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring, u32 base_add_l, base_add_h; u32 j = 0; - sprintf(result[j++], "%8u", index); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", index); + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_BD_NUM_REG)); - sprintf(result[j++], "%2u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TC_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG)); - sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_FBDNUM_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_OFFSET_REG)); - sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_PKTNUM_RECORD_REG)); - sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG) ? "on" : "off"); if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) - sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_EN_REG) ? "on" : "off"); else - sprintf(result[j++], "%10s", "NA"); + sprintf(result[j++], "%s", "NA"); base_add_h = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_BASEADDR_H_REG); @@ -848,15 +848,15 @@ static void hns3_dump_rx_bd_info(struct hns3_nic_priv *priv, { unsigned int j = 0; - sprintf(result[j++], "%5d", idx); + sprintf(result[j++], "%d", idx); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.l234_info)); - sprintf(result[j++], "%7u", le16_to_cpu(desc->rx.pkt_len)); - sprintf(result[j++], "%4u", le16_to_cpu(desc->rx.size)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.pkt_len)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.size)); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.rss_hash)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->rx.fd_id)); - sprintf(result[j++], "%8u", le16_to_cpu(desc->rx.vlan_tag)); - sprintf(result[j++], "%15u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); - sprintf(result[j++], "%11u", le16_to_cpu(desc->rx.ot_vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.fd_id)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); + sprintf(result[j++], "%u", le16_to_cpu(desc->rx.ot_vlan_tag)); sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.bd_base_info)); if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) { u32 ol_info = le32_to_cpu(desc->rx.ol_info); @@ -930,19 +930,19 @@ static void hns3_dump_tx_bd_info(struct hns3_nic_priv *priv, { unsigned int j = 0; - sprintf(result[j++], "%6d", idx); + sprintf(result[j++], "%d", idx); sprintf(result[j++], "%#llx", le64_to_cpu(desc->addr)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.vlan_tag)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.send_size)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.send_size)); sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.type_cs_vlan_tso_len)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.outer_vlan_tag)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.tv)); - sprintf(result[j++], "%10u", + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.outer_vlan_tag)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.tv)); + sprintf(result[j++], "%u", le32_to_cpu(desc->tx.ol_type_vlan_len_msec)); sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.paylen_ol4cs)); sprintf(result[j++], "%#x", le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri)); - sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.mss_hw_csum)); + sprintf(result[j++], "%u", le16_to_cpu(desc->tx.mss_hw_csum)); } static int hns3_dbg_tx_bd_info(struct hns3_dbg_data *d, char *buf, int len) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 14dc12c2155d..a3ee7875d6a7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5203,6 +5203,13 @@ static void hns3_state_init(struct hnae3_handle *handle) set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state); } +static void hns3_state_uninit(struct hnae3_handle *handle) +{ + struct hns3_nic_priv *priv = handle->priv; + + clear_bit(HNS3_NIC_STATE_INITED, &priv->state); +} + static int hns3_client_init(struct hnae3_handle *handle) { struct pci_dev *pdev = handle->pdev; @@ -5320,7 +5327,9 @@ static int hns3_client_init(struct hnae3_handle *handle) return ret; out_reg_netdev_fail: + hns3_state_uninit(handle); hns3_dbg_uninit(handle); + hns3_client_stop(handle); out_client_start: hns3_free_rx_cpu_rmap(netdev); hns3_nic_uninit_irq(priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 6799d16de34b..7998ca617a92 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -94,6 +94,13 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len, enum hclge_comm_cmd_status status; struct hclge_desc desc; + if (msg_len > HCLGE_MBX_MAX_MSG_SIZE) { + dev_err(&hdev->pdev->dev, + "msg data length(=%u) exceeds maximum(=%u)\n", + msg_len, HCLGE_MBX_MAX_MSG_SIZE); + return -EMSGSIZE; + } + resp_pf_to_vf = (struct hclge_mbx_pf_to_vf_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_PF_TO_VF, false); @@ -176,7 +183,7 @@ static int hclge_get_ring_chain_from_mbx( ring_num = req->msg.ring_num; if (ring_num > HCLGE_MBX_MAX_RING_CHAIN_PARAM_NUM) - return -ENOMEM; + return -EINVAL; for (i = 0; i < ring_num; i++) { if (req->msg.param[i].tqp_index >= vport->nic.kinfo.rss_size) { @@ -587,9 +594,9 @@ static int hclge_set_vf_mtu(struct hclge_vport *vport, return hclge_set_vport_mtu(vport, mtu); } -static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *mbx_req, - struct hclge_respond_to_vf_msg *resp_msg) +static int hclge_get_queue_id_in_pf(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req, + struct hclge_respond_to_vf_msg *resp_msg) { struct hnae3_handle *handle = &vport->nic; struct hclge_dev *hdev = vport->back; @@ -599,17 +606,18 @@ static void hclge_get_queue_id_in_pf(struct hclge_vport *vport, if (queue_id >= handle->kinfo.num_tqps) { dev_err(&hdev->pdev->dev, "Invalid queue id(%u) from VF %u\n", queue_id, mbx_req->mbx_src_vfid); - return; + return -EINVAL; } qid_in_pf = hclge_covert_handle_qid_global(&vport->nic, queue_id); memcpy(resp_msg->data, &qid_in_pf, sizeof(qid_in_pf)); resp_msg->len = sizeof(qid_in_pf); + return 0; } -static void hclge_get_rss_key(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *mbx_req, - struct hclge_respond_to_vf_msg *resp_msg) +static int hclge_get_rss_key(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req, + struct hclge_respond_to_vf_msg *resp_msg) { #define HCLGE_RSS_MBX_RESP_LEN 8 struct hclge_dev *hdev = vport->back; @@ -627,13 +635,14 @@ static void hclge_get_rss_key(struct hclge_vport *vport, dev_warn(&hdev->pdev->dev, "failed to get the rss hash key, the index(%u) invalid !\n", index); - return; + return -EINVAL; } memcpy(resp_msg->data, &rss_cfg->rss_hash_key[index * HCLGE_RSS_MBX_RESP_LEN], HCLGE_RSS_MBX_RESP_LEN); resp_msg->len = HCLGE_RSS_MBX_RESP_LEN; + return 0; } static void hclge_link_fail_parse(struct hclge_dev *hdev, u8 link_fail_code) @@ -809,10 +818,10 @@ void hclge_mbx_handler(struct hclge_dev *hdev) "VF fail(%d) to set mtu\n", ret); break; case HCLGE_MBX_GET_QID_IN_PF: - hclge_get_queue_id_in_pf(vport, req, &resp_msg); + ret = hclge_get_queue_id_in_pf(vport, req, &resp_msg); break; case HCLGE_MBX_GET_RSS_KEY: - hclge_get_rss_key(vport, req, &resp_msg); + ret = hclge_get_rss_key(vport, req, &resp_msg); break; case HCLGE_MBX_GET_LINK_MODE: hclge_get_link_mode(vport, req); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 77683909ca3d..5c5931dba51d 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3210,13 +3210,8 @@ static void ibmvnic_get_ringparam(struct net_device *netdev, { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) { - ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; - ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; - } else { - ring->rx_max_pending = IBMVNIC_MAX_QUEUE_SZ; - ring->tx_max_pending = IBMVNIC_MAX_QUEUE_SZ; - } + ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; + ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; ring->rx_mini_max_pending = 0; ring->rx_jumbo_max_pending = 0; ring->rx_pending = adapter->req_rx_add_entries_per_subcrq; @@ -3231,23 +3226,21 @@ static int ibmvnic_set_ringparam(struct net_device *netdev, struct netlink_ext_ack *extack) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int ret; - ret = 0; + if (ring->rx_pending > adapter->max_rx_add_entries_per_subcrq || + ring->tx_pending > adapter->max_tx_entries_per_subcrq) { + netdev_err(netdev, "Invalid request.\n"); + netdev_err(netdev, "Max tx buffers = %llu\n", + adapter->max_rx_add_entries_per_subcrq); + netdev_err(netdev, "Max rx buffers = %llu\n", + adapter->max_tx_entries_per_subcrq); + return -EINVAL; + } + adapter->desired.rx_entries = ring->rx_pending; adapter->desired.tx_entries = ring->tx_pending; - ret = wait_for_reset(adapter); - - if (!ret && - (adapter->req_rx_add_entries_per_subcrq != ring->rx_pending || - adapter->req_tx_entries_per_subcrq != ring->tx_pending)) - netdev_info(netdev, - "Could not match full ringsize request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n", - ring->rx_pending, ring->tx_pending, - adapter->req_rx_add_entries_per_subcrq, - adapter->req_tx_entries_per_subcrq); - return ret; + return wait_for_reset(adapter); } static void ibmvnic_get_channels(struct net_device *netdev, @@ -3255,14 +3248,8 @@ static void ibmvnic_get_channels(struct net_device *netdev, { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - if (adapter->priv_flags & IBMVNIC_USE_SERVER_MAXES) { - channels->max_rx = adapter->max_rx_queues; - channels->max_tx = adapter->max_tx_queues; - } else { - channels->max_rx = IBMVNIC_MAX_QUEUES; - channels->max_tx = IBMVNIC_MAX_QUEUES; - } - + channels->max_rx = adapter->max_rx_queues; + channels->max_tx = adapter->max_tx_queues; channels->max_other = 0; channels->max_combined = 0; channels->rx_count = adapter->req_rx_queues; @@ -3275,22 +3262,11 @@ static int ibmvnic_set_channels(struct net_device *netdev, struct ethtool_channels *channels) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int ret; - ret = 0; adapter->desired.rx_queues = channels->rx_count; adapter->desired.tx_queues = channels->tx_count; - ret = wait_for_reset(adapter); - - if (!ret && - (adapter->req_rx_queues != channels->rx_count || - adapter->req_tx_queues != channels->tx_count)) - netdev_info(netdev, - "Could not match full channels request. Requested: RX %d, TX %d; Allowed: RX %llu, TX %llu\n", - channels->rx_count, channels->tx_count, - adapter->req_rx_queues, adapter->req_tx_queues); - return ret; + return wait_for_reset(adapter); } static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) @@ -3298,43 +3274,32 @@ static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) struct ibmvnic_adapter *adapter = netdev_priv(dev); int i; - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); - i++, data += ETH_GSTRING_LEN) - memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); + if (stringset != ETH_SS_STATS) + return; - for (i = 0; i < adapter->req_tx_queues; i++) { - snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++, data += ETH_GSTRING_LEN) + memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); - snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < adapter->req_tx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); + data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, - "tx%d_dropped_packets", i); - data += ETH_GSTRING_LEN; - } + snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); + data += ETH_GSTRING_LEN; - for (i = 0; i < adapter->req_rx_queues; i++) { - snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); - data += ETH_GSTRING_LEN; + snprintf(data, ETH_GSTRING_LEN, "tx%d_dropped_packets", i); + data += ETH_GSTRING_LEN; + } - snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < adapter->req_rx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); + data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); - data += ETH_GSTRING_LEN; - } - break; + snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); + data += ETH_GSTRING_LEN; - case ETH_SS_PRIV_FLAGS: - for (i = 0; i < ARRAY_SIZE(ibmvnic_priv_flags); i++) - strcpy(data + i * ETH_GSTRING_LEN, - ibmvnic_priv_flags[i]); - break; - default: - return; + snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); + data += ETH_GSTRING_LEN; } } @@ -3347,8 +3312,6 @@ static int ibmvnic_get_sset_count(struct net_device *dev, int sset) return ARRAY_SIZE(ibmvnic_stats) + adapter->req_tx_queues * NUM_TX_STATS + adapter->req_rx_queues * NUM_RX_STATS; - case ETH_SS_PRIV_FLAGS: - return ARRAY_SIZE(ibmvnic_priv_flags); default: return -EOPNOTSUPP; } @@ -3401,26 +3364,6 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev, } } -static u32 ibmvnic_get_priv_flags(struct net_device *netdev) -{ - struct ibmvnic_adapter *adapter = netdev_priv(netdev); - - return adapter->priv_flags; -} - -static int ibmvnic_set_priv_flags(struct net_device *netdev, u32 flags) -{ - struct ibmvnic_adapter *adapter = netdev_priv(netdev); - bool which_maxes = !!(flags & IBMVNIC_USE_SERVER_MAXES); - - if (which_maxes) - adapter->priv_flags |= IBMVNIC_USE_SERVER_MAXES; - else - adapter->priv_flags &= ~IBMVNIC_USE_SERVER_MAXES; - - return 0; -} - static const struct ethtool_ops ibmvnic_ethtool_ops = { .get_drvinfo = ibmvnic_get_drvinfo, .get_msglevel = ibmvnic_get_msglevel, @@ -3434,8 +3377,6 @@ static const struct ethtool_ops ibmvnic_ethtool_ops = { .get_sset_count = ibmvnic_get_sset_count, .get_ethtool_stats = ibmvnic_get_ethtool_stats, .get_link_ksettings = ibmvnic_get_link_ksettings, - .get_priv_flags = ibmvnic_get_priv_flags, - .set_priv_flags = ibmvnic_set_priv_flags, }; /* Routines for managing CRQs/sCRQs */ diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 8f5cefb932dd..1310c861bf83 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -41,11 +41,6 @@ #define IBMVNIC_RESET_DELAY 100 -static const char ibmvnic_priv_flags[][ETH_GSTRING_LEN] = { -#define IBMVNIC_USE_SERVER_MAXES 0x1 - "use-server-maxes" -}; - struct ibmvnic_login_buffer { __be32 len; __be32 version; @@ -883,7 +878,6 @@ struct ibmvnic_adapter { struct ibmvnic_control_ip_offload_buffer ip_offload_ctrl; dma_addr_t ip_offload_ctrl_tok; u32 msg_enable; - u32 priv_flags; /* Vital Product Data (VPD) */ struct ibmvnic_vpd *vpd; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index d60e2016d03c..e6c8e6d5234f 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1009,8 +1009,8 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) { u32 reg = link << (E1000_LTRV_REQ_SHIFT + E1000_LTRV_NOSNOOP_SHIFT) | link << E1000_LTRV_REQ_SHIFT | E1000_LTRV_SEND; - u16 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ - u16 lat_enc_d = 0; /* latency decoded */ + u32 max_ltr_enc_d = 0; /* maximum LTR decoded by platform */ + u32 lat_enc_d = 0; /* latency decoded */ u16 lat_enc = 0; /* latency encoded */ if (link) { diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 190590d32faf..7dfcf78b57fb 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2871,7 +2871,6 @@ continue_reset: running = adapter->state == __IAVF_RUNNING; if (running) { - netdev->flags &= ~IFF_UP; netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; @@ -2988,7 +2987,7 @@ continue_reset: * to __IAVF_RUNNING */ iavf_up_complete(adapter); - netdev->flags |= IFF_UP; + iavf_irq_enable(adapter, true); } else { iavf_change_state(adapter, __IAVF_DOWN); @@ -3004,10 +3003,8 @@ continue_reset: reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (running) { + if (running) iavf_change_state(adapter, __IAVF_RUNNING); - netdev->flags |= IFF_UP; - } dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index d4f1874df7d0..8ed3c9ab7ff7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -301,7 +301,6 @@ enum ice_vsi_state { ICE_VSI_NETDEV_REGISTERED, ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, - ICE_VSI_VLAN_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, ICE_VSI_STATE_NBITS /* must be last */ }; @@ -672,7 +671,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev) static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 5daade32ea62..fba178e07600 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -577,7 +577,7 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; - if (!vsi || vsi->type != ICE_VSI_PF || !vsi->arfs_fltr_list) + if (!vsi || vsi->type != ICE_VSI_PF) return; netdev = vsi->netdev; @@ -599,7 +599,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) int base_idx, i; if (!vsi || vsi->type != ICE_VSI_PF) - return -EINVAL; + return 0; pf = vsi->back; netdev = vsi->netdev; @@ -636,7 +636,6 @@ void ice_remove_arfs(struct ice_pf *pf) if (!pf_vsi) return; - ice_free_cpu_rx_rmap(pf_vsi); ice_clear_arfs(pf_vsi); } @@ -653,9 +652,5 @@ void ice_rebuild_arfs(struct ice_pf *pf) return; ice_remove_arfs(pf); - if (ice_set_cpu_rx_rmap(pf_vsi)) { - dev_err(ice_pf_to_dev(pf), "Failed to rebuild aRFS\n"); - return; - } ice_init_arfs(pf_vsi); } diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 9a84d746a6c4..6a463b242c7d 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -361,7 +361,8 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) np = netdev_priv(netdev); vsi = np->vsi; - if (ice_is_reset_in_progress(vsi->back->state)) + if (ice_is_reset_in_progress(vsi->back->state) || + test_bit(ICE_VF_DIS, vsi->back->state)) return NETDEV_TX_BUSY; repr = ice_netdev_to_repr(netdev); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index bd58d9d2e565..6a413331572b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -52,7 +52,7 @@ static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { } static inline int ice_eswitch_configure(struct ice_pf *pf) { - return -EOPNOTSUPP; + return 0; } static inline int ice_eswitch_rebuild(struct ice_pf *pf) diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index af57eb114966..85a94483c2ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -58,7 +58,16 @@ int ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -73,7 +82,16 @@ int ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -87,7 +105,16 @@ int ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** @@ -101,7 +128,16 @@ int ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index b897926f817d..6d19c58ccacd 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1480,6 +1480,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; ring->count = vsi->num_tx_desc; + ring->txq_teid = ICE_INVAL_TEID; if (dvm_ena) ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG2; else @@ -2688,6 +2689,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; + ice_free_cpu_rx_rmap(vsi); + ice_for_each_q_vector(vsi, i) { u16 vector = i + base; int irq_num; @@ -2701,7 +2704,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) continue; /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); + if (!IS_ENABLED(CONFIG_RFS_ACCEL)) + irq_set_affinity_notifier(irq_num, NULL); /* clear the affinity_mask in the IRQ descriptor */ irq_set_affinity_hint(irq_num, NULL); @@ -2983,6 +2987,8 @@ int ice_vsi_release(struct ice_vsi *vsi) } } + if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) + ice_clear_dflt_vsi(pf->first_sw); ice_fltr_remove_all(vsi); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b588d7995631..9a0a358a15c2 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -243,8 +243,7 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) { return test_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); } /** @@ -260,10 +259,15 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -280,10 +284,15 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -302,7 +311,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; u32 changed_flags = 0; - u8 promisc_m; int err; if (!vsi->netdev) @@ -320,7 +328,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (ice_vsi_fltr_changed(vsi)) { clear_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); clear_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); - clear_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); /* grab the netdev's addr_list_lock */ netif_addr_lock_bh(netdev); @@ -369,29 +376,15 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { if (vsi->current_netdev_flags & IFF_ALLMULTI) { - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_set_promisc(vsi, promisc_m); + err = ice_set_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags &= ~IFF_ALLMULTI; goto out_promisc; } } else { /* !(vsi->current_netdev_flags & IFF_ALLMULTI) */ - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_clear_promisc(vsi, promisc_m); + err = ice_clear_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags |= IFF_ALLMULTI; goto out_promisc; } @@ -2517,6 +2510,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } + err = ice_set_cpu_rx_rmap(vsi); + if (err) { + netdev_err(vsi->netdev, "Failed to setup CPU RMAP on VSI %u: %pe\n", + vsi->vsi_num, ERR_PTR(err)); + goto free_q_irqs; + } + vsi->irqs_ready = true; return 0; @@ -2569,7 +2569,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) spin_lock_init(&xdp_ring->tx_lock); for (j = 0; j < xdp_ring->count; j++) { tx_desc = ICE_TX_DESC(xdp_ring, j); - tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE); + tx_desc->cmd_type_offset_bsz = 0; } } @@ -2765,8 +2765,10 @@ free_qmap: ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { - if (vsi->xdp_rings[i]->desc) + if (vsi->xdp_rings[i]->desc) { + synchronize_rcu(); ice_free_tx_ring(vsi->xdp_rings[i]); + } kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; } @@ -3488,6 +3490,20 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + + /* Add multicast promisc rule for the VLAN ID to be added if + * all-multicast is currently enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + vid); + if (ret) + goto finish; + } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Add a switch rule for this VLAN ID so its corresponding VLAN tagged @@ -3495,8 +3511,23 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) */ vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->add_vlan(vsi, &vlan); - if (!ret) - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + if (ret) + goto finish; + + /* If all-multicast is currently enabled and this VLAN ID is only one + * besides VLAN-0 we have to update look-up type of multicast promisc + * rule for VLAN-0 from ICE_SW_LKUP_PROMISC to ICE_SW_LKUP_PROMISC_VLAN. + */ + if ((vsi->current_netdev_flags & IFF_ALLMULTI) && + ice_vsi_num_non_zero_vlans(vsi) == 1) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, 0); + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); return ret; } @@ -3522,6 +3553,9 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Make sure VLAN delete is successful before updating VLAN @@ -3530,10 +3564,33 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->del_vlan(vsi, &vlan); if (ret) - return ret; + goto finish; - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); - return 0; + /* Remove multicast promisc rule for the removed VLAN ID if + * all-multicast is enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, vid); + + if (!ice_vsi_has_non_zero_vlans(vsi)) { + /* Update look-up type of multicast promisc rule for VLAN 0 + * from ICE_SW_LKUP_PROMISC_VLAN to ICE_SW_LKUP_PROMISC when + * all-multicast is enabled and VLAN 0 is the only VLAN rule. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + } + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); + + return ret; } /** @@ -3642,20 +3699,12 @@ static int ice_setup_pf_sw(struct ice_pf *pf) */ ice_napi_add(vsi); - status = ice_set_cpu_rx_rmap(vsi); - if (status) { - dev_err(dev, "Failed to set CPU Rx map VSI %d error %d\n", - vsi->vsi_num, status); - goto unroll_napi_add; - } status = ice_init_mac_fltr(pf); if (status) - goto free_cpu_rx_map; + goto unroll_napi_add; return 0; -free_cpu_rx_map: - ice_free_cpu_rx_rmap(vsi); unroll_napi_add: ice_tc_indir_block_unregister(vsi); unroll_cfg_netdev: @@ -5117,7 +5166,6 @@ static int __maybe_unused ice_suspend(struct device *dev) continue; ice_vsi_free_q_vectors(pf->vsi[v]); } - ice_free_cpu_rx_rmap(ice_get_main_vsi(pf)); ice_clear_interrupt_scheme(pf); pci_save_state(pdev); @@ -5475,16 +5523,19 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* Add filter for new MAC. If filter exists, return success */ err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (err == -EEXIST) + if (err == -EEXIST) { /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - else if (err) + + return 0; + } else if (err) { /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; + } err_update_filters: if (err) { @@ -6878,12 +6929,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); +#define ICE_EMP_RESET_SLEEP_MS 5000 if (reset_type == ICE_RESET_EMPR) { /* If an EMP reset has occurred, any previously pending flash * update will have completed. We no longer know whether or * not the NVM update EMP reset is restricted. */ pf->fw_emp_reset_disabled = false; + + msleep(ICE_EMP_RESET_SLEEP_MS); } err = ice_init_all_ctrlq(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 4eb0599714f4..13cdb5ea594d 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -641,6 +641,7 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, status = ice_read_flash_module(hw, bank, ICE_SR_1ST_OROM_BANK_PTR, 0, orom_data, hw->flash.banks.orom_size); if (status) { + vfree(orom_data); ice_debug(hw, ICE_DBG_NVM, "Unable to read Option ROM data\n"); return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 8915a9d39e36..0c438219f7a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1046,8 +1046,8 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!num_vfs) { if (!pci_vfs_assigned(pdev)) { - ice_mbx_deinit_snapshot(&pf->hw); ice_free_vfs(pf); + ice_mbx_deinit_snapshot(&pf->hw); if (pf->lag) ice_enable_lag(pf->lag); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 3f1a63815bac..b72606c9e6d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1358,9 +1358,9 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - /* Skip queue if not enabled */ if (!test_bit(vf_q_id, vf->txq_ena)) - continue; + dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n", + vf_q_id, vsi->vsi_num); ice_fill_txq_meta(vsi, ring, &txq_meta); @@ -3625,6 +3625,8 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) return; } + mutex_lock(&vf->cfg_lock); + /* Check if VF is disabled. */ if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { err = -EPERM; @@ -3642,32 +3644,20 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) err = -EINVAL; } - if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { - ice_vc_send_msg_to_vf(vf, v_opcode, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, - 0); - ice_put_vf(vf); - return; - } - error_handler: if (err) { ice_vc_send_msg_to_vf(vf, v_opcode, VIRTCHNL_STATUS_ERR_PARAM, NULL, 0); dev_err(dev, "Invalid message from VF %d, opcode %d, len %d, error %d\n", vf_id, v_opcode, msglen, err); - ice_put_vf(vf); - return; + goto finish; } - /* VF is being configured in another context that triggers a VFR, so no - * need to process this message - */ - if (!mutex_trylock(&vf->cfg_lock)) { - dev_info(dev, "VF %u is being configured in another context that will trigger a VFR, so there is no need to handle this message\n", - vf->vf_id); - ice_put_vf(vf); - return; + if (!ice_vc_is_opcode_allowed(vf, v_opcode)) { + ice_vc_send_msg_to_vf(vf, v_opcode, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, NULL, + 0); + goto finish; } switch (v_opcode) { @@ -3780,6 +3770,7 @@ error_handler: vf_id, v_opcode, err); } +finish: mutex_unlock(&vf->cfg_lock); ice_put_vf(vf); } diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index dfbcaf08520e..9dd38f667059 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -41,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) + if (ice_is_xdp_ena_vsi(vsi)) { + synchronize_rcu(); ice_clean_tx_ring(vsi->xdp_rings[q_idx]); + } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -413,8 +415,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, */ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) { + u32 nb_buffs_extra = 0, nb_buffs = 0; union ice_32b_rx_flex_desc *rx_desc; - u32 nb_buffs_extra = 0, nb_buffs; u16 ntu = rx_ring->next_to_use; u16 total_count = count; struct xdp_buff **xdp; @@ -426,6 +428,10 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, rx_ring->count - ntu); + if (nb_buffs_extra != rx_ring->count - ntu) { + ntu += nb_buffs_extra; + goto exit; + } rx_desc = ICE_RX_DESC(rx_ring, 0); xdp = ice_xdp_buf(rx_ring, 0); ntu = 0; @@ -439,6 +445,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) if (ntu == rx_ring->count) ntu = 0; +exit: if (rx_ring->next_to_use != ntu) ice_release_rx_desc(rx_ring, ntu); @@ -918,7 +925,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index 66ea566488d1..59d5c467ea6e 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -156,8 +156,15 @@ void igc_release_swfw_sync_i225(struct igc_hw *hw, u16 mask) { u32 swfw_sync; - while (igc_get_hw_semaphore_i225(hw)) - ; /* Empty */ + /* Releasing the resource requires first getting the HW semaphore. + * If we fail to get the semaphore, there is nothing we can do, + * except log an error and quit. We are not allowed to hang here + * indefinitely, as it may cause denial of service or system crash. + */ + if (igc_get_hw_semaphore_i225(hw)) { + hw_dbg("Failed to release SW_FW_SYNC.\n"); + return; + } swfw_sync = rd32(IGC_SW_FW_SYNC); swfw_sync &= ~mask; diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 40dbf4b43234..6961f65d36b9 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -581,7 +581,7 @@ static s32 igc_read_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 *data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; @@ -638,7 +638,7 @@ static s32 igc_write_phy_reg_mdic(struct igc_hw *hw, u32 offset, u16 data) * the lower time out */ for (i = 0; i < IGC_GEN_POLL_TIMEOUT; i++) { - usleep_range(500, 1000); + udelay(50); mdic = rd32(IGC_MDIC); if (mdic & IGC_MDIC_READY) break; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 0d6e3215e98f..653e9f1e35b5 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -992,6 +992,17 @@ static void igc_ptp_time_restore(struct igc_adapter *adapter) igc_ptp_write_i225(adapter, &ts); } +static void igc_ptm_stop(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 ctrl; + + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_EN; + + wr32(IGC_PTM_CTRL, ctrl); +} + /** * igc_ptp_suspend - Disable PTP work items and prepare for suspend * @adapter: Board private structure @@ -1009,8 +1020,10 @@ void igc_ptp_suspend(struct igc_adapter *adapter) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state); - if (pci_device_is_present(adapter->pdev)) + if (pci_device_is_present(adapter->pdev)) { igc_ptp_time_save(adapter); + igc_ptm_stop(adapter); + } } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index e596e1a9fc75..69d11ff7677d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -903,7 +903,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) /* Tx IPsec offload doesn't seem to work on this * device, so block these requests for now. */ - if (!(sam->flags & XFRM_OFFLOAD_INBOUND)) { + sam->flags = sam->flags & ~XFRM_OFFLOAD_IPV6; + if (sam->flags != XFRM_OFFLOAD_INBOUND) { err = -EOPNOTSUPP; goto err_out; } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 5f9ab1842d49..c18801490649 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2751,7 +2751,7 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, } ret = of_get_mac_address(pnp, ppd.mac_addr); - if (ret) + if (ret == -EPROBE_DEFER) return ret; mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size); diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 939b692ffc33..ce843ea91464 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -650,6 +650,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client, return 0; errout: + mutex_destroy(&mlxsw_i2c->cmd.lock); i2c_set_clientdata(client, NULL); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index b73466470f75..fe663b0ab708 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -423,7 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, parms = mlxsw_sp_ipip_netdev_parms4(to_dev); ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, - 0, 0, parms.link, tun->fwmark, 0); + 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0); rt = ip_route_output_key(tun->net, &fl4); if (IS_ERR(rt)) diff --git a/drivers/net/ethernet/micrel/Kconfig b/drivers/net/ethernet/micrel/Kconfig index 93df3049cdc0..830363bafcce 100644 --- a/drivers/net/ethernet/micrel/Kconfig +++ b/drivers/net/ethernet/micrel/Kconfig @@ -28,6 +28,7 @@ config KS8842 config KS8851 tristate "Micrel KS8851 SPI" depends on SPI + depends on PTP_1588_CLOCK_OPTIONAL select MII select CRC32 select EEPROM_93CX6 @@ -39,6 +40,7 @@ config KS8851 config KS8851_MLL tristate "Micrel KS8851 MLL" depends on HAS_IOMEM + depends on PTP_1588_CLOCK_OPTIONAL select MII select CRC32 select EEPROM_93CX6 diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c index ce5970bdcc6a..005e56ea5da1 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c @@ -346,7 +346,8 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, lan966x_mac_process_raw_entry(&raw_entries[column], mac, &vid, &dest_idx); - WARN_ON(dest_idx > lan966x->num_phys_ports); + if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) + continue; /* If the entry in SW is found, then there is nothing * to do @@ -392,7 +393,8 @@ static void lan966x_mac_irq_process(struct lan966x *lan966x, u32 row, lan966x_mac_process_raw_entry(&raw_entries[column], mac, &vid, &dest_idx); - WARN_ON(dest_idx > lan966x->num_phys_ports); + if (WARN_ON(dest_idx >= lan966x->num_phys_ports)) + continue; mac_entry = lan966x_mac_alloc_entry(mac, vid, dest_idx); if (!mac_entry) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 1f8c67f0261b..95830e3e2b1f 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -446,6 +446,12 @@ static bool lan966x_hw_offload(struct lan966x *lan966x, u32 port, ANA_CPU_FWD_CFG_MLD_REDIR_ENA))) return true; + if (eth_type_vlan(skb->protocol)) { + skb = skb_vlan_untag(skb); + if (unlikely(!skb)) + return false; + } + if (skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->protocol == IPPROTO_IGMP) return false; @@ -665,6 +671,9 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) disable_irq(lan966x->ana_irq); lan966x->ana_irq = -ENXIO; } + + if (lan966x->ptp_irq) + devm_free_irq(lan966x->dev, lan966x->ptp_irq, lan966x); } static int lan966x_probe_port(struct lan966x *lan966x, u32 p, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c index ae782778d6dd..0a1041da4384 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -29,10 +29,10 @@ enum { static u64 lan966x_ptp_get_nominal_value(void) { - u64 res = 0x304d2df1; - - res <<= 32; - return res; + /* This is the default value that for each system clock, the time of day + * is increased. It has the format 5.59 nanosecond. + */ + return 0x304d4873ecade305; } int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c index e3555c94294d..df2bee678559 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c @@ -322,8 +322,7 @@ static int lan966x_port_prechangeupper(struct net_device *dev, if (netif_is_bridge_master(info->upper_dev) && !info->linking) switchdev_bridge_port_unoffload(port->dev, port, - &lan966x_switchdev_nb, - &lan966x_switchdev_blocking_nb); + NULL, NULL); return NOTIFY_DONE; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index e443bd8b2d09..ca71b62a44dc 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -551,7 +551,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, struct ocelot_vcap_block *block = &ocelot->block[VCAP_IS1]; struct ocelot_port *ocelot_port = ocelot->ports[port]; struct ocelot_vcap_filter *filter; - int err; + int err = 0; u32 val; list_for_each_entry(filter, &block->rules, list) { @@ -570,7 +570,7 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, if (vlan_aware) err = ocelot_del_vlan_unaware_pvid(ocelot, port, ocelot_port->bridge); - else + else if (ocelot_port->bridge) err = ocelot_add_vlan_unaware_pvid(ocelot, port, ocelot_port->bridge); if (err) @@ -629,6 +629,13 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, { int err; + /* Ignore VID 0 added to our RX filter by the 8021q module, since + * that collides with OCELOT_STANDALONE_PVID and changes it from + * egress-untagged to egress-tagged. + */ + if (!vid) + return 0; + err = ocelot_vlan_member_add(ocelot, port, vid, untagged); if (err) return err; @@ -651,6 +658,9 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) bool del_pvid = false; int err; + if (!vid) + return 0; + if (ocelot_port->pvid_vlan && ocelot_port->pvid_vlan->vid == vid) del_pvid = true; @@ -2859,6 +2869,8 @@ static void ocelot_port_set_mcast_flood(struct ocelot *ocelot, int port, val = BIT(port); ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MC); + ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV4); + ocelot_rmw_rix(ocelot, val, BIT(port), ANA_PGID_PGID, PGID_MCIPV6); } static void ocelot_port_set_bcast_flood(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 50ac3ee2577a..21d2645885ce 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2903,11 +2903,9 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb, status = myri10ge_xmit(curr, dev); if (status != 0) { dev_kfree_skb_any(curr); - if (segs != NULL) { - curr = segs; - segs = next; + skb_list_walk_safe(next, curr, next) { curr->next = NULL; - dev_kfree_skb_any(segs); + dev_kfree_skb_any(curr); } goto drop; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index e3edca187ddf..5250d1d1e49c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -489,7 +489,7 @@ struct split_type_defs { #define STATIC_DEBUG_LINE_DWORDS 9 -#define NUM_COMMON_GLOBAL_PARAMS 11 +#define NUM_COMMON_GLOBAL_PARAMS 10 #define MAX_RECURSION_DEPTH 10 diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index b242000a77fd..b7cc36589f59 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -748,6 +748,9 @@ qede_build_skb(struct qede_rx_queue *rxq, buf = page_address(bd->data) + bd->page_offset; skb = build_skb(buf, rxq->rx_buf_seg_size); + if (unlikely(!skb)) + return NULL; + skb_reserve(skb, pad); skb_put(skb, len); diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index f9064532beb6..377df8b7f015 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -786,6 +786,85 @@ void efx_remove_channels(struct efx_nic *efx) kfree(efx->xdp_tx_queues); } +static int efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, + struct efx_tx_queue *tx_queue) +{ + if (xdp_queue_number >= efx->xdp_tx_queue_count) + return -EINVAL; + + netif_dbg(efx, drv, efx->net_dev, + "Channel %u TXQ %u is XDP %u, HW %u\n", + tx_queue->channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); + efx->xdp_tx_queues[xdp_queue_number] = tx_queue; + return 0; +} + +static void efx_set_xdp_channels(struct efx_nic *efx) +{ + struct efx_tx_queue *tx_queue; + struct efx_channel *channel; + unsigned int next_queue = 0; + int xdp_queue_number = 0; + int rc; + + /* We need to mark which channels really have RX and TX + * queues, and adjust the TX queue numbers if we have separate + * RX-only and TX-only channels. + */ + efx_for_each_channel(channel, efx) { + if (channel->channel < efx->tx_channel_offset) + continue; + + if (efx_channel_is_xdp_tx(channel)) { + efx_for_each_channel_tx_queue(tx_queue, channel) { + tx_queue->queue = next_queue++; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, + tx_queue); + if (rc == 0) + xdp_queue_number++; + } + } else { + efx_for_each_channel_tx_queue(tx_queue, channel) { + tx_queue->queue = next_queue++; + netif_dbg(efx, drv, efx->net_dev, + "Channel %u TXQ %u is HW %u\n", + channel->channel, tx_queue->label, + tx_queue->queue); + } + + /* If XDP is borrowing queues from net stack, it must + * use the queue with no csum offload, which is the + * first one of the channel + * (note: tx_queue_by_type is not initialized yet) + */ + if (efx->xdp_txq_queues_mode == + EFX_XDP_TX_QUEUES_BORROWED) { + tx_queue = &channel->tx_queue[0]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, + tx_queue); + if (rc == 0) + xdp_queue_number++; + } + } + } + WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number != efx->xdp_tx_queue_count); + WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number > efx->xdp_tx_queue_count); + + /* If we have more CPUs than assigned XDP TX queues, assign the already + * existing queues to the exceeding CPUs + */ + next_queue = 0; + while (xdp_queue_number < efx->xdp_tx_queue_count) { + tx_queue = efx->xdp_tx_queues[next_queue++]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) + xdp_queue_number++; + } +} + int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) { struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel; @@ -857,6 +936,7 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) efx_init_napi_channel(efx->channel[i]); } + efx_set_xdp_channels(efx); out: /* Destroy unused channel structures */ for (i = 0; i < efx->n_channels; i++) { @@ -889,26 +969,9 @@ rollback: goto out; } -static inline int -efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, - struct efx_tx_queue *tx_queue) -{ - if (xdp_queue_number >= efx->xdp_tx_queue_count) - return -EINVAL; - - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - tx_queue->channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); - efx->xdp_tx_queues[xdp_queue_number] = tx_queue; - return 0; -} - int efx_set_channels(struct efx_nic *efx) { - struct efx_tx_queue *tx_queue; struct efx_channel *channel; - unsigned int next_queue = 0; - int xdp_queue_number; int rc; efx->tx_channel_offset = @@ -926,61 +989,14 @@ int efx_set_channels(struct efx_nic *efx) return -ENOMEM; } - /* We need to mark which channels really have RX and TX - * queues, and adjust the TX queue numbers if we have separate - * RX-only and TX-only channels. - */ - xdp_queue_number = 0; efx_for_each_channel(channel, efx) { if (channel->channel < efx->n_rx_channels) channel->rx_queue.core_index = channel->channel; else channel->rx_queue.core_index = -1; - - if (channel->channel >= efx->tx_channel_offset) { - if (efx_channel_is_xdp_tx(channel)) { - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->queue = next_queue++; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } - } else { - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->queue = next_queue++; - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is HW %u\n", - channel->channel, tx_queue->label, - tx_queue->queue); - } - - /* If XDP is borrowing queues from net stack, it must use the queue - * with no csum offload, which is the first one of the channel - * (note: channel->tx_queue_by_type is not initialized yet) - */ - if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) { - tx_queue = &channel->tx_queue[0]; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } - } - } } - WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && - xdp_queue_number != efx->xdp_tx_queue_count); - WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && - xdp_queue_number > efx->xdp_tx_queue_count); - /* If we have more CPUs than assigned XDP TX queues, assign the already - * existing queues to the exceeding CPUs - */ - next_queue = 0; - while (xdp_queue_number < efx->xdp_tx_queue_count) { - tx_queue = efx->xdp_tx_queues[next_queue++]; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } + efx_set_xdp_channels(efx); rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); if (rc) @@ -1124,7 +1140,7 @@ void efx_start_channels(struct efx_nic *efx) struct efx_rx_queue *rx_queue; struct efx_channel *channel; - efx_for_each_channel(channel, efx) { + efx_for_each_channel_rev(channel, efx) { efx_for_each_channel_tx_queue(tx_queue, channel) { efx_init_tx_queue(tx_queue); atomic_inc(&efx->active_queues); diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 1b22c7be0088..fa8b9aacca11 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -150,6 +150,9 @@ static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue) struct efx_nic *efx = rx_queue->efx; int i; + if (unlikely(!rx_queue->page_ring)) + return; + /* Unmap and release the pages in the recycle ring. Remove the ring. */ for (i = 0; i <= rx_queue->page_ptr_mask; i++) { struct page *page = rx_queue->page_ring[i]; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index d16e031e95f4..6983799e1c05 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -443,6 +443,9 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, if (unlikely(!tx_queue)) return -EINVAL; + if (!tx_queue->initialised) + return -EINVAL; + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu); diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index d530cde2b864..9bc8281b7f5b 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -101,6 +101,8 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev, "shutting down TX queue %d\n", tx_queue->queue); + tx_queue->initialised = false; + if (!tx_queue->buffer) return; diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c index cd478d2cd871..00f6d347eaf7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c @@ -57,10 +57,6 @@ #define TSE_PCS_USE_SGMII_ENA BIT(0) #define TSE_PCS_IF_USE_SGMII 0x03 -#define SGMII_ADAPTER_CTRL_REG 0x00 -#define SGMII_ADAPTER_DISABLE 0x0001 -#define SGMII_ADAPTER_ENABLE 0x0000 - #define AUTONEGO_LINK_TIMER 20 static int tse_pcs_reset(void __iomem *base, struct tse_pcs *pcs) @@ -202,12 +198,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, unsigned int speed) { void __iomem *tse_pcs_base = pcs->tse_pcs_base; - void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; u32 val; - writew(SGMII_ADAPTER_ENABLE, - sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); - pcs->autoneg = phy_dev->autoneg; if (phy_dev->autoneg == AUTONEG_ENABLE) { diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h index 442812c0a4bd..694ac25ef426 100644 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h +++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h @@ -10,6 +10,10 @@ #include <linux/phy.h> #include <linux/timer.h> +#define SGMII_ADAPTER_CTRL_REG 0x00 +#define SGMII_ADAPTER_ENABLE 0x0000 +#define SGMII_ADAPTER_DISABLE 0x0001 + struct tse_pcs { struct device *dev; void __iomem *tse_pcs_base; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index ecf759ee1c9f..017dbbda0c1c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -205,7 +205,7 @@ static const struct pci_device_id loongson_dwmac_id_table[] = { }; MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); -struct pci_driver loongson_dwmac_driver = { +static struct pci_driver loongson_dwmac_driver = { .name = "dwmac-loongson-pci", .id_table = loongson_dwmac_id_table, .probe = loongson_dwmac_probe, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index b7c2579c963b..6b447d8f0bd8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -18,9 +18,6 @@ #include "altr_tse_pcs.h" -#define SGMII_ADAPTER_CTRL_REG 0x00 -#define SGMII_ADAPTER_DISABLE 0x0001 - #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII 0x0 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII 0x1 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RMII 0x2 @@ -62,14 +59,13 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) { struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv; void __iomem *splitter_base = dwmac->splitter_base; - void __iomem *tse_pcs_base = dwmac->pcs.tse_pcs_base; void __iomem *sgmii_adapter_base = dwmac->pcs.sgmii_adapter_base; struct device *dev = dwmac->dev; struct net_device *ndev = dev_get_drvdata(dev); struct phy_device *phy_dev = ndev->phydev; u32 val; - if ((tse_pcs_base) && (sgmii_adapter_base)) + if (sgmii_adapter_base) writew(SGMII_ADAPTER_DISABLE, sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); @@ -93,8 +89,11 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) writel(val, splitter_base + EMAC_SPLITTER_CTRL_REG); } - if (tse_pcs_base && sgmii_adapter_base) + if (phy_dev && sgmii_adapter_base) { + writew(SGMII_ADAPTER_ENABLE, + sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); tse_pcs_fix_mac_speed(&dwmac->pcs, phy_dev, speed); + } } static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device *dev) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 22fea0f67245..92d32940aff0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -71,9 +71,9 @@ static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) writel(value, ioaddr + PTP_TCR); /* wait for present system time initialize to complete */ - return readl_poll_timeout(ioaddr + PTP_TCR, value, + return readl_poll_timeout_atomic(ioaddr + PTP_TCR, value, !(value & PTP_TCR_TSINIT), - 10000, 100000); + 10, 100000); } static int config_addend(void __iomem *ioaddr, u32 addend) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5d29f336315b..11e1055e8260 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -431,8 +431,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->phylink_node = np; /* Get max speed of operation from device tree */ - if (of_property_read_u32(np, "max-speed", &plat->max_speed)) - plat->max_speed = -1; + of_property_read_u32(np, "max-speed", &plat->max_speed); plat->bus_id = of_alias_get_id(np, "ethernet"); if (plat->bus_id < 0) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 0f9c88dd1a4a..d5c1e5c4a508 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -433,8 +433,6 @@ struct axienet_local { struct net_device *ndev; struct device *dev; - struct device_node *phy_node; - struct phylink *phylink; struct phylink_config phylink_config; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index c7eb05e4a6bf..d6fc3f7acdf0 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2064,25 +2064,33 @@ static int axienet_probe(struct platform_device *pdev) if (ret) goto cleanup_clk; - lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); - if (lp->phy_node) { - ret = axienet_mdio_setup(lp); - if (ret) - dev_warn(&pdev->dev, - "error registering MDIO bus: %d\n", ret); - } + ret = axienet_mdio_setup(lp); + if (ret) + dev_warn(&pdev->dev, + "error registering MDIO bus: %d\n", ret); + if (lp->phy_mode == PHY_INTERFACE_MODE_SGMII || lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) { - if (!lp->phy_node) { - dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n"); + np = of_parse_phandle(pdev->dev.of_node, "pcs-handle", 0); + if (!np) { + /* Deprecated: Always use "pcs-handle" for pcs_phy. + * Falling back to "phy-handle" here is only for + * backward compatibility with old device trees. + */ + np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + } + if (!np) { + dev_err(&pdev->dev, "pcs-handle (preferred) or phy-handle required for 1000BaseX/SGMII\n"); ret = -EINVAL; goto cleanup_mdio; } - lp->pcs_phy = of_mdio_find_device(lp->phy_node); + lp->pcs_phy = of_mdio_find_device(np); if (!lp->pcs_phy) { ret = -EPROBE_DEFER; + of_node_put(np); goto cleanup_mdio; } + of_node_put(np); lp->pcs.ops = &axienet_pcs_ops; lp->pcs.poll = true; } @@ -2125,8 +2133,6 @@ cleanup_mdio: put_device(&lp->pcs_phy->dev); if (lp->mii_bus) axienet_mdio_teardown(lp); - of_node_put(lp->phy_node); - cleanup_clk: clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks); clk_disable_unprepare(lp->axi_clk); @@ -2155,9 +2161,6 @@ static int axienet_remove(struct platform_device *pdev) clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks); clk_disable_unprepare(lp->axi_clk); - of_node_put(lp->phy_node); - lp->phy_node = NULL; - free_netdev(ndev); return 0; diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 16105292b140..74e845fa2e07 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -1355,7 +1355,9 @@ static int rr_close(struct net_device *dev) rrpriv->fw_running = 0; + spin_unlock_irqrestore(&rrpriv->lock, flags); del_timer_sync(&rrpriv->timer); + spin_lock_irqsave(&rrpriv->lock, flags); writel(0, ®s->TxPi); writel(0, ®s->IpRxPi); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 069e8824c264..b00bc8173abe 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -460,8 +460,10 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) return RX_HANDLER_CONSUMED; *pskb = skb; eth = eth_hdr(skb); - if (macvlan_forward_source(skb, port, eth->h_source)) + if (macvlan_forward_source(skb, port, eth->h_source)) { + kfree_skb(skb); return RX_HANDLER_CONSUMED; + } src = macvlan_hash_lookup(port, eth->h_source); if (src && src->mode != MACVLAN_MODE_VEPA && src->mode != MACVLAN_MODE_BRIDGE) { @@ -480,8 +482,10 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) return RX_HANDLER_PASS; } - if (macvlan_forward_source(skb, port, eth->h_source)) + if (macvlan_forward_source(skb, port, eth->h_source)) { + kfree_skb(skb); return RX_HANDLER_CONSUMED; + } if (macvlan_passthru(port)) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index baf7afac7857..53846c6b56ca 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -553,7 +553,7 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev, hdr->source_slave = ((llsrc << 1) & 0xff) | 0x01; mhdr->ver = 0x01; - return 0; + return sizeof(struct mctp_i2c_hdr); } static int mctp_i2c_tx_thread(void *data) diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index 1becb1a731f6..1c1584fca632 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -43,6 +43,11 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, int rc; rc = fwnode_irq_get(child, 0); + /* Don't wait forever if the IRQ provider doesn't become available, + * just fall back to poll mode + */ + if (rc == -EPROBE_DEFER) + rc = driver_deferred_probe_check_state(&phy->mdio.dev); if (rc == -EPROBE_DEFER) return rc; diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index c483ba67c21f..582969751b4c 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -102,6 +102,9 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum) u32 val; int ret; + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + ret = mscc_miim_wait_pending(bus); if (ret) goto out; @@ -145,6 +148,9 @@ static int mscc_miim_write(struct mii_bus *bus, int mii_id, struct mscc_miim_dev *miim = bus->priv; int ret; + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + ret = mscc_miim_wait_pending(bus); if (ret < 0) goto out; diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index b6fea119fe13..2b7d0720720b 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -880,7 +880,7 @@ static int mv3310_read_status_copper(struct phy_device *phydev) cssr1 = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_CSSR1); if (cssr1 < 0) - return val; + return cssr1; /* If the link settings are not resolved, mark the link down */ if (!(cssr1 & MV_PCS_CSSR1_RESOLVED)) { diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 19b11e896460..fc53b71dc872 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -99,15 +99,6 @@ #define PTP_TIMESTAMP_EN_PDREQ_ BIT(2) #define PTP_TIMESTAMP_EN_PDRES_ BIT(3) -#define PTP_RX_LATENCY_1000 0x0224 -#define PTP_TX_LATENCY_1000 0x0225 - -#define PTP_RX_LATENCY_100 0x0222 -#define PTP_TX_LATENCY_100 0x0223 - -#define PTP_RX_LATENCY_10 0x0220 -#define PTP_TX_LATENCY_10 0x0221 - #define PTP_TX_PARSE_L2_ADDR_EN 0x0284 #define PTP_RX_PARSE_L2_ADDR_EN 0x0244 @@ -268,15 +259,6 @@ struct lan8814_ptp_rx_ts { u16 seq_id; }; -struct kszphy_latencies { - u16 rx_10; - u16 tx_10; - u16 rx_100; - u16 tx_100; - u16 rx_1000; - u16 tx_1000; -}; - struct kszphy_ptp_priv { struct mii_timestamper mii_ts; struct phy_device *phydev; @@ -296,7 +278,6 @@ struct kszphy_ptp_priv { struct kszphy_priv { struct kszphy_ptp_priv ptp_priv; - struct kszphy_latencies latencies; const struct kszphy_type *type; int led_mode; bool rmii_ref_clk_sel; @@ -304,14 +285,6 @@ struct kszphy_priv { u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; }; -static struct kszphy_latencies lan8814_latencies = { - .rx_10 = 0x22AA, - .tx_10 = 0x2E4A, - .rx_100 = 0x092A, - .tx_100 = 0x02C1, - .rx_1000 = 0x01AD, - .tx_1000 = 0x00C9, -}; static const struct kszphy_type ksz8021_type = { .led_mode_reg = MII_KSZPHY_CTRL_2, .has_broadcast_disable = true, @@ -2618,55 +2591,6 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev) return 0; } -static int lan8814_read_status(struct phy_device *phydev) -{ - struct kszphy_priv *priv = phydev->priv; - struct kszphy_latencies *latencies = &priv->latencies; - int err; - int regval; - - err = genphy_read_status(phydev); - if (err) - return err; - - switch (phydev->speed) { - case SPEED_1000: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_1000, - latencies->rx_1000); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_1000, - latencies->tx_1000); - break; - case SPEED_100: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_100, - latencies->rx_100); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_100, - latencies->tx_100); - break; - case SPEED_10: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_10, - latencies->rx_10); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_10, - latencies->tx_10); - break; - default: - break; - } - - /* Make sure the PHY is not broken. Read idle error count, - * and reset the PHY if it is maxed out. - */ - regval = phy_read(phydev, MII_STAT1000); - if ((regval & 0xFF) == 0xFF) { - phy_init_hw(phydev); - phydev->link = 0; - if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev)) - phydev->drv->config_intr(phydev); - return genphy_config_aneg(phydev); - } - - return 0; -} - static int lan8814_config_init(struct phy_device *phydev) { int val; @@ -2690,30 +2614,8 @@ static int lan8814_config_init(struct phy_device *phydev) return 0; } -static void lan8814_parse_latency(struct phy_device *phydev) -{ - const struct device_node *np = phydev->mdio.dev.of_node; - struct kszphy_priv *priv = phydev->priv; - struct kszphy_latencies *latency = &priv->latencies; - u32 val; - - if (!of_property_read_u32(np, "lan8814,latency_rx_10", &val)) - latency->rx_10 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_10", &val)) - latency->tx_10 = val; - if (!of_property_read_u32(np, "lan8814,latency_rx_100", &val)) - latency->rx_100 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_100", &val)) - latency->tx_100 = val; - if (!of_property_read_u32(np, "lan8814,latency_rx_1000", &val)) - latency->rx_1000 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_1000", &val)) - latency->tx_1000 = val; -} - static int lan8814_probe(struct phy_device *phydev) { - const struct device_node *np = phydev->mdio.dev.of_node; struct kszphy_priv *priv; u16 addr; int err; @@ -2724,13 +2626,10 @@ static int lan8814_probe(struct phy_device *phydev) priv->led_mode = -1; - priv->latencies = lan8814_latencies; - phydev->priv = priv; if (!IS_ENABLED(CONFIG_PTP_1588_CLOCK) || - !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING) || - of_property_read_bool(np, "lan8814,ignore-ts")) + !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) return 0; /* Strap-in value for PHY address, below register read gives starting @@ -2746,7 +2645,6 @@ static int lan8814_probe(struct phy_device *phydev) return err; } - lan8814_parse_latency(phydev); lan8814_ptp_init(phydev); return 0; @@ -2928,7 +2826,7 @@ static struct phy_driver ksphy_driver[] = { .config_init = lan8814_config_init, .probe = lan8814_probe, .soft_reset = genphy_soft_reset, - .read_status = lan8814_read_status, + .read_status = ksz9031_read_status, .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index 389df3f4293c..c2c0e361fd3d 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -706,7 +706,6 @@ static int lan87xx_read_status(struct phy_device *phydev) static int lan87xx_config_aneg(struct phy_device *phydev) { u16 ctl = 0; - int rc; switch (phydev->master_slave_set) { case MASTER_SLAVE_CFG_MASTER_FORCE: @@ -722,11 +721,7 @@ static int lan87xx_config_aneg(struct phy_device *phydev) return -EOPNOTSUPP; } - rc = phy_modify_changed(phydev, MII_CTRL1000, CTL1000_AS_MASTER, ctl); - if (rc == 1) - rc = genphy_soft_reset(phydev); - - return rc; + return phy_modify_changed(phydev, MII_CTRL1000, CTL1000_AS_MASTER, ctl); } static struct phy_driver microchip_t1_phy_driver[] = { @@ -748,6 +743,7 @@ static struct phy_driver microchip_t1_phy_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_LAN937X), .name = "Microchip LAN937x T1", + .flags = PHY_POLL_CABLE_TEST, .features = PHY_BASIC_T1_FEATURES, .config_init = lan87xx_config_init, .suspend = genphy_suspend, diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 88396ff99f03..6865d32270e5 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -469,7 +469,7 @@ static void sl_tx_timeout(struct net_device *dev, unsigned int txqueue) spin_lock(&sl->lock); if (netif_queue_stopped(dev)) { - if (!netif_running(dev)) + if (!netif_running(dev) || !sl->tty) goto out; /* May be we must check transmitter timeout here ? diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 276a0e42ca8e..dbe4c0a4be2c 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1124,7 +1124,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) /* NETIF_F_LLTX requires to do our own update of trans_start */ queue = netdev_get_tx_queue(dev, txq); - queue->trans_start = jiffies; + txq_trans_cond_update(queue); /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index ea06d10e1c21..ca409d450a29 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -1102,10 +1102,15 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (start_of_descs != desc_offset) goto err; - /* self check desc_offset from header*/ - if (desc_offset >= skb_len) + /* self check desc_offset from header and make sure that the + * bounds of the metadata array are inside the SKB + */ + if (pkt_count * 2 + desc_offset >= skb_len) goto err; + /* Packets must not overlap the metadata array */ + skb_trim(skb, desc_offset); + if (pkt_count == 0) goto err; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 1b5714926d81..eb0121a64d6d 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -320,7 +320,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); rcv = rcu_dereference(priv->peer); - if (unlikely(!rcv)) { + if (unlikely(!rcv) || !pskb_may_pull(skb, ETH_HLEN)) { kfree_skb(skb); goto drop; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 87838cbe38cf..cbba9d2e8f32 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1005,6 +1005,24 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, * xdp.data_meta were adjusted */ len = xdp.data_end - xdp.data + vi->hdr_len + metasize; + + /* recalculate headroom if xdp.data or xdp_data_meta + * were adjusted, note that offset should always point + * to the start of the reserved bytes for virtio_net + * header which are followed by xdp.data, that means + * that offset is equal to the headroom (when buf is + * starting at the beginning of the page, otherwise + * there is a base offset inside the page) but it's used + * with a different starting point (buf start) than + * xdp.data (buf start + vnet hdr size). If xdp.data or + * data_meta were adjusted by the xdp prog then the + * headroom size has changed and so has the offset, we + * can use data_hard_start, which points at buf start + + * vnet hdr size, to calculate the new headroom and use + * it later to compute buf start in page_to_skb() + */ + headroom = xdp.data - xdp.data_hard_start - metasize; + /* We can only create skb based on xdp_page. */ if (unlikely(xdp_page != page)) { rcu_read_unlock(); @@ -1012,7 +1030,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, head_skb = page_to_skb(vi, rq, xdp_page, offset, len, PAGE_SIZE, false, metasize, - VIRTIO_XDP_HEADROOM); + headroom); return head_skb; } break; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 85e362461d71..cfc30ce4c6e1 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1265,6 +1265,7 @@ static int vrf_prepare_mac_header(struct sk_buff *skb, eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. @@ -1294,9 +1295,9 @@ static int vrf_prepare_mac_header(struct sk_buff *skb, */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, - u16 proto) + u16 proto, struct net_device *orig_dev) { - if (skb_mac_header_was_set(skb)) + if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); @@ -1402,6 +1403,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { + struct net_device *orig_dev = skb->dev; + vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; @@ -1410,7 +1413,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, - ETH_P_IPV6); + ETH_P_IPV6, + orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); @@ -1440,6 +1444,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { + struct net_device *orig_dev = skb->dev; + skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; @@ -1460,7 +1466,8 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, if (!list_empty(&vrf_dev->ptype_all)) { int err; - err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP); + err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, + orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index de97ff98d36e..8a5e3a6d32d7 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -651,11 +651,11 @@ static int vxlan_fdb_append(struct vxlan_fdb *f, rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) - return -ENOBUFS; + return -ENOMEM; if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { kfree(rd); - return -ENOBUFS; + return -ENOMEM; } rd->remote_ip = *ip; diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 23d2954d9747..1e5672019922 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -349,7 +349,7 @@ static int __init cosa_init(void) } } else { cosa_major = register_chrdev(0, "cosa", &cosa_fops); - if (!cosa_major) { + if (cosa_major < 0) { pr_warn("unable to register chardev\n"); err = -EIO; goto out; diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 0fad1331303c..aa9a7a5970fd 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -19,6 +19,7 @@ #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/suspend.h> +#include <net/dst_metadata.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/ip_tunnels.h> @@ -167,7 +168,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) goto err_peer; } - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; __skb_queue_head_init(&packets); if (!skb_is_gso(skb)) { diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 63e1c2d783c5..73693c66cef1 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -1633,7 +1633,7 @@ static void ath10k_sdio_hif_power_down(struct ath10k *ar) return; } - ret = mmc_hw_reset(ar_sdio->func->card->host); + ret = mmc_hw_reset(ar_sdio->func->card); if (ret) ath10k_warn(ar, "unable to reset sdio: %d\n", ret); diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index d5b83f90d27a..e6b34b0d61bd 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -3136,6 +3136,20 @@ static void ath11k_mac_op_bss_info_changed(struct ieee80211_hw *hw, arvif->do_not_send_tmpl = true; else arvif->do_not_send_tmpl = false; + + if (vif->bss_conf.he_support) { + ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, + WMI_VDEV_PARAM_BA_MODE, + WMI_BA_MODE_BUFFER_SIZE_256); + if (ret) + ath11k_warn(ar->ab, + "failed to set BA BUFFER SIZE 256 for vdev: %d\n", + arvif->vdev_id); + else + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, + "Set BA BUFFER SIZE 256 for VDEV: %d\n", + arvif->vdev_id); + } } if (changed & (BSS_CHANGED_BEACON_INFO | BSS_CHANGED_BEACON)) { @@ -3171,14 +3185,6 @@ static void ath11k_mac_op_bss_info_changed(struct ieee80211_hw *hw, if (arvif->is_up && vif->bss_conf.he_support && vif->bss_conf.he_oper.params) { - ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, - WMI_VDEV_PARAM_BA_MODE, - WMI_BA_MODE_BUFFER_SIZE_256); - if (ret) - ath11k_warn(ar->ab, - "failed to set BA BUFFER SIZE 256 for vdev: %d\n", - arvif->vdev_id); - param_id = WMI_VDEV_PARAM_HEOPS_0_31; param_value = vif->bss_conf.he_oper.params; ret = ath11k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 98090e40e1cf..e2791d45f5f5 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -839,7 +839,7 @@ static bool ath9k_txq_list_has_key(struct list_head *txq_list, u32 keyix) continue; txinfo = IEEE80211_SKB_CB(bf->bf_mpdu); - fi = (struct ath_frame_info *)&txinfo->rate_driver_data[0]; + fi = (struct ath_frame_info *)&txinfo->status.status_driver_data[0]; if (fi->keyix == keyix) return true; } diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index d0caf1de2bde..db83cc4ba810 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -141,8 +141,8 @@ static struct ath_frame_info *get_frame_info(struct sk_buff *skb) { struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); BUILD_BUG_ON(sizeof(struct ath_frame_info) > - sizeof(tx_info->rate_driver_data)); - return (struct ath_frame_info *) &tx_info->rate_driver_data[0]; + sizeof(tx_info->status.status_driver_data)); + return (struct ath_frame_info *) &tx_info->status.status_driver_data[0]; } static void ath_send_bar(struct ath_atx_tid *tid, u16 seqno) @@ -2542,6 +2542,16 @@ skip_tx_complete: spin_unlock_irqrestore(&sc->tx.txbuflock, flags); } +static void ath_clear_tx_status(struct ieee80211_tx_info *tx_info) +{ + void *ptr = &tx_info->status; + + memset(ptr + sizeof(tx_info->status.rates), 0, + sizeof(tx_info->status) - + sizeof(tx_info->status.rates) - + sizeof(tx_info->status.status_driver_data)); +} + static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, struct ath_tx_status *ts, int nframes, int nbad, int txok) @@ -2553,6 +2563,8 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, struct ath_hw *ah = sc->sc_ah; u8 i, tx_rateindex; + ath_clear_tx_status(tx_info); + if (txok) tx_info->status.ack_signal = ts->ts_rssi; @@ -2567,6 +2579,13 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, tx_info->status.ampdu_len = nframes; tx_info->status.ampdu_ack_len = nframes - nbad; + tx_info->status.rates[tx_rateindex].count = ts->ts_longretry + 1; + + for (i = tx_rateindex + 1; i < hw->max_rates; i++) { + tx_info->status.rates[i].count = 0; + tx_info->status.rates[i].idx = -1; + } + if ((ts->ts_status & ATH9K_TXERR_FILT) == 0 && (tx_info->flags & IEEE80211_TX_CTL_NO_ACK) == 0) { /* @@ -2588,16 +2607,6 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf, tx_info->status.rates[tx_rateindex].count = hw->max_rate_tries; } - - for (i = tx_rateindex + 1; i < hw->max_rates; i++) { - tx_info->status.rates[i].count = 0; - tx_info->status.rates[i].idx = -1; - } - - tx_info->status.rates[tx_rateindex].count = ts->ts_longretry + 1; - - /* we report airtime in ath_tx_count_airtime(), don't report twice */ - tx_info->status.tx_time = 0; } static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index ba3c159111d3..212fbbe1cd7e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -557,7 +557,7 @@ enum brcmf_sdio_frmtype { BRCMF_SDIO_FT_SUB, }; -#define SDIOD_DRVSTR_KEY(chip, pmu) (((chip) << 16) | (pmu)) +#define SDIOD_DRVSTR_KEY(chip, pmu) (((unsigned int)(chip) << 16) | (pmu)) /* SDIO Pad drive strength to select value mappings */ struct sdiod_drive_str { @@ -4165,7 +4165,7 @@ static int brcmf_sdio_bus_reset(struct device *dev) /* reset the adapter */ sdio_claim_host(sdiodev->func1); - mmc_hw_reset(sdiodev->func1->card->host); + mmc_hw_reset(sdiodev->func1->card); sdio_release_host(sdiodev->func1); brcmf_bus_change_state(sdiodev->bus_if, BRCMF_BUS_DOWN); diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index bde9e4bbfffe..4f3238d2a171 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -2639,7 +2639,7 @@ static void mwifiex_sdio_card_reset_work(struct mwifiex_adapter *adapter) /* Run a HW reset of the SDIO interface. */ sdio_claim_host(func); - ret = mmc_hw_reset(func->card->host); + ret = mmc_hw_reset(func->card); sdio_release_host(func); switch (ret) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c index 8a22ee581674..df85ebc6e1df 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c @@ -80,7 +80,7 @@ mt76x2e_probe(struct pci_dev *pdev, const struct pci_device_id *id) mt76_rmw_field(dev, 0x15a10, 0x1f << 16, 0x9); /* RG_SSUSB_G1_CDR_BIC_LTR = 0xf */ - mt76_rmw_field(dev, 0x15a0c, 0xf << 28, 0xf); + mt76_rmw_field(dev, 0x15a0c, 0xfU << 28, 0xf); /* RG_SSUSB_CDR_BR_PE1D = 0x3 */ mt76_rmw_field(dev, 0x15c58, 0x3 << 6, 0x3); diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index 72fc41ac83c0..9140b0163474 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -146,7 +146,7 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue) * To guarantee that the SDIO card is power cycled, as required to make * the FW programming to succeed, let's do a brute force HW reset. */ - mmc_hw_reset(card->host); + mmc_hw_reset(card); sdio_enable_func(func); sdio_release_host(func); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index efb85c6d8e2d..e1846d04817f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -366,7 +366,7 @@ static inline void nvme_end_req(struct request *req) { blk_status_t status = nvme_error_status(nvme_req(req)->status); - if (unlikely(nvme_req(req)->status != NVME_SC_SUCCESS)) + if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) nvme_log_error(req); nvme_end_req_zoned(req); nvme_trace_bio_complete(req); @@ -1015,6 +1015,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, goto out; } + req->rq_flags |= RQF_QUIET; ret = nvme_execute_rq(req, at_head); if (result && ret >= 0) *result = nvme_req(req)->result; @@ -1287,6 +1288,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_EUI64_LEN; memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN); return NVME_NIDT_EUI64_LEN; case NVME_NIDT_NGUID: @@ -1295,6 +1298,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_NGUID_LEN; memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN); return NVME_NIDT_NGUID_LEN; case NVME_NIDT_UUID: @@ -1303,6 +1308,8 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids, warn_str, cur->nidl); return -1; } + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) + return NVME_NIDT_UUID_LEN; uuid_copy(&ids->uuid, data + sizeof(*cur)); return NVME_NIDT_UUID_LEN; case NVME_NIDT_CSI: @@ -1399,12 +1406,18 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, if ((*id)->ncap == 0) /* namespace not allocated or attached */ goto out_free_id; - if (ctrl->vs >= NVME_VS(1, 1, 0) && - !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) - memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); - if (ctrl->vs >= NVME_VS(1, 2, 0) && - !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) - memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); + + if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) { + dev_info(ctrl->device, + "Ignoring bogus Namespace Identifiers\n"); + } else { + if (ctrl->vs >= NVME_VS(1, 1, 0) && + !memchr_inv(ids->eui64, 0, sizeof(ids->eui64))) + memcpy(ids->eui64, (*id)->eui64, sizeof(ids->eui64)); + if (ctrl->vs >= NVME_VS(1, 2, 0) && + !memchr_inv(ids->nguid, 0, sizeof(ids->nguid))) + memcpy(ids->nguid, (*id)->nguid, sizeof(ids->nguid)); + } return 0; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 1393bbf82d71..a2b53ca63335 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -144,6 +144,11 @@ enum nvme_quirks { * encoding the generation sequence number. */ NVME_QUIRK_SKIP_CID_GEN = (1 << 17), + + /* + * Reports garbage in the namespace identifiers (eui64, nguid, uuid). + */ + NVME_QUIRK_BOGUS_NID = (1 << 18), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d817ca17463e..3aacf1c0d5a5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3409,7 +3409,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS | - NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + NVME_QUIRK_DISABLE_WRITE_ZEROES | + NVME_QUIRK_BOGUS_NID, }, + { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x126f, 0x2263), /* Silicon Motion unidentified */ .driver_data = NVME_QUIRK_NO_NS_DESC_LIST, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ @@ -3447,6 +3450,10 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x1e4B, 0x1002), /* MAXIO MAP1002 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4B, 0x1202), /* MAXIO MAP1202 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 558b35aba610..d270a204324e 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3407,6 +3407,15 @@ static int hv_pci_probe(struct hv_device *hdev, hbus->bridge->domain_nr = dom; #ifdef CONFIG_X86 hbus->sysdata.domain = dom; +#elif defined(CONFIG_ARM64) + /* + * Set the PCI bus parent to be the corresponding VMbus + * device. Then the VMbus device will be assigned as the + * ACPI companion in pcibios_root_bridge_prepare() and + * pci_dma_configure() will propagate device coherence + * information to devices created on the bus. + */ + hbus->sysdata.parent = hdev->device.parent; #endif hbus->hdev = hdev; diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index afdcb91601d2..1e2d69453771 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -187,7 +187,7 @@ source "drivers/perf/hisilicon/Kconfig" config MARVELL_CN10K_DDR_PMU tristate "Enable MARVELL CN10K DRAM Subsystem(DSS) PMU Support" - depends on ARM64 || (COMPILE_TEST && 64BIT) + depends on ARCH_THUNDER || (COMPILE_TEST && 64BIT) help Enable perf support for Marvell DDR Performance monitoring event on CN10K platform. diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 9694370651fa..59d3980b8ca2 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -400,6 +400,9 @@ validate_group(struct perf_event *event) if (!validate_event(event->pmu, &fake_pmu, leader)) return -EINVAL; + if (event == leader) + return 0; + for_each_sibling_event(sibling, leader) { if (!validate_event(event->pmu, &fake_pmu, sibling)) return -EINVAL; @@ -489,12 +492,7 @@ __hw_perf_event_init(struct perf_event *event) local64_set(&hwc->period_left, hwc->sample_period); } - if (event->group_leader != event) { - if (validate_group(event) != 0) - return -EINVAL; - } - - return 0; + return validate_group(event); } static int armpmu_event_init(struct perf_event *event) diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 94ebc1ecace7..b1b2a55de77f 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -29,7 +29,7 @@ #define CNTL_OVER_MASK 0xFFFFFFFE #define CNTL_CSV_SHIFT 24 -#define CNTL_CSV_MASK (0xFF << CNTL_CSV_SHIFT) +#define CNTL_CSV_MASK (0xFFU << CNTL_CSV_SHIFT) #define EVENT_CYCLES_ID 0 #define EVENT_CYCLES_COUNTER 0 diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c index 7640491aab12..30234c261b05 100644 --- a/drivers/perf/qcom_l2_pmu.c +++ b/drivers/perf/qcom_l2_pmu.c @@ -736,7 +736,7 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( { u64 mpidr; int cpu_cluster_id; - struct cluster_pmu *cluster = NULL; + struct cluster_pmu *cluster; /* * This assumes that the cluster_id is in MPIDR[aff1] for @@ -758,10 +758,10 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( cluster->cluster_id); cpumask_set_cpu(cpu, &cluster->cluster_cpus); *per_cpu_ptr(l2cache_pmu->pmu_cluster, cpu) = cluster; - break; + return cluster; } - return cluster; + return NULL; } static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) diff --git a/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c b/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c index 5b471ab80fe2..54d65a6f0fcc 100644 --- a/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c +++ b/drivers/phy/amlogic/phy-meson-g12a-usb3-pcie.c @@ -414,19 +414,19 @@ static int phy_g12a_usb3_pcie_probe(struct platform_device *pdev) ret = clk_prepare_enable(priv->clk_ref); if (ret) - goto err_disable_clk_ref; + return ret; priv->reset = devm_reset_control_array_get_exclusive(dev); - if (IS_ERR(priv->reset)) - return PTR_ERR(priv->reset); + if (IS_ERR(priv->reset)) { + ret = PTR_ERR(priv->reset); + goto err_disable_clk_ref; + } priv->phy = devm_phy_create(dev, np, &phy_g12a_usb3_pcie_ops); if (IS_ERR(priv->phy)) { ret = PTR_ERR(priv->phy); - if (ret != -EPROBE_DEFER) - dev_err(dev, "failed to create PHY\n"); - - return ret; + dev_err_probe(dev, ret, "failed to create PHY\n"); + goto err_disable_clk_ref; } phy_set_drvdata(priv->phy, priv); @@ -434,8 +434,12 @@ static int phy_g12a_usb3_pcie_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, phy_g12a_usb3_pcie_xlate); + if (IS_ERR(phy_provider)) { + ret = PTR_ERR(phy_provider); + goto err_disable_clk_ref; + } - return PTR_ERR_OR_ZERO(phy_provider); + return 0; err_disable_clk_ref: clk_disable_unprepare(priv->clk_ref); diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 5172971f4c36..3cd4d51c247c 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -629,7 +629,8 @@ idle: cleanup: if (error < 0) phy_mdm6600_device_power_off(ddata); - + pm_runtime_disable(ddata->dev); + pm_runtime_dont_use_autosuspend(ddata->dev); return error; } diff --git a/drivers/phy/samsung/phy-exynos5250-sata.c b/drivers/phy/samsung/phy-exynos5250-sata.c index 9ec234243f7c..595adba5fb8f 100644 --- a/drivers/phy/samsung/phy-exynos5250-sata.c +++ b/drivers/phy/samsung/phy-exynos5250-sata.c @@ -187,6 +187,7 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) return -EINVAL; sata_phy->client = of_find_i2c_device_by_node(node); + of_node_put(node); if (!sata_phy->client) return -EPROBE_DEFER; @@ -195,20 +196,21 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) sata_phy->phyclk = devm_clk_get(dev, "sata_phyctrl"); if (IS_ERR(sata_phy->phyclk)) { dev_err(dev, "failed to get clk for PHY\n"); - return PTR_ERR(sata_phy->phyclk); + ret = PTR_ERR(sata_phy->phyclk); + goto put_dev; } ret = clk_prepare_enable(sata_phy->phyclk); if (ret < 0) { dev_err(dev, "failed to enable source clk\n"); - return ret; + goto put_dev; } sata_phy->phy = devm_phy_create(dev, NULL, &exynos_sata_phy_ops); if (IS_ERR(sata_phy->phy)) { - clk_disable_unprepare(sata_phy->phyclk); dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(sata_phy->phy); + ret = PTR_ERR(sata_phy->phy); + goto clk_disable; } phy_set_drvdata(sata_phy->phy, sata_phy); @@ -216,11 +218,18 @@ static int exynos_sata_phy_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); if (IS_ERR(phy_provider)) { - clk_disable_unprepare(sata_phy->phyclk); - return PTR_ERR(phy_provider); + ret = PTR_ERR(phy_provider); + goto clk_disable; } return 0; + +clk_disable: + clk_disable_unprepare(sata_phy->phyclk); +put_dev: + put_device(&sata_phy->client->dev); + + return ret; } static const struct of_device_id exynos_sata_phy_of_match[] = { diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c index c1211c4f863c..0be727bb9f79 100644 --- a/drivers/phy/ti/phy-am654-serdes.c +++ b/drivers/phy/ti/phy-am654-serdes.c @@ -838,7 +838,7 @@ static int serdes_am654_probe(struct platform_device *pdev) clk_err: of_clk_del_provider(node); - + pm_runtime_disable(dev); return ret; } diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index 3a505fe5715a..31a775877f6e 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -215,7 +215,7 @@ static int omap_usb2_enable_clocks(struct omap_usb *phy) return 0; err1: - clk_disable(phy->wkupclk); + clk_disable_unprepare(phy->wkupclk); err0: return ret; diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c index 2cbc91e535d4..f502c36f3be5 100644 --- a/drivers/phy/ti/phy-ti-pipe3.c +++ b/drivers/phy/ti/phy-ti-pipe3.c @@ -696,6 +696,7 @@ static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) } control_pdev = of_find_device_by_node(control_node); + of_node_put(control_node); if (!control_pdev) { dev_err(dev, "Failed to get control device\n"); return -EINVAL; diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c index a0cdbcadf09e..c3ab4b69ea68 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -155,7 +155,7 @@ static int tusb1210_set_mode(struct phy *phy, enum phy_mode mode, int submode) } #ifdef CONFIG_POWER_SUPPLY -const char * const tusb1210_chg_det_states[] = { +static const char * const tusb1210_chg_det_states[] = { "CHG_DET_CONNECTING", "CHG_DET_START_DET", "CHG_DET_READ_DET", @@ -537,12 +537,18 @@ static int tusb1210_probe(struct ulpi *ulpi) tusb1210_probe_charger_detect(tusb); tusb->phy = ulpi_phy_create(ulpi, &phy_ops); - if (IS_ERR(tusb->phy)) - return PTR_ERR(tusb->phy); + if (IS_ERR(tusb->phy)) { + ret = PTR_ERR(tusb->phy); + goto err_remove_charger; + } phy_set_drvdata(tusb->phy, tusb); ulpi_set_drvdata(ulpi, tusb); return 0; + +err_remove_charger: + tusb1210_remove_charger_detect(tusb); + return ret; } static void tusb1210_remove(struct ulpi *ulpi) diff --git a/drivers/pinctrl/intel/pinctrl-alderlake.c b/drivers/pinctrl/intel/pinctrl-alderlake.c index 32ba50efbceb..62dbd1e67513 100644 --- a/drivers/pinctrl/intel/pinctrl-alderlake.c +++ b/drivers/pinctrl/intel/pinctrl-alderlake.c @@ -14,11 +14,17 @@ #include "pinctrl-intel.h" -#define ADL_PAD_OWN 0x0a0 -#define ADL_PADCFGLOCK 0x110 -#define ADL_HOSTSW_OWN 0x150 -#define ADL_GPI_IS 0x200 -#define ADL_GPI_IE 0x220 +#define ADL_N_PAD_OWN 0x020 +#define ADL_N_PADCFGLOCK 0x080 +#define ADL_N_HOSTSW_OWN 0x0b0 +#define ADL_N_GPI_IS 0x100 +#define ADL_N_GPI_IE 0x120 + +#define ADL_S_PAD_OWN 0x0a0 +#define ADL_S_PADCFGLOCK 0x110 +#define ADL_S_HOSTSW_OWN 0x150 +#define ADL_S_GPI_IS 0x200 +#define ADL_S_GPI_IE 0x220 #define ADL_GPP(r, s, e, g) \ { \ @@ -28,14 +34,28 @@ .gpio_base = (g), \ } -#define ADL_COMMUNITY(b, s, e, g) \ +#define ADL_N_COMMUNITY(b, s, e, g) \ + { \ + .barno = (b), \ + .padown_offset = ADL_N_PAD_OWN, \ + .padcfglock_offset = ADL_N_PADCFGLOCK, \ + .hostown_offset = ADL_N_HOSTSW_OWN, \ + .is_offset = ADL_N_GPI_IS, \ + .ie_offset = ADL_N_GPI_IE, \ + .pin_base = (s), \ + .npins = ((e) - (s) + 1), \ + .gpps = (g), \ + .ngpps = ARRAY_SIZE(g), \ + } + +#define ADL_S_COMMUNITY(b, s, e, g) \ { \ .barno = (b), \ - .padown_offset = ADL_PAD_OWN, \ - .padcfglock_offset = ADL_PADCFGLOCK, \ - .hostown_offset = ADL_HOSTSW_OWN, \ - .is_offset = ADL_GPI_IS, \ - .ie_offset = ADL_GPI_IE, \ + .padown_offset = ADL_S_PAD_OWN, \ + .padcfglock_offset = ADL_S_PADCFGLOCK, \ + .hostown_offset = ADL_S_HOSTSW_OWN, \ + .is_offset = ADL_S_GPI_IS, \ + .ie_offset = ADL_S_GPI_IE, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ .gpps = (g), \ @@ -342,10 +362,10 @@ static const struct intel_padgroup adln_community5_gpps[] = { }; static const struct intel_community adln_communities[] = { - ADL_COMMUNITY(0, 0, 66, adln_community0_gpps), - ADL_COMMUNITY(1, 67, 168, adln_community1_gpps), - ADL_COMMUNITY(2, 169, 248, adln_community4_gpps), - ADL_COMMUNITY(3, 249, 256, adln_community5_gpps), + ADL_N_COMMUNITY(0, 0, 66, adln_community0_gpps), + ADL_N_COMMUNITY(1, 67, 168, adln_community1_gpps), + ADL_N_COMMUNITY(2, 169, 248, adln_community4_gpps), + ADL_N_COMMUNITY(3, 249, 256, adln_community5_gpps), }; static const struct intel_pinctrl_soc_data adln_soc_data = { @@ -713,11 +733,11 @@ static const struct intel_padgroup adls_community5_gpps[] = { }; static const struct intel_community adls_communities[] = { - ADL_COMMUNITY(0, 0, 94, adls_community0_gpps), - ADL_COMMUNITY(1, 95, 150, adls_community1_gpps), - ADL_COMMUNITY(2, 151, 199, adls_community3_gpps), - ADL_COMMUNITY(3, 200, 269, adls_community4_gpps), - ADL_COMMUNITY(4, 270, 303, adls_community5_gpps), + ADL_S_COMMUNITY(0, 0, 94, adls_community0_gpps), + ADL_S_COMMUNITY(1, 95, 150, adls_community1_gpps), + ADL_S_COMMUNITY(2, 151, 199, adls_community3_gpps), + ADL_S_COMMUNITY(3, 200, 269, adls_community4_gpps), + ADL_S_COMMUNITY(4, 270, 303, adls_community5_gpps), }; static const struct intel_pinctrl_soc_data adls_soc_data = { diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index 8dca1ef04965..40accd110c3d 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -30,6 +30,7 @@ config PINCTRL_MTK_MOORE select GENERIC_PINMUX_FUNCTIONS select GPIOLIB select OF_GPIO + select EINT_MTK select PINCTRL_MTK_V2 config PINCTRL_MTK_PARIS diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index 8d271c6b0ca4..5de691c630b4 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -1374,10 +1374,10 @@ static int pistachio_gpio_register(struct pistachio_pinctrl *pctl) } irq = irq_of_parse_and_map(child, 0); - if (irq < 0) { - dev_err(pctl->dev, "No IRQ for bank %u: %d\n", i, irq); + if (!irq) { + dev_err(pctl->dev, "No IRQ for bank %u\n", i); of_node_put(child); - ret = irq; + ret = -EINVAL; goto err; } diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index a1b598b86aa9..2cb79e649fcf 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -457,95 +457,110 @@ static struct rockchip_mux_recalced_data rk3128_mux_recalced_data[] = { static struct rockchip_mux_recalced_data rk3308_mux_recalced_data[] = { { + /* gpio1b6_sel */ .num = 1, .pin = 14, .reg = 0x28, .bit = 12, .mask = 0xf }, { + /* gpio1b7_sel */ .num = 1, .pin = 15, .reg = 0x2c, .bit = 0, .mask = 0x3 }, { + /* gpio1c2_sel */ .num = 1, .pin = 18, .reg = 0x30, .bit = 4, .mask = 0xf }, { + /* gpio1c3_sel */ .num = 1, .pin = 19, .reg = 0x30, .bit = 8, .mask = 0xf }, { + /* gpio1c4_sel */ .num = 1, .pin = 20, .reg = 0x30, .bit = 12, .mask = 0xf }, { + /* gpio1c5_sel */ .num = 1, .pin = 21, .reg = 0x34, .bit = 0, .mask = 0xf }, { + /* gpio1c6_sel */ .num = 1, .pin = 22, .reg = 0x34, .bit = 4, .mask = 0xf }, { + /* gpio1c7_sel */ .num = 1, .pin = 23, .reg = 0x34, .bit = 8, .mask = 0xf }, { - .num = 3, - .pin = 12, - .reg = 0x68, - .bit = 8, - .mask = 0xf - }, { - .num = 3, - .pin = 13, - .reg = 0x68, - .bit = 12, - .mask = 0xf - }, { + /* gpio2a2_sel */ .num = 2, .pin = 2, - .reg = 0x608, - .bit = 0, - .mask = 0x7 + .reg = 0x40, + .bit = 4, + .mask = 0x3 }, { + /* gpio2a3_sel */ .num = 2, .pin = 3, - .reg = 0x608, - .bit = 4, - .mask = 0x7 + .reg = 0x40, + .bit = 6, + .mask = 0x3 }, { + /* gpio2c0_sel */ .num = 2, .pin = 16, - .reg = 0x610, - .bit = 8, - .mask = 0x7 + .reg = 0x50, + .bit = 0, + .mask = 0x3 }, { + /* gpio3b2_sel */ .num = 3, .pin = 10, - .reg = 0x610, - .bit = 0, - .mask = 0x7 + .reg = 0x68, + .bit = 4, + .mask = 0x3 }, { + /* gpio3b3_sel */ .num = 3, .pin = 11, - .reg = 0x610, - .bit = 4, - .mask = 0x7 + .reg = 0x68, + .bit = 6, + .mask = 0x3 + }, { + /* gpio3b4_sel */ + .num = 3, + .pin = 12, + .reg = 0x68, + .bit = 8, + .mask = 0xf + }, { + /* gpio3b5_sel */ + .num = 3, + .pin = 13, + .reg = 0x68, + .bit = 12, + .mask = 0xf }, }; diff --git a/drivers/pinctrl/qcom/pinctrl-sm6350.c b/drivers/pinctrl/qcom/pinctrl-sm6350.c index 4d37b817b232..a91a86628f2f 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm6350.c +++ b/drivers/pinctrl/qcom/pinctrl-sm6350.c @@ -264,14 +264,14 @@ static const struct pinctrl_pin_desc sm6350_pins[] = { PINCTRL_PIN(153, "GPIO_153"), PINCTRL_PIN(154, "GPIO_154"), PINCTRL_PIN(155, "GPIO_155"), - PINCTRL_PIN(156, "SDC1_RCLK"), - PINCTRL_PIN(157, "SDC1_CLK"), - PINCTRL_PIN(158, "SDC1_CMD"), - PINCTRL_PIN(159, "SDC1_DATA"), - PINCTRL_PIN(160, "SDC2_CLK"), - PINCTRL_PIN(161, "SDC2_CMD"), - PINCTRL_PIN(162, "SDC2_DATA"), - PINCTRL_PIN(163, "UFS_RESET"), + PINCTRL_PIN(156, "UFS_RESET"), + PINCTRL_PIN(157, "SDC1_RCLK"), + PINCTRL_PIN(158, "SDC1_CLK"), + PINCTRL_PIN(159, "SDC1_CMD"), + PINCTRL_PIN(160, "SDC1_DATA"), + PINCTRL_PIN(161, "SDC2_CLK"), + PINCTRL_PIN(162, "SDC2_CMD"), + PINCTRL_PIN(163, "SDC2_DATA"), }; #define DECLARE_MSM_GPIO_PINS(pin) \ diff --git a/drivers/pinctrl/samsung/Kconfig b/drivers/pinctrl/samsung/Kconfig index dfd805e76862..7b0576f71376 100644 --- a/drivers/pinctrl/samsung/Kconfig +++ b/drivers/pinctrl/samsung/Kconfig @@ -4,14 +4,13 @@ # config PINCTRL_SAMSUNG bool - depends on OF_GPIO + select GPIOLIB select PINMUX select PINCONF config PINCTRL_EXYNOS bool "Pinctrl common driver part for Samsung Exynos SoCs" - depends on OF_GPIO - depends on ARCH_EXYNOS || ARCH_S5PV210 || COMPILE_TEST + depends on ARCH_EXYNOS || ARCH_S5PV210 || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG select PINCTRL_EXYNOS_ARM if ARM && (ARCH_EXYNOS || ARCH_S5PV210) select PINCTRL_EXYNOS_ARM64 if ARM64 && ARCH_EXYNOS @@ -26,12 +25,10 @@ config PINCTRL_EXYNOS_ARM64 config PINCTRL_S3C24XX bool "Samsung S3C24XX SoC pinctrl driver" - depends on OF_GPIO - depends on ARCH_S3C24XX || COMPILE_TEST + depends on ARCH_S3C24XX || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG config PINCTRL_S3C64XX bool "Samsung S3C64XX SoC pinctrl driver" - depends on OF_GPIO - depends on ARCH_S3C64XX || COMPILE_TEST + depends on ARCH_S3C64XX || (COMPILE_TEST && OF) select PINCTRL_SAMSUNG diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c index d291819c2f77..cb965cf93705 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c @@ -770,7 +770,7 @@ static const struct samsung_pin_bank_data fsd_pin_banks2[] __initconst = { EXYNOS850_PIN_BANK_EINTN(3, 0x00, "gpq0"), }; -const struct samsung_pin_ctrl fsd_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl fsd_pin_ctrl[] __initconst = { { /* pin-controller instance 0 FSYS0 data */ .pin_banks = fsd_pin_banks0, diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index 9ed764731570..f7c9459f6628 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -225,6 +225,13 @@ static void stm32_gpio_free(struct gpio_chip *chip, unsigned offset) pinctrl_gpio_free(chip->base + offset); } +static int stm32_gpio_get_noclk(struct gpio_chip *chip, unsigned int offset) +{ + struct stm32_gpio_bank *bank = gpiochip_get_data(chip); + + return !!(readl_relaxed(bank->base + STM32_GPIO_IDR) & BIT(offset)); +} + static int stm32_gpio_get(struct gpio_chip *chip, unsigned offset) { struct stm32_gpio_bank *bank = gpiochip_get_data(chip); @@ -232,7 +239,7 @@ static int stm32_gpio_get(struct gpio_chip *chip, unsigned offset) clk_enable(bank->clk); - ret = !!(readl_relaxed(bank->base + STM32_GPIO_IDR) & BIT(offset)); + ret = stm32_gpio_get_noclk(chip, offset); clk_disable(bank->clk); @@ -311,8 +318,12 @@ static void stm32_gpio_irq_trigger(struct irq_data *d) struct stm32_gpio_bank *bank = d->domain->host_data; int level; + /* Do not access the GPIO if this is not LEVEL triggered IRQ. */ + if (!(bank->irq_type[d->hwirq] & IRQ_TYPE_LEVEL_MASK)) + return; + /* If level interrupt type then retrig */ - level = stm32_gpio_get(&bank->gpio_chip, d->hwirq); + level = stm32_gpio_get_noclk(&bank->gpio_chip, d->hwirq); if ((level == 0 && bank->irq_type[d->hwirq] == IRQ_TYPE_LEVEL_LOW) || (level == 1 && bank->irq_type[d->hwirq] == IRQ_TYPE_LEVEL_HIGH)) irq_chip_retrigger_hierarchy(d); @@ -354,6 +365,7 @@ static int stm32_gpio_irq_request_resources(struct irq_data *irq_data) { struct stm32_gpio_bank *bank = irq_data->domain->host_data; struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent); + unsigned long flags; int ret; ret = stm32_gpio_direction_input(&bank->gpio_chip, irq_data->hwirq); @@ -367,6 +379,10 @@ static int stm32_gpio_irq_request_resources(struct irq_data *irq_data) return ret; } + flags = irqd_get_trigger_type(irq_data); + if (flags & IRQ_TYPE_LEVEL_MASK) + clk_enable(bank->clk); + return 0; } @@ -374,6 +390,9 @@ static void stm32_gpio_irq_release_resources(struct irq_data *irq_data) { struct stm32_gpio_bank *bank = irq_data->domain->host_data; + if (bank->irq_type[irq_data->hwirq] & IRQ_TYPE_LEVEL_MASK) + clk_disable(bank->clk); + gpiochip_unlock_as_irq(&bank->gpio_chip, irq_data->hwirq); } diff --git a/drivers/pinctrl/sunplus/sppctl_sp7021.c b/drivers/pinctrl/sunplus/sppctl_sp7021.c index 9748345b9298..cd657760a644 100644 --- a/drivers/pinctrl/sunplus/sppctl_sp7021.c +++ b/drivers/pinctrl/sunplus/sppctl_sp7021.c @@ -419,7 +419,15 @@ static const struct sppctl_grp sp7021grps_prbp[] = { EGRP("PROBE_PORT2", 2, pins_prp2), }; +/* + * Due to compatible reason, the first valid item should start at the third + * position of the array. Please keep the first two items of the table + * no use (dummy). + */ const struct sppctl_func sppctl_list_funcs[] = { + FNCN("", pinmux_type_fpmx, 0x00, 0, 0), + FNCN("", pinmux_type_fpmx, 0x00, 0, 0), + FNCN("L2SW_CLK_OUT", pinmux_type_fpmx, 0x00, 0, 7), FNCN("L2SW_MAC_SMI_MDC", pinmux_type_fpmx, 0x00, 8, 7), FNCN("L2SW_LED_FLASH0", pinmux_type_fpmx, 0x01, 0, 7), diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c index 6b8b3ab8db48..3463629f8764 100644 --- a/drivers/platform/x86/acerhdf.c +++ b/drivers/platform/x86/acerhdf.c @@ -584,21 +584,6 @@ static struct platform_driver acerhdf_driver = { .remove = acerhdf_remove, }; -/* checks if str begins with start */ -static int str_starts_with(const char *str, const char *start) -{ - unsigned long str_len = 0, start_len = 0; - - str_len = strlen(str); - start_len = strlen(start); - - if (str_len >= start_len && - !strncmp(str, start, start_len)) - return 1; - - return 0; -} - /* check hardware */ static int __init acerhdf_check_hardware(void) { @@ -651,9 +636,9 @@ static int __init acerhdf_check_hardware(void) * check if actual hardware BIOS vendor, product and version * IDs start with the strings of BIOS table entry */ - if (str_starts_with(vendor, bt->vendor) && - str_starts_with(product, bt->product) && - str_starts_with(version, bt->version)) { + if (strstarts(vendor, bt->vendor) && + strstarts(product, bt->product) && + strstarts(version, bt->version)) { found = 1; break; } diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index e9d0dbbb2887..fa4123dbdf7f 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -160,8 +160,10 @@ MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism"); static struct amd_pmc_dev pmc; static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret); -static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data); static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf); +#ifdef CONFIG_SUSPEND +static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data); +#endif static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset) { @@ -325,6 +327,7 @@ static int get_metrics_table(struct amd_pmc_dev *pdev, struct smu_metrics *table return 0; } +#ifdef CONFIG_SUSPEND static void amd_pmc_validate_deepest(struct amd_pmc_dev *pdev) { struct smu_metrics table; @@ -338,6 +341,7 @@ static void amd_pmc_validate_deepest(struct amd_pmc_dev *pdev) dev_dbg(pdev->dev, "Last suspend in deepest state for %lluus\n", table.timein_s0i3_lastcapture); } +#endif #ifdef CONFIG_DEBUG_FS static int smu_fw_info_show(struct seq_file *s, void *unused) @@ -569,6 +573,7 @@ out_unlock: return rc; } +#ifdef CONFIG_SUSPEND static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) { switch (dev->cpu_id) { @@ -694,6 +699,7 @@ static struct acpi_s2idle_dev_ops amd_pmc_s2idle_dev_ops = { .prepare = amd_pmc_s2idle_prepare, .restore = amd_pmc_s2idle_restore, }; +#endif static const struct pci_device_id pmc_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) }, @@ -733,6 +739,7 @@ static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) return 0; } +#ifdef CONFIG_SUSPEND static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data) { int err; @@ -753,6 +760,7 @@ static int amd_pmc_write_stb(struct amd_pmc_dev *dev, u32 data) return 0; } +#endif static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf) { @@ -859,9 +867,11 @@ static int amd_pmc_probe(struct platform_device *pdev) amd_pmc_get_smu_version(dev); platform_set_drvdata(pdev, dev); +#ifdef CONFIG_SUSPEND err = acpi_register_lps0_dev(&amd_pmc_s2idle_dev_ops); if (err) dev_warn(dev->dev, "failed to register LPS0 sleep handler, expect increased power consumption\n"); +#endif amd_pmc_dbgfs_register(dev); return 0; @@ -875,7 +885,9 @@ static int amd_pmc_remove(struct platform_device *pdev) { struct amd_pmc_dev *dev = platform_get_drvdata(pdev); +#ifdef CONFIG_SUSPEND acpi_unregister_lps0_dev(&amd_pmc_s2idle_dev_ops); +#endif amd_pmc_dbgfs_unregister(dev); pci_dev_put(dev->rdev); mutex_destroy(&dev->lock); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 2104a2621e50..0e7fbed8a50d 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -371,10 +371,14 @@ static int asus_wmi_evaluate_method_buf(u32 method_id, switch (obj->type) { case ACPI_TYPE_BUFFER: - if (obj->buffer.length > size) + if (obj->buffer.length > size) { err = -ENOSPC; - if (obj->buffer.length == 0) + break; + } + if (obj->buffer.length == 0) { err = -ENODATA; + break; + } memcpy(ret_buffer, obj->buffer.pointer, obj->buffer.length); break; @@ -2223,9 +2227,10 @@ static int fan_curve_check_present(struct asus_wmi *asus, bool *available, err = fan_curve_get_factory_default(asus, fan_dev); if (err) { - if (err == -ENODEV || err == -ENODATA) - return 0; - return err; + pr_debug("fan_curve_get_factory_default(0x%08x) failed: %d\n", + fan_dev, err); + /* Don't cause probe to fail on devices without fan-curves */ + return 0; } *available = true; diff --git a/drivers/platform/x86/barco-p50-gpio.c b/drivers/platform/x86/barco-p50-gpio.c index f5c72e33f9ae..05534287bc26 100644 --- a/drivers/platform/x86/barco-p50-gpio.c +++ b/drivers/platform/x86/barco-p50-gpio.c @@ -10,7 +10,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/io.h> #include <linux/delay.h> #include <linux/dmi.h> #include <linux/err.h> diff --git a/drivers/platform/x86/dell/dell-laptop.c b/drivers/platform/x86/dell/dell-laptop.c index 8230e7a68a5e..1321687d923e 100644 --- a/drivers/platform/x86/dell/dell-laptop.c +++ b/drivers/platform/x86/dell/dell-laptop.c @@ -80,6 +80,10 @@ static struct quirk_entry quirk_dell_inspiron_1012 = { .kbd_led_not_present = true, }; +static struct quirk_entry quirk_dell_latitude_7520 = { + .kbd_missing_ac_tag = true, +}; + static struct platform_driver platform_driver = { .driver = { .name = "dell-laptop", @@ -336,6 +340,15 @@ static const struct dmi_system_id dell_quirks[] __initconst = { }, .driver_data = &quirk_dell_inspiron_1012, }, + { + .callback = dmi_matched, + .ident = "Dell Latitude 7520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 7520"), + }, + .driver_data = &quirk_dell_latitude_7520, + }, { } }; diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 658bab4b7964..e87a931eab1e 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -148,6 +148,7 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550I AORUS PRO AX"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B660 GAMING X DDR4"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z390 I AORUS PRO WIFI-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 AORUS ELITE"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 GAMING X"), diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index a46d3b53bf61..7a059e02c265 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -236,7 +236,7 @@ enum ppfear_regs { #define ADL_LPM_STATUS_LATCH_EN_OFFSET 0x1704 #define ADL_LPM_LIVE_STATUS_OFFSET 0x1764 -const char *pmc_lpm_modes[] = { +static const char *pmc_lpm_modes[] = { "S0i2.0", "S0i2.1", "S0i2.2", diff --git a/drivers/platform/x86/intel/sdsi.c b/drivers/platform/x86/intel/sdsi.c index 11d14cc0ff0a..c830e98dfa38 100644 --- a/drivers/platform/x86/intel/sdsi.c +++ b/drivers/platform/x86/intel/sdsi.c @@ -51,6 +51,8 @@ #define MBOX_TIMEOUT_US 2000 #define MBOX_TIMEOUT_ACQUIRE_US 1000 #define MBOX_POLLING_PERIOD_US 100 +#define MBOX_ACQUIRE_NUM_RETRIES 5 +#define MBOX_ACQUIRE_RETRY_DELAY_MS 500 #define MBOX_MAX_PACKETS 4 #define MBOX_OWNER_NONE 0x00 @@ -81,7 +83,7 @@ enum sdsi_command { struct sdsi_mbox_info { u64 *payload; - u64 *buffer; + void *buffer; int size; }; @@ -163,9 +165,7 @@ static int sdsi_mbox_cmd_read(struct sdsi_priv *priv, struct sdsi_mbox_info *inf total = 0; loop = 0; do { - int offset = SDSI_SIZE_MAILBOX * loop; - void __iomem *addr = priv->mbox_addr + offset; - u64 *buf = info->buffer + offset / SDSI_SIZE_CMD; + void *buf = info->buffer + (SDSI_SIZE_MAILBOX * loop); u32 packet_size; /* Poll on ready bit */ @@ -196,7 +196,7 @@ static int sdsi_mbox_cmd_read(struct sdsi_priv *priv, struct sdsi_mbox_info *inf break; } - sdsi_memcpy64_fromio(buf, addr, round_up(packet_size, SDSI_SIZE_CMD)); + sdsi_memcpy64_fromio(buf, priv->mbox_addr, round_up(packet_size, SDSI_SIZE_CMD)); total += packet_size; @@ -243,8 +243,8 @@ static int sdsi_mbox_cmd_write(struct sdsi_priv *priv, struct sdsi_mbox_info *in FIELD_PREP(CTRL_PACKET_SIZE, info->size); writeq(control, priv->control_addr); - /* Poll on run_busy bit */ - ret = readq_poll_timeout(priv->control_addr, control, !(control & CTRL_RUN_BUSY), + /* Poll on ready bit */ + ret = readq_poll_timeout(priv->control_addr, control, control & CTRL_READY, MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_US); if (ret) @@ -263,7 +263,7 @@ static int sdsi_mbox_acquire(struct sdsi_priv *priv, struct sdsi_mbox_info *info { u64 control; u32 owner; - int ret; + int ret, retries = 0; lockdep_assert_held(&priv->mb_lock); @@ -273,13 +273,29 @@ static int sdsi_mbox_acquire(struct sdsi_priv *priv, struct sdsi_mbox_info *info if (owner != MBOX_OWNER_NONE) return -EBUSY; - /* Write first qword of payload */ - writeq(info->payload[0], priv->mbox_addr); + /* + * If there has been no recent transaction and no one owns the mailbox, + * we should acquire it in under 1ms. However, if we've accessed it + * recently it may take up to 2.1 seconds to acquire it again. + */ + do { + /* Write first qword of payload */ + writeq(info->payload[0], priv->mbox_addr); + + /* Check for ownership */ + ret = readq_poll_timeout(priv->control_addr, control, + FIELD_GET(CTRL_OWNER, control) == MBOX_OWNER_INBAND, + MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_ACQUIRE_US); + + if (FIELD_GET(CTRL_OWNER, control) == MBOX_OWNER_NONE && + retries++ < MBOX_ACQUIRE_NUM_RETRIES) { + msleep(MBOX_ACQUIRE_RETRY_DELAY_MS); + continue; + } - /* Check for ownership */ - ret = readq_poll_timeout(priv->control_addr, control, - FIELD_GET(CTRL_OWNER, control) & MBOX_OWNER_INBAND, - MBOX_POLLING_PERIOD_US, MBOX_TIMEOUT_ACQUIRE_US); + /* Either we got it or someone else did. */ + break; + } while (true); return ret; } diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c index c61f804dd44e..8f9c571d7257 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c @@ -212,6 +212,9 @@ static int __init intel_uncore_init(void) const struct x86_cpu_id *id; int ret; + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + id = x86_match_cpu(intel_uncore_cpu_ids); if (!id) return -ENODEV; diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index c1d9ed9b7b67..19f6b456234f 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -1121,8 +1121,6 @@ static void kbd_led_set(struct led_classdev *led_cdev, if (value > samsung->kbd_led.max_brightness) value = samsung->kbd_led.max_brightness; - else if (value < 0) - value = 0; samsung->kbd_led_wk = value; queue_work(samsung->led_workqueue, &samsung->kbd_led_work); diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index bce17ca97947..a01a92769c1a 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -740,16 +740,8 @@ static ssize_t certificate_store(struct kobject *kobj, if (!tlmi_priv.certificate_support) return -EOPNOTSUPP; - new_cert = kstrdup(buf, GFP_KERNEL); - if (!new_cert) - return -ENOMEM; - /* Strip out CR if one is present */ - strip_cr(new_cert); - /* If empty then clear installed certificate */ - if (new_cert[0] == '\0') { /* Clear installed certificate */ - kfree(new_cert); - + if ((buf[0] == '\0') || (buf[0] == '\n')) { /* Clear installed certificate */ /* Check that signature is set */ if (!setting->signature || !setting->signature[0]) return -EACCES; @@ -763,14 +755,16 @@ static ssize_t certificate_store(struct kobject *kobj, ret = tlmi_simple_call(LENOVO_CLEAR_BIOS_CERT_GUID, auth_str); kfree(auth_str); - if (ret) - return ret; - kfree(setting->certificate); - setting->certificate = NULL; - return count; + return ret ?: count; } + new_cert = kstrdup(buf, GFP_KERNEL); + if (!new_cert) + return -ENOMEM; + /* Strip out CR if one is present */ + strip_cr(new_cert); + if (setting->cert_installed) { /* Certificate is installed so this is an update */ if (!setting->signature || !setting->signature[0]) { @@ -792,21 +786,14 @@ static ssize_t certificate_store(struct kobject *kobj, auth_str = kasprintf(GFP_KERNEL, "%s,%s", new_cert, setting->password); } - if (!auth_str) { - kfree(new_cert); + kfree(new_cert); + if (!auth_str) return -ENOMEM; - } ret = tlmi_simple_call(guid, auth_str); kfree(auth_str); - if (ret) { - kfree(new_cert); - return ret; - } - kfree(setting->certificate); - setting->certificate = new_cert; - return count; + return ret ?: count; } static struct kobj_attribute auth_certificate = __ATTR_WO(certificate); @@ -1194,6 +1181,10 @@ static void tlmi_release_attr(void) kset_unregister(tlmi_priv.attribute_kset); + /* Free up any saved signatures */ + kfree(tlmi_priv.pwd_admin->signature); + kfree(tlmi_priv.pwd_admin->save_signature); + /* Authentication structures */ sysfs_remove_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group); kobject_put(&tlmi_priv.pwd_admin->kobj); @@ -1210,11 +1201,6 @@ static void tlmi_release_attr(void) } kset_unregister(tlmi_priv.authentication_kset); - - /* Free up any saved certificates/signatures */ - kfree(tlmi_priv.pwd_admin->certificate); - kfree(tlmi_priv.pwd_admin->signature); - kfree(tlmi_priv.pwd_admin->save_signature); } static int tlmi_sysfs_init(void) diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h index 4f69df6eed07..4daba6151cd6 100644 --- a/drivers/platform/x86/think-lmi.h +++ b/drivers/platform/x86/think-lmi.h @@ -63,7 +63,6 @@ struct tlmi_pwd_setting { int index; /*Used for HDD and NVME auth */ enum level_option level; bool cert_installed; - char *certificate; char *signature; char *save_signature; }; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index ea02c8dcd748..d925cb137e12 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -604,6 +604,12 @@ int power_supply_get_battery_info(struct power_supply *psy, err = samsung_sdi_battery_get_info(&psy->dev, value, &info); if (!err) goto out_ret_pointer; + else if (err == -ENODEV) + /* + * Device does not have a static battery. + * Proceed to look for a simple battery. + */ + err = 0; if (strcmp("simple-battery", value)) { err = -ENODEV; diff --git a/drivers/power/supply/samsung-sdi-battery.c b/drivers/power/supply/samsung-sdi-battery.c index 9d59f277f519..b33daab798b9 100644 --- a/drivers/power/supply/samsung-sdi-battery.c +++ b/drivers/power/supply/samsung-sdi-battery.c @@ -824,6 +824,7 @@ static struct samsung_sdi_battery samsung_sdi_batteries[] = { .constant_charge_current_max_ua = 900000, .constant_charge_voltage_max_uv = 4200000, .charge_term_current_ua = 200000, + .charge_restart_voltage_uv = 4170000, .maintenance_charge = samsung_maint_charge_table, .maintenance_charge_size = ARRAY_SIZE(samsung_maint_charge_table), .alert_low_temp_charge_current_ua = 300000, @@ -867,6 +868,7 @@ static struct samsung_sdi_battery samsung_sdi_batteries[] = { .constant_charge_current_max_ua = 1500000, .constant_charge_voltage_max_uv = 4350000, .charge_term_current_ua = 120000, + .charge_restart_voltage_uv = 4300000, .maintenance_charge = samsung_maint_charge_table, .maintenance_charge_size = ARRAY_SIZE(samsung_maint_charge_table), .alert_low_temp_charge_current_ua = 300000, diff --git a/drivers/regulator/atc260x-regulator.c b/drivers/regulator/atc260x-regulator.c index 05147d2c3842..485e58b264c0 100644 --- a/drivers/regulator/atc260x-regulator.c +++ b/drivers/regulator/atc260x-regulator.c @@ -292,6 +292,7 @@ enum atc2603c_reg_ids { .bypass_mask = BIT(5), \ .active_discharge_reg = ATC2603C_PMU_SWITCH_CTL, \ .active_discharge_mask = BIT(1), \ + .active_discharge_on = BIT(1), \ .owner = THIS_MODULE, \ } diff --git a/drivers/regulator/rtq2134-regulator.c b/drivers/regulator/rtq2134-regulator.c index f21e3f8b21f2..8e13dea354a2 100644 --- a/drivers/regulator/rtq2134-regulator.c +++ b/drivers/regulator/rtq2134-regulator.c @@ -285,6 +285,7 @@ static const unsigned int rtq2134_buck_ramp_delay_table[] = { .enable_mask = RTQ2134_VOUTEN_MASK, \ .active_discharge_reg = RTQ2134_REG_BUCK##_id##_CFG0, \ .active_discharge_mask = RTQ2134_ACTDISCHG_MASK, \ + .active_discharge_on = RTQ2134_ACTDISCHG_MASK, \ .ramp_reg = RTQ2134_REG_BUCK##_id##_RSPCFG, \ .ramp_mask = RTQ2134_RSPUP_MASK, \ .ramp_delay_table = rtq2134_buck_ramp_delay_table, \ diff --git a/drivers/regulator/wm8994-regulator.c b/drivers/regulator/wm8994-regulator.c index cadea0344486..40befdd9dfa9 100644 --- a/drivers/regulator/wm8994-regulator.c +++ b/drivers/regulator/wm8994-regulator.c @@ -82,6 +82,35 @@ static const struct regulator_desc wm8994_ldo_desc[] = { .min_uV = 2400000, .uV_step = 100000, .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, + { + .name = "LDO2", + .id = 2, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO2_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_2, + .vsel_mask = WM8994_LDO2_VSEL_MASK, + .ops = &wm8994_ldo2_ops, + .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, +}; + +static const struct regulator_desc wm8958_ldo_desc[] = { + { + .name = "LDO1", + .id = 1, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO1_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_1, + .vsel_mask = WM8994_LDO1_VSEL_MASK, + .ops = &wm8994_ldo1_ops, + .min_uV = 2400000, + .uV_step = 100000, + .enable_time = 3000, .owner = THIS_MODULE, }, { @@ -172,9 +201,16 @@ static int wm8994_ldo_probe(struct platform_device *pdev) * regulator core and we need not worry about it on the * error path. */ - ldo->regulator = devm_regulator_register(&pdev->dev, - &wm8994_ldo_desc[id], - &config); + if (ldo->wm8994->type == WM8994) { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8994_ldo_desc[id], + &config); + } else { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8958_ldo_desc[id], + &config); + } + if (IS_ERR(ldo->regulator)) { ret = PTR_ERR(ldo->regulator); dev_err(wm8994->dev, "Failed to register LDO%d: %d\n", diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c index 1e8315038850..a8dde4606360 100644 --- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c +++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c @@ -121,7 +121,9 @@ static int rzg2l_usbphy_ctrl_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(priv->rstc), "failed to get reset\n"); - reset_control_deassert(priv->rstc); + error = reset_control_deassert(priv->rstc); + if (error) + return error; priv->rcdev.ops = &rzg2l_usbphy_ctrl_reset_ops; priv->rcdev.of_reset_n_cells = 1; diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c index 24d3395964cc..4c5bba52b105 100644 --- a/drivers/reset/tegra/reset-bpmp.c +++ b/drivers/reset/tegra/reset-bpmp.c @@ -20,6 +20,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc); struct mrq_reset_request request; struct tegra_bpmp_message msg; + int err; memset(&request, 0, sizeof(request)); request.cmd = command; @@ -30,7 +31,13 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, msg.tx.data = &request; msg.tx.size = sizeof(request); - return tegra_bpmp_transfer(bpmp, &msg); + err = tegra_bpmp_transfer(bpmp, &msg); + if (err) + return err; + if (msg.rx.ret) + return -EINVAL; + + return 0; } static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc, diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c index 5f554a3a0f62..caeebfb67149 100644 --- a/drivers/scsi/aha152x.c +++ b/drivers/scsi/aha152x.c @@ -317,14 +317,18 @@ enum { }; struct aha152x_cmd_priv { - struct scsi_pointer scsi_pointer; + char *ptr; + int this_residual; + struct scatterlist *buffer; + int status; + int message; + int sent_command; + int phase; }; -static struct scsi_pointer *aha152x_scsi_pointer(struct scsi_cmnd *cmd) +static struct aha152x_cmd_priv *aha152x_priv(struct scsi_cmnd *cmd) { - struct aha152x_cmd_priv *acmd = scsi_cmd_priv(cmd); - - return &acmd->scsi_pointer; + return scsi_cmd_priv(cmd); } MODULE_AUTHOR("Jürgen Fischer"); @@ -890,17 +894,16 @@ void aha152x_release(struct Scsi_Host *shpnt) static int setup_expected_interrupts(struct Scsi_Host *shpnt) { if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; - if (scsi_pointer->phase & selecting) { + if (acp->phase & selecting) { SETPORT(SSTAT1, SELTO); SETPORT(SIMODE0, ENSELDO | (DISCONNECTED_SC ? ENSELDI : 0)); SETPORT(SIMODE1, ENSELTIMO); } else { - SETPORT(SIMODE0, (scsi_pointer->phase & spiordy) ? ENSPIORDY : 0); + SETPORT(SIMODE0, (acp->phase & spiordy) ? ENSPIORDY : 0); SETPORT(SIMODE1, ENPHASEMIS | ENSCSIRST | ENSCSIPERR | ENBUSFREE); } } else if(STATE==seldi) { @@ -924,17 +927,16 @@ static int setup_expected_interrupts(struct Scsi_Host *shpnt) static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, struct completion *complete, int phase) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(SCpnt); + struct aha152x_cmd_priv *acp = aha152x_priv(SCpnt); struct Scsi_Host *shpnt = SCpnt->device->host; unsigned long flags; - scsi_pointer->phase = not_issued | phase; - scsi_pointer->Status = 0x1; /* Ilegal status by SCSI standard */ - scsi_pointer->Message = 0; - scsi_pointer->have_data_in = 0; - scsi_pointer->sent_command = 0; + acp->phase = not_issued | phase; + acp->status = 0x1; /* Illegal status by SCSI standard */ + acp->message = 0; + acp->sent_command = 0; - if (scsi_pointer->phase & (resetting | check_condition)) { + if (acp->phase & (resetting | check_condition)) { if (!SCpnt->host_scribble || SCSEM(SCpnt) || SCNEXT(SCpnt)) { scmd_printk(KERN_ERR, SCpnt, "cannot reuse command\n"); return FAILED; @@ -957,15 +959,15 @@ static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, SCp.phase : current state of the command */ if ((phase & resetting) || !scsi_sglist(SCpnt)) { - scsi_pointer->ptr = NULL; - scsi_pointer->this_residual = 0; + acp->ptr = NULL; + acp->this_residual = 0; scsi_set_resid(SCpnt, 0); - scsi_pointer->buffer = NULL; + acp->buffer = NULL; } else { scsi_set_resid(SCpnt, scsi_bufflen(SCpnt)); - scsi_pointer->buffer = scsi_sglist(SCpnt); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = scsi_sglist(SCpnt); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } DO_LOCK(flags); @@ -1015,7 +1017,7 @@ static void reset_done(struct scsi_cmnd *SCpnt) static void aha152x_scsi_done(struct scsi_cmnd *SCpnt) { - if (aha152x_scsi_pointer(SCpnt)->phase & resetting) + if (aha152x_priv(SCpnt)->phase & resetting) reset_done(SCpnt); else scsi_done(SCpnt); @@ -1101,7 +1103,7 @@ static int aha152x_device_reset(struct scsi_cmnd * SCpnt) DO_LOCK(flags); - if (aha152x_scsi_pointer(SCpnt)->phase & resetted) { + if (aha152x_priv(SCpnt)->phase & resetted) { HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); @@ -1395,31 +1397,30 @@ static void busfree_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRBUSFREE); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase &= ~syncneg; + acp->phase &= ~syncneg; - if (scsi_pointer->phase & completed) { + if (acp->phase & completed) { /* target sent COMMAND COMPLETE */ - done(shpnt, scsi_pointer->Status, DID_OK); + done(shpnt, acp->status, DID_OK); - } else if (scsi_pointer->phase & aborted) { - done(shpnt, scsi_pointer->Status, DID_ABORT); + } else if (acp->phase & aborted) { + done(shpnt, acp->status, DID_ABORT); - } else if (scsi_pointer->phase & resetted) { - done(shpnt, scsi_pointer->Status, DID_RESET); + } else if (acp->phase & resetted) { + done(shpnt, acp->status, DID_RESET); - } else if (scsi_pointer->phase & disconnected) { + } else if (acp->phase & disconnected) { /* target sent DISCONNECT */ #if defined(AHA152X_STAT) HOSTDATA(shpnt)->disconnections++; #endif append_SC(&DISCONNECTED_SC, CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; CURRENT_SC = NULL; } else { @@ -1438,24 +1439,23 @@ static void busfree_run(struct Scsi_Host *shpnt) action++; #endif - if (aha152x_scsi_pointer(DONE_SC)->phase & check_condition) { + if (aha152x_priv(DONE_SC)->phase & check_condition) { struct scsi_cmnd *cmd = HOSTDATA(shpnt)->done_SC; struct aha152x_scdata *sc = SCDATA(cmd); scsi_eh_restore_cmnd(cmd, &sc->ses); - aha152x_scsi_pointer(cmd)->Status = SAM_STAT_CHECK_CONDITION; + aha152x_priv(cmd)->status = SAM_STAT_CHECK_CONDITION; HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - } else if (aha152x_scsi_pointer(DONE_SC)->Status == - SAM_STAT_CHECK_CONDITION) { + } else if (aha152x_priv(DONE_SC)->status == SAM_STAT_CHECK_CONDITION) { #if defined(AHA152X_STAT) HOSTDATA(shpnt)->busfree_with_check_condition++; #endif - if(!(aha152x_scsi_pointer(DONE_SC)->phase & not_issued)) { + if (!(aha152x_priv(DONE_SC)->phase & not_issued)) { struct aha152x_scdata *sc; struct scsi_cmnd *ptr = DONE_SC; DONE_SC=NULL; @@ -1480,7 +1480,7 @@ static void busfree_run(struct Scsi_Host *shpnt) if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - if (!(aha152x_scsi_pointer(ptr)->phase & resetting)) { + if (!(aha152x_priv(ptr)->phase & resetting)) { kfree(ptr->host_scribble); ptr->host_scribble=NULL; } @@ -1503,13 +1503,12 @@ static void busfree_run(struct Scsi_Host *shpnt) DO_UNLOCK(flags); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase |= selecting; + acp->phase |= selecting; /* clear selection timeout */ SETPORT(SSTAT1, SELTO); @@ -1537,13 +1536,13 @@ static void busfree_run(struct Scsi_Host *shpnt) */ static void seldo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); SETPORT(SCSISIG, 0); SETPORT(SSTAT1, CLRBUSFREE); SETPORT(SSTAT1, CLRPHASECHG); - scsi_pointer->phase &= ~(selecting | not_issued); + acp->phase &= ~(selecting | not_issued); SETPORT(SCSISEQ, 0); @@ -1558,12 +1557,12 @@ static void seldo_run(struct Scsi_Host *shpnt) ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); - if (scsi_pointer->phase & aborting) { + if (acp->phase & aborting) { ADDMSGO(ABORT); - } else if (scsi_pointer->phase & resetting) { + } else if (acp->phase & resetting) { ADDMSGO(BUS_DEVICE_RESET); } else if (SYNCNEG==0 && SYNCHRONOUS) { - scsi_pointer->phase |= syncneg; + acp->phase |= syncneg; MSGOLEN += spi_populate_sync_msg(&MSGO(MSGOLEN), 50, 8); SYNCNEG=1; /* negotiation in progress */ } @@ -1578,7 +1577,7 @@ static void seldo_run(struct Scsi_Host *shpnt) */ static void selto_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp; SETPORT(SCSISEQ, 0); SETPORT(SSTAT1, CLRSELTIMO); @@ -1586,9 +1585,10 @@ static void selto_run(struct Scsi_Host *shpnt) if (!CURRENT_SC) return; - scsi_pointer->phase &= ~selecting; + acp = aha152x_priv(CURRENT_SC); + acp->phase &= ~selecting; - if (scsi_pointer->phase & aborted) + if (acp->phase & aborted) done(shpnt, SAM_STAT_GOOD, DID_ABORT); else if (TESTLO(SSTAT0, SELINGO)) done(shpnt, SAM_STAT_GOOD, DID_BUS_BUSY); @@ -1616,10 +1616,9 @@ static void seldi_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRPHASECHG); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - if (!(scsi_pointer->phase & not_issued)) + if (!(acp->phase & not_issued)) scmd_printk(KERN_ERR, CURRENT_SC, "command should not have been issued yet\n"); @@ -1676,7 +1675,7 @@ static void seldi_run(struct Scsi_Host *shpnt) static void msgi_run(struct Scsi_Host *shpnt) { for(;;) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; int sstat1 = GETPORT(SSTAT1); if(sstat1 & (PHASECHG|PHASEMIS|BUSFREE) || !(sstat1 & REQINIT)) @@ -1714,9 +1713,9 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); - scsi_pointer->phase &= ~disconnected; + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); + acp->phase &= ~disconnected; MSGILEN=0; @@ -1724,8 +1723,8 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); switch (MSGI(0)) { case DISCONNECT: @@ -1733,11 +1732,11 @@ static void msgi_run(struct Scsi_Host *shpnt) scmd_printk(KERN_WARNING, CURRENT_SC, "target was not allowed to disconnect\n"); - scsi_pointer->phase |= disconnected; + acp->phase |= disconnected; break; case COMMAND_COMPLETE: - scsi_pointer->phase |= completed; + acp->phase |= completed; break; case MESSAGE_REJECT: @@ -1867,11 +1866,9 @@ static void msgi_end(struct Scsi_Host *shpnt) */ static void msgo_init(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if(MSGOLEN==0) { - if ((scsi_pointer->phase & syncneg) && SYNCNEG==2 && - SYNCRATE==0) { + if ((aha152x_priv(CURRENT_SC)->phase & syncneg) && + SYNCNEG == 2 && SYNCRATE == 0) { ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); } else { scmd_printk(KERN_INFO, CURRENT_SC, @@ -1888,7 +1885,7 @@ static void msgo_init(struct Scsi_Host *shpnt) */ static void msgo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); while(MSGO_I<MSGOLEN) { if (TESTLO(SSTAT0, SPIORDY)) @@ -1901,13 +1898,13 @@ static void msgo_run(struct Scsi_Host *shpnt) if (MSGO(MSGO_I) & IDENTIFY_BASE) - scsi_pointer->phase |= identified; + acp->phase |= identified; if (MSGO(MSGO_I)==ABORT) - scsi_pointer->phase |= aborted; + acp->phase |= aborted; if (MSGO(MSGO_I)==BUS_DEVICE_RESET) - scsi_pointer->phase |= resetted; + acp->phase |= resetted; SETPORT(SCSIDAT, MSGO(MSGO_I++)); } @@ -1936,7 +1933,7 @@ static void msgo_end(struct Scsi_Host *shpnt) */ static void cmd_init(struct Scsi_Host *shpnt) { - if (aha152x_scsi_pointer(CURRENT_SC)->sent_command) { + if (aha152x_priv(CURRENT_SC)->sent_command) { scmd_printk(KERN_ERR, CURRENT_SC, "command already sent\n"); done(shpnt, SAM_STAT_GOOD, DID_ERROR); @@ -1967,7 +1964,7 @@ static void cmd_end(struct Scsi_Host *shpnt) "command sent incompletely (%d/%d)\n", CMD_I, CURRENT_SC->cmd_len); else - aha152x_scsi_pointer(CURRENT_SC)->sent_command++; + aha152x_priv(CURRENT_SC)->sent_command++; } /* @@ -1979,7 +1976,7 @@ static void status_run(struct Scsi_Host *shpnt) if (TESTLO(SSTAT0, SPIORDY)) return; - aha152x_scsi_pointer(CURRENT_SC)->Status = GETPORT(SCSIDAT); + aha152x_priv(CURRENT_SC)->status = GETPORT(SCSIDAT); } @@ -2003,7 +2000,7 @@ static void datai_init(struct Scsi_Host *shpnt) static void datai_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; unsigned long the_time; int fifodata, data_count; @@ -2041,36 +2038,35 @@ static void datai_run(struct Scsi_Host *shpnt) fifodata = GETPORT(FIFOSTAT); } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if (scsi_pointer->this_residual > 0) { - while (fifodata > 0 && scsi_pointer->this_residual > 0) { - data_count = fifodata > scsi_pointer->this_residual ? - scsi_pointer->this_residual : - fifodata; + acp = aha152x_priv(CURRENT_SC); + if (acp->this_residual > 0) { + while (fifodata > 0 && acp->this_residual > 0) { + data_count = fifodata > acp->this_residual ? + acp->this_residual : fifodata; fifodata -= data_count; if (data_count & 1) { SETPORT(DMACNTRL0, ENDMA|_8BIT); - *scsi_pointer->ptr++ = GETPORT(DATAPORT); - scsi_pointer->this_residual--; + *acp->ptr++ = GETPORT(DATAPORT); + acp->this_residual--; DATA_LEN++; SETPORT(DMACNTRL0, ENDMA); } if (data_count > 1) { data_count >>= 1; - insw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + insw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; DATA_LEN += 2 * data_count; } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && + !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } } } else if (fifodata > 0) { @@ -2138,15 +2134,15 @@ static void datao_init(struct Scsi_Host *shpnt) static void datao_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); unsigned long the_time; int data_count; /* until phase changes or all data sent */ - while (TESTLO(DMASTAT, INTSTAT) && scsi_pointer->this_residual > 0) { + while (TESTLO(DMASTAT, INTSTAT) && acp->this_residual > 0) { data_count = 128; - if (data_count > scsi_pointer->this_residual) - data_count = scsi_pointer->this_residual; + if (data_count > acp->this_residual) + data_count = acp->this_residual; if(TESTLO(DMASTAT, DFIFOEMP)) { scmd_printk(KERN_ERR, CURRENT_SC, @@ -2157,26 +2153,25 @@ static void datao_run(struct Scsi_Host *shpnt) if(data_count & 1) { SETPORT(DMACNTRL0,WRITE_READ|ENDMA|_8BIT); - SETPORT(DATAPORT, *scsi_pointer->ptr++); - scsi_pointer->this_residual--; + SETPORT(DATAPORT, *acp->ptr++); + acp->this_residual--; CMD_INC_RESID(CURRENT_SC, -1); SETPORT(DMACNTRL0,WRITE_READ|ENDMA); } if(data_count > 1) { data_count >>= 1; - outsw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + outsw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; CMD_INC_RESID(CURRENT_SC, -2 * data_count); } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } the_time=jiffies + 100*HZ; @@ -2192,7 +2187,7 @@ static void datao_run(struct Scsi_Host *shpnt) static void datao_end(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); if(TESTLO(DMASTAT, DFIFOEMP)) { u32 datao_cnt = GETSTCNT(); @@ -2211,10 +2206,9 @@ static void datao_end(struct Scsi_Host *shpnt) sg = sg_next(sg); } - scsi_pointer->buffer = sg; - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer) + done; - scsi_pointer->this_residual = scsi_pointer->buffer->length - - done; + acp->buffer = sg; + acp->ptr = SG_ADDRESS(acp->buffer) + done; + acp->this_residual = acp->buffer->length - done; } SETPORT(SXFRCTL0, CH1|CLRCH1|CLRSTCNT); @@ -2229,7 +2223,6 @@ static void datao_end(struct Scsi_Host *shpnt) */ static int update_state(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); int dataphase=0; unsigned int stat0 = GETPORT(SSTAT0); unsigned int stat1 = GETPORT(SSTAT1); @@ -2244,7 +2237,7 @@ static int update_state(struct Scsi_Host *shpnt) } else if (stat0 & SELDI && PREVSTATE == busfree) { STATE=seldi; } else if (stat0 & SELDO && CURRENT_SC && - (scsi_pointer->phase & selecting)) { + (aha152x_priv(CURRENT_SC)->phase & selecting)) { STATE=seldo; } else if(stat1 & SELTO) { STATE=selto; @@ -2376,8 +2369,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(SXFRCTL0, CH1); SETPORT(DMACNTRL0, 0); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase &= - ~spiordy; + aha152x_priv(CURRENT_SC)->phase &= ~spiordy; } /* @@ -2399,8 +2391,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(DMACNTRL0, 0); SETPORT(SXFRCTL0, CH1|SPIOEN); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase |= - spiordy; + aha152x_priv(CURRENT_SC)->phase |= spiordy; } /* @@ -2490,7 +2481,7 @@ static void disp_enintr(struct Scsi_Host *shpnt) */ static void show_command(struct scsi_cmnd *ptr) { - const int phase = aha152x_scsi_pointer(ptr)->phase; + const int phase = aha152x_priv(ptr)->phase; scsi_print_command(ptr); scmd_printk(KERN_DEBUG, ptr, @@ -2538,8 +2529,8 @@ static void show_queues(struct Scsi_Host *shpnt) static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(ptr); - const int phase = scsi_pointer->phase; + struct aha152x_cmd_priv *acp = aha152x_priv(ptr); + const int phase = acp->phase; int i; seq_printf(m, "%p: target=%d; lun=%d; cmnd=( ", @@ -2549,8 +2540,8 @@ static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) seq_printf(m, "0x%02x ", ptr->cmnd[i]); seq_printf(m, "); resid=%d; residual=%d; buffers=%d; phase |", - scsi_get_resid(ptr), scsi_pointer->this_residual, - sg_nents(scsi_pointer->buffer) - 1); + scsi_get_resid(ptr), acp->this_residual, + sg_nents(acp->buffer) - 1); if (phase & not_issued) seq_puts(m, "not issued|"); diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.h b/drivers/scsi/aic7xxx/aic79xx_osm.h index 679a4fd13874..793fe19993a9 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.h +++ b/drivers/scsi/aic7xxx/aic79xx_osm.h @@ -420,8 +420,6 @@ ahd_unlock(struct ahd_softc *ahd, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e /****************************** PCI-X definitions *****************************/ #define PCIXR_COMMAND 0x96 diff --git a/drivers/scsi/aic7xxx/aic79xx_pci.c b/drivers/scsi/aic7xxx/aic79xx_pci.c index 2f0bdb9225a4..5fad41b1ab58 100644 --- a/drivers/scsi/aic7xxx/aic79xx_pci.c +++ b/drivers/scsi/aic7xxx/aic79xx_pci.c @@ -260,8 +260,8 @@ ahd_find_pci_device(ahd_dev_softc_t pci) vendor = ahd_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahd_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahd_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahd_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahd_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahd_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahd_compose_id(device, vendor, subdevice, @@ -298,7 +298,7 @@ ahd_pci_config(struct ahd_softc *ahd, const struct ahd_pci_identity *entry) * Record if this is an HP board. */ subvendor = ahd_pci_read_config(ahd->dev_softc, - PCIR_SUBVEND_0, /*bytes*/2); + PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); if (subvendor == SUBID_HP) ahd->flags |= AHD_HP_BOARD; diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.h b/drivers/scsi/aic7xxx/aic7xxx_osm.h index 4782a304e93c..51d9f4de0734 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.h +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.h @@ -433,8 +433,6 @@ ahc_unlock(struct ahc_softc *ahc, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e typedef enum { diff --git a/drivers/scsi/aic7xxx/aic7xxx_pci.c b/drivers/scsi/aic7xxx/aic7xxx_pci.c index dab3a6d12c4d..2d4c85426dc3 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_pci.c @@ -673,8 +673,8 @@ ahc_find_pci_device(ahc_dev_softc_t pci) vendor = ahc_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahc_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahc_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahc_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahc_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahc_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahc_compose_id(device, vendor, subdevice, subvendor); /* diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 0103f811cc25..776544385598 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -1169,7 +1169,7 @@ static void bnx2fc_process_ofld_cmpl(struct bnx2fc_hba *hba, ofld_kcqe->fcoe_conn_context_id); interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mismatch\n"); goto ofld_cmpl_err; } /* @@ -1226,12 +1226,12 @@ static void bnx2fc_process_enable_conn_cmpl(struct bnx2fc_hba *hba, * and enable */ if (tgt->context_id != context_id) { - printk(KERN_ERR PFX "context id mis-match\n"); + printk(KERN_ERR PFX "context id mismatch\n"); return; } interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mismatch\n"); goto enbl_cmpl_err; } if (!ofld_kcqe->completion_status) diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index 5521469ce678..6c864b093ac9 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -1977,7 +1977,7 @@ static int bnx2i_process_new_cqes(struct bnx2i_conn *bnx2i_conn) if (nopin->cq_req_sn != qp->cqe_exp_seq_sn) break; - if (unlikely(test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx))) { + if (unlikely(test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { if (nopin->op_code == ISCSI_OP_NOOP_IN && nopin->itt == (u16) RESERVED_ITT) { printk(KERN_ALERT "bnx2i: Unsolicited " @@ -2398,7 +2398,7 @@ static void bnx2i_process_conn_destroy_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "conn destroy- error hba mis-match\n"); + printk(KERN_ALERT "conn destroy- error hba mismatch\n"); return; } @@ -2432,7 +2432,7 @@ static void bnx2i_process_ofld_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "ofld_cmpl: error hba mis-match\n"); + printk(KERN_ALERT "ofld_cmpl: error hba mismatch\n"); return; } diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c index fe86fd61a995..15fbd09baa94 100644 --- a/drivers/scsi/bnx2i/bnx2i_iscsi.c +++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c @@ -1721,7 +1721,7 @@ static int bnx2i_tear_down_conn(struct bnx2i_hba *hba, struct iscsi_conn *conn = ep->conn->cls_conn->dd_data; /* Must suspend all rx queue activity for this ep */ - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); } /* CONN_DISCONNECT timeout may or may not be an issue depending * on what transcribed in TCP layer, different targets behave diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 8c7d4dda4cf2..4365d52c6430 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -1634,11 +1634,11 @@ void cxgbi_conn_pdu_ready(struct cxgbi_sock *csk) log_debug(1 << CXGBI_DBG_PDU_RX, "csk 0x%p, conn 0x%p.\n", csk, conn); - if (unlikely(!conn || conn->suspend_rx)) { + if (unlikely(!conn || test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { log_debug(1 << CXGBI_DBG_PDU_RX, - "csk 0x%p, conn 0x%p, id %d, suspend_rx %lu!\n", + "csk 0x%p, conn 0x%p, id %d, conn flags 0x%lx!\n", csk, conn, conn ? conn->id : 0xFF, - conn ? conn->suspend_rx : 0xFF); + conn ? conn->flags : 0xFF); return; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 461ef8a76c4c..4bda2f6cb352 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -442,7 +442,6 @@ void hisi_sas_task_deliver(struct hisi_hba *hisi_hba, case SAS_PROTOCOL_INTERNAL_ABORT: hisi_sas_task_prep_abort(hisi_hba, slot); break; - fallthrough; default: return; } diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 80238e6a3c98..eee1a24f7e15 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -36,7 +36,7 @@ #define IBMVSCSIS_VERSION "v0.2" -#define INITIAL_SRP_LIMIT 800 +#define INITIAL_SRP_LIMIT 1024 #define DEFAULT_MAX_SECTORS 256 #define MAX_TXU 1024 * 1024 diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c index d690d9cf7eb1..35589b6af90d 100644 --- a/drivers/scsi/isci/host.c +++ b/drivers/scsi/isci/host.c @@ -413,7 +413,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for io request object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -428,7 +428,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for remote device object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -462,7 +462,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) } else dev_err(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received event 0x%x " - "for remote device object 0x%0x that doesnt " + "for remote device object 0x%0x that doesn't " "exist.\n", __func__, ihost, diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index d09926e6c8a8..797abf4f5399 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -678,7 +678,8 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, struct iscsi_task *task; itt_t itt; - if (session->state == ISCSI_STATE_TERMINATE) + if (session->state == ISCSI_STATE_TERMINATE || + !test_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags)) return NULL; if (opcode == ISCSI_OP_LOGIN || opcode == ISCSI_OP_TEXT) { @@ -1392,8 +1393,8 @@ static bool iscsi_set_conn_failed(struct iscsi_conn *conn) if (conn->stop_stage == 0) session->state = ISCSI_STATE_FAILED; - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); return true; } @@ -1454,7 +1455,7 @@ static int iscsi_xmit_task(struct iscsi_conn *conn, struct iscsi_task *task, * Do this after dropping the extra ref because if this was a requeue * it's removed from that list and cleanup_queued_task would miss it. */ - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { /* * Save the task and ref in case we weren't cleaning up this * task and get woken up again. @@ -1532,7 +1533,7 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) int rc = 0; spin_lock_bh(&conn->session->frwd_lock); - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { ISCSI_DBG_SESSION(conn->session, "Tx suspended!\n"); spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; @@ -1746,7 +1747,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto fault; } - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { reason = FAILURE_SESSION_IN_RECOVERY; sc->result = DID_REQUEUE << 16; goto fault; @@ -1935,7 +1936,7 @@ static void fail_scsi_tasks(struct iscsi_conn *conn, u64 lun, int error) void iscsi_suspend_queue(struct iscsi_conn *conn) { spin_lock_bh(&conn->session->frwd_lock); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); spin_unlock_bh(&conn->session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_suspend_queue); @@ -1953,7 +1954,7 @@ void iscsi_suspend_tx(struct iscsi_conn *conn) struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); if (ihost->workq) flush_workqueue(ihost->workq); } @@ -1961,7 +1962,7 @@ EXPORT_SYMBOL_GPL(iscsi_suspend_tx); static void iscsi_start_tx(struct iscsi_conn *conn) { - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); iscsi_conn_queue_work(conn); } @@ -2214,6 +2215,8 @@ void iscsi_conn_unbind(struct iscsi_cls_conn *cls_conn, bool is_active) iscsi_suspend_tx(conn); spin_lock_bh(&session->frwd_lock); + clear_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags); + if (!is_active) { /* * if logout timed out before userspace could even send a PDU @@ -3045,7 +3048,6 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, if (!cls_conn) return NULL; conn = cls_conn->dd_data; - memset(conn, 0, sizeof(*conn) + dd_size); conn->dd_data = cls_conn->dd_data + sizeof(*conn); conn->session = session; @@ -3318,6 +3320,8 @@ int iscsi_conn_bind(struct iscsi_cls_session *cls_session, spin_lock_bh(&session->frwd_lock); if (is_leading) session->leadconn = conn; + + set_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags); spin_unlock_bh(&session->frwd_lock); /* @@ -3330,8 +3334,8 @@ int iscsi_conn_bind(struct iscsi_cls_session *cls_session, /* * Unblock xmitworker(), Login Phase will pass through. */ - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); return 0; } EXPORT_SYMBOL_GPL(iscsi_conn_bind); diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 2e9ffe3d1a55..883005757ddb 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -927,7 +927,7 @@ int iscsi_tcp_recv_skb(struct iscsi_conn *conn, struct sk_buff *skb, */ conn->last_recv = jiffies; - if (unlikely(conn->suspend_rx)) { + if (unlikely(test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags))) { ISCSI_DBG_TCP(conn, "Rx suspended!\n"); *status = ISCSI_TCP_SUSPENDED; return 0; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index f0cf8ffdc5f3..0025760230e5 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -897,6 +897,11 @@ enum lpfc_irq_chann_mode { NHT_MODE, }; +enum lpfc_hba_bit_flags { + FABRIC_COMANDS_BLOCKED, + HBA_PCI_ERR, +}; + struct lpfc_hba { /* SCSI interface function jump table entries */ struct lpfc_io_buf * (*lpfc_get_scsi_buf) @@ -1043,7 +1048,6 @@ struct lpfc_hba { * Firmware supports Forced Link Speed * capability */ -#define HBA_PCI_ERR 0x80000 /* The PCI slot is offline */ #define HBA_FLOGI_ISSUED 0x100000 /* FLOGI was issued */ #define HBA_SHORT_CMF 0x200000 /* shorter CMF timer routine */ #define HBA_CGN_DAY_WRAP 0x400000 /* HBA Congestion info day wraps */ @@ -1350,7 +1354,6 @@ struct lpfc_hba { atomic_t fabric_iocb_count; struct timer_list fabric_block_timer; unsigned long bit_flags; -#define FABRIC_COMANDS_BLOCKED 0 atomic_t num_rsrc_err; atomic_t num_cmd_success; unsigned long last_rsrc_error_time; diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index 96408cd6c4c8..9897a1aa387b 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -670,3 +670,6 @@ struct lpfc_vmid *lpfc_get_vmid_from_hashtable(struct lpfc_vport *vport, uint32_t hash, uint8_t *buf); void lpfc_vmid_vport_cleanup(struct lpfc_vport *vport); int lpfc_issue_els_qfpa(struct lpfc_vport *vport); + +void lpfc_sli_rpi_release(struct lpfc_vport *vport, + struct lpfc_nodelist *ndlp); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 0144da30e3db..2b877dff5ed4 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -109,8 +109,8 @@ lpfc_rport_invalid(struct fc_rport *rport) ndlp = rdata->pnode; if (!rdata->pnode) { - pr_err("**** %s: NULL ndlp on rport x%px SID x%x\n", - __func__, rport, rport->scsi_target_id); + pr_info("**** %s: NULL ndlp on rport x%px SID x%x\n", + __func__, rport, rport->scsi_target_id); return -EINVAL; } @@ -169,9 +169,10 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, "3181 dev_loss_callbk x%06x, rport x%px flg x%x " - "load_flag x%x refcnt %d\n", + "load_flag x%x refcnt %d state %d xpt x%x\n", ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag, - vport->load_flag, kref_read(&ndlp->kref)); + vport->load_flag, kref_read(&ndlp->kref), + ndlp->nlp_state, ndlp->fc4_xpt_flags); /* Don't schedule a worker thread event if the vport is going down. * The teardown process cleans up the node via lpfc_drop_node. @@ -181,6 +182,11 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; ndlp->fc4_xpt_flags &= ~SCSI_XPT_REGD; + /* clear the NLP_XPT_REGD if the node is not registered + * with nvme-fc + */ + if (ndlp->fc4_xpt_flags == NLP_XPT_REGD) + ndlp->fc4_xpt_flags &= ~NLP_XPT_REGD; /* Remove the node reference from remote_port_add now. * The driver will not call remote_port_delete. @@ -225,18 +231,36 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; spin_unlock_irqrestore(&ndlp->lock, iflags); - /* We need to hold the node by incrementing the reference - * count until this queued work is done - */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); + if (phba->worker_thread) { + /* We need to hold the node by incrementing the reference + * count until this queued work is done + */ + evtp->evt_arg1 = lpfc_nlp_get(ndlp); + + spin_lock_irqsave(&phba->hbalock, iflags); + if (evtp->evt_arg1) { + evtp->evt = LPFC_EVT_DEV_LOSS; + list_add_tail(&evtp->evt_listp, &phba->work_list); + lpfc_worker_wake_up(phba); + } + spin_unlock_irqrestore(&phba->hbalock, iflags); + } else { + lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, + "3188 worker thread is stopped %s x%06x, " + " rport x%px flg x%x load_flag x%x refcnt " + "%d\n", __func__, ndlp->nlp_DID, + ndlp->rport, ndlp->nlp_flag, + vport->load_flag, kref_read(&ndlp->kref)); + if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD)) { + spin_lock_irqsave(&ndlp->lock, iflags); + /* Node is in dev loss. No further transaction. */ + ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; + spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_disc_state_machine(vport, ndlp, NULL, + NLP_EVT_DEVICE_RM); + } - spin_lock_irqsave(&phba->hbalock, iflags); - if (evtp->evt_arg1) { - evtp->evt = LPFC_EVT_DEV_LOSS; - list_add_tail(&evtp->evt_listp, &phba->work_list); - lpfc_worker_wake_up(phba); } - spin_unlock_irqrestore(&phba->hbalock, iflags); return; } @@ -503,11 +527,12 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, "0203 Devloss timeout on " "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x " - "NPort x%06x Data: x%x x%x x%x\n", + "NPort x%06x Data: x%x x%x x%x refcnt %d\n", *name, *(name+1), *(name+2), *(name+3), *(name+4), *(name+5), *(name+6), *(name+7), ndlp->nlp_DID, ndlp->nlp_flag, - ndlp->nlp_state, ndlp->nlp_rpi); + ndlp->nlp_state, ndlp->nlp_rpi, + kref_read(&ndlp->kref)); } else { lpfc_printf_vlog(vport, KERN_INFO, LOG_TRACE_EVENT, "0204 Devloss timeout on " @@ -755,18 +780,22 @@ lpfc_work_list_done(struct lpfc_hba *phba) int free_evt; int fcf_inuse; uint32_t nlp_did; + bool hba_pci_err; spin_lock_irq(&phba->hbalock); while (!list_empty(&phba->work_list)) { list_remove_head((&phba->work_list), evtp, typeof(*evtp), evt_listp); spin_unlock_irq(&phba->hbalock); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); free_evt = 1; switch (evtp->evt) { case LPFC_EVT_ELS_RETRY: ndlp = (struct lpfc_nodelist *) (evtp->evt_arg1); - lpfc_els_retry_delay_handler(ndlp); - free_evt = 0; /* evt is part of ndlp */ + if (!hba_pci_err) { + lpfc_els_retry_delay_handler(ndlp); + free_evt = 0; /* evt is part of ndlp */ + } /* decrement the node reference count held * for this queued work */ @@ -788,8 +817,10 @@ lpfc_work_list_done(struct lpfc_hba *phba) break; case LPFC_EVT_RECOVER_PORT: ndlp = (struct lpfc_nodelist *)(evtp->evt_arg1); - lpfc_sli_abts_recover_port(ndlp->vport, ndlp); - free_evt = 0; + if (!hba_pci_err) { + lpfc_sli_abts_recover_port(ndlp->vport, ndlp); + free_evt = 0; + } /* decrement the node reference count held for * this queued work */ @@ -859,14 +890,18 @@ lpfc_work_done(struct lpfc_hba *phba) struct lpfc_vport **vports; struct lpfc_vport *vport; int i; + bool hba_pci_err; + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); spin_lock_irq(&phba->hbalock); ha_copy = phba->work_ha; phba->work_ha = 0; spin_unlock_irq(&phba->hbalock); + if (hba_pci_err) + ha_copy = 0; /* First, try to post the next mailbox command to SLI4 device */ - if (phba->pci_dev_grp == LPFC_PCI_DEV_OC) + if (phba->pci_dev_grp == LPFC_PCI_DEV_OC && !hba_pci_err) lpfc_sli4_post_async_mbox(phba); if (ha_copy & HA_ERATT) { @@ -886,7 +921,7 @@ lpfc_work_done(struct lpfc_hba *phba) lpfc_handle_latt(phba); /* Handle VMID Events */ - if (lpfc_is_vmid_enabled(phba)) { + if (lpfc_is_vmid_enabled(phba) && !hba_pci_err) { if (phba->pport->work_port_events & WORKER_CHECK_VMID_ISSUE_QFPA) { lpfc_check_vmid_qfpa_issue(phba); @@ -936,6 +971,8 @@ lpfc_work_done(struct lpfc_hba *phba) work_port_events = vport->work_port_events; vport->work_port_events &= ~work_port_events; spin_unlock_irq(&vport->work_port_lock); + if (hba_pci_err) + continue; if (work_port_events & WORKER_DISC_TMO) lpfc_disc_timeout_handler(vport); if (work_port_events & WORKER_ELS_TMO) @@ -1173,12 +1210,14 @@ lpfc_linkdown(struct lpfc_hba *phba) struct lpfc_vport **vports; LPFC_MBOXQ_t *mb; int i; + int offline; if (phba->link_state == LPFC_LINK_DOWN) return 0; /* Block all SCSI stack I/Os */ lpfc_scsi_dev_block(phba); + offline = pci_channel_offline(phba->pcidev); phba->defer_flogi_acc_flag = false; @@ -1219,7 +1258,7 @@ lpfc_linkdown(struct lpfc_hba *phba) lpfc_destroy_vport_work_array(phba, vports); /* Clean up any SLI3 firmware default rpi's */ - if (phba->sli_rev > LPFC_SLI_REV3) + if (phba->sli_rev > LPFC_SLI_REV3 || offline) goto skip_unreg_did; mb = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); @@ -4712,6 +4751,11 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) spin_lock_irqsave(&ndlp->lock, iflags); if (!(ndlp->fc4_xpt_flags & NLP_XPT_REGD)) { spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "0999 %s Not regd: ndlp x%px rport x%px DID " + "x%x FLG x%x XPT x%x\n", + __func__, ndlp, ndlp->rport, ndlp->nlp_DID, + ndlp->nlp_flag, ndlp->fc4_xpt_flags); return; } @@ -4722,6 +4766,13 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->fc4_xpt_flags & SCSI_XPT_REGD) { vport->phba->nport_event_cnt++; lpfc_unregister_remote_port(ndlp); + } else if (!ndlp->rport) { + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "1999 %s NDLP in devloss x%px DID x%x FLG x%x" + " XPT x%x refcnt %d\n", + __func__, ndlp, ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->fc4_xpt_flags, + kref_read(&ndlp->kref)); } if (ndlp->fc4_xpt_flags & NVME_XPT_REGD) { @@ -5371,6 +5422,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; mempool_free(mbox, phba->mbox_mem_pool); acc_plogi = 1; + lpfc_nlp_put(ndlp); } } else { lpfc_printf_vlog(vport, KERN_INFO, @@ -6097,12 +6149,34 @@ lpfc_disc_flush_list(struct lpfc_vport *vport) } } +/* + * lpfc_notify_xport_npr - notifies xport of node disappearance + * @vport: Pointer to Virtual Port object. + * + * Transitions all ndlps to NPR state. When lpfc_nlp_set_state + * calls lpfc_nlp_state_cleanup, the ndlp->rport is unregistered + * and transport notified that the node is gone. + * Return Code: + * none + */ +static void +lpfc_notify_xport_npr(struct lpfc_vport *vport) +{ + struct lpfc_nodelist *ndlp, *next_ndlp; + + list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, + nlp_listp) { + lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + } +} void lpfc_cleanup_discovery_resources(struct lpfc_vport *vport) { lpfc_els_flush_rscn(vport); lpfc_els_flush_cmd(vport); lpfc_disc_flush_list(vport); + if (pci_channel_offline(vport->phba->pcidev)) + lpfc_notify_xport_npr(vport); } /*****************************************************************************/ diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index eed6464bd880..461d333b1b3a 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -95,6 +95,7 @@ static void lpfc_sli4_oas_verify(struct lpfc_hba *phba); static uint16_t lpfc_find_cpu_handle(struct lpfc_hba *, uint16_t, int); static void lpfc_setup_bg(struct lpfc_hba *, struct Scsi_Host *); static int lpfc_sli4_cgn_parm_chg_evt(struct lpfc_hba *); +static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba); static struct scsi_transport_template *lpfc_transport_template = NULL; static struct scsi_transport_template *lpfc_vport_transport_template = NULL; @@ -1642,7 +1643,7 @@ lpfc_sli4_offline_eratt(struct lpfc_hba *phba) { spin_lock_irq(&phba->hbalock); if (phba->link_state == LPFC_HBA_ERROR && - phba->hba_flag & HBA_PCI_ERR) { + test_bit(HBA_PCI_ERR, &phba->bit_flags)) { spin_unlock_irq(&phba->hbalock); return; } @@ -1985,6 +1986,7 @@ lpfc_handle_eratt_s4(struct lpfc_hba *phba) if (pci_channel_offline(phba->pcidev)) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "3166 pci channel is offline\n"); + lpfc_sli_flush_io_rings(phba); return; } @@ -2973,6 +2975,22 @@ lpfc_cleanup(struct lpfc_vport *vport) NLP_EVT_DEVICE_RM); } + /* This is a special case flush to return all + * IOs before entering this loop. There are + * two points in the code where a flush is + * avoided if the FC_UNLOADING flag is set. + * one is in the multipool destroy, + * (this prevents a crash) and the other is + * in the nvme abort handler, ( also prevents + * a crash). Both of these exceptions are + * cases where the slot is still accessible. + * The flush here is only when the pci slot + * is offline. + */ + if (vport->load_flag & FC_UNLOADING && + pci_channel_offline(phba->pcidev)) + lpfc_sli_flush_io_rings(vport->phba); + /* At this point, ALL ndlp's should be gone * because of the previous NLP_EVT_DEVICE_RM. * Lets wait for this to happen, if needed. @@ -2985,7 +3003,7 @@ lpfc_cleanup(struct lpfc_vport *vport) list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) { lpfc_printf_vlog(ndlp->vport, KERN_ERR, - LOG_TRACE_EVENT, + LOG_DISCOVERY, "0282 did:x%x ndlp:x%px " "refcnt:%d xflags x%x nflag x%x\n", ndlp->nlp_DID, (void *)ndlp, @@ -3682,7 +3700,8 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) struct lpfc_vport **vports; struct Scsi_Host *shost; int i; - int offline = 0; + int offline; + bool hba_pci_err; if (vport->fc_flag & FC_OFFLINE_MODE) return; @@ -3692,6 +3711,7 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) lpfc_linkdown(phba); offline = pci_channel_offline(phba->pcidev); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); /* Issue an unreg_login to all nodes on all vports */ vports = lpfc_create_vport_work_array(phba); @@ -3715,11 +3735,14 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) ndlp->nlp_flag &= ~NLP_NPR_ADISC; spin_unlock_irq(&ndlp->lock); - if (offline) { + if (offline || hba_pci_err) { spin_lock_irq(&ndlp->lock); ndlp->nlp_flag &= ~(NLP_UNREG_INP | NLP_RPI_REGISTERED); spin_unlock_irq(&ndlp->lock); + if (phba->sli_rev == LPFC_SLI_REV4) + lpfc_sli_rpi_release(vports[i], + ndlp); } else { lpfc_unreg_rpi(vports[i], ndlp); } @@ -13354,8 +13377,9 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Abort all iocbs associated with the hba */ lpfc_sli_hba_iocb_abort(phba); - /* Wait for completion of device XRI exchange busy */ - lpfc_sli4_xri_exchange_busy_wait(phba); + if (!pci_channel_offline(phba->pcidev)) + /* Wait for completion of device XRI exchange busy */ + lpfc_sli4_xri_exchange_busy_wait(phba); /* per-phba callback de-registration for hotplug event */ if (phba->pport) @@ -13374,15 +13398,12 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Disable FW logging to host memory */ lpfc_ras_stop_fwlog(phba); - /* Unset the queues shared with the hardware then release all - * allocated resources. - */ - lpfc_sli4_queue_unset(phba); - lpfc_sli4_queue_destroy(phba); - /* Reset SLI4 HBA FCoE function */ lpfc_pci_function_reset(phba); + /* release all queue allocated resources. */ + lpfc_sli4_queue_destroy(phba); + /* Free RAS DMA memory */ if (phba->ras_fwlog.ras_enabled) lpfc_sli4_ras_dma_free(phba); @@ -14262,6 +14283,7 @@ lpfc_sli_prep_dev_for_perm_failure(struct lpfc_hba *phba) "2711 PCI channel permanent disable for failure\n"); /* Block all SCSI devices' I/Os on the host */ lpfc_scsi_dev_block(phba); + lpfc_sli4_prep_dev_for_reset(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); @@ -15057,24 +15079,28 @@ lpfc_sli4_prep_dev_for_recover(struct lpfc_hba *phba) static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba) { - lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "2826 PCI channel disable preparing for reset\n"); + int offline = pci_channel_offline(phba->pcidev); + + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2826 PCI channel disable preparing for reset offline" + " %d\n", offline); /* Block any management I/Os to the device */ lpfc_block_mgmt_io(phba, LPFC_MBX_NO_WAIT); - /* Block all SCSI devices' I/Os on the host */ - lpfc_scsi_dev_block(phba); + /* HBA_PCI_ERR was set in io_error_detect */ + lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT); /* Flush all driver's outstanding I/Os as we are to reset */ lpfc_sli_flush_io_rings(phba); + lpfc_offline(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); + lpfc_sli4_queue_destroy(phba); /* Disable interrupt and pci device */ lpfc_sli4_disable_intr(phba); - lpfc_sli4_queue_destroy(phba); pci_disable_device(phba->pcidev); } @@ -15123,6 +15149,7 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) { struct Scsi_Host *shost = pci_get_drvdata(pdev); struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; + bool hba_pci_err; switch (state) { case pci_channel_io_normal: @@ -15130,17 +15157,24 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) lpfc_sli4_prep_dev_for_recover(phba); return PCI_ERS_RESULT_CAN_RECOVER; case pci_channel_io_frozen: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Fatal error, prepare for slot reset */ - lpfc_sli4_prep_dev_for_reset(phba); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); + else + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2832 Already handling PCI error " + "state: x%x\n", state); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: - phba->hba_flag |= HBA_PCI_ERR; + set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Permanent failure, prepare for device down */ lpfc_sli4_prep_dev_for_perm_failure(phba); return PCI_ERS_RESULT_DISCONNECT; default: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); /* Unknown state, prepare and request slot reset */ lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "2825 Unknown PCI error state: x%x\n", state); @@ -15174,17 +15208,21 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; struct lpfc_sli *psli = &phba->sli; uint32_t intr_mode; + bool hba_pci_err; dev_printk(KERN_INFO, &pdev->dev, "recovering from a slot reset.\n"); if (pci_enable_device_mem(pdev)) { printk(KERN_ERR "lpfc: Cannot re-enable " - "PCI device after reset.\n"); + "PCI device after reset.\n"); return PCI_ERS_RESULT_DISCONNECT; } pci_restore_state(pdev); - phba->hba_flag &= ~HBA_PCI_ERR; + hba_pci_err = test_and_clear_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + dev_info(&pdev->dev, + "hba_pci_err was not set, recovering slot reset.\n"); /* * As the new kernel behavior of pci_restore_state() API call clears * device saved_state flag, need to save the restored state again. @@ -15198,6 +15236,8 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) psli->sli_flag &= ~LPFC_SLI_ACTIVE; spin_unlock_irq(&phba->hbalock); + /* Init cpu_map array */ + lpfc_cpu_map_array_init(phba); /* Configure and enable interrupt */ intr_mode = lpfc_sli4_enable_intr(phba, phba->intr_mode); if (intr_mode == LPFC_INTR_ERROR) { @@ -15239,8 +15279,6 @@ lpfc_io_resume_s4(struct pci_dev *pdev) */ if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE)) { /* Perform device reset */ - lpfc_offline_prep(phba, LPFC_MBX_WAIT); - lpfc_offline(phba); lpfc_sli_brdrestart(phba); /* Bring the device back online */ lpfc_online(phba); diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 1213a299f9aa..8d26f207ebd2 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -93,6 +93,11 @@ lpfc_nvme_create_queue(struct nvme_fc_local_port *pnvme_lport, lport = (struct lpfc_nvme_lport *)pnvme_lport->private; vport = lport->vport; + + if (!vport || vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; + qhandle = kzalloc(sizeof(struct lpfc_nvme_qhandle), GFP_KERNEL); if (qhandle == NULL) return -ENOMEM; @@ -267,7 +272,8 @@ lpfc_nvme_handle_lsreq(struct lpfc_hba *phba, return -EINVAL; remoteport = lpfc_rport->remoteport; - if (!vport->localport) + if (!vport->localport || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -EINVAL; lport = vport->localport->private; @@ -559,6 +565,8 @@ __lpfc_nvme_ls_req(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_DID, ntype, nstate); return -ENODEV; } + if (vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; if (!vport->phba->sli4_hba.nvmels_wq) return -ENOMEM; @@ -662,7 +670,8 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport, return -EINVAL; vport = lport->vport; - if (vport->load_flag & FC_UNLOADING) + if (vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -ENODEV; atomic_inc(&lport->fc4NvmeLsRequests); @@ -1516,7 +1525,8 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, phba = vport->phba; - if (unlikely(vport->load_flag & FC_UNLOADING)) { + if ((unlikely(vport->load_flag & FC_UNLOADING)) || + phba->hba_flag & HBA_IOQ_FLUSH) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, "6124 Fail IO, Driver unload\n"); atomic_inc(&lport->xmt_fcp_err); @@ -2169,8 +2179,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_nvme = 0; for (i = 0; i < phba->cfg_hdw_queue; i++) { qp = &phba->sli4_hba.hdwq[i]; - if (!vport || !vport->localport || - !qp || !qp->io_wq) + if (!vport->localport || !qp || !qp->io_wq) return; pring = qp->io_wq->pring; @@ -2180,8 +2189,9 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_scsi += qp->abts_scsi_io_bufs; abts_nvme += qp->abts_nvme_io_bufs; } - if (!vport || !vport->localport || - vport->phba->hba_flag & HBA_PCI_ERR) + if (!vport->localport || + test_bit(HBA_PCI_ERR, &vport->phba->bit_flags) || + vport->load_flag & FC_UNLOADING) return; lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, @@ -2541,8 +2551,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) * return values is ignored. The upcall is a courtesy to the * transport. */ - if (vport->load_flag & FC_UNLOADING || - unlikely(vport->phba->hba_flag & HBA_PCI_ERR)) + if (vport->load_flag & FC_UNLOADING) (void)nvme_fc_set_remoteport_devloss(remoteport, 0); ret = nvme_fc_unregister_remoteport(remoteport); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 3c132604fd91..ba9dbb51b75f 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5929,13 +5929,15 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) } lpfc_cmd->waitq = &waitq; - if (phba->sli_rev == LPFC_SLI_REV4) + if (phba->sli_rev == LPFC_SLI_REV4) { spin_unlock(&pring_s4->ring_lock); - else + ret_val = lpfc_sli4_issue_abort_iotag(phba, iocb, + lpfc_sli_abort_fcp_cmpl); + } else { pring = &phba->sli.sli3_ring[LPFC_FCP_RING]; - - ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, - lpfc_sli_abort_fcp_cmpl); + ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, + lpfc_sli_abort_fcp_cmpl); + } /* Make sure HBA is alive */ lpfc_issue_hb_tmo(phba); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 20d40957a385..bda2a7ba4e77 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -2828,6 +2828,12 @@ __lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; } +void +lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) +{ + __lpfc_sli_rpi_release(vport, ndlp); +} + /** * lpfc_sli_def_mbox_cmpl - Default mailbox completion handler * @phba: Pointer to HBA context object. @@ -3715,7 +3721,15 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, unsigned long iflag; u32 ulp_command, ulp_status, ulp_word4, ulp_context, iotag; + if (phba->sli_rev == LPFC_SLI_REV4) + spin_lock_irqsave(&pring->ring_lock, iflag); + else + spin_lock_irqsave(&phba->hbalock, iflag); cmdiocbp = lpfc_sli_iocbq_lookup(phba, pring, saveq); + if (phba->sli_rev == LPFC_SLI_REV4) + spin_unlock_irqrestore(&pring->ring_lock, iflag); + else + spin_unlock_irqrestore(&phba->hbalock, iflag); ulp_command = get_job_cmnd(phba, saveq); ulp_status = get_job_ulpstatus(phba, saveq); @@ -4052,10 +4066,8 @@ lpfc_sli_handle_fast_ring_event(struct lpfc_hba *phba, break; } - spin_unlock_irqrestore(&phba->hbalock, iflag); cmdiocbq = lpfc_sli_iocbq_lookup(phba, pring, &rspiocbq); - spin_lock_irqsave(&phba->hbalock, iflag); if (unlikely(!cmdiocbq)) break; if (cmdiocbq->cmd_flag & LPFC_DRIVER_ABORTED) @@ -4536,42 +4548,62 @@ lpfc_sli_handle_slow_ring_event_s4(struct lpfc_hba *phba, void lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring) { - LIST_HEAD(completions); + LIST_HEAD(tx_completions); + LIST_HEAD(txcmplq_completions); struct lpfc_iocbq *iocb, *next_iocb; + int offline; if (pring->ringno == LPFC_ELS_RING) { lpfc_fabric_abort_hba(phba); } + offline = pci_channel_offline(phba->pcidev); /* Error everything on txq and txcmplq * First do the txq. */ if (phba->sli_rev >= LPFC_SLI_REV4) { spin_lock_irq(&pring->ring_lock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - spin_unlock_irq(&pring->ring_lock); - spin_lock_irq(&phba->hbalock); - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); - spin_unlock_irq(&phba->hbalock); + if (offline) { + list_splice_init(&pring->txcmplq, + &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } + spin_unlock_irq(&pring->ring_lock); } else { spin_lock_irq(&phba->hbalock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); + if (offline) { + list_splice_init(&pring->txcmplq, &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } spin_unlock_irq(&phba->hbalock); } - /* Make sure HBA is alive */ - lpfc_issue_hb_tmo(phba); + if (offline) { + /* Cancel all the IOCBs from the completions list */ + lpfc_sli_cancel_iocbs(phba, &txcmplq_completions, + IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); + } else { + /* Make sure HBA is alive */ + lpfc_issue_hb_tmo(phba); + } /* Cancel all the IOCBs from the completions list */ - lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT, + lpfc_sli_cancel_iocbs(phba, &tx_completions, IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); } @@ -4624,11 +4656,6 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba) struct lpfc_iocbq *piocb, *next_iocb; spin_lock_irq(&phba->hbalock); - if (phba->hba_flag & HBA_IOQ_FLUSH || - !phba->sli4_hba.hdwq) { - spin_unlock_irq(&phba->hbalock); - return; - } /* Indicate the I/O queues are flushed */ phba->hba_flag |= HBA_IOQ_FLUSH; spin_unlock_irq(&phba->hbalock); @@ -10997,6 +11024,10 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number, unsigned long iflags; int rc; + /* If the PCI channel is in offline state, do not post iocbs. */ + if (unlikely(pci_channel_offline(phba->pcidev))) + return IOCB_ERROR; + if (phba->sli_rev == LPFC_SLI_REV4) { lpfc_sli_prep_wqe(phba, piocb); diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index e52f37e5d896..a4d3259b8c52 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "14.2.0.0" +#define LPFC_DRIVER_VERSION "14.2.0.1" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index 611871ef15b5..4919ea54b827 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -2560,6 +2560,9 @@ struct megasas_instance_template { #define MEGASAS_IS_LOGICAL(sdev) \ ((sdev->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1) +#define MEGASAS_IS_LUN_VALID(sdev) \ + (((sdev)->lun == 0) ? 1 : 0) + #define MEGASAS_DEV_INDEX(scp) \ (((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) + \ scp->device->id) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 8bf72dbc33b7..db6793608447 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -2126,6 +2126,9 @@ static int megasas_slave_alloc(struct scsi_device *sdev) goto scan_target; } return -ENXIO; + } else if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return -ENXIO; } scan_target: @@ -2156,6 +2159,10 @@ static void megasas_slave_destroy(struct scsi_device *sdev) instance = megasas_lookup_instance(sdev->host->host_no); if (MEGASAS_IS_LOGICAL(sdev)) { + if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return; + } ld_tgt_id = MEGASAS_TARGET_ID(sdev); instance->ld_tgtid_status[ld_tgt_id] = LD_TARGET_ID_DELETED; if (megasas_dbg_lvl & LD_PD_DEBUG) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index b57f1803371e..538d2c0cd971 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5716,13 +5716,12 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc) /** * mpt3sas_check_same_4gb_region - checks whether all reply queues in a set are * having same upper 32bits in their base memory address. - * @reply_pool_start_address: Base address of a reply queue set + * @start_address: Base address of a reply queue set * @pool_sz: Size of single Reply Descriptor Post Queues pool size * * Return: 1 if reply queues in a set have a same upper 32bits in their base * memory address, else 0. */ - static int mpt3sas_check_same_4gb_region(dma_addr_t start_address, u32 pool_sz) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c index 0563078227de..a8dd14c91efd 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_config.c +++ b/drivers/scsi/mpt3sas/mpt3sas_config.c @@ -394,10 +394,13 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t retry_count++; if (ioc->config_cmds.smid == smid) mpt3sas_base_free_smid(ioc, smid); - if ((ioc->shost_recovery) || (ioc->config_cmds.status & - MPT3_CMD_RESET) || ioc->pci_error_recovery) + if (ioc->config_cmds.status & MPT3_CMD_RESET) goto retry_config; - issue_host_reset = 1; + if (ioc->shost_recovery || ioc->pci_error_recovery) { + issue_host_reset = 0; + r = -EFAULT; + } else + issue_host_reset = 1; goto free_mem; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 00792767c620..7e476f50935b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -11035,6 +11035,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, { struct _sas_port *mpt3sas_port, *next; unsigned long flags; + int port_id; /* remove sibling ports attached to this expander */ list_for_each_entry_safe(mpt3sas_port, next, @@ -11055,6 +11056,8 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, mpt3sas_port->hba_port); } + port_id = sas_expander->port->port_id; + mpt3sas_transport_port_remove(ioc, sas_expander->sas_address, sas_expander->sas_address_parent, sas_expander->port); @@ -11062,7 +11065,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, "expander_remove: handle(0x%04x), sas_addr(0x%016llx), port:%d\n", sas_expander->handle, (unsigned long long) sas_expander->sas_address, - sas_expander->port->port_id); + port_id); spin_lock_irqsave(&ioc->sas_node_lock, flags); list_del(&sas_expander->list); diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c index 7ac63eb5ccd3..2fde496fff5f 100644 --- a/drivers/scsi/mvsas/mv_init.c +++ b/drivers/scsi/mvsas/mv_init.c @@ -647,6 +647,7 @@ static struct pci_device_id mvs_pci_table[] = { { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1300), chip_1300 }, { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1320), chip_1320 }, { PCI_VDEVICE(ADAPTEC2, 0x0450), chip_6440 }, + { PCI_VDEVICE(TTI, 0x2640), chip_6440 }, { PCI_VDEVICE(TTI, 0x2710), chip_9480 }, { PCI_VDEVICE(TTI, 0x2720), chip_9480 }, { PCI_VDEVICE(TTI, 0x2721), chip_9480 }, diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c index c4a838635893..5d7dfefd6f6c 100644 --- a/drivers/scsi/pcmcia/sym53c500_cs.c +++ b/drivers/scsi/pcmcia/sym53c500_cs.c @@ -192,10 +192,11 @@ struct sym53c500_data { int fast_pio; }; -static struct scsi_pointer *sym53c500_scsi_pointer(struct scsi_cmnd *cmd) -{ - return scsi_cmd_priv(cmd); -} +struct sym53c500_cmd_priv { + int status; + int message; + int phase; +}; enum Phase { idle, @@ -356,7 +357,7 @@ SYM53C500_intr(int irq, void *dev_id) struct sym53c500_data *data = (struct sym53c500_data *)dev->hostdata; struct scsi_cmnd *curSC = data->current_SC; - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(curSC); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(curSC); int fast_pio = data->fast_pio; spin_lock_irqsave(dev->host_lock, flags); @@ -403,12 +404,11 @@ SYM53C500_intr(int irq, void *dev_id) if (int_reg & 0x20) { /* Disconnect */ DEB(printk("SYM53C500: disconnect intr received\n")); - if (scsi_pointer->phase != message_in) { /* Unexpected disconnect */ + if (scp->phase != message_in) { /* Unexpected disconnect */ curSC->result = DID_NO_CONNECT << 16; } else { /* Command complete, return status and message */ - curSC->result = (scsi_pointer->Status & 0xff) | - ((scsi_pointer->Message & 0xff) << 8) | - (DID_OK << 16); + curSC->result = (scp->status & 0xff) | + ((scp->message & 0xff) << 8) | (DID_OK << 16); } goto idle_out; } @@ -419,7 +419,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_out; + scp->phase = data_out; VDEB(printk("SYM53C500: Data-Out phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -438,7 +438,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_in; + scp->phase = data_in; VDEB(printk("SYM53C500: Data-In phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -453,12 +453,12 @@ SYM53C500_intr(int irq, void *dev_id) break; case 0x02: /* COMMAND */ - scsi_pointer->phase = command_ph; + scp->phase = command_ph; printk("SYM53C500: Warning: Unknown interrupt occurred in command phase!\n"); break; case 0x03: /* STATUS */ - scsi_pointer->phase = status_ph; + scp->phase = status_ph; VDEB(printk("SYM53C500: Status phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); outb(INIT_CMD_COMPLETE, port_base + CMD_REG); @@ -471,24 +471,22 @@ SYM53C500_intr(int irq, void *dev_id) case 0x06: /* MESSAGE-OUT */ DEB(printk("SYM53C500: Message-Out phase\n")); - scsi_pointer->phase = message_out; + scp->phase = message_out; outb(SET_ATN, port_base + CMD_REG); /* Reject the message */ outb(MSG_ACCEPT, port_base + CMD_REG); break; case 0x07: /* MESSAGE-IN */ VDEB(printk("SYM53C500: Message-In phase\n")); - scsi_pointer->phase = message_in; + scp->phase = message_in; - scsi_pointer->Status = inb(port_base + SCSI_FIFO); - scsi_pointer->Message = inb(port_base + SCSI_FIFO); + scp->status = inb(port_base + SCSI_FIFO); + scp->message = inb(port_base + SCSI_FIFO); VDEB(printk("SCSI FIFO size=%d\n", inb(port_base + FIFO_FLAGS) & 0x1f)); - DEB(printk("Status = %02x Message = %02x\n", - scsi_pointer->Status, scsi_pointer->Message)); + DEB(printk("Status = %02x Message = %02x\n", scp->status, scp->message)); - if (scsi_pointer->Message == SAVE_POINTERS || - scsi_pointer->Message == DISCONNECT) { + if (scp->message == SAVE_POINTERS || scp->message == DISCONNECT) { outb(SET_ATN, port_base + CMD_REG); /* Reject message */ DEB(printk("Discarding SAVE_POINTERS message\n")); } @@ -500,7 +498,7 @@ out: return IRQ_HANDLED; idle_out: - scsi_pointer->phase = idle; + scp->phase = idle; scsi_done(curSC); goto out; } @@ -548,7 +546,7 @@ SYM53C500_info(struct Scsi_Host *SChost) static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) { - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(SCpnt); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(SCpnt); int i; int port_base = SCpnt->device->host->io_port; struct sym53c500_data *data = @@ -565,9 +563,9 @@ static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) VDEB(printk("\n")); data->current_SC = SCpnt; - scsi_pointer->phase = command_ph; - scsi_pointer->Status = 0; - scsi_pointer->Message = 0; + scp->phase = command_ph; + scp->status = 0; + scp->message = 0; /* We are locked here already by the mid layer */ REG0(port_base); @@ -682,7 +680,7 @@ static struct scsi_host_template sym53c500_driver_template = { .this_id = 7, .sg_tablesize = 32, .shost_groups = SYM53C500_shost_groups, - .cmd_size = sizeof(struct scsi_pointer), + .cmd_size = sizeof(struct sym53c500_cmd_priv), }; static int SYM53C500_config_check(struct pcmcia_device *p_dev, void *priv_data) diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index f90b707c190b..01c5e8ff4cc5 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -766,6 +766,10 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha) pm8001_ha->main_cfg_tbl.pm80xx_tbl.pcs_event_log_severity = 0x01; pm8001_ha->main_cfg_tbl.pm80xx_tbl.fatal_err_interrupt = 0x01; + /* Enable higher IQs and OQs, 32 to 63, bit 16 */ + if (pm8001_ha->max_q_num > 32) + pm8001_ha->main_cfg_tbl.pm80xx_tbl.fatal_err_interrupt |= + 1 << 16; /* Disable end to end CRC checking */ pm8001_ha->main_cfg_tbl.pm80xx_tbl.crc_core_dump = (0x1 << 16); @@ -1027,6 +1031,13 @@ static int mpi_init_check(struct pm8001_hba_info *pm8001_ha) if (0x0000 != gst_len_mpistate) return -EBUSY; + /* + * As per controller datasheet, after successful MPI + * initialization minimum 500ms delay is required before + * issuing commands. + */ + msleep(500); + return 0; } @@ -1727,10 +1738,11 @@ static void pm80xx_chip_interrupt_enable(struct pm8001_hba_info *pm8001_ha, u8 vec) { #ifdef PM8001_USE_MSIX - u32 mask; - mask = (u32)(1 << vec); - - pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR, (u32)(mask & 0xFFFFFFFF)); + if (vec < 32) + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR, 1U << vec); + else + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_CLR_U, + 1U << (vec - 32)); return; #endif pm80xx_chip_intx_interrupt_enable(pm8001_ha); @@ -1746,12 +1758,15 @@ static void pm80xx_chip_interrupt_disable(struct pm8001_hba_info *pm8001_ha, u8 vec) { #ifdef PM8001_USE_MSIX - u32 mask; - if (vec == 0xFF) - mask = 0xFFFFFFFF; + if (vec == 0xFF) { + /* disable all vectors 0-31, 32-63 */ + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, 0xFFFFFFFF); + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_U, 0xFFFFFFFF); + } else if (vec < 32) + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, 1U << vec); else - mask = (u32)(1 << vec); - pm8001_cw32(pm8001_ha, 0, MSGU_ODMR, (u32)(mask & 0xFFFFFFFF)); + pm8001_cw32(pm8001_ha, 0, MSGU_ODMR_U, + 1U << (vec - 32)); return; #endif pm80xx_chip_intx_interrupt_disable(pm8001_ha); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 928532180d32..fd674ed1febe 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -3182,124 +3182,6 @@ static int pmcraid_build_ioadl( } /** - * pmcraid_free_sglist - Frees an allocated SG buffer list - * @sglist: scatter/gather list pointer - * - * Free a DMA'able memory previously allocated with pmcraid_alloc_sglist - * - * Return value: - * none - */ -static void pmcraid_free_sglist(struct pmcraid_sglist *sglist) -{ - sgl_free_order(sglist->scatterlist, sglist->order); - kfree(sglist); -} - -/** - * pmcraid_alloc_sglist - Allocates memory for a SG list - * @buflen: buffer length - * - * Allocates a DMA'able buffer in chunks and assembles a scatter/gather - * list. - * - * Return value - * pointer to sglist / NULL on failure - */ -static struct pmcraid_sglist *pmcraid_alloc_sglist(int buflen) -{ - struct pmcraid_sglist *sglist; - int sg_size; - int order; - - sg_size = buflen / (PMCRAID_MAX_IOADLS - 1); - order = (sg_size > 0) ? get_order(sg_size) : 0; - - /* Allocate a scatter/gather list for the DMA */ - sglist = kzalloc(sizeof(struct pmcraid_sglist), GFP_KERNEL); - if (sglist == NULL) - return NULL; - - sglist->order = order; - sgl_alloc_order(buflen, order, false, GFP_KERNEL | __GFP_ZERO, - &sglist->num_sg); - - return sglist; -} - -/** - * pmcraid_copy_sglist - Copy user buffer to kernel buffer's SG list - * @sglist: scatter/gather list pointer - * @buffer: buffer pointer - * @len: buffer length - * @direction: data transfer direction - * - * Copy a user buffer into a buffer allocated by pmcraid_alloc_sglist - * - * Return value: - * 0 on success / other on failure - */ -static int pmcraid_copy_sglist( - struct pmcraid_sglist *sglist, - void __user *buffer, - u32 len, - int direction -) -{ - struct scatterlist *sg; - void *kaddr; - int bsize_elem; - int i; - int rc = 0; - - /* Determine the actual number of bytes per element */ - bsize_elem = PAGE_SIZE * (1 << sglist->order); - - sg = sglist->scatterlist; - - for (i = 0; i < (len / bsize_elem); i++, sg = sg_next(sg), buffer += bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, bsize_elem); - else - rc = copy_to_user(buffer, kaddr, bsize_elem); - - kunmap(page); - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - return -EFAULT; - } - - sg->length = bsize_elem; - } - - if (len % bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, len % bsize_elem); - else - rc = copy_to_user(buffer, kaddr, len % bsize_elem); - - kunmap(page); - - sg->length = len % bsize_elem; - } - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - rc = -EFAULT; - } - - return rc; -} - -/** * pmcraid_queuecommand_lck - Queue a mid-layer request * @scsi_cmd: scsi command struct * @@ -3454,365 +3336,6 @@ static int pmcraid_chr_fasync(int fd, struct file *filep, int mode) return rc; } - -/** - * pmcraid_build_passthrough_ioadls - builds SG elements for passthrough - * commands sent over IOCTL interface - * - * @cmd : pointer to struct pmcraid_cmd - * @buflen : length of the request buffer - * @direction : data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static int pmcraid_build_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = NULL; - struct scatterlist *sg = NULL; - struct pmcraid_ioarcb *ioarcb = &cmd->ioa_cb->ioarcb; - struct pmcraid_ioadl_desc *ioadl; - int i; - - sglist = pmcraid_alloc_sglist(buflen); - - if (!sglist) { - pmcraid_err("can't allocate memory for passthrough SGls\n"); - return -ENOMEM; - } - - sglist->num_dma_sg = dma_map_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, direction); - - if (!sglist->num_dma_sg || sglist->num_dma_sg > PMCRAID_MAX_IOADLS) { - dev_err(&cmd->drv_inst->pdev->dev, - "Failed to map passthrough buffer!\n"); - pmcraid_free_sglist(sglist); - return -EIO; - } - - cmd->sglist = sglist; - ioarcb->request_flags0 |= NO_LINK_DESCS; - - ioadl = pmcraid_init_ioadls(cmd, sglist->num_dma_sg); - - /* Initialize IOADL descriptor addresses */ - for_each_sg(sglist->scatterlist, sg, sglist->num_dma_sg, i) { - ioadl[i].data_len = cpu_to_le32(sg_dma_len(sg)); - ioadl[i].address = cpu_to_le64(sg_dma_address(sg)); - ioadl[i].flags = 0; - } - - /* setup the last descriptor */ - ioadl[i - 1].flags = IOADL_FLAGS_LAST_DESC; - - return 0; -} - - -/** - * pmcraid_release_passthrough_ioadls - release passthrough ioadls - * - * @cmd: pointer to struct pmcraid_cmd for which ioadls were allocated - * @buflen: size of the request buffer - * @direction: data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static void pmcraid_release_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = cmd->sglist; - - if (buflen > 0) { - dma_unmap_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, - direction); - pmcraid_free_sglist(sglist); - cmd->sglist = NULL; - } -} - -/** - * pmcraid_ioctl_passthrough - handling passthrough IOCTL commands - * - * @pinstance: pointer to adapter instance structure - * @ioctl_cmd: ioctl code - * @buflen: unused - * @arg: pointer to pmcraid_passthrough_buffer user buffer - * - * Return value - * 0 on success, non-zero error code on failure - */ -static long pmcraid_ioctl_passthrough( - struct pmcraid_instance *pinstance, - unsigned int ioctl_cmd, - unsigned int buflen, - void __user *arg -) -{ - struct pmcraid_passthrough_ioctl_buffer *buffer; - struct pmcraid_ioarcb *ioarcb; - struct pmcraid_cmd *cmd; - struct pmcraid_cmd *cancel_cmd; - void __user *request_buffer; - unsigned long request_offset; - unsigned long lock_flags; - void __user *ioasa; - u32 ioasc; - int request_size; - int buffer_size; - u8 direction; - int rc = 0; - - /* If IOA reset is in progress, wait 10 secs for reset to complete */ - if (pinstance->ioa_reset_in_progress) { - rc = wait_event_interruptible_timeout( - pinstance->reset_wait_q, - !pinstance->ioa_reset_in_progress, - msecs_to_jiffies(10000)); - - if (!rc) - return -ETIMEDOUT; - else if (rc < 0) - return -ERESTARTSYS; - } - - /* If adapter is not in operational state, return error */ - if (pinstance->ioa_state != IOA_STATE_OPERATIONAL) { - pmcraid_err("IOA is not operational\n"); - return -ENOTTY; - } - - buffer_size = sizeof(struct pmcraid_passthrough_ioctl_buffer); - buffer = kmalloc(buffer_size, GFP_KERNEL); - - if (!buffer) { - pmcraid_err("no memory for passthrough buffer\n"); - return -ENOMEM; - } - - request_offset = - offsetof(struct pmcraid_passthrough_ioctl_buffer, request_buffer); - - request_buffer = arg + request_offset; - - rc = copy_from_user(buffer, arg, - sizeof(struct pmcraid_passthrough_ioctl_buffer)); - - ioasa = arg + offsetof(struct pmcraid_passthrough_ioctl_buffer, ioasa); - - if (rc) { - pmcraid_err("ioctl: can't copy passthrough buffer\n"); - rc = -EFAULT; - goto out_free_buffer; - } - - request_size = le32_to_cpu(buffer->ioarcb.data_transfer_length); - - if (buffer->ioarcb.request_flags0 & TRANSFER_DIR_WRITE) { - direction = DMA_TO_DEVICE; - } else { - direction = DMA_FROM_DEVICE; - } - - if (request_size < 0) { - rc = -EINVAL; - goto out_free_buffer; - } - - /* check if we have any additional command parameters */ - if (le16_to_cpu(buffer->ioarcb.add_cmd_param_length) - > PMCRAID_ADD_CMD_PARAM_LEN) { - rc = -EINVAL; - goto out_free_buffer; - } - - cmd = pmcraid_get_free_cmd(pinstance); - - if (!cmd) { - pmcraid_err("free command block is not available\n"); - rc = -ENOMEM; - goto out_free_buffer; - } - - cmd->scsi_cmd = NULL; - ioarcb = &(cmd->ioa_cb->ioarcb); - - /* Copy the user-provided IOARCB stuff field by field */ - ioarcb->resource_handle = buffer->ioarcb.resource_handle; - ioarcb->data_transfer_length = buffer->ioarcb.data_transfer_length; - ioarcb->cmd_timeout = buffer->ioarcb.cmd_timeout; - ioarcb->request_type = buffer->ioarcb.request_type; - ioarcb->request_flags0 = buffer->ioarcb.request_flags0; - ioarcb->request_flags1 = buffer->ioarcb.request_flags1; - memcpy(ioarcb->cdb, buffer->ioarcb.cdb, PMCRAID_MAX_CDB_LEN); - - if (buffer->ioarcb.add_cmd_param_length) { - ioarcb->add_cmd_param_length = - buffer->ioarcb.add_cmd_param_length; - ioarcb->add_cmd_param_offset = - buffer->ioarcb.add_cmd_param_offset; - memcpy(ioarcb->add_data.u.add_cmd_params, - buffer->ioarcb.add_data.u.add_cmd_params, - le16_to_cpu(buffer->ioarcb.add_cmd_param_length)); - } - - /* set hrrq number where the IOA should respond to. Note that all cmds - * generated internally uses hrrq_id 0, exception to this is the cmd - * block of scsi_cmd which is re-used (e.g. cancel/abort), which uses - * hrrq_id assigned here in queuecommand - */ - ioarcb->hrrq_id = atomic_add_return(1, &(pinstance->last_message_id)) % - pinstance->num_hrrq; - - if (request_size) { - rc = pmcraid_build_passthrough_ioadls(cmd, - request_size, - direction); - if (rc) { - pmcraid_err("couldn't build passthrough ioadls\n"); - goto out_free_cmd; - } - } - - /* If data is being written into the device, copy the data from user - * buffers - */ - if (direction == DMA_TO_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - goto out_free_sglist; - } - } - - /* passthrough ioctl is a blocking command so, put the user to sleep - * until timeout. Note that a timeout value of 0 means, do timeout. - */ - cmd->cmd_done = pmcraid_internal_done; - init_completion(&cmd->wait_for_completion); - cmd->completion_req = 1; - - pmcraid_info("command(%d) (CDB[0] = %x) for %x\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0], - le32_to_cpu(cmd->ioa_cb->ioarcb.resource_handle)); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - _pmcraid_fire_command(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - /* NOTE ! Remove the below line once abort_task is implemented - * in firmware. This line disables ioctl command timeout handling logic - * similar to IO command timeout handling, making ioctl commands to wait - * until the command completion regardless of timeout value specified in - * ioarcb - */ - buffer->ioarcb.cmd_timeout = 0; - - /* If command timeout is specified put caller to wait till that time, - * otherwise it would be blocking wait. If command gets timed out, it - * will be aborted. - */ - if (buffer->ioarcb.cmd_timeout == 0) { - wait_for_completion(&cmd->wait_for_completion); - } else if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(le16_to_cpu(buffer->ioarcb.cmd_timeout) * 1000))) { - - pmcraid_info("aborting cmd %d (CDB[0] = %x) due to timeout\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0]); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - cancel_cmd = pmcraid_abort_cmd(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - if (cancel_cmd) { - wait_for_completion(&cancel_cmd->wait_for_completion); - ioasc = le32_to_cpu(cancel_cmd->ioa_cb->ioasa.ioasc); - pmcraid_return_cmd(cancel_cmd); - - /* if abort task couldn't find the command i.e it got - * completed prior to aborting, return good completion. - * if command got aborted successfully or there was IOA - * reset due to abort task itself getting timedout then - * return -ETIMEDOUT - */ - if (ioasc == PMCRAID_IOASC_IOA_WAS_RESET || - PMCRAID_IOASC_SENSE_KEY(ioasc) == 0x00) { - if (ioasc != PMCRAID_IOASC_GC_IOARCB_NOTFOUND) - rc = -ETIMEDOUT; - goto out_handle_response; - } - } - - /* no command block for abort task or abort task failed to abort - * the IOARCB, then wait for 150 more seconds and initiate reset - * sequence after timeout - */ - if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(150 * 1000))) { - pmcraid_reset_bringup(cmd->drv_inst); - rc = -ETIMEDOUT; - } - } - -out_handle_response: - /* copy entire IOASA buffer and return IOCTL success. - * If copying IOASA to user-buffer fails, return - * EFAULT - */ - if (copy_to_user(ioasa, &cmd->ioa_cb->ioasa, - sizeof(struct pmcraid_ioasa))) { - pmcraid_err("failed to copy ioasa buffer to user\n"); - rc = -EFAULT; - } - - /* If the data transfer was from device, copy the data onto user - * buffers - */ - else if (direction == DMA_FROM_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - rc = -EFAULT; - } - } - -out_free_sglist: - pmcraid_release_passthrough_ioadls(cmd, request_size, direction); - -out_free_cmd: - pmcraid_return_cmd(cmd); - -out_free_buffer: - kfree(buffer); - - return rc; -} - - - - /** * pmcraid_ioctl_driver - ioctl handler for commands handled by driver itself * @@ -3922,20 +3445,6 @@ static long pmcraid_chr_ioctl( switch (_IOC_TYPE(cmd)) { - case PMCRAID_PASSTHROUGH_IOCTL: - /* If ioctl code is to download microcode, we need to block - * mid-layer requests. - */ - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_block_requests(pinstance->host); - - retval = pmcraid_ioctl_passthrough(pinstance, cmd, - hdr->buffer_length, argp); - - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_unblock_requests(pinstance->host); - break; - case PMCRAID_DRIVER_IOCTL: arg += sizeof(struct pmcraid_ioctl_header); retval = pmcraid_ioctl_driver(pinstance, cmd, diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h index bbb75318f1e7..9f59930e8b4f 100644 --- a/drivers/scsi/pmcraid.h +++ b/drivers/scsi/pmcraid.h @@ -1023,40 +1023,15 @@ struct pmcraid_ioctl_header { #define PMCRAID_IOCTL_SIGNATURE "PMCRAID" /* - * pmcraid_passthrough_ioctl_buffer - structure given as argument to - * passthrough(or firmware handled) IOCTL commands. Note that ioarcb requires - * 32-byte alignment so, it is necessary to pack this structure to avoid any - * holes between ioctl_header and passthrough buffer - * - * .ioactl_header : ioctl header - * .ioarcb : filled-up ioarcb buffer, driver always reads this buffer - * .ioasa : buffer for ioasa, driver fills this with IOASA from firmware - * .request_buffer: The I/O buffer (flat), driver reads/writes to this based on - * the transfer directions passed in ioarcb.flags0. Contents - * of this buffer are valid only when ioarcb.data_transfer_len - * is not zero. - */ -struct pmcraid_passthrough_ioctl_buffer { - struct pmcraid_ioctl_header ioctl_header; - struct pmcraid_ioarcb ioarcb; - struct pmcraid_ioasa ioasa; - u8 request_buffer[]; -} __attribute__ ((packed, aligned(PMCRAID_IOARCB_ALIGNMENT))); - -/* * keys to differentiate between driver handled IOCTLs and passthrough * IOCTLs passed to IOA. driver determines the ioctl type using macro * _IOC_TYPE */ #define PMCRAID_DRIVER_IOCTL 'D' -#define PMCRAID_PASSTHROUGH_IOCTL 'F' #define DRV_IOCTL(n, size) \ _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_DRIVER_IOCTL, (n), (size)) -#define FMW_IOCTL(n, size) \ - _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_PASSTHROUGH_IOCTL, (n), (size)) - /* * _ARGSIZE: macro that gives size of the argument type passed to an IOCTL cmd. * This is to facilitate applications avoiding un-necessary memory allocations. @@ -1069,12 +1044,4 @@ struct pmcraid_passthrough_ioctl_buffer { #define PMCRAID_IOCTL_RESET_ADAPTER \ DRV_IOCTL(5, sizeof(struct pmcraid_ioctl_header)) -/* passthrough/firmware handled commands */ -#define PMCRAID_IOCTL_PASSTHROUGH_COMMAND \ - FMW_IOCTL(1, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - -#define PMCRAID_IOCTL_DOWNLOAD_MICROCODE \ - FMW_IOCTL(2, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - - #endif /* _PMCRAID_H */ diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 8196f89f404e..31ec429104e2 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -860,6 +860,37 @@ static int qedi_task_xmit(struct iscsi_task *task) return qedi_iscsi_send_ioreq(task); } +static void qedi_offload_work(struct work_struct *work) +{ + struct qedi_endpoint *qedi_ep = + container_of(work, struct qedi_endpoint, offload_work); + struct qedi_ctx *qedi; + int wait_delay = 5 * HZ; + int ret; + + qedi = qedi_ep->qedi; + + ret = qedi_iscsi_offload_conn(qedi_ep); + if (ret) { + QEDI_ERR(&qedi->dbg_ctx, + "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n", + qedi_ep->iscsi_cid, qedi_ep, ret); + qedi_ep->state = EP_STATE_OFLDCONN_FAILED; + return; + } + + ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait, + (qedi_ep->state == + EP_STATE_OFLDCONN_COMPL), + wait_delay); + if (ret <= 0 || qedi_ep->state != EP_STATE_OFLDCONN_COMPL) { + qedi_ep->state = EP_STATE_OFLDCONN_FAILED; + QEDI_ERR(&qedi->dbg_ctx, + "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n", + qedi_ep->iscsi_cid, qedi_ep); + } +} + static struct iscsi_endpoint * qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, int non_blocking) @@ -908,6 +939,7 @@ qedi_ep_connect(struct Scsi_Host *shost, struct sockaddr *dst_addr, } qedi_ep = ep->dd_data; memset(qedi_ep, 0, sizeof(struct qedi_endpoint)); + INIT_WORK(&qedi_ep->offload_work, qedi_offload_work); qedi_ep->state = EP_STATE_IDLE; qedi_ep->iscsi_cid = (u32)-1; qedi_ep->qedi = qedi; @@ -1056,12 +1088,11 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) qedi_ep = ep->dd_data; qedi = qedi_ep->qedi; + flush_work(&qedi_ep->offload_work); + if (qedi_ep->state == EP_STATE_OFLDCONN_START) goto ep_exit_recover; - if (qedi_ep->state != EP_STATE_OFLDCONN_NONE) - flush_work(&qedi_ep->offload_work); - if (qedi_ep->conn) { qedi_conn = qedi_ep->conn; abrt_conn = qedi_conn->abrt_conn; @@ -1235,37 +1266,6 @@ static int qedi_data_avail(struct qedi_ctx *qedi, u16 vlanid) return rc; } -static void qedi_offload_work(struct work_struct *work) -{ - struct qedi_endpoint *qedi_ep = - container_of(work, struct qedi_endpoint, offload_work); - struct qedi_ctx *qedi; - int wait_delay = 5 * HZ; - int ret; - - qedi = qedi_ep->qedi; - - ret = qedi_iscsi_offload_conn(qedi_ep); - if (ret) { - QEDI_ERR(&qedi->dbg_ctx, - "offload error: iscsi_cid=%u, qedi_ep=%p, ret=%d\n", - qedi_ep->iscsi_cid, qedi_ep, ret); - qedi_ep->state = EP_STATE_OFLDCONN_FAILED; - return; - } - - ret = wait_event_interruptible_timeout(qedi_ep->tcp_ofld_wait, - (qedi_ep->state == - EP_STATE_OFLDCONN_COMPL), - wait_delay); - if ((ret <= 0) || (qedi_ep->state != EP_STATE_OFLDCONN_COMPL)) { - qedi_ep->state = EP_STATE_OFLDCONN_FAILED; - QEDI_ERR(&qedi->dbg_ctx, - "Offload conn TIMEOUT iscsi_cid=%u, qedi_ep=%p\n", - qedi_ep->iscsi_cid, qedi_ep); - } -} - static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) { struct qedi_ctx *qedi; @@ -1381,7 +1381,6 @@ static int qedi_set_path(struct Scsi_Host *shost, struct iscsi_path *path_data) qedi_ep->dst_addr, qedi_ep->dst_port); } - INIT_WORK(&qedi_ep->offload_work, qedi_offload_work); queue_work(qedi->offload_thread, &qedi_ep->offload_work); ret = 0; diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index c607755cce00..592a290e6cfa 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -32,7 +32,6 @@ #include <linux/blkdev.h> #include <linux/crc-t10dif.h> #include <linux/spinlock.h> -#include <linux/mutex.h> #include <linux/interrupt.h> #include <linux/atomic.h> #include <linux/hrtimer.h> @@ -732,9 +731,7 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEM_P1 + 1] = { {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} }, }; -static atomic_t sdebug_num_hosts; -static DEFINE_MUTEX(add_host_mutex); - +static int sdebug_num_hosts; static int sdebug_add_host = DEF_NUM_HOST; /* in sysfs this is relative */ static int sdebug_ato = DEF_ATO; static int sdebug_cdb_len = DEF_CDB_LEN; @@ -781,7 +778,6 @@ static int sdebug_uuid_ctl = DEF_UUID_CTL; static bool sdebug_random = DEF_RANDOM; static bool sdebug_per_host_store = DEF_PER_HOST_STORE; static bool sdebug_removable = DEF_REMOVABLE; -static bool sdebug_deflect_incoming; static bool sdebug_clustering; static bool sdebug_host_lock = DEF_HOST_LOCK; static bool sdebug_strict = DEF_STRICT; @@ -5122,10 +5118,6 @@ static int scsi_debug_slave_configure(struct scsi_device *sdp) sdp->host->host_no, sdp->channel, sdp->id, sdp->lun); if (sdp->host->max_cmd_len != SDEBUG_MAX_CMD_LEN) sdp->host->max_cmd_len = SDEBUG_MAX_CMD_LEN; - if (smp_load_acquire(&sdebug_deflect_incoming)) { - pr_info("Exit early due to deflect_incoming\n"); - return 1; - } if (devip == NULL) { devip = find_build_dev_info(sdp); if (devip == NULL) @@ -5211,7 +5203,7 @@ static bool stop_queued_cmnd(struct scsi_cmnd *cmnd) } /* Deletes (stops) timers or work queues of all queued commands */ -static void stop_all_queued(bool done_with_no_conn) +static void stop_all_queued(void) { unsigned long iflags; int j, k; @@ -5220,15 +5212,13 @@ static void stop_all_queued(bool done_with_no_conn) struct sdebug_queued_cmd *sqcp; struct sdebug_dev_info *devip; struct sdebug_defer *sd_dp; - struct scsi_cmnd *scp; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { spin_lock_irqsave(&sqp->qc_lock, iflags); for (k = 0; k < SDEBUG_CANQUEUE; ++k) { if (test_bit(k, sqp->in_use_bm)) { sqcp = &sqp->qc_arr[k]; - scp = sqcp->a_cmnd; - if (!scp) + if (sqcp->a_cmnd == NULL) continue; devip = (struct sdebug_dev_info *) sqcp->a_cmnd->device->hostdata; @@ -5243,10 +5233,6 @@ static void stop_all_queued(bool done_with_no_conn) l_defer_t = SDEB_DEFER_NONE; spin_unlock_irqrestore(&sqp->qc_lock, iflags); stop_qc_helper(sd_dp, l_defer_t); - if (done_with_no_conn && l_defer_t != SDEB_DEFER_NONE) { - scp->result = DID_NO_CONNECT << 16; - scsi_done(scp); - } clear_bit(k, sqp->in_use_bm); spin_lock_irqsave(&sqp->qc_lock, iflags); } @@ -5389,7 +5375,7 @@ static int scsi_debug_host_reset(struct scsi_cmnd *SCpnt) } } spin_unlock(&sdebug_host_list_lock); - stop_all_queued(false); + stop_all_queued(); if (SDEBUG_OPT_RESET_NOISE & sdebug_opts) sdev_printk(KERN_INFO, SCpnt->device, "%s: %d device(s) found\n", __func__, k); @@ -5449,50 +5435,13 @@ static void sdebug_build_parts(unsigned char *ramp, unsigned long store_size) } } -static void sdeb_block_all_queues(void) -{ - int j; - struct sdebug_queue *sqp; - - for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) - atomic_set(&sqp->blocked, (int)true); -} - -static void sdeb_unblock_all_queues(void) +static void block_unblock_all_queues(bool block) { int j; struct sdebug_queue *sqp; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) - atomic_set(&sqp->blocked, (int)false); -} - -static void -sdeb_add_n_hosts(int num_hosts) -{ - if (num_hosts < 1) - return; - do { - bool found; - unsigned long idx; - struct sdeb_store_info *sip; - bool want_phs = (sdebug_fake_rw == 0) && sdebug_per_host_store; - - found = false; - if (want_phs) { - xa_for_each_marked(per_store_ap, idx, sip, SDEB_XA_NOT_IN_USE) { - sdeb_most_recent_idx = (int)idx; - found = true; - break; - } - if (found) /* re-use case */ - sdebug_add_host_helper((int)idx); - else - sdebug_do_add_host(true /* make new store */); - } else { - sdebug_do_add_host(false); - } - } while (--num_hosts); + atomic_set(&sqp->blocked, (int)block); } /* Adjust (by rounding down) the sdebug_cmnd_count so abs(every_nth)-1 @@ -5505,10 +5454,10 @@ static void tweak_cmnd_count(void) modulo = abs(sdebug_every_nth); if (modulo < 2) return; - sdeb_block_all_queues(); + block_unblock_all_queues(true); count = atomic_read(&sdebug_cmnd_count); atomic_set(&sdebug_cmnd_count, (count / modulo) * modulo); - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } static void clear_queue_stats(void) @@ -5526,15 +5475,6 @@ static bool inject_on_this_cmd(void) return (atomic_read(&sdebug_cmnd_count) % abs(sdebug_every_nth)) == 0; } -static int process_deflect_incoming(struct scsi_cmnd *scp) -{ - u8 opcode = scp->cmnd[0]; - - if (opcode == SYNCHRONIZE_CACHE || opcode == SYNCHRONIZE_CACHE_16) - return 0; - return DID_NO_CONNECT << 16; -} - #define INCLUSIVE_TIMING_MAX_NS 1000000 /* 1 millisecond */ /* Complete the processing of the thread that queued a SCSI command to this @@ -5544,7 +5484,8 @@ static int process_deflect_incoming(struct scsi_cmnd *scp) */ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, int scsi_result, - int (*pfp)(struct scsi_cmnd *, struct sdebug_dev_info *), + int (*pfp)(struct scsi_cmnd *, + struct sdebug_dev_info *), int delta_jiff, int ndelay) { bool new_sd_dp; @@ -5565,27 +5506,13 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, } sdp = cmnd->device; - if (delta_jiff == 0) { - sqp = get_queue(cmnd); - if (atomic_read(&sqp->blocked)) { - if (smp_load_acquire(&sdebug_deflect_incoming)) - return process_deflect_incoming(cmnd); - else - return SCSI_MLQUEUE_HOST_BUSY; - } + if (delta_jiff == 0) goto respond_in_thread; - } sqp = get_queue(cmnd); spin_lock_irqsave(&sqp->qc_lock, iflags); if (unlikely(atomic_read(&sqp->blocked))) { spin_unlock_irqrestore(&sqp->qc_lock, iflags); - if (smp_load_acquire(&sdebug_deflect_incoming)) { - scsi_result = process_deflect_incoming(cmnd); - goto respond_in_thread; - } - if (sdebug_verbose) - pr_info("blocked --> SCSI_MLQUEUE_HOST_BUSY\n"); return SCSI_MLQUEUE_HOST_BUSY; } num_in_q = atomic_read(&devip->num_in_q); @@ -5774,12 +5701,8 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, respond_in_thread: /* call back to mid-layer using invocation thread */ cmnd->result = pfp != NULL ? pfp(cmnd, devip) : 0; cmnd->result &= ~SDEG_RES_IMMED_MASK; - if (cmnd->result == 0 && scsi_result != 0) { + if (cmnd->result == 0 && scsi_result != 0) cmnd->result = scsi_result; - if (sdebug_verbose) - pr_info("respond_in_thread: tag=0x%x, scp->result=0x%x\n", - blk_mq_unique_tag(scsi_cmd_to_rq(cmnd)), scsi_result); - } scsi_done(cmnd); return 0; } @@ -6064,7 +5987,7 @@ static ssize_t delay_store(struct device_driver *ddp, const char *buf, int j, k; struct sdebug_queue *sqp; - sdeb_block_all_queues(); + block_unblock_all_queues(true); for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { k = find_first_bit(sqp->in_use_bm, @@ -6078,7 +6001,7 @@ static ssize_t delay_store(struct device_driver *ddp, const char *buf, sdebug_jdelay = jdelay; sdebug_ndelay = 0; } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } return res; } @@ -6104,7 +6027,7 @@ static ssize_t ndelay_store(struct device_driver *ddp, const char *buf, int j, k; struct sdebug_queue *sqp; - sdeb_block_all_queues(); + block_unblock_all_queues(true); for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { k = find_first_bit(sqp->in_use_bm, @@ -6119,7 +6042,7 @@ static ssize_t ndelay_store(struct device_driver *ddp, const char *buf, sdebug_jdelay = ndelay ? JDELAY_OVERRIDDEN : DEF_JDELAY; } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); } return res; } @@ -6433,7 +6356,7 @@ static ssize_t max_queue_store(struct device_driver *ddp, const char *buf, if ((count > 0) && (1 == sscanf(buf, "%d", &n)) && (n > 0) && (n <= SDEBUG_CANQUEUE) && (sdebug_host_max_queue == 0)) { - sdeb_block_all_queues(); + block_unblock_all_queues(true); k = 0; for (j = 0, sqp = sdebug_q_arr; j < submit_queues; ++j, ++sqp) { @@ -6448,7 +6371,7 @@ static ssize_t max_queue_store(struct device_driver *ddp, const char *buf, atomic_set(&retired_max_queue, k + 1); else atomic_set(&retired_max_queue, 0); - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return count; } return -EINVAL; @@ -6537,48 +6460,43 @@ static DRIVER_ATTR_RW(virtual_gb); static ssize_t add_host_show(struct device_driver *ddp, char *buf) { /* absolute number of hosts currently active is what is shown */ - return scnprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&sdebug_num_hosts)); + return scnprintf(buf, PAGE_SIZE, "%d\n", sdebug_num_hosts); } -/* - * Accept positive and negative values. Hex values (only positive) may be prefixed by '0x'. - * To remove all hosts use a large negative number (e.g. -9999). The value 0 does nothing. - * Returns -EBUSY if another add_host sysfs invocation is active. - */ static ssize_t add_host_store(struct device_driver *ddp, const char *buf, size_t count) { + bool found; + unsigned long idx; + struct sdeb_store_info *sip; + bool want_phs = (sdebug_fake_rw == 0) && sdebug_per_host_store; int delta_hosts; - if (count == 0 || kstrtoint(buf, 0, &delta_hosts)) + if (sscanf(buf, "%d", &delta_hosts) != 1) return -EINVAL; - if (sdebug_verbose) - pr_info("prior num_hosts=%d, num_to_add=%d\n", - atomic_read(&sdebug_num_hosts), delta_hosts); - if (delta_hosts == 0) - return count; - if (mutex_trylock(&add_host_mutex) == 0) - return -EBUSY; if (delta_hosts > 0) { - sdeb_add_n_hosts(delta_hosts); - } else if (delta_hosts < 0) { - smp_store_release(&sdebug_deflect_incoming, true); - sdeb_block_all_queues(); - if (delta_hosts >= atomic_read(&sdebug_num_hosts)) - stop_all_queued(true); do { - if (atomic_read(&sdebug_num_hosts) < 1) { - free_all_queued(); - break; + found = false; + if (want_phs) { + xa_for_each_marked(per_store_ap, idx, sip, + SDEB_XA_NOT_IN_USE) { + sdeb_most_recent_idx = (int)idx; + found = true; + break; + } + if (found) /* re-use case */ + sdebug_add_host_helper((int)idx); + else + sdebug_do_add_host(true); + } else { + sdebug_do_add_host(false); } + } while (--delta_hosts); + } else if (delta_hosts < 0) { + do { sdebug_do_remove_host(false); } while (++delta_hosts); - sdeb_unblock_all_queues(); - smp_store_release(&sdebug_deflect_incoming, false); } - mutex_unlock(&add_host_mutex); - if (sdebug_verbose) - pr_info("post num_hosts=%d\n", atomic_read(&sdebug_num_hosts)); return count; } static DRIVER_ATTR_RW(add_host); @@ -7089,10 +7007,6 @@ static int __init scsi_debug_init(void) sdebug_add_host = 0; for (k = 0; k < hosts_to_add; k++) { - if (smp_load_acquire(&sdebug_deflect_incoming)) { - pr_info("exit early as sdebug_deflect_incoming is set\n"); - return 0; - } if (want_store && k == 0) { ret = sdebug_add_host_helper(idx); if (ret < 0) { @@ -7110,12 +7024,8 @@ static int __init scsi_debug_init(void) } } if (sdebug_verbose) - pr_info("built %d host(s)\n", atomic_read(&sdebug_num_hosts)); + pr_info("built %d host(s)\n", sdebug_num_hosts); - /* - * Even though all the hosts have been established, due to async device (LU) scanning - * by the scsi mid-level, there may still be devices (LUs) being set up. - */ return 0; bus_unreg: @@ -7131,17 +7041,12 @@ free_q_arr: static void __exit scsi_debug_exit(void) { - int k; + int k = sdebug_num_hosts; - /* Possible race with LUs still being set up; stop them asap */ - sdeb_block_all_queues(); - smp_store_release(&sdebug_deflect_incoming, true); - stop_all_queued(false); - for (k = 0; atomic_read(&sdebug_num_hosts) > 0; k++) + stop_all_queued(); + for (; k; k--) sdebug_do_remove_host(true); free_all_queued(); - if (sdebug_verbose) - pr_info("removed %d hosts\n", k); driver_unregister(&sdebug_driverfs_driver); bus_unregister(&pseudo_lld_bus); root_device_unregister(pseudo_primary); @@ -7311,13 +7216,13 @@ static int sdebug_add_host_helper(int per_host_idx) sdbg_host->dev.bus = &pseudo_lld_bus; sdbg_host->dev.parent = pseudo_primary; sdbg_host->dev.release = &sdebug_release_adapter; - dev_set_name(&sdbg_host->dev, "adapter%d", atomic_read(&sdebug_num_hosts)); + dev_set_name(&sdbg_host->dev, "adapter%d", sdebug_num_hosts); error = device_register(&sdbg_host->dev); if (error) goto clean; - atomic_inc(&sdebug_num_hosts); + ++sdebug_num_hosts; return 0; clean: @@ -7381,7 +7286,7 @@ static void sdebug_do_remove_host(bool the_end) return; device_unregister(&sdbg_host->dev); - atomic_dec(&sdebug_num_hosts); + --sdebug_num_hosts; } static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) @@ -7389,10 +7294,10 @@ static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) int num_in_q = 0; struct sdebug_dev_info *devip; - sdeb_block_all_queues(); + block_unblock_all_queues(true); devip = (struct sdebug_dev_info *)sdev->hostdata; if (NULL == devip) { - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return -ENODEV; } num_in_q = atomic_read(&devip->num_in_q); @@ -7411,7 +7316,7 @@ static int sdebug_change_qdepth(struct scsi_device *sdev, int qdepth) sdev_printk(KERN_INFO, sdev, "%s: qdepth=%d, num_in_q=%d\n", __func__, qdepth, num_in_q); } - sdeb_unblock_all_queues(); + block_unblock_all_queues(false); return sdev->queue_depth; } @@ -7519,12 +7424,13 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) struct sdebug_defer *sd_dp; sqp = sdebug_q_arr + queue_num; - qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); - if (qc_idx >= sdebug_max_queue) - return 0; spin_lock_irqsave(&sqp->qc_lock, iflags); + qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); + if (qc_idx >= sdebug_max_queue) + goto unlock; + for (first = true; first || qc_idx + 1 < sdebug_max_queue; ) { if (first) { first = false; @@ -7589,6 +7495,7 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) break; } +unlock: spin_unlock_irqrestore(&sqp->qc_lock, iflags); if (num_entries > 0) diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c index ff89de86545d..b02af340c2d3 100644 --- a/drivers/scsi/scsi_logging.c +++ b/drivers/scsi/scsi_logging.c @@ -30,7 +30,7 @@ static inline const char *scmd_name(const struct scsi_cmnd *scmd) { struct request *rq = scsi_cmd_to_rq((struct scsi_cmnd *)scmd); - if (!rq->q->disk) + if (!rq->q || !rq->q->disk) return NULL; return rq->q->disk->disk_name; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index f4e6c68ac99e..2ef78083f1ef 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -223,6 +223,8 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, int ret; struct sbitmap sb_backup; + depth = min_t(unsigned int, depth, scsi_device_max_queue_depth(sdev)); + /* * realloc if new shift is calculated, which is caused by setting * up one new default queue depth after calling ->slave_configure @@ -245,6 +247,9 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, scsi_device_max_queue_depth(sdev), new_shift, GFP_KERNEL, sdev->request_queue->node, false, true); + if (!ret) + sbitmap_resize(&sdev->budget_map, depth); + if (need_free) { if (ret) sdev->budget_map = sb_backup; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 226a50944c00..dc6872e352bd 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1384,10 +1384,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) if (IS_ENABLED(CONFIG_BLK_DEV_BSG)) { sdev->bsg_dev = scsi_bsg_register_queue(sdev); if (IS_ERR(sdev->bsg_dev)) { - /* - * We're treating error on bsg register as non-fatal, so - * pretend nothing went wrong. - */ error = PTR_ERR(sdev->bsg_dev); sdev_printk(KERN_INFO, sdev, "Failed to register bsg queue, errno=%d\n", diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 27951ea05dd4..2c0dd64159b0 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -86,6 +86,9 @@ struct iscsi_internal { struct transport_container session_cont; }; +static DEFINE_IDR(iscsi_ep_idr); +static DEFINE_MUTEX(iscsi_ep_idr_mutex); + static atomic_t iscsi_session_nr; /* sysfs session id for next new session */ static struct workqueue_struct *iscsi_conn_cleanup_workq; @@ -168,6 +171,11 @@ struct device_attribute dev_attr_##_prefix##_##_name = \ static void iscsi_endpoint_release(struct device *dev) { struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); + + mutex_lock(&iscsi_ep_idr_mutex); + idr_remove(&iscsi_ep_idr, ep->id); + mutex_unlock(&iscsi_ep_idr_mutex); + kfree(ep); } @@ -180,7 +188,7 @@ static ssize_t show_ep_handle(struct device *dev, struct device_attribute *attr, char *buf) { struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); - return sysfs_emit(buf, "%llu\n", (unsigned long long) ep->id); + return sysfs_emit(buf, "%d\n", ep->id); } static ISCSI_ATTR(ep, handle, S_IRUGO, show_ep_handle, NULL); @@ -193,48 +201,32 @@ static struct attribute_group iscsi_endpoint_group = { .attrs = iscsi_endpoint_attrs, }; -#define ISCSI_MAX_EPID -1 - -static int iscsi_match_epid(struct device *dev, const void *data) -{ - struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev); - const uint64_t *epid = data; - - return *epid == ep->id; -} - struct iscsi_endpoint * iscsi_create_endpoint(int dd_size) { - struct device *dev; struct iscsi_endpoint *ep; - uint64_t id; - int err; - - for (id = 1; id < ISCSI_MAX_EPID; id++) { - dev = class_find_device(&iscsi_endpoint_class, NULL, &id, - iscsi_match_epid); - if (!dev) - break; - else - put_device(dev); - } - if (id == ISCSI_MAX_EPID) { - printk(KERN_ERR "Too many connections. Max supported %u\n", - ISCSI_MAX_EPID - 1); - return NULL; - } + int err, id; ep = kzalloc(sizeof(*ep) + dd_size, GFP_KERNEL); if (!ep) return NULL; + mutex_lock(&iscsi_ep_idr_mutex); + id = idr_alloc(&iscsi_ep_idr, ep, 0, -1, GFP_NOIO); + if (id < 0) { + mutex_unlock(&iscsi_ep_idr_mutex); + printk(KERN_ERR "Could not allocate endpoint ID. Error %d.\n", + id); + goto free_ep; + } + mutex_unlock(&iscsi_ep_idr_mutex); + ep->id = id; ep->dev.class = &iscsi_endpoint_class; - dev_set_name(&ep->dev, "ep-%llu", (unsigned long long) id); + dev_set_name(&ep->dev, "ep-%d", id); err = device_register(&ep->dev); if (err) - goto free_ep; + goto free_id; err = sysfs_create_group(&ep->dev.kobj, &iscsi_endpoint_group); if (err) @@ -248,6 +240,10 @@ unregister_dev: device_unregister(&ep->dev); return NULL; +free_id: + mutex_lock(&iscsi_ep_idr_mutex); + idr_remove(&iscsi_ep_idr, id); + mutex_unlock(&iscsi_ep_idr_mutex); free_ep: kfree(ep); return NULL; @@ -275,14 +271,17 @@ EXPORT_SYMBOL_GPL(iscsi_put_endpoint); */ struct iscsi_endpoint *iscsi_lookup_endpoint(u64 handle) { - struct device *dev; + struct iscsi_endpoint *ep; - dev = class_find_device(&iscsi_endpoint_class, NULL, &handle, - iscsi_match_epid); - if (!dev) - return NULL; + mutex_lock(&iscsi_ep_idr_mutex); + ep = idr_find(&iscsi_ep_idr, handle); + if (!ep) + goto unlock; - return iscsi_dev_to_endpoint(dev); + get_device(&ep->dev); +unlock: + mutex_unlock(&iscsi_ep_idr_mutex); + return ep; } EXPORT_SYMBOL_GPL(iscsi_lookup_endpoint); @@ -2202,10 +2201,10 @@ static void iscsi_stop_conn(struct iscsi_cls_conn *conn, int flag) switch (flag) { case STOP_CONN_RECOVER: - conn->state = ISCSI_CONN_FAILED; + WRITE_ONCE(conn->state, ISCSI_CONN_FAILED); break; case STOP_CONN_TERM: - conn->state = ISCSI_CONN_DOWN; + WRITE_ONCE(conn->state, ISCSI_CONN_DOWN); break; default: iscsi_cls_conn_printk(KERN_ERR, conn, "invalid stop flag %d\n", @@ -2217,6 +2216,49 @@ static void iscsi_stop_conn(struct iscsi_cls_conn *conn, int flag) ISCSI_DBG_TRANS_CONN(conn, "Stopping conn done.\n"); } +static void iscsi_ep_disconnect(struct iscsi_cls_conn *conn, bool is_active) +{ + struct iscsi_cls_session *session = iscsi_conn_to_session(conn); + struct iscsi_endpoint *ep; + + ISCSI_DBG_TRANS_CONN(conn, "disconnect ep.\n"); + WRITE_ONCE(conn->state, ISCSI_CONN_FAILED); + + if (!conn->ep || !session->transport->ep_disconnect) + return; + + ep = conn->ep; + conn->ep = NULL; + + session->transport->unbind_conn(conn, is_active); + session->transport->ep_disconnect(ep); + ISCSI_DBG_TRANS_CONN(conn, "disconnect ep done.\n"); +} + +static void iscsi_if_disconnect_bound_ep(struct iscsi_cls_conn *conn, + struct iscsi_endpoint *ep, + bool is_active) +{ + /* Check if this was a conn error and the kernel took ownership */ + spin_lock_irq(&conn->lock); + if (!test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); + iscsi_ep_disconnect(conn, is_active); + } else { + spin_unlock_irq(&conn->lock); + ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); + mutex_unlock(&conn->ep_mutex); + + flush_work(&conn->cleanup_work); + /* + * Userspace is now done with the EP so we can release the ref + * iscsi_cleanup_conn_work_fn took. + */ + iscsi_put_endpoint(ep); + mutex_lock(&conn->ep_mutex); + } +} + static int iscsi_if_stop_conn(struct iscsi_transport *transport, struct iscsi_uevent *ev) { @@ -2238,11 +2280,24 @@ static int iscsi_if_stop_conn(struct iscsi_transport *transport, iscsi_stop_conn(conn, flag); } else { /* + * For offload, when iscsid is restarted it won't know about + * existing endpoints so it can't do a ep_disconnect. We clean + * it up here for userspace. + */ + mutex_lock(&conn->ep_mutex); + if (conn->ep) + iscsi_if_disconnect_bound_ep(conn, conn->ep, true); + mutex_unlock(&conn->ep_mutex); + + /* * Figure out if it was the kernel or userspace initiating this. */ + spin_lock_irq(&conn->lock); if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); iscsi_stop_conn(conn, flag); } else { + spin_unlock_irq(&conn->lock); ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); flush_work(&conn->cleanup_work); @@ -2251,31 +2306,14 @@ static int iscsi_if_stop_conn(struct iscsi_transport *transport, * Only clear for recovery to avoid extra cleanup runs during * termination. */ + spin_lock_irq(&conn->lock); clear_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags); + spin_unlock_irq(&conn->lock); } ISCSI_DBG_TRANS_CONN(conn, "iscsi if conn stop done.\n"); return 0; } -static void iscsi_ep_disconnect(struct iscsi_cls_conn *conn, bool is_active) -{ - struct iscsi_cls_session *session = iscsi_conn_to_session(conn); - struct iscsi_endpoint *ep; - - ISCSI_DBG_TRANS_CONN(conn, "disconnect ep.\n"); - conn->state = ISCSI_CONN_FAILED; - - if (!conn->ep || !session->transport->ep_disconnect) - return; - - ep = conn->ep; - conn->ep = NULL; - - session->transport->unbind_conn(conn, is_active); - session->transport->ep_disconnect(ep); - ISCSI_DBG_TRANS_CONN(conn, "disconnect ep done.\n"); -} - static void iscsi_cleanup_conn_work_fn(struct work_struct *work) { struct iscsi_cls_conn *conn = container_of(work, struct iscsi_cls_conn, @@ -2284,18 +2322,11 @@ static void iscsi_cleanup_conn_work_fn(struct work_struct *work) mutex_lock(&conn->ep_mutex); /* - * If we are not at least bound there is nothing for us to do. Userspace - * will do a ep_disconnect call if offload is used, but will not be - * doing a stop since there is nothing to clean up, so we have to clear - * the cleanup bit here. + * Get a ref to the ep, so we don't release its ID until after + * userspace is done referencing it in iscsi_if_disconnect_bound_ep. */ - if (conn->state != ISCSI_CONN_BOUND && conn->state != ISCSI_CONN_UP) { - ISCSI_DBG_TRANS_CONN(conn, "Got error while conn is already failed. Ignoring.\n"); - clear_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags); - mutex_unlock(&conn->ep_mutex); - return; - } - + if (conn->ep) + get_device(&conn->ep->dev); iscsi_ep_disconnect(conn, false); if (system_state != SYSTEM_RUNNING) { @@ -2340,11 +2371,12 @@ iscsi_alloc_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid) conn->dd_data = &conn[1]; mutex_init(&conn->ep_mutex); + spin_lock_init(&conn->lock); INIT_LIST_HEAD(&conn->conn_list); INIT_WORK(&conn->cleanup_work, iscsi_cleanup_conn_work_fn); conn->transport = transport; conn->cid = cid; - conn->state = ISCSI_CONN_DOWN; + WRITE_ONCE(conn->state, ISCSI_CONN_DOWN); /* this is released in the dev's release function */ if (!get_device(&session->dev)) @@ -2542,9 +2574,32 @@ void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error) struct iscsi_uevent *ev; struct iscsi_internal *priv; int len = nlmsg_total_size(sizeof(*ev)); + unsigned long flags; + int state; - if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) - queue_work(iscsi_conn_cleanup_workq, &conn->cleanup_work); + spin_lock_irqsave(&conn->lock, flags); + /* + * Userspace will only do a stop call if we are at least bound. And, we + * only need to do the in kernel cleanup if in the UP state so cmds can + * be released to upper layers. If in other states just wait for + * userspace to avoid races that can leave the cleanup_work queued. + */ + state = READ_ONCE(conn->state); + switch (state) { + case ISCSI_CONN_BOUND: + case ISCSI_CONN_UP: + if (!test_and_set_bit(ISCSI_CLS_CONN_BIT_CLEANUP, + &conn->flags)) { + queue_work(iscsi_conn_cleanup_workq, + &conn->cleanup_work); + } + break; + default: + ISCSI_DBG_TRANS_CONN(conn, "Got conn error in state %d\n", + state); + break; + } + spin_unlock_irqrestore(&conn->lock, flags); priv = iscsi_if_transport_lookup(conn->transport); if (!priv) @@ -2894,7 +2949,7 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) char *data = (char*)ev + sizeof(*ev); struct iscsi_cls_conn *conn; struct iscsi_cls_session *session; - int err = 0, value = 0; + int err = 0, value = 0, state; if (ev->u.set_param.len > PAGE_SIZE) return -EINVAL; @@ -2911,8 +2966,8 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) session->recovery_tmo = value; break; default: - if ((conn->state == ISCSI_CONN_BOUND) || - (conn->state == ISCSI_CONN_UP)) { + state = READ_ONCE(conn->state); + if (state == ISCSI_CONN_BOUND || state == ISCSI_CONN_UP) { err = transport->set_param(conn, ev->u.set_param.param, data, ev->u.set_param.len); } else { @@ -2984,16 +3039,7 @@ static int iscsi_if_ep_disconnect(struct iscsi_transport *transport, } mutex_lock(&conn->ep_mutex); - /* Check if this was a conn error and the kernel took ownership */ - if (test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { - ISCSI_DBG_TRANS_CONN(conn, "flush kernel conn cleanup.\n"); - mutex_unlock(&conn->ep_mutex); - - flush_work(&conn->cleanup_work); - goto put_ep; - } - - iscsi_ep_disconnect(conn, false); + iscsi_if_disconnect_bound_ep(conn, ep, false); mutex_unlock(&conn->ep_mutex); put_ep: iscsi_put_endpoint(ep); @@ -3696,24 +3742,17 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, return -EINVAL; mutex_lock(&conn->ep_mutex); + spin_lock_irq(&conn->lock); if (test_bit(ISCSI_CLS_CONN_BIT_CLEANUP, &conn->flags)) { + spin_unlock_irq(&conn->lock); mutex_unlock(&conn->ep_mutex); ev->r.retcode = -ENOTCONN; return 0; } + spin_unlock_irq(&conn->lock); switch (nlh->nlmsg_type) { case ISCSI_UEVENT_BIND_CONN: - if (conn->ep) { - /* - * For offload boot support where iscsid is restarted - * during the pivot root stage, the ep will be intact - * here when the new iscsid instance starts up and - * reconnects. - */ - iscsi_ep_disconnect(conn, true); - } - session = iscsi_session_lookup(ev->u.b_conn.sid); if (!session) { err = -EINVAL; @@ -3724,7 +3763,7 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, ev->u.b_conn.transport_eph, ev->u.b_conn.is_leading); if (!ev->r.retcode) - conn->state = ISCSI_CONN_BOUND; + WRITE_ONCE(conn->state, ISCSI_CONN_BOUND); if (ev->r.retcode || !transport->ep_connect) break; @@ -3743,7 +3782,8 @@ static int iscsi_if_transport_conn(struct iscsi_transport *transport, case ISCSI_UEVENT_START_CONN: ev->r.retcode = transport->start_conn(conn); if (!ev->r.retcode) - conn->state = ISCSI_CONN_UP; + WRITE_ONCE(conn->state, ISCSI_CONN_UP); + break; case ISCSI_UEVENT_SEND_PDU: pdu_len = nlh->nlmsg_len - sizeof(*nlh) - sizeof(*ev); @@ -4050,10 +4090,11 @@ static ssize_t show_conn_state(struct device *dev, { struct iscsi_cls_conn *conn = iscsi_dev_to_conn(dev->parent); const char *state = "unknown"; + int conn_state = READ_ONCE(conn->state); - if (conn->state >= 0 && - conn->state < ARRAY_SIZE(connection_state_names)) - state = connection_state_names[conn->state]; + if (conn_state >= 0 && + conn_state < ARRAY_SIZE(connection_state_names)) + state = connection_state_names[conn_state]; return sysfs_emit(buf, "%s\n", state); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a390679cf458..dc6e55761fd1 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3216,6 +3216,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_block_limits(sdkp); sd_read_block_characteristics(sdkp); sd_zbc_read_zones(sdkp, buffer); + sd_read_cpr(sdkp); } sd_print_capacity(sdkp, old_capacity); @@ -3225,7 +3226,6 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); - sd_read_cpr(sdkp); } /* @@ -3475,6 +3475,7 @@ static int sd_probe(struct device *dev) error = device_add_disk(dev, gd, NULL); if (error) { put_device(&sdkp->disk_dev); + blk_cleanup_disk(gd); goto out; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 5ba9df334968..cbd92891a762 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -535,7 +535,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, scsi_autopm_get_device(sdev); - if (ret != CDROMCLOSETRAY && ret != CDROMEJECT) { + if (cmd != CDROMCLOSETRAY && cmd != CDROMEJECT) { ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) goto put; diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c index ddd00efc4882..fbdb5124d7f7 100644 --- a/drivers/scsi/sr_ioctl.c +++ b/drivers/scsi/sr_ioctl.c @@ -41,7 +41,7 @@ static int sr_read_tochdr(struct cdrom_device_info *cdi, int result; unsigned char *buffer; - buffer = kmalloc(32, GFP_KERNEL); + buffer = kzalloc(32, GFP_KERNEL); if (!buffer) return -ENOMEM; @@ -55,10 +55,13 @@ static int sr_read_tochdr(struct cdrom_device_info *cdi, cgc.data_direction = DMA_FROM_DEVICE; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; tochdr->cdth_trk0 = buffer[2]; tochdr->cdth_trk1 = buffer[3]; +err: kfree(buffer); return result; } @@ -71,7 +74,7 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, int result; unsigned char *buffer; - buffer = kmalloc(32, GFP_KERNEL); + buffer = kzalloc(32, GFP_KERNEL); if (!buffer) return -ENOMEM; @@ -86,6 +89,8 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, cgc.data_direction = DMA_FROM_DEVICE; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; tocentry->cdte_ctrl = buffer[5] & 0xf; tocentry->cdte_adr = buffer[5] >> 4; @@ -98,6 +103,7 @@ static int sr_read_tocentry(struct cdrom_device_info *cdi, tocentry->cdte_addr.lba = (((((buffer[8] << 8) + buffer[9]) << 8) + buffer[10]) << 8) + buffer[11]; +err: kfree(buffer); return result; } @@ -384,7 +390,7 @@ int sr_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn) { Scsi_CD *cd = cdi->handle; struct packet_command cgc; - char *buffer = kmalloc(32, GFP_KERNEL); + char *buffer = kzalloc(32, GFP_KERNEL); int result; if (!buffer) @@ -400,10 +406,13 @@ int sr_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn) cgc.data_direction = DMA_FROM_DEVICE; cgc.timeout = IOCTL_TIMEOUT; result = sr_do_ioctl(cd, &cgc); + if (result) + goto err; memcpy(mcn->medium_catalog_number, buffer + 9, 13); mcn->medium_catalog_number[13] = 0; +err: kfree(buffer); return result; } diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index 0d2e950d0865..586c0e567ff9 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -957,18 +957,6 @@ static const struct reset_control_ops ufs_qcom_reset_ops = { .deassert = ufs_qcom_reset_deassert, }; -#define ANDROID_BOOT_DEV_MAX 30 -static char android_boot_dev[ANDROID_BOOT_DEV_MAX]; - -#ifndef MODULE -static int __init get_android_boot_dev(char *str) -{ - strlcpy(android_boot_dev, str, ANDROID_BOOT_DEV_MAX); - return 1; -} -__setup("androidboot.bootdevice=", get_android_boot_dev); -#endif - /** * ufs_qcom_init - bind phy with controller * @hba: host controller instance @@ -988,9 +976,6 @@ static int ufs_qcom_init(struct ufs_hba *hba) struct resource *res; struct ufs_clk_info *clki; - if (strlen(android_boot_dev) && strcmp(android_boot_dev, dev_name(dev))) - return -ENODEV; - host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); if (!host) { err = -ENOMEM; diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index f76692053ca1..e892b9feffb1 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -428,6 +428,12 @@ static int ufs_intel_adl_init(struct ufs_hba *hba) return ufs_intel_common_init(hba); } +static int ufs_intel_mtl_init(struct ufs_hba *hba) +{ + hba->caps |= UFSHCD_CAP_CRYPTO | UFSHCD_CAP_WB_EN; + return ufs_intel_common_init(hba); +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .init = ufs_intel_common_init, @@ -465,6 +471,16 @@ static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = { .device_reset = ufs_intel_device_reset, }; +static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_mtl_init, + .exit = ufs_intel_common_exit, + .hce_enable_notify = ufs_intel_hce_enable_notify, + .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, + .device_reset = ufs_intel_device_reset, +}; + #ifdef CONFIG_PM_SLEEP static int ufshcd_pci_restore(struct device *dev) { @@ -579,6 +595,7 @@ static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops }, { PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, { PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x7E47), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 88c20f3608c2..94f545be183a 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -820,8 +820,6 @@ struct ufs_hba { enum ufs_pm_level rpm_lvl; /* Desired UFS power management level during system PM */ enum ufs_pm_level spm_lvl; - struct device_attribute rpm_lvl_attr; - struct device_attribute spm_lvl_attr; int pm_op_in_progress; /* Auto-Hibernate Idle Timer register value */ diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index b2bec19022cd..81099b68bbfb 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -867,12 +867,6 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) struct ufshpb_region *rgn, *victim_rgn = NULL; list_for_each_entry(rgn, &lru_info->lh_lru_rgn, list_lru_rgn) { - if (!rgn) { - dev_err(&hpb->sdev_ufs_lu->sdev_dev, - "%s: no region allocated\n", - __func__); - return NULL; - } if (ufshpb_check_srgns_issue_state(hpb, rgn)) continue; @@ -888,6 +882,11 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) break; } + if (!victim_rgn) + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "%s: no region allocated\n", + __func__); + return victim_rgn; } diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 0e6110da69e7..578c4b6d0f7d 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -988,7 +988,7 @@ static struct virtio_driver virtio_scsi_driver = { .remove = virtscsi_remove, }; -static int __init init(void) +static int __init virtio_scsi_init(void) { int ret = -ENOMEM; @@ -1020,14 +1020,14 @@ error: return ret; } -static void __exit fini(void) +static void __exit virtio_scsi_fini(void) { unregister_virtio_driver(&virtio_scsi_driver); mempool_destroy(virtscsi_cmd_pool); kmem_cache_destroy(virtscsi_cmd_cache); } -module_init(init); -module_exit(fini); +module_init(virtio_scsi_init); +module_exit(virtio_scsi_fini); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio SCSI HBA driver"); diff --git a/drivers/scsi/zorro7xx.c b/drivers/scsi/zorro7xx.c index 27b9e2baab1a..7acf9193a9e8 100644 --- a/drivers/scsi/zorro7xx.c +++ b/drivers/scsi/zorro7xx.c @@ -159,6 +159,8 @@ static void zorro7xx_remove_one(struct zorro_dev *z) scsi_remove_host(host); NCR_700_release(host); + if (host->base > 0x01000000) + iounmap(hostdata->base); kfree(hostdata); free_irq(host->irq, host); zorro_release_device(z); diff --git a/drivers/soc/imx/imx8m-blk-ctrl.c b/drivers/soc/imx/imx8m-blk-ctrl.c index 122f9c884b38..ccd0577a771e 100644 --- a/drivers/soc/imx/imx8m-blk-ctrl.c +++ b/drivers/soc/imx/imx8m-blk-ctrl.c @@ -50,7 +50,7 @@ struct imx8m_blk_ctrl_domain_data { u32 mipi_phy_rst_mask; }; -#define DOMAIN_MAX_CLKS 3 +#define DOMAIN_MAX_CLKS 4 struct imx8m_blk_ctrl_domain { struct generic_pm_domain genpd; diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index 92d9610df1fd..938017a60c8e 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -277,6 +277,9 @@ static int atmel_qspi_find_mode(const struct spi_mem_op *op) static bool atmel_qspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { + if (!spi_mem_default_supports_op(mem, op)) + return false; + if (atmel_qspi_find_mode(op) < 0) return false; diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 86c76211b3d3..cad2d55dcd3d 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1205,7 +1205,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, addr = op->addr.val; len = op->data.nbytes; - if (bcm_qspi_bspi_ver_three(qspi) == true) { + if (has_bspi(qspi) && bcm_qspi_bspi_ver_three(qspi) == true) { /* * The address coming into this function is a raw flash offset. * But for BSPI <= V3, we need to convert it to a remapped BSPI @@ -1224,7 +1224,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, len < 4) mspi_read = true; - if (mspi_read) + if (!has_bspi(qspi) || mspi_read) return bcm_qspi_mspi_exec_mem_op(spi, op); ret = bcm_qspi_bspi_set_mode(qspi, op, 0); diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index b0c9f62ccefb..19686fb47bb3 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -19,6 +19,7 @@ #include <linux/iopoll.h> #include <linux/jiffies.h> #include <linux/kernel.h> +#include <linux/log2.h> #include <linux/module.h> #include <linux/of_device.h> #include <linux/of.h> @@ -102,12 +103,6 @@ struct cqspi_driver_platdata { #define CQSPI_TIMEOUT_MS 500 #define CQSPI_READ_TIMEOUT_MS 10 -/* Instruction type */ -#define CQSPI_INST_TYPE_SINGLE 0 -#define CQSPI_INST_TYPE_DUAL 1 -#define CQSPI_INST_TYPE_QUAD 2 -#define CQSPI_INST_TYPE_OCTAL 3 - #define CQSPI_DUMMY_CLKS_PER_BYTE 8 #define CQSPI_DUMMY_BYTES_MAX 4 #define CQSPI_DUMMY_CLKS_MAX 31 @@ -376,10 +371,6 @@ static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, const struct spi_mem_op *op) { - f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - /* * For an op to be DTR, cmd phase along with every other non-empty * phase should have dtr field set to 1. If an op phase has zero @@ -389,32 +380,23 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, (!op->addr.nbytes || op->addr.dtr) && (!op->data.nbytes || op->data.dtr); - switch (op->data.buswidth) { - case 0: - break; - case 1: - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - break; - case 2: - f_pdata->data_width = CQSPI_INST_TYPE_DUAL; - break; - case 4: - f_pdata->data_width = CQSPI_INST_TYPE_QUAD; - break; - case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; - break; - default: - return -EINVAL; - } + f_pdata->inst_width = 0; + if (op->cmd.buswidth) + f_pdata->inst_width = ilog2(op->cmd.buswidth); + + f_pdata->addr_width = 0; + if (op->addr.buswidth) + f_pdata->addr_width = ilog2(op->addr.buswidth); + + f_pdata->data_width = 0; + if (op->data.buswidth) + f_pdata->data_width = ilog2(op->data.buswidth); /* Right now we only support 8-8-8 DTR mode. */ if (f_pdata->dtr) { switch (op->cmd.buswidth) { case 0: - break; case 8: - f_pdata->inst_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -422,9 +404,7 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, switch (op->addr.buswidth) { case 0: - break; case 8: - f_pdata->addr_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -432,9 +412,7 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, switch (op->data.buswidth) { case 0: - break; case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -1437,9 +1415,24 @@ static bool cqspi_supports_mem_op(struct spi_mem *mem, all_false = !op->cmd.dtr && !op->addr.dtr && !op->dummy.dtr && !op->data.dtr; - /* Mixed DTR modes not supported. */ - if (!(all_true || all_false)) + if (all_true) { + /* Right now we only support 8-8-8 DTR mode. */ + if (op->cmd.nbytes && op->cmd.buswidth != 8) + return false; + if (op->addr.nbytes && op->addr.buswidth != 8) + return false; + if (op->data.nbytes && op->data.buswidth != 8) + return false; + } else if (all_false) { + /* Only 1-1-X ops are supported without DTR */ + if (op->cmd.nbytes && op->cmd.buswidth > 1) + return false; + if (op->addr.nbytes && op->addr.buswidth > 1) + return false; + } else { + /* Mixed DTR modes are not supported. */ return false; + } return spi_mem_default_supports_op(mem, op); } diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index a5ef7a526a7f..f6eec7a869b6 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -72,6 +72,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x4da4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0x51a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x54a4), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0x7a24), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0x7aa4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info }, diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c index 94fb09696677..d167699a1a96 100644 --- a/drivers/spi/spi-mtk-nor.c +++ b/drivers/spi/spi-mtk-nor.c @@ -960,7 +960,17 @@ static int __maybe_unused mtk_nor_suspend(struct device *dev) static int __maybe_unused mtk_nor_resume(struct device *dev) { - return pm_runtime_force_resume(dev); + struct spi_controller *ctlr = dev_get_drvdata(dev); + struct mtk_nor *sp = spi_controller_get_devdata(ctlr); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + mtk_nor_init(sp); + + return 0; } static const struct dev_pm_ops mtk_nor_pm_ops = { diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c index 55c092069301..65be8e085ab8 100644 --- a/drivers/spi/spi-mxic.c +++ b/drivers/spi/spi-mxic.c @@ -813,6 +813,7 @@ static int mxic_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "spi_register_master failed\n"); pm_runtime_disable(&pdev->dev); + mxic_spi_mem_ecc_remove(mxic); } return ret; diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c index fe82f3575df4..24ec1c83f379 100644 --- a/drivers/spi/spi-rpc-if.c +++ b/drivers/spi/spi-rpc-if.c @@ -158,14 +158,18 @@ static int rpcif_spi_probe(struct platform_device *pdev) error = rpcif_hw_init(rpc, false); if (error) - return error; + goto out_disable_rpm; error = spi_register_controller(ctlr); if (error) { dev_err(&pdev->dev, "spi_register_controller failed\n"); - rpcif_disable_rpm(rpc); + goto out_disable_rpm; } + return 0; + +out_disable_rpm: + rpcif_disable_rpm(rpc); return error; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c4dd1200fe99..2e6d6bbeb784 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1130,11 +1130,15 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg) if (ctlr->dma_tx) tx_dev = ctlr->dma_tx->device->dev; + else if (ctlr->dma_map_dev) + tx_dev = ctlr->dma_map_dev; else tx_dev = ctlr->dev.parent; if (ctlr->dma_rx) rx_dev = ctlr->dma_rx->device->dev; + else if (ctlr->dma_map_dev) + rx_dev = ctlr->dma_map_dev; else rx_dev = ctlr->dev.parent; @@ -2406,7 +2410,8 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data) } else { struct acpi_device *adev; - if (acpi_bus_get_device(parent_handle, &adev)) + adev = acpi_fetch_acpi_dev(parent_handle); + if (!adev) return -ENODEV; ctlr = acpi_spi_find_controller_by_adev(adev); diff --git a/drivers/staging/r8188eu/core/rtw_br_ext.c b/drivers/staging/r8188eu/core/rtw_br_ext.c index d68611ef22f8..f056204c0fdb 100644 --- a/drivers/staging/r8188eu/core/rtw_br_ext.c +++ b/drivers/staging/r8188eu/core/rtw_br_ext.c @@ -70,7 +70,7 @@ static int __nat25_add_pppoe_tag(struct sk_buff *skb, struct pppoe_tag *tag) struct pppoe_hdr *ph = (struct pppoe_hdr *)(skb->data + ETH_HLEN); int data_len; - data_len = tag->tag_len + TAG_HDR_LEN; + data_len = be16_to_cpu(tag->tag_len) + TAG_HDR_LEN; if (skb_tailroom(skb) < data_len) return -1; diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index ff292b75e23f..60dafe4c581b 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -588,7 +588,7 @@ static void pscsi_destroy_device(struct se_device *dev) } static void pscsi_complete_cmd(struct se_cmd *cmd, u8 scsi_status, - unsigned char *req_sense) + unsigned char *req_sense, int valid_data) { struct pscsi_dev_virt *pdv = PSCSI_DEV(cmd->se_dev); struct scsi_device *sd = pdv->pdv_sd; @@ -681,7 +681,7 @@ after_mode_select: * back despite framework assumption that a * check condition means there is no data */ - if (sd->type == TYPE_TAPE && + if (sd->type == TYPE_TAPE && valid_data && cmd->data_direction == DMA_FROM_DEVICE) { /* * is sense data valid, fixed format, @@ -1032,6 +1032,7 @@ static void pscsi_req_done(struct request *req, blk_status_t status) struct se_cmd *cmd = req->end_io_data; struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(req); enum sam_status scsi_status = scmd->result & 0xff; + int valid_data = cmd->data_length - scmd->resid_len; u8 *cdb = cmd->priv; if (scsi_status != SAM_STAT_GOOD) { @@ -1039,12 +1040,11 @@ static void pscsi_req_done(struct request *req, blk_status_t status) " 0x%02x Result: 0x%08x\n", cmd, cdb[0], scmd->result); } - pscsi_complete_cmd(cmd, scsi_status, scmd->sense_buffer); + pscsi_complete_cmd(cmd, scsi_status, scmd->sense_buffer, valid_data); switch (host_byte(scmd->result)) { case DID_OK: - target_complete_cmd_with_length(cmd, scsi_status, - cmd->data_length - scmd->resid_len); + target_complete_cmd_with_length(cmd, scsi_status, valid_data); break; default: pr_debug("PSCSI Host Byte exception at cmd: %p CDB:" diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 95d4ca50a605..fd7267baa707 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1821,6 +1821,7 @@ static struct page *tcmu_try_get_data_page(struct tcmu_dev *udev, uint32_t dpi) mutex_lock(&udev->cmdr_lock); page = xa_load(&udev->data_pages, dpi); if (likely(page)) { + get_page(page); mutex_unlock(&udev->cmdr_lock); return page; } @@ -1877,6 +1878,7 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) /* For the vmalloc()ed cmd area pages */ addr = (void *)(unsigned long)info->mem[mi].addr + offset; page = vmalloc_to_page(addr); + get_page(page); } else { uint32_t dpi; @@ -1887,7 +1889,6 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } - get_page(page); vmf->page = page; return 0; } diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c index a5eb4ef46971..c9b3b2cfb2b2 100644 --- a/drivers/tee/optee/ffa_abi.c +++ b/drivers/tee/optee/ffa_abi.c @@ -865,6 +865,7 @@ err_rhashtable_free: rhashtable_free_and_destroy(&optee->ffa.global_ids, rh_free_fn, NULL); optee_supp_uninit(&optee->supp); mutex_destroy(&optee->call_queue.mutex); + mutex_destroy(&optee->ffa.mutex); err_unreg_supp_teedev: tee_device_unregister(optee->supp_teedev); err_unreg_teedev: diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index e37691e0bf20..0e5cc948373c 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -113,8 +113,10 @@ config THERMAL_DEFAULT_GOV_USER_SPACE bool "user_space" select THERMAL_GOV_USER_SPACE help - Select this if you want to let the user space manage the - platform thermals. + The Userspace governor allows to get trip point crossed + notification from the kernel via uevents. It is recommended + to use the netlink interface instead which gives richer + information about the thermal framework events. config THERMAL_DEFAULT_GOV_POWER_ALLOCATOR bool "power_allocator" diff --git a/drivers/thermal/gov_user_space.c b/drivers/thermal/gov_user_space.c index 64a18e354a20..a62a4e90bd3f 100644 --- a/drivers/thermal/gov_user_space.c +++ b/drivers/thermal/gov_user_space.c @@ -17,8 +17,7 @@ static int user_space_bind(struct thermal_zone_device *tz) { - pr_warn_once("Userspace governor deprecated: use thermal netlink " \ - "notification instead\n"); + pr_info_once("Consider using thermal netlink events interface\n"); return 0; } diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 4954800b9850..d97f496bab9b 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -68,7 +68,7 @@ static int evaluate_odvp(struct int3400_thermal_priv *priv); struct odvp_attr { int odvp; struct int3400_thermal_priv *priv; - struct kobj_attribute attr; + struct device_attribute attr; }; static ssize_t data_vault_read(struct file *file, struct kobject *kobj, @@ -311,7 +311,7 @@ end: return result; } -static ssize_t odvp_show(struct kobject *kobj, struct kobj_attribute *attr, +static ssize_t odvp_show(struct device *dev, struct device_attribute *attr, char *buf) { struct odvp_attr *odvp_attr; diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index f154bada2906..1c4aac8464a7 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -610,9 +610,6 @@ cur_state_store(struct device *dev, struct device_attribute *attr, unsigned long state; int result; - dev_warn_once(&cdev->device, - "Setting cooling device state is deprecated\n"); - if (sscanf(buf, "%ld\n", &state) != 1) return -EINVAL; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index fa92f727fdf8..a38b922bcbc1 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -73,6 +73,8 @@ module_param(debug, int, 0600); */ #define MAX_MRU 1500 #define MAX_MTU 1500 +/* SOF, ADDR, CTRL, LEN1, LEN2, ..., FCS, EOF */ +#define PROT_OVERHEAD 7 #define GSM_NET_TX_TIMEOUT (HZ*10) /* @@ -219,7 +221,6 @@ struct gsm_mux { int encoding; u8 control; u8 fcs; - u8 received_fcs; u8 *txframe; /* TX framing buffer */ /* Method for the receiver side */ @@ -231,6 +232,7 @@ struct gsm_mux { int initiator; /* Did we initiate connection */ bool dead; /* Has the mux been shut down */ struct gsm_dlci *dlci[NUM_DLCI]; + int old_c_iflag; /* termios c_iflag value before attach */ bool constipated; /* Asked by remote to shut up */ spinlock_t tx_lock; @@ -271,10 +273,6 @@ static DEFINE_SPINLOCK(gsm_mux_lock); static struct tty_driver *gsm_tty_driver; -/* Save dlci open address */ -static int addr_open[256] = { 0 }; -/* Save dlci open count */ -static int addr_cnt; /* * This section of the driver logic implements the GSM encodings * both the basic and the 'advanced'. Reliable transport is not @@ -369,6 +367,7 @@ static const u8 gsm_fcs8[256] = { #define GOOD_FCS 0xCF static int gsmld_output(struct gsm_mux *gsm, u8 *data, int len); +static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk); /** * gsm_fcs_add - update FCS @@ -832,7 +831,7 @@ static int gsm_dlci_data_output(struct gsm_mux *gsm, struct gsm_dlci *dlci) break; case 2: /* Unstructed with modem bits. Always one byte as we never send inline break data */ - *dp++ = gsm_encode_modem(dlci); + *dp++ = (gsm_encode_modem(dlci) << 1) | EA; break; } WARN_ON(kfifo_out_locked(&dlci->fifo, dp , len, &dlci->lock) != len); @@ -917,6 +916,66 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm, } /** + * gsm_dlci_modem_output - try and push modem status out of a DLCI + * @gsm: mux + * @dlci: the DLCI to pull modem status from + * @brk: break signal + * + * Push an empty frame in to the transmit queue to update the modem status + * bits and to transmit an optional break. + * + * Caller must hold the tx_lock of the mux. + */ + +static int gsm_dlci_modem_output(struct gsm_mux *gsm, struct gsm_dlci *dlci, + u8 brk) +{ + u8 *dp = NULL; + struct gsm_msg *msg; + int size = 0; + + /* for modem bits without break data */ + switch (dlci->adaption) { + case 1: /* Unstructured */ + break; + case 2: /* Unstructured with modem bits. */ + size++; + if (brk > 0) + size++; + break; + default: + pr_err("%s: unsupported adaption %d\n", __func__, + dlci->adaption); + return -EINVAL; + } + + msg = gsm_data_alloc(gsm, dlci->addr, size, gsm->ftype); + if (!msg) { + pr_err("%s: gsm_data_alloc error", __func__); + return -ENOMEM; + } + dp = msg->data; + switch (dlci->adaption) { + case 1: /* Unstructured */ + break; + case 2: /* Unstructured with modem bits. */ + if (brk == 0) { + *dp++ = (gsm_encode_modem(dlci) << 1) | EA; + } else { + *dp++ = gsm_encode_modem(dlci) << 1; + *dp++ = (brk << 4) | 2 | EA; /* Length, Break, EA */ + } + break; + default: + /* Handled above */ + break; + } + + __gsm_data_queue(dlci, msg); + return size; +} + +/** * gsm_dlci_data_sweep - look for data to send * @gsm: the GSM mux * @@ -1093,7 +1152,6 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) { unsigned int addr = 0; unsigned int modem = 0; - unsigned int brk = 0; struct gsm_dlci *dlci; int len = clen; int slen; @@ -1123,17 +1181,8 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) return; } len--; - if (len > 0) { - while (gsm_read_ea(&brk, *dp++) == 0) { - len--; - if (len == 0) - return; - } - modem <<= 7; - modem |= (brk & 0x7f); - } tty = tty_port_tty_get(&dlci->port); - gsm_process_modem(tty, dlci, modem, slen); + gsm_process_modem(tty, dlci, modem, slen - len); if (tty) { tty_wakeup(tty); tty_kref_put(tty); @@ -1193,7 +1242,6 @@ static void gsm_control_rls(struct gsm_mux *gsm, const u8 *data, int clen) } static void gsm_dlci_begin_close(struct gsm_dlci *dlci); -static void gsm_dlci_close(struct gsm_dlci *dlci); /** * gsm_control_message - DLCI 0 control processing @@ -1212,28 +1260,15 @@ static void gsm_control_message(struct gsm_mux *gsm, unsigned int command, { u8 buf[1]; unsigned long flags; - struct gsm_dlci *dlci; - int i; - int address; switch (command) { case CMD_CLD: { - if (addr_cnt > 0) { - for (i = 0; i < addr_cnt; i++) { - address = addr_open[i]; - dlci = gsm->dlci[address]; - gsm_dlci_close(dlci); - addr_open[i] = 0; - } - } + struct gsm_dlci *dlci = gsm->dlci[0]; /* Modem wishes to close down */ - dlci = gsm->dlci[0]; if (dlci) { dlci->dead = true; gsm->dead = true; - gsm_dlci_close(dlci); - addr_cnt = 0; - gsm_response(gsm, 0, UA|PF); + gsm_dlci_begin_close(dlci); } } break; @@ -1326,11 +1361,12 @@ static void gsm_control_response(struct gsm_mux *gsm, unsigned int command, static void gsm_control_transmit(struct gsm_mux *gsm, struct gsm_control *ctrl) { - struct gsm_msg *msg = gsm_data_alloc(gsm, 0, ctrl->len + 1, gsm->ftype); + struct gsm_msg *msg = gsm_data_alloc(gsm, 0, ctrl->len + 2, gsm->ftype); if (msg == NULL) return; - msg->data[0] = (ctrl->cmd << 1) | 2 | EA; /* command */ - memcpy(msg->data + 1, ctrl->data, ctrl->len); + msg->data[0] = (ctrl->cmd << 1) | CR | EA; /* command */ + msg->data[1] = (ctrl->len << 1) | EA; + memcpy(msg->data + 2, ctrl->data, ctrl->len); gsm_data_queue(gsm->dlci[0], msg); } @@ -1353,7 +1389,6 @@ static void gsm_control_retransmit(struct timer_list *t) spin_lock_irqsave(&gsm->control_lock, flags); ctrl = gsm->pending_cmd; if (ctrl) { - gsm->cretries--; if (gsm->cretries == 0) { gsm->pending_cmd = NULL; ctrl->error = -ETIMEDOUT; @@ -1362,6 +1397,7 @@ static void gsm_control_retransmit(struct timer_list *t) wake_up(&gsm->event); return; } + gsm->cretries--; gsm_control_transmit(gsm, ctrl); mod_timer(&gsm->t2_timer, jiffies + gsm->t2 * HZ / 100); } @@ -1402,7 +1438,7 @@ retry: /* If DLCI0 is in ADM mode skip retries, it won't respond */ if (gsm->dlci[0]->mode == DLCI_MODE_ADM) - gsm->cretries = 1; + gsm->cretries = 0; else gsm->cretries = gsm->n2; @@ -1450,20 +1486,22 @@ static int gsm_control_wait(struct gsm_mux *gsm, struct gsm_control *control) static void gsm_dlci_close(struct gsm_dlci *dlci) { + unsigned long flags; + del_timer(&dlci->t1); if (debug & 8) pr_debug("DLCI %d goes closed.\n", dlci->addr); dlci->state = DLCI_CLOSED; if (dlci->addr != 0) { tty_port_tty_hangup(&dlci->port, false); + spin_lock_irqsave(&dlci->lock, flags); kfifo_reset(&dlci->fifo); + spin_unlock_irqrestore(&dlci->lock, flags); /* Ensure that gsmtty_open() can return. */ tty_port_set_initialized(&dlci->port, 0); wake_up_interruptible(&dlci->port.open_wait); } else dlci->gsm->dead = true; - /* Unregister gsmtty driver,report gsmtty dev remove uevent for user */ - tty_unregister_device(gsm_tty_driver, dlci->addr); wake_up(&dlci->gsm->event); /* A DLCI 0 close is a MUX termination so we need to kick that back to userspace somehow */ @@ -1485,8 +1523,9 @@ static void gsm_dlci_open(struct gsm_dlci *dlci) dlci->state = DLCI_OPEN; if (debug & 8) pr_debug("DLCI %d goes open.\n", dlci->addr); - /* Register gsmtty driver,report gsmtty dev add uevent for user */ - tty_register_device(gsm_tty_driver, dlci->addr, NULL); + /* Send current modem state */ + if (dlci->addr) + gsm_modem_update(dlci, 0); wake_up(&dlci->gsm->event); } @@ -1623,6 +1662,7 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, const u8 *data, int clen) tty = tty_port_tty_get(port); if (tty) { gsm_process_modem(tty, dlci, modem, slen); + tty_wakeup(tty); tty_kref_put(tty); } fallthrough; @@ -1793,19 +1833,7 @@ static void gsm_queue(struct gsm_mux *gsm) struct gsm_dlci *dlci; u8 cr; int address; - int i, j, k, address_tmp; - /* We have to sneak a look at the packet body to do the FCS. - A somewhat layering violation in the spec */ - if ((gsm->control & ~PF) == UI) - gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, gsm->len); - if (gsm->encoding == 0) { - /* WARNING: gsm->received_fcs is used for - gsm->encoding = 0 only. - In this case it contain the last piece of data - required to generate final CRC */ - gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->received_fcs); - } if (gsm->fcs != GOOD_FCS) { gsm->bad_fcs++; if (debug & 4) @@ -1836,11 +1864,6 @@ static void gsm_queue(struct gsm_mux *gsm) else { gsm_response(gsm, address, UA|PF); gsm_dlci_open(dlci); - /* Save dlci open address */ - if (address) { - addr_open[addr_cnt] = address; - addr_cnt++; - } } break; case DISC|PF: @@ -1851,35 +1874,9 @@ static void gsm_queue(struct gsm_mux *gsm) return; } /* Real close complete */ - if (!address) { - if (addr_cnt > 0) { - for (i = 0; i < addr_cnt; i++) { - address = addr_open[i]; - dlci = gsm->dlci[address]; - gsm_dlci_close(dlci); - addr_open[i] = 0; - } - } - dlci = gsm->dlci[0]; - gsm_dlci_close(dlci); - addr_cnt = 0; - gsm_response(gsm, 0, UA|PF); - } else { - gsm_response(gsm, address, UA|PF); - gsm_dlci_close(dlci); - /* clear dlci address */ - for (j = 0; j < addr_cnt; j++) { - address_tmp = addr_open[j]; - if (address_tmp == address) { - for (k = j; k < addr_cnt; k++) - addr_open[k] = addr_open[k+1]; - addr_cnt--; - break; - } - } - } + gsm_response(gsm, address, UA|PF); + gsm_dlci_close(dlci); break; - case UA: case UA|PF: if (cr == 0 || dlci == NULL) break; @@ -1993,19 +1990,25 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c) break; case GSM_DATA: /* Data */ gsm->buf[gsm->count++] = c; - if (gsm->count == gsm->len) + if (gsm->count == gsm->len) { + /* Calculate final FCS for UI frames over all data */ + if ((gsm->control & ~PF) != UIH) { + gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, + gsm->count); + } gsm->state = GSM_FCS; + } break; case GSM_FCS: /* FCS follows the packet */ - gsm->received_fcs = c; - gsm_queue(gsm); + gsm->fcs = gsm_fcs_add(gsm->fcs, c); gsm->state = GSM_SSOF; break; case GSM_SSOF: - if (c == GSM0_SOF) { - gsm->state = GSM_SEARCH; - break; - } + gsm->state = GSM_SEARCH; + if (c == GSM0_SOF) + gsm_queue(gsm); + else + gsm->bad_size++; break; default: pr_debug("%s: unhandled state: %d\n", __func__, gsm->state); @@ -2023,12 +2026,35 @@ static void gsm0_receive(struct gsm_mux *gsm, unsigned char c) static void gsm1_receive(struct gsm_mux *gsm, unsigned char c) { + /* handle XON/XOFF */ + if ((c & ISO_IEC_646_MASK) == XON) { + gsm->constipated = true; + return; + } else if ((c & ISO_IEC_646_MASK) == XOFF) { + gsm->constipated = false; + /* Kick the link in case it is idling */ + gsm_data_kick(gsm, NULL); + return; + } if (c == GSM1_SOF) { - /* EOF is only valid in frame if we have got to the data state - and received at least one byte (the FCS) */ - if (gsm->state == GSM_DATA && gsm->count) { - /* Extract the FCS */ + /* EOF is only valid in frame if we have got to the data state */ + if (gsm->state == GSM_DATA) { + if (gsm->count < 1) { + /* Missing FSC */ + gsm->malformed++; + gsm->state = GSM_START; + return; + } + /* Remove the FCS from data */ gsm->count--; + if ((gsm->control & ~PF) != UIH) { + /* Calculate final FCS for UI frames over all + * data but FCS + */ + gsm->fcs = gsm_fcs_add_block(gsm->fcs, gsm->buf, + gsm->count); + } + /* Add the FCS itself to test against GOOD_FCS */ gsm->fcs = gsm_fcs_add(gsm->fcs, gsm->buf[gsm->count]); gsm->len = gsm->count; gsm_queue(gsm); @@ -2037,7 +2063,8 @@ static void gsm1_receive(struct gsm_mux *gsm, unsigned char c) } /* Any partial frame was a runt so go back to start */ if (gsm->state != GSM_START) { - gsm->malformed++; + if (gsm->state != GSM_SEARCH) + gsm->malformed++; gsm->state = GSM_START; } /* A SOF in GSM_START means we are still reading idling or @@ -2106,74 +2133,43 @@ static void gsm_error(struct gsm_mux *gsm) gsm->io_error++; } -static int gsm_disconnect(struct gsm_mux *gsm) -{ - struct gsm_dlci *dlci = gsm->dlci[0]; - struct gsm_control *gc; - - if (!dlci) - return 0; - - /* In theory disconnecting DLCI 0 is sufficient but for some - modems this is apparently not the case. */ - gc = gsm_control_send(gsm, CMD_CLD, NULL, 0); - if (gc) - gsm_control_wait(gsm, gc); - - del_timer_sync(&gsm->t2_timer); - /* Now we are sure T2 has stopped */ - - gsm_dlci_begin_close(dlci); - wait_event_interruptible(gsm->event, - dlci->state == DLCI_CLOSED); - - if (signal_pending(current)) - return -EINTR; - - return 0; -} - /** * gsm_cleanup_mux - generic GSM protocol cleanup * @gsm: our mux + * @disc: disconnect link? * * Clean up the bits of the mux which are the same for all framing * protocols. Remove the mux from the mux table, stop all the timers * and then shut down each device hanging up the channels as we go. */ -static void gsm_cleanup_mux(struct gsm_mux *gsm) +static void gsm_cleanup_mux(struct gsm_mux *gsm, bool disc) { int i; struct gsm_dlci *dlci = gsm->dlci[0]; struct gsm_msg *txq, *ntxq; gsm->dead = true; + mutex_lock(&gsm->mutex); - spin_lock(&gsm_mux_lock); - for (i = 0; i < MAX_MUX; i++) { - if (gsm_mux[i] == gsm) { - gsm_mux[i] = NULL; - break; + if (dlci) { + if (disc && dlci->state != DLCI_CLOSED) { + gsm_dlci_begin_close(dlci); + wait_event(gsm->event, dlci->state == DLCI_CLOSED); } + dlci->dead = true; } - spin_unlock(&gsm_mux_lock); - /* open failed before registering => nothing to do */ - if (i == MAX_MUX) - return; + /* Finish outstanding timers, making sure they are done */ del_timer_sync(&gsm->t2_timer); - /* Now we are sure T2 has stopped */ - if (dlci) - dlci->dead = true; - /* Free up any link layer users */ - mutex_lock(&gsm->mutex); - for (i = 0; i < NUM_DLCI; i++) + /* Free up any link layer users and finally the control channel */ + for (i = NUM_DLCI - 1; i >= 0; i--) if (gsm->dlci[i]) gsm_dlci_release(gsm->dlci[i]); mutex_unlock(&gsm->mutex); /* Now wipe the queues */ + tty_ldisc_flush(gsm->tty); list_for_each_entry_safe(txq, ntxq, &gsm->tx_list, list) kfree(txq); INIT_LIST_HEAD(&gsm->tx_list); @@ -2191,7 +2187,6 @@ static void gsm_cleanup_mux(struct gsm_mux *gsm) static int gsm_activate_mux(struct gsm_mux *gsm) { struct gsm_dlci *dlci; - int i = 0; timer_setup(&gsm->t2_timer, gsm_control_retransmit, 0); init_waitqueue_head(&gsm->event); @@ -2203,18 +2198,6 @@ static int gsm_activate_mux(struct gsm_mux *gsm) else gsm->receive = gsm1_receive; - spin_lock(&gsm_mux_lock); - for (i = 0; i < MAX_MUX; i++) { - if (gsm_mux[i] == NULL) { - gsm->num = i; - gsm_mux[i] = gsm; - break; - } - } - spin_unlock(&gsm_mux_lock); - if (i == MAX_MUX) - return -EBUSY; - dlci = gsm_dlci_alloc(gsm, 0); if (dlci == NULL) return -ENOMEM; @@ -2230,6 +2213,15 @@ static int gsm_activate_mux(struct gsm_mux *gsm) */ static void gsm_free_mux(struct gsm_mux *gsm) { + int i; + + for (i = 0; i < MAX_MUX; i++) { + if (gsm == gsm_mux[i]) { + gsm_mux[i] = NULL; + break; + } + } + mutex_destroy(&gsm->mutex); kfree(gsm->txframe); kfree(gsm->buf); kfree(gsm); @@ -2249,12 +2241,20 @@ static void gsm_free_muxr(struct kref *ref) static inline void mux_get(struct gsm_mux *gsm) { + unsigned long flags; + + spin_lock_irqsave(&gsm_mux_lock, flags); kref_get(&gsm->ref); + spin_unlock_irqrestore(&gsm_mux_lock, flags); } static inline void mux_put(struct gsm_mux *gsm) { + unsigned long flags; + + spin_lock_irqsave(&gsm_mux_lock, flags); kref_put(&gsm->ref, gsm_free_muxr); + spin_unlock_irqrestore(&gsm_mux_lock, flags); } static inline unsigned int mux_num_to_base(struct gsm_mux *gsm) @@ -2275,6 +2275,7 @@ static inline unsigned int mux_line_to_num(unsigned int line) static struct gsm_mux *gsm_alloc_mux(void) { + int i; struct gsm_mux *gsm = kzalloc(sizeof(struct gsm_mux), GFP_KERNEL); if (gsm == NULL) return NULL; @@ -2283,7 +2284,7 @@ static struct gsm_mux *gsm_alloc_mux(void) kfree(gsm); return NULL; } - gsm->txframe = kmalloc(2 * MAX_MRU + 2, GFP_KERNEL); + gsm->txframe = kmalloc(2 * (MAX_MTU + PROT_OVERHEAD - 1), GFP_KERNEL); if (gsm->txframe == NULL) { kfree(gsm->buf); kfree(gsm); @@ -2304,6 +2305,26 @@ static struct gsm_mux *gsm_alloc_mux(void) gsm->mtu = 64; gsm->dead = true; /* Avoid early tty opens */ + /* Store the instance to the mux array or abort if no space is + * available. + */ + spin_lock(&gsm_mux_lock); + for (i = 0; i < MAX_MUX; i++) { + if (!gsm_mux[i]) { + gsm_mux[i] = gsm; + gsm->num = i; + break; + } + } + spin_unlock(&gsm_mux_lock); + if (i == MAX_MUX) { + mutex_destroy(&gsm->mutex); + kfree(gsm->txframe); + kfree(gsm->buf); + kfree(gsm); + return NULL; + } + return gsm; } @@ -2339,7 +2360,7 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) /* Check the MRU/MTU range looks sane */ if (c->mru > MAX_MRU || c->mtu > MAX_MTU || c->mru < 8 || c->mtu < 8) return -EINVAL; - if (c->n2 < 3) + if (c->n2 > 255) return -EINVAL; if (c->encapsulation > 1) /* Basic, advanced, no I */ return -EINVAL; @@ -2370,19 +2391,11 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) /* * Close down what is needed, restart and initiate the new - * configuration + * configuration. On the first time there is no DLCI[0] + * and closing or cleaning up is not necessary. */ - - if (gsm->initiator && (need_close || need_restart)) { - int ret; - - ret = gsm_disconnect(gsm); - - if (ret) - return ret; - } - if (need_restart) - gsm_cleanup_mux(gsm); + if (need_close || need_restart) + gsm_cleanup_mux(gsm, true); gsm->initiator = c->initiator; gsm->mru = c->mru; @@ -2450,25 +2463,26 @@ static int gsmld_attach_gsm(struct tty_struct *tty, struct gsm_mux *gsm) int ret, i; gsm->tty = tty_kref_get(tty); + /* Turn off tty XON/XOFF handling to handle it explicitly. */ + gsm->old_c_iflag = tty->termios.c_iflag; + tty->termios.c_iflag &= (IXON | IXOFF); ret = gsm_activate_mux(gsm); if (ret != 0) tty_kref_put(gsm->tty); else { /* Don't register device 0 - this is the control channel and not a usable tty interface */ - if (gsm->initiator) { - base = mux_num_to_base(gsm); /* Base for this MUX */ - for (i = 1; i < NUM_DLCI; i++) { - struct device *dev; + base = mux_num_to_base(gsm); /* Base for this MUX */ + for (i = 1; i < NUM_DLCI; i++) { + struct device *dev; - dev = tty_register_device(gsm_tty_driver, + dev = tty_register_device(gsm_tty_driver, base + i, NULL); - if (IS_ERR(dev)) { - for (i--; i >= 1; i--) - tty_unregister_device(gsm_tty_driver, - base + i); - return PTR_ERR(dev); - } + if (IS_ERR(dev)) { + for (i--; i >= 1; i--) + tty_unregister_device(gsm_tty_driver, + base + i); + return PTR_ERR(dev); } } } @@ -2490,11 +2504,10 @@ static void gsmld_detach_gsm(struct tty_struct *tty, struct gsm_mux *gsm) int i; WARN_ON(tty != gsm->tty); - if (gsm->initiator) { - for (i = 1; i < NUM_DLCI; i++) - tty_unregister_device(gsm_tty_driver, base + i); - } - gsm_cleanup_mux(gsm); + for (i = 1; i < NUM_DLCI; i++) + tty_unregister_device(gsm_tty_driver, base + i); + /* Restore tty XON/XOFF handling. */ + gsm->tty->termios.c_iflag = gsm->old_c_iflag; tty_kref_put(gsm->tty); gsm->tty = NULL; } @@ -2559,6 +2572,12 @@ static void gsmld_close(struct tty_struct *tty) { struct gsm_mux *gsm = tty->disc_data; + /* The ldisc locks and closes the port before calling our close. This + * means we have no way to do a proper disconnect. We will not bother + * to do one. + */ + gsm_cleanup_mux(gsm, false); + gsmld_detach_gsm(tty, gsm); gsmld_flush_buffer(tty); @@ -2597,7 +2616,7 @@ static int gsmld_open(struct tty_struct *tty) ret = gsmld_attach_gsm(tty, gsm); if (ret != 0) { - gsm_cleanup_mux(gsm); + gsm_cleanup_mux(gsm, false); mux_put(gsm); } return ret; @@ -2954,26 +2973,78 @@ static struct tty_ldisc_ops tty_ldisc_packet = { #define TX_SIZE 512 -static int gsmtty_modem_update(struct gsm_dlci *dlci, u8 brk) +/** + * gsm_modem_upd_via_data - send modem bits via convergence layer + * @dlci: channel + * @brk: break signal + * + * Send an empty frame to signal mobile state changes and to transmit the + * break signal for adaption 2. + */ + +static void gsm_modem_upd_via_data(struct gsm_dlci *dlci, u8 brk) { - u8 modembits[5]; + struct gsm_mux *gsm = dlci->gsm; + unsigned long flags; + + if (dlci->state != DLCI_OPEN || dlci->adaption != 2) + return; + + spin_lock_irqsave(&gsm->tx_lock, flags); + gsm_dlci_modem_output(gsm, dlci, brk); + spin_unlock_irqrestore(&gsm->tx_lock, flags); +} + +/** + * gsm_modem_upd_via_msc - send modem bits via control frame + * @dlci: channel + * @brk: break signal + */ + +static int gsm_modem_upd_via_msc(struct gsm_dlci *dlci, u8 brk) +{ + u8 modembits[3]; struct gsm_control *ctrl; int len = 2; - if (brk) - len++; + if (dlci->gsm->encoding != 0) + return 0; - modembits[0] = len << 1 | EA; /* Data bytes */ - modembits[1] = dlci->addr << 2 | 3; /* DLCI, EA, 1 */ - modembits[2] = gsm_encode_modem(dlci) << 1 | EA; - if (brk) - modembits[3] = brk << 4 | 2 | EA; /* Valid, EA */ - ctrl = gsm_control_send(dlci->gsm, CMD_MSC, modembits, len + 1); + modembits[0] = (dlci->addr << 2) | 2 | EA; /* DLCI, Valid, EA */ + if (!brk) { + modembits[1] = (gsm_encode_modem(dlci) << 1) | EA; + } else { + modembits[1] = gsm_encode_modem(dlci) << 1; + modembits[2] = (brk << 4) | 2 | EA; /* Length, Break, EA */ + len++; + } + ctrl = gsm_control_send(dlci->gsm, CMD_MSC, modembits, len); if (ctrl == NULL) return -ENOMEM; return gsm_control_wait(dlci->gsm, ctrl); } +/** + * gsm_modem_update - send modem status line state + * @dlci: channel + * @brk: break signal + */ + +static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk) +{ + if (dlci->adaption == 2) { + /* Send convergence layer type 2 empty data frame. */ + gsm_modem_upd_via_data(dlci, brk); + return 0; + } else if (dlci->gsm->encoding == 0) { + /* Send as MSC control message. */ + return gsm_modem_upd_via_msc(dlci, brk); + } + + /* Modem status lines are not supported. */ + return -EPROTONOSUPPORT; +} + static int gsm_carrier_raised(struct tty_port *port) { struct gsm_dlci *dlci = container_of(port, struct gsm_dlci, port); @@ -3006,7 +3077,7 @@ static void gsm_dtr_rts(struct tty_port *port, int onoff) modem_tx &= ~(TIOCM_DTR | TIOCM_RTS); if (modem_tx != dlci->modem_tx) { dlci->modem_tx = modem_tx; - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } } @@ -3155,13 +3226,17 @@ static unsigned int gsmtty_chars_in_buffer(struct tty_struct *tty) static void gsmtty_flush_buffer(struct tty_struct *tty) { struct gsm_dlci *dlci = tty->driver_data; + unsigned long flags; + if (dlci->state == DLCI_CLOSED) return; /* Caution needed: If we implement reliable transport classes then the data being transmitted can't simply be junked once it has first hit the stack. Until then we can just blow it away */ + spin_lock_irqsave(&dlci->lock, flags); kfifo_reset(&dlci->fifo); + spin_unlock_irqrestore(&dlci->lock, flags); /* Need to unhook this DLCI from the transmit queue logic */ } @@ -3193,7 +3268,7 @@ static int gsmtty_tiocmset(struct tty_struct *tty, if (modem_tx != dlci->modem_tx) { dlci->modem_tx = modem_tx; - return gsmtty_modem_update(dlci, 0); + return gsm_modem_update(dlci, 0); } return 0; } @@ -3254,7 +3329,7 @@ static void gsmtty_throttle(struct tty_struct *tty) dlci->modem_tx &= ~TIOCM_RTS; dlci->throttled = true; /* Send an MSC with RTS cleared */ - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } static void gsmtty_unthrottle(struct tty_struct *tty) @@ -3266,7 +3341,7 @@ static void gsmtty_unthrottle(struct tty_struct *tty) dlci->modem_tx |= TIOCM_RTS; dlci->throttled = false; /* Send an MSC with RTS set */ - gsmtty_modem_update(dlci, 0); + gsm_modem_update(dlci, 0); } static int gsmtty_break_ctl(struct tty_struct *tty, int state) @@ -3284,7 +3359,7 @@ static int gsmtty_break_ctl(struct tty_struct *tty, int state) if (encode > 0x0F) encode = 0x0F; /* Best effort */ } - return gsmtty_modem_update(dlci, encode); + return gsm_modem_update(dlci, encode); } static void gsmtty_cleanup(struct tty_struct *tty) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index e17e97ea86fa..a293e9f107d0 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -2667,7 +2667,7 @@ enum pci_board_num_t { pbn_panacom2, pbn_panacom4, pbn_plx_romulus, - pbn_endrun_2_4000000, + pbn_endrun_2_3906250, pbn_oxsemi, pbn_oxsemi_1_3906250, pbn_oxsemi_2_3906250, @@ -3195,10 +3195,10 @@ static struct pciserial_board pci_boards[] = { * signal now many ports are available * 2 port 952 Uart support */ - [pbn_endrun_2_4000000] = { + [pbn_endrun_2_3906250] = { .flags = FL_BASE0, .num_ports = 2, - .base_baud = 4000000, + .base_baud = 3906250, .uart_offset = 0x200, .first_offset = 0x1000, }, @@ -4115,7 +4115,7 @@ static const struct pci_device_id serial_pci_tbl[] = { */ { PCI_VENDOR_ID_ENDRUN, PCI_DEVICE_ID_ENDRUN_1588, PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_endrun_2_4000000 }, + pbn_endrun_2_3906250 }, /* * Quatech cards. These actually have configurable clocks but for * now we just use the default. diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 318af6f13605..1fbd5bf264be 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1675,11 +1675,11 @@ static void serial8250_start_tx(struct uart_port *port) struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; - serial8250_rpm_get_tx(up); - if (!port->x_char && uart_circ_empty(&port->state->xmit)) return; + serial8250_rpm_get_tx(up); + if (em485 && em485->active_timer == &em485->start_tx_timer) return; @@ -3329,7 +3329,7 @@ static void serial8250_console_restore(struct uart_8250_port *up) serial8250_set_divisor(port, baud, quot, frac); serial_port_out(port, UART_LCR, up->lcr); - serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS); + serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); } /* diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 51ecb050ae40..4d11a3e547f9 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1255,13 +1255,18 @@ static inline bool pl011_dma_rx_running(struct uart_amba_port *uap) static void pl011_rs485_tx_stop(struct uart_amba_port *uap) { + /* + * To be on the safe side only time out after twice as many iterations + * as fifo size. + */ + const int MAX_TX_DRAIN_ITERS = uap->port.fifosize * 2; struct uart_port *port = &uap->port; int i = 0; u32 cr; /* Wait until hardware tx queue is empty */ while (!pl011_tx_empty(port)) { - if (i == port->fifosize) { + if (i > MAX_TX_DRAIN_ITERS) { dev_warn(port->dev, "timeout while draining hardware tx queue\n"); break; @@ -2052,7 +2057,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios, * with the given baud rate. We use this as the poll interval when we * wait for the tx queue to empty. */ - uap->rs485_tx_drain_interval = (bits * 1000 * 1000) / baud; + uap->rs485_tx_drain_interval = DIV_ROUND_UP(bits * 1000 * 1000, baud); pl011_setup_status_masks(port, termios); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index fd38e6ed4fda..a2100be8d554 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -1448,7 +1448,7 @@ static int imx_uart_startup(struct uart_port *port) imx_uart_writel(sport, ucr1, UCR1); ucr4 = imx_uart_readl(sport, UCR4) & ~(UCR4_OREN | UCR4_INVR); - if (!sport->dma_is_enabled) + if (!dma_is_inited) ucr4 |= UCR4_OREN; if (sport->inverted_rx) ucr4 |= UCR4_INVR; diff --git a/drivers/tty/serial/mpc52xx_uart.c b/drivers/tty/serial/mpc52xx_uart.c index 8a6958377764..3acc0f185762 100644 --- a/drivers/tty/serial/mpc52xx_uart.c +++ b/drivers/tty/serial/mpc52xx_uart.c @@ -436,31 +436,31 @@ static void mpc512x_psc_fifo_init(struct uart_port *port) out_be32(&FIFO_512x(port)->rximr, MPC512x_PSC_FIFO_ALARM); } -static int mpc512x_psc_raw_rx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_raw_rx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_512x(port)->rxsr) & MPC512x_PSC_FIFO_EMPTY); } -static int mpc512x_psc_raw_tx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_raw_tx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_512x(port)->txsr) & MPC512x_PSC_FIFO_FULL); } -static int mpc512x_psc_rx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_rx_rdy(struct uart_port *port) { return in_be32(&FIFO_512x(port)->rxsr) & in_be32(&FIFO_512x(port)->rximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc512x_psc_tx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_tx_rdy(struct uart_port *port) { return in_be32(&FIFO_512x(port)->txsr) & in_be32(&FIFO_512x(port)->tximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc512x_psc_tx_empty(struct uart_port *port) +static unsigned int mpc512x_psc_tx_empty(struct uart_port *port) { return in_be32(&FIFO_512x(port)->txsr) & MPC512x_PSC_FIFO_EMPTY; @@ -780,29 +780,29 @@ static void mpc5125_psc_fifo_init(struct uart_port *port) out_be32(&FIFO_5125(port)->rximr, MPC512x_PSC_FIFO_ALARM); } -static int mpc5125_psc_raw_rx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_raw_rx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_5125(port)->rxsr) & MPC512x_PSC_FIFO_EMPTY); } -static int mpc5125_psc_raw_tx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_raw_tx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_5125(port)->txsr) & MPC512x_PSC_FIFO_FULL); } -static int mpc5125_psc_rx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_rx_rdy(struct uart_port *port) { return in_be32(&FIFO_5125(port)->rxsr) & in_be32(&FIFO_5125(port)->rximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc5125_psc_tx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_tx_rdy(struct uart_port *port) { return in_be32(&FIFO_5125(port)->txsr) & in_be32(&FIFO_5125(port)->tximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc5125_psc_tx_empty(struct uart_port *port) +static unsigned int mpc5125_psc_tx_empty(struct uart_port *port) { return in_be32(&FIFO_5125(port)->txsr) & MPC512x_PSC_FIFO_EMPTY; } diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index e857fb61efbf..5fb201c1b563 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1238,12 +1238,10 @@ static void sc16is7xx_shutdown(struct uart_port *port) /* Disable all interrupts */ sc16is7xx_port_write(port, SC16IS7XX_IER_REG, 0); - /* Disable TX/RX, clear auto RS485 and RTS invert */ + /* Disable TX/RX */ sc16is7xx_port_update(port, SC16IS7XX_EFCR_REG, SC16IS7XX_EFCR_RXDISABLE_BIT | - SC16IS7XX_EFCR_TXDISABLE_BIT | - SC16IS7XX_EFCR_AUTO_RS485_BIT | - SC16IS7XX_EFCR_RTS_INVERT_BIT, + SC16IS7XX_EFCR_TXDISABLE_BIT, SC16IS7XX_EFCR_RXDISABLE_BIT | SC16IS7XX_EFCR_TXDISABLE_BIT); diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index f9af7ebe003d..d6d515d598dc 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -2684,6 +2684,7 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) struct usb_request *request; struct cdns3_request *priv_req; struct cdns3_trb *trb = NULL; + struct cdns3_trb trb_tmp; int ret; int val; @@ -2693,8 +2694,10 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) if (request) { priv_req = to_cdns3_request(request); trb = priv_req->trb; - if (trb) + if (trb) { + trb_tmp = *trb; trb->control = trb->control ^ cpu_to_le32(TRB_CYCLE); + } } writel(EP_CMD_CSTALL | EP_CMD_EPRST, &priv_dev->regs->ep_cmd); @@ -2709,7 +2712,7 @@ int __cdns3_gadget_ep_clear_halt(struct cdns3_endpoint *priv_ep) if (request) { if (trb) - trb->control = trb->control ^ cpu_to_le32(TRB_CYCLE); + *trb = trb_tmp; cdns3_rearm_transfer(priv_ep, 1); } diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6abb7294e919..b5b85bf80329 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -1209,12 +1209,16 @@ static int do_proc_control(struct usb_dev_state *ps, usb_unlock_device(dev); i = usbfs_start_wait_urb(urb, tmo, &actlen); + + /* Linger a bit, prior to the next control message. */ + if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) + msleep(200); usb_lock_device(dev); snoop_urb(dev, NULL, pipe, actlen, i, COMPLETE, tbuf, actlen); if (!i && actlen) { if (copy_to_user(ctrl->data, tbuf, actlen)) { ret = -EFAULT; - goto recv_fault; + goto done; } } } else { @@ -1231,6 +1235,10 @@ static int do_proc_control(struct usb_dev_state *ps, usb_unlock_device(dev); i = usbfs_start_wait_urb(urb, tmo, &actlen); + + /* Linger a bit, prior to the next control message. */ + if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) + msleep(200); usb_lock_device(dev); snoop_urb(dev, NULL, pipe, actlen, i, COMPLETE, NULL, 0); } @@ -1242,10 +1250,6 @@ static int do_proc_control(struct usb_dev_state *ps, } ret = (i < 0 ? i : actlen); - recv_fault: - /* Linger a bit, prior to the next control message. */ - if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) - msleep(200); done: kfree(dr); usb_free_urb(urb); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index d3c14b5ed4a1..97b44a68668a 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -404,6 +404,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0b05, 0x17e0), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Realtek Semiconductor Corp. Mass Storage Device (Multicard Reader)*/ + { USB_DEVICE(0x0bda, 0x0151), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Realtek hub in Dell WD19 (Type-C) */ { USB_DEVICE(0x0bda, 0x0487), .driver_info = USB_QUIRK_NO_LPM }, @@ -507,6 +510,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* VCOM device */ + { USB_DEVICE(0x4296, 0x7570), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 1170b800acdc..d28cd1a6709b 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -274,7 +274,8 @@ int dwc3_core_soft_reset(struct dwc3 *dwc) reg = dwc3_readl(dwc->regs, DWC3_DCTL); reg |= DWC3_DCTL_CSFTRST; - dwc3_writel(dwc->regs, DWC3_DCTL, reg); + reg &= ~DWC3_DCTL_RUN_STOP; + dwc3_gadget_dctl_write_safe(dwc, reg); /* * For DWC_usb31 controller 1.90a and later, the DCTL.CSFRST bit @@ -1377,10 +1378,10 @@ static void dwc3_get_properties(struct dwc3 *dwc) u8 lpm_nyet_threshold; u8 tx_de_emphasis; u8 hird_threshold; - u8 rx_thr_num_pkt_prd; - u8 rx_max_burst_prd; - u8 tx_thr_num_pkt_prd; - u8 tx_max_burst_prd; + u8 rx_thr_num_pkt_prd = 0; + u8 rx_max_burst_prd = 0; + u8 tx_thr_num_pkt_prd = 0; + u8 tx_max_burst_prd = 0; u8 tx_fifo_resize_max_num; const char *usb_psy_name; int ret; @@ -1690,21 +1691,44 @@ static int dwc3_probe(struct platform_device *pdev) /* * Clocks are optional, but new DT platforms should support all * clocks as required by the DT-binding. + * Some devices have different clock names in legacy device trees, + * check for them to retain backwards compatibility. */ dwc->bus_clk = devm_clk_get_optional(dev, "bus_early"); if (IS_ERR(dwc->bus_clk)) return dev_err_probe(dev, PTR_ERR(dwc->bus_clk), "could not get bus clock\n"); + if (dwc->bus_clk == NULL) { + dwc->bus_clk = devm_clk_get_optional(dev, "bus_clk"); + if (IS_ERR(dwc->bus_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->bus_clk), + "could not get bus clock\n"); + } + dwc->ref_clk = devm_clk_get_optional(dev, "ref"); if (IS_ERR(dwc->ref_clk)) return dev_err_probe(dev, PTR_ERR(dwc->ref_clk), "could not get ref clock\n"); + if (dwc->ref_clk == NULL) { + dwc->ref_clk = devm_clk_get_optional(dev, "ref_clk"); + if (IS_ERR(dwc->ref_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->ref_clk), + "could not get ref clock\n"); + } + dwc->susp_clk = devm_clk_get_optional(dev, "suspend"); if (IS_ERR(dwc->susp_clk)) return dev_err_probe(dev, PTR_ERR(dwc->susp_clk), "could not get suspend clock\n"); + + if (dwc->susp_clk == NULL) { + dwc->susp_clk = devm_clk_get_optional(dev, "suspend_clk"); + if (IS_ERR(dwc->susp_clk)) + return dev_err_probe(dev, PTR_ERR(dwc->susp_clk), + "could not get suspend clock\n"); + } } ret = reset_control_deassert(dwc->reset); diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c index b60b5f7b6dff..8cad9e7d3368 100644 --- a/drivers/usb/dwc3/drd.c +++ b/drivers/usb/dwc3/drd.c @@ -584,16 +584,15 @@ int dwc3_drd_init(struct dwc3 *dwc) { int ret, irq; + if (ROLE_SWITCH && + device_property_read_bool(dwc->dev, "usb-role-switch")) + return dwc3_setup_role_switch(dwc); + dwc->edev = dwc3_get_extcon(dwc); if (IS_ERR(dwc->edev)) return PTR_ERR(dwc->edev); - if (ROLE_SWITCH && - device_property_read_bool(dwc->dev, "usb-role-switch")) { - ret = dwc3_setup_role_switch(dwc); - if (ret < 0) - return ret; - } else if (dwc->edev) { + if (dwc->edev) { dwc->edev_nb.notifier_call = dwc3_drd_notifier; ret = extcon_register_notifier(dwc->edev, EXTCON_USB_HOST, &dwc->edev_nb); diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 33f657d83246..2e19e0e4ea53 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -45,6 +45,8 @@ #define PCI_DEVICE_ID_INTEL_ADLM 0x54ee #define PCI_DEVICE_ID_INTEL_ADLS 0x7ae1 #define PCI_DEVICE_ID_INTEL_RPLS 0x7a61 +#define PCI_DEVICE_ID_INTEL_MTLP 0x7ec1 +#define PCI_DEVICE_ID_INTEL_MTL 0x7e7e #define PCI_DEVICE_ID_INTEL_TGL 0x9a15 #define PCI_DEVICE_ID_AMD_MR 0x163a @@ -456,6 +458,12 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPLS), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLP), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index ab725d2262d6..0b9c2493844a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -3274,6 +3274,7 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, const struct dwc3_event_depevt *event, struct dwc3_request *req, int status) { + int request_status; int ret; if (req->request.num_mapped_sgs) @@ -3294,7 +3295,35 @@ static int dwc3_gadget_ep_cleanup_completed_request(struct dwc3_ep *dep, req->needs_extra_trb = false; } - dwc3_gadget_giveback(dep, req, status); + /* + * The event status only reflects the status of the TRB with IOC set. + * For the requests that don't set interrupt on completion, the driver + * needs to check and return the status of the completed TRBs associated + * with the request. Use the status of the last TRB of the request. + */ + if (req->request.no_interrupt) { + struct dwc3_trb *trb; + + trb = dwc3_ep_prev_trb(dep, dep->trb_dequeue); + switch (DWC3_TRB_SIZE_TRBSTS(trb->size)) { + case DWC3_TRBSTS_MISSED_ISOC: + /* Isoc endpoint only */ + request_status = -EXDEV; + break; + case DWC3_TRB_STS_XFER_IN_PROG: + /* Applicable when End Transfer with ForceRM=0 */ + case DWC3_TRBSTS_SETUP_PENDING: + /* Control endpoint only */ + case DWC3_TRBSTS_OK: + default: + request_status = 0; + break; + } + } else { + request_status = status; + } + + dwc3_gadget_giveback(dep, req, request_status); out: return ret; diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 1fb837d9271e..84b73cb03f87 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1438,6 +1438,8 @@ static void configfs_composite_unbind(struct usb_gadget *gadget) usb_ep_autoconfig_reset(cdev->gadget); spin_lock_irqsave(&gi->spinlock, flags); cdev->gadget = NULL; + cdev->deactivations = 0; + gadget->deactivated = false; set_gadget_data(gadget, NULL); spin_unlock_irqrestore(&gi->spinlock, flags); } diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c index d852ac9e47e7..2cda982f3765 100644 --- a/drivers/usb/gadget/function/uvc_queue.c +++ b/drivers/usb/gadget/function/uvc_queue.c @@ -264,6 +264,8 @@ void uvcg_queue_cancel(struct uvc_video_queue *queue, int disconnect) buf->state = UVC_BUF_STATE_ERROR; vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_ERROR); } + queue->buf_used = 0; + /* This must be protected by the irqlock spinlock to avoid race * conditions between uvc_queue_buffer and the disconnection event that * could result in an interruptible wait in uvc_dequeue_buffer. Do not diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 3d82e0b853be..684164fa9716 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -1103,6 +1103,26 @@ static void ehci_remove_device(struct usb_hcd *hcd, struct usb_device *udev) #ifdef CONFIG_PM +/* Clear wakeup signal locked in zhaoxin platform when device plug in. */ +static void ehci_zx_wakeup_clear(struct ehci_hcd *ehci) +{ + u32 __iomem *reg = &ehci->regs->port_status[4]; + u32 t1 = ehci_readl(ehci, reg); + + t1 &= (u32)~0xf0000; + t1 |= PORT_TEST_FORCE; + ehci_writel(ehci, t1, reg); + t1 = ehci_readl(ehci, reg); + msleep(1); + t1 &= (u32)~0xf0000; + ehci_writel(ehci, t1, reg); + ehci_readl(ehci, reg); + msleep(1); + t1 = ehci_readl(ehci, reg); + ehci_writel(ehci, t1 | PORT_CSC, reg); + ehci_readl(ehci, reg); +} + /* suspend/resume, section 4.3 */ /* These routines handle the generic parts of controller suspend/resume */ @@ -1154,6 +1174,9 @@ int ehci_resume(struct usb_hcd *hcd, bool force_reset) if (ehci->shutdown) return 0; /* Controller is dead */ + if (ehci->zx_wakeup_clear_needed) + ehci_zx_wakeup_clear(ehci); + /* * If CF is still set and reset isn't forced * then we maintained suspend power. diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 638f03b89739..9937c5a7efc2 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -231,6 +231,10 @@ static int ehci_pci_setup(struct usb_hcd *hcd) ehci->is_aspeed = 1; } break; + case PCI_VENDOR_ID_ZHAOXIN: + if (pdev->device == 0x3104 && (pdev->revision & 0xf0) == 0x90) + ehci->zx_wakeup_clear_needed = 1; + break; } /* optional debug port, normally in the first BAR */ diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h index fdd073cc053b..ad3f13a3eaf1 100644 --- a/drivers/usb/host/ehci.h +++ b/drivers/usb/host/ehci.h @@ -220,6 +220,7 @@ struct ehci_hcd { /* one per controller */ unsigned imx28_write_fix:1; /* For Freescale i.MX28 */ unsigned spurious_oc:1; unsigned is_aspeed:1; + unsigned zx_wakeup_clear_needed:1; /* required for usb32 quirk */ #define OHCI_CTRL_HCFS (3 << 6) diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 1e7dc130c39a..f65f1ba2b592 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1434,7 +1434,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, } spin_unlock_irqrestore(&xhci->lock, flags); if (!wait_for_completion_timeout(&bus_state->u3exit_done[wIndex], - msecs_to_jiffies(100))) + msecs_to_jiffies(500))) xhci_dbg(xhci, "missing U0 port change event for port %d-%d\n", hcd->self.busnum, wIndex + 1); spin_lock_irqsave(&xhci->lock, flags); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 5c351970cdf1..d7e0e6ebf080 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -59,6 +59,7 @@ #define PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI 0x9a13 #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138 #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI 0x461e +#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed #define PCI_DEVICE_ID_AMD_RENOIR_XHCI 0x1639 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9 @@ -266,7 +267,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) pdev->device == PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI || - pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI)) + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI)) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (pdev->vendor == PCI_VENDOR_ID_ETRON && diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index d0b6806275e0..f9707997969d 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3141,6 +3141,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) if (event_loop++ < TRBS_PER_SEGMENT / 2) continue; xhci_update_erst_dequeue(xhci, event_ring_deq); + event_ring_deq = xhci->event_ring->dequeue; /* ring is half-full, force isoc trbs to interrupt more often */ if (xhci->isoc_bei_interval > AVOID_BEI_INTERVAL_MIN) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index c8af2cd2216d..996958a6565c 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1034,13 +1034,13 @@ static int tegra_xusb_unpowergate_partitions(struct tegra_xusb *tegra) int rc; if (tegra->use_genpd) { - rc = pm_runtime_get_sync(tegra->genpd_dev_ss); + rc = pm_runtime_resume_and_get(tegra->genpd_dev_ss); if (rc < 0) { dev_err(dev, "failed to enable XUSB SS partition\n"); return rc; } - rc = pm_runtime_get_sync(tegra->genpd_dev_host); + rc = pm_runtime_resume_and_get(tegra->genpd_dev_host); if (rc < 0) { dev_err(dev, "failed to enable XUSB Host partition\n"); pm_runtime_put_sync(tegra->genpd_dev_ss); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 642610c78f58..25b87e99b4dd 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -781,6 +781,17 @@ void xhci_shutdown(struct usb_hcd *hcd) if (xhci->quirks & XHCI_SPURIOUS_REBOOT) usb_disable_xhci_ports(to_pci_dev(hcd->self.sysdev)); + /* Don't poll the roothubs after shutdown. */ + xhci_dbg(xhci, "%s: stopping usb%d port polling.\n", + __func__, hcd->self.busnum); + clear_bit(HCD_FLAG_POLL_RH, &hcd->flags); + del_timer_sync(&hcd->rh_timer); + + if (xhci->shared_hcd) { + clear_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags); + del_timer_sync(&xhci->shared_hcd->rh_timer); + } + spin_lock_irq(&xhci->lock); xhci_halt(xhci); /* Workaround for spurious wakeups at shutdown with HSW */ diff --git a/drivers/usb/misc/qcom_eud.c b/drivers/usb/misc/qcom_eud.c index f929bffdc5d1..b7f13df00764 100644 --- a/drivers/usb/misc/qcom_eud.c +++ b/drivers/usb/misc/qcom_eud.c @@ -186,16 +186,16 @@ static int eud_probe(struct platform_device *pdev) chip->dev = &pdev->dev; - ret = devm_add_action_or_reset(chip->dev, eud_role_switch_release, chip); - if (ret) - return dev_err_probe(chip->dev, ret, - "failed to add role switch release action\n"); - chip->role_sw = usb_role_switch_get(&pdev->dev); if (IS_ERR(chip->role_sw)) return dev_err_probe(chip->dev, PTR_ERR(chip->role_sw), "failed to get role switch\n"); + ret = devm_add_action_or_reset(chip->dev, eud_role_switch_release, chip); + if (ret) + return dev_err_probe(chip->dev, ret, + "failed to add role switch release action\n"); + chip->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(chip->base)) return PTR_ERR(chip->base); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index 748139d26263..0be8efcda15d 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -71,6 +71,7 @@ static void destroy_priv(struct kref *kref) dev_dbg(&priv->usbdev->dev, "destroying priv datastructure\n"); usb_put_dev(priv->usbdev); + priv->usbdev = NULL; kfree(priv); } @@ -736,7 +737,6 @@ static int uss720_probe(struct usb_interface *intf, parport_announce_port(pp); usb_set_intfdata(intf, pp); - usb_put_dev(usbdev); return 0; probe_abort: @@ -754,7 +754,6 @@ static void uss720_disconnect(struct usb_interface *intf) usb_set_intfdata(intf, NULL); if (pp) { priv = pp->private_data; - priv->usbdev = NULL; priv->pp = NULL; dev_dbg(&intf->dev, "parport_remove_port\n"); parport_remove_port(pp); diff --git a/drivers/usb/mtu3/mtu3_dr.c b/drivers/usb/mtu3/mtu3_dr.c index a6b04831b20b..9b8aded3d95e 100644 --- a/drivers/usb/mtu3/mtu3_dr.c +++ b/drivers/usb/mtu3/mtu3_dr.c @@ -21,10 +21,8 @@ static inline struct ssusb_mtk *otg_sx_to_ssusb(struct otg_switch_mtk *otg_sx) static void toggle_opstate(struct ssusb_mtk *ssusb) { - if (!ssusb->otg_switch.is_u3_drd) { - mtu3_setbits(ssusb->mac_base, U3D_DEVICE_CONTROL, DC_SESSION); - mtu3_setbits(ssusb->mac_base, U3D_POWER_MANAGEMENT, SOFT_CONN); - } + mtu3_setbits(ssusb->mac_base, U3D_DEVICE_CONTROL, DC_SESSION); + mtu3_setbits(ssusb->mac_base, U3D_POWER_MANAGEMENT, SOFT_CONN); } /* only port0 supports dual-role mode */ diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c index 661a229c105d..34b9f8140187 100644 --- a/drivers/usb/phy/phy-generic.c +++ b/drivers/usb/phy/phy-generic.c @@ -268,6 +268,13 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop) return -EPROBE_DEFER; } + nop->vbus_draw = devm_regulator_get_exclusive(dev, "vbus"); + if (PTR_ERR(nop->vbus_draw) == -ENODEV) + nop->vbus_draw = NULL; + if (IS_ERR(nop->vbus_draw)) + return dev_err_probe(dev, PTR_ERR(nop->vbus_draw), + "could not get vbus regulator\n"); + nop->dev = dev; nop->phy.dev = nop->dev; nop->phy.label = "nop-xceiv"; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index a27f7efcec6a..c374620a486f 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -194,6 +194,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x16DC, 0x0015) }, /* W-IE-NE-R Plein & Baus GmbH CML Control, Monitoring and Data Logger */ { USB_DEVICE(0x17A8, 0x0001) }, /* Kamstrup Optical Eye/3-wire */ { USB_DEVICE(0x17A8, 0x0005) }, /* Kamstrup M-Bus Master MultiPort 250D */ + { USB_DEVICE(0x17A8, 0x0101) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Int Ant) */ + { USB_DEVICE(0x17A8, 0x0102) }, /* Kamstrup 868 MHz wM-Bus C-Mode Meter Reader (Ext Ant) */ { USB_DEVICE(0x17F4, 0xAAAA) }, /* Wavesense Jazz blood glucose meter */ { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e7755d9cfc61..1364ce7f0abf 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -432,6 +432,8 @@ static void option_instat_callback(struct urb *urb); #define CINTERION_PRODUCT_CLS8 0x00b0 #define CINTERION_PRODUCT_MV31_MBIM 0x00b3 #define CINTERION_PRODUCT_MV31_RMNET 0x00b7 +#define CINTERION_PRODUCT_MV32_WA 0x00f1 +#define CINTERION_PRODUCT_MV32_WB 0x00f2 /* Olivetti products */ #define OLIVETTI_VENDOR_ID 0x0b3c @@ -1217,6 +1219,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1056, 0xff), /* Telit FD980 */ .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1057, 0xff), /* Telit FN980 */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1058, 0xff), /* Telit FN980 (PCIe) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1060, 0xff), /* Telit LN920 (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1061, 0xff), /* Telit LN920 (MBIM) */ @@ -1233,6 +1239,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990 (PCIe) */ + .driver_info = RSVD(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -1969,6 +1977,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3)}, { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV31_RMNET, 0xff), .driver_info = RSVD(0)}, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WA, 0xff), + .driver_info = RSVD(3)}, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_MV32_WB, 0xff), + .driver_info = RSVD(3)}, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100), .driver_info = RSVD(4) }, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120), diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c index da65d14c9ed5..06aad0d727dd 100644 --- a/drivers/usb/serial/whiteheat.c +++ b/drivers/usb/serial/whiteheat.c @@ -584,9 +584,8 @@ static int firm_send_command(struct usb_serial_port *port, __u8 command, switch (command) { case WHITEHEAT_GET_DTR_RTS: info = usb_get_serial_port_data(port); - memcpy(&info->mcr, command_info->result_buffer, - sizeof(struct whiteheat_dr_info)); - break; + info->mcr = command_info->result_buffer[0]; + break; } } exit: diff --git a/drivers/usb/typec/Kconfig b/drivers/usb/typec/Kconfig index 8f921213b17d..ba24847fb245 100644 --- a/drivers/usb/typec/Kconfig +++ b/drivers/usb/typec/Kconfig @@ -56,6 +56,7 @@ config TYPEC_RT1719 tristate "Richtek RT1719 Sink Only Type-C controller driver" depends on USB_ROLE_SWITCH || !USB_ROLE_SWITCH depends on I2C + depends on POWER_SUPPLY select REGMAP_I2C help Say Y or M here if your system has Richtek RT1719 sink only diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index f0c2fa19f3e0..a6045aef0d04 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -949,6 +949,8 @@ static int ucsi_dr_swap(struct typec_port *port, enum typec_data_role role) role == TYPEC_HOST)) goto out_unlock; + reinit_completion(&con->complete); + command = UCSI_SET_UOR | UCSI_CONNECTOR_NUMBER(con->num); command |= UCSI_SET_UOR_ROLE(role); command |= UCSI_SET_UOR_ACCEPT_ROLE_SWAPS; @@ -956,14 +958,18 @@ static int ucsi_dr_swap(struct typec_port *port, enum typec_data_role role) if (ret < 0) goto out_unlock; + mutex_unlock(&con->lock); + if (!wait_for_completion_timeout(&con->complete, - msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) - ret = -ETIMEDOUT; + msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) + return -ETIMEDOUT; + + return 0; out_unlock: mutex_unlock(&con->lock); - return ret < 0 ? ret : 0; + return ret; } static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) @@ -985,6 +991,8 @@ static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) if (cur_role == role) goto out_unlock; + reinit_completion(&con->complete); + command = UCSI_SET_PDR | UCSI_CONNECTOR_NUMBER(con->num); command |= UCSI_SET_PDR_ROLE(role); command |= UCSI_SET_PDR_ACCEPT_ROLE_SWAPS; @@ -992,11 +1000,13 @@ static int ucsi_pr_swap(struct typec_port *port, enum typec_role role) if (ret < 0) goto out_unlock; + mutex_unlock(&con->lock); + if (!wait_for_completion_timeout(&con->complete, - msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) { - ret = -ETIMEDOUT; - goto out_unlock; - } + msecs_to_jiffies(UCSI_SWAP_TIMEOUT_MS))) + return -ETIMEDOUT; + + mutex_lock(&con->lock); /* Something has gone wrong while swapping the role */ if (UCSI_CONSTAT_PWR_OPMODE(con->status.flags) != diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2f4fb09f1e89..79001301b383 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -163,6 +163,7 @@ struct mlx5_vdpa_net { u32 cur_num_vqs; struct notifier_block nb; struct vdpa_callback config_cb; + struct mlx5_vdpa_wq_ent cvq_ent; }; static void free_resources(struct mlx5_vdpa_net *ndev); @@ -1658,6 +1659,12 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) mvdev = wqent->mvdev; ndev = to_mlx5_vdpa_ndev(mvdev); cvq = &mvdev->cvq; + + mutex_lock(&ndev->reslock); + + if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto out; + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))) goto out; @@ -1696,9 +1703,13 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) if (vringh_need_notify_iotlb(&cvq->vring)) vringh_notify(&cvq->vring); + + queue_work(mvdev->wq, &wqent->work); + break; } + out: - kfree(wqent); + mutex_unlock(&ndev->reslock); } static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) @@ -1706,7 +1717,6 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; - struct mlx5_vdpa_wq_ent *wqent; if (!is_index_valid(mvdev, idx)) return; @@ -1715,13 +1725,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) if (!mvdev->wq || !mvdev->cvq.ready) return; - wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); - if (!wqent) - return; - - wqent->mvdev = mvdev; - INIT_WORK(&wqent->work, mlx5_cvq_kick_handler); - queue_work(mvdev->wq, &wqent->work); + queue_work(mvdev->wq, &ndev->cvq_ent.work); return; } @@ -2180,7 +2184,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb goto err_mr; if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) - return 0; + goto err_mr; restore_channels_info(ndev); err = setup_driver(mvdev); @@ -2195,12 +2199,14 @@ err_mr: return err; } +/* reslock must be held for this function */ static int setup_driver(struct mlx5_vdpa_dev *mvdev) { struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); int err; - mutex_lock(&ndev->reslock); + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (ndev->setup) { mlx5_vdpa_warn(mvdev, "setup driver called for already setup driver\n"); err = 0; @@ -2230,7 +2236,6 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev) goto err_fwd; } ndev->setup = true; - mutex_unlock(&ndev->reslock); return 0; @@ -2241,23 +2246,23 @@ err_tir: err_rqt: teardown_virtqueues(ndev); out: - mutex_unlock(&ndev->reslock); return err; } +/* reslock must be held for this function */ static void teardown_driver(struct mlx5_vdpa_net *ndev) { - mutex_lock(&ndev->reslock); + + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (!ndev->setup) - goto out; + return; remove_fwd_to_tir(ndev); destroy_tir(ndev); destroy_rqt(ndev); teardown_virtqueues(ndev); ndev->setup = false; -out: - mutex_unlock(&ndev->reslock); } static void clear_vqs_ready(struct mlx5_vdpa_net *ndev) @@ -2278,6 +2283,8 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) print_status(mvdev, status, true); + mutex_lock(&ndev->reslock); + if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) { if (status & VIRTIO_CONFIG_S_DRIVER_OK) { err = setup_driver(mvdev); @@ -2287,16 +2294,19 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) } } else { mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n"); - return; + goto err_clear; } } ndev->mvdev.status = status; + mutex_unlock(&ndev->reslock); return; err_setup: mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; +err_clear: + mutex_unlock(&ndev->reslock); } static int mlx5_vdpa_reset(struct vdpa_device *vdev) @@ -2306,6 +2316,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) print_status(mvdev, 0, true); mlx5_vdpa_info(mvdev, "performing device reset\n"); + + mutex_lock(&ndev->reslock); teardown_driver(ndev); clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); @@ -2318,6 +2330,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) if (mlx5_vdpa_create_mr(mvdev, NULL)) mlx5_vdpa_warn(mvdev, "create MR failed\n"); } + mutex_unlock(&ndev->reslock); return 0; } @@ -2353,19 +2366,24 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev) static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); bool change_map; int err; + mutex_lock(&ndev->reslock); + err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map); if (err) { mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err); - return err; + goto err; } if (change_map) - return mlx5_vdpa_change_map(mvdev, iotlb); + err = mlx5_vdpa_change_map(mvdev, iotlb); - return 0; +err: + mutex_unlock(&ndev->reslock); + return err; } static void mlx5_vdpa_free(struct vdpa_device *vdev) @@ -2740,6 +2758,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, if (err) goto err_mr; + ndev->cvq_ent.mvdev = mvdev; + INIT_WORK(&ndev->cvq_ent.work, mlx5_cvq_kick_handler); mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq"); if (!mvdev->wq) { err = -ENOMEM; diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index b7bb16f92ac6..06b6f3594a13 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -36,6 +36,10 @@ static bool nointxmask; static bool disable_vga; static bool disable_idle_d3; +/* List of PF's that vfio_pci_core_sriov_configure() has been called on */ +static DEFINE_MUTEX(vfio_pci_sriov_pfs_mutex); +static LIST_HEAD(vfio_pci_sriov_pfs); + static inline bool vfio_vga_disabled(void) { #ifdef CONFIG_VFIO_PCI_VGA @@ -434,47 +438,17 @@ out: } EXPORT_SYMBOL_GPL(vfio_pci_core_disable); -static struct vfio_pci_core_device *get_pf_vdev(struct vfio_pci_core_device *vdev) -{ - struct pci_dev *physfn = pci_physfn(vdev->pdev); - struct vfio_device *pf_dev; - - if (!vdev->pdev->is_virtfn) - return NULL; - - pf_dev = vfio_device_get_from_dev(&physfn->dev); - if (!pf_dev) - return NULL; - - if (pci_dev_driver(physfn) != pci_dev_driver(vdev->pdev)) { - vfio_device_put(pf_dev); - return NULL; - } - - return container_of(pf_dev, struct vfio_pci_core_device, vdev); -} - -static void vfio_pci_vf_token_user_add(struct vfio_pci_core_device *vdev, int val) -{ - struct vfio_pci_core_device *pf_vdev = get_pf_vdev(vdev); - - if (!pf_vdev) - return; - - mutex_lock(&pf_vdev->vf_token->lock); - pf_vdev->vf_token->users += val; - WARN_ON(pf_vdev->vf_token->users < 0); - mutex_unlock(&pf_vdev->vf_token->lock); - - vfio_device_put(&pf_vdev->vdev); -} - void vfio_pci_core_close_device(struct vfio_device *core_vdev) { struct vfio_pci_core_device *vdev = container_of(core_vdev, struct vfio_pci_core_device, vdev); - vfio_pci_vf_token_user_add(vdev, -1); + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + WARN_ON(!vdev->sriov_pf_core_dev->vf_token->users); + vdev->sriov_pf_core_dev->vf_token->users--; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_core_disable(vdev); @@ -495,7 +469,12 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev) { vfio_pci_probe_mmaps(vdev); vfio_spapr_pci_eeh_open(vdev->pdev); - vfio_pci_vf_token_user_add(vdev, 1); + + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + vdev->sriov_pf_core_dev->vf_token->users++; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } } EXPORT_SYMBOL_GPL(vfio_pci_core_finish_enable); @@ -1583,11 +1562,8 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, * * If the VF token is provided but unused, an error is generated. */ - if (!vdev->pdev->is_virtfn && !vdev->vf_token && !vf_token) - return 0; /* No VF token provided or required */ - if (vdev->pdev->is_virtfn) { - struct vfio_pci_core_device *pf_vdev = get_pf_vdev(vdev); + struct vfio_pci_core_device *pf_vdev = vdev->sriov_pf_core_dev; bool match; if (!pf_vdev) { @@ -1600,7 +1576,6 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, } if (!vf_token) { - vfio_device_put(&pf_vdev->vdev); pci_info_ratelimited(vdev->pdev, "VF token required to access device\n"); return -EACCES; @@ -1610,8 +1585,6 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, match = uuid_equal(uuid, &pf_vdev->vf_token->uuid); mutex_unlock(&pf_vdev->vf_token->lock); - vfio_device_put(&pf_vdev->vdev); - if (!match) { pci_info_ratelimited(vdev->pdev, "Incorrect VF token provided for device\n"); @@ -1732,8 +1705,30 @@ static int vfio_pci_bus_notifier(struct notifier_block *nb, static int vfio_pci_vf_init(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; + struct vfio_pci_core_device *cur; + struct pci_dev *physfn; int ret; + if (pdev->is_virtfn) { + /* + * If this VF was created by our vfio_pci_core_sriov_configure() + * then we can find the PF vfio_pci_core_device now, and due to + * the locking in pci_disable_sriov() it cannot change until + * this VF device driver is removed. + */ + physfn = pci_physfn(vdev->pdev); + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_for_each_entry(cur, &vfio_pci_sriov_pfs, sriov_pfs_item) { + if (cur->pdev == physfn) { + vdev->sriov_pf_core_dev = cur; + break; + } + } + mutex_unlock(&vfio_pci_sriov_pfs_mutex); + return 0; + } + + /* Not a SRIOV PF */ if (!pdev->is_physfn) return 0; @@ -1805,6 +1800,7 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, INIT_LIST_HEAD(&vdev->ioeventfds_list); mutex_init(&vdev->vma_lock); INIT_LIST_HEAD(&vdev->vma_list); + INIT_LIST_HEAD(&vdev->sriov_pfs_item); init_rwsem(&vdev->memory_lock); } EXPORT_SYMBOL_GPL(vfio_pci_core_init_device); @@ -1896,7 +1892,7 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; - pci_disable_sriov(pdev); + vfio_pci_core_sriov_configure(pdev, 0); vfio_unregister_group_dev(&vdev->vdev); @@ -1935,21 +1931,49 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_aer_err_detected); int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn) { + struct vfio_pci_core_device *vdev; struct vfio_device *device; int ret = 0; + device_lock_assert(&pdev->dev); + device = vfio_device_get_from_dev(&pdev->dev); if (!device) return -ENODEV; - if (nr_virtfn == 0) - pci_disable_sriov(pdev); - else + vdev = container_of(device, struct vfio_pci_core_device, vdev); + + if (nr_virtfn) { + mutex_lock(&vfio_pci_sriov_pfs_mutex); + /* + * The thread that adds the vdev to the list is the only thread + * that gets to call pci_enable_sriov() and we will only allow + * it to be called once without going through + * pci_disable_sriov() + */ + if (!list_empty(&vdev->sriov_pfs_item)) { + ret = -EINVAL; + goto out_unlock; + } + list_add_tail(&vdev->sriov_pfs_item, &vfio_pci_sriov_pfs); + mutex_unlock(&vfio_pci_sriov_pfs_mutex); ret = pci_enable_sriov(pdev, nr_virtfn); + if (ret) + goto out_del; + ret = nr_virtfn; + goto out_put; + } - vfio_device_put(device); + pci_disable_sriov(pdev); - return ret < 0 ? ret : nr_virtfn; +out_del: + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_del_init(&vdev->sriov_pfs_item); +out_unlock: + mutex_unlock(&vfio_pci_sriov_pfs_mutex); +out_put: + vfio_device_put(device); + return ret; } EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure); diff --git a/drivers/video/fbdev/arkfb.c b/drivers/video/fbdev/arkfb.c index edf169d0816e..eb3e47c58c5f 100644 --- a/drivers/video/fbdev/arkfb.c +++ b/drivers/video/fbdev/arkfb.c @@ -566,6 +566,9 @@ static int arkfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { int rv, mem, step; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (arkfb_formats, var, NULL); if (rv < 0) diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c index 6ff16d3132e5..b26c81233b6b 100644 --- a/drivers/video/fbdev/aty/aty128fb.c +++ b/drivers/video/fbdev/aty/aty128fb.c @@ -68,7 +68,6 @@ #ifdef CONFIG_PPC_PMAC #include <asm/machdep.h> #include <asm/pmac_feature.h> -#include <asm/prom.h> #include "../macmodes.h" #endif diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index 1aef3d6ebd88..a3e6faed7745 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -79,7 +79,6 @@ #ifdef __powerpc__ #include <asm/machdep.h> -#include <asm/prom.h> #include "../macmodes.h" #endif #ifdef __sparc__ diff --git a/drivers/video/fbdev/aty/radeon_pm.c b/drivers/video/fbdev/aty/radeon_pm.c index b5fbd5329652..97a5972f5b1f 100644 --- a/drivers/video/fbdev/aty/radeon_pm.c +++ b/drivers/video/fbdev/aty/radeon_pm.c @@ -22,7 +22,6 @@ #ifdef CONFIG_PPC_PMAC #include <asm/machdep.h> -#include <asm/prom.h> #include <asm/pmac_feature.h> #endif diff --git a/drivers/video/fbdev/aty/radeonfb.h b/drivers/video/fbdev/aty/radeonfb.h index 93f403cbb415..91d81b576231 100644 --- a/drivers/video/fbdev/aty/radeonfb.h +++ b/drivers/video/fbdev/aty/radeonfb.h @@ -21,7 +21,7 @@ #include <asm/io.h> -#if defined(CONFIG_PPC) || defined(CONFIG_SPARC) +#ifdef CONFIG_SPARC #include <asm/prom.h> #endif diff --git a/drivers/video/fbdev/clps711x-fb.c b/drivers/video/fbdev/clps711x-fb.c index c5d15c6db287..771ce1f76951 100644 --- a/drivers/video/fbdev/clps711x-fb.c +++ b/drivers/video/fbdev/clps711x-fb.c @@ -268,8 +268,7 @@ static int clps711x_fb_probe(struct platform_device *pdev) goto out_fb_release; } - cfb->syscon = - syscon_regmap_lookup_by_compatible("cirrus,ep7209-syscon1"); + cfb->syscon = syscon_regmap_lookup_by_phandle(np, "syscon"); if (IS_ERR(cfb->syscon)) { ret = PTR_ERR(cfb->syscon); goto out_fb_release; diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c index bd59e7b11ed5..aba46118b208 100644 --- a/drivers/video/fbdev/controlfb.c +++ b/drivers/video/fbdev/controlfb.c @@ -47,9 +47,6 @@ #include <linux/nvram.h> #include <linux/adb.h> #include <linux/cuda.h> -#ifdef CONFIG_PPC_PMAC -#include <asm/prom.h> -#endif #ifdef CONFIG_BOOTX_TEXT #include <asm/btext.h> #endif diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 34d6bb1bf82e..a6bb0e438216 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1579,7 +1579,14 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a, * If it's not a platform device, at least print a warning. A * fix would add code to remove the device from the system. */ - if (dev_is_platform(device)) { + if (!device) { + /* TODO: Represent each OF framebuffer as its own + * device in the device hierarchy. For now, offb + * doesn't have such a device, so unregister the + * framebuffer as before without warning. + */ + do_unregister_framebuffer(registered_fb[i]); + } else if (dev_is_platform(device)) { registered_fb[i]->forced_out = true; platform_device_unregister(to_platform_device(device)); } else { diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c index 52cce0db8bd3..09dd85553d4f 100644 --- a/drivers/video/fbdev/i740fb.c +++ b/drivers/video/fbdev/i740fb.c @@ -657,6 +657,9 @@ static int i740fb_decode_var(const struct fb_var_screeninfo *var, static int i740fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { + if (!var->pixclock) + return -EINVAL; + switch (var->bits_per_pixel) { case 8: var->red.offset = var->green.offset = var->blue.offset = 0; @@ -740,7 +743,7 @@ static int i740fb_set_par(struct fb_info *info) if (i) return i; - memset(info->screen_base, 0, info->screen_size); + memset_io(info->screen_base, 0, info->screen_size); vga_protect(par); diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c index 68288756ffff..a2f644c97f28 100644 --- a/drivers/video/fbdev/imxfb.c +++ b/drivers/video/fbdev/imxfb.c @@ -925,10 +925,12 @@ static int imxfb_probe(struct platform_device *pdev) sizeof(struct imx_fb_videomode), GFP_KERNEL); if (!fbi->mode) { ret = -ENOMEM; + of_node_put(display_np); goto failed_of_parse; } ret = imxfb_of_read_mode(&pdev->dev, display_np, fbi->mode); + of_node_put(display_np); if (ret) goto failed_of_parse; } diff --git a/drivers/video/fbdev/kyro/fbdev.c b/drivers/video/fbdev/kyro/fbdev.c index 25801e8e3f74..d57772f96ad2 100644 --- a/drivers/video/fbdev/kyro/fbdev.c +++ b/drivers/video/fbdev/kyro/fbdev.c @@ -494,6 +494,8 @@ static int kyrofb_set_par(struct fb_info *info) info->var.hsync_len + info->var.left_margin)) / 1000; + if (!lineclock) + return -EINVAL; /* time for a frame in ns (precision in 32bpp) */ frameclock = lineclock * (info->var.yres + diff --git a/drivers/video/fbdev/matrox/matroxfb_base.h b/drivers/video/fbdev/matrox/matroxfb_base.h index 759dee996af1..958be6805f87 100644 --- a/drivers/video/fbdev/matrox/matroxfb_base.h +++ b/drivers/video/fbdev/matrox/matroxfb_base.h @@ -47,7 +47,6 @@ #include <asm/unaligned.h> #if defined(CONFIG_PPC_PMAC) -#include <asm/prom.h> #include "../macmodes.h" #endif diff --git a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c index 63721337a377..a7508f5be343 100644 --- a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c +++ b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c @@ -18,6 +18,8 @@ #include <linux/interrupt.h> #include <linux/pci.h> #if defined(CONFIG_OF) +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #endif #include "mb862xxfb.h" diff --git a/drivers/video/fbdev/mmp/core.c b/drivers/video/fbdev/mmp/core.c index 154127256a2c..03707461eced 100644 --- a/drivers/video/fbdev/mmp/core.c +++ b/drivers/video/fbdev/mmp/core.c @@ -127,19 +127,18 @@ EXPORT_SYMBOL_GPL(mmp_unregister_panel); */ struct mmp_path *mmp_get_path(const char *name) { - struct mmp_path *path; - int found = 0; + struct mmp_path *path = NULL, *iter; mutex_lock(&disp_lock); - list_for_each_entry(path, &path_list, node) { - if (!strcmp(name, path->name)) { - found = 1; + list_for_each_entry(iter, &path_list, node) { + if (!strcmp(name, iter->name)) { + path = iter; break; } } mutex_unlock(&disp_lock); - return found ? path : NULL; + return path; } EXPORT_SYMBOL_GPL(mmp_get_path); diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c index 966df2a07360..28d32cbf496b 100644 --- a/drivers/video/fbdev/neofb.c +++ b/drivers/video/fbdev/neofb.c @@ -585,7 +585,7 @@ neofb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) DBG("neofb_check_var"); - if (var->pixclock && PICOS2KHZ(var->pixclock) > par->maxClock) + if (!var->pixclock || PICOS2KHZ(var->pixclock) > par->maxClock) return -EINVAL; /* Is the mode larger than the LCD panel? */ diff --git a/drivers/video/fbdev/omap/hwa742.c b/drivers/video/fbdev/omap/hwa742.c index b191bef22d98..9d9fe5c3a7a1 100644 --- a/drivers/video/fbdev/omap/hwa742.c +++ b/drivers/video/fbdev/omap/hwa742.c @@ -964,7 +964,7 @@ static int hwa742_init(struct omapfb_device *fbdev, int ext_mode, if ((r = calc_extif_timings(ext_clk, &extif_mem_div)) < 0) goto err3; hwa742.extif->set_timings(&hwa742.reg_timings); - clk_enable(hwa742.sys_ck); + clk_prepare_enable(hwa742.sys_ck); calc_hwa742_clk_rates(ext_clk, &sys_clk, &pix_clk); if ((r = calc_extif_timings(sys_clk, &extif_mem_div)) < 0) @@ -1023,7 +1023,7 @@ static int hwa742_init(struct omapfb_device *fbdev, int ext_mode, return 0; err4: - clk_disable(hwa742.sys_ck); + clk_disable_unprepare(hwa742.sys_ck); err3: hwa742.extif->cleanup(); err2: @@ -1037,7 +1037,7 @@ static void hwa742_cleanup(void) hwa742_set_update_mode(OMAPFB_UPDATE_DISABLED); hwa742.extif->cleanup(); hwa742.int_ctrl->cleanup(); - clk_disable(hwa742.sys_ck); + clk_disable_unprepare(hwa742.sys_ck); } struct lcd_ctrl hwa742_ctrl = { diff --git a/drivers/video/fbdev/omap/lcdc.c b/drivers/video/fbdev/omap/lcdc.c index 7317c9aad677..97d20dc0d1d0 100644 --- a/drivers/video/fbdev/omap/lcdc.c +++ b/drivers/video/fbdev/omap/lcdc.c @@ -711,7 +711,7 @@ static int omap_lcdc_init(struct omapfb_device *fbdev, int ext_mode, dev_err(fbdev->dev, "failed to adjust LCD rate\n"); goto fail1; } - clk_enable(lcdc.lcd_ck); + clk_prepare_enable(lcdc.lcd_ck); r = request_irq(OMAP_LCDC_IRQ, lcdc_irq_handler, 0, MODULE_NAME, fbdev); if (r) { @@ -746,7 +746,7 @@ fail4: fail3: free_irq(OMAP_LCDC_IRQ, lcdc.fbdev); fail2: - clk_disable(lcdc.lcd_ck); + clk_disable_unprepare(lcdc.lcd_ck); fail1: clk_put(lcdc.lcd_ck); fail0: @@ -760,7 +760,7 @@ static void omap_lcdc_cleanup(void) free_fbmem(); omap_free_lcd_dma(); free_irq(OMAP_LCDC_IRQ, lcdc.fbdev); - clk_disable(lcdc.lcd_ck); + clk_disable_unprepare(lcdc.lcd_ck); clk_put(lcdc.lcd_ck); } diff --git a/drivers/video/fbdev/omap/sossi.c b/drivers/video/fbdev/omap/sossi.c index 80ac67f27f0d..b9cb8b386627 100644 --- a/drivers/video/fbdev/omap/sossi.c +++ b/drivers/video/fbdev/omap/sossi.c @@ -598,7 +598,7 @@ static int sossi_init(struct omapfb_device *fbdev) l &= ~CONF_SOSSI_RESET_R; omap_writel(l, MOD_CONF_CTRL_1); - clk_enable(sossi.fck); + clk_prepare_enable(sossi.fck); l = omap_readl(ARM_IDLECT2); l &= ~(1 << 8); /* DMACK_REQ */ omap_writel(l, ARM_IDLECT2); @@ -649,7 +649,7 @@ static int sossi_init(struct omapfb_device *fbdev) return 0; err: - clk_disable(sossi.fck); + clk_disable_unprepare(sossi.fck); clk_put(sossi.fck); return r; } @@ -657,6 +657,7 @@ err: static void sossi_cleanup(void) { omap_lcdc_free_dma_callback(); + clk_unprepare(sossi.fck); clk_put(sossi.fck); iounmap(sossi.base); } diff --git a/drivers/video/fbdev/platinumfb.c b/drivers/video/fbdev/platinumfb.c index ce413a9df06e..5b9e26ea6449 100644 --- a/drivers/video/fbdev/platinumfb.c +++ b/drivers/video/fbdev/platinumfb.c @@ -30,9 +30,9 @@ #include <linux/fb.h> #include <linux/init.h> #include <linux/nvram.h> +#include <linux/of_address.h> #include <linux/of_device.h> #include <linux/of_platform.h> -#include <asm/prom.h> #include "macmodes.h" #include "platinumfb.h" diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c index c68725eebee3..d3be2c64f1c0 100644 --- a/drivers/video/fbdev/pm2fb.c +++ b/drivers/video/fbdev/pm2fb.c @@ -1504,9 +1504,7 @@ static const struct fb_ops pm2fb_ops = { /** - * Device initialisation - * - * Initialise and allocate resource for PCI device. + * pm2fb_probe - Initialise and allocate resource for PCI device. * * @pdev: PCI device. * @id: PCI device ID. @@ -1711,9 +1709,7 @@ static int pm2fb_probe(struct pci_dev *pdev, const struct pci_device_id *id) } /** - * Device removal. - * - * Release all device resources. + * pm2fb_remove - Release all device resources. * * @pdev: PCI device to clean up. */ diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c index f1551e00eb12..8ad91c251fe6 100644 --- a/drivers/video/fbdev/pxafb.c +++ b/drivers/video/fbdev/pxafb.c @@ -2256,10 +2256,10 @@ static int pxafb_probe(struct platform_device *dev) goto failed; for (i = 0; i < inf->num_modes; i++) inf->modes[i] = pdata->modes[i]; + } else { + inf = of_pxafb_of_mach_info(&dev->dev); } - if (!pdata) - inf = of_pxafb_of_mach_info(&dev->dev); if (IS_ERR_OR_NULL(inf)) goto failed; diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c index 5c74253e7b2c..b93c8eb02336 100644 --- a/drivers/video/fbdev/s3fb.c +++ b/drivers/video/fbdev/s3fb.c @@ -549,6 +549,9 @@ static int s3fb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) int rv, mem, step; u16 m, n, r; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (s3fb_formats, var, NULL); diff --git a/drivers/video/fbdev/sh_mobile_lcdcfb.c b/drivers/video/fbdev/sh_mobile_lcdcfb.c index aa4ebe3192ec..9a4417430b4e 100644 --- a/drivers/video/fbdev/sh_mobile_lcdcfb.c +++ b/drivers/video/fbdev/sh_mobile_lcdcfb.c @@ -531,9 +531,6 @@ static void sh_mobile_lcdc_display_off(struct sh_mobile_lcdc_chan *ch) ch->tx_dev->ops->display_off(ch->tx_dev); } -static int sh_mobile_lcdc_check_var(struct fb_var_screeninfo *var, - struct fb_info *info); - /* ----------------------------------------------------------------------------- * Format helpers */ diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 742f62986b80..f28fd69d5eb7 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -4463,7 +4463,7 @@ static void sisfb_post_sis300(struct pci_dev *pdev) SiS_SetReg(SISCR, 0x37, 0x02); SiS_SetReg(SISPART2, 0x00, 0x1c); v4 = 0x00; v5 = 0x00; v6 = 0x10; - if(ivideo->SiS_Pr.UseROM) { + if (ivideo->SiS_Pr.UseROM && bios) { v4 = bios[0xf5]; v5 = bios[0xf6]; v6 = bios[0xf7]; diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c index 4d20cb557ff0..319131bd72cf 100644 --- a/drivers/video/fbdev/tridentfb.c +++ b/drivers/video/fbdev/tridentfb.c @@ -996,6 +996,9 @@ static int tridentfb_check_var(struct fb_var_screeninfo *var, int ramdac = 230000; /* 230MHz for most 3D chips */ debug("enter\n"); + if (!var->pixclock) + return -EINVAL; + /* check color depth */ if (bpp == 24) bpp = var->bits_per_pixel = 32; diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index b6ec0b8e2b72..d280733f283b 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -1650,8 +1650,9 @@ static int dlfb_usb_probe(struct usb_interface *intf, const struct device_attribute *attr; struct dlfb_data *dlfb; struct fb_info *info; - int retval = -ENOMEM; + int retval; struct usb_device *usbdev = interface_to_usbdev(intf); + struct usb_endpoint_descriptor *out; /* usb initialization */ dlfb = kzalloc(sizeof(*dlfb), GFP_KERNEL); @@ -1665,6 +1666,12 @@ static int dlfb_usb_probe(struct usb_interface *intf, dlfb->udev = usb_get_dev(usbdev); usb_set_intfdata(intf, dlfb); + retval = usb_find_common_endpoints(intf->cur_altsetting, NULL, &out, NULL, NULL); + if (retval) { + dev_err(&intf->dev, "Device should have at lease 1 bulk endpoint!\n"); + goto error; + } + dev_dbg(&intf->dev, "console enable=%d\n", console); dev_dbg(&intf->dev, "fb_defio enable=%d\n", fb_defio); dev_dbg(&intf->dev, "shadow enable=%d\n", shadow); @@ -1674,6 +1681,7 @@ static int dlfb_usb_probe(struct usb_interface *intf, if (!dlfb_parse_vendor_descriptor(dlfb, intf)) { dev_err(&intf->dev, "firmware not recognized, incompatible device?\n"); + retval = -ENODEV; goto error; } @@ -1687,8 +1695,10 @@ static int dlfb_usb_probe(struct usb_interface *intf, /* allocates framebuffer driver structure, not framebuffer memory */ info = framebuffer_alloc(0, &dlfb->udev->dev); - if (!info) + if (!info) { + retval = -ENOMEM; goto error; + } dlfb->info = info; info->par = dlfb; diff --git a/drivers/video/fbdev/valkyriefb.c b/drivers/video/fbdev/valkyriefb.c index 8425afe37d7c..a6c9d4f26669 100644 --- a/drivers/video/fbdev/valkyriefb.c +++ b/drivers/video/fbdev/valkyriefb.c @@ -54,10 +54,9 @@ #include <linux/nvram.h> #include <linux/adb.h> #include <linux/cuda.h> +#include <linux/of_address.h> #ifdef CONFIG_MAC #include <asm/macintosh.h> -#else -#include <asm/prom.h> #endif #include "macmodes.h" diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c index 7a959e5ba90b..a92a8c670cf0 100644 --- a/drivers/video/fbdev/vt8623fb.c +++ b/drivers/video/fbdev/vt8623fb.c @@ -321,6 +321,9 @@ static int vt8623fb_check_var(struct fb_var_screeninfo *var, struct fb_info *inf { int rv, mem, step; + if (!var->pixclock) + return -EINVAL; + /* Find appropriate format */ rv = svga_match_format (vt8623fb_formats, var, NULL); if (rv < 0) diff --git a/drivers/video/of_display_timing.c b/drivers/video/of_display_timing.c index f93b6abbe258..bebd371c6b93 100644 --- a/drivers/video/of_display_timing.c +++ b/drivers/video/of_display_timing.c @@ -199,7 +199,7 @@ struct display_timings *of_get_display_timings(const struct device_node *np) struct display_timing *dt; int r; - dt = kzalloc(sizeof(*dt), GFP_KERNEL); + dt = kmalloc(sizeof(*dt), GFP_KERNEL); if (!dt) { pr_err("%pOF: could not allocate display_timing struct\n", np); diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 75c8d560bbd3..22f15f444f75 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -526,9 +526,8 @@ int virtio_device_restore(struct virtio_device *dev) goto err; } - /* If restore didn't do it, mark device DRIVER_OK ourselves. */ - if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) - virtio_device_ready(dev); + /* Finally, tell the device we're all set */ + virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); virtio_config_enable(dev); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index dfe26fa17e95..617a7f4f07a8 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -689,29 +689,34 @@ void xen_free_ballooned_pages(unsigned int nr_pages, struct page **pages) } EXPORT_SYMBOL(xen_free_ballooned_pages); -#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC) -static void __init balloon_add_region(unsigned long start_pfn, - unsigned long pages) +static void __init balloon_add_regions(void) { +#if defined(CONFIG_XEN_PV) + unsigned long start_pfn, pages; unsigned long pfn, extra_pfn_end; + unsigned int i; - /* - * If the amount of usable memory has been limited (e.g., with - * the 'mem' command line parameter), don't add pages beyond - * this limit. - */ - extra_pfn_end = min(max_pfn, start_pfn + pages); + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + pages = xen_extra_mem[i].n_pfns; + if (!pages) + continue; - for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) { - /* totalram_pages and totalhigh_pages do not - include the boot-time balloon extension, so - don't subtract from it. */ - balloon_append(pfn_to_page(pfn)); - } + start_pfn = xen_extra_mem[i].start_pfn; - balloon_stats.total_pages += extra_pfn_end - start_pfn; -} + /* + * If the amount of usable memory has been limited (e.g., with + * the 'mem' command line parameter), don't add pages beyond + * this limit. + */ + extra_pfn_end = min(max_pfn, start_pfn + pages); + + for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) + balloon_append(pfn_to_page(pfn)); + + balloon_stats.total_pages += extra_pfn_end - start_pfn; + } #endif +} static int __init balloon_init(void) { @@ -745,20 +750,7 @@ static int __init balloon_init(void) register_sysctl_table(xen_root); #endif -#if defined(CONFIG_XEN_PV) && !defined(CONFIG_XEN_UNPOPULATED_ALLOC) - { - int i; - - /* - * Initialize the balloon with pages from the extra memory - * regions (see arch/x86/xen/setup.c). - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) - if (xen_extra_mem[i].n_pfns) - balloon_add_region(xen_extra_mem[i].start_pfn, - xen_extra_mem[i].n_pfns); - } -#endif + balloon_add_regions(); task = kthread_run(balloon_thread, NULL, "xen-balloon"); if (IS_ERR(task)) { diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 4849f94372a4..55acb32842a3 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -178,9 +178,9 @@ static void __del_gref(struct gntalloc_gref *gref) unsigned long addr; if (gref->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) { - uint8_t *tmp = kmap(gref->page); + uint8_t *tmp = kmap_local_page(gref->page); tmp[gref->notify.pgoff] = 0; - kunmap(gref->page); + kunmap_local(tmp); } if (gref->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { notify_remote_via_evtchn(gref->notify.event); diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index a8b41057c382..a39f2d36dd9c 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -230,39 +230,6 @@ void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages) } EXPORT_SYMBOL(xen_free_unpopulated_pages); -#ifdef CONFIG_XEN_PV -static int __init init(void) -{ - unsigned int i; - - if (!xen_domain()) - return -ENODEV; - - if (!xen_pv_domain()) - return 0; - - /* - * Initialize with pages from the extra memory regions (see - * arch/x86/xen/setup.c). - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - unsigned int j; - - for (j = 0; j < xen_extra_mem[i].n_pfns; j++) { - struct page *pg = - pfn_to_page(xen_extra_mem[i].start_pfn + j); - - pg->zone_device_data = page_list; - page_list = pg; - list_count++; - } - } - - return 0; -} -subsys_initcall(init); -#endif - static int __init unpopulated_init(void) { int ret; diff --git a/fs/afs/write.c b/fs/afs/write.c index 6bcf1475511b..4763132ca57e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -616,8 +616,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, _debug("write discard %x @%llx [%llx]", len, start, i_size); /* The dirty region was entirely beyond the EOF. */ - fscache_clear_page_bits(afs_vnode_cache(vnode), - mapping, start, len, caching); + fscache_clear_page_bits(mapping, start, len, caching); afs_pages_written_back(vnode, start, len); ret = 0; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6556e13ed95f..63c7ebb0da89 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1117,11 +1117,11 @@ out_free_interp: * independently randomized mmap region (0 load_bias * without MAP_FIXED nor MAP_FIXED_NOREPLACE). */ - alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); - if (interpreter || alignment > ELF_MIN_ALIGN) { + if (interpreter) { load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); + alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); if (alignment) load_bias &= ~(alignment - 1); elf_flags |= MAP_FIXED_NOREPLACE; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c22d287e020b..0dd6de994199 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2503,12 +2503,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - /* - * New block group is likely to be used soon. Try to activate it now. - * Failure is OK for now. - */ - btrfs_zone_activate(cache); - ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ @@ -2946,7 +2940,6 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans) struct btrfs_path *path = NULL; LIST_HEAD(dirty); struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; int loops = 0; spin_lock(&cur_trans->dirty_bgs_lock); @@ -3012,7 +3005,6 @@ again: cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; /* @@ -3113,7 +3105,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) int should_put; struct btrfs_path *path; struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; path = btrfs_alloc_path(); if (!path) @@ -3171,7 +3162,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; list_add_tail(&cache->io_list, io); } else { @@ -3455,7 +3445,7 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type) return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); } -static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) +static struct btrfs_block_group *do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) { struct btrfs_block_group *bg; int ret; @@ -3542,7 +3532,11 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) out: btrfs_trans_release_chunk_metadata(trans); - return ret; + if (ret) + return ERR_PTR(ret); + + btrfs_get_block_group(bg); + return bg; } /* @@ -3657,10 +3651,17 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *space_info; + struct btrfs_block_group *ret_bg; bool wait_for_alloc = false; bool should_alloc = false; + bool from_extent_allocation = false; int ret = 0; + if (force == CHUNK_ALLOC_FORCE_FOR_EXTENT) { + from_extent_allocation = true; + force = CHUNK_ALLOC_FORCE; + } + /* Don't re-enter if we're already allocating a chunk */ if (trans->allocating_chunk) return -ENOSPC; @@ -3750,9 +3751,22 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, force_metadata_allocation(fs_info); } - ret = do_chunk_alloc(trans, flags); + ret_bg = do_chunk_alloc(trans, flags); trans->allocating_chunk = false; + if (IS_ERR(ret_bg)) { + ret = PTR_ERR(ret_bg); + } else if (from_extent_allocation) { + /* + * New block group is likely to be used soon. Try to activate + * it now. Failure is OK for now. + */ + btrfs_zone_activate(ret_bg); + } + + if (!ret) + btrfs_put_block_group(ret_bg); + spin_lock(&space_info->lock); if (ret < 0) { if (ret == -ENOSPC) diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 93aabc68bb6a..e8308f2ad07d 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -35,11 +35,15 @@ enum btrfs_discard_state { * the FS with empty chunks * * CHUNK_ALLOC_FORCE means it must try to allocate one + * + * CHUNK_ALLOC_FORCE_FOR_EXTENT like CHUNK_ALLOC_FORCE but called from + * find_free_extent() that also activaes the zone */ enum btrfs_chunk_alloc_enum { CHUNK_ALLOC_NO_FORCE, CHUNK_ALLOC_LIMITED, CHUNK_ALLOC_FORCE, + CHUNK_ALLOC_FORCE_FOR_EXTENT, }; struct btrfs_caching_control { diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index be476f094300..19bf36d8ffea 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -537,6 +537,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, cb->orig_bio = NULL; cb->nr_pages = nr_pages; + if (blkcg_css) + kthread_associate_blkcg(blkcg_css); + while (cur_disk_bytenr < disk_start + compressed_len) { u64 offset = cur_disk_bytenr - disk_start; unsigned int index = offset >> PAGE_SHIFT; @@ -555,6 +558,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, bio = NULL; goto finish_cb; } + if (blkcg_css) + bio->bi_opf |= REQ_CGROUP_PUNT; } /* * We should never reach next_stripe_start start as we will @@ -612,6 +617,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, return 0; finish_cb: + if (blkcg_css) + kthread_associate_blkcg(NULL); + if (bio) { bio->bi_status = ret; bio_endio(bio); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b7631b88426e..077c95e9baa5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1060,6 +1060,7 @@ struct btrfs_fs_info { */ spinlock_t relocation_bg_lock; u64 data_reloc_bg; + struct mutex zoned_data_reloc_io_lock; u64 nr_global_roots; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 71fd99b48283..f26202621989 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -734,7 +734,12 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); - /* Commit dev_replace state and reserve 1 item for it. */ + /* + * Commit dev_replace state and reserve 1 item for it. + * This is crucial to ensure we won't miss copying extents for new block + * groups that are allocated after we started the device replace, and + * must be done after setting up the device replace state. + */ trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b30309f187cf..ed8e288cc369 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1850,9 +1850,10 @@ again: ret = btrfs_insert_fs_root(fs_info, root); if (ret) { - btrfs_put_root(root); - if (ret == -EEXIST) + if (ret == -EEXIST) { + btrfs_put_root(root); goto again; + } goto fail; } return root; @@ -3156,6 +3157,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info) mutex_init(&fs_info->reloc_mutex); mutex_init(&fs_info->delalloc_root_mutex); mutex_init(&fs_info->zoned_meta_io_lock); + mutex_init(&fs_info->zoned_data_reloc_io_lock); seqlock_init(&fs_info->profiles_lock); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f477035a2ac2..6aa92f84f465 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4082,7 +4082,7 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info, } ret = btrfs_chunk_alloc(trans, ffe_ctl->flags, - CHUNK_ALLOC_FORCE); + CHUNK_ALLOC_FORCE_FOR_EXTENT); /* Do not bail out on ENOSPC since we can do more. */ if (ret == -ENOSPC) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 724e8fe06aa0..33c19f51d79b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2658,6 +2658,7 @@ int btrfs_repair_one_sector(struct inode *inode, repair_bio = btrfs_bio_alloc(1); repair_bbio = btrfs_bio(repair_bio); + repair_bbio->file_offset = start; repair_bio->bi_opf = REQ_OP_READ; repair_bio->bi_end_io = failed_bio->bi_end_io; repair_bio->bi_iter.bi_sector = failrec->logical >> 9; @@ -3333,24 +3334,37 @@ static int alloc_new_bio(struct btrfs_inode *inode, ret = calc_bio_boundaries(bio_ctrl, inode, file_offset); if (ret < 0) goto error; - if (wbc) { - struct block_device *bdev; - bdev = fs_info->fs_devices->latest_dev->bdev; - bio_set_dev(bio, bdev); - wbc_init_bio(wbc, bio); - } - if (bio_op(bio) == REQ_OP_ZONE_APPEND) { - struct btrfs_device *device; + if (wbc) { + /* + * For Zone append we need the correct block_device that we are + * going to write to set in the bio to be able to respect the + * hardware limitation. Look it up here: + */ + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + struct btrfs_device *dev; + + dev = btrfs_zoned_get_device(fs_info, disk_bytenr, + fs_info->sectorsize); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto error; + } - device = btrfs_zoned_get_device(fs_info, disk_bytenr, - fs_info->sectorsize); - if (IS_ERR(device)) { - ret = PTR_ERR(device); - goto error; + bio_set_dev(bio, dev->bdev); + } else { + /* + * Otherwise pick the last added device to support + * cgroup writeback. For multi-device file systems this + * means blk-cgroup policies have to always be set on the + * last added/replaced device. This is a bit odd but has + * been like that for a long time. + */ + bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev); } - - btrfs_bio(bio)->device = device; + wbc_init_bio(wbc, bio); + } else { + ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND); } return 0; error: diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 0399cf8e3c32..151e9da5da2d 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -118,7 +118,7 @@ struct btrfs_bio_ctrl { */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ - unsigned int bytes_changed; + u64 bytes_changed; /* Changed ranges */ struct ulist range_changed; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9f455c96c974..380054c94e4b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2957,8 +2957,9 @@ out: return ret; } -static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) +static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; @@ -2990,6 +2991,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out_only_mutex; } + ret = file_modified(file); + if (ret) + goto out_only_mutex; + lockstart = round_up(offset, btrfs_inode_sectorsize(BTRFS_I(inode))); lockend = round_down(offset + len, btrfs_inode_sectorsize(BTRFS_I(inode))) - 1; @@ -3430,7 +3435,7 @@ static long btrfs_fallocate(struct file *file, int mode, return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) - return btrfs_punch_hole(inode, offset, len); + return btrfs_punch_hole(file, offset, len); /* * Only trigger disk allocation, don't trigger qgroup reserve @@ -3452,6 +3457,10 @@ static long btrfs_fallocate(struct file *file, int mode, goto out; } + ret = file_modified(file); + if (ret) + goto out; + /* * TODO: Move these two operations after we have checked * accurate reserved space, or fallocate can still fail but diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6bfc4343c98d..1c8a43ecfb9f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1128,7 +1128,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode, int ret = 0; if (btrfs_is_free_space_inode(inode)) { - WARN_ON_ONCE(1); ret = -EINVAL; goto out_unlock; } @@ -2017,8 +2016,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page * to use run_delalloc_nocow() here, like for regular * preallocated inodes. */ - ASSERT(!zoned || - (zoned && btrfs_is_data_reloc_root(inode->root))); + ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root)); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, nr_written); } else if (!inode_can_compress(inode) || @@ -4488,6 +4486,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); return -EPERM; } + if (atomic_read(&dest->nr_swapfiles)) { + spin_unlock(&dest->root_item_lock); + btrfs_warn(fs_info, + "attempt to delete subvolume %llu with active swapfile", + root->root_key.objectid); + return -EPERM; + } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); @@ -7438,6 +7443,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, u64 block_start, orig_start, orig_block_len, ram_bytes; bool can_nocow = false; bool space_reserved = false; + u64 prev_len; int ret = 0; /* @@ -7465,6 +7471,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, can_nocow = true; } + prev_len = len; if (can_nocow) { struct extent_map *em2; @@ -7494,8 +7501,6 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, goto out; } } else { - const u64 prev_len = len; - /* Our caller expects us to free the input extent map. */ free_extent_map(em); *map = NULL; @@ -7526,7 +7531,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, * We have created our ordered extent, so we can now release our reservation * for an outstanding extent. */ - btrfs_delalloc_release_extents(BTRFS_I(inode), len); + btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len); /* * Need to update the i_size under the extent lock so buffered @@ -7805,8 +7810,6 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM); struct bio_vec bvec; struct bvec_iter iter; - const u64 orig_file_offset = dip->file_offset; - u64 start = orig_file_offset; u32 bio_offset = 0; blk_status_t err = BLK_STS_OK; @@ -7816,6 +7819,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len); pgoff = bvec.bv_offset; for (i = 0; i < nr_sectors; i++) { + u64 start = bbio->file_offset + bio_offset; + ASSERT(pgoff < PAGE_SIZE); if (uptodate && (!csum || !check_data_csum(inode, bbio, @@ -7828,17 +7833,13 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip, } else { int ret; - ASSERT((start - orig_file_offset) < UINT_MAX); - ret = btrfs_repair_one_sector(inode, - &bbio->bio, - start - orig_file_offset, - bvec.bv_page, pgoff, + ret = btrfs_repair_one_sector(inode, &bbio->bio, + bio_offset, bvec.bv_page, pgoff, start, bbio->mirror_num, submit_dio_repair_bio); if (ret) err = errno_to_blk_status(ret); } - start += sectorsize; ASSERT(bio_offset + sectorsize > bio_offset); bio_offset += sectorsize; pgoff += sectorsize; @@ -7865,6 +7866,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode, static void btrfs_end_dio_bio(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; + struct btrfs_bio *bbio = btrfs_bio(bio); blk_status_t err = bio->bi_status; if (err) @@ -7875,12 +7877,12 @@ static void btrfs_end_dio_bio(struct bio *bio) bio->bi_iter.bi_size, err); if (bio_op(bio) == REQ_OP_READ) - err = btrfs_check_read_dio_bio(dip, btrfs_bio(bio), !err); + err = btrfs_check_read_dio_bio(dip, bbio, !err); if (err) dip->dio_bio->bi_status = err; - btrfs_record_physical_zoned(dip->inode, dip->file_offset, bio); + btrfs_record_physical_zoned(dip->inode, bbio->file_offset, bio); bio_put(bio); btrfs_dio_private_put(dip); @@ -8041,6 +8043,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter, bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len); bio->bi_private = dip; bio->bi_end_io = btrfs_end_dio_bio; + btrfs_bio(bio)->file_offset = file_offset; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { status = extract_ordered_extent(BTRFS_I(inode), bio, @@ -11107,8 +11110,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, * set. We use this counter to prevent snapshots. We must increment it * before walking the extents because we don't want a concurrent * snapshot to run after we've already checked the extents. + * + * It is possible that subvolume is marked for deletion but still not + * removed yet. To prevent this race, we check the root status before + * activating the swapfile. */ + spin_lock(&root->root_item_lock); + if (btrfs_root_dead(root)) { + spin_unlock(&root->root_item_lock); + + btrfs_exclop_finish(fs_info); + btrfs_warn(fs_info, + "cannot activate swapfile because subvolume %llu is being deleted", + root->root_key.objectid); + return -EPERM; + } atomic_inc(&root->nr_swapfiles); + spin_unlock(&root->root_item_lock); isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 238cee5b5254..be6c24577dbe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1239,7 +1239,7 @@ static u32 get_extent_max_capacity(const struct extent_map *em) } static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, - bool locked) + u32 extent_thresh, u64 newer_than, bool locked) { struct extent_map *next; bool ret = false; @@ -1249,11 +1249,12 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, return false; /* - * We want to check if the next extent can be merged with the current - * one, which can be an extent created in a past generation, so we pass - * a minimum generation of 0 to defrag_lookup_extent(). + * Here we need to pass @newer_then when checking the next extent, or + * we will hit a case we mark current extent for defrag, but the next + * one will not be a target. + * This will just cause extra IO without really reducing the fragments. */ - next = defrag_lookup_extent(inode, em->start + em->len, 0, locked); + next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked); /* No more em or hole */ if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) goto out; @@ -1265,6 +1266,13 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, */ if (next->len >= get_extent_max_capacity(em)) goto out; + /* Skip older extent */ + if (next->generation < newer_than) + goto out; + /* Also check extent size */ + if (next->len >= extent_thresh) + goto out; + ret = true; out: free_extent_map(next); @@ -1470,7 +1478,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto next; next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, - locked); + extent_thresh, newer_than, locked); if (!next_mergeable) { struct defrag_target_range *last; @@ -5448,8 +5456,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_fs_info(fs_info, argp); case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(fs_info, argp); - case BTRFS_IOC_BALANCE: - return btrfs_ioctl_balance(file, NULL); case BTRFS_IOC_TREE_SEARCH: return btrfs_ioctl_tree_search(inode, argp); case BTRFS_IOC_TREE_SEARCH_V2: diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 11089568b287..8cd713d37ad2 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3699,6 +3699,31 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (!cache) goto skip; + ASSERT(cache->start <= chunk_offset); + /* + * We are using the commit root to search for device extents, so + * that means we could have found a device extent item from a + * block group that was deleted in the current transaction. The + * logical start offset of the deleted block group, stored at + * @chunk_offset, might be part of the logical address range of + * a new block group (which uses different physical extents). + * In this case btrfs_lookup_block_group() has returned the new + * block group, and its start address is less than @chunk_offset. + * + * We skip such new block groups, because it's pointless to + * process them, as we won't find their extents because we search + * for them using the commit root of the extent tree. For a device + * replace it's also fine to skip it, we won't miss copying them + * to the target device because we have the write duplication + * setup through the regular write path (by btrfs_map_block()), + * and we have committed a transaction when we started the device + * replace, right after setting up the device replace state. + */ + if (cache->start < chunk_offset) { + btrfs_put_block_group(cache); + goto skip; + } + if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { spin_lock(&cache->lock); if (!cache->to_copy) { @@ -3822,7 +3847,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, dev_replace->item_needs_writeback = 1; up_write(&dev_replace->rwsem); - ASSERT(cache->start == chunk_offset); ret = scrub_chunk(sctx, cache, scrub_dev, found_key.offset, dev_extent_len); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 571dae8ad65e..09e4f1a04e6f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3188,6 +3188,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, ret = btrfs_alloc_log_tree_node(trans, log_root_tree); if (ret) { mutex_unlock(&fs_info->tree_root->log_mutex); + blk_finish_plug(&plug); goto out; } } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1be7cb2f955f..a8cc736731fd 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1896,23 +1896,18 @@ static void update_dev_time(const char *device_path) path_put(&path); } -static int btrfs_rm_dev_item(struct btrfs_device *device) +static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans, + struct btrfs_device *device) { struct btrfs_root *root = device->fs_info->chunk_root; int ret; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_trans_handle *trans; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) { - btrfs_free_path(path); - return PTR_ERR(trans); - } key.objectid = BTRFS_DEV_ITEMS_OBJECTID; key.type = BTRFS_DEV_ITEM_KEY; key.offset = device->devid; @@ -1923,21 +1918,12 @@ static int btrfs_rm_dev_item(struct btrfs_device *device) if (ret) { if (ret > 0) ret = -ENOENT; - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); goto out; } ret = btrfs_del_item(trans, root, path); - if (ret) { - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); - } - out: btrfs_free_path(path); - if (!ret) - ret = btrfs_commit_transaction(trans); return ret; } @@ -2078,6 +2064,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, struct block_device **bdev, fmode_t *mode) { + struct btrfs_trans_handle *trans; struct btrfs_device *device; struct btrfs_fs_devices *cur_devices; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; @@ -2098,7 +2085,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1); if (ret) - goto out; + return ret; device = btrfs_find_device(fs_info->fs_devices, args); if (!device) { @@ -2106,27 +2093,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND; else ret = -ENOENT; - goto out; + return ret; } if (btrfs_pinned_by_swapfile(fs_info, device)) { btrfs_warn_in_rcu(fs_info, "cannot remove device %s (devid %llu) due to active swapfile", rcu_str_deref(device->name), device->devid); - ret = -ETXTBSY; - goto out; + return -ETXTBSY; } - if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { - ret = BTRFS_ERROR_DEV_TGT_REPLACE; - goto out; - } + if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) + return BTRFS_ERROR_DEV_TGT_REPLACE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && - fs_info->fs_devices->rw_devices == 1) { - ret = BTRFS_ERROR_DEV_ONLY_WRITABLE; - goto out; - } + fs_info->fs_devices->rw_devices == 1) + return BTRFS_ERROR_DEV_ONLY_WRITABLE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { mutex_lock(&fs_info->chunk_mutex); @@ -2139,14 +2121,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, if (ret) goto error_undo; - /* - * TODO: the superblock still includes this device in its num_devices - * counter although write_all_supers() is not locked out. This - * could give a filesystem state which requires a degraded mount. - */ - ret = btrfs_rm_dev_item(device); - if (ret) + trans = btrfs_start_transaction(fs_info->chunk_root, 0); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); goto error_undo; + } + + ret = btrfs_rm_dev_item(trans, device); + if (ret) { + /* Any error in dev item removal is critical */ + btrfs_crit(fs_info, + "failed to remove device item for devid %llu: %d", + device->devid, ret); + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); btrfs_scrub_cancel_dev(device); @@ -2229,7 +2219,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, free_fs_devices(cur_devices); } -out: + ret = btrfs_commit_transaction(trans); + return ret; error_undo: @@ -2240,7 +2231,7 @@ error_undo: device->fs_devices->rw_devices++; mutex_unlock(&fs_info->chunk_mutex); } - goto out; + return ret; } void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev) @@ -4439,10 +4430,12 @@ static int balance_kthread(void *data) struct btrfs_fs_info *fs_info = data; int ret = 0; + sb_start_write(fs_info->sb); mutex_lock(&fs_info->balance_mutex); if (fs_info->balance_ctl) ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL); mutex_unlock(&fs_info->balance_mutex); + sb_end_write(fs_info->sb); return ret; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index bd297f23d19e..f3e28f11cfb6 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -328,6 +328,9 @@ struct btrfs_fs_devices { struct btrfs_bio { unsigned int mirror_num; + /* for direct I/O */ + u64 file_offset; + /* @device is for stripe IO submission. */ struct btrfs_device *device; u8 *csum; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b7b5fac1c779..1b1b310c3c51 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1801,7 +1801,6 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info, map = em->map_lookup; /* We only support single profile for now */ - ASSERT(map->num_stripes == 1); device = map->stripes[0].dev; free_extent_map(em); @@ -1976,18 +1975,16 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) { + struct btrfs_fs_info *fs_info = fs_devices->fs_info; struct btrfs_device *device; bool ret = false; - if (!btrfs_is_zoned(fs_devices->fs_info)) + if (!btrfs_is_zoned(fs_info)) return true; - /* Non-single profiles are not supported yet */ - ASSERT((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0); - /* Check if there is a device with active zones left */ - mutex_lock(&fs_devices->device_list_mutex); - list_for_each_entry(device, &fs_devices->devices, dev_list) { + mutex_lock(&fs_info->chunk_mutex); + list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { struct btrfs_zoned_device_info *zinfo = device->zone_info; if (!device->bdev) @@ -1999,7 +1996,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) break; } } - mutex_unlock(&fs_devices->device_list_mutex); + mutex_unlock(&fs_info->chunk_mutex); return ret; } diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index cbf016a7bb5d..6dee76248cb4 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -359,7 +359,7 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) - btrfs_inode_lock(&inode->vfs_inode, 0); + mutex_lock(&root->fs_info->zoned_data_reloc_io_lock); } static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode) @@ -367,7 +367,7 @@ static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode) struct btrfs_root *root = inode->root; if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info)) - btrfs_inode_unlock(&inode->vfs_inode, 0); + mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock); } #endif diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index f256c8aff7bb..ca9f3e4ec4b3 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -57,6 +57,16 @@ static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, trace_cachefiles_mark_inactive(object, inode); } +static void cachefiles_do_unmark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct inode *inode = d_backing_inode(dentry); + + inode_lock(inode); + __cachefiles_unmark_inode_in_use(object, dentry); + inode_unlock(inode); +} + /* * Unmark a backing inode and tell cachefilesd that there's something that can * be culled. @@ -68,9 +78,7 @@ void cachefiles_unmark_inode_in_use(struct cachefiles_object *object, struct inode *inode = file_inode(file); if (inode) { - inode_lock(inode); - __cachefiles_unmark_inode_in_use(object, file->f_path.dentry); - inode_unlock(inode); + cachefiles_do_unmark_inode_in_use(object, file->f_path.dentry); if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) { atomic_long_add(inode->i_blocks, &cache->b_released); @@ -484,7 +492,7 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) object, d_backing_inode(path.dentry), ret, cachefiles_trace_trunc_error); file = ERR_PTR(ret); - goto out_dput; + goto out_unuse; } } @@ -494,15 +502,20 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, d_backing_inode(path.dentry), PTR_ERR(file), cachefiles_trace_open_error); - goto out_dput; + goto out_unuse; } if (unlikely(!file->f_op->read_iter) || unlikely(!file->f_op->write_iter)) { fput(file); pr_notice("Cache does not support read_iter and write_iter\n"); file = ERR_PTR(-EINVAL); + goto out_unuse; } + goto out_dput; + +out_unuse: + cachefiles_do_unmark_inode_in_use(object, path.dentry); out_dput: dput(path.dentry); out: @@ -590,14 +603,16 @@ static bool cachefiles_open_file(struct cachefiles_object *object, check_failed: fscache_cookie_lookup_negative(object->cookie); cachefiles_unmark_inode_in_use(object, file); - if (ret == -ESTALE) { - fput(file); - dput(dentry); + fput(file); + dput(dentry); + if (ret == -ESTALE) return cachefiles_create_file(object); - } + return false; + error_fput: fput(file); error: + cachefiles_do_unmark_inode_in_use(object, dentry); dput(dentry); return false; } diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 35465109d9c4..00b087c14995 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -203,7 +203,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) if (!buf) return false; buf->reserved = cpu_to_be32(0); - memcpy(buf->data, p, len); + memcpy(buf->data, p, volume->vcookie->coherency_len); ret = cachefiles_inject_write_error(); if (ret == 0) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index f1ad6884d4da..5c14ef04e474 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2274,6 +2274,8 @@ retry: list_for_each_entry(req, &ci->i_unsafe_dirops, r_unsafe_dir_item) { s = req->r_session; + if (!s) + continue; if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); for (i = 0; i < max_sessions; i++) { @@ -2294,6 +2296,8 @@ retry: list_for_each_entry(req, &ci->i_unsafe_iops, r_unsafe_target_item) { s = req->r_session; + if (!s) + continue; if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); for (i = 0; i < max_sessions; i++) { @@ -3870,6 +3874,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, dout("handle_cap_export inode %p ci %p mds%d mseq %d target %d\n", inode, ci, mds, mseq, target); retry: + down_read(&mdsc->snap_rwsem); spin_lock(&ci->i_ceph_lock); cap = __get_cap_for_mds(ci, mds); if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id)) @@ -3933,6 +3938,7 @@ retry: } spin_unlock(&ci->i_ceph_lock); + up_read(&mdsc->snap_rwsem); mutex_unlock(&session->s_mutex); /* open target session */ @@ -3958,6 +3964,7 @@ retry: out_unlock: spin_unlock(&ci->i_ceph_lock); + up_read(&mdsc->snap_rwsem); mutex_unlock(&session->s_mutex); if (tsession) { mutex_unlock(&tsession->s_mutex); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index fa38c013126d..00c3de177dd6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4434,8 +4434,6 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc) bool check_session_state(struct ceph_mds_session *s) { - struct ceph_fs_client *fsc = s->s_mdsc->fsc; - switch (s->s_state) { case CEPH_MDS_SESSION_OPEN: if (s->s_ttl && time_after(jiffies, s->s_ttl)) { @@ -4444,10 +4442,6 @@ bool check_session_state(struct ceph_mds_session *s) } break; case CEPH_MDS_SESSION_CLOSING: - /* Should never reach this when not force unmounting */ - WARN_ON_ONCE(s->s_ttl && - READ_ONCE(fsc->mount_state) != CEPH_MOUNT_SHUTDOWN); - fallthrough; case CEPH_MDS_SESSION_NEW: case CEPH_MDS_SESSION_RESTARTING: case CEPH_MDS_SESSION_CLOSED: diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index a47fa44b6d52..2b1a1c029c75 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -266,22 +266,24 @@ static void cifs_kill_sb(struct super_block *sb) * before we kill the sb. */ if (cifs_sb->root) { + for (node = rb_first(root); node; node = rb_next(node)) { + tlink = rb_entry(node, struct tcon_link, tl_rbnode); + tcon = tlink_tcon(tlink); + if (IS_ERR(tcon)) + continue; + cfid = &tcon->crfid; + mutex_lock(&cfid->fid_mutex); + if (cfid->dentry) { + dput(cfid->dentry); + cfid->dentry = NULL; + } + mutex_unlock(&cfid->fid_mutex); + } + + /* finally release root dentry */ dput(cifs_sb->root); cifs_sb->root = NULL; } - node = rb_first(root); - while (node != NULL) { - tlink = rb_entry(node, struct tcon_link, tl_rbnode); - tcon = tlink_tcon(tlink); - cfid = &tcon->crfid; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } - mutex_unlock(&cfid->fid_mutex); - node = rb_next(node); - } kill_anon_super(sb); cifs_umount(cifs_sb); @@ -944,7 +946,7 @@ cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) ssize_t rc; struct inode *inode = file_inode(iocb->ki_filp); - if (iocb->ki_filp->f_flags & O_DIRECT) + if (iocb->ki_flags & IOCB_DIRECT) return cifs_user_readv(iocb, iter); rc = cifs_revalidate_mapping(inode); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 15a5c5db038b..c0542bdcd06b 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -153,5 +153,5 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ #define SMB3_PRODUCT_BUILD 35 -#define CIFS_VERSION "2.35" +#define CIFS_VERSION "2.36" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ee3b7c15e884..42e14f408856 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -453,9 +453,7 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_ return rc; } -static int -reconnect_dfs_server(struct TCP_Server_Info *server, - bool mark_smb_session) +static int reconnect_dfs_server(struct TCP_Server_Info *server) { int rc = 0; const char *refpath = server->current_fullpath + 1; @@ -479,7 +477,12 @@ reconnect_dfs_server(struct TCP_Server_Info *server, if (!cifs_tcp_ses_needs_reconnect(server, num_targets)) return 0; - cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session); + /* + * Unconditionally mark all sessions & tcons for reconnect as we might be connecting to a + * different server or share during failover. It could be improved by adding some logic to + * only do that in case it connects to a different server or share, though. + */ + cifs_mark_tcp_ses_conns_for_reconnect(server, true); cifs_abort_connection(server); @@ -531,13 +534,20 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { /* If tcp session is not an dfs connection, then reconnect to last target server */ spin_lock(&cifs_tcp_ses_lock); - if (!server->is_dfs_conn || !server->origin_fullpath || !server->leaf_fullpath) { + if (!server->is_dfs_conn) { spin_unlock(&cifs_tcp_ses_lock); return __cifs_reconnect(server, mark_smb_session); } spin_unlock(&cifs_tcp_ses_lock); - return reconnect_dfs_server(server, mark_smb_session); + mutex_lock(&server->refpath_lock); + if (!server->origin_fullpath || !server->leaf_fullpath) { + mutex_unlock(&server->refpath_lock); + return __cifs_reconnect(server, mark_smb_session); + } + mutex_unlock(&server->refpath_lock); + + return reconnect_dfs_server(server); } #else int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) @@ -1046,7 +1056,7 @@ smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_hdr_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, le16_to_cpu(shdr->CreditRequest), in_flight); cifs_server_dbg(FYI, "%s: added %u credits total=%d\n", @@ -3672,9 +3682,11 @@ static void setup_server_referral_paths(struct mount_ctx *mnt_ctx) { struct TCP_Server_Info *server = mnt_ctx->server; + mutex_lock(&server->refpath_lock); server->origin_fullpath = mnt_ctx->origin_fullpath; server->leaf_fullpath = mnt_ctx->leaf_fullpath; server->current_fullpath = mnt_ctx->leaf_fullpath; + mutex_unlock(&server->refpath_lock); mnt_ctx->origin_fullpath = mnt_ctx->leaf_fullpath = NULL; } @@ -4465,7 +4477,7 @@ static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tco */ if (rc && server->current_fullpath != server->origin_fullpath) { server->current_fullpath = server->origin_fullpath; - cifs_reconnect(tcon->ses->server, true); + cifs_signal_cifsd_for_reconnect(server, true); } dfs_cache_free_tgts(tl); diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 30e040da4f09..956f8e5cf3e7 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1422,12 +1422,14 @@ static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool struct TCP_Server_Info *server = tcon->ses->server; mutex_lock(&server->refpath_lock); - if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) - __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + if (server->origin_fullpath) { + if (server->leaf_fullpath && strcasecmp(server->leaf_fullpath, + server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); + } mutex_unlock(&server->refpath_lock); - __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); - return 0; } @@ -1530,11 +1532,14 @@ static void refresh_mounts(struct cifs_ses **sessions) list_del_init(&tcon->ulist); mutex_lock(&server->refpath_lock); - if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) - __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + if (server->origin_fullpath) { + if (server->leaf_fullpath && strcasecmp(server->leaf_fullpath, + server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); + } mutex_unlock(&server->refpath_lock); - __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); cifs_put_tcon(tcon); } } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 852e54ee82c2..bbdf3281559c 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -85,6 +85,9 @@ parse_mf_symlink(const u8 *buf, unsigned int buf_len, unsigned int *_link_len, if (rc != 1) return -EINVAL; + if (link_len > CIFS_MF_SYMLINK_LINK_MAXLEN) + return -EINVAL; + rc = symlink_hash(link_len, link_str, md5_hash); if (rc) { cifs_dbg(FYI, "%s: MD5 hash failure: %d\n", __func__, rc); diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index ebe236b9d9f5..235aa1b395eb 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -896,7 +896,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr) if (class == ERRSRV && code == ERRbaduid) { cifs_dbg(FYI, "Server returned 0x%x, reconnecting session...\n", code); - cifs_reconnect(mid->server, false); + cifs_signal_cifsd_for_reconnect(mid->server, false); } } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index c653beb735b8..3fe47a88f47d 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -150,16 +150,18 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) struct smb2_transform_hdr *thdr = (struct smb2_transform_hdr *)buf; struct cifs_ses *ses = NULL; + struct cifs_ses *iter; /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &srvr->smb_ses_list, smb_ses_list) { - if (ses->Suid == le64_to_cpu(thdr->SessionId)) + list_for_each_entry(iter, &srvr->smb_ses_list, smb_ses_list) { + if (iter->Suid == le64_to_cpu(thdr->SessionId)) { + ses = iter; break; + } } spin_unlock(&cifs_tcp_ses_lock); - if (list_entry_is_head(ses, &srvr->smb_ses_list, - smb_ses_list)) { + if (!ses) { cifs_dbg(VFS, "no decryption - session id not found\n"); return 1; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index db23f5b404ba..d6aaeff4a30a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -86,6 +86,9 @@ smb2_add_credits(struct TCP_Server_Info *server, if (*val > 65000) { *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ pr_warn_once("server overflowed SMB3 credits\n"); + trace_smb3_overflow_credits(server->CurrentMid, + server->conn_id, server->hostname, *val, + add, server->in_flight); } server->in_flight--; if (server->in_flight == 0 && @@ -251,7 +254,7 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_wait_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -(credits->value), in_flight); cifs_dbg(FYI, "%s: removed %u credits total=%d\n", __func__, credits->value, scredits); @@ -300,7 +303,7 @@ smb2_adjust_credits(struct TCP_Server_Info *server, spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_adj_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, credits->value - new_val, in_flight); cifs_dbg(FYI, "%s: adjust added %u credits total=%d\n", @@ -1855,9 +1858,17 @@ smb2_copychunk_range(const unsigned int xid, int chunks_copied = 0; bool chunk_sizes_updated = false; ssize_t bytes_written, total_bytes_written = 0; + struct inode *inode; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); + /* + * We need to flush all unwritten data before we can send the + * copychunk ioctl to the server. + */ + inode = d_inode(trgtfile->dentry); + filemap_write_and_wait(inode->i_mapping); + if (pcchunk == NULL) return -ENOMEM; @@ -2492,7 +2503,7 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server) spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_pend_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, le16_to_cpu(shdr->CreditRequest), in_flight); cifs_dbg(FYI, "%s: status pending add %u credits total=%d\n", diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index 6cecf302dcfd..bc279616c513 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -1006,6 +1006,13 @@ DEFINE_SMB3_CREDIT_EVENT(credit_timeout); DEFINE_SMB3_CREDIT_EVENT(insufficient_credits); DEFINE_SMB3_CREDIT_EVENT(too_many_credits); DEFINE_SMB3_CREDIT_EVENT(add_credits); +DEFINE_SMB3_CREDIT_EVENT(adj_credits); +DEFINE_SMB3_CREDIT_EVENT(hdr_credits); +DEFINE_SMB3_CREDIT_EVENT(nblk_credits); +DEFINE_SMB3_CREDIT_EVENT(pend_credits); +DEFINE_SMB3_CREDIT_EVENT(wait_credits); +DEFINE_SMB3_CREDIT_EVENT(waitff_credits); +DEFINE_SMB3_CREDIT_EVENT(overflow_credits); DEFINE_SMB3_CREDIT_EVENT(set_credits); #endif /* _CIFS_TRACE_H */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index eeb1a699bd6f..c667e6ddfe2f 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -464,13 +464,12 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, return -EIO; } - tr_hdr = kmalloc(sizeof(*tr_hdr), GFP_NOFS); + tr_hdr = kzalloc(sizeof(*tr_hdr), GFP_NOFS); if (!tr_hdr) return -ENOMEM; memset(&cur_rqst[0], 0, sizeof(cur_rqst)); memset(&iov, 0, sizeof(iov)); - memset(tr_hdr, 0, sizeof(*tr_hdr)); iov.iov_base = tr_hdr; iov.iov_len = sizeof(*tr_hdr); @@ -542,7 +541,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_nblk_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -1, in_flight); cifs_dbg(FYI, "%s: remove %u credits total=%d\n", __func__, 1, scredits); @@ -648,7 +647,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_waitff_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -(num_credits), in_flight); cifs_dbg(FYI, "%s: remove %u credits total=%d\n", diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 0ed880f42525..e6dea6dfca16 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1066,12 +1066,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, /* wake up the caller thread for sync decompression */ if (sync) { - unsigned long flags; - - spin_lock_irqsave(&io->u.wait.lock, flags); if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); + complete(&io->u.done); + return; } @@ -1217,7 +1214,7 @@ jobqueue_init(struct super_block *sb, } else { fg_out: q = fgq; - init_waitqueue_head(&fgq->u.wait); + init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); } q->sb = sb; @@ -1419,8 +1416,7 @@ static void z_erofs_runqueue(struct super_block *sb, return; /* wait until all bios are completed */ - io_wait_event(io[JQ_SUBMIT].u.wait, - !atomic_read(&io[JQ_SUBMIT].pending_bios)); + wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index e043216b545f..800b11c53f57 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -97,7 +97,7 @@ struct z_erofs_decompressqueue { z_erofs_next_pcluster_t head; union { - wait_queue_head_t wait; + struct completion done; struct work_struct work; } u; }; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3f87cca49f0c..a743b1e3b89e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2273,6 +2273,10 @@ static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi) * Structure of a directory entry */ #define EXT4_NAME_LEN 255 +/* + * Base length of the ext4 directory entry excluding the name length + */ +#define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN) struct ext4_dir_entry { __le32 inode; /* Inode number */ @@ -3032,7 +3036,7 @@ extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); -extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); +extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); @@ -3064,6 +3068,7 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); +int ext4_update_overhead(struct super_block *sb); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0d98cf402282..e473fde6b64b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4500,9 +4500,9 @@ retry: return ret > 0 ? ret2 : ret; } -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) @@ -4574,6 +4574,10 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4690,7 +4694,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) { - ret = ext4_punch_hole(inode, offset, len); + ret = ext4_punch_hole(file, offset, len); goto exit; } @@ -4699,12 +4703,12 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto exit; if (mode & FALLOC_FL_COLLAPSE_RANGE) { - ret = ext4_collapse_range(inode, offset, len); + ret = ext4_collapse_range(file, offset, len); goto exit; } if (mode & FALLOC_FL_INSERT_RANGE) { - ret = ext4_insert_range(inode, offset, len); + ret = ext4_insert_range(file, offset, len); goto exit; } @@ -4740,6 +4744,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out; + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); if (ret) goto out; @@ -5241,8 +5249,9 @@ out: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; ext4_lblk_t punch_start, punch_stop; @@ -5294,6 +5303,10 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -5387,8 +5400,9 @@ out_mutex: * by len bytes. * Returns 0 on success, error otherwise. */ -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; @@ -5445,6 +5459,10 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 13740f2d0e61..646ece9b3455 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3953,12 +3953,14 @@ int ext4_break_layouts(struct inode *inode) * Returns: 0 on success or negative on failure */ -int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) +int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; ext4_lblk_t first_block, stop_block; struct address_space *mapping = inode->i_mapping; - loff_t first_block_offset, last_block_offset; + loff_t first_block_offset, last_block_offset, max_length; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; unsigned int credits; int ret = 0, ret2 = 0; @@ -4001,6 +4003,14 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) offset; } + /* + * For punch hole the length + offset needs to be within one block + * before last range. Adjust the length if it goes beyond that limit. + */ + max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize; + if (offset + length > max_length) + length = max_length - offset; + if (offset & (sb->s_blocksize - 1) || (offset + length) & (sb->s_blocksize - 1)) { /* @@ -4016,6 +4026,10 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 992229ca2d83..ba44fa1be70a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1652,3 +1652,19 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif + +static void set_overhead(struct ext4_super_block *es, const void *arg) +{ + es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); +} + +int ext4_update_overhead(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (sb_rdonly(sb) || sbi->s_overhead == 0 || + sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters)) + return 0; + + return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); +} diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index e37da8d5cd0c..767b4bfe39c3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1466,10 +1466,10 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; - while ((char *) de < dlimit) { + while ((char *) de < dlimit - EXT4_BASE_DIR_LEN) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ - if ((char *) de + de->name_len <= dlimit && + if (de->name + de->name_len <= dlimit && ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 495ce59fb4ad..14695e2b5042 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -134,8 +134,10 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (bio->bi_status) + if (bio->bi_status) { + set_buffer_write_io_error(bh); buffer_io_error(bh); + } } while ((bh = bh->b_this_page) != head); spin_unlock_irqrestore(&head->b_uptodate_lock, flags); if (!under_io) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 81749eaddf4c..1466fbdbc8e3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1199,20 +1199,25 @@ static void ext4_put_super(struct super_block *sb) int aborted = 0; int i, err; - ext4_unregister_li_request(sb); - ext4_quota_off_umount(sb); - - flush_work(&sbi->s_error_work); - destroy_workqueue(sbi->rsv_conversion_wq); - ext4_release_orphan_info(sb); - /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL + * Unregister sysfs before flush sbi->s_error_work. + * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If + * read metadata verify failed then will queue error work. + * flush_stashed_error_work will call start_this_handle may trigger + * BUG_ON. */ ext4_unregister_sysfs(sb); + ext4_unregister_li_request(sb); + ext4_quota_off_umount(sb); + + flush_work(&sbi->s_error_work); + destroy_workqueue(sbi->rsv_conversion_wq); + ext4_release_orphan_info(sb); + if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); @@ -4172,9 +4177,11 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; + int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) - return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + return (has_super + ext4_bg_num_gdb(sb, grp) + + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + @@ -5282,9 +5289,18 @@ no_journal: * Get the # of file system overhead blocks from the * superblock if present. */ - if (es->s_overhead_clusters) - sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); - else { + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + /* ignore the precalculated value if it is ridiculous */ + if (sbi->s_overhead > ext4_blocks_count(es)) + sbi->s_overhead = 0; + /* + * If the bigalloc feature is not enabled recalculating the + * overhead doesn't take long, so we might as well just redo + * it to make sure we are using the correct value. + */ + if (!ext4_has_feature_bigalloc(sb)) + sbi->s_overhead = 0; + if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; @@ -5602,6 +5618,8 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " "Quota mode: %s.", descr, ext4_quota_mode(sb)); + /* Update the s_overhead_clusters if necessary */ + ext4_update_overhead(sb); return 0; free_sbi: diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f5366feea82d..909085a78f9c 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -98,9 +98,9 @@ repeat: } if (unlikely(!PageUptodate(page))) { - if (page->index == sbi->metapage_eio_ofs && - sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO) { - set_ckpt_flags(sbi, CP_ERROR_FLAG); + if (page->index == sbi->metapage_eio_ofs) { + if (sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO) + set_ckpt_flags(sbi, CP_ERROR_FLAG); } else { sbi->metapage_eio_ofs = page->index; sbi->metapage_eio_cnt = 0; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8e0c2e773c8d..9a1a526f2092 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -388,11 +388,23 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) return 0; } -static void __attach_io_flag(struct f2fs_io_info *fio, unsigned int io_flag) +static unsigned int f2fs_io_flags(struct f2fs_io_info *fio) { unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1; - unsigned int fua_flag = io_flag & temp_mask; - unsigned int meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask; + unsigned int fua_flag, meta_flag, io_flag; + unsigned int op_flags = 0; + + if (fio->op != REQ_OP_WRITE) + return 0; + if (fio->type == DATA) + io_flag = fio->sbi->data_io_flag; + else if (fio->type == NODE) + io_flag = fio->sbi->node_io_flag; + else + return 0; + + fua_flag = io_flag & temp_mask; + meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask; /* * data/node io flag bits per temp: @@ -401,9 +413,10 @@ static void __attach_io_flag(struct f2fs_io_info *fio, unsigned int io_flag) * Cold | Warm | Hot | Cold | Warm | Hot | */ if ((1 << fio->temp) & meta_flag) - fio->op_flags |= REQ_META; + op_flags |= REQ_META; if ((1 << fio->temp) & fua_flag) - fio->op_flags |= REQ_FUA; + op_flags |= REQ_FUA; + return op_flags; } static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) @@ -413,14 +426,10 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages) sector_t sector; struct bio *bio; - if (fio->type == DATA) - __attach_io_flag(fio, sbi->data_io_flag); - else if (fio->type == NODE) - __attach_io_flag(fio, sbi->node_io_flag); - bdev = f2fs_target_device(sbi, fio->new_blkaddr, §or); - bio = bio_alloc_bioset(bdev, npages, fio->op | fio->op_flags, GFP_NOIO, - &f2fs_bioset); + bio = bio_alloc_bioset(bdev, npages, + fio->op | fio->op_flags | f2fs_io_flags(fio), + GFP_NOIO, &f2fs_bioset); bio->bi_iter.bi_sector = sector; if (is_read_io(fio->op)) { bio->bi_end_io = f2fs_read_end_io; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cd1e65bcf0b0..8c570de21ed5 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -154,7 +154,6 @@ struct f2fs_mount_info { int s_jquota_fmt; /* Format of quota to use */ #endif /* For which write hints are passed down to block layer */ - int whint_mode; int alloc_mode; /* segment allocation policy */ int fsync_mode; /* fsync policy */ int fs_mode; /* fs mode: LFS or ADAPTIVE */ @@ -1334,12 +1333,6 @@ enum { }; enum { - WHINT_MODE_OFF, /* not pass down write hints */ - WHINT_MODE_USER, /* try to pass down hints given by users */ - WHINT_MODE_FS, /* pass down hints with F2FS policy */ -}; - -enum { ALLOC_MODE_DEFAULT, /* stay default */ ALLOC_MODE_REUSE, /* reuse segments as much as possible */ }; @@ -3657,8 +3650,6 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi); int __init f2fs_create_segment_manager_caches(void); void f2fs_destroy_segment_manager_caches(void); int f2fs_rw_hint_to_seg_type(enum rw_hint hint); -enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, - enum page_type type, enum temp_type temp); unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, unsigned int segno); unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 71f232dcf3c2..83639238a1fe 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -550,7 +550,8 @@ make_now: } f2fs_set_inode_flags(inode); - if (file_should_truncate(inode)) { + if (file_should_truncate(inode) && + !is_sbi_flag_set(sbi, SBI_POR_DOING)) { ret = f2fs_truncate(inode); if (ret) goto bad_inode; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 22dfeb991529..bd9731cdec56 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3243,101 +3243,6 @@ int f2fs_rw_hint_to_seg_type(enum rw_hint hint) } } -/* This returns write hints for each segment type. This hints will be - * passed down to block layer. There are mapping tables which depend on - * the mount option 'whint_mode'. - * - * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. - * - * 2) whint_mode=user-based. F2FS tries to pass down hints given by users. - * - * User F2FS Block - * ---- ---- ----- - * META WRITE_LIFE_NOT_SET - * HOT_NODE " - * WARM_NODE " - * COLD_NODE " - * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME - * extension list " " - * - * -- buffered io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " " - * WRITE_LIFE_MEDIUM " " - * WRITE_LIFE_LONG " " - * - * -- direct io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " WRITE_LIFE_NONE - * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM - * WRITE_LIFE_LONG " WRITE_LIFE_LONG - * - * 3) whint_mode=fs-based. F2FS passes down hints with its policy. - * - * User F2FS Block - * ---- ---- ----- - * META WRITE_LIFE_MEDIUM; - * HOT_NODE WRITE_LIFE_NOT_SET - * WARM_NODE " - * COLD_NODE WRITE_LIFE_NONE - * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME - * extension list " " - * - * -- buffered io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG - * WRITE_LIFE_NONE " " - * WRITE_LIFE_MEDIUM " " - * WRITE_LIFE_LONG " " - * - * -- direct io - * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME - * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT - * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET - * WRITE_LIFE_NONE " WRITE_LIFE_NONE - * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM - * WRITE_LIFE_LONG " WRITE_LIFE_LONG - */ - -enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, - enum page_type type, enum temp_type temp) -{ - if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) { - if (type == DATA) { - if (temp == WARM) - return WRITE_LIFE_NOT_SET; - else if (temp == HOT) - return WRITE_LIFE_SHORT; - else if (temp == COLD) - return WRITE_LIFE_EXTREME; - } else { - return WRITE_LIFE_NOT_SET; - } - } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) { - if (type == DATA) { - if (temp == WARM) - return WRITE_LIFE_LONG; - else if (temp == HOT) - return WRITE_LIFE_SHORT; - else if (temp == COLD) - return WRITE_LIFE_EXTREME; - } else if (type == NODE) { - if (temp == WARM || temp == HOT) - return WRITE_LIFE_NOT_SET; - else if (temp == COLD) - return WRITE_LIFE_NONE; - } else if (type == META) { - return WRITE_LIFE_MEDIUM; - } - } - return WRITE_LIFE_NOT_SET; -} - static int __get_segment_type_2(struct f2fs_io_info *fio) { if (fio->type == DATA) diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index ea939db18f88..4368f90571bd 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -138,7 +138,6 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, - Opt_whint, Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, @@ -214,7 +213,6 @@ static match_table_t f2fs_tokens = { {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, - {Opt_whint, "whint_mode=%s"}, {Opt_alloc, "alloc_mode=%s"}, {Opt_fsync, "fsync_mode=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption=%s"}, @@ -975,22 +973,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) f2fs_info(sbi, "quota operations not supported"); break; #endif - case Opt_whint: - name = match_strdup(&args[0]); - if (!name) - return -ENOMEM; - if (!strcmp(name, "user-based")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER; - } else if (!strcmp(name, "off")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; - } else if (!strcmp(name, "fs-based")) { - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS; - } else { - kfree(name); - return -EINVAL; - } - kfree(name); - break; case Opt_alloc: name = match_strdup(&args[0]); if (!name) @@ -1328,12 +1310,6 @@ default_check: return -EINVAL; } - /* Not pass down write hints if the number of active logs is lesser - * than NR_CURSEG_PERSIST_TYPE. - */ - if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE) - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; - if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) { f2fs_err(sbi, "Allow to mount readonly mode only"); return -EROFS; @@ -1978,10 +1954,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",prjquota"); #endif f2fs_show_quota_options(seq, sbi->sb); - if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) - seq_printf(seq, ",whint_mode=%s", "user-based"); - else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) - seq_printf(seq, ",whint_mode=%s", "fs-based"); fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb); @@ -2033,7 +2005,6 @@ static void default_options(struct f2fs_sb_info *sbi) F2FS_OPTION(sbi).active_logs = NR_CURSEG_PERSIST_TYPE; F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS; - F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); @@ -2314,8 +2285,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) need_stop_gc = true; } - if (*flags & SB_RDONLY || - F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) { + if (*flags & SB_RDONLY) { sync_inodes_sb(sb); set_sbi_flag(sbi, SBI_IS_DIRTY); diff --git a/fs/file_table.c b/fs/file_table.c index 7d2e692b66a9..ada8fe814db9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -412,6 +412,7 @@ void __fput_sync(struct file *file) } EXPORT_SYMBOL(fput); +EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 76316c4a3fb7..b313a978ae0a 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -38,6 +38,3 @@ config FSCACHE_DEBUG enabled by setting bits in /sys/modules/fscache/parameter/debug. See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_OLD_API - bool diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index 2749933852a9..d645f8b302a2 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -214,7 +214,7 @@ void fscache_relinquish_cache(struct fscache_cache *cache) cache->ops = NULL; cache->cache_priv = NULL; - smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_NOT_PRESENT); fscache_put_cache(cache, where); } EXPORT_SYMBOL(fscache_relinquish_cache); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 9bb1ab5fe5ed..9d3cf0111709 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -30,7 +30,7 @@ static DEFINE_SPINLOCK(fscache_cookie_lru_lock); DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD"; -unsigned int fscache_lru_cookie_timeout = 10 * HZ; +static unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) { @@ -1069,6 +1069,7 @@ void __fscache_invalidate(struct fscache_cookie *cookie, } EXPORT_SYMBOL(__fscache_invalidate); +#ifdef CONFIG_PROC_FS /* * Generate a list of extant cookies in /proc/fs/fscache/cookies */ @@ -1145,3 +1146,4 @@ const struct seq_operations fscache_cookies_seq_ops = { .stop = fscache_cookies_seq_stop, .show = fscache_cookies_seq_show, }; +#endif diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index ed1c9ed737f2..1336f517e9b1 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -56,7 +56,9 @@ static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, * cookie.c */ extern struct kmem_cache *fscache_cookie_jar; +#ifdef CONFIG_PROC_FS extern const struct seq_operations fscache_cookies_seq_ops; +#endif extern struct timer_list fscache_cookie_lru_timer; extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); @@ -137,7 +139,9 @@ int fscache_stats_show(struct seq_file *m, void *v); /* * volume.c */ +#ifdef CONFIG_PROC_FS extern const struct seq_operations fscache_volumes_seq_ops; +#endif struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where); diff --git a/fs/fscache/io.c b/fs/fscache/io.c index c8c7fe9e9a6e..3af3b08a9bb3 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -235,8 +235,7 @@ static void fscache_wreq_done(void *priv, ssize_t transferred_or_error, { struct fscache_write_request *wreq = priv; - fscache_clear_page_bits(fscache_cres_cookie(&wreq->cache_resources), - wreq->mapping, wreq->start, wreq->len, + fscache_clear_page_bits(wreq->mapping, wreq->start, wreq->len, wreq->set_bits); if (wreq->term_func) @@ -296,7 +295,7 @@ abandon_end: abandon_free: kfree(wreq); abandon: - fscache_clear_page_bits(cookie, mapping, start, len, cond); + fscache_clear_page_bits(mapping, start, len, cond); if (term_func) term_func(term_func_priv, ret, false); } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 22b41acfbbc3..48f01323c37c 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -899,10 +899,10 @@ retry: ret = gfs2_glock_nq(gh); if (ret) goto out_uninit; -retry_under_glock: /* Silently fall back to buffered I/O when writing beyond EOF */ if (iocb->ki_pos + iov_iter_count(from) > i_size_read(&ip->i_inode)) goto out; +retry_under_glock: from->nofault = true; ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, @@ -991,8 +991,6 @@ retry_under_glock: if (leftover != window_size) { if (gfs2_holder_queued(&gh)) goto retry_under_glock; - if (written) - goto out_uninit; goto retry; } } @@ -1069,8 +1067,6 @@ retry_under_glock: from->count = min(from->count, window_size - leftover); if (gfs2_holder_queued(gh)) goto retry_under_glock; - if (read && !(iocb->ki_flags & IOCB_DIRECT)) - goto out_uninit; goto retry; } } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 99c7477cee5c..dd3a088db11d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -206,7 +206,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); @@ -222,7 +222,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); - info.high_limit = current->mm->mmap_base; + info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -237,7 +237,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); addr = vm_unmapped_area(&info); } @@ -251,6 +251,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); + const unsigned long mmap_end = arch_get_mmap_end(addr); if (len & ~huge_page_mask(h)) return -EINVAL; @@ -266,7 +267,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (mmap_end - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/fs/io_uring.c b/fs/io_uring.c index a8413f006417..e01f595f5b7d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -63,7 +63,6 @@ #include <net/sock.h> #include <net/af_unix.h> #include <net/scm.h> -#include <net/busy_poll.h> #include <linux/anon_inodes.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> @@ -112,8 +111,7 @@ IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS) #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ - REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ - REQ_F_ASYNC_DATA) + REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA) #define IO_TCTX_REFS_CACHE_NR (1U << 10) @@ -412,11 +410,6 @@ struct io_ring_ctx { struct list_head sqd_list; unsigned long check_cq_overflow; -#ifdef CONFIG_NET_RX_BUSY_POLL - /* used to track busy poll napi_id */ - struct list_head napi_list; - spinlock_t napi_lock; /* napi_list lock */ -#endif struct { unsigned cached_cq_tail; @@ -500,7 +493,6 @@ struct io_uring_task { const struct io_ring_ctx *last; struct io_wq *io_wq; struct percpu_counter inflight; - atomic_t inflight_tracked; atomic_t in_idle; spinlock_t task_lock; @@ -592,7 +584,8 @@ struct io_rw { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct kiocb kiocb; u64 addr; - u64 len; + u32 len; + u32 flags; }; struct io_connect { @@ -654,10 +647,10 @@ struct io_epoll { struct io_splice { struct file *file_out; - struct file *file_in; loff_t off_out; loff_t off_in; u64 len; + int splice_fd_in; unsigned int flags; }; @@ -914,7 +907,11 @@ struct io_kiocb { u64 user_data; u32 result; - u32 cflags; + /* fd initially, then cflags for completion */ + union { + u32 cflags; + int fd; + }; struct io_ring_ctx *ctx; struct task_struct *task; @@ -923,8 +920,12 @@ struct io_kiocb { /* store used ubuf, so we can prevent reloading */ struct io_mapped_ubuf *imu; - /* used by request caches, completion batching and iopoll */ - struct io_wq_work_node comp_list; + union { + /* used by request caches, completion batching and iopoll */ + struct io_wq_work_node comp_list; + /* cache ->apoll->events */ + int apoll_events; + }; atomic_t refs; atomic_t poll_refs; struct io_task_work io_task_work; @@ -1182,8 +1183,11 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, struct io_uring_rsrc_update2 *up, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); -static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned issue_flags); +static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd); +static void io_drop_inflight_file(struct io_kiocb *req); +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -1313,13 +1317,20 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx) } static inline void io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx) + struct io_ring_ctx *ctx, + unsigned int issue_flags) { if (!req->fixed_rsrc_refs) { req->fixed_rsrc_refs = &ctx->rsrc_node->refs; - ctx->rsrc_cached_refs--; - if (unlikely(ctx->rsrc_cached_refs < 0)) - io_rsrc_refs_refill(ctx); + + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + lockdep_assert_held(&ctx->uring_lock); + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); + } else { + percpu_ref_get(req->fixed_rsrc_refs); + } } } @@ -1424,29 +1435,9 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *req; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; -} - -static bool io_match_linked(struct io_kiocb *head) -{ - struct io_kiocb *req; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; + return cancel_all; } /* @@ -1456,24 +1447,9 @@ static bool io_match_linked(struct io_kiocb *head) static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all) { - bool matched; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - if (head->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = head->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); - matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); - } else { - matched = io_match_linked(head); - } - return matched; + return cancel_all; } static inline bool req_has_async_data(struct io_kiocb *req) @@ -1595,10 +1571,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_WQ_LIST(&ctx->locked_free_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); -#ifdef CONFIG_NET_RX_BUSY_POLL - INIT_LIST_HEAD(&ctx->napi_list); - spin_lock_init(&ctx->napi_lock); -#endif return ctx; err: kfree(ctx->dummy_ubuf); @@ -1636,14 +1608,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req) return req->flags & REQ_F_FIXED_FILE; } -static inline void io_req_track_inflight(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; - atomic_inc(¤t->io_uring->inflight_tracked); - } -} - static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) @@ -1687,14 +1651,6 @@ static void io_prep_async_work(struct io_kiocb *req) if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } - - switch (req->opcode) { - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!S_ISREG(file_inode(req->splice.file_in)->i_mode)) - req->work.flags |= IO_WQ_WORK_UNBOUND; - break; - } } static void io_prep_async_link(struct io_kiocb *req) @@ -1788,12 +1744,11 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) __must_hold(&ctx->completion_lock) { u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + struct io_kiocb *req, *tmp; spin_lock_irq(&ctx->timeout_lock); - while (!list_empty(&ctx->timeout_list)) { + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { u32 events_needed, events_got; - struct io_kiocb *req = list_first_entry(&ctx->timeout_list, - struct io_kiocb, timeout.list); if (io_is_timeout_noseq(req)) break; @@ -1810,7 +1765,6 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) if (events_got < events_needed) break; - list_del_init(&req->timeout.list); io_kill_timeout(req, 0); } ctx->cq_last_tm_flush = seq; @@ -2562,6 +2516,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) WARN_ON_ONCE(!tctx); + io_drop_inflight_file(req); + spin_lock_irqsave(&tctx->task_lock, flags); if (priority) wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list); @@ -2841,11 +2797,10 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) /* order with io_complete_rw_iopoll(), e.g. ->result updates */ if (!smp_load_acquire(&req->iopoll_completed)) break; + nr_events++; if (unlikely(req->flags & REQ_F_CQE_SKIP)) continue; - __io_fill_cqe_req(req, req->result, io_put_kbuf(req, 0)); - nr_events++; } if (unlikely(!nr_events)) @@ -3186,42 +3141,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req) static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; - struct file *file = req->file; unsigned ioprio; int ret; - if (!io_req_ffs_set(req)) - req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; - kiocb->ki_pos = READ_ONCE(sqe->off); - kiocb->ki_flags = iocb_flags(file); - ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); - if (unlikely(ret)) - return ret; - - /* - * If the file is marked O_NONBLOCK, still allow retry for it if it - * supports async. Otherwise it's impossible to use O_NONBLOCK files - * reliably. If not, or it IOCB_NOWAIT is set, don't retry. - */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || - ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) - req->flags |= REQ_F_NOWAIT; - - if (ctx->flags & IORING_SETUP_IOPOLL) { - if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) - return -EOPNOTSUPP; - - kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; - kiocb->ki_complete = io_complete_rw_iopoll; - req->iopoll_completed = 0; - } else { - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - kiocb->ki_complete = io_complete_rw; - } ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { @@ -3237,6 +3161,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = NULL; req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); + req->rw.flags = READ_ONCE(sqe->rw_flags); req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -3265,19 +3190,18 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; - bool is_stream = req->file->f_mode & FMODE_STREAM; - if (kiocb->ki_pos == -1) { - if (!is_stream) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; - return &kiocb->ki_pos; - } else { - kiocb->ki_pos = 0; - return NULL; - } + if (kiocb->ki_pos != -1) + return &kiocb->ki_pos; + + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; } - return is_stream ? NULL : &kiocb->ki_pos; + + kiocb->ki_pos = 0; + return NULL; } static void kiocb_done(struct io_kiocb *req, ssize_t ret, @@ -3367,7 +3291,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter return 0; } -static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + unsigned int issue_flags) { struct io_mapped_ubuf *imu = req->imu; u16 index, buf_index = req->buf_index; @@ -3377,7 +3302,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, issue_flags); index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = READ_ONCE(ctx->user_bufs[index]); req->imu = imu; @@ -3539,7 +3464,7 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - ret = io_import_fixed(req, rw, iter); + ret = io_import_fixed(req, rw, iter, issue_flags); if (ret) return ERR_PTR(ret); return NULL; @@ -3740,13 +3665,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) return 0; } -static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_READ))) - return -EBADF; - return io_prep_rw(req, sqe); -} - /* * This is our waitqueue callback handler, registered through __folio_lock_async() * when we initially tried to do the IO with the iocb armed our waitqueue. @@ -3834,6 +3752,50 @@ static bool need_read_all(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +{ + struct kiocb *kiocb = &req->rw.kiocb; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (unlikely(!file || !(file->f_mode & mode))) + return -EBADF; + + if (!io_req_ffs_set(req)) + req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; + + kiocb->ki_flags = iocb_flags(file); + ret = kiocb_set_rw_flags(kiocb, req->rw.flags); + if (unlikely(ret)) + return ret; + + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) + req->flags |= REQ_F_NOWAIT; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) + return -EOPNOTSUPP; + + kiocb->private = NULL; + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; + kiocb->ki_complete = io_complete_rw_iopoll; + req->iopoll_completed = 0; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + kiocb->ki_complete = io_complete_rw; + } + + return 0; +} + static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3869,6 +3831,11 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_READ); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -3972,13 +3939,6 @@ out_free: return 0; } -static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_WRITE))) - return -EBADF; - return io_prep_rw(req, sqe); -} - static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3999,6 +3959,11 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_WRITE); + if (unlikely(ret)) { + kfree(iovec); + return ret; + } req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -4369,18 +4334,11 @@ static int __io_splice_prep(struct io_kiocb *req, if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - sp->file_in = NULL; sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); - if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; - - sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in), - (sp->flags & SPLICE_F_FD_IN_FIXED)); - if (!sp->file_in) - return -EBADF; - req->flags |= REQ_F_NEED_CLEANUP; + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); return 0; } @@ -4395,20 +4353,29 @@ static int io_tee_prep(struct io_kiocb *req, static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + if (sp->len) ret = do_tee(in, out, sp->len, flags); if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); @@ -4427,15 +4394,24 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; @@ -4444,8 +4420,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); @@ -4513,9 +4488,6 @@ static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - if (!req->file) - return -EBADF; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || @@ -5236,6 +5208,8 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); @@ -5447,6 +5421,8 @@ static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; + if (unlikely(sqe->addr2 || sqe->file_index)) + return -EINVAL; sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr)); sr->len = READ_ONCE(sqe->len); @@ -5757,108 +5733,6 @@ IO_NETOP_FN(send); IO_NETOP_FN(recv); #endif /* CONFIG_NET */ -#ifdef CONFIG_NET_RX_BUSY_POLL - -#define NAPI_TIMEOUT (60 * SEC_CONVERSION) - -struct napi_entry { - struct list_head list; - unsigned int napi_id; - unsigned long timeout; -}; - -/* - * Add busy poll NAPI ID from sk. - */ -static void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ - unsigned int napi_id; - struct socket *sock; - struct sock *sk; - struct napi_entry *ne; - - if (!net_busy_loop_on()) - return; - - sock = sock_from_file(file); - if (!sock) - return; - - sk = sock->sk; - if (!sk) - return; - - napi_id = READ_ONCE(sk->sk_napi_id); - - /* Non-NAPI IDs can be rejected */ - if (napi_id < MIN_NAPI_ID) - return; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(ne, &ctx->napi_list, list) { - if (ne->napi_id == napi_id) { - ne->timeout = jiffies + NAPI_TIMEOUT; - goto out; - } - } - - ne = kmalloc(sizeof(*ne), GFP_NOWAIT); - if (!ne) - goto out; - - ne->napi_id = napi_id; - ne->timeout = jiffies + NAPI_TIMEOUT; - list_add_tail(&ne->list, &ctx->napi_list); -out: - spin_unlock(&ctx->napi_lock); -} - -static inline void io_check_napi_entry_timeout(struct napi_entry *ne) -{ - if (time_after(jiffies, ne->timeout)) { - list_del(&ne->list); - kfree(ne); - } -} - -/* - * Busy poll if globally on and supporting sockets found - */ -static bool io_napi_busy_loop(struct list_head *napi_list) -{ - struct napi_entry *ne, *n; - - list_for_each_entry_safe(ne, n, napi_list, list) { - napi_busy_loop(ne->napi_id, NULL, NULL, true, - BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - } - return !list_empty(napi_list); -} - -static void io_free_napi_list(struct io_ring_ctx *ctx) -{ - spin_lock(&ctx->napi_lock); - while (!list_empty(&ctx->napi_list)) { - struct napi_entry *ne = - list_first_entry(&ctx->napi_list, struct napi_entry, - list); - - list_del(&ne->list); - kfree(ne); - } - spin_unlock(&ctx->napi_lock); -} -#else -static inline void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ -} - -static inline void io_free_napi_list(struct io_ring_ctx *ctx) -{ -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - struct io_poll_table { struct poll_table_struct pt; struct io_kiocb *req; @@ -5972,10 +5846,9 @@ static void io_poll_remove_entries(struct io_kiocb *req) * either spurious wakeup or multishot CQE is served. 0 when it's done with * the request, then the mask is stored in req->result. */ -static int io_poll_check_events(struct io_kiocb *req) +static int io_poll_check_events(struct io_kiocb *req, bool locked) { struct io_ring_ctx *ctx = req->ctx; - struct io_poll_iocb *poll = io_poll_get_single(req); int v; /* req->task == current here, checking PF_EXITING is safe */ @@ -5992,14 +5865,17 @@ static int io_poll_check_events(struct io_kiocb *req) return -ECANCELED; if (!req->result) { - struct poll_table_struct pt = { ._key = req->cflags }; + struct poll_table_struct pt = { ._key = req->apoll_events }; + unsigned flags = locked ? 0 : IO_URING_F_UNLOCKED; - req->result = vfs_poll(req->file, &pt) & req->cflags; + if (unlikely(!io_assign_file(req, flags))) + return -EBADF; + req->result = vfs_poll(req->file, &pt) & req->apoll_events; } /* multishot, just fill an CQE and proceed */ - if (req->result && !(req->cflags & EPOLLONESHOT)) { - __poll_t mask = mangle_poll(req->result & poll->events); + if (req->result && !(req->apoll_events & EPOLLONESHOT)) { + __poll_t mask = mangle_poll(req->result & req->apoll_events); bool filled; spin_lock(&ctx->completion_lock); @@ -6010,7 +5886,6 @@ static int io_poll_check_events(struct io_kiocb *req) if (unlikely(!filled)) return -ECANCELED; io_cqring_ev_posted(ctx); - io_add_napi(req->file, ctx); } else if (req->result) { return 0; } @@ -6029,7 +5904,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -6054,7 +5929,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -6078,7 +5953,7 @@ static void __io_poll_execute(struct io_kiocb *req, int mask, int events) * CPU. We want to avoid pulling in req->apoll->events for that * case. */ - req->cflags = events; + req->apoll_events = events; if (req->opcode == IORING_OP_POLL_ADD) req->io_task_work.func = io_poll_task_func; else @@ -6261,7 +6136,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req, __io_poll_execute(req, mask, poll->events); return 0; } - io_add_napi(req->file, req->ctx); /* * Release ownership. If someone tried to queue a tw while it was @@ -6471,7 +6345,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return -EINVAL; io_req_set_refcount(req); - req->cflags = poll->events = io_poll_parse_events(sqe, flags); + req->apoll_events = poll->events = io_poll_parse_events(sqe, flags); return 0; } @@ -6766,6 +6640,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) return -EINVAL; + INIT_LIST_HEAD(&req->timeout.list); data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); @@ -6972,6 +6847,7 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) up.nr = 0; up.tags = 0; up.resv = 0; + up.resv2 = 0; io_ring_submit_lock(ctx, needs_lock); ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, @@ -6992,11 +6868,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - return io_read_prep(req, sqe); case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - return io_write_prep(req, sqe); + return io_prep_rw(req, sqe); case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: @@ -7179,11 +7054,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(io->free_iov); break; } - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED)) - io_put_file(req->splice.file_in); - break; case IORING_OP_OPENAT: case IORING_OP_OPENAT2: if (req->open.filename) @@ -7218,11 +7088,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(req->apoll); req->apoll = NULL; } - if (req->flags & REQ_F_INFLIGHT) { - struct io_uring_task *tctx = req->task->io_uring; - - atomic_dec(&tctx->inflight_tracked); - } if (req->flags & REQ_F_CREDS) put_cred(req->creds); if (req->flags & REQ_F_ASYNC_DATA) { @@ -7232,11 +7097,31 @@ static void io_clean_op(struct io_kiocb *req) req->flags &= ~IO_REQ_CLEAN_FLAGS; } +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) +{ + if (req->file || !io_op_defs[req->opcode].needs_file) + return true; + + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->fd, issue_flags); + else + req->file = io_file_get_normal(req, req->fd); + if (req->file) + return true; + + req_set_fail(req); + req->result = -EBADF; + return false; +} + static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { const struct cred *creds = NULL; int ret; + if (unlikely(!io_assign_file(req, issue_flags))) + return -EBADF; + if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) creds = override_creds(req->creds); @@ -7386,10 +7271,11 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + const struct io_op_def *def = &io_op_defs[req->opcode]; unsigned int issue_flags = IO_URING_F_UNLOCKED; bool needs_poll = false; struct io_kiocb *timeout; - int ret = 0; + int ret = 0, err = -ECANCELED; /* one will be dropped by ->io_free_work() after returning to io-wq */ if (!(req->flags & REQ_F_REFCOUNT)) @@ -7401,14 +7287,20 @@ static void io_wq_submit_work(struct io_wq_work *work) if (timeout) io_queue_linked_timeout(timeout); + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { - io_req_task_queue_fail(req, -ECANCELED); +fail: + io_req_task_queue_fail(req, err); return; } + if (!io_assign_file(req, issue_flags)) { + err = -EBADF; + work->flags |= IO_WQ_WORK_CANCEL; + goto fail; + } if (req->flags & REQ_F_FORCE_ASYNC) { - const struct io_op_def *def = &io_op_defs[req->opcode]; bool opcode_poll = def->pollin || def->pollout; if (opcode_poll && file_can_poll(req->file)) { @@ -7465,46 +7357,56 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file file_slot->file_ptr = file_ptr; } -static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; unsigned long file_ptr; + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); file_ptr &= ~FFS_MASK; /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, 0); +out: + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); return file; } -static struct file *io_file_get_normal(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +/* + * Drop the file for requeue operations. Only used of req->file is the + * io_uring descriptor itself. + */ +static void io_drop_inflight_file(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_INFLIGHT)) { + fput(req->file); + req->file = NULL; + req->flags &= ~REQ_F_INFLIGHT; + } +} + +static struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); - trace_io_uring_file_get(ctx, req, req->user_data, fd); + trace_io_uring_file_get(req->ctx, req, req->user_data, fd); /* we don't allow fixed io_uring files */ - if (file && unlikely(file->f_op == &io_uring_fops)) - io_req_track_inflight(req); + if (file && file->f_op == &io_uring_fops) + req->flags |= REQ_F_INFLIGHT; return file; } -static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) -{ - if (fixed) - return io_file_get_fixed(ctx, req, fd); - else - return io_file_get_normal(ctx, req, fd); -} - static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; @@ -7744,6 +7646,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[opcode].needs_file) { struct io_submit_state *state = &ctx->submit_state; + req->fd = READ_ONCE(sqe->fd); + /* * Plug now if we have more than 2 IO left after this, and the * target is potentially a read/write to block based storage. @@ -7753,11 +7657,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, state->need_plug = false; blk_start_plug_nr_ios(&state->plug, state->submit_nr); } - - req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); - if (unlikely(!req->file)) - return -EBADF; } personality = READ_ONCE(sqe->personality); @@ -8032,13 +7931,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) !(ctx->flags & IORING_SETUP_R_DISABLED)) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); -#ifdef CONFIG_NET_RX_BUSY_POLL - spin_lock(&ctx->napi_lock); - if (!list_empty(&ctx->napi_list) && - io_napi_busy_loop(&ctx->napi_list)) - ++ret; - spin_unlock(&ctx->napi_lock); -#endif + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) wake_up(&ctx->sqo_sq_wait); if (creds) @@ -8176,9 +8069,6 @@ struct io_wait_queue { struct io_ring_ctx *ctx; unsigned cq_tail; unsigned nr_timeouts; -#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned busy_poll_to; -#endif }; static inline bool io_should_wake(struct io_wait_queue *iowq) @@ -8240,87 +8130,6 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, return 1; } -#ifdef CONFIG_NET_RX_BUSY_POLL -static void io_adjust_busy_loop_timeout(struct timespec64 *ts, - struct io_wait_queue *iowq) -{ - unsigned busy_poll_to = READ_ONCE(sysctl_net_busy_poll); - struct timespec64 pollto = ns_to_timespec64(1000 * (s64)busy_poll_to); - - if (timespec64_compare(ts, &pollto) > 0) { - *ts = timespec64_sub(*ts, pollto); - iowq->busy_poll_to = busy_poll_to; - } else { - u64 to = timespec64_to_ns(ts); - - do_div(to, 1000); - iowq->busy_poll_to = to; - ts->tv_sec = 0; - ts->tv_nsec = 0; - } -} - -static inline bool io_busy_loop_timeout(unsigned long start_time, - unsigned long bp_usec) -{ - if (bp_usec) { - unsigned long end_time = start_time + bp_usec; - unsigned long now = busy_loop_current_time(); - - return time_after(now, end_time); - } - return true; -} - -static bool io_busy_loop_end(void *p, unsigned long start_time) -{ - struct io_wait_queue *iowq = p; - - return signal_pending(current) || - io_should_wake(iowq) || - io_busy_loop_timeout(start_time, iowq->busy_poll_to); -} - -static void io_blocking_napi_busy_loop(struct list_head *napi_list, - struct io_wait_queue *iowq) -{ - unsigned long start_time = - list_is_singular(napi_list) ? 0 : - busy_loop_current_time(); - - do { - if (list_is_singular(napi_list)) { - struct napi_entry *ne = - list_first_entry(napi_list, - struct napi_entry, list); - - napi_busy_loop(ne->napi_id, io_busy_loop_end, iowq, - true, BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - break; - } - } while (io_napi_busy_loop(napi_list) && - !io_busy_loop_end(iowq, start_time)); -} - -static void io_putback_napi_list(struct io_ring_ctx *ctx, - struct list_head *napi_list) -{ - struct napi_entry *cne, *lne; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(cne, &ctx->napi_list, list) - list_for_each_entry(lne, napi_list, list) - if (cne->napi_id == lne->napi_id) { - list_del(&lne->list); - kfree(lne); - break; - } - list_splice(napi_list, &ctx->napi_list); - spin_unlock(&ctx->napi_lock); -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. @@ -8333,9 +8142,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, struct io_rings *rings = ctx->rings; ktime_t timeout = KTIME_MAX; int ret; -#ifdef CONFIG_NET_RX_BUSY_POLL - LIST_HEAD(local_napi_list); -#endif do { io_cqring_overflow_flush(ctx); @@ -8358,29 +8164,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } -#ifdef CONFIG_NET_RX_BUSY_POLL - iowq.busy_poll_to = 0; - if (!(ctx->flags & IORING_SETUP_SQPOLL)) { - spin_lock(&ctx->napi_lock); - list_splice_init(&ctx->napi_list, &local_napi_list); - spin_unlock(&ctx->napi_lock); - } -#endif if (uts) { struct timespec64 ts; if (get_timespec64(&ts, uts)) return -EFAULT; -#ifdef CONFIG_NET_RX_BUSY_POLL - if (!list_empty(&local_napi_list)) - io_adjust_busy_loop_timeout(&ts, &iowq); -#endif timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } -#ifdef CONFIG_NET_RX_BUSY_POLL - else if (!list_empty(&local_napi_list)) - iowq.busy_poll_to = READ_ONCE(sysctl_net_busy_poll); -#endif init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; @@ -8390,12 +8180,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; trace_io_uring_cqring_wait(ctx, min_events); -#ifdef CONFIG_NET_RX_BUSY_POLL - if (iowq.busy_poll_to) - io_blocking_napi_busy_loop(&local_napi_list, &iowq); - if (!list_empty(&local_napi_list)) - io_putback_napi_list(ctx, &local_napi_list); -#endif do { /* if we can't even flush overflow, don't wait for more */ if (!io_cqring_overflow_flush(ctx)) { @@ -8864,8 +8648,12 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_queue_head(&sk->sk_receive_queue, skb); - for (i = 0; i < nr_files; i++) - fput(fpl->fp[i]); + for (i = 0; i < nr; i++) { + struct file *file = io_file_from_index(ctx, i + offset); + + if (file) + fput(file); + } } else { kfree_skb(skb); free_uid(fpl->user); @@ -9156,13 +8944,15 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { + u64 *tag_slot = io_get_tag_slot(data, idx); struct io_rsrc_put *prsrc; prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); if (!prsrc) return -ENOMEM; - prsrc->tag = *io_get_tag_slot(data, idx); + prsrc->tag = *tag_slot; + *tag_slot = 0; prsrc->rsrc = rsrc; list_add(&prsrc->list, &node->rsrc_list); return 0; @@ -9231,7 +9021,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_fixed_file *file_slot; struct file *file; - int ret, i; + int ret; io_ring_submit_lock(ctx, needs_lock); ret = -ENXIO; @@ -9244,8 +9034,8 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) if (ret) goto out; - i = array_index_nospec(offset, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, i); + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); ret = -EBADF; if (!file_slot->file_ptr) goto out; @@ -9301,8 +9091,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (file_slot->file_ptr) { file = (struct file *)(file_slot->file_ptr & FFS_MASK); - err = io_queue_rsrc_removal(data, up->offset + done, - ctx->rsrc_node, file); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); if (err) break; file_slot->file_ptr = 0; @@ -9327,7 +9116,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - *io_get_tag_slot(data, up->offset + done) = tag; + *io_get_tag_slot(data, i) = tag; io_fixed_file_set(file_slot, file); err = io_sqe_file_register(ctx, file, i); if (err) { @@ -9411,7 +9200,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task, xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); atomic_set(&tctx->in_idle, 0); - atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); @@ -9986,7 +9774,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, i = array_index_nospec(offset, ctx->nr_user_bufs); if (ctx->user_bufs[i] != ctx->dummy_ubuf) { - err = io_queue_rsrc_removal(ctx->buf_data, offset, + err = io_queue_rsrc_removal(ctx->buf_data, i, ctx->rsrc_node, ctx->user_bufs[i]); if (unlikely(err)) { io_buffer_unmap(ctx, &imu); @@ -10181,7 +9969,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_req_caches_free(ctx); if (ctx->hash_map) io_wq_put_hash(ctx->hash_map); - io_free_napi_list(ctx); kfree(ctx->cancel_hash); kfree(ctx->dummy_ubuf); kfree(ctx->io_buffers); @@ -10604,7 +10391,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) { if (tracked) - return atomic_read(&tctx->inflight_tracked); + return 0; return percpu_counter_sum(&tctx->inflight); } @@ -10755,6 +10542,11 @@ static int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, break; } + if (reg.resv) { + ret = -EINVAL; + break; + } + if (reg.offset == -1U) { start = 0; end = IO_RINGFD_REG_MAX; @@ -10801,7 +10593,7 @@ static int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, ret = -EFAULT; break; } - if (reg.offset >= IO_RINGFD_REG_MAX) { + if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) { ret = -EINVAL; break; } @@ -10928,6 +10720,8 @@ static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz return -EINVAL; if (copy_from_user(&arg, argp, sizeof(arg))) return -EFAULT; + if (arg.pad) + return -EINVAL; *sig = u64_to_user_ptr(arg.sigmask); *argsz = arg.sigmask_sz; *ts = u64_to_user_ptr(arg.ts); @@ -11409,7 +11203,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | - IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP; + IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP | + IORING_FEAT_LINKED_FILE; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -11620,8 +11415,6 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, __u32 tmp; int err; - if (up->resv) - return -EINVAL; if (check_add_overflow(up->offset, nr_args, &tmp)) return -EOVERFLOW; err = io_rsrc_node_switch_start(ctx); @@ -11647,6 +11440,8 @@ static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, memset(&up, 0, sizeof(up)); if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) return -EFAULT; + if (up.resv || up.resv2) + return -EINVAL; return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); } @@ -11659,7 +11454,7 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; - if (!up.nr || up.resv) + if (!up.nr || up.resv || up.resv2) return -EINVAL; return __io_register_rsrc_update(ctx, type, &up, up.nr); } @@ -11707,7 +11502,15 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, if (len > cpumask_size()) len = cpumask_size(); - if (copy_from_user(new_mask, arg, len)) { + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } + + if (ret) { free_cpumask_var(new_mask); return -EFAULT; } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 5b9408e3b370..ac7f067b7bdd 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -488,7 +488,6 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_wait_updates(journal); commit_transaction->t_state = T_SWITCH; - write_unlock(&journal->j_state_lock); J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= journal->j_max_transaction_buffers); @@ -508,6 +507,8 @@ void jbd2_journal_commit_transaction(journal_t *journal) * has reserved. This is consistent with the existing behaviour * that multiple jbd2_journal_get_write_access() calls to the same * buffer are perfectly permissible. + * We use journal->j_state_lock here to serialize processing of + * t_reserved_list with eviction of buffers from journal_unmap_buffer(). */ while (commit_transaction->t_reserved_list) { jh = commit_transaction->t_reserved_list; @@ -527,6 +528,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_refile_buffer(journal, jh); } + write_unlock(&journal->j_state_lock); /* * Now try to drop any written-back buffers from the journal's * checkpoint lists. We do this *before* commit because it potentially diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 61a8edc4ba8b..e205fde7163a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1406,7 +1406,12 @@ static void __kernfs_remove(struct kernfs_node *kn) */ void kernfs_remove(struct kernfs_node *kn) { - struct kernfs_root *root = kernfs_root(kn); + struct kernfs_root *root; + + if (!kn) + return; + + root = kernfs_root(kn); down_write(&root->kernfs_rwsem); __kernfs_remove(kn); diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 60e7ac62c917..1e2076a53bed 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -158,19 +158,41 @@ out: * Return : windows path string or error */ -char *convert_to_nt_pathname(char *filename) +char *convert_to_nt_pathname(struct ksmbd_share_config *share, + struct path *path) { - char *ab_pathname; + char *pathname, *ab_pathname, *nt_pathname; + int share_path_len = share->path_sz; - if (strlen(filename) == 0) - filename = "\\"; + pathname = kmalloc(PATH_MAX, GFP_KERNEL); + if (!pathname) + return ERR_PTR(-EACCES); - ab_pathname = kstrdup(filename, GFP_KERNEL); - if (!ab_pathname) - return NULL; + ab_pathname = d_path(path, pathname, PATH_MAX); + if (IS_ERR(ab_pathname)) { + nt_pathname = ERR_PTR(-EACCES); + goto free_pathname; + } + + if (strncmp(ab_pathname, share->path, share_path_len)) { + nt_pathname = ERR_PTR(-EACCES); + goto free_pathname; + } + + nt_pathname = kzalloc(strlen(&ab_pathname[share_path_len]) + 2, GFP_KERNEL); + if (!nt_pathname) { + nt_pathname = ERR_PTR(-ENOMEM); + goto free_pathname; + } + if (ab_pathname[share_path_len] == '\0') + strcpy(nt_pathname, "/"); + strcat(nt_pathname, &ab_pathname[share_path_len]); + + ksmbd_conv_path_to_windows(nt_pathname); - ksmbd_conv_path_to_windows(ab_pathname); - return ab_pathname; +free_pathname: + kfree(pathname); + return nt_pathname; } int get_nlink(struct kstat *st) diff --git a/fs/ksmbd/misc.h b/fs/ksmbd/misc.h index 253366bd0951..aae2a252945f 100644 --- a/fs/ksmbd/misc.h +++ b/fs/ksmbd/misc.h @@ -14,7 +14,8 @@ struct ksmbd_file; int match_pattern(const char *str, size_t len, const char *pattern); int ksmbd_validate_filename(char *filename); int parse_stream_name(char *filename, char **stream_name, int *s_type); -char *convert_to_nt_pathname(char *filename); +char *convert_to_nt_pathname(struct ksmbd_share_config *share, + struct path *path); int get_nlink(struct kstat *st); void ksmbd_conv_path_to_unix(char *path); void ksmbd_strip_last_slash(char *path); diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 23871b18a429..8b5560574d4c 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1694,33 +1694,3 @@ out: read_unlock(&lease_list_lock); return ret_op; } - -int smb2_check_durable_oplock(struct ksmbd_file *fp, - struct lease_ctx_info *lctx, char *name) -{ - struct oplock_info *opinfo = opinfo_get(fp); - int ret = 0; - - if (opinfo && opinfo->is_lease) { - if (!lctx) { - pr_err("open does not include lease\n"); - ret = -EBADF; - goto out; - } - if (memcmp(opinfo->o_lease->lease_key, lctx->lease_key, - SMB2_LEASE_KEY_SIZE)) { - pr_err("invalid lease key\n"); - ret = -EBADF; - goto out; - } - if (name && strcmp(fp->filename, name)) { - pr_err("invalid name reconnect %s\n", name); - ret = -EINVAL; - goto out; - } - } -out: - if (opinfo) - opinfo_put(opinfo); - return ret; -} diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 0cf7a2b5bbc0..09753448f779 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -124,6 +124,4 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); -int smb2_check_durable_oplock(struct ksmbd_file *fp, - struct lease_ctx_info *lctx, char *name); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 3bf6c56c654c..16c803a9d996 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -11,6 +11,7 @@ #include <linux/statfs.h> #include <linux/ethtool.h> #include <linux/falloc.h> +#include <linux/mount.h> #include "glob.h" #include "smbfsctl.h" @@ -2918,7 +2919,6 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } - fp->filename = name; fp->cdoption = req->CreateDisposition; fp->daccess = daccess; fp->saccess = req->ShareAccess; @@ -3270,14 +3270,13 @@ err_out1: if (!rsp->hdr.Status) rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; - if (!fp || !fp->filename) - kfree(name); if (fp) ksmbd_fd_put(work, fp); smb2_set_err_rsp(work); ksmbd_debug(SMB, "Error response: %x\n", rsp->hdr.Status); } + kfree(name); kfree(lc); return 0; @@ -3895,8 +3894,6 @@ int smb2_query_dir(struct ksmbd_work *work) ksmbd_debug(SMB, "Search pattern is %s\n", srch_ptr); } - ksmbd_debug(SMB, "Directory name is %s\n", dir_fp->filename); - if (srch_flag & SMB2_REOPEN || srch_flag & SMB2_RESTART_SCANS) { ksmbd_debug(SMB, "Restart directory scan\n"); generic_file_llseek(dir_fp->filp, 0, SEEK_SET); @@ -4390,9 +4387,9 @@ static int get_file_all_info(struct ksmbd_work *work, return -EACCES; } - filename = convert_to_nt_pathname(fp->filename); - if (!filename) - return -ENOMEM; + filename = convert_to_nt_pathname(work->tcon->share_conf, &fp->filp->f_path); + if (IS_ERR(filename)) + return PTR_ERR(filename); inode = file_inode(fp->filp); generic_fillattr(file_mnt_user_ns(fp->filp), inode, &stat); @@ -4999,15 +4996,17 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, case FS_SECTOR_SIZE_INFORMATION: { struct smb3_fs_ss_info *info; + unsigned int sector_size = + min_t(unsigned int, path.mnt->mnt_sb->s_blocksize, 4096); info = (struct smb3_fs_ss_info *)(rsp->Buffer); - info->LogicalBytesPerSector = cpu_to_le32(stfs.f_bsize); + info->LogicalBytesPerSector = cpu_to_le32(sector_size); info->PhysicalBytesPerSectorForAtomicity = - cpu_to_le32(stfs.f_bsize); - info->PhysicalBytesPerSectorForPerf = cpu_to_le32(stfs.f_bsize); + cpu_to_le32(sector_size); + info->PhysicalBytesPerSectorForPerf = cpu_to_le32(sector_size); info->FSEffPhysicalBytesPerSectorForAtomicity = - cpu_to_le32(stfs.f_bsize); + cpu_to_le32(sector_size); info->Flags = cpu_to_le32(SSINFO_FLAGS_ALIGNED_DEVICE | SSINFO_FLAGS_PARTITION_ALIGNED_ON_DEVICE); info->ByteOffsetForSectorAlignment = 0; @@ -5683,8 +5682,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, size = i_size_read(inode); rc = ksmbd_vfs_truncate(work, fp, alloc_blks * 512); if (rc) { - pr_err("truncate failed! filename : %s, err %d\n", - fp->filename, rc); + pr_err("truncate failed!, err %d\n", rc); return rc; } if (size < alloc_blks * 512) @@ -5714,12 +5712,10 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, * truncated range. */ if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC) { - ksmbd_debug(SMB, "filename : %s truncated to newsize %lld\n", - fp->filename, newsize); + ksmbd_debug(SMB, "truncated to newsize %lld\n", newsize); rc = ksmbd_vfs_truncate(work, fp, newsize); if (rc) { - ksmbd_debug(SMB, "truncate failed! filename : %s err %d\n", - fp->filename, rc); + ksmbd_debug(SMB, "truncate failed!, err %d\n", rc); if (rc != -EAGAIN) rc = -EBADF; return rc; @@ -5765,8 +5761,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, if (parent_fp) { if (parent_fp->daccess & FILE_DELETE_LE) { pr_err("parent dir is opened with delete access\n"); + ksmbd_fd_put(work, parent_fp); return -ESHARE; } + ksmbd_fd_put(work, parent_fp); } next: return smb2_rename(work, fp, user_ns, rename_info, diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 9cebb6ba555b..dcdd07c6efff 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -398,8 +398,7 @@ int ksmbd_vfs_read(struct ksmbd_work *work, struct ksmbd_file *fp, size_t count, nbytes = kernel_read(filp, rbuf, count, pos); if (nbytes < 0) { - pr_err("smb read failed for (%s), err = %zd\n", - fp->filename, nbytes); + pr_err("smb read failed, err = %zd\n", nbytes); return nbytes; } @@ -875,8 +874,7 @@ int ksmbd_vfs_truncate(struct ksmbd_work *work, err = vfs_truncate(&filp->f_path, size); if (err) - pr_err("truncate failed for filename : %s err %d\n", - fp->filename, err); + pr_err("truncate failed, err %d\n", err); return err; } diff --git a/fs/ksmbd/vfs_cache.c b/fs/ksmbd/vfs_cache.c index 29c1db66bd0f..c4d59d2735f0 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/ksmbd/vfs_cache.c @@ -328,7 +328,6 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) kfree(smb_lock); } - kfree(fp->filename); if (ksmbd_stream_fd(fp)) kfree(fp->stream.name); kmem_cache_free(filp_cache, fp); @@ -497,6 +496,7 @@ struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode) list_for_each_entry(lfp, &ci->m_fp_list, node) { if (inode == file_inode(lfp->filp)) { atomic_dec(&ci->m_count); + lfp = ksmbd_fp_get(lfp); read_unlock(&ci->m_lock); return lfp; } diff --git a/fs/ksmbd/vfs_cache.h b/fs/ksmbd/vfs_cache.h index 36239ce31afd..fcb13413fa8d 100644 --- a/fs/ksmbd/vfs_cache.h +++ b/fs/ksmbd/vfs_cache.h @@ -62,7 +62,6 @@ struct ksmbd_inode { struct ksmbd_file { struct file *filp; - char *filename; u64 persistent_id; u64 volatile_id; diff --git a/fs/namei.c b/fs/namei.c index 3f1829b3ab5b..509657fdf4f5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3673,18 +3673,14 @@ static struct dentry *filename_create(int dfd, struct filename *name, { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; + bool want_dir = lookup_flags & LOOKUP_DIRECTORY; + unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; + unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; int type; int err2; int error; - bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); - /* - * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any - * other flags passed in are ignored! - */ - lookup_flags &= LOOKUP_REVAL; - - error = filename_parentat(dfd, name, lookup_flags, path, &last, &type); + error = filename_parentat(dfd, name, reval_flag, path, &last, &type); if (error) return ERR_PTR(error); @@ -3698,11 +3694,13 @@ static struct dentry *filename_create(int dfd, struct filename *name, /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* - * Do the final lookup. + * Do the final lookup. Suppress 'create' if there is a trailing + * '/', and a directory wasn't requested. */ - lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; + if (last.name[last.len] && !want_dir) + create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, lookup_flags); + dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; @@ -3716,7 +3714,7 @@ static struct dentry *filename_create(int dfd, struct filename *name, * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ - if (unlikely(!is_dir && last.name[last.len])) { + if (unlikely(!create_flags)) { error = -ENOENT; goto fail; } diff --git a/fs/namespace.c b/fs/namespace.c index a0a36bfa3aa0..afe2b64b14f1 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4058,10 +4058,22 @@ static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) if (err) { struct mount *p; - for (p = mnt; p != m; p = next_mnt(p, mnt)) { + /* + * If we had to call mnt_hold_writers() MNT_WRITE_HOLD will + * be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all + * mounts and needs to take care to include the first mount. + */ + for (p = mnt; p; p = next_mnt(p, mnt)) { /* If we had to hold writers unblock them. */ if (p->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(p); + + /* + * We're done once the first mount we changed got + * MNT_WRITE_HOLD unset. + */ + if (p == m) + break; } } return err; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 47a53b3362b6..14a72224b657 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -4,10 +4,6 @@ config NFS_FS depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC - select CRYPTO - select CRYPTO_HASH - select XXHASH - select CRYPTO_XXHASH select NFS_ACL_SUPPORT if NFS_V3_ACL help Choose Y here if you want to access files residing on other diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bac4cf1a308e..c6b263b5faf1 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -39,7 +39,7 @@ #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> -#include <linux/xxhash.h> +#include <linux/hash.h> #include "delegation.h" #include "iostat.h" @@ -350,10 +350,7 @@ out: * of directory cookies. Content is addressed by the value of the * cookie index of the first readdir entry in a page. * - * The xxhash algorithm is chosen because it is fast, and is supposed - * to result in a decent flat distribution of hashes. - * - * We then select only the first 18 bits to avoid issues with excessive + * We select only the first 18 bits to avoid issues with excessive * memory use for the page cache XArray. 18 bits should allow the caching * of 262144 pages of sequences of readdir entries. Since each page holds * 127 readdir entries for a typical 64-bit system, that works out to a @@ -363,7 +360,7 @@ static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie) { if (cookie == 0) return 0; - return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK; + return hash_64(cookie, 18); } static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, @@ -1991,16 +1988,6 @@ const struct dentry_operations nfs4_dentry_operations = { }; EXPORT_SYMBOL_GPL(nfs4_dentry_operations); -static fmode_t flags_to_mode(int flags) -{ - fmode_t res = (__force fmode_t)flags & FMODE_EXEC; - if ((flags & O_ACCMODE) != O_WRONLY) - res |= FMODE_READ; - if ((flags & O_ACCMODE) != O_RDONLY) - res |= FMODE_WRITE; - return res; -} - static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp) { return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7eb3b08d702f..b4e46b0ffa2d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1180,7 +1180,6 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } -EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 57b0497105c8..7eefa16ed381 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) return true; } +static inline fmode_t flags_to_mode(int flags) +{ + fmode_t res = (__force fmode_t)flags & FMODE_EXEC; + if ((flags & O_ACCMODE) != O_WRONLY) + res |= FMODE_READ; + if ((flags & O_ACCMODE) != O_RDONLY) + res |= FMODE_WRITE; + return res; +} + /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index ad3405c64b9e..e7b34f7e0614 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -997,7 +997,7 @@ int __init nfs4_xattr_cache_init(void) nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", sizeof(struct nfs4_xattr_cache), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT), + (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), nfs4_xattr_cache_init_once); if (nfs4_xattr_cache_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index d258933cf8c8..7b861e4f0533 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct dentry *parent = NULL; struct inode *dir; unsigned openflags = filp->f_flags; + fmode_t f_mode; struct iattr attr; int err; @@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (err) return err; + f_mode = filp->f_mode; if ((openflags & O_ACCMODE) == 3) - return nfs_open(inode, filp); + f_mode |= flags_to_mode(openflags); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); @@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) parent = dget_parent(dentry); dir = d_inode(parent); - ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp); + ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e3f5b380cefe..16106f805ffa 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -9615,6 +9615,8 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0); task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return ERR_CAST(task); status = rpc_wait_for_completion_task(task); if (status != 0) diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 5fa11e1aca4c..6f325e10056c 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -347,6 +347,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) return ERR_PTR(-ENOMEM); + task_setup_data.task = &data->task; task_setup_data.callback_data = data; data->cred = get_current_cred(); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index c08882f5867b..2c1b027774d4 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -237,6 +237,13 @@ nfsd_file_check_write_error(struct nfsd_file *nf) } static void +nfsd_file_flush(struct nfsd_file *nf) +{ + if (nf->nf_file && vfs_fsync(nf->nf_file, 1) != 0) + nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); +} + +static void nfsd_file_do_unhash(struct nfsd_file *nf) { lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); @@ -295,19 +302,15 @@ nfsd_file_put_noref(struct nfsd_file *nf) void nfsd_file_put(struct nfsd_file *nf) { - bool is_hashed; - set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (refcount_read(&nf->nf_ref) > 2 || !nf->nf_file) { + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) { + nfsd_file_flush(nf); nfsd_file_put_noref(nf); - return; + } else { + nfsd_file_put_noref(nf); + if (nf->nf_file) + nfsd_file_schedule_laundrette(); } - - filemap_flush(nf->nf_file->f_mapping); - is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0; - nfsd_file_put_noref(nf); - if (is_hashed) - nfsd_file_schedule_laundrette(); if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) nfsd_file_gc(); } @@ -328,6 +331,7 @@ nfsd_file_dispose_list(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); + nfsd_file_flush(nf); nfsd_file_put_noref(nf); } } @@ -341,6 +345,7 @@ nfsd_file_dispose_list_sync(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); + nfsd_file_flush(nf); if (!refcount_dec_and_test(&nf->nf_ref)) continue; if (nfsd_file_free(nf)) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 367551bddfc6..b5760801d377 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -249,34 +249,34 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) int w; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; if (dentry == NULL || d_really_is_negative(dentry)) - return 1; + return true; inode = d_inode(dentry); if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return 0; + return false; rqstp->rq_res.page_len = w = nfsacl_size( (resp->mask & NFS_ACL) ? resp->acl_access : NULL, (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { if (!*(rqstp->rq_next_page++)) - return 1; + return true; w -= PAGE_SIZE; } if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, resp->mask & NFS_ACL, 0)) - return 0; + return false; if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) - return 0; + return false; - return 1; + return true; } /* ACCESS */ @@ -286,17 +286,17 @@ nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->access) < 0) - return 0; + return false; break; } - return 1; + return true; } /* diff --git a/fs/pipe.c b/fs/pipe.c index 9648ac15164a..e140ea150bbb 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -804,7 +804,7 @@ struct pipe_inode_info *alloc_pipe_info(void) if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; - pipe->bufs = kvcalloc(pipe_bufs, sizeof(struct pipe_buffer), + pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { @@ -849,7 +849,7 @@ void free_pipe_info(struct pipe_inode_info *pipe) #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); - kvfree(pipe->bufs); + kfree(pipe->bufs); kfree(pipe); } @@ -1264,7 +1264,8 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) if (nr_slots < n) return -EBUSY; - bufs = kvcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT); + bufs = kcalloc(nr_slots, sizeof(*bufs), + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; @@ -1291,7 +1292,7 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) head = n; tail = 0; - kvfree(pipe->bufs); + kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 80acb6885cf9..962d32468eb4 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -759,9 +759,14 @@ static void posix_acl_fix_xattr_userns( } void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value, @@ -769,9 +774,14 @@ void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, } void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value, diff --git a/fs/stat.c b/fs/stat.c index 7f734be0e57e..5c2c94464e8b 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -348,9 +348,6 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat # define choose_32_64(a,b) b #endif -#define valid_dev(x) choose_32_64(old_valid_dev(x),true) -#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) - #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif @@ -359,7 +356,9 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; - if (!valid_dev(stat->dev) || !valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) @@ -367,7 +366,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) #endif INIT_STRUCT_STAT_PADDING(tmp); - tmp.st_dev = encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -377,7 +376,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; @@ -665,11 +664,13 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); - tmp.st_dev = old_encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -679,7 +680,7 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = old_encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 42dcf96881b6..a12ac0356c69 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -703,19 +703,6 @@ int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) ktype = get_ktype(kobj); if (ktype) { - struct attribute **kattr; - - /* - * Change owner of the default attributes associated with the - * ktype of @kobj. - */ - for (kattr = ktype->default_attrs; kattr && *kattr; kattr++) { - error = sysfs_file_change_owner(kobj, (*kattr)->name, - kuid, kgid); - if (error) - return error; - } - /* * Change owner of the default groups associated with the * ktype of @kobj. diff --git a/fs/xattr.c b/fs/xattr.c index 5c8c5175b385..998045165916 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -569,7 +569,8 @@ setxattr(struct user_namespace *mnt_userns, struct dentry *d, } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size); + posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d), + kvalue, size); } error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags); @@ -667,7 +668,8 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d, if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error); + posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d), + kvalue, error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index e1afb9e503e1..bf4e60871068 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -406,7 +406,7 @@ xfs_buf_alloc_pages( STATIC int _xfs_buf_map_pages( struct xfs_buf *bp, - uint flags) + xfs_buf_flags_t flags) { ASSERT(bp->b_flags & _XBF_PAGES); if (bp->b_page_count == 1) { @@ -868,7 +868,7 @@ xfs_buf_read_uncached( struct xfs_buftarg *target, xfs_daddr_t daddr, size_t numblks, - int flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { @@ -903,7 +903,7 @@ int xfs_buf_get_uncached( struct xfs_buftarg *target, size_t numblks, - int flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp) { int error; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index edcb6254fa6a..1ee3056ff9cf 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -22,28 +22,28 @@ struct xfs_buf; #define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL)) -#define XBF_READ (1 << 0) /* buffer intended for reading from device */ -#define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ -#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ -#define XBF_NO_IOACCT (1 << 3) /* bypass I/O accounting (non-LRU bufs) */ -#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ -#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ -#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ -#define XBF_WRITE_FAIL (1 << 7) /* async writes have failed on this buffer */ +#define XBF_READ (1u << 0) /* buffer intended for reading from device */ +#define XBF_WRITE (1u << 1) /* buffer intended for writing to device */ +#define XBF_READ_AHEAD (1u << 2) /* asynchronous read-ahead */ +#define XBF_NO_IOACCT (1u << 3) /* bypass I/O accounting (non-LRU bufs) */ +#define XBF_ASYNC (1u << 4) /* initiator will not wait for completion */ +#define XBF_DONE (1u << 5) /* all pages in the buffer uptodate */ +#define XBF_STALE (1u << 6) /* buffer has been staled, do not find it */ +#define XBF_WRITE_FAIL (1u << 7) /* async writes have failed on this buffer */ /* buffer type flags for write callbacks */ -#define _XBF_INODES (1 << 16)/* inode buffer */ -#define _XBF_DQUOTS (1 << 17)/* dquot buffer */ -#define _XBF_LOGRECOVERY (1 << 18)/* log recovery buffer */ +#define _XBF_INODES (1u << 16)/* inode buffer */ +#define _XBF_DQUOTS (1u << 17)/* dquot buffer */ +#define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */ /* flags used only internally */ -#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ -#define _XBF_KMEM (1 << 21)/* backed by heap memory */ -#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ +#define _XBF_PAGES (1u << 20)/* backed by refcounted pages */ +#define _XBF_KMEM (1u << 21)/* backed by heap memory */ +#define _XBF_DELWRI_Q (1u << 22)/* buffer on a delwri queue */ /* flags used only as arguments to access routines */ -#define XBF_TRYLOCK (1 << 30)/* lock requested, but do not wait */ -#define XBF_UNMAPPED (1 << 31)/* do not map the buffer */ +#define XBF_TRYLOCK (1u << 30)/* lock requested, but do not wait */ +#define XBF_UNMAPPED (1u << 31)/* do not map the buffer */ typedef unsigned int xfs_buf_flags_t; @@ -58,7 +58,7 @@ typedef unsigned int xfs_buf_flags_t; { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ { _XBF_INODES, "INODES" }, \ { _XBF_DQUOTS, "DQUOTS" }, \ - { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ + { _XBF_LOGRECOVERY, "LOG_RECOVERY" }, \ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ @@ -247,11 +247,11 @@ xfs_buf_readahead( return xfs_buf_readahead_map(target, &map, 1, ops); } -int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int flags, - struct xfs_buf **bpp); +int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, + xfs_buf_flags_t flags, struct xfs_buf **bpp); int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, - size_t numblks, int flags, struct xfs_buf **bpp, - const struct xfs_buf_ops *ops); + size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp, + const struct xfs_buf_ops *ops); int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags); void xfs_buf_hold(struct xfs_buf *bp); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 9de6205fe134..39ae53efb3ab 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2594,14 +2594,13 @@ xfs_ifree_cluster( } /* - * This is called to return an inode to the inode free list. - * The inode should already be truncated to 0 length and have - * no pages associated with it. This routine also assumes that - * the inode is already a part of the transaction. + * This is called to return an inode to the inode free list. The inode should + * already be truncated to 0 length and have no pages associated with it. This + * routine also assumes that the inode is already a part of the transaction. * - * The on-disk copy of the inode will have been added to the list - * of unlinked inodes in the AGI. We need to remove the inode from - * that list atomically with respect to freeing it here. + * The on-disk copy of the inode will have been added to the list of unlinked + * inodes in the AGI. We need to remove the inode from that list atomically with + * respect to freeing it here. */ int xfs_ifree( @@ -2623,13 +2622,16 @@ xfs_ifree( pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); /* - * Pull the on-disk inode from the AGI unlinked list. + * Free the inode first so that we guarantee that the AGI lock is going + * to be taken before we remove the inode from the unlinked list. This + * makes the AGI lock -> unlinked list modification order the same as + * used in O_TMPFILE creation. */ - error = xfs_iunlink_remove(tp, pag, ip); + error = xfs_difree(tp, pag, ip->i_ino, &xic); if (error) - goto out; + return error; - error = xfs_difree(tp, pag, ip->i_ino, &xic); + error = xfs_iunlink_remove(tp, pag, ip); if (error) goto out; diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index de177842b951..0c82673238f4 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -175,7 +175,7 @@ xfs_trans_get_buf( struct xfs_buftarg *target, xfs_daddr_t blkno, int numblks, - uint flags, + xfs_buf_flags_t flags, struct xfs_buf **bpp) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 3614c7834007..e20e7c841489 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -35,6 +35,17 @@ static inline int zonefs_zone_mgmt(struct inode *inode, lockdep_assert_held(&zi->i_truncate_mutex); + /* + * With ZNS drives, closing an explicitly open zone that has not been + * written will change the zone state to "closed", that is, the zone + * will remain active. Since this can then cause failure of explicit + * open operation on other zones if the drive active zone resources + * are exceeded, make sure that the zone does not remain active by + * resetting it. + */ + if (op == REQ_OP_ZONE_CLOSE && !zi->i_wpoffset) + op = REQ_OP_ZONE_RESET; + trace_zonefs_zone_mgmt(inode, op); ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector, zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS); @@ -1142,6 +1153,7 @@ static struct inode *zonefs_alloc_inode(struct super_block *sb) inode_init_once(&zi->i_vnode); mutex_init(&zi->i_truncate_mutex); zi->i_wr_refcnt = 0; + zi->i_flags = 0; return &zi->i_vnode; } @@ -1293,12 +1305,13 @@ static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode, inc_nlink(parent); } -static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, - enum zonefs_ztype type) +static int zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, + enum zonefs_ztype type) { struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); struct zonefs_inode_info *zi = ZONEFS_I(inode); + int ret = 0; inode->i_ino = zone->start >> sbi->s_zone_sectors_shift; inode->i_mode = S_IFREG | sbi->s_perm; @@ -1323,6 +1336,22 @@ static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone, sb->s_maxbytes = max(zi->i_max_size, sb->s_maxbytes); sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits; sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits; + + /* + * For sequential zones, make sure that any open zone is closed first + * to ensure that the initial number of open zones is 0, in sync with + * the open zone accounting done when the mount option + * ZONEFS_MNTOPT_EXPLICIT_OPEN is used. + */ + if (type == ZONEFS_ZTYPE_SEQ && + (zone->cond == BLK_ZONE_COND_IMP_OPEN || + zone->cond == BLK_ZONE_COND_EXP_OPEN)) { + mutex_lock(&zi->i_truncate_mutex); + ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE); + mutex_unlock(&zi->i_truncate_mutex); + } + + return ret; } static struct dentry *zonefs_create_inode(struct dentry *parent, @@ -1332,6 +1361,7 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, struct inode *dir = d_inode(parent); struct dentry *dentry; struct inode *inode; + int ret; dentry = d_alloc_name(parent, name); if (!dentry) @@ -1342,10 +1372,16 @@ static struct dentry *zonefs_create_inode(struct dentry *parent, goto dput; inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime; - if (zone) - zonefs_init_file_inode(inode, zone, type); - else + if (zone) { + ret = zonefs_init_file_inode(inode, zone, type); + if (ret) { + iput(inode); + goto dput; + } + } else { zonefs_init_dir_inode(dir, inode, type); + } + d_add(dentry, inode); dir->i_size++; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3f7f01f03869..c4b78c21d793 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -509,7 +509,6 @@ extern int unregister_acpi_notifier(struct notifier_block *); * External Functions */ -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device); struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle); acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index edb0e2a602a8..ba1f860af38b 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -21,6 +21,12 @@ #include <linux/panic.h> #include <linux/printk.h> +struct warn_args; +struct pt_regs; + +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args); + #ifdef CONFIG_BUG #ifdef CONFIG_GENERIC_BUG @@ -110,11 +116,6 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); #endif /* used internally by panic.c */ -struct warn_args; -struct pt_regs; - -void __warn(const char *file, int line, void *caller, unsigned taint, - struct pt_regs *regs, struct warn_args *args); #ifndef WARN_ON #define WARN_ON(condition) ({ \ diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c08758b6b364..c05d2ce9b6cd 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -269,6 +269,7 @@ bool hv_isolation_type_snp(void); u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); +void hv_setup_dma_ops(struct device *dev, bool coherent); void *hv_map_memory(void *addr, unsigned long size); void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index fd7feb5c7894..eee6f7763a39 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ - if (_sz == PMD_SIZE) \ - tlb_flush_pmd_range(tlb, address, _sz); \ - else if (_sz == PUD_SIZE) \ + if (_sz >= P4D_SIZE) \ + tlb_flush_p4d_range(tlb, address, _sz); \ + else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ + else if (_sz >= PMD_SIZE) \ + tlb_flush_pmd_range(tlb, address, _sz); \ + else \ + tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 8fc637379899..df30f11b4a46 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -143,7 +143,7 @@ static inline void put_unaligned_be48(const u64 val, void *p) static inline u64 __get_unaligned_be48(const u8 *p) { - return (u64)p[0] << 40 | (u64)p[1] << 32 | p[2] << 24 | + return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } diff --git a/include/dt-bindings/clock/microchip,mpfs-clock.h b/include/dt-bindings/clock/microchip,mpfs-clock.h index 73f2a9324857..4048669bf756 100644 --- a/include/dt-bindings/clock/microchip,mpfs-clock.h +++ b/include/dt-bindings/clock/microchip,mpfs-clock.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* * Daire McNamara,<daire.mcnamara@microchip.com> - * Copyright (C) 2020 Microchip Technology Inc. All rights reserved. + * Copyright (C) 2020-2022 Microchip Technology Inc. All rights reserved. */ #ifndef _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ @@ -42,4 +42,7 @@ #define CLK_ATHENA 31 #define CLK_CFM 32 +#define CLK_RTCREF 33 +#define CLK_MSSPLL 34 + #endif /* _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ */ diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 51c19381108c..cd6d8f260eab 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -76,8 +76,6 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -bool kvm_timer_is_pending(struct kvm_vcpu *vcpu); - u64 kvm_phys_timer_read(void); void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu); diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index 0e2509d27910..1188f116cf4e 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -40,4 +40,12 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu, vcpu_set_reg(vcpu, 3, a3); } +struct kvm_one_reg; + +void kvm_arm_init_hypercalls(struct kvm *kvm); +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); + #endif diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 20193416d214..c0b868ce6a8f 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -20,13 +20,19 @@ struct kvm_pmc { struct perf_event *perf_event; }; +struct kvm_pmu_events { + u32 events_host; + u32 events_guest; +}; + struct kvm_pmu { - int irq_num; + struct irq_work overflow_work; + struct kvm_pmu_events events; struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS]; DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS); + int irq_num; bool created; bool irq_level; - struct irq_work overflow_work; }; struct arm_pmu_entry { @@ -66,6 +72,25 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); + +struct kvm_pmu_events *kvm_get_pmu_events(void); +void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu); +void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); + +#define kvm_vcpu_has_pmu(vcpu) \ + (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) + +/* + * Updates the vcpu's view of the pmu events for this cpu. + * Must be called before every vcpu run after disabling interrupts, to ensure + * that an interrupt cannot fire and update the structure. + */ +#define kvm_pmu_update_vcpu_events(vcpu) \ + do { \ + if (!has_vhe() && kvm_vcpu_has_pmu(vcpu)) \ + vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ + } while (0) + #else struct kvm_pmu { }; @@ -127,6 +152,11 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) return 0; } +#define kvm_vcpu_has_pmu(vcpu) ({ false; }) +static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {} +static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} +static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} + #endif #endif diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index 68b96c3826c3..6e55b9283789 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -39,11 +39,4 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu) int kvm_psci_call(struct kvm_vcpu *vcpu); -struct kvm_one_reg; - -int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); - #endif /* __KVM_ARM_PSCI_H__ */ diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index bb30a6803d9f..2d8f2e90edc2 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -231,6 +231,9 @@ struct vgic_dist { /* Implementation revision as reported in the GICD_IIDR */ u32 implementation_rev; +#define KVM_VGIC_IMP_REV_2 2 /* GICv2 restorable groups */ +#define KVM_VGIC_IMP_REV_3 3 /* GICv3 GICR_CTLR.{IW,CES,RWP} */ +#define KVM_VGIC_IMP_REV_LATEST KVM_VGIC_IMP_REV_3 /* Userspace can write to GICv2 IGROUPR */ bool v2_groups_user_writable; @@ -344,11 +347,12 @@ struct vgic_cpu { struct vgic_io_device rd_iodev; struct vgic_redist_region *rdreg; u32 rdreg_index; + atomic_t syncr_busy; /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; - - bool lpis_enabled; + /* GICR_CTLR.{ENABLE_LPIS,RWP} */ + atomic_t ctlr; /* Cache guest priority bits */ u32 num_pri_bits; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c1fc4af47f69..3a9d2d7cc6b7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -570,9 +570,11 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +/* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) { - return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; + return prog->type == BPF_PROG_TYPE_EXT ? + prog->aux->dst_prog->type : prog->type; } #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9cf51e41e697..54dc2f9a2d56 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -167,7 +167,7 @@ static inline int suspend_disable_secondary_cpus(void) { return 0; } static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ -void cpu_startup_entry(enum cpuhp_state state); +void __noreturn cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h deleted file mode 100644 index 19fa0b5ae5ec..000000000000 --- a/include/linux/dma-buf-map.h +++ /dev/null @@ -1,266 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Pointer to dma-buf-mapped memory, plus helpers. - */ - -#ifndef __DMA_BUF_MAP_H__ -#define __DMA_BUF_MAP_H__ - -#include <linux/io.h> -#include <linux/string.h> - -/** - * DOC: overview - * - * Calling dma-buf's vmap operation returns a pointer to the buffer's memory. - * Depending on the location of the buffer, users may have to access it with - * I/O operations or memory load/store operations. For example, copying to - * system memory could be done with memcpy(), copying to I/O memory would be - * done with memcpy_toio(). - * - * .. code-block:: c - * - * void *vaddr = ...; // pointer to system memory - * memcpy(vaddr, src, len); - * - * void *vaddr_iomem = ...; // pointer to I/O memory - * memcpy_toio(vaddr, _iomem, src, len); - * - * When using dma-buf's vmap operation, the returned pointer is encoded as - * :c:type:`struct dma_buf_map <dma_buf_map>`. - * :c:type:`struct dma_buf_map <dma_buf_map>` stores the buffer's address in - * system or I/O memory and a flag that signals the required method of - * accessing the buffer. Use the returned instance and the helper functions - * to access the buffer's memory in the correct way. - * - * The type :c:type:`struct dma_buf_map <dma_buf_map>` and its helpers are - * actually independent from the dma-buf infrastructure. When sharing buffers - * among devices, drivers have to know the location of the memory to access - * the buffers in a safe way. :c:type:`struct dma_buf_map <dma_buf_map>` - * solves this problem for dma-buf and its users. If other drivers or - * sub-systems require similar functionality, the type could be generalized - * and moved to a more prominent header file. - * - * Open-coding access to :c:type:`struct dma_buf_map <dma_buf_map>` is - * considered bad style. Rather then accessing its fields directly, use one - * of the provided helper functions, or implement your own. For example, - * instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be initialized - * statically with DMA_BUF_MAP_INIT_VADDR(), or at runtime with - * dma_buf_map_set_vaddr(). These helpers will set an address in system memory. - * - * .. code-block:: c - * - * struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf); - * - * dma_buf_map_set_vaddr(&map, 0xdeadbeaf); - * - * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem(). - * - * .. code-block:: c - * - * dma_buf_map_set_vaddr_iomem(&map, 0xdeadbeaf); - * - * Instances of struct dma_buf_map do not have to be cleaned up, but - * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings - * always refer to system memory. - * - * .. code-block:: c - * - * dma_buf_map_clear(&map); - * - * Test if a mapping is valid with either dma_buf_map_is_set() or - * dma_buf_map_is_null(). - * - * .. code-block:: c - * - * if (dma_buf_map_is_set(&map) != dma_buf_map_is_null(&map)) - * // always true - * - * Instances of :c:type:`struct dma_buf_map <dma_buf_map>` can be compared - * for equality with dma_buf_map_is_equal(). Mappings the point to different - * memory spaces, system or I/O, are never equal. That's even true if both - * spaces are located in the same address space, both mappings contain the - * same address value, or both mappings refer to NULL. - * - * .. code-block:: c - * - * struct dma_buf_map sys_map; // refers to system memory - * struct dma_buf_map io_map; // refers to I/O memory - * - * if (dma_buf_map_is_equal(&sys_map, &io_map)) - * // always false - * - * A set up instance of struct dma_buf_map can be used to access or manipulate - * the buffer memory. Depending on the location of the memory, the provided - * helpers will pick the correct operations. Data can be copied into the memory - * with dma_buf_map_memcpy_to(). The address can be manipulated with - * dma_buf_map_incr(). - * - * .. code-block:: c - * - * const void *src = ...; // source buffer - * size_t len = ...; // length of src - * - * dma_buf_map_memcpy_to(&map, src, len); - * dma_buf_map_incr(&map, len); // go to first byte after the memcpy - */ - -/** - * struct dma_buf_map - Pointer to vmap'ed dma-buf memory. - * @vaddr_iomem: The buffer's address if in I/O memory - * @vaddr: The buffer's address if in system memory - * @is_iomem: True if the dma-buf memory is located in I/O - * memory, or false otherwise. - */ -struct dma_buf_map { - union { - void __iomem *vaddr_iomem; - void *vaddr; - }; - bool is_iomem; -}; - -/** - * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory - * @vaddr_: A system-memory address - */ -#define DMA_BUF_MAP_INIT_VADDR(vaddr_) \ - { \ - .vaddr = (vaddr_), \ - .is_iomem = false, \ - } - -/** - * dma_buf_map_set_vaddr - Sets a dma-buf mapping structure to an address in system memory - * @map: The dma-buf mapping structure - * @vaddr: A system-memory address - * - * Sets the address and clears the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr) -{ - map->vaddr = vaddr; - map->is_iomem = false; -} - -/** - * dma_buf_map_set_vaddr_iomem - Sets a dma-buf mapping structure to an address in I/O memory - * @map: The dma-buf mapping structure - * @vaddr_iomem: An I/O-memory address - * - * Sets the address and the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr_iomem(struct dma_buf_map *map, - void __iomem *vaddr_iomem) -{ - map->vaddr_iomem = vaddr_iomem; - map->is_iomem = true; -} - -/** - * dma_buf_map_is_equal - Compares two dma-buf mapping structures for equality - * @lhs: The dma-buf mapping structure - * @rhs: A dma-buf mapping structure to compare with - * - * Two dma-buf mapping structures are equal if they both refer to the same type of memory - * and to the same address within that memory. - * - * Returns: - * True is both structures are equal, or false otherwise. - */ -static inline bool dma_buf_map_is_equal(const struct dma_buf_map *lhs, - const struct dma_buf_map *rhs) -{ - if (lhs->is_iomem != rhs->is_iomem) - return false; - else if (lhs->is_iomem) - return lhs->vaddr_iomem == rhs->vaddr_iomem; - else - return lhs->vaddr == rhs->vaddr; -} - -/** - * dma_buf_map_is_null - Tests for a dma-buf mapping to be NULL - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping is NULL. - * - * Returns: - * True if the mapping is NULL, or false otherwise. - */ -static inline bool dma_buf_map_is_null(const struct dma_buf_map *map) -{ - if (map->is_iomem) - return !map->vaddr_iomem; - return !map->vaddr; -} - -/** - * dma_buf_map_is_set - Tests is the dma-buf mapping has been set - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping has been set. - * - * Returns: - * True if the mapping is been set, or false otherwise. - */ -static inline bool dma_buf_map_is_set(const struct dma_buf_map *map) -{ - return !dma_buf_map_is_null(map); -} - -/** - * dma_buf_map_clear - Clears a dma-buf mapping structure - * @map: The dma-buf mapping structure - * - * Clears all fields to zero; including struct dma_buf_map.is_iomem. So - * mapping structures that were set to point to I/O memory are reset for - * system memory. Pointers are cleared to NULL. This is the default. - */ -static inline void dma_buf_map_clear(struct dma_buf_map *map) -{ - if (map->is_iomem) { - map->vaddr_iomem = NULL; - map->is_iomem = false; - } else { - map->vaddr = NULL; - } -} - -/** - * dma_buf_map_memcpy_to - Memcpy into dma-buf mapping - * @dst: The dma-buf mapping structure - * @src: The source buffer - * @len: The number of byte in src - * - * Copies data into a dma-buf mapping. The source buffer is in system - * memory. Depending on the buffer's location, the helper picks the correct - * method of accessing the memory. - */ -static inline void dma_buf_map_memcpy_to(struct dma_buf_map *dst, const void *src, size_t len) -{ - if (dst->is_iomem) - memcpy_toio(dst->vaddr_iomem, src, len); - else - memcpy(dst->vaddr, src, len); -} - -/** - * dma_buf_map_incr - Increments the address stored in a dma-buf mapping - * @map: The dma-buf mapping structure - * @incr: The number of bytes to increment - * - * Increments the address stored in a dma-buf mapping. Depending on the - * buffer's location, the correct value will be updated. - */ -static inline void dma_buf_map_incr(struct dma_buf_map *map, size_t incr) -{ - if (map->is_iomem) - map->vaddr_iomem += incr; - else - map->vaddr += incr; -} - -#endif /* __DMA_BUF_MAP_H__ */ diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index fec374f69e12..ec7f25def392 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -61,6 +61,21 @@ to_dma_fence_array(struct dma_fence *fence) return container_of(fence, struct dma_fence_array, base); } +/** + * dma_fence_array_for_each - iterate over all fences in array + * @fence: current fence + * @index: index into the array + * @head: potential dma_fence_array object + * + * Test if @array is a dma_fence_array object and if yes iterate over all fences + * in the array. If not just iterate over the fence in @array itself. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). + */ +#define dma_fence_array_for_each(fence, index, head) \ + for (index = 0, fence = dma_fence_array_first(head); fence; \ + ++(index), fence = dma_fence_array_next(head, index)) + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, @@ -68,4 +83,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, bool dma_fence_match_context(struct dma_fence *fence, u64 context); +struct dma_fence *dma_fence_array_first(struct dma_fence *head); +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index); + #endif /* __LINUX_DMA_FENCE_ARRAY_H */ diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 10d51bcdf7b7..4bdf0b96da28 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -112,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain) * * Iterate over all fences in the chain. We keep a reference to the current * fence while inside the loop which must be dropped when breaking out. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_chain_for_each(iter, head) \ for (iter = dma_fence_get(head); iter; \ diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h new file mode 100644 index 000000000000..77e335a1bcac --- /dev/null +++ b/include/linux/dma-fence-unwrap.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#ifndef __LINUX_DMA_FENCE_UNWRAP_H +#define __LINUX_DMA_FENCE_UNWRAP_H + +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-array.h> + +/** + * struct dma_fence_unwrap - cursor into the container structure + * + * Should be used with dma_fence_unwrap_for_each() iterator macro. + */ +struct dma_fence_unwrap { + /** + * @chain: potential dma_fence_chain, but can be other fence as well + */ + struct dma_fence *chain; + /** + * @array: potential dma_fence_array, but can be other fence as well + */ + struct dma_fence *array; + /** + * @index: last returned index if @array is really a dma_fence_array + */ + unsigned int index; +}; + +/* Internal helper to start new array iteration, don't use directly */ +static inline struct dma_fence * +__dma_fence_unwrap_array(struct dma_fence_unwrap * cursor) +{ + cursor->array = dma_fence_chain_contained(cursor->chain); + cursor->index = 0; + return dma_fence_array_first(cursor->array); +} + +/** + * dma_fence_unwrap_first - return the first fence from fence containers + * @head: the entrypoint into the containers + * @cursor: current position inside the containers + * + * Unwraps potential dma_fence_chain/dma_fence_array containers and return the + * first fence. + */ +static inline struct dma_fence * +dma_fence_unwrap_first(struct dma_fence *head, struct dma_fence_unwrap *cursor) +{ + cursor->chain = dma_fence_get(head); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_next - return the next fence from a fence containers + * @cursor: current position inside the containers + * + * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return + * the next fence from them. + */ +static inline struct dma_fence * +dma_fence_unwrap_next(struct dma_fence_unwrap *cursor) +{ + struct dma_fence *tmp; + + ++cursor->index; + tmp = dma_fence_array_next(cursor->array, cursor->index); + if (tmp) + return tmp; + + cursor->chain = dma_fence_chain_walk(cursor->chain); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_for_each - iterate over all fences in containers + * @fence: current fence + * @cursor: current position inside the containers + * @head: starting point for the iterator + * + * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all + * potential fences in them. If @head is just a normal fence only that one is + * returned. + */ +#define dma_fence_unwrap_for_each(fence, cursor, head) \ + for (fence = dma_fence_unwrap_first(head, cursor); fence; \ + fence = dma_fence_unwrap_next(cursor)) + +#endif diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6727fb0db619..e25539072463 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -573,7 +573,6 @@ int fscache_write(struct netfs_cache_resources *cres, /** * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages - * @cookie: The cookie representing the cache object * @mapping: The netfs inode to use as the source * @start: The start position in @mapping * @len: The amount of data to unlock @@ -582,8 +581,7 @@ int fscache_write(struct netfs_cache_resources *cres, * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's * waiting. */ -static inline void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, +static inline void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) { diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 761f8f1885c7..3e3d36fc2109 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -613,9 +613,11 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, +struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, true) #else @@ -627,8 +629,10 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ alloc_pages(gfp_mask, order) +#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ + folio_alloc(gfp, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c3aa8b330e1c..e71f6e1bfafe 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -688,7 +688,7 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label); #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ @@ -705,6 +705,12 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, return -ENXIO; } +static inline struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, + char *label) +{ + return ERR_PTR(-ENOSYS); +} + #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..874aabd270c9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -222,6 +222,15 @@ struct gpio_irq_chip { bool per_parent_data; /** + * @initialized: + * + * Flag to track GPIO chip irq member's initialization. + * This flag will make sure GPIO chip irq members are not used + * before they are initialized. + */ + bool initialized; + + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when * a particular driver wants to clear IRQ related registers diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 53c1b6082a4c..ac2a1d758a80 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -169,6 +169,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_huge_page(struct page *page, struct list_head *list); int get_hwpoison_huge_page(struct page *page, bool *hugetlb); +int get_huge_page_for_hwpoison(unsigned long pfn, int flags); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -378,6 +379,11 @@ static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return 0; } +static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} + static inline void putback_active_hugepage(struct page *page) { } diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 12d91f0dedf9..728691365464 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -127,6 +127,8 @@ #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) +#define GICR_CTLR_CES (1UL << 1) +#define GICR_CTLR_IR (1UL << 2) #define GICR_CTLR_RWP (1UL << 3) #define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 08ba5995aa8b..fe6efb24d151 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -64,15 +64,6 @@ ) /** - * lower_48_bits() - return bits 0-47 of a number - * @n: the number we're accessing - */ -static inline u64 lower_48_bits(u64 n) -{ - return n & ((1ull << 48) - 1); -} - -/** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing * @@ -294,7 +285,7 @@ static inline char *hex_byte_pack_upper(char *buf, u8 byte) return buf; } -extern int hex_to_bin(char ch); +extern int hex_to_bin(unsigned char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); extern char *bin2hex(char *dst, const void *src, size_t count); diff --git a/include/linux/kfence.h b/include/linux/kfence.h index f49e64222628..726857a4b680 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -204,6 +204,22 @@ static __always_inline __must_check bool kfence_free(void *addr) */ bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +/** + * __kfence_obj_info() - fill kmem_obj_info struct + * @kpp: kmem_obj_info to be filled + * @object: the object + * + * Return: + * * false - not a KFENCE object + * * true - a KFENCE object, filled @kpp + * + * Copies information to @kpp for KFENCE objects. + */ +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +#endif + #else /* CONFIG_KFENCE */ static inline bool is_kfence_address(const void *addr) { return false; } @@ -221,6 +237,14 @@ static inline bool __must_check kfence_handle_page_fault(unsigned long addr, boo return false; } +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +static inline bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + return false; +} +#endif + #endif #endif /* _LINUX_KFENCE_H */ diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c7b47399b36a..57fb972fea05 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -120,7 +120,6 @@ extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; - struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f94f72bbd2d3..883e86ec8e8c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -315,7 +315,10 @@ struct kvm_vcpu { int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index in kvm->vcpus array */ - int srcu_idx; + int ____srcu_idx; /* Don't use this directly. You've been warned. */ +#ifdef CONFIG_PROVE_RCU + int srcu_depth; +#endif int mode; u64 requests; unsigned long guest_debug; @@ -842,6 +845,25 @@ static inline void kvm_vm_bugged(struct kvm *kvm) unlikely(__ret); \ }) +static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(vcpu->srcu_depth++, + "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); +#endif + vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) +{ + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); + +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(--vcpu->srcu_depth, + "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); +#endif +} + static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); @@ -2199,6 +2221,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end); +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); + #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 6d635e8306d6..975e33b793a7 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) -# define local_lock_acquire(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_release(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_debug_init(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a68dce3873fc..89b14729d59f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1012,6 +1012,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); +void mem_cgroup_flush_stats_delayed(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1455,6 +1456,10 @@ static inline void mem_cgroup_flush_stats(void) { } +static inline void mem_cgroup_flush_stats_delayed(void) +{ +} + static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { diff --git a/include/linux/mm.h b/include/linux/mm.h index e34edb775334..9f44254af8ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3197,6 +3197,14 @@ extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); +#ifdef CONFIG_MEMORY_FAILURE +extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); +#else +static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} +#endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 71101d1ec825..de5c64bbdb72 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -175,7 +175,7 @@ void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); -int mmc_hw_reset(struct mmc_host *host); +int mmc_hw_reset(struct mmc_card *card); int mmc_sw_reset(struct mmc_host *host); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 962b14d403e8..46ffab808f03 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1397,13 +1397,16 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms) static inline struct mem_section *__nr_to_section(unsigned long nr) { + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + #ifdef CONFIG_SPARSEMEM_EXTREME - if (!mem_section) + if (!mem_section || !mem_section[root]) return NULL; #endif - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; + return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 151607e9d64a..955aee14b0f7 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -389,10 +389,8 @@ struct mtd_info { /* List of partitions attached to this MTD device */ struct list_head partitions; - union { - struct mtd_part part; - struct mtd_master master; - }; + struct mtd_part part; + struct mtd_master master; }; static inline struct mtd_info *mtd_get_master(struct mtd_info *mtd) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59e27a2b7bf0..b1fbe21650bb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -199,10 +199,10 @@ struct net_device_stats { * Try to fit them in a single cache line, for dev_get_stats() sake. */ struct net_device_core_stats { - local_t rx_dropped; - local_t tx_dropped; - local_t rx_nohandler; -} __aligned(4 * sizeof(local_t)); + unsigned long rx_dropped; + unsigned long tx_dropped; + unsigned long rx_nohandler; +} __aligned(4 * sizeof(unsigned long)); #include <linux/cache.h> #include <linux/skbuff.h> @@ -3843,15 +3843,15 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev); +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev); -static inline struct net_device_core_stats *dev_core_stats(struct net_device *dev) +static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); if (likely(p)) - return this_cpu_ptr(p); + return p; return netdev_core_stats_alloc(dev); } @@ -3859,14 +3859,11 @@ static inline struct net_device_core_stats *dev_core_stats(struct net_device *de #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ - struct net_device_core_stats *p; \ + struct net_device_core_stats __percpu *p; \ \ - preempt_disable(); \ p = dev_core_stats(dev); \ - \ if (p) \ - local_inc(&p->FIELD); \ - preempt_enable(); \ + this_cpu_inc(p->FIELD); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 49ba486aea5f..2863e5a69c6a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1694,6 +1694,7 @@ struct nfs_unlinkdata { struct nfs_renamedata { struct nfs_renameargs args; struct nfs_renameres res; + struct rpc_task task; const struct cred *cred; struct inode *old_dir; struct dentry *old_dentry; diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 060e8d203181..1766e1de6956 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -34,15 +34,19 @@ posix_acl_xattr_count(size_t size) #ifdef CONFIG_FS_POSIX_ACL void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); #else static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..a8911b1f35aa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1443,6 +1443,7 @@ struct task_struct { int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; + struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a80356e9dc69..1ad1f4bfa025 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -136,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU +#ifndef arch_get_mmap_end +#define arch_get_mmap_end(addr) (TASK_SIZE) +#endif + +#ifndef arch_get_mmap_base +#define arch_get_mmap_base(addr, base) (base) +#endif + extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3e56a9751c06..df53bed9d71f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -180,13 +180,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -196,6 +196,14 @@ extern long __static_call_return0(void); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -217,12 +225,12 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; } }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) #define static_call_cond(name) (void)__static_call(name) @@ -248,10 +262,7 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } -static inline long __static_call_return0(void) -{ - return 0; -} +extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ @@ -281,11 +292,14 @@ static inline long __static_call_return0(void) .func = _func_init, \ } +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + #define DEFINE_STATIC_CALL_NULL(name, _func) \ - DECLARE_STATIC_CALL(name, _func); \ - struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = NULL, \ - } + __DEFINE_STATIC_CALL(name, _func, NULL) + +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) static inline void __static_call_nop(void) { } @@ -327,10 +341,4 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ -#define DEFINE_STATIC_CALL(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, _func) - -#define DEFINE_STATIC_CALL_RET0(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, __static_call_return0) - #endif /* _LINUX_STATIC_CALL_H */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a5dda4987e8b..217711fc9cac 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -395,6 +395,7 @@ struct svc_deferred_req { size_t addrlen; struct sockaddr_storage daddr; /* where reply must come from */ size_t daddrlen; + void *xprt_ctxt; struct cache_deferred_req handle; size_t xprt_hlen; int argslen; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 45a9530d3839..522bbf937957 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -144,7 +144,7 @@ struct rpc_xprt_ops { unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - void (*prepare_request)(struct rpc_rqst *req); + int (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*wait_for_reply_request)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -358,10 +358,9 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); -void xprt_request_enqueue_receive(struct rpc_task *task); +int xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_request_dequeue_xprt(struct rpc_task *task); bool xprt_request_need_retransmit(struct rpc_task *task); diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index a4b1af581f69..248f4ac95642 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -59,6 +59,15 @@ struct crc64_pi_tuple { __u8 ref_tag[6]; }; +/** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); diff --git a/include/linux/timex.h b/include/linux/timex.h index 059b18eb1f1f..5745c90c8800 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -75,7 +75,7 @@ * By default we use get_cycles() for this purpose, but individual * architectures may override this in their asm/timex.h header file. */ -#define random_get_entropy() get_cycles() +#define random_get_entropy() ((unsigned long)get_cycles()) #endif /* diff --git a/include/linux/usb/pd_bdo.h b/include/linux/usb/pd_bdo.h index 033fe3e17141..7c25b88d79f9 100644 --- a/include/linux/usb/pd_bdo.h +++ b/include/linux/usb/pd_bdo.h @@ -15,7 +15,7 @@ #define BDO_MODE_CARRIER2 (5 << 28) #define BDO_MODE_CARRIER3 (6 << 28) #define BDO_MODE_EYE (7 << 28) -#define BDO_MODE_TESTDATA (8 << 28) +#define BDO_MODE_TESTDATA (8U << 28) #define BDO_MODE_MASK(mode) ((mode) & 0xf0000000) diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 74a4a0f17b28..48f2dd3c568c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -133,6 +133,8 @@ struct vfio_pci_core_device { struct mutex ioeventfds_lock; struct list_head ioeventfds_list; struct vfio_pci_vf_token *vf_token; + struct list_head sriov_pfs_item; + struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct mutex vma_lock; struct list_head vma_list; diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index dafdc7f48c01..b341dd62aa4d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -23,8 +23,6 @@ struct virtio_shm_region { * any of @get/@set, @get_status/@set_status, or @get_features/ * @finalize_features are NOT safe to be called from an atomic * context. - * @enable_cbs: enable the callbacks - * vdev: the virtio_device * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field @@ -78,7 +76,6 @@ struct virtio_shm_region { */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { - void (*enable_cbs)(struct virtio_device *vdev); void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); void (*set)(struct virtio_device *vdev, unsigned offset, @@ -233,9 +230,6 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - if (dev->config->enable_cbs) - dev->config->enable_cbs(dev); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3b1df7da402d..b159c2789961 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -26,7 +26,7 @@ struct notifier_block; /* in notifier.h */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -153,7 +153,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); diff --git a/include/memory/renesas-rpc-if.h b/include/memory/renesas-rpc-if.h index 7c93f5177532..9c0ad64b8d29 100644 --- a/include/memory/renesas-rpc-if.h +++ b/include/memory/renesas-rpc-if.h @@ -72,6 +72,7 @@ struct rpcif { enum rpcif_type type; enum rpcif_data_dir dir; u8 bus_size; + u8 xfer_size; void *buffer; u32 xferlen; u32 smcr; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5cb095b09a94..69ef31cea582 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -578,6 +578,7 @@ enum { #define HCI_ERROR_CONNECTION_TIMEOUT 0x08 #define HCI_ERROR_REJ_LIMITED_RESOURCES 0x0d #define HCI_ERROR_REJ_BAD_ADDR 0x0f +#define HCI_ERROR_INVALID_PARAMETERS 0x12 #define HCI_ERROR_REMOTE_USER_TERM 0x13 #define HCI_ERROR_REMOTE_LOW_RESOURCES 0x14 #define HCI_ERROR_REMOTE_POWER_OFF 0x15 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d5377740e99c..8abd08245326 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1156,7 +1156,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); -void hci_le_conn_failed(struct hci_conn *conn, u8 status); +void hci_conn_failed(struct hci_conn *conn, u8 status); /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an diff --git a/include/net/esp.h b/include/net/esp.h index 90cd02ff77ef..9c5637d41d95 100644 --- a/include/net/esp.h +++ b/include/net/esp.h @@ -4,8 +4,6 @@ #include <linux/skbuff.h> -#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER) - struct ip_esp_hdr; static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb) diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index aa33e1092e2c..9f65f1bfbd24 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -59,6 +59,8 @@ struct flow_dissector_key_vlan { __be16 vlan_tci; }; __be16 vlan_tpid; + __be16 vlan_eth_type; + u16 padding; }; struct flow_dissector_mpls_lse { diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index a38c4f1e4e5c..74b369bddf49 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -58,7 +58,7 @@ struct ip6_tnl { /* These fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ - __u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int hlen; /* tun_hlen + encap_hlen */ int tun_hlen; /* Precalculated header length */ int encap_hlen; /* Encap header length (FOU,GUE) */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 0219fe907b26..c24fa934221d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -116,7 +116,7 @@ struct ip_tunnel { /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ - u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ @@ -243,11 +243,18 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id) static inline void ip_tunnel_init_flow(struct flowi4 *fl4, int proto, __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif, + __be32 key, __u8 tos, + struct net *net, int oif, __u32 mark, __u32 tun_inner_hash) { memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; + + if (oif) { + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + /* Legacy VRF/l3mdev use case */ + fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; + } + fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; diff --git a/include/net/mctp.h b/include/net/mctp.h index d37268fe6825..82800d521c3d 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -36,8 +36,6 @@ struct mctp_hdr { #define MCTP_HDR_TAG_SHIFT 0 #define MCTP_HDR_TAG_MASK GENMASK(2, 0) -#define MCTP_HEADER_MAXLEN 4 - #define MCTP_INITIAL_DEFAULT_NET 1 static inline bool mctp_address_unicast(mctp_eid_t eid) diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3d83b64471d3..b4af4837d80b 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -75,8 +75,8 @@ struct netns_ipv6 { struct list_head fib6_walkers; rwlock_t fib6_walker_lock; spinlock_t fib6_gc_lock; - unsigned int ip6_rt_gc_expire; - unsigned long ip6_rt_last_gc; + atomic_t ip6_rt_gc_expire; + unsigned long ip6_rt_last_gc; unsigned char flowlabel_has_excl; #ifdef CONFIG_IPV6_MULTIPLE_TABLES bool fib6_has_custom_rules; diff --git a/include/net/tcp.h b/include/net/tcp.h index 70ca4a5e330a..cc1295037533 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -480,6 +480,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES @@ -620,6 +621,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); +void tcp_check_space(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -1042,6 +1044,7 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ @@ -1164,6 +1167,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); +static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) +{ + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); +} + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 5554ee75e7da..647722e847b4 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -97,6 +97,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, struct net_device *dev, u16 queue_id); +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_destroy(struct xsk_buff_pool *pool); void xp_get_pool(struct xsk_buff_pool *pool); bool xp_put_pool(struct xsk_buff_pool *pool); diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index e76c94697c1b..d0a24779c52d 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -53,8 +53,10 @@ enum { #define ISID_SIZE 6 -/* Connection suspend "bit" */ -#define ISCSI_SUSPEND_BIT 1 +/* Connection flags */ +#define ISCSI_CONN_FLAG_SUSPEND_TX BIT(0) +#define ISCSI_CONN_FLAG_SUSPEND_RX BIT(1) +#define ISCSI_CONN_FLAG_BOUND BIT(2) #define ISCSI_ITT_MASK 0x1fff #define ISCSI_TOTAL_CMDS_MAX 4096 @@ -211,8 +213,7 @@ struct iscsi_conn { struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ struct work_struct xmitwork; /* per-conn. xmit workqueue */ - unsigned long suspend_tx; /* suspend Tx */ - unsigned long suspend_rx; /* suspend Rx */ + unsigned long flags; /* ISCSI_CONN_FLAGs */ /* negotiated params */ unsigned max_recv_dlength; /* initiator_max_recv_dsl*/ diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 38e4a67f5922..9acb8422f680 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -211,6 +211,8 @@ struct iscsi_cls_conn { struct mutex ep_mutex; struct iscsi_endpoint *ep; + /* Used when accessing flags and queueing work. */ + spinlock_t lock; unsigned long flags; struct work_struct cleanup_work; @@ -295,7 +297,7 @@ extern void iscsi_host_for_each_session(struct Scsi_Host *shost, struct iscsi_endpoint { void *dd_data; /* LLD private data */ struct device dev; - uint64_t id; + int id; struct iscsi_cls_conn *conn; }; diff --git a/include/sound/core.h b/include/sound/core.h index b7e9b58d3c78..6d4cc49584c6 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -284,6 +284,7 @@ int snd_card_disconnect(struct snd_card *card); void snd_card_disconnect_sync(struct snd_card *card); int snd_card_free(struct snd_card *card); int snd_card_free_when_closed(struct snd_card *card); +int snd_card_free_on_error(struct device *dev, int ret); void snd_card_set_id(struct snd_card *card, const char *id); int snd_card_register(struct snd_card *card); int snd_card_info_init(void); diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h index 653dfffb3ac8..8d79cebf95f3 100644 --- a/include/sound/memalloc.h +++ b/include/sound/memalloc.h @@ -51,6 +51,11 @@ struct snd_dma_device { #define SNDRV_DMA_TYPE_DEV_SG SNDRV_DMA_TYPE_DEV /* no SG-buf support */ #define SNDRV_DMA_TYPE_DEV_WC_SG SNDRV_DMA_TYPE_DEV_WC #endif +/* fallback types, don't use those directly */ +#ifdef CONFIG_SND_DMA_SGBUF +#define SNDRV_DMA_TYPE_DEV_SG_FALLBACK 10 +#define SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK 11 +#endif /* * info for buffer allocation diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index a52080407b98..766dc6f009c0 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -179,6 +179,10 @@ struct snd_soc_component_driver { struct snd_pcm_hw_params *params); bool use_dai_pcm_id; /* use DAI link PCM ID as PCM device number */ int be_pcm_base; /* base device ID for all BE PCMs */ + +#ifdef CONFIG_DEBUG_FS + const char *debugfs_prefix; +#endif }; struct snd_soc_component { diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 0f34f13ebd55..3995c58a1c51 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1004,7 +1004,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force); -DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup); DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy); DECLARE_EVENT_CLASS(rpc_xprt_event, @@ -2016,17 +2015,18 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_STRUCT__entry( __field(const void *, dr) __field(u32, xid) - __string(addr, dr->xprt->xpt_remotebuf) + __array(__u8, addr, INET6_ADDRSTRLEN + 10) ), TP_fast_assign( __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); - __assign_str(addr, dr->xprt->xpt_remotebuf); + snprintf(__entry->addr, sizeof(__entry->addr) - 1, + "%pISpc", (struct sockaddr *)&dr->addr); ), - TP_printk("addr=%s dr=%p xid=0x%08x", __get_str(addr), __entry->dr, + TP_printk("addr=%s dr=%p xid=0x%08x", __entry->addr, __entry->dr, __entry->xid) ); diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..429bec8dd70a 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -42,7 +42,7 @@ typedef __s64 Elf64_Sxword; /* ARM MTE memory tag segment type */ -#define PT_ARM_MEMTAG_MTE (PT_LOPROC + 0x1) +#define PT_AARCH64_MEMTAG_MTE (PT_LOPROC + 0x2) /* * Extended Numbering @@ -431,6 +431,8 @@ typedef struct elf64_shdr { #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index 4c14e8be7267..3a49913d006c 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -182,7 +182,7 @@ struct fb_fix_screeninfo { * * For pseudocolor: offset and length should be the same for all color * components. Offset specifies the position of the least significant bit - * of the pallette index in a pixel value. Length indicates the number + * of the palette index in a pixel value. Length indicates the number * of available palette entries (i.e. # of entries = 1 << length). */ struct fb_bitfield { diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7989d9483ea7..dff8e7f17074 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -662,6 +662,27 @@ /* Select an area of screen to be copied */ #define KEY_SELECTIVE_SCREENSHOT 0x27a +/* Move the focus to the next or previous user controllable element within a UI container */ +#define KEY_NEXT_ELEMENT 0x27b +#define KEY_PREVIOUS_ELEMENT 0x27c + +/* Toggle Autopilot engagement */ +#define KEY_AUTOPILOT_ENGAGE_TOGGLE 0x27d + +/* Shortcut Keys */ +#define KEY_MARK_WAYPOINT 0x27e +#define KEY_SOS 0x27f +#define KEY_NAV_CHART 0x280 +#define KEY_FISHING_CHART 0x281 +#define KEY_SINGLE_RANGE_RADAR 0x282 +#define KEY_DUAL_RANGE_RADAR 0x283 +#define KEY_RADAR_OVERLAY 0x284 +#define KEY_TRADITIONAL_SONAR 0x285 +#define KEY_CLEARVU_SONAR 0x286 +#define KEY_SIDEVU_SONAR 0x287 +#define KEY_NAV_INFO 0x288 +#define KEY_BRIGHTNESS_MENU 0x289 + /* * Some keyboards have keys which do not have a defined meaning, these keys * are intended to be programmed / bound to macros by the user. For most diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 784adc6f6ed2..1845cf7c80ba 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -296,6 +296,7 @@ struct io_uring_params { #define IORING_FEAT_NATIVE_WORKERS (1U << 9) #define IORING_FEAT_RSRC_TAGS (1U << 10) #define IORING_FEAT_CQE_SKIP (1U << 11) +#define IORING_FEAT_LINKED_FILE (1U << 12) /* * io_uring_register(2) opcodes and arguments diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e10d131edd80..5088bd9f1922 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -444,7 +444,9 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 -#define KVM_SYSTEM_EVENT_SEV_TERM 4 +#define KVM_SYSTEM_EVENT_WAKEUP 4 +#define KVM_SYSTEM_EVENT_SUSPEND 5 +#define KVM_SYSTEM_EVENT_SEV_TERM 6 __u32 type; __u32 ndata; union { @@ -647,6 +649,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 #define KVM_MP_STATE_AP_RESET_HOLD 9 +#define KVM_MP_STATE_SUSPENDED 10 struct kvm_mp_state { __u32 mp_state; @@ -1153,6 +1156,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DISABLE_QUIRKS2 213 #define KVM_CAP_VM_TSC_CONTROL 214 #define KVM_CAP_SYSTEM_EVENT_DATA 215 +#define KVM_CAP_ARM_SYSTEM_SUSPEND 216 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index e998764f0262..a5e06dcbba13 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,6 +272,15 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 3021ea25a284..7837ba4fe728 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_STDDEF_H +#define _UAPI_LINUX_STDDEF_H + #include <linux/compiler_types.h> #ifndef __always_inline @@ -41,3 +44,4 @@ struct { } __empty_ ## NAME; \ TYPE NAME[]; \ } +#endif diff --git a/kernel/Makefile b/kernel/Makefile index 471d71935e90..847a82bfe0e3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -114,7 +114,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ obj-$(CONFIG_KCSAN) += kcsan/ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o -obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/cpu.c b/kernel/cpu.c index 5797c2a7a93f..d0a9aa0b42e8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -71,7 +71,6 @@ struct cpuhp_cpu_state { bool rollback; bool single; bool bringup; - int cpu; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; @@ -475,7 +474,7 @@ static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state -cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; @@ -486,14 +485,15 @@ cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) st->target = target; st->single = false; st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); return prev_state; } static inline void -cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state prev_state) { bool bringup = !st->bringup; @@ -520,8 +520,8 @@ cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) } st->bringup = bringup; - if (cpu_dying(st->cpu) != !bringup) - set_cpu_dying(st->cpu, !bringup); + if (cpu_dying(cpu) != !bringup) + set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ @@ -541,15 +541,16 @@ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) wait_for_ap_thread(st, st->bringup); } -static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } @@ -581,7 +582,7 @@ static int bringup_wait_for_ap(unsigned int cpu) if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; - return cpuhp_kick_ap(st, st->target); + return cpuhp_kick_ap(cpu, st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -704,7 +705,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); @@ -721,7 +722,6 @@ static void cpuhp_create(unsigned int cpu) init_completion(&st->done_up); init_completion(&st->done_down); - st->cpu = cpu; } static int cpuhp_should_run(unsigned int cpu) @@ -875,7 +875,7 @@ static int cpuhp_kick_ap_work(unsigned int cpu) cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); - ret = cpuhp_kick_ap(st, st->target); + ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; @@ -1107,7 +1107,7 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret, cpu, cpuhp_get_step(st->state)->name, st->state); - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, @@ -1134,7 +1134,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = cpuhp_set_state(st, target); + prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. @@ -1165,7 +1165,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { - cpuhp_reset_state(st, prev_state); + cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); @@ -1352,7 +1352,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - cpuhp_set_state(st, target); + cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 4632b0f4f72e..8a6cd53dbe8c 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -114,6 +114,7 @@ static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, dma_direct_sync_single_for_cpu(dev, addr, size, dir); if (unlikely(is_swiotlb_buffer(dev, phys))) - swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs); + swiotlb_tbl_unmap_single(dev, phys, size, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC); } #endif /* _KERNEL_DMA_DIRECT_H */ diff --git a/kernel/entry/common.c b/kernel/entry/common.c index e57a224d6b79..93c3b86e781c 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -392,7 +392,7 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); void dynamic_irqentry_exit_cond_resched(void) { - if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) + if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) return; raw_irqentry_exit_cond_resched(); } diff --git a/kernel/events/core.c b/kernel/events/core.c index cfde994ce61c..7858bafffa9d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -574,8 +574,7 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, enum event_type_t event_type); static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void update_context_time(struct perf_event_context *ctx); static u64 perf_event_time(struct perf_event *event); @@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, static inline void update_cgrp_time_from_event(struct perf_event *event) { struct perf_cgroup_info *info; - struct perf_cgroup *cgrp; /* * ensure we access cgroup data only when needed and @@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current, event->ctx); + info = this_cpu_ptr(event->cgrp->info); /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { - info = this_cpu_ptr(event->cgrp->info); + if (info->active) __update_cgrp_time(info, perf_clock(), true); - } } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp; + struct perf_event_context *ctx = &cpuctx->ctx; + struct perf_cgroup *cgrp = cpuctx->cgrp; struct perf_cgroup_info *info; struct cgroup_subsys_state *css; @@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task, * ensure we do not access cgroup data * unless we have the cgroup pinned (css_get) */ - if (!task || !ctx->nr_cgroups) + if (!cgrp) return; - cgrp = perf_cgroup_from_task(task, ctx); + WARN_ON_ONCE(!ctx->nr_cgroups); for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); @@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); -#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ -#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ - /* * reschedule events based on the cgroup constraint of task. - * - * mode SWOUT : schedule out everything - * mode SWIN : schedule in based on cgroup for next */ -static void perf_cgroup_switch(struct task_struct *task, int mode) +static void perf_cgroup_switch(struct task_struct *task) { + struct perf_cgroup *cgrp; struct perf_cpu_context *cpuctx, *tmp; struct list_head *list; unsigned long flags; @@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) */ local_irq_save(flags); + cgrp = perf_cgroup_from_task(task, NULL); + list = this_cpu_ptr(&cgrp_cpuctx_list); list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) { WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); + if (READ_ONCE(cpuctx->cgrp) == cgrp) + continue; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(cpuctx->ctx.pmu); - if (mode & PERF_CGROUP_SWOUT) { - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - /* - * must not be done before ctxswout due - * to event_filter_match() in event_sched_out() - */ - cpuctx->cgrp = NULL; - } + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to update_cgrp_time_from_cpuctx() in + * ctx_sched_out() + */ + cpuctx->cgrp = cgrp; + /* + * set cgrp before ctxsw in to allow + * perf_cgroup_set_timestamp() in ctx_sched_in() + * to not have to pass task around + */ + cpu_ctx_sched_in(cpuctx, EVENT_ALL); - if (mode & PERF_CGROUP_SWIN) { - WARN_ON_ONCE(cpuctx->cgrp); - /* - * set cgrp before ctxsw in to allow - * event_filter_match() to not have to pass - * task around - * we pass the cpuctx->ctx to perf_cgroup_from_task() - * because cgorup events are only per-cpu - */ - cpuctx->cgrp = perf_cgroup_from_task(task, - &cpuctx->ctx); - cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); - } perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } @@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_restore(flags); } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(next, NULL); - - /* - * only schedule out current cgroup events if we know - * that we are switching to a different cgroup. Otherwise, - * do no touch the cgroup events. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWOUT); - - rcu_read_unlock(); -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(prev, NULL); - - /* - * only need to schedule in cgroup events if we are changing - * cgroup during ctxsw. Cgroup events were not scheduled - * out of ctxsw out if that was not the case. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWIN); - - rcu_read_unlock(); -} - static int perf_cgroup_ensure_storage(struct perf_event *event, struct cgroup_subsys_state *css) { @@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct */ cpuctx = container_of(ctx, struct perf_cpu_context, ctx); - /* - * Since setting cpuctx->cgrp is conditional on the current @cgrp - * matching the event's cgroup, we must do this for every new event, - * because if the first would mismatch, the second would not try again - * and we would leave cpuctx->cgrp unset. - */ - if (ctx->is_active && !cpuctx->cgrp) { - struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); - - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - cpuctx->cgrp = cgrp; - } - if (ctx->nr_cgroups++) return; + cpuctx->cgrp = perf_cgroup_from_task(current, ctx); list_add(&cpuctx->cgrp_cpuctx_entry, per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); } @@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c if (--ctx->nr_cgroups) return; - if (ctx->is_active && cpuctx->cgrp) - cpuctx->cgrp = NULL; - + cpuctx->cgrp = NULL; list_del(&cpuctx->cgrp_cpuctx_entry); } @@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, { } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ -} - static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, struct perf_event_attr *attr, struct perf_event *group_leader) @@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) -{ -} - -static inline void -perf_cgroup_switch(struct task_struct *task, struct task_struct *next) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { } @@ -1147,6 +1052,10 @@ static inline void perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) { } + +static void perf_cgroup_switch(struct task_struct *task) +{ +} #endif /* @@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, @@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, - struct task_struct *task) + struct perf_event_context *ctx) { - cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_PINNED); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_PINNED); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); } /* @@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, else if (ctx_event_type & EVENT_PINNED) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); } @@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event, return; if (!event_filter_match(event)) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event, * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * cgroup event are system-wide mode only */ if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_out(task, next); + perf_cgroup_switch(next); } /* @@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { int is_active = ctx->is_active; @@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (is_active ^ EVENT_TIME) { /* start ctx time */ __update_context_time(ctx, false); - perf_cgroup_set_timestamp(task, ctx); + perf_cgroup_set_timestamp(cpuctx); /* * CPU-release for the below ->is_active store, * see __load_acquire() in perf_event_time_now() @@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx, } static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { struct perf_event_context *ctx = &cpuctx->ctx; - ctx_sched_in(ctx, cpuctx, event_type, task); + ctx_sched_in(ctx, cpuctx, event_type); } static void perf_event_context_sched_in(struct perf_event_context *ctx, @@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, */ if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, ctx, task); + perf_event_sched_in(cpuctx, ctx); if (cpuctx->sched_cb_usage && pmu->sched_task) pmu->sched_task(cpuctx->task_ctx, true); @@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; - /* - * If cgroup events exist on this CPU, then we need to check if we have - * to switch in PMU state; cgroup event are system-wide mode only. - * - * Since cgroup events are CPU events, we must schedule these in before - * we schedule in the task events. - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); - for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx) if (cpu_event) rotate_ctx(&cpuctx->ctx, cpu_event); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn) clone_ctx = unclone_ctx(ctx); ctx_resched(cpuctx, ctx, event_type); } else { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); } perf_ctx_unlock(cpuctx, ctx); @@ -6352,7 +6247,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) again: mutex_lock(&event->mmap_mutex); if (event->rb) { - if (event->rb->nr_pages != nr_pages) { + if (data_page_nr(event->rb) != nr_pages) { ret = -EINVAL; goto unlock; } @@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->state = PERF_EVENT_STATE_INACTIVE; + if (parent_event) + event->event_caps = parent_event->event_caps; + if (event->attr.sigtrap) atomic_set(&event->event_limit, 1); @@ -13562,7 +13460,7 @@ static int __perf_cgroup_move(void *info) { struct task_struct *task = info; rcu_read_lock(); - perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + perf_cgroup_switch(task); rcu_read_unlock(); return 0; } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 082832738c8f..5150d5f84c03 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -116,6 +116,11 @@ static inline int page_order(struct perf_buffer *rb) } #endif +static inline int data_page_nr(struct perf_buffer *rb) +{ + return rb->nr_pages << page_order(rb); +} + static inline unsigned long perf_data_size(struct perf_buffer *rb) { return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 52868716ec35..fb35b926024c 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -859,11 +859,6 @@ void rb_free(struct perf_buffer *rb) } #else -static int data_page_nr(struct perf_buffer *rb) -{ - return rb->nr_pages << page_order(rb); -} - static struct page * __perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff) { diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f7ff8919dc9b..fdf170404650 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -269,8 +269,9 @@ static int __irq_build_affinity_masks(unsigned int startvec, */ if (numvecs <= nodes) { for_each_node_mask(n, nodemsk) { - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, - node_to_cpumask[n]); + /* Ensure that only CPUs which are in both masks are set */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); if (++curvec == last_affv) curvec = firstvec; } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index f7df715ec28e..7afa40fe5cc4 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -137,7 +137,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu) if (!irq_work_claim(work)) return false; - kasan_record_aux_stack(work); + kasan_record_aux_stack_noalloc(work); preempt_disable(); if (cpu != smp_processor_id()) { diff --git a/kernel/kcov.c b/kernel/kcov.c index 475524bd900a..b3732b210593 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -475,8 +475,11 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma) vma->vm_flags |= VM_DONTEXPAND; for (off = 0; off < size; off += PAGE_SIZE) { page = vmalloc_to_page(kcov->area + off); - if (vm_insert_page(vma, vma->vm_start + off, page)) - WARN_ONCE(1, "vm_insert_page() failed"); + res = vm_insert_page(vma, vma->vm_start + off, page); + if (res) { + pr_warn_once("kcov: vm_insert_page() failed\n"); + return res; + } } return 0; exit: diff --git a/kernel/kprobes.c b/kernel/kprobes.c index dbe57df2e199..dd58c0be9ce2 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2126,7 +2126,7 @@ static void kretprobe_rethook_handler(struct rethook_node *rh, void *data, struct kprobe_ctlblk *kcb; /* The data must NOT be null. This means rethook data structure is broken. */ - if (WARN_ON_ONCE(!data)) + if (WARN_ON_ONCE(!data) || !rp->handler) return; __this_cpu_write(current_kprobe, &rp->kp); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..51efaabac3e4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5752,6 +5752,8 @@ static inline struct task_struct *pick_task(struct rq *rq) extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi); +static void queue_core_balance(struct rq *rq); + static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { @@ -5801,7 +5803,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } rq->core_pick = NULL; - return next; + goto out; } put_prev_task_balance(rq, prev, rf); @@ -5851,7 +5853,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) */ WARN_ON_ONCE(fi_before); task_vruntime_update(rq, next, false); - goto done; + goto out_set_next; } } @@ -5970,8 +5972,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) resched_curr(rq_i); } -done: +out_set_next: set_next_task(rq, next); +out: + if (rq->core->core_forceidle_count && next == rq->idle) + queue_core_balance(rq); + return next; } @@ -6000,7 +6006,7 @@ static bool try_steal_cookie(int this, int that) if (p == src->core_pick || p == src->curr) goto next; - if (!cpumask_test_cpu(this, &p->cpus_mask)) + if (!is_cpu_allowed(p, this)) goto next; if (p->core_occupation > dst->idle->core_occupation) @@ -6066,7 +6072,7 @@ static void sched_core_balance(struct rq *rq) static DEFINE_PER_CPU(struct callback_head, core_balance_head); -void queue_core_balance(struct rq *rq) +static void queue_core_balance(struct rq *rq) { if (!sched_core_enabled(rq)) return; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d4bd299d67ab..a68482d66535 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3829,11 +3829,11 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s se->avg.runnable_sum = se->avg.runnable_avg * divider; - se->avg.load_sum = divider; - if (se_weight(se)) { - se->avg.load_sum = - div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se)); - } + se->avg.load_sum = se->avg.load_avg * divider; + if (se_weight(se) < se->avg.load_sum) + se->avg.load_sum = div_u64(se->avg.load_sum, se_weight(se)); + else + se->avg.load_sum = 1; enqueue_load_avg(cfs_rq, se); cfs_rq->avg.util_avg += se->avg.util_avg; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f8b5020e76a..ecb0d7052877 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -434,7 +434,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir { update_idle_core(rq); schedstat_inc(rq->sched_goidle); - queue_core_balance(rq); } #ifdef CONFIG_SMP diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58263f90c559..8dccb34eb190 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1232,8 +1232,6 @@ static inline bool sched_group_cookie_match(struct rq *rq, return false; } -extern void queue_core_balance(struct rq *rq); - static inline bool sched_core_enqueued(struct task_struct *p) { return !RB_EMPTY_NODE(&p->core_node); @@ -1267,10 +1265,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq) return &rq->__lock; } -static inline void queue_core_balance(struct rq *rq) -{ -} - static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p) { return true; diff --git a/kernel/smp.c b/kernel/smp.c index 01a7c1706a58..65a630f62363 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -579,7 +579,7 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline) /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && - !warned && !llist_empty(head))) { + !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); diff --git a/kernel/static_call.c b/kernel/static_call.c index f2b8baea35d2..e9c3e69f3837 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -1,549 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/init.h> #include <linux/static_call.h> -#include <linux/bug.h> -#include <linux/smp.h> -#include <linux/sort.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/processor.h> -#include <asm/sections.h> - -extern struct static_call_site __start_static_call_sites[], - __stop_static_call_sites[]; -extern struct static_call_tramp_key __start_static_call_tramp_key[], - __stop_static_call_tramp_key[]; - -static bool static_call_initialized; - -/* mutex to protect key modules/sites */ -static DEFINE_MUTEX(static_call_mutex); - -static void static_call_lock(void) -{ - mutex_lock(&static_call_mutex); -} - -static void static_call_unlock(void) -{ - mutex_unlock(&static_call_mutex); -} - -static inline void *static_call_addr(struct static_call_site *site) -{ - return (void *)((long)site->addr + (long)&site->addr); -} - -static inline unsigned long __static_call_key(const struct static_call_site *site) -{ - return (long)site->key + (long)&site->key; -} - -static inline struct static_call_key *static_call_key(const struct static_call_site *site) -{ - return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); -} - -/* These assume the key is word-aligned. */ -static inline bool static_call_is_init(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_INIT; -} - -static inline bool static_call_is_tail(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_TAIL; -} - -static inline void static_call_set_init(struct static_call_site *site) -{ - site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - - (long)&site->key; -} - -static int static_call_site_cmp(const void *_a, const void *_b) -{ - const struct static_call_site *a = _a; - const struct static_call_site *b = _b; - const struct static_call_key *key_a = static_call_key(a); - const struct static_call_key *key_b = static_call_key(b); - - if (key_a < key_b) - return -1; - - if (key_a > key_b) - return 1; - - return 0; -} - -static void static_call_site_swap(void *_a, void *_b, int size) -{ - long delta = (unsigned long)_a - (unsigned long)_b; - struct static_call_site *a = _a; - struct static_call_site *b = _b; - struct static_call_site tmp = *a; - - a->addr = b->addr - delta; - a->key = b->key - delta; - - b->addr = tmp.addr + delta; - b->key = tmp.key + delta; -} - -static inline void static_call_sort_entries(struct static_call_site *start, - struct static_call_site *stop) -{ - sort(start, stop - start, sizeof(struct static_call_site), - static_call_site_cmp, static_call_site_swap); -} - -static inline bool static_call_key_has_mods(struct static_call_key *key) -{ - return !(key->type & 1); -} - -static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) -{ - if (!static_call_key_has_mods(key)) - return NULL; - - return key->mods; -} - -static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) -{ - if (static_call_key_has_mods(key)) - return NULL; - - return (struct static_call_site *)(key->type & ~1); -} - -void __static_call_update(struct static_call_key *key, void *tramp, void *func) -{ - struct static_call_site *site, *stop; - struct static_call_mod *site_mod, first; - - cpus_read_lock(); - static_call_lock(); - - if (key->func == func) - goto done; - - key->func = func; - - arch_static_call_transform(NULL, tramp, func, false); - - /* - * If uninitialized, we'll not update the callsites, but they still - * point to the trampoline and we just patched that. - */ - if (WARN_ON_ONCE(!static_call_initialized)) - goto done; - - first = (struct static_call_mod){ - .next = static_call_key_next(key), - .mod = NULL, - .sites = static_call_key_sites(key), - }; - - for (site_mod = &first; site_mod; site_mod = site_mod->next) { - bool init = system_state < SYSTEM_RUNNING; - struct module *mod = site_mod->mod; - - if (!site_mod->sites) { - /* - * This can happen if the static call key is defined in - * a module which doesn't use it. - * - * It also happens in the has_mods case, where the - * 'first' entry has no sites associated with it. - */ - continue; - } - - stop = __stop_static_call_sites; - - if (mod) { -#ifdef CONFIG_MODULES - stop = mod->static_call_sites + - mod->num_static_call_sites; - init = mod->state == MODULE_STATE_COMING; -#endif - } - - for (site = site_mod->sites; - site < stop && static_call_key(site) == key; site++) { - void *site_addr = static_call_addr(site); - - if (!init && static_call_is_init(site)) - continue; - - if (!kernel_text_address((unsigned long)site_addr)) { - /* - * This skips patching built-in __exit, which - * is part of init_section_contains() but is - * not part of kernel_text_address(). - * - * Skipping built-in __exit is fine since it - * will never be executed. - */ - WARN_ONCE(!static_call_is_init(site), - "can't patch static call site at %pS", - site_addr); - continue; - } - - arch_static_call_transform(site_addr, NULL, func, - static_call_is_tail(site)); - } - } - -done: - static_call_unlock(); - cpus_read_unlock(); -} -EXPORT_SYMBOL_GPL(__static_call_update); - -static int __static_call_init(struct module *mod, - struct static_call_site *start, - struct static_call_site *stop) -{ - struct static_call_site *site; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod; - - if (start == stop) - return 0; - - static_call_sort_entries(start, stop); - - for (site = start; site < stop; site++) { - void *site_addr = static_call_addr(site); - - if ((mod && within_module_init((unsigned long)site_addr, mod)) || - (!mod && init_section_contains(site_addr, 1))) - static_call_set_init(site); - - key = static_call_key(site); - if (key != prev_key) { - prev_key = key; - - /* - * For vmlinux (!mod) avoid the allocation by storing - * the sites pointer in the key itself. Also see - * __static_call_update()'s @first. - * - * This allows architectures (eg. x86) to call - * static_call_init() before memory allocation works. - */ - if (!mod) { - key->sites = site; - key->type |= 1; - goto do_transform; - } - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - - /* - * When the key has a direct sites pointer, extract - * that into an explicit struct static_call_mod, so we - * can have a list of modules. - */ - if (static_call_key_sites(key)) { - site_mod->mod = NULL; - site_mod->next = NULL; - site_mod->sites = static_call_key_sites(key); - - key->mods = site_mod; - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - } - - site_mod->mod = mod; - site_mod->sites = site; - site_mod->next = static_call_key_next(key); - key->mods = site_mod; - } - -do_transform: - arch_static_call_transform(site_addr, NULL, key->func, - static_call_is_tail(site)); - } - - return 0; -} - -static int addr_conflict(struct static_call_site *site, void *start, void *end) -{ - unsigned long addr = (unsigned long)static_call_addr(site); - - if (addr <= (unsigned long)end && - addr + CALL_INSN_SIZE > (unsigned long)start) - return 1; - - return 0; -} - -static int __static_call_text_reserved(struct static_call_site *iter_start, - struct static_call_site *iter_stop, - void *start, void *end, bool init) -{ - struct static_call_site *iter = iter_start; - - while (iter < iter_stop) { - if (init || !static_call_is_init(iter)) { - if (addr_conflict(iter, start, end)) - return 1; - } - iter++; - } - - return 0; -} - -#ifdef CONFIG_MODULES - -static int __static_call_mod_text_reserved(void *start, void *end) -{ - struct module *mod; - int ret; - - preempt_disable(); - mod = __module_text_address((unsigned long)start); - WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); - if (!try_module_get(mod)) - mod = NULL; - preempt_enable(); - - if (!mod) - return 0; - - ret = __static_call_text_reserved(mod->static_call_sites, - mod->static_call_sites + mod->num_static_call_sites, - start, end, mod->state == MODULE_STATE_COMING); - - module_put(mod); - - return ret; -} - -static unsigned long tramp_key_lookup(unsigned long addr) -{ - struct static_call_tramp_key *start = __start_static_call_tramp_key; - struct static_call_tramp_key *stop = __stop_static_call_tramp_key; - struct static_call_tramp_key *tramp_key; - - for (tramp_key = start; tramp_key != stop; tramp_key++) { - unsigned long tramp; - - tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; - if (tramp == addr) - return (long)tramp_key->key + (long)&tramp_key->key; - } - - return 0; -} - -static int static_call_add_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = start + mod->num_static_call_sites; - struct static_call_site *site; - - for (site = start; site != stop; site++) { - unsigned long s_key = __static_call_key(site); - unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; - unsigned long key; - - /* - * Is the key is exported, 'addr' points to the key, which - * means modules are allowed to call static_call_update() on - * it. - * - * Otherwise, the key isn't exported, and 'addr' points to the - * trampoline so we need to lookup the key. - * - * We go through this dance to prevent crazy modules from - * abusing sensitive static calls. - */ - if (!kernel_text_address(addr)) - continue; - - key = tramp_key_lookup(addr); - if (!key) { - pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", - static_call_addr(site)); - return -EINVAL; - } - - key |= s_key & STATIC_CALL_SITE_FLAGS; - site->key = key - (long)&site->key; - } - - return __static_call_init(mod, start, stop); -} - -static void static_call_del_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = mod->static_call_sites + - mod->num_static_call_sites; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod, **prev; - struct static_call_site *site; - - for (site = start; site < stop; site++) { - key = static_call_key(site); - if (key == prev_key) - continue; - - prev_key = key; - - for (prev = &key->mods, site_mod = key->mods; - site_mod && site_mod->mod != mod; - prev = &site_mod->next, site_mod = site_mod->next) - ; - - if (!site_mod) - continue; - - *prev = site_mod->next; - kfree(site_mod); - } -} - -static int static_call_module_notify(struct notifier_block *nb, - unsigned long val, void *data) -{ - struct module *mod = data; - int ret = 0; - - cpus_read_lock(); - static_call_lock(); - - switch (val) { - case MODULE_STATE_COMING: - ret = static_call_add_module(mod); - if (ret) { - WARN(1, "Failed to allocate memory for static calls"); - static_call_del_module(mod); - } - break; - case MODULE_STATE_GOING: - static_call_del_module(mod); - break; - } - - static_call_unlock(); - cpus_read_unlock(); - - return notifier_from_errno(ret); -} - -static struct notifier_block static_call_module_nb = { - .notifier_call = static_call_module_notify, -}; - -#else - -static inline int __static_call_mod_text_reserved(void *start, void *end) -{ - return 0; -} - -#endif /* CONFIG_MODULES */ - -int static_call_text_reserved(void *start, void *end) -{ - bool init = system_state < SYSTEM_RUNNING; - int ret = __static_call_text_reserved(__start_static_call_sites, - __stop_static_call_sites, start, end, init); - - if (ret) - return ret; - - return __static_call_mod_text_reserved(start, end); -} - -int __init static_call_init(void) -{ - int ret; - - if (static_call_initialized) - return 0; - - cpus_read_lock(); - static_call_lock(); - ret = __static_call_init(NULL, __start_static_call_sites, - __stop_static_call_sites); - static_call_unlock(); - cpus_read_unlock(); - - if (ret) { - pr_err("Failed to allocate memory for static_call!\n"); - BUG(); - } - - static_call_initialized = true; - -#ifdef CONFIG_MODULES - register_module_notifier(&static_call_module_nb); -#endif - return 0; -} -early_initcall(static_call_init); long __static_call_return0(void) { return 0; } EXPORT_SYMBOL_GPL(__static_call_return0); - -#ifdef CONFIG_STATIC_CALL_SELFTEST - -static int func_a(int x) -{ - return x+1; -} - -static int func_b(int x) -{ - return x+2; -} - -DEFINE_STATIC_CALL(sc_selftest, func_a); - -static struct static_call_data { - int (*func)(int); - int val; - int expect; -} static_call_data [] __initdata = { - { NULL, 2, 3 }, - { func_b, 2, 4 }, - { func_a, 2, 3 } -}; - -static int __init test_static_call_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { - struct static_call_data *scd = &static_call_data[i]; - - if (scd->func) - static_call_update(sc_selftest, scd->func); - - WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); - } - - return 0; -} -early_initcall(test_static_call_init); - -#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c new file mode 100644 index 000000000000..dc5665b62814 --- /dev/null +++ b/kernel/static_call_inline.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/static_call.h> +#include <linux/bug.h> +#include <linux/smp.h> +#include <linux/sort.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/processor.h> +#include <asm/sections.h> + +extern struct static_call_site __start_static_call_sites[], + __stop_static_call_sites[]; +extern struct static_call_tramp_key __start_static_call_tramp_key[], + __stop_static_call_tramp_key[]; + +static bool static_call_initialized; + +/* mutex to protect key modules/sites */ +static DEFINE_MUTEX(static_call_mutex); + +static void static_call_lock(void) +{ + mutex_lock(&static_call_mutex); +} + +static void static_call_unlock(void) +{ + mutex_unlock(&static_call_mutex); +} + +static inline void *static_call_addr(struct static_call_site *site) +{ + return (void *)((long)site->addr + (long)&site->addr); +} + +static inline unsigned long __static_call_key(const struct static_call_site *site) +{ + return (long)site->key + (long)&site->key; +} + +static inline struct static_call_key *static_call_key(const struct static_call_site *site) +{ + return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); +} + +/* These assume the key is word-aligned. */ +static inline bool static_call_is_init(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_INIT; +} + +static inline bool static_call_is_tail(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_TAIL; +} + +static inline void static_call_set_init(struct static_call_site *site) +{ + site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - + (long)&site->key; +} + +static int static_call_site_cmp(const void *_a, const void *_b) +{ + const struct static_call_site *a = _a; + const struct static_call_site *b = _b; + const struct static_call_key *key_a = static_call_key(a); + const struct static_call_key *key_b = static_call_key(b); + + if (key_a < key_b) + return -1; + + if (key_a > key_b) + return 1; + + return 0; +} + +static void static_call_site_swap(void *_a, void *_b, int size) +{ + long delta = (unsigned long)_a - (unsigned long)_b; + struct static_call_site *a = _a; + struct static_call_site *b = _b; + struct static_call_site tmp = *a; + + a->addr = b->addr - delta; + a->key = b->key - delta; + + b->addr = tmp.addr + delta; + b->key = tmp.key + delta; +} + +static inline void static_call_sort_entries(struct static_call_site *start, + struct static_call_site *stop) +{ + sort(start, stop - start, sizeof(struct static_call_site), + static_call_site_cmp, static_call_site_swap); +} + +static inline bool static_call_key_has_mods(struct static_call_key *key) +{ + return !(key->type & 1); +} + +static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) +{ + if (!static_call_key_has_mods(key)) + return NULL; + + return key->mods; +} + +static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) +{ + if (static_call_key_has_mods(key)) + return NULL; + + return (struct static_call_site *)(key->type & ~1); +} + +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + struct static_call_site *site, *stop; + struct static_call_mod *site_mod, first; + + cpus_read_lock(); + static_call_lock(); + + if (key->func == func) + goto done; + + key->func = func; + + arch_static_call_transform(NULL, tramp, func, false); + + /* + * If uninitialized, we'll not update the callsites, but they still + * point to the trampoline and we just patched that. + */ + if (WARN_ON_ONCE(!static_call_initialized)) + goto done; + + first = (struct static_call_mod){ + .next = static_call_key_next(key), + .mod = NULL, + .sites = static_call_key_sites(key), + }; + + for (site_mod = &first; site_mod; site_mod = site_mod->next) { + bool init = system_state < SYSTEM_RUNNING; + struct module *mod = site_mod->mod; + + if (!site_mod->sites) { + /* + * This can happen if the static call key is defined in + * a module which doesn't use it. + * + * It also happens in the has_mods case, where the + * 'first' entry has no sites associated with it. + */ + continue; + } + + stop = __stop_static_call_sites; + + if (mod) { +#ifdef CONFIG_MODULES + stop = mod->static_call_sites + + mod->num_static_call_sites; + init = mod->state == MODULE_STATE_COMING; +#endif + } + + for (site = site_mod->sites; + site < stop && static_call_key(site) == key; site++) { + void *site_addr = static_call_addr(site); + + if (!init && static_call_is_init(site)) + continue; + + if (!kernel_text_address((unsigned long)site_addr)) { + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ + WARN_ONCE(!static_call_is_init(site), + "can't patch static call site at %pS", + site_addr); + continue; + } + + arch_static_call_transform(site_addr, NULL, func, + static_call_is_tail(site)); + } + } + +done: + static_call_unlock(); + cpus_read_unlock(); +} +EXPORT_SYMBOL_GPL(__static_call_update); + +static int __static_call_init(struct module *mod, + struct static_call_site *start, + struct static_call_site *stop) +{ + struct static_call_site *site; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod; + + if (start == stop) + return 0; + + static_call_sort_entries(start, stop); + + for (site = start; site < stop; site++) { + void *site_addr = static_call_addr(site); + + if ((mod && within_module_init((unsigned long)site_addr, mod)) || + (!mod && init_section_contains(site_addr, 1))) + static_call_set_init(site); + + key = static_call_key(site); + if (key != prev_key) { + prev_key = key; + + /* + * For vmlinux (!mod) avoid the allocation by storing + * the sites pointer in the key itself. Also see + * __static_call_update()'s @first. + * + * This allows architectures (eg. x86) to call + * static_call_init() before memory allocation works. + */ + if (!mod) { + key->sites = site; + key->type |= 1; + goto do_transform; + } + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + + /* + * When the key has a direct sites pointer, extract + * that into an explicit struct static_call_mod, so we + * can have a list of modules. + */ + if (static_call_key_sites(key)) { + site_mod->mod = NULL; + site_mod->next = NULL; + site_mod->sites = static_call_key_sites(key); + + key->mods = site_mod; + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + } + + site_mod->mod = mod; + site_mod->sites = site; + site_mod->next = static_call_key_next(key); + key->mods = site_mod; + } + +do_transform: + arch_static_call_transform(site_addr, NULL, key->func, + static_call_is_tail(site)); + } + + return 0; +} + +static int addr_conflict(struct static_call_site *site, void *start, void *end) +{ + unsigned long addr = (unsigned long)static_call_addr(site); + + if (addr <= (unsigned long)end && + addr + CALL_INSN_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +static int __static_call_text_reserved(struct static_call_site *iter_start, + struct static_call_site *iter_stop, + void *start, void *end, bool init) +{ + struct static_call_site *iter = iter_start; + + while (iter < iter_stop) { + if (init || !static_call_is_init(iter)) { + if (addr_conflict(iter, start, end)) + return 1; + } + iter++; + } + + return 0; +} + +#ifdef CONFIG_MODULES + +static int __static_call_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + int ret; + + preempt_disable(); + mod = __module_text_address((unsigned long)start); + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + if (!try_module_get(mod)) + mod = NULL; + preempt_enable(); + + if (!mod) + return 0; + + ret = __static_call_text_reserved(mod->static_call_sites, + mod->static_call_sites + mod->num_static_call_sites, + start, end, mod->state == MODULE_STATE_COMING); + + module_put(mod); + + return ret; +} + +static unsigned long tramp_key_lookup(unsigned long addr) +{ + struct static_call_tramp_key *start = __start_static_call_tramp_key; + struct static_call_tramp_key *stop = __stop_static_call_tramp_key; + struct static_call_tramp_key *tramp_key; + + for (tramp_key = start; tramp_key != stop; tramp_key++) { + unsigned long tramp; + + tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; + if (tramp == addr) + return (long)tramp_key->key + (long)&tramp_key->key; + } + + return 0; +} + +static int static_call_add_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = start + mod->num_static_call_sites; + struct static_call_site *site; + + for (site = start; site != stop; site++) { + unsigned long s_key = __static_call_key(site); + unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; + unsigned long key; + + /* + * Is the key is exported, 'addr' points to the key, which + * means modules are allowed to call static_call_update() on + * it. + * + * Otherwise, the key isn't exported, and 'addr' points to the + * trampoline so we need to lookup the key. + * + * We go through this dance to prevent crazy modules from + * abusing sensitive static calls. + */ + if (!kernel_text_address(addr)) + continue; + + key = tramp_key_lookup(addr); + if (!key) { + pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", + static_call_addr(site)); + return -EINVAL; + } + + key |= s_key & STATIC_CALL_SITE_FLAGS; + site->key = key - (long)&site->key; + } + + return __static_call_init(mod, start, stop); +} + +static void static_call_del_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = mod->static_call_sites + + mod->num_static_call_sites; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod, **prev; + struct static_call_site *site; + + for (site = start; site < stop; site++) { + key = static_call_key(site); + if (key == prev_key) + continue; + + prev_key = key; + + for (prev = &key->mods, site_mod = key->mods; + site_mod && site_mod->mod != mod; + prev = &site_mod->next, site_mod = site_mod->next) + ; + + if (!site_mod) + continue; + + *prev = site_mod->next; + kfree(site_mod); + } +} + +static int static_call_module_notify(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + int ret = 0; + + cpus_read_lock(); + static_call_lock(); + + switch (val) { + case MODULE_STATE_COMING: + ret = static_call_add_module(mod); + if (ret) { + WARN(1, "Failed to allocate memory for static calls"); + static_call_del_module(mod); + } + break; + case MODULE_STATE_GOING: + static_call_del_module(mod); + break; + } + + static_call_unlock(); + cpus_read_unlock(); + + return notifier_from_errno(ret); +} + +static struct notifier_block static_call_module_nb = { + .notifier_call = static_call_module_notify, +}; + +#else + +static inline int __static_call_mod_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif /* CONFIG_MODULES */ + +int static_call_text_reserved(void *start, void *end) +{ + bool init = system_state < SYSTEM_RUNNING; + int ret = __static_call_text_reserved(__start_static_call_sites, + __stop_static_call_sites, start, end, init); + + if (ret) + return ret; + + return __static_call_mod_text_reserved(start, end); +} + +int __init static_call_init(void) +{ + int ret; + + if (static_call_initialized) + return 0; + + cpus_read_lock(); + static_call_lock(); + ret = __static_call_init(NULL, __start_static_call_sites, + __stop_static_call_sites); + static_call_unlock(); + cpus_read_unlock(); + + if (ret) { + pr_err("Failed to allocate memory for static_call!\n"); + BUG(); + } + + static_call_initialized = true; + +#ifdef CONFIG_MODULES + register_module_notifier(&static_call_module_nb); +#endif + return 0; +} +early_initcall(static_call_init); + +#ifdef CONFIG_STATIC_CALL_SELFTEST + +static int func_a(int x) +{ + return x+1; +} + +static int func_b(int x) +{ + return x+2; +} + +DEFINE_STATIC_CALL(sc_selftest, func_a); + +static struct static_call_data { + int (*func)(int); + int val; + int expect; +} static_call_data [] __initdata = { + { NULL, 2, 3 }, + { func_b, 2, 4 }, + { func_a, 2, 3 } +}; + +static int __init test_static_call_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { + struct static_call_data *scd = &static_call_data[i]; + + if (scd->func) + static_call_update(sc_selftest, scd->func); + + WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); + } + + return 0; +} +early_initcall(test_static_call_init); + +#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/sys.c b/kernel/sys.c index 374f83e95239..b911fa6d81ab 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -117,6 +117,12 @@ #ifndef SVE_GET_VL # define SVE_GET_VL() (-EINVAL) #endif +#ifndef SME_SET_VL +# define SME_SET_VL(a) (-EINVAL) +#endif +#ifndef SME_GET_VL +# define SME_GET_VL() (-EINVAL) +#endif #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif @@ -2541,6 +2547,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SVE_GET_VL: error = SVE_GET_VL(); break; + case PR_SME_SET_VL: + error = SME_SET_VL(arg2); + break; + case PR_SME_GET_VL: + error = SME_GET_VL(); + break; case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 2d76c91b85de..d257721c68b8 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -188,7 +188,7 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) */ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL - WARN_ON(tick_nohz_full_running); + WARN_ON_ONCE(tick_nohz_full_running); #endif tick_do_timer_cpu = cpu; } @@ -1538,7 +1538,7 @@ void tick_cancel_sched_timer(int cpu) } #endif -/** +/* * Async notification about clocksource changes */ void tick_clock_notify(void) @@ -1559,7 +1559,7 @@ void tick_oneshot_notify(void) set_bit(0, &ts->check_clocks); } -/** +/* * Check, if a change happened, which makes oneshot possible. * * Called cyclic from the hrtimer softirq (driven by the timer diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 85f1021ad459..9dd2a39cb3b0 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1722,11 +1722,14 @@ static inline void __run_timers(struct timer_base *base) time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* - * The only possible reason for not finding any expired - * timer at this clk is that all matching timers have been - * dequeued. + * The two possible reasons for not finding any expired + * timer at this clk are that all matching timers have been + * dequeued or no timer has been queued since + * base::next_expiry was set to base::clk + + * NEXT_TIMER_MAX_DELTA. */ - WARN_ON_ONCE(!levels && !base->next_expiry_recalc); + WARN_ON_ONCE(!levels && !base->next_expiry_recalc + && base->timers_pending); base->clk++; base->next_expiry = __next_timer_interrupt(base); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7fa2ebc07f60..d8553f46caa2 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2349,11 +2349,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip, } static int -kprobe_multi_resolve_syms(const void *usyms, u32 cnt, +kprobe_multi_resolve_syms(const void __user *usyms, u32 cnt, unsigned long *addrs) { unsigned long addr, size; - const char **syms; + const char __user **syms; int err = -ENOMEM; unsigned int i; char *func; diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index ab463a4d2b23..b56833700d23 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -65,7 +65,7 @@ static void rethook_free_rcu(struct rcu_head *head) */ void rethook_free(struct rethook *rh) { - rcu_assign_pointer(rh->handler, NULL); + WRITE_ONCE(rh->handler, NULL); call_rcu(&rh->rcu, rethook_free_rcu); } diff --git a/lib/hexdump.c b/lib/hexdump.c index 9301578f98e8..06833d404398 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -22,15 +22,33 @@ EXPORT_SYMBOL(hex_asc_upper); * * hex_to_bin() converts one hex digit to its actual value or -1 in case of bad * input. + * + * This function is used to load cryptographic keys, so it is coded in such a + * way that there are no conditions or memory accesses that depend on data. + * + * Explanation of the logic: + * (ch - '9' - 1) is negative if ch <= '9' + * ('0' - 1 - ch) is negative if ch >= '0' + * we "and" these two values, so the result is negative if ch is in the range + * '0' ... '9' + * we are only interested in the sign, so we do a shift ">> 8"; note that right + * shift of a negative value is implementation-defined, so we cast the + * value to (unsigned) before the shift --- we have 0xffffff if ch is in + * the range '0' ... '9', 0 otherwise + * we "and" this value with (ch - '0' + 1) --- we have a value 1 ... 10 if ch is + * in the range '0' ... '9', 0 otherwise + * we add this value to -1 --- we have a value 0 ... 9 if ch is in the range '0' + * ... '9', -1 otherwise + * the next line is similar to the previous one, but we need to decode both + * uppercase and lowercase letters, so we use (ch & 0xdf), which converts + * lowercase to uppercase */ -int hex_to_bin(char ch) +int hex_to_bin(unsigned char ch) { - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - ch = tolower(ch); - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - return -1; + unsigned char cu = ch & 0xdf; + return -1 + + ((ch - '0' + 1) & (unsigned)((ch - '9' - 1) & ('0' - 1 - ch)) >> 8) + + ((cu - 'A' + 11) & (unsigned)((cu - 'F' - 1) & ('A' - 1 - cu)) >> 8); } EXPORT_SYMBOL(hex_to_bin); @@ -45,10 +63,13 @@ EXPORT_SYMBOL(hex_to_bin); int hex2bin(u8 *dst, const char *src, size_t count) { while (count--) { - int hi = hex_to_bin(*src++); - int lo = hex_to_bin(*src++); + int hi, lo; - if ((hi < 0) || (lo < 0)) + hi = hex_to_bin(*src++); + if (unlikely(hi < 0)) + return -EINVAL; + lo = hex_to_bin(*src++); + if (unlikely(lo < 0)) return -EINVAL; *dst++ = (hi << 4) | lo; diff --git a/lib/kobject.c b/lib/kobject.c index 56fa037501b5..5f0e71ab292c 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -54,32 +54,6 @@ void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) kobj->ktype->get_ownership(kobj, uid, gid); } -/* - * populate_dir - populate directory with attributes. - * @kobj: object we're working on. - * - * Most subsystems have a set of default attributes that are associated - * with an object that registers with them. This is a helper called during - * object registration that loops through the default attributes of the - * subsystem and creates attributes files for them in sysfs. - */ -static int populate_dir(struct kobject *kobj) -{ - const struct kobj_type *t = get_ktype(kobj); - struct attribute *attr; - int error = 0; - int i; - - if (t && t->default_attrs) { - for (i = 0; (attr = t->default_attrs[i]) != NULL; i++) { - error = sysfs_create_file(kobj, attr); - if (error) - break; - } - } - return error; -} - static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); @@ -90,12 +64,6 @@ static int create_dir(struct kobject *kobj) if (error) return error; - error = populate_dir(kobj); - if (error) { - sysfs_remove_dir(kobj); - return error; - } - if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 926f4823d5ea..fd1728d94bab 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -271,8 +271,12 @@ static FORCE_INLINE int LZ4_decompress_generic( ip += length; op += length; - /* Necessarily EOF, due to parsing restrictions */ - if (!partialDecoding || (cpy == oend)) + /* Necessarily EOF when !partialDecoding. + * When partialDecoding, it is EOF if we've either + * filled the output buffer or + * can't proceed with reading an offset for following match. + */ + if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2))) break; } else { /* may overwrite up to WILDCOPYLENGTH beyond cpy */ diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 08fc72d3ed16..6432b8c3e431 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -25,7 +25,7 @@ * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ -static inline long do_strncpy_from_user(char *dst, const char __user *src, +static __always_inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index bffa0ebf9f8b..feeb935a2299 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -20,7 +20,7 @@ * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ -static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) +static __always_inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; diff --git a/lib/xarray.c b/lib/xarray.c index 4acc88ea7c21..54e646e8e6ee 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -207,6 +207,8 @@ static void *xas_descend(struct xa_state *xas, struct xa_node *node) if (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); + if (node->shift && xa_is_node(entry)) + entry = XA_RETRY_ENTRY; } xas->xa_offset = offset; diff --git a/mm/compaction.c b/mm/compaction.c index c3e37aa9ff9e..fe915db6149b 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -26,6 +26,11 @@ #include "internal.h" #ifdef CONFIG_COMPACTION +/* + * Fragmentation score check interval for proactive compaction purposes. + */ +#define HPAGE_FRAG_CHECK_INTERVAL_MSEC (500) + static inline void count_compact_event(enum vm_event_item item) { count_vm_event(item); @@ -51,11 +56,6 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #define pageblock_end_pfn(pfn) block_end_pfn(pfn, pageblock_order) /* - * Fragmentation score check interval for proactive compaction purposes. - */ -static const unsigned int HPAGE_FRAG_CHECK_INTERVAL_MSEC = 500; - -/* * Page order with-respect-to which proactive compaction * calculates external fragmentation, which is used as * the "fragmentation score" of a node/zone. diff --git a/mm/filemap.c b/mm/filemap.c index 3a5ffb5587cd..9a1eef6c5d35 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1063,12 +1063,6 @@ void __init pagecache_init(void) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); - - /* - * tmpfs uses the ZERO_PAGE for reading holes: it is up-to-date, - * and splice's page_cache_pipe_buf_confirm() needs to see that. - */ - SetPageUptodate(ZERO_PAGE(0)); } /* diff --git a/mm/highmem.c b/mm/highmem.c index 0cc0c4da7ed9..1a692997fac4 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -624,7 +624,7 @@ void __kmap_local_sched_out(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) @@ -661,7 +661,7 @@ void __kmap_local_sched_in(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2fe38212e07c..c468fee595ff 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2145,15 +2145,14 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * pmd against. Otherwise we can end up replacing wrong folio. */ VM_BUG_ON(freeze && !folio); - if (folio) { - VM_WARN_ON_ONCE(!folio_test_locked(folio)); - if (folio != page_folio(pmd_page(*pmd))) - goto out; - } + VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) + is_pmd_migration_entry(*pmd)) { + if (folio && folio != page_folio(pmd_page(*pmd))) + goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); + } out: spin_unlock(ptl); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b34f50156f7e..3fc721789743 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3475,7 +3475,6 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) { int nr_nodes, node; struct page *page; - int rc = 0; lockdep_assert_held(&hugetlb_lock); @@ -3486,15 +3485,19 @@ static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) } for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { - if (!list_empty(&h->hugepage_freelists[node])) { - page = list_entry(h->hugepage_freelists[node].next, - struct page, lru); - rc = demote_free_huge_page(h, page); - break; + list_for_each_entry(page, &h->hugepage_freelists[node], lru) { + if (PageHWPoison(page)) + continue; + + return demote_free_huge_page(h, page); } } - return rc; + /* + * Only way to get here is if all pages on free lists are poisoned. + * Return -EBUSY so that caller will not retry. + */ + return -EBUSY; } #define HSTATE_ATTR_RO(_name) \ @@ -6782,6 +6785,16 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return ret; } +int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + int ret; + + spin_lock_irq(&hugetlb_lock); + ret = __get_huge_page_for_hwpoison(pfn, flags); + spin_unlock_irq(&hugetlb_lock); + return ret; +} + void putback_active_hugepage(struct page *page) { spin_lock_irq(&hugetlb_lock); diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 07a76c46daa5..9e1b6544bfa8 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -336,8 +336,6 @@ void __kasan_poison_vmalloc(const void *start, unsigned long size) #endif -#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) - void kasan_enable_tagging(void) { if (kasan_arg_mode == KASAN_ARG_MODE_ASYNC) @@ -347,6 +345,9 @@ void kasan_enable_tagging(void) else hw_enable_tagging_sync(); } + +#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) + EXPORT_SYMBOL_GPL(kasan_enable_tagging); void kasan_force_async_fault(void) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index d79b83d673b1..b01b4bbe0409 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -355,25 +355,27 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define hw_set_mem_tag_range(addr, size, tag, init) \ arch_set_mem_tag_range((addr), (size), (tag), (init)) +void kasan_enable_tagging(void); + #else /* CONFIG_KASAN_HW_TAGS */ #define hw_enable_tagging_sync() #define hw_enable_tagging_async() #define hw_enable_tagging_asymm() +static inline void kasan_enable_tagging(void) { } + #endif /* CONFIG_KASAN_HW_TAGS */ #if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) -void kasan_enable_tagging(void); void kasan_force_async_fault(void); -#else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ +#else /* CONFIG_KASAN_HW_TAGS && CONFIG_KASAN_KUNIT_TEST */ -static inline void kasan_enable_tagging(void) { } static inline void kasan_force_async_fault(void) { } -#endif /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */ +#endif /* CONFIG_KASAN_HW_TAGS && CONFIG_KASAN_KUNIT_TEST */ #ifdef CONFIG_KASAN_SW_TAGS u8 kasan_random_tag(void); diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 08291ed33e93..0a9def8ce5e8 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -315,6 +315,13 @@ static void per_cpu_remove_cache(void *arg) struct qlist_head *q; q = this_cpu_ptr(&cpu_quarantine); + /* + * Ensure the ordering between the writing to q->offline and + * per_cpu_remove_cache. Prevent cpu_quarantine from being corrupted + * by interrupt. + */ + if (READ_ONCE(q->offline)) + return; qlist_move_cache(q, &to_free, cache); qlist_free_all(&to_free, cache); } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index a203747ad2c0..9b2b5f56f4ae 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -231,27 +231,6 @@ static bool kfence_unprotect(unsigned long addr) return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); } -static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) -{ - long index; - - /* The checks do not affect performance; only called from slow-paths. */ - - if (!is_kfence_address((void *)addr)) - return NULL; - - /* - * May be an invalid index if called with an address at the edge of - * __kfence_pool, in which case we would report an "invalid access" - * error. - */ - index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; - if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) - return NULL; - - return &kfence_metadata[index]; -} - static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) { unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 9a6c4b1b12a8..600f2e2431d6 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -96,6 +96,27 @@ struct kfence_metadata { extern struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; +static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) +{ + long index; + + /* The checks do not affect performance; only called from slow-paths. */ + + if (!is_kfence_address((void *)addr)) + return NULL; + + /* + * May be an invalid index if called with an address at the edge of + * __kfence_pool, in which case we would report an "invalid access" + * error. + */ + index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; + if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) + return NULL; + + return &kfence_metadata[index]; +} + /* KFENCE error types for report generation. */ enum kfence_error_type { KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ diff --git a/mm/kfence/report.c b/mm/kfence/report.c index f93a7b2a338b..f5a6d8ba3e21 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -273,3 +273,50 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r /* We encountered a memory safety error, taint the kernel! */ add_taint(TAINT_BAD_PAGE, LOCKDEP_STILL_OK); } + +#ifdef CONFIG_PRINTK +static void kfence_to_kp_stack(const struct kfence_track *track, void **kp_stack) +{ + int i, j; + + i = get_stack_skipnr(track->stack_entries, track->num_stack_entries, NULL); + for (j = 0; i < track->num_stack_entries && j < KS_ADDRS_COUNT; ++i, ++j) + kp_stack[j] = (void *)track->stack_entries[i]; + if (j < KS_ADDRS_COUNT) + kp_stack[j] = NULL; +} + +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + struct kfence_metadata *meta = addr_to_metadata((unsigned long)object); + unsigned long flags; + + if (!meta) + return false; + + /* + * If state is UNUSED at least show the pointer requested; the rest + * would be garbage data. + */ + kpp->kp_ptr = object; + + /* Requesting info an a never-used object is almost certainly a bug. */ + if (WARN_ON(meta->state == KFENCE_OBJECT_UNUSED)) + return true; + + raw_spin_lock_irqsave(&meta->lock, flags); + + kpp->kp_slab = slab; + kpp->kp_slab_cache = meta->cache; + kpp->kp_objp = (void *)meta->addr; + kfence_to_kp_stack(&meta->alloc_track, kpp->kp_stack); + if (meta->state == KFENCE_OBJECT_FREED) + kfence_to_kp_stack(&meta->free_track, kpp->kp_free_stack); + /* get_stack_skipnr() ensures the first entry is outside allocator. */ + kpp->kp_ret = kpp->kp_stack[0]; + + raw_spin_unlock_irqrestore(&meta->lock, flags); + + return true; +} +#endif diff --git a/mm/kmemleak.c b/mm/kmemleak.c index acd7cbb82e16..a182f5ddaf68 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1132,7 +1132,7 @@ EXPORT_SYMBOL(kmemleak_no_scan); void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, gfp_t gfp) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_alloc(__va(phys), size, min_count, gfp); } EXPORT_SYMBOL(kmemleak_alloc_phys); @@ -1146,7 +1146,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys); */ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_free_part(__va(phys), size); } EXPORT_SYMBOL(kmemleak_free_part_phys); @@ -1158,7 +1158,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys); */ void __ref kmemleak_not_leak_phys(phys_addr_t phys) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_not_leak(__va(phys)); } EXPORT_SYMBOL(kmemleak_not_leak_phys); @@ -1170,7 +1170,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys); */ void __ref kmemleak_ignore_phys(phys_addr_t phys) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_ignore(__va(phys)); } EXPORT_SYMBOL(kmemleak_ignore_phys); diff --git a/mm/list_lru.c b/mm/list_lru.c index c669d87001a6..ba76428ceece 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -395,12 +395,6 @@ static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, struct list_lru_one *src, *dst; /* - * If there is no lru entry in this nlru, we can skip it immediately. - */ - if (!READ_ONCE(nlru->nr_items)) - return; - - /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 725f76723220..598fece89e2b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -587,6 +587,9 @@ static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); static DEFINE_SPINLOCK(stats_flush_lock); static DEFINE_PER_CPU(unsigned int, stats_updates); static atomic_t stats_flush_threshold = ATOMIC_INIT(0); +static u64 flush_next_time; + +#define FLUSH_TIME (2UL*HZ) /* * Accessors to ensure that preemption is disabled on PREEMPT_RT because it can @@ -637,6 +640,7 @@ static void __mem_cgroup_flush_stats(void) if (!spin_trylock_irqsave(&stats_flush_lock, flag)) return; + flush_next_time = jiffies_64 + 2*FLUSH_TIME; cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); spin_unlock_irqrestore(&stats_flush_lock, flag); @@ -648,10 +652,16 @@ void mem_cgroup_flush_stats(void) __mem_cgroup_flush_stats(); } +void mem_cgroup_flush_stats_delayed(void) +{ + if (time_after64(jiffies_64, flush_next_time)) + mem_cgroup_flush_stats(); +} + static void flush_memcg_stats_dwork(struct work_struct *w) { __mem_cgroup_flush_stats(); - queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ); + queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME); } /** diff --git a/mm/memory-failure.c b/mm/memory-failure.c index dcb6bb9cf731..27760c19bad7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1498,50 +1498,113 @@ static int try_to_split_thp_page(struct page *page, const char *msg) return 0; } -static int memory_failure_hugetlb(unsigned long pfn, int flags) +/* + * Called from hugetlb code with hugetlb_lock held. + * + * Return values: + * 0 - free hugepage + * 1 - in-use hugepage + * 2 - not a hugepage + * -EBUSY - the hugepage is busy (try to retry) + * -EHWPOISON - the hugepage is already hwpoisoned + */ +int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + struct page *page = pfn_to_page(pfn); + struct page *head = compound_head(page); + int ret = 2; /* fallback to normal page handling */ + bool count_increased = false; + + if (!PageHeadHuge(head)) + goto out; + + if (flags & MF_COUNT_INCREASED) { + ret = 1; + count_increased = true; + } else if (HPageFreed(head) || HPageMigratable(head)) { + ret = get_page_unless_zero(head); + if (ret) + count_increased = true; + } else { + ret = -EBUSY; + goto out; + } + + if (TestSetPageHWPoison(head)) { + ret = -EHWPOISON; + goto out; + } + + return ret; +out: + if (count_increased) + put_page(head); + return ret; +} + +#ifdef CONFIG_HUGETLB_PAGE +/* + * Taking refcount of hugetlb pages needs extra care about race conditions + * with basic operations like hugepage allocation/free/demotion. + * So some of prechecks for hwpoison (pinning, and testing/setting + * PageHWPoison) should be done in single hugetlb_lock range. + */ +static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) { - struct page *p = pfn_to_page(pfn); - struct page *head = compound_head(p); int res; + struct page *p = pfn_to_page(pfn); + struct page *head; unsigned long page_flags; + bool retry = true; - if (TestSetPageHWPoison(head)) { - pr_err("Memory failure: %#lx: already hardware poisoned\n", - pfn); - res = -EHWPOISON; - if (flags & MF_ACTION_REQUIRED) + *hugetlb = 1; +retry: + res = get_huge_page_for_hwpoison(pfn, flags); + if (res == 2) { /* fallback to normal page handling */ + *hugetlb = 0; + return 0; + } else if (res == -EHWPOISON) { + pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); + if (flags & MF_ACTION_REQUIRED) { + head = compound_head(p); res = kill_accessing_process(current, page_to_pfn(head), flags); + } + return res; + } else if (res == -EBUSY) { + if (retry) { + retry = false; + goto retry; + } + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); return res; } + head = compound_head(p); + lock_page(head); + + if (hwpoison_filter(p)) { + ClearPageHWPoison(head); + res = -EOPNOTSUPP; + goto out; + } + num_poisoned_pages_inc(); - if (!(flags & MF_COUNT_INCREASED)) { - res = get_hwpoison_page(p, flags); - if (!res) { - lock_page(head); - if (hwpoison_filter(p)) { - if (TestClearPageHWPoison(head)) - num_poisoned_pages_dec(); - unlock_page(head); - return -EOPNOTSUPP; - } - unlock_page(head); - res = MF_FAILED; - if (__page_handle_poison(p)) { - page_ref_inc(p); - res = MF_RECOVERED; - } - action_result(pfn, MF_MSG_FREE_HUGE, res); - return res == MF_RECOVERED ? 0 : -EBUSY; - } else if (res < 0) { - action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); - return -EBUSY; + /* + * Handling free hugepage. The possible race with hugepage allocation + * or demotion can be prevented by PageHWPoison flag. + */ + if (res == 0) { + unlock_page(head); + res = MF_FAILED; + if (__page_handle_poison(p)) { + page_ref_inc(p); + res = MF_RECOVERED; } + action_result(pfn, MF_MSG_FREE_HUGE, res); + return res == MF_RECOVERED ? 0 : -EBUSY; } - lock_page(head); - /* * The page could have changed compound pages due to race window. * If this happens just bail out. @@ -1554,14 +1617,6 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) page_flags = head->flags; - if (hwpoison_filter(p)) { - if (TestClearPageHWPoison(head)) - num_poisoned_pages_dec(); - put_page(p); - res = -EOPNOTSUPP; - goto out; - } - /* * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so * simply disable it. In order to make it work properly, we need @@ -1588,6 +1643,12 @@ out: unlock_page(head); return res; } +#else +static inline int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb) +{ + return 0; +} +#endif static int memory_failure_dev_pagemap(unsigned long pfn, int flags, struct dev_pagemap *pgmap) @@ -1712,6 +1773,7 @@ int memory_failure(unsigned long pfn, int flags) int res = 0; unsigned long page_flags; bool retry = true; + int hugetlb = 0; if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); @@ -1739,10 +1801,9 @@ int memory_failure(unsigned long pfn, int flags) } try_again: - if (PageHuge(p)) { - res = memory_failure_hugetlb(pfn, flags); + res = try_memory_failure_hugetlb(pfn, flags, &hugetlb); + if (hugetlb) goto unlock_mutex; - } if (TestSetPageHWPoison(p)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", @@ -1800,6 +1861,19 @@ try_again: if (PageTransHuge(hpage)) { /* + * Bail out before SetPageHasHWPoisoned() if hpage is + * huge_zero_page, although PG_has_hwpoisoned is not + * checked in set_huge_zero_page(). + * + * TODO: Handle memory failure of huge_zero_page thoroughly. + */ + if (is_huge_zero_page(hpage)) { + action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); + res = -EBUSY; + goto unlock_mutex; + } + + /* * The flag must be set after the refcount is bumped * otherwise it may race with THP split. * And the flag can't be set in get_hwpoison_page() since diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a2516d31db6c..8c74107a2b15 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1191,8 +1191,10 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, */ static struct page *new_page(struct page *page, unsigned long start) { + struct folio *dst, *src = page_folio(page); struct vm_area_struct *vma; unsigned long address; + gfp_t gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL; vma = find_vma(current->mm, start); while (vma) { @@ -1202,24 +1204,19 @@ static struct page *new_page(struct page *page, unsigned long start) vma = vma->vm_next; } - if (PageHuge(page)) { - return alloc_huge_page_vma(page_hstate(compound_head(page)), + if (folio_test_hugetlb(src)) + return alloc_huge_page_vma(page_hstate(&src->page), vma, address); - } else if (PageTransHuge(page)) { - struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); - if (!thp) - return NULL; - prep_transhuge_page(thp); - return thp; - } + if (folio_test_large(src)) + gfp = GFP_TRANSHUGE; + /* - * if !vma, alloc_page_vma() will use task or system default policy + * if !vma, vma_alloc_folio() will use task or system default policy */ - return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, - vma, address); + dst = vma_alloc_folio(gfp, folio_order(src), vma, address, + folio_test_large(src)); + return &dst->page; } #else @@ -2227,6 +2224,19 @@ out: } EXPORT_SYMBOL(alloc_pages_vma); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage) +{ + struct folio *folio; + + folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr, + hugepage); + if (folio && order > 1) + prep_transhuge_page(&folio->page); + + return folio; +} + /** * alloc_pages - Allocate pages. * @gfp: GFP flags. @@ -2733,6 +2743,7 @@ alloc_new: mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; + atomic_set(&mpol_new->refcnt, 1); goto restart; } diff --git a/mm/migrate.c b/mm/migrate.c index de175e2fdba5..6c31ee1e1c9b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1520,10 +1520,11 @@ out: struct page *alloc_migration_target(struct page *page, unsigned long private) { + struct folio *folio = page_folio(page); struct migration_target_control *mtc; gfp_t gfp_mask; unsigned int order = 0; - struct page *new_page = NULL; + struct folio *new_folio = NULL; int nid; int zidx; @@ -1531,34 +1532,31 @@ struct page *alloc_migration_target(struct page *page, unsigned long private) gfp_mask = mtc->gfp_mask; nid = mtc->nid; if (nid == NUMA_NO_NODE) - nid = page_to_nid(page); + nid = folio_nid(folio); - if (PageHuge(page)) { - struct hstate *h = page_hstate(compound_head(page)); + if (folio_test_hugetlb(folio)) { + struct hstate *h = page_hstate(&folio->page); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); } - if (PageTransHuge(page)) { + if (folio_test_large(folio)) { /* * clear __GFP_RECLAIM to make the migration callback * consistent with regular THP allocations. */ gfp_mask &= ~__GFP_RECLAIM; gfp_mask |= GFP_TRANSHUGE; - order = HPAGE_PMD_ORDER; + order = folio_order(folio); } - zidx = zone_idx(page_zone(page)); + zidx = zone_idx(folio_zone(folio)); if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) gfp_mask |= __GFP_HIGHMEM; - new_page = __alloc_pages(gfp_mask, order, nid, mtc->nmask); - - if (new_page && PageTransHuge(new_page)) - prep_transhuge_page(new_page); + new_folio = __folio_alloc(gfp_mask, order, nid, mtc->nmask); - return new_page; + return &new_folio->page; } #ifdef CONFIG_NUMA @@ -1999,32 +1997,20 @@ static struct page *alloc_misplaced_dst_page(struct page *page, unsigned long data) { int nid = (int) data; - struct page *newpage; - - newpage = __alloc_pages_node(nid, - (GFP_HIGHUSER_MOVABLE | - __GFP_THISNODE | __GFP_NOMEMALLOC | - __GFP_NORETRY | __GFP_NOWARN) & - ~__GFP_RECLAIM, 0); - - return newpage; -} - -static struct page *alloc_misplaced_dst_page_thp(struct page *page, - unsigned long data) -{ - int nid = (int) data; - struct page *newpage; - - newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!newpage) - goto out; - - prep_transhuge_page(newpage); + int order = compound_order(page); + gfp_t gfp = __GFP_THISNODE; + struct folio *new; + + if (order > 0) + gfp |= GFP_TRANSHUGE_LIGHT; + else { + gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY | + __GFP_NOWARN; + gfp &= ~__GFP_RECLAIM; + } + new = __folio_alloc_node(gfp, order, nid); -out: - return newpage; + return &new->page; } static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) @@ -2082,23 +2068,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); - new_page_t *new; - bool compound; int nr_pages = thp_nr_pages(page); /* - * PTE mapped THP or HugeTLB page can't reach here so the page could - * be either base page or THP. And it must be head page if it is - * THP. - */ - compound = PageTransHuge(page); - - if (compound) - new = alloc_misplaced_dst_page_thp; - else - new = alloc_misplaced_dst_page; - - /* * Don't migrate file pages that are mapped in multiple processes * with execute permissions as they are probably shared libraries. */ @@ -2118,9 +2090,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, *new, NULL, node, - MIGRATE_ASYNC, MR_NUMA_MISPLACED, - &nr_succeeded); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED, &nr_succeeded); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/mmap.c b/mm/mmap.c index 3aa839f81e63..313b57d55a63 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2117,14 +2117,6 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) return addr; } -#ifndef arch_get_mmap_end -#define arch_get_mmap_end(addr) (TASK_SIZE) -#endif - -#ifndef arch_get_mmap_base -#define arch_get_mmap_base(addr, base) (base) -#endif - /* Get an address range which is currently unmapped. * For shmat() with addr=0. * diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 459d195d2ff6..f45ff1b7626a 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -1036,6 +1036,18 @@ int mmu_interval_notifier_insert_locked( } EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked); +static bool +mmu_interval_seq_released(struct mmu_notifier_subscriptions *subscriptions, + unsigned long seq) +{ + bool ret; + + spin_lock(&subscriptions->lock); + ret = subscriptions->invalidate_seq != seq; + spin_unlock(&subscriptions->lock); + return ret; +} + /** * mmu_interval_notifier_remove - Remove a interval notifier * @interval_sub: Interval subscription to unregister @@ -1083,7 +1095,7 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub) lock_map_release(&__mmu_notifier_invalidate_range_start_map); if (seq) wait_event(subscriptions->wq, - READ_ONCE(subscriptions->invalidate_seq) != seq); + mmu_interval_seq_released(subscriptions, seq)); /* pairs with mmgrab in mmu_interval_notifier_insert() */ mmdrop(mm); diff --git a/mm/mremap.c b/mm/mremap.c index 9d76da79594d..303d3290b938 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -486,6 +486,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma, pmd_t *old_pmd, *new_pmd; pud_t *old_pud, *new_pud; + if (!len) + return 0; + old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); diff --git a/mm/nommu.c b/mm/nommu.c index 55a9e48a7a02..9d7afc2d959e 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -226,6 +226,8 @@ void *vmalloc(unsigned long size) } EXPORT_SYMBOL(vmalloc); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __weak __alias(__vmalloc); + /* * vzalloc - allocate virtually contiguous memory with zero fill * diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 7ec38194f8e1..49d7df39b02d 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -632,7 +632,7 @@ done: */ set_bit(MMF_OOM_SKIP, &mm->flags); - /* Drop a reference taken by wake_oom_reaper */ + /* Drop a reference taken by queue_oom_reaper */ put_task_struct(tsk); } @@ -644,12 +644,12 @@ static int oom_reaper(void *unused) struct task_struct *tsk = NULL; wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL); - spin_lock(&oom_reaper_lock); + spin_lock_irq(&oom_reaper_lock); if (oom_reaper_list != NULL) { tsk = oom_reaper_list; oom_reaper_list = tsk->oom_reaper_list; } - spin_unlock(&oom_reaper_lock); + spin_unlock_irq(&oom_reaper_lock); if (tsk) oom_reap_task(tsk); @@ -658,22 +658,48 @@ static int oom_reaper(void *unused) return 0; } -static void wake_oom_reaper(struct task_struct *tsk) +static void wake_oom_reaper(struct timer_list *timer) { - /* mm is already queued? */ - if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) - return; + struct task_struct *tsk = container_of(timer, struct task_struct, + oom_reaper_timer); + struct mm_struct *mm = tsk->signal->oom_mm; + unsigned long flags; - get_task_struct(tsk); + /* The victim managed to terminate on its own - see exit_mmap */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + put_task_struct(tsk); + return; + } - spin_lock(&oom_reaper_lock); + spin_lock_irqsave(&oom_reaper_lock, flags); tsk->oom_reaper_list = oom_reaper_list; oom_reaper_list = tsk; - spin_unlock(&oom_reaper_lock); + spin_unlock_irqrestore(&oom_reaper_lock, flags); trace_wake_reaper(tsk->pid); wake_up(&oom_reaper_wait); } +/* + * Give the OOM victim time to exit naturally before invoking the oom_reaping. + * The timers timeout is arbitrary... the longer it is, the longer the worst + * case scenario for the OOM can take. If it is too small, the oom_reaper can + * get in the way and release resources needed by the process exit path. + * e.g. The futex robust list can sit in Anon|Private memory that gets reaped + * before the exit path is able to wake the futex waiters. + */ +#define OOM_REAPER_DELAY (2*HZ) +static void queue_oom_reaper(struct task_struct *tsk) +{ + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) + return; + + get_task_struct(tsk); + timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0); + tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY; + add_timer(&tsk->oom_reaper_timer); +} + static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); @@ -681,7 +707,7 @@ static int __init oom_init(void) } subsys_initcall(oom_init) #else -static inline void wake_oom_reaper(struct task_struct *tsk) +static inline void queue_oom_reaper(struct task_struct *tsk) { } #endif /* CONFIG_MMU */ @@ -932,7 +958,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) rcu_read_unlock(); if (can_oom_reap) - wake_oom_reaper(victim); + queue_oom_reaper(victim); mmdrop(mm); put_task_struct(victim); @@ -968,7 +994,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) task_lock(victim); if (task_will_free_mem(victim)) { mark_oom_victim(victim); - wake_oom_reaper(victim); + queue_oom_reaper(victim); task_unlock(victim); put_task_struct(victim); return; @@ -1067,7 +1093,7 @@ bool out_of_memory(struct oom_control *oc) */ if (task_will_free_mem(current)) { mark_oom_victim(current); - wake_oom_reaper(current); + queue_oom_reaper(current); return true; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2db95780e003..0e42038382c1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -128,7 +128,7 @@ static DEFINE_MUTEX(pcp_batch_high_lock); struct pagesets { local_lock_t lock; }; -static DEFINE_PER_CPU(struct pagesets, pagesets) __maybe_unused = { +static DEFINE_PER_CPU(struct pagesets, pagesets) = { .lock = INIT_LOCAL_LOCK(lock), }; @@ -6131,7 +6131,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) do { zone_type--; zone = pgdat->node_zones + zone_type; - if (managed_zone(zone)) { + if (populated_zone(zone)) { zoneref_set_zone(zone, &zonerefs[nr_zones++]); check_highest_zone(zone_type); } @@ -8919,7 +8919,7 @@ void *__init alloc_large_system_hash(const char *tablename, table = memblock_alloc_raw(size, SMP_CACHE_BYTES); } else if (get_order(size) >= MAX_ORDER || hashdist) { - table = __vmalloc(size, gfp_flags); + table = vmalloc_huge(size, gfp_flags); virt = true; if (table) huge = is_vm_area_hugepages(table); diff --git a/mm/page_io.c b/mm/page_io.c index b417f000b49e..89fbf3cae30f 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -51,54 +51,6 @@ void end_swap_bio_write(struct bio *bio) bio_put(bio); } -static void swap_slot_free_notify(struct page *page) -{ - struct swap_info_struct *sis; - struct gendisk *disk; - swp_entry_t entry; - - /* - * There is no guarantee that the page is in swap cache - the software - * suspend code (at least) uses end_swap_bio_read() against a non- - * swapcache page. So we must check PG_swapcache before proceeding with - * this optimization. - */ - if (unlikely(!PageSwapCache(page))) - return; - - sis = page_swap_info(page); - if (data_race(!(sis->flags & SWP_BLKDEV))) - return; - - /* - * The swap subsystem performs lazy swap slot freeing, - * expecting that the page will be swapped out again. - * So we can avoid an unnecessary write if the page - * isn't redirtied. - * This is good for real swap storage because we can - * reduce unnecessary I/O and enhance wear-leveling - * if an SSD is used as the as swap device. - * But if in-memory swap device (eg zram) is used, - * this causes a duplicated copy between uncompressed - * data in VM-owned memory and compressed data in - * zram-owned memory. So let's free zram-owned memory - * and make the VM-owned decompressed page *dirty*, - * so the page should be swapped out somewhere again if - * we again wish to reclaim it. - */ - disk = sis->bdev->bd_disk; - entry.val = page_private(page); - if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) { - unsigned long offset; - - offset = swp_offset(entry); - - SetPageDirty(page); - disk->fops->swap_slot_free_notify(sis->bdev, - offset); - } -} - static void end_swap_bio_read(struct bio *bio) { struct page *page = bio_first_page_all(bio); @@ -114,7 +66,6 @@ static void end_swap_bio_read(struct bio *bio) } SetPageUptodate(page); - swap_slot_free_notify(page); out: unlock_page(page); WRITE_ONCE(bio->bi_private, NULL); @@ -394,11 +345,6 @@ int swap_readpage(struct page *page, bool synchronous) if (sis->flags & SWP_SYNCHRONOUS_IO) { ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); if (!ret) { - if (trylock_page(page)) { - swap_slot_free_notify(page); - unlock_page(page); - } - count_vm_event(PSWPIN); goto out; } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 1187f9c1ec5b..14a5cda73dee 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -163,7 +163,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); if (unlikely(is_vm_hugetlb_page(vma))) { - unsigned long size = pvmw->nr_pages * PAGE_SIZE; + struct hstate *hstate = hstate_vma(vma); + unsigned long size = huge_page_size(hstate); /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); @@ -173,8 +174,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (!pvmw->pte) return false; - pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm, - pvmw->pte); + pvmw->ptl = huge_pte_lockptr(hstate, mm, pvmw->pte); spin_lock(pvmw->ptl); if (!check_pte(pvmw)) return not_found(pvmw); diff --git a/mm/secretmem.c b/mm/secretmem.c index 098638d3b8a4..3b3cf2892b6a 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -158,6 +158,22 @@ const struct address_space_operations secretmem_aops = { .isolate_page = secretmem_isolate_page, }; +static int secretmem_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry, struct iattr *iattr) +{ + struct inode *inode = d_inode(dentry); + unsigned int ia_valid = iattr->ia_valid; + + if ((ia_valid & ATTR_SIZE) && inode->i_size) + return -EINVAL; + + return simple_setattr(mnt_userns, dentry, iattr); +} + +static const struct inode_operations secretmem_iops = { + .setattr = secretmem_setattr, +}; + static struct vfsmount *secretmem_mnt; static struct file *secretmem_file_create(unsigned long flags) @@ -177,6 +193,7 @@ static struct file *secretmem_file_create(unsigned long flags) mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); + inode->i_op = &secretmem_iops; inode->i_mapping->a_ops = &secretmem_aops; /* pretend we are a normal file with zero size */ diff --git a/mm/shmem.c b/mm/shmem.c index 529c9ad3e926..4b2fea33158e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2513,7 +2513,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) pgoff_t end_index; unsigned long nr, ret; loff_t i_size = i_size_read(inode); - bool got_page; end_index = i_size >> PAGE_SHIFT; if (index > end_index) @@ -2570,24 +2569,34 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) */ if (!offset) mark_page_accessed(page); - got_page = true; + /* + * Ok, we have the page, and it's up-to-date, so + * now we can copy it to user space... + */ + ret = copy_page_to_iter(page, offset, nr, to); + put_page(page); + + } else if (iter_is_iovec(to)) { + /* + * Copy to user tends to be so well optimized, but + * clear_user() not so much, that it is noticeably + * faster to copy the zero page instead of clearing. + */ + ret = copy_page_to_iter(ZERO_PAGE(0), offset, nr, to); } else { - page = ZERO_PAGE(0); - got_page = false; + /* + * But submitting the same page twice in a row to + * splice() - or others? - can result in confusion: + * so don't attempt that optimization on pipes etc. + */ + ret = iov_iter_zero(nr, to); } - /* - * Ok, we have the page, and it's up-to-date, so - * now we can copy it to user space... - */ - ret = copy_page_to_iter(page, offset, nr, to); retval += ret; offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; - if (got_page) - put_page(page); if (!iov_iter_count(to)) break; if (ret < nr) { diff --git a/mm/slab.c b/mm/slab.c index b04e40078bdf..0edb474edef1 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3665,7 +3665,7 @@ EXPORT_SYMBOL(__kmalloc_node_track_caller); #endif /* CONFIG_NUMA */ #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { struct kmem_cache *cachep; unsigned int objnr; diff --git a/mm/slab.h b/mm/slab.h index fd7ae2024897..95eb34174c1b 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -868,7 +868,7 @@ struct kmem_obj_info { void *kp_stack[KS_ADDRS_COUNT]; void *kp_free_stack[KS_ADDRS_COUNT]; }; -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); #endif #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR diff --git a/mm/slab_common.c b/mm/slab_common.c index 6ee64d6208b3..2b3206a2c3b5 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -555,6 +555,13 @@ bool kmem_valid_obj(void *object) } EXPORT_SYMBOL_GPL(kmem_valid_obj); +static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + if (__kfence_obj_info(kpp, object, slab)) + return; + __kmem_obj_info(kpp, object, slab); +} + /** * kmem_dump_obj - Print available slab provenance information * @object: slab object for which to find provenance information. @@ -590,6 +597,8 @@ void kmem_dump_obj(void *object) pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name); else pr_cont(" slab%s", cp); + if (is_kfence_address(object)) + pr_cont(" (kfence)"); if (kp.kp_objp) pr_cont(" start %px", kp.kp_objp); if (kp.kp_data_offset) diff --git a/mm/slob.c b/mm/slob.c index dfa6808dff36..40ea6e2d4ccd 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -463,7 +463,7 @@ out: } #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { kpp->kp_ptr = object; kpp->kp_slab = slab; diff --git a/mm/slub.c b/mm/slub.c index 74d92aa4a3a2..ed5c2c03a47a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4312,7 +4312,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s) } #ifdef CONFIG_PRINTK -void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) { void *base; int __maybe_unused i; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 0cb8e5ef1713..e9bb6db002aa 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -72,12 +72,15 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, _dst_pte = pte_mkdirty(_dst_pte); if (page_in_cache && !vm_shared) writable = false; - if (writable) { - if (wp_copy) - _dst_pte = pte_mkuffd_wp(_dst_pte); - else - _dst_pte = pte_mkwrite(_dst_pte); - } + + /* + * Always mark a PTE as write-protected when needed, regardless of + * VM_WRITE, which the user might change. + */ + if (wp_copy) + _dst_pte = pte_mkuffd_wp(_dst_pte); + else if (writable) + _dst_pte = pte_mkwrite(_dst_pte); dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); diff --git a/mm/util.c b/mm/util.c index 54e5e761a9a9..3492a9e81aa3 100644 --- a/mm/util.c +++ b/mm/util.c @@ -592,8 +592,15 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) return NULL; } - return __vmalloc_node(size, 1, flags, node, - __builtin_return_address(0)); + /* + * kvmalloc() can always use VM_ALLOW_HUGE_VMAP, + * since the callers already cannot assume anything + * about the resulting pointer, and cannot play + * protection games. + */ + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, + node, __builtin_return_address(0)); } EXPORT_SYMBOL(kvmalloc_node); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e163372d3967..cadfbb5155ea 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1671,17 +1671,6 @@ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); -#ifdef CONFIG_X86_64 -/* - * called before a call to iounmap() if the caller wants vm_area_struct's - * immediately freed. - */ -void set_iounmap_nonlazy(void) -{ - atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); -} -#endif /* CONFIG_X86_64 */ - /* * Purges all lazily-freed vmap areas. */ @@ -2664,15 +2653,18 @@ static void __vunmap(const void *addr, int deallocate_pages) vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { - unsigned int page_order = vm_area_page_order(area); - int i, step = 1U << page_order; + int i; - for (i = 0; i < area->nr_pages; i += step) { + for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -step); - __free_pages(page, page_order); + mod_memcg_page_state(page, MEMCG_VMALLOC, -1); + /* + * High-order allocs for huge vmallocs are split, so + * can be freed as an array of order-0 allocations + */ + __free_pages(page, 0); cond_resched(); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2925,12 +2917,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, if (nr != nr_pages_request) break; } - } else - /* - * Compound pages required for remap_vmalloc_page if - * high-order pages. - */ - gfp |= __GFP_COMP; + } /* High-order pages or fallback path if "bulk" fails. */ @@ -2944,6 +2931,15 @@ vm_area_alloc_pages(gfp_t gfp, int nid, page = alloc_pages_node(nid, gfp, order); if (unlikely(!page)) break; + /* + * Higher order allocations must be able to be treated as + * indepdenent small pages by callers (as they can with + * small-page vmallocs). Some drivers do their own refcounting + * on vmalloc_to_page() pages, some use page->mapping, + * page->lru, etc. + */ + if (order) + split_page(page, order); /* * Careful, we allocate and map page-order pages, but @@ -3003,11 +2999,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, atomic_long_add(area->nr_pages, &nr_vmalloc_pages); if (gfp_mask & __GFP_ACCOUNT) { - int i, step = 1U << page_order; + int i; - for (i = 0; i < area->nr_pages; i += step) - mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, - step); + for (i = 0; i < area->nr_pages; i++) + mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1); } /* @@ -3106,7 +3101,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return NULL; } - if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) { + if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { unsigned long size_per_node; /* @@ -3273,21 +3268,24 @@ void *vmalloc(unsigned long size) EXPORT_SYMBOL(vmalloc); /** - * vmalloc_no_huge - allocate virtually contiguous memory using small pages - * @size: allocation size + * vmalloc_huge - allocate virtually contiguous memory, allow huge pages + * @size: allocation size + * @gfp_mask: flags for the page level allocator * - * Allocate enough non-huge pages to cover @size from the page level + * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. + * If @size is greater than or equal to PMD_SIZE, allow using + * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_no_huge(unsigned long size) +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) { return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL, PAGE_KERNEL, VM_NO_HUGE_VMAP, + gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_no_huge); +EXPORT_SYMBOL_GPL(vmalloc_huge); /** * vzalloc - allocate virtually contiguous memory with zero fill diff --git a/mm/workingset.c b/mm/workingset.c index 8a3828acc0bf..592569a8974c 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -355,7 +355,7 @@ void workingset_refault(struct folio *folio, void *shadow) mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_delayed(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 84312c836549..fe803bee419a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -670,7 +670,7 @@ static void le_conn_timeout(struct work_struct *work) /* Disable LE Advertising */ le_disable_advertising(hdev); hci_dev_lock(hdev); - hci_le_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); + hci_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); hci_dev_unlock(hdev); return; } @@ -873,7 +873,7 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) EXPORT_SYMBOL(hci_get_route); /* This function requires the caller holds hdev->lock */ -void hci_le_conn_failed(struct hci_conn *conn, u8 status) +static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; struct hci_conn_params *params; @@ -886,8 +886,6 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) params->conn = NULL; } - conn->state = BT_CLOSED; - /* If the status indicates successful cancellation of * the attempt (i.e. Unknown Connection Id) there's no point of * notifying failure since we'll go back to keep trying to @@ -899,10 +897,6 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); - hci_connect_cfm(conn, status); - - hci_conn_del(conn); - /* Since we may have temporarily stopped the background scanning in * favor of connection establishment, we should restart it. */ @@ -914,6 +908,28 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) hci_enable_advertising(hdev); } +/* This function requires the caller holds hdev->lock */ +void hci_conn_failed(struct hci_conn *conn, u8 status) +{ + struct hci_dev *hdev = conn->hdev; + + bt_dev_dbg(hdev, "status 0x%2.2x", status); + + switch (conn->type) { + case LE_LINK: + hci_le_conn_failed(conn, status); + break; + case ACL_LINK: + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + break; + } + + conn->state = BT_CLOSED; + hci_connect_cfm(conn, status); + hci_conn_del(conn); +} + static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index abaabfae19cc..66451661283c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2834,7 +2834,7 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the - * hci_le_conn_failed function which is triggered by the HCI + * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) @@ -2859,7 +2859,7 @@ static void hci_cs_le_ext_create_conn(struct hci_dev *hdev, u8 status) bt_dev_dbg(hdev, "status 0x%2.2x", status); /* All connection failure handling is taken care of by the - * hci_le_conn_failed function which is triggered by the HCI + * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ if (status) @@ -3067,18 +3067,20 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, { struct hci_ev_conn_complete *ev = data; struct hci_conn *conn; + u8 status = ev->status; - if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for invalid handle"); - return; - } - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { + /* In case of error status and there is no connection pending + * just unlock as there is nothing to cleanup. + */ + if (ev->status) + goto unlock; + /* Connection may not exist if auto-connected. Check the bredr * allowlist to see if this device is allowed to auto connect. * If link is an ACL type, create a connection class @@ -3122,8 +3124,14 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } - if (!ev->status) { + if (!status) { conn->handle = __le16_to_cpu(ev->handle); + if (conn->handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + conn->handle, HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + goto done; + } if (conn->type == ACL_LINK) { conn->state = BT_CONFIG; @@ -3164,19 +3172,14 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, hci_send_cmd(hdev, HCI_OP_CHANGE_CONN_PTYPE, sizeof(cp), &cp); } - } else { - conn->state = BT_CLOSED; - if (conn->type == ACL_LINK) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, ev->status); } if (conn->type == ACL_LINK) hci_sco_setup(conn, ev->status); - if (ev->status) { - hci_connect_cfm(conn, ev->status); - hci_conn_del(conn); +done: + if (status) { + hci_conn_failed(conn, status); } else if (ev->link_type == SCO_LINK) { switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_CVSD: @@ -3185,7 +3188,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, break; } - hci_connect_cfm(conn, ev->status); + hci_connect_cfm(conn, status); } unlock: @@ -4676,6 +4679,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, { struct hci_ev_sync_conn_complete *ev = data; struct hci_conn *conn; + u8 status = ev->status; switch (ev->link_type) { case SCO_LINK: @@ -4690,12 +4694,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, return; } - if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete for invalid handle"); - return; - } - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); + bt_dev_dbg(hdev, "status 0x%2.2x", status); hci_dev_lock(hdev); @@ -4729,9 +4728,17 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } - switch (ev->status) { + switch (status) { case 0x00: conn->handle = __le16_to_cpu(ev->handle); + if (conn->handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", + conn->handle, HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + conn->state = BT_CLOSED; + break; + } + conn->state = BT_CONNECTED; conn->type = ev->link_type; @@ -4775,8 +4782,8 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, } } - hci_connect_cfm(conn, ev->status); - if (ev->status) + hci_connect_cfm(conn, status); + if (status) hci_conn_del(conn); unlock: @@ -5527,11 +5534,6 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, struct smp_irk *irk; u8 addr_type; - if (handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Ignoring HCI_LE_Connection_Complete for invalid handle"); - return; - } - hci_dev_lock(hdev); /* All controllers implicitly stop advertising in the event of a @@ -5541,6 +5543,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn = hci_lookup_le_connect(hdev); if (!conn) { + /* In case of error status and there is no connection pending + * just unlock as there is nothing to cleanup. + */ + if (status) + goto unlock; + conn = hci_conn_add(hdev, LE_LINK, bdaddr, role); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); @@ -5603,8 +5611,14 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = ev_bdaddr_type(hdev, conn->dst_type, NULL); + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", handle, + HCI_CONN_HANDLE_MAX); + status = HCI_ERROR_INVALID_PARAMETERS; + } + if (status) { - hci_le_conn_failed(conn, status); + hci_conn_failed(conn, status); goto unlock; } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 8f4c5698913d..13600bf120b0 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4408,12 +4408,21 @@ static int hci_reject_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, static int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { + int err; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: return hci_disconnect_sync(hdev, conn, reason); case BT_CONNECT: - return hci_connect_cancel_sync(hdev, conn); + err = hci_connect_cancel_sync(hdev, conn); + /* Cleanup hci_conn object if it cannot be cancelled as it + * likelly means the controller and host stack are out of sync. + */ + if (err) + hci_conn_failed(conn, err); + + return err; case BT_CONNECT2: return hci_reject_conn_sync(hdev, conn, reason); default: diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e7b9c2636d10..af709c182674 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -108,6 +108,7 @@ struct xdp_test_data { struct page_pool *pp; struct xdp_frame **frames; struct sk_buff **skbs; + struct xdp_mem_info mem; u32 batch_size; u32 frame_cnt; }; @@ -147,7 +148,6 @@ static void xdp_test_run_init_page(struct page *page, void *arg) static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_ctx) { - struct xdp_mem_info mem = {}; struct page_pool *pp; int err = -ENOMEM; struct page_pool_params pp_params = { @@ -174,7 +174,7 @@ static int xdp_test_run_setup(struct xdp_test_data *xdp, struct xdp_buff *orig_c } /* will copy 'mem.id' into pp->xdp_mem_id */ - err = xdp_reg_mem_model(&mem, MEM_TYPE_PAGE_POOL, pp); + err = xdp_reg_mem_model(&xdp->mem, MEM_TYPE_PAGE_POOL, pp); if (err) goto err_mmodel; @@ -202,6 +202,7 @@ err_skbs: static void xdp_test_run_teardown(struct xdp_test_data *xdp) { + xdp_unreg_mem_model(&xdp->mem); page_pool_destroy(xdp->pp); kfree(xdp->frames); kfree(xdp->skbs); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 8cc44c367231..18affda2b522 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -353,6 +353,8 @@ static int br_switchdev_vlan_attr_replay(struct net_device *br_dev, attr.orig_dev = br_dev; vg = br_vlan_group(br); + if (!vg) + return 0; list_for_each_entry(v, &vg->vlan_list, vlist) { if (v->msti) { diff --git a/net/can/isotp.c b/net/can/isotp.c index bafb0fb5f0e0..ff5d7870294e 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -906,6 +906,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; + s64 hrtimer_sec = 0; int off; int err; @@ -1004,7 +1005,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) isotp_create_fframe(cf, so, ae); /* start timeout for FC */ - hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); + hrtimer_sec = 1; + hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), + HRTIMER_MODE_REL_SOFT); } /* send the first or only CAN frame */ @@ -1017,6 +1020,11 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); + + /* no transmission -> no timeout monitoring */ + if (hrtimer_sec) + hrtimer_cancel(&so->txtimer); + goto err_out_drop; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 1c5815530e0d..83eb97c94e83 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2385,7 +2385,11 @@ again: if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) { err = -ENOSPC; } else { - pr_warn_ratelimited("FULL or reached pool quota\n"); + if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) + pr_warn_ratelimited("cluster is full (osdmap FULL)\n"); + else + pr_warn_ratelimited("pool %lld is full or reached quota\n", + req->r_t.base_oloc.pool); req->r_t.paused = true; maybe_request_map(osdc); } diff --git a/net/core/dev.c b/net/core/dev.c index 8c6c08446556..1461c2d9dec8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10304,7 +10304,7 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, } EXPORT_SYMBOL(netdev_stats_to_stats64); -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) { struct net_device_core_stats __percpu *p; @@ -10315,11 +10315,7 @@ struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ - p = READ_ONCE(dev->core_stats); - if (!p) - return NULL; - - return this_cpu_ptr(p); + return READ_ONCE(dev->core_stats); } EXPORT_SYMBOL(netdev_core_stats_alloc); @@ -10356,9 +10352,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); - storage->rx_dropped += local_read(&core_stats->rx_dropped); - storage->tx_dropped += local_read(&core_stats->tx_dropped); - storage->rx_nohandler += local_read(&core_stats->rx_nohandler); + storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); + storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); + storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); } } return storage; diff --git a/net/core/filter.c b/net/core/filter.c index a7044e98765e..64470a727ef7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7016,24 +7016,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (!th->ack || th->rst || th->syn) return -ENOENT; + if (unlikely(iph_len < sizeof(struct iphdr))) + return -EINVAL; + if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; cookie = ntohl(th->ack_seq) - 1; - switch (sk->sk_family) { - case AF_INET: - if (unlikely(iph_len < sizeof(struct iphdr))) + /* Both struct iphdr and struct ipv6hdr have the version field at the + * same offset so we can cast to the shorter header (struct iphdr). + */ + switch (((struct iphdr *)iph)->version) { + case 4: + if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); break; #if IS_BUILTIN(CONFIG_IPV6) - case AF_INET6: + case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; + if (sk->sk_family != AF_INET6) + return -EINVAL; + ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); break; #endif /* CONFIG_IPV6 */ diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 03b6e649c428..6f7ec72016dc 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1032,7 +1032,7 @@ bool __skb_flow_dissect(const struct net *net, key_eth_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS, target_container); - memcpy(key_eth_addrs, ð->h_dest, sizeof(*key_eth_addrs)); + memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs)); } proto_again: @@ -1183,6 +1183,7 @@ proto_again: VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; + key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 349480ef68a5..8b6b5e72b217 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -159,10 +159,8 @@ static int bpf_output(struct net *net, struct sock *sk, struct sk_buff *skb) return dst->lwtstate->orig_output(net, sk, skb); } -static int xmit_check_hhlen(struct sk_buff *skb) +static int xmit_check_hhlen(struct sk_buff *skb, int hh_len) { - int hh_len = skb_dst(skb)->dev->hard_header_len; - if (skb_headroom(skb) < hh_len) { int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); @@ -274,6 +272,7 @@ static int bpf_xmit(struct sk_buff *skb) bpf = bpf_lwt_lwtunnel(dst->lwtstate); if (bpf->xmit.prog) { + int hh_len = dst->dev->hard_header_len; __be16 proto = skb->protocol; int ret; @@ -291,7 +290,7 @@ static int bpf_xmit(struct sk_buff *skb) /* If the header was expanded, headroom might be too * small for L2 header to come, expand as needed. */ - ret = xmit_check_hhlen(skb); + ret = xmit_check_hhlen(skb, hh_len); if (unlikely(ret)) return ret; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 159c9c61e6af..d1381ea6d52e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5242,6 +5242,8 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, *prividx = attr_id_l3_stats; size_l3 = rtnl_offload_xstats_get_size_stats(dev, t_l3); + if (!size_l3) + goto skip_l3_stats; attr = nla_reserve_64bit(skb, attr_id_l3_stats, size_l3, IFLA_OFFLOAD_XSTATS_UNSPEC); if (!attr) @@ -5253,6 +5255,7 @@ static int rtnl_offload_xstats_fill(struct sk_buff *skb, struct net_device *dev, return err; have_data = true; +skip_l3_stats: *prividx = 0; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 10bde7c6db44..30b523fa4ad2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5276,11 +5276,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* The page pool signature of struct page will eventually figure out - * which pages can be recycled or not but for now let's prohibit slab - * allocated and page_pool allocated SKBs from being coalesced. + /* In general, avoid mixing slab allocated and page_pool allocated + * pages within the same SKB. However when @to is not pp_recycle and + * @from is cloned, we can transition frag pages from page_pool to + * reference counted. + * + * On the other hand, don't allow coalescing two pp_recycle SKBs if + * @from is cloned, in case the SKB is using page_pool fragment + * references (PP_FLAG_PAGE_FRAG). Since we only take full page + * references for cloned SKBs at the moment that would result in + * inconsistent reference counts. */ - if (to->pp_recycle != from->pp_recycle) + if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index ca6af86964bc..cf933225df32 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -562,7 +562,6 @@ static void dsa_port_teardown(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; struct dsa_switch *ds = dp->ds; - struct net_device *slave; if (!dp->setup) return; @@ -584,11 +583,9 @@ static void dsa_port_teardown(struct dsa_port *dp) dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_USER: - slave = dp->slave; - - if (slave) { + if (dp->slave) { + dsa_slave_destroy(dp->slave); dp->slave = NULL; - dsa_slave_destroy(slave); } break; } @@ -1147,17 +1144,17 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) if (err) goto teardown_cpu_ports; - err = dsa_tree_setup_master(dst); + err = dsa_tree_setup_ports(dst); if (err) goto teardown_switches; - err = dsa_tree_setup_ports(dst); + err = dsa_tree_setup_master(dst); if (err) - goto teardown_master; + goto teardown_ports; err = dsa_tree_setup_lags(dst); if (err) - goto teardown_ports; + goto teardown_master; dst->setup = true; @@ -1165,10 +1162,10 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) return 0; -teardown_ports: - dsa_tree_teardown_ports(dst); teardown_master: dsa_tree_teardown_master(dst); +teardown_ports: + dsa_tree_teardown_ports(dst); teardown_switches: dsa_tree_teardown_switches(dst); teardown_cpu_ports: @@ -1186,10 +1183,10 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_lags(dst); - dsa_tree_teardown_ports(dst); - dsa_tree_teardown_master(dst); + dsa_tree_teardown_ports(dst); + dsa_tree_teardown_switches(dst); dsa_tree_teardown_cpu_ports(dst); diff --git a/net/dsa/master.c b/net/dsa/master.c index 991c2930d631..2851e44c4cf0 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -335,11 +335,24 @@ static const struct attribute_group dsa_group = { .attrs = dsa_slave_attrs, }; +static void dsa_master_reset_mtu(struct net_device *dev) +{ + int err; + + err = dev_set_mtu(dev, ETH_DATA_LEN); + if (err) + netdev_dbg(dev, + "Unable to reset MTU to exclude DSA overheads\n"); +} + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { + const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; struct device_link *consumer_link; - int ret; + int mtu, ret; + + mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); /* The DSA master must use SET_NETDEV_DEV for this to work. */ consumer_link = device_link_add(ds->dev, dev->dev.parent, @@ -349,6 +362,15 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) "Failed to create a device link to DSA switch %s\n", dev_name(ds->dev)); + /* The switch driver may not implement ->port_change_mtu(), case in + * which dsa_slave_change_mtu() will not update the master MTU either, + * so we need to do that here. + */ + ret = dev_set_mtu(dev, mtu); + if (ret) + netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n", + ret, mtu); + /* If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get * sent to the tag format's receive function. @@ -384,6 +406,7 @@ void dsa_master_teardown(struct net_device *dev) sysfs_remove_group(&dev->dev.kobj, &dsa_group); dsa_netdev_ops_set(dev, NULL); dsa_master_ethtool_teardown(dev); + dsa_master_reset_mtu(dev); dsa_master_set_promiscuity(dev, -1); dev->dsa_ptr = NULL; diff --git a/net/dsa/port.c b/net/dsa/port.c index 32d472a82241..cdc56ba11f52 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1620,8 +1620,10 @@ int dsa_port_link_register_of(struct dsa_port *dp) if (ds->ops->phylink_mac_link_down) ds->ops->phylink_mac_link_down(ds, port, MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); + of_node_put(phy_np); return dsa_port_phylink_register(dp); } + of_node_put(phy_np); return 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 41c69a6e7854..8022d50584db 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -285,7 +285,7 @@ static void dsa_port_manage_cpu_flood(struct dsa_port *dp) if (other_dp->slave->flags & IFF_ALLMULTI) flags.val |= BR_MCAST_FLOOD; if (other_dp->slave->flags & IFF_PROMISC) - flags.val |= BR_FLOOD; + flags.val |= BR_FLOOD | BR_MCAST_FLOOD; } err = dsa_port_pre_bridge_flags(dp, flags, NULL); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index f64b805303cd..eb204ad36eee 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -21,6 +21,14 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, struct dsa_port *dp = dsa_slave_to_port(dev); u8 *tag; + /* Calculate checksums (if required) before adding the trailer tag to + * avoid including it in calculations. That would lead to wrong + * checksums after the switch strips the tag. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + return NULL; + /* Tag encoding */ tag = skb_put(skb, HELLCREEK_TAG_LEN); *tag = BIT(dp->index); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 70e6c87fbe3d..d747166bb291 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -446,7 +446,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz; /* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { @@ -456,8 +455,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * return err; } - allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index cc8e84ef2ae4..ccb62038f6a4 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -889,8 +889,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, } if (cfg->fc_oif || cfg->fc_gw_family) { - struct fib_nh *nh = fib_info_nh(fi, 0); + struct fib_nh *nh; + + /* cannot match on nexthop object attributes */ + if (fi->nh) + return 1; + nh = fib_info_nh(fi, 0); if (cfg->fc_encap) { if (fib_encap_match(net, cfg->fc_encap_type, cfg->fc_encap, nh, cfg, extack)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 99db2e41ed10..aacee9dd771b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -459,14 +459,12 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, - tunnel->parms.o_flags, proto, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + flags, proto, tunnel->parms.o_key, + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -504,7 +502,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -581,7 +579,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) } gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -605,8 +603,8 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), - key->tos & ~INET_ECN_MASK, 0, skb->mark, - skb_get_hash(skb)); + key->tos & ~INET_ECN_MASK, dev_net(dev), 0, + skb->mark, skb_get_hash(skb)); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 5a473319d3a5..94017a8c3994 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -294,8 +294,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark, 0); + RT_TOS(iph->tos), dev_net(dev), + tunnel->parms.link, tunnel->fwmark, 0); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -570,7 +570,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), RT_TOS(tos), - 0, skb->mark, skb_get_hash(skb)); + dev_net(dev), 0, skb->mark, skb_get_hash(skb)); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; @@ -726,7 +726,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->parms.o_key, RT_TOS(tos), + dev_net(dev), tunnel->parms.link, tunnel->fwmark, skb_get_hash(skb)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ /dev/null diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2cb3b852d148..f33c31dd7366 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -281,6 +281,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, EXPORT_SYMBOL(cookie_ecn_ok); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { @@ -297,6 +298,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return NULL; treq = tcp_rsk(req); + + /* treq->af_specific might be used to perform TCP_MD5 lookup */ + treq->af_specific = af_ops; + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); @@ -364,7 +369,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2088f93fa37b..60f99e9fb6d1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3867,7 +3867,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_process_tlp_ack(sk, ack, flag); if (tcp_ack_is_dubious(sk, flag)) { - if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) { + if (!(flag & (FLAG_SND_UNA_ADVANCED | + FLAG_NOT_DUP | FLAG_DSACKING_ACK))) { num_dupack = 1; /* Consider if pure acks were aggregated in tcp_add_backlog() */ if (!(flag & FLAG_DATA)) @@ -5454,7 +5455,17 @@ static void tcp_new_space(struct sock *sk) INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); } -static void tcp_check_space(struct sock *sk) +/* Caller made space either from: + * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced) + * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt) + * + * We might be able to generate EPOLLOUT to the application if: + * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2 + * 2) notsent amount (tp->write_seq - tp->snd_nxt) became + * small enough that tcp_stream_memory_free() decides it + * is time to generate EPOLLOUT. + */ +void tcp_check_space(struct sock *sk) { /* pairs with tcp_poll() */ smp_mb(); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6366df7aaf2a..6854bb1fb32b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -531,7 +531,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) + if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req))) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9ede847f4199..1ca2f28c9981 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -82,6 +82,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); + tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index fbab921670cc..9a8e014d9b5b 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -74,27 +74,32 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) * * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is * called multiple times. We favor the information from the most recently - * sent skb, i.e., the skb with the highest prior_delivered count. + * sent skb, i.e., the skb with the most recently sent time and the highest + * sequence. */ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + u64 tx_tstamp; if (!scb->tx.delivered_mstamp) return; + tx_tstamp = tcp_skb_timestamp_us(skb); if (!rs->prior_delivered || - after(scb->tx.delivered, rs->prior_delivered)) { + tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp, + scb->end_seq, rs->last_end_seq)) { rs->prior_delivered_ce = scb->tx.delivered_ce; rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; + rs->last_end_seq = scb->end_seq; /* Record send time of most recently ACKed packet: */ - tp->first_tx_mstamp = tcp_skb_timestamp_us(skb); + tp->first_tx_mstamp = tx_tstamp; /* Find the duration of the "send phase" of this window: */ rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp, scb->tx.first_tx_mstamp); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 55d604c9b3b3..f2120e92caf1 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -482,7 +482,6 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; - unsigned int allocsz; if (x->encap) { int err = esp6_output_encap(x, skb, esp); @@ -491,8 +490,8 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info return err; } - allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); - if (allocsz > ESP_SKB_FRAG_MAXSIZE) + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 8753e9cec326..5136959b3dc5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -724,6 +724,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, { struct ip6_tnl *tunnel = netdev_priv(dev); __be16 protocol; + __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -733,16 +734,13 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr; - if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) - return -ENOMEM; - /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; if (tunnel->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; - __be16 flags; + int tun_hlen; tun_info = skb_tunnel_info_txcheck(skb); if (IS_ERR(tun_info) || @@ -760,21 +758,27 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, dsfield = key->tos; flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); - tunnel->tun_hlen = gre_calc_hlen(flags); + tun_hlen = gre_calc_hlen(flags); - gre_build_header(skb, tunnel->tun_hlen, + if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) + return -ENOMEM; + + gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) + return -ENOMEM; + + flags = tunnel->parms.o_flags; - gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) + : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -1052,7 +1056,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* Push GRE header. */ proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) : htons(ETH_P_ERSPAN2); - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e23f058166af..fa63ef2bd99c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -485,7 +485,7 @@ int ip6_forward(struct sk_buff *skb) goto drop; if (!net->ipv6.devconf_all->disable_policy && - !idev->cnf.disable_policy && + (!idev || !idev->cnf.disable_policy) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index a9775c830194..4e74bc61a3db 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1653,7 +1653,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, mifi_t mifi; struct net *net = sock_net(sk); struct mr_table *mrt; - bool do_wrmifwhole; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1761,6 +1760,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: { + bool do_wrmifwhole; int v; if (optlen != sizeof(v)) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 1da332450d98..8ce60ab89015 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,14 +24,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff { const struct ipv6hdr *iph = ipv6_hdr(skb); struct sock *sk = sk_to_full_sk(sk_partial); + struct net_device *dev = skb_dst(skb)->dev; struct flow_keys flkeys; unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { - .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, @@ -39,6 +38,13 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff }; int err; + if (sk && sk->sk_bound_dev_if) + fl6.flowi6_oif = sk->sk_bound_dev_if; + else if (strict) + fl6.flowi6_oif = dev->ifindex; + else + fl6.flowi6_oif = l3mdev_master_ifindex(dev); + fib6_rules_early_flow_dissect(net, skb, &fl6, &flkeys); dst = ip6_route_output(net, sk, &fl6); err = dst->error; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2fa10e60cccd..c4b6ce017d5e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3292,6 +3292,7 @@ static int ip6_dst_gc(struct dst_ops *ops) int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + unsigned int val; int entries; entries = dst_entries_get_fast(ops); @@ -3302,13 +3303,13 @@ static int ip6_dst_gc(struct dst_ops *ops) entries <= rt_max_size) goto out; - net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); + fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) - net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; + atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: - net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; + val = atomic_read(&net->ipv6.ip6_rt_gc_expire); + atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); return entries > rt_max_size; } @@ -4484,7 +4485,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) struct inet6_dev *idev; int type; - if (netif_is_l3_master(skb->dev) && + if (netif_is_l3_master(skb->dev) || dst->dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else @@ -6509,7 +6510,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; - net->ipv6.ip6_rt_gc_expire = 30*HZ; + atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index d1b61d00368e..9cc123f000fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); if (!req) goto out; diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index 4eb8892fb2ff..ca10916340b0 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -147,7 +147,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) dev = dev_get_by_index_rcu(net, ifindex); while (dev && !netif_is_l3_master(dev)) - dev = netdev_master_upper_dev_get(dev); + dev = netdev_master_upper_dev_get_rcu(dev); return dev ? dev->ifindex : 0; } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 9479f2787ea7..88d9cc945a21 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -441,7 +441,7 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, #define PRINT_HT_CAP(_cond, _str) \ do { \ if (_cond) \ - p += scnprintf(p, sizeof(buf)+buf-p, "\t" _str "\n"); \ + p += scnprintf(p, bufsz + buf - p, "\t" _str "\n"); \ } while (0) char *buf, *p; int i; diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index f0702d920d8d..e22b0cbb2f35 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -93,13 +93,13 @@ out_release: static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); - const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr); int rc, addrlen = msg->msg_namelen; struct sock *sk = sock->sk; struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb; struct mctp_route *rt; - struct sk_buff *skb; + struct sk_buff *skb = NULL; + int hlen; if (addr) { const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER | @@ -129,6 +129,34 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (addr->smctp_network == MCTP_NET_ANY) addr->smctp_network = mctp_default_net(sock_net(sk)); + /* direct addressing */ + if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, + extaddr, msg->msg_name); + struct net_device *dev; + + rc = -EINVAL; + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex); + /* check for correct halen */ + if (dev && extaddr->smctp_halen == dev->addr_len) { + hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr); + rc = 0; + } + rcu_read_unlock(); + if (rc) + goto err_free; + rt = NULL; + } else { + rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, + addr->smctp_addr.s_addr); + if (!rt) { + rc = -EHOSTUNREACH; + goto err_free; + } + hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr); + } + skb = sock_alloc_send_skb(sk, hlen + 1 + len, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) @@ -147,8 +175,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) cb = __mctp_cb(skb); cb->net = addr->smctp_network; - /* direct addressing */ - if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + if (!rt) { + /* fill extended address in cb */ DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, extaddr, msg->msg_name); @@ -159,17 +187,9 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } cb->ifindex = extaddr->smctp_ifindex; + /* smctp_halen is checked above */ cb->halen = extaddr->smctp_halen; memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen); - - rt = NULL; - } else { - rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, - addr->smctp_addr.s_addr); - if (!rt) { - rc = -EHOSTUNREACH; - goto err_free; - } } rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, diff --git a/net/mctp/device.c b/net/mctp/device.c index f49be882e98e..99a3bda8852f 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -313,6 +313,7 @@ void mctp_dev_hold(struct mctp_dev *mdev) void mctp_dev_put(struct mctp_dev *mdev) { if (mdev && refcount_dec_and_test(&mdev->refs)) { + kfree(mdev->addrs); dev_put(mdev->dev); kfree_rcu(mdev, rcu); } @@ -441,7 +442,6 @@ static void mctp_unregister(struct net_device *dev) mctp_route_remove_dev(mdev); mctp_neigh_remove_dev(mdev); - kfree(mdev->addrs); mctp_dev_put(mdev); } diff --git a/net/mctp/route.c b/net/mctp/route.c index d5e7db83fe9d..3b24b8d18b5b 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -503,6 +503,11 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) if (cb->ifindex) { /* direct route; use the hwaddr we stashed in sendmsg */ + if (cb->halen != skb->dev->addr_len) { + /* sanity check, sendmsg should have already caught this */ + kfree_skb(skb); + return -EMSGSIZE; + } daddr = cb->haddr; } else { /* If lookup fails let the device handle daddr==NULL */ @@ -512,7 +517,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol), daddr, skb->dev->dev_addr, skb->len); - if (rc) { + if (rc < 0) { kfree_skb(skb); return -EHOSTUNREACH; } @@ -756,7 +761,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, { const unsigned int hlen = sizeof(struct mctp_hdr); struct mctp_hdr *hdr, *hdr2; - unsigned int pos, size; + unsigned int pos, size, headroom; struct sk_buff *skb2; int rc; u8 seq; @@ -770,6 +775,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, return -EMSGSIZE; } + /* keep same headroom as the original skb */ + headroom = skb_headroom(skb); + /* we've got the header */ skb_pull(skb, hlen); @@ -777,7 +785,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* size of message payload */ size = min(mtu - hlen, skb->len - pos); - skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL); + skb2 = alloc_skb(headroom + hlen + size, GFP_KERNEL); if (!skb2) { rc = -ENOMEM; break; @@ -793,7 +801,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, skb_set_owner_w(skb2, skb->sk); /* establish packet */ - skb_reserve(skb2, MCTP_HEADER_MAXLEN); + skb_reserve(skb2, headroom); skb_reset_network_header(skb2); skb_put(skb2, hlen + size); skb2->transport_header = skb2->network_header + hlen; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 2c467c422dc6..fb67f1ca2495 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,7 +1495,7 @@ int __init ip_vs_conn_init(void) pr_info("Connection hash table configured " "(size=%d, memory=%ldKbytes)\n", ip_vs_conn_tab_size, - (long)(ip_vs_conn_tab_size*sizeof(struct list_head))/1024); + (long)(ip_vs_conn_tab_size*sizeof(*ip_vs_conn_tab))/1024); IP_VS_DBG(0, "Each connection entry needs %zd bytes at least\n", sizeof(struct ip_vs_conn)); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 8ec55cd72572..204a5cdff5b1 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -556,24 +556,14 @@ static bool tcp_in_window(struct nf_conn *ct, } } - } else if (((state->state == TCP_CONNTRACK_SYN_SENT - && dir == IP_CT_DIR_ORIGINAL) - || (state->state == TCP_CONNTRACK_SYN_RECV - && dir == IP_CT_DIR_REPLY)) - && after(end, sender->td_end)) { + } else if (tcph->syn && + after(end, sender->td_end) && + (state->state == TCP_CONNTRACK_SYN_SENT || + state->state == TCP_CONNTRACK_SYN_RECV)) { /* * RFC 793: "if a TCP is reinitialized ... then it need * not wait at all; it must only be sure to use sequence * numbers larger than those recently used." - */ - sender->td_end = - sender->td_maxend = end; - sender->td_maxwin = (win == 0 ? 1 : win); - - tcp_options(skb, dataoff, tcph, sender); - } else if (tcph->syn && dir == IP_CT_DIR_REPLY && - state->state == TCP_CONNTRACK_SYN_SENT) { - /* Retransmitted syn-ack, or syn (simultaneous open). * * Re-init state for this direction, just like for the first * syn(-ack) reply, it might differ in seq, ack or tcp options. @@ -581,7 +571,8 @@ static bool tcp_in_window(struct nf_conn *ct, tcp_init_sender(sender, receiver, skb, dataoff, tcph, end, win); - if (!tcph->ack) + + if (dir == IP_CT_DIR_REPLY && !tcph->ack) return true; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 3e1afd10a9b6..55aa55b252b2 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -823,7 +823,7 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, -#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD) +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = { .procname = "nf_flowtable_udp_timeout", .maxlen = sizeof(unsigned int), diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5ddfdb2adaf1..16c3a39689f4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5526,7 +5526,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, int err, i, k; for (i = 0; i < set->num_exprs; i++) { - expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL); + expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT); if (!expr) goto err_expr; @@ -9363,7 +9363,7 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) } EXPORT_SYMBOL_GPL(nft_parse_u32_check); -static unsigned int nft_parse_register(const struct nlattr *attr, u32 *preg) +static int nft_parse_register(const struct nlattr *attr, u32 *preg) { unsigned int reg; diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 38caa66632b4..f590ee1c8a1b 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -290,7 +290,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track, if (!track->regs[priv->sreg].selector) return false; - bitwise = nft_expr_priv(expr); + bitwise = nft_expr_priv(track->regs[priv->dreg].selector); if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector && track->regs[priv->sreg].num_reg == 0 && track->regs[priv->dreg].bitwise && @@ -442,7 +442,7 @@ static bool nft_bitwise_fast_reduce(struct nft_regs_track *track, if (!track->regs[priv->sreg].selector) return false; - bitwise = nft_expr_priv(expr); + bitwise = nft_expr_priv(track->regs[priv->dreg].selector); if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector && track->regs[priv->dreg].bitwise && track->regs[priv->dreg].bitwise->ops == expr->ops && diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 9de1462e4ac4..d657f999a11b 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -77,7 +77,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx, invert = true; } - priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL); + priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL_ACCOUNT); if (!priv->list) return -ENOMEM; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index da9083605a61..f4d3573e8782 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -62,7 +62,7 @@ static int nft_counter_do_init(const struct nlattr * const tb[], struct nft_counter __percpu *cpu_stats; struct nft_counter *this_cpu; - cpu_stats = alloc_percpu(struct nft_counter); + cpu_stats = alloc_percpu_gfp(struct nft_counter, GFP_KERNEL_ACCOUNT); if (cpu_stats == NULL) return -ENOMEM; diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 43d0d4aadb1f..bb15a55dad5c 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -30,7 +30,7 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, u64 last_jiffies; int err; - last = kzalloc(sizeof(*last), GFP_KERNEL); + last = kzalloc(sizeof(*last), GFP_KERNEL_ACCOUNT); if (!last) return -ENOMEM; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index d4a6cf3cd697..04ea8b9bf202 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -90,7 +90,7 @@ static int nft_limit_init(struct nft_limit_priv *priv, priv->rate); } - priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL); + priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT); if (!priv->limit) return -ENOMEM; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index d7db57ed3bc1..e6b0df68feea 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -90,7 +90,7 @@ static int nft_quota_do_init(const struct nlattr * const tb[], return -EOPNOTSUPP; } - priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL); + priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL_ACCOUNT); if (!priv->consumed) return -ENOMEM; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index d600a566da32..7325bee7d144 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -349,7 +349,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, *ext = &rbe->ext; return -EEXIST; } else { - p = &parent->rb_left; + overlap = false; + if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; } } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index bd3792f080ed..05ae5a338b6f 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -37,12 +37,11 @@ static void nft_socket_wildcard(const struct nft_pktinfo *pkt, #ifdef CONFIG_SOCK_CGROUP_DATA static noinline bool -nft_sock_get_eval_cgroupv2(u32 *dest, const struct nft_pktinfo *pkt, u32 level) +nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo *pkt, u32 level) { - struct sock *sk = skb_to_full_sk(pkt->skb); struct cgroup *cgrp; - if (!sk || !sk_fullsock(sk) || !net_eq(nft_net(pkt), sock_net(sk))) + if (!sk_fullsock(sk)) return false; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); @@ -55,6 +54,32 @@ nft_sock_get_eval_cgroupv2(u32 *dest, const struct nft_pktinfo *pkt, u32 level) } #endif +static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) +{ + const struct net_device *indev = nft_in(pkt); + const struct sk_buff *skb = pkt->skb; + struct sock *sk = NULL; + + if (!indev) + return NULL; + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, indev); + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, indev); + break; +#endif + default: + WARN_ON_ONCE(1); + break; + } + + return sk; +} + static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -68,20 +93,7 @@ static void nft_socket_eval(const struct nft_expr *expr, sk = NULL; if (!sk) - switch(nft_pf(pkt)) { - case NFPROTO_IPV4: - sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt)); - break; -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) - case NFPROTO_IPV6: - sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt)); - break; -#endif - default: - WARN_ON_ONCE(1); - regs->verdict.code = NFT_BREAK; - return; - } + sk = nft_socket_do_lookup(pkt); if (!sk) { regs->verdict.code = NFT_BREAK; @@ -109,7 +121,7 @@ static void nft_socket_eval(const struct nft_expr *expr, break; #ifdef CONFIG_SOCK_CGROUP_DATA case NFT_SOCKET_CGROUPV2: - if (!nft_sock_get_eval_cgroupv2(dest, pkt, priv->level)) { + if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) { regs->verdict.code = NFT_BREAK; return; } @@ -225,6 +237,16 @@ static bool nft_socket_reduce(struct nft_regs_track *track, return nft_expr_reduce_bitwise(track, expr); } +static int nft_socket_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT)); +} + static struct nft_expr_type nft_socket_type; static const struct nft_expr_ops nft_socket_ops = { .type = &nft_socket_type, @@ -232,6 +254,7 @@ static const struct nft_expr_ops nft_socket_ops = { .eval = nft_socket_eval, .init = nft_socket_init, .dump = nft_socket_dump, + .validate = nft_socket_validate, .reduce = nft_socket_reduce, }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 47a876ccd288..05a3795eac8e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2263,6 +2263,13 @@ static int netlink_dump(struct sock *sk) * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); + + /* Make sure malicious BPF programs can not read unitialized memory + * from skb->head -> skb->data + */ + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index d2537383a3e8..6a193cce2a75 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -560,6 +560,10 @@ static int nci_close_device(struct nci_dev *ndev) mutex_lock(&ndev->req_lock); if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { + /* Need to flush the cmd wq in case + * there is a queued/running cmd_work + */ + flush_workqueue(ndev->cmd_wq); del_timer_sync(&ndev->cmd_timer); del_timer_sync(&ndev->data_timer); mutex_unlock(&ndev->req_lock); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 7056cb1b8ba0..1b5d73079dc9 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1051,7 +1051,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb, int rem = nla_len(attr); bool dont_clone_flow_key; - /* The first action is always 'OVS_CLONE_ATTR_ARG'. */ + /* The first action is always 'OVS_CLONE_ATTR_EXEC'. */ clone_arg = nla_data(attr); dont_clone_flow_key = nla_get_u32(clone_arg); actions = nla_next(clone_arg, &rem); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index cc282a58b75b..4c09cf8a0ab2 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2317,6 +2317,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size) return sfa; } +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len); + +static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action) +{ + const struct nlattr *a; + int rem; + + nla_for_each_nested(a, action, rem) { + switch (nla_type(a)) { + case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL: + case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER: + ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); + break; + } + } +} + +static void ovs_nla_free_clone_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_CLONE_ATTR_EXEC: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + +static void ovs_nla_free_dec_ttl_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + + switch (nla_type(a)) { + case OVS_DEC_TTL_ATTR_ACTION: + ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); + break; + } +} + +static void ovs_nla_free_sample_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_SAMPLE_ATTR_ARG: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + static void ovs_nla_free_set_action(const struct nlattr *a) { const struct nlattr *ovs_key = nla_data(a); @@ -2330,25 +2386,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a) } } -void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) { const struct nlattr *a; int rem; - if (!sf_acts) + /* Whenever new actions are added, the need to update this + * function should be considered. + */ + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23); + + if (!actions) return; - nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) { + nla_for_each_attr(a, actions, len, rem) { switch (nla_type(a)) { - case OVS_ACTION_ATTR_SET: - ovs_nla_free_set_action(a); + case OVS_ACTION_ATTR_CHECK_PKT_LEN: + ovs_nla_free_check_pkt_len_action(a); + break; + + case OVS_ACTION_ATTR_CLONE: + ovs_nla_free_clone_action(a); break; + case OVS_ACTION_ATTR_CT: ovs_ct_free_action(a); break; + + case OVS_ACTION_ATTR_DEC_TTL: + ovs_nla_free_dec_ttl_action(a); + break; + + case OVS_ACTION_ATTR_SAMPLE: + ovs_nla_free_sample_action(a); + break; + + case OVS_ACTION_ATTR_SET: + ovs_nla_free_set_action(a); + break; } } +} + +void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +{ + if (!sf_acts) + return; + ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len); kfree(sf_acts); } @@ -2380,7 +2465,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { + if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) { OVS_NLERR(log, "Flow action size exceeds max %u", MAX_ACTIONS_BUFSIZE); return ERR_PTR(-EMSGSIZE); @@ -3458,7 +3543,9 @@ static int clone_action_to_attr(const struct nlattr *attr, if (!start) return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(attr), rem, skb); + /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */ + attr = nla_next(nla_data(attr), &rem); + err = ovs_nla_put_actions(attr, rem, skb); if (err) nla_nest_cancel(skb, start); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c39c09899fd0..002d2b9c69dd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2858,8 +2858,9 @@ tpacket_error: status = TP_STATUS_SEND_REQUEST; err = po->xmit(skb); - if (unlikely(err > 0)) { - err = net_xmit_errno(err); + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ @@ -3060,8 +3061,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->no_fcs = 1; err = po->xmit(skb); - if (err > 0 && (err = net_xmit_errno(err)) != 0) - goto out_unlock; + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); + if (err) + goto out_unlock; + } dev_put(dev); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 25bbc4cc8b13..cc7e30733feb 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -115,6 +115,8 @@ static __net_exit void rxrpc_exit_net(struct net *net) rxnet->live = false; del_timer_sync(&rxnet->peer_keepalive_timer); cancel_work_sync(&rxnet->peer_keepalive_work); + /* Remove the timer again as the worker may have restarted it. */ + del_timer_sync(&rxnet->peer_keepalive_timer); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet); rxrpc_destroy_all_peers(rxnet); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2957f8f5cea7..f0699f39afdb 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1672,10 +1672,10 @@ static int tcf_chain_tp_insert(struct tcf_chain *chain, if (chain->flushing) return -EAGAIN; + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); if (*chain_info->pprev == chain->filter_chain) tcf_chain0_head_change(chain, tp); tcf_proto_get(tp); - RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); rcu_assign_pointer(*chain_info->pprev, tp); return 0; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c80fc49c0da1..ed5e6f08e74a 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1013,6 +1013,7 @@ static int fl_set_key_mpls(struct nlattr **tb, static void fl_set_key_vlan(struct nlattr **tb, __be16 ethertype, int vlan_id_key, int vlan_prio_key, + int vlan_next_eth_type_key, struct flow_dissector_key_vlan *key_val, struct flow_dissector_key_vlan *key_mask) { @@ -1031,6 +1032,11 @@ static void fl_set_key_vlan(struct nlattr **tb, } key_val->vlan_tpid = ethertype; key_mask->vlan_tpid = cpu_to_be16(~0); + if (tb[vlan_next_eth_type_key]) { + key_val->vlan_eth_type = + nla_get_be16(tb[vlan_next_eth_type_key]); + key_mask->vlan_eth_type = cpu_to_be16(~0); + } } static void fl_set_key_flag(u32 flower_key, u32 flower_mask, @@ -1602,8 +1608,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (eth_type_vlan(ethertype)) { fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID, - TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, - &mask->vlan); + TCA_FLOWER_KEY_VLAN_PRIO, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, + &key->vlan, &mask->vlan); if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) { ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]); @@ -1611,6 +1618,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_CVLAN_ID, TCA_FLOWER_KEY_CVLAN_PRIO, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, &key->cvlan, &mask->cvlan); fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, @@ -3002,13 +3010,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, goto nla_put_failure; if (mask->basic.n_proto) { - if (mask->cvlan.vlan_tpid) { + if (mask->cvlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, key->basic.n_proto)) goto nla_put_failure; - } else if (mask->vlan.vlan_tpid) { + } else if (mask->vlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, - key->basic.n_proto)) + key->vlan.vlan_eth_type)) goto nla_put_failure; } } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index cf5649292ee0..4d27300c287c 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -386,14 +386,19 @@ static int u32_init(struct tcf_proto *tp) return 0; } -static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) +static void __u32_destroy_key(struct tc_u_knode *n) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); tcf_exts_destroy(&n->exts); - tcf_exts_put_net(&n->exts); if (ht && --ht->refcnt == 0) kfree(ht); + kfree(n); +} + +static void u32_destroy_key(struct tc_u_knode *n, bool free_pf) +{ + tcf_exts_put_net(&n->exts); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); @@ -402,8 +407,7 @@ static int u32_destroy_key(struct tc_u_knode *n, bool free_pf) if (free_pf) free_percpu(n->pcpu_success); #endif - kfree(n); - return 0; + __u32_destroy_key(n); } /* u32_delete_key_rcu should be called when free'ing a copied @@ -811,10 +815,6 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); - /* bump reference count as long as we hold pointer to structure */ - if (ht) - ht->refcnt++; - #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update * so we must keep them in tact. When the node is later destroyed @@ -836,6 +836,10 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, return NULL; } + /* bump reference count as long as we hold pointer to structure */ + if (ht) + ht->refcnt++; + return new; } @@ -900,13 +904,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, extack); if (err) { - u32_destroy_key(new, false); + __u32_destroy_key(new); return err; } err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { - u32_destroy_key(new, false); + __u32_destroy_key(new); return err; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 377f896bdedc..b9c71a304d39 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -417,7 +417,8 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, { struct taprio_sched *q = qdisc_priv(sch); - if (skb->sk && sock_flag(skb->sk, SOCK_TXTIME)) { + /* sk_flags are only safe to use on full sockets. */ + if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) return qdisc_drop(skb, sch, to_free); } else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index a18609f608fb..e213aaf45d67 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -914,6 +914,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) ctx->asoc->base.sk->sk_err = -error; return; } + ctx->asoc->stats.octrlchunks++; break; case SCTP_CID_ABORT: @@ -938,7 +939,10 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) case SCTP_CID_HEARTBEAT: if (chunk->pmtu_probe) { - sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); + error = sctp_packet_singleton(ctx->transport, + chunk, ctx->gfp); + if (!error) + ctx->asoc->stats.octrlchunks++; break; } fallthrough; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b3815b568e8e..463c4a58d2c3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -458,6 +458,10 @@ void sctp_generate_reconf_event(struct timer_list *t) goto out_unlock; } + /* This happens when the response arrives after the timer is triggered. */ + if (!asoc->strreset_chunk) + goto out_unlock; + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_RECONF), asoc->state, asoc->ep, asoc, diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7f342bc12735..52edee1322fc 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -781,7 +781,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, } } - if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } @@ -932,7 +932,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, /* Set peer label for connection. */ if (security_sctp_assoc_established((struct sctp_association *)asoc, - chunk->skb)) + chunk->head_skb ?: chunk->skb)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Verify that the chunk length for the COOKIE-ACK is OK. @@ -2262,7 +2262,7 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } /* Update socket peer label if first association. */ - if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3e1a9600be5e..7b0427658056 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5636,7 +5636,7 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) * Set the daddr and initialize id to something more random and also * copy over any ip options. */ - sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk); + sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk); sp->pf->copy_ip_options(sk, sock->sk); /* Populate the fields of the newsk from the oldsk and migrate the diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index f0d118e9f155..fce16b9d6e1a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -121,6 +121,7 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, bool *own_req) { struct smc_sock *smc; + struct sock *child; smc = smc_clcsock_user_data(sk); @@ -134,8 +135,17 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk, } /* passthrough to original syn recv sock fct */ - return smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, - own_req); + child = smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash, + own_req); + /* child must not inherit smc or its ops */ + if (child) { + rcu_assign_sk_user_data(child, NULL); + + /* v4-mapped sockets don't inherit parent ops. Don't restore. */ + if (inet_csk(child)->icsk_af_ops == inet_csk(sk)->icsk_af_ops) + inet_csk(child)->icsk_af_ops = smc->ori_af_ops; + } + return child; drop: dst_release(dst); @@ -233,11 +243,27 @@ struct proto smc_proto6 = { }; EXPORT_SYMBOL_GPL(smc_proto6); +static void smc_fback_restore_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = NULL; + + smc_clcsock_restore_cb(&clcsk->sk_state_change, &smc->clcsk_state_change); + smc_clcsock_restore_cb(&clcsk->sk_data_ready, &smc->clcsk_data_ready); + smc_clcsock_restore_cb(&clcsk->sk_write_space, &smc->clcsk_write_space); + smc_clcsock_restore_cb(&clcsk->sk_error_report, &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); +} + static void smc_restore_fallback_changes(struct smc_sock *smc) { if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ smc->clcsock->file->private_data = smc->sk.sk_socket; smc->clcsock->file = NULL; + smc_fback_restore_callbacks(smc); } } @@ -363,6 +389,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); mutex_init(&smc->clcsock_release_lock); + smc_init_saved_callbacks(smc); return sk; } @@ -734,47 +761,73 @@ out: static void smc_fback_state_change(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_state_change); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_data_ready(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_data_ready); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_write_space(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_write_space); + read_unlock_bh(&clcsk->sk_callback_lock); } static void smc_fback_error_report(struct sock *clcsk) { - struct smc_sock *smc = - smc_clcsock_user_data(clcsk); + struct smc_sock *smc; - if (!smc) - return; - smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report); + read_lock_bh(&clcsk->sk_callback_lock); + smc = smc_clcsock_user_data(clcsk); + if (smc) + smc_fback_forward_wakeup(smc, clcsk, + smc->clcsk_error_report); + read_unlock_bh(&clcsk->sk_callback_lock); +} + +static void smc_fback_replace_callbacks(struct smc_sock *smc) +{ + struct sock *clcsk = smc->clcsock->sk; + + write_lock_bh(&clcsk->sk_callback_lock); + clcsk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + + smc_clcsock_replace_cb(&clcsk->sk_state_change, smc_fback_state_change, + &smc->clcsk_state_change); + smc_clcsock_replace_cb(&clcsk->sk_data_ready, smc_fback_data_ready, + &smc->clcsk_data_ready); + smc_clcsock_replace_cb(&clcsk->sk_write_space, smc_fback_write_space, + &smc->clcsk_write_space); + smc_clcsock_replace_cb(&clcsk->sk_error_report, smc_fback_error_report, + &smc->clcsk_error_report); + + write_unlock_bh(&clcsk->sk_callback_lock); } static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { - struct sock *clcsk; int rc = 0; mutex_lock(&smc->clcsock_release_lock); @@ -782,10 +835,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) rc = -EBADF; goto out; } - clcsk = smc->clcsock->sk; - if (smc->use_fallback) - goto out; smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); @@ -800,18 +850,7 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * in smc sk->sk_wq and they should be woken up * as clcsock's wait queue is woken up. */ - smc->clcsk_state_change = clcsk->sk_state_change; - smc->clcsk_data_ready = clcsk->sk_data_ready; - smc->clcsk_write_space = clcsk->sk_write_space; - smc->clcsk_error_report = clcsk->sk_error_report; - - clcsk->sk_state_change = smc_fback_state_change; - clcsk->sk_data_ready = smc_fback_data_ready; - clcsk->sk_write_space = smc_fback_write_space; - clcsk->sk_error_report = smc_fback_error_report; - - smc->clcsock->sk->sk_user_data = - (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_fback_replace_callbacks(smc); } out: mutex_unlock(&smc->clcsock_release_lock); @@ -1465,6 +1504,8 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_state = SMC_CLOSED; if (rc == -EPIPE || rc == -EAGAIN) smc->sk.sk_err = EPIPE; + else if (rc == -ECONNREFUSED) + smc->sk.sk_err = ECONNREFUSED; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); sock_put(&smc->sk); /* passive closing */ @@ -1584,6 +1625,19 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) * function; switch it back to the original sk_data_ready function */ new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready; + + /* if new clcsock has also inherited the fallback-specific callback + * functions, switch them back to the original ones. + */ + if (lsmc->use_fallback) { + if (lsmc->clcsk_state_change) + new_clcsock->sk->sk_state_change = lsmc->clcsk_state_change; + if (lsmc->clcsk_write_space) + new_clcsock->sk->sk_write_space = lsmc->clcsk_write_space; + if (lsmc->clcsk_error_report) + new_clcsock->sk->sk_error_report = lsmc->clcsk_error_report; + } + (*new_smc)->clcsock = new_clcsock; out: return rc; @@ -2343,17 +2397,20 @@ out: static void smc_clcsock_data_ready(struct sock *listen_clcsock) { - struct smc_sock *lsmc = - smc_clcsock_user_data(listen_clcsock); + struct smc_sock *lsmc; + read_lock_bh(&listen_clcsock->sk_callback_lock); + lsmc = smc_clcsock_user_data(listen_clcsock); if (!lsmc) - return; + goto out; lsmc->clcsk_data_ready(listen_clcsock); if (lsmc->sk.sk_state == SMC_LISTEN) { sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */ if (!queue_work(smc_tcp_ls_wq, &lsmc->tcp_listen_work)) sock_put(&lsmc->sk); } +out: + read_unlock_bh(&listen_clcsock->sk_callback_lock); } static int smc_listen(struct socket *sock, int backlog) @@ -2385,10 +2442,12 @@ static int smc_listen(struct socket *sock, int backlog) /* save original sk_data_ready function and establish * smc-specific sk_data_ready function */ - smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready; - smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + smc_clcsock_replace_cb(&smc->clcsock->sk->sk_data_ready, + smc_clcsock_data_ready, &smc->clcsk_data_ready); + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); /* save original ops */ smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops; @@ -2403,7 +2462,11 @@ static int smc_listen(struct socket *sock, int backlog) rc = kernel_listen(smc->clcsock, backlog); if (rc) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); + smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); goto out; } sk->sk_max_ack_backlog = backlog; @@ -2664,8 +2727,10 @@ static int smc_shutdown(struct socket *sock, int how) if (smc->use_fallback) { rc = kernel_sock_shutdown(smc->clcsock, how); sk->sk_shutdown = smc->clcsock->sk->sk_shutdown; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (sk->sk_shutdown == SHUTDOWN_MASK) { sk->sk_state = SMC_CLOSED; + sock_put(sk); + } goto out; } switch (how) { diff --git a/net/smc/smc.h b/net/smc/smc.h index ea0620529ebe..5ed765ea0c73 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -288,12 +288,41 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +static inline void smc_init_saved_callbacks(struct smc_sock *smc) +{ + smc->clcsk_state_change = NULL; + smc->clcsk_data_ready = NULL; + smc->clcsk_write_space = NULL; + smc->clcsk_error_report = NULL; +} + static inline struct smc_sock *smc_clcsock_user_data(const struct sock *clcsk) { return (struct smc_sock *) ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY); } +/* save target_cb in saved_cb, and replace target_cb with new_cb */ +static inline void smc_clcsock_replace_cb(void (**target_cb)(struct sock *), + void (*new_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + /* only save once */ + if (!*saved_cb) + *saved_cb = *target_cb; + *target_cb = new_cb; +} + +/* restore target_cb to saved_cb, and reset saved_cb to NULL */ +static inline void smc_clcsock_restore_cb(void (**target_cb)(struct sock *), + void (**saved_cb)(struct sock *)) +{ + if (!*saved_cb) + return; + *target_cb = *saved_cb; + *saved_cb = NULL; +} + extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ extern struct workqueue_struct *smc_close_wq; /* wq for close work */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index ce27399b38b1..f9f3f59c79de 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -191,7 +191,8 @@ static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, flags, SMC_NETLINK_DUMP_UEID); if (!hdr) return -ENOMEM; - snprintf(ueid_str, sizeof(ueid_str), "%s", ueid); + memcpy(ueid_str, ueid, SMC_MAX_EID_LEN); + ueid_str[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; @@ -252,7 +253,8 @@ int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb) goto end; smc_ism_get_system_eid(&seid); - snprintf(seid_str, sizeof(seid_str), "%s", seid); + memcpy(seid_str, seid, SMC_MAX_EID_LEN); + seid_str[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SEID_ENTRY, seid_str)) goto err; read_lock(&smc_clc_eid_table.lock); diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 676cb2333d3c..31db7438857c 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -214,8 +214,11 @@ again: sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); /* wake up accept */ if (smc->clcsock && smc->clcsock->sk) { - smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + write_lock_bh(&smc->clcsock->sk->sk_callback_lock); + smc_clcsock_restore_cb(&smc->clcsock->sk->sk_data_ready, + &smc->clcsk_data_ready); smc->clcsock->sk->sk_user_data = NULL; + write_unlock_bh(&smc->clcsock->sk->sk_callback_lock); rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } smc_close_cleanup_listen(sk); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7984f8883472..7055ed10e316 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -311,8 +311,9 @@ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || - !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, - IB_DEVICE_NAME_MAX - 1)) { + (ibdev->ibdev->dev.parent && + !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, + IB_DEVICE_NAME_MAX - 1))) { goto out; } } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8bf2af8546d2..af0174d7ce5a 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1127,6 +1127,8 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data) struct rpc_task *task; task = rpc_new_task(task_setup_data); + if (IS_ERR(task)) + return task; if (!RPC_IS_ASYNC(task)) task->tk_flags |= RPC_TASK_CRED_NOREF; @@ -1227,6 +1229,11 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) * Create an rpc_task to send the data */ task = rpc_new_task(&task_setup_data); + if (IS_ERR(task)) { + xprt_free_bc_request(req); + return task; + } + xprt_init_bc_request(req, task); task->tk_action = call_bc_encode; @@ -1858,6 +1865,9 @@ call_encode(struct rpc_task *task) xprt_request_dequeue_xprt(task); /* Encode here so that rpcsec_gss can use correct sequence number. */ rpc_xdr_encode(task); + /* Add task to reply queue before transmission to avoid races */ + if (task->tk_status == 0 && rpc_reply_expected(task)) + task->tk_status = xprt_request_enqueue_receive(task); /* Did the encode result in an error condition? */ if (task->tk_status != 0) { /* Was the error nonfatal? */ @@ -1881,9 +1891,6 @@ call_encode(struct rpc_task *task) return; } - /* Add task to reply queue before transmission to avoid races */ - if (rpc_reply_expected(task)) - xprt_request_enqueue_receive(task); xprt_request_enqueue_transmit(task); out: task->tk_action = call_transmit; @@ -2200,6 +2207,7 @@ call_transmit_status(struct rpc_task *task) * socket just returned a connection error, * then hold onto the transport lock. */ + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2283,6 +2291,7 @@ call_bc_transmit_status(struct rpc_task *task) case -ENOTCONN: case -EPIPE: break; + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2365,6 +2374,11 @@ call_status(struct rpc_task *task) case -EPIPE: case -EAGAIN: break; + case -ENFILE: + case -ENOBUFS: + case -ENOMEM: + rpc_delay(task, HZ>>2); + break; case -EIO: /* shutdown or soft timeout */ goto out_exit; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b258b87a3ec2..7f70c1e608b7 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -1128,6 +1128,11 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) if (task == NULL) { task = rpc_alloc_task(); + if (task == NULL) { + rpc_release_calldata(setup_data->callback_ops, + setup_data->callback_data); + return ERR_PTR(-ENOMEM); + } flags = RPC_TASK_DYNAMIC; } diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 05b38bf68316..71ba4cf513bc 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -221,12 +221,6 @@ static int xprt_send_kvec(struct socket *sock, struct msghdr *msg, static int xprt_send_pagedata(struct socket *sock, struct msghdr *msg, struct xdr_buf *xdr, size_t base) { - int err; - - err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); - if (err < 0) - return err; - iov_iter_bvec(&msg->msg_iter, WRITE, xdr->bvec, xdr_buf_pagecount(xdr), xdr->page_len + xdr->page_base); return xprt_sendmsg(sock, msg, base + xdr->page_base); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 297c49855038..5b59e2103526 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1231,6 +1231,8 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; dr->xprt_hlen = rqstp->rq_xprt_hlen; + dr->xprt_ctxt = rqstp->rq_xprt_ctxt; + rqstp->rq_xprt_ctxt = NULL; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; @@ -1269,6 +1271,7 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_xprt_hlen = dr->xprt_hlen; rqstp->rq_daddr = dr->daddr; rqstp->rq_respages = rqstp->rq_pages; + rqstp->rq_xprt_ctxt = dr->xprt_ctxt; svc_xprt_received(rqstp->rq_xprt); return (dr->argslen<<2) - dr->xprt_hlen; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 478f857cdaed..cc35ec433400 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -579,15 +579,18 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) if (svc_xprt_is_dead(xprt)) goto out_notconn; + err = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (err < 0) + goto out_unlock; + err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); if (err == -ECONNREFUSED) { /* ICMP error on earlier request. */ err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); } + xdr_free_bvec(xdr); trace_svcsock_udp_send(xprt, err); - +out_unlock: mutex_unlock(&xprt->xpt_mutex); if (err < 0) return err; @@ -1096,7 +1099,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr, int ret; *sentp = 0; - xdr_alloc_bvec(xdr, GFP_KERNEL); + ret = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (ret < 0) + return ret; ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len); if (ret < 0) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 515501f79290..86d62cffba0d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -69,10 +69,11 @@ /* * Local functions */ -static void xprt_init(struct rpc_xprt *xprt, struct net *net); +static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); -static void xprt_destroy(struct rpc_xprt *xprt); -static void xprt_request_init(struct rpc_task *task); +static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); +static int xprt_request_prepare(struct rpc_rqst *req); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -929,12 +930,7 @@ void xprt_connect(struct rpc_task *task) if (!xprt_lock_write(xprt, task)) return; - if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) { - trace_xprt_disconnect_cleanup(xprt); - xprt->ops->close(xprt); - } - - if (!xprt_connected(xprt)) { + if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; rpc_sleep_on_timeout(&xprt->pending, task, NULL, xprt_request_timeout(task->tk_rqstp)); @@ -1143,16 +1139,19 @@ xprt_request_need_enqueue_receive(struct rpc_task *task, struct rpc_rqst *req) * @task: RPC task * */ -void +int xprt_request_enqueue_receive(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; + int ret; if (!xprt_request_need_enqueue_receive(task, req)) - return; + return 0; - xprt_request_prepare(task->tk_rqstp); + ret = xprt_request_prepare(task->tk_rqstp); + if (ret) + return ret; spin_lock(&xprt->queue_lock); /* Update the softirq receive buffer */ @@ -1166,6 +1165,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) /* Turn off autodisconnect */ del_singleshot_timer_sync(&xprt->timer); + return 0; } /** @@ -1452,14 +1452,16 @@ xprt_request_dequeue_xprt(struct rpc_task *task) * * Calls into the transport layer to do whatever is needed to prepare * the request for transmission or receive. + * Returns error, or zero. */ -void +static int xprt_request_prepare(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; if (xprt->ops->prepare_request) - xprt->ops->prepare_request(req); + return xprt->ops->prepare_request(req); + return 0; } /** diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index cf76a6ad127b..864131a9fc6e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -831,7 +831,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_err; if (ret == 0) goto out_drop; - rqstp->rq_xprt_hlen = ret; + rqstp->rq_xprt_hlen = 0; if (svc_rdma_is_reverse_direction_reply(xprt, ctxt)) goto out_backchannel; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 78af7518f263..8ab64ea46870 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -822,12 +822,17 @@ static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait) return ret; } -static void +static int xs_stream_prepare_request(struct rpc_rqst *req) { + gfp_t gfp = rpc_task_gfp_mask(); + int ret; + + ret = xdr_alloc_bvec(&req->rq_snd_buf, gfp); + if (ret < 0) + return ret; xdr_free_bvec(&req->rq_rcv_buf); - req->rq_task->tk_status = xdr_alloc_bvec( - &req->rq_rcv_buf, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + return xdr_alloc_bvec(&req->rq_rcv_buf, gfp); } /* @@ -879,7 +884,7 @@ static int xs_local_send_request(struct rpc_rqst *req) /* Close the stream if the previous transmission was incomplete */ if (xs_send_request_was_aborted(transport, req)) { - xs_close(xprt); + xprt_force_disconnect(xprt); return -ENOTCONN; } @@ -915,7 +920,7 @@ static int xs_local_send_request(struct rpc_rqst *req) -status); fallthrough; case -EPIPE: - xs_close(xprt); + xprt_force_disconnect(xprt); status = -ENOTCONN; } @@ -956,6 +961,9 @@ static int xs_udp_send_request(struct rpc_rqst *req) if (!xprt_request_get_cong(xprt, req)) return -EBADSLT; + status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (status < 0) + return status; req->rq_xtime = ktime_get(); status = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, 0, &sent); @@ -1185,6 +1193,16 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + /* + * Make sure we're calling this in a context from which it is safe + * to call __fput_sync(). In practice that means rpciod and the + * system workqueue. + */ + if (!(current->flags & PF_WQ_WORKER)) { + WARN_ON_ONCE(1); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + return; + } if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); @@ -1208,7 +1226,7 @@ static void xs_reset_transport(struct sock_xprt *transport) mutex_unlock(&transport->recv_mutex); trace_rpc_socket_close(xprt, sock); - fput(filp); + __fput_sync(filp); xprt_disconnect_done(xprt); } @@ -2544,6 +2562,9 @@ static int bc_sendto(struct rpc_rqst *req) int err; req->rq_xtime = ktime_get(); + err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (err < 0) + return err; err = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, marker, &sent); xdr_free_bvec(xdr); if (err < 0 || sent != (xdr->len + sizeof(marker))) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 12f7b56771d9..af875ad4a822 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -483,11 +483,13 @@ handle_error: copy = min_t(size_t, size, (pfrag->size - pfrag->offset)); copy = min_t(size_t, copy, (max_open_record_len - record->len)); - rc = tls_device_copy_data(page_address(pfrag->page) + - pfrag->offset, copy, msg_iter); - if (rc) - goto handle_error; - tls_append_frag(record, pfrag, copy); + if (copy) { + rc = tls_device_copy_data(page_address(pfrag->page) + + pfrag->offset, copy, msg_iter); + if (rc) + goto handle_error; + tls_append_frag(record, pfrag, copy); + } size -= copy; if (!size) { diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0024a692f0f8..a8976ef95528 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1496,7 +1496,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (prot->version == TLS_1_3_VERSION || prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) memcpy(iv + iv_offset, tls_ctx->rx.iv, - crypto_aead_ivsize(ctx->aead_recv)); + prot->iv_size + prot->salt_size); else memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ee1c2b6b6971..21e808fcb676 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -528,7 +528,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { .len = IEEE80211_MAX_MESH_ID_LEN }, [NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT, - [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 }, + /* allow 3 for NUL-termination, we used to declare this NLA_STRING */ + [NL80211_ATTR_REG_ALPHA2] = NLA_POLICY_RANGE(NLA_BINARY, 2, 3), [NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED }, [NL80211_ATTR_BSS_CTS_PROT] = { .type = NLA_U8 }, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index b2fdac96bab0..4a6d86432910 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2018,11 +2018,13 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, /* this is a nontransmitting bss, we need to add it to * transmitting bss' list if it is not there */ + spin_lock_bh(&rdev->bss_lock); if (cfg80211_add_nontrans_list(non_tx_data->tx_bss, &res->pub)) { if (__cfg80211_unlink_bss(rdev, res)) rdev->bss_generation++; } + spin_unlock_bh(&rdev->bss_lock); } trace_cfg80211_return_bss(&res->pub); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 2c34caee0fd1..3a9348030e20 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -639,7 +639,7 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ - if (xsk_no_wakeup(sk)) + if (xs->zc && xsk_no_wakeup(sk)) return 0; pool = xs->pool; @@ -967,6 +967,19 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xp_get_pool(umem_xs->pool); xs->pool = umem_xs->pool; + + /* If underlying shared umem was created without Tx + * ring, allocate Tx descs array that Tx batching API + * utilizes + */ + if (xs->tx && !xs->pool->tx_descs) { + err = xp_alloc_tx_descs(xs->pool, xs); + if (err) { + xp_put_pool(xs->pool); + sockfd_put(sock); + goto out_unlock; + } + } } xdp_get_umem(umem_xs->umem); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index af040ffa14ff..87bdd71c7bb6 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -42,6 +42,16 @@ void xp_destroy(struct xsk_buff_pool *pool) kvfree(pool); } +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs) +{ + pool->tx_descs = kvcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), + GFP_KERNEL); + if (!pool->tx_descs) + return -ENOMEM; + + return 0; +} + struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem) { @@ -59,11 +69,9 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, if (!pool->heads) goto out; - if (xs->tx) { - pool->tx_descs = kcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), GFP_KERNEL); - if (!pool->tx_descs) + if (xs->tx) + if (xp_alloc_tx_descs(pool, xs)) goto out; - } pool->chunk_mask = ~((u64)umem->chunk_size - 1); pool->addrs_cnt = umem->size; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 19aa994f5d2c..00bd0ecff5a1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2593,12 +2593,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { __u32 mark = 0; + int oif; if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; - dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, + oif = fl->flowi_oif ? : fl->flowi_l3mdev; + dst = xfrm_dst_lookup(xfrm[i], tos, oif, &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 9717e6f6fb31..33c1ed581522 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -231,7 +231,7 @@ objtool_args = \ $(if $(part-of-module), --module) \ $(if $(CONFIG_X86_KERNEL_IBT), --lto --ibt) \ $(if $(CONFIG_FRAME_POINTER),, --no-fp) \ - $(if $(CONFIG_GCOV_KERNEL)$(CONFIG_LTO_CLANG), --no-unreachable)\ + $(if $(CONFIG_GCOV_KERNEL), --no-unreachable) \ $(if $(CONFIG_RETPOLINE), --retpoline) \ $(if $(CONFIG_X86_SMAP), --uaccess) \ $(if $(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL), --mcount) \ diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c index 589454bce930..8425da41de0d 100644 --- a/scripts/gcc-plugins/latent_entropy_plugin.c +++ b/scripts/gcc-plugins/latent_entropy_plugin.c @@ -86,25 +86,31 @@ static struct plugin_info latent_entropy_plugin_info = { .help = "disable\tturn off latent entropy instrumentation\n", }; -static unsigned HOST_WIDE_INT seed; -/* - * get_random_seed() (this is a GCC function) generates the seed. - * This is a simple random generator without any cryptographic security because - * the entropy doesn't come from here. - */ +static unsigned HOST_WIDE_INT deterministic_seed; +static unsigned HOST_WIDE_INT rnd_buf[32]; +static size_t rnd_idx = ARRAY_SIZE(rnd_buf); +static int urandom_fd = -1; + static unsigned HOST_WIDE_INT get_random_const(void) { - unsigned int i; - unsigned HOST_WIDE_INT ret = 0; - - for (i = 0; i < 8 * sizeof(ret); i++) { - ret = (ret << 1) | (seed & 1); - seed >>= 1; - if (ret & 1) - seed ^= 0xD800000000000000ULL; + if (deterministic_seed) { + unsigned HOST_WIDE_INT w = deterministic_seed; + w ^= w << 13; + w ^= w >> 7; + w ^= w << 17; + deterministic_seed = w; + return deterministic_seed; } - return ret; + if (urandom_fd < 0) { + urandom_fd = open("/dev/urandom", O_RDONLY); + gcc_assert(urandom_fd >= 0); + } + if (rnd_idx >= ARRAY_SIZE(rnd_buf)) { + gcc_assert(read(urandom_fd, rnd_buf, sizeof(rnd_buf)) == sizeof(rnd_buf)); + rnd_idx = 0; + } + return rnd_buf[rnd_idx++]; } static tree tree_get_random_const(tree type) @@ -537,8 +543,6 @@ static void latent_entropy_start_unit(void *gcc_data __unused, tree type, id; int quals; - seed = get_random_seed(false); - if (in_lto_p) return; @@ -573,6 +577,12 @@ __visible int plugin_init(struct plugin_name_args *plugin_info, const struct plugin_argument * const argv = plugin_info->argv; int i; + /* + * Call get_random_seed() with noinit=true, so that this returns + * 0 in the case where no seed has been passed via -frandom-seed. + */ + deterministic_seed = get_random_seed(true); + static const struct ggc_root_tab gt_ggc_r_gt_latent_entropy[] = { { .base = &latent_entropy_decl, diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 8caabddf817c..e6906f79833d 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -111,7 +111,8 @@ static bool is_ignored_symbol(const char *name, char type) ".L", /* local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. */ "__crc_", /* modversions */ "__efistub_", /* arm64 EFI stub namespace */ - "__kvm_nvhe_", /* arm64 non-VHE KVM namespace */ + "__kvm_nvhe_$", /* arm64 local symbols in non-VHE KVM namespace */ + "__kvm_nvhe_.L", /* arm64 local symbols in non-VHE KVM namespace */ "__AArch64ADRPThunk_", /* arm64 lld */ "__ARMV5PILongThunk_", /* arm lld */ "__ARMV7PILongThunk_", diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 20f44504a644..9361a1ef02c9 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -140,7 +140,7 @@ objtool_link() if ! is_enabled CONFIG_FRAME_POINTER; then objtoolopt="${objtoolopt} --no-fp" fi - if is_enabled CONFIG_GCOV_KERNEL || is_enabled CONFIG_LTO_CLANG; then + if is_enabled CONFIG_GCOV_KERNEL; then objtoolopt="${objtoolopt} --no-unreachable" fi if is_enabled CONFIG_RETPOLINE; then diff --git a/sound/core/init.c b/sound/core/init.c index 31ba7024e3ad..726a8353201f 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -209,6 +209,12 @@ static void __snd_card_release(struct device *dev, void *data) * snd_card_register(), the very first devres action to call snd_card_free() * is added automatically. In that way, the resource disconnection is assured * at first, then released in the expected order. + * + * If an error happens at the probe before snd_card_register() is called and + * there have been other devres resources, you'd need to free the card manually + * via snd_card_free() call in the error; otherwise it may lead to UAF due to + * devres call orders. You can use snd_card_free_on_error() helper for + * handling it more easily. */ int snd_devm_card_new(struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size, @@ -235,6 +241,28 @@ int snd_devm_card_new(struct device *parent, int idx, const char *xid, } EXPORT_SYMBOL_GPL(snd_devm_card_new); +/** + * snd_card_free_on_error - a small helper for handling devm probe errors + * @dev: the managed device object + * @ret: the return code from the probe callback + * + * This function handles the explicit snd_card_free() call at the error from + * the probe callback. It's just a small helper for simplifying the error + * handling with the managed devices. + */ +int snd_card_free_on_error(struct device *dev, int ret) +{ + struct snd_card *card; + + if (!ret) + return 0; + card = devres_find(dev, __snd_card_release, NULL, NULL); + if (card) + snd_card_free(card); + return ret; +} +EXPORT_SYMBOL_GPL(snd_card_free_on_error); + static int snd_card_init(struct snd_card *card, struct device *parent, int idx, const char *xid, struct module *module, size_t extra_size) diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 6fd763d4d15b..15dc7160ba34 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -499,6 +499,10 @@ static const struct snd_malloc_ops snd_dma_wc_ops = { }; #endif /* CONFIG_X86 */ +#ifdef CONFIG_SND_DMA_SGBUF +static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size); +#endif + /* * Non-contiguous pages allocator */ @@ -509,8 +513,18 @@ static void *snd_dma_noncontig_alloc(struct snd_dma_buffer *dmab, size_t size) sgt = dma_alloc_noncontiguous(dmab->dev.dev, size, dmab->dev.dir, DEFAULT_GFP, 0); - if (!sgt) + if (!sgt) { +#ifdef CONFIG_SND_DMA_SGBUF + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) + dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; + else + dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK; + return snd_dma_sg_fallback_alloc(dmab, size); +#else return NULL; +#endif + } + dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, sg_dma_address(sgt->sgl)); p = dma_vmap_noncontiguous(dmab->dev.dev, size, sgt); @@ -633,6 +647,8 @@ static void *snd_dma_sg_wc_alloc(struct snd_dma_buffer *dmab, size_t size) if (!p) return NULL; + if (dmab->dev.type != SNDRV_DMA_TYPE_DEV_WC_SG) + return p; for_each_sgtable_page(sgt, &iter, 0) set_memory_wc(sg_wc_address(&iter), 1); return p; @@ -665,6 +681,95 @@ static const struct snd_malloc_ops snd_dma_sg_wc_ops = { .get_page = snd_dma_noncontig_get_page, .get_chunk_size = snd_dma_noncontig_get_chunk_size, }; + +/* Fallback SG-buffer allocations for x86 */ +struct snd_dma_sg_fallback { + size_t count; + struct page **pages; + dma_addr_t *addrs; +}; + +static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab, + struct snd_dma_sg_fallback *sgbuf) +{ + size_t i; + + if (sgbuf->count && dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wb(sgbuf->pages, sgbuf->count); + for (i = 0; i < sgbuf->count && sgbuf->pages[i]; i++) + dma_free_coherent(dmab->dev.dev, PAGE_SIZE, + page_address(sgbuf->pages[i]), + sgbuf->addrs[i]); + kvfree(sgbuf->pages); + kvfree(sgbuf->addrs); + kfree(sgbuf); +} + +static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) +{ + struct snd_dma_sg_fallback *sgbuf; + struct page **pages; + size_t i, count; + void *p; + + sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL); + if (!sgbuf) + return NULL; + count = PAGE_ALIGN(size) >> PAGE_SHIFT; + pages = kvcalloc(count, sizeof(*pages), GFP_KERNEL); + if (!pages) + goto error; + sgbuf->pages = pages; + sgbuf->addrs = kvcalloc(count, sizeof(*sgbuf->addrs), GFP_KERNEL); + if (!sgbuf->addrs) + goto error; + + for (i = 0; i < count; sgbuf->count++, i++) { + p = dma_alloc_coherent(dmab->dev.dev, PAGE_SIZE, + &sgbuf->addrs[i], DEFAULT_GFP); + if (!p) + goto error; + sgbuf->pages[i] = virt_to_page(p); + } + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wc(pages, count); + p = vmap(pages, count, VM_MAP, PAGE_KERNEL); + if (!p) + goto error; + dmab->private_data = sgbuf; + return p; + + error: + __snd_dma_sg_fallback_free(dmab, sgbuf); + return NULL; +} + +static void snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab) +{ + vunmap(dmab->area); + __snd_dma_sg_fallback_free(dmab, dmab->private_data); +} + +static int snd_dma_sg_fallback_mmap(struct snd_dma_buffer *dmab, + struct vm_area_struct *area) +{ + struct snd_dma_sg_fallback *sgbuf = dmab->private_data; + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + area->vm_page_prot = pgprot_writecombine(area->vm_page_prot); + return vm_map_pages(area, sgbuf->pages, sgbuf->count); +} + +static const struct snd_malloc_ops snd_dma_sg_fallback_ops = { + .alloc = snd_dma_sg_fallback_alloc, + .free = snd_dma_sg_fallback_free, + .mmap = snd_dma_sg_fallback_mmap, + /* reuse vmalloc helpers */ + .get_addr = snd_dma_vmalloc_get_addr, + .get_page = snd_dma_vmalloc_get_page, + .get_chunk_size = snd_dma_vmalloc_get_chunk_size, +}; #endif /* CONFIG_SND_DMA_SGBUF */ /* @@ -736,6 +841,10 @@ static const struct snd_malloc_ops *dma_ops[] = { #ifdef CONFIG_GENERIC_ALLOCATOR [SNDRV_DMA_TYPE_DEV_IRAM] = &snd_dma_iram_ops, #endif /* CONFIG_GENERIC_ALLOCATOR */ +#ifdef CONFIG_SND_DMA_SGBUF + [SNDRV_DMA_TYPE_DEV_SG_FALLBACK] = &snd_dma_sg_fallback_ops, + [SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK] = &snd_dma_sg_fallback_ops, +#endif #endif /* CONFIG_HAS_DMA */ }; diff --git a/sound/core/pcm_misc.c b/sound/core/pcm_misc.c index 4866aed97aac..5588b6a1ee8b 100644 --- a/sound/core/pcm_misc.c +++ b/sound/core/pcm_misc.c @@ -433,7 +433,7 @@ int snd_pcm_format_set_silence(snd_pcm_format_t format, void *data, unsigned int return 0; width = pcm_formats[(INT)format].phys; /* physical width */ pat = pcm_formats[(INT)format].silence; - if (! width) + if (!width || !pat) return -EINVAL; /* signed or 1 byte data */ if (pcm_formats[(INT)format].signd == 1 || width <= 8) { diff --git a/sound/drivers/mtpav.c b/sound/drivers/mtpav.c index 11235baaf6fa..f212f233ea61 100644 --- a/sound/drivers/mtpav.c +++ b/sound/drivers/mtpav.c @@ -693,8 +693,6 @@ static int snd_mtpav_probe(struct platform_device *dev) mtp_card->outmidihwport = 0xffffffff; timer_setup(&mtp_card->timer, snd_mtpav_output_timer, 0); - card->private_free = snd_mtpav_free; - err = snd_mtpav_get_RAWMIDI(mtp_card); if (err < 0) return err; @@ -716,6 +714,8 @@ static int snd_mtpav_probe(struct platform_device *dev) if (err < 0) return err; + card->private_free = snd_mtpav_free; + platform_set_drvdata(dev, card); printk(KERN_INFO "Motu MidiTimePiece on parallel port irq: %d ioport: 0x%lx\n", irq, port); return 0; diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index efe810af28c5..3f35972e1cf7 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -116,16 +116,24 @@ static int i915_component_master_match(struct device *dev, int subcomponent, return 0; } -/* check whether intel graphics is present */ -static bool i915_gfx_present(void) +/* check whether Intel graphics is present and reachable */ +static int i915_gfx_present(struct pci_dev *hdac_pci) { - static const struct pci_device_id ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_ANY_ID), - .class = PCI_BASE_CLASS_DISPLAY << 16, - .class_mask = 0xff << 16 }, - {} - }; - return pci_dev_present(ids); + unsigned int class = PCI_BASE_CLASS_DISPLAY << 16; + struct pci_dev *display_dev = NULL; + bool match = false; + + do { + display_dev = pci_get_class(class, display_dev); + + if (display_dev && display_dev->vendor == PCI_VENDOR_ID_INTEL && + connectivity_check(display_dev, hdac_pci)) { + pci_dev_put(display_dev); + match = true; + } + } while (!match && display_dev); + + return match; } /** @@ -145,7 +153,7 @@ int snd_hdac_i915_init(struct hdac_bus *bus) struct drm_audio_component *acomp; int err; - if (!i915_gfx_present()) + if (!i915_gfx_present(to_pci_dev(bus->dev))) return -ENODEV; err = snd_hdac_acomp_init(bus, NULL, diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 70fd8b13938e..a8fe01764b25 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -390,26 +390,49 @@ static const struct config_entry config_table[] = { /* Alder Lake */ #if IS_ENABLED(CONFIG_SND_SOC_SOF_ALDERLAKE) + /* Alderlake-S */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x7ad0, }, + /* RaptorLake-S */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, - .device = 0x51c8, + .device = 0x7a50, }, + /* Alderlake-P */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, - .device = 0x51cc, + .device = 0x51c8, }, { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x51cd, }, + /* Alderlake-PS */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51c9, + }, + /* Alderlake-M */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51cc, + }, + /* Alderlake-N */ { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = 0x54c8, }, + /* RaptorLake-P */ + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51ca, + }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = 0x51cb, + }, #endif }; diff --git a/sound/isa/galaxy/galaxy.c b/sound/isa/galaxy/galaxy.c index ea001c80149d..3164eb8510fa 100644 --- a/sound/isa/galaxy/galaxy.c +++ b/sound/isa/galaxy/galaxy.c @@ -478,7 +478,7 @@ static void snd_galaxy_free(struct snd_card *card) galaxy_set_config(galaxy, galaxy->config); } -static int snd_galaxy_probe(struct device *dev, unsigned int n) +static int __snd_galaxy_probe(struct device *dev, unsigned int n) { struct snd_galaxy *galaxy; struct snd_wss *chip; @@ -598,6 +598,11 @@ static int snd_galaxy_probe(struct device *dev, unsigned int n) return 0; } +static int snd_galaxy_probe(struct device *dev, unsigned int n) +{ + return snd_card_free_on_error(dev, __snd_galaxy_probe(dev, n)); +} + static struct isa_driver snd_galaxy_driver = { .match = snd_galaxy_match, .probe = snd_galaxy_probe, diff --git a/sound/isa/sc6000.c b/sound/isa/sc6000.c index 26ab7ff80768..60398fced046 100644 --- a/sound/isa/sc6000.c +++ b/sound/isa/sc6000.c @@ -537,7 +537,7 @@ static void snd_sc6000_free(struct snd_card *card) sc6000_setup_board(vport, 0); } -static int snd_sc6000_probe(struct device *devptr, unsigned int dev) +static int __snd_sc6000_probe(struct device *devptr, unsigned int dev) { static const int possible_irqs[] = { 5, 7, 9, 10, 11, -1 }; static const int possible_dmas[] = { 1, 3, 0, -1 }; @@ -662,6 +662,11 @@ static int snd_sc6000_probe(struct device *devptr, unsigned int dev) return 0; } +static int snd_sc6000_probe(struct device *devptr, unsigned int dev) +{ + return snd_card_free_on_error(devptr, __snd_sc6000_probe(devptr, dev)); +} + static struct isa_driver snd_sc6000_driver = { .match = snd_sc6000_match, .probe = snd_sc6000_probe, diff --git a/sound/oss/dmasound/dmasound.h b/sound/oss/dmasound/dmasound.h index c1c52b479da2..ad8ce6a1c25c 100644 --- a/sound/oss/dmasound/dmasound.h +++ b/sound/oss/dmasound/dmasound.h @@ -88,11 +88,7 @@ static inline int ioctl_return(int __user *addr, int value) */ extern int dmasound_init(void); -#ifdef MODULE extern void dmasound_deinit(void); -#else -#define dmasound_deinit() do { } while (0) -#endif /* description of the set-up applies to either hard or soft settings */ @@ -114,9 +110,7 @@ typedef struct { void *(*dma_alloc)(unsigned int, gfp_t); void (*dma_free)(void *, unsigned int); int (*irqinit)(void); -#ifdef MODULE void (*irqcleanup)(void); -#endif void (*init)(void); void (*silence)(void); int (*setFormat)(int); diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 0c95828ac0b1..164335d3c200 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -206,12 +206,10 @@ module_param(writeBufSize, int, 0); MODULE_LICENSE("GPL"); -#ifdef MODULE static int sq_unit = -1; static int mixer_unit = -1; static int state_unit = -1; static int irq_installed; -#endif /* MODULE */ /* control over who can modify resources shared between play/record */ static fmode_t shared_resource_owner; @@ -391,9 +389,6 @@ static const struct file_operations mixer_fops = static void mixer_init(void) { -#ifndef MODULE - int mixer_unit; -#endif mixer_unit = register_sound_mixer(&mixer_fops, -1); if (mixer_unit < 0) return; @@ -1171,9 +1166,6 @@ static const struct file_operations sq_fops = static int sq_init(void) { const struct file_operations *fops = &sq_fops; -#ifndef MODULE - int sq_unit; -#endif sq_unit = register_sound_dsp(fops, -1); if (sq_unit < 0) { @@ -1366,9 +1358,6 @@ static const struct file_operations state_fops = { static int state_init(void) { -#ifndef MODULE - int state_unit; -#endif state_unit = register_sound_special(&state_fops, SND_DEV_STATUS); if (state_unit < 0) return state_unit ; @@ -1386,10 +1375,9 @@ static int state_init(void) int dmasound_init(void) { int res ; -#ifdef MODULE + if (irq_installed) return -EBUSY; -#endif /* Set up sound queue, /dev/audio and /dev/dsp. */ @@ -1408,9 +1396,7 @@ int dmasound_init(void) printk(KERN_ERR "DMA sound driver: Interrupt initialization failed\n"); return -ENODEV; } -#ifdef MODULE irq_installed = 1; -#endif printk(KERN_INFO "%s DMA sound driver rev %03d installed\n", dmasound.mach.name, (DMASOUND_CORE_REVISION<<4) + @@ -1424,8 +1410,6 @@ int dmasound_init(void) return 0; } -#ifdef MODULE - void dmasound_deinit(void) { if (irq_installed) { @@ -1444,9 +1428,7 @@ void dmasound_deinit(void) unregister_sound_dsp(sq_unit); } -#else /* !MODULE */ - -static int dmasound_setup(char *str) +static int __maybe_unused dmasound_setup(char *str) { int ints[6], size; @@ -1489,8 +1471,6 @@ static int dmasound_setup(char *str) __setup("dmasound=", dmasound_setup); -#endif /* !MODULE */ - /* * Conversion tables */ @@ -1577,9 +1557,7 @@ char dmasound_alaw2dma8[] = { EXPORT_SYMBOL(dmasound); EXPORT_SYMBOL(dmasound_init); -#ifdef MODULE EXPORT_SYMBOL(dmasound_deinit); -#endif EXPORT_SYMBOL(dmasound_write_sq); EXPORT_SYMBOL(dmasound_catchRadius); #ifdef HAS_8BIT_TABLES diff --git a/sound/pci/ad1889.c b/sound/pci/ad1889.c index bba4dae8dcc7..50e30704bf6f 100644 --- a/sound/pci/ad1889.c +++ b/sound/pci/ad1889.c @@ -844,8 +844,8 @@ snd_ad1889_create(struct snd_card *card, struct pci_dev *pci) } static int -snd_ad1889_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +__snd_ad1889_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { int err; static int devno; @@ -904,6 +904,12 @@ snd_ad1889_probe(struct pci_dev *pci, return 0; } +static int snd_ad1889_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ad1889_probe(pci, pci_id)); +} + static const struct pci_device_id snd_ad1889_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_ANALOG_DEVICES, PCI_DEVICE_ID_AD1889JS) }, { 0, }, diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c index 92eb59db106d..2378a39abaeb 100644 --- a/sound/pci/ali5451/ali5451.c +++ b/sound/pci/ali5451/ali5451.c @@ -2124,8 +2124,8 @@ static int snd_ali_create(struct snd_card *card, return 0; } -static int snd_ali_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_ali_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct snd_ali *codec; @@ -2170,6 +2170,12 @@ static int snd_ali_probe(struct pci_dev *pci, return 0; } +static int snd_ali_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ali_probe(pci, pci_id)); +} + static struct pci_driver ali5451_driver = { .name = KBUILD_MODNAME, .id_table = snd_ali_ids, diff --git a/sound/pci/als300.c b/sound/pci/als300.c index b86565dcdbe4..c70aff060120 100644 --- a/sound/pci/als300.c +++ b/sound/pci/als300.c @@ -708,7 +708,7 @@ static int snd_als300_probe(struct pci_dev *pci, err = snd_als300_create(card, pci, chip_type); if (err < 0) - return err; + goto error; strcpy(card->driver, "ALS300"); if (chip->chip_type == DEVICE_ALS300_PLUS) @@ -723,11 +723,15 @@ static int snd_als300_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver als300_driver = { diff --git a/sound/pci/als4000.c b/sound/pci/als4000.c index 535eccd124be..f33aeb692a11 100644 --- a/sound/pci/als4000.c +++ b/sound/pci/als4000.c @@ -806,8 +806,8 @@ static void snd_card_als4000_free( struct snd_card *card ) snd_als4000_free_gameport(acard); } -static int snd_card_als4000_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_als4000_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -930,6 +930,12 @@ static int snd_card_als4000_probe(struct pci_dev *pci, return 0; } +static int snd_card_als4000_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_als4000_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_als4000_suspend(struct device *dev) { diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c index b8e035d5930d..43d01f1847ed 100644 --- a/sound/pci/atiixp.c +++ b/sound/pci/atiixp.c @@ -1572,8 +1572,8 @@ static int snd_atiixp_init(struct snd_card *card, struct pci_dev *pci) } -static int snd_atiixp_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct atiixp *chip; @@ -1623,6 +1623,12 @@ static int snd_atiixp_probe(struct pci_dev *pci, return 0; } +static int snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_atiixp_probe(pci, pci_id)); +} + static struct pci_driver atiixp_driver = { .name = KBUILD_MODNAME, .id_table = snd_atiixp_ids, diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c index 178dce8ef1e9..8864c4c3c7e1 100644 --- a/sound/pci/atiixp_modem.c +++ b/sound/pci/atiixp_modem.c @@ -1201,8 +1201,8 @@ static int snd_atiixp_init(struct snd_card *card, struct pci_dev *pci) } -static int snd_atiixp_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct atiixp_modem *chip; @@ -1247,6 +1247,12 @@ static int snd_atiixp_probe(struct pci_dev *pci, return 0; } +static int snd_atiixp_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_atiixp_probe(pci, pci_id)); +} + static struct pci_driver atiixp_modem_driver = { .name = KBUILD_MODNAME, .id_table = snd_atiixp_ids, diff --git a/sound/pci/au88x0/au88x0.c b/sound/pci/au88x0/au88x0.c index 342ef2a6655e..eb234153691b 100644 --- a/sound/pci/au88x0/au88x0.c +++ b/sound/pci/au88x0/au88x0.c @@ -193,7 +193,7 @@ snd_vortex_create(struct snd_card *card, struct pci_dev *pci) // constructor -- see "Constructor" sub-section static int -snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -310,6 +310,12 @@ snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_vortex_probe(pci, pci_id)); +} + // pci_driver definition static struct pci_driver vortex_driver = { .name = KBUILD_MODNAME, diff --git a/sound/pci/aw2/aw2-alsa.c b/sound/pci/aw2/aw2-alsa.c index d56f126d6fdd..29a4bcdec237 100644 --- a/sound/pci/aw2/aw2-alsa.c +++ b/sound/pci/aw2/aw2-alsa.c @@ -275,7 +275,7 @@ static int snd_aw2_probe(struct pci_dev *pci, /* (3) Create main component */ err = snd_aw2_create(card, pci); if (err < 0) - return err; + goto error; /* initialize mutex */ mutex_init(&chip->mtx); @@ -294,13 +294,17 @@ static int snd_aw2_probe(struct pci_dev *pci, /* (6) Register card instance */ err = snd_card_register(card); if (err < 0) - return err; + goto error; /* (7) Set PCI driver data */ pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } /* open callback */ diff --git a/sound/pci/azt3328.c b/sound/pci/azt3328.c index 089050470ff2..7f329dfc5404 100644 --- a/sound/pci/azt3328.c +++ b/sound/pci/azt3328.c @@ -2427,7 +2427,7 @@ snd_azf3328_create(struct snd_card *card, } static int -snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2520,6 +2520,12 @@ snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_azf3328_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_azf3328_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static inline void snd_azf3328_suspend_regs(const struct snd_azf3328 *chip, diff --git a/sound/pci/bt87x.c b/sound/pci/bt87x.c index d23f93163841..621985bfee5d 100644 --- a/sound/pci/bt87x.c +++ b/sound/pci/bt87x.c @@ -805,8 +805,8 @@ static int snd_bt87x_detect_card(struct pci_dev *pci) return SND_BT87X_BOARD_UNKNOWN; } -static int snd_bt87x_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_bt87x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -889,6 +889,12 @@ static int snd_bt87x_probe(struct pci_dev *pci, return 0; } +static int snd_bt87x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_bt87x_probe(pci, pci_id)); +} + /* default entries for all Bt87x cards - it's not exported */ /* driver_data is set to 0 to call detection */ static const struct pci_device_id snd_bt87x_default_ids[] = { diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c index 8577f9fa5ea6..cf1bac7a435f 100644 --- a/sound/pci/ca0106/ca0106_main.c +++ b/sound/pci/ca0106/ca0106_main.c @@ -1725,8 +1725,8 @@ static int snd_ca0106_midi(struct snd_ca0106 *chip, unsigned int channel) } -static int snd_ca0106_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_ca0106_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1786,6 +1786,12 @@ static int snd_ca0106_probe(struct pci_dev *pci, return 0; } +static int snd_ca0106_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_ca0106_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_ca0106_suspend(struct device *dev) { diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c index dab801d9d3b4..727db6d43391 100644 --- a/sound/pci/cmipci.c +++ b/sound/pci/cmipci.c @@ -3247,15 +3247,19 @@ static int snd_cmipci_probe(struct pci_dev *pci, err = snd_cmipci_create(card, pci, dev); if (err < 0) - return err; + goto error; err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } #ifdef CONFIG_PM_SLEEP diff --git a/sound/pci/cs4281.c b/sound/pci/cs4281.c index e7367402b84a..0c9cadf7b3b8 100644 --- a/sound/pci/cs4281.c +++ b/sound/pci/cs4281.c @@ -1827,8 +1827,8 @@ static void snd_cs4281_opl3_command(struct snd_opl3 *opl3, unsigned short cmd, spin_unlock_irqrestore(&opl3->reg_lock, flags); } -static int snd_cs4281_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_cs4281_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1888,6 +1888,12 @@ static int snd_cs4281_probe(struct pci_dev *pci, return 0; } +static int snd_cs4281_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_cs4281_probe(pci, pci_id)); +} + /* * Power Management */ diff --git a/sound/pci/cs5535audio/cs5535audio.c b/sound/pci/cs5535audio/cs5535audio.c index 499fa0148f9a..440b8f9b40c9 100644 --- a/sound/pci/cs5535audio/cs5535audio.c +++ b/sound/pci/cs5535audio/cs5535audio.c @@ -281,8 +281,8 @@ static int snd_cs5535audio_create(struct snd_card *card, return 0; } -static int snd_cs5535audio_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_cs5535audio_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -331,6 +331,12 @@ static int snd_cs5535audio_probe(struct pci_dev *pci, return 0; } +static int snd_cs5535audio_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_cs5535audio_probe(pci, pci_id)); +} + static struct pci_driver cs5535audio_driver = { .name = KBUILD_MODNAME, .id_table = snd_cs5535audio_ids, diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c index 25b012ef5c3e..c70c3ac4e99a 100644 --- a/sound/pci/echoaudio/echoaudio.c +++ b/sound/pci/echoaudio/echoaudio.c @@ -1970,8 +1970,8 @@ static int snd_echo_create(struct snd_card *card, } /* constructor */ -static int snd_echo_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_echo_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2139,6 +2139,11 @@ static int snd_echo_probe(struct pci_dev *pci, return 0; } +static int snd_echo_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_echo_probe(pci, pci_id)); +} #if defined(CONFIG_PM_SLEEP) diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c index c49c44dc1082..89043392f3ec 100644 --- a/sound/pci/emu10k1/emu10k1x.c +++ b/sound/pci/emu10k1/emu10k1x.c @@ -1491,8 +1491,8 @@ static int snd_emu10k1x_midi(struct emu10k1x *emu) return 0; } -static int snd_emu10k1x_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_emu10k1x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1554,6 +1554,12 @@ static int snd_emu10k1x_probe(struct pci_dev *pci, return 0; } +static int snd_emu10k1x_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_emu10k1x_probe(pci, pci_id)); +} + // PCI IDs static const struct pci_device_id snd_emu10k1x_ids[] = { { PCI_VDEVICE(CREATIVE, 0x0006), 0 }, /* Dell OEM version (EMU10K1) */ diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c index 2651f0c64c06..94efe347a97a 100644 --- a/sound/pci/ens1370.c +++ b/sound/pci/ens1370.c @@ -2304,8 +2304,8 @@ static irqreturn_t snd_audiopci_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static int snd_audiopci_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_audiopci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2369,6 +2369,12 @@ static int snd_audiopci_probe(struct pci_dev *pci, return 0; } +static int snd_audiopci_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_audiopci_probe(pci, pci_id)); +} + static struct pci_driver ens137x_driver = { .name = KBUILD_MODNAME, .id_table = snd_audiopci_ids, diff --git a/sound/pci/es1938.c b/sound/pci/es1938.c index 00b976f42a3d..e34ec6f89e7e 100644 --- a/sound/pci/es1938.c +++ b/sound/pci/es1938.c @@ -1716,8 +1716,8 @@ static int snd_es1938_mixer(struct es1938 *chip) } -static int snd_es1938_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_es1938_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1796,6 +1796,12 @@ static int snd_es1938_probe(struct pci_dev *pci, return 0; } +static int snd_es1938_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_es1938_probe(pci, pci_id)); +} + static struct pci_driver es1938_driver = { .name = KBUILD_MODNAME, .id_table = snd_es1938_ids, diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c index 6a8a02a9ecf4..4a7e20bb11bc 100644 --- a/sound/pci/es1968.c +++ b/sound/pci/es1968.c @@ -2741,8 +2741,8 @@ static int snd_es1968_create(struct snd_card *card, /* */ -static int snd_es1968_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_es1968_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2848,6 +2848,12 @@ static int snd_es1968_probe(struct pci_dev *pci, return 0; } +static int snd_es1968_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_es1968_probe(pci, pci_id)); +} + static struct pci_driver es1968_driver = { .name = KBUILD_MODNAME, .id_table = snd_es1968_ids, diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c index 9c22ff19e56d..62b3cb126c6d 100644 --- a/sound/pci/fm801.c +++ b/sound/pci/fm801.c @@ -1268,8 +1268,8 @@ static int snd_fm801_create(struct snd_card *card, return 0; } -static int snd_card_fm801_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_card_fm801_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1333,6 +1333,12 @@ static int snd_card_fm801_probe(struct pci_dev *pci, return 0; } +static int snd_card_fm801_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_fm801_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static const unsigned char saved_regs[] = { FM801_PCM_VOL, FM801_I2S_VOL, FM801_FM_VOL, FM801_REC_SRC, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 3e086eebf88d..31fe41795571 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1395,7 +1395,7 @@ static int hdmi_find_pcm_slot(struct hdmi_spec *spec, last_try: /* the last try; check the empty slots in pins */ - for (i = 0; i < spec->num_nids; i++) { + for (i = 0; i < spec->pcm_used; i++) { if (!test_bit(i, &spec->pcm_bitmap)) return i; } @@ -2325,7 +2325,9 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec) * dev_num is the device entry number in a pin */ - if (codec->mst_no_extra_pcms) + if (spec->dyn_pcm_no_legacy && codec->mst_no_extra_pcms) + pcm_num = spec->num_cvts; + else if (codec->mst_no_extra_pcms) pcm_num = spec->num_nids; else pcm_num = spec->num_nids + spec->dev_num - 1; @@ -4551,6 +4553,7 @@ HDA_CODEC_ENTRY(0x80862819, "DG2 HDMI", patch_i915_adlp_hdmi), HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi), HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_adlp_hdmi), +HDA_CODEC_ENTRY(0x8086281f, "Raptorlake-P HDMI", patch_i915_adlp_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4e12af24b4d3..4c0c593f3c0a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2619,6 +2619,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65e5, "Clevo PC50D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x65f1, "Clevo PC50HS", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65f5, "Clevo PD50PN[NRT]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e5, "Clevo PC70D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), @@ -7005,6 +7006,7 @@ enum { ALC285_FIXUP_LEGION_Y9000X_AUTOMUTE, ALC287_FIXUP_LEGION_16ACHG6, ALC287_FIXUP_CS35L41_I2C_2, + ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED, ALC245_FIXUP_CS35L41_SPI_2, ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED, ALC245_FIXUP_CS35L41_SPI_4, @@ -8768,6 +8770,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, }, + [ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC285_FIXUP_HP_MUTE_LED, + }, [ALC245_FIXUP_CS35L41_SPI_2] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_spi_two, @@ -9024,9 +9032,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8992, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x103c, 0x8994, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8994, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8995, "HP EliteBook 855 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x89a4, "HP ProBook 440 G9", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89a6, "HP ProBook 450 G9", ALC236_FIXUP_HP_GPIO_LED), @@ -9162,6 +9170,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x8562, "Clevo NH[57][0-9]RZ[Q]", ALC269_FIXUP_DMIC), SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x866d, "Clevo NP5[05]PN[HJK]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x867c, "Clevo NP7[01]PNP", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x867d, "Clevo NP7[01]PN[HJK]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC256_FIXUP_MIC_NO_PRESENCE_AND_RESUME), @@ -9264,6 +9273,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x505d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x505f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x5062, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x508b, "Thinkpad X12 Gen 1", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x511e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), diff --git a/sound/pci/ice1712/ice1724.c b/sound/pci/ice1712/ice1724.c index f6275868877a..6fab2ad85bbe 100644 --- a/sound/pci/ice1712/ice1724.c +++ b/sound/pci/ice1712/ice1724.c @@ -2519,8 +2519,8 @@ static int snd_vt1724_create(struct snd_card *card, * */ -static int snd_vt1724_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_vt1724_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2662,6 +2662,12 @@ static int snd_vt1724_probe(struct pci_dev *pci, return 0; } +static int snd_vt1724_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_vt1724_probe(pci, pci_id)); +} + #ifdef CONFIG_PM_SLEEP static int snd_vt1724_suspend(struct device *dev) { diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c index a51032b3ac4d..ae285c0a629c 100644 --- a/sound/pci/intel8x0.c +++ b/sound/pci/intel8x0.c @@ -3109,8 +3109,8 @@ static int check_default_spdif_aclink(struct pci_dev *pci) return 0; } -static int snd_intel8x0_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_intel8x0_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct intel8x0 *chip; @@ -3189,6 +3189,12 @@ static int snd_intel8x0_probe(struct pci_dev *pci, return 0; } +static int snd_intel8x0_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_intel8x0_probe(pci, pci_id)); +} + static struct pci_driver intel8x0_driver = { .name = KBUILD_MODNAME, .id_table = snd_intel8x0_ids, diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c index 7de3cb2f17b5..2845cc006d0c 100644 --- a/sound/pci/intel8x0m.c +++ b/sound/pci/intel8x0m.c @@ -1178,8 +1178,8 @@ static struct shortname_table { { 0 }, }; -static int snd_intel8x0m_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_intel8x0m_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct intel8x0m *chip; @@ -1225,6 +1225,12 @@ static int snd_intel8x0m_probe(struct pci_dev *pci, return 0; } +static int snd_intel8x0m_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_intel8x0m_probe(pci, pci_id)); +} + static struct pci_driver intel8x0m_driver = { .name = KBUILD_MODNAME, .id_table = snd_intel8x0m_ids, diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c index 5c9e240ff6a9..33b4f95d65b3 100644 --- a/sound/pci/korg1212/korg1212.c +++ b/sound/pci/korg1212/korg1212.c @@ -2355,7 +2355,7 @@ snd_korg1212_probe(struct pci_dev *pci, err = snd_korg1212_create(card, pci); if (err < 0) - return err; + goto error; strcpy(card->driver, "korg1212"); strcpy(card->shortname, "korg1212"); @@ -2366,10 +2366,14 @@ snd_korg1212_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver korg1212_driver = { diff --git a/sound/pci/lola/lola.c b/sound/pci/lola/lola.c index 5269a1d396a5..1aa30e90b86a 100644 --- a/sound/pci/lola/lola.c +++ b/sound/pci/lola/lola.c @@ -637,8 +637,8 @@ static int lola_create(struct snd_card *card, struct pci_dev *pci, int dev) return 0; } -static int lola_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __lola_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -687,6 +687,12 @@ static int lola_probe(struct pci_dev *pci, return 0; } +static int lola_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __lola_probe(pci, pci_id)); +} + /* PCI IDs */ static const struct pci_device_id lola_ids[] = { { PCI_VDEVICE(DIGIGRAM, 0x0001) }, diff --git a/sound/pci/lx6464es/lx6464es.c b/sound/pci/lx6464es/lx6464es.c index 168a1084f730..bd9b6148dd6f 100644 --- a/sound/pci/lx6464es/lx6464es.c +++ b/sound/pci/lx6464es/lx6464es.c @@ -1019,7 +1019,7 @@ static int snd_lx6464es_probe(struct pci_dev *pci, err = snd_lx6464es_create(card, pci); if (err < 0) { dev_err(card->dev, "error during snd_lx6464es_create\n"); - return err; + goto error; } strcpy(card->driver, "LX6464ES"); @@ -1036,12 +1036,16 @@ static int snd_lx6464es_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; dev_dbg(chip->card->dev, "initialization successful\n"); pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver lx6464es_driver = { diff --git a/sound/pci/maestro3.c b/sound/pci/maestro3.c index 056838ead21d..261850775c80 100644 --- a/sound/pci/maestro3.c +++ b/sound/pci/maestro3.c @@ -2637,7 +2637,7 @@ snd_m3_create(struct snd_card *card, struct pci_dev *pci, /* */ static int -snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2702,6 +2702,12 @@ snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_m3_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_m3_probe(pci, pci_id)); +} + static struct pci_driver m3_driver = { .name = KBUILD_MODNAME, .id_table = snd_m3_ids, diff --git a/sound/pci/nm256/nm256.c b/sound/pci/nm256/nm256.c index c9c178504959..f99a1e96e923 100644 --- a/sound/pci/nm256/nm256.c +++ b/sound/pci/nm256/nm256.c @@ -1573,7 +1573,6 @@ snd_nm256_create(struct snd_card *card, struct pci_dev *pci) chip->coeffs_current = 0; snd_nm256_init_chip(chip); - card->private_free = snd_nm256_free; // pci_set_master(pci); /* needed? */ return 0; @@ -1680,6 +1679,7 @@ static int snd_nm256_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) return err; + card->private_free = snd_nm256_free; pci_set_drvdata(pci, card); return 0; diff --git a/sound/pci/oxygen/oxygen_lib.c b/sound/pci/oxygen/oxygen_lib.c index 4fb3f2484fdb..92ffe9dc20c5 100644 --- a/sound/pci/oxygen/oxygen_lib.c +++ b/sound/pci/oxygen/oxygen_lib.c @@ -576,7 +576,7 @@ static void oxygen_card_free(struct snd_card *card) mutex_destroy(&chip->mutex); } -int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, +static int __oxygen_pci_probe(struct pci_dev *pci, int index, char *id, struct module *owner, const struct pci_device_id *ids, int (*get_model)(struct oxygen *chip, @@ -701,6 +701,16 @@ int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, pci_set_drvdata(pci, card); return 0; } + +int oxygen_pci_probe(struct pci_dev *pci, int index, char *id, + struct module *owner, + const struct pci_device_id *ids, + int (*get_model)(struct oxygen *chip, + const struct pci_device_id *id)) +{ + return snd_card_free_on_error(&pci->dev, + __oxygen_pci_probe(pci, index, id, owner, ids, get_model)); +} EXPORT_SYMBOL(oxygen_pci_probe); #ifdef CONFIG_PM_SLEEP diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c index 5a987c683c41..b37c877c2c16 100644 --- a/sound/pci/riptide/riptide.c +++ b/sound/pci/riptide/riptide.c @@ -2023,7 +2023,7 @@ static void snd_riptide_joystick_remove(struct pci_dev *pci) #endif static int -snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -2124,6 +2124,12 @@ snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_card_riptide_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_card_riptide_probe(pci, pci_id)); +} + static struct pci_driver driver = { .name = KBUILD_MODNAME, .id_table = snd_riptide_ids, diff --git a/sound/pci/rme32.c b/sound/pci/rme32.c index 5b6bd9f0b2f7..9c0ac025e143 100644 --- a/sound/pci/rme32.c +++ b/sound/pci/rme32.c @@ -1875,7 +1875,7 @@ static void snd_rme32_card_free(struct snd_card *card) } static int -snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +__snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { static int dev; struct rme32 *rme32; @@ -1927,6 +1927,12 @@ snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return 0; } +static int +snd_rme32_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_rme32_probe(pci, pci_id)); +} + static struct pci_driver rme32_driver = { .name = KBUILD_MODNAME, .id_table = snd_rme32_ids, diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c index 8fc811504920..bccb7e0d3d11 100644 --- a/sound/pci/rme96.c +++ b/sound/pci/rme96.c @@ -2430,8 +2430,8 @@ static void snd_rme96_card_free(struct snd_card *card) } static int -snd_rme96_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +__snd_rme96_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct rme96 *rme96; @@ -2498,6 +2498,12 @@ snd_rme96_probe(struct pci_dev *pci, return 0; } +static int snd_rme96_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_rme96_probe(pci, pci_id)); +} + static struct pci_driver rme96_driver = { .name = KBUILD_MODNAME, .id_table = snd_rme96_ids, diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 96c12dfb24cf..3db641318d3a 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -5444,17 +5444,21 @@ static int snd_hdsp_probe(struct pci_dev *pci, hdsp->pci = pci; err = snd_hdsp_create(card, hdsp); if (err) - return err; + goto error; strcpy(card->shortname, "Hammerfall DSP"); sprintf(card->longname, "%s at 0x%lx, irq %d", hdsp->card_name, hdsp->port, hdsp->irq); err = snd_card_register(card); if (err) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver hdsp_driver = { diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index ff06ee82607c..fa1812e7a49d 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -6895,7 +6895,7 @@ static int snd_hdspm_probe(struct pci_dev *pci, err = snd_hdspm_create(card, hdspm); if (err < 0) - return err; + goto error; if (hdspm->io_type != MADIface) { snprintf(card->shortname, sizeof(card->shortname), "%s_%x", @@ -6914,12 +6914,16 @@ static int snd_hdspm_probe(struct pci_dev *pci, err = snd_card_register(card); if (err < 0) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver hdspm_driver = { diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c index 7755e19aa776..1d614fe89a6a 100644 --- a/sound/pci/rme9652/rme9652.c +++ b/sound/pci/rme9652/rme9652.c @@ -2572,7 +2572,7 @@ static int snd_rme9652_probe(struct pci_dev *pci, rme9652->pci = pci; err = snd_rme9652_create(card, rme9652, precise_ptr[dev]); if (err) - return err; + goto error; strcpy(card->shortname, rme9652->card_name); @@ -2580,10 +2580,14 @@ static int snd_rme9652_probe(struct pci_dev *pci, card->shortname, rme9652->port, rme9652->irq); err = snd_card_register(card); if (err) - return err; + goto error; pci_set_drvdata(pci, card); dev++; return 0; + + error: + snd_card_free(card); + return err; } static struct pci_driver rme9652_driver = { diff --git a/sound/pci/sis7019.c b/sound/pci/sis7019.c index 0b722b0e0604..fabe393607f8 100644 --- a/sound/pci/sis7019.c +++ b/sound/pci/sis7019.c @@ -1331,8 +1331,8 @@ static int sis_chip_create(struct snd_card *card, return 0; } -static int snd_sis7019_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_sis7019_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct sis7019 *sis; @@ -1352,8 +1352,8 @@ static int snd_sis7019_probe(struct pci_dev *pci, if (!codecs) codecs = SIS_PRIMARY_CODEC_PRESENT; - rc = snd_card_new(&pci->dev, index, id, THIS_MODULE, - sizeof(*sis), &card); + rc = snd_devm_card_new(&pci->dev, index, id, THIS_MODULE, + sizeof(*sis), &card); if (rc < 0) return rc; @@ -1386,6 +1386,12 @@ static int snd_sis7019_probe(struct pci_dev *pci, return 0; } +static int snd_sis7019_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_sis7019_probe(pci, pci_id)); +} + static struct pci_driver sis7019_driver = { .name = KBUILD_MODNAME, .id_table = snd_sis7019_ids, diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c index c8c49881008f..f91cbf6eeca0 100644 --- a/sound/pci/sonicvibes.c +++ b/sound/pci/sonicvibes.c @@ -1387,8 +1387,8 @@ static int snd_sonicvibes_midi(struct sonicvibes *sonic, return 0; } -static int snd_sonic_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_sonic_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { static int dev; struct snd_card *card; @@ -1459,6 +1459,12 @@ static int snd_sonic_probe(struct pci_dev *pci, return 0; } +static int snd_sonic_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_sonic_probe(pci, pci_id)); +} + static struct pci_driver sonicvibes_driver = { .name = KBUILD_MODNAME, .id_table = snd_sonic_ids, diff --git a/sound/pci/via82xx.c b/sound/pci/via82xx.c index 65514f7e42d7..361b83fd721e 100644 --- a/sound/pci/via82xx.c +++ b/sound/pci/via82xx.c @@ -2458,8 +2458,8 @@ static int check_dxs_list(struct pci_dev *pci, int revision) return VIA_DXS_48K; }; -static int snd_via82xx_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct via82xx *chip; @@ -2569,6 +2569,12 @@ static int snd_via82xx_probe(struct pci_dev *pci, return 0; } +static int snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_via82xx_probe(pci, pci_id)); +} + static struct pci_driver via82xx_driver = { .name = KBUILD_MODNAME, .id_table = snd_via82xx_ids, diff --git a/sound/pci/via82xx_modem.c b/sound/pci/via82xx_modem.c index 234f7fbed236..ca7f024bf8ec 100644 --- a/sound/pci/via82xx_modem.c +++ b/sound/pci/via82xx_modem.c @@ -1103,8 +1103,8 @@ static int snd_via82xx_create(struct snd_card *card, } -static int snd_via82xx_probe(struct pci_dev *pci, - const struct pci_device_id *pci_id) +static int __snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) { struct snd_card *card; struct via82xx_modem *chip; @@ -1157,6 +1157,12 @@ static int snd_via82xx_probe(struct pci_dev *pci, return 0; } +static int snd_via82xx_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + return snd_card_free_on_error(&pci->dev, __snd_via82xx_probe(pci, pci_id)); +} + static struct pci_driver via82xx_modem_driver = { .name = KBUILD_MODNAME, .id_table = snd_via82xx_modem_ids, diff --git a/sound/soc/atmel/sam9g20_wm8731.c b/sound/soc/atmel/sam9g20_wm8731.c index 33e43013ff77..0d639a33ad96 100644 --- a/sound/soc/atmel/sam9g20_wm8731.c +++ b/sound/soc/atmel/sam9g20_wm8731.c @@ -46,35 +46,6 @@ */ #undef ENABLE_MIC_INPUT -static struct clk *mclk; - -static int at91sam9g20ek_set_bias_level(struct snd_soc_card *card, - struct snd_soc_dapm_context *dapm, - enum snd_soc_bias_level level) -{ - static int mclk_on; - int ret = 0; - - switch (level) { - case SND_SOC_BIAS_ON: - case SND_SOC_BIAS_PREPARE: - if (!mclk_on) - ret = clk_enable(mclk); - if (ret == 0) - mclk_on = 1; - break; - - case SND_SOC_BIAS_OFF: - case SND_SOC_BIAS_STANDBY: - if (mclk_on) - clk_disable(mclk); - mclk_on = 0; - break; - } - - return ret; -} - static const struct snd_soc_dapm_widget at91sam9g20ek_dapm_widgets[] = { SND_SOC_DAPM_MIC("Int Mic", NULL), SND_SOC_DAPM_SPK("Ext Spk", NULL), @@ -135,7 +106,6 @@ static struct snd_soc_card snd_soc_at91sam9g20ek = { .owner = THIS_MODULE, .dai_link = &at91sam9g20ek_dai, .num_links = 1, - .set_bias_level = at91sam9g20ek_set_bias_level, .dapm_widgets = at91sam9g20ek_dapm_widgets, .num_dapm_widgets = ARRAY_SIZE(at91sam9g20ek_dapm_widgets), @@ -148,7 +118,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct device_node *codec_np, *cpu_np; - struct clk *pllb; struct snd_soc_card *card = &snd_soc_at91sam9g20ek; int ret; @@ -162,31 +131,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) return -EINVAL; } - /* - * Codec MCLK is supplied by PCK0 - set it up. - */ - mclk = clk_get(NULL, "pck0"); - if (IS_ERR(mclk)) { - dev_err(&pdev->dev, "Failed to get MCLK\n"); - ret = PTR_ERR(mclk); - goto err; - } - - pllb = clk_get(NULL, "pllb"); - if (IS_ERR(pllb)) { - dev_err(&pdev->dev, "Failed to get PLLB\n"); - ret = PTR_ERR(pllb); - goto err_mclk; - } - ret = clk_set_parent(mclk, pllb); - clk_put(pllb); - if (ret != 0) { - dev_err(&pdev->dev, "Failed to set MCLK parent\n"); - goto err_mclk; - } - - clk_set_rate(mclk, MCLK_RATE); - card->dev = &pdev->dev; /* Parse device node info */ @@ -230,9 +174,6 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) return ret; -err_mclk: - clk_put(mclk); - mclk = NULL; err: atmel_ssc_put_audio(0); return ret; @@ -242,8 +183,6 @@ static int at91sam9g20ek_audio_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev); - clk_disable(mclk); - mclk = NULL; snd_soc_unregister_card(card); atmel_ssc_put_audio(0); diff --git a/sound/soc/codecs/cs35l41-lib.c b/sound/soc/codecs/cs35l41-lib.c index e5a56bcbb223..aa6823fbd1a4 100644 --- a/sound/soc/codecs/cs35l41-lib.c +++ b/sound/soc/codecs/cs35l41-lib.c @@ -822,8 +822,8 @@ int cs35l41_otp_unpack(struct device *dev, struct regmap *regmap) word_offset = otp_map_match->word_offset; for (i = 0; i < otp_map_match->num_elements; i++) { - dev_dbg(dev, "bitoffset= %d, word_offset=%d, bit_sum mod 32=%d\n", - bit_offset, word_offset, bit_sum % 32); + dev_dbg(dev, "bitoffset= %d, word_offset=%d, bit_sum mod 32=%d otp_map[i].size = %d\n", + bit_offset, word_offset, bit_sum % 32, otp_map[i].size); if (bit_offset + otp_map[i].size - 1 >= 32) { otp_val = (otp_mem[word_offset] & GENMASK(31, bit_offset)) >> bit_offset; @@ -831,12 +831,14 @@ int cs35l41_otp_unpack(struct device *dev, struct regmap *regmap) GENMASK(bit_offset + otp_map[i].size - 33, 0)) << (32 - bit_offset); bit_offset += otp_map[i].size - 32; - } else { + } else if (bit_offset + otp_map[i].size - 1 >= 0) { otp_val = (otp_mem[word_offset] & GENMASK(bit_offset + otp_map[i].size - 1, bit_offset) ) >> bit_offset; bit_offset += otp_map[i].size; - } + } else /* both bit_offset and otp_map[i].size are 0 */ + otp_val = 0; + bit_sum += otp_map[i].size; if (bit_offset == 32) { diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index 6884ae505e33..3143f9cd7277 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -3566,12 +3566,16 @@ static int rx_macro_probe(struct platform_device *pdev) return PTR_ERR(rx->pds); base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto err; + } rx->regmap = devm_regmap_init_mmio(dev, base, &rx_regmap_config); - if (IS_ERR(rx->regmap)) - return PTR_ERR(rx->regmap); + if (IS_ERR(rx->regmap)) { + ret = PTR_ERR(rx->regmap); + goto err; + } dev_set_drvdata(dev, rx); @@ -3632,6 +3636,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(rx->macro); err: + lpass_macro_pds_exit(rx->pds); + return ret; } diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 714a411d5337..55503ba480bb 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -1828,8 +1828,10 @@ static int tx_macro_probe(struct platform_device *pdev) return PTR_ERR(tx->pds); base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto err; + } /* Update defaults for lpass sc7280 */ if (of_device_is_compatible(np, "qcom,sc7280-lpass-tx-macro")) { @@ -1846,8 +1848,10 @@ static int tx_macro_probe(struct platform_device *pdev) } tx->regmap = devm_regmap_init_mmio(dev, base, &tx_regmap_config); - if (IS_ERR(tx->regmap)) - return PTR_ERR(tx->regmap); + if (IS_ERR(tx->regmap)) { + ret = PTR_ERR(tx->regmap); + goto err; + } dev_set_drvdata(dev, tx); @@ -1907,6 +1911,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(tx->macro); err: + lpass_macro_pds_exit(tx->pds); + return ret; } diff --git a/sound/soc/codecs/lpass-va-macro.c b/sound/soc/codecs/lpass-va-macro.c index f3cb596058e0..d18b56e60433 100644 --- a/sound/soc/codecs/lpass-va-macro.c +++ b/sound/soc/codecs/lpass-va-macro.c @@ -1434,8 +1434,10 @@ static int va_macro_probe(struct platform_device *pdev) va->dmic_clk_div = VA_MACRO_CLK_DIV_2; } else { ret = va_macro_validate_dmic_sample_rate(sample_rate, va); - if (!ret) - return -EINVAL; + if (!ret) { + ret = -EINVAL; + goto err; + } } base = devm_platform_ioremap_resource(pdev, 0); @@ -1492,6 +1494,8 @@ err_mclk: err_dcodec: clk_disable_unprepare(va->macro); err: + lpass_macro_pds_exit(va->pds); + return ret; } diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c index 9ad7fc0baf07..20a07c92b2fc 100644 --- a/sound/soc/codecs/msm8916-wcd-digital.c +++ b/sound/soc/codecs/msm8916-wcd-digital.c @@ -1206,9 +1206,16 @@ static int msm8916_wcd_digital_probe(struct platform_device *pdev) dev_set_drvdata(dev, priv); - return devm_snd_soc_register_component(dev, &msm8916_wcd_digital, + ret = devm_snd_soc_register_component(dev, &msm8916_wcd_digital, msm8916_wcd_digital_dai, ARRAY_SIZE(msm8916_wcd_digital_dai)); + if (ret) + goto err_mclk; + + return 0; + +err_mclk: + clk_disable_unprepare(priv->mclk); err_clk: clk_disable_unprepare(priv->ahbclk); return ret; diff --git a/sound/soc/codecs/rk817_codec.c b/sound/soc/codecs/rk817_codec.c index 8fffe378618d..cce6f4e7992f 100644 --- a/sound/soc/codecs/rk817_codec.c +++ b/sound/soc/codecs/rk817_codec.c @@ -489,7 +489,7 @@ static int rk817_platform_probe(struct platform_device *pdev) rk817_codec_parse_dt_property(&pdev->dev, rk817_codec_data); - rk817_codec_data->mclk = clk_get(pdev->dev.parent, "mclk"); + rk817_codec_data->mclk = devm_clk_get(pdev->dev.parent, "mclk"); if (IS_ERR(rk817_codec_data->mclk)) { dev_dbg(&pdev->dev, "Unable to get mclk\n"); ret = -ENXIO; diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index be68d573a490..2b6c6d6b9771 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -1100,6 +1100,15 @@ void rt5682_jack_detect_handler(struct work_struct *work) return; } + if (rt5682->is_sdw) { + if (pm_runtime_status_suspended(rt5682->slave->dev.parent)) { + dev_dbg(&rt5682->slave->dev, + "%s: parent device is pm_runtime_status_suspended, skipping jack detection\n", + __func__); + return; + } + } + dapm = snd_soc_component_get_dapm(rt5682->component); snd_soc_dapm_mutex_lock(dapm); @@ -2822,14 +2831,11 @@ static int rt5682_bclk_set_rate(struct clk_hw *hw, unsigned long rate, for_each_component_dais(component, dai) if (dai->id == RT5682_AIF1) - break; - if (!dai) { - dev_err(rt5682->i2c_dev, "dai %d not found in component\n", - RT5682_AIF1); - return -ENODEV; - } + return rt5682_set_bclk1_ratio(dai, factor); - return rt5682_set_bclk1_ratio(dai, factor); + dev_err(rt5682->i2c_dev, "dai %d not found in component\n", + RT5682_AIF1); + return -ENODEV; } static const struct clk_ops rt5682_dai_clk_ops[RT5682_DAI_NUM_CLKS] = { diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c index 1cba8ec7cedb..b55f3ac3a267 100644 --- a/sound/soc/codecs/rt5682s.c +++ b/sound/soc/codecs/rt5682s.c @@ -2687,14 +2687,11 @@ static int rt5682s_bclk_set_rate(struct clk_hw *hw, unsigned long rate, for_each_component_dais(component, dai) if (dai->id == RT5682S_AIF1) - break; - if (!dai) { - dev_err(component->dev, "dai %d not found in component\n", - RT5682S_AIF1); - return -ENODEV; - } + return rt5682s_set_bclk1_ratio(dai, factor); - return rt5682s_set_bclk1_ratio(dai, factor); + dev_err(component->dev, "dai %d not found in component\n", + RT5682S_AIF1); + return -ENODEV; } static const struct clk_ops rt5682s_dai_clk_ops[RT5682S_DAI_NUM_CLKS] = { diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c index 6770825d037a..ea25fd58d43a 100644 --- a/sound/soc/codecs/rt711.c +++ b/sound/soc/codecs/rt711.c @@ -245,6 +245,13 @@ static void rt711_jack_detect_handler(struct work_struct *work) if (!rt711->component->card->instantiated) return; + if (pm_runtime_status_suspended(rt711->slave->dev.parent)) { + dev_dbg(&rt711->slave->dev, + "%s: parent device is pm_runtime_status_suspended, skipping jack detection\n", + __func__); + return; + } + reg = RT711_VERB_GET_PIN_SENSE | RT711_HP_OUT; ret = regmap_read(rt711->regmap, reg, &jack_status); if (ret < 0) diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index 1e75e93cf28f..6298ebe96e94 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -1274,29 +1274,7 @@ static int wcd934x_set_sido_input_src(struct wcd934x_codec *wcd, int sido_src) if (sido_src == wcd->sido_input_src) return 0; - if (sido_src == SIDO_SOURCE_INTERNAL) { - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_EN_MASK, 0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_PRE_ENX_MASK, 0x0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_RCO, - WCD934X_ANA_RCO_BG_EN_MASK, 0); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_PRE_EN1_MASK, - WCD934X_ANA_BUCK_PRE_EN1_ENABLE); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_PRE_EN2_MASK, - WCD934X_ANA_BUCK_PRE_EN2_ENABLE); - usleep_range(100, 110); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BUCK_CTL, - WCD934X_ANA_BUCK_HI_ACCU_EN_MASK, - WCD934X_ANA_BUCK_HI_ACCU_ENABLE); - usleep_range(100, 110); - } else if (sido_src == SIDO_SOURCE_RCO_BG) { + if (sido_src == SIDO_SOURCE_RCO_BG) { regmap_update_bits(wcd->regmap, WCD934X_ANA_RCO, WCD934X_ANA_RCO_BG_EN_MASK, WCD934X_ANA_RCO_BG_ENABLE); @@ -1382,8 +1360,6 @@ static int wcd934x_disable_ana_bias_and_syclk(struct wcd934x_codec *wcd) regmap_update_bits(wcd->regmap, WCD934X_CLK_SYS_MCLK_PRG, WCD934X_EXT_CLK_BUF_EN_MASK | WCD934X_MCLK_EN_MASK, 0x0); - wcd934x_set_sido_input_src(wcd, SIDO_SOURCE_INTERNAL); - regmap_update_bits(wcd->regmap, WCD934X_ANA_BIAS, WCD934X_ANA_BIAS_EN_MASK, 0); regmap_update_bits(wcd->regmap, WCD934X_ANA_BIAS, diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c index 5d4949c2ec9b..b14c6d104e6d 100644 --- a/sound/soc/codecs/wm8731.c +++ b/sound/soc/codecs/wm8731.c @@ -602,7 +602,7 @@ static int wm8731_hw_init(struct device *dev, struct wm8731_priv *wm8731) ret = wm8731_reset(wm8731->regmap); if (ret < 0) { dev_err(dev, "Failed to issue reset: %d\n", ret); - goto err_regulator_enable; + goto err; } /* Clear POWEROFF, keep everything else disabled */ @@ -619,10 +619,7 @@ static int wm8731_hw_init(struct device *dev, struct wm8731_priv *wm8731) regcache_mark_dirty(wm8731->regmap); -err_regulator_enable: - /* Regulators will be enabled by bias management */ - regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies), wm8731->supplies); - +err: return ret; } @@ -760,21 +757,27 @@ static int wm8731_i2c_probe(struct i2c_client *i2c, ret = PTR_ERR(wm8731->regmap); dev_err(&i2c->dev, "Failed to allocate register map: %d\n", ret); - return ret; + goto err_regulator_enable; } ret = wm8731_hw_init(&i2c->dev, wm8731); if (ret != 0) - return ret; + goto err_regulator_enable; ret = devm_snd_soc_register_component(&i2c->dev, &soc_component_dev_wm8731, &wm8731_dai, 1); if (ret != 0) { dev_err(&i2c->dev, "Failed to register CODEC: %d\n", ret); - return ret; + goto err_regulator_enable; } return 0; + +err_regulator_enable: + /* Regulators will be enabled by bias management */ + regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies), wm8731->supplies); + + return ret; } static const struct i2c_device_id wm8731_i2c_id[] = { diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 4650a6931a94..ffc24afb5a7a 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -372,7 +372,7 @@ static int fsl_sai_set_bclk(struct snd_soc_dai *dai, bool tx, u32 freq) continue; if (ratio == 1 && !support_1_1_ratio) continue; - else if (ratio & 1) + if ((ratio & 1) && ratio > 1) continue; diff = abs((long)clk_rate - ratio * freq); diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 8e037835bc58..f2157944247f 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -364,13 +364,15 @@ static int asoc_simple_set_tdm(struct snd_soc_dai *dai, struct snd_pcm_hw_params *params) { int sample_bits = params_width(params); - int slot_width = simple_dai->slot_width; - int slot_count = simple_dai->slots; + int slot_width, slot_count; int i, ret; if (!simple_dai || !simple_dai->tdm_width_map) return 0; + slot_width = simple_dai->slot_width; + slot_count = simple_dai->slots; + if (slot_width == 0) slot_width = sample_bits; diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c index 5e0529aa4f1d..9d617831dd20 100644 --- a/sound/soc/intel/boards/sof_es8336.c +++ b/sound/soc/intel/boards/sof_es8336.c @@ -27,9 +27,11 @@ #define SOF_ES8336_SSP_CODEC(quirk) ((quirk) & GENMASK(3, 0)) #define SOF_ES8336_SSP_CODEC_MASK (GENMASK(3, 0)) -#define SOF_ES8336_TGL_GPIO_QUIRK BIT(4) +#define SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK BIT(4) #define SOF_ES8336_ENABLE_DMIC BIT(5) #define SOF_ES8336_JD_INVERTED BIT(6) +#define SOF_ES8336_HEADPHONE_GPIO BIT(7) +#define SOC_ES8336_HEADSET_MIC1 BIT(8) static unsigned long quirk; @@ -39,7 +41,7 @@ MODULE_PARM_DESC(quirk, "Board-specific quirk override"); struct sof_es8336_private { struct device *codec_dev; - struct gpio_desc *gpio_pa; + struct gpio_desc *gpio_speakers, *gpio_headphone; struct snd_soc_jack jack; struct list_head hdmi_pcm_list; bool speaker_en; @@ -51,19 +53,31 @@ struct sof_hdmi_pcm { int device; }; -static const struct acpi_gpio_params pa_enable_gpio = { 0, 0, true }; -static const struct acpi_gpio_mapping acpi_es8336_gpios[] = { - { "pa-enable-gpios", &pa_enable_gpio, 1 }, +static const struct acpi_gpio_params enable_gpio0 = { 0, 0, true }; +static const struct acpi_gpio_params enable_gpio1 = { 1, 0, true }; + +static const struct acpi_gpio_mapping acpi_speakers_enable_gpio0[] = { + { "speakers-enable-gpios", &enable_gpio0, 1 }, { } }; -static const struct acpi_gpio_params quirk_pa_enable_gpio = { 1, 0, true }; -static const struct acpi_gpio_mapping quirk_acpi_es8336_gpios[] = { - { "pa-enable-gpios", &quirk_pa_enable_gpio, 1 }, +static const struct acpi_gpio_mapping acpi_speakers_enable_gpio1[] = { + { "speakers-enable-gpios", &enable_gpio1, 1 }, +}; + +static const struct acpi_gpio_mapping acpi_enable_both_gpios[] = { + { "speakers-enable-gpios", &enable_gpio0, 1 }, + { "headphone-enable-gpios", &enable_gpio1, 1 }, { } }; -static const struct acpi_gpio_mapping *gpio_mapping = acpi_es8336_gpios; +static const struct acpi_gpio_mapping acpi_enable_both_gpios_rev_order[] = { + { "speakers-enable-gpios", &enable_gpio1, 1 }, + { "headphone-enable-gpios", &enable_gpio0, 1 }, + { } +}; + +static const struct acpi_gpio_mapping *gpio_mapping = acpi_speakers_enable_gpio0; static void log_quirks(struct device *dev) { @@ -71,10 +85,14 @@ static void log_quirks(struct device *dev) dev_info(dev, "quirk SSP%ld\n", SOF_ES8336_SSP_CODEC(quirk)); if (quirk & SOF_ES8336_ENABLE_DMIC) dev_info(dev, "quirk DMIC enabled\n"); - if (quirk & SOF_ES8336_TGL_GPIO_QUIRK) - dev_info(dev, "quirk TGL GPIO enabled\n"); + if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + dev_info(dev, "Speakers GPIO1 quirk enabled\n"); + if (quirk & SOF_ES8336_HEADPHONE_GPIO) + dev_info(dev, "quirk headphone GPIO enabled\n"); if (quirk & SOF_ES8336_JD_INVERTED) dev_info(dev, "quirk JD inverted enabled\n"); + if (quirk & SOC_ES8336_HEADSET_MIC1) + dev_info(dev, "quirk headset at mic1 port enabled\n"); } static int sof_es8316_speaker_power_event(struct snd_soc_dapm_widget *w, @@ -83,12 +101,23 @@ static int sof_es8316_speaker_power_event(struct snd_soc_dapm_widget *w, struct snd_soc_card *card = w->dapm->card; struct sof_es8336_private *priv = snd_soc_card_get_drvdata(card); + if (priv->speaker_en == !SND_SOC_DAPM_EVENT_ON(event)) + return 0; + + priv->speaker_en = !SND_SOC_DAPM_EVENT_ON(event); + + if (SND_SOC_DAPM_EVENT_ON(event)) + msleep(70); + + gpiod_set_value_cansleep(priv->gpio_speakers, priv->speaker_en); + + if (!(quirk & SOF_ES8336_HEADPHONE_GPIO)) + return 0; + if (SND_SOC_DAPM_EVENT_ON(event)) - priv->speaker_en = false; - else - priv->speaker_en = true; + msleep(70); - gpiod_set_value_cansleep(priv->gpio_pa, priv->speaker_en); + gpiod_set_value_cansleep(priv->gpio_headphone, priv->speaker_en); return 0; } @@ -114,18 +143,23 @@ static const struct snd_soc_dapm_route sof_es8316_audio_map[] = { /* * There is no separate speaker output instead the speakers are muxed to - * the HP outputs. The mux is controlled by the "Speaker Power" supply. + * the HP outputs. The mux is controlled Speaker and/or headphone switch. */ {"Speaker", NULL, "HPOL"}, {"Speaker", NULL, "HPOR"}, {"Speaker", NULL, "Speaker Power"}, }; -static const struct snd_soc_dapm_route sof_es8316_intmic_in1_map[] = { +static const struct snd_soc_dapm_route sof_es8316_headset_mic2_map[] = { {"MIC1", NULL, "Internal Mic"}, {"MIC2", NULL, "Headset Mic"}, }; +static const struct snd_soc_dapm_route sof_es8316_headset_mic1_map[] = { + {"MIC2", NULL, "Internal Mic"}, + {"MIC1", NULL, "Headset Mic"}, +}; + static const struct snd_soc_dapm_route dmic_map[] = { /* digital mics */ {"DMic", NULL, "SoC DMIC"}, @@ -199,8 +233,13 @@ static int sof_es8316_init(struct snd_soc_pcm_runtime *runtime) card->dapm.idle_bias_off = true; - custom_map = sof_es8316_intmic_in1_map; - num_routes = ARRAY_SIZE(sof_es8316_intmic_in1_map); + if (quirk & SOC_ES8336_HEADSET_MIC1) { + custom_map = sof_es8316_headset_mic1_map; + num_routes = ARRAY_SIZE(sof_es8316_headset_mic1_map); + } else { + custom_map = sof_es8316_headset_mic2_map; + num_routes = ARRAY_SIZE(sof_es8316_headset_mic2_map); + } ret = snd_soc_dapm_add_routes(&card->dapm, custom_map, num_routes); if (ret) @@ -233,8 +272,14 @@ static int sof_es8336_quirk_cb(const struct dmi_system_id *id) { quirk = (unsigned long)id->driver_data; - if (quirk & SOF_ES8336_TGL_GPIO_QUIRK) - gpio_mapping = quirk_acpi_es8336_gpios; + if (quirk & SOF_ES8336_HEADPHONE_GPIO) { + if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + gpio_mapping = acpi_enable_both_gpios; + else + gpio_mapping = acpi_enable_both_gpios_rev_order; + } else if (quirk & SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) { + gpio_mapping = acpi_speakers_enable_gpio1; + } return 1; } @@ -257,7 +302,16 @@ static const struct dmi_system_id sof_es8336_quirk_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "IP3 tech"), DMI_MATCH(DMI_BOARD_NAME, "WN1"), }, - .driver_data = (void *)(SOF_ES8336_TGL_GPIO_QUIRK) + .driver_data = (void *)(SOF_ES8336_SPEAKERS_EN_GPIO1_QUIRK) + }, + { + .callback = sof_es8336_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HUAWEI"), + DMI_MATCH(DMI_BOARD_NAME, "BOHB-WAX9-PCB-B2"), + }, + .driver_data = (void *)(SOF_ES8336_HEADPHONE_GPIO | + SOC_ES8336_HEADSET_MIC1) }, {} }; @@ -585,10 +639,17 @@ static int sof_es8336_probe(struct platform_device *pdev) if (ret) dev_warn(codec_dev, "unable to add GPIO mapping table\n"); - priv->gpio_pa = gpiod_get_optional(codec_dev, "pa-enable", GPIOD_OUT_LOW); - if (IS_ERR(priv->gpio_pa)) { - ret = dev_err_probe(dev, PTR_ERR(priv->gpio_pa), - "could not get pa-enable GPIO\n"); + priv->gpio_speakers = gpiod_get_optional(codec_dev, "speakers-enable", GPIOD_OUT_LOW); + if (IS_ERR(priv->gpio_speakers)) { + ret = dev_err_probe(dev, PTR_ERR(priv->gpio_speakers), + "could not get speakers-enable GPIO\n"); + goto err_put_codec; + } + + priv->gpio_headphone = gpiod_get_optional(codec_dev, "headphone-enable", GPIOD_OUT_LOW); + if (IS_ERR(priv->gpio_headphone)) { + ret = dev_err_probe(dev, PTR_ERR(priv->gpio_headphone), + "could not get headphone-enable GPIO\n"); goto err_put_codec; } @@ -604,7 +665,7 @@ static int sof_es8336_probe(struct platform_device *pdev) ret = devm_snd_soc_register_card(dev, card); if (ret) { - gpiod_put(priv->gpio_pa); + gpiod_put(priv->gpio_speakers); dev_err(dev, "snd_soc_register_card failed: %d\n", ret); goto err_put_codec; } @@ -622,7 +683,7 @@ static int sof_es8336_remove(struct platform_device *pdev) struct snd_soc_card *card = platform_get_drvdata(pdev); struct sof_es8336_private *priv = snd_soc_card_get_drvdata(card); - gpiod_put(priv->gpio_pa); + gpiod_put(priv->gpio_speakers); device_remove_software_node(priv->codec_dev); put_device(priv->codec_dev); diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index ebec4d15edaa..7126fcb63d90 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -212,6 +212,19 @@ static const struct dmi_system_id sof_rt5682_quirk_table[] = { SOF_SSP_BT_OFFLOAD_PRESENT), }, + { + .callback = sof_rt5682_quirk_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Brya"), + DMI_MATCH(DMI_OEM_STRING, "AUDIO-MAX98360_ALC5682I_I2S_AMP_SSP2"), + }, + .driver_data = (void *)(SOF_RT5682_MCLK_EN | + SOF_RT5682_SSP_CODEC(0) | + SOF_SPEAKER_AMP_PRESENT | + SOF_MAX98360A_SPEAKER_AMP_PRESENT | + SOF_RT5682_SSP_AMP(2) | + SOF_RT5682_NUM_HDMIDEV(4)), + }, {} }; diff --git a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c index 6edc9b7108cd..ef19150e7b2e 100644 --- a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c @@ -132,13 +132,13 @@ static const struct snd_soc_acpi_adr_device mx8373_1_adr[] = { { .adr = 0x000123019F837300ull, .num_endpoints = 1, - .endpoints = &spk_l_endpoint, + .endpoints = &spk_r_endpoint, .name_prefix = "Right" }, { .adr = 0x000127019F837300ull, .num_endpoints = 1, - .endpoints = &spk_r_endpoint, + .endpoints = &spk_l_endpoint, .name_prefix = "Left" } }; diff --git a/sound/soc/meson/aiu-acodec-ctrl.c b/sound/soc/meson/aiu-acodec-ctrl.c index 27a6d3259c50..22e181646bc3 100644 --- a/sound/soc/meson/aiu-acodec-ctrl.c +++ b/sound/soc/meson/aiu-acodec-ctrl.c @@ -193,6 +193,9 @@ static const struct snd_soc_component_driver aiu_acodec_ctrl_component = { .of_xlate_dai_name = aiu_acodec_of_xlate_dai_name, .endianness = 1, .non_legacy_dai_naming = 1, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "acodec", +#endif }; int aiu_acodec_ctrl_register_component(struct device *dev) diff --git a/sound/soc/meson/aiu-codec-ctrl.c b/sound/soc/meson/aiu-codec-ctrl.c index c3ea733fce91..59ee66fc2bcd 100644 --- a/sound/soc/meson/aiu-codec-ctrl.c +++ b/sound/soc/meson/aiu-codec-ctrl.c @@ -140,6 +140,9 @@ static const struct snd_soc_component_driver aiu_hdmi_ctrl_component = { .of_xlate_dai_name = aiu_hdmi_of_xlate_dai_name, .endianness = 1, .non_legacy_dai_naming = 1, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "hdmi", +#endif }; int aiu_hdmi_ctrl_register_component(struct device *dev) diff --git a/sound/soc/meson/aiu.c b/sound/soc/meson/aiu.c index d299a70db7e5..88e611e64d14 100644 --- a/sound/soc/meson/aiu.c +++ b/sound/soc/meson/aiu.c @@ -103,6 +103,9 @@ static const struct snd_soc_component_driver aiu_cpu_component = { .pointer = aiu_fifo_pointer, .probe = aiu_cpu_component_probe, .remove = aiu_cpu_component_remove, +#ifdef CONFIG_DEBUG_FS + .debugfs_prefix = "cpu", +#endif }; static struct snd_soc_dai_driver aiu_cpu_dai_drv[] = { diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index ce153ac2c3ab..8c7da82a62ca 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2587,6 +2587,11 @@ int snd_soc_component_initialize(struct snd_soc_component *component, component->dev = dev; component->driver = driver; +#ifdef CONFIG_DEBUG_FS + if (!component->debugfs_prefix) + component->debugfs_prefix = driver->debugfs_prefix; +#endif + return 0; } EXPORT_SYMBOL_GPL(snd_soc_component_initialize); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index b435b5c4cfb7..ca917a849c42 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1687,8 +1687,7 @@ static void dapm_seq_run(struct snd_soc_card *card, switch (w->id) { case snd_soc_dapm_pre: if (!w->event) - list_for_each_entry_safe_continue(w, n, list, - power_list); + continue; if (event == SND_SOC_DAPM_STREAM_START) ret = w->event(w, @@ -1700,8 +1699,7 @@ static void dapm_seq_run(struct snd_soc_card *card, case snd_soc_dapm_post: if (!w->event) - list_for_each_entry_safe_continue(w, n, list, - power_list); + continue; if (event == SND_SOC_DAPM_STREAM_START) ret = w->event(w, diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 9a954680d492..11c9853e9e80 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1214,7 +1214,7 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe, be_substream->pcm->nonatomic = 1; } - dpcm = kzalloc(sizeof(struct snd_soc_dpcm), GFP_ATOMIC); + dpcm = kzalloc(sizeof(struct snd_soc_dpcm), GFP_KERNEL); if (!dpcm) return -ENOMEM; diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 72e50df7052c..3bb90a819650 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1436,12 +1436,12 @@ static int soc_tplg_dapm_widget_create(struct soc_tplg *tplg, template.num_kcontrols = le32_to_cpu(w->num_kcontrols); kc = devm_kcalloc(tplg->dev, le32_to_cpu(w->num_kcontrols), sizeof(*kc), GFP_KERNEL); if (!kc) - goto err; + goto hdr_err; kcontrol_type = devm_kcalloc(tplg->dev, le32_to_cpu(w->num_kcontrols), sizeof(unsigned int), GFP_KERNEL); if (!kcontrol_type) - goto err; + goto hdr_err; for (i = 0; i < le32_to_cpu(w->num_kcontrols); i++) { control_hdr = (struct snd_soc_tplg_ctl_hdr *)tplg->pos; diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index 4c9596742844..12f5cff22448 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -83,7 +83,14 @@ static const struct dmi_system_id sof_tplg_table[] = { }, .driver_data = "sof-adl-max98357a-rt5682-2way.tplg", }, - + { + .callback = sof_tplg_cb, + .matches = { + DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Brya"), + DMI_MATCH(DMI_OEM_STRING, "AUDIO-MAX98360_ALC5682I_I2S_AMP_SSP2"), + }, + .driver_data = "sof-adl-max98357a-rt5682.tplg", + }, {} }; diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index 9b11e9795a7a..3e5b319b44c7 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -904,8 +904,10 @@ static int sof_control_load(struct snd_soc_component *scomp, int index, return -ENOMEM; scontrol->name = kstrdup(hdr->name, GFP_KERNEL); - if (!scontrol->name) + if (!scontrol->name) { + kfree(scontrol); return -ENOMEM; + } scontrol->scomp = scomp; scontrol->access = kc->access; @@ -941,11 +943,13 @@ static int sof_control_load(struct snd_soc_component *scomp, int index, default: dev_warn(scomp->dev, "control type not supported %d:%d:%d\n", hdr->ops.get, hdr->ops.put, hdr->ops.info); + kfree(scontrol->name); kfree(scontrol); return 0; } if (ret < 0) { + kfree(scontrol->name); kfree(scontrol); return ret; } @@ -1068,6 +1072,46 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp, return 0; } +static void sof_disconnect_dai_widget(struct snd_soc_component *scomp, + struct snd_soc_dapm_widget *w) +{ + struct snd_soc_card *card = scomp->card; + struct snd_soc_pcm_runtime *rtd; + struct snd_soc_dai *cpu_dai; + int i; + + if (!w->sname) + return; + + list_for_each_entry(rtd, &card->rtd_list, list) { + /* does stream match DAI link ? */ + if (!rtd->dai_link->stream_name || + strcmp(w->sname, rtd->dai_link->stream_name)) + continue; + + switch (w->id) { + case snd_soc_dapm_dai_out: + for_each_rtd_cpu_dais(rtd, i, cpu_dai) { + if (cpu_dai->capture_widget == w) { + cpu_dai->capture_widget = NULL; + break; + } + } + break; + case snd_soc_dapm_dai_in: + for_each_rtd_cpu_dais(rtd, i, cpu_dai) { + if (cpu_dai->playback_widget == w) { + cpu_dai->playback_widget = NULL; + break; + } + } + break; + default: + break; + } + } +} + /* bind PCM ID to host component ID */ static int spcm_bind(struct snd_soc_component *scomp, struct snd_sof_pcm *spcm, int dir) @@ -1353,6 +1397,9 @@ static int sof_widget_unload(struct snd_soc_component *scomp, if (dai) list_del(&dai->list); + + sof_disconnect_dai_widget(scomp, widget); + break; default: break; @@ -1380,6 +1427,7 @@ static int sof_widget_unload(struct snd_soc_component *scomp, } kfree(scontrol->ipc_control_data); list_del(&scontrol->list); + kfree(scontrol->name); kfree(scontrol); } diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 2c01649c70f6..7c6ca2b433a5 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1194,6 +1194,7 @@ static void snd_usbmidi_output_drain(struct snd_rawmidi_substream *substream) } while (drain_urbs && timeout); finish_wait(&ep->drain_wait, &wait); } + port->active = 0; spin_unlock_irq(&ep->buffer_lock); } diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 64f5544d0a0a..7ef7a8abcc2b 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -599,6 +599,10 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x0db0, 0x419c), .map = msi_mpg_x570s_carbon_max_wifi_alc4080_map, }, + { /* MSI MAG X570S Torpedo Max */ + .id = USB_ID(0x0db0, 0xa073), + .map = msi_mpg_x570s_carbon_max_wifi_alc4080_map, + }, { /* MSI TRX40 */ .id = USB_ID(0x0db0, 0x543d), .map = trx40_mobo_map, diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index cec6e91afea2..6d699065e81a 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -669,9 +669,9 @@ static const struct snd_pcm_hardware snd_usb_hardware = SNDRV_PCM_INFO_PAUSE, .channels_min = 1, .channels_max = 256, - .buffer_bytes_max = 1024 * 1024, + .buffer_bytes_max = INT_MAX, /* limited by BUFFER_TIME later */ .period_bytes_min = 64, - .period_bytes_max = 512 * 1024, + .period_bytes_max = INT_MAX, /* limited by PERIOD_TIME later */ .periods_min = 2, .periods_max = 1024, }; @@ -1064,6 +1064,18 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre return err; } + /* set max period and buffer sizes for 1 and 2 seconds, respectively */ + err = snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_PERIOD_TIME, + 0, 1000000); + if (err < 0) + return err; + err = snd_pcm_hw_constraint_minmax(runtime, + SNDRV_PCM_HW_PARAM_BUFFER_TIME, + 0, 2000000); + if (err < 0) + return err; + /* additional hw constraints for implicit fb */ err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, hw_rule_format_implicit_fb, subs, diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index 167834133b9b..b8359a0aa008 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -8,7 +8,7 @@ */ /* handling of USB vendor/product ID pairs as 32-bit numbers */ -#define USB_ID(vendor, product) (((vendor) << 16) | (product)) +#define USB_ID(vendor, product) (((unsigned int)(vendor) << 16) | (product)) #define USB_ID_VENDOR(id) ((id) >> 16) #define USB_ID_PRODUCT(id) ((u16)(id)) diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c index b00634663346..0d828e35b401 100644 --- a/sound/x86/intel_hdmi_audio.c +++ b/sound/x86/intel_hdmi_audio.c @@ -1652,7 +1652,7 @@ static void hdmi_lpe_audio_free(struct snd_card *card) * This function is called when the i915 driver creates the * hdmi-lpe-audio platform device. */ -static int hdmi_lpe_audio_probe(struct platform_device *pdev) +static int __hdmi_lpe_audio_probe(struct platform_device *pdev) { struct snd_card *card; struct snd_intelhad_card *card_ctx; @@ -1815,6 +1815,11 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) return 0; } +static int hdmi_lpe_audio_probe(struct platform_device *pdev) +{ + return snd_card_free_on_error(&pdev->dev, __hdmi_lpe_audio_probe(pdev)); +} + static const struct dev_pm_ops hdmi_lpe_audio_pm = { SET_SYSTEM_SLEEP_PM_OPS(hdmi_lpe_audio_suspend, hdmi_lpe_audio_resume) }; diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 9afcc6467a09..e09d6908a21d 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 0eb90d21049e..ee15311b6be1 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -128,9 +128,9 @@ #define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ #define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ -/* SRBDS support */ #define MSR_IA32_MCU_OPT_CTRL 0x00000123 -#define RNGDS_MITG_DIS BIT(0) +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 91af2850b505..7678af364793 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -828,8 +828,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) s->map_cnt = %zu; \n\ s->map_skel_sz = sizeof(*s->maps); \n\ s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ - if (!s->maps) \n\ + if (!s->maps) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ ", map_cnt ); @@ -870,8 +872,10 @@ codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_li s->prog_cnt = %zu; \n\ s->prog_skel_sz = sizeof(*s->progs); \n\ s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ - if (!s->progs) \n\ + if (!s->progs) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ ", prog_cnt ); @@ -1182,10 +1186,13 @@ static int do_skeleton(int argc, char **argv) %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ struct bpf_object_skeleton *s; \n\ + int err; \n\ \n\ s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ - if (!s) \n\ + if (!s) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -1206,7 +1213,7 @@ static int do_skeleton(int argc, char **argv) return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ - return -ENOMEM; \n\ + return err; \n\ } \n\ \n\ static inline const void *%2$s__elf_bytes(size_t *sz) \n\ @@ -1466,12 +1473,12 @@ static int do_subskeleton(int argc, char **argv) \n\ obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ if (!obj) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ if (!s) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ s->sz = sizeof(*s); \n\ @@ -1483,7 +1490,7 @@ static int do_subskeleton(int argc, char **argv) s->var_cnt = %2$d; \n\ s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ if (!s->vars) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ ", @@ -1538,6 +1545,7 @@ static int do_subskeleton(int argc, char **argv) return obj; \n\ err: \n\ %1$s__destroy(obj); \n\ + errno = -err; \n\ return NULL; \n\ } \n\ \n\ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 1480910c792e..de66e1cc0734 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -217,9 +217,16 @@ strip-libs = $(filter-out -l%,$(1)) PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) -PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` +PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) +ifeq ($(CC_NO_CLANG), 0) + PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro +endif + $(OUTPUT)test-libperl.bin: $(BUILD) $(FLAGS_PERL_EMBED) diff --git a/tools/include/linux/arm-smccc.h b/tools/include/linux/arm-smccc.h new file mode 100644 index 000000000000..63ce9bebccd3 --- /dev/null +++ b/tools/include/linux/arm-smccc.h @@ -0,0 +1,193 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2015, Linaro Limited + */ +#ifndef __LINUX_ARM_SMCCC_H +#define __LINUX_ARM_SMCCC_H + +#include <linux/const.h> + +/* + * This file provides common defines for ARM SMC Calling Convention as + * specified in + * https://developer.arm.com/docs/den0028/latest + * + * This code is up-to-date with version DEN 0028 C + */ + +#define ARM_SMCCC_STD_CALL _AC(0,U) +#define ARM_SMCCC_FAST_CALL _AC(1,U) +#define ARM_SMCCC_TYPE_SHIFT 31 + +#define ARM_SMCCC_SMC_32 0 +#define ARM_SMCCC_SMC_64 1 +#define ARM_SMCCC_CALL_CONV_SHIFT 30 + +#define ARM_SMCCC_OWNER_MASK 0x3F +#define ARM_SMCCC_OWNER_SHIFT 24 + +#define ARM_SMCCC_FUNC_MASK 0xFFFF + +#define ARM_SMCCC_IS_FAST_CALL(smc_val) \ + ((smc_val) & (ARM_SMCCC_FAST_CALL << ARM_SMCCC_TYPE_SHIFT)) +#define ARM_SMCCC_IS_64(smc_val) \ + ((smc_val) & (ARM_SMCCC_SMC_64 << ARM_SMCCC_CALL_CONV_SHIFT)) +#define ARM_SMCCC_FUNC_NUM(smc_val) ((smc_val) & ARM_SMCCC_FUNC_MASK) +#define ARM_SMCCC_OWNER_NUM(smc_val) \ + (((smc_val) >> ARM_SMCCC_OWNER_SHIFT) & ARM_SMCCC_OWNER_MASK) + +#define ARM_SMCCC_CALL_VAL(type, calling_convention, owner, func_num) \ + (((type) << ARM_SMCCC_TYPE_SHIFT) | \ + ((calling_convention) << ARM_SMCCC_CALL_CONV_SHIFT) | \ + (((owner) & ARM_SMCCC_OWNER_MASK) << ARM_SMCCC_OWNER_SHIFT) | \ + ((func_num) & ARM_SMCCC_FUNC_MASK)) + +#define ARM_SMCCC_OWNER_ARCH 0 +#define ARM_SMCCC_OWNER_CPU 1 +#define ARM_SMCCC_OWNER_SIP 2 +#define ARM_SMCCC_OWNER_OEM 3 +#define ARM_SMCCC_OWNER_STANDARD 4 +#define ARM_SMCCC_OWNER_STANDARD_HYP 5 +#define ARM_SMCCC_OWNER_VENDOR_HYP 6 +#define ARM_SMCCC_OWNER_TRUSTED_APP 48 +#define ARM_SMCCC_OWNER_TRUSTED_APP_END 49 +#define ARM_SMCCC_OWNER_TRUSTED_OS 50 +#define ARM_SMCCC_OWNER_TRUSTED_OS_END 63 + +#define ARM_SMCCC_FUNC_QUERY_CALL_UID 0xff01 + +#define ARM_SMCCC_QUIRK_NONE 0 +#define ARM_SMCCC_QUIRK_QCOM_A6 1 /* Save/restore register a6 */ + +#define ARM_SMCCC_VERSION_1_0 0x10000 +#define ARM_SMCCC_VERSION_1_1 0x10001 +#define ARM_SMCCC_VERSION_1_2 0x10002 +#define ARM_SMCCC_VERSION_1_3 0x10003 + +#define ARM_SMCCC_1_3_SVE_HINT 0x10000 + +#define ARM_SMCCC_VERSION_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0) + +#define ARM_SMCCC_ARCH_FEATURES_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 1) + +#define ARM_SMCCC_ARCH_SOC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 2) + +#define ARM_SMCCC_ARCH_WORKAROUND_1 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x8000) + +#define ARM_SMCCC_ARCH_WORKAROUND_2 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x7fff) + +#define ARM_SMCCC_ARCH_WORKAROUND_3 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x3fff) + +#define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_FUNC_QUERY_CALL_UID) + +/* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */ +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 0xb66fb428U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 0xe911c52eU +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 0x564bcaa9U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3 0x743a004dU + +/* KVM "vendor specific" services */ +#define ARM_SMCCC_KVM_FUNC_FEATURES 0 +#define ARM_SMCCC_KVM_FUNC_PTP 1 +#define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 +#define ARM_SMCCC_KVM_NUM_FUNCS 128 + +#define ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_FEATURES) + +#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1 + +/* + * ptp_kvm is a feature used for time sync between vm and host. + * ptp_kvm module in guest kernel will get service from host using + * this hypercall ID. + */ +#define ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_PTP) + +/* ptp_kvm counter type ID */ +#define KVM_PTP_VIRT_COUNTER 0 +#define KVM_PTP_PHYS_COUNTER 1 + +/* Paravirtualised time calls (defined by ARM DEN0057A) */ +#define ARM_SMCCC_HV_PV_TIME_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x20) + +#define ARM_SMCCC_HV_PV_TIME_ST \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x21) + +/* TRNG entropy source calls (defined by ARM DEN0098) */ +#define ARM_SMCCC_TRNG_VERSION \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x50) + +#define ARM_SMCCC_TRNG_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x51) + +#define ARM_SMCCC_TRNG_GET_UUID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x52) + +#define ARM_SMCCC_TRNG_RND32 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x53) + +#define ARM_SMCCC_TRNG_RND64 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x53) + +/* + * Return codes defined in ARM DEN 0070A + * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C + */ +#define SMCCC_RET_SUCCESS 0 +#define SMCCC_RET_NOT_SUPPORTED -1 +#define SMCCC_RET_NOT_REQUIRED -2 +#define SMCCC_RET_INVALID_PARAMETER -3 + +#endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h index f41d8a0eb1a4..0616409513eb 100644 --- a/tools/include/linux/slab.h +++ b/tools/include/linux/slab.h @@ -28,7 +28,13 @@ static inline void *kzalloc(size_t size, gfp_t gfp) return kmalloc(size, gfp | __GFP_ZERO); } -void *kmem_cache_alloc(struct kmem_cache *cachep, int flags); +struct list_lru; + +void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *, int flags); +static inline void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) +{ + return kmem_cache_alloc_lru(cachep, NULL, flags); +} void kmem_cache_free(struct kmem_cache *cachep, void *objp); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c998860d7bbc..5d99e7c242a2 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -150,4 +150,11 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) + +/* Get the config size */ +#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + #endif diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 1b15ba13c477..a09315538a30 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, { struct perf_evsel *evsel; const struct perf_cpu_map *cpus = evlist->user_requested_cpus; - const struct perf_thread_map *threads = evlist->threads; if (!ops || !ops->get || !ops->mmap) return -EINVAL; @@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, perf_evlist__for_each_entry(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) + perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0) return -ENOMEM; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 6de5085e3e5a..ca5b74603008 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -184,6 +184,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "do_group_exit", "stop_this_cpu", "__invalid_creds", + "cpu_startup_entry", }; if (!func) @@ -559,12 +560,12 @@ static int add_dead_ends(struct objtool_file *file) else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { - WARN("can't find unreachable insn at %s+0x%x", + WARN("can't find unreachable insn at %s+0x%lx", reloc->sym->sec->name, reloc->addend); return -1; } } else { - WARN("can't find unreachable insn at %s+0x%x", + WARN("can't find unreachable insn at %s+0x%lx", reloc->sym->sec->name, reloc->addend); return -1; } @@ -594,12 +595,12 @@ reachable: else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { - WARN("can't find reachable insn at %s+0x%x", + WARN("can't find reachable insn at %s+0x%lx", reloc->sym->sec->name, reloc->addend); return -1; } } else { - WARN("can't find reachable insn at %s+0x%x", + WARN("can't find reachable insn at %s+0x%lx", reloc->sym->sec->name, reloc->addend); return -1; } @@ -1155,6 +1156,17 @@ static void annotate_call_site(struct objtool_file *file, : arch_nop_insn(insn->len)); insn->type = sibling ? INSN_RETURN : INSN_NOP; + + if (sibling) { + /* + * We've replaced the tail-call JMP insn by two new + * insn: RET; INT3, except we only have a single struct + * insn here. Mark it retpoline_safe to avoid the SLS + * warning, instead of adding another insn. + */ + insn->retpoline_safe = true; + } + return; } @@ -1239,11 +1251,20 @@ static bool same_function(struct instruction *insn1, struct instruction *insn2) return insn1->func->pfunc == insn2->func->pfunc; } -static bool is_first_func_insn(struct instruction *insn) +static bool is_first_func_insn(struct objtool_file *file, struct instruction *insn) { - return insn->offset == insn->func->offset || - (insn->type == INSN_ENDBR && - insn->offset == insn->func->offset + insn->len); + if (insn->offset == insn->func->offset) + return true; + + if (ibt) { + struct instruction *prev = prev_insn_same_sym(file, insn); + + if (prev && prev->type == INSN_ENDBR && + insn->offset == insn->func->offset + prev->len) + return true; + } + + return false; } /* @@ -1251,12 +1272,19 @@ static bool is_first_func_insn(struct instruction *insn) */ static int add_jump_destinations(struct objtool_file *file) { - struct instruction *insn; + struct instruction *insn, *jump_dest; struct reloc *reloc; struct section *dest_sec; unsigned long dest_off; for_each_insn(file, insn) { + if (insn->jump_dest) { + /* + * handle_group_alt() may have previously set + * 'jump_dest' for some alternatives. + */ + continue; + } if (!is_static_jump(insn)) continue; @@ -1271,7 +1299,10 @@ static int add_jump_destinations(struct objtool_file *file) add_retpoline_call(file, insn); continue; } else if (insn->func) { - /* internal or external sibling call (with reloc) */ + /* + * External sibling call or internal sibling call with + * STT_FUNC reloc. + */ add_call_dest(file, insn, reloc->sym, true); continue; } else if (reloc->sym->sec->idx) { @@ -1283,17 +1314,8 @@ static int add_jump_destinations(struct objtool_file *file) continue; } - insn->jump_dest = find_insn(file, dest_sec, dest_off); - if (!insn->jump_dest) { - - /* - * This is a special case where an alt instruction - * jumps past the end of the section. These are - * handled later in handle_group_alt(). - */ - if (!strcmp(insn->sec->name, ".altinstr_replacement")) - continue; - + jump_dest = find_insn(file, dest_sec, dest_off); + if (!jump_dest) { WARN_FUNC("can't find jump dest instruction at %s+0x%lx", insn->sec, insn->offset, dest_sec->name, dest_off); @@ -1303,8 +1325,8 @@ static int add_jump_destinations(struct objtool_file *file) /* * Cross-function jump. */ - if (insn->func && insn->jump_dest->func && - insn->func != insn->jump_dest->func) { + if (insn->func && jump_dest->func && + insn->func != jump_dest->func) { /* * For GCC 8+, create parent/child links for any cold @@ -1322,16 +1344,22 @@ static int add_jump_destinations(struct objtool_file *file) * subfunction is through a jump table. */ if (!strstr(insn->func->name, ".cold") && - strstr(insn->jump_dest->func->name, ".cold")) { - insn->func->cfunc = insn->jump_dest->func; - insn->jump_dest->func->pfunc = insn->func; + strstr(jump_dest->func->name, ".cold")) { + insn->func->cfunc = jump_dest->func; + jump_dest->func->pfunc = insn->func; - } else if (!same_function(insn, insn->jump_dest) && - is_first_func_insn(insn->jump_dest)) { - /* internal sibling call (without reloc) */ - add_call_dest(file, insn, insn->jump_dest->func, true); + } else if (!same_function(insn, jump_dest) && + is_first_func_insn(file, jump_dest)) { + /* + * Internal sibling call without reloc or with + * STT_SECTION reloc. + */ + add_call_dest(file, insn, jump_dest->func, true); + continue; } } + + insn->jump_dest = jump_dest; } return 0; @@ -1520,13 +1548,13 @@ static int handle_group_alt(struct objtool_file *file, continue; dest_off = arch_jump_destination(insn); - if (dest_off == special_alt->new_off + special_alt->new_len) + if (dest_off == special_alt->new_off + special_alt->new_len) { insn->jump_dest = next_insn_same_sec(file, last_orig_insn); - - if (!insn->jump_dest) { - WARN_FUNC("can't find alternative jump destination", - insn->sec, insn->offset); - return -1; + if (!insn->jump_dest) { + WARN_FUNC("can't find alternative jump destination", + insn->sec, insn->offset); + return -1; + } } } @@ -2225,14 +2253,14 @@ static int decode_sections(struct objtool_file *file) return ret; /* - * Must be before add_special_section_alts() as that depends on - * jump_dest being set. + * Must be before add_jump_destinations(), which depends on 'func' + * being set for alternatives, to enable proper sibling call detection. */ - ret = add_jump_destinations(file); + ret = add_special_section_alts(file); if (ret) return ret; - ret = add_special_section_alts(file); + ret = add_jump_destinations(file); if (ret) return ret; @@ -3190,9 +3218,8 @@ validate_ibt_reloc(struct objtool_file *file, struct reloc *reloc) static void warn_noendbr(const char *msg, struct section *sec, unsigned long offset, struct instruction *dest) { - WARN_FUNC("%srelocation to !ENDBR: %s+0x%lx", sec, offset, msg, - dest->func ? dest->func->name : dest->sec->name, - dest->func ? dest->offset - dest->func->offset : dest->offset); + WARN_FUNC("%srelocation to !ENDBR: %s", sec, offset, msg, + offstr(dest->sec, dest->offset)); } static void validate_ibt_dest(struct objtool_file *file, struct instruction *insn, @@ -3283,7 +3310,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, while (1) { next_insn = next_insn_to_validate(file, insn); - if (file->c_file && func && insn->func && func != insn->func->pfunc) { + if (func && insn->func && func != insn->func->pfunc) { WARN("%s() falls through to next function %s()", func->name, insn->func->name); return 1; @@ -3796,11 +3823,8 @@ static int validate_ibt(struct objtool_file *file) struct instruction *dest; dest = validate_ibt_reloc(file, reloc); - if (is_data && dest && !dest->noendbr) { - warn_noendbr("data ", reloc->sym->sec, - reloc->sym->offset + reloc->addend, - dest); - } + if (is_data && dest && !dest->noendbr) + warn_noendbr("data ", sec, reloc->offset, dest); } } diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d7b99a737496..ebf2ba5755c1 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -546,7 +546,7 @@ static struct section *elf_create_reloc_section(struct elf *elf, int reltype); int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, int addend) + unsigned int type, struct symbol *sym, long addend) { struct reloc *reloc; @@ -575,37 +575,180 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, return 0; } -int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, - unsigned long offset, unsigned int type, - struct section *insn_sec, unsigned long insn_off) +/* + * Ensure that any reloc section containing references to @sym is marked + * changed such that it will get re-generated in elf_rebuild_reloc_sections() + * with the new symbol index. + */ +static void elf_dirty_reloc_sym(struct elf *elf, struct symbol *sym) +{ + struct section *sec; + + list_for_each_entry(sec, &elf->sections, list) { + struct reloc *reloc; + + if (sec->changed) + continue; + + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym == sym) { + sec->changed = true; + break; + } + } + } +} + +/* + * Move the first global symbol, as per sh_info, into a new, higher symbol + * index. This fees up the shndx for a new local symbol. + */ +static int elf_move_global_symbol(struct elf *elf, struct section *symtab, + struct section *symtab_shndx) { + Elf_Data *data, *shndx_data = NULL; + Elf32_Word first_non_local; struct symbol *sym; - int addend; + Elf_Scn *s; - if (insn_sec->sym) { - sym = insn_sec->sym; - addend = insn_off; + first_non_local = symtab->sh.sh_info; - } else { - /* - * The Clang assembler strips section symbols, so we have to - * reference the function symbol instead: - */ - sym = find_symbol_containing(insn_sec, insn_off); - if (!sym) { - /* - * Hack alert. This happens when we need to reference - * the NOP pad insn immediately after the function. - */ - sym = find_symbol_containing(insn_sec, insn_off - 1); + sym = find_symbol_by_index(elf, first_non_local); + if (!sym) { + WARN("no non-local symbols !?"); + return first_non_local; + } + + s = elf_getscn(elf->elf, symtab->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; + } + + data = elf_newdata(s); + if (!data) { + WARN_ELF("elf_newdata"); + return -1; + } + + data->d_buf = &sym->sym; + data->d_size = sizeof(sym->sym); + data->d_align = 1; + data->d_type = ELF_T_SYM; + + sym->idx = symtab->sh.sh_size / sizeof(sym->sym); + elf_dirty_reloc_sym(elf, sym); + + symtab->sh.sh_info += 1; + symtab->sh.sh_size += data->d_size; + symtab->changed = true; + + if (symtab_shndx) { + s = elf_getscn(elf->elf, symtab_shndx->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; } - if (!sym) { - WARN("can't find symbol containing %s+0x%lx", insn_sec->name, insn_off); + shndx_data = elf_newdata(s); + if (!shndx_data) { + WARN_ELF("elf_newshndx_data"); return -1; } - addend = insn_off - sym->offset; + shndx_data->d_buf = &sym->sec->idx; + shndx_data->d_size = sizeof(Elf32_Word); + shndx_data->d_align = 4; + shndx_data->d_type = ELF_T_WORD; + + symtab_shndx->sh.sh_size += 4; + symtab_shndx->changed = true; + } + + return first_non_local; +} + +static struct symbol * +elf_create_section_symbol(struct elf *elf, struct section *sec) +{ + struct section *symtab, *symtab_shndx; + Elf_Data *shndx_data = NULL; + struct symbol *sym; + Elf32_Word shndx; + + symtab = find_section_by_name(elf, ".symtab"); + if (symtab) { + symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); + if (symtab_shndx) + shndx_data = symtab_shndx->data; + } else { + WARN("no .symtab"); + return NULL; + } + + sym = malloc(sizeof(*sym)); + if (!sym) { + perror("malloc"); + return NULL; + } + memset(sym, 0, sizeof(*sym)); + + sym->idx = elf_move_global_symbol(elf, symtab, symtab_shndx); + if (sym->idx < 0) { + WARN("elf_move_global_symbol"); + return NULL; + } + + sym->name = sec->name; + sym->sec = sec; + + // st_name 0 + sym->sym.st_info = GELF_ST_INFO(STB_LOCAL, STT_SECTION); + // st_other 0 + // st_value 0 + // st_size 0 + shndx = sec->idx; + if (shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) { + sym->sym.st_shndx = shndx; + if (!shndx_data) + shndx = 0; + } else { + sym->sym.st_shndx = SHN_XINDEX; + if (!shndx_data) { + WARN("no .symtab_shndx"); + return NULL; + } + } + + if (!gelf_update_symshndx(symtab->data, shndx_data, sym->idx, &sym->sym, shndx)) { + WARN_ELF("gelf_update_symshndx"); + return NULL; + } + + elf_add_symbol(elf, sym); + + return sym; +} + +int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, + unsigned long offset, unsigned int type, + struct section *insn_sec, unsigned long insn_off) +{ + struct symbol *sym = insn_sec->sym; + int addend = insn_off; + + if (!sym) { + /* + * Due to how weak functions work, we must use section based + * relocations. Symbol based relocations would result in the + * weak and non-weak function annotations being overlaid on the + * non-weak function after linking. + */ + sym = elf_create_section_symbol(elf, insn_sec); + if (!sym) + return -1; + + insn_sec->sym = sym; } return elf_add_reloc(elf, sec, offset, type, sym, addend); diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 22ba7e2b816e..9b36802ed86f 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -73,7 +73,7 @@ struct reloc { struct symbol *sym; unsigned long offset; unsigned int type; - int addend; + long addend; int idx; bool jump_table_start; }; @@ -135,7 +135,7 @@ struct elf *elf_open_read(const char *name, int flags); struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr); int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, int addend); + unsigned int type, struct symbol *sym, long addend); int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int type, struct section *insn_sec, unsigned long insn_off); diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h index 7a5c13a78f87..a6e72d916807 100644 --- a/tools/objtool/include/objtool/objtool.h +++ b/tools/objtool/include/objtool/objtool.h @@ -27,7 +27,7 @@ struct objtool_file { struct list_head static_call_list; struct list_head mcount_loc_list; struct list_head endbr_list; - bool ignore_unreachables, c_file, hints, rodata; + bool ignore_unreachables, hints, rodata; unsigned int nr_endbr; unsigned int nr_endbr_int; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index b09946f4e1d6..843ff3c2f28e 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -129,7 +129,6 @@ struct objtool_file *objtool_open_read(const char *_objname) INIT_LIST_HEAD(&file.static_call_list); INIT_LIST_HEAD(&file.mcount_loc_list); INIT_LIST_HEAD(&file.endbr_list); - file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment"); file.ignore_unreachables = no_unreachable; file.hints = false; diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 9c330cdfa973..71ebdf8125de 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1], linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1], linkperf:perf-evlist[1], linkperf:perf-ftrace[1], linkperf:perf-help[1], linkperf:perf-inject[1], -linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1], +linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1], linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1], linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1], linkperf:perf-script[1], linkperf:perf-test[1], diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 96ad944ca6a8..f3bf9297bcc0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + ifeq ($(CC_NO_CLANG), 0) + PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS)) + endif endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) @@ -790,6 +793,9 @@ else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) CFLAGS += -DHAVE_LIBPERL_SUPPORT + ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -Wno-compound-token-split-by-macro + endif $(call detected,CONFIG_LIBPERL) endif endif diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 86e2e926aa0e..e8b577d33e53 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, bool privileged = perf_event_paranoid_check(-1); struct evsel *tracking_evsel; int err; + u64 bit; sper->evlist = evlist; @@ -239,6 +240,21 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, arm_spe_set_timestamp(itr, arm_spe_evsel); } + /* + * Set this only so that perf report knows that SPE generates memory info. It has no effect + * on the opening of the event or the SPE data produced. + */ + evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); + + /* + * The PHYS_ADDR flag does not affect the driver behaviour, it is used to + * inform that the resulting output's SPE samples contain physical addresses + * where applicable. + */ + bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable"); + if (arm_spe_evsel->core.attr.config & bit) + evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR); + /* Add dummy event to keep tracking */ err = parse_events(evlist, "dummy:u", NULL); if (err) diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index d2ce31e28cd7..41c1596e5207 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -8,27 +8,6 @@ #include "callchain.h" #include "record.h" -/* On arm64, kernel text segment starts at high memory address, - * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory - * address, like 0xffff 0000 00ax xxxx. When only small amount of - * memory is used by modules, gap between end of module's text segment - * and start of kernel text segment may reach 2G. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -#define SYMBOL_LIMIT (1 << 12) /* 4K */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) || - (strchr(p->name, '[') == NULL && strchr(c->name, '['))) - /* Limit range of last symbol in module and kernel */ - p->end += SYMBOL_LIMIT; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} - void arch__add_leaf_frame_record_opts(struct record_opts *opts) { opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 8a79c4126e5b..0115f3166568 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,5 +1,4 @@ perf-y += header.o -perf-y += machine.o perf-y += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c deleted file mode 100644 index e652a1aa8132..000000000000 --- a/tools/perf/arch/powerpc/util/machine.c +++ /dev/null @@ -1,25 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <inttypes.h> -#include <stdio.h> -#include <string.h> -#include <internal/lib.h> // page_size -#include "debug.h" -#include "symbol.h" - -/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000 - * whereas the modules are located at very high memory addresses, - * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very high. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Limit the range of last kernel symbol */ - p->end += page_size; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index 7644a4f6d4a4..98bc3f39d5f3 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) return 0; } - -/* On s390 kernel text segment start is located at very low memory addresses, - * for example 0x10000. Modules are located at very high memory addresses, - * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very big. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Last kernel symbol mapped to end of page */ - p->end = roundup(p->end, page_size); - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 134612bde0cb..4256dc5d6236 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0; + int nrcpus; + size_t size; if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) init_fdmaps(w, 50); if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 37de970c9743..2728b0140853 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -291,9 +291,11 @@ static void print_summary(void) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0, events = EPOLLIN; + int nrcpus; + size_t size; if (oneshot) events |= EPOLLONESHOT; @@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) } if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index dbcecec4eeda..f05db4cf983d 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -122,12 +122,14 @@ static void print_summary(void) int bench_futex_hash(int argc, const char **argv) { int ret = 0; - cpu_set_t cpuset; + cpu_set_t *cpuset; struct sigaction act; unsigned int i; pthread_attr_t thread_attr; struct worker *worker = NULL; struct perf_cpu_map *cpu; + int nrcpus; + size_t size; argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); if (argc) { @@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = params.nthreads; pthread_attr_init(&thread_attr); gettimeofday(&bench__start, NULL); + + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex)); if (!worker[i].futex) goto errmem; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); - + } ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, (void *)(struct worker *) &worker[i]); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); pthread_attr_destroy(&thread_attr); pthread_mutex_lock(&thread_lock); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6fc9a3d55c1f..0abb3f7ee24f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -120,11 +120,17 @@ static void *workerfn(void *arg) static void create_threads(struct worker *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; @@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, } else worker[i].futex = &global_futex; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) + if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } int bench_futex_lock_pi(int argc, const char **argv) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 2f59d5d1c509..b6faabfafb8e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 861deb934745..e47f46a3a47e 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void print_run(struct thread_data *waking_worker, unsigned int run_num) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index cfda48bef1d7..201a3555f09a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -97,22 +97,32 @@ static void print_summary(void) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; - + size_t size; + int nrcpus = perf_cpu_map__nr(cpu); threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index f2640179ada9..44e1f8a44087 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -34,6 +34,7 @@ #include <linux/numa.h> #include <linux/zalloc.h> +#include "../util/header.h" #include <numa.h> #include <numaif.h> @@ -54,7 +55,7 @@ struct thread_data { int curr_cpu; - cpu_set_t bind_cpumask; + cpu_set_t *bind_cpumask; int bind_node; u8 *process_data; int process_nr; @@ -266,71 +267,115 @@ static bool node_has_cpus(int node) return ret; } -static cpu_set_t bind_to_cpu(int target_cpu) +static cpu_set_t *bind_to_cpu(int target_cpu) { - cpu_set_t orig_mask, mask; - int ret; + int nrcpus = numa_num_possible_cpus(); + cpu_set_t *orig_mask, *mask; + size_t size; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); + + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; + + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; - CPU_ZERO(&mask); + CPU_ZERO_S(size, mask); if (target_cpu == -1) { int cpu; for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { - BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus); - CPU_SET(target_cpu, &mask); + if (target_cpu < 0 || target_cpu >= g->p.nr_cpus) + goto err; + + CPU_SET_S(target_cpu, size, mask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); } -static cpu_set_t bind_to_node(int target_node) +static cpu_set_t *bind_to_node(int target_node) { - cpu_set_t orig_mask, mask; + int nrcpus = numa_num_possible_cpus(); + size_t size; + cpu_set_t *orig_mask, *mask; int cpu; - int ret; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); - CPU_ZERO(&mask); + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; + + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; + + CPU_ZERO_S(size, mask); if (target_node == NUMA_NO_NODE) { for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { struct bitmask *cpumask = numa_allocate_cpumask(); - BUG_ON(!cpumask); + if (!cpumask) + goto err; + if (!numa_node_to_cpus(target_node, cpumask)) { for (cpu = 0; cpu < (int)cpumask->size; cpu++) { if (numa_bitmask_isbitset(cpumask, cpu)) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } } numa_free_cpumask(cpumask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); } -static void bind_to_cpumask(cpu_set_t mask) +static void bind_to_cpumask(cpu_set_t *mask) { int ret; + size_t size = CPU_ALLOC_SIZE(numa_num_possible_cpus()); - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + ret = sched_setaffinity(0, size, mask); + if (ret) { + CPU_FREE(mask); + BUG_ON(ret); + } } static void mempol_restore(void) @@ -376,7 +421,7 @@ do { \ static u8 *alloc_data(ssize_t bytes0, int map_flags, int init_zero, int init_cpu0, int thp, int init_random) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask = NULL; ssize_t bytes; u8 *buf; int ret; @@ -434,6 +479,7 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags, /* Restore affinity: */ if (init_cpu0) { bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); mempol_restore(); } @@ -585,10 +631,16 @@ static int parse_setup_cpu_list(void) return -1; } + if (is_cpu_online(bind_cpu_0) != 1 || is_cpu_online(bind_cpu_1) != 1) { + printf("\nTest not applicable, bind_cpu_0 or bind_cpu_1 is offline\n"); + return -1; + } + BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0); BUG_ON(bind_cpu_0 > bind_cpu_1); for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { + size_t size = CPU_ALLOC_SIZE(g->p.nr_cpus); int i; for (i = 0; i < mul; i++) { @@ -608,10 +660,15 @@ static int parse_setup_cpu_list(void) tprintf("%2d", bind_cpu); } - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(size, td->bind_cpumask); for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) { - BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus); - CPU_SET(cpu, &td->bind_cpumask); + if (cpu < 0 || cpu >= g->p.nr_cpus) { + CPU_FREE(td->bind_cpumask); + BUG_ON(-1); + } + CPU_SET_S(cpu, size, td->bind_cpumask); } t++; } @@ -752,8 +809,6 @@ static int parse_nodes_opt(const struct option *opt __maybe_unused, return parse_node_list(arg); } -#define BIT(x) (1ul << x) - static inline uint32_t lfsr_32(uint32_t lfsr) { const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31); @@ -1241,7 +1296,7 @@ static void *worker_thread(void *__tdata) * by migrating to CPU#0: */ if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask; int target_cpu; int this_cpu; @@ -1265,6 +1320,7 @@ static void *worker_thread(void *__tdata) printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu); bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); } if (details >= 3) { @@ -1398,21 +1454,31 @@ static void init_thread_data(void) for (t = 0; t < g->p.nr_tasks; t++) { struct thread_data *td = g->threads + t; + size_t cpuset_size = CPU_ALLOC_SIZE(g->p.nr_cpus); int cpu; /* Allow all nodes by default: */ td->bind_node = NUMA_NO_NODE; /* Allow all CPUs by default: */ - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(cpuset_size, td->bind_cpumask); for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &td->bind_cpumask); + CPU_SET_S(cpu, cpuset_size, td->bind_cpumask); } } static void deinit_thread_data(void) { ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + int t; + + /* Free the bind_cpumask allocated for thread_data */ + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + CPU_FREE(td->bind_cpumask); + } free_data(g->threads, size); } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index ba74fab02e62..069825c48d40 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -989,8 +989,11 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru struct mmap *overwrite_mmap = evlist->overwrite_mmap; struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; - thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, - thread_data->mask->maps.nbits); + if (cpu_map__is_dummy(cpus)) + thread_data->nr_mmaps = nr_mmaps; + else + thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, + thread_data->mask->maps.nbits); if (mmap) { thread_data->maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *)); if (!thread_data->maps) @@ -1007,16 +1010,17 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps); for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) { - if (test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { + if (cpu_map__is_dummy(cpus) || + test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { if (thread_data->maps) { thread_data->maps[tm] = &mmap[m]; pr_debug2("thread_data[%p]: cpu%d: maps[%d] -> mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } if (thread_data->overwrite_maps) { thread_data->overwrite_maps[tm] = &overwrite_mmap[m]; pr_debug2("thread_data[%p]: cpu%d: ow_maps[%d] -> ow_mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } tm++; } @@ -3329,6 +3333,9 @@ static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_c { int c; + if (cpu_map__is_dummy(cpus)) + return; + for (c = 0; c < cpus->nr; c++) set_bit(cpus->map[c].cpu, mask->bits); } @@ -3680,6 +3687,11 @@ static int record__init_thread_masks(struct record *rec) if (!record__threads_enabled(rec)) return record__init_thread_default_masks(rec, cpus); + if (cpu_map__is_dummy(cpus)) { + pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n"); + return -EINVAL; + } + switch (rec->opts.threads_spec) { case THREAD_SPEC__CPU: ret = record__init_thread_cpu_masks(rec, cpus); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1ad75c7ba074..afe4a5539ecc 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -353,6 +353,7 @@ static int report__setup_sample_type(struct report *rep) struct perf_session *session = rep->session; u64 sample_type = evlist__combined_sample_type(session->evlist); bool is_pipe = perf_data__is_pipe(session->data); + struct evsel *evsel; if (session->itrace_synth_opts->callchain || session->itrace_synth_opts->add_callchain || @@ -407,6 +408,19 @@ static int report__setup_sample_type(struct report *rep) } if (sort__mode == SORT_MODE__MEMORY) { + /* + * FIXUP: prior to kernel 5.18, Arm SPE missed to set + * PERF_SAMPLE_DATA_SRC bit in sample type. For backward + * compatibility, set the bit if it's an old perf data file. + */ + evlist__for_each_entry(session->evlist, evsel) { + if (strstr(evsel->name, "arm_spe") && + !(sample_type & PERF_SAMPLE_DATA_SRC)) { + evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC; + sample_type |= PERF_SAMPLE_DATA_SRC; + } + } + if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) { ui__error("Selected --mem-mode but no mem data. " "Did you call perf record without -d?\n"); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a2f117936188..cf5eab5431b4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -461,7 +461,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(DATA_SRC) && - evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC)) + evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set)) return -EINVAL; if (PRINT_FIELD(WEIGHT) && diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 2f6b67189b42..0170cb0819d6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -55,6 +55,7 @@ struct cmd_struct { }; static struct cmd_struct commands[] = { + { "archive", NULL, 0 }, { "buildid-cache", cmd_buildid_cache, 0 }, { "buildid-list", cmd_buildid_list, 0 }, { "config", cmd_config, 0 }, @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "iostat", NULL, 0 }, { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, @@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(commands); i++) { struct cmd_struct *p = commands+i; + if (p->fn == NULL) + continue; if (strcmp(p->cmd, cmd)) continue; exit(run_builtin(p, argc, argv)); @@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void) static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { - return eprintf(level, verbose, fmt, ap); + return veprintf(level, verbose, fmt, ap); } int main(int argc, const char **argv) diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README index 454505d343fa..eb3f7d4bb324 100644 --- a/tools/perf/tests/attr/README +++ b/tools/perf/tests/attr/README @@ -60,6 +60,7 @@ Following tests are defined (with perf commands): perf record -R kill (test-record-raw) perf record -c 2 -e arm_spe_0// -- kill (test-record-spe-period) perf record -e arm_spe_0/period=3/ -- kill (test-record-spe-period-term) + perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address) perf stat -e cycles kill (test-stat-basic) perf stat kill (test-stat-default) perf stat -d kill (test-stat-detailed-1) diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address new file mode 100644 index 000000000000..7ebcf5012ce3 --- /dev/null +++ b/tools/perf/tests/attr/test-record-spe-physical-address @@ -0,0 +1,12 @@ +[config] +command = record +args = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1 +ret = 1 +arch = aarch64 + +[event-10:base-record-spe] +# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR +sample_type=622727 + +# dummy event +[event-1:base-record-spe]
\ No newline at end of file diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2dab2d262060..afdca7f2959f 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr } err = unwind__get_entries(unwind_entry, &cnt, thread, - &sample, MAX_STACK); + &sample, MAX_STACK, false); if (err) pr_debug("unwind failed\n"); else if (cnt != MAX_STACK) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index d12d0ad81801..4ad0dfbc8b21 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -47,6 +47,17 @@ } \ } +static int test__tsc_is_supported(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture\n"); + return TEST_SKIP; + } + + return TEST_OK; +} + /** * test__perf_time_to_tsc - test converting perf time to TSC. * @@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su struct perf_cpu_map *cpus = NULL; struct evlist *evlist = NULL; struct evsel *evsel = NULL; - int err = -1, ret, i; + int err = TEST_FAIL, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; struct perf_event_mmap_page *pc; @@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; - if (!TSC_IS_SUPPORTED) { - pr_debug("Test not supported on this architecture"); - return TEST_SKIP; - } threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -116,6 +123,10 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su evsel->core.attr.enable_on_exec = 0; } + if (evlist__open(evlist) == -ENOENT) { + err = TEST_SKIP; + goto out_err; + } CHECK__(evlist__open(evlist)); CHECK__(evlist__mmap(evlist, UINT_MAX)); @@ -124,8 +135,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { - fprintf(stderr, " (not supported)"); - return 0; + pr_debug("perf_read_tsc_conversion is not supported in current kernel\n"); + err = TEST_SKIP; } goto out_err; } @@ -191,7 +202,7 @@ next_event: test_tsc >= comm2_tsc) goto out_err; - err = 0; + err = TEST_OK; out_err: evlist__delete(evlist); @@ -200,4 +211,15 @@ out_err: return err; } -DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); +static struct test_case time_to_tsc_tests[] = { + TEST_CASE_REASON("TSC support", tsc_is_supported, + "This architecture does not support"), + TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc, + "perf_read_tsc_conversion is not supported"), + { .name = NULL, } +}; + +struct test_suite suite__perf_time_to_tsc = { + .desc = "Convert perf time to TSC", + .test_cases = time_to_tsc_tests, +}; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e4c641b240df..82cc396ef516 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) objdump_process.argv = objdump_argv; objdump_process.out = -1; objdump_process.err = -1; + objdump_process.no_stderr = 1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index d2b64e3f588b..1a80151baed9 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -1033,10 +1033,11 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & + (PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR); attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC | - PERF_SAMPLE_WEIGHT; + PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR; if (spe->timeless_decoding) attr.sample_type &= ~(u64)PERF_SAMPLE_TIME; else diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 2242a885fbd7..4940be4a0569 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; } - ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); sample->user_regs = old_regs; if (ret || entries.length != 2) diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index df7b18fb6b6e..1aad7d6d34aa 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -20,7 +20,11 @@ #include "llvm/Option/Option.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/ManagedStatic.h" +#if CLANG_VERSION_MAJOR >= 14 +#include "llvm/MC/TargetRegistry.h" +#else #include "llvm/Support/TargetRegistry.h" +#endif #include "llvm/Support/TargetSelect.h" #include "llvm/Target/TargetMachine.h" #include "llvm/Target/TargetOptions.h" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d546ff724dbe..a27132e5a5ef 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -983,6 +983,57 @@ static int write_dir_format(struct feat_fd *ff, return do_write(ff, &data->dir.version, sizeof(data->dir.version)); } +/* + * Check whether a CPU is online + * + * Returns: + * 1 -> if CPU is online + * 0 -> if CPU is offline + * -1 -> error case + */ +int is_cpu_online(unsigned int cpu) +{ + char *str; + size_t strlen; + char buf[256]; + int status = -1; + struct stat statbuf; + + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d", cpu); + if (stat(buf, &statbuf) != 0) + return 0; + + /* + * Check if /sys/devices/system/cpu/cpux/online file + * exists. Some cases cpu0 won't have online file since + * it is not expected to be turned off generally. + * In kernels without CONFIG_HOTPLUG_CPU, this + * file won't exist + */ + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d/online", cpu); + if (stat(buf, &statbuf) != 0) + return 1; + + /* + * Read online file using sysfs__read_str. + * If read or open fails, return -1. + * If read succeeds, return value from file + * which gets stored in "str" + */ + snprintf(buf, sizeof(buf), + "devices/system/cpu/cpu%d/online", cpu); + + if (sysfs__read_str(buf, &str, &strlen) < 0) + return status; + + status = atoi(str); + + free(str); + return status; +} + #ifdef HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff, struct evlist *evlist __maybe_unused) diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index c9e3265832d9..0eb4bc29a5a4 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -158,6 +158,7 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size); int write_padded(struct feat_fd *fd, const void *bf, size_t count, size_t count_aligned); +int is_cpu_online(unsigned int cpu); /* * arch specific callback */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b80048546451..95391236f5f6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; return unwind__get_entries(unwind_entry, cursor, - thread, sample, max_stack); + thread, sample, max_stack, false); } int thread__resolve_callchain(struct thread *thread, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 24997925ae00..dd84fed698a3 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1523,7 +1523,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, bool use_uncore_alias; LIST_HEAD(config_terms); - if (verbose > 1) { + pmu = parse_state->fake_pmu ?: perf_pmu__find(name); + + if (verbose > 1 && !(pmu && pmu->selectable)) { fprintf(stderr, "Attempting to add event pmu '%s' with '", name); if (head_config) { @@ -1536,7 +1538,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, fprintf(stderr, "' that may result in non-fatal errors\n"); } - pmu = parse_state->fake_pmu ?: perf_pmu__find(name); if (!pmu) { char *err_str; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 3b8dfe603e50..f9a320694b85 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2095,6 +2095,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, bool needs_swap, union perf_event *error) { union perf_event *event; + u16 event_size; /* * Ensure we have enough space remaining to read @@ -2107,15 +2108,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size <= mmap_size) + event_size = event->header.size; + if (head + event_size <= mmap_size) return event; /* We're not fetching the event so swap back again */ if (needs_swap) perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" - " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); + /* Check if the event fits into the next mmapped buf. */ + if (event_size <= mmap_size - head % page_size) { + /* Remap buf and fetch again. */ + return NULL; + } + + /* Invalid input. Event size should never exceed mmap_size. */ + pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size); return error; } @@ -2567,7 +2576,7 @@ int perf_session__process_events(struct perf_session *session) if (perf_data__is_pipe(session->data)) return __perf_session__process_pipe_events(session); - if (perf_data__is_dir(session->data)) + if (perf_data__is_dir(session->data) && session->data->dir.nr) return __perf_session__process_dir_events(session); return __perf_session__process_events(session); diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 483f05004e68..c255a2c90cd6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,14 @@ -from os import getenv +from os import getenv, path from subprocess import Popen, PIPE from re import sub cc = getenv("CC") cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline() +src_feature_tests = getenv('srctree') + '/tools/build/feature' def clang_has_option(option): - return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] + cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() + return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ] if cc_is_clang: from distutils.sysconfig import get_config_vars @@ -23,6 +25,8 @@ if cc_is_clang: vars[var] = sub("-fstack-protector-strong", "", vars[var]) if not clang_has_option("-fno-semantic-interposition"): vars[var] = sub("-fno-semantic-interposition", "", vars[var]) + if not clang_has_option("-ffat-lto-objects"): + vars[var] = sub("-ffat-lto-objects", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ee6f03481215..817a2de264b4 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <linux/err.h> #include <inttypes.h> #include <math.h> #include <string.h> @@ -311,7 +312,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, if (!mask) { mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL); - if (!mask) + if (IS_ERR(mask)) return -ENOMEM; counter->per_pkg_mask = mask; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 31cd59a2b66e..ecd377938eea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dea0fc495185..f72baf636724 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str) return tail - str; } -void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - p->end = c->start; -} - const char * __weak arch__normalize_symbol_name(const char *name) { return name; @@ -217,7 +212,8 @@ again: } } -void symbols__fixup_end(struct rb_root_cached *symbols) +/* Update zero-sized symbols using the address of the next symbol */ +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -231,8 +227,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols) prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start || prev->end != curr->start) - arch__symbols__fixup_end(prev, curr); + /* + * On some architecture kernel text segment start is located at + * some low memory address, while modules are located at high + * memory addresses (or vice versa). The gap between end of + * kernel text segment and beginning of first module's text + * segment is very big. Therefore do not fill this gap and do + * not assign it to the kernel dso map (kallsyms). + * + * In kallsyms, it determines module symbols using '[' character + * like in: + * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi] + */ + if (prev->end == prev->start) { + /* Last kernel/module symbol mapped to end of page */ + if (is_kallsyms && (!strchr(prev->name, '[') != + !strchr(curr->name, '['))) + prev->end = roundup(prev->end + 4096, 4096); + else + prev->end = curr->start; + + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", + __func__, prev->name, prev->end); + } } /* Last entry */ @@ -1467,7 +1484,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, if (kallsyms__delta(kmap, filename, &delta)) return -1; - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, true); symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_SPACE__KERNEL_GUEST) @@ -1659,7 +1676,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) #undef bfd_asymbol_section #endif - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); dso->adjust_symbols = 1; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fbf866d82dcc..0b893dcc8ea6 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); -void symbols__fixup_end(struct rb_root_cached *symbols); +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms); void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); @@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name); #define SYMBOL_A 0 #define SYMBOL_B 1 -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c); int arch__compare_symbol_names(const char *namea, const char *nameb); int arch__compare_symbol_names_n(const char *namea, const char *nameb, unsigned int n); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index a74b517f7497..94aa40f6e348 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg) bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg) report_module(pc, ui); if (!dwfl_frame_pc(state, &pc, &isactivation)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, - int max_stack) + int max_stack, + bool best_effort) { struct unwind_info *ui, ui_buf = { .sample = data, @@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .cb = cb, .arg = arg, .max_stack = max_stack, + .best_effort = best_effort }; Dwarf_Word ip; int err = -EINVAL, i; diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 0cbd2650e280..8c88bc4f2304 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -20,6 +20,7 @@ struct unwind_info { void *arg; int max_stack; int idx; + bool best_effort; struct unwind_entry entries[]; }; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a353349181..41e29fc7648a 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -96,6 +96,7 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; + bool best_effort; }; #define dw_read(ptr, type, end) ({ \ @@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as, ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { - pr_err("unwind: can't read reg %d\n", regnum); + if (!ui->best_effort) + pr_err("unwind: can't read reg %d\n", regnum); return ret; } @@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -1; ret = unw_init_remote(&c, addr_space, ui); - if (ret) + if (ret && !ui->best_effort) display_error(ret); while (!ret && (unw_step(&c) > 0) && i < max_stack) { @@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { struct unwind_info ui = { .sample = data, .thread = thread, .machine = thread->maps->machine, + .best_effort = best_effort }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e89a5479b361..509c287ee762 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { if (thread->maps->unwind_libunwind_ops) - return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, + max_stack, best_effort); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index ab8ad469c8de..b2a03fa5289b 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -23,13 +23,19 @@ struct unwind_libunwind_ops { void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, bool best_effort); }; #ifdef HAVE_DWARF_UNWIND_SUPPORT +/* + * When best_effort is set, don't report errors and fail silently. This could + * be expanded in the future to be more permissive about things other than + * error messages. + */ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, + bool best_effort); /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT #ifndef LIBUNWIND__ARCH_REG_ID @@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, - int max_stack __maybe_unused) + int max_stack __maybe_unused, + bool best_effort __maybe_unused) { return 0; } diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile index 846f785e278d..7221f2f55e8b 100644 --- a/tools/power/x86/intel-speed-select/Makefile +++ b/tools/power/x86/intel-speed-select/Makefile @@ -42,7 +42,7 @@ ISST_IN := $(OUTPUT)intel-speed-select-in.o $(ISST_IN): prepare FORCE $(Q)$(MAKE) $(build)=intel-speed-select $(OUTPUT)intel-speed-select: $(ISST_IN) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ + $(QUIET_LINK)$(CC) $(CFLAGS) $< $(LDFLAGS) -o $@ clean: rm -f $(ALL_PROGRAMS) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 65dbdda3a054..1da76ccde448 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1842,7 +1842,7 @@ static int nfit_test_dimm_init(struct nfit_test *t) return 0; } -static void security_init(struct nfit_test *t) +static void nfit_security_init(struct nfit_test *t) { int i; @@ -1938,7 +1938,7 @@ static int nfit_test0_alloc(struct nfit_test *t) if (nfit_test_dimm_init(t)) return -ENOMEM; smart_init(t); - security_init(t); + nfit_security_init(t); return ars_state_init(&t->pdev.dev, &t->ars_state); } diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 81539f543954..d5c1bcba86fe 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -25,7 +25,8 @@ struct kmem_cache { void (*ctor)(void *); }; -void *kmem_cache_alloc(struct kmem_cache *cachep, int gfp) +void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru, + int gfp) { void *p; diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index 5aa52cc31dc2..c11832657d2b 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -2,6 +2,7 @@ /* Copyright (C) 2021. Huawei Technologies Co., Ltd */ #include <test_progs.h> #include "dummy_st_ops.skel.h" +#include "trace_dummy_st_ops.skel.h" /* Need to keep consistent with definition in include/linux/bpf.h */ struct bpf_dummy_ops_state { @@ -56,6 +57,7 @@ static void test_dummy_init_ptr_arg(void) .ctx_in = args, .ctx_size_in = sizeof(args), ); + struct trace_dummy_st_ops *trace_skel; struct dummy_st_ops *skel; int fd, err; @@ -64,12 +66,33 @@ static void test_dummy_init_ptr_arg(void) return; fd = bpf_program__fd(skel->progs.test_1); + + trace_skel = trace_dummy_st_ops__open(); + if (!ASSERT_OK_PTR(trace_skel, "trace_dummy_st_ops__open")) + goto done; + + err = bpf_program__set_attach_target(trace_skel->progs.fentry_test_1, + fd, "test_1"); + if (!ASSERT_OK(err, "set_attach_target(fentry_test_1)")) + goto done; + + err = trace_dummy_st_ops__load(trace_skel); + if (!ASSERT_OK(err, "load(trace_skel)")) + goto done; + + err = trace_dummy_st_ops__attach(trace_skel); + if (!ASSERT_OK(err, "attach(trace_skel)")) + goto done; + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret"); ASSERT_EQ(attr.retval, exp_retval, "test_ret"); + ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val"); +done: dummy_st_ops__destroy(skel); + trace_dummy_st_ops__destroy(trace_skel); } static void test_dummy_multiple_args(void) diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index b64df94ec476..db388f593d0a 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -367,7 +367,7 @@ static inline int check_array_of_maps(void) VERIFY(check_default(&array_of_maps->map, map)); inner_map = bpf_map_lookup_elem(array_of_maps, &key); - VERIFY(inner_map != 0); + VERIFY(inner_map != NULL); VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; @@ -394,7 +394,7 @@ static inline int check_hash_of_maps(void) VERIFY(check_default(&hash_of_maps->map, map)); inner_map = bpf_map_lookup_elem(hash_of_maps, &key); - VERIFY(inner_map != 0); + VERIFY(inner_map != NULL); VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; diff --git a/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c new file mode 100644 index 000000000000..00a4be9d3074 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +int val = 0; + +SEC("fentry/test_1") +int BPF_PROG(fentry_test_1, __u64 *st_ops_ctx) +{ + __u64 state; + + /* Read the traced st_ops arg1 which is a pointer */ + bpf_probe_read_kernel(&state, sizeof(__u64), (void *)st_ops_ctx); + /* Read state->val */ + bpf_probe_read_kernel(&val, sizeof(__u32), (void *)state); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index b9e991d43155..e7775d3bbe08 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -18,8 +18,9 @@ #include "bpf_rlimit.h" #include "cgroup_helpers.h" -static int start_server(const struct sockaddr *addr, socklen_t len) +static int start_server(const struct sockaddr *addr, socklen_t len, bool dual) { + int mode = !dual; int fd; fd = socket(addr->sa_family, SOCK_STREAM, 0); @@ -28,6 +29,14 @@ static int start_server(const struct sockaddr *addr, socklen_t len) goto out; } + if (addr->sa_family == AF_INET6) { + if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode, + sizeof(mode)) == -1) { + log_err("Failed to set the dual-stack mode"); + goto close_out; + } + } + if (bind(fd, addr, len) == -1) { log_err("Failed to bind server socket"); goto close_out; @@ -47,24 +56,17 @@ out: return fd; } -static int connect_to_server(int server_fd) +static int connect_to_server(const struct sockaddr *addr, socklen_t len) { - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); int fd = -1; - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { - log_err("Failed to get server addr"); - goto out; - } - - fd = socket(addr.ss_family, SOCK_STREAM, 0); + fd = socket(addr->sa_family, SOCK_STREAM, 0); if (fd == -1) { log_err("Failed to create client socket"); goto out; } - if (connect(fd, (const struct sockaddr *)&addr, len) == -1) { + if (connect(fd, (const struct sockaddr *)addr, len) == -1) { log_err("Fail to connect to server"); goto close_out; } @@ -116,7 +118,8 @@ err: return map_fd; } -static int run_test(int server_fd, int results_fd, bool xdp) +static int run_test(int server_fd, int results_fd, bool xdp, + const struct sockaddr *addr, socklen_t len) { int client = -1, srv_client = -1; int ret = 0; @@ -142,7 +145,7 @@ static int run_test(int server_fd, int results_fd, bool xdp) goto err; } - client = connect_to_server(server_fd); + client = connect_to_server(addr, len); if (client == -1) goto err; @@ -199,12 +202,30 @@ out: return ret; } +static bool get_port(int server_fd, in_port_t *port) +{ + struct sockaddr_in addr; + socklen_t len = sizeof(addr); + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + return false; + } + + /* sin_port and sin6_port are located at the same offset. */ + *port = addr.sin_port; + return true; +} + int main(int argc, char **argv) { struct sockaddr_in addr4; struct sockaddr_in6 addr6; + struct sockaddr_in addr4dual; + struct sockaddr_in6 addr6dual; int server = -1; int server_v6 = -1; + int server_dual = -1; int results = -1; int err = 0; bool xdp; @@ -224,25 +245,43 @@ int main(int argc, char **argv) addr4.sin_family = AF_INET; addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); addr4.sin_port = 0; + memcpy(&addr4dual, &addr4, sizeof(addr4dual)); memset(&addr6, 0, sizeof(addr6)); addr6.sin6_family = AF_INET6; addr6.sin6_addr = in6addr_loopback; addr6.sin6_port = 0; - server = start_server((const struct sockaddr *)&addr4, sizeof(addr4)); - if (server == -1) + memset(&addr6dual, 0, sizeof(addr6dual)); + addr6dual.sin6_family = AF_INET6; + addr6dual.sin6_addr = in6addr_any; + addr6dual.sin6_port = 0; + + server = start_server((const struct sockaddr *)&addr4, sizeof(addr4), + false); + if (server == -1 || !get_port(server, &addr4.sin_port)) goto err; server_v6 = start_server((const struct sockaddr *)&addr6, - sizeof(addr6)); - if (server_v6 == -1) + sizeof(addr6), false); + if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port)) + goto err; + + server_dual = start_server((const struct sockaddr *)&addr6dual, + sizeof(addr6dual), true); + if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port)) + goto err; + + if (run_test(server, results, xdp, + (const struct sockaddr *)&addr4, sizeof(addr4))) goto err; - if (run_test(server, results, xdp)) + if (run_test(server_v6, results, xdp, + (const struct sockaddr *)&addr6, sizeof(addr6))) goto err; - if (run_test(server_v6, results, xdp)) + if (run_test(server_dual, results, xdp, + (const struct sockaddr *)&addr4dual, sizeof(addr4dual))) goto err; printf("ok\n"); @@ -252,6 +291,7 @@ err: out: close(server); close(server_v6); + close(server_dual); close(results); return err; } diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh index 429f7ee735cf..fd23c80eba31 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh @@ -159,6 +159,17 @@ flooding_remotes_add() local lsb local i + # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + for i in $(eval echo {1..$num_remotes}); do lsb=$((i + 1)) @@ -195,6 +206,12 @@ flooding_filters_del() done tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact } flooding_check_packets() diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh index fedcb7b35af9..af5ea50ed5c0 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh @@ -172,6 +172,17 @@ flooding_filters_add() local lsb local i + # Prevent unwanted packets from entering the bridge and interfering + # with the test. + tc qdisc add dev br0 clsact + tc filter add dev br0 egress protocol all pref 1 handle 1 \ + matchall skip_hw action drop + tc qdisc add dev $h1 clsact + tc filter add dev $h1 egress protocol all pref 1 handle 1 \ + flower skip_hw dst_mac de:ad:be:ef:13:37 action pass + tc filter add dev $h1 egress protocol all pref 2 handle 2 \ + matchall skip_hw action drop + tc qdisc add dev $rp2 clsact for i in $(eval echo {1..$num_remotes}); do @@ -194,6 +205,12 @@ flooding_filters_del() done tc qdisc del dev $rp2 clsact + + tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall + tc filter del dev $h1 egress protocol all pref 1 handle 1 flower + tc qdisc del dev $h1 clsact + tc filter del dev br0 egress protocol all pref 1 handle 1 matchall + tc qdisc del dev br0 clsact } flooding_check_packets() diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 11779405dc80..25f4d54067c0 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -64,6 +64,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include <setjmp.h> #include "kselftest.h" @@ -183,7 +184,10 @@ struct __test_metadata *_metadata, \ struct __fixture_variant_metadata *variant) \ { \ - test_name(_metadata); \ + _metadata->setup_completed = true; \ + if (setjmp(_metadata->env) == 0) \ + test_name(_metadata); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata _##test_name##_object = \ { .name = #test_name, \ @@ -287,7 +291,9 @@ #define FIXTURE_TEARDOWN(fixture_name) \ void fixture_name##_teardown( \ struct __test_metadata __attribute__((unused)) *_metadata, \ - FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ + const FIXTURE_VARIANT(fixture_name) \ + __attribute__((unused)) *variant) /** * FIXTURE_VARIANT() - Optionally called once per fixture @@ -302,9 +308,9 @@ * ... * }; * - * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F() - * as *variant*. Variants allow the same tests to be run with different - * arguments. + * Defines type of constant parameters provided to FIXTURE_SETUP(), TEST_F() and + * FIXTURE_TEARDOWN as *variant*. Variants allow the same tests to be run with + * different arguments. */ #define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name @@ -356,10 +362,7 @@ * Defines a test that depends on a fixture (e.g., is part of a test case). * Very similar to TEST() except that *self* is the setup instance of fixture's * datatype exposed for use by the implementation. - * - * Warning: use of ASSERT_* here will skip TEARDOWN. */ -/* TODO(wad) register fixtures on dedicated test lists. */ #define TEST_F(fixture_name, test_name) \ __TEST_F_IMPL(fixture_name, test_name, -1, TEST_TIMEOUT_DEFAULT) @@ -381,12 +384,17 @@ /* fixture data is alloced, setup, and torn down per call. */ \ FIXTURE_DATA(fixture_name) self; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ - fixture_name##_setup(_metadata, &self, variant->data); \ - /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ - return; \ - fixture_name##_##test_name(_metadata, &self, variant->data); \ - fixture_name##_teardown(_metadata, &self); \ + if (setjmp(_metadata->env) == 0) { \ + fixture_name##_setup(_metadata, &self, variant->data); \ + /* Let setup failure terminate early. */ \ + if (!_metadata->passed) \ + return; \ + _metadata->setup_completed = true; \ + fixture_name##_##test_name(_metadata, &self, variant->data); \ + } \ + if (_metadata->setup_completed) \ + fixture_name##_teardown(_metadata, &self, variant->data); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata \ _##fixture_name##_##test_name##_object = { \ @@ -683,7 +691,7 @@ */ #define OPTIONAL_HANDLER(_assert) \ for (; _metadata->trigger; _metadata->trigger = \ - __bail(_assert, _metadata->no_print, _metadata->step)) + __bail(_assert, _metadata)) #define __INC_STEP(_metadata) \ /* Keep "step" below 255 (which is used for "SKIP" reporting). */ \ @@ -830,6 +838,9 @@ struct __test_metadata { bool timed_out; /* did this test timeout instead of exiting? */ __u8 step; bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + bool aborted; /* stopped test due to failed ASSERT */ + bool setup_completed; /* did setup finish? */ + jmp_buf env; /* for exiting out of test early */ struct __test_results *results; struct __test_metadata *prev, *next; }; @@ -848,16 +859,26 @@ static inline void __register_test(struct __test_metadata *t) __LIST_APPEND(t->fixture->tests, t); } -static inline int __bail(int for_realz, bool no_print, __u8 step) +static inline int __bail(int for_realz, struct __test_metadata *t) { + /* if this is ASSERT, return immediately. */ if (for_realz) { - if (no_print) - _exit(step); - abort(); + t->aborted = true; + longjmp(t->env, 1); } + /* otherwise, end the for loop and continue. */ return 0; } +static inline void __test_check_assert(struct __test_metadata *t) +{ + if (t->aborted) { + if (t->no_print) + _exit(t->step); + abort(); + } +} + struct __test_metadata *__active_test; static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) { diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 56140068b763..54fc269c1788 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -2,7 +2,8 @@ /aarch64/arch_timer /aarch64/debug-exceptions /aarch64/get-reg-list -/aarch64/psci_cpu_on_test +/aarch64/hypercalls +/aarch64/psci_test /aarch64/vcpu_width_config /aarch64/vgic_init /aarch64/vgic_irq diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index d0d09ca0d495..81470a99ed1c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -107,7 +107,8 @@ TEST_GEN_PROGS_x86_64 += system_counter_offset_test TEST_GEN_PROGS_aarch64 += aarch64/arch_timer TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list -TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test +TEST_GEN_PROGS_aarch64 += aarch64/hypercalls +TEST_GEN_PROGS_aarch64 += aarch64/psci_test TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config TEST_GEN_PROGS_aarch64 += aarch64/vgic_init TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index 0b571f3fe64c..d3a7dbfcbb3d 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -294,6 +294,11 @@ static void print_reg(struct vcpu_config *c, __u64 id) "%s: Unexpected bits set in FW reg id: 0x%llx", config_name(c), id); printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff); break; + case KVM_REG_ARM_FW_FEAT_BMAP: + TEST_ASSERT(id == KVM_REG_ARM_FW_FEAT_BMAP_REG(id & 0xffff), + "%s: Unexpected bits set in the bitmap feature FW reg id: 0x%llx", config_name(c), id); + printf("\tKVM_REG_ARM_FW_FEAT_BMAP_REG(%lld),\n", id & 0xffff); + break; case KVM_REG_ARM64_SVE: if (has_cap(c, KVM_CAP_ARM_SVE)) printf("\t%s,\n", sve_id_to_str(c, id)); @@ -692,6 +697,9 @@ static __u64 base_regs[] = { KVM_REG_ARM_FW_REG(1), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 */ KVM_REG_ARM_FW_REG(2), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 */ KVM_REG_ARM_FW_REG(3), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 */ + KVM_REG_ARM_FW_FEAT_BMAP_REG(0), /* KVM_REG_ARM_STD_BMAP */ + KVM_REG_ARM_FW_FEAT_BMAP_REG(1), /* KVM_REG_ARM_STD_HYP_BMAP */ + KVM_REG_ARM_FW_FEAT_BMAP_REG(2), /* KVM_REG_ARM_VENDOR_HYP_BMAP */ ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ ARM64_SYS_REG(3, 3, 14, 0, 2), diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c new file mode 100644 index 000000000000..41e0210b7a5e --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* hypercalls: Check the ARM64's psuedo-firmware bitmap register interface. + * + * The test validates the basic hypercall functionalities that are exposed + * via the psuedo-firmware bitmap register. This includes the registers' + * read/write behavior before and after the VM has started, and if the + * hypercalls are properly masked or unmasked to the guest when disabled or + * enabled from the KVM userspace, respectively. + */ + +#include <errno.h> +#include <linux/arm-smccc.h> +#include <asm/kvm.h> +#include <kvm_util.h> + +#include "processor.h" + +#define FW_REG_ULIMIT_VAL(max_feat_bit) (GENMASK(max_feat_bit, 0)) + +/* Last valid bits of the bitmapped firmware registers */ +#define KVM_REG_ARM_STD_BMAP_BIT_MAX 0 +#define KVM_REG_ARM_STD_HYP_BMAP_BIT_MAX 0 +#define KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_MAX 1 + +struct kvm_fw_reg_info { + uint64_t reg; /* Register definition */ + uint64_t max_feat_bit; /* Bit that represents the upper limit of the feature-map */ +}; + +#define FW_REG_INFO(r) \ + { \ + .reg = r, \ + .max_feat_bit = r##_BIT_MAX, \ + } + +static const struct kvm_fw_reg_info fw_reg_info[] = { + FW_REG_INFO(KVM_REG_ARM_STD_BMAP), + FW_REG_INFO(KVM_REG_ARM_STD_HYP_BMAP), + FW_REG_INFO(KVM_REG_ARM_VENDOR_HYP_BMAP), +}; + +enum test_stage { + TEST_STAGE_REG_IFACE, + TEST_STAGE_HVC_IFACE_FEAT_DISABLED, + TEST_STAGE_HVC_IFACE_FEAT_ENABLED, + TEST_STAGE_HVC_IFACE_FALSE_INFO, + TEST_STAGE_END, +}; + +static int stage = TEST_STAGE_REG_IFACE; + +struct test_hvc_info { + uint32_t func_id; + uint64_t arg1; +}; + +#define TEST_HVC_INFO(f, a1) \ + { \ + .func_id = f, \ + .arg1 = a1, \ + } + +static const struct test_hvc_info hvc_info[] = { + /* KVM_REG_ARM_STD_BMAP */ + TEST_HVC_INFO(ARM_SMCCC_TRNG_VERSION, 0), + TEST_HVC_INFO(ARM_SMCCC_TRNG_FEATURES, ARM_SMCCC_TRNG_RND64), + TEST_HVC_INFO(ARM_SMCCC_TRNG_GET_UUID, 0), + TEST_HVC_INFO(ARM_SMCCC_TRNG_RND32, 0), + TEST_HVC_INFO(ARM_SMCCC_TRNG_RND64, 0), + + /* KVM_REG_ARM_STD_HYP_BMAP */ + TEST_HVC_INFO(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_HV_PV_TIME_FEATURES), + TEST_HVC_INFO(ARM_SMCCC_HV_PV_TIME_FEATURES, ARM_SMCCC_HV_PV_TIME_ST), + TEST_HVC_INFO(ARM_SMCCC_HV_PV_TIME_ST, 0), + + /* KVM_REG_ARM_VENDOR_HYP_BMAP */ + TEST_HVC_INFO(ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID, + ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID), + TEST_HVC_INFO(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0), + TEST_HVC_INFO(ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID, KVM_PTP_VIRT_COUNTER), +}; + +/* Feed false hypercall info to test the KVM behavior */ +static const struct test_hvc_info false_hvc_info[] = { + /* Feature support check against a different family of hypercalls */ + TEST_HVC_INFO(ARM_SMCCC_TRNG_FEATURES, ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID), + TEST_HVC_INFO(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_TRNG_RND64), + TEST_HVC_INFO(ARM_SMCCC_HV_PV_TIME_FEATURES, ARM_SMCCC_TRNG_RND64), +}; + +static void guest_test_hvc(const struct test_hvc_info *hc_info) +{ + unsigned int i; + struct arm_smccc_res res; + unsigned int hvc_info_arr_sz; + + hvc_info_arr_sz = + hc_info == hvc_info ? ARRAY_SIZE(hvc_info) : ARRAY_SIZE(false_hvc_info); + + for (i = 0; i < hvc_info_arr_sz; i++, hc_info++) { + memset(&res, 0, sizeof(res)); + smccc_hvc(hc_info->func_id, hc_info->arg1, 0, 0, 0, 0, 0, 0, &res); + + switch (stage) { + case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: + case TEST_STAGE_HVC_IFACE_FALSE_INFO: + GUEST_ASSERT_3(res.a0 == SMCCC_RET_NOT_SUPPORTED, + res.a0, hc_info->func_id, hc_info->arg1); + break; + case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: + GUEST_ASSERT_3(res.a0 != SMCCC_RET_NOT_SUPPORTED, + res.a0, hc_info->func_id, hc_info->arg1); + break; + default: + GUEST_ASSERT_1(0, stage); + } + } +} + +static void guest_code(void) +{ + while (stage != TEST_STAGE_END) { + switch (stage) { + case TEST_STAGE_REG_IFACE: + break; + case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: + case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: + guest_test_hvc(hvc_info); + break; + case TEST_STAGE_HVC_IFACE_FALSE_INFO: + guest_test_hvc(false_hvc_info); + break; + default: + GUEST_ASSERT_1(0, stage); + } + + GUEST_SYNC(stage); + } + + GUEST_DONE(); +} + +static int set_fw_reg(struct kvm_vm *vm, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg = { + .id = id, + .addr = (uint64_t)&val, + }; + + return _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); +} + +static void get_fw_reg(struct kvm_vm *vm, uint64_t id, uint64_t *addr) +{ + struct kvm_one_reg reg = { + .id = id, + .addr = (uint64_t)addr, + }; + + vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); +} + +struct st_time { + uint32_t rev; + uint32_t attr; + uint64_t st_time; +}; + +#define STEAL_TIME_SIZE ((sizeof(struct st_time) + 63) & ~63) +#define ST_GPA_BASE (1 << 30) + +static void steal_time_init(struct kvm_vm *vm) +{ + uint64_t st_ipa = (ulong)ST_GPA_BASE; + unsigned int gpages; + struct kvm_device_attr dev = { + .group = KVM_ARM_VCPU_PVTIME_CTRL, + .attr = KVM_ARM_VCPU_PVTIME_IPA, + .addr = (uint64_t)&st_ipa, + }; + + gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0); + + vcpu_ioctl(vm, 0, KVM_SET_DEVICE_ATTR, &dev); +} + +static void test_fw_regs_before_vm_start(struct kvm_vm *vm) +{ + uint64_t val; + unsigned int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(fw_reg_info); i++) { + const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; + + /* First 'read' should be an upper limit of the features supported */ + get_fw_reg(vm, reg_info->reg, &val); + TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), + "Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx\n", + reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val); + + /* Test a 'write' by disabling all the features of the register map */ + ret = set_fw_reg(vm, reg_info->reg, 0); + TEST_ASSERT(ret == 0, + "Failed to clear all the features of reg: 0x%lx; ret: %d\n", + reg_info->reg, errno); + + get_fw_reg(vm, reg_info->reg, &val); + TEST_ASSERT(val == 0, + "Expected all the features to be cleared for reg: 0x%lx\n", reg_info->reg); + + /* + * Test enabling a feature that's not supported. + * Avoid this check if all the bits are occupied. + */ + if (reg_info->max_feat_bit < 63) { + ret = set_fw_reg(vm, reg_info->reg, BIT(reg_info->max_feat_bit + 1)); + TEST_ASSERT(ret != 0 && errno == EINVAL, + "Unexpected behavior or return value (%d) while setting an unsupported feature for reg: 0x%lx\n", + errno, reg_info->reg); + } + } +} + +static void test_fw_regs_after_vm_start(struct kvm_vm *vm) +{ + uint64_t val; + unsigned int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(fw_reg_info); i++) { + const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; + + /* + * Before starting the VM, the test clears all the bits. + * Check if that's still the case. + */ + get_fw_reg(vm, reg_info->reg, &val); + TEST_ASSERT(val == 0, + "Expected all the features to be cleared for reg: 0x%lx\n", + reg_info->reg); + + /* + * Since the VM has run at least once, KVM shouldn't allow modification of + * the registers and should return EBUSY. Set the registers and check for + * the expected errno. + */ + ret = set_fw_reg(vm, reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit)); + TEST_ASSERT(ret != 0 && errno == EBUSY, + "Unexpected behavior or return value (%d) while setting a feature while VM is running for reg: 0x%lx\n", + errno, reg_info->reg); + } +} + +static struct kvm_vm *test_vm_create(void) +{ + struct kvm_vm *vm; + + vm = vm_create_default(0, 0, guest_code); + + ucall_init(vm, NULL); + steal_time_init(vm); + + return vm; +} + +static struct kvm_vm *test_guest_stage(struct kvm_vm *vm) +{ + struct kvm_vm *ret_vm = vm; + + pr_debug("Stage: %d\n", stage); + + switch (stage) { + case TEST_STAGE_REG_IFACE: + test_fw_regs_after_vm_start(vm); + break; + case TEST_STAGE_HVC_IFACE_FEAT_DISABLED: + /* Start a new VM so that all the features are now enabled by default */ + kvm_vm_free(vm); + ret_vm = test_vm_create(); + break; + case TEST_STAGE_HVC_IFACE_FEAT_ENABLED: + case TEST_STAGE_HVC_IFACE_FALSE_INFO: + break; + default: + TEST_FAIL("Unknown test stage: %d\n", stage); + } + + stage++; + sync_global_to_guest(vm, stage); + + return ret_vm; +} + +static void test_run(void) +{ + struct kvm_vm *vm; + struct ucall uc; + bool guest_done = false; + + vm = test_vm_create(); + + test_fw_regs_before_vm_start(vm); + + while (!guest_done) { + vcpu_run(vm, 0); + + switch (get_ucall(vm, 0, &uc)) { + case UCALL_SYNC: + vm = test_guest_stage(vm); + break; + case UCALL_DONE: + guest_done = true; + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld\n\tvalues: 0x%lx, 0x%lx; 0x%lx, stage: %u", + (const char *)uc.args[0], __FILE__, uc.args[1], + uc.args[2], uc.args[3], uc.args[4], stage); + break; + default: + TEST_FAIL("Unexpected guest exit\n"); + } + } + + kvm_vm_free(vm); +} + +int main(void) +{ + setbuf(stdout, NULL); + + test_run(); + return 0; +} diff --git a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c deleted file mode 100644 index 4c5f6814030f..000000000000 --- a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c +++ /dev/null @@ -1,121 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the - * CPU_ON PSCI call matches what the caller requested. - * - * Copyright (c) 2021 Google LLC. - * - * This is a regression test for a race between KVM servicing the PSCI call and - * userspace reading the vCPUs registers. - */ - -#define _GNU_SOURCE - -#include <linux/psci.h> - -#include "kvm_util.h" -#include "processor.h" -#include "test_util.h" - -#define VCPU_ID_SOURCE 0 -#define VCPU_ID_TARGET 1 - -#define CPU_ON_ENTRY_ADDR 0xfeedf00dul -#define CPU_ON_CONTEXT_ID 0xdeadc0deul - -static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, - uint64_t context_id) -{ - register uint64_t x0 asm("x0") = PSCI_0_2_FN64_CPU_ON; - register uint64_t x1 asm("x1") = target_cpu; - register uint64_t x2 asm("x2") = entry_addr; - register uint64_t x3 asm("x3") = context_id; - - asm("hvc #0" - : "=r"(x0) - : "r"(x0), "r"(x1), "r"(x2), "r"(x3) - : "memory"); - - return x0; -} - -static uint64_t psci_affinity_info(uint64_t target_affinity, - uint64_t lowest_affinity_level) -{ - register uint64_t x0 asm("x0") = PSCI_0_2_FN64_AFFINITY_INFO; - register uint64_t x1 asm("x1") = target_affinity; - register uint64_t x2 asm("x2") = lowest_affinity_level; - - asm("hvc #0" - : "=r"(x0) - : "r"(x0), "r"(x1), "r"(x2) - : "memory"); - - return x0; -} - -static void guest_main(uint64_t target_cpu) -{ - GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID)); - uint64_t target_state; - - do { - target_state = psci_affinity_info(target_cpu, 0); - - GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) || - (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF)); - } while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON); - - GUEST_DONE(); -} - -int main(void) -{ - uint64_t target_mpidr, obs_pc, obs_x0; - struct kvm_vcpu_init init; - struct kvm_vm *vm; - struct ucall uc; - - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name); - ucall_init(vm, NULL); - - vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); - init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); - - aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_main); - - /* - * make sure the target is already off when executing the test. - */ - init.features[0] |= (1 << KVM_ARM_VCPU_POWER_OFF); - aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_main); - - get_reg(vm, VCPU_ID_TARGET, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); - vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK); - vcpu_run(vm, VCPU_ID_SOURCE); - - switch (get_ucall(vm, VCPU_ID_SOURCE, &uc)) { - case UCALL_DONE: - break; - case UCALL_ABORT: - TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, - uc.args[1]); - break; - default: - TEST_FAIL("Unhandled ucall: %lu", uc.cmd); - } - - get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.pc), &obs_pc); - get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.regs[0]), &obs_x0); - - TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, - "unexpected target cpu pc: %lx (expected: %lx)", - obs_pc, CPU_ON_ENTRY_ADDR); - TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID, - "unexpected target context id: %lx (expected: %lx)", - obs_x0, CPU_ON_CONTEXT_ID); - - kvm_vm_free(vm); - return 0; -} diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c new file mode 100644 index 000000000000..88541de21c41 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/psci_test.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the + * CPU_ON PSCI call matches what the caller requested. + * + * Copyright (c) 2021 Google LLC. + * + * This is a regression test for a race between KVM servicing the PSCI call and + * userspace reading the vCPUs registers. + */ + +#define _GNU_SOURCE + +#include <linux/psci.h> + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +#define VCPU_ID_SOURCE 0 +#define VCPU_ID_TARGET 1 + +#define CPU_ON_ENTRY_ADDR 0xfeedf00dul +#define CPU_ON_CONTEXT_ID 0xdeadc0deul + +static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr, + uint64_t context_id) +{ + struct arm_smccc_res res; + + smccc_hvc(PSCI_0_2_FN64_CPU_ON, target_cpu, entry_addr, context_id, + 0, 0, 0, 0, &res); + + return res.a0; +} + +static uint64_t psci_affinity_info(uint64_t target_affinity, + uint64_t lowest_affinity_level) +{ + struct arm_smccc_res res; + + smccc_hvc(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity, lowest_affinity_level, + 0, 0, 0, 0, 0, &res); + + return res.a0; +} + +static uint64_t psci_system_suspend(uint64_t entry_addr, uint64_t context_id) +{ + struct arm_smccc_res res; + + smccc_hvc(PSCI_1_0_FN64_SYSTEM_SUSPEND, entry_addr, context_id, + 0, 0, 0, 0, 0, &res); + + return res.a0; +} + +static uint64_t psci_features(uint32_t func_id) +{ + struct arm_smccc_res res; + + smccc_hvc(PSCI_1_0_FN_PSCI_FEATURES, func_id, 0, 0, 0, 0, 0, 0, &res); + + return res.a0; +} + +static void vcpu_power_off(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_mp_state mp_state = { + .mp_state = KVM_MP_STATE_STOPPED, + }; + + vcpu_set_mp_state(vm, vcpuid, &mp_state); +} + +static struct kvm_vm *setup_vm(void *guest_code) +{ + struct kvm_vcpu_init init; + struct kvm_vm *vm; + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name); + ucall_init(vm, NULL); + + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); + + aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_code); + aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_code); + + return vm; +} + +static void enter_guest(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct ucall uc; + + vcpu_run(vm, vcpuid); + if (get_ucall(vm, vcpuid, &uc) == UCALL_ABORT) + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__, + uc.args[1]); +} + +static void assert_vcpu_reset(struct kvm_vm *vm, uint32_t vcpuid) +{ + uint64_t obs_pc, obs_x0; + + get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &obs_pc); + get_reg(vm, vcpuid, ARM64_CORE_REG(regs.regs[0]), &obs_x0); + + TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, + "unexpected target cpu pc: %lx (expected: %lx)", + obs_pc, CPU_ON_ENTRY_ADDR); + TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID, + "unexpected target context id: %lx (expected: %lx)", + obs_x0, CPU_ON_CONTEXT_ID); +} + +static void guest_test_cpu_on(uint64_t target_cpu) +{ + uint64_t target_state; + + GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID)); + + do { + target_state = psci_affinity_info(target_cpu, 0); + + GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) || + (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF)); + } while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON); + + GUEST_DONE(); +} + +static void host_test_cpu_on(void) +{ + uint64_t target_mpidr; + struct kvm_vm *vm; + struct ucall uc; + + vm = setup_vm(guest_test_cpu_on); + + /* + * make sure the target is already off when executing the test. + */ + vcpu_power_off(vm, VCPU_ID_TARGET); + + get_reg(vm, VCPU_ID_TARGET, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); + vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK); + enter_guest(vm, VCPU_ID_SOURCE); + + if (get_ucall(vm, VCPU_ID_SOURCE, &uc) != UCALL_DONE) + TEST_FAIL("Unhandled ucall: %lu", uc.cmd); + + assert_vcpu_reset(vm, VCPU_ID_TARGET); + kvm_vm_free(vm); +} + +static void enable_system_suspend(struct kvm_vm *vm) +{ + struct kvm_enable_cap cap = { + .cap = KVM_CAP_ARM_SYSTEM_SUSPEND, + }; + + vm_enable_cap(vm, &cap); +} + +static void guest_test_system_suspend(void) +{ + uint64_t ret; + + /* assert that SYSTEM_SUSPEND is discoverable */ + GUEST_ASSERT(!psci_features(PSCI_1_0_FN_SYSTEM_SUSPEND)); + GUEST_ASSERT(!psci_features(PSCI_1_0_FN64_SYSTEM_SUSPEND)); + + ret = psci_system_suspend(CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID); + GUEST_SYNC(ret); +} + +static void host_test_system_suspend(void) +{ + struct kvm_run *run; + struct kvm_vm *vm; + + vm = setup_vm(guest_test_system_suspend); + enable_system_suspend(vm); + + vcpu_power_off(vm, VCPU_ID_TARGET); + run = vcpu_state(vm, VCPU_ID_SOURCE); + + enter_guest(vm, VCPU_ID_SOURCE); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_SYSTEM_EVENT, + "Unhandled exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->system_event.type == KVM_SYSTEM_EVENT_SUSPEND, + "Unhandled system event: %u (expected: %u)", + run->system_event.type, KVM_SYSTEM_EVENT_SUSPEND); + + kvm_vm_free(vm); +} + +int main(void) +{ + if (!kvm_check_cap(KVM_CAP_ARM_SYSTEM_SUSPEND)) { + print_skip("KVM_CAP_ARM_SYSTEM_SUSPEND not supported"); + exit(KSFT_SKIP); + } + + host_test_cpu_on(); + host_test_system_suspend(); + return 0; +} diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 8f9f46979a00..59ece9d4e0d1 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -185,4 +185,26 @@ static inline void local_irq_disable(void) asm volatile("msr daifset, #3" : : : "memory"); } +/** + * struct arm_smccc_res - Result from SMC/HVC call + * @a0-a3 result values from registers 0 to 3 + */ +struct arm_smccc_res { + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; +}; + +/** + * smccc_hvc - Invoke a SMCCC function using the hvc conduit + * @function_id: the SMCCC function to be called + * @arg0-arg6: SMCCC function arguments, corresponding to registers x1-x7 + * @res: pointer to write the return values from registers x0-x3 + * + */ +void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, + uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, + uint64_t arg6, struct arm_smccc_res *res); + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 37db341d4cc5..d0d51adec76e 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -60,6 +60,23 @@ /* CPUID.0x8000_0001.EDX */ #define CPUID_GBPAGES (1ul << 26) +/* Page table bitfield declarations */ +#define PTE_PRESENT_MASK BIT_ULL(0) +#define PTE_WRITABLE_MASK BIT_ULL(1) +#define PTE_USER_MASK BIT_ULL(2) +#define PTE_ACCESSED_MASK BIT_ULL(5) +#define PTE_DIRTY_MASK BIT_ULL(6) +#define PTE_LARGE_MASK BIT_ULL(7) +#define PTE_GLOBAL_MASK BIT_ULL(8) +#define PTE_NX_MASK BIT_ULL(63) + +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1ULL << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) + +#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12) +#define PTE_GET_PFN(pte) (((pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT) + /* General Registers in 64-Bit Mode */ struct gpr64_regs { u64 rax; diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index ba1fdc3dcf4a..2c4a7563a4f8 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -278,7 +278,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) else guest_test_phys_mem = p->phys_offset; #ifdef __s390x__ - alignment = max(0x100000, alignment); + alignment = max(0x100000UL, alignment); #endif guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 9343d82519b4..6a041289fa80 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -500,3 +500,28 @@ void __attribute__((constructor)) init_guest_modes(void) { guest_modes_append_default(); } + +void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, + uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, + uint64_t arg6, struct arm_smccc_res *res) +{ + asm volatile("mov w0, %w[function_id]\n" + "mov x1, %[arg0]\n" + "mov x2, %[arg1]\n" + "mov x3, %[arg2]\n" + "mov x4, %[arg3]\n" + "mov x5, %[arg4]\n" + "mov x6, %[arg5]\n" + "mov x7, %[arg6]\n" + "hvc #0\n" + "mov %[res0], x0\n" + "mov %[res1], x1\n" + "mov %[res2], x2\n" + "mov %[res3], x3\n" + : [res0] "=r"(res->a0), [res1] "=r"(res->a1), + [res2] "=r"(res->a2), [res3] "=r"(res->a3) + : [function_id] "r"(function_id), [arg0] "r"(arg0), + [arg1] "r"(arg1), [arg2] "r"(arg2), [arg3] "r"(arg3), + [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6) + : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7"); +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 9f000dfb5594..33ea5e9955d9 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,38 +19,6 @@ vm_vaddr_t exception_handlers; -/* Virtual translation table structure declarations */ -struct pageUpperEntry { - uint64_t present:1; - uint64_t writable:1; - uint64_t user:1; - uint64_t write_through:1; - uint64_t cache_disable:1; - uint64_t accessed:1; - uint64_t ignored_06:1; - uint64_t page_size:1; - uint64_t ignored_11_08:4; - uint64_t pfn:40; - uint64_t ignored_62_52:11; - uint64_t execute_disable:1; -}; - -struct pageTableEntry { - uint64_t present:1; - uint64_t writable:1; - uint64_t user:1; - uint64_t write_through:1; - uint64_t cache_disable:1; - uint64_t accessed:1; - uint64_t dirty:1; - uint64_t reserved_07:1; - uint64_t global:1; - uint64_t ignored_11_09:3; - uint64_t pfn:40; - uint64_t ignored_62_52:11; - uint64_t execute_disable:1; -}; - void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -195,23 +163,21 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr, return &page_table[index]; } -static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm, - uint64_t pt_pfn, - uint64_t vaddr, - uint64_t paddr, - int level, - enum x86_page_size page_size) +static uint64_t *virt_create_upper_pte(struct kvm_vm *vm, + uint64_t pt_pfn, + uint64_t vaddr, + uint64_t paddr, + int level, + enum x86_page_size page_size) { - struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level); - - if (!pte->present) { - pte->writable = true; - pte->present = true; - pte->page_size = (level == page_size); - if (pte->page_size) - pte->pfn = paddr >> vm->page_shift; + uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level); + + if (!(*pte & PTE_PRESENT_MASK)) { + *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK; + if (level == page_size) + *pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK); else - pte->pfn = vm_alloc_page_table(vm) >> vm->page_shift; + *pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK; } else { /* * Entry already present. Assert that the caller doesn't want @@ -221,7 +187,7 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm, TEST_ASSERT(level != page_size, "Cannot create hugepage at level: %u, vaddr: 0x%lx\n", page_size, vaddr); - TEST_ASSERT(!pte->page_size, + TEST_ASSERT(!(*pte & PTE_LARGE_MASK), "Cannot create page table at level: %u, vaddr: 0x%lx\n", level, vaddr); } @@ -232,8 +198,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, enum x86_page_size page_size) { const uint64_t pg_size = 1ull << ((page_size * 9) + 12); - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -257,24 +223,22 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, */ pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift, vaddr, paddr, 3, page_size); - if (pml4e->page_size) + if (*pml4e & PTE_LARGE_MASK) return; - pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size); - if (pdpe->page_size) + pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size); + if (*pdpe & PTE_LARGE_MASK) return; - pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size); - if (pde->page_size) + pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size); + if (*pde & PTE_LARGE_MASK) return; /* Fill in page table entry. */ - pte = virt_get_pte(vm, pde->pfn, vaddr, 0); - TEST_ASSERT(!pte->present, + pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0); + TEST_ASSERT(!(*pte & PTE_PRESENT_MASK), "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr); - pte->pfn = paddr >> vm->page_shift; - pte->writable = true; - pte->present = 1; + *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK); } void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) @@ -282,22 +246,22 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) __virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K); } -static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, +static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) { uint16_t index[4]; - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; struct kvm_cpuid_entry2 *entry; struct kvm_sregs sregs; int max_phy_addr; - /* Set the bottom 52 bits. */ - uint64_t rsvd_mask = 0x000fffffffffffff; + uint64_t rsvd_mask = 0; entry = kvm_get_supported_cpuid_index(0x80000008, 0); max_phy_addr = entry->eax & 0x000000ff; - /* Clear the bottom bits of the reserved mask. */ - rsvd_mask = (rsvd_mask >> max_phy_addr) << max_phy_addr; + /* Set the high bits in the reserved mask. */ + if (max_phy_addr < 52) + rsvd_mask = GENMASK_ULL(51, max_phy_addr); /* * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries @@ -307,7 +271,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc */ vcpu_sregs_get(vm, vcpuid, &sregs); if ((sregs.efer & EFER_NX) == 0) { - rsvd_mask |= (1ull << 63); + rsvd_mask |= PTE_NX_MASK; } TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " @@ -329,30 +293,29 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc index[3] = (vaddr >> 39) & 0x1ffu; pml4e = addr_gpa2hva(vm, vm->pgd); - TEST_ASSERT(pml4e[index[3]].present, + TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK, "Expected pml4e to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT((*(uint64_t*)(&pml4e[index[3]]) & - (rsvd_mask | (1ull << 7))) == 0, + TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0, "Unexpected reserved bits set."); - pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size); - TEST_ASSERT(pdpe[index[2]].present, + pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); + TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK, "Expected pdpe to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(pdpe[index[2]].page_size == 0, + TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK), "Expected pdpe to map a pde not a 1-GByte page."); - TEST_ASSERT((*(uint64_t*)(&pdpe[index[2]]) & rsvd_mask) == 0, + TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0, "Unexpected reserved bits set."); - pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size); - TEST_ASSERT(pde[index[1]].present, + pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); + TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK, "Expected pde to be present for gva: 0x%08lx", vaddr); - TEST_ASSERT(pde[index[1]].page_size == 0, + TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK), "Expected pde to map a pte not a 2-MByte page."); - TEST_ASSERT((*(uint64_t*)(&pde[index[1]]) & rsvd_mask) == 0, + TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0, "Unexpected reserved bits set."); - pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size); - TEST_ASSERT(pte[index[0]].present, + pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); + TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK, "Expected pte to be present for gva: 0x%08lx", vaddr); return &pte[index[0]]; @@ -360,7 +323,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) { - struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); + uint64_t *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); return *(uint64_t *)pte; } @@ -368,18 +331,17 @@ uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr) void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr, uint64_t pte) { - struct pageTableEntry *new_pte = _vm_get_page_table_entry(vm, vcpuid, - vaddr); + uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpuid, vaddr); *(uint64_t *)new_pte = pte; } void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { - struct pageUpperEntry *pml4e, *pml4e_start; - struct pageUpperEntry *pdpe, *pdpe_start; - struct pageUpperEntry *pde, *pde_start; - struct pageTableEntry *pte, *pte_start; + uint64_t *pml4e, *pml4e_start; + uint64_t *pdpe, *pdpe_start; + uint64_t *pde, *pde_start; + uint64_t *pte, *pte_start; if (!vm->pgd_created) return; @@ -389,58 +351,58 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) fprintf(stream, "%*s index hvaddr gpaddr " "addr w exec dirty\n", indent, ""); - pml4e_start = (struct pageUpperEntry *) addr_gpa2hva(vm, vm->pgd); + pml4e_start = (uint64_t *) addr_gpa2hva(vm, vm->pgd); for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) { pml4e = &pml4e_start[n1]; - if (!pml4e->present) + if (!(*pml4e & PTE_PRESENT_MASK)) continue; - fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u " + fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10llx %u " " %u\n", indent, "", pml4e - pml4e_start, pml4e, - addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->pfn, - pml4e->writable, pml4e->execute_disable); + addr_hva2gpa(vm, pml4e), PTE_GET_PFN(*pml4e), + !!(*pml4e & PTE_WRITABLE_MASK), !!(*pml4e & PTE_NX_MASK)); - pdpe_start = addr_gpa2hva(vm, pml4e->pfn * vm->page_size); + pdpe_start = addr_gpa2hva(vm, *pml4e & PHYSICAL_PAGE_MASK); for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) { pdpe = &pdpe_start[n2]; - if (!pdpe->present) + if (!(*pdpe & PTE_PRESENT_MASK)) continue; - fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10lx " + fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10llx " "%u %u\n", indent, "", pdpe - pdpe_start, pdpe, addr_hva2gpa(vm, pdpe), - (uint64_t) pdpe->pfn, pdpe->writable, - pdpe->execute_disable); + PTE_GET_PFN(*pdpe), !!(*pdpe & PTE_WRITABLE_MASK), + !!(*pdpe & PTE_NX_MASK)); - pde_start = addr_gpa2hva(vm, pdpe->pfn * vm->page_size); + pde_start = addr_gpa2hva(vm, *pdpe & PHYSICAL_PAGE_MASK); for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) { pde = &pde_start[n3]; - if (!pde->present) + if (!(*pde & PTE_PRESENT_MASK)) continue; fprintf(stream, "%*spde 0x%-3zx %p " - "0x%-12lx 0x%-10lx %u %u\n", + "0x%-12lx 0x%-10llx %u %u\n", indent, "", pde - pde_start, pde, addr_hva2gpa(vm, pde), - (uint64_t) pde->pfn, pde->writable, - pde->execute_disable); + PTE_GET_PFN(*pde), !!(*pde & PTE_WRITABLE_MASK), + !!(*pde & PTE_NX_MASK)); - pte_start = addr_gpa2hva(vm, pde->pfn * vm->page_size); + pte_start = addr_gpa2hva(vm, *pde & PHYSICAL_PAGE_MASK); for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) { pte = &pte_start[n4]; - if (!pte->present) + if (!(*pte & PTE_PRESENT_MASK)) continue; fprintf(stream, "%*spte 0x%-3zx %p " - "0x%-12lx 0x%-10lx %u %u " + "0x%-12lx 0x%-10llx %u %u " " %u 0x%-10lx\n", indent, "", pte - pte_start, pte, addr_hva2gpa(vm, pte), - (uint64_t) pte->pfn, - pte->writable, - pte->execute_disable, - pte->dirty, + PTE_GET_PFN(*pte), + !!(*pte & PTE_WRITABLE_MASK), + !!(*pte & PTE_NX_MASK), + !!(*pte & PTE_DIRTY_MASK), ((uint64_t) n1 << 27) | ((uint64_t) n2 << 18) | ((uint64_t) n3 << 9) @@ -558,8 +520,8 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) { uint16_t index[4]; - struct pageUpperEntry *pml4e, *pdpe, *pde; - struct pageTableEntry *pte; + uint64_t *pml4e, *pdpe, *pde; + uint64_t *pte; TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use " "unknown or unsupported guest mode, mode: 0x%x", vm->mode); @@ -572,22 +534,22 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) if (!vm->pgd_created) goto unmapped_gva; pml4e = addr_gpa2hva(vm, vm->pgd); - if (!pml4e[index[3]].present) + if (!(pml4e[index[3]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size); - if (!pdpe[index[2]].present) + pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size); + if (!(pdpe[index[2]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size); - if (!pde[index[1]].present) + pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size); + if (!(pde[index[1]] & PTE_PRESENT_MASK)) goto unmapped_gva; - pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size); - if (!pte[index[0]].present) + pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size); + if (!(pte[index[0]] & PTE_PRESENT_MASK)) goto unmapped_gva; - return (pte[index[0]].pfn * vm->page_size) + (gva & 0xfffu); + return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK); unmapped_gva: TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 62f2eb9ee3d5..8c4e811bd586 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -118,17 +118,10 @@ struct st_time { static int64_t smccc(uint32_t func, uint64_t arg) { - unsigned long ret; + struct arm_smccc_res res; - asm volatile( - "mov w0, %w1\n" - "mov x1, %2\n" - "hvc #0\n" - "mov %0, x0\n" - : "=r" (ret) : "r" (func), "r" (arg) : - "x0", "x1", "x2", "x3"); - - return ret; + smccc_hvc(func, arg, 0, 0, 0, 0, 0, 0, &res); + return res.a0; } static void check_status(struct st_time *st) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 52a3ef6629e8..76f65c22796f 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -29,7 +29,6 @@ #define X86_FEATURE_XSAVE (1 << 26) #define X86_FEATURE_OSXSAVE (1 << 27) -#define PAGE_SIZE (1 << 12) #define NUM_TILES 8 #define TILE_SIZE 1024 #define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c index f070ff0224fa..aeb3850f81bd 100644 --- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c +++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c @@ -12,7 +12,6 @@ #include "vmx.h" #define VCPU_ID 1 -#define PAGE_SIZE 4096 #define MAXPHYADDR 36 #define MEM_REGION_GVA 0x0000123456789000 diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index a626d40fdb48..b4e0c860769e 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -21,8 +21,6 @@ #define VCPU_ID 1 -#define PAGE_SIZE 4096 - #define SMRAM_SIZE 65536 #define SMRAM_MEMSLOT ((1 << 16) | 1) #define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index e683d0ac3e45..19b35c607dc6 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -32,7 +32,6 @@ #define MSR_IA32_TSC_ADJUST 0x3b #endif -#define PAGE_SIZE 4096 #define VCPU_ID 5 #define TSC_ADJUST_VALUE (1ll << 32) diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 5e6f40633ea6..7a51bb648fbb 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -23,7 +23,6 @@ #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 -#define PAGE_SIZE 4096 #define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE)) #define DUMMY_REGION_SLOT 11 diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index adc94452b57c..b30fe9de1d4f 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -15,7 +15,6 @@ #define HCALL_REGION_GPA 0xc0000000ULL #define HCALL_REGION_SLOT 10 -#define PAGE_SIZE 4096 static struct kvm_vm *vm; diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c index b019e0b8221c..84fda3b49073 100644 --- a/tools/testing/selftests/mqueue/mq_perf_tests.c +++ b/tools/testing/selftests/mqueue/mq_perf_tests.c @@ -180,6 +180,9 @@ void shutdown(int exit_val, char *err_cause, int line_no) if (in_shutdown++) return; + /* Free the cpu_set allocated using CPU_ALLOC in main function */ + CPU_FREE(cpu_set); + for (i = 0; i < num_cpus_to_pin; i++) if (cpu_threads[i]) { pthread_kill(cpu_threads[i], SIGUSR1); @@ -551,6 +554,12 @@ int main(int argc, char *argv[]) perror("sysconf(_SC_NPROCESSORS_ONLN)"); exit(1); } + + if (getuid() != 0) + ksft_exit_skip("Not running as root, but almost all tests " + "require root in order to modify\nsystem settings. " + "Exiting.\n"); + cpus_online = min(MAX_CPUS, sysconf(_SC_NPROCESSORS_ONLN)); cpu_set = CPU_ALLOC(cpus_online); if (cpu_set == NULL) { @@ -589,7 +598,7 @@ int main(int argc, char *argv[]) cpu_set)) { fprintf(stderr, "Any given CPU may " "only be given once.\n"); - exit(1); + goto err_code; } else CPU_SET_S(cpus_to_pin[cpu], cpu_set_size, cpu_set); @@ -607,7 +616,7 @@ int main(int argc, char *argv[]) queue_path = malloc(strlen(option) + 2); if (!queue_path) { perror("malloc()"); - exit(1); + goto err_code; } queue_path[0] = '/'; queue_path[1] = 0; @@ -622,17 +631,12 @@ int main(int argc, char *argv[]) fprintf(stderr, "Must pass at least one CPU to continuous " "mode.\n"); poptPrintUsage(popt_context, stderr, 0); - exit(1); + goto err_code; } else if (!continuous_mode) { num_cpus_to_pin = 1; cpus_to_pin[0] = cpus_online - 1; } - if (getuid() != 0) - ksft_exit_skip("Not running as root, but almost all tests " - "require root in order to modify\nsystem settings. " - "Exiting.\n"); - max_msgs = fopen(MAX_MSGS, "r+"); max_msgsize = fopen(MAX_MSGSIZE, "r+"); if (!max_msgs) @@ -740,4 +744,9 @@ int main(int argc, char *argv[]) sleep(1); } shutdown(0, "", 0); + +err_code: + CPU_FREE(cpu_set); + exit(1); + } diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index d444ee6aa3cb..b3bf5319bb0e 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1208,6 +1208,20 @@ ipv4_fcnal() set +e check_nexthop "dev veth1" "" log_test $? 0 "Nexthops removed on admin down" + + # nexthop route delete warning: route add with nhid and delete + # using device + run_cmd "$IP li set dev veth1 up" + run_cmd "$IP nexthop add id 12 via 172.16.1.3 dev veth1" + out1=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l` + run_cmd "$IP route add 172.16.101.1/32 nhid 12" + run_cmd "$IP route delete 172.16.101.1/32 dev veth1" + out2=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l` + [ $out1 -eq $out2 ] + rc=$? + log_test $rc 0 "Delete nexthop route warning" + run_cmd "$IP route delete 172.16.101.1/32 nhid 12" + run_cmd "$IP nexthop del id 12" } ipv4_grp_fcnal() diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile index dcaefa224ca0..edafaca1aeb3 100644 --- a/tools/testing/selftests/pid_namespace/Makefile +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g -I../../../../usr/include/ -TEST_GEN_PROGS := regression_enomem +TEST_GEN_PROGS = regression_enomem -include ../lib.mk +LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h -$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h +include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 17999e082aa7..070c1c876df1 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -95,7 +95,6 @@ TEST(wait_states) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 18a3bde8bc96..28604c9f805c 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -46,6 +46,8 @@ #include <sys/time.h> #include <sys/resource.h> +#include "../kselftest.h" + static inline long sys_execveat(int dirfd, const char *pathname, char **argv, char **envp, int flags) { return syscall(SYS_execveat, dirfd, pathname, argv, envp, flags); @@ -368,7 +370,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } @@ -417,7 +419,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } } diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index c4aea794725a..e691a3cf1491 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -20,6 +20,7 @@ #include <limits.h> #include "vdso_config.h" +#include "../kselftest.h" static const char **name; @@ -306,10 +307,8 @@ static void test_clock_gettime(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime(-1, "invalid"); @@ -370,10 +369,8 @@ static void test_clock_gettime64(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime64(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime64(-1, "invalid"); diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c index 7c0b0617b9f8..db0270127aeb 100644 --- a/tools/testing/selftests/vm/mremap_test.c +++ b/tools/testing/selftests/vm/mremap_test.c @@ -6,9 +6,11 @@ #include <errno.h> #include <stdlib.h> +#include <stdio.h> #include <string.h> #include <sys/mman.h> #include <time.h> +#include <stdbool.h> #include "../kselftest.h" @@ -64,6 +66,59 @@ enum { } /* + * Returns false if the requested remap region overlaps with an + * existing mapping (e.g text, stack) else returns true. + */ +static bool is_remap_region_valid(void *addr, unsigned long long size) +{ + void *remap_addr = NULL; + bool ret = true; + + /* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */ + remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + + if (remap_addr == MAP_FAILED) { + if (errno == EEXIST) + ret = false; + } else { + munmap(remap_addr, size); + } + + return ret; +} + +/* Returns mmap_min_addr sysctl tunable from procfs */ +static unsigned long long get_mmap_min_addr(void) +{ + FILE *fp; + int n_matched; + static unsigned long long addr; + + if (addr) + return addr; + + fp = fopen("/proc/sys/vm/mmap_min_addr", "r"); + if (fp == NULL) { + ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + exit(KSFT_SKIP); + } + + n_matched = fscanf(fp, "%llu", &addr); + if (n_matched != 1) { + ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n", + strerror(errno)); + fclose(fp); + exit(KSFT_SKIP); + } + + fclose(fp); + return addr; +} + +/* * Returns the start address of the mapping on success, else returns * NULL on failure. */ @@ -71,11 +126,18 @@ static void *get_source_mapping(struct config c) { unsigned long long addr = 0ULL; void *src_addr = NULL; + unsigned long long mmap_min_addr; + + mmap_min_addr = get_mmap_min_addr(); + retry: addr += c.src_alignment; + if (addr < mmap_min_addr) + goto retry; + src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE, - MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, - -1, 0); + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); if (src_addr == MAP_FAILED) { if (errno == EPERM || errno == EEXIST) goto retry; @@ -90,8 +152,10 @@ retry: * alignment in the tests. */ if (((unsigned long long) src_addr & (c.src_alignment - 1)) || - !((unsigned long long) src_addr & c.src_alignment)) + !((unsigned long long) src_addr & c.src_alignment)) { + munmap(src_addr, c.region_size); goto retry; + } if (!src_addr) goto error; @@ -140,9 +204,20 @@ static long long remap_region(struct config c, unsigned int threshold_mb, if (!((unsigned long long) addr & c.dest_alignment)) addr = (void *) ((unsigned long long) addr | c.dest_alignment); + /* Don't destroy existing mappings unless expected to overlap */ + while (!is_remap_region_valid(addr, c.region_size) && !c.overlapping) { + /* Check for unsigned overflow */ + if (addr + c.dest_alignment < addr) { + ksft_print_msg("Couldn't find a valid region to remap to\n"); + ret = -1; + goto out; + } + addr += c.dest_alignment; + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr = mremap(src_addr, c.region_size, c.region_size, - MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); + MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); clock_gettime(CLOCK_MONOTONIC, &t_end); if (dest_addr == MAP_FAILED) { @@ -193,7 +268,7 @@ static void run_mremap_test_case(struct test test_case, int *failures, if (remap_time < 0) { if (test_case.expect_failure) - ksft_test_result_pass("%s\n\tExpected mremap failure\n", + ksft_test_result_xfail("%s\n\tExpected mremap failure\n", test_case.name); else { ksft_test_result_fail("%s\n", test_case.name); diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 3b265f140c25..352ba00cf26b 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -291,11 +291,16 @@ echo "-------------------" echo "running mremap_test" echo "-------------------" ./mremap_test -if [ $? -ne 0 ]; then +ret_val=$? + +if [ $ret_val -eq 0 ]; then + echo "[PASS]" +elif [ $ret_val -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip +else echo "[FAIL]" exitcode=1 -else - echo "[PASS]" fi echo "-----------------" diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config index a85025d7206e..a9b4fe795048 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/i686.config +++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config @@ -1,3 +1,4 @@ +CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config index 00a1ef4869d5..45dd53a0d760 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config @@ -1,3 +1,4 @@ +CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 53df7d3893d3..0388c4d60af0 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -92,6 +92,10 @@ warn_32bit_failure: echo "If you are using a Fedora-like distribution, try:"; \ echo ""; \ echo " yum install glibc-devel.*i686"; \ + echo ""; \ + echo "If you are using a SUSE-like distribution, try:"; \ + echo ""; \ + echo " zypper install gcc-32bit glibc-devel-static-32bit"; \ exit 0; endif diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 222ecc81d7df..f4c2a6eb1666 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +// SPDX-License-Identifier: GPL-2.0-only /* * KVM dirty ring implementation * diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 655365b2cbe8..342043b30125 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -164,6 +164,10 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, { } +__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ +} + bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) { /* @@ -357,6 +361,12 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); #endif +static void kvm_flush_shadow_all(struct kvm *kvm) +{ + kvm_arch_flush_shadow_all(kvm); + kvm_arch_guest_memory_reclaimed(kvm); +} + #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, gfp_t gfp_flags) @@ -485,12 +495,15 @@ typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start, unsigned long end); +typedef void (*on_unlock_fn_t)(struct kvm *kvm); + struct kvm_hva_range { unsigned long start; unsigned long end; pte_t pte; hva_handler_t handler; on_lock_fn_t on_lock; + on_unlock_fn_t on_unlock; bool flush_on_ret; bool may_block; }; @@ -578,8 +591,11 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); - if (locked) + if (locked) { KVM_MMU_UNLOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_unlock)) + range->on_unlock(kvm); + } srcu_read_unlock(&kvm->srcu, idx); @@ -600,6 +616,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, .pte = pte, .handler = handler, .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = true, .may_block = false, }; @@ -619,6 +636,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn .pte = __pte(0), .handler = handler, .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = false, }; @@ -662,7 +680,7 @@ void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start, kvm->mmu_notifier_range_end = end; } else { /* - * Fully tracking multiple concurrent ranges has dimishing + * Fully tracking multiple concurrent ranges has diminishing * returns. Keep things simple and just find the minimal range * which includes the current and new ranges. As there won't be * enough information to subtract a range after its invalidate @@ -687,6 +705,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, .pte = __pte(0), .handler = kvm_unmap_gfn_range, .on_lock = kvm_inc_notifier_count, + .on_unlock = kvm_arch_guest_memory_reclaimed, .flush_on_ret = true, .may_block = mmu_notifier_range_blockable(range), }; @@ -741,6 +760,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, .pte = __pte(0), .handler = (void *)kvm_null_fn, .on_lock = kvm_dec_notifier_count, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; @@ -813,7 +833,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, int idx; idx = srcu_read_lock(&kvm->srcu); - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } @@ -955,12 +975,6 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd) int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; - /* - * Force subsequent debugfs file creations to fail if the VM directory - * is not created. - */ - kvm->debugfs_dentry = ERR_PTR(-ENOENT); - if (!debugfs_initialized()) return 0; @@ -1082,6 +1096,12 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); + /* + * Force subsequent debugfs file creations to fail if the VM directory + * is not created (by kvm_create_vm_debugfs()). + */ + kvm->debugfs_dentry = ERR_PTR(-ENOENT); + if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; if (init_srcu_struct(&kvm->irq_srcu)) @@ -1226,7 +1246,7 @@ static void kvm_destroy_vm(struct kvm *kvm) WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); kvm->mn_active_invalidate_count = 0; #else - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); @@ -1653,6 +1673,7 @@ static void kvm_invalidate_memslot(struct kvm *kvm, * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, old); + kvm_arch_guest_memory_reclaimed(kvm); /* Was released by kvm_swap_active_memslots, reacquire. */ mutex_lock(&kvm->slots_arch_lock); @@ -1800,7 +1821,7 @@ static int kvm_set_memslot(struct kvm *kvm, /* * No need to refresh new->arch, changes after dropping slots_arch_lock - * will directly hit the final, active memsot. Architectures are + * will directly hit the final, active memslot. Architectures are * responsible for knowing that new->arch may be stale. */ kvm_commit_memory_region(kvm, old, new, change); diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index 34ca40823260..41da467d99c9 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_MM_H__ #define __KVM_MM_H__ 1 |