diff options
| author | Paolo Bonzini <pbonzini@redhat.com> | 2024-10-06 09:59:22 +0200 |
|---|---|---|
| committer | Paolo Bonzini <pbonzini@redhat.com> | 2024-10-06 09:59:22 +0200 |
| commit | c8d430db8eec7d4fd13a6bea27b7086a54eda6da (patch) | |
| tree | 3c9b35bc9372232183e745cc2a03995a8d053ff6 /arch/x86 | |
| parent | x86/reboot: emergency callbacks are now registered by common KVM code (diff) | |
| parent | KVM: arm64: Fix kvm_has_feat*() handling of negative features (diff) | |
| download | linux-c8d430db8eec7d4fd13a6bea27b7086a54eda6da.tar.xz linux-c8d430db8eec7d4fd13a6bea27b7086a54eda6da.zip | |
Merge tag 'kvmarm-fixes-6.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 fixes for 6.12, take #1
- Fix pKVM error path on init, making sure we do not change critical
system registers as we're about to fail
- Make sure that the host's vector length is at capped by a value
common to all CPUs
- Fix kvm_has_feat*() handling of "negative" features, as the current
code is pretty broken
- Promote Joey to the status of official reviewer, while James steps
down -- hopefully only temporarly
Diffstat (limited to 'arch/x86')
150 files changed, 3034 insertions, 3111 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 007bab9f2a0e..2852fcd82cbd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -28,6 +28,7 @@ config X86_64 select ARCH_HAS_GIGANTIC_PAGE select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select ARCH_SUPPORTS_PER_VMA_LOCK + select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE select HAVE_ARCH_SOFT_DIRTY select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE @@ -79,6 +80,7 @@ config X86 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE select ARCH_HAS_DEVMEM_IS_ALLOWED + select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN select ARCH_HAS_EARLY_DEBUG if KGDB select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER @@ -107,6 +109,7 @@ config X86 select ARCH_HAS_DEBUG_WX select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_NMI_SAFE_CMPXCHG + select ARCH_HAVE_EXTRA_ELF_NOTES select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT @@ -122,6 +125,7 @@ config X86 select ARCH_USES_CFI_TRAPS if X86_64 && CFI_CLANG select ARCH_SUPPORTS_LTO_CLANG select ARCH_SUPPORTS_LTO_CLANG_THIN + select ARCH_SUPPORTS_RT select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if X86_CMPXCHG64 select ARCH_USE_MEMTEST @@ -296,6 +300,7 @@ config X86 select NEED_PER_CPU_EMBED_FIRST_CHUNK select NEED_PER_CPU_PAGE_FIRST_CHUNK select NEED_SG_DMA_LENGTH + select NUMA_MEMBLKS if NUMA select PCI_DOMAINS if PCI select PCI_LOCKLESS_CONFIG if PCI select PERF_EVENTS @@ -943,7 +948,6 @@ config DMI config GART_IOMMU bool "Old AMD GART IOMMU support" - select DMA_OPS select IOMMU_HELPER select SWIOTLB depends on X86_64 && PCI && AMD_NB @@ -1599,14 +1603,6 @@ config X86_64_ACPI_NUMA help Enable ACPI SRAT based node topology detection. -config NUMA_EMU - bool "NUMA emulation" - depends on NUMA - help - Enable NUMA emulation. A flat machine will be split - into virtual nodes when booted with "numa=fake=N", where N is the - number of nodes. This is only useful for debugging. - config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP range 1 10 @@ -1806,6 +1802,7 @@ config X86_PAT def_bool y prompt "x86 PAT support" if EXPERT depends on MTRR + select ARCH_USES_PG_ARCH_2 help Use PAT attributes to setup page level cache control. @@ -1817,10 +1814,6 @@ config X86_PAT If unsure, say Y. -config ARCH_USES_PG_UNCACHED - def_bool y - depends on X86_PAT - config X86_UMIP def_bool y prompt "User Mode Instruction Prevention" if EXPERT @@ -1889,6 +1882,10 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS If unsure, say y. +config ARCH_PKEY_BITS + int + default 4 + choice prompt "TSX enable mode" depends on CPU_SUP_INTEL @@ -2610,24 +2607,15 @@ config MITIGATION_SLS against straight line speculation. The kernel image might be slightly larger. -config MITIGATION_GDS_FORCE - bool "Force GDS Mitigation" +config MITIGATION_GDS + bool "Mitigate Gather Data Sampling" depends on CPU_SUP_INTEL - default n + default y help - Gather Data Sampling (GDS) is a hardware vulnerability which allows - unprivileged speculative access to data which was previously stored in - vector registers. - - This option is equivalent to setting gather_data_sampling=force on the - command line. The microcode mitigation is used if present, otherwise - AVX is disabled as a mitigation. On affected systems that are missing - the microcode any userspace code that unconditionally uses AVX will - break with this option set. - - Setting this option on systems not vulnerable to GDS has no effect. - - If in doubt, say N. + Enable mitigation for Gather Data Sampling (GDS). GDS is a hardware + vulnerability which allows unprivileged speculative access to data + which was previously stored in vector registers. The attacker uses gather + instructions to infer the stale vector register data. config MITIGATION_RFDS bool "RFDS Mitigation" @@ -2650,6 +2638,107 @@ config MITIGATION_SPECTRE_BHI indirect branches. See <file:Documentation/admin-guide/hw-vuln/spectre.rst> +config MITIGATION_MDS + bool "Mitigate Microarchitectural Data Sampling (MDS) hardware bug" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Microarchitectural Data Sampling (MDS). MDS is + a hardware vulnerability which allows unprivileged speculative access + to data which is available in various CPU internal buffers. + See also <file:Documentation/admin-guide/hw-vuln/mds.rst> + +config MITIGATION_TAA + bool "Mitigate TSX Asynchronous Abort (TAA) hardware bug" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for TSX Asynchronous Abort (TAA). TAA is a hardware + vulnerability that allows unprivileged speculative access to data + which is available in various CPU internal buffers by using + asynchronous aborts within an Intel TSX transactional region. + See also <file:Documentation/admin-guide/hw-vuln/tsx_async_abort.rst> + +config MITIGATION_MMIO_STALE_DATA + bool "Mitigate MMIO Stale Data hardware bug" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for MMIO Stale Data hardware bugs. Processor MMIO + Stale Data Vulnerabilities are a class of memory-mapped I/O (MMIO) + vulnerabilities that can expose data. The vulnerabilities require the + attacker to have access to MMIO. + See also + <file:Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst> + +config MITIGATION_L1TF + bool "Mitigate L1 Terminal Fault (L1TF) hardware bug" + depends on CPU_SUP_INTEL + default y + help + Mitigate L1 Terminal Fault (L1TF) hardware bug. L1 Terminal Fault is a + hardware vulnerability which allows unprivileged speculative access to data + available in the Level 1 Data Cache. + See <file:Documentation/admin-guide/hw-vuln/l1tf.rst + +config MITIGATION_RETBLEED + bool "Mitigate RETBleed hardware bug" + depends on (CPU_SUP_INTEL && MITIGATION_SPECTRE_V2) || MITIGATION_UNRET_ENTRY || MITIGATION_IBPB_ENTRY + default y + help + Enable mitigation for RETBleed (Arbitrary Speculative Code Execution + with Return Instructions) vulnerability. RETBleed is a speculative + execution attack which takes advantage of microarchitectural behavior + in many modern microprocessors, similar to Spectre v2. An + unprivileged attacker can use these flaws to bypass conventional + memory security restrictions to gain read access to privileged memory + that would otherwise be inaccessible. + +config MITIGATION_SPECTRE_V1 + bool "Mitigate SPECTRE V1 hardware bug" + default y + help + Enable mitigation for Spectre V1 (Bounds Check Bypass). Spectre V1 is a + class of side channel attacks that takes advantage of speculative + execution that bypasses conditional branch instructions used for + memory access bounds check. + See also <file:Documentation/admin-guide/hw-vuln/spectre.rst> + +config MITIGATION_SPECTRE_V2 + bool "Mitigate SPECTRE V2 hardware bug" + default y + help + Enable mitigation for Spectre V2 (Branch Target Injection). Spectre + V2 is a class of side channel attacks that takes advantage of + indirect branch predictors inside the processor. In Spectre variant 2 + attacks, the attacker can steer speculative indirect branches in the + victim to gadget code by poisoning the branch target buffer of a CPU + used for predicting indirect branch addresses. + See also <file:Documentation/admin-guide/hw-vuln/spectre.rst> + +config MITIGATION_SRBDS + bool "Mitigate Special Register Buffer Data Sampling (SRBDS) hardware bug" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Special Register Buffer Data Sampling (SRBDS). + SRBDS is a hardware vulnerability that allows Microarchitectural Data + Sampling (MDS) techniques to infer values returned from special + register accesses. An unprivileged user can extract values returned + from RDRAND and RDSEED executed on another core or sibling thread + using MDS techniques. + See also + <file:Documentation/admin-guide/hw-vuln/special-register-buffer-data-sampling.rst> + +config MITIGATION_SSB + bool "Mitigate Speculative Store Bypass (SSB) hardware bug" + default y + help + Enable mitigation for Speculative Store Bypass (SSB). SSB is a + hardware security vulnerability and its exploitation takes advantage + of speculative execution in a similar way to the Meltdown and Spectre + security vulnerabilities. + endif config ARCH_HAS_ADD_PAGES @@ -2979,9 +3068,13 @@ config OLPC_XO15_SCI - AC adapter status updates - Battery status updates +config GEODE_COMMON + bool + config ALIX bool "PCEngines ALIX System Support (LED setup)" select GPIOLIB + select GEODE_COMMON help This option enables system support for the PCEngines ALIX. At present this just sets up LEDs for GPIO control on @@ -2996,12 +3089,14 @@ config ALIX config NET5501 bool "Soekris Engineering net5501 System Support (LEDS, GPIO, etc)" select GPIOLIB + select GEODE_COMMON help This option enables system support for the Soekris Engineering net5501. config GEOS bool "Traverse Technologies GEOS System Support (LEDS, GPIO, etc)" select GPIOLIB + select GEODE_COMMON depends on DMI help This option enables system support for the Traverse Technologies GEOS. diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 801fd85c3ef6..cd75e78a06c1 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -24,11 +24,15 @@ RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) ifdef CONFIG_MITIGATION_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern +RETHUNK_RUSTFLAGS := -Zfunction-return=thunk-extern RETPOLINE_CFLAGS += $(RETHUNK_CFLAGS) +RETPOLINE_RUSTFLAGS += $(RETHUNK_RUSTFLAGS) endif export RETHUNK_CFLAGS +export RETHUNK_RUSTFLAGS export RETPOLINE_CFLAGS +export RETPOLINE_RUSTFLAGS export RETPOLINE_VDSO_CFLAGS # For gcc stack alignment is specified with -mpreferred-stack-boundary, @@ -218,9 +222,10 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_MITIGATION_RETPOLINE KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) + KBUILD_RUSTFLAGS += $(RETPOLINE_RUSTFLAGS) # Additionally, avoid generating expensive indirect jumps which # are subject to retpolines for small number of switch cases. - # clang turns off jump table generation by default when under + # LLVM turns off jump table generation by default when under # retpoline builds, however, gcc does not for x86. This has # only been fixed starting from gcc stable version 8.4.0 and # onwards, but not for older ones. See gcc bug #86952. @@ -237,6 +242,10 @@ ifdef CONFIG_CALL_PADDING PADDING_CFLAGS := -fpatchable-function-entry=$(CONFIG_FUNCTION_PADDING_BYTES),$(CONFIG_FUNCTION_PADDING_BYTES) KBUILD_CFLAGS += $(PADDING_CFLAGS) export PADDING_CFLAGS + +PADDING_RUSTFLAGS := -Zpatchable-function-entry=$(CONFIG_FUNCTION_PADDING_BYTES),$(CONFIG_FUNCTION_PADDING_BYTES) +KBUILD_RUSTFLAGS += $(PADDING_RUSTFLAGS) +export PADDING_RUSTFLAGS endif KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 944454306ef4..04a35b2c26e9 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -511,7 +511,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) if (init_unaccepted_memory()) { debug_putstr("Accepting memory... "); - accept_memory(__pa(output), __pa(output) + needed_size); + accept_memory(__pa(output), needed_size); } entry_offset = decompress_kernel(output, virt_addr, error); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index b353a7be380c..dd8d1a85f671 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -256,6 +256,6 @@ static inline bool init_unaccepted_memory(void) { return false; } /* Defined in EFI stub */ extern struct efi_unaccepted_memory *unaccepted_table; -void accept_memory(phys_addr_t start, phys_addr_t end); +void accept_memory(phys_addr_t start, unsigned long size); #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index da8b66dce0da..327c45c5013f 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -16,6 +16,7 @@ #include <asm/insn-eval.h> #include <asm/pgtable.h> #include <asm/set_memory.h> +#include <asm/traps.h> /* MMIO direction */ #define EPT_READ 0 @@ -433,6 +434,11 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EINVAL; } + if (!fault_in_kernel_space(ve->gla)) { + WARN_ONCE(1, "Access to userspace address is not supported"); + return -EINVAL; + } + /* * Reject EPT violation #VEs that split pages. * diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index be3ee4294903..aabafa3faa6d 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1,6 +1,2 @@ CONFIG_NOHIGHMEM=y -# CONFIG_HIGHMEM4G is not set -# CONFIG_HIGHMEM64G is not set -# CONFIG_UNWINDER_ORC is not set CONFIG_UNWINDER_GUESS=y -# CONFIG_UNWINDER_FRAME_POINTER is not set diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig index 24875e6295f2..7b1bebed879d 100644 --- a/arch/x86/crypto/Kconfig +++ b/arch/x86/crypto/Kconfig @@ -14,7 +14,7 @@ config CRYPTO_CURVE25519_X86 - ADX (large integer arithmetic) config CRYPTO_AES_NI_INTEL - tristate "Ciphers: AES, modes: ECB, CBC, CTS, CTR, XTR, XTS, GCM (AES-NI)" + tristate "Ciphers: AES, modes: ECB, CBC, CTS, CTR, XCTR, XTS, GCM (AES-NI/VAES)" depends on X86 select CRYPTO_AEAD select CRYPTO_LIB_AES @@ -25,10 +25,14 @@ config CRYPTO_AES_NI_INTEL help Block cipher: AES cipher algorithms AEAD cipher: AES with GCM - Length-preserving ciphers: AES with ECB, CBC, CTS, CTR, XTR, XTS + Length-preserving ciphers: AES with ECB, CBC, CTS, CTR, XCTR, XTS Architecture: x86 (32-bit and 64-bit) using: - AES-NI (AES new instructions) + - VAES (Vector AES) + + Some algorithm implementations are supported only in 64-bit builds, + and some have additional prerequisites such as AVX2 or AVX512. config CRYPTO_BLOWFISH_X86_64 tristate "Ciphers: Blowfish, modes: ECB, CBC" diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index cd37de5ec404..b0dd83555499 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1366,6 +1366,8 @@ gcm_crypt(struct aead_request *req, int flags) err = skcipher_walk_aead_encrypt(&walk, req, false); else err = skcipher_walk_aead_decrypt(&walk, req, false); + if (err) + return err; /* * Since the AES-GCM assembly code requires that at least three assembly @@ -1381,37 +1383,31 @@ gcm_crypt(struct aead_request *req, int flags) gcm_process_assoc(key, ghash_acc, req->src, assoclen, flags); /* En/decrypt the data and pass the ciphertext through GHASH. */ - while ((nbytes = walk.nbytes) != 0) { - if (unlikely(nbytes < walk.total)) { - /* - * Non-last segment. In this case, the assembly - * function requires that the length be a multiple of 16 - * (AES_BLOCK_SIZE) bytes. The needed buffering of up - * to 16 bytes is handled by the skcipher_walk. Here we - * just need to round down to a multiple of 16. - */ - nbytes = round_down(nbytes, AES_BLOCK_SIZE); - aes_gcm_update(key, le_ctr, ghash_acc, - walk.src.virt.addr, walk.dst.virt.addr, - nbytes, flags); - le_ctr[0] += nbytes / AES_BLOCK_SIZE; - kernel_fpu_end(); - err = skcipher_walk_done(&walk, walk.nbytes - nbytes); - kernel_fpu_begin(); - } else { - /* Last segment: process all remaining data. */ - aes_gcm_update(key, le_ctr, ghash_acc, - walk.src.virt.addr, walk.dst.virt.addr, - nbytes, flags); - err = skcipher_walk_done(&walk, 0); - /* - * The low word of the counter isn't used by the - * finalize, so there's no need to increment it here. - */ - } + while (unlikely((nbytes = walk.nbytes) < walk.total)) { + /* + * Non-last segment. In this case, the assembly function + * requires that the length be a multiple of 16 (AES_BLOCK_SIZE) + * bytes. The needed buffering of up to 16 bytes is handled by + * the skcipher_walk. Here we just need to round down to a + * multiple of 16. + */ + nbytes = round_down(nbytes, AES_BLOCK_SIZE); + aes_gcm_update(key, le_ctr, ghash_acc, walk.src.virt.addr, + walk.dst.virt.addr, nbytes, flags); + le_ctr[0] += nbytes / AES_BLOCK_SIZE; + kernel_fpu_end(); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + if (err) + return err; + kernel_fpu_begin(); } - if (err) - goto out; + /* Last segment: process all remaining data. */ + aes_gcm_update(key, le_ctr, ghash_acc, walk.src.virt.addr, + walk.dst.virt.addr, nbytes, flags); + /* + * The low word of the counter isn't used by the finalize, so there's no + * need to increment it here. + */ /* Finalize */ taglen = crypto_aead_authsize(tfm); @@ -1439,8 +1435,9 @@ gcm_crypt(struct aead_request *req, int flags) datalen, tag, taglen, flags)) err = -EBADMSG; } -out: kernel_fpu_end(); + if (nbytes) + skcipher_walk_done(&walk, 0); return err; } @@ -1753,6 +1750,6 @@ static void __exit aesni_exit(void) late_initcall(aesni_init); module_exit(aesni_exit); -MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); +MODULE_DESCRIPTION("AES cipher and modes, optimized with AES-NI or VAES instructions"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CRYPTO("aes"); diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 0ffb072be956..0bbec1c75cd0 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -592,22 +592,22 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) leaq K256+0*32(%rip), INP ## reuse INP as scratch reg vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) - FOUR_ROUNDS_AND_SCHED _XFER + 0*32 + FOUR_ROUNDS_AND_SCHED (_XFER + 0*32) leaq K256+1*32(%rip), INP vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) - FOUR_ROUNDS_AND_SCHED _XFER + 1*32 + FOUR_ROUNDS_AND_SCHED (_XFER + 1*32) leaq K256+2*32(%rip), INP vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 2*32+_XFER(%rsp, SRND) - FOUR_ROUNDS_AND_SCHED _XFER + 2*32 + FOUR_ROUNDS_AND_SCHED (_XFER + 2*32) leaq K256+3*32(%rip), INP vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 3*32+_XFER(%rsp, SRND) - FOUR_ROUNDS_AND_SCHED _XFER + 3*32 + FOUR_ROUNDS_AND_SCHED (_XFER + 3*32) add $4*32, SRND cmp $3*4*32, SRND @@ -618,12 +618,12 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) leaq K256+0*32(%rip), INP vpaddd (INP, SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) - DO_4ROUNDS _XFER + 0*32 + DO_4ROUNDS (_XFER + 0*32) leaq K256+1*32(%rip), INP vpaddd (INP, SRND), X1, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) - DO_4ROUNDS _XFER + 1*32 + DO_4ROUNDS (_XFER + 1*32) add $2*32, SRND vmovdqa X2, X0 @@ -651,8 +651,8 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) xor SRND, SRND .align 16 .Lloop3: - DO_4ROUNDS _XFER + 0*32 + 16 - DO_4ROUNDS _XFER + 1*32 + 16 + DO_4ROUNDS (_XFER + 0*32 + 16) + DO_4ROUNDS (_XFER + 1*32 + 16) add $2*32, SRND cmp $4*4*32, SRND jb .Lloop3 diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 51cc9c7cb9bd..94941c5a10ac 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -150,7 +150,7 @@ early_param("ia32_emulation", ia32_emulation_override_cmdline); #endif /* - * Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. + * Invoke a 32-bit syscall. Called with IRQs on in CT_STATE_KERNEL. */ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) { diff --git a/arch/x86/entry/vdso/vgetrandom.c b/arch/x86/entry/vdso/vgetrandom.c index 52d3c7faae2e..430862b8977c 100644 --- a/arch/x86/entry/vdso/vgetrandom.c +++ b/arch/x86/entry/vdso/vgetrandom.c @@ -6,8 +6,6 @@ #include "../../../../lib/vdso/getrandom.c" -ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len); - ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) { return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len); diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 6d83ceb7f1ba..b8fed8b8b9cc 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -38,6 +38,9 @@ struct vdso_data *arch_get_vdso_data(void *vvar_page) } #undef EMIT_VVAR +DEFINE_VVAR(struct vdso_data, _vdso_data); +DEFINE_VVAR_SINGLE(struct vdso_rng_data, _vdso_rng_data); + unsigned int vclocks_used __read_mostly; #if defined(CONFIG_X86_64) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index be01823b1bb4..65ab6460aed4 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -41,6 +41,8 @@ #include <asm/desc.h> #include <asm/ldt.h> #include <asm/unwind.h> +#include <asm/uprobes.h> +#include <asm/ibt.h> #include "perf_event.h" @@ -2816,6 +2818,46 @@ static unsigned long get_segment_base(unsigned int segment) return get_desc_base(desc); } +#ifdef CONFIG_UPROBES +/* + * Heuristic-based check if uprobe is installed at the function entry. + * + * Under assumption of user code being compiled with frame pointers, + * `push %rbp/%ebp` is a good indicator that we indeed are. + * + * Similarly, `endbr64` (assuming 64-bit mode) is also a common pattern. + * If we get this wrong, captured stack trace might have one extra bogus + * entry, but the rest of stack trace will still be meaningful. + */ +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + struct arch_uprobe *auprobe; + + if (!current->utask) + return false; + + auprobe = current->utask->auprobe; + if (!auprobe) + return false; + + /* push %rbp/%ebp */ + if (auprobe->insn[0] == 0x55) + return true; + + /* endbr64 (64-bit only) */ + if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn)) + return true; + + return false; +} + +#else +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_UPROBES */ + #ifdef CONFIG_IA32_EMULATION #include <linux/compat.h> @@ -2827,6 +2869,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const struct stack_frame_ia32 __user *fp; + u32 ret_addr; if (user_64bit_mode(regs)) return 0; @@ -2836,6 +2879,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); + + /* see perf_callchain_user() below for why we do this */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const u32 __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; @@ -2864,6 +2913,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs { struct stack_frame frame; const struct stack_frame __user *fp; + unsigned long ret_addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ @@ -2887,6 +2937,19 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs return; pagefault_disable(); + + /* + * If we are called from uprobe handler, and we are indeed at the very + * entry to user function (which is normally a `push %rbp` instruction, + * under assumption of application being compiled with frame pointers), + * we should read return address from *regs->sp before proceeding + * to follow frame pointers, otherwise we'll skip immediate caller + * as %rbp is not yet setup. + */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const unsigned long __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 974e917e65b2..8f78b0c900ef 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -557,9 +557,6 @@ static int bts_event_init(struct perf_event *event) * disabled, so disallow intel_bts driver for unprivileged * users on paranoid systems since it provides trace data * to the user in a zero-copy fashion. - * - * Note that the default paranoia setting permits unprivileged - * users to profile the kernel. */ if (event->attr.exclude_kernel) { ret = perf_allow_kernel(&event->attr); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9e519d8a810a..d879478db3f5 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3972,8 +3972,12 @@ static int intel_pmu_hw_config(struct perf_event *event) x86_pmu.pebs_aliases(event); } - if (needs_branch_stack(event) && is_sampling_event(event)) - event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK; + if (needs_branch_stack(event)) { + /* Avoid branch stack setup for counting events in SAMPLE READ */ + if (is_sampling_event(event) || + !(event->attr.sample_type & PERF_SAMPLE_READ)) + event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK; + } if (branch_sample_counters(event)) { struct perf_event *leader, *sibling; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 9f116dfc4728..ae4ec16156bb 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -128,10 +128,6 @@ static ssize_t __cstate_##_var##_show(struct device *dev, \ static struct device_attribute format_attr_##_var = \ __ATTR(_name, 0444, __cstate_##_var##_show, NULL) -static ssize_t cstate_get_attr_cpumask(struct device *dev, - struct device_attribute *attr, - char *buf); - /* Model -> events mapping */ struct cstate_model { unsigned long core_events; @@ -206,22 +202,9 @@ static struct attribute_group cstate_format_attr_group = { .attrs = cstate_format_attrs, }; -static cpumask_t cstate_core_cpu_mask; -static DEVICE_ATTR(cpumask, S_IRUGO, cstate_get_attr_cpumask, NULL); - -static struct attribute *cstate_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static struct attribute_group cpumask_attr_group = { - .attrs = cstate_cpumask_attrs, -}; - static const struct attribute_group *cstate_attr_groups[] = { &cstate_events_attr_group, &cstate_format_attr_group, - &cpumask_attr_group, NULL, }; @@ -269,8 +252,6 @@ static struct perf_msr pkg_msr[] = { [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &group_cstate_pkg_c10, test_msr }, }; -static cpumask_t cstate_pkg_cpu_mask; - /* cstate_module PMU */ static struct pmu cstate_module_pmu; static bool has_cstate_module; @@ -291,28 +272,9 @@ static struct perf_msr module_msr[] = { [PERF_CSTATE_MODULE_C6_RES] = { MSR_MODULE_C6_RES_MS, &group_cstate_module_c6, test_msr }, }; -static cpumask_t cstate_module_cpu_mask; - -static ssize_t cstate_get_attr_cpumask(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct pmu *pmu = dev_get_drvdata(dev); - - if (pmu == &cstate_core_pmu) - return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask); - else if (pmu == &cstate_pkg_pmu) - return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask); - else if (pmu == &cstate_module_pmu) - return cpumap_print_to_pagebuf(true, buf, &cstate_module_cpu_mask); - else - return 0; -} - static int cstate_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config; - int cpu; if (event->attr.type != event->pmu->type) return -ENOENT; @@ -331,20 +293,13 @@ static int cstate_pmu_event_init(struct perf_event *event) if (!(core_msr_mask & (1 << cfg))) return -EINVAL; event->hw.event_base = core_msr[cfg].msr; - cpu = cpumask_any_and(&cstate_core_cpu_mask, - topology_sibling_cpumask(event->cpu)); } else if (event->pmu == &cstate_pkg_pmu) { if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) return -EINVAL; cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX); if (!(pkg_msr_mask & (1 << cfg))) return -EINVAL; - - event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; - event->hw.event_base = pkg_msr[cfg].msr; - cpu = cpumask_any_and(&cstate_pkg_cpu_mask, - topology_die_cpumask(event->cpu)); } else if (event->pmu == &cstate_module_pmu) { if (cfg >= PERF_CSTATE_MODULE_EVENT_MAX) return -EINVAL; @@ -352,16 +307,10 @@ static int cstate_pmu_event_init(struct perf_event *event) if (!(module_msr_mask & (1 << cfg))) return -EINVAL; event->hw.event_base = module_msr[cfg].msr; - cpu = cpumask_any_and(&cstate_module_cpu_mask, - topology_cluster_cpumask(event->cpu)); } else { return -ENOENT; } - if (cpu >= nr_cpu_ids) - return -ENODEV; - - event->cpu = cpu; event->hw.config = cfg; event->hw.idx = -1; return 0; @@ -412,84 +361,6 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode) return 0; } -/* - * Check if exiting cpu is the designated reader. If so migrate the - * events when there is a valid target available - */ -static int cstate_cpu_exit(unsigned int cpu) -{ - unsigned int target; - - if (has_cstate_core && - cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) { - - target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu); - /* Migrate events if there is a valid target */ - if (target < nr_cpu_ids) { - cpumask_set_cpu(target, &cstate_core_cpu_mask); - perf_pmu_migrate_context(&cstate_core_pmu, cpu, target); - } - } - - if (has_cstate_pkg && - cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) { - - target = cpumask_any_but(topology_die_cpumask(cpu), cpu); - /* Migrate events if there is a valid target */ - if (target < nr_cpu_ids) { - cpumask_set_cpu(target, &cstate_pkg_cpu_mask); - perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target); - } - } - - if (has_cstate_module && - cpumask_test_and_clear_cpu(cpu, &cstate_module_cpu_mask)) { - - target = cpumask_any_but(topology_cluster_cpumask(cpu), cpu); - /* Migrate events if there is a valid target */ - if (target < nr_cpu_ids) { - cpumask_set_cpu(target, &cstate_module_cpu_mask); - perf_pmu_migrate_context(&cstate_module_pmu, cpu, target); - } - } - return 0; -} - -static int cstate_cpu_init(unsigned int cpu) -{ - unsigned int target; - - /* - * If this is the first online thread of that core, set it in - * the core cpu mask as the designated reader. - */ - target = cpumask_any_and(&cstate_core_cpu_mask, - topology_sibling_cpumask(cpu)); - - if (has_cstate_core && target >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_core_cpu_mask); - - /* - * If this is the first online thread of that package, set it - * in the package cpu mask as the designated reader. - */ - target = cpumask_any_and(&cstate_pkg_cpu_mask, - topology_die_cpumask(cpu)); - if (has_cstate_pkg && target >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); - - /* - * If this is the first online thread of that cluster, set it - * in the cluster cpu mask as the designated reader. - */ - target = cpumask_any_and(&cstate_module_cpu_mask, - topology_cluster_cpumask(cpu)); - if (has_cstate_module && target >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_module_cpu_mask); - - return 0; -} - static const struct attribute_group *core_attr_update[] = { &group_cstate_core_c1, &group_cstate_core_c3, @@ -526,6 +397,7 @@ static struct pmu cstate_core_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, + .scope = PERF_PMU_SCOPE_CORE, .module = THIS_MODULE, }; @@ -541,6 +413,7 @@ static struct pmu cstate_pkg_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, + .scope = PERF_PMU_SCOPE_PKG, .module = THIS_MODULE, }; @@ -556,6 +429,7 @@ static struct pmu cstate_module_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, + .scope = PERF_PMU_SCOPE_CLUSTER, .module = THIS_MODULE, }; @@ -810,9 +684,6 @@ static int __init cstate_probe(const struct cstate_model *cm) static inline void cstate_cleanup(void) { - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING); - if (has_cstate_core) perf_pmu_unregister(&cstate_core_pmu); @@ -827,11 +698,6 @@ static int __init cstate_init(void) { int err; - cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING, - "perf/x86/cstate:starting", cstate_cpu_init, NULL); - cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE, - "perf/x86/cstate:online", NULL, cstate_cpu_exit); - if (has_cstate_core) { err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1); if (err) { @@ -844,6 +710,8 @@ static int __init cstate_init(void) if (has_cstate_pkg) { if (topology_max_dies_per_package() > 1) { + /* CLX-AP is multi-die and the cstate is die-scope */ + cstate_pkg_pmu.scope = PERF_PMU_SCOPE_DIE; err = perf_pmu_register(&cstate_pkg_pmu, "cstate_die", -1); } else { diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index b4aa8daa4773..fd4670a6694e 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -416,7 +416,7 @@ static bool pt_event_valid(struct perf_event *event) static void pt_config_start(struct perf_event *event) { struct pt *pt = this_cpu_ptr(&pt_ctx); - u64 ctl = event->hw.config; + u64 ctl = event->hw.aux_config; ctl |= RTIT_CTL_TRACEEN; if (READ_ONCE(pt->vmx_on)) @@ -424,7 +424,7 @@ static void pt_config_start(struct perf_event *event) else wrmsrl(MSR_IA32_RTIT_CTL, ctl); - WRITE_ONCE(event->hw.config, ctl); + WRITE_ONCE(event->hw.aux_config, ctl); } /* Address ranges and their corresponding msr configuration registers */ @@ -503,7 +503,7 @@ static void pt_config(struct perf_event *event) u64 reg; /* First round: clear STATUS, in particular the PSB byte counter. */ - if (!event->hw.config) { + if (!event->hw.aux_config) { perf_event_itrace_started(event); wrmsrl(MSR_IA32_RTIT_STATUS, 0); } @@ -533,14 +533,14 @@ static void pt_config(struct perf_event *event) reg |= (event->attr.config & PT_CONFIG_MASK); - event->hw.config = reg; + event->hw.aux_config = reg; pt_config_start(event); } static void pt_config_stop(struct perf_event *event) { struct pt *pt = this_cpu_ptr(&pt_ctx); - u64 ctl = READ_ONCE(event->hw.config); + u64 ctl = READ_ONCE(event->hw.aux_config); /* may be already stopped by a PMI */ if (!(ctl & RTIT_CTL_TRACEEN)) @@ -550,7 +550,7 @@ static void pt_config_stop(struct perf_event *event) if (!READ_ONCE(pt->vmx_on)) wrmsrl(MSR_IA32_RTIT_CTL, ctl); - WRITE_ONCE(event->hw.config, ctl); + WRITE_ONCE(event->hw.aux_config, ctl); /* * A wrmsr that disables trace generation serializes other PT @@ -1557,7 +1557,7 @@ void intel_pt_handle_vmx(int on) /* Turn PTs back on */ if (!on && event) - wrmsrl(MSR_IA32_RTIT_CTL, event->hw.config); + wrmsrl(MSR_IA32_RTIT_CTL, event->hw.aux_config); local_irq_restore(flags); } @@ -1606,6 +1606,7 @@ static void pt_event_stop(struct perf_event *event, int mode) * see comment in intel_pt_interrupt(). */ WRITE_ONCE(pt->handle_nmi, 0); + barrier(); pt_config_stop(event); @@ -1657,11 +1658,10 @@ static long pt_event_snapshot_aux(struct perf_event *event, return 0; /* - * Here, handle_nmi tells us if the tracing is on + * There is no PT interrupt in this mode, so stop the trace and it will + * remain stopped while the buffer is copied. */ - if (READ_ONCE(pt->handle_nmi)) - pt_config_stop(event); - + pt_config_stop(event); pt_read_offset(buf); pt_update_head(pt); @@ -1673,11 +1673,10 @@ static long pt_event_snapshot_aux(struct perf_event *event, ret = perf_output_copy_aux(&pt->handle, handle, from, to); /* - * If the tracing was on when we turned up, restart it. - * Compiler barrier not needed as we couldn't have been - * preempted by anything that touches pt->handle_nmi. + * Here, handle_nmi tells us if the tracing was on. + * If the tracing was on, restart it. */ - if (pt->handle_nmi) + if (READ_ONCE(pt->handle_nmi)) pt_config_start(event); return ret; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 64ca8625eb58..d98fac567684 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1816,6 +1816,11 @@ static const struct intel_uncore_init_fun mtl_uncore_init __initconst = { .mmio_init = adl_uncore_mmio_init, }; +static const struct intel_uncore_init_fun lnl_uncore_init __initconst = { + .cpu_init = lnl_uncore_cpu_init, + .mmio_init = lnl_uncore_mmio_init, +}; + static const struct intel_uncore_init_fun icx_uncore_init __initconst = { .cpu_init = icx_uncore_cpu_init, .pci_init = icx_uncore_pci_init, @@ -1893,6 +1898,10 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_uncore_init), X86_MATCH_VFM(INTEL_METEORLAKE, &mtl_uncore_init), X86_MATCH_VFM(INTEL_METEORLAKE_L, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_ARROWLAKE, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_ARROWLAKE_U, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_ARROWLAKE_H, &mtl_uncore_init), + X86_MATCH_VFM(INTEL_LUNARLAKE_M, &lnl_uncore_init), X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &gnr_uncore_init), diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 027ef292c602..79ff32e13dcc 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -611,10 +611,12 @@ void skl_uncore_cpu_init(void); void icl_uncore_cpu_init(void); void tgl_uncore_cpu_init(void); void adl_uncore_cpu_init(void); +void lnl_uncore_cpu_init(void); void mtl_uncore_cpu_init(void); void tgl_uncore_mmio_init(void); void tgl_l_uncore_mmio_init(void); void adl_uncore_mmio_init(void); +void lnl_uncore_mmio_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 9462fd9f3b7a..3934e1e4e3b1 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -252,6 +252,7 @@ DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); DEFINE_UNCORE_FORMAT_ATTR(threshold, threshold, "config:24-29"); +DEFINE_UNCORE_FORMAT_ATTR(threshold2, threshold, "config:24-31"); /* Sandy Bridge uncore support */ static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) @@ -746,6 +747,34 @@ void mtl_uncore_cpu_init(void) uncore_msr_uncores = mtl_msr_uncores; } +static struct intel_uncore_type *lnl_msr_uncores[] = { + &mtl_uncore_cbox, + &mtl_uncore_arb, + NULL +}; + +#define LNL_UNC_MSR_GLOBAL_CTL 0x240e + +static void lnl_uncore_msr_init_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) + wrmsrl(LNL_UNC_MSR_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN); +} + +static struct intel_uncore_ops lnl_uncore_msr_ops = { + .init_box = lnl_uncore_msr_init_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +void lnl_uncore_cpu_init(void) +{ + mtl_uncore_cbox.num_boxes = 4; + mtl_uncore_cbox.ops = &lnl_uncore_msr_ops; + uncore_msr_uncores = lnl_msr_uncores; +} + enum { SNB_PCI_UNCORE_IMC, }; @@ -1475,39 +1504,45 @@ static struct pci_dev *tgl_uncore_get_mc_dev(void) ids++; } + /* Just try to grab 00:00.0 device */ + if (!mc_dev) + mc_dev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0)); + return mc_dev; } #define TGL_UNCORE_MMIO_IMC_MEM_OFFSET 0x10000 #define TGL_UNCORE_PCI_IMC_MAP_SIZE 0xe000 -static void __uncore_imc_init_box(struct intel_uncore_box *box, - unsigned int base_offset) +static void +uncore_get_box_mmio_addr(struct intel_uncore_box *box, + unsigned int base_offset, + int bar_offset, int step) { struct pci_dev *pdev = tgl_uncore_get_mc_dev(); struct intel_uncore_pmu *pmu = box->pmu; struct intel_uncore_type *type = pmu->type; resource_size_t addr; - u32 mch_bar; + u32 bar; if (!pdev) { pr_warn("perf uncore: Cannot find matched IMC device.\n"); return; } - pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET, &mch_bar); - /* MCHBAR is disabled */ - if (!(mch_bar & BIT(0))) { - pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n"); + pci_read_config_dword(pdev, bar_offset, &bar); + if (!(bar & BIT(0))) { + pr_warn("perf uncore: BAR 0x%x is disabled. Failed to map %s counters.\n", + bar_offset, type->name); pci_dev_put(pdev); return; } - mch_bar &= ~BIT(0); - addr = (resource_size_t)(mch_bar + TGL_UNCORE_MMIO_IMC_MEM_OFFSET * pmu->pmu_idx); + bar &= ~BIT(0); + addr = (resource_size_t)(bar + step * pmu->pmu_idx); #ifdef CONFIG_PHYS_ADDR_T_64BIT - pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET + 4, &mch_bar); - addr |= ((resource_size_t)mch_bar << 32); + pci_read_config_dword(pdev, bar_offset + 4, &bar); + addr |= ((resource_size_t)bar << 32); #endif addr += base_offset; @@ -1518,6 +1553,14 @@ static void __uncore_imc_init_box(struct intel_uncore_box *box, pci_dev_put(pdev); } +static void __uncore_imc_init_box(struct intel_uncore_box *box, + unsigned int base_offset) +{ + uncore_get_box_mmio_addr(box, base_offset, + SNB_UNCORE_PCI_IMC_BAR_OFFSET, + TGL_UNCORE_MMIO_IMC_MEM_OFFSET); +} + static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) { __uncore_imc_init_box(box, 0); @@ -1612,14 +1655,17 @@ static void adl_uncore_mmio_enable_box(struct intel_uncore_box *box) writel(0, box->io_addr + uncore_mmio_box_ctl(box)); } +#define MMIO_UNCORE_COMMON_OPS() \ + .exit_box = uncore_mmio_exit_box, \ + .disable_box = adl_uncore_mmio_disable_box, \ + .enable_box = adl_uncore_mmio_enable_box, \ + .disable_event = intel_generic_uncore_mmio_disable_event, \ + .enable_event = intel_generic_uncore_mmio_enable_event, \ + .read_counter = uncore_mmio_read_counter, + static struct intel_uncore_ops adl_uncore_mmio_ops = { .init_box = adl_uncore_imc_init_box, - .exit_box = uncore_mmio_exit_box, - .disable_box = adl_uncore_mmio_disable_box, - .enable_box = adl_uncore_mmio_enable_box, - .disable_event = intel_generic_uncore_mmio_disable_event, - .enable_event = intel_generic_uncore_mmio_enable_event, - .read_counter = uncore_mmio_read_counter, + MMIO_UNCORE_COMMON_OPS() }; #define ADL_UNC_CTL_CHMASK_MASK 0x00000f00 @@ -1703,3 +1749,108 @@ void adl_uncore_mmio_init(void) } /* end of Alder Lake MMIO uncore support */ + +/* Lunar Lake MMIO uncore support */ +#define LNL_UNCORE_PCI_SAFBAR_OFFSET 0x68 +#define LNL_UNCORE_MAP_SIZE 0x1000 +#define LNL_UNCORE_SNCU_BASE 0xE4B000 +#define LNL_UNCORE_SNCU_CTR 0x390 +#define LNL_UNCORE_SNCU_CTRL 0x398 +#define LNL_UNCORE_SNCU_BOX_CTL 0x380 +#define LNL_UNCORE_GLOBAL_CTL 0x700 +#define LNL_UNCORE_HBO_BASE 0xE54000 +#define LNL_UNCORE_HBO_OFFSET -4096 +#define LNL_UNCORE_HBO_CTR 0x570 +#define LNL_UNCORE_HBO_CTRL 0x550 +#define LNL_UNCORE_HBO_BOX_CTL 0x548 + +#define LNL_UNC_CTL_THRESHOLD 0xff000000 +#define LNL_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + LNL_UNC_CTL_THRESHOLD) + +static struct attribute *lnl_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_threshold2.attr, + NULL +}; + +static const struct attribute_group lnl_uncore_format_group = { + .name = "format", + .attrs = lnl_uncore_formats_attr, +}; + +static void lnl_uncore_hbo_init_box(struct intel_uncore_box *box) +{ + uncore_get_box_mmio_addr(box, LNL_UNCORE_HBO_BASE, + LNL_UNCORE_PCI_SAFBAR_OFFSET, + LNL_UNCORE_HBO_OFFSET); +} + +static struct intel_uncore_ops lnl_uncore_hbo_ops = { + .init_box = lnl_uncore_hbo_init_box, + MMIO_UNCORE_COMMON_OPS() +}; + +static struct intel_uncore_type lnl_uncore_hbo = { + .name = "hbo", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 64, + .perf_ctr = LNL_UNCORE_HBO_CTR, + .event_ctl = LNL_UNCORE_HBO_CTRL, + .event_mask = LNL_UNC_RAW_EVENT_MASK, + .box_ctl = LNL_UNCORE_HBO_BOX_CTL, + .mmio_map_size = LNL_UNCORE_MAP_SIZE, + .ops = &lnl_uncore_hbo_ops, + .format_group = &lnl_uncore_format_group, +}; + +static void lnl_uncore_sncu_init_box(struct intel_uncore_box *box) +{ + uncore_get_box_mmio_addr(box, LNL_UNCORE_SNCU_BASE, + LNL_UNCORE_PCI_SAFBAR_OFFSET, + 0); + + if (box->io_addr) + writel(ADL_UNCORE_IMC_CTL_INT, box->io_addr + LNL_UNCORE_GLOBAL_CTL); +} + +static struct intel_uncore_ops lnl_uncore_sncu_ops = { + .init_box = lnl_uncore_sncu_init_box, + MMIO_UNCORE_COMMON_OPS() +}; + +static struct intel_uncore_type lnl_uncore_sncu = { + .name = "sncu", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 64, + .perf_ctr = LNL_UNCORE_SNCU_CTR, + .event_ctl = LNL_UNCORE_SNCU_CTRL, + .event_mask = LNL_UNC_RAW_EVENT_MASK, + .box_ctl = LNL_UNCORE_SNCU_BOX_CTL, + .mmio_map_size = LNL_UNCORE_MAP_SIZE, + .ops = &lnl_uncore_sncu_ops, + .format_group = &lnl_uncore_format_group, +}; + +static struct intel_uncore_type *lnl_mmio_uncores[] = { + &adl_uncore_imc, + &lnl_uncore_hbo, + &lnl_uncore_sncu, + &adl_uncore_imc_free_running, + NULL +}; + +void lnl_uncore_mmio_init(void) +{ + uncore_mmio_uncores = lnl_mmio_uncores; +} + +/* end of Lunar Lake MMIO uncore support */ diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index b985ca79cf97..a481a939862e 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -103,6 +103,19 @@ static struct perf_pmu_events_attr event_attr_##v = { \ .event_str = str, \ }; +/* + * RAPL Package energy counter scope: + * 1. AMD/HYGON platforms have a per-PKG package energy counter + * 2. For Intel platforms + * 2.1. CLX-AP is multi-die and its RAPL MSRs are die-scope + * 2.2. Other Intel platforms are single die systems so the scope can be + * considered as either pkg-scope or die-scope, and we are considering + * them as die-scope. + */ +#define rapl_pmu_is_pkg_scope() \ + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || \ + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) + struct rapl_pmu { raw_spinlock_t lock; int n_active; @@ -140,9 +153,25 @@ static unsigned int rapl_cntr_mask; static u64 rapl_timer_ms; static struct perf_msr *rapl_msrs; +/* + * Helper functions to get the correct topology macros according to the + * RAPL PMU scope. + */ +static inline unsigned int get_rapl_pmu_idx(int cpu) +{ + return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) : + topology_logical_die_id(cpu); +} + +static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu) +{ + return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) : + topology_die_cpumask(cpu); +} + static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { - unsigned int rapl_pmu_idx = topology_logical_die_id(cpu); + unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu); /* * The unsigned check also catches the '-1' return value for non @@ -552,7 +581,7 @@ static int rapl_cpu_offline(unsigned int cpu) pmu->cpu = -1; /* Find a new cpu to collect rapl events */ - target = cpumask_any_but(topology_die_cpumask(cpu), cpu); + target = cpumask_any_but(get_rapl_pmu_cpumask(cpu), cpu); /* Migrate rapl events to the new target */ if (target < nr_cpu_ids) { @@ -565,6 +594,11 @@ static int rapl_cpu_offline(unsigned int cpu) static int rapl_cpu_online(unsigned int cpu) { + s32 rapl_pmu_idx = get_rapl_pmu_idx(cpu); + if (rapl_pmu_idx < 0) { + pr_err("topology_logical_(package/die)_id() returned a negative value"); + return -EINVAL; + } struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; @@ -579,14 +613,14 @@ static int rapl_cpu_online(unsigned int cpu) pmu->timer_interval = ms_to_ktime(rapl_timer_ms); rapl_hrtimer_init(pmu); - rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu; + rapl_pmus->pmus[rapl_pmu_idx] = pmu; } /* * Check if there is an online cpu in the package which collects rapl * events already. */ - target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu)); + target = cpumask_any_and(&rapl_cpu_mask, get_rapl_pmu_cpumask(cpu)); if (target < nr_cpu_ids) return 0; @@ -675,7 +709,10 @@ static const struct attribute_group *rapl_attr_update[] = { static int __init init_rapl_pmus(void) { - int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package(); + int nr_rapl_pmu = topology_max_packages(); + + if (!rapl_pmu_is_pkg_scope()) + nr_rapl_pmu *= topology_max_dies_per_package(); rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL); if (!rapl_pmus) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 17a71e92a343..95eada2994e1 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -35,7 +35,6 @@ #include <clocksource/hyperv_timer.h> #include <linux/highmem.h> -int hyperv_init_cpuhp; u64 hv_current_partition_id = ~0ull; EXPORT_SYMBOL_GPL(hv_current_partition_id); @@ -607,8 +606,6 @@ skip_hypercall_pg_init: register_syscore_ops(&hv_syscore_ops); - hyperv_init_cpuhp = cpuhp; - if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID) hv_get_partition_id(); @@ -637,7 +634,7 @@ skip_hypercall_pg_init: clean_guest_os_id: wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0); - cpuhp_remove_state(cpuhp); + cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE); free_ghcb_page: free_percpu(hv_ghcb_pg); free_vp_assist_page: diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index b4a851d27c7c..60fc3ed72830 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -321,9 +321,9 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) vmsa->efer = native_read_msr(MSR_EFER); - asm volatile("movq %%cr4, %%rax;" : "=a" (vmsa->cr4)); - asm volatile("movq %%cr3, %%rax;" : "=a" (vmsa->cr3)); - asm volatile("movq %%cr0, %%rax;" : "=a" (vmsa->cr0)); + vmsa->cr4 = native_read_cr4(); + vmsa->cr3 = __native_read_cr3(); + vmsa->cr0 = native_read_cr0(); vmsa->xcr0 = 1; vmsa->g_pat = HV_AP_INIT_GPAT_DEFAULT; diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index a192bdea69e2..6c23d1661b17 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -11,3 +11,4 @@ generated-y += xen-hypercalls.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h +generic-y += mmzone.h diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 21bc53f5ed0c..5ab1a4598d00 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -174,6 +174,14 @@ void acpi_generic_reduced_hw_init(void); void x86_default_set_root_pointer(u64 addr); u64 x86_default_get_root_pointer(void); +#ifdef CONFIG_XEN_PV +/* A Xen PV domain needs a special acpi_os_ioremap() handling. */ +extern void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, + acpi_size size); +void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size); +#define acpi_os_ioremap acpi_os_ioremap +#endif + #else /* !CONFIG_ACPI */ #define acpi_lapic 0 diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 9327eb00e96d..f21ff1932699 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -18,6 +18,11 @@ #define ARCH_APICTIMER_STOPS_ON_C3 1 +/* Macros for apic_extnmi which controls external NMI masking */ +#define APIC_EXTNMI_BSP 0 /* Default */ +#define APIC_EXTNMI_ALL 1 +#define APIC_EXTNMI_NONE 2 + /* * Debugging macros */ @@ -25,22 +30,22 @@ #define APIC_VERBOSE 1 #define APIC_DEBUG 2 -/* Macros for apic_extnmi which controls external NMI masking */ -#define APIC_EXTNMI_BSP 0 /* Default */ -#define APIC_EXTNMI_ALL 1 -#define APIC_EXTNMI_NONE 2 - /* - * Define the default level of output to be very little - * This can be turned up by using apic=verbose for more - * information and apic=debug for _lots_ of information. - * apic_verbosity is defined in apic.c + * Define the default level of output to be very little This can be turned + * up by using apic=verbose for more information and apic=debug for _lots_ + * of information. apic_verbosity is defined in apic.c */ -#define apic_printk(v, s, a...) do { \ - if ((v) <= apic_verbosity) \ - printk(s, ##a); \ - } while (0) - +#define apic_printk(v, s, a...) \ +do { \ + if ((v) <= apic_verbosity) \ + printk(s, ##a); \ +} while (0) + +#define apic_pr_verbose(s, a...) apic_printk(APIC_VERBOSE, KERN_INFO s, ##a) +#define apic_pr_debug(s, a...) apic_printk(APIC_DEBUG, KERN_DEBUG s, ##a) +#define apic_pr_debug_cont(s, a...) apic_printk(APIC_DEBUG, KERN_CONT s, ##a) +/* Unconditional debug prints for code which is guarded by apic_verbosity already */ +#define apic_dbg(s, a...) printk(KERN_DEBUG s, ##a) #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) extern void x86_32_probe_apic(void); @@ -122,8 +127,6 @@ static inline bool apic_is_x2apic_enabled(void) extern void enable_IR_x2apic(void); -extern int get_physical_broadcast(void); - extern int lapic_get_maxlvt(void); extern void clear_local_APIC(void); extern void disconnect_bsp_APIC(int virt_wire_setup); @@ -345,20 +348,12 @@ extern struct apic *apic; * APIC drivers are probed based on how they are listed in the .apicdrivers * section. So the order is important and enforced by the ordering * of different apic driver files in the Makefile. - * - * For the files having two apic drivers, we use apic_drivers() - * to enforce the order with in them. */ #define apic_driver(sym) \ static const struct apic *__apicdrivers_##sym __used \ __aligned(sizeof(struct apic *)) \ __section(".apicdrivers") = { &sym } -#define apic_drivers(sym1, sym2) \ - static struct apic *__apicdrivers_##sym1##sym2[2] __used \ - __aligned(sizeof(struct apic *)) \ - __section(".apicdrivers") = { &sym1, &sym2 } - extern struct apic *__apicdrivers[], *__apicdrivers_end[]; /* @@ -484,7 +479,6 @@ static inline u64 apic_icr_read(void) { return 0; } static inline void apic_icr_write(u32 low, u32 high) { } static inline void apic_wait_icr_idle(void) { } static inline u32 safe_apic_wait_icr_idle(void) { return 0; } -static inline void apic_set_eoi_cb(void (*eoi)(void)) {} static inline void apic_native_eoi(void) { WARN_ON_ONCE(1); } static inline void apic_setup_apic_calls(void) { } @@ -512,8 +506,6 @@ static inline bool is_vector_pending(unsigned int vector) #define TRAMPOLINE_PHYS_LOW 0x467 #define TRAMPOLINE_PHYS_HIGH 0x469 -extern void generic_bigsmp_probe(void); - #ifdef CONFIG_X86_LOCAL_APIC #include <asm/smp.h> @@ -536,8 +528,6 @@ static inline int default_acpi_madt_oem_check(char *a, char *b) { return 0; } static inline void x86_64_probe_apic(void) { } #endif -extern int default_apic_id_valid(u32 apicid); - extern u32 apic_default_calc_apicid(unsigned int cpu); extern u32 apic_flat_calc_apicid(unsigned int cpu); diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 8db2ec4d6cda..1f650b4dde50 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -163,20 +163,18 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) } #define arch_atomic64_dec_return arch_atomic64_dec_return -static __always_inline s64 arch_atomic64_add(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) { __alternative_atomic64(add, add_return, ASM_OUTPUT2("+A" (i), "+c" (v)), ASM_NO_INPUT_CLOBBER("memory")); - return i; } -static __always_inline s64 arch_atomic64_sub(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v) { __alternative_atomic64(sub, sub_return, ASM_OUTPUT2("+A" (i), "+c" (v)), ASM_NO_INPUT_CLOBBER("memory")); - return i; } static __always_inline void arch_atomic64_inc(atomic64_t *v) diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index a3ec87d198ac..806649c7f23d 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -13,6 +13,18 @@ #define INSN_UD2 0x0b0f #define LEN_UD2 2 +/* + * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit. + */ +#define INSN_ASOP 0x67 +#define OPCODE_ESCAPE 0x0f +#define SECOND_BYTE_OPCODE_UD1 0xb9 +#define SECOND_BYTE_OPCODE_UD2 0x0b + +#define BUG_NONE 0xffff +#define BUG_UD1 0xfffe +#define BUG_UD2 0xfffd + #ifdef CONFIG_GENERIC_BUG #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index 3831f612e89c..e4121d9aa9e1 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -193,26 +193,6 @@ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, X86_MODEL_ANY, data) /** - * X86_MATCH_INTEL_FAM6_MODEL - Match vendor INTEL, family 6 and model - * @model: The model name without the INTEL_FAM6_ prefix or ANY - * The model name is expanded to INTEL_FAM6_@model internally - * @data: Driver specific data or NULL. The internal storage - * format is unsigned long. The supplied value, pointer - * etc. is casted to unsigned long internally. - * - * The vendor is set to INTEL, the family to 6 and all other missing - * arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are set to wildcards. - * - * See X86_MATCH_VENDOR_FAM_MODEL_FEATURE() for further information. - */ -#define X86_MATCH_INTEL_FAM6_MODEL(model, data) \ - X86_MATCH_VENDOR_FAM_MODEL(INTEL, 6, INTEL_FAM6_##model, data) - -#define X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(model, steppings, data) \ - X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \ - steppings, X86_FEATURE_ANY, data) - -/** * X86_MATCH_VFM - Match encoded vendor/family/model * @vfm: Encoded 8-bits each for vendor, family, model * @data: Driver specific data or NULL. The internal storage diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index aa21c105eef1..ca4243318aad 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -197,7 +197,12 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) for_each_possible_hypervisor_cpuid_base(base) { cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); - if (!memcmp(sig, signature, 12) && + /* + * This must not compile to "call memcmp" because it's called + * from PVH early boot code before instrumentation is set up + * and memcmp() itself may be instrumented. + */ + if (!__builtin_memcmp(sig, signature, 12) && (leaves == 0 || ((eax - base) >= leaves))) return base; } diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index fb2809b20b0a..77d20555e04d 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -8,6 +8,7 @@ #include <asm/nospec-branch.h> #include <asm/io_bitmap.h> #include <asm/fpu/api.h> +#include <asm/fred.h> /* Check that the stack and regs on entry from user mode are sane. */ static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) @@ -44,8 +45,7 @@ static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) } #define arch_enter_from_user_mode arch_enter_from_user_mode -static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, - unsigned long ti_work) +static inline void arch_exit_work(unsigned long ti_work) { if (ti_work & _TIF_USER_RETURN_NOTIFY) fire_user_return_notifiers(); @@ -56,6 +56,15 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, fpregs_assert_state_consistent(); if (unlikely(ti_work & _TIF_NEED_FPU_LOAD)) switch_fpu_return(); +} + +static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, + unsigned long ti_work) +{ + if (IS_ENABLED(CONFIG_X86_DEBUG_FPU) || unlikely(ti_work)) + arch_exit_work(ti_work); + + fred_update_rsp0(); #ifdef CONFIG_COMPAT /* diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h index eeed395c3177..a0e0c6b50155 100644 --- a/arch/x86/include/asm/extable.h +++ b/arch/x86/include/asm/extable.h @@ -37,7 +37,6 @@ struct pt_regs; extern int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr); -extern int fixup_bug(struct pt_regs *regs, int trapnr); extern int ex_get_fixup_type(unsigned long ip); extern void early_fixup_exception(struct pt_regs *regs, int trapnr); diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index 611fa41711af..eccc75bc9c4f 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -29,7 +29,7 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long fpu__get_fpstate_size(void); -extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); +extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size, u32 pkru); extern void fpu__clear_user_states(struct fpu *fpu); extern bool fpu__restore_sig(void __user *buf, int ia32_frame); diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h index e86c7ba32435..25ca00bd70e8 100644 --- a/arch/x86/include/asm/fred.h +++ b/arch/x86/include/asm/fred.h @@ -36,6 +36,7 @@ #ifdef CONFIG_X86_FRED #include <linux/kernel.h> +#include <linux/sched/task_stack.h> #include <asm/ptrace.h> @@ -84,13 +85,33 @@ static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int } void cpu_init_fred_exceptions(void); +void cpu_init_fred_rsps(void); void fred_complete_exception_setup(void); +DECLARE_PER_CPU(unsigned long, fred_rsp0); + +static __always_inline void fred_sync_rsp0(unsigned long rsp0) +{ + __this_cpu_write(fred_rsp0, rsp0); +} + +static __always_inline void fred_update_rsp0(void) +{ + unsigned long rsp0 = (unsigned long) task_stack_page(current) + THREAD_SIZE; + + if (cpu_feature_enabled(X86_FEATURE_FRED) && (__this_cpu_read(fred_rsp0) != rsp0)) { + wrmsrns(MSR_IA32_FRED_RSP0, rsp0); + __this_cpu_write(fred_rsp0, rsp0); + } +} #else /* CONFIG_X86_FRED */ static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; } static inline void cpu_init_fred_exceptions(void) { } +static inline void cpu_init_fred_rsps(void) { } static inline void fred_complete_exception_setup(void) { } -static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { } +static inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { } +static inline void fred_sync_rsp0(unsigned long rsp0) { } +static inline void fred_update_rsp0(void) { } #endif /* CONFIG_X86_FRED */ #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index c67fa6ad098a..6ffa8b75f4cd 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -69,7 +69,11 @@ extern u64 arch_irq_stat(void); #define local_softirq_pending_ref pcpu_hot.softirq_pending #if IS_ENABLED(CONFIG_KVM_INTEL) -static inline void kvm_set_cpu_l1tf_flush_l1d(void) +/* + * This function is called from noinstr interrupt contexts + * and must be inlined to not get instrumentation. + */ +static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1); } @@ -84,7 +88,7 @@ static __always_inline bool kvm_get_cpu_l1tf_flush_l1d(void) return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d); } #else /* !IS_ENABLED(CONFIG_KVM_INTEL) */ -static inline void kvm_set_cpu_l1tf_flush_l1d(void) { } +static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { } #endif /* IS_ENABLED(CONFIG_KVM_INTEL) */ #endif /* _ASM_X86_HARDIRQ_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index d4f24499b256..ad5c68f0509d 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -212,8 +212,8 @@ __visible noinstr void func(struct pt_regs *regs, \ irqentry_state_t state = irqentry_enter(regs); \ u32 vector = (u32)(u8)error_code; \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ run_irq_on_irqstack_cond(__##func, regs, vector); \ instrumentation_end(); \ irqentry_exit(regs, state); \ @@ -250,7 +250,6 @@ static void __##func(struct pt_regs *regs); \ \ static __always_inline void instr_##func(struct pt_regs *regs) \ { \ - kvm_set_cpu_l1tf_flush_l1d(); \ run_sysvec_on_irqstack_cond(__##func, regs); \ } \ \ @@ -258,6 +257,7 @@ __visible noinstr void func(struct pt_regs *regs) \ { \ irqentry_state_t state = irqentry_enter(regs); \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ instr_##func (regs); \ instrumentation_end(); \ @@ -288,7 +288,6 @@ static __always_inline void __##func(struct pt_regs *regs); \ static __always_inline void instr_##func(struct pt_regs *regs) \ { \ __irq_enter_raw(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ __##func (regs); \ __irq_exit_raw(); \ } \ @@ -297,6 +296,7 @@ __visible noinstr void func(struct pt_regs *regs) \ { \ irqentry_state_t state = irqentry_enter(regs); \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ instr_##func (regs); \ instrumentation_end(); \ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index f81a851c46dc..1a42f829667a 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -10,7 +10,7 @@ * that group keep the CPUID for the variants sorted by model number. * * The defined symbol names have the following form: - * INTEL_FAM6{OPTFAMILY}_{MICROARCH}{OPTDIFF} + * INTEL_{OPTFAMILY}_{MICROARCH}{OPTDIFF} * where: * OPTFAMILY Describes the family of CPUs that this belongs to. Default * is assumed to be "_CORE" (and should be omitted). Other values @@ -42,219 +42,145 @@ #define IFM(_fam, _model) VFM_MAKE(X86_VENDOR_INTEL, _fam, _model) -/* Wildcard match for FAM6 so X86_MATCH_INTEL_FAM6_MODEL(ANY) works */ -#define INTEL_FAM6_ANY X86_MODEL_ANY -/* Wildcard match for FAM6 so X86_MATCH_VFM(ANY) works */ +/* Wildcard match so X86_MATCH_VFM(ANY) works */ #define INTEL_ANY IFM(X86_FAMILY_ANY, X86_MODEL_ANY) -#define INTEL_FAM6_CORE_YONAH 0x0E +#define INTEL_PENTIUM_PRO IFM(6, 0x01) + #define INTEL_CORE_YONAH IFM(6, 0x0E) -#define INTEL_FAM6_CORE2_MEROM 0x0F #define INTEL_CORE2_MEROM IFM(6, 0x0F) -#define INTEL_FAM6_CORE2_MEROM_L 0x16 #define INTEL_CORE2_MEROM_L IFM(6, 0x16) -#define INTEL_FAM6_CORE2_PENRYN 0x17 #define INTEL_CORE2_PENRYN IFM(6, 0x17) -#define INTEL_FAM6_CORE2_DUNNINGTON 0x1D #define INTEL_CORE2_DUNNINGTON IFM(6, 0x1D) -#define INTEL_FAM6_NEHALEM 0x1E #define INTEL_NEHALEM IFM(6, 0x1E) -#define INTEL_FAM6_NEHALEM_G 0x1F /* Auburndale / Havendale */ #define INTEL_NEHALEM_G IFM(6, 0x1F) /* Auburndale / Havendale */ -#define INTEL_FAM6_NEHALEM_EP 0x1A #define INTEL_NEHALEM_EP IFM(6, 0x1A) -#define INTEL_FAM6_NEHALEM_EX 0x2E #define INTEL_NEHALEM_EX IFM(6, 0x2E) -#define INTEL_FAM6_WESTMERE 0x25 #define INTEL_WESTMERE IFM(6, 0x25) -#define INTEL_FAM6_WESTMERE_EP 0x2C #define INTEL_WESTMERE_EP IFM(6, 0x2C) -#define INTEL_FAM6_WESTMERE_EX 0x2F #define INTEL_WESTMERE_EX IFM(6, 0x2F) -#define INTEL_FAM6_SANDYBRIDGE 0x2A #define INTEL_SANDYBRIDGE IFM(6, 0x2A) -#define INTEL_FAM6_SANDYBRIDGE_X 0x2D #define INTEL_SANDYBRIDGE_X IFM(6, 0x2D) -#define INTEL_FAM6_IVYBRIDGE 0x3A #define INTEL_IVYBRIDGE IFM(6, 0x3A) -#define INTEL_FAM6_IVYBRIDGE_X 0x3E #define INTEL_IVYBRIDGE_X IFM(6, 0x3E) -#define INTEL_FAM6_HASWELL 0x3C #define INTEL_HASWELL IFM(6, 0x3C) -#define INTEL_FAM6_HASWELL_X 0x3F #define INTEL_HASWELL_X IFM(6, 0x3F) -#define INTEL_FAM6_HASWELL_L 0x45 #define INTEL_HASWELL_L IFM(6, 0x45) -#define INTEL_FAM6_HASWELL_G 0x46 #define INTEL_HASWELL_G IFM(6, 0x46) -#define INTEL_FAM6_BROADWELL 0x3D #define INTEL_BROADWELL IFM(6, 0x3D) -#define INTEL_FAM6_BROADWELL_G 0x47 #define INTEL_BROADWELL_G IFM(6, 0x47) -#define INTEL_FAM6_BROADWELL_X 0x4F #define INTEL_BROADWELL_X IFM(6, 0x4F) -#define INTEL_FAM6_BROADWELL_D 0x56 #define INTEL_BROADWELL_D IFM(6, 0x56) -#define INTEL_FAM6_SKYLAKE_L 0x4E /* Sky Lake */ #define INTEL_SKYLAKE_L IFM(6, 0x4E) /* Sky Lake */ -#define INTEL_FAM6_SKYLAKE 0x5E /* Sky Lake */ #define INTEL_SKYLAKE IFM(6, 0x5E) /* Sky Lake */ -#define INTEL_FAM6_SKYLAKE_X 0x55 /* Sky Lake */ #define INTEL_SKYLAKE_X IFM(6, 0x55) /* Sky Lake */ /* CASCADELAKE_X 0x55 Sky Lake -- s: 7 */ /* COOPERLAKE_X 0x55 Sky Lake -- s: 11 */ -#define INTEL_FAM6_KABYLAKE_L 0x8E /* Sky Lake */ #define INTEL_KABYLAKE_L IFM(6, 0x8E) /* Sky Lake */ /* AMBERLAKE_L 0x8E Sky Lake -- s: 9 */ /* COFFEELAKE_L 0x8E Sky Lake -- s: 10 */ /* WHISKEYLAKE_L 0x8E Sky Lake -- s: 11,12 */ -#define INTEL_FAM6_KABYLAKE 0x9E /* Sky Lake */ #define INTEL_KABYLAKE IFM(6, 0x9E) /* Sky Lake */ /* COFFEELAKE 0x9E Sky Lake -- s: 10-13 */ -#define INTEL_FAM6_COMETLAKE 0xA5 /* Sky Lake */ #define INTEL_COMETLAKE IFM(6, 0xA5) /* Sky Lake */ -#define INTEL_FAM6_COMETLAKE_L 0xA6 /* Sky Lake */ #define INTEL_COMETLAKE_L IFM(6, 0xA6) /* Sky Lake */ -#define INTEL_FAM6_CANNONLAKE_L 0x66 /* Palm Cove */ #define INTEL_CANNONLAKE_L IFM(6, 0x66) /* Palm Cove */ -#define INTEL_FAM6_ICELAKE_X 0x6A /* Sunny Cove */ #define INTEL_ICELAKE_X IFM(6, 0x6A) /* Sunny Cove */ -#define INTEL_FAM6_ICELAKE_D 0x6C /* Sunny Cove */ #define INTEL_ICELAKE_D IFM(6, 0x6C) /* Sunny Cove */ -#define INTEL_FAM6_ICELAKE 0x7D /* Sunny Cove */ #define INTEL_ICELAKE IFM(6, 0x7D) /* Sunny Cove */ -#define INTEL_FAM6_ICELAKE_L 0x7E /* Sunny Cove */ #define INTEL_ICELAKE_L IFM(6, 0x7E) /* Sunny Cove */ -#define INTEL_FAM6_ICELAKE_NNPI 0x9D /* Sunny Cove */ #define INTEL_ICELAKE_NNPI IFM(6, 0x9D) /* Sunny Cove */ -#define INTEL_FAM6_ROCKETLAKE 0xA7 /* Cypress Cove */ #define INTEL_ROCKETLAKE IFM(6, 0xA7) /* Cypress Cove */ -#define INTEL_FAM6_TIGERLAKE_L 0x8C /* Willow Cove */ #define INTEL_TIGERLAKE_L IFM(6, 0x8C) /* Willow Cove */ -#define INTEL_FAM6_TIGERLAKE 0x8D /* Willow Cove */ #define INTEL_TIGERLAKE IFM(6, 0x8D) /* Willow Cove */ -#define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */ #define INTEL_SAPPHIRERAPIDS_X IFM(6, 0x8F) /* Golden Cove */ -#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF #define INTEL_EMERALDRAPIDS_X IFM(6, 0xCF) -#define INTEL_FAM6_GRANITERAPIDS_X 0xAD #define INTEL_GRANITERAPIDS_X IFM(6, 0xAD) -#define INTEL_FAM6_GRANITERAPIDS_D 0xAE #define INTEL_GRANITERAPIDS_D IFM(6, 0xAE) /* "Hybrid" Processors (P-Core/E-Core) */ -#define INTEL_FAM6_LAKEFIELD 0x8A /* Sunny Cove / Tremont */ #define INTEL_LAKEFIELD IFM(6, 0x8A) /* Sunny Cove / Tremont */ -#define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_ALDERLAKE IFM(6, 0x97) /* Golden Cove / Gracemont */ -#define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ #define INTEL_ALDERLAKE_L IFM(6, 0x9A) /* Golden Cove / Gracemont */ -#define INTEL_FAM6_RAPTORLAKE 0xB7 /* Raptor Cove / Enhanced Gracemont */ #define INTEL_RAPTORLAKE IFM(6, 0xB7) /* Raptor Cove / Enhanced Gracemont */ -#define INTEL_FAM6_RAPTORLAKE_P 0xBA #define INTEL_RAPTORLAKE_P IFM(6, 0xBA) -#define INTEL_FAM6_RAPTORLAKE_S 0xBF #define INTEL_RAPTORLAKE_S IFM(6, 0xBF) -#define INTEL_FAM6_METEORLAKE 0xAC #define INTEL_METEORLAKE IFM(6, 0xAC) -#define INTEL_FAM6_METEORLAKE_L 0xAA #define INTEL_METEORLAKE_L IFM(6, 0xAA) -#define INTEL_FAM6_ARROWLAKE_H 0xC5 #define INTEL_ARROWLAKE_H IFM(6, 0xC5) -#define INTEL_FAM6_ARROWLAKE 0xC6 #define INTEL_ARROWLAKE IFM(6, 0xC6) -#define INTEL_FAM6_ARROWLAKE_U 0xB5 #define INTEL_ARROWLAKE_U IFM(6, 0xB5) -#define INTEL_FAM6_LUNARLAKE_M 0xBD #define INTEL_LUNARLAKE_M IFM(6, 0xBD) +#define INTEL_PANTHERLAKE_L IFM(6, 0xCC) + /* "Small Core" Processors (Atom/E-Core) */ -#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ #define INTEL_ATOM_BONNELL IFM(6, 0x1C) /* Diamondville, Pineview */ -#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */ #define INTEL_ATOM_BONNELL_MID IFM(6, 0x26) /* Silverthorne, Lincroft */ -#define INTEL_FAM6_ATOM_SALTWELL 0x36 /* Cedarview */ #define INTEL_ATOM_SALTWELL IFM(6, 0x36) /* Cedarview */ -#define INTEL_FAM6_ATOM_SALTWELL_MID 0x27 /* Penwell */ #define INTEL_ATOM_SALTWELL_MID IFM(6, 0x27) /* Penwell */ -#define INTEL_FAM6_ATOM_SALTWELL_TABLET 0x35 /* Cloverview */ #define INTEL_ATOM_SALTWELL_TABLET IFM(6, 0x35) /* Cloverview */ -#define INTEL_FAM6_ATOM_SILVERMONT 0x37 /* Bay Trail, Valleyview */ #define INTEL_ATOM_SILVERMONT IFM(6, 0x37) /* Bay Trail, Valleyview */ -#define INTEL_FAM6_ATOM_SILVERMONT_D 0x4D /* Avaton, Rangely */ #define INTEL_ATOM_SILVERMONT_D IFM(6, 0x4D) /* Avaton, Rangely */ -#define INTEL_FAM6_ATOM_SILVERMONT_MID 0x4A /* Merriefield */ #define INTEL_ATOM_SILVERMONT_MID IFM(6, 0x4A) /* Merriefield */ -#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* Cherry Trail, Braswell */ #define INTEL_ATOM_AIRMONT IFM(6, 0x4C) /* Cherry Trail, Braswell */ -#define INTEL_FAM6_ATOM_AIRMONT_MID 0x5A /* Moorefield */ #define INTEL_ATOM_AIRMONT_MID IFM(6, 0x5A) /* Moorefield */ -#define INTEL_FAM6_ATOM_AIRMONT_NP 0x75 /* Lightning Mountain */ #define INTEL_ATOM_AIRMONT_NP IFM(6, 0x75) /* Lightning Mountain */ -#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */ #define INTEL_ATOM_GOLDMONT IFM(6, 0x5C) /* Apollo Lake */ -#define INTEL_FAM6_ATOM_GOLDMONT_D 0x5F /* Denverton */ #define INTEL_ATOM_GOLDMONT_D IFM(6, 0x5F) /* Denverton */ /* Note: the micro-architecture is "Goldmont Plus" */ -#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */ #define INTEL_ATOM_GOLDMONT_PLUS IFM(6, 0x7A) /* Gemini Lake */ -#define INTEL_FAM6_ATOM_TREMONT_D 0x86 /* Jacobsville */ #define INTEL_ATOM_TREMONT_D IFM(6, 0x86) /* Jacobsville */ -#define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */ #define INTEL_ATOM_TREMONT IFM(6, 0x96) /* Elkhart Lake */ -#define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */ #define INTEL_ATOM_TREMONT_L IFM(6, 0x9C) /* Jasper Lake */ -#define INTEL_FAM6_ATOM_GRACEMONT 0xBE /* Alderlake N */ #define INTEL_ATOM_GRACEMONT IFM(6, 0xBE) /* Alderlake N */ -#define INTEL_FAM6_ATOM_CRESTMONT_X 0xAF /* Sierra Forest */ #define INTEL_ATOM_CRESTMONT_X IFM(6, 0xAF) /* Sierra Forest */ -#define INTEL_FAM6_ATOM_CRESTMONT 0xB6 /* Grand Ridge */ #define INTEL_ATOM_CRESTMONT IFM(6, 0xB6) /* Grand Ridge */ -#define INTEL_FAM6_ATOM_DARKMONT_X 0xDD /* Clearwater Forest */ #define INTEL_ATOM_DARKMONT_X IFM(6, 0xDD) /* Clearwater Forest */ /* Xeon Phi */ -#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ #define INTEL_XEON_PHI_KNL IFM(6, 0x57) /* Knights Landing */ -#define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */ #define INTEL_XEON_PHI_KNM IFM(6, 0x85) /* Knights Mill */ /* Family 5 */ #define INTEL_FAM5_QUARK_X1000 0x09 /* Quark X1000 SoC */ #define INTEL_QUARK_X1000 IFM(5, 0x09) /* Quark X1000 SoC */ +/* Family 19 */ +#define INTEL_PANTHERCOVE_X IFM(19, 0x01) /* Diamond Rapids */ + #endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h deleted file mode 100644 index 8537f597d20a..000000000000 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_INTEL_SCU_IPC_H_ -#define _ASM_X86_INTEL_SCU_IPC_H_ - -#include <linux/ioport.h> - -struct device; -struct intel_scu_ipc_dev; - -/** - * struct intel_scu_ipc_data - Data used to configure SCU IPC - * @mem: Base address of SCU IPC MMIO registers - * @irq: The IRQ number used for SCU (optional) - */ -struct intel_scu_ipc_data { - struct resource mem; - int irq; -}; - -struct intel_scu_ipc_dev * -__intel_scu_ipc_register(struct device *parent, - const struct intel_scu_ipc_data *scu_data, - struct module *owner); - -#define intel_scu_ipc_register(parent, scu_data) \ - __intel_scu_ipc_register(parent, scu_data, THIS_MODULE) - -void intel_scu_ipc_unregister(struct intel_scu_ipc_dev *scu); - -struct intel_scu_ipc_dev * -__devm_intel_scu_ipc_register(struct device *parent, - const struct intel_scu_ipc_data *scu_data, - struct module *owner); - -#define devm_intel_scu_ipc_register(parent, scu_data) \ - __devm_intel_scu_ipc_register(parent, scu_data, THIS_MODULE) - -struct intel_scu_ipc_dev *intel_scu_ipc_dev_get(void); -void intel_scu_ipc_dev_put(struct intel_scu_ipc_dev *scu); -struct intel_scu_ipc_dev *devm_intel_scu_ipc_dev_get(struct device *dev); - -int intel_scu_ipc_dev_ioread8(struct intel_scu_ipc_dev *scu, u16 addr, - u8 *data); -int intel_scu_ipc_dev_iowrite8(struct intel_scu_ipc_dev *scu, u16 addr, - u8 data); -int intel_scu_ipc_dev_readv(struct intel_scu_ipc_dev *scu, u16 *addr, - u8 *data, size_t len); -int intel_scu_ipc_dev_writev(struct intel_scu_ipc_dev *scu, u16 *addr, - u8 *data, size_t len); - -int intel_scu_ipc_dev_update(struct intel_scu_ipc_dev *scu, u16 addr, - u8 data, u8 mask); - -int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, - int sub); -int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd, - int sub, const void *in, size_t inlen, - size_t size, void *out, size_t outlen); - -static inline int intel_scu_ipc_dev_command(struct intel_scu_ipc_dev *scu, int cmd, - int sub, const void *in, size_t inlen, - void *out, size_t outlen) -{ - return intel_scu_ipc_dev_command_with_size(scu, cmd, sub, in, inlen, - inlen, out, outlen); -} - -#endif diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h index 8046e70dfd7c..43b7657febca 100644 --- a/arch/x86/include/asm/intel_telemetry.h +++ b/arch/x86/include/asm/intel_telemetry.h @@ -10,7 +10,7 @@ #define TELEM_MAX_EVENTS_SRAM 28 #define TELEM_MAX_OS_ALLOCATED_EVENTS 20 -#include <asm/intel_scu_ipc.h> +#include <linux/platform_data/x86/intel_scu_ipc.h> enum telemetry_unit { TELEM_PSS = 0, diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 13aea8fc3d45..47051871b436 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -18,8 +18,8 @@ * Vectors 0 ... 31 : system traps and exceptions - hardcoded events * Vectors 32 ... 127 : device interrupts * Vector 128 : legacy int80 syscall interface - * Vectors 129 ... LOCAL_TIMER_VECTOR-1 - * Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts + * Vectors 129 ... FIRST_SYSTEM_VECTOR-1 : device interrupts + * Vectors FIRST_SYSTEM_VECTOR ... 255 : special interrupts * * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table. * diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 3ad29b128943..3b9970117a0f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -221,7 +221,7 @@ static inline int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) { return -EINVAL; } #endif -void mce_setup(struct mce *m); +void mce_prep_record(struct mce *m); void mce_log(struct mce *m); DECLARE_PER_CPU(struct device *, mce_device); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 8dac45a2c7fc..2886cb668d7f 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -88,7 +88,13 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) #ifdef CONFIG_ADDRESS_MASKING static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) { - return mm->context.lam_cr3_mask; + /* + * When switch_mm_irqs_off() is called for a kthread, it may race with + * LAM enablement. switch_mm_irqs_off() uses the LAM mask to do two + * things: populate CR3 and populate 'cpu_tlbstate.lam'. Make sure it + * reads a single value for both. + */ + return READ_ONCE(mm->context.lam_cr3_mask); } static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) @@ -232,11 +238,6 @@ static inline bool is_64bit_mm(struct mm_struct *mm) } #endif -static inline void arch_unmap(struct mm_struct *mm, unsigned long start, - unsigned long end) -{ -} - /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other diff --git a/arch/x86/include/asm/mmzone.h b/arch/x86/include/asm/mmzone.h deleted file mode 100644 index c41b41edd691..000000000000 --- a/arch/x86/include/asm/mmzone.h +++ /dev/null @@ -1,6 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifdef CONFIG_X86_32 -# include <asm/mmzone_32.h> -#else -# include <asm/mmzone_64.h> -#endif diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h deleted file mode 100644 index 2d4515e8b7df..000000000000 --- a/arch/x86/include/asm/mmzone_32.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Written by Pat Gaughen (gone@us.ibm.com) Mar 2002 - * - */ - -#ifndef _ASM_X86_MMZONE_32_H -#define _ASM_X86_MMZONE_32_H - -#include <asm/smp.h> - -#ifdef CONFIG_NUMA -extern struct pglist_data *node_data[]; -#define NODE_DATA(nid) (node_data[nid]) -#endif /* CONFIG_NUMA */ - -#endif /* _ASM_X86_MMZONE_32_H */ diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h deleted file mode 100644 index 0c585046f744..000000000000 --- a/arch/x86/include/asm/mmzone_64.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* K8 NUMA support */ -/* Copyright 2002,2003 by Andi Kleen, SuSE Labs */ -/* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */ -#ifndef _ASM_X86_MMZONE_64_H -#define _ASM_X86_MMZONE_64_H - -#ifdef CONFIG_NUMA - -#include <linux/mmdebug.h> -#include <asm/smp.h> - -extern struct pglist_data *node_data[]; - -#define NODE_DATA(nid) (node_data[nid]) - -#endif -#endif /* _ASM_X86_MMZONE_64_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 390c4d13956d..5f0bc6a6d025 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -40,7 +40,6 @@ static inline unsigned char hv_get_nmi_reason(void) } #if IS_ENABLED(CONFIG_HYPERV) -extern int hyperv_init_cpuhp; extern bool hyperv_paravisor_present; extern void *hv_hypercall_pg; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 72c2c0ecb62c..3ae84c3b8e6d 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -261,6 +261,8 @@ #define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) +#define MSR_INTEGRITY_CAPS_SBAF_BIT 8 +#define MSR_INTEGRITY_CAPS_SBAF BIT(MSR_INTEGRITY_CAPS_SBAF_BIT) #define MSR_INTEGRITY_CAPS_SAF_GEN_MASK GENMASK_ULL(10, 9) #define MSR_LBR_NHM_FROM 0x00000680 diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index d642037f9ed5..001853541f1e 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -99,19 +99,6 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) : : "c" (msr), "a"(low), "d" (high) : "memory"); } -/* - * WRMSRNS behaves exactly like WRMSR with the only difference being - * that it is not a serializing instruction by default. - */ -static __always_inline void __wrmsrns(u32 msr, u32 low, u32 high) -{ - /* Instruction opcode for WRMSRNS; supported in binutils >= 2.40. */ - asm volatile("1: .byte 0x0f,0x01,0xc6\n" - "2:\n" - _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) - : : "c" (msr), "a"(low), "d" (high)); -} - #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = __rdmsr((msr)); \ @@ -312,9 +299,19 @@ do { \ #endif /* !CONFIG_PARAVIRT_XXL */ +/* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */ +#define WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6) + +/* Non-serializing WRMSR, when available. Falls back to a serializing WRMSR. */ static __always_inline void wrmsrns(u32 msr, u64 val) { - __wrmsrns(msr, val, val >> 32); + /* + * WRMSR is 2 bytes. WRMSRNS is 3 bytes. Pad WRMSR with a redundant + * DS prefix to avoid a trailing NOP. + */ + asm volatile("1: " ALTERNATIVE("ds wrmsr", WRMSRNS, X86_FEATURE_WRMSRNS) + "2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) + : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32))); } /* diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 090d658a85a6..4218248083d9 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -69,7 +69,6 @@ extern int mtrr_add_page(unsigned long base, unsigned long size, unsigned int type, bool increment); extern int mtrr_del(int reg, unsigned long base, unsigned long size); extern int mtrr_del_page(int reg, unsigned long base, unsigned long size); -extern void mtrr_bp_restore(void); extern int mtrr_trim_uncached_memory(unsigned long end_pfn); extern int amd_special_default_mtrr(void); void mtrr_disable(void); @@ -117,7 +116,6 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) return 0; } #define mtrr_bp_init() do {} while (0) -#define mtrr_bp_restore() do {} while (0) #define mtrr_disable() do {} while (0) #define mtrr_enable() do {} while (0) #define mtrr_generic_set_state() do {} while (0) diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index ef2844d69173..5469d7a7c40f 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -10,8 +10,6 @@ #ifdef CONFIG_NUMA -#define NR_NODE_MEMBLKS (MAX_NUMNODES*2) - extern int numa_off; /* @@ -25,9 +23,6 @@ extern int numa_off; extern s16 __apicid_to_node[MAX_LOCAL_APIC]; extern nodemask_t numa_nodes_parsed __initdata; -extern int __init numa_add_memblk(int nodeid, u64 start, u64 end); -extern void __init numa_set_distance(int from, int to, int distance); - static inline void set_apicid_to_node(int apicid, s16 node) { __apicid_to_node[apicid] = node; @@ -54,31 +49,20 @@ static inline int numa_cpu_node(int cpu) extern void numa_set_node(int cpu, int node); extern void numa_clear_node(int cpu); extern void __init init_cpu_to_node(void); -extern void numa_add_cpu(int cpu); -extern void numa_remove_cpu(int cpu); +extern void numa_add_cpu(unsigned int cpu); +extern void numa_remove_cpu(unsigned int cpu); extern void init_gi_nodes(void); #else /* CONFIG_NUMA */ static inline void numa_set_node(int cpu, int node) { } static inline void numa_clear_node(int cpu) { } static inline void init_cpu_to_node(void) { } -static inline void numa_add_cpu(int cpu) { } -static inline void numa_remove_cpu(int cpu) { } +static inline void numa_add_cpu(unsigned int cpu) { } +static inline void numa_remove_cpu(unsigned int cpu) { } static inline void init_gi_nodes(void) { } #endif /* CONFIG_NUMA */ #ifdef CONFIG_DEBUG_PER_CPU_MAPS -void debug_cpumask_set_cpu(int cpu, int node, bool enable); +void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable); #endif -#ifdef CONFIG_NUMA_EMU -#define FAKE_NODE_MIN_SIZE ((u64)32 << 20) -#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) -int numa_emu_cmdline(char *str); -#else /* CONFIG_NUMA_EMU */ -static inline int numa_emu_cmdline(char *str) -{ - return -EINVAL; -} -#endif /* CONFIG_NUMA_EMU */ - #endif /* _ASM_X86_NUMA_H */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e39311a89bf4..4c2d080d26b4 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -120,6 +120,34 @@ extern pmdval_t early_pmd_flags; #define arch_end_context_switch(prev) do {} while(0) #endif /* CONFIG_PARAVIRT_XXL */ +static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) +{ + pmdval_t v = native_pmd_val(pmd); + + return native_make_pmd(v | set); +} + +static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) +{ + pmdval_t v = native_pmd_val(pmd); + + return native_make_pmd(v & ~clear); +} + +static inline pud_t pud_set_flags(pud_t pud, pudval_t set) +{ + pudval_t v = native_pud_val(pud); + + return native_make_pud(v | set); +} + +static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) +{ + pudval_t v = native_pud_val(pud); + + return native_make_pud(v & ~clear); +} + /* * The following only work if pte_present() is true. * Undefined behaviour if not.. @@ -174,6 +202,13 @@ static inline int pud_young(pud_t pud) return pud_flags(pud) & _PAGE_ACCESSED; } +static inline bool pud_shstk(pud_t pud) +{ + return cpu_feature_enabled(X86_FEATURE_SHSTK) && + (pud_flags(pud) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == + (_PAGE_DIRTY | _PAGE_PSE); +} + static inline int pte_write(pte_t pte) { /* @@ -310,6 +345,30 @@ static inline int pud_devmap(pud_t pud) } #endif +#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP +static inline bool pmd_special(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_SPECIAL; +} + +static inline pmd_t pmd_mkspecial(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_SPECIAL); +} +#endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ + +#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP +static inline bool pud_special(pud_t pud) +{ + return pud_flags(pud) & _PAGE_SPECIAL; +} + +static inline pud_t pud_mkspecial(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_SPECIAL); +} +#endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ + static inline int pgd_devmap(pgd_t pgd) { return 0; @@ -480,20 +539,6 @@ static inline pte_t pte_mkdevmap(pte_t pte) return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); } -static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) -{ - pmdval_t v = native_pmd_val(pmd); - - return native_make_pmd(v | set); -} - -static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) -{ - pmdval_t v = native_pmd_val(pmd); - - return native_make_pmd(v & ~clear); -} - /* See comments above mksaveddirty_shift() */ static inline pmd_t pmd_mksaveddirty(pmd_t pmd) { @@ -588,20 +633,6 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); #define pmd_mkwrite pmd_mkwrite -static inline pud_t pud_set_flags(pud_t pud, pudval_t set) -{ - pudval_t v = native_pud_val(pud); - - return native_make_pud(v | set); -} - -static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) -{ - pudval_t v = native_pud_val(pud); - - return native_make_pud(v & ~clear); -} - /* See comments above mksaveddirty_shift() */ static inline pud_t pud_mksaveddirty(pud_t pud) { @@ -780,6 +811,12 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd) __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } +static inline pud_t pud_mkinvalid(pud_t pud) +{ + return pfn_pud(pud_pfn(pud), + __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); +} + static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) @@ -827,14 +864,8 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) pmd_result = __pmd(val); /* - * To avoid creating Write=0,Dirty=1 PMDs, pte_modify() needs to avoid: - * 1. Marking Write=0 PMDs Dirty=1 - * 2. Marking Dirty=1 PMDs Write=0 - * - * The first case cannot happen because the _PAGE_CHG_MASK will filter - * out any Dirty bit passed in newprot. Handle the second case by - * going through the mksaveddirty exercise. Only do this if the old - * value was Write=1 to avoid doing this on Shadow Stack PTEs. + * Avoid creating shadow stack PMD by accident. See comment in + * pte_modify(). */ if (oldval & _PAGE_RW) pmd_result = pmd_mksaveddirty(pmd_result); @@ -844,6 +875,29 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) return pmd_result; } +static inline pud_t pud_modify(pud_t pud, pgprot_t newprot) +{ + pudval_t val = pud_val(pud), oldval = val; + pud_t pud_result; + + val &= _HPAGE_CHG_MASK; + val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; + val = flip_protnone_guard(oldval, val, PHYSICAL_PUD_PAGE_MASK); + + pud_result = __pud(val); + + /* + * Avoid creating shadow stack PUD by accident. See comment in + * pte_modify(). + */ + if (oldval & _PAGE_RW) + pud_result = pud_mksaveddirty(pud_result); + else + pud_result = pud_clear_saveddirty(pud_result); + + return pud_result; +} + /* * mprotect needs to preserve PAT and encryption bits when updating * vm_page_prot @@ -1078,8 +1132,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) #define pud_leaf pud_leaf static inline bool pud_leaf(pud_t pud) { - return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) == - (_PAGE_PSE | _PAGE_PRESENT); + return pud_val(pud) & _PAGE_PSE; } static inline int pud_bad(pud_t pud) @@ -1383,10 +1436,28 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, } #endif +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline pud_t pudp_establish(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, pud_t pud) +{ + page_table_check_pud_set(vma->vm_mm, pudp, pud); + if (IS_ENABLED(CONFIG_SMP)) { + return xchg(pudp, pud); + } else { + pud_t old = *pudp; + WRITE_ONCE(*pudp, pud); + return old; + } +} +#endif + #define __HAVE_ARCH_PMDP_INVALIDATE_AD extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); +pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp); + /* * Page table pages are page-aligned. The lower half of the top * level is used for userspace and the top half for the kernel. @@ -1668,6 +1739,9 @@ void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); #define arch_check_zapped_pmd arch_check_zapped_pmd void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd); +#define arch_check_zapped_pud arch_check_zapped_pud +void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud); + #ifdef CONFIG_XEN_PV #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young static inline bool arch_has_hw_nonleaf_pmd_young(void) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 3c4407271d08..d1426b64c1b9 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -245,7 +245,6 @@ extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN -#define HAVE_ARCH_UNMAPPED_AREA_VMFLAGS #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 @@ -271,5 +270,26 @@ static inline bool gup_fast_permitted(unsigned long start, unsigned long end) #include <asm/pgtable-invert.h> -#endif /* !__ASSEMBLY__ */ +#else /* __ASSEMBLY__ */ + +#define l4_index(x) (((x) >> 39) & 511) +#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4) +L4_START_KERNEL = l4_index(__START_KERNEL_map) + +L3_START_KERNEL = pud_index(__START_KERNEL_map) + +#define SYM_DATA_START_PAGE_ALIGNED(name) \ + SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) + +/* Automate the creation of 1 to 1 mapping pmd entries */ +#define PMDS(START, PERM, COUNT) \ + i = 0 ; \ + .rept (COUNT) ; \ + .quad (START) + (i << PMD_SHIFT) + (PERM) ; \ + i = i + 1 ; \ + .endr + +#endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 2f321137736c..6f82e75b6149 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -517,8 +517,6 @@ typedef struct page *pgtable_t; extern pteval_t __supported_pte_mask; extern pteval_t __default_kernel_pte_mask; -extern void set_nx(void); -extern int nx_enabled; #define pgprot_writecombine pgprot_writecombine extern pgprot_t pgprot_writecombine(pgprot_t prot); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a75a07f4931f..4a686f0e5dbf 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -582,7 +582,8 @@ extern void switch_gdt_and_percpu_base(int); extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); extern void cpu_init(void); -extern void cpu_init_exception_handling(void); +extern void cpu_init_exception_handling(bool boot_cpu); +extern void cpu_init_replace_early_idt(void); extern void cr4_init(void); extern void set_task_blockstep(struct task_struct *task, bool on); @@ -691,8 +692,6 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu) } #ifdef CONFIG_CPU_SUP_AMD -extern u32 amd_get_highest_perf(void); - /* * Issue a DIV 0/1 insn to clear any division data from previous DIV * operations. @@ -705,7 +704,6 @@ static __always_inline void amd_clear_divider(void) extern void amd_check_microcode(void); #else -static inline u32 amd_get_highest_perf(void) { return 0; } static inline void amd_clear_divider(void) { } static inline void amd_check_microcode(void) { } #endif diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 0c92db84469d..6e4f8fae3ce9 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -5,6 +5,7 @@ #include <asm/clocksource.h> #include <asm/pvclock-abi.h> +struct timespec64; /* some helper functions for xen and kvm pv clock sources */ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); u64 pvclock_clocksource_read_nowd(struct pvclock_vcpu_time_info *src); diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 2d8525a51478..ecd58ea9a837 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -31,6 +31,8 @@ void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback); void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback); void cpu_emergency_disable_virtualization(void); #else +static inline void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback) {} +static inline void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback) {} static inline void cpu_emergency_disable_virtualization(void) {} #endif /* CONFIG_KVM_X86 */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 79bbe2be900e..ee34ab00a8d6 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -164,7 +164,7 @@ struct snp_guest_msg_hdr { struct snp_guest_msg { struct snp_guest_msg_hdr hdr; - u8 payload[4000]; + u8 payload[PAGE_SIZE - sizeof(struct snp_guest_msg_hdr)]; } __packed; struct sev_guest_platform_data { diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 64df897c0ee3..3918c7a434f5 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -31,13 +31,4 @@ #endif /* CONFIG_SPARSEMEM */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_NUMA_KEEP_MEMINFO -extern int phys_to_target_node(phys_addr_t start); -#define phys_to_target_node phys_to_target_node -extern int memory_add_physaddr_to_nid(u64 start); -#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid -#endif -#endif /* __ASSEMBLY__ */ - #endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index c3bd0c0758c9..75248546403d 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -70,13 +70,9 @@ static inline void update_task_stack(struct task_struct *task) #ifdef CONFIG_X86_32 this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); #else - if (cpu_feature_enabled(X86_FEATURE_FRED)) { - /* WRMSRNS is a baseline feature for FRED. */ - wrmsrns(MSR_IA32_FRED_RSP0, (unsigned long)task_stack_page(task) + THREAD_SIZE); - } else if (cpu_feature_enabled(X86_FEATURE_XENPV)) { + if (!cpu_feature_enabled(X86_FEATURE_FRED) && cpu_feature_enabled(X86_FEATURE_XENPV)) /* Xen PV enters the kernel on the thread stack. */ load_sp0(task_top_of_stack(task)); - } #endif } diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 2fc7bc3863ff..7c488ff0c764 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -82,7 +82,12 @@ static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) { - memcpy(args, ®s->bx, 6 * sizeof(args[0])); + args[0] = regs->bx; + args[1] = regs->cx; + args[2] = regs->dx; + args[3] = regs->si; + args[4] = regs->di; + args[5] = regs->bp; } static inline int syscall_get_arch(struct task_struct *task) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 25726893c6f4..69e79fff41b8 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -399,11 +399,10 @@ static inline u64 tlbstate_lam_cr3_mask(void) return lam << X86_CR3_LAM_U57_BIT; } -static inline void set_tlbstate_lam_mode(struct mm_struct *mm) +static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask) { - this_cpu_write(cpu_tlbstate.lam, - mm->context.lam_cr3_mask >> X86_CR3_LAM_U57_BIT); - this_cpu_write(tlbstate_untag_mask, mm->context.untag_mask); + this_cpu_write(cpu_tlbstate.lam, lam >> X86_CR3_LAM_U57_BIT); + this_cpu_write(tlbstate_untag_mask, untag_mask); } #else @@ -413,7 +412,7 @@ static inline u64 tlbstate_lam_cr3_mask(void) return 0; } -static inline void set_tlbstate_lam_mode(struct mm_struct *mm) +static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask) { } #endif diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index abe3a8f22cbd..aef70336d624 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -282,9 +282,22 @@ static inline long arch_scale_freq_capacity(int cpu) } #define arch_scale_freq_capacity arch_scale_freq_capacity +bool arch_enable_hybrid_capacity_scale(void); +void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap, + unsigned long cap_freq, unsigned long base_freq); + +unsigned long arch_scale_cpu_capacity(int cpu); +#define arch_scale_cpu_capacity arch_scale_cpu_capacity + extern void arch_set_max_freq_ratio(bool turbo_disabled); extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled); #else +static inline bool arch_enable_hybrid_capacity_scale(void) { return false; } +static inline void arch_set_cpu_capacity(int cpu, unsigned long cap, + unsigned long max_cap, + unsigned long cap_freq, + unsigned long base_freq) { } + static inline void arch_set_max_freq_ratio(bool turbo_disabled) { } static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { } #endif diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 04789f45ab2b..afce8ee5d7b7 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -54,6 +54,17 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, #define valid_user_address(x) ((__force long)(x) >= 0) /* + * Masking the user address is an alternative to a conditional + * user_access_begin that can avoid the fencing. This only works + * for dense accesses starting at the address. + */ +#define mask_user_address(x) ((typeof(x))((long)(x)|((long)(x)>>63))) +#define masked_user_access_begin(x) ({ \ + __auto_type __masked_ptr = (x); \ + __masked_ptr = mask_user_address(__masked_ptr); \ + __uaccess_begin(); __masked_ptr; }) + +/* * User pointers can have tag bits on x86-64. This scheme tolerates * arbitrary values in those bits rather then masking them off. * diff --git a/arch/x86/include/asm/uv/uv_irq.h b/arch/x86/include/asm/uv/uv_irq.h index d6b17c760622..1876b5edd142 100644 --- a/arch/x86/include/asm/uv/uv_irq.h +++ b/arch/x86/include/asm/uv/uv_irq.h @@ -31,7 +31,6 @@ enum { UV_AFFINITY_CPU }; -extern int uv_irq_2_mmr_info(int, unsigned long *, int *); extern int uv_setup_irq(char *, int, int, unsigned long, int); extern void uv_teardown_irq(unsigned int); diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/vdso/getrandom.h index b96e674cafde..ff5334ad32a0 100644 --- a/arch/x86/include/asm/vdso/getrandom.h +++ b/arch/x86/include/asm/vdso/getrandom.h @@ -37,19 +37,6 @@ static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void return &__vdso_rng_data; } -/** - * __arch_chacha20_blocks_nostack - Generate ChaCha20 stream without using the stack. - * @dst_bytes: Destination buffer to hold @nblocks * 64 bytes of output. - * @key: 32-byte input key. - * @counter: 8-byte counter, read on input and updated on return. - * @nblocks: Number of blocks to generate. - * - * Generates a given positive number of blocks of ChaCha20 output with nonce=0, and does not write - * to any stack or memory outside of the parameters passed to it, in order to mitigate stack data - * leaking into forked child processes. - */ -extern void __arch_chacha20_blocks_nostack(u8 *dst_bytes, const u32 *key, u32 *counter, size_t nblocks); - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h index 972415a8be31..67fedf1698b5 100644 --- a/arch/x86/include/asm/vdso/vsyscall.h +++ b/arch/x86/include/asm/vdso/vsyscall.h @@ -9,9 +9,6 @@ #include <asm/vgtod.h> #include <asm/vvar.h> -DEFINE_VVAR(struct vdso_data, _vdso_data); -DEFINE_VVAR_SINGLE(struct vdso_rng_data, _vdso_rng_data); - /* * Update the vDSO data page to keep in sync with kernel timekeeping. */ @@ -22,6 +19,13 @@ struct vdso_data *__x86_get_k_vdso_data(void) } #define __arch_get_k_vdso_data __x86_get_k_vdso_data +static __always_inline +struct vdso_rng_data *__x86_get_k_vdso_rng_data(void) +{ + return &_vdso_rng_data; +} +#define __arch_get_k_vdso_rng_data __x86_get_k_vdso_rng_data + /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/x86/include/uapi/asm/elf.h b/arch/x86/include/uapi/asm/elf.h new file mode 100644 index 000000000000..468e135fa285 --- /dev/null +++ b/arch/x86/include/uapi/asm/elf.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_X86_ELF_H +#define _UAPI_ASM_X86_ELF_H + +#include <linux/types.h> + +struct x86_xfeat_component { + __u32 type; + __u32 size; + __u32 offset; + __u32 flags; +} __packed; + +_Static_assert(sizeof(struct x86_xfeat_component) % 4 == 0, "x86_xfeat_component is not aligned"); + +#endif /* _UAPI_ASM_X86_ELF_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a847180836e4..f7918980667a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -35,6 +35,14 @@ KMSAN_SANITIZE_nmi.o := n # If instrumentation of the following files is enabled, boot hangs during # first second. KCOV_INSTRUMENT_head$(BITS).o := n +# These are called from save_stack_trace() on debug paths, +# and produce large amounts of uninteresting coverage. +KCOV_INSTRUMENT_stacktrace.o := n +KCOV_INSTRUMENT_dumpstack.o := n +KCOV_INSTRUMENT_dumpstack_$(BITS).o := n +KCOV_INSTRUMENT_unwind_orc.o := n +KCOV_INSTRUMENT_unwind_frame.o := n +KCOV_INSTRUMENT_unwind_guess.o := n CFLAGS_irq.o := -I $(src)/../include/asm/trace diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 9f4618dcd704..4efecac49863 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1778,3 +1778,14 @@ u64 x86_default_get_root_pointer(void) { return boot_params.acpi_rsdp_addr; } + +#ifdef CONFIG_XEN_PV +void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +{ + return ioremap_cache(phys, size); +} + +void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, acpi_size size) = + x86_acpi_os_ioremap; +EXPORT_SYMBOL_GPL(acpi_os_ioremap); +#endif diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index ff8f25faca3d..956984054bf3 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -9,6 +9,17 @@ #include <asm/processor.h> #include <asm/topology.h> +#define CPPC_HIGHEST_PERF_PERFORMANCE 196 +#define CPPC_HIGHEST_PERF_PREFCORE 166 + +enum amd_pref_core { + AMD_PREF_CORE_UNKNOWN = 0, + AMD_PREF_CORE_SUPPORTED, + AMD_PREF_CORE_UNSUPPORTED, +}; +static enum amd_pref_core amd_pref_core_detected; +static u64 boost_numerator; + /* Refer to drivers/acpi/cppc_acpi.c for the description of functions */ bool cpc_supported_by_cpu(void) @@ -69,31 +80,30 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) static void amd_set_max_freq_ratio(void) { struct cppc_perf_caps perf_caps; - u64 highest_perf, nominal_perf; + u64 numerator, nominal_perf; u64 perf_ratio; int rc; rc = cppc_get_perf_caps(0, &perf_caps); if (rc) { - pr_debug("Could not retrieve perf counters (%d)\n", rc); + pr_warn("Could not retrieve perf counters (%d)\n", rc); return; } - highest_perf = amd_get_highest_perf(); + rc = amd_get_boost_ratio_numerator(0, &numerator); + if (rc) { + pr_warn("Could not retrieve highest performance (%d)\n", rc); + return; + } nominal_perf = perf_caps.nominal_perf; - if (!highest_perf || !nominal_perf) { - pr_debug("Could not retrieve highest or nominal performance\n"); + if (!nominal_perf) { + pr_warn("Could not retrieve nominal performance\n"); return; } - perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf); /* midpoint between max_boost and max_P */ - perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1; - if (!perf_ratio) { - pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n"); - return; - } + perf_ratio = (div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf) + SCHED_CAPACITY_SCALE) >> 1; freq_invariance_set_perf_ratio(perf_ratio, false); } @@ -116,3 +126,143 @@ void init_freq_invariance_cppc(void) init_done = true; mutex_unlock(&freq_invariance_lock); } + +/* + * Get the highest performance register value. + * @cpu: CPU from which to get highest performance. + * @highest_perf: Return address for highest performance value. + * + * Return: 0 for success, negative error code otherwise. + */ +int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf) +{ + u64 val; + int ret; + + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { + ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val); + if (ret) + goto out; + + val = AMD_CPPC_HIGHEST_PERF(val); + } else { + ret = cppc_get_highest_perf(cpu, &val); + if (ret) + goto out; + } + + WRITE_ONCE(*highest_perf, (u32)val); +out: + return ret; +} +EXPORT_SYMBOL_GPL(amd_get_highest_perf); + +/** + * amd_detect_prefcore: Detect if CPUs in the system support preferred cores + * @detected: Output variable for the result of the detection. + * + * Determine whether CPUs in the system support preferred cores. On systems + * that support preferred cores, different highest perf values will be found + * on different cores. On other systems, the highest perf value will be the + * same on all cores. + * + * The result of the detection will be stored in the 'detected' parameter. + * + * Return: 0 for success, negative error code otherwise + */ +int amd_detect_prefcore(bool *detected) +{ + int cpu, count = 0; + u64 highest_perf[2] = {0}; + + if (WARN_ON(!detected)) + return -EINVAL; + + switch (amd_pref_core_detected) { + case AMD_PREF_CORE_SUPPORTED: + *detected = true; + return 0; + case AMD_PREF_CORE_UNSUPPORTED: + *detected = false; + return 0; + default: + break; + } + + for_each_present_cpu(cpu) { + u32 tmp; + int ret; + + ret = amd_get_highest_perf(cpu, &tmp); + if (ret) + return ret; + + if (!count || (count == 1 && tmp != highest_perf[0])) + highest_perf[count++] = tmp; + + if (count == 2) + break; + } + + *detected = (count == 2); + boost_numerator = highest_perf[0]; + + amd_pref_core_detected = *detected ? AMD_PREF_CORE_SUPPORTED : + AMD_PREF_CORE_UNSUPPORTED; + + pr_debug("AMD CPPC preferred core is %ssupported (highest perf: 0x%llx)\n", + *detected ? "" : "un", highest_perf[0]); + + return 0; +} +EXPORT_SYMBOL_GPL(amd_detect_prefcore); + +/** + * amd_get_boost_ratio_numerator: Get the numerator to use for boost ratio calculation + * @cpu: CPU to get numerator for. + * @numerator: Output variable for numerator. + * + * Determine the numerator to use for calculating the boost ratio on + * a CPU. On systems that support preferred cores, this will be a hardcoded + * value. On other systems this will the highest performance register value. + * + * If booting the system with amd-pstate enabled but preferred cores disabled then + * the correct boost numerator will be returned to match hardware capabilities + * even if the preferred cores scheduling hints are not enabled. + * + * Return: 0 for success, negative error code otherwise. + */ +int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator) +{ + bool prefcore; + int ret; + + ret = amd_detect_prefcore(&prefcore); + if (ret) + return ret; + + /* without preferred cores, return the highest perf register value */ + if (!prefcore) { + *numerator = boost_numerator; + return 0; + } + + /* + * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f, + * the highest performance level is set to 196. + * https://bugzilla.kernel.org/show_bug.cgi?id=218759 + */ + if (cpu_feature_enabled(X86_FEATURE_ZEN4)) { + switch (boot_cpu_data.x86_model) { + case 0x70 ... 0x7f: + *numerator = CPPC_HIGHEST_PERF_PERFORMANCE; + return 0; + default: + break; + } + } + *numerator = CPPC_HIGHEST_PERF_PREFCORE; + + return 0; +} +EXPORT_SYMBOL_GPL(amd_get_boost_ratio_numerator); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 059e5c16af05..dc5d3216af24 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -26,6 +26,7 @@ #define PCI_DEVICE_ID_AMD_19H_M70H_ROOT 0x14e8 #define PCI_DEVICE_ID_AMD_1AH_M00H_ROOT 0x153a #define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 +#define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122 #define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb #define PCI_DEVICE_ID_AMD_MI300_ROOT 0x14f8 @@ -43,6 +44,8 @@ #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4 +#define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4 0x124c +#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4 0x12bc #define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4 #define PCI_DEVICE_ID_AMD_MI300_DF_F4 0x152c @@ -63,6 +66,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_ROOT) }, {} @@ -95,6 +99,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F3) }, @@ -122,6 +127,8 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F4) }, {} diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 373638691cd4..6513c53c9459 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -677,7 +677,7 @@ calibrate_by_pmtimer(u32 deltapm, long *delta, long *deltatsc) return -1; #endif - apic_printk(APIC_VERBOSE, "... PM-Timer delta = %u\n", deltapm); + apic_pr_verbose("... PM-Timer delta = %u\n", deltapm); /* Check, if the PM timer is available */ if (!deltapm) @@ -687,14 +687,14 @@ calibrate_by_pmtimer(u32 deltapm, long *delta, long *deltatsc) if (deltapm > (pm_100ms - pm_thresh) && deltapm < (pm_100ms + pm_thresh)) { - apic_printk(APIC_VERBOSE, "... PM-Timer result ok\n"); + apic_pr_verbose("... PM-Timer result ok\n"); return 0; } res = (((u64)deltapm) * mult) >> 22; do_div(res, 1000000); - pr_warn("APIC calibration not consistent " - "with PM-Timer: %ldms instead of 100ms\n", (long)res); + pr_warn("APIC calibration not consistent with PM-Timer: %ldms instead of 100ms\n", + (long)res); /* Correct the lapic counter value */ res = (((u64)(*delta)) * pm_100ms); @@ -707,9 +707,8 @@ calibrate_by_pmtimer(u32 deltapm, long *delta, long *deltatsc) if (boot_cpu_has(X86_FEATURE_TSC)) { res = (((u64)(*deltatsc)) * pm_100ms); do_div(res, deltapm); - apic_printk(APIC_VERBOSE, "TSC delta adjusted to " - "PM-Timer: %lu (%ld)\n", - (unsigned long)res, *deltatsc); + apic_pr_verbose("TSC delta adjusted to PM-Timer: %lu (%ld)\n", + (unsigned long)res, *deltatsc); *deltatsc = (long)res; } @@ -792,8 +791,7 @@ static int __init calibrate_APIC_clock(void) * in the clockevent structure and return. */ if (!lapic_init_clockevent()) { - apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n", - lapic_timer_period); + apic_pr_verbose("lapic timer already calibrated %d\n", lapic_timer_period); /* * Direct calibration methods must have an always running * local APIC timer, no need for broadcast timer. @@ -802,8 +800,7 @@ static int __init calibrate_APIC_clock(void) return 0; } - apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" - "calibrating APIC timer ...\n"); + apic_pr_verbose("Using local APIC timer interrupts. Calibrating APIC timer ...\n"); /* * There are platforms w/o global clockevent devices. Instead of @@ -866,7 +863,7 @@ static int __init calibrate_APIC_clock(void) /* Build delta t1-t2 as apic timer counts down */ delta = lapic_cal_t1 - lapic_cal_t2; - apic_printk(APIC_VERBOSE, "... lapic delta = %ld\n", delta); + apic_pr_verbose("... lapic delta = %ld\n", delta); deltatsc = (long)(lapic_cal_tsc2 - lapic_cal_tsc1); @@ -877,22 +874,19 @@ static int __init calibrate_APIC_clock(void) lapic_timer_period = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; lapic_init_clockevent(); - apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta); - apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult); - apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", - lapic_timer_period); + apic_pr_verbose("..... delta %ld\n", delta); + apic_pr_verbose("..... mult: %u\n", lapic_clockevent.mult); + apic_pr_verbose("..... calibration result: %u\n", lapic_timer_period); if (boot_cpu_has(X86_FEATURE_TSC)) { - apic_printk(APIC_VERBOSE, "..... CPU clock speed is " - "%ld.%04ld MHz.\n", - (deltatsc / LAPIC_CAL_LOOPS) / (1000000 / HZ), - (deltatsc / LAPIC_CAL_LOOPS) % (1000000 / HZ)); + apic_pr_verbose("..... CPU clock speed is %ld.%04ld MHz.\n", + (deltatsc / LAPIC_CAL_LOOPS) / (1000000 / HZ), + (deltatsc / LAPIC_CAL_LOOPS) % (1000000 / HZ)); } - apic_printk(APIC_VERBOSE, "..... host bus clock speed is " - "%u.%04u MHz.\n", - lapic_timer_period / (1000000 / HZ), - lapic_timer_period % (1000000 / HZ)); + apic_pr_verbose("..... host bus clock speed is %u.%04u MHz.\n", + lapic_timer_period / (1000000 / HZ), + lapic_timer_period % (1000000 / HZ)); /* * Do a sanity check on the APIC calibration result @@ -911,7 +905,7 @@ static int __init calibrate_APIC_clock(void) * available. */ if (!pm_referenced && global_clock_event) { - apic_printk(APIC_VERBOSE, "... verify APIC timer\n"); + apic_pr_verbose("... verify APIC timer\n"); /* * Setup the apic timer manually @@ -932,11 +926,11 @@ static int __init calibrate_APIC_clock(void) /* Jiffies delta */ deltaj = lapic_cal_j2 - lapic_cal_j1; - apic_printk(APIC_VERBOSE, "... jiffies delta = %lu\n", deltaj); + apic_pr_verbose("... jiffies delta = %lu\n", deltaj); /* Check, if the jiffies result is consistent */ if (deltaj >= LAPIC_CAL_LOOPS-2 && deltaj <= LAPIC_CAL_LOOPS+2) - apic_printk(APIC_VERBOSE, "... jiffies result ok\n"); + apic_pr_verbose("... jiffies result ok\n"); else levt->features |= CLOCK_EVT_FEAT_DUMMY; } @@ -1221,9 +1215,8 @@ void __init sync_Arb_IDs(void) */ apic_wait_icr_idle(); - apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n"); - apic_write(APIC_ICR, APIC_DEST_ALLINC | - APIC_INT_LEVELTRIG | APIC_DM_INIT); + apic_pr_debug("Synchronizing Arb IDs.\n"); + apic_write(APIC_ICR, APIC_DEST_ALLINC | APIC_INT_LEVELTRIG | APIC_DM_INIT); } enum apic_intr_mode_id apic_intr_mode __ro_after_init; @@ -1409,10 +1402,10 @@ static void lapic_setup_esr(void) if (maxlvt > 3) apic_write(APIC_ESR, 0); value = apic_read(APIC_ESR); - if (value != oldvalue) - apic_printk(APIC_VERBOSE, "ESR value before enabling " - "vector: 0x%08x after: 0x%08x\n", - oldvalue, value); + if (value != oldvalue) { + apic_pr_verbose("ESR value before enabling vector: 0x%08x after: 0x%08x\n", + oldvalue, value); + } } #define APIC_IR_REGS APIC_ISR_NR @@ -1599,10 +1592,10 @@ static void setup_local_APIC(void) value = apic_read(APIC_LVT0) & APIC_LVT_MASKED; if (!cpu && (pic_mode || !value || ioapic_is_disabled)) { value = APIC_DM_EXTINT; - apic_printk(APIC_VERBOSE, "enabled ExtINT on CPU#%d\n", cpu); + apic_pr_verbose("Enabled ExtINT on CPU#%d\n", cpu); } else { value = APIC_DM_EXTINT | APIC_LVT_MASKED; - apic_printk(APIC_VERBOSE, "masked ExtINT on CPU#%d\n", cpu); + apic_pr_verbose("Masked ExtINT on CPU#%d\n", cpu); } apic_write(APIC_LVT0, value); @@ -2067,8 +2060,7 @@ static __init void apic_set_fixmap(bool read_apic) { set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr); apic_mmio_base = APIC_BASE; - apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", - apic_mmio_base, mp_lapic_addr); + apic_pr_verbose("Mapped APIC to %16lx (%16lx)\n", apic_mmio_base, mp_lapic_addr); if (read_apic) apic_read_boot_cpu_id(false); } @@ -2171,18 +2163,17 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_error_interrupt) apic_eoi(); atomic_inc(&irq_err_count); - apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x", - smp_processor_id(), v); + apic_pr_debug("APIC error on CPU%d: %02x", smp_processor_id(), v); v &= 0xff; while (v) { if (v & 0x1) - apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]); + apic_pr_debug_cont(" : %s", error_interrupt_reason[i]); i++; v >>= 1; } - apic_printk(APIC_DEBUG, KERN_CONT "\n"); + apic_pr_debug_cont("\n"); trace_error_apic_exit(ERROR_APIC_VECTOR); } @@ -2202,8 +2193,7 @@ static void __init connect_bsp_APIC(void) * PIC mode, enable APIC mode in the IMCR, i.e. connect BSP's * local APIC to INT and NMI lines. */ - apic_printk(APIC_VERBOSE, "leaving PIC mode, " - "enabling APIC mode.\n"); + apic_pr_verbose("Leaving PIC mode, enabling APIC mode.\n"); imcr_pic_to_apic(); } #endif @@ -2228,8 +2218,7 @@ void disconnect_bsp_APIC(int virt_wire_setup) * IPIs, won't work beyond this point! The only exception are * INIT IPIs. */ - apic_printk(APIC_VERBOSE, "disabling APIC mode, " - "entering PIC mode.\n"); + apic_pr_verbose("Disabling APIC mode, entering PIC mode.\n"); imcr_apic_to_pic(); return; } diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f37ad3392fec..e0308d8c4e6c 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -8,129 +8,25 @@ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and * James Cleverdon. */ -#include <linux/cpumask.h> #include <linux/export.h> -#include <linux/acpi.h> -#include <asm/jailhouse_para.h> #include <asm/apic.h> #include "local.h" -static struct apic apic_physflat; -static struct apic apic_flat; - -struct apic *apic __ro_after_init = &apic_flat; -EXPORT_SYMBOL_GPL(apic); - -static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) -{ - return 1; -} - -static void _flat_send_IPI_mask(unsigned long mask, int vector) -{ - unsigned long flags; - - local_irq_save(flags); - __default_send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL); - local_irq_restore(flags); -} - -static void flat_send_IPI_mask(const struct cpumask *cpumask, int vector) -{ - unsigned long mask = cpumask_bits(cpumask)[0]; - - _flat_send_IPI_mask(mask, vector); -} - -static void -flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) -{ - unsigned long mask = cpumask_bits(cpumask)[0]; - int cpu = smp_processor_id(); - - if (cpu < BITS_PER_LONG) - __clear_bit(cpu, &mask); - - _flat_send_IPI_mask(mask, vector); -} - -static u32 flat_get_apic_id(u32 x) +static u32 physflat_get_apic_id(u32 x) { return (x >> 24) & 0xFF; } -static int flat_probe(void) +static int physflat_probe(void) { return 1; } -static struct apic apic_flat __ro_after_init = { - .name = "flat", - .probe = flat_probe, - .acpi_madt_oem_check = flat_acpi_madt_oem_check, - - .dest_mode_logical = true, - - .disable_esr = 0, - - .init_apic_ldr = default_init_apic_ldr, - .cpu_present_to_apicid = default_cpu_present_to_apicid, - - .max_apic_id = 0xFE, - .get_apic_id = flat_get_apic_id, - - .calc_dest_apicid = apic_flat_calc_apicid, - - .send_IPI = default_send_IPI_single, - .send_IPI_mask = flat_send_IPI_mask, - .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, - .send_IPI_allbutself = default_send_IPI_allbutself, - .send_IPI_all = default_send_IPI_all, - .send_IPI_self = default_send_IPI_self, - .nmi_to_offline_cpu = true, - - .read = native_apic_mem_read, - .write = native_apic_mem_write, - .eoi = native_apic_mem_eoi, - .icr_read = native_apic_icr_read, - .icr_write = native_apic_icr_write, - .wait_icr_idle = apic_mem_wait_icr_idle, - .safe_wait_icr_idle = apic_mem_wait_icr_idle_timeout, -}; - -/* - * Physflat mode is used when there are more than 8 CPUs on a system. - * We cannot use logical delivery in this case because the mask - * overflows, so use physical mode. - */ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { -#ifdef CONFIG_ACPI - /* - * Quirk: some x86_64 machines can only use physical APIC mode - * regardless of how many processors are present (x86_64 ES7000 - * is an example). - */ - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) { - printk(KERN_DEBUG "system APIC only can use physical flat"); - return 1; - } - - if (!strncmp(oem_id, "IBM", 3) && !strncmp(oem_table_id, "EXA", 3)) { - printk(KERN_DEBUG "IBM Summit detected, will use apic physical"); - return 1; - } -#endif - - return 0; -} - -static int physflat_probe(void) -{ - return apic == &apic_physflat || num_possible_cpus() > 8 || jailhouse_paravirt(); + return 1; } static struct apic apic_physflat __ro_after_init = { @@ -146,7 +42,7 @@ static struct apic apic_physflat __ro_after_init = { .cpu_present_to_apicid = default_cpu_present_to_apicid, .max_apic_id = 0xFE, - .get_apic_id = flat_get_apic_id, + .get_apic_id = physflat_get_apic_id, .calc_dest_apicid = apic_default_calc_apicid, @@ -166,8 +62,7 @@ static struct apic apic_physflat __ro_after_init = { .wait_icr_idle = apic_mem_wait_icr_idle, .safe_wait_icr_idle = apic_mem_wait_icr_idle_timeout, }; +apic_driver(apic_physflat); -/* - * We need to check for physflat first, so this order is important. - */ -apic_drivers(apic_physflat, apic_flat); +struct apic *apic __ro_after_init = &apic_physflat; +EXPORT_SYMBOL_GPL(apic); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 477b740b2f26..1029ea4ac8ba 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -86,8 +86,8 @@ static unsigned int ioapic_dynirq_base; static int ioapic_initialized; struct irq_pin_list { - struct list_head list; - int apic, pin; + struct list_head list; + int apic, pin; }; struct mp_chip_data { @@ -96,7 +96,7 @@ struct mp_chip_data { bool is_level; bool active_low; bool isa_irq; - u32 count; + u32 count; }; struct mp_ioapic_gsi { @@ -105,21 +105,17 @@ struct mp_ioapic_gsi { }; static struct ioapic { - /* - * # of IRQ routing registers - */ - int nr_registers; - /* - * Saved state during suspend/resume, or while enabling intr-remap. - */ - struct IO_APIC_route_entry *saved_registers; + /* # of IRQ routing registers */ + int nr_registers; + /* Saved state during suspend/resume, or while enabling intr-remap. */ + struct IO_APIC_route_entry *saved_registers; /* I/O APIC config */ - struct mpc_ioapic mp_config; + struct mpc_ioapic mp_config; /* IO APIC gsi routing info */ - struct mp_ioapic_gsi gsi_config; - struct ioapic_domain_cfg irqdomain_cfg; - struct irq_domain *irqdomain; - struct resource *iomem_res; + struct mp_ioapic_gsi gsi_config; + struct ioapic_domain_cfg irqdomain_cfg; + struct irq_domain *irqdomain; + struct resource *iomem_res; } ioapics[MAX_IO_APICS]; #define mpc_ioapic_ver(ioapic_idx) ioapics[ioapic_idx].mp_config.apicver @@ -205,10 +201,9 @@ void mp_save_irq(struct mpc_intsrc *m) { int i; - apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x," - " IRQ %02x, APIC ID %x, APIC INT %02x\n", - m->irqtype, m->irqflag & 3, (m->irqflag >> 2) & 3, m->srcbus, - m->srcbusirq, m->dstapic, m->dstirq); + apic_pr_verbose("Int: type %d, pol %d, trig %d, bus %02x, IRQ %02x, APIC ID %x, APIC INT %02x\n", + m->irqtype, m->irqflag & 3, (m->irqflag >> 2) & 3, m->srcbus, + m->srcbusirq, m->dstapic, m->dstirq); for (i = 0; i < mp_irq_entries; i++) { if (!memcmp(&mp_irqs[i], m, sizeof(*m))) @@ -269,12 +264,14 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) static inline void io_apic_eoi(unsigned int apic, unsigned int vector) { struct io_apic __iomem *io_apic = io_apic_base(apic); + writel(vector, &io_apic->eoi); } unsigned int native_io_apic_read(unsigned int apic, unsigned int reg) { struct io_apic __iomem *io_apic = io_apic_base(apic); + writel(reg, &io_apic->index); return readl(&io_apic->data); } @@ -300,14 +297,8 @@ static struct IO_APIC_route_entry __ioapic_read_entry(int apic, int pin) static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin) { - struct IO_APIC_route_entry entry; - unsigned long flags; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - entry = __ioapic_read_entry(apic, pin); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - - return entry; + guard(raw_spinlock_irqsave)(&ioapic_lock); + return __ioapic_read_entry(apic, pin); } /* @@ -324,11 +315,8 @@ static void __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) { - unsigned long flags; - - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); __ioapic_write_entry(apic, pin, e); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); } /* @@ -339,12 +327,10 @@ static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) static void ioapic_mask_entry(int apic, int pin) { struct IO_APIC_route_entry e = { .masked = true }; - unsigned long flags; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); io_apic_write(apic, 0x10 + 2*pin, e.w1); io_apic_write(apic, 0x11 + 2*pin, e.w2); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); } /* @@ -352,68 +338,39 @@ static void ioapic_mask_entry(int apic, int pin) * shared ISA-space IRQs, so we have to support them. We are super * fast in the common case, and fast for shared ISA-space IRQs. */ -static int __add_pin_to_irq_node(struct mp_chip_data *data, - int node, int apic, int pin) +static bool add_pin_to_irq_node(struct mp_chip_data *data, int node, int apic, int pin) { struct irq_pin_list *entry; - /* don't allow duplicates */ - for_each_irq_pin(entry, data->irq_2_pin) + /* Don't allow duplicates */ + for_each_irq_pin(entry, data->irq_2_pin) { if (entry->apic == apic && entry->pin == pin) - return 0; + return true; + } entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node); if (!entry) { - pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", - node, apic, pin); - return -ENOMEM; + pr_err("Cannot allocate irq_pin_list (%d,%d,%d)\n", node, apic, pin); + return false; } + entry->apic = apic; entry->pin = pin; list_add_tail(&entry->list, &data->irq_2_pin); - - return 0; + return true; } static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin) { struct irq_pin_list *tmp, *entry; - list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list) + list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list) { if (entry->apic == apic && entry->pin == pin) { list_del(&entry->list); kfree(entry); return; } -} - -static void add_pin_to_irq_node(struct mp_chip_data *data, - int node, int apic, int pin) -{ - if (__add_pin_to_irq_node(data, node, apic, pin)) - panic("IO-APIC: failed to add irq-pin. Can not proceed\n"); -} - -/* - * Reroute an IRQ to a different pin. - */ -static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node, - int oldapic, int oldpin, - int newapic, int newpin) -{ - struct irq_pin_list *entry; - - for_each_irq_pin(entry, data->irq_2_pin) { - if (entry->apic == oldapic && entry->pin == oldpin) { - entry->apic = newapic; - entry->pin = newpin; - /* every one is different, right? */ - return; - } } - - /* old apic/pin didn't exist, so just add new ones */ - add_pin_to_irq_node(data, node, newapic, newpin); } static void io_apic_modify_irq(struct mp_chip_data *data, bool masked, @@ -430,12 +387,12 @@ static void io_apic_modify_irq(struct mp_chip_data *data, bool masked, } } +/* + * Synchronize the IO-APIC and the CPU by doing a dummy read from the + * IO-APIC + */ static void io_apic_sync(struct irq_pin_list *entry) { - /* - * Synchronize the IO-APIC and the CPU by doing - * a dummy read from the IO-APIC - */ struct io_apic __iomem *io_apic; io_apic = io_apic_base(entry->apic); @@ -445,11 +402,9 @@ static void io_apic_sync(struct irq_pin_list *entry) static void mask_ioapic_irq(struct irq_data *irq_data) { struct mp_chip_data *data = irq_data->chip_data; - unsigned long flags; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); io_apic_modify_irq(data, true, &io_apic_sync); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); } static void __unmask_ioapic(struct mp_chip_data *data) @@ -460,11 +415,9 @@ static void __unmask_ioapic(struct mp_chip_data *data) static void unmask_ioapic_irq(struct irq_data *irq_data) { struct mp_chip_data *data = irq_data->chip_data; - unsigned long flags; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); __unmask_ioapic(data); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); } /* @@ -492,30 +445,24 @@ static void __eoi_ioapic_pin(int apic, int pin, int vector) entry = entry1 = __ioapic_read_entry(apic, pin); - /* - * Mask the entry and change the trigger mode to edge. - */ + /* Mask the entry and change the trigger mode to edge. */ entry1.masked = true; entry1.is_level = false; __ioapic_write_entry(apic, pin, entry1); - /* - * Restore the previous level triggered entry. - */ + /* Restore the previous level triggered entry. */ __ioapic_write_entry(apic, pin, entry); } } static void eoi_ioapic_pin(int vector, struct mp_chip_data *data) { - unsigned long flags; struct irq_pin_list *entry; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); for_each_irq_pin(entry, data->irq_2_pin) __eoi_ioapic_pin(entry->apic, entry->pin, vector); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); } static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) @@ -538,8 +485,6 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) } if (entry.irr) { - unsigned long flags; - /* * Make sure the trigger mode is set to level. Explicit EOI * doesn't clear the remote-IRR if the trigger mode is not @@ -549,9 +494,8 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) entry.is_level = true; ioapic_write_entry(apic, pin, entry); } - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); __eoi_ioapic_pin(apic, pin, entry.vector); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); } /* @@ -586,28 +530,23 @@ static int pirq_entries[MAX_PIRQS] = { static int __init ioapic_pirq_setup(char *str) { - int i, max; - int ints[MAX_PIRQS+1]; + int i, max, ints[MAX_PIRQS+1]; get_options(str, ARRAY_SIZE(ints), ints); - apic_printk(APIC_VERBOSE, KERN_INFO - "PIRQ redirection, working around broken MP-BIOS.\n"); + apic_pr_verbose("PIRQ redirection, working around broken MP-BIOS.\n"); + max = MAX_PIRQS; if (ints[0] < MAX_PIRQS) max = ints[0]; for (i = 0; i < max; i++) { - apic_printk(APIC_VERBOSE, KERN_DEBUG - "... PIRQ%d -> IRQ %d\n", i, ints[i+1]); - /* - * PIRQs are mapped upside down, usually. - */ + apic_pr_verbose("... PIRQ%d -> IRQ %d\n", i, ints[i + 1]); + /* PIRQs are mapped upside down, usually */ pirq_entries[MAX_PIRQS-i-1] = ints[i+1]; } return 1; } - __setup("pirq=", ioapic_pirq_setup); #endif /* CONFIG_X86_32 */ @@ -626,8 +565,7 @@ int save_ioapic_entries(void) } for_each_pin(apic, pin) - ioapics[apic].saved_registers[pin] = - ioapic_read_entry(apic, pin); + ioapics[apic].saved_registers[pin] = ioapic_read_entry(apic, pin); } return err; @@ -668,8 +606,7 @@ int restore_ioapic_entries(void) continue; for_each_pin(apic, pin) - ioapic_write_entry(apic, pin, - ioapics[apic].saved_registers[pin]); + ioapic_write_entry(apic, pin, ioapics[apic].saved_registers[pin]); } return 0; } @@ -681,12 +618,13 @@ static int find_irq_entry(int ioapic_idx, int pin, int type) { int i; - for (i = 0; i < mp_irq_entries; i++) + for (i = 0; i < mp_irq_entries; i++) { if (mp_irqs[i].irqtype == type && (mp_irqs[i].dstapic == mpc_ioapic_id(ioapic_idx) || mp_irqs[i].dstapic == MP_APIC_ALL) && mp_irqs[i].dstirq == pin) return i; + } return -1; } @@ -701,10 +639,8 @@ static int __init find_isa_irq_pin(int irq, int type) for (i = 0; i < mp_irq_entries; i++) { int lbus = mp_irqs[i].srcbus; - if (test_bit(lbus, mp_bus_not_pci) && - (mp_irqs[i].irqtype == type) && + if (test_bit(lbus, mp_bus_not_pci) && (mp_irqs[i].irqtype == type) && (mp_irqs[i].srcbusirq == irq)) - return mp_irqs[i].dstirq; } return -1; @@ -717,8 +653,7 @@ static int __init find_isa_irq_apic(int irq, int type) for (i = 0; i < mp_irq_entries; i++) { int lbus = mp_irqs[i].srcbus; - if (test_bit(lbus, mp_bus_not_pci) && - (mp_irqs[i].irqtype == type) && + if (test_bit(lbus, mp_bus_not_pci) && (mp_irqs[i].irqtype == type) && (mp_irqs[i].srcbusirq == irq)) break; } @@ -726,9 +661,10 @@ static int __init find_isa_irq_apic(int irq, int type) if (i < mp_irq_entries) { int ioapic_idx; - for_each_ioapic(ioapic_idx) + for_each_ioapic(ioapic_idx) { if (mpc_ioapic_id(ioapic_idx) == mp_irqs[i].dstapic) return ioapic_idx; + } } return -1; @@ -769,8 +705,7 @@ static bool EISA_ELCR(unsigned int irq) unsigned int port = PIC_ELCR1 + (irq >> 3); return (inb(port) >> (irq & 7)) & 1; } - apic_printk(APIC_VERBOSE, KERN_INFO - "Broken MPtable reports ISA irq %d\n", irq); + apic_pr_verbose("Broken MPtable reports ISA irq %d\n", irq); return false; } @@ -947,9 +882,9 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, struct irq_alloc_info *info) { + int type = ioapics[ioapic].irqdomain_cfg.type; bool legacy = false; int irq = -1; - int type = ioapics[ioapic].irqdomain_cfg.type; switch (type) { case IOAPIC_DOMAIN_LEGACY: @@ -971,8 +906,7 @@ static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, return -1; } - return __irq_domain_alloc_irqs(domain, irq, 1, - ioapic_alloc_attr_node(info), + return __irq_domain_alloc_irqs(domain, irq, 1, ioapic_alloc_attr_node(info), info, legacy, NULL); } @@ -986,13 +920,12 @@ static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be * multiple pins sharing the same legacy IRQ number when ACPI is disabled. */ -static int alloc_isa_irq_from_domain(struct irq_domain *domain, - int irq, int ioapic, int pin, +static int alloc_isa_irq_from_domain(struct irq_domain *domain, int irq, int ioapic, int pin, struct irq_alloc_info *info) { - struct mp_chip_data *data; struct irq_data *irq_data = irq_get_irq_data(irq); int node = ioapic_alloc_attr_node(info); + struct mp_chip_data *data; /* * Legacy ISA IRQ has already been allocated, just add pin to @@ -1002,13 +935,11 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, if (irq_data && irq_data->parent_data) { if (!mp_check_pin_attr(irq, info)) return -EBUSY; - if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic, - info->ioapic.pin)) + if (!add_pin_to_irq_node(irq_data->chip_data, node, ioapic, info->ioapic.pin)) return -ENOMEM; } else { info->flags |= X86_IRQ_ALLOC_LEGACY; - irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true, - NULL); + irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true, NULL); if (irq >= 0) { irq_data = irq_domain_get_irq_data(domain, irq); data = irq_data->chip_data; @@ -1022,11 +953,11 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, unsigned int flags, struct irq_alloc_info *info) { - int irq; - bool legacy = false; + struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); struct irq_alloc_info tmp; struct mp_chip_data *data; - struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); + bool legacy = false; + int irq; if (!domain) return -ENOSYS; @@ -1046,7 +977,7 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, return -EINVAL; } - mutex_lock(&ioapic_mutex); + guard(mutex)(&ioapic_mutex); if (!(flags & IOAPIC_MAP_ALLOC)) { if (!legacy) { irq = irq_find_mapping(domain, pin); @@ -1067,8 +998,6 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, data->count++; } } - mutex_unlock(&ioapic_mutex); - return irq; } @@ -1076,26 +1005,20 @@ static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags) { u32 gsi = mp_pin_to_gsi(ioapic, pin); - /* - * Debugging check, we are in big trouble if this message pops up! - */ + /* Debugging check, we are in big trouble if this message pops up! */ if (mp_irqs[idx].dstirq != pin) pr_err("broken BIOS or MPTABLE parser, ayiee!!\n"); #ifdef CONFIG_X86_32 - /* - * PCI IRQ command line redirection. Yes, limits are hardcoded. - */ + /* PCI IRQ command line redirection. Yes, limits are hardcoded. */ if ((pin >= 16) && (pin <= 23)) { - if (pirq_entries[pin-16] != -1) { - if (!pirq_entries[pin-16]) { - apic_printk(APIC_VERBOSE, KERN_DEBUG - "disabling PIRQ%d\n", pin-16); + if (pirq_entries[pin - 16] != -1) { + if (!pirq_entries[pin - 16]) { + apic_pr_verbose("Disabling PIRQ%d\n", pin - 16); } else { int irq = pirq_entries[pin-16]; - apic_printk(APIC_VERBOSE, KERN_DEBUG - "using PIRQ%d -> IRQ %d\n", - pin-16, irq); + + apic_pr_verbose("Using PIRQ%d -> IRQ %d\n", pin - 16, irq); return irq; } } @@ -1133,10 +1056,9 @@ void mp_unmap_irq(int irq) if (!data || data->isa_irq) return; - mutex_lock(&ioapic_mutex); + guard(mutex)(&ioapic_mutex); if (--data->count == 0) irq_domain_free_irqs(irq, 1); - mutex_unlock(&ioapic_mutex); } /* @@ -1147,12 +1069,10 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) { int irq, i, best_ioapic = -1, best_idx = -1; - apic_printk(APIC_DEBUG, - "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n", - bus, slot, pin); + apic_pr_debug("Querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n", + bus, slot, pin); if (test_bit(bus, mp_bus_not_pci)) { - apic_printk(APIC_VERBOSE, - "PCI BIOS passed nonexistent PCI bus %d!\n", bus); + apic_pr_verbose("PCI BIOS passed nonexistent PCI bus %d!\n", bus); return -1; } @@ -1197,8 +1117,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) return -1; out: - return pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq, - IOAPIC_MAP_ALLOC); + return pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq, IOAPIC_MAP_ALLOC); } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); @@ -1209,17 +1128,16 @@ static void __init setup_IO_APIC_irqs(void) unsigned int ioapic, pin; int idx; - apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); + apic_pr_verbose("Init IO_APIC IRQs\n"); for_each_ioapic_pin(ioapic, pin) { idx = find_irq_entry(ioapic, pin, mp_INT); - if (idx < 0) - apic_printk(APIC_VERBOSE, - KERN_DEBUG " apic %d pin %d not connected\n", - mpc_ioapic_id(ioapic), pin); - else - pin_2_irq(idx, ioapic, pin, - ioapic ? 0 : IOAPIC_MAP_ALLOC); + if (idx < 0) { + apic_pr_verbose("apic %d pin %d not connected\n", + mpc_ioapic_id(ioapic), pin); + } else { + pin_2_irq(idx, ioapic, pin, ioapic ? 0 : IOAPIC_MAP_ALLOC); + } } } @@ -1234,26 +1152,21 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) char buf[256]; int i; - printk(KERN_DEBUG "IOAPIC %d:\n", apic); + apic_dbg("IOAPIC %d:\n", apic); for (i = 0; i <= nr_entries; i++) { entry = ioapic_read_entry(apic, i); - snprintf(buf, sizeof(buf), - " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)", - i, - entry.masked ? "disabled" : "enabled ", + snprintf(buf, sizeof(buf), " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)", + i, entry.masked ? "disabled" : "enabled ", entry.is_level ? "level" : "edge ", entry.active_low ? "low " : "high", entry.vector, entry.irr, entry.delivery_status); if (entry.ir_format) { - printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n", - buf, - (entry.ir_index_15 << 15) | entry.ir_index_0_14, - entry.ir_zero); + apic_dbg("%s, remapped, I(%04X), Z(%X)\n", buf, + (entry.ir_index_15 << 15) | entry.ir_index_0_14, entry.ir_zero); } else { - printk(KERN_DEBUG "%s, %s, D(%02X%02X), M(%1d)\n", buf, - entry.dest_mode_logical ? "logical " : "physical", - entry.virt_destid_8_14, entry.destid_0_7, - entry.delivery_mode); + apic_dbg("%s, %s, D(%02X%02X), M(%1d)\n", buf, + entry.dest_mode_logical ? "logical " : "physic al", + entry.virt_destid_8_14, entry.destid_0_7, entry.delivery_mode); } } } @@ -1264,30 +1177,25 @@ static void __init print_IO_APIC(int ioapic_idx) union IO_APIC_reg_01 reg_01; union IO_APIC_reg_02 reg_02; union IO_APIC_reg_03 reg_03; - unsigned long flags; - raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(ioapic_idx, 0); - reg_01.raw = io_apic_read(ioapic_idx, 1); - if (reg_01.bits.version >= 0x10) - reg_02.raw = io_apic_read(ioapic_idx, 2); - if (reg_01.bits.version >= 0x20) - reg_03.raw = io_apic_read(ioapic_idx, 3); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - - printk(KERN_DEBUG "IO APIC #%d......\n", mpc_ioapic_id(ioapic_idx)); - printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); - printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); - printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type); - printk(KERN_DEBUG "....... : LTS : %X\n", reg_00.bits.LTS); - - printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)®_01); - printk(KERN_DEBUG "....... : max redirection entries: %02X\n", - reg_01.bits.entries); - - printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ); - printk(KERN_DEBUG "....... : IO APIC version: %02X\n", - reg_01.bits.version); + scoped_guard (raw_spinlock_irqsave, &ioapic_lock) { + reg_00.raw = io_apic_read(ioapic_idx, 0); + reg_01.raw = io_apic_read(ioapic_idx, 1); + if (reg_01.bits.version >= 0x10) + reg_02.raw = io_apic_read(ioapic_idx, 2); + if (reg_01.bits.version >= 0x20) + reg_03.raw = io_apic_read(ioapic_idx, 3); + } + + apic_dbg("IO APIC #%d......\n", mpc_ioapic_id(ioapic_idx)); + apic_dbg(".... register #00: %08X\n", reg_00.raw); + apic_dbg("....... : physical APIC id: %02X\n", reg_00.bits.ID); + apic_dbg("....... : Delivery Type: %X\n", reg_00.bits.delivery_type); + apic_dbg("....... : LTS : %X\n", reg_00.bits.LTS); + apic_dbg(".... register #01: %08X\n", *(int *)®_01); + apic_dbg("....... : max redirection entries: %02X\n", reg_01.bits.entries); + apic_dbg("....... : PRQ implemented: %X\n", reg_01.bits.PRQ); + apic_dbg("....... : IO APIC version: %02X\n", reg_01.bits.version); /* * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02, @@ -1295,8 +1203,8 @@ static void __init print_IO_APIC(int ioapic_idx) * value, so ignore it if reg_02 == reg_01. */ if (reg_01.bits.version >= 0x10 && reg_02.raw != reg_01.raw) { - printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw); - printk(KERN_DEBUG "....... : arbitration: %02X\n", reg_02.bits.arbitration); + apic_dbg(".... register #02: %08X\n", reg_02.raw); + apic_dbg("....... : arbitration: %02X\n", reg_02.bits.arbitration); } /* @@ -1306,11 +1214,11 @@ static void __init print_IO_APIC(int ioapic_idx) */ if (reg_01.bits.version >= 0x20 && reg_03.raw != reg_02.raw && reg_03.raw != reg_01.raw) { - printk(KERN_DEBUG ".... register #03: %08X\n", reg_03.raw); - printk(KERN_DEBUG "....... : Boot DT : %X\n", reg_03.bits.boot_DT); + apic_dbg(".... register #03: %08X\n", reg_03.raw); + apic_dbg("....... : Boot DT : %X\n", reg_03.bits.boot_DT); } - printk(KERN_DEBUG ".... IRQ redirection table:\n"); + apic_dbg(".... IRQ redirection table:\n"); io_apic_print_entries(ioapic_idx, reg_01.bits.entries); } @@ -1319,11 +1227,11 @@ void __init print_IO_APICs(void) int ioapic_idx; unsigned int irq; - printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); - for_each_ioapic(ioapic_idx) - printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", - mpc_ioapic_id(ioapic_idx), - ioapics[ioapic_idx].nr_registers); + apic_dbg("number of MP IRQ sources: %d.\n", mp_irq_entries); + for_each_ioapic(ioapic_idx) { + apic_dbg("number of IO-APIC #%d registers: %d.\n", + mpc_ioapic_id(ioapic_idx), ioapics[ioapic_idx].nr_registers); + } /* * We are a bit conservative about what we expect. We have to @@ -1334,7 +1242,7 @@ void __init print_IO_APICs(void) for_each_ioapic(ioapic_idx) print_IO_APIC(ioapic_idx); - printk(KERN_DEBUG "IRQ to pin mappings:\n"); + apic_dbg("IRQ to pin mappings:\n"); for_each_active_irq(irq) { struct irq_pin_list *entry; struct irq_chip *chip; @@ -1349,7 +1257,7 @@ void __init print_IO_APICs(void) if (list_empty(&data->irq_2_pin)) continue; - printk(KERN_DEBUG "IRQ%d ", irq); + apic_dbg("IRQ%d ", irq); for_each_irq_pin(entry, data->irq_2_pin) pr_cont("-> %d:%d", entry->apic, entry->pin); pr_cont("\n"); @@ -1363,8 +1271,7 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 }; void __init enable_IO_APIC(void) { - int i8259_apic, i8259_pin; - int apic, pin; + int i8259_apic, i8259_pin, apic, pin; if (ioapic_is_disabled) nr_ioapics = 0; @@ -1376,19 +1283,21 @@ void __init enable_IO_APIC(void) /* See if any of the pins is in ExtINT mode */ struct IO_APIC_route_entry entry = ioapic_read_entry(apic, pin); - /* If the interrupt line is enabled and in ExtInt mode - * I have found the pin where the i8259 is connected. + /* + * If the interrupt line is enabled and in ExtInt mode I + * have found the pin where the i8259 is connected. */ - if (!entry.masked && - entry.delivery_mode == APIC_DELIVERY_MODE_EXTINT) { + if (!entry.masked && entry.delivery_mode == APIC_DELIVERY_MODE_EXTINT) { ioapic_i8259.apic = apic; ioapic_i8259.pin = pin; - goto found_i8259; + break; } } - found_i8259: - /* Look to see what if the MP table has reported the ExtINT */ - /* If we could not find the appropriate pin by looking at the ioapic + + /* + * Look to see what if the MP table has reported the ExtINT + * + * If we could not find the appropriate pin by looking at the ioapic * the i8259 probably is not connected the ioapic but give the * mptable a chance anyway. */ @@ -1396,29 +1305,24 @@ void __init enable_IO_APIC(void) i8259_apic = find_isa_irq_apic(0, mp_ExtINT); /* Trust the MP table if nothing is setup in the hardware */ if ((ioapic_i8259.pin == -1) && (i8259_pin >= 0)) { - printk(KERN_WARNING "ExtINT not setup in hardware but reported by MP table\n"); + pr_warn("ExtINT not setup in hardware but reported by MP table\n"); ioapic_i8259.pin = i8259_pin; ioapic_i8259.apic = i8259_apic; } /* Complain if the MP table and the hardware disagree */ if (((ioapic_i8259.apic != i8259_apic) || (ioapic_i8259.pin != i8259_pin)) && - (i8259_pin >= 0) && (ioapic_i8259.pin >= 0)) - { - printk(KERN_WARNING "ExtINT in hardware and MP table differ\n"); - } + (i8259_pin >= 0) && (ioapic_i8259.pin >= 0)) + pr_warn("ExtINT in hardware and MP table differ\n"); - /* - * Do not trust the IO-APIC being empty at bootup - */ + /* Do not trust the IO-APIC being empty at bootup */ clear_IO_APIC(); } void native_restore_boot_irq_mode(void) { /* - * If the i8259 is routed through an IOAPIC - * Put that IOAPIC in virtual wire mode - * so legacy interrupts can be delivered. + * If the i8259 is routed through an IOAPIC Put that IOAPIC in + * virtual wire mode so legacy interrupts can be delivered. */ if (ioapic_i8259.pin != -1) { struct IO_APIC_route_entry entry; @@ -1433,9 +1337,7 @@ void native_restore_boot_irq_mode(void) entry.destid_0_7 = apic_id & 0xFF; entry.virt_destid_8_14 = apic_id >> 8; - /* - * Add it to the IO-APIC irq-routing table: - */ + /* Add it to the IO-APIC irq-routing table */ ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry); } @@ -1464,7 +1366,6 @@ static void __init setup_ioapic_ids_from_mpc_nocheck(void) const u32 broadcast_id = 0xF; union IO_APIC_reg_00 reg_00; unsigned char old_id; - unsigned long flags; int ioapic_idx, i; /* @@ -1478,9 +1379,8 @@ static void __init setup_ioapic_ids_from_mpc_nocheck(void) */ for_each_ioapic(ioapic_idx) { /* Read the register 0 value */ - raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(ioapic_idx, 0); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); + scoped_guard (raw_spinlock_irqsave, &ioapic_lock) + reg_00.raw = io_apic_read(ioapic_idx, 0); old_id = mpc_ioapic_id(ioapic_idx); @@ -1508,47 +1408,42 @@ static void __init setup_ioapic_ids_from_mpc_nocheck(void) set_bit(i, phys_id_present_map); ioapics[ioapic_idx].mp_config.apicid = i; } else { - apic_printk(APIC_VERBOSE, "Setting %d in the phys_id_present_map\n", - mpc_ioapic_id(ioapic_idx)); + apic_pr_verbose("Setting %d in the phys_id_present_map\n", + mpc_ioapic_id(ioapic_idx)); set_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map); } /* - * We need to adjust the IRQ routing table - * if the ID changed. + * We need to adjust the IRQ routing table if the ID + * changed. */ - if (old_id != mpc_ioapic_id(ioapic_idx)) - for (i = 0; i < mp_irq_entries; i++) + if (old_id != mpc_ioapic_id(ioapic_idx)) { + for (i = 0; i < mp_irq_entries; i++) { if (mp_irqs[i].dstapic == old_id) - mp_irqs[i].dstapic - = mpc_ioapic_id(ioapic_idx); + mp_irqs[i].dstapic = mpc_ioapic_id(ioapic_idx); + } + } /* - * Update the ID register according to the right value - * from the MPC table if they are different. + * Update the ID register according to the right value from + * the MPC table if they are different. */ if (mpc_ioapic_id(ioapic_idx) == reg_00.bits.ID) continue; - apic_printk(APIC_VERBOSE, KERN_INFO - "...changing IO-APIC physical APIC ID to %d ...", - mpc_ioapic_id(ioapic_idx)); + apic_pr_verbose("...changing IO-APIC physical APIC ID to %d ...", + mpc_ioapic_id(ioapic_idx)); reg_00.bits.ID = mpc_ioapic_id(ioapic_idx); - raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic_idx, 0, reg_00.raw); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - - /* - * Sanity check - */ - raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(ioapic_idx, 0); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); + scoped_guard (raw_spinlock_irqsave, &ioapic_lock) { + io_apic_write(ioapic_idx, 0, reg_00.raw); + reg_00.raw = io_apic_read(ioapic_idx, 0); + } + /* Sanity check */ if (reg_00.bits.ID != mpc_ioapic_id(ioapic_idx)) pr_cont("could not set ID!\n"); else - apic_printk(APIC_VERBOSE, " ok.\n"); + apic_pr_verbose(" ok.\n"); } } @@ -1593,8 +1488,7 @@ static void __init delay_with_tsc(void) do { rep_nop(); now = rdtsc(); - } while ((now - start) < 40000000000ULL / HZ && - time_before_eq(jiffies, end)); + } while ((now - start) < 40000000000ULL / HZ && time_before_eq(jiffies, end)); } static void __init delay_without_tsc(void) @@ -1655,36 +1549,29 @@ static int __init timer_irq_works(void) * so we 'resend' these IRQs via IPIs, to the same CPU. It's much * better to do it this way as thus we do not have to be aware of * 'pending' interrupts in the IRQ path, except at this point. - */ -/* - * Edge triggered needs to resend any interrupt - * that was delayed but this is now handled in the device - * independent code. - */ - -/* - * Starting up a edge-triggered IO-APIC interrupt is - * nasty - we need to make sure that we get the edge. - * If it is already asserted for some reason, we need - * return 1 to indicate that is was pending. * - * This is not complete - we should be able to fake - * an edge even if it isn't on the 8259A... + * + * Edge triggered needs to resend any interrupt that was delayed but this + * is now handled in the device independent code. + * + * Starting up a edge-triggered IO-APIC interrupt is nasty - we need to + * make sure that we get the edge. If it is already asserted for some + * reason, we need return 1 to indicate that is was pending. + * + * This is not complete - we should be able to fake an edge even if it + * isn't on the 8259A... */ static unsigned int startup_ioapic_irq(struct irq_data *data) { int was_pending = 0, irq = data->irq; - unsigned long flags; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); if (irq < nr_legacy_irqs()) { legacy_pic->mask(irq); if (legacy_pic->irq_pending(irq)) was_pending = 1; } __unmask_ioapic(data->chip_data); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return was_pending; } @@ -1694,9 +1581,8 @@ atomic_t irq_mis_count; static bool io_apic_level_ack_pending(struct mp_chip_data *data) { struct irq_pin_list *entry; - unsigned long flags; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); for_each_irq_pin(entry, data->irq_2_pin) { struct IO_APIC_route_entry e; int pin; @@ -1704,13 +1590,9 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data) pin = entry->pin; e.w1 = io_apic_read(entry->apic, 0x10 + pin*2); /* Is the remote IRR bit set? */ - if (e.irr) { - raw_spin_unlock_irqrestore(&ioapic_lock, flags); + if (e.irr) return true; - } } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return false; } @@ -1728,7 +1610,8 @@ static inline bool ioapic_prepare_move(struct irq_data *data) static inline void ioapic_finish_move(struct irq_data *data, bool moveit) { if (unlikely(moveit)) { - /* Only migrate the irq if the ack has been received. + /* + * Only migrate the irq if the ack has been received. * * On rare occasions the broadcast level triggered ack gets * delayed going to ioapics, and if we reprogram the @@ -1911,18 +1794,16 @@ static void ioapic_configure_entry(struct irq_data *irqd) __ioapic_write_entry(entry->apic, entry->pin, mpd->entry); } -static int ioapic_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) +static int ioapic_set_affinity(struct irq_data *irq_data, const struct cpumask *mask, bool force) { struct irq_data *parent = irq_data->parent_data; - unsigned long flags; int ret; ret = parent->chip->irq_set_affinity(parent, mask, force); - raw_spin_lock_irqsave(&ioapic_lock, flags); + + guard(raw_spinlock_irqsave)(&ioapic_lock); if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) ioapic_configure_entry(irq_data); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); return ret; } @@ -1941,9 +1822,8 @@ static int ioapic_set_affinity(struct irq_data *irq_data, * * Verify that the corresponding Remote-IRR bits are clear. */ -static int ioapic_irq_get_chip_state(struct irq_data *irqd, - enum irqchip_irq_state which, - bool *state) +static int ioapic_irq_get_chip_state(struct irq_data *irqd, enum irqchip_irq_state which, + bool *state) { struct mp_chip_data *mcd = irqd->chip_data; struct IO_APIC_route_entry rentry; @@ -1953,7 +1833,8 @@ static int ioapic_irq_get_chip_state(struct irq_data *irqd, return -EINVAL; *state = false; - raw_spin_lock(&ioapic_lock); + + guard(raw_spinlock)(&ioapic_lock); for_each_irq_pin(p, mcd->irq_2_pin) { rentry = __ioapic_read_entry(p->apic, p->pin); /* @@ -1967,7 +1848,6 @@ static int ioapic_irq_get_chip_state(struct irq_data *irqd, break; } } - raw_spin_unlock(&ioapic_lock); return 0; } @@ -2008,14 +1888,13 @@ static inline void init_IO_APIC_traps(void) cfg = irq_cfg(irq); if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) { /* - * Hmm.. We don't have an entry for this, - * so default to an old-fashioned 8259 - * interrupt if we can.. + * Hmm.. We don't have an entry for this, so + * default to an old-fashioned 8259 interrupt if we + * can. Otherwise set the dummy interrupt chip. */ if (irq < nr_legacy_irqs()) legacy_pic->make_irq(irq); else - /* Strange. Oh, well.. */ irq_set_chip(irq, &no_irq_chip); } } @@ -2024,20 +1903,17 @@ static inline void init_IO_APIC_traps(void) /* * The local APIC irq-chip implementation: */ - static void mask_lapic_irq(struct irq_data *data) { - unsigned long v; + unsigned long v = apic_read(APIC_LVT0); - v = apic_read(APIC_LVT0); apic_write(APIC_LVT0, v | APIC_LVT_MASKED); } static void unmask_lapic_irq(struct irq_data *data) { - unsigned long v; + unsigned long v = apic_read(APIC_LVT0); - v = apic_read(APIC_LVT0); apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED); } @@ -2056,8 +1932,7 @@ static struct irq_chip lapic_chip __read_mostly = { static void lapic_register_intr(int irq) { irq_clear_status_flags(irq, IRQ_LEVEL); - irq_set_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq, - "edge"); + irq_set_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq, "edge"); } /* @@ -2069,9 +1944,9 @@ static void lapic_register_intr(int irq) */ static inline void __init unlock_ExtINT_logic(void) { - int apic, pin, i; - struct IO_APIC_route_entry entry0, entry1; unsigned char save_control, save_freq_select; + struct IO_APIC_route_entry entry0, entry1; + int apic, pin, i; u32 apic_id; pin = find_isa_irq_pin(8, mp_INT); @@ -2131,10 +2006,10 @@ static int __init disable_timer_pin_setup(char *arg) } early_param("disable_timer_pin_1", disable_timer_pin_setup); -static int mp_alloc_timer_irq(int ioapic, int pin) +static int __init mp_alloc_timer_irq(int ioapic, int pin) { - int irq = -1; struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); + int irq = -1; if (domain) { struct irq_alloc_info info; @@ -2142,21 +2017,36 @@ static int mp_alloc_timer_irq(int ioapic, int pin) ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0); info.devid = mpc_ioapic_id(ioapic); info.ioapic.pin = pin; - mutex_lock(&ioapic_mutex); + guard(mutex)(&ioapic_mutex); irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info); - mutex_unlock(&ioapic_mutex); } return irq; } +static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node, + int oldapic, int oldpin, + int newapic, int newpin) +{ + struct irq_pin_list *entry; + + for_each_irq_pin(entry, data->irq_2_pin) { + if (entry->apic == oldapic && entry->pin == oldpin) { + entry->apic = newapic; + entry->pin = newpin; + return; + } + } + + /* Old apic/pin didn't exist, so just add a new one */ + add_pin_to_irq_node(data, node, newapic, newpin); +} + /* * This code may look a bit paranoid, but it's supposed to cooperate with * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ * is so screwy. Thanks to Brian Perkins for testing/hacking this beast * fanatically on his truly buggy board. - * - * FIXME: really need to revamp this for all platforms. */ static inline void __init check_timer(void) { @@ -2194,9 +2084,8 @@ static inline void __init check_timer(void) pin2 = ioapic_i8259.pin; apic2 = ioapic_i8259.apic; - apic_printk(APIC_QUIET, KERN_INFO "..TIMER: vector=0x%02X " - "apic1=%d pin1=%d apic2=%d pin2=%d\n", - cfg->vector, apic1, pin1, apic2, pin2); + pr_info("..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n", + cfg->vector, apic1, pin1, apic2, pin2); /* * Some BIOS writers are clueless and report the ExtINTA @@ -2240,13 +2129,10 @@ static inline void __init check_timer(void) panic_if_irq_remap("timer doesn't work through Interrupt-remapped IO-APIC"); clear_IO_APIC_pin(apic1, pin1); if (!no_pin1) - apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: " - "8254 timer not connected to IO-APIC\n"); + pr_err("..MP-BIOS bug: 8254 timer not connected to IO-APIC\n"); - apic_printk(APIC_QUIET, KERN_INFO "...trying to set up timer " - "(IRQ0) through the 8259A ...\n"); - apic_printk(APIC_QUIET, KERN_INFO - "..... (found apic %d pin %d) ...\n", apic2, pin2); + pr_info("...trying to set up timer (IRQ0) through the 8259A ...\n"); + pr_info("..... (found apic %d pin %d) ...\n", apic2, pin2); /* * legacy devices should be connected to IO APIC #0 */ @@ -2255,7 +2141,7 @@ static inline void __init check_timer(void) irq_domain_activate_irq(irq_data, false); legacy_pic->unmask(0); if (timer_irq_works()) { - apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); + pr_info("....... works.\n"); goto out; } /* @@ -2263,26 +2149,24 @@ static inline void __init check_timer(void) */ legacy_pic->mask(0); clear_IO_APIC_pin(apic2, pin2); - apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n"); + pr_info("....... failed.\n"); } - apic_printk(APIC_QUIET, KERN_INFO - "...trying to set up timer as Virtual Wire IRQ...\n"); + pr_info("...trying to set up timer as Virtual Wire IRQ...\n"); lapic_register_intr(0); apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */ legacy_pic->unmask(0); if (timer_irq_works()) { - apic_printk(APIC_QUIET, KERN_INFO "..... works.\n"); + pr_info("..... works.\n"); goto out; } legacy_pic->mask(0); apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector); - apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n"); + pr_info("..... failed.\n"); - apic_printk(APIC_QUIET, KERN_INFO - "...trying to set up timer as ExtINT IRQ...\n"); + pr_info("...trying to set up timer as ExtINT IRQ...\n"); legacy_pic->init(0); legacy_pic->make_irq(0); @@ -2292,14 +2176,15 @@ static inline void __init check_timer(void) unlock_ExtINT_logic(); if (timer_irq_works()) { - apic_printk(APIC_QUIET, KERN_INFO "..... works.\n"); + pr_info("..... works.\n"); goto out; } - apic_printk(APIC_QUIET, KERN_INFO "..... failed :(.\n"); - if (apic_is_x2apic_enabled()) - apic_printk(APIC_QUIET, KERN_INFO - "Perhaps problem with the pre-enabled x2apic mode\n" - "Try booting with x2apic and interrupt-remapping disabled in the bios.\n"); + + pr_info("..... failed :\n"); + if (apic_is_x2apic_enabled()) { + pr_info("Perhaps problem with the pre-enabled x2apic mode\n" + "Try booting with x2apic and interrupt-remapping disabled in the bios.\n"); + } panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a " "report. Then try booting with the 'noapic' option.\n"); out: @@ -2327,11 +2212,11 @@ out: static int mp_irqdomain_create(int ioapic) { - struct irq_domain *parent; + struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); int hwirqs = mp_ioapic_pin_count(ioapic); struct ioapic *ip = &ioapics[ioapic]; struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg; - struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); + struct irq_domain *parent; struct fwnode_handle *fn; struct irq_fwspec fwspec; @@ -2367,10 +2252,8 @@ static int mp_irqdomain_create(int ioapic) return -ENOMEM; } - if (cfg->type == IOAPIC_DOMAIN_LEGACY || - cfg->type == IOAPIC_DOMAIN_STRICT) - ioapic_dynirq_base = max(ioapic_dynirq_base, - gsi_cfg->gsi_end + 1); + if (cfg->type == IOAPIC_DOMAIN_LEGACY || cfg->type == IOAPIC_DOMAIN_STRICT) + ioapic_dynirq_base = max(ioapic_dynirq_base, gsi_cfg->gsi_end + 1); return 0; } @@ -2397,13 +2280,11 @@ void __init setup_IO_APIC(void) io_apic_irqs = nr_legacy_irqs() ? ~PIC_IRQS : ~0UL; - apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); + apic_pr_verbose("ENABLING IO-APIC IRQs\n"); for_each_ioapic(ioapic) BUG_ON(mp_irqdomain_create(ioapic)); - /* - * Set up IO-APIC IRQ routing. - */ + /* Set up IO-APIC IRQ routing. */ x86_init.mpparse.setup_ioapic_ids(); sync_Arb_IDs(); @@ -2417,16 +2298,14 @@ void __init setup_IO_APIC(void) static void resume_ioapic_id(int ioapic_idx) { - unsigned long flags; union IO_APIC_reg_00 reg_00; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); reg_00.raw = io_apic_read(ioapic_idx, 0); if (reg_00.bits.ID != mpc_ioapic_id(ioapic_idx)) { reg_00.bits.ID = mpc_ioapic_id(ioapic_idx); io_apic_write(ioapic_idx, 0, reg_00.raw); } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); } static void ioapic_resume(void) @@ -2440,8 +2319,8 @@ static void ioapic_resume(void) } static struct syscore_ops ioapic_syscore_ops = { - .suspend = save_ioapic_entries, - .resume = ioapic_resume, + .suspend = save_ioapic_entries, + .resume = ioapic_resume, }; static int __init ioapic_init_ops(void) @@ -2456,15 +2335,13 @@ device_initcall(ioapic_init_ops); static int io_apic_get_redir_entries(int ioapic) { union IO_APIC_reg_01 reg_01; - unsigned long flags; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); reg_01.raw = io_apic_read(ioapic, 1); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - /* The register returns the maximum index redir index - * supported, which is one less than the total number of redir - * entries. + /* + * The register returns the maximum index redir index supported, + * which is one less than the total number of redir entries. */ return reg_01.bits.entries + 1; } @@ -2494,16 +2371,14 @@ static int io_apic_get_unique_id(int ioapic, int apic_id) static DECLARE_BITMAP(apic_id_map, MAX_LOCAL_APIC); const u32 broadcast_id = 0xF; union IO_APIC_reg_00 reg_00; - unsigned long flags; int i = 0; /* Initialize the ID map */ if (bitmap_empty(apic_id_map, MAX_LOCAL_APIC)) copy_phys_cpu_present_map(apic_id_map); - raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(ioapic, 0); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); + scoped_guard (raw_spinlock_irqsave, &ioapic_lock) + reg_00.raw = io_apic_read(ioapic, 0); if (apic_id >= broadcast_id) { pr_warn("IOAPIC[%d]: Invalid apic_id %d, trying %d\n", @@ -2530,21 +2405,19 @@ static int io_apic_get_unique_id(int ioapic, int apic_id) if (reg_00.bits.ID != apic_id) { reg_00.bits.ID = apic_id; - raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic, 0, reg_00.raw); - reg_00.raw = io_apic_read(ioapic, 0); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); + scoped_guard (raw_spinlock_irqsave, &ioapic_lock) { + io_apic_write(ioapic, 0, reg_00.raw); + reg_00.raw = io_apic_read(ioapic, 0); + } /* Sanity check */ if (reg_00.bits.ID != apic_id) { - pr_err("IOAPIC[%d]: Unable to change apic_id!\n", - ioapic); + pr_err("IOAPIC[%d]: Unable to change apic_id!\n", ioapic); return -1; } } - apic_printk(APIC_VERBOSE, KERN_INFO - "IOAPIC[%d]: Assigned apic_id %d\n", ioapic, apic_id); + apic_pr_verbose("IOAPIC[%d]: Assigned apic_id %d\n", ioapic, apic_id); return apic_id; } @@ -2560,7 +2433,6 @@ static u8 io_apic_unique_id(int idx, u8 id) { union IO_APIC_reg_00 reg_00; DECLARE_BITMAP(used, 256); - unsigned long flags; u8 new_id; int i; @@ -2576,26 +2448,23 @@ static u8 io_apic_unique_id(int idx, u8 id) * Read the current id from the ioapic and keep it if * available. */ - raw_spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(idx, 0); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); + scoped_guard (raw_spinlock_irqsave, &ioapic_lock) + reg_00.raw = io_apic_read(idx, 0); + new_id = reg_00.bits.ID; if (!test_bit(new_id, used)) { - apic_printk(APIC_VERBOSE, KERN_INFO - "IOAPIC[%d]: Using reg apic_id %d instead of %d\n", - idx, new_id, id); + apic_pr_verbose("IOAPIC[%d]: Using reg apic_id %d instead of %d\n", + idx, new_id, id); return new_id; } - /* - * Get the next free id and write it to the ioapic. - */ + /* Get the next free id and write it to the ioapic. */ new_id = find_first_zero_bit(used, 256); reg_00.bits.ID = new_id; - raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(idx, 0, reg_00.raw); - reg_00.raw = io_apic_read(idx, 0); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); + scoped_guard (raw_spinlock_irqsave, &ioapic_lock) { + io_apic_write(idx, 0, reg_00.raw); + reg_00.raw = io_apic_read(idx, 0); + } /* Sanity check */ BUG_ON(reg_00.bits.ID != new_id); @@ -2605,12 +2474,10 @@ static u8 io_apic_unique_id(int idx, u8 id) static int io_apic_get_version(int ioapic) { - union IO_APIC_reg_01 reg_01; - unsigned long flags; + union IO_APIC_reg_01 reg_01; - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); reg_01.raw = io_apic_read(ioapic, 1); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); return reg_01.bits.version; } @@ -2625,8 +2492,8 @@ static struct resource *ioapic_resources; static struct resource * __init ioapic_setup_resources(void) { - unsigned long n; struct resource *res; + unsigned long n; char *mem; int i; @@ -2686,9 +2553,7 @@ void __init io_apic_init_mappings(void) ioapic_phys = mpc_ioapic_addr(i); #ifdef CONFIG_X86_32 if (!ioapic_phys) { - printk(KERN_ERR - "WARNING: bogus zero IO-APIC " - "address found in MPTABLE, " + pr_err("WARNING: bogus zero IO-APIC address found in MPTABLE, " "disabling IO/APIC support!\n"); smp_found_config = 0; ioapic_is_disabled = true; @@ -2707,9 +2572,8 @@ fake_ioapic_page: ioapic_phys = __pa(ioapic_phys); } io_apic_set_fixmap(idx, ioapic_phys); - apic_printk(APIC_VERBOSE, "mapped IOAPIC to %08lx (%08lx)\n", - __fix_to_virt(idx) + (ioapic_phys & ~PAGE_MASK), - ioapic_phys); + apic_pr_verbose("mapped IOAPIC to %08lx (%08lx)\n", + __fix_to_virt(idx) + (ioapic_phys & ~PAGE_MASK), ioapic_phys); idx++; ioapic_res->start = ioapic_phys; @@ -2720,13 +2584,12 @@ fake_ioapic_page: void __init ioapic_insert_resources(void) { - int i; struct resource *r = ioapic_resources; + int i; if (!r) { if (nr_ioapics > 0) - printk(KERN_ERR - "IO APIC resources couldn't be allocated.\n"); + pr_err("IO APIC resources couldn't be allocated.\n"); return; } @@ -2746,11 +2609,12 @@ int mp_find_ioapic(u32 gsi) /* Find the IOAPIC that manages this GSI. */ for_each_ioapic(i) { struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(i); + if (gsi >= gsi_cfg->gsi_base && gsi <= gsi_cfg->gsi_end) return i; } - printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); + pr_err("ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); return -1; } @@ -2789,12 +2653,10 @@ static int bad_ioapic_register(int idx) static int find_free_ioapic_entry(void) { - int idx; - - for (idx = 0; idx < MAX_IO_APICS; idx++) + for (int idx = 0; idx < MAX_IO_APICS; idx++) { if (ioapics[idx].nr_registers == 0) return idx; - + } return MAX_IO_APICS; } @@ -2805,8 +2667,7 @@ static int find_free_ioapic_entry(void) * @gsi_base: base of GSI associated with the IOAPIC * @cfg: configuration information for the IOAPIC */ -int mp_register_ioapic(int id, u32 address, u32 gsi_base, - struct ioapic_domain_cfg *cfg) +int mp_register_ioapic(int id, u32 address, u32 gsi_base, struct ioapic_domain_cfg *cfg) { bool hotplug = !!ioapic_initialized; struct mp_ioapic_gsi *gsi_cfg; @@ -2817,12 +2678,13 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base, pr_warn("Bogus (zero) I/O APIC address found, skipping!\n"); return -EINVAL; } - for_each_ioapic(ioapic) + + for_each_ioapic(ioapic) { if (ioapics[ioapic].mp_config.apicaddr == address) { - pr_warn("address 0x%x conflicts with IOAPIC%d\n", - address, ioapic); + pr_warn("address 0x%x conflicts with IOAPIC%d\n", address, ioapic); return -EEXIST; } + } idx = find_free_ioapic_entry(); if (idx >= MAX_IO_APICS) { @@ -2857,8 +2719,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base, (gsi_end >= gsi_cfg->gsi_base && gsi_end <= gsi_cfg->gsi_end)) { pr_warn("GSI range [%u-%u] for new IOAPIC conflicts with GSI[%u-%u]\n", - gsi_base, gsi_end, - gsi_cfg->gsi_base, gsi_cfg->gsi_end); + gsi_base, gsi_end, gsi_cfg->gsi_base, gsi_cfg->gsi_end); clear_fixmap(FIX_IO_APIC_BASE_0 + idx); return -ENOSPC; } @@ -2892,8 +2753,7 @@ int mp_register_ioapic(int id, u32 address, u32 gsi_base, ioapics[idx].nr_registers = entries; pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n", - idx, mpc_ioapic_id(idx), - mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), + idx, mpc_ioapic_id(idx), mpc_ioapic_ver(idx), mpc_ioapic_addr(idx), gsi_cfg->gsi_base, gsi_cfg->gsi_end); return 0; @@ -2904,11 +2764,13 @@ int mp_unregister_ioapic(u32 gsi_base) int ioapic, pin; int found = 0; - for_each_ioapic(ioapic) + for_each_ioapic(ioapic) { if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) { found = 1; break; } + } + if (!found) { pr_warn("can't find IOAPIC for GSI %d\n", gsi_base); return -ENODEV; @@ -2922,8 +2784,7 @@ int mp_unregister_ioapic(u32 gsi_base) if (irq >= 0) { data = irq_get_chip_data(irq); if (data && data->count) { - pr_warn("pin%d on IOAPIC%d is still in use.\n", - pin, ioapic); + pr_warn("pin%d on IOAPIC%d is still in use.\n", pin, ioapic); return -EBUSY; } } @@ -2958,8 +2819,7 @@ static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data, if (info && info->ioapic.valid) { data->is_level = info->ioapic.is_level; data->active_low = info->ioapic.active_low; - } else if (__acpi_get_override_irq(gsi, &data->is_level, - &data->active_low) < 0) { + } else if (__acpi_get_override_irq(gsi, &data->is_level, &data->active_low) < 0) { /* PCI interrupts are always active low level triggered. */ data->is_level = true; data->active_low = true; @@ -3017,10 +2877,8 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, return -ENOMEM; ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); - if (ret < 0) { - kfree(data); - return ret; - } + if (ret < 0) + goto free_data; INIT_LIST_HEAD(&data->irq_2_pin); irq_data->hwirq = info->ioapic.pin; @@ -3029,7 +2887,10 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info); - add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + if (!add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin)) { + ret = -ENOMEM; + goto free_irqs; + } mp_preconfigure_entry(data); mp_register_handler(virq, data->is_level); @@ -3039,11 +2900,15 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, legacy_pic->mask(virq); local_irq_restore(flags); - apic_printk(APIC_VERBOSE, KERN_DEBUG - "IOAPIC[%d]: Preconfigured routing entry (%d-%d -> IRQ %d Level:%i ActiveLow:%i)\n", - ioapic, mpc_ioapic_id(ioapic), pin, virq, - data->is_level, data->active_low); + apic_pr_verbose("IOAPIC[%d]: Preconfigured routing entry (%d-%d -> IRQ %d Level:%i ActiveLow:%i)\n", + ioapic, mpc_ioapic_id(ioapic), pin, virq, data->is_level, data->active_low); return 0; + +free_irqs: + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +free_data: + kfree(data); + return ret; } void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, @@ -3056,22 +2921,17 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, irq_data = irq_domain_get_irq_data(domain, virq); if (irq_data && irq_data->chip_data) { data = irq_data->chip_data; - __remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain), - (int)irq_data->hwirq); + __remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain), (int)irq_data->hwirq); WARN_ON(!list_empty(&data->irq_2_pin)); kfree(irq_data->chip_data); } irq_domain_free_irqs_top(domain, virq, nr_irqs); } -int mp_irqdomain_activate(struct irq_domain *domain, - struct irq_data *irq_data, bool reserve) +int mp_irqdomain_activate(struct irq_domain *domain, struct irq_data *irq_data, bool reserve) { - unsigned long flags; - - raw_spin_lock_irqsave(&ioapic_lock, flags); + guard(raw_spinlock_irqsave)(&ioapic_lock); ioapic_configure_entry(irq_data); - raw_spin_unlock_irqrestore(&ioapic_lock, flags); return 0; } @@ -3079,8 +2939,7 @@ void mp_irqdomain_deactivate(struct irq_domain *domain, struct irq_data *irq_data) { /* It won't be called for IRQ with multiple IOAPIC pins associated */ - ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain), - (int)irq_data->hwirq); + ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain), (int)irq_data->hwirq); } int mp_irqdomain_ioapic_idx(struct irq_domain *domain) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 1e0fe5f8ab84..015971adadfc 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1190,22 +1190,6 @@ unsigned long amd_get_dr_addr_mask(unsigned int dr) } EXPORT_SYMBOL_GPL(amd_get_dr_addr_mask); -u32 amd_get_highest_perf(void) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - - if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || - (c->x86_model >= 0x70 && c->x86_model < 0x80))) - return 166; - - if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || - (c->x86_model >= 0x40 && c->x86_model < 0x70))) - return 166; - - return 255; -} -EXPORT_SYMBOL_GPL(amd_get_highest_perf); - static void zenbleed_check_cpu(void *unused) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 0b69bfbf345d..f642de2ebdac 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -349,9 +349,89 @@ static DECLARE_WORK(disable_freq_invariance_work, DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale); +static DEFINE_STATIC_KEY_FALSE(arch_hybrid_cap_scale_key); + +struct arch_hybrid_cpu_scale { + unsigned long capacity; + unsigned long freq_ratio; +}; + +static struct arch_hybrid_cpu_scale __percpu *arch_cpu_scale; + +/** + * arch_enable_hybrid_capacity_scale() - Enable hybrid CPU capacity scaling + * + * Allocate memory for per-CPU data used by hybrid CPU capacity scaling, + * initialize it and set the static key controlling its code paths. + * + * Must be called before arch_set_cpu_capacity(). + */ +bool arch_enable_hybrid_capacity_scale(void) +{ + int cpu; + + if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) { + WARN_ONCE(1, "Hybrid CPU capacity scaling already enabled"); + return true; + } + + arch_cpu_scale = alloc_percpu(struct arch_hybrid_cpu_scale); + if (!arch_cpu_scale) + return false; + + for_each_possible_cpu(cpu) { + per_cpu_ptr(arch_cpu_scale, cpu)->capacity = SCHED_CAPACITY_SCALE; + per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio = arch_max_freq_ratio; + } + + static_branch_enable(&arch_hybrid_cap_scale_key); + + pr_info("Hybrid CPU capacity scaling enabled\n"); + + return true; +} + +/** + * arch_set_cpu_capacity() - Set scale-invariance parameters for a CPU + * @cpu: Target CPU. + * @cap: Capacity of @cpu at its maximum frequency, relative to @max_cap. + * @max_cap: System-wide maximum CPU capacity. + * @cap_freq: Frequency of @cpu corresponding to @cap. + * @base_freq: Frequency of @cpu at which MPERF counts. + * + * The units in which @cap and @max_cap are expressed do not matter, so long + * as they are consistent, because the former is effectively divided by the + * latter. Analogously for @cap_freq and @base_freq. + * + * After calling this function for all CPUs, call arch_rebuild_sched_domains() + * to let the scheduler know that capacity-aware scheduling can be used going + * forward. + */ +void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap, + unsigned long cap_freq, unsigned long base_freq) +{ + if (static_branch_likely(&arch_hybrid_cap_scale_key)) { + WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity, + div_u64(cap << SCHED_CAPACITY_SHIFT, max_cap)); + WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio, + div_u64(cap_freq << SCHED_CAPACITY_SHIFT, base_freq)); + } else { + WARN_ONCE(1, "Hybrid CPU capacity scaling not enabled"); + } +} + +unsigned long arch_scale_cpu_capacity(int cpu) +{ + if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) + return READ_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity); + + return SCHED_CAPACITY_SCALE; +} +EXPORT_SYMBOL_GPL(arch_scale_cpu_capacity); + static void scale_freq_tick(u64 acnt, u64 mcnt) { - u64 freq_scale; + u64 freq_scale, freq_ratio; if (!arch_scale_freq_invariant()) return; @@ -359,7 +439,12 @@ static void scale_freq_tick(u64 acnt, u64 mcnt) if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) goto error; - if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt) + if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) + freq_ratio = READ_ONCE(this_cpu_ptr(arch_cpu_scale)->freq_ratio); + else + freq_ratio = arch_max_freq_ratio; + + if (check_mul_overflow(mcnt, freq_ratio, &mcnt) || !mcnt) goto error; freq_scale = div64_u64(acnt, mcnt); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 45675da354f3..d1915427b4ff 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -233,7 +233,8 @@ static void x86_amd_ssb_disable(void) #define pr_fmt(fmt) "MDS: " fmt /* Default mitigation for MDS-affected CPUs */ -static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL; +static enum mds_mitigations mds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_MDS) ? MDS_MITIGATION_FULL : MDS_MITIGATION_OFF; static bool mds_nosmt __ro_after_init = false; static const char * const mds_strings[] = { @@ -293,7 +294,8 @@ enum taa_mitigations { }; /* Default mitigation for TAA-affected CPUs */ -static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static enum taa_mitigations taa_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_TAA) ? TAA_MITIGATION_VERW : TAA_MITIGATION_OFF; static bool taa_nosmt __ro_after_init; static const char * const taa_strings[] = { @@ -391,7 +393,8 @@ enum mmio_mitigations { }; /* Default mitigation for Processor MMIO Stale Data vulnerabilities */ -static enum mmio_mitigations mmio_mitigation __ro_after_init = MMIO_MITIGATION_VERW; +static enum mmio_mitigations mmio_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_MMIO_STALE_DATA) ? MMIO_MITIGATION_VERW : MMIO_MITIGATION_OFF; static bool mmio_nosmt __ro_after_init = false; static const char * const mmio_strings[] = { @@ -605,7 +608,8 @@ enum srbds_mitigations { SRBDS_MITIGATION_HYPERVISOR, }; -static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL; +static enum srbds_mitigations srbds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_SRBDS) ? SRBDS_MITIGATION_FULL : SRBDS_MITIGATION_OFF; static const char * const srbds_strings[] = { [SRBDS_MITIGATION_OFF] = "Vulnerable", @@ -731,11 +735,8 @@ enum gds_mitigations { GDS_MITIGATION_HYPERVISOR, }; -#if IS_ENABLED(CONFIG_MITIGATION_GDS_FORCE) -static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; -#else -static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; -#endif +static enum gds_mitigations gds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_GDS) ? GDS_MITIGATION_FULL : GDS_MITIGATION_OFF; static const char * const gds_strings[] = { [GDS_MITIGATION_OFF] = "Vulnerable", @@ -871,7 +872,8 @@ enum spectre_v1_mitigation { }; static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init = - SPECTRE_V1_MITIGATION_AUTO; + IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V1) ? + SPECTRE_V1_MITIGATION_AUTO : SPECTRE_V1_MITIGATION_NONE; static const char * const spectre_v1_strings[] = { [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers", @@ -986,7 +988,7 @@ static const char * const retbleed_strings[] = { static enum retbleed_mitigation retbleed_mitigation __ro_after_init = RETBLEED_MITIGATION_NONE; static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init = - RETBLEED_CMD_AUTO; + IS_ENABLED(CONFIG_MITIGATION_RETBLEED) ? RETBLEED_CMD_AUTO : RETBLEED_CMD_OFF; static int __ro_after_init retbleed_nosmt = false; @@ -1447,17 +1449,18 @@ static void __init spec_v2_print_cond(const char *reason, bool secure) static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { - enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; + enum spectre_v2_mitigation_cmd cmd; char arg[20]; int ret, i; + cmd = IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V2) ? SPECTRE_V2_CMD_AUTO : SPECTRE_V2_CMD_NONE; if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") || cpu_mitigations_off()) return SPECTRE_V2_CMD_NONE; ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); if (ret < 0) - return SPECTRE_V2_CMD_AUTO; + return cmd; for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { if (!match_option(arg, ret, mitigation_options[i].option)) @@ -1467,8 +1470,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", arg); - return SPECTRE_V2_CMD_AUTO; + pr_err("unknown option (%s). Switching to default mode\n", arg); + return cmd; } if ((cmd == SPECTRE_V2_CMD_RETPOLINE || @@ -2021,10 +2024,12 @@ static const struct { static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) { - enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO; + enum ssb_mitigation_cmd cmd; char arg[20]; int ret, i; + cmd = IS_ENABLED(CONFIG_MITIGATION_SSB) ? + SPEC_STORE_BYPASS_CMD_AUTO : SPEC_STORE_BYPASS_CMD_NONE; if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") || cpu_mitigations_off()) { return SPEC_STORE_BYPASS_CMD_NONE; @@ -2032,7 +2037,7 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", arg, sizeof(arg)); if (ret < 0) - return SPEC_STORE_BYPASS_CMD_AUTO; + return cmd; for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) { if (!match_option(arg, ret, ssb_mitigation_options[i].option)) @@ -2043,8 +2048,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) } if (i >= ARRAY_SIZE(ssb_mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", arg); - return SPEC_STORE_BYPASS_CMD_AUTO; + pr_err("unknown option (%s). Switching to default mode\n", arg); + return cmd; } } @@ -2371,7 +2376,8 @@ EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); #define pr_fmt(fmt) "L1TF: " fmt /* Default mitigation for L1TF-affected CPUs */ -enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH; +enum l1tf_mitigations l1tf_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_L1TF) ? L1TF_MITIGATION_FLUSH : L1TF_MITIGATION_OFF; #if IS_ENABLED(CONFIG_KVM_INTEL) EXPORT_SYMBOL_GPL(l1tf_mitigation); #endif @@ -2551,10 +2557,9 @@ static void __init srso_select_mitigation(void) { bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE); - if (cpu_mitigations_off()) - return; - - if (!boot_cpu_has_bug(X86_BUG_SRSO)) { + if (!boot_cpu_has_bug(X86_BUG_SRSO) || + cpu_mitigations_off() || + srso_cmd == SRSO_CMD_OFF) { if (boot_cpu_has(X86_FEATURE_SBPB)) x86_pred_cmd = PRED_CMD_SBPB; return; @@ -2585,11 +2590,6 @@ static void __init srso_select_mitigation(void) } switch (srso_cmd) { - case SRSO_CMD_OFF: - if (boot_cpu_has(X86_FEATURE_SBPB)) - x86_pred_cmd = PRED_CMD_SBPB; - return; - case SRSO_CMD_MICROCODE: if (has_microcode) { srso_mitigation = SRSO_MITIGATION_MICROCODE; @@ -2643,6 +2643,8 @@ static void __init srso_select_mitigation(void) pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); } break; + default: + break; } out: diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d4e539d4e158..07a34d723505 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1165,8 +1165,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(INTEL_CORE_YONAH, NO_SSB), - VULNWL_INTEL(INTEL_ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(INTEL_ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(INTEL_ATOM_AIRMONT_MID, NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY), + VULNWL_INTEL(INTEL_ATOM_AIRMONT_NP, NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(INTEL_ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), VULNWL_INTEL(INTEL_ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), @@ -1510,6 +1510,11 @@ static void __init cpu_parse_early_param(void) if (cmdline_find_option_bool(boot_command_line, "nousershstk")) setup_clear_cpu_cap(X86_FEATURE_USER_SHSTK); + /* Minimize the gap between FRED is available and available but disabled. */ + arglen = cmdline_find_option(boot_command_line, "fred", arg, sizeof(arg)); + if (arglen != 2 || strncmp(arg, "on", 2)) + setup_clear_cpu_cap(X86_FEATURE_FRED); + arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg)); if (arglen <= 0) return; @@ -2171,7 +2176,7 @@ static inline void tss_setup_io_bitmap(struct tss_struct *tss) * Setup everything needed to handle exceptions from the IDT, including the IST * exceptions which use paranoid_entry(). */ -void cpu_init_exception_handling(void) +void cpu_init_exception_handling(bool boot_cpu) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); int cpu = raw_smp_processor_id(); @@ -2190,10 +2195,23 @@ void cpu_init_exception_handling(void) /* GHCB needs to be setup to handle #VC. */ setup_ghcb(); + if (cpu_feature_enabled(X86_FEATURE_FRED)) { + /* The boot CPU has enabled FRED during early boot */ + if (!boot_cpu) + cpu_init_fred_exceptions(); + + cpu_init_fred_rsps(); + } else { + load_current_idt(); + } +} + +void __init cpu_init_replace_early_idt(void) +{ if (cpu_feature_enabled(X86_FEATURE_FRED)) cpu_init_fred_exceptions(); else - load_current_idt(); + idt_setup_early_pf(); } /* diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index b7d9f530ae16..8bd84114c2d9 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -83,7 +83,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, { X86_FEATURE_SHSTK, X86_FEATURE_XSAVES }, { X86_FEATURE_FRED, X86_FEATURE_LKGS }, - { X86_FEATURE_FRED, X86_FEATURE_WRMSRNS }, {} }; diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index 1640ae76548f..4a4118784c13 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -188,7 +188,7 @@ update_caps: update_sgx: if (!(msr & FEAT_CTL_SGX_ENABLED)) { if (enable_sgx_kvm || enable_sgx_driver) - pr_err_once("SGX disabled by BIOS.\n"); + pr_err_once("SGX disabled or unsupported by BIOS.\n"); clear_cpu_cap(c, X86_FEATURE_SGX); return; } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 08b95a35b5cb..e7656cbef68d 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -311,16 +311,18 @@ static void early_init_intel(struct cpuinfo_x86 *c) } /* - * There is a known erratum on Pentium III and Core Solo - * and Core Duo CPUs. - * " Page with PAT set to WC while associated MTRR is UC - * may consolidate to UC " - * Because of this erratum, it is better to stick with - * setting WC in MTRR rather than using PAT on these CPUs. + * PAT is broken on early family 6 CPUs, the last of which + * is "Yonah" where the erratum is named "AN7": * - * Enable PAT WC only on P4, Core 2 or later CPUs. + * Page with PAT (Page Attribute Table) Set to USWC + * (Uncacheable Speculative Write Combine) While + * Associated MTRR (Memory Type Range Register) Is UC + * (Uncacheable) May Consolidate to UC + * + * Disable PAT and fall back to MTRR on these CPUs. */ - if (c->x86 == 6 && c->x86_model < 15) + if (c->x86_vfm >= INTEL_PENTIUM_PRO && + c->x86_vfm <= INTEL_CORE_YONAH) clear_cpu_cap(c, X86_FEATURE_PAT); /* diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 9a0133ef7e20..14bf8c232e45 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -780,7 +780,7 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) { struct mce m; - mce_setup(&m); + mce_prep_record(&m); m.status = status; m.misc = misc; diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 7f7309ff67d0..3885fe05f01e 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -44,7 +44,7 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) else lsb = PAGE_SHIFT; - mce_setup(&m); + mce_prep_record(&m); m.bank = -1; /* Fake a memory read error with unknown channel */ m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f; @@ -66,6 +66,7 @@ EXPORT_SYMBOL_GPL(apei_mce_report_mem_error); int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) { const u64 *i_mce = ((const u64 *) (ctx_info + 1)); + bool apicid_found = false; unsigned int cpu; struct mce m; @@ -97,20 +98,19 @@ int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) if (ctx_info->reg_arr_size < 48) return -EINVAL; - mce_setup(&m); - - m.extcpu = -1; - m.socketid = -1; - for_each_possible_cpu(cpu) { if (cpu_data(cpu).topo.initial_apicid == lapic_id) { - m.extcpu = cpu; - m.socketid = cpu_data(m.extcpu).topo.pkg_id; + apicid_found = true; break; } } - m.apicid = lapic_id; + if (!apicid_found) + return -EINVAL; + + mce_prep_record_common(&m); + mce_prep_record_per_cpu(cpu, &m); + m.bank = (ctx_info->msr_addr >> 4) & 0xFF; m.status = *i_mce; m.addr = *(i_mce + 1); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index b85ec7a4ec9e..2a938f429c4d 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -117,20 +117,32 @@ static struct irq_work mce_irq_work; */ BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); -/* Do initial initialization of a struct mce */ -void mce_setup(struct mce *m) +void mce_prep_record_common(struct mce *m) { memset(m, 0, sizeof(struct mce)); - m->cpu = m->extcpu = smp_processor_id(); + + m->cpuid = cpuid_eax(1); + m->cpuvendor = boot_cpu_data.x86_vendor; + m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP); /* need the internal __ version to avoid deadlocks */ - m->time = __ktime_get_real_seconds(); - m->cpuvendor = boot_cpu_data.x86_vendor; - m->cpuid = cpuid_eax(1); - m->socketid = cpu_data(m->extcpu).topo.pkg_id; - m->apicid = cpu_data(m->extcpu).topo.initial_apicid; - m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP); - m->ppin = cpu_data(m->extcpu).ppin; - m->microcode = boot_cpu_data.microcode; + m->time = __ktime_get_real_seconds(); +} + +void mce_prep_record_per_cpu(unsigned int cpu, struct mce *m) +{ + m->cpu = cpu; + m->extcpu = cpu; + m->apicid = cpu_data(cpu).topo.initial_apicid; + m->microcode = cpu_data(cpu).microcode; + m->ppin = topology_ppin(cpu); + m->socketid = topology_physical_package_id(cpu); +} + +/* Do initial initialization of a struct mce */ +void mce_prep_record(struct mce *m) +{ + mce_prep_record_common(m); + mce_prep_record_per_cpu(smp_processor_id(), m); } DEFINE_PER_CPU(struct mce, injectm); @@ -436,11 +448,11 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v) static noinstr void mce_gather_info(struct mce *m, struct pt_regs *regs) { /* - * Enable instrumentation around mce_setup() which calls external + * Enable instrumentation around mce_prep_record() which calls external * facilities. */ instrumentation_begin(); - mce_setup(m); + mce_prep_record(m); instrumentation_end(); m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index a05ac0716ecf..af44fd5dbd7c 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -314,7 +314,7 @@ static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, /* * Need to give user space some time to set everything up, - * so do it a jiffie or two later everywhere. + * so do it a jiffy or two later everywhere. */ schedule_timeout(2); @@ -331,7 +331,6 @@ static const struct file_operations mce_chrdev_ops = { .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static struct miscdevice mce_chrdev_device = { diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 01f8f03969e6..43c7f3b71df5 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -261,6 +261,8 @@ enum mca_msr { /* Decide whether to add MCE record to MCE event pool or filter it out. */ extern bool filter_mce(struct mce *m); +void mce_prep_record_common(struct mce *m); +void mce_prep_record_per_cpu(unsigned int cpu, struct mce *m); #ifdef CONFIG_X86_MCE_AMD extern bool amd_filter_mce(struct mce *m); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index c0d56c02b8da..f63b051f25a0 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -89,6 +89,31 @@ static struct equiv_cpu_table { struct equiv_cpu_entry *entry; } equiv_table; +union zen_patch_rev { + struct { + __u32 rev : 8, + stepping : 4, + model : 4, + __reserved : 4, + ext_model : 4, + ext_fam : 8; + }; + __u32 ucode_rev; +}; + +union cpuid_1_eax { + struct { + __u32 stepping : 4, + model : 4, + family : 4, + __reserved0 : 4, + ext_model : 4, + ext_fam : 8, + __reserved1 : 4; + }; + __u32 full; +}; + /* * This points to the current valid container of microcode patches which we will * save from the initrd/builtin before jettisoning its contents. @mc is the @@ -96,7 +121,6 @@ static struct equiv_cpu_table { */ struct cont_desc { struct microcode_amd *mc; - u32 cpuid_1_eax; u32 psize; u8 *data; size_t size; @@ -109,10 +133,42 @@ struct cont_desc { static const char ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin"; +/* + * This is CPUID(1).EAX on the BSP. It is used in two ways: + * + * 1. To ignore the equivalence table on Zen1 and newer. + * + * 2. To match which patches to load because the patch revision ID + * already contains the f/m/s for which the microcode is destined + * for. + */ +static u32 bsp_cpuid_1_eax __ro_after_init; + +static union cpuid_1_eax ucode_rev_to_cpuid(unsigned int val) +{ + union zen_patch_rev p; + union cpuid_1_eax c; + + p.ucode_rev = val; + c.full = 0; + + c.stepping = p.stepping; + c.model = p.model; + c.ext_model = p.ext_model; + c.family = 0xf; + c.ext_fam = p.ext_fam; + + return c; +} + static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig) { unsigned int i; + /* Zen and newer do not need an equivalence table. */ + if (x86_family(bsp_cpuid_1_eax) >= 0x17) + return 0; + if (!et || !et->num_entries) return 0; @@ -159,6 +215,10 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size) if (!verify_container(buf, buf_size)) return false; + /* Zen and newer do not need an equivalence table. */ + if (x86_family(bsp_cpuid_1_eax) >= 0x17) + return true; + cont_type = hdr[1]; if (cont_type != UCODE_EQUIV_CPU_TABLE_TYPE) { pr_debug("Wrong microcode container equivalence table type: %u.\n", @@ -222,8 +282,9 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize) * exceed the per-family maximum). @sh_psize is the size read from the section * header. */ -static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size) +static unsigned int __verify_patch_size(u32 sh_psize, size_t buf_size) { + u8 family = x86_family(bsp_cpuid_1_eax); u32 max_size; if (family >= 0x15) @@ -258,9 +319,9 @@ static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size * positive: patch is not for this family, skip it * 0: success */ -static int -verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size) +static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size) { + u8 family = x86_family(bsp_cpuid_1_eax); struct microcode_header_amd *mc_hdr; unsigned int ret; u32 sh_psize; @@ -286,7 +347,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size) return -1; } - ret = __verify_patch_size(family, sh_psize, buf_size); + ret = __verify_patch_size(sh_psize, buf_size); if (!ret) { pr_debug("Per-family patch size mismatch.\n"); return -1; @@ -308,6 +369,15 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size) return 0; } +static bool mc_patch_matches(struct microcode_amd *mc, u16 eq_id) +{ + /* Zen and newer do not need an equivalence table. */ + if (x86_family(bsp_cpuid_1_eax) >= 0x17) + return ucode_rev_to_cpuid(mc->hdr.patch_id).full == bsp_cpuid_1_eax; + else + return eq_id == mc->hdr.processor_rev_id; +} + /* * This scans the ucode blob for the proper container as we can have multiple * containers glued together. Returns the equivalence ID from the equivalence @@ -336,7 +406,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) * doesn't contain a patch for the CPU, scan through the whole container * so that it can be skipped in case there are other containers appended. */ - eq_id = find_equiv_id(&table, desc->cpuid_1_eax); + eq_id = find_equiv_id(&table, bsp_cpuid_1_eax); buf += hdr[2] + CONTAINER_HDR_SZ; size -= hdr[2] + CONTAINER_HDR_SZ; @@ -350,7 +420,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) u32 patch_size; int ret; - ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size); + ret = verify_patch(buf, size, &patch_size); if (ret < 0) { /* * Patch verification failed, skip to the next container, if @@ -363,7 +433,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) } mc = (struct microcode_amd *)(buf + SECTION_HDR_SIZE); - if (eq_id == mc->hdr.processor_rev_id) { + if (mc_patch_matches(mc, eq_id)) { desc->psize = patch_size; desc->mc = mc; } @@ -421,6 +491,7 @@ static int __apply_microcode_amd(struct microcode_amd *mc) /* verify patch application was successful */ native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (rev != mc->hdr.patch_id) return -1; @@ -438,14 +509,12 @@ static int __apply_microcode_amd(struct microcode_amd *mc) * * Returns true if container found (sets @desc), false otherwise. */ -static bool early_apply_microcode(u32 cpuid_1_eax, u32 old_rev, void *ucode, size_t size) +static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size) { struct cont_desc desc = { 0 }; struct microcode_amd *mc; bool ret = false; - desc.cpuid_1_eax = cpuid_1_eax; - scan_containers(ucode, size, &desc); mc = desc.mc; @@ -463,9 +532,10 @@ static bool early_apply_microcode(u32 cpuid_1_eax, u32 old_rev, void *ucode, siz return !__apply_microcode_amd(mc); } -static bool get_builtin_microcode(struct cpio_data *cp, u8 family) +static bool get_builtin_microcode(struct cpio_data *cp) { char fw_name[36] = "amd-ucode/microcode_amd.bin"; + u8 family = x86_family(bsp_cpuid_1_eax); struct firmware fw; if (IS_ENABLED(CONFIG_X86_32)) @@ -484,11 +554,11 @@ static bool get_builtin_microcode(struct cpio_data *cp, u8 family) return false; } -static void __init find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret) +static void __init find_blobs_in_containers(struct cpio_data *ret) { struct cpio_data cp; - if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax))) + if (!get_builtin_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path); *ret = cp; @@ -499,16 +569,18 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_ struct cpio_data cp = { }; u32 dummy; + bsp_cpuid_1_eax = cpuid_1_eax; + native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->old_rev, dummy); /* Needed in load_microcode_amd() */ ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax; - find_blobs_in_containers(cpuid_1_eax, &cp); + find_blobs_in_containers(&cp); if (!(cp.data && cp.size)) return; - if (early_apply_microcode(cpuid_1_eax, ed->old_rev, cp.data, cp.size)) + if (early_apply_microcode(ed->old_rev, cp.data, cp.size)) native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy); } @@ -525,12 +597,10 @@ static int __init save_microcode_in_initrd(void) if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) return 0; - find_blobs_in_containers(cpuid_1_eax, &cp); + find_blobs_in_containers(&cp); if (!(cp.data && cp.size)) return -EINVAL; - desc.cpuid_1_eax = cpuid_1_eax; - scan_containers(cp.data, cp.size, &desc); if (!desc.mc) return -EINVAL; @@ -543,26 +613,65 @@ static int __init save_microcode_in_initrd(void) } early_initcall(save_microcode_in_initrd); +static inline bool patch_cpus_equivalent(struct ucode_patch *p, struct ucode_patch *n) +{ + /* Zen and newer hardcode the f/m/s in the patch ID */ + if (x86_family(bsp_cpuid_1_eax) >= 0x17) { + union cpuid_1_eax p_cid = ucode_rev_to_cpuid(p->patch_id); + union cpuid_1_eax n_cid = ucode_rev_to_cpuid(n->patch_id); + + /* Zap stepping */ + p_cid.stepping = 0; + n_cid.stepping = 0; + + return p_cid.full == n_cid.full; + } else { + return p->equiv_cpu == n->equiv_cpu; + } +} + /* * a small, trivial cache of per-family ucode patches */ -static struct ucode_patch *cache_find_patch(u16 equiv_cpu) +static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equiv_cpu) { struct ucode_patch *p; + struct ucode_patch n; + + n.equiv_cpu = equiv_cpu; + n.patch_id = uci->cpu_sig.rev; + + WARN_ON_ONCE(!n.patch_id); list_for_each_entry(p, µcode_cache, plist) - if (p->equiv_cpu == equiv_cpu) + if (patch_cpus_equivalent(p, &n)) return p; + return NULL; } +static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n) +{ + /* Zen and newer hardcode the f/m/s in the patch ID */ + if (x86_family(bsp_cpuid_1_eax) >= 0x17) { + union zen_patch_rev zp, zn; + + zp.ucode_rev = p->patch_id; + zn.ucode_rev = n->patch_id; + + return zn.rev > zp.rev; + } else { + return n->patch_id > p->patch_id; + } +} + static void update_cache(struct ucode_patch *new_patch) { struct ucode_patch *p; list_for_each_entry(p, µcode_cache, plist) { - if (p->equiv_cpu == new_patch->equiv_cpu) { - if (p->patch_id >= new_patch->patch_id) { + if (patch_cpus_equivalent(p, new_patch)) { + if (!patch_newer(p, new_patch)) { /* we already have the latest patch */ kfree(new_patch->data); kfree(new_patch); @@ -593,13 +702,22 @@ static void free_cache(void) static struct ucode_patch *find_patch(unsigned int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - u16 equiv_id; + u32 rev, dummy __always_unused; + u16 equiv_id = 0; - equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig); - if (!equiv_id) - return NULL; + /* fetch rev if not populated yet: */ + if (!uci->cpu_sig.rev) { + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + uci->cpu_sig.rev = rev; + } + + if (x86_family(bsp_cpuid_1_eax) < 0x17) { + equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig); + if (!equiv_id) + return NULL; + } - return cache_find_patch(equiv_id); + return cache_find_patch(uci, equiv_id); } void reload_ucode_amd(unsigned int cpu) @@ -649,7 +767,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct ucode_cpu_info *uci; struct ucode_patch *p; enum ucode_state ret; - u32 rev, dummy __always_unused; + u32 rev; BUG_ON(raw_smp_processor_id() != cpu); @@ -659,11 +777,11 @@ static enum ucode_state apply_microcode_amd(int cpu) if (!p) return UCODE_NFOUND; + rev = uci->cpu_sig.rev; + mc_amd = p->data; uci->mc = p->data; - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - /* need to apply patch? */ if (rev > mc_amd->hdr.patch_id) { ret = UCODE_OK; @@ -709,6 +827,10 @@ static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size) hdr = (const u32 *)buf; equiv_tbl_len = hdr[2]; + /* Zen and newer do not need an equivalence table. */ + if (x86_family(bsp_cpuid_1_eax) >= 0x17) + goto out; + equiv_table.entry = vmalloc(equiv_tbl_len); if (!equiv_table.entry) { pr_err("failed to allocate equivalent CPU table\n"); @@ -718,12 +840,16 @@ static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size) memcpy(equiv_table.entry, buf + CONTAINER_HDR_SZ, equiv_tbl_len); equiv_table.num_entries = equiv_tbl_len / sizeof(struct equiv_cpu_entry); +out: /* add header length */ return equiv_tbl_len + CONTAINER_HDR_SZ; } static void free_equiv_cpu_table(void) { + if (x86_family(bsp_cpuid_1_eax) >= 0x17) + return; + vfree(equiv_table.entry); memset(&equiv_table, 0, sizeof(equiv_table)); } @@ -749,7 +875,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover, u16 proc_id; int ret; - ret = verify_patch(family, fw, leftover, patch_size); + ret = verify_patch(fw, leftover, patch_size); if (ret) return ret; @@ -774,7 +900,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover, patch->patch_id = mc_hdr->patch_id; patch->equiv_cpu = proc_id; - pr_debug("%s: Added patch_id: 0x%08x, proc_id: 0x%04x\n", + pr_debug("%s: Adding patch_id: 0x%08x, proc_id: 0x%04x\n", __func__, patch->patch_id, proc_id); /* ... and add to cache. */ diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e0fd57a8ba84..d18078834ded 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -16,7 +16,6 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kexec.h> -#include <linux/i8253.h> #include <linux/random.h> #include <asm/processor.h> #include <asm/hypervisor.h> @@ -199,8 +198,8 @@ static void hv_machine_shutdown(void) * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor * corrupts the old VP Assist Pages and can crash the kexec kernel. */ - if (kexec_in_progress && hyperv_init_cpuhp > 0) - cpuhp_remove_state(hyperv_init_cpuhp); + if (kexec_in_progress) + cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE); /* The function calls stop_other_cpus(). */ native_machine_shutdown(); @@ -424,6 +423,7 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { x86_platform.calibrate_tsc = hv_get_tsc_khz; x86_platform.calibrate_cpu = hv_get_tsc_khz; + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); } if (ms_hyperv.priv_high & HV_ISOLATION) { @@ -449,9 +449,23 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.hints &= ~HV_X64_APIC_ACCESS_RECOMMENDED; if (!ms_hyperv.paravisor_present) { - /* To be supported: more work is required. */ + /* + * Mark the Hyper-V TSC page feature as disabled + * in a TDX VM without paravisor so that the + * Invariant TSC, which is a better clocksource + * anyway, is used instead. + */ ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE; + /* + * The Invariant TSC is expected to be available + * in a TDX VM without paravisor, but if not, + * print a warning message. The slower Hyper-V MSR-based + * Ref Counter should end up being the clocksource. + */ + if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT)) + pr_warn("Hyper-V: Invariant TSC is unavailable\n"); + /* HV_MSR_CRASH_CTL is unsupported. */ ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; @@ -522,16 +536,6 @@ static void __init ms_hyperv_init_platform(void) if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; - /* - * Hyper-V VMs have a PIT emulation quirk such that zeroing the - * counter register during PIT shutdown restarts the PIT. So it - * continues to interrupt @18.2 HZ. Setting i8253_clear_counter - * to false tells pit_shutdown() not to zero the counter so that - * the PIT really is shutdown. Generation 2 VMs don't have a PIT, - * and setting this value has no effect. - */ - i8253_clear_counter_on_shutdown = false; - #if IS_ENABLED(CONFIG_HYPERV) if ((hv_get_isolation_type() == HV_ISOLATION_TYPE_VBS) || ms_hyperv.paravisor_present) diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index e69489d48625..972e6b6b0481 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -1567,7 +1567,6 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) static const struct file_operations pseudo_lock_dev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = NULL, .write = NULL, .open = pseudo_lock_dev_open, diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 27892e57c4ef..9ace84486499 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -475,24 +475,25 @@ struct sgx_epc_page *__sgx_alloc_epc_page(void) { struct sgx_epc_page *page; int nid_of_current = numa_node_id(); - int nid = nid_of_current; + int nid_start, nid; - if (node_isset(nid_of_current, sgx_numa_mask)) { - page = __sgx_alloc_epc_page_from_node(nid_of_current); - if (page) - return page; - } - - /* Fall back to the non-local NUMA nodes: */ - while (true) { - nid = next_node_in(nid, sgx_numa_mask); - if (nid == nid_of_current) - break; + /* + * Try local node first. If it doesn't have an EPC section, + * fall back to the non-local NUMA nodes. + */ + if (node_isset(nid_of_current, sgx_numa_mask)) + nid_start = nid_of_current; + else + nid_start = next_node_in(nid_of_current, sgx_numa_mask); + nid = nid_start; + do { page = __sgx_alloc_epc_page_from_node(nid); if (page) return page; - } + + nid = next_node_in(nid, sgx_numa_mask); + } while (nid != nid_start); return ERR_PTR(-ENOMEM); } @@ -732,7 +733,7 @@ out: return 0; } -/** +/* * A section metric is concatenated in a way that @low bits 12-31 define the * bits 12-31 of the metric and @high bits 0-19 define the bits 32-51 of the * metric. @@ -847,6 +848,13 @@ static bool __init sgx_page_cache_init(void) return false; } + for_each_online_node(nid) { + if (!node_isset(nid, sgx_numa_mask) && + node_state(nid, N_MEMORY) && node_state(nid, N_CPU)) + pr_info("node%d has both CPUs and memory but doesn't have an EPC section\n", + nid); + } + return true; } @@ -895,10 +903,10 @@ int sgx_set_attribute(unsigned long *allowed_attributes, { struct fd f = fdget(attribute_fd); - if (!f.file) + if (!fd_file(f)) return -EINVAL; - if (f.file->f_op != &sgx_provision_fops) { + if (fd_file(f)->f_op != &sgx_provision_fops) { fdput(f); return -EINVAL; } diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index 53935b4d62e3..9535a6507db7 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -11,15 +11,15 @@ static __init int eisa_bus_probe(void) { - void __iomem *p; + u32 *p; if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return 0; - p = ioremap(0x0FFFD9, 4); - if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24)) + p = memremap(0x0FFFD9, 4, MEMREMAP_WB); + if (p && *p == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24)) EISA_bus = 1; - iounmap(p); + memunmap(p); return 0; } subsys_initcall(eisa_bus_probe); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 247f2225aa9f..1065ab995305 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -64,6 +64,16 @@ setfx: } /* + * Update the value of PKRU register that was already pushed onto the signal frame. + */ +static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru) +{ + if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) + return 0; + return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU)); +} + +/* * Signal frame handlers. */ static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf) @@ -156,10 +166,17 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, return !err; } -static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) +static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru) { - if (use_xsave()) - return xsave_to_user_sigframe(buf); + int err = 0; + + if (use_xsave()) { + err = xsave_to_user_sigframe(buf); + if (!err) + err = update_pkru_in_sigframe(buf, pkru); + return err; + } + if (use_fxsr()) return fxsave_to_user_sigframe((struct fxregs_state __user *) buf); else @@ -185,7 +202,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) * For [f]xsave state, update the SW reserved fields in the [f]xsave frame * indicating the absence/presence of the extended state to the user. */ -bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) +bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru) { struct task_struct *tsk = current; struct fpstate *fpstate = tsk->thread.fpu.fpstate; @@ -228,7 +245,7 @@ retry: fpregs_restore_userregs(); pagefault_disable(); - ret = copy_fpregs_to_sigframe(buf_fx); + ret = copy_fpregs_to_sigframe(buf_fx, pkru); pagefault_enable(); fpregs_unlock(); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1339f8328db5..22abb5ee0cf2 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -13,6 +13,7 @@ #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/vmalloc.h> +#include <linux/coredump.h> #include <asm/fpu/api.h> #include <asm/fpu/regset.h> @@ -23,6 +24,8 @@ #include <asm/prctl.h> #include <asm/elf.h> +#include <uapi/asm/elf.h> + #include "context.h" #include "internal.h" #include "legacy.h" @@ -996,6 +999,19 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) } EXPORT_SYMBOL_GPL(get_xsave_addr); +/* + * Given an xstate feature nr, calculate where in the xsave buffer the state is. + * The xsave buffer should be in standard format, not compacted (e.g. user mode + * signal frames). + */ +void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr) +{ + if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) + return NULL; + + return (void __user *)xsave + xstate_offsets[xfeature_nr]; +} + #ifdef CONFIG_ARCH_HAS_PKEYS /* @@ -1841,3 +1857,89 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, return 0; } #endif /* CONFIG_PROC_PID_ARCH_STATUS */ + +#ifdef CONFIG_COREDUMP +static const char owner_name[] = "LINUX"; + +/* + * Dump type, size, offset and flag values for every xfeature that is present. + */ +static int dump_xsave_layout_desc(struct coredump_params *cprm) +{ + int num_records = 0; + int i; + + for_each_extended_xfeature(i, fpu_user_cfg.max_features) { + struct x86_xfeat_component xc = { + .type = i, + .size = xstate_sizes[i], + .offset = xstate_offsets[i], + /* reserved for future use */ + .flags = 0, + }; + + if (!dump_emit(cprm, &xc, sizeof(xc))) + return 0; + + num_records++; + } + return num_records; +} + +static u32 get_xsave_desc_size(void) +{ + u32 cnt = 0; + u32 i; + + for_each_extended_xfeature(i, fpu_user_cfg.max_features) + cnt++; + + return cnt * (sizeof(struct x86_xfeat_component)); +} + +int elf_coredump_extra_notes_write(struct coredump_params *cprm) +{ + int num_records = 0; + struct elf_note en; + + if (!fpu_user_cfg.max_features) + return 0; + + en.n_namesz = sizeof(owner_name); + en.n_descsz = get_xsave_desc_size(); + en.n_type = NT_X86_XSAVE_LAYOUT; + + if (!dump_emit(cprm, &en, sizeof(en))) + return 1; + if (!dump_emit(cprm, owner_name, en.n_namesz)) + return 1; + if (!dump_align(cprm, 4)) + return 1; + + num_records = dump_xsave_layout_desc(cprm); + if (!num_records) + return 1; + + /* Total size should be equal to the number of records */ + if ((sizeof(struct x86_xfeat_component) * num_records) != en.n_descsz) + return 1; + + return 0; +} + +int elf_coredump_extra_notes_size(void) +{ + int size; + + if (!fpu_user_cfg.max_features) + return 0; + + /* .note header */ + size = sizeof(struct elf_note); + /* Name plus alignment to 4 bytes */ + size += roundup(sizeof(owner_name), 4); + size += get_xsave_desc_size(); + + return size; +} +#endif /* CONFIG_COREDUMP */ diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index afb404cd2059..0b86a5002c84 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -54,6 +54,8 @@ extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void extern void fpu__init_cpu_xstate(void); extern void fpu__init_system_xstate(unsigned int legacy_size); +extern void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr); + static inline u64 xfeatures_mask_supervisor(void) { return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED; diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c index 4bcd8791ad96..8d32c3f48abc 100644 --- a/arch/x86/kernel/fred.c +++ b/arch/x86/kernel/fred.c @@ -21,17 +21,53 @@ #define FRED_STKLVL(vector, lvl) ((lvl) << (2 * (vector))) +DEFINE_PER_CPU(unsigned long, fred_rsp0); +EXPORT_PER_CPU_SYMBOL(fred_rsp0); + void cpu_init_fred_exceptions(void) { /* When FRED is enabled by default, remove this log message */ pr_info("Initialize FRED on CPU%d\n", smp_processor_id()); + /* + * If a kernel event is delivered before a CPU goes to user level for + * the first time, its SS is NULL thus NULL is pushed into the SS field + * of the FRED stack frame. But before ERETS is executed, the CPU may + * context switch to another task and go to user level. Then when the + * CPU comes back to kernel mode, SS is changed to __KERNEL_DS. Later + * when ERETS is executed to return from the kernel event handler, a #GP + * fault is generated because SS doesn't match the SS saved in the FRED + * stack frame. + * + * Initialize SS to __KERNEL_DS when enabling FRED to avoid such #GPs. + */ + loadsegment(ss, __KERNEL_DS); + wrmsrl(MSR_IA32_FRED_CONFIG, /* Reserve for CALL emulation */ FRED_CONFIG_REDZONE | FRED_CONFIG_INT_STKLVL(0) | FRED_CONFIG_ENTRYPOINT(asm_fred_entrypoint_user)); + wrmsrl(MSR_IA32_FRED_STKLVLS, 0); + wrmsrl(MSR_IA32_FRED_RSP0, 0); + wrmsrl(MSR_IA32_FRED_RSP1, 0); + wrmsrl(MSR_IA32_FRED_RSP2, 0); + wrmsrl(MSR_IA32_FRED_RSP3, 0); + + /* Enable FRED */ + cr4_set_bits(X86_CR4_FRED); + /* Any further IDT use is a bug */ + idt_invalidate(); + + /* Use int $0x80 for 32-bit system calls in FRED mode */ + setup_clear_cpu_cap(X86_FEATURE_SYSENTER32); + setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); +} + +/* Must be called after setup_cpu_entry_areas() */ +void cpu_init_fred_rsps(void) +{ /* * The purpose of separate stacks for NMI, #DB and #MC *in the kernel* * (remember that user space faults are always taken on stack level 0) @@ -47,13 +83,4 @@ void cpu_init_fred_exceptions(void) wrmsrl(MSR_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB)); wrmsrl(MSR_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI)); wrmsrl(MSR_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF)); - - /* Enable FRED */ - cr4_set_bits(X86_CR4_FRED); - /* Any further IDT use is a bug */ - idt_invalidate(); - - /* Use int $0x80 for 32-bit system calls in FRED mode */ - setup_clear_cpu_cap(X86_FEATURE_SYSENTER32); - setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index a817ed0724d1..4b9d4557fc94 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -559,10 +559,11 @@ void early_setup_idt(void) */ void __head startup_64_setup_gdt_idt(void) { + struct desc_struct *gdt = (void *)(__force unsigned long)init_per_cpu_var(gdt_page.gdt); void *handler = NULL; struct desc_ptr startup_gdt_descr = { - .address = (unsigned long)&RIP_REL_REF(init_per_cpu_var(gdt_page.gdt)), + .address = (unsigned long)&RIP_REL_REF(*gdt), .size = GDT_SIZE - 1, }; diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 330922b328bf..16752b8dfa89 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -32,13 +32,6 @@ * We are not able to switch in one step to the final KERNEL ADDRESS SPACE * because we need identity-mapped pages. */ -#define l4_index(x) (((x) >> 39) & 511) -#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) - -L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4) -L4_START_KERNEL = l4_index(__START_KERNEL_map) - -L3_START_KERNEL = pud_index(__START_KERNEL_map) __HEAD .code64 @@ -577,9 +570,6 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb) SYM_CODE_END(vc_no_ghcb) #endif -#define SYM_DATA_START_PAGE_ALIGNED(name) \ - SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) - #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Each PGD needs to be 8k long and 8k aligned. We do not @@ -601,14 +591,6 @@ SYM_CODE_END(vc_no_ghcb) #define PTI_USER_PGD_FILL 0 #endif -/* Automate the creation of 1 to 1 mapping pmd entries */ -#define PMDS(START, PERM, COUNT) \ - i = 0 ; \ - .rept (COUNT) ; \ - .quad (START) + (i << PMD_SHIFT) + (PERM) ; \ - i = i + 1 ; \ - .endr - __INITDATA .balign 4 @@ -708,8 +690,6 @@ SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt) .endr SYM_DATA_END(level1_fixmap_pgt) -#undef PMDS - .data .align 16 diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 2b7999a1a50a..80e262bb627f 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -8,6 +8,7 @@ #include <linux/timex.h> #include <linux/i8253.h> +#include <asm/hypervisor.h> #include <asm/apic.h> #include <asm/hpet.h> #include <asm/time.h> @@ -39,9 +40,15 @@ static bool __init use_pit(void) bool __init pit_timer_init(void) { - if (!use_pit()) + if (!use_pit()) { + /* + * Don't just ignore the PIT. Ensure it's stopped, because + * VMMs otherwise steal CPU time just to pointlessly waggle + * the (masked) IRQ. + */ + clockevent_i8253_disable(); return false; - + } clockevent_i8253_init(true); global_clock_event = &i8253_clockevent; return true; diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index df337860612d..cd8ed1edbf9e 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/reboot.h> #include <linux/serial_8250.h> +#include <linux/acpi.h> #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/acpi.h> diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index cc0f7f70b17b..9c9ac606893e 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -28,6 +28,7 @@ #include <asm/setup.h> #include <asm/set_memory.h> #include <asm/cpu.h> +#include <asm/efi.h> #ifdef CONFIG_ACPI /* @@ -87,6 +88,8 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p) { #ifdef CONFIG_EFI unsigned long mstart, mend; + void *kaddr; + int ret; if (!efi_enabled(EFI_BOOT)) return 0; @@ -102,6 +105,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p) if (!mstart) return 0; + ret = kernel_ident_mapping_init(info, level4p, mstart, mend); + if (ret) + return ret; + + kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB); + if (!kaddr) { + pr_err("Could not map UEFI system table\n"); + return -ENOMEM; + } + + mstart = efi_config_table; + + if (efi_enabled(EFI_64BIT)) { + efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr; + + mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables; + } else { + efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr; + + mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables; + } + + memunmap(kaddr); + return kernel_ident_mapping_init(info, level4p, mstart, mend); #endif return 0; diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index c94dec6a1834..1f54eedc3015 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -9,6 +9,7 @@ #include <linux/pci.h> #include <linux/dmi.h> #include <linux/range.h> +#include <linux/acpi.h> #include <asm/pci-direct.h> #include <linux/sort.h> diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index e89171b0347a..4a1b1b28abf9 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -68,7 +68,7 @@ static void __init mpc_oem_bus_info(struct mpc_bus *m, char *str) { memcpy(str, m->bustype, 6); str[6] = 0; - apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->busid, str); + apic_pr_verbose("Bus #%d is %s\n", m->busid, str); } static void __init MP_bus_info(struct mpc_bus *m) @@ -417,7 +417,7 @@ static unsigned long __init get_mpc_size(unsigned long physptr) mpc = early_memremap(physptr, PAGE_SIZE); size = mpc->length; early_memunmap(mpc, PAGE_SIZE); - apic_printk(APIC_VERBOSE, " mpc: %lx-%lx\n", physptr, physptr + size); + apic_pr_verbose(" mpc: %lx-%lx\n", physptr, physptr + size); return size; } @@ -560,8 +560,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) struct mpf_intel *mpf; int ret = 0; - apic_printk(APIC_VERBOSE, "Scan for SMP in [mem %#010lx-%#010lx]\n", - base, base + length - 1); + apic_pr_verbose("Scan for SMP in [mem %#010lx-%#010lx]\n", base, base + length - 1); BUILD_BUG_ON(sizeof(*mpf) != 16); while (length > 0) { @@ -683,13 +682,13 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) { int i; - apic_printk(APIC_VERBOSE, "OLD "); + apic_pr_verbose("OLD "); print_mp_irq_info(m); i = get_MP_intsrc_index(m); if (i > 0) { memcpy(m, &mp_irqs[i], sizeof(*m)); - apic_printk(APIC_VERBOSE, "NEW "); + apic_pr_verbose("NEW "); print_mp_irq_info(&mp_irqs[i]); return; } @@ -772,7 +771,7 @@ static int __init replace_intsrc_all(struct mpc_table *mpc, continue; if (nr_m_spare > 0) { - apic_printk(APIC_VERBOSE, "*NEW* found\n"); + apic_pr_verbose("*NEW* found\n"); nr_m_spare--; memcpy(m_spare[nr_m_spare], &mp_irqs[i], sizeof(mp_irqs[i])); m_spare[nr_m_spare] = NULL; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6d3d20e3e43a..226472332a70 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -798,6 +798,32 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) #define LAM_U57_BITS 6 +static void enable_lam_func(void *__mm) +{ + struct mm_struct *mm = __mm; + unsigned long lam; + + if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) { + lam = mm_lam_cr3_mask(mm); + write_cr3(__read_cr3() | lam); + cpu_tlbstate_update_lam(lam, mm_untag_mask(mm)); + } +} + +static void mm_enable_lam(struct mm_struct *mm) +{ + mm->context.lam_cr3_mask = X86_CR3_LAM_U57; + mm->context.untag_mask = ~GENMASK(62, 57); + + /* + * Even though the process must still be single-threaded at this + * point, kernel threads may be using the mm. IPI those kernel + * threads if they exist. + */ + on_each_cpu_mask(mm_cpumask(mm), enable_lam_func, mm, true); + set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags); +} + static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) { if (!cpu_feature_enabled(X86_FEATURE_LAM)) @@ -814,25 +840,21 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) if (mmap_write_lock_killable(mm)) return -EINTR; + /* + * MM_CONTEXT_LOCK_LAM is set on clone. Prevent LAM from + * being enabled unless the process is single threaded: + */ if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags)) { mmap_write_unlock(mm); return -EBUSY; } - if (!nr_bits) { - mmap_write_unlock(mm); - return -EINVAL; - } else if (nr_bits <= LAM_U57_BITS) { - mm->context.lam_cr3_mask = X86_CR3_LAM_U57; - mm->context.untag_mask = ~GENMASK(62, 57); - } else { + if (!nr_bits || nr_bits > LAM_U57_BITS) { mmap_write_unlock(mm); return -EINVAL; } - write_cr3(__read_cr3() | mm->context.lam_cr3_mask); - set_tlbstate_lam_mode(mm); - set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags); + mm_enable_lam(mm); mmap_write_unlock(mm); diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 042c9a0334e9..e9e88c342f75 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -170,6 +170,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) wbinvd .Lsme_off: + /* Save the preserve_context to %r11 as swap_pages clobbers %rcx. */ movq %rcx, %r11 call swap_pages @@ -258,7 +259,7 @@ SYM_CODE_END(virtual_mapped) /* Do the copies */ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) UNWIND_HINT_END_OF_STACK - movq %rdi, %rcx /* Put the page_list in %rcx */ + movq %rdi, %rcx /* Put the indirection_page in %rcx */ xorl %edi, %edi xorl %esi, %esi jmp 1f @@ -289,18 +290,21 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) movq %rcx, %rsi /* For ever source page do a copy */ andq $0xfffffffffffff000, %rsi - movq %rdi, %rdx - movq %rsi, %rax + movq %rdi, %rdx /* Save destination page to %rdx */ + movq %rsi, %rax /* Save source page to %rax */ + /* copy source page to swap page */ movq %r10, %rdi movl $512, %ecx rep ; movsq + /* copy destination page to source page */ movq %rax, %rdi movq %rdx, %rsi movl $512, %ecx rep ; movsq + /* copy swap page to destination page */ movq %rdx, %rdi movq %r10, %rsi movl $512, %ecx diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6129dc2ba784..f1fea506e20f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1039,7 +1039,12 @@ void __init setup_arch(char **cmdline_p) init_mem_mapping(); - idt_setup_early_pf(); + /* + * init_mem_mapping() relies on the early IDT page fault handling. + * Now either enable FRED or install the real page fault handler + * for 64-bit in the IDT. + */ + cpu_init_replace_early_idt(); /* * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 31b6f5dddfc2..5f441039b572 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -61,6 +61,24 @@ static inline int is_x32_frame(struct ksignal *ksig) } /* + * Enable all pkeys temporarily, so as to ensure that both the current + * execution stack as well as the alternate signal stack are writeable. + * The application can use any of the available pkeys to protect the + * alternate signal stack, and we don't know which one it is, so enable + * all. The PKRU register will be reset to init_pkru later in the flow, + * in fpu__clear_user_states(), and it is the application's responsibility + * to enable the appropriate pkey as the first step in the signal handler + * so that the handler does not segfault. + */ +static inline u32 sig_prepare_pkru(void) +{ + u32 orig_pkru = read_pkru(); + + write_pkru(0); + return orig_pkru; +} + +/* * Set up a signal frame. */ @@ -84,6 +102,7 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, unsigned long math_size = 0; unsigned long sp = regs->sp; unsigned long buf_fx = 0; + u32 pkru; /* redzone */ if (!ia32_frame) @@ -138,9 +157,17 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; } + /* Update PKRU to enable access to the alternate signal stack. */ + pkru = sig_prepare_pkru(); /* save i387 and extended state */ - if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size)) + if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size, pkru)) { + /* + * Restore PKRU to the original, user-defined value; disable + * extra pkeys enabled for the alternate signal stack, if any. + */ + write_pkru(pkru); return (void __user *)-1L; + } return (void __user *)sp; } diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 8a94053c5444..ee9453891901 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -260,13 +260,13 @@ SYSCALL_DEFINE0(rt_sigreturn) set_current_blocked(&set); - if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) + if (restore_altstack(&frame->uc.uc_stack)) goto badframe; - if (restore_signal_shadow_stack()) + if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; - if (restore_altstack(&frame->uc.uc_stack)) + if (restore_signal_shadow_stack()) goto badframe; return regs->ax; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0c35207320cb..766f092dab80 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -60,6 +60,7 @@ #include <linux/stackprotector.h> #include <linux/cpuhotplug.h> #include <linux/mc146818rtc.h> +#include <linux/acpi.h> #include <asm/acpi.h> #include <asm/cacheinfo.h> @@ -246,7 +247,7 @@ static void notrace start_secondary(void *unused) __flush_tlb_all(); } - cpu_init_exception_handling(); + cpu_init_exception_handling(false); /* * Load the microcode before reaching the AP alive synchronization diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 01d7cd85ef97..87f8c9a71c49 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -121,7 +121,7 @@ static inline unsigned long stack_guard_placement(vm_flags_t vm_flags) } unsigned long -arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, +arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; @@ -158,7 +158,7 @@ arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned l } unsigned long -arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr0, +arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { @@ -228,20 +228,5 @@ bottomup: * can happen with large stack limits and large mmap() * allocations. */ - return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); -} - -unsigned long -arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); -} - -unsigned long -arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) -{ - return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, 0); + return arch_get_unmapped_area(filp, addr0, len, pgoff, flags, 0); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4fa0b17e5043..d05392db5d0f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -42,6 +42,7 @@ #include <linux/hardirq.h> #include <linux/atomic.h> #include <linux/iommu.h> +#include <linux/ubsan.h> #include <asm/stacktrace.h> #include <asm/processor.h> @@ -91,6 +92,47 @@ __always_inline int is_valid_bugaddr(unsigned long addr) return *(unsigned short *)addr == INSN_UD2; } +/* + * Check for UD1 or UD2, accounting for Address Size Override Prefixes. + * If it's a UD1, get the ModRM byte to pass along to UBSan. + */ +__always_inline int decode_bug(unsigned long addr, u32 *imm) +{ + u8 v; + + if (addr < TASK_SIZE_MAX) + return BUG_NONE; + + v = *(u8 *)(addr++); + if (v == INSN_ASOP) + v = *(u8 *)(addr++); + if (v != OPCODE_ESCAPE) + return BUG_NONE; + + v = *(u8 *)(addr++); + if (v == SECOND_BYTE_OPCODE_UD2) + return BUG_UD2; + + if (!IS_ENABLED(CONFIG_UBSAN_TRAP) || v != SECOND_BYTE_OPCODE_UD1) + return BUG_NONE; + + /* Retrieve the immediate (type value) for the UBSAN UD1 */ + v = *(u8 *)(addr++); + if (X86_MODRM_RM(v) == 4) + addr++; + + *imm = 0; + if (X86_MODRM_MOD(v) == 1) + *imm = *(u8 *)addr; + else if (X86_MODRM_MOD(v) == 2) + *imm = *(u32 *)addr; + else + WARN_ONCE(1, "Unexpected MODRM_MOD: %u\n", X86_MODRM_MOD(v)); + + return BUG_UD1; +} + + static nokprobe_inline int do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str, struct pt_regs *regs, long error_code) @@ -216,6 +258,8 @@ static inline void handle_invalid_op(struct pt_regs *regs) static noinstr bool handle_bug(struct pt_regs *regs) { bool handled = false; + int ud_type; + u32 imm; /* * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug() @@ -223,7 +267,8 @@ static noinstr bool handle_bug(struct pt_regs *regs) * irqentry_enter(). */ kmsan_unpoison_entry_regs(regs); - if (!is_valid_bugaddr(regs->ip)) + ud_type = decode_bug(regs->ip, &imm); + if (ud_type == BUG_NONE) return handled; /* @@ -236,10 +281,14 @@ static noinstr bool handle_bug(struct pt_regs *regs) */ if (regs->flags & X86_EFLAGS_IF) raw_local_irq_enable(); - if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN || - handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) { - regs->ip += LEN_UD2; - handled = true; + if (ud_type == BUG_UD2) { + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN || + handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) { + regs->ip += LEN_UD2; + handled = true; + } + } else if (IS_ENABLED(CONFIG_UBSAN_TRAP)) { + pr_crit("%s at %pS\n", report_ubsan_failure(regs, imm), (void *)regs->ip); } if (regs->flags & X86_EFLAGS_IF) raw_local_irq_disable(); @@ -1402,34 +1451,8 @@ DEFINE_IDTENTRY_SW(iret_error) } #endif -/* Do not enable FRED by default yet. */ -static bool enable_fred __ro_after_init = false; - -#ifdef CONFIG_X86_FRED -static int __init fred_setup(char *str) -{ - if (!str) - return -EINVAL; - - if (!cpu_feature_enabled(X86_FEATURE_FRED)) - return 0; - - if (!strcmp(str, "on")) - enable_fred = true; - else if (!strcmp(str, "off")) - enable_fred = false; - else - pr_warn("invalid FRED option: 'fred=%s'\n", str); - return 0; -} -early_param("fred", fred_setup); -#endif - void __init trap_init(void) { - if (cpu_feature_enabled(X86_FEATURE_FRED) && !enable_fred) - setup_clear_cpu_cap(X86_FEATURE_FRED); - /* Init cpu_entry_area before IST entries are set up */ setup_cpu_entry_areas(); @@ -1437,7 +1460,7 @@ void __init trap_init(void) sev_es_init_vc_handling(); /* Initialize TSS before setting up traps so ISTs work */ - cpu_init_exception_handling(); + cpu_init_exception_handling(true); /* Setup traps as cpu_init() might #GP */ if (!cpu_feature_enabled(X86_FEATURE_FRED)) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index d4462fb26299..dfe6847fd99e 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -28,6 +28,7 @@ #include <asm/apic.h> #include <asm/cpu_device_id.h> #include <asm/i8259.h> +#include <asm/topology.h> #include <asm/uv/uv.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ @@ -1253,15 +1254,12 @@ static void __init check_system_tsc_reliable(void) * - TSC which does not stop in C-States * - the TSC_ADJUST register which allows to detect even minimal * modifications - * - not more than two sockets. As the number of sockets cannot be - * evaluated at the early boot stage where this has to be - * invoked, check the number of online memory nodes as a - * fallback solution which is an reasonable estimate. + * - not more than four packages */ if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && boot_cpu_has(X86_FEATURE_TSC_ADJUST) && - nr_online_nodes <= 4) + topology_max_packages() <= 4) tsc_disable_clocksource_watchdog(); } @@ -1290,7 +1288,7 @@ int unsynchronized_tsc(void) */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { /* assume multi socket systems are not synchronized: */ - if (num_possible_cpus() > 1) + if (topology_max_packages() > 1) return 1; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 6e73403e874f..6726be89b7a6 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -357,8 +357,7 @@ SECTIONS PERCPU_SECTION(INTERNODE_CACHE_BYTES) #endif - RUNTIME_CONST(shift, d_hash_shift) - RUNTIME_CONST(ptr, dentry_hashtable) + RUNTIME_CONST_VARIABLES . = ALIGN(PAGE_SIZE); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 82b128d3f309..0a2bbd674a6d 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -8,6 +8,7 @@ #include <linux/ioport.h> #include <linux/export.h> #include <linux/pci.h> +#include <linux/acpi.h> #include <asm/acpi.h> #include <asm/bios_ebda.h> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 912bad4fa88c..a9a23e058555 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4703,16 +4703,14 @@ out_unlock: bool kvm_mmu_may_ignore_guest_pat(void) { /* - * When EPT is enabled (shadow_memtype_mask is non-zero), the CPU does - * not support self-snoop (or is affected by an erratum), and the VM + * When EPT is enabled (shadow_memtype_mask is non-zero), and the VM * has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is to * honor the memtype from the guest's PAT so that guest accesses to * memory that is DMA'd aren't cached against the guest's wishes. As a * result, KVM _may_ ignore guest PAT, whereas without non-coherent DMA, - * KVM _always_ ignores or honors guest PAT, i.e. doesn't toggle SPTE - * bits in response to non-coherent device (un)registration. + * KVM _always_ ignores guest PAT (when EPT is enabled). */ - return !static_cpu_has(X86_FEATURE_SELFSNOOP) && shadow_memtype_mask; + return shadow_memtype_mask; } int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 714c517dd4b7..0b851ef937f2 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -534,10 +534,10 @@ static int __sev_issue_cmd(int fd, int id, void *data, int *error) int ret; f = fdget(fd); - if (!f.file) + if (!fd_file(f)) return -EBADF; - ret = sev_issue_cmd_external_user(f.file, id, data, error); + ret = sev_issue_cmd_external_user(fd_file(f), id, data, error); fdput(f); return ret; @@ -2078,15 +2078,15 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) bool charged = false; int ret; - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (!file_is_kvm(f.file)) { + if (!file_is_kvm(fd_file(f))) { ret = -EBADF; goto out_fput; } - source_kvm = f.file->private_data; + source_kvm = fd_file(f)->private_data; ret = sev_lock_two_vms(kvm, source_kvm); if (ret) goto out_fput; @@ -2803,15 +2803,15 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) struct kvm_sev_info *source_sev, *mirror_sev; int ret; - if (!f.file) + if (!fd_file(f)) return -EBADF; - if (!file_is_kvm(f.file)) { + if (!file_is_kvm(fd_file(f))) { ret = -EBADF; goto e_source_fput; } - source_kvm = f.file->private_data; + source_kvm = fd_file(f)->private_data; ret = sev_lock_two_vms(kvm, source_kvm); if (ret) goto e_source_fput; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c67e448c6ebd..1a4438358c5e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7665,13 +7665,11 @@ u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) /* * Force WB and ignore guest PAT if the VM does NOT have a non-coherent - * device attached and the CPU doesn't support self-snoop. Letting the - * guest control memory types on Intel CPUs without self-snoop may - * result in unexpected behavior, and so KVM's (historical) ABI is to - * trust the guest to behave only as a last resort. + * device attached. Letting the guest control memory types on Intel + * CPUs may result in unexpected behavior, and so KVM's ABI is to trust + * the guest to behave only as a last resort. */ - if (!static_cpu_has(X86_FEATURE_SELFSNOOP) && - !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT); diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 90afb488b396..b2eff07d65e4 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -16,6 +16,11 @@ cmpxchg8b (\reg) .endm +.macro read64_nonatomic reg + movl (\reg), %eax + movl 4(\reg), %edx +.endm + SYM_FUNC_START(atomic64_read_cx8) read64 %ecx RET @@ -51,7 +56,7 @@ SYM_FUNC_START(atomic64_\func\()_return_cx8) movl %edx, %edi movl %ecx, %ebp - read64 %ecx + read64_nonatomic %ecx 1: movl %eax, %ebx movl %edx, %ecx @@ -79,7 +84,7 @@ addsub_return sub sub sbb SYM_FUNC_START(atomic64_\func\()_return_cx8) pushl %ebx - read64 %esi + read64_nonatomic %esi 1: movl %eax, %ebx movl %edx, %ecx diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 8d3a00e5c528..690fbf48e853 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -57,7 +57,6 @@ obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o -obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 9332b36a1091..628833afee37 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/nodemask.h> #include <linux/memblock.h> +#include <linux/numa_memblks.h> #include <asm/io.h> #include <linux/pci_ids.h> diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index e91500a80963..575f863f3c75 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -164,7 +164,7 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu) } } #else -static inline void percpu_setup_exception_stacks(unsigned int cpu) +static void __init percpu_setup_exception_stacks(unsigned int cpu) { struct cpu_entry_area *cea = get_cpu_entry_area(cpu); diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index c45127265f2f..437e96fb4977 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -99,18 +99,31 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; + bool use_gbpage; next = (addr & PUD_MASK) + PUD_SIZE; if (next > end) next = end; - if (info->direct_gbpages) { - pud_t pudval; + /* if this is already a gbpage, this portion is already mapped */ + if (pud_leaf(*pud)) + continue; + + /* Is using a gbpage allowed? */ + use_gbpage = info->direct_gbpages; - if (pud_present(*pud)) - continue; + /* Don't use gbpage if it maps more than the requested region. */ + /* at the begining: */ + use_gbpage &= ((addr & ~PUD_MASK) == 0); + /* ... or at the end: */ + use_gbpage &= ((next & ~PUD_MASK) == 0); + + /* Never overwrite existing mappings */ + use_gbpage &= !pud_present(*pud); + + if (use_gbpage) { + pud_t pudval; - addr &= PUD_MASK; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index aa7d279321ea..70b02fc61d93 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/io.h> #include <linux/ioport.h> +#include <linux/ioremap.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mmiotrace.h> @@ -457,7 +458,7 @@ void iounmap(volatile void __iomem *addr) { struct vm_struct *p, *o; - if ((void __force *)addr <= high_memory) + if (WARN_ON_ONCE(!is_ioremap_addr((void __force *)addr))) return; /* diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 6ce10e3c6228..64e5cdb2460a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <linux/topology.h> #include <linux/sort.h> +#include <linux/numa_memblks.h> #include <asm/e820/api.h> #include <asm/proto.h> @@ -22,16 +23,6 @@ #include "numa_internal.h" int numa_off; -nodemask_t numa_nodes_parsed __initdata; - -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); - -static struct numa_meminfo numa_meminfo __initdata_or_meminfo; -static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; - -static int numa_distance_cnt; -static u8 *numa_distance; static __init int numa_setup(char *opt) { @@ -124,456 +115,27 @@ void __init setup_node_to_cpumask_map(void) pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); } -static int __init numa_add_memblk_to(int nid, u64 start, u64 end, - struct numa_meminfo *mi) -{ - /* ignore zero length blks */ - if (start == end) - return 0; - - /* whine about and ignore invalid blks */ - if (start > end || nid < 0 || nid >= MAX_NUMNODES) { - pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n", - nid, start, end - 1); - return 0; - } - - if (mi->nr_blks >= NR_NODE_MEMBLKS) { - pr_err("too many memblk ranges\n"); - return -EINVAL; - } - - mi->blk[mi->nr_blks].start = start; - mi->blk[mi->nr_blks].end = end; - mi->blk[mi->nr_blks].nid = nid; - mi->nr_blks++; - return 0; -} - -/** - * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo - * @idx: Index of memblk to remove - * @mi: numa_meminfo to remove memblk from - * - * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and - * decrementing @mi->nr_blks. - */ -void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) -{ - mi->nr_blks--; - memmove(&mi->blk[idx], &mi->blk[idx + 1], - (mi->nr_blks - idx) * sizeof(mi->blk[0])); -} - -/** - * numa_move_tail_memblk - Move a numa_memblk from one numa_meminfo to another - * @dst: numa_meminfo to append block to - * @idx: Index of memblk to remove - * @src: numa_meminfo to remove memblk from - */ -static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx, - struct numa_meminfo *src) -{ - dst->blk[dst->nr_blks++] = src->blk[idx]; - numa_remove_memblk_from(idx, src); -} - -/** - * numa_add_memblk - Add one numa_memblk to numa_meminfo - * @nid: NUMA node ID of the new memblk - * @start: Start address of the new memblk - * @end: End address of the new memblk - * - * Add a new memblk to the default numa_meminfo. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_add_memblk(int nid, u64 start, u64 end) -{ - return numa_add_memblk_to(nid, start, end, &numa_meminfo); -} - -/* Allocate NODE_DATA for a node on the local memory */ -static void __init alloc_node_data(int nid) +static int __init numa_register_nodes(void) { - const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); - u64 nd_pa; - void *nd; - int tnid; - - /* - * Allocate node data. Try node-local memory and then any node. - * Never allocate in DMA zone. - */ - nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); - if (!nd_pa) { - pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", - nd_size, nid); - return; - } - nd = __va(nd_pa); - - /* report and initialize */ - printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid, - nd_pa, nd_pa + nd_size - 1); - tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); - if (tnid != nid) - printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid); - - node_data[nid] = nd; - memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); - - node_set_online(nid); -} - -/** - * numa_cleanup_meminfo - Cleanup a numa_meminfo - * @mi: numa_meminfo to clean up - * - * Sanitize @mi by merging and removing unnecessary memblks. Also check for - * conflicts and clear unused memblks. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_cleanup_meminfo(struct numa_meminfo *mi) -{ - const u64 low = 0; - const u64 high = PFN_PHYS(max_pfn); - int i, j, k; - - /* first, trim all entries */ - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - /* move / save reserved memory ranges */ - if (!memblock_overlaps_region(&memblock.memory, - bi->start, bi->end - bi->start)) { - numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi); - continue; - } - - /* make sure all non-reserved blocks are inside the limits */ - bi->start = max(bi->start, low); - - /* preserve info for non-RAM areas above 'max_pfn': */ - if (bi->end > high) { - numa_add_memblk_to(bi->nid, high, bi->end, - &numa_reserved_meminfo); - bi->end = high; - } - - /* and there's no empty block */ - if (bi->start >= bi->end) - numa_remove_memblk_from(i--, mi); - } - - /* merge neighboring / overlapping entries */ - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - for (j = i + 1; j < mi->nr_blks; j++) { - struct numa_memblk *bj = &mi->blk[j]; - u64 start, end; - - /* - * See whether there are overlapping blocks. Whine - * about but allow overlaps of the same nid. They - * will be merged below. - */ - if (bi->end > bj->start && bi->start < bj->end) { - if (bi->nid != bj->nid) { - pr_err("node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, - bj->nid, bj->start, bj->end - 1); - return -EINVAL; - } - pr_warn("Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, - bj->start, bj->end - 1); - } - - /* - * Join together blocks on the same node, holes - * between which don't overlap with memory on other - * nodes. - */ - if (bi->nid != bj->nid) - continue; - start = min(bi->start, bj->start); - end = max(bi->end, bj->end); - for (k = 0; k < mi->nr_blks; k++) { - struct numa_memblk *bk = &mi->blk[k]; - - if (bi->nid == bk->nid) - continue; - if (start < bk->end && end > bk->start) - break; - } - if (k < mi->nr_blks) - continue; - printk(KERN_INFO "NUMA: Node %d [mem %#010Lx-%#010Lx] + [mem %#010Lx-%#010Lx] -> [mem %#010Lx-%#010Lx]\n", - bi->nid, bi->start, bi->end - 1, bj->start, - bj->end - 1, start, end - 1); - bi->start = start; - bi->end = end; - numa_remove_memblk_from(j--, mi); - } - } - - /* clear unused ones */ - for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) { - mi->blk[i].start = mi->blk[i].end = 0; - mi->blk[i].nid = NUMA_NO_NODE; - } - - return 0; -} - -/* - * Set nodes, which have memory in @mi, in *@nodemask. - */ -static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, - const struct numa_meminfo *mi) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mi->blk); i++) - if (mi->blk[i].start != mi->blk[i].end && - mi->blk[i].nid != NUMA_NO_NODE) - node_set(mi->blk[i].nid, *nodemask); -} - -/** - * numa_reset_distance - Reset NUMA distance table - * - * The current table is freed. The next numa_set_distance() call will - * create a new one. - */ -void __init numa_reset_distance(void) -{ - size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - - /* numa_distance could be 1LU marking allocation failure, test cnt */ - if (numa_distance_cnt) - memblock_free(numa_distance, size); - numa_distance_cnt = 0; - numa_distance = NULL; /* enable table creation */ -} - -static int __init numa_alloc_distance(void) -{ - nodemask_t nodes_parsed; - size_t size; - int i, j, cnt = 0; - u64 phys; - - /* size the new table and allocate it */ - nodes_parsed = numa_nodes_parsed; - numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo); - - for_each_node_mask(i, nodes_parsed) - cnt = i; - cnt++; - size = cnt * cnt * sizeof(numa_distance[0]); - - phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0, - PFN_PHYS(max_pfn_mapped)); - if (!phys) { - pr_warn("Warning: can't allocate distance table!\n"); - /* don't retry until explicitly reset */ - numa_distance = (void *)1LU; - return -ENOMEM; - } - - numa_distance = __va(phys); - numa_distance_cnt = cnt; - - /* fill with the default distances */ - for (i = 0; i < cnt; i++) - for (j = 0; j < cnt; j++) - numa_distance[i * cnt + j] = i == j ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt); - - return 0; -} - -/** - * numa_set_distance - Set NUMA distance from one NUMA to another - * @from: the 'from' node to set distance - * @to: the 'to' node to set distance - * @distance: NUMA distance - * - * Set the distance from node @from to @to to @distance. If distance table - * doesn't exist, one which is large enough to accommodate all the currently - * known nodes will be created. - * - * If such table cannot be allocated, a warning is printed and further - * calls are ignored until the distance table is reset with - * numa_reset_distance(). - * - * If @from or @to is higher than the highest known node or lower than zero - * at the time of table creation or @distance doesn't make sense, the call - * is ignored. - * This is to allow simplification of specific NUMA config implementations. - */ -void __init numa_set_distance(int from, int to, int distance) -{ - if (!numa_distance && numa_alloc_distance() < 0) - return; - - if (from >= numa_distance_cnt || to >= numa_distance_cnt || - from < 0 || to < 0) { - pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - if ((u8)distance != distance || - (from == to && distance != LOCAL_DISTANCE)) { - pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - numa_distance[from * numa_distance_cnt + to] = distance; -} - -int __node_distance(int from, int to) -{ - if (from >= numa_distance_cnt || to >= numa_distance_cnt) - return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; - return numa_distance[from * numa_distance_cnt + to]; -} -EXPORT_SYMBOL(__node_distance); - -/* - * Mark all currently memblock-reserved physical memory (which covers the - * kernel's own memory ranges) as hot-unswappable. - */ -static void __init numa_clear_kernel_node_hotplug(void) -{ - nodemask_t reserved_nodemask = NODE_MASK_NONE; - struct memblock_region *mb_region; - int i; - - /* - * We have to do some preprocessing of memblock regions, to - * make them suitable for reservation. - * - * At this time, all memory regions reserved by memblock are - * used by the kernel, but those regions are not split up - * along node boundaries yet, and don't necessarily have their - * node ID set yet either. - * - * So iterate over all memory known to the x86 architecture, - * and use those ranges to set the nid in memblock.reserved. - * This will split up the memblock regions along node - * boundaries and will set the node IDs as well. - */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = numa_meminfo.blk + i; - int ret; - - ret = memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid); - WARN_ON_ONCE(ret); - } - - /* - * Now go over all reserved memblock regions, to construct a - * node mask of all kernel reserved memory areas. - * - * [ Note, when booting with mem=nn[kMG] or in a kdump kernel, - * numa_meminfo might not include all memblock.reserved - * memory ranges, because quirks such as trim_snb_memory() - * reserve specific pages for Sandy Bridge graphics. ] - */ - for_each_reserved_mem_region(mb_region) { - int nid = memblock_get_region_node(mb_region); - - if (nid != NUMA_NO_NODE) - node_set(nid, reserved_nodemask); - } - - /* - * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory - * belonging to the reserved node mask. - * - * Note that this will include memory regions that reside - * on nodes that contain kernel memory - entire nodes - * become hot-unpluggable: - */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = numa_meminfo.blk + i; - - if (!node_isset(mb->nid, reserved_nodemask)) - continue; - - memblock_clear_hotplug(mb->start, mb->end - mb->start); - } -} - -static int __init numa_register_memblks(struct numa_meminfo *mi) -{ - int i, nid; - - /* Account for nodes with cpus and no memory */ - node_possible_map = numa_nodes_parsed; - numa_nodemask_from_meminfo(&node_possible_map, mi); - if (WARN_ON(nodes_empty(node_possible_map))) - return -EINVAL; - - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *mb = &mi->blk[i]; - memblock_set_node(mb->start, mb->end - mb->start, - &memblock.memory, mb->nid); - } - - /* - * At very early time, the kernel have to use some memory such as - * loading the kernel image. We cannot prevent this anyway. So any - * node the kernel resides in should be un-hotpluggable. - * - * And when we come here, alloc node data won't fail. - */ - numa_clear_kernel_node_hotplug(); - - /* - * If sections array is gonna be used for pfn -> nid mapping, check - * whether its granularity is fine enough. - */ - if (IS_ENABLED(NODE_NOT_IN_PAGE_FLAGS)) { - unsigned long pfn_align = node_map_pfn_alignment(); - - if (pfn_align && pfn_align < PAGES_PER_SECTION) { - pr_warn("Node alignment %LuMB < min %LuMB, rejecting NUMA config\n", - PFN_PHYS(pfn_align) >> 20, - PFN_PHYS(PAGES_PER_SECTION) >> 20); - return -EINVAL; - } - } + int nid; if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; /* Finally register nodes. */ for_each_node_mask(nid, node_possible_map) { - u64 start = PFN_PHYS(max_pfn); - u64 end = 0; - - for (i = 0; i < mi->nr_blks; i++) { - if (nid != mi->blk[i].nid) - continue; - start = min(mi->blk[i].start, start); - end = max(mi->blk[i].end, end); - } + unsigned long start_pfn, end_pfn; - if (start >= end) + /* + * Note, get_pfn_range_for_nid() depends on + * memblock_set_node() having already happened + */ + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + if (start_pfn >= end_pfn) continue; alloc_node_data(nid); + node_set_online(nid); } /* Dump memblock with node info and return. */ @@ -609,39 +171,11 @@ static int __init numa_init(int (*init_func)(void)) for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE); - nodes_clear(numa_nodes_parsed); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - memset(&numa_meminfo, 0, sizeof(numa_meminfo)); - WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, - NUMA_NO_NODE)); - WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, - NUMA_NO_NODE)); - /* In case that parsing SRAT failed. */ - WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); - numa_reset_distance(); - - ret = init_func(); - if (ret < 0) - return ret; - - /* - * We reset memblock back to the top-down direction - * here because if we configured ACPI_NUMA, we have - * parsed SRAT in init_func(). It is ok to have the - * reset here even if we did't configure ACPI_NUMA - * or acpi numa init fails and fallbacks to dummy - * numa init. - */ - memblock_set_bottom_up(false); - - ret = numa_cleanup_meminfo(&numa_meminfo); + ret = numa_memblks_init(init_func, /* memblock_force_top_down */ true); if (ret < 0) return ret; - numa_emulation(&numa_meminfo, numa_distance_cnt); - - ret = numa_register_memblks(&numa_meminfo); + ret = numa_register_nodes(); if (ret < 0) return ret; @@ -782,12 +316,12 @@ void __init init_cpu_to_node(void) #ifndef CONFIG_DEBUG_PER_CPU_MAPS # ifndef CONFIG_NUMA_EMU -void numa_add_cpu(int cpu) +void numa_add_cpu(unsigned int cpu) { cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } -void numa_remove_cpu(int cpu) +void numa_remove_cpu(unsigned int cpu) { cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } @@ -825,7 +359,7 @@ int early_cpu_to_node(int cpu) return per_cpu(x86_cpu_to_node_map, cpu); } -void debug_cpumask_set_cpu(int cpu, int node, bool enable) +void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable) { struct cpumask *mask; @@ -857,12 +391,12 @@ static void numa_set_cpumask(int cpu, bool enable) debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable); } -void numa_add_cpu(int cpu) +void numa_add_cpu(unsigned int cpu) { numa_set_cpumask(cpu, true); } -void numa_remove_cpu(int cpu) +void numa_remove_cpu(unsigned int cpu) { numa_set_cpumask(cpu, false); } @@ -893,113 +427,29 @@ EXPORT_SYMBOL(cpumask_of_node); #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ -#ifdef CONFIG_NUMA_KEEP_MEMINFO -static int meminfo_to_nid(struct numa_meminfo *mi, u64 start) +#ifdef CONFIG_NUMA_EMU +void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys, + unsigned int nr_emu_nids) { - int i; - - for (i = 0; i < mi->nr_blks; i++) - if (mi->blk[i].start <= start && mi->blk[i].end > start) - return mi->blk[i].nid; - return NUMA_NO_NODE; -} - -int phys_to_target_node(phys_addr_t start) -{ - int nid = meminfo_to_nid(&numa_meminfo, start); + int i, j; /* - * Prefer online nodes, but if reserved memory might be - * hot-added continue the search with reserved ranges. + * Transform __apicid_to_node table to use emulated nids by + * reverse-mapping phys_nid. The maps should always exist but fall + * back to zero just in case. */ - if (nid != NUMA_NO_NODE) - return nid; - - return meminfo_to_nid(&numa_reserved_meminfo, start); -} -EXPORT_SYMBOL_GPL(phys_to_target_node); - -int memory_add_physaddr_to_nid(u64 start) -{ - int nid = meminfo_to_nid(&numa_meminfo, start); - - if (nid == NUMA_NO_NODE) - nid = numa_meminfo.blk[0].nid; - return nid; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); - -#endif - -static int __init cmp_memblk(const void *a, const void *b) -{ - const struct numa_memblk *ma = *(const struct numa_memblk **)a; - const struct numa_memblk *mb = *(const struct numa_memblk **)b; - - return (ma->start > mb->start) - (ma->start < mb->start); + for (i = 0; i < ARRAY_SIZE(__apicid_to_node); i++) { + if (__apicid_to_node[i] == NUMA_NO_NODE) + continue; + for (j = 0; j < nr_emu_nids; j++) + if (__apicid_to_node[i] == emu_nid_to_phys[j]) + break; + __apicid_to_node[i] = j < nr_emu_nids ? j : 0; + } } -static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; - -/** - * numa_fill_memblks - Fill gaps in numa_meminfo memblks - * @start: address to begin fill - * @end: address to end fill - * - * Find and extend numa_meminfo memblks to cover the physical - * address range @start-@end - * - * RETURNS: - * 0 : Success - * NUMA_NO_MEMBLK : No memblks exist in address range @start-@end - */ - -int __init numa_fill_memblks(u64 start, u64 end) +u64 __init numa_emu_dma_end(void) { - struct numa_memblk **blk = &numa_memblk_list[0]; - struct numa_meminfo *mi = &numa_meminfo; - int count = 0; - u64 prev_end; - - /* - * Create a list of pointers to numa_meminfo memblks that - * overlap start, end. The list is used to make in-place - * changes that fill out the numa_meminfo memblks. - */ - for (int i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - if (memblock_addrs_overlap(start, end - start, bi->start, - bi->end - bi->start)) { - blk[count] = &mi->blk[i]; - count++; - } - } - if (!count) - return NUMA_NO_MEMBLK; - - /* Sort the list of pointers in memblk->start order */ - sort(&blk[0], count, sizeof(blk[0]), cmp_memblk, NULL); - - /* Make sure the first/last memblks include start/end */ - blk[0]->start = min(blk[0]->start, start); - blk[count - 1]->end = max(blk[count - 1]->end, end); - - /* - * Fill any gaps by tracking the previous memblks - * end address and backfilling to it if needed. - */ - prev_end = blk[0]->end; - for (int i = 1; i < count; i++) { - struct numa_memblk *curr = blk[i]; - - if (prev_end >= curr->start) { - if (prev_end < curr->end) - prev_end = curr->end; - } else { - curr->start = prev_end; - prev_end = curr->end; - } - } - return 0; + return PFN_PHYS(MAX_DMA32_PFN); } +#endif /* CONFIG_NUMA_EMU */ diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c deleted file mode 100644 index 9a9305367fdd..000000000000 --- a/arch/x86/mm/numa_emulation.c +++ /dev/null @@ -1,585 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * NUMA emulation - */ -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/topology.h> -#include <linux/memblock.h> -#include <asm/dma.h> - -#include "numa_internal.h" - -static int emu_nid_to_phys[MAX_NUMNODES]; -static char *emu_cmdline __initdata; - -int __init numa_emu_cmdline(char *str) -{ - emu_cmdline = str; - return 0; -} - -static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi) -{ - int i; - - for (i = 0; i < mi->nr_blks; i++) - if (mi->blk[i].nid == nid) - return i; - return -ENOENT; -} - -static u64 __init mem_hole_size(u64 start, u64 end) -{ - unsigned long start_pfn = PFN_UP(start); - unsigned long end_pfn = PFN_DOWN(end); - - if (start_pfn < end_pfn) - return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn)); - return 0; -} - -/* - * Sets up nid to range from @start to @end. The return value is -errno if - * something went wrong, 0 otherwise. - */ -static int __init emu_setup_memblk(struct numa_meminfo *ei, - struct numa_meminfo *pi, - int nid, int phys_blk, u64 size) -{ - struct numa_memblk *eb = &ei->blk[ei->nr_blks]; - struct numa_memblk *pb = &pi->blk[phys_blk]; - - if (ei->nr_blks >= NR_NODE_MEMBLKS) { - pr_err("NUMA: Too many emulated memblks, failing emulation\n"); - return -EINVAL; - } - - ei->nr_blks++; - eb->start = pb->start; - eb->end = pb->start + size; - eb->nid = nid; - - if (emu_nid_to_phys[nid] == NUMA_NO_NODE) - emu_nid_to_phys[nid] = pb->nid; - - pb->start += size; - if (pb->start >= pb->end) { - WARN_ON_ONCE(pb->start > pb->end); - numa_remove_memblk_from(phys_blk, pi); - } - - printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n", - nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20); - return 0; -} - -/* - * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr - * to max_addr. - * - * Returns zero on success or negative on error. - */ -static int __init split_nodes_interleave(struct numa_meminfo *ei, - struct numa_meminfo *pi, - u64 addr, u64 max_addr, int nr_nodes) -{ - nodemask_t physnode_mask = numa_nodes_parsed; - u64 size; - int big; - int nid = 0; - int i, ret; - - if (nr_nodes <= 0) - return -1; - if (nr_nodes > MAX_NUMNODES) { - pr_info("numa=fake=%d too large, reducing to %d\n", - nr_nodes, MAX_NUMNODES); - nr_nodes = MAX_NUMNODES; - } - - /* - * Calculate target node size. x86_32 freaks on __udivdi3() so do - * the division in ulong number of pages and convert back. - */ - size = max_addr - addr - mem_hole_size(addr, max_addr); - size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes); - - /* - * Calculate the number of big nodes that can be allocated as a result - * of consolidating the remainder. - */ - big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) / - FAKE_NODE_MIN_SIZE; - - size &= FAKE_NODE_MIN_HASH_MASK; - if (!size) { - pr_err("Not enough memory for each node. " - "NUMA emulation disabled.\n"); - return -1; - } - - /* - * Continue to fill physical nodes with fake nodes until there is no - * memory left on any of them. - */ - while (!nodes_empty(physnode_mask)) { - for_each_node_mask(i, physnode_mask) { - u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); - u64 start, limit, end; - int phys_blk; - - phys_blk = emu_find_memblk_by_nid(i, pi); - if (phys_blk < 0) { - node_clear(i, physnode_mask); - continue; - } - start = pi->blk[phys_blk].start; - limit = pi->blk[phys_blk].end; - end = start + size; - - if (nid < big) - end += FAKE_NODE_MIN_SIZE; - - /* - * Continue to add memory to this fake node if its - * non-reserved memory is less than the per-node size. - */ - while (end - start - mem_hole_size(start, end) < size) { - end += FAKE_NODE_MIN_SIZE; - if (end > limit) { - end = limit; - break; - } - } - - /* - * If there won't be at least FAKE_NODE_MIN_SIZE of - * non-reserved memory in ZONE_DMA32 for the next node, - * this one must extend to the boundary. - */ - if (end < dma32_end && dma32_end - end - - mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) - end = dma32_end; - - /* - * If there won't be enough non-reserved memory for the - * next node, this one must extend to the end of the - * physical node. - */ - if (limit - end - mem_hole_size(end, limit) < size) - end = limit; - - ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes, - phys_blk, - min(end, limit) - start); - if (ret < 0) - return ret; - } - } - return 0; -} - -/* - * Returns the end address of a node so that there is at least `size' amount of - * non-reserved memory or `max_addr' is reached. - */ -static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) -{ - u64 end = start + size; - - while (end - start - mem_hole_size(start, end) < size) { - end += FAKE_NODE_MIN_SIZE; - if (end > max_addr) { - end = max_addr; - break; - } - } - return end; -} - -static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes) -{ - unsigned long max_pfn = PHYS_PFN(max_addr); - unsigned long base_pfn = PHYS_PFN(base); - unsigned long hole_pfns = PHYS_PFN(hole); - - return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes); -} - -/* - * Sets up fake nodes of `size' interleaved over physical nodes ranging from - * `addr' to `max_addr'. - * - * Returns zero on success or negative on error. - */ -static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, - struct numa_meminfo *pi, - u64 addr, u64 max_addr, u64 size, - int nr_nodes, struct numa_memblk *pblk, - int nid) -{ - nodemask_t physnode_mask = numa_nodes_parsed; - int i, ret, uniform = 0; - u64 min_size; - - if ((!size && !nr_nodes) || (nr_nodes && !pblk)) - return -1; - - /* - * In the 'uniform' case split the passed in physical node by - * nr_nodes, in the non-uniform case, ignore the passed in - * physical block and try to create nodes of at least size - * @size. - * - * In the uniform case, split the nodes strictly by physical - * capacity, i.e. ignore holes. In the non-uniform case account - * for holes and treat @size as a minimum floor. - */ - if (!nr_nodes) - nr_nodes = MAX_NUMNODES; - else { - nodes_clear(physnode_mask); - node_set(pblk->nid, physnode_mask); - uniform = 1; - } - - if (uniform) { - min_size = uniform_size(max_addr, addr, 0, nr_nodes); - size = min_size; - } else { - /* - * The limit on emulated nodes is MAX_NUMNODES, so the - * size per node is increased accordingly if the - * requested size is too small. This creates a uniform - * distribution of node sizes across the entire machine - * (but not necessarily over physical nodes). - */ - min_size = uniform_size(max_addr, addr, - mem_hole_size(addr, max_addr), nr_nodes); - } - min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE); - if (size < min_size) { - pr_err("Fake node size %LuMB too small, increasing to %LuMB\n", - size >> 20, min_size >> 20); - size = min_size; - } - size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE); - - /* - * Fill physical nodes with fake nodes of size until there is no memory - * left on any of them. - */ - while (!nodes_empty(physnode_mask)) { - for_each_node_mask(i, physnode_mask) { - u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); - u64 start, limit, end; - int phys_blk; - - phys_blk = emu_find_memblk_by_nid(i, pi); - if (phys_blk < 0) { - node_clear(i, physnode_mask); - continue; - } - - start = pi->blk[phys_blk].start; - limit = pi->blk[phys_blk].end; - - if (uniform) - end = start + size; - else - end = find_end_of_node(start, limit, size); - /* - * If there won't be at least FAKE_NODE_MIN_SIZE of - * non-reserved memory in ZONE_DMA32 for the next node, - * this one must extend to the boundary. - */ - if (end < dma32_end && dma32_end - end - - mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) - end = dma32_end; - - /* - * If there won't be enough non-reserved memory for the - * next node, this one must extend to the end of the - * physical node. - */ - if ((limit - end - mem_hole_size(end, limit) < size) - && !uniform) - end = limit; - - ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, - phys_blk, - min(end, limit) - start); - if (ret < 0) - return ret; - } - } - return nid; -} - -static int __init split_nodes_size_interleave(struct numa_meminfo *ei, - struct numa_meminfo *pi, - u64 addr, u64 max_addr, u64 size) -{ - return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, - 0, NULL, 0); -} - -static int __init setup_emu2phys_nid(int *dfl_phys_nid) -{ - int i, max_emu_nid = 0; - - *dfl_phys_nid = NUMA_NO_NODE; - for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) { - if (emu_nid_to_phys[i] != NUMA_NO_NODE) { - max_emu_nid = i; - if (*dfl_phys_nid == NUMA_NO_NODE) - *dfl_phys_nid = emu_nid_to_phys[i]; - } - } - - return max_emu_nid; -} - -/** - * numa_emulation - Emulate NUMA nodes - * @numa_meminfo: NUMA configuration to massage - * @numa_dist_cnt: The size of the physical NUMA distance table - * - * Emulate NUMA nodes according to the numa=fake kernel parameter. - * @numa_meminfo contains the physical memory configuration and is modified - * to reflect the emulated configuration on success. @numa_dist_cnt is - * used to determine the size of the physical distance table. - * - * On success, the following modifications are made. - * - * - @numa_meminfo is updated to reflect the emulated nodes. - * - * - __apicid_to_node[] is updated such that APIC IDs are mapped to the - * emulated nodes. - * - * - NUMA distance table is rebuilt to represent distances between emulated - * nodes. The distances are determined considering how emulated nodes - * are mapped to physical nodes and match the actual distances. - * - * - emu_nid_to_phys[] reflects how emulated nodes are mapped to physical - * nodes. This is used by numa_add_cpu() and numa_remove_cpu(). - * - * If emulation is not enabled or fails, emu_nid_to_phys[] is filled with - * identity mapping and no other modification is made. - */ -void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) -{ - static struct numa_meminfo ei __initdata; - static struct numa_meminfo pi __initdata; - const u64 max_addr = PFN_PHYS(max_pfn); - u8 *phys_dist = NULL; - size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]); - int max_emu_nid, dfl_phys_nid; - int i, j, ret; - - if (!emu_cmdline) - goto no_emu; - - memset(&ei, 0, sizeof(ei)); - pi = *numa_meminfo; - - for (i = 0; i < MAX_NUMNODES; i++) - emu_nid_to_phys[i] = NUMA_NO_NODE; - - /* - * If the numa=fake command-line contains a 'M' or 'G', it represents - * the fixed node size. Otherwise, if it is just a single number N, - * split the system RAM into N fake nodes. - */ - if (strchr(emu_cmdline, 'U')) { - nodemask_t physnode_mask = numa_nodes_parsed; - unsigned long n; - int nid = 0; - - n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); - ret = -1; - for_each_node_mask(i, physnode_mask) { - /* - * The reason we pass in blk[0] is due to - * numa_remove_memblk_from() called by - * emu_setup_memblk() will delete entry 0 - * and then move everything else up in the pi.blk - * array. Therefore we should always be looking - * at blk[0]. - */ - ret = split_nodes_size_interleave_uniform(&ei, &pi, - pi.blk[0].start, pi.blk[0].end, 0, - n, &pi.blk[0], nid); - if (ret < 0) - break; - if (ret < n) { - pr_info("%s: phys: %d only got %d of %ld nodes, failing\n", - __func__, i, ret, n); - ret = -1; - break; - } - nid = ret; - } - } else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) { - u64 size; - - size = memparse(emu_cmdline, &emu_cmdline); - ret = split_nodes_size_interleave(&ei, &pi, 0, max_addr, size); - } else { - unsigned long n; - - n = simple_strtoul(emu_cmdline, &emu_cmdline, 0); - ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n); - } - if (*emu_cmdline == ':') - emu_cmdline++; - - if (ret < 0) - goto no_emu; - - if (numa_cleanup_meminfo(&ei) < 0) { - pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n"); - goto no_emu; - } - - /* copy the physical distance table */ - if (numa_dist_cnt) { - u64 phys; - - phys = memblock_phys_alloc_range(phys_size, PAGE_SIZE, 0, - PFN_PHYS(max_pfn_mapped)); - if (!phys) { - pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); - goto no_emu; - } - phys_dist = __va(phys); - - for (i = 0; i < numa_dist_cnt; i++) - for (j = 0; j < numa_dist_cnt; j++) - phys_dist[i * numa_dist_cnt + j] = - node_distance(i, j); - } - - /* - * Determine the max emulated nid and the default phys nid to use - * for unmapped nodes. - */ - max_emu_nid = setup_emu2phys_nid(&dfl_phys_nid); - - /* commit */ - *numa_meminfo = ei; - - /* Make sure numa_nodes_parsed only contains emulated nodes */ - nodes_clear(numa_nodes_parsed); - for (i = 0; i < ARRAY_SIZE(ei.blk); i++) - if (ei.blk[i].start != ei.blk[i].end && - ei.blk[i].nid != NUMA_NO_NODE) - node_set(ei.blk[i].nid, numa_nodes_parsed); - - /* - * Transform __apicid_to_node table to use emulated nids by - * reverse-mapping phys_nid. The maps should always exist but fall - * back to zero just in case. - */ - for (i = 0; i < ARRAY_SIZE(__apicid_to_node); i++) { - if (__apicid_to_node[i] == NUMA_NO_NODE) - continue; - for (j = 0; j < ARRAY_SIZE(emu_nid_to_phys); j++) - if (__apicid_to_node[i] == emu_nid_to_phys[j]) - break; - __apicid_to_node[i] = j < ARRAY_SIZE(emu_nid_to_phys) ? j : 0; - } - - /* make sure all emulated nodes are mapped to a physical node */ - for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) - if (emu_nid_to_phys[i] == NUMA_NO_NODE) - emu_nid_to_phys[i] = dfl_phys_nid; - - /* transform distance table */ - numa_reset_distance(); - for (i = 0; i < max_emu_nid + 1; i++) { - for (j = 0; j < max_emu_nid + 1; j++) { - int physi = emu_nid_to_phys[i]; - int physj = emu_nid_to_phys[j]; - int dist; - - if (get_option(&emu_cmdline, &dist) == 2) - ; - else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt) - dist = physi == physj ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - else - dist = phys_dist[physi * numa_dist_cnt + physj]; - - numa_set_distance(i, j, dist); - } - } - - /* free the copied physical distance table */ - memblock_free(phys_dist, phys_size); - return; - -no_emu: - /* No emulation. Build identity emu_nid_to_phys[] for numa_add_cpu() */ - for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) - emu_nid_to_phys[i] = i; -} - -#ifndef CONFIG_DEBUG_PER_CPU_MAPS -void numa_add_cpu(int cpu) -{ - int physnid, nid; - - nid = early_cpu_to_node(cpu); - BUG_ON(nid == NUMA_NO_NODE || !node_online(nid)); - - physnid = emu_nid_to_phys[nid]; - - /* - * Map the cpu to each emulated node that is allocated on the physical - * node of the cpu's apic id. - */ - for_each_online_node(nid) - if (emu_nid_to_phys[nid] == physnid) - cpumask_set_cpu(cpu, node_to_cpumask_map[nid]); -} - -void numa_remove_cpu(int cpu) -{ - int i; - - for_each_online_node(i) - cpumask_clear_cpu(cpu, node_to_cpumask_map[i]); -} -#else /* !CONFIG_DEBUG_PER_CPU_MAPS */ -static void numa_set_cpumask(int cpu, bool enable) -{ - int nid, physnid; - - nid = early_cpu_to_node(cpu); - if (nid == NUMA_NO_NODE) { - /* early_cpu_to_node() already emits a warning and trace */ - return; - } - - physnid = emu_nid_to_phys[nid]; - - for_each_online_node(nid) { - if (emu_nid_to_phys[nid] != physnid) - continue; - - debug_cpumask_set_cpu(cpu, nid, enable); - } -} - -void numa_add_cpu(int cpu) -{ - numa_set_cpumask(cpu, true); -} - -void numa_remove_cpu(int cpu) -{ - numa_set_cpumask(cpu, false); -} -#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index 86860f279662..11e1ff370c10 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -5,30 +5,6 @@ #include <linux/types.h> #include <asm/numa.h> -struct numa_memblk { - u64 start; - u64 end; - int nid; -}; - -struct numa_meminfo { - int nr_blks; - struct numa_memblk blk[NR_NODE_MEMBLKS]; -}; - -void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi); -int __init numa_cleanup_meminfo(struct numa_meminfo *mi); -void __init numa_reset_distance(void); - void __init x86_numa_init(void); -#ifdef CONFIG_NUMA_EMU -void __init numa_emulation(struct numa_meminfo *numa_meminfo, - int numa_dist_cnt); -#else -static inline void numa_emulation(struct numa_meminfo *numa_meminfo, - int numa_dist_cnt) -{ } -#endif - #endif /* __X86_MM_NUMA_INTERNAL_H */ diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 6c4e29457c10..feb8cc6a12bf 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -104,7 +104,7 @@ __setup("debugpat", pat_debug_setup); #ifdef CONFIG_X86_PAT /* - * X86 PAT uses page flags arch_1 and uncached together to keep track of + * X86 PAT uses page flags arch_1 and arch_2 together to keep track of * memory type of pages that have backing page struct. * * X86 PAT supports 4 different memory types: @@ -118,9 +118,9 @@ __setup("debugpat", pat_debug_setup); #define _PGMT_WB 0 #define _PGMT_WC (1UL << PG_arch_1) -#define _PGMT_UC_MINUS (1UL << PG_uncached) -#define _PGMT_WT (1UL << PG_uncached | 1UL << PG_arch_1) -#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_UC_MINUS (1UL << PG_arch_2) +#define _PGMT_WT (1UL << PG_arch_2 | 1UL << PG_arch_1) +#define _PGMT_MASK (1UL << PG_arch_2 | 1UL << PG_arch_1) #define _PGMT_CLEAR_MASK (~_PGMT_MASK) static inline enum page_cache_mode get_page_memtype(struct page *pg) @@ -935,23 +935,20 @@ static void free_pfn_range(u64 paddr, unsigned long size) static int follow_phys(struct vm_area_struct *vma, unsigned long *prot, resource_size_t *phys) { - pte_t *ptep, pte; - spinlock_t *ptl; + struct follow_pfnmap_args args = { .vma = vma, .address = vma->vm_start }; - if (follow_pte(vma, vma->vm_start, &ptep, &ptl)) + if (follow_pfnmap_start(&args)) return -EINVAL; - pte = ptep_get(ptep); - /* Never return PFNs of anon folios in COW mappings. */ - if (vm_normal_folio(vma, vma->vm_start, pte)) { - pte_unmap_unlock(ptep, ptl); + if (!args.special) { + follow_pfnmap_end(&args); return -EINVAL; } - *prot = pgprot_val(pte_pgprot(pte)); - *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; - pte_unmap_unlock(ptep, ptl); + *prot = pgprot_val(args.pgprot); + *phys = (resource_size_t)args.pfn << PAGE_SHIFT; + follow_pfnmap_end(&args); return 0; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index f5931499c2d6..5745a354a241 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -641,6 +641,18 @@ pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, } #endif +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ + defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) +pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp) +{ + VM_WARN_ON_ONCE(!pud_present(*pudp)); + pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp)); + flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); + return old; +} +#endif + /** * reserve_top_address - reserves a hole in the top of kernel address space * @reserve - size of hole to reserve @@ -926,3 +938,9 @@ void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pmd_shstk(pmd)); } + +void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) +{ + /* See note in arch_check_zapped_pte() */ + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pud_shstk(pud)); +} diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 9c52a95937ad..6f8e0f21c710 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -57,8 +57,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) } set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); - printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", - pxm, apic_id, node); + pr_debug("SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node); } /* Callback for Proximity Domain -> LAPIC mapping */ @@ -98,8 +97,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) set_apicid_to_node(apic_id, node); node_set(node, numa_nodes_parsed); - printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", - pxm, apic_id, node); + pr_debug("SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node); } int __init x86_acpi_numa_init(void) diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index bda73cb7a044..ae295659ca14 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -144,3 +144,4 @@ static void __exit cleanup(void) module_init(init); module_exit(cleanup); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Test module for mmiotrace"); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 44ac64f3a047..86593d1b787d 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -11,6 +11,7 @@ #include <linux/sched/smt.h> #include <linux/task_work.h> #include <linux/mmu_notifier.h> +#include <linux/mmu_context.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -85,9 +86,6 @@ * */ -/* There are 12 bits of space for ASIDS in CR3 */ -#define CR3_HW_ASID_BITS 12 - /* * When enabled, MITIGATION_PAGE_TABLE_ISOLATION consumes a single bit for * user/kernel switches @@ -160,7 +158,6 @@ static inline unsigned long build_cr3(pgd_t *pgd, u16 asid, unsigned long lam) unsigned long cr3 = __sme_pa(pgd) | lam; if (static_cpu_has(X86_FEATURE_PCID)) { - VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); cr3 |= kern_pcid(asid); } else { VM_WARN_ON_ONCE(asid != 0); @@ -503,9 +500,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, { struct mm_struct *prev = this_cpu_read(cpu_tlbstate.loaded_mm); u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); - unsigned long new_lam = mm_lam_cr3_mask(next); bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy); unsigned cpu = smp_processor_id(); + unsigned long new_lam; u64 next_tlb_gen; bool need_flush; u16 new_asid; @@ -619,9 +616,7 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, cpumask_clear_cpu(cpu, mm_cpumask(prev)); } - /* - * Start remote flushes and then read tlb_gen. - */ + /* Start receiving IPIs and then read tlb_gen (and LAM below) */ if (next != &init_mm) cpumask_set_cpu(cpu, mm_cpumask(next)); next_tlb_gen = atomic64_read(&next->context.tlb_gen); @@ -633,7 +628,7 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, barrier(); } - set_tlbstate_lam_mode(next); + new_lam = mm_lam_cr3_mask(next); if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); @@ -652,6 +647,7 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); + cpu_tlbstate_update_lam(new_lam, mm_untag_mask(next)); if (next != prev) { cr4_update_pce_mm(next); @@ -698,6 +694,7 @@ void initialize_tlbstate_and_flush(void) int i; struct mm_struct *mm = this_cpu_read(cpu_tlbstate.loaded_mm); u64 tlb_gen = atomic64_read(&init_mm.context.tlb_gen); + unsigned long lam = mm_lam_cr3_mask(mm); unsigned long cr3 = __read_cr3(); /* Assert that CR3 already references the right mm. */ @@ -705,7 +702,7 @@ void initialize_tlbstate_and_flush(void) /* LAM expected to be disabled */ WARN_ON(cr3 & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57)); - WARN_ON(mm_lam_cr3_mask(mm)); + WARN_ON(lam); /* * Assert that CR4.PCIDE is set if needed. (CR4.PCIDE initialization @@ -724,7 +721,7 @@ void initialize_tlbstate_and_flush(void) this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, tlb_gen); - set_tlbstate_lam_mode(mm); + cpu_tlbstate_update_lam(lam, mm_untag_mask(mm)); for (i = 1; i < TLB_NR_DYN_ASIDS; i++) this_cpu_write(cpu_tlbstate.ctxs[i].ctx_id, 0); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index d25d81c8ecc0..06b080b61aa5 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -64,6 +64,56 @@ static bool is_imm8(int value) return value <= 127 && value >= -128; } +/* + * Let us limit the positive offset to be <= 123. + * This is to ensure eventual jit convergence For the following patterns: + * ... + * pass4, final_proglen=4391: + * ... + * 20e: 48 85 ff test rdi,rdi + * 211: 74 7d je 0x290 + * 213: 48 8b 77 00 mov rsi,QWORD PTR [rdi+0x0] + * ... + * 289: 48 85 ff test rdi,rdi + * 28c: 74 17 je 0x2a5 + * 28e: e9 7f ff ff ff jmp 0x212 + * 293: bf 03 00 00 00 mov edi,0x3 + * Note that insn at 0x211 is 2-byte cond jump insn for offset 0x7d (-125) + * and insn at 0x28e is 5-byte jmp insn with offset -129. + * + * pass5, final_proglen=4392: + * ... + * 20e: 48 85 ff test rdi,rdi + * 211: 0f 84 80 00 00 00 je 0x297 + * 217: 48 8b 77 00 mov rsi,QWORD PTR [rdi+0x0] + * ... + * 28d: 48 85 ff test rdi,rdi + * 290: 74 1a je 0x2ac + * 292: eb 84 jmp 0x218 + * 294: bf 03 00 00 00 mov edi,0x3 + * Note that insn at 0x211 is 6-byte cond jump insn now since its offset + * becomes 0x80 based on previous round (0x293 - 0x213 = 0x80). + * At the same time, insn at 0x292 is a 2-byte insn since its offset is + * -124. + * + * pass6 will repeat the same code as in pass4 and this will prevent + * eventual convergence. + * + * To fix this issue, we need to break je (2->6 bytes) <-> jmp (5->2 bytes) + * cycle in the above. In the above example je offset <= 0x7c should work. + * + * For other cases, je <-> je needs offset <= 0x7b to avoid no convergence + * issue. For jmp <-> je and jmp <-> jmp cases, jmp offset <= 0x7c should + * avoid no convergence issue. + * + * Overall, let us limit the positive offset for 8bit cond/uncond jmp insn + * to maximum 123 (0x7b). This way, the jit pass can eventually converge. + */ +static bool is_imm8_jmp_offset(int value) +{ + return value <= 123 && value >= -128; +} + static bool is_simm32(s64 value) { return value == (s64)(s32)value; @@ -273,7 +323,7 @@ struct jit_context { /* Number of bytes emit_patch() needs to generate instructions */ #define X86_PATCH_SIZE 5 /* Number of bytes that will be skipped on tailcall */ -#define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE) +#define X86_TAIL_CALL_OFFSET (12 + ENDBR_INSN_SIZE) static void push_r12(u8 **pprog) { @@ -403,6 +453,37 @@ static void emit_cfi(u8 **pprog, u32 hash) *pprog = prog; } +static void emit_prologue_tail_call(u8 **pprog, bool is_subprog) +{ + u8 *prog = *pprog; + + if (!is_subprog) { + /* cmp rax, MAX_TAIL_CALL_CNT */ + EMIT4(0x48, 0x83, 0xF8, MAX_TAIL_CALL_CNT); + EMIT2(X86_JA, 6); /* ja 6 */ + /* rax is tail_call_cnt if <= MAX_TAIL_CALL_CNT. + * case1: entry of main prog. + * case2: tail callee of main prog. + */ + EMIT1(0x50); /* push rax */ + /* Make rax as tail_call_cnt_ptr. */ + EMIT3(0x48, 0x89, 0xE0); /* mov rax, rsp */ + EMIT2(0xEB, 1); /* jmp 1 */ + /* rax is tail_call_cnt_ptr if > MAX_TAIL_CALL_CNT. + * case: tail callee of subprog. + */ + EMIT1(0x50); /* push rax */ + /* push tail_call_cnt_ptr */ + EMIT1(0x50); /* push rax */ + } else { /* is_subprog */ + /* rax is tail_call_cnt_ptr. */ + EMIT1(0x50); /* push rax */ + EMIT1(0x50); /* push rax */ + } + + *pprog = prog; +} + /* * Emit x86-64 prologue code for BPF program. * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes @@ -424,10 +505,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, /* When it's the entry of the whole tailcall context, * zeroing rax means initialising tail_call_cnt. */ - EMIT2(0x31, 0xC0); /* xor eax, eax */ + EMIT3(0x48, 0x31, 0xC0); /* xor rax, rax */ else /* Keep the same instruction layout. */ - EMIT2(0x66, 0x90); /* nop2 */ + emit_nops(&prog, 3); /* nop3 */ } /* Exception callback receives FP as third parameter */ if (is_exception_cb) { @@ -453,7 +534,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, if (stack_depth) EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8)); if (tail_call_reachable) - EMIT1(0x50); /* push rax */ + emit_prologue_tail_call(&prog, is_subprog); *pprog = prog; } @@ -589,13 +670,15 @@ static void emit_return(u8 **pprog, u8 *ip) *pprog = prog; } +#define BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack) (-16 - round_up(stack, 8)) + /* * Generate the following code: * * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... * if (index >= array->map.max_entries) * goto out; - * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) + * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT) * goto out; * prog = array->ptrs[index]; * if (prog == NULL) @@ -608,7 +691,7 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, u32 stack_depth, u8 *ip, struct jit_context *ctx) { - int tcc_off = -4 - round_up(stack_depth, 8); + int tcc_ptr_off = BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack_depth); u8 *prog = *pprog, *start = *pprog; int offset; @@ -630,16 +713,14 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, EMIT2(X86_JBE, offset); /* jbe out */ /* - * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) + * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT) * goto out; */ - EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ - EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ + EMIT3_off32(0x48, 0x8B, 0x85, tcc_ptr_off); /* mov rax, qword ptr [rbp - tcc_ptr_off] */ + EMIT4(0x48, 0x83, 0x38, MAX_TAIL_CALL_CNT); /* cmp qword ptr [rax], MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_indirect_label - (prog + 2 - start); EMIT2(X86_JAE, offset); /* jae out */ - EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ - EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ /* prog = array->ptrs[index]; */ EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6, /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */ @@ -654,6 +735,9 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, offset = ctx->tail_call_indirect_label - (prog + 2 - start); EMIT2(X86_JE, offset); /* je out */ + /* Inc tail_call_cnt if the slot is populated. */ + EMIT4(0x48, 0x83, 0x00, 0x01); /* add qword ptr [rax], 1 */ + if (bpf_prog->aux->exception_boundary) { pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); @@ -663,6 +747,11 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, pop_r12(&prog); } + /* Pop tail_call_cnt_ptr. */ + EMIT1(0x58); /* pop rax */ + /* Pop tail_call_cnt, if it's main prog. + * Pop tail_call_cnt_ptr, if it's subprog. + */ EMIT1(0x58); /* pop rax */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xC4, /* add rsp, sd */ @@ -691,21 +780,19 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, bool *callee_regs_used, u32 stack_depth, struct jit_context *ctx) { - int tcc_off = -4 - round_up(stack_depth, 8); + int tcc_ptr_off = BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack_depth); u8 *prog = *pprog, *start = *pprog; int offset; /* - * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) + * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT) * goto out; */ - EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ - EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ + EMIT3_off32(0x48, 0x8B, 0x85, tcc_ptr_off); /* mov rax, qword ptr [rbp - tcc_ptr_off] */ + EMIT4(0x48, 0x83, 0x38, MAX_TAIL_CALL_CNT); /* cmp qword ptr [rax], MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_direct_label - (prog + 2 - start); EMIT2(X86_JAE, offset); /* jae out */ - EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ - EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ poke->tailcall_bypass = ip + (prog - start); poke->adj_off = X86_TAIL_CALL_OFFSET; @@ -715,6 +802,9 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE, poke->tailcall_bypass); + /* Inc tail_call_cnt if the slot is populated. */ + EMIT4(0x48, 0x83, 0x00, 0x01); /* add qword ptr [rax], 1 */ + if (bpf_prog->aux->exception_boundary) { pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); @@ -724,6 +814,11 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, pop_r12(&prog); } + /* Pop tail_call_cnt_ptr. */ + EMIT1(0x58); /* pop rax */ + /* Pop tail_call_cnt, if it's main prog. + * Pop tail_call_cnt_ptr, if it's subprog. + */ EMIT1(0x58); /* pop rax */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8)); @@ -1311,9 +1406,11 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op) #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) -/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ -#define RESTORE_TAIL_CALL_CNT(stack) \ - EMIT3_off32(0x48, 0x8B, 0x85, -round_up(stack, 8) - 8) +#define __LOAD_TCC_PTR(off) \ + EMIT3_off32(0x48, 0x8B, 0x85, off) +/* mov rax, qword ptr [rbp - rounded_stack_depth - 16] */ +#define LOAD_TAIL_CALL_CNT_PTR(stack) \ + __LOAD_TCC_PTR(BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack)) static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) @@ -2031,7 +2128,7 @@ populate_extable: func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { - RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth); + LOAD_TAIL_CALL_CNT_PTR(bpf_prog->aux->stack_depth); ip += 7; } if (!imm32) @@ -2184,7 +2281,7 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ return -EFAULT; } jmp_offset = addrs[i + insn->off] - addrs[i]; - if (is_imm8(jmp_offset)) { + if (is_imm8_jmp_offset(jmp_offset)) { if (jmp_padding) { /* To keep the jmp_offset valid, the extra bytes are * padded before the jump insn, so we subtract the @@ -2266,7 +2363,7 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ break; } emit_jmp: - if (is_imm8(jmp_offset)) { + if (is_imm8_jmp_offset(jmp_offset)) { if (jmp_padding) { /* To avoid breaking jmp_offset, the extra bytes * are padded before the actual jmp insn, so @@ -2706,6 +2803,10 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, return 0; } +/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ +#define LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack) \ + __LOAD_TCC_PTR(-round_up(stack, 8) - 8) + /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 @@ -2826,7 +2927,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im * [ ... ] * [ stack_arg2 ] * RBP - arg_stack_off [ stack_arg1 ] - * RSP [ tail_call_cnt ] BPF_TRAMP_F_TAIL_CALL_CTX + * RSP [ tail_call_cnt_ptr ] BPF_TRAMP_F_TAIL_CALL_CTX */ /* room for return value of orig_call or fentry prog */ @@ -2955,10 +3056,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im save_args(m, &prog, arg_stack_off, true); if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { - /* Before calling the original function, restore the - * tail_call_cnt from stack to rax. + /* Before calling the original function, load the + * tail_call_cnt_ptr from stack to rax. */ - RESTORE_TAIL_CALL_CNT(stack_size); + LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack_size); } if (flags & BPF_TRAMP_F_ORIG_STACK) { @@ -3017,10 +3118,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im goto cleanup; } } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { - /* Before running the original function, restore the - * tail_call_cnt from stack to rax. + /* Before running the original function, load the + * tail_call_cnt_ptr from stack to rax. */ - RESTORE_TAIL_CALL_CNT(stack_size); + LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack_size); } /* restore return value of orig_call or fentry prog back into RAX */ diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index b33afb240601..98a9bb92d75c 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -980,7 +980,7 @@ static void amd_rp_pme_suspend(struct pci_dev *dev) return; rp = pcie_find_root_port(dev); - if (!rp->pm_cap) + if (!rp || !rp->pm_cap) return; rp->pme_support &= ~((PCI_PM_CAP_PME_D3hot|PCI_PM_CAP_PME_D3cold) >> @@ -994,7 +994,7 @@ static void amd_rp_pme_resume(struct pci_dev *dev) u16 pmc; rp = pcie_find_root_port(dev); - if (!rp->pm_cap) + if (!rp || !rp->pm_cap) return; pci_read_config_word(rp, rp->pm_cap + PCI_PM_PMC, &pmc); diff --git a/arch/x86/platform/geode/Makefile b/arch/x86/platform/geode/Makefile index a8a6b1dedb01..34b53e97a0ad 100644 --- a/arch/x86/platform/geode/Makefile +++ b/arch/x86/platform/geode/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_GEODE_COMMON) += geode-common.o obj-$(CONFIG_ALIX) += alix.o obj-$(CONFIG_NET5501) += net5501.o obj-$(CONFIG_GEOS) += geos.o diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c index b39bf3b5e108..be65cd704e21 100644 --- a/arch/x86/platform/geode/alix.c +++ b/arch/x86/platform/geode/alix.c @@ -18,15 +18,12 @@ #include <linux/io.h> #include <linux/string.h> #include <linux/moduleparam.h> -#include <linux/leds.h> -#include <linux/platform_device.h> -#include <linux/input.h> -#include <linux/gpio_keys.h> -#include <linux/gpio/machine.h> #include <linux/dmi.h> #include <asm/geode.h> +#include "geode-common.h" + #define BIOS_SIGNATURE_TINYBIOS 0xf0000 #define BIOS_SIGNATURE_COREBOOT 0x500 #define BIOS_REGION_SIZE 0x10000 @@ -41,79 +38,16 @@ module_param(force, bool, 0444); /* FIXME: Award bios is not automatically detected as Alix platform */ MODULE_PARM_DESC(force, "Force detection as ALIX.2/ALIX.3 platform"); -static struct gpio_keys_button alix_gpio_buttons[] = { - { - .code = KEY_RESTART, - .gpio = 24, - .active_low = 1, - .desc = "Reset button", - .type = EV_KEY, - .wakeup = 0, - .debounce_interval = 100, - .can_disable = 0, - } -}; -static struct gpio_keys_platform_data alix_buttons_data = { - .buttons = alix_gpio_buttons, - .nbuttons = ARRAY_SIZE(alix_gpio_buttons), - .poll_interval = 20, -}; - -static struct platform_device alix_buttons_dev = { - .name = "gpio-keys-polled", - .id = 1, - .dev = { - .platform_data = &alix_buttons_data, - } -}; - -static struct gpio_led alix_leds[] = { - { - .name = "alix:1", - .default_trigger = "default-on", - }, - { - .name = "alix:2", - .default_trigger = "default-off", - }, - { - .name = "alix:3", - .default_trigger = "default-off", - }, -}; - -static struct gpio_led_platform_data alix_leds_data = { - .num_leds = ARRAY_SIZE(alix_leds), - .leds = alix_leds, -}; - -static struct gpiod_lookup_table alix_leds_gpio_table = { - .dev_id = "leds-gpio", - .table = { - /* The Geode GPIOs should be on the CS5535 companion chip */ - GPIO_LOOKUP_IDX("cs5535-gpio", 6, NULL, 0, GPIO_ACTIVE_LOW), - GPIO_LOOKUP_IDX("cs5535-gpio", 25, NULL, 1, GPIO_ACTIVE_LOW), - GPIO_LOOKUP_IDX("cs5535-gpio", 27, NULL, 2, GPIO_ACTIVE_LOW), - { } - }, -}; - -static struct platform_device alix_leds_dev = { - .name = "leds-gpio", - .id = -1, - .dev.platform_data = &alix_leds_data, -}; - -static struct platform_device *alix_devs[] __initdata = { - &alix_buttons_dev, - &alix_leds_dev, +static const struct geode_led alix_leds[] __initconst = { + { 6, true }, + { 25, false }, + { 27, false }, }; static void __init register_alix(void) { - /* Setup LED control through leds-gpio driver */ - gpiod_add_lookup_table(&alix_leds_gpio_table); - platform_add_devices(alix_devs, ARRAY_SIZE(alix_devs)); + geode_create_restart_key(24); + geode_create_leds("alix", alix_leds, ARRAY_SIZE(alix_leds)); } static bool __init alix_present(unsigned long bios_phys, diff --git a/arch/x86/platform/geode/geode-common.c b/arch/x86/platform/geode/geode-common.c new file mode 100644 index 000000000000..8fd78e60bf15 --- /dev/null +++ b/arch/x86/platform/geode/geode-common.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared helpers to register GPIO-connected buttons and LEDs + * on AMD Geode boards. + */ + +#include <linux/err.h> +#include <linux/gpio/machine.h> +#include <linux/gpio/property.h> +#include <linux/input.h> +#include <linux/leds.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "geode-common.h" + +static const struct software_node geode_gpiochip_node = { + .name = "cs5535-gpio", +}; + +static const struct property_entry geode_gpio_keys_props[] = { + PROPERTY_ENTRY_U32("poll-interval", 20), + { } +}; + +static const struct software_node geode_gpio_keys_node = { + .name = "geode-gpio-keys", + .properties = geode_gpio_keys_props, +}; + +static struct property_entry geode_restart_key_props[] = { + { /* Placeholder for GPIO property */ }, + PROPERTY_ENTRY_U32("linux,code", KEY_RESTART), + PROPERTY_ENTRY_STRING("label", "Reset button"), + PROPERTY_ENTRY_U32("debounce-interval", 100), + { } +}; + +static const struct software_node geode_restart_key_node = { + .parent = &geode_gpio_keys_node, + .properties = geode_restart_key_props, +}; + +static const struct software_node *geode_gpio_keys_swnodes[] __initconst = { + &geode_gpiochip_node, + &geode_gpio_keys_node, + &geode_restart_key_node, + NULL +}; + +/* + * Creates gpio-keys-polled device for the restart key. + * + * Note that it needs to be called first, before geode_create_leds(), + * because it registers gpiochip software node used by both gpio-keys and + * leds-gpio devices. + */ +int __init geode_create_restart_key(unsigned int pin) +{ + struct platform_device_info keys_info = { + .name = "gpio-keys-polled", + .id = 1, + }; + struct platform_device *pd; + int err; + + geode_restart_key_props[0] = PROPERTY_ENTRY_GPIO("gpios", + &geode_gpiochip_node, + pin, GPIO_ACTIVE_LOW); + + err = software_node_register_node_group(geode_gpio_keys_swnodes); + if (err) { + pr_err("failed to register gpio-keys software nodes: %d\n", err); + return err; + } + + keys_info.fwnode = software_node_fwnode(&geode_gpio_keys_node); + + pd = platform_device_register_full(&keys_info); + err = PTR_ERR_OR_ZERO(pd); + if (err) { + pr_err("failed to create gpio-keys device: %d\n", err); + software_node_unregister_node_group(geode_gpio_keys_swnodes); + return err; + } + + return 0; +} + +static const struct software_node geode_gpio_leds_node = { + .name = "geode-leds", +}; + +#define MAX_LEDS 3 + +int __init geode_create_leds(const char *label, const struct geode_led *leds, + unsigned int n_leds) +{ + const struct software_node *group[MAX_LEDS + 2] = { 0 }; + struct software_node *swnodes; + struct property_entry *props; + struct platform_device_info led_info = { + .name = "leds-gpio", + .id = PLATFORM_DEVID_NONE, + }; + struct platform_device *led_dev; + const char *node_name; + int err; + int i; + + if (n_leds > MAX_LEDS) { + pr_err("%s: too many LEDs\n", __func__); + return -EINVAL; + } + + swnodes = kcalloc(n_leds, sizeof(*swnodes), GFP_KERNEL); + if (!swnodes) + return -ENOMEM; + + /* + * Each LED is represented by 3 properties: "gpios", + * "linux,default-trigger", and am empty terminator. + */ + props = kcalloc(n_leds * 3, sizeof(*props), GFP_KERNEL); + if (!props) { + err = -ENOMEM; + goto err_free_swnodes; + } + + group[0] = &geode_gpio_leds_node; + for (i = 0; i < n_leds; i++) { + node_name = kasprintf(GFP_KERNEL, "%s:%d", label, i); + if (!node_name) { + err = -ENOMEM; + goto err_free_names; + } + + props[i * 3 + 0] = + PROPERTY_ENTRY_GPIO("gpios", &geode_gpiochip_node, + leds[i].pin, GPIO_ACTIVE_LOW); + props[i * 3 + 1] = + PROPERTY_ENTRY_STRING("linux,default-trigger", + leds[i].default_on ? + "default-on" : "default-off"); + /* props[i * 3 + 2] is an empty terminator */ + + swnodes[i] = SOFTWARE_NODE(node_name, &props[i * 3], + &geode_gpio_leds_node); + group[i + 1] = &swnodes[i]; + } + + err = software_node_register_node_group(group); + if (err) { + pr_err("failed to register LED software nodes: %d\n", err); + goto err_free_names; + } + + led_info.fwnode = software_node_fwnode(&geode_gpio_leds_node); + + led_dev = platform_device_register_full(&led_info); + err = PTR_ERR_OR_ZERO(led_dev); + if (err) { + pr_err("failed to create LED device: %d\n", err); + goto err_unregister_group; + } + + return 0; + +err_unregister_group: + software_node_unregister_node_group(group); +err_free_names: + while (--i >= 0) + kfree(swnodes[i].name); + kfree(props); +err_free_swnodes: + kfree(swnodes); + return err; +} diff --git a/arch/x86/platform/geode/geode-common.h b/arch/x86/platform/geode/geode-common.h new file mode 100644 index 000000000000..9e0afd34bfad --- /dev/null +++ b/arch/x86/platform/geode/geode-common.h @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared helpers to register GPIO-connected buttons and LEDs + * on AMD Geode boards. + */ + +#ifndef __PLATFORM_GEODE_COMMON_H +#define __PLATFORM_GEODE_COMMON_H + +#include <linux/property.h> + +struct geode_led { + unsigned int pin; + bool default_on; +}; + +int geode_create_restart_key(unsigned int pin); +int geode_create_leds(const char *label, const struct geode_led *leds, + unsigned int n_leds); + +#endif /* __PLATFORM_GEODE_COMMON_H */ diff --git a/arch/x86/platform/geode/geos.c b/arch/x86/platform/geode/geos.c index d263528c90bb..98027fb1ec32 100644 --- a/arch/x86/platform/geode/geos.c +++ b/arch/x86/platform/geode/geos.c @@ -16,88 +16,22 @@ #include <linux/init.h> #include <linux/io.h> #include <linux/string.h> -#include <linux/leds.h> -#include <linux/platform_device.h> -#include <linux/input.h> -#include <linux/gpio_keys.h> -#include <linux/gpio/machine.h> #include <linux/dmi.h> #include <asm/geode.h> -static struct gpio_keys_button geos_gpio_buttons[] = { - { - .code = KEY_RESTART, - .gpio = 3, - .active_low = 1, - .desc = "Reset button", - .type = EV_KEY, - .wakeup = 0, - .debounce_interval = 100, - .can_disable = 0, - } -}; -static struct gpio_keys_platform_data geos_buttons_data = { - .buttons = geos_gpio_buttons, - .nbuttons = ARRAY_SIZE(geos_gpio_buttons), - .poll_interval = 20, -}; - -static struct platform_device geos_buttons_dev = { - .name = "gpio-keys-polled", - .id = 1, - .dev = { - .platform_data = &geos_buttons_data, - } -}; - -static struct gpio_led geos_leds[] = { - { - .name = "geos:1", - .default_trigger = "default-on", - }, - { - .name = "geos:2", - .default_trigger = "default-off", - }, - { - .name = "geos:3", - .default_trigger = "default-off", - }, -}; - -static struct gpio_led_platform_data geos_leds_data = { - .num_leds = ARRAY_SIZE(geos_leds), - .leds = geos_leds, -}; - -static struct gpiod_lookup_table geos_leds_gpio_table = { - .dev_id = "leds-gpio", - .table = { - /* The Geode GPIOs should be on the CS5535 companion chip */ - GPIO_LOOKUP_IDX("cs5535-gpio", 6, NULL, 0, GPIO_ACTIVE_LOW), - GPIO_LOOKUP_IDX("cs5535-gpio", 25, NULL, 1, GPIO_ACTIVE_LOW), - GPIO_LOOKUP_IDX("cs5535-gpio", 27, NULL, 2, GPIO_ACTIVE_LOW), - { } - }, -}; - -static struct platform_device geos_leds_dev = { - .name = "leds-gpio", - .id = -1, - .dev.platform_data = &geos_leds_data, -}; +#include "geode-common.h" -static struct platform_device *geos_devs[] __initdata = { - &geos_buttons_dev, - &geos_leds_dev, +static const struct geode_led geos_leds[] __initconst = { + { 6, true }, + { 25, false }, + { 27, false }, }; static void __init register_geos(void) { - /* Setup LED control through leds-gpio driver */ - gpiod_add_lookup_table(&geos_leds_gpio_table); - platform_add_devices(geos_devs, ARRAY_SIZE(geos_devs)); + geode_create_restart_key(3); + geode_create_leds("geos", geos_leds, ARRAY_SIZE(geos_leds)); } static int __init geos_init(void) diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c index 558384acd777..c9cee7dea99b 100644 --- a/arch/x86/platform/geode/net5501.c +++ b/arch/x86/platform/geode/net5501.c @@ -16,80 +16,25 @@ #include <linux/init.h> #include <linux/io.h> #include <linux/string.h> -#include <linux/leds.h> -#include <linux/platform_device.h> #include <linux/input.h> -#include <linux/gpio_keys.h> #include <linux/gpio/machine.h> +#include <linux/gpio/property.h> #include <asm/geode.h> +#include "geode-common.h" + #define BIOS_REGION_BASE 0xffff0000 #define BIOS_REGION_SIZE 0x00010000 -static struct gpio_keys_button net5501_gpio_buttons[] = { - { - .code = KEY_RESTART, - .gpio = 24, - .active_low = 1, - .desc = "Reset button", - .type = EV_KEY, - .wakeup = 0, - .debounce_interval = 100, - .can_disable = 0, - } -}; -static struct gpio_keys_platform_data net5501_buttons_data = { - .buttons = net5501_gpio_buttons, - .nbuttons = ARRAY_SIZE(net5501_gpio_buttons), - .poll_interval = 20, -}; - -static struct platform_device net5501_buttons_dev = { - .name = "gpio-keys-polled", - .id = 1, - .dev = { - .platform_data = &net5501_buttons_data, - } -}; - -static struct gpio_led net5501_leds[] = { - { - .name = "net5501:1", - .default_trigger = "default-on", - }, -}; - -static struct gpio_led_platform_data net5501_leds_data = { - .num_leds = ARRAY_SIZE(net5501_leds), - .leds = net5501_leds, -}; - -static struct gpiod_lookup_table net5501_leds_gpio_table = { - .dev_id = "leds-gpio", - .table = { - /* The Geode GPIOs should be on the CS5535 companion chip */ - GPIO_LOOKUP_IDX("cs5535-gpio", 6, NULL, 0, GPIO_ACTIVE_HIGH), - { } - }, -}; - -static struct platform_device net5501_leds_dev = { - .name = "leds-gpio", - .id = -1, - .dev.platform_data = &net5501_leds_data, -}; - -static struct platform_device *net5501_devs[] __initdata = { - &net5501_buttons_dev, - &net5501_leds_dev, +static const struct geode_led net5501_leds[] __initconst = { + { 6, true }, }; static void __init register_net5501(void) { - /* Setup LED control through leds-gpio driver */ - gpiod_add_lookup_table(&net5501_leds_gpio_table); - platform_add_devices(net5501_devs, ARRAY_SIZE(net5501_devs)); + geode_create_restart_key(24); + geode_create_leds("net5501", net5501_leds, ARRAY_SIZE(net5501_leds)); } struct net5501_board { diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index f83bbe0acd4a..a8e75f8c14fd 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -27,9 +27,10 @@ #include <asm/intel-mid.h> #include <asm/io.h> #include <asm/i8259.h> -#include <asm/intel_scu_ipc.h> #include <asm/reboot.h> +#include <linux/platform_data/x86/intel_scu_ipc.h> + #define IPCMSG_COLD_OFF 0x80 /* Only for Tangier */ #define IPCMSG_COLD_RESET 0xF1 diff --git a/arch/x86/platform/pvh/Makefile b/arch/x86/platform/pvh/Makefile index 5dec5067c9fb..c43fb7964dc4 100644 --- a/arch/x86/platform/pvh/Makefile +++ b/arch/x86/platform/pvh/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_head.o := y +KASAN_SANITIZE := n obj-$(CONFIG_PVH) += enlighten.o obj-$(CONFIG_PVH) += head.o diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 944e0290f2c0..2263885d16ba 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -130,7 +130,11 @@ void __init xen_prepare_pvh(void) BUG(); } - memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); + /* + * This must not compile to "call memset" because memset() may be + * instrumented. + */ + __builtin_memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); hypervisor_specific_init(xen_guest); diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index f7235ef87bc3..64fca49cd88f 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -7,6 +7,7 @@ .code32 .text #define _pa(x) ((x) - __START_KERNEL_map) +#define rva(x) ((x) - pvh_start_xen) #include <linux/elfnote.h> #include <linux/init.h> @@ -15,6 +16,7 @@ #include <asm/segment.h> #include <asm/asm.h> #include <asm/boot.h> +#include <asm/pgtable.h> #include <asm/processor-flags.h> #include <asm/msr.h> #include <asm/nospec-branch.h> @@ -54,7 +56,25 @@ SYM_CODE_START_LOCAL(pvh_start_xen) UNWIND_HINT_END_OF_STACK cld - lgdt (_pa(gdt)) + /* + * See the comment for startup_32 for more details. We need to + * execute a call to get the execution address to be position + * independent, but we don't have a stack. Save and restore the + * magic field of start_info in ebx, and use that as the stack. + */ + mov (%ebx), %eax + leal 4(%ebx), %esp + ANNOTATE_INTRA_FUNCTION_CALL + call 1f +1: popl %ebp + mov %eax, (%ebx) + subl $rva(1b), %ebp + movl $0, %esp + + leal rva(gdt)(%ebp), %eax + leal rva(gdt_start)(%ebp), %ecx + movl %ecx, 2(%eax) + lgdt (%eax) mov $PVH_DS_SEL,%eax mov %eax,%ds @@ -62,14 +82,14 @@ SYM_CODE_START_LOCAL(pvh_start_xen) mov %eax,%ss /* Stash hvm_start_info. */ - mov $_pa(pvh_start_info), %edi + leal rva(pvh_start_info)(%ebp), %edi mov %ebx, %esi - mov _pa(pvh_start_info_sz), %ecx + movl rva(pvh_start_info_sz)(%ebp), %ecx shr $2,%ecx rep movsl - mov $_pa(early_stack_end), %esp + leal rva(early_stack_end)(%ebp), %esp /* Enable PAE mode. */ mov %cr4, %eax @@ -83,31 +103,86 @@ SYM_CODE_START_LOCAL(pvh_start_xen) btsl $_EFER_LME, %eax wrmsr + mov %ebp, %ebx + subl $_pa(pvh_start_xen), %ebx /* offset */ + jz .Lpagetable_done + + /* Fixup page-tables for relocation. */ + leal rva(pvh_init_top_pgt)(%ebp), %edi + movl $PTRS_PER_PGD, %ecx +2: + testl $_PAGE_PRESENT, 0x00(%edi) + jz 1f + addl %ebx, 0x00(%edi) +1: + addl $8, %edi + decl %ecx + jnz 2b + + /* L3 ident has a single entry. */ + leal rva(pvh_level3_ident_pgt)(%ebp), %edi + addl %ebx, 0x00(%edi) + + leal rva(pvh_level3_kernel_pgt)(%ebp), %edi + addl %ebx, (PAGE_SIZE - 16)(%edi) + addl %ebx, (PAGE_SIZE - 8)(%edi) + + /* pvh_level2_ident_pgt is fine - large pages */ + + /* pvh_level2_kernel_pgt needs adjustment - large pages */ + leal rva(pvh_level2_kernel_pgt)(%ebp), %edi + movl $PTRS_PER_PMD, %ecx +2: + testl $_PAGE_PRESENT, 0x00(%edi) + jz 1f + addl %ebx, 0x00(%edi) +1: + addl $8, %edi + decl %ecx + jnz 2b + +.Lpagetable_done: /* Enable pre-constructed page tables. */ - mov $_pa(init_top_pgt), %eax + leal rva(pvh_init_top_pgt)(%ebp), %eax mov %eax, %cr3 mov $(X86_CR0_PG | X86_CR0_PE), %eax mov %eax, %cr0 /* Jump to 64-bit mode. */ - ljmp $PVH_CS_SEL, $_pa(1f) + pushl $PVH_CS_SEL + leal rva(1f)(%ebp), %eax + pushl %eax + lretl /* 64-bit entry point. */ .code64 1: + UNWIND_HINT_END_OF_STACK + /* Set base address in stack canary descriptor. */ mov $MSR_GS_BASE,%ecx - mov $_pa(canary), %eax + leal canary(%rip), %eax xor %edx, %edx wrmsr + /* + * Calculate load offset and store in phys_base. __pa() needs + * phys_base set to calculate the hypercall page in xen_pvh_init(). + */ + movq %rbp, %rbx + subq $_pa(pvh_start_xen), %rbx + movq %rbx, phys_base(%rip) call xen_prepare_pvh + /* + * Clear phys_base. __startup_64 will *add* to its value, + * so reset to 0. + */ + xor %rbx, %rbx + movq %rbx, phys_base(%rip) /* startup_64 expects boot_params in %rsi. */ - mov $_pa(pvh_bootparams), %rsi - mov $_pa(startup_64), %rax - ANNOTATE_RETPOLINE_SAFE - jmp *%rax + lea pvh_bootparams(%rip), %rsi + jmp startup_64 #else /* CONFIG_X86_64 */ @@ -143,7 +218,7 @@ SYM_CODE_END(pvh_start_xen) .balign 8 SYM_DATA_START_LOCAL(gdt) .word gdt_end - gdt_start - .long _pa(gdt_start) + .long _pa(gdt_start) /* x86-64 will overwrite if relocated. */ .word 0 SYM_DATA_END(gdt) SYM_DATA_START_LOCAL(gdt_start) @@ -163,5 +238,67 @@ SYM_DATA_START_LOCAL(early_stack) .fill BOOT_STACK_SIZE, 1, 0 SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end) +#ifdef CONFIG_X86_64 +/* + * Xen PVH needs a set of identity mapped and kernel high mapping + * page tables. pvh_start_xen starts running on the identity mapped + * page tables, but xen_prepare_pvh calls into the high mapping. + * These page tables need to be relocatable and are only used until + * startup_64 transitions to init_top_pgt. + */ +SYM_DATA_START_PAGE_ALIGNED(pvh_init_top_pgt) + .quad pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .org pvh_init_top_pgt + L4_PAGE_OFFSET * 8, 0 + .quad pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .org pvh_init_top_pgt + L4_START_KERNEL * 8, 0 + /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ + .quad pvh_level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC +SYM_DATA_END(pvh_init_top_pgt) + +SYM_DATA_START_PAGE_ALIGNED(pvh_level3_ident_pgt) + .quad pvh_level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .fill 511, 8, 0 +SYM_DATA_END(pvh_level3_ident_pgt) +SYM_DATA_START_PAGE_ALIGNED(pvh_level2_ident_pgt) + /* + * Since I easily can, map the first 1G. + * Don't set NX because code runs from these pages. + * + * Note: This sets _PAGE_GLOBAL despite whether + * the CPU supports it or it is enabled. But, + * the CPU should ignore the bit. + */ + PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) +SYM_DATA_END(pvh_level2_ident_pgt) +SYM_DATA_START_PAGE_ALIGNED(pvh_level3_kernel_pgt) + .fill L3_START_KERNEL, 8, 0 + /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ + .quad pvh_level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .quad 0 /* no fixmap */ +SYM_DATA_END(pvh_level3_kernel_pgt) + +SYM_DATA_START_PAGE_ALIGNED(pvh_level2_kernel_pgt) + /* + * Kernel high mapping. + * + * The kernel code+data+bss must be located below KERNEL_IMAGE_SIZE in + * virtual address space, which is 1 GiB if RANDOMIZE_BASE is enabled, + * 512 MiB otherwise. + * + * (NOTE: after that starts the module area, see MODULES_VADDR.) + * + * This table is eventually used by the kernel during normal runtime. + * Care must be taken to clear out undesired bits later, like _PAGE_RW + * or _PAGE_GLOBAL in some cases. + */ + PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE / PMD_SIZE) +SYM_DATA_END(pvh_level2_kernel_pgt) + + ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_RELOC, + .long CONFIG_PHYSICAL_ALIGN; + .long LOAD_PHYSICAL_ADDR; + .long KERNEL_IMAGE_SIZE - 1) +#endif + ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY, _ASM_PTR (pvh_start_xen - __START_KERNEL_map)) diff --git a/arch/x86/um/sysrq_32.c b/arch/x86/um/sysrq_32.c index f2383484840d..a1ee415c008d 100644 --- a/arch/x86/um/sysrq_32.c +++ b/arch/x86/um/sysrq_32.c @@ -9,7 +9,6 @@ #include <linux/sched/debug.h> #include <linux/kallsyms.h> #include <asm/ptrace.h> -#include <asm/sysrq.h> /* This is declared by <linux/sched.h> */ void show_regs(struct pt_regs *regs) diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c index 0bf6de40abff..340d8a243c8a 100644 --- a/arch/x86/um/sysrq_64.c +++ b/arch/x86/um/sysrq_64.c @@ -12,7 +12,6 @@ #include <linux/utsname.h> #include <asm/current.h> #include <asm/ptrace.h> -#include <asm/sysrq.h> void show_regs(struct pt_regs *regs) { diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index 76d9f6ce7a3d..f238f7b33cdd 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -52,8 +52,11 @@ subsys_initcall(init_vdso); int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - int err; + struct vm_area_struct *vma; struct mm_struct *mm = current->mm; + static struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + }; if (!vdso_enabled) return 0; @@ -61,12 +64,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (mmap_write_lock_killable(mm)) return -EINTR; - err = install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, + vdso_mapping.pages = vdsop; + vma = _install_special_mapping(mm, um_vdso_addr, PAGE_SIZE, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - vdsop); + &vdso_mapping); mmap_write_unlock(mm); - return err; + return IS_ERR(vma) ? PTR_ERR(vma) : 0; } diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 728a4366ca85..bf68c329fc01 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -4,6 +4,7 @@ #include <linux/mm.h> #include <xen/hvc-console.h> +#include <xen/acpi.h> #include <asm/bootparam.h> #include <asm/io_apic.h> @@ -28,6 +29,28 @@ bool __ro_after_init xen_pvh; EXPORT_SYMBOL_GPL(xen_pvh); +#ifdef CONFIG_XEN_DOM0 +int xen_pvh_setup_gsi(int gsi, int trigger, int polarity) +{ + int ret; + struct physdev_setup_gsi setup_gsi; + + setup_gsi.gsi = gsi; + setup_gsi.triggering = (trigger == ACPI_EDGE_SENSITIVE ? 0 : 1); + setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1); + + ret = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi); + if (ret == -EEXIST) { + xen_raw_printk("Already setup the GSI :%d\n", gsi); + ret = 0; + } else if (ret) + xen_raw_printk("Fail to setup GSI (%d)!\n", gsi); + + return ret; +} +EXPORT_SYMBOL_GPL(xen_pvh_setup_gsi); +#endif + /* * Reserve e820 UNUSABLE regions to inflate the memory balloon. * diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index f1ce39d6d32c..55a4996d0c04 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -665,7 +665,7 @@ static spinlock_t *xen_pte_lock(struct page *page, struct mm_struct *mm) { spinlock_t *ptl = NULL; -#if USE_SPLIT_PTE_PTLOCKS +#if defined(CONFIG_SPLIT_PTE_PTLOCKS) ptl = ptlock_ptr(page_ptdesc(page)); spin_lock_nest_lock(ptl, &mm->page_table_lock); #endif @@ -1553,7 +1553,8 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned) + if (level == PT_PTE && IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS) && + !pinned) __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); xen_mc_issue(XEN_LAZY_MMU); @@ -1581,7 +1582,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level) if (pinned) { xen_mc_batch(); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) + if (level == PT_PTE && IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS)) __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); __set_pfn_prot(pfn, PAGE_KERNEL); @@ -2018,10 +2019,7 @@ void __init xen_reserve_special_pages(void) void __init xen_pt_check_e820(void) { - if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) { - xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n"); - BUG(); - } + xen_chk_is_e820_usable(xen_pt_base, xen_pt_size, "page table"); } static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 7c735b730acd..b52d3e17e2c1 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -70,6 +70,7 @@ #include <linux/memblock.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/acpi.h> #include <asm/cache.h> #include <asm/setup.h> @@ -80,6 +81,7 @@ #include <asm/xen/hypervisor.h> #include <xen/balloon.h> #include <xen/grant_table.h> +#include <xen/hvc-console.h> #include "xen-ops.h" @@ -792,6 +794,102 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, return ret; } +/* Remapped non-RAM areas */ +#define NR_NONRAM_REMAP 4 +static struct nonram_remap { + phys_addr_t maddr; + phys_addr_t paddr; + size_t size; +} xen_nonram_remap[NR_NONRAM_REMAP] __ro_after_init; +static unsigned int nr_nonram_remap __ro_after_init; + +/* + * Do the real remapping of non-RAM regions as specified in the + * xen_nonram_remap[] array. + * In case of an error just crash the system. + */ +void __init xen_do_remap_nonram(void) +{ + unsigned int i; + unsigned int remapped = 0; + const struct nonram_remap *remap = xen_nonram_remap; + unsigned long pfn, mfn, end_pfn; + + for (i = 0; i < nr_nonram_remap; i++) { + end_pfn = PFN_UP(remap->paddr + remap->size); + pfn = PFN_DOWN(remap->paddr); + mfn = PFN_DOWN(remap->maddr); + while (pfn < end_pfn) { + if (!set_phys_to_machine(pfn, mfn)) + panic("Failed to set p2m mapping for pfn=%lx mfn=%lx\n", + pfn, mfn); + + pfn++; + mfn++; + remapped++; + } + + remap++; + } + + pr_info("Remapped %u non-RAM page(s)\n", remapped); +} + +#ifdef CONFIG_ACPI +/* + * Xen variant of acpi_os_ioremap() taking potentially remapped non-RAM + * regions into account. + * Any attempt to map an area crossing a remap boundary will produce a + * WARN() splat. + * phys is related to remap->maddr on input and will be rebased to remap->paddr. + */ +static void __iomem *xen_acpi_os_ioremap(acpi_physical_address phys, + acpi_size size) +{ + unsigned int i; + const struct nonram_remap *remap = xen_nonram_remap; + + for (i = 0; i < nr_nonram_remap; i++) { + if (phys + size > remap->maddr && + phys < remap->maddr + remap->size) { + WARN_ON(phys < remap->maddr || + phys + size > remap->maddr + remap->size); + phys += remap->paddr - remap->maddr; + break; + } + } + + return x86_acpi_os_ioremap(phys, size); +} +#endif /* CONFIG_ACPI */ + +/* + * Add a new non-RAM remap entry. + * In case of no free entry found, just crash the system. + */ +void __init xen_add_remap_nonram(phys_addr_t maddr, phys_addr_t paddr, + unsigned long size) +{ + BUG_ON((maddr & ~PAGE_MASK) != (paddr & ~PAGE_MASK)); + + if (nr_nonram_remap == NR_NONRAM_REMAP) { + xen_raw_console_write("Number of required E820 entry remapping actions exceed maximum value\n"); + BUG(); + } + +#ifdef CONFIG_ACPI + /* Switch to the Xen acpi_os_ioremap() variant. */ + if (nr_nonram_remap == 0) + acpi_os_ioremap = xen_acpi_os_ioremap; +#endif + + xen_nonram_remap[nr_nonram_remap].maddr = maddr; + xen_nonram_remap[nr_nonram_remap].paddr = paddr; + xen_nonram_remap[nr_nonram_remap].size = size; + + nr_nonram_remap++; +} + #ifdef CONFIG_XEN_DEBUG_FS #include <linux/debugfs.h> static int p2m_dump_show(struct seq_file *m, void *v) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 806ddb2391d9..c3db71d96c43 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -15,12 +15,12 @@ #include <linux/cpuidle.h> #include <linux/cpufreq.h> #include <linux/memory_hotplug.h> +#include <linux/acpi.h> #include <asm/elf.h> #include <asm/vdso.h> #include <asm/e820/api.h> #include <asm/setup.h> -#include <asm/acpi.h> #include <asm/numa.h> #include <asm/idtentry.h> #include <asm/xen/hypervisor.h> @@ -46,6 +46,9 @@ bool xen_pv_pci_possible; /* E820 map used during setting up memory. */ static struct e820_table xen_e820_table __initdata; +/* Number of initially usable memory pages. */ +static unsigned long ini_nr_pages __initdata; + /* * Buffer used to remap identity mapped pages. We only need the virtual space. * The physical page behind this address is remapped as needed to different @@ -212,7 +215,7 @@ static int __init xen_free_mfn(unsigned long mfn) * as a fallback if the remapping fails. */ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, - unsigned long end_pfn, unsigned long nr_pages) + unsigned long end_pfn) { unsigned long pfn, end; int ret; @@ -220,7 +223,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, WARN_ON(start_pfn > end_pfn); /* Release pages first. */ - end = min(end_pfn, nr_pages); + end = min(end_pfn, ini_nr_pages); for (pfn = start_pfn; pfn < end; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); @@ -341,15 +344,14 @@ static void __init xen_do_set_identity_and_remap_chunk( * to Xen and not remapped. */ static unsigned long __init xen_set_identity_and_remap_chunk( - unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, - unsigned long remap_pfn) + unsigned long start_pfn, unsigned long end_pfn, unsigned long remap_pfn) { unsigned long pfn; unsigned long i = 0; unsigned long n = end_pfn - start_pfn; if (remap_pfn == 0) - remap_pfn = nr_pages; + remap_pfn = ini_nr_pages; while (i < n) { unsigned long cur_pfn = start_pfn + i; @@ -358,19 +360,19 @@ static unsigned long __init xen_set_identity_and_remap_chunk( unsigned long remap_range_size; /* Do not remap pages beyond the current allocation */ - if (cur_pfn >= nr_pages) { + if (cur_pfn >= ini_nr_pages) { /* Identity map remaining pages */ set_phys_range_identity(cur_pfn, cur_pfn + size); break; } - if (cur_pfn + size > nr_pages) - size = nr_pages - cur_pfn; + if (cur_pfn + size > ini_nr_pages) + size = ini_nr_pages - cur_pfn; remap_range_size = xen_find_pfn_range(&remap_pfn); if (!remap_range_size) { pr_warn("Unable to find available pfn range, not remapping identity pages\n"); xen_set_identity_and_release_chunk(cur_pfn, - cur_pfn + left, nr_pages); + cur_pfn + left); break; } /* Adjust size to fit in current e820 RAM region */ @@ -397,18 +399,18 @@ static unsigned long __init xen_set_identity_and_remap_chunk( } static unsigned long __init xen_count_remap_pages( - unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, + unsigned long start_pfn, unsigned long end_pfn, unsigned long remap_pages) { - if (start_pfn >= nr_pages) + if (start_pfn >= ini_nr_pages) return remap_pages; - return remap_pages + min(end_pfn, nr_pages) - start_pfn; + return remap_pages + min(end_pfn, ini_nr_pages) - start_pfn; } -static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, +static unsigned long __init xen_foreach_remap_area( unsigned long (*func)(unsigned long start_pfn, unsigned long end_pfn, - unsigned long nr_pages, unsigned long last_val)) + unsigned long last_val)) { phys_addr_t start = 0; unsigned long ret_val = 0; @@ -436,8 +438,7 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, end_pfn = PFN_UP(entry->addr); if (start_pfn < end_pfn) - ret_val = func(start_pfn, end_pfn, nr_pages, - ret_val); + ret_val = func(start_pfn, end_pfn, ret_val); start = end; } } @@ -494,6 +495,8 @@ void __init xen_remap_memory(void) set_pte_mfn(buf, mfn_save, PAGE_KERNEL); pr_info("Remapped %ld page(s)\n", remapped); + + xen_do_remap_nonram(); } static unsigned long __init xen_get_pages_limit(void) @@ -567,7 +570,7 @@ static void __init xen_ignore_unusable(void) } } -bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) +static bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) { struct e820_entry *entry; unsigned mapcnt; @@ -625,6 +628,111 @@ phys_addr_t __init xen_find_free_area(phys_addr_t size) } /* + * Swap a non-RAM E820 map entry with RAM above ini_nr_pages. + * Note that the E820 map is modified accordingly, but the P2M map isn't yet. + * The adaption of the P2M must be deferred until page allocation is possible. + */ +static void __init xen_e820_swap_entry_with_ram(struct e820_entry *swap_entry) +{ + struct e820_entry *entry; + unsigned int mapcnt; + phys_addr_t mem_end = PFN_PHYS(ini_nr_pages); + phys_addr_t swap_addr, swap_size, entry_end; + + swap_addr = PAGE_ALIGN_DOWN(swap_entry->addr); + swap_size = PAGE_ALIGN(swap_entry->addr - swap_addr + swap_entry->size); + entry = xen_e820_table.entries; + + for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) { + entry_end = entry->addr + entry->size; + if (entry->type == E820_TYPE_RAM && entry->size >= swap_size && + entry_end - swap_size >= mem_end) { + /* Reduce RAM entry by needed space (whole pages). */ + entry->size -= swap_size; + + /* Add new entry at the end of E820 map. */ + entry = xen_e820_table.entries + + xen_e820_table.nr_entries; + xen_e820_table.nr_entries++; + + /* Fill new entry (keep size and page offset). */ + entry->type = swap_entry->type; + entry->addr = entry_end - swap_size + + swap_addr - swap_entry->addr; + entry->size = swap_entry->size; + + /* Convert old entry to RAM, align to pages. */ + swap_entry->type = E820_TYPE_RAM; + swap_entry->addr = swap_addr; + swap_entry->size = swap_size; + + /* Remember PFN<->MFN relation for P2M update. */ + xen_add_remap_nonram(swap_addr, entry_end - swap_size, + swap_size); + + /* Order E820 table and merge entries. */ + e820__update_table(&xen_e820_table); + + return; + } + + entry++; + } + + xen_raw_console_write("No suitable area found for required E820 entry remapping action\n"); + BUG(); +} + +/* + * Look for non-RAM memory types in a specific guest physical area and move + * those away if possible (ACPI NVS only for now). + */ +static void __init xen_e820_resolve_conflicts(phys_addr_t start, + phys_addr_t size) +{ + struct e820_entry *entry; + unsigned int mapcnt; + phys_addr_t end; + + if (!size) + return; + + end = start + size; + entry = xen_e820_table.entries; + + for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) { + if (entry->addr >= end) + return; + + if (entry->addr + entry->size > start && + entry->type == E820_TYPE_NVS) + xen_e820_swap_entry_with_ram(entry); + + entry++; + } +} + +/* + * Check for an area in physical memory to be usable for non-movable purposes. + * An area is considered to usable if the used E820 map lists it to be RAM or + * some other type which can be moved to higher PFNs while keeping the MFNs. + * In case the area is not usable, crash the system with an error message. + */ +void __init xen_chk_is_e820_usable(phys_addr_t start, phys_addr_t size, + const char *component) +{ + xen_e820_resolve_conflicts(start, size); + + if (!xen_is_e820_reserved(start, size)) + return; + + xen_raw_console_write("Xen hypervisor allocated "); + xen_raw_console_write(component); + xen_raw_console_write(" memory conflicts with E820 map\n"); + BUG(); +} + +/* * Like memcpy, but with physical addresses for dest and src. */ static void __init xen_phys_memcpy(phys_addr_t dest, phys_addr_t src, @@ -683,7 +791,7 @@ static void __init xen_reserve_xen_mfnlist(void) **/ char * __init xen_memory_setup(void) { - unsigned long max_pfn, pfn_s, n_pfns; + unsigned long pfn_s, n_pfns; phys_addr_t mem_end, addr, size, chunk_size; u32 type; int rc; @@ -695,9 +803,8 @@ char * __init xen_memory_setup(void) int op; xen_parse_512gb(); - max_pfn = xen_get_pages_limit(); - max_pfn = min(max_pfn, xen_start_info->nr_pages); - mem_end = PFN_PHYS(max_pfn); + ini_nr_pages = min(xen_get_pages_limit(), xen_start_info->nr_pages); + mem_end = PFN_PHYS(ini_nr_pages); memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries); set_xen_guest_handle(memmap.buffer, xen_e820_table.entries); @@ -747,13 +854,35 @@ char * __init xen_memory_setup(void) /* Make sure the Xen-supplied memory map is well-ordered. */ e820__update_table(&xen_e820_table); + /* + * Check whether the kernel itself conflicts with the target E820 map. + * Failing now is better than running into weird problems later due + * to relocating (and even reusing) pages with kernel text or data. + */ + xen_chk_is_e820_usable(__pa_symbol(_text), + __pa_symbol(_end) - __pa_symbol(_text), + "kernel"); + + /* + * Check for a conflict of the xen_start_info memory with the target + * E820 map. + */ + xen_chk_is_e820_usable(__pa(xen_start_info), sizeof(*xen_start_info), + "xen_start_info"); + + /* + * Check for a conflict of the hypervisor supplied page tables with + * the target E820 map. + */ + xen_pt_check_e820(); + max_pages = xen_get_max_pages(); /* How many extra pages do we need due to remapping? */ - max_pages += xen_foreach_remap_area(max_pfn, xen_count_remap_pages); + max_pages += xen_foreach_remap_area(xen_count_remap_pages); - if (max_pages > max_pfn) - extra_pages += max_pages - max_pfn; + if (max_pages > ini_nr_pages) + extra_pages += max_pages - ini_nr_pages; /* * Clamp the amount of extra memory to a EXTRA_MEM_RATIO @@ -762,8 +891,8 @@ char * __init xen_memory_setup(void) * Make sure we have no memory above max_pages, as this area * isn't handled by the p2m management. */ - maxmem_pages = EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)); - extra_pages = min3(maxmem_pages, extra_pages, max_pages - max_pfn); + maxmem_pages = EXTRA_MEM_RATIO * min(ini_nr_pages, PFN_DOWN(MAXMEM)); + extra_pages = min3(maxmem_pages, extra_pages, max_pages - ini_nr_pages); i = 0; addr = xen_e820_table.entries[0].addr; size = xen_e820_table.entries[0].size; @@ -819,23 +948,6 @@ char * __init xen_memory_setup(void) e820__update_table(e820_table); - /* - * Check whether the kernel itself conflicts with the target E820 map. - * Failing now is better than running into weird problems later due - * to relocating (and even reusing) pages with kernel text or data. - */ - if (xen_is_e820_reserved(__pa_symbol(_text), - __pa_symbol(__bss_stop) - __pa_symbol(_text))) { - xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n"); - BUG(); - } - - /* - * Check for a conflict of the hypervisor supplied page tables with - * the target E820 map. - */ - xen_pt_check_e820(); - xen_reserve_xen_mfnlist(); /* Check for a conflict of the initrd with the target E820 map. */ @@ -863,7 +975,7 @@ char * __init xen_memory_setup(void) * Set identity map on non-RAM pages and prepare remapping the * underlying RAM. */ - xen_foreach_remap_area(max_pfn, xen_set_identity_and_remap_chunk); + xen_foreach_remap_area(xen_set_identity_and_remap_chunk); pr_info("Released %ld page(s)\n", xen_released_pages); diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 0cf16fc79e0b..e1b782e823e6 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -47,8 +47,12 @@ void xen_mm_unpin_all(void); #ifdef CONFIG_X86_64 void __init xen_relocate_p2m(void); #endif +void __init xen_do_remap_nonram(void); +void __init xen_add_remap_nonram(phys_addr_t maddr, phys_addr_t paddr, + unsigned long size); -bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size); +void __init xen_chk_is_e820_usable(phys_addr_t start, phys_addr_t size, + const char *component); unsigned long __ref xen_chk_extra_mem(unsigned long pfn); void __init xen_inv_extra_mem(void); void __init xen_remap_memory(void); |