diff options
176 files changed, 4232 insertions, 924 deletions
diff --git a/Documentation/devicetree/bindings/hwlock/hwlock.txt b/Documentation/devicetree/bindings/hwlock/hwlock.txt new file mode 100644 index 000000000000..085d1f5c916a --- /dev/null +++ b/Documentation/devicetree/bindings/hwlock/hwlock.txt @@ -0,0 +1,59 @@ +Generic hwlock bindings +======================= + +Generic bindings that are common to all the hwlock platform specific driver +implementations. + +Please also look through the individual platform specific hwlock binding +documentations for identifying any additional properties specific to that +platform. + +hwlock providers: +================= + +Required properties: +- #hwlock-cells: Specifies the number of cells needed to represent a + specific lock. + +hwlock users: +============= + +Consumers that require specific hwlock(s) should specify them using the +property "hwlocks", and an optional "hwlock-names" property. + +Required properties: +- hwlocks: List of phandle to a hwlock provider node and an + associated hwlock args specifier as indicated by + #hwlock-cells. The list can have just a single hwlock + or multiple hwlocks, with each hwlock represented by + a phandle and a corresponding args specifier. + +Optional properties: +- hwlock-names: List of hwlock name strings defined in the same order + as the hwlocks, with one name per hwlock. Consumers can + use the hwlock-names to match and get a specific hwlock. + + +1. Example of a node using a single specific hwlock: + +The following example has a node requesting a hwlock in the bank defined by +the node hwlock1. hwlock1 is a hwlock provider with an argument specifier +of length 1. + + node { + ... + hwlocks = <&hwlock1 2>; + ... + }; + +2. Example of a node using multiple specific hwlocks: + +The following example has a node requesting two hwlocks, a hwlock within +the hwlock device node 'hwlock1' with #hwlock-cells value of 1, and another +hwlock within the hwlock device node 'hwlock2' with #hwlock-cells value of 2. + + node { + ... + hwlocks = <&hwlock1 2>, <&hwlock2 0 3>; + ... + }; diff --git a/Documentation/devicetree/bindings/hwlock/omap-hwspinlock.txt b/Documentation/devicetree/bindings/hwlock/omap-hwspinlock.txt new file mode 100644 index 000000000000..2c9804f4f4ac --- /dev/null +++ b/Documentation/devicetree/bindings/hwlock/omap-hwspinlock.txt @@ -0,0 +1,26 @@ +OMAP4+ HwSpinlock Driver +======================== + +Required properties: +- compatible: Should be "ti,omap4-hwspinlock" for + OMAP44xx, OMAP54xx, AM33xx, AM43xx, DRA7xx SoCs +- reg: Contains the hwspinlock module register address space + (base address and length) +- ti,hwmods: Name of the hwmod associated with the hwspinlock device +- #hwlock-cells: Should be 1. The OMAP hwspinlock users will use a + 0-indexed relative hwlock number as the argument + specifier value for requesting a specific hwspinlock + within a hwspinlock bank. + +Please look at the generic hwlock binding for usage information for consumers, +"Documentation/devicetree/bindings/hwlock/hwlock.txt" + +Example: + +/* OMAP4 */ +hwspinlock: spinlock@4a0f6000 { + compatible = "ti,omap4-hwspinlock"; + reg = <0x4a0f6000 0x1000>; + ti,hwmods = "spinlock"; + #hwlock-cells = <1>; +}; diff --git a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt new file mode 100644 index 000000000000..4563f524556b --- /dev/null +++ b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.txt @@ -0,0 +1,39 @@ +Qualcomm Hardware Mutex Block: + +The hardware block provides mutexes utilized between different processors on +the SoC as part of the communication protocol used by these processors. + +- compatible: + Usage: required + Value type: <string> + Definition: must be one of: + "qcom,sfpb-mutex", + "qcom,tcsr-mutex" + +- syscon: + Usage: required + Value type: <prop-encoded-array> + Definition: one cell containing: + syscon phandle + offset of the hwmutex block within the syscon + stride of the hwmutex registers + +- #hwlock-cells: + Usage: required + Value type: <u32> + Definition: must be 1, the specified cell represent the lock id + (hwlock standard property, see hwlock.txt) + +Example: + + tcsr_mutex_block: syscon@fd484000 { + compatible = "syscon"; + reg = <0xfd484000 0x2000>; + }; + + hwlock@fd484000 { + compatible = "qcom,tcsr-mutex"; + syscon = <&tcsr_mutex_block 0 0x80>; + + #hwlock-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/hwlock/sirf,hwspinlock.txt b/Documentation/devicetree/bindings/hwlock/sirf,hwspinlock.txt new file mode 100644 index 000000000000..9bb1240a68e0 --- /dev/null +++ b/Documentation/devicetree/bindings/hwlock/sirf,hwspinlock.txt @@ -0,0 +1,28 @@ +SIRF Hardware spinlock device Binding +----------------------------------------------- + +Required properties : +- compatible : shall contain only one of the following: + "sirf,hwspinlock" + +- reg : the register address of hwspinlock + +- #hwlock-cells : hwlock users only use the hwlock id to represent a specific + hwlock, so the number of cells should be <1> here. + +Please look at the generic hwlock binding for usage information for consumers, +"Documentation/devicetree/bindings/hwlock/hwlock.txt" + +Example of hwlock provider: + hwlock { + compatible = "sirf,hwspinlock"; + reg = <0x13240000 0x00010000>; + #hwlock-cells = <1>; + }; + +Example of hwlock users: + node { + ... + hwlocks = <&hwlock 2>; + ... + }; diff --git a/Documentation/devicetree/bindings/remoteproc/wkup_m3_rproc.txt b/Documentation/devicetree/bindings/remoteproc/wkup_m3_rproc.txt new file mode 100644 index 000000000000..3a70073797eb --- /dev/null +++ b/Documentation/devicetree/bindings/remoteproc/wkup_m3_rproc.txt @@ -0,0 +1,52 @@ +TI Wakeup M3 Remoteproc Driver +============================== + +The TI AM33xx and AM43xx family of devices use a small Cortex M3 co-processor +(commonly referred to as Wakeup M3 or CM3) to help with various low power tasks +that cannot be controlled from the MPU. This CM3 processor requires a firmware +binary to accomplish this. The wkup_m3 remoteproc driver handles the loading of +the firmware and booting of the CM3. + +Wkup M3 Device Node: +==================== +A wkup_m3 device node is used to represent the Wakeup M3 processor instance +within the SoC. It is added as a child node of the parent interconnect bus +(l4_wkup) through which it is accessible to the MPU. + +Required properties: +-------------------- +- compatible: Should be one of, + "ti,am3352-wkup-m3" for AM33xx SoCs + "ti,am4372-wkup-m3" for AM43xx SoCs +- reg: Should contain the address ranges for the two internal + memory regions, UMEM and DMEM. The parent node should + provide an appropriate ranges property for properly + translating these into bus addresses. +- reg-names: Contains the corresponding names for the two memory + regions. These should be named "umem" & "dmem". +- ti,hwmods: Name of the hwmod associated with the wkupm3 device. +- ti,pm-firmware: Name of firmware file to be used for loading and + booting the wkup_m3 remote processor. + +Example: +-------- +/* AM33xx */ +ocp { + l4_wkup: l4_wkup@44c00000 { + compatible = "am335-l4-wkup", "simple-bus"; + ranges = <0 0x44c00000 0x400000>; + #address-cells = <1>; + #size-cells = <1>; + + wkup_m3: wkup_m3@100000 { + compatible = "ti,am3352-wkup-m3"; + reg = <0x100000 0x4000>, + <0x180000 0x2000>; + reg-names = "umem", "dmem"; + ti,hwmods = "wkup_m3"; + ti,pm-firmware = "am335x-pm-firmware.elf"; + }; + }; + + ... +}; diff --git a/Documentation/hwmon/submitting-patches b/Documentation/hwmon/submitting-patches index 3d1bac399a22..d201828d202f 100644 --- a/Documentation/hwmon/submitting-patches +++ b/Documentation/hwmon/submitting-patches @@ -81,6 +81,13 @@ increase the chances of your change being accepted. * Provide a detect function if and only if a chip can be detected reliably. +* Only the following I2C addresses shall be probed: 0x18-0x1f, 0x28-0x2f, + 0x48-0x4f, 0x58, 0x5c, 0x73 and 0x77. Probing other addresses is strongly + discouraged as it is known to cause trouble with other (non-hwmon) I2C + chips. If your chip lives at an address which can't be probed then the + device will have to be instantiated explicitly (which is always better + anyway.) + * Avoid writing to chip registers in the detect function. If you have to write, only do it after you have already gathered enough data to be certain that the detection is going to be successful. diff --git a/Documentation/hwmon/w83792d b/Documentation/hwmon/w83792d index 53f7b6866fec..f2ffc402ea45 100644 --- a/Documentation/hwmon/w83792d +++ b/Documentation/hwmon/w83792d @@ -8,6 +8,7 @@ Supported chips: Datasheet: http://www.winbond.com.tw Author: Shane Huang (Winbond) +Updated: Roger Lucas Module Parameters @@ -38,9 +39,16 @@ parameter; this will put it into a more well-behaved state first. The driver implements three temperature sensors, seven fan rotation speed sensors, nine voltage sensors, and two automatic fan regulation strategies called: Smart Fan I (Thermal Cruise mode) and Smart Fan II. -Automatic fan control mode is possible only for fan1-fan3. Fan4-fan7 can run -synchronized with selected fan (fan1-fan3). This functionality and manual PWM -control for fan4-fan7 is not yet implemented. + +The driver also implements up to seven fan control outputs: pwm1-7. Pwm1-7 +can be configured to PWM output or Analogue DC output via their associated +pwmX_mode. Outputs pwm4 through pwm7 may or may not be present depending on +how the W83792AD/D was configured by the BIOS. + +Automatic fan control mode is possible only for fan1-fan3. + +For all pwmX outputs, a value of 0 means minimum fan speed and a value of +255 means maximum fan speed. Temperatures are measured in degrees Celsius and measurement resolution is 1 degC for temp1 and 0.5 degC for temp2 and temp3. An alarm is triggered when @@ -157,14 +165,14 @@ for each fan. /sys files ---------- -pwm[1-3] - this file stores PWM duty cycle or DC value (fan speed) in range: +pwm[1-7] - this file stores PWM duty cycle or DC value (fan speed) in range: 0 (stop) to 255 (full) pwm[1-3]_enable - this file controls mode of fan/temperature control: * 0 Disabled * 1 Manual mode * 2 Smart Fan II * 3 Thermal Cruise -pwm[1-3]_mode - Select PWM of DC mode +pwm[1-7]_mode - Select PWM or DC mode * 0 DC * 1 PWM thermal_cruise[1-3] - Selects the desired temperature for cruise (degC) diff --git a/Documentation/hwspinlock.txt b/Documentation/hwspinlock.txt index 62f7d4ea6e26..61c1ee98e59f 100644 --- a/Documentation/hwspinlock.txt +++ b/Documentation/hwspinlock.txt @@ -48,6 +48,16 @@ independent, drivers. ids for predefined purposes. Should be called from a process context (might sleep). + int of_hwspin_lock_get_id(struct device_node *np, int index); + - retrieve the global lock id for an OF phandle-based specific lock. + This function provides a means for DT users of a hwspinlock module + to get the global lock id of a specific hwspinlock, so that it can + be requested using the normal hwspin_lock_request_specific() API. + The function returns a lock id number on success, -EPROBE_DEFER if + the hwspinlock device is not yet registered with the core, or other + error values. + Should be called from a process context (might sleep). + int hwspin_lock_free(struct hwspinlock *hwlock); - free a previously-assigned hwspinlock; returns 0 on success, or an appropriate error code on failure (e.g. -EINVAL if the hwspinlock diff --git a/Documentation/remoteproc.txt b/Documentation/remoteproc.txt index e6469fdcf89a..ef0219fa4bb4 100644 --- a/Documentation/remoteproc.txt +++ b/Documentation/remoteproc.txt @@ -51,6 +51,12 @@ cost. rproc_shutdown() returns, and users can still use it with a subsequent rproc_boot(), if needed. + struct rproc *rproc_get_by_phandle(phandle phandle) + - Find an rproc handle using a device tree phandle. Returns the rproc + handle on success, and NULL on failure. This function increments + the remote processor's refcount, so always use rproc_put() to + decrement it back once rproc isn't needed anymore. + 3. Typical usage #include <linux/remoteproc.h> diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 7c1f9fad6674..9da6f3512249 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -406,7 +406,7 @@ Protocol: 2.00+ - If 0, the protected-mode code is loaded at 0x10000. - If 1, the protected-mode code is loaded at 0x100000. - Bit 1 (kernel internal): ALSR_FLAG + Bit 1 (kernel internal): KASLR_FLAG - Used internally by the compressed kernel to communicate KASLR status to kernel proper. If 1, KASLR enabled. diff --git a/Documentation/x86/entry_64.txt b/Documentation/x86/entry_64.txt index 33884d156125..c1df8eba9dfd 100644 --- a/Documentation/x86/entry_64.txt +++ b/Documentation/x86/entry_64.txt @@ -1,14 +1,14 @@ This file documents some of the kernel entries in -arch/x86/kernel/entry_64.S. A lot of this explanation is adapted from +arch/x86/entry/entry_64.S. A lot of this explanation is adapted from an email from Ingo Molnar: http://lkml.kernel.org/r/<20110529191055.GC9835%40elte.hu> The x86 architecture has quite a few different ways to jump into kernel code. Most of these entry points are registered in -arch/x86/kernel/traps.c and implemented in arch/x86/kernel/entry_64.S -for 64-bit, arch/x86/kernel/entry_32.S for 32-bit and finally -arch/x86/ia32/ia32entry.S which implements the 32-bit compatibility +arch/x86/kernel/traps.c and implemented in arch/x86/entry/entry_64.S +for 64-bit, arch/x86/entry/entry_32.S for 32-bit and finally +arch/x86/entry/entry_64_compat.S which implements the 32-bit compatibility syscall entry points and thus provides for 32-bit processes the ability to execute syscalls when running on 64-bit kernels. diff --git a/MAINTAINERS b/MAINTAINERS index 86ea2084bc58..e23ff1cbd12b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7364,7 +7364,6 @@ M: Ohad Ben-Cohen <ohad@wizery.com> L: linux-omap@vger.kernel.org S: Maintained F: drivers/hwspinlock/omap_hwspinlock.c -F: arch/arm/mach-omap2/hwspinlock.c OMAP MMC SUPPORT M: Jarkko Lavinen <jarkko.lavinen@nokia.com> diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index f1a68c63dc99..903c85be2897 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -274,8 +274,5 @@ obj-y += $(nand-m) $(nand-y) smsc911x-$(CONFIG_SMSC911X) := gpmc-smsc911x.o obj-y += $(smsc911x-m) $(smsc911x-y) -ifneq ($(CONFIG_HWSPINLOCK_OMAP),) -obj-y += hwspinlock.o -endif obj-y += common-board-devices.o twl-common.o dss-common.o diff --git a/arch/arm/mach-omap2/hwspinlock.c b/arch/arm/mach-omap2/hwspinlock.c deleted file mode 100644 index ef175acaeaa2..000000000000 --- a/arch/arm/mach-omap2/hwspinlock.c +++ /dev/null @@ -1,60 +0,0 @@ -/* - * OMAP hardware spinlock device initialization - * - * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com - * - * Contact: Simon Que <sque@ti.com> - * Hari Kanigeri <h-kanigeri2@ti.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/err.h> -#include <linux/hwspinlock.h> - -#include "soc.h" -#include "omap_hwmod.h" -#include "omap_device.h" - -static struct hwspinlock_pdata omap_hwspinlock_pdata __initdata = { - .base_id = 0, -}; - -static int __init hwspinlocks_init(void) -{ - int retval = 0; - struct omap_hwmod *oh; - struct platform_device *pdev; - const char *oh_name = "spinlock"; - const char *dev_name = "omap_hwspinlock"; - - /* - * Hwmod lookup will fail in case our platform doesn't support the - * hardware spinlock module, so it is safe to run this initcall - * on all omaps - */ - oh = omap_hwmod_lookup(oh_name); - if (oh == NULL) - return -EINVAL; - - pdev = omap_device_build(dev_name, 0, oh, &omap_hwspinlock_pdata, - sizeof(struct hwspinlock_pdata)); - if (IS_ERR(pdev)) { - pr_err("Can't build omap_device for %s:%s\n", dev_name, - oh_name); - retval = PTR_ERR(pdev); - } - - return retval; -} -/* early board code might need to reserve specific hwspinlock instances */ -omap_postcore_initcall(hwspinlocks_init); diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index 7ce589ca54a4..9047cab68fd3 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -15,7 +15,7 @@ #include <asm/cpuidle.h> #include <asm/cpu_ops.h> -int arm_cpuidle_init(unsigned int cpu) +int __init arm_cpuidle_init(unsigned int cpu) { int ret = -EOPNOTSUPP; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index e7d934d3afe0..7a1a5da6c8c1 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -31,7 +31,6 @@ #include <asm/current.h> #include <asm/debug-monitors.h> #include <asm/hw_breakpoint.h> -#include <asm/kdebug.h> #include <asm/traps.h> #include <asm/cputype.h> #include <asm/system_misc.h> diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 702591f6180a..b31e9a4b6275 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1318,7 +1318,7 @@ static int armpmu_device_probe(struct platform_device *pdev) /* Don't bother with PPIs; they're already affine */ irq = platform_get_irq(pdev, 0); if (irq >= 0 && irq_is_percpu(irq)) - return 0; + goto out; irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); if (!irqs) @@ -1340,12 +1340,13 @@ static int armpmu_device_probe(struct platform_device *pdev) if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL)) break; - of_node_put(dn); if (cpu >= nr_cpu_ids) { pr_warn("Failed to find logical CPU for %s\n", dn->name); + of_node_put(dn); break; } + of_node_put(dn); irqs[i] = cpu; } @@ -1355,6 +1356,7 @@ static int armpmu_device_probe(struct platform_device *pdev) else kfree(irqs); +out: cpu_pmu->plat_device = pdev; return 0; } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 4b2121bd7f9c..695801a54ca5 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -396,13 +396,13 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) { u64 hwid = processor->arm_mpidr; - if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) { - pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid); + if (!(processor->flags & ACPI_MADT_ENABLED)) { + pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid); return; } - if (!(processor->flags & ACPI_MADT_ENABLED)) { - pr_err("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid); + if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) { + pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid); return; } @@ -693,7 +693,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); if ((unsigned)ipinr < NR_IPI) { - trace_ipi_entry(ipi_types[ipinr]); + trace_ipi_entry_rcuidle(ipi_types[ipinr]); __inc_irq_stat(cpu, ipi_irqs[ipinr]); } @@ -736,7 +736,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) } if ((unsigned)ipinr < NR_IPI) - trace_ipi_exit(ipi_types[ipinr]); + trace_ipi_exit_rcuidle(ipi_types[ipinr]); set_irq_regs(old_regs); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index a12251c074a8..566bc4c35040 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -335,7 +335,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if (call_undef_hook(regs) == 0) return; - if (show_unhandled_signals_ratelimited() && unhandled_signal(current, SIGILL)) { + if (unhandled_signal(current, SIGILL) && show_unhandled_signals_ratelimited()) { pr_info("%s[%d]: undefined instruction: pc=%p\n", current->comm, task_pid_nr(current), pc); dump_instr(KERN_INFO, regs); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index b1fc69cd1499..94d98cd1aad8 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -115,7 +115,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr, { struct siginfo si; - if (show_unhandled_signals_ratelimited() && unhandled_signal(tsk, sig)) { + if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) { pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n", tsk->comm, task_pid_nr(tsk), fault_name(esr), sig, addr, esr); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index cccc4af87a03..831ec534d449 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -33,13 +33,13 @@ int pmd_huge(pmd_t pmd) { - return !(pmd_val(pmd) & PMD_TABLE_BIT); + return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } int pud_huge(pud_t pud) { #ifndef __PAGETABLE_PMD_FOLDED - return !(pud_val(pud) & PUD_TABLE_BIT); + return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT); #else return 0; #endif diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 82d3435bf14f..a4ede4e2ddd1 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -117,7 +117,7 @@ void split_pud(pud_t *old_pud, pmd_t *pmd) int i = 0; do { - set_pmd(pmd, __pmd(addr | prot)); + set_pmd(pmd, __pmd(addr | pgprot_val(prot))); addr += PMD_SIZE; } while (pmd++, i++, i < PTRS_PER_PMD); } diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index de0a81a539a0..98a26ce82d26 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -110,6 +110,10 @@ /* Rd = Rn >> shift; signed */ #define A64_ASR(sf, Rd, Rn, shift) A64_SBFM(sf, Rd, Rn, shift, (sf) ? 63 : 31) +/* Zero extend */ +#define A64_UXTH(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 15) +#define A64_UXTW(sf, Rd, Rn) A64_UBFM(sf, Rd, Rn, 0, 31) + /* Move wide (immediate) */ #define A64_MOVEW(sf, Rd, imm16, shift, type) \ aarch64_insn_gen_movewide(Rd, imm16, shift, \ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index dc6a4842683a..c047598b09e0 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -113,9 +113,9 @@ static inline void emit_a64_mov_i(const int is64, const int reg, static inline int bpf2a64_offset(int bpf_to, int bpf_from, const struct jit_ctx *ctx) { - int to = ctx->offset[bpf_to + 1]; + int to = ctx->offset[bpf_to]; /* -1 to account for the Branch instruction */ - int from = ctx->offset[bpf_from + 1] - 1; + int from = ctx->offset[bpf_from] - 1; return to - from; } @@ -289,23 +289,41 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) case BPF_ALU | BPF_END | BPF_FROM_BE: #ifdef CONFIG_CPU_BIG_ENDIAN if (BPF_SRC(code) == BPF_FROM_BE) - break; + goto emit_bswap_uxt; #else /* !CONFIG_CPU_BIG_ENDIAN */ if (BPF_SRC(code) == BPF_FROM_LE) - break; + goto emit_bswap_uxt; #endif switch (imm) { case 16: emit(A64_REV16(is64, dst, dst), ctx); + /* zero-extend 16 bits into 64 bits */ + emit(A64_UXTH(is64, dst, dst), ctx); break; case 32: emit(A64_REV32(is64, dst, dst), ctx); + /* upper 32 bits already cleared */ break; case 64: emit(A64_REV64(dst, dst), ctx); break; } break; +emit_bswap_uxt: + switch (imm) { + case 16: + /* zero-extend 16 bits into 64 bits */ + emit(A64_UXTH(is64, dst, dst), ctx); + break; + case 32: + /* zero-extend 32 bits into 64 bits */ + emit(A64_UXTW(is64, dst, dst), ctx); + break; + case 64: + /* nop */ + break; + } + break; /* dst = imm */ case BPF_ALU | BPF_MOV | BPF_K: case BPF_ALU64 | BPF_MOV | BPF_K: @@ -640,10 +658,11 @@ static int build_body(struct jit_ctx *ctx) const struct bpf_insn *insn = &prog->insnsi[i]; int ret; + ret = build_insn(insn, ctx); + if (ctx->image == NULL) ctx->offset[i] = ctx->idx; - ret = build_insn(insn, ctx); if (ret > 0) { i++; continue; diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c index be186a75f622..9e3cc8a40ee9 100644 --- a/arch/nios2/kernel/time.c +++ b/arch/nios2/kernel/time.c @@ -19,7 +19,9 @@ #include <linux/io.h> #include <linux/slab.h> -#define ALTERA_TIMER_STATUS_REG 0 +#define ALTR_TIMER_COMPATIBLE "altr,timer-1.0" + +#define ALTERA_TIMER_STATUS_REG 0 #define ALTERA_TIMER_CONTROL_REG 4 #define ALTERA_TIMER_PERIODL_REG 8 #define ALTERA_TIMER_PERIODH_REG 12 @@ -304,7 +306,16 @@ void read_persistent_clock(struct timespec *ts) void __init time_init(void) { + struct device_node *np; + int count = 0; + + for_each_compatible_node(np, NULL, ALTR_TIMER_COMPATIBLE) + count++; + + if (count < 2) + panic("%d timer is found, it needs 2 timers in system\n", count); + clocksource_of_init(); } -CLOCKSOURCE_OF_DECLARE(nios2_timer, "altr,timer-1.0", nios2_time_init); +CLOCKSOURCE_OF_DECLARE(nios2_timer, ALTR_TIMER_COMPATIBLE, nios2_time_init); diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index d3f896a35b98..2eeb0a0f506d 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -456,8 +456,6 @@ static const struct super_operations hypfs_s_ops = { .show_options = hypfs_show_options, }; -static struct kobject *s390_kobj; - static int __init hypfs_init(void) { int rc; @@ -481,18 +479,16 @@ static int __init hypfs_init(void) rc = -ENODATA; goto fail_hypfs_sprp_exit; } - s390_kobj = kobject_create_and_add("s390", hypervisor_kobj); - if (!s390_kobj) { - rc = -ENOMEM; + rc = sysfs_create_mount_point(hypervisor_kobj, "s390"); + if (rc) goto fail_hypfs_diag0c_exit; - } rc = register_filesystem(&hypfs_type); if (rc) goto fail_filesystem; return 0; fail_filesystem: - kobject_put(s390_kobj); + sysfs_remove_mount_point(hypervisor_kobj, "s390"); fail_hypfs_diag0c_exit: hypfs_diag0c_exit(); fail_hypfs_sprp_exit: @@ -510,7 +506,7 @@ fail_dbfs_exit: static void __exit hypfs_exit(void) { unregister_filesystem(&hypfs_type); - kobject_put(s390_kobj); + sysfs_remove_mount_point(hypervisor_kobj, "s390"); hypfs_diag0c_exit(); hypfs_sprp_exit(); hypfs_vm_exit(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9fc5e3d9d9c8..922c5e0cea4c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -742,7 +742,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); - fpu__init_system(c); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -754,6 +753,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); setup_force_cpu_cap(X86_FEATURE_ALWAYS); + fpu__init_system(c); } void __init early_cpu_init(void) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 5801a14f7524..3658de47900f 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -357,34 +357,24 @@ void x86_release_hardware(void) */ int x86_add_exclusive(unsigned int what) { - int ret = -EBUSY, i; - - if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) - return 0; + int i; - mutex_lock(&pmc_reserve_mutex); - for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { - if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) - goto out; + if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { + mutex_lock(&pmc_reserve_mutex); + for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { + if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) + goto fail_unlock; + } + atomic_inc(&x86_pmu.lbr_exclusive[what]); + mutex_unlock(&pmc_reserve_mutex); } - atomic_inc(&x86_pmu.lbr_exclusive[what]); - ret = 0; + atomic_inc(&active_events); + return 0; -out: +fail_unlock: mutex_unlock(&pmc_reserve_mutex); - - /* - * Assuming that all exclusive events will share the PMI handler - * (which checks active_events for whether there is work to do), - * we can bump active_events counter right here, except for - * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init() - * path, which already bumps active_events for them. - */ - if (!ret && what != x86_lbr_exclusive_lbr) - atomic_inc(&active_events); - - return ret; + return -EBUSY; } void x86_del_exclusive(unsigned int what) diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index fc878fee6a51..32826791e675 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -95,11 +95,12 @@ static void __init fpu__init_system_mxcsr(void) unsigned int mask = 0; if (cpu_has_fxsr) { - struct fxregs_state fx_tmp __aligned(32) = { }; + /* Static because GCC does not get 16-byte stack alignment right: */ + static struct fxregs_state fxregs __initdata; - asm volatile("fxsave %0" : "+m" (fx_tmp)); + asm volatile("fxsave %0" : "+m" (fxregs)); - mask = fx_tmp.mxcsr_mask; + mask = fxregs.mxcsr_mask; /* * If zero then use the default features mask, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d3b95b89e9b2..80f874bf999e 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -461,19 +461,18 @@ static void __init e820_reserve_setup_data(void) { struct setup_data *data; u64 pa_data; - int found = 0; pa_data = boot_params.hdr.setup_data; + if (!pa_data) + return; + while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); e820_update_range(pa_data, sizeof(*data)+data->len, E820_RAM, E820_RESERVED_KERN); - found = 1; pa_data = data->next; early_memunmap(data, sizeof(*data)); } - if (!found) - return; sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); memcpy(&e820_saved, &e820, sizeof(struct e820map)); diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index 34338d7438f5..d1d6141920d3 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -1474,6 +1474,7 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid, nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride]; nvmeq->q_depth = depth; nvmeq->qid = qid; + nvmeq->cq_vector = -1; dev->queues[qid] = nvmeq; /* make sure queue descriptor is set before queue count, for kthread */ @@ -1726,8 +1727,10 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev) nvmeq->cq_vector = 0; result = queue_request_irq(dev, nvmeq, nvmeq->irqname); - if (result) + if (result) { + nvmeq->cq_vector = -1; goto free_nvmeq; + } return result; @@ -2213,8 +2216,10 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) dev->max_qid = nr_io_queues; result = queue_request_irq(dev, adminq, adminq->irqname); - if (result) + if (result) { + adminq->cq_vector = -1; goto free_queues; + } /* Free previously allocated queues that are no longer usable */ nvme_free_queues(dev, nr_io_queues + 1); diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c index 5bcd575fa96f..e6b658faef63 100644 --- a/drivers/crypto/mv_cesa.c +++ b/drivers/crypto/mv_cesa.c @@ -1034,8 +1034,8 @@ static int mv_cesa_get_sram(struct platform_device *pdev, &sram_size); cp->sram_size = sram_size; - cp->sram_pool = of_get_named_gen_pool(pdev->dev.of_node, - "marvell,crypto-srams", 0); + cp->sram_pool = of_gen_pool_get(pdev->dev.of_node, + "marvell,crypto-srams", 0); if (cp->sram_pool) { cp->sram = gen_pool_dma_alloc(cp->sram_pool, sram_size, &cp->sram_dma); diff --git a/drivers/edac/octeon_edac-l2c.c b/drivers/edac/octeon_edac-l2c.c index 7e98084d3645..afea7fc625cc 100644 --- a/drivers/edac/octeon_edac-l2c.c +++ b/drivers/edac/octeon_edac-l2c.c @@ -151,7 +151,7 @@ static int octeon_l2c_probe(struct platform_device *pdev) l2c->ctl_name = "octeon_l2c_err"; - if (OCTEON_IS_MODEL(OCTEON_FAM_1_PLUS)) { + if (OCTEON_IS_OCTEON1PLUS()) { union cvmx_l2t_err l2t_err; union cvmx_l2d_err l2d_err; diff --git a/drivers/edac/octeon_edac-lmc.c b/drivers/edac/octeon_edac-lmc.c index bb19e0732681..cda6dab5067a 100644 --- a/drivers/edac/octeon_edac-lmc.c +++ b/drivers/edac/octeon_edac-lmc.c @@ -234,7 +234,7 @@ static int octeon_lmc_edac_probe(struct platform_device *pdev) layers[0].size = 1; layers[0].is_virt_csrow = false; - if (OCTEON_IS_MODEL(OCTEON_FAM_1_PLUS)) { + if (OCTEON_IS_OCTEON1PLUS()) { union cvmx_lmcx_mem_cfg0 cfg0; cfg0.u64 = cvmx_read_csr(CVMX_LMCX_MEM_CFG0(0)); diff --git a/drivers/edac/octeon_edac-pc.c b/drivers/edac/octeon_edac-pc.c index 0f83c33a7d1f..2ab6cf24c959 100644 --- a/drivers/edac/octeon_edac-pc.c +++ b/drivers/edac/octeon_edac-pc.c @@ -73,7 +73,7 @@ static int co_cache_error_event(struct notifier_block *this, edac_device_handle_ce(p->ed, cpu, 0, "dcache"); /* Clear the error indication */ - if (OCTEON_IS_MODEL(OCTEON_FAM_2)) + if (OCTEON_IS_OCTEON2()) write_octeon_c0_dcacheerr(1); else write_octeon_c0_dcacheerr(0); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index ca617f40574a..9fa8084a7c8d 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -66,7 +66,6 @@ static int __init parse_efi_cmdline(char *str) early_param("efi", parse_efi_cmdline); struct kobject *efi_kobj; -static struct kobject *efivars_kobj; /* * Let's not leave out systab information that snuck into @@ -218,10 +217,9 @@ static int __init efisubsys_init(void) goto err_remove_group; /* and the standard mountpoint for efivarfs */ - efivars_kobj = kobject_create_and_add("efivars", efi_kobj); - if (!efivars_kobj) { + error = sysfs_create_mount_point(efi_kobj, "efivars"); + if (error) { pr_err("efivars: Subsystem registration failed.\n"); - error = -ENOMEM; goto err_remove_group; } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index b69ed97d447c..b9ba06176eb1 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -4732,7 +4732,7 @@ int drm_mode_connector_update_edid_property(struct drm_connector *connector, return 0; if (edid) - size = EDID_LENGTH + (1 + edid->extensions); + size = EDID_LENGTH * (1 + edid->extensions); ret = drm_property_replace_global_blob(dev, &connector->edid_blob_ptr, diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index b10353b31806..697007afb99c 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -1937,27 +1937,11 @@ static inline void w83627ehf_init_device(struct w83627ehf_data *data, static void w82627ehf_swap_tempreg(struct w83627ehf_data *data, int r1, int r2) { - u16 tmp; - - tmp = data->temp_src[r1]; - data->temp_src[r1] = data->temp_src[r2]; - data->temp_src[r2] = tmp; - - tmp = data->reg_temp[r1]; - data->reg_temp[r1] = data->reg_temp[r2]; - data->reg_temp[r2] = tmp; - - tmp = data->reg_temp_over[r1]; - data->reg_temp_over[r1] = data->reg_temp_over[r2]; - data->reg_temp_over[r2] = tmp; - - tmp = data->reg_temp_hyst[r1]; - data->reg_temp_hyst[r1] = data->reg_temp_hyst[r2]; - data->reg_temp_hyst[r2] = tmp; - - tmp = data->reg_temp_config[r1]; - data->reg_temp_config[r1] = data->reg_temp_config[r2]; - data->reg_temp_config[r2] = tmp; + swap(data->temp_src[r1], data->temp_src[r2]); + swap(data->reg_temp[r1], data->reg_temp[r2]); + swap(data->reg_temp_over[r1], data->reg_temp_over[r2]); + swap(data->reg_temp_hyst[r1], data->reg_temp_hyst[r2]); + swap(data->reg_temp_config[r1], data->reg_temp_config[r2]); } static void diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c index 4068db4d9580..0a8bce726b4b 100644 --- a/drivers/hwmon/w83792d.c +++ b/drivers/hwmon/w83792d.c @@ -289,10 +289,7 @@ struct w83792d_data { u8 temp1[3]; /* current, over, thyst */ u8 temp_add[2][6]; /* Register value */ u8 fan_div[7]; /* Register encoding, shifted right */ - u8 pwm[7]; /* - * We only consider the first 3 set of pwm, - * although 792 chip has 7 set of pwm. - */ + u8 pwm[7]; /* The 7 PWM outputs */ u8 pwmenable[3]; u32 alarms; /* realtime status register encoding,combined */ u8 chassis; /* Chassis status */ @@ -1075,6 +1072,10 @@ static DEVICE_ATTR(intrusion0_alarm, S_IRUGO | S_IWUSR, static SENSOR_DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 0); static SENSOR_DEVICE_ATTR(pwm2, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 1); static SENSOR_DEVICE_ATTR(pwm3, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 2); +static SENSOR_DEVICE_ATTR(pwm4, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 3); +static SENSOR_DEVICE_ATTR(pwm5, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 4); +static SENSOR_DEVICE_ATTR(pwm6, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 5); +static SENSOR_DEVICE_ATTR(pwm7, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 6); static SENSOR_DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO, show_pwmenable, store_pwmenable, 1); static SENSOR_DEVICE_ATTR(pwm2_enable, S_IWUSR | S_IRUGO, @@ -1087,6 +1088,14 @@ static SENSOR_DEVICE_ATTR(pwm2_mode, S_IWUSR | S_IRUGO, show_pwm_mode, store_pwm_mode, 1); static SENSOR_DEVICE_ATTR(pwm3_mode, S_IWUSR | S_IRUGO, show_pwm_mode, store_pwm_mode, 2); +static SENSOR_DEVICE_ATTR(pwm4_mode, S_IWUSR | S_IRUGO, + show_pwm_mode, store_pwm_mode, 3); +static SENSOR_DEVICE_ATTR(pwm5_mode, S_IWUSR | S_IRUGO, + show_pwm_mode, store_pwm_mode, 4); +static SENSOR_DEVICE_ATTR(pwm6_mode, S_IWUSR | S_IRUGO, + show_pwm_mode, store_pwm_mode, 5); +static SENSOR_DEVICE_ATTR(pwm7_mode, S_IWUSR | S_IRUGO, + show_pwm_mode, store_pwm_mode, 6); static SENSOR_DEVICE_ATTR(tolerance1, S_IWUSR | S_IRUGO, show_tolerance, store_tolerance, 1); static SENSOR_DEVICE_ATTR(tolerance2, S_IWUSR | S_IRUGO, @@ -1177,30 +1186,38 @@ static SENSOR_DEVICE_ATTR(fan6_div, S_IWUSR | S_IRUGO, static SENSOR_DEVICE_ATTR(fan7_div, S_IWUSR | S_IRUGO, show_fan_div, store_fan_div, 7); -static struct attribute *w83792d_attributes_fan[4][5] = { +static struct attribute *w83792d_attributes_fan[4][7] = { { &sensor_dev_attr_fan4_input.dev_attr.attr, &sensor_dev_attr_fan4_min.dev_attr.attr, &sensor_dev_attr_fan4_div.dev_attr.attr, &sensor_dev_attr_fan4_alarm.dev_attr.attr, + &sensor_dev_attr_pwm4.dev_attr.attr, + &sensor_dev_attr_pwm4_mode.dev_attr.attr, NULL }, { &sensor_dev_attr_fan5_input.dev_attr.attr, &sensor_dev_attr_fan5_min.dev_attr.attr, &sensor_dev_attr_fan5_div.dev_attr.attr, &sensor_dev_attr_fan5_alarm.dev_attr.attr, + &sensor_dev_attr_pwm5.dev_attr.attr, + &sensor_dev_attr_pwm5_mode.dev_attr.attr, NULL }, { &sensor_dev_attr_fan6_input.dev_attr.attr, &sensor_dev_attr_fan6_min.dev_attr.attr, &sensor_dev_attr_fan6_div.dev_attr.attr, &sensor_dev_attr_fan6_alarm.dev_attr.attr, + &sensor_dev_attr_pwm6.dev_attr.attr, + &sensor_dev_attr_pwm6_mode.dev_attr.attr, NULL }, { &sensor_dev_attr_fan7_input.dev_attr.attr, &sensor_dev_attr_fan7_min.dev_attr.attr, &sensor_dev_attr_fan7_div.dev_attr.attr, &sensor_dev_attr_fan7_alarm.dev_attr.attr, + &sensor_dev_attr_pwm7.dev_attr.attr, + &sensor_dev_attr_pwm7_mode.dev_attr.attr, NULL } }; diff --git a/drivers/hwspinlock/Kconfig b/drivers/hwspinlock/Kconfig index 3612cb5b30b2..73a401662853 100644 --- a/drivers/hwspinlock/Kconfig +++ b/drivers/hwspinlock/Kconfig @@ -18,6 +18,30 @@ config HWSPINLOCK_OMAP If unsure, say N. +config HWSPINLOCK_QCOM + tristate "Qualcomm Hardware Spinlock device" + depends on ARCH_QCOM + select HWSPINLOCK + select MFD_SYSCON + help + Say y here to support the Qualcomm Hardware Mutex functionality, which + provides a synchronisation mechanism for the various processors on + the SoC. + + If unsure, say N. + +config HWSPINLOCK_SIRF + tristate "SIRF Hardware Spinlock device" + depends on ARCH_SIRF + select HWSPINLOCK + help + Say y here to support the SIRF Hardware Spinlock device, which + provides a synchronisation mechanism for the various processors + on the SoC. + + It's safe to say n here if you're not interested in SIRF hardware + spinlock or just want a bare minimum kernel. + config HSEM_U8500 tristate "STE Hardware Semaphore functionality" depends on ARCH_U8500 diff --git a/drivers/hwspinlock/Makefile b/drivers/hwspinlock/Makefile index 93eb64b66486..6b59cb5a4f3a 100644 --- a/drivers/hwspinlock/Makefile +++ b/drivers/hwspinlock/Makefile @@ -4,4 +4,6 @@ obj-$(CONFIG_HWSPINLOCK) += hwspinlock_core.o obj-$(CONFIG_HWSPINLOCK_OMAP) += omap_hwspinlock.o +obj-$(CONFIG_HWSPINLOCK_QCOM) += qcom_hwspinlock.o +obj-$(CONFIG_HWSPINLOCK_SIRF) += sirf_hwspinlock.o obj-$(CONFIG_HSEM_U8500) += u8500_hsem.o diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 461a0d739d75..52f708bcf77f 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -27,6 +27,7 @@ #include <linux/hwspinlock.h> #include <linux/pm_runtime.h> #include <linux/mutex.h> +#include <linux/of.h> #include "hwspinlock_internal.h" @@ -257,6 +258,84 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags) } EXPORT_SYMBOL_GPL(__hwspin_unlock); +/** + * of_hwspin_lock_simple_xlate - translate hwlock_spec to return a lock id + * @bank: the hwspinlock device bank + * @hwlock_spec: hwlock specifier as found in the device tree + * + * This is a simple translation function, suitable for hwspinlock platform + * drivers that only has a lock specifier length of 1. + * + * Returns a relative index of the lock within a specified bank on success, + * or -EINVAL on invalid specifier cell count. + */ +static inline int +of_hwspin_lock_simple_xlate(const struct of_phandle_args *hwlock_spec) +{ + if (WARN_ON(hwlock_spec->args_count != 1)) + return -EINVAL; + + return hwlock_spec->args[0]; +} + +/** + * of_hwspin_lock_get_id() - get lock id for an OF phandle-based specific lock + * @np: device node from which to request the specific hwlock + * @index: index of the hwlock in the list of values + * + * This function provides a means for DT users of the hwspinlock module to + * get the global lock id of a specific hwspinlock using the phandle of the + * hwspinlock device, so that it can be requested using the normal + * hwspin_lock_request_specific() API. + * + * Returns the global lock id number on success, -EPROBE_DEFER if the hwspinlock + * device is not yet registered, -EINVAL on invalid args specifier value or an + * appropriate error as returned from the OF parsing of the DT client node. + */ +int of_hwspin_lock_get_id(struct device_node *np, int index) +{ + struct of_phandle_args args; + struct hwspinlock *hwlock; + struct radix_tree_iter iter; + void **slot; + int id; + int ret; + + ret = of_parse_phandle_with_args(np, "hwlocks", "#hwlock-cells", index, + &args); + if (ret) + return ret; + + /* Find the hwspinlock device: we need its base_id */ + ret = -EPROBE_DEFER; + rcu_read_lock(); + radix_tree_for_each_slot(slot, &hwspinlock_tree, &iter, 0) { + hwlock = radix_tree_deref_slot(slot); + if (unlikely(!hwlock)) + continue; + + if (hwlock->bank->dev->of_node == args.np) { + ret = 0; + break; + } + } + rcu_read_unlock(); + if (ret < 0) + goto out; + + id = of_hwspin_lock_simple_xlate(&args); + if (id < 0 || id >= hwlock->bank->num_locks) { + ret = -EINVAL; + goto out; + } + id += hwlock->bank->base_id; + +out: + of_node_put(args.np); + return ret ? ret : id; +} +EXPORT_SYMBOL_GPL(of_hwspin_lock_get_id); + static int hwspin_lock_register_single(struct hwspinlock *hwlock, int id) { struct hwspinlock *tmp; diff --git a/drivers/hwspinlock/omap_hwspinlock.c b/drivers/hwspinlock/omap_hwspinlock.c index 47a275c6ece1..ad2f8cac8487 100644 --- a/drivers/hwspinlock/omap_hwspinlock.c +++ b/drivers/hwspinlock/omap_hwspinlock.c @@ -1,7 +1,7 @@ /* * OMAP hardware spinlock driver * - * Copyright (C) 2010 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2010-2015 Texas Instruments Incorporated - http://www.ti.com * * Contact: Simon Que <sque@ti.com> * Hari Kanigeri <h-kanigeri2@ti.com> @@ -27,6 +27,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/hwspinlock.h> +#include <linux/of.h> #include <linux/platform_device.h> #include "hwspinlock_internal.h" @@ -80,14 +81,16 @@ static const struct hwspinlock_ops omap_hwspinlock_ops = { static int omap_hwspinlock_probe(struct platform_device *pdev) { - struct hwspinlock_pdata *pdata = pdev->dev.platform_data; + struct device_node *node = pdev->dev.of_node; struct hwspinlock_device *bank; struct hwspinlock *hwlock; struct resource *res; void __iomem *io_base; int num_locks, i, ret; + /* Only a single hwspinlock block device is supported */ + int base_id = 0; - if (!pdata) + if (!node) return -ENODEV; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -141,7 +144,7 @@ static int omap_hwspinlock_probe(struct platform_device *pdev) hwlock->priv = io_base + LOCK_BASE_OFFSET + sizeof(u32) * i; ret = hwspin_lock_register(bank, &pdev->dev, &omap_hwspinlock_ops, - pdata->base_id, num_locks); + base_id, num_locks); if (ret) goto reg_fail; @@ -174,11 +177,18 @@ static int omap_hwspinlock_remove(struct platform_device *pdev) return 0; } +static const struct of_device_id omap_hwspinlock_of_match[] = { + { .compatible = "ti,omap4-hwspinlock", }, + { /* end */ }, +}; +MODULE_DEVICE_TABLE(of, omap_hwspinlock_of_match); + static struct platform_driver omap_hwspinlock_driver = { .probe = omap_hwspinlock_probe, .remove = omap_hwspinlock_remove, .driver = { .name = "omap_hwspinlock", + .of_match_table = of_match_ptr(omap_hwspinlock_of_match), }, }; diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c new file mode 100644 index 000000000000..c752447fbac7 --- /dev/null +++ b/drivers/hwspinlock/qcom_hwspinlock.c @@ -0,0 +1,181 @@ +/* + * Copyright (c) 2013, The Linux Foundation. All rights reserved. + * Copyright (c) 2015, Sony Mobile Communications AB + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/hwspinlock.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> + +#include "hwspinlock_internal.h" + +#define QCOM_MUTEX_APPS_PROC_ID 1 +#define QCOM_MUTEX_NUM_LOCKS 32 + +static int qcom_hwspinlock_trylock(struct hwspinlock *lock) +{ + struct regmap_field *field = lock->priv; + u32 lock_owner; + int ret; + + ret = regmap_field_write(field, QCOM_MUTEX_APPS_PROC_ID); + if (ret) + return ret; + + ret = regmap_field_read(field, &lock_owner); + if (ret) + return ret; + + return lock_owner == QCOM_MUTEX_APPS_PROC_ID; +} + +static void qcom_hwspinlock_unlock(struct hwspinlock *lock) +{ + struct regmap_field *field = lock->priv; + u32 lock_owner; + int ret; + + ret = regmap_field_read(field, &lock_owner); + if (ret) { + pr_err("%s: unable to query spinlock owner\n", __func__); + return; + } + + if (lock_owner != QCOM_MUTEX_APPS_PROC_ID) { + pr_err("%s: spinlock not owned by us (actual owner is %d)\n", + __func__, lock_owner); + } + + ret = regmap_field_write(field, 0); + if (ret) + pr_err("%s: failed to unlock spinlock\n", __func__); +} + +static const struct hwspinlock_ops qcom_hwspinlock_ops = { + .trylock = qcom_hwspinlock_trylock, + .unlock = qcom_hwspinlock_unlock, +}; + +static const struct of_device_id qcom_hwspinlock_of_match[] = { + { .compatible = "qcom,sfpb-mutex" }, + { .compatible = "qcom,tcsr-mutex" }, + { } +}; +MODULE_DEVICE_TABLE(of, qcom_hwspinlock_of_match); + +static int qcom_hwspinlock_probe(struct platform_device *pdev) +{ + struct hwspinlock_device *bank; + struct device_node *syscon; + struct reg_field field; + struct regmap *regmap; + size_t array_size; + u32 stride; + u32 base; + int ret; + int i; + + syscon = of_parse_phandle(pdev->dev.of_node, "syscon", 0); + if (!syscon) { + dev_err(&pdev->dev, "no syscon property\n"); + return -ENODEV; + } + + regmap = syscon_node_to_regmap(syscon); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + ret = of_property_read_u32_index(pdev->dev.of_node, "syscon", 1, &base); + if (ret < 0) { + dev_err(&pdev->dev, "no offset in syscon\n"); + return -EINVAL; + } + + ret = of_property_read_u32_index(pdev->dev.of_node, "syscon", 2, &stride); + if (ret < 0) { + dev_err(&pdev->dev, "no stride syscon\n"); + return -EINVAL; + } + + array_size = QCOM_MUTEX_NUM_LOCKS * sizeof(struct hwspinlock); + bank = devm_kzalloc(&pdev->dev, sizeof(*bank) + array_size, GFP_KERNEL); + if (!bank) + return -ENOMEM; + + platform_set_drvdata(pdev, bank); + + for (i = 0; i < QCOM_MUTEX_NUM_LOCKS; i++) { + field.reg = base + i * stride; + field.lsb = 0; + field.msb = 31; + + bank->lock[i].priv = devm_regmap_field_alloc(&pdev->dev, + regmap, field); + } + + pm_runtime_enable(&pdev->dev); + + ret = hwspin_lock_register(bank, &pdev->dev, &qcom_hwspinlock_ops, + 0, QCOM_MUTEX_NUM_LOCKS); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static int qcom_hwspinlock_remove(struct platform_device *pdev) +{ + struct hwspinlock_device *bank = platform_get_drvdata(pdev); + int ret; + + ret = hwspin_lock_unregister(bank); + if (ret) { + dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret); + return ret; + } + + pm_runtime_disable(&pdev->dev); + + return 0; +} + +static struct platform_driver qcom_hwspinlock_driver = { + .probe = qcom_hwspinlock_probe, + .remove = qcom_hwspinlock_remove, + .driver = { + .name = "qcom_hwspinlock", + .of_match_table = qcom_hwspinlock_of_match, + }, +}; + +static int __init qcom_hwspinlock_init(void) +{ + return platform_driver_register(&qcom_hwspinlock_driver); +} +/* board init code might need to reserve hwspinlocks for predefined purposes */ +postcore_initcall(qcom_hwspinlock_init); + +static void __exit qcom_hwspinlock_exit(void) +{ + platform_driver_unregister(&qcom_hwspinlock_driver); +} +module_exit(qcom_hwspinlock_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Hardware spinlock driver for Qualcomm SoCs"); diff --git a/drivers/hwspinlock/sirf_hwspinlock.c b/drivers/hwspinlock/sirf_hwspinlock.c new file mode 100644 index 000000000000..16018544d431 --- /dev/null +++ b/drivers/hwspinlock/sirf_hwspinlock.c @@ -0,0 +1,136 @@ +/* + * SIRF hardware spinlock driver + * + * Copyright (c) 2015 Cambridge Silicon Radio Limited, a CSR plc group company. + * + * Licensed under GPLv2. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/pm_runtime.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/hwspinlock.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/of_address.h> + +#include "hwspinlock_internal.h" + +struct sirf_hwspinlock { + void __iomem *io_base; + struct hwspinlock_device bank; +}; + +/* Number of Hardware Spinlocks*/ +#define HW_SPINLOCK_NUMBER 30 + +/* Hardware spinlock register offsets */ +#define HW_SPINLOCK_BASE 0x404 +#define HW_SPINLOCK_OFFSET(x) (HW_SPINLOCK_BASE + 0x4 * (x)) + +static int sirf_hwspinlock_trylock(struct hwspinlock *lock) +{ + void __iomem *lock_addr = lock->priv; + + /* attempt to acquire the lock by reading value == 1 from it */ + return !!readl(lock_addr); +} + +static void sirf_hwspinlock_unlock(struct hwspinlock *lock) +{ + void __iomem *lock_addr = lock->priv; + + /* release the lock by writing 0 to it */ + writel(0, lock_addr); +} + +static const struct hwspinlock_ops sirf_hwspinlock_ops = { + .trylock = sirf_hwspinlock_trylock, + .unlock = sirf_hwspinlock_unlock, +}; + +static int sirf_hwspinlock_probe(struct platform_device *pdev) +{ + struct sirf_hwspinlock *hwspin; + struct hwspinlock *hwlock; + int idx, ret; + + if (!pdev->dev.of_node) + return -ENODEV; + + hwspin = devm_kzalloc(&pdev->dev, sizeof(*hwspin) + + sizeof(*hwlock) * HW_SPINLOCK_NUMBER, GFP_KERNEL); + if (!hwspin) + return -ENOMEM; + + /* retrieve io base */ + hwspin->io_base = of_iomap(pdev->dev.of_node, 0); + if (!hwspin->io_base) + return -ENOMEM; + + for (idx = 0; idx < HW_SPINLOCK_NUMBER; idx++) { + hwlock = &hwspin->bank.lock[idx]; + hwlock->priv = hwspin->io_base + HW_SPINLOCK_OFFSET(idx); + } + + platform_set_drvdata(pdev, hwspin); + + pm_runtime_enable(&pdev->dev); + + ret = hwspin_lock_register(&hwspin->bank, &pdev->dev, + &sirf_hwspinlock_ops, 0, + HW_SPINLOCK_NUMBER); + if (ret) + goto reg_failed; + + return 0; + +reg_failed: + pm_runtime_disable(&pdev->dev); + iounmap(hwspin->io_base); + + return ret; +} + +static int sirf_hwspinlock_remove(struct platform_device *pdev) +{ + struct sirf_hwspinlock *hwspin = platform_get_drvdata(pdev); + int ret; + + ret = hwspin_lock_unregister(&hwspin->bank); + if (ret) { + dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret); + return ret; + } + + pm_runtime_disable(&pdev->dev); + + iounmap(hwspin->io_base); + + return 0; +} + +static const struct of_device_id sirf_hwpinlock_ids[] = { + { .compatible = "sirf,hwspinlock", }, + {}, +}; +MODULE_DEVICE_TABLE(of, sirf_hwpinlock_ids); + +static struct platform_driver sirf_hwspinlock_driver = { + .probe = sirf_hwspinlock_probe, + .remove = sirf_hwspinlock_remove, + .driver = { + .name = "atlas7_hwspinlock", + .of_match_table = of_match_ptr(sirf_hwpinlock_ids), + }, +}; + +module_platform_driver(sirf_hwspinlock_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("SIRF Hardware spinlock driver"); +MODULE_AUTHOR("Wei Chen <wei.chen@csr.com>"); diff --git a/drivers/input/input.c b/drivers/input/input.c index f31578423636..78d24990a816 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -677,12 +677,9 @@ static void input_dev_release_keys(struct input_dev *dev) int code; if (is_event_supported(EV_KEY, dev->evbit, EV_MAX)) { - for (code = 0; code <= KEY_MAX; code++) { - if (is_event_supported(code, dev->keybit, KEY_MAX) && - __test_and_clear_bit(code, dev->key)) { - input_pass_event(dev, EV_KEY, code, 0); - } - } + for_each_set_bit(code, dev->key, KEY_CNT) + input_pass_event(dev, EV_KEY, code, 0); + memset(dev->key, 0, sizeof(dev->key)); input_pass_event(dev, EV_SYN, SYN_REPORT, 1); } } @@ -1626,10 +1623,7 @@ static int input_dev_uevent(struct device *device, struct kobj_uevent_env *env) if (!test_bit(EV_##type, dev->evbit)) \ break; \ \ - for (i = 0; i < type##_MAX; i++) { \ - if (!test_bit(i, dev->bits##bit)) \ - continue; \ - \ + for_each_set_bit(i, dev->bits##bit, type##_CNT) { \ active = test_bit(i, dev->bits); \ if (!active && !on) \ continue; \ @@ -1980,22 +1974,12 @@ static unsigned int input_estimate_events_per_packet(struct input_dev *dev) events = mt_slots + 1; /* count SYN_MT_REPORT and SYN_REPORT */ - if (test_bit(EV_ABS, dev->evbit)) { - for (i = 0; i < ABS_CNT; i++) { - if (test_bit(i, dev->absbit)) { - if (input_is_mt_axis(i)) - events += mt_slots; - else - events++; - } - } - } + if (test_bit(EV_ABS, dev->evbit)) + for_each_set_bit(i, dev->absbit, ABS_CNT) + events += input_is_mt_axis(i) ? mt_slots : 1; - if (test_bit(EV_REL, dev->evbit)) { - for (i = 0; i < REL_CNT; i++) - if (test_bit(i, dev->relbit)) - events++; - } + if (test_bit(EV_REL, dev->evbit)) + events += bitmap_weight(dev->relbit, REL_CNT); /* Make room for KEY and MSC events */ events += 7; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 61c761156371..f8850f9cb331 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -344,6 +344,7 @@ struct usb_xpad { int mapping; /* map d-pad to buttons or to axes */ int xtype; /* type of xbox device */ + unsigned long led_no; /* led to lit on xbox360 controllers */ }; /* @@ -488,6 +489,8 @@ static void xpad360_process_packet(struct usb_xpad *xpad, input_sync(dev); } +static void xpad_identify_controller(struct usb_xpad *xpad); + /* * xpad360w_process_packet * @@ -510,6 +513,11 @@ static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned cha if (data[1] & 0x80) { xpad->pad_present = 1; usb_submit_urb(xpad->bulk_out, GFP_ATOMIC); + /* + * Light up the segment corresponding to + * controller number. + */ + xpad_identify_controller(xpad); } else xpad->pad_present = 0; } @@ -881,17 +889,63 @@ struct xpad_led { struct usb_xpad *xpad; }; +/** + * @param command + * 0: off + * 1: all blink, then previous setting + * 2: 1/top-left blink, then on + * 3: 2/top-right blink, then on + * 4: 3/bottom-left blink, then on + * 5: 4/bottom-right blink, then on + * 6: 1/top-left on + * 7: 2/top-right on + * 8: 3/bottom-left on + * 9: 4/bottom-right on + * 10: rotate + * 11: blink, based on previous setting + * 12: slow blink, based on previous setting + * 13: rotate with two lights + * 14: persistent slow all blink + * 15: blink once, then previous setting + */ static void xpad_send_led_command(struct usb_xpad *xpad, int command) { - if (command >= 0 && command < 14) { - mutex_lock(&xpad->odata_mutex); + command %= 16; + + mutex_lock(&xpad->odata_mutex); + + switch (xpad->xtype) { + case XTYPE_XBOX360: xpad->odata[0] = 0x01; xpad->odata[1] = 0x03; xpad->odata[2] = command; xpad->irq_out->transfer_buffer_length = 3; - usb_submit_urb(xpad->irq_out, GFP_KERNEL); - mutex_unlock(&xpad->odata_mutex); + break; + case XTYPE_XBOX360W: + xpad->odata[0] = 0x00; + xpad->odata[1] = 0x00; + xpad->odata[2] = 0x08; + xpad->odata[3] = 0x40 + command; + xpad->odata[4] = 0x00; + xpad->odata[5] = 0x00; + xpad->odata[6] = 0x00; + xpad->odata[7] = 0x00; + xpad->odata[8] = 0x00; + xpad->odata[9] = 0x00; + xpad->odata[10] = 0x00; + xpad->odata[11] = 0x00; + xpad->irq_out->transfer_buffer_length = 12; + break; } + + usb_submit_urb(xpad->irq_out, GFP_KERNEL); + mutex_unlock(&xpad->odata_mutex); +} + +static void xpad_identify_controller(struct usb_xpad *xpad) +{ + /* Light up the segment corresponding to controller number */ + xpad_send_led_command(xpad, (xpad->led_no % 4) + 2); } static void xpad_led_set(struct led_classdev *led_cdev, @@ -905,22 +959,21 @@ static void xpad_led_set(struct led_classdev *led_cdev, static int xpad_led_probe(struct usb_xpad *xpad) { - static atomic_t led_seq = ATOMIC_INIT(-1); - unsigned long led_no; + static atomic_t led_seq = ATOMIC_INIT(-1); struct xpad_led *led; struct led_classdev *led_cdev; int error; - if (xpad->xtype != XTYPE_XBOX360) + if (xpad->xtype != XTYPE_XBOX360 && xpad->xtype != XTYPE_XBOX360W) return 0; xpad->led = led = kzalloc(sizeof(struct xpad_led), GFP_KERNEL); if (!led) return -ENOMEM; - led_no = atomic_inc_return(&led_seq); + xpad->led_no = atomic_inc_return(&led_seq); - snprintf(led->name, sizeof(led->name), "xpad%lu", led_no); + snprintf(led->name, sizeof(led->name), "xpad%lu", xpad->led_no); led->xpad = xpad; led_cdev = &led->led_cdev; @@ -934,10 +987,8 @@ static int xpad_led_probe(struct usb_xpad *xpad) return error; } - /* - * Light up the segment corresponding to controller number - */ - xpad_send_led_command(xpad, (led_no % 4) + 2); + /* Light up the segment corresponding to controller number */ + xpad_identify_controller(xpad); return 0; } @@ -954,6 +1005,7 @@ static void xpad_led_disconnect(struct usb_xpad *xpad) #else static int xpad_led_probe(struct usb_xpad *xpad) { return 0; } static void xpad_led_disconnect(struct usb_xpad *xpad) { } +static void xpad_identify_controller(struct usb_xpad *xpad) { } #endif diff --git a/drivers/input/keyboard/imx_keypad.c b/drivers/input/keyboard/imx_keypad.c index 2e855e6f3565..d2ea863d6a45 100644 --- a/drivers/input/keyboard/imx_keypad.c +++ b/drivers/input/keyboard/imx_keypad.c @@ -506,7 +506,9 @@ static int imx_keypad_probe(struct platform_device *pdev) input_set_drvdata(input_dev, keypad); /* Ensure that the keypad will stay dormant until opened */ - clk_prepare_enable(keypad->clk); + error = clk_prepare_enable(keypad->clk); + if (error) + return error; imx_keypad_inhibit(keypad); clk_disable_unprepare(keypad->clk); diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c index f1c844739cd7..10e140af5aac 100644 --- a/drivers/input/misc/axp20x-pek.c +++ b/drivers/input/misc/axp20x-pek.c @@ -167,9 +167,13 @@ static irqreturn_t axp20x_pek_irq(int irq, void *pwr) struct input_dev *idev = pwr; struct axp20x_pek *axp20x_pek = input_get_drvdata(idev); - if (irq == axp20x_pek->irq_dbr) + /* + * The power-button is connected to ground so a falling edge (dbf) + * means it is pressed. + */ + if (irq == axp20x_pek->irq_dbf) input_report_key(idev, KEY_POWER, true); - else if (irq == axp20x_pek->irq_dbf) + else if (irq == axp20x_pek->irq_dbr) input_report_key(idev, KEY_POWER, false); input_sync(idev); diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig index 77833d7a004b..200841b77edb 100644 --- a/drivers/input/serio/Kconfig +++ b/drivers/input/serio/Kconfig @@ -244,6 +244,7 @@ config SERIO_PS2MULT config SERIO_ARC_PS2 tristate "ARC PS/2 support" + depends on HAS_IOMEM help Say Y here if you have an ARC FPGA platform with a PS/2 controller in it. diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index d20fe1dff403..a854c6e5f09e 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -658,6 +658,18 @@ config TOUCHSCREEN_PIXCIR To compile this driver as a module, choose M here: the module will be called pixcir_i2c_ts. +config TOUCHSCREEN_WDT87XX_I2C + tristate "Weida HiTech I2C touchscreen" + depends on I2C + help + Say Y here if you have a Weida WDT87XX I2C touchscreen + connected to your system. + + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called wdt87xx_i2c. + config TOUCHSCREEN_WM831X tristate "Support for WM831x touchscreen controllers" depends on MFD_WM831X diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index 44deea743d02..fa3d33bac7fc 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -72,6 +72,7 @@ obj-$(CONFIG_TOUCHSCREEN_TSC2007) += tsc2007.o obj-$(CONFIG_TOUCHSCREEN_UCB1400) += ucb1400_ts.o obj-$(CONFIG_TOUCHSCREEN_WACOM_W8001) += wacom_w8001.o obj-$(CONFIG_TOUCHSCREEN_WACOM_I2C) += wacom_i2c.o +obj-$(CONFIG_TOUCHSCREEN_WDT87XX_I2C) += wdt87xx_i2c.o obj-$(CONFIG_TOUCHSCREEN_WM831X) += wm831x-ts.o obj-$(CONFIG_TOUCHSCREEN_WM97XX) += wm97xx-ts.o wm97xx-ts-$(CONFIG_TOUCHSCREEN_WM9705) += wm9705.o diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index e6aef3e48bd9..394b1de9a2a3 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -1035,20 +1035,15 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client, input->id.bustype = BUS_I2C; input->dev.parent = &client->dev; - __set_bit(EV_KEY, input->evbit); - __set_bit(EV_ABS, input->evbit); - __set_bit(BTN_TOUCH, input->keybit); - input_set_abs_params(input, ABS_X, 0, tsdata->num_x * 64 - 1, 0, 0); - input_set_abs_params(input, ABS_Y, 0, tsdata->num_y * 64 - 1, 0, 0); input_set_abs_params(input, ABS_MT_POSITION_X, 0, tsdata->num_x * 64 - 1, 0, 0); input_set_abs_params(input, ABS_MT_POSITION_Y, 0, tsdata->num_y * 64 - 1, 0, 0); if (!pdata) - touchscreen_parse_of_params(input); + touchscreen_parse_of_params(input, true); - error = input_mt_init_slots(input, MAX_SUPPORT_POINTS, 0); + error = input_mt_init_slots(input, MAX_SUPPORT_POINTS, INPUT_MT_DIRECT); if (error) { dev_err(&client->dev, "Unable to init MT slots.\n"); return error; diff --git a/drivers/input/touchscreen/of_touchscreen.c b/drivers/input/touchscreen/of_touchscreen.c index b82b5207c78b..806cd0ad160f 100644 --- a/drivers/input/touchscreen/of_touchscreen.c +++ b/drivers/input/touchscreen/of_touchscreen.c @@ -14,14 +14,22 @@ #include <linux/input/mt.h> #include <linux/input/touchscreen.h> -static u32 of_get_optional_u32(struct device_node *np, - const char *property) +static bool touchscreen_get_prop_u32(struct device_node *np, + const char *property, + unsigned int default_value, + unsigned int *value) { - u32 val = 0; + u32 val; + int error; - of_property_read_u32(np, property, &val); + error = of_property_read_u32(np, property, &val); + if (error) { + *value = default_value; + return false; + } - return val; + *value = val; + return true; } static void touchscreen_set_params(struct input_dev *dev, @@ -54,34 +62,45 @@ static void touchscreen_set_params(struct input_dev *dev, * input device accordingly. The function keeps previously setuped default * values if no value is specified via DT. */ -void touchscreen_parse_of_params(struct input_dev *dev) +void touchscreen_parse_of_params(struct input_dev *dev, bool multitouch) { struct device_node *np = dev->dev.parent->of_node; - u32 maximum, fuzz; + unsigned int axis; + unsigned int maximum, fuzz; + bool data_present; input_alloc_absinfo(dev); if (!dev->absinfo) return; - maximum = of_get_optional_u32(np, "touchscreen-size-x"); - fuzz = of_get_optional_u32(np, "touchscreen-fuzz-x"); - if (maximum || fuzz) { - touchscreen_set_params(dev, ABS_X, maximum, fuzz); - touchscreen_set_params(dev, ABS_MT_POSITION_X, maximum, fuzz); - } + axis = multitouch ? ABS_MT_POSITION_X : ABS_X; + data_present = touchscreen_get_prop_u32(np, "touchscreen-size-x", + input_abs_get_max(dev, axis), + &maximum) | + touchscreen_get_prop_u32(np, "touchscreen-fuzz-x", + input_abs_get_fuzz(dev, axis), + &fuzz); + if (data_present) + touchscreen_set_params(dev, axis, maximum, fuzz); - maximum = of_get_optional_u32(np, "touchscreen-size-y"); - fuzz = of_get_optional_u32(np, "touchscreen-fuzz-y"); - if (maximum || fuzz) { - touchscreen_set_params(dev, ABS_Y, maximum, fuzz); - touchscreen_set_params(dev, ABS_MT_POSITION_Y, maximum, fuzz); - } + axis = multitouch ? ABS_MT_POSITION_Y : ABS_Y; + data_present = touchscreen_get_prop_u32(np, "touchscreen-size-y", + input_abs_get_max(dev, axis), + &maximum) | + touchscreen_get_prop_u32(np, "touchscreen-fuzz-y", + input_abs_get_fuzz(dev, axis), + &fuzz); + if (data_present) + touchscreen_set_params(dev, axis, maximum, fuzz); - maximum = of_get_optional_u32(np, "touchscreen-max-pressure"); - fuzz = of_get_optional_u32(np, "touchscreen-fuzz-pressure"); - if (maximum || fuzz) { - touchscreen_set_params(dev, ABS_PRESSURE, maximum, fuzz); - touchscreen_set_params(dev, ABS_MT_PRESSURE, maximum, fuzz); - } + axis = multitouch ? ABS_MT_PRESSURE : ABS_PRESSURE; + data_present = touchscreen_get_prop_u32(np, "touchscreen-max-pressure", + input_abs_get_max(dev, axis), + &maximum) | + touchscreen_get_prop_u32(np, "touchscreen-fuzz-pressure", + input_abs_get_fuzz(dev, axis), + &fuzz); + if (data_present) + touchscreen_set_params(dev, axis, maximum, fuzz); } EXPORT_SYMBOL(touchscreen_parse_of_params); diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c index 72657c579430..d8c025b0f88c 100644 --- a/drivers/input/touchscreen/tsc2005.c +++ b/drivers/input/touchscreen/tsc2005.c @@ -709,7 +709,7 @@ static int tsc2005_probe(struct spi_device *spi) input_set_abs_params(input_dev, ABS_PRESSURE, 0, max_p, fudge_p, 0); if (np) - touchscreen_parse_of_params(input_dev); + touchscreen_parse_of_params(input_dev, false); input_dev->open = tsc2005_open; input_dev->close = tsc2005_close; diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c new file mode 100644 index 000000000000..fb92ae1c5fae --- /dev/null +++ b/drivers/input/touchscreen/wdt87xx_i2c.c @@ -0,0 +1,1149 @@ +/* + * Weida HiTech WDT87xx TouchScreen I2C driver + * + * Copyright (c) 2015 Weida Hi-Tech Co., Ltd. + * HN Chen <hn.chen@weidahitech.com> + * + * This software is licensed under the terms of the GNU General Public + * License, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + */ + +#include <linux/i2c.h> +#include <linux/input.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/firmware.h> +#include <linux/input/mt.h> +#include <linux/acpi.h> +#include <asm/unaligned.h> + +#define WDT87XX_NAME "wdt87xx_i2c" +#define WDT87XX_DRV_VER "0.9.6" +#define WDT87XX_FW_NAME "wdt87xx_fw.bin" +#define WDT87XX_CFG_NAME "wdt87xx_cfg.bin" + +#define MODE_ACTIVE 0x01 +#define MODE_READY 0x02 +#define MODE_IDLE 0x03 +#define MODE_SLEEP 0x04 +#define MODE_STOP 0xFF + +#define WDT_MAX_FINGER 10 +#define WDT_RAW_BUF_COUNT 54 +#define WDT_V1_RAW_BUF_COUNT 74 +#define WDT_FIRMWARE_ID 0xa9e368f5 + +#define PG_SIZE 0x1000 +#define MAX_RETRIES 3 + +#define MAX_UNIT_AXIS 0x7FFF + +#define PKT_READ_SIZE 72 +#define PKT_WRITE_SIZE 80 + +/* the finger definition of the report event */ +#define FINGER_EV_OFFSET_ID 0 +#define FINGER_EV_OFFSET_X 1 +#define FINGER_EV_OFFSET_Y 3 +#define FINGER_EV_SIZE 5 + +#define FINGER_EV_V1_OFFSET_ID 0 +#define FINGER_EV_V1_OFFSET_W 1 +#define FINGER_EV_V1_OFFSET_P 2 +#define FINGER_EV_V1_OFFSET_X 3 +#define FINGER_EV_V1_OFFSET_Y 5 +#define FINGER_EV_V1_SIZE 7 + +/* The definition of a report packet */ +#define TOUCH_PK_OFFSET_REPORT_ID 0 +#define TOUCH_PK_OFFSET_EVENT 1 +#define TOUCH_PK_OFFSET_SCAN_TIME 51 +#define TOUCH_PK_OFFSET_FNGR_NUM 53 + +#define TOUCH_PK_V1_OFFSET_REPORT_ID 0 +#define TOUCH_PK_V1_OFFSET_EVENT 1 +#define TOUCH_PK_V1_OFFSET_SCAN_TIME 71 +#define TOUCH_PK_V1_OFFSET_FNGR_NUM 73 + +/* The definition of the controller parameters */ +#define CTL_PARAM_OFFSET_FW_ID 0 +#define CTL_PARAM_OFFSET_PLAT_ID 2 +#define CTL_PARAM_OFFSET_XMLS_ID1 4 +#define CTL_PARAM_OFFSET_XMLS_ID2 6 +#define CTL_PARAM_OFFSET_PHY_CH_X 8 +#define CTL_PARAM_OFFSET_PHY_CH_Y 10 +#define CTL_PARAM_OFFSET_PHY_X0 12 +#define CTL_PARAM_OFFSET_PHY_X1 14 +#define CTL_PARAM_OFFSET_PHY_Y0 16 +#define CTL_PARAM_OFFSET_PHY_Y1 18 +#define CTL_PARAM_OFFSET_PHY_W 22 +#define CTL_PARAM_OFFSET_PHY_H 24 +#define CTL_PARAM_OFFSET_FACTOR 32 + +/* Communication commands */ +#define PACKET_SIZE 56 +#define VND_REQ_READ 0x06 +#define VND_READ_DATA 0x07 +#define VND_REQ_WRITE 0x08 + +#define VND_CMD_START 0x00 +#define VND_CMD_STOP 0x01 +#define VND_CMD_RESET 0x09 + +#define VND_CMD_ERASE 0x1A + +#define VND_GET_CHECKSUM 0x66 + +#define VND_SET_DATA 0x83 +#define VND_SET_COMMAND_DATA 0x84 +#define VND_SET_CHECKSUM_CALC 0x86 +#define VND_SET_CHECKSUM_LENGTH 0x87 + +#define VND_CMD_SFLCK 0xFC +#define VND_CMD_SFUNL 0xFD + +#define CMD_SFLCK_KEY 0xC39B +#define CMD_SFUNL_KEY 0x95DA + +#define STRIDX_PLATFORM_ID 0x80 +#define STRIDX_PARAMETERS 0x81 + +#define CMD_BUF_SIZE 8 +#define PKT_BUF_SIZE 64 + +/* The definition of the command packet */ +#define CMD_REPORT_ID_OFFSET 0x0 +#define CMD_TYPE_OFFSET 0x1 +#define CMD_INDEX_OFFSET 0x2 +#define CMD_KEY_OFFSET 0x3 +#define CMD_LENGTH_OFFSET 0x4 +#define CMD_DATA_OFFSET 0x8 + +/* The definition of firmware chunk tags */ +#define FOURCC_ID_RIFF 0x46464952 +#define FOURCC_ID_WHIF 0x46494857 +#define FOURCC_ID_FRMT 0x544D5246 +#define FOURCC_ID_FRWR 0x52575246 +#define FOURCC_ID_CNFG 0x47464E43 + +#define CHUNK_ID_FRMT FOURCC_ID_FRMT +#define CHUNK_ID_FRWR FOURCC_ID_FRWR +#define CHUNK_ID_CNFG FOURCC_ID_CNFG + +#define FW_FOURCC1_OFFSET 0 +#define FW_SIZE_OFFSET 4 +#define FW_FOURCC2_OFFSET 8 +#define FW_PAYLOAD_OFFSET 40 + +#define FW_CHUNK_ID_OFFSET 0 +#define FW_CHUNK_SIZE_OFFSET 4 +#define FW_CHUNK_TGT_START_OFFSET 8 +#define FW_CHUNK_PAYLOAD_LEN_OFFSET 12 +#define FW_CHUNK_SRC_START_OFFSET 16 +#define FW_CHUNK_VERSION_OFFSET 20 +#define FW_CHUNK_ATTR_OFFSET 24 +#define FW_CHUNK_PAYLOAD_OFFSET 32 + +/* Controller requires minimum 300us between commands */ +#define WDT_COMMAND_DELAY_MS 2 +#define WDT_FLASH_WRITE_DELAY_MS 4 + +struct wdt87xx_sys_param { + u16 fw_id; + u16 plat_id; + u16 xmls_id1; + u16 xmls_id2; + u16 phy_ch_x; + u16 phy_ch_y; + u16 phy_w; + u16 phy_h; + u16 scaling_factor; + u32 max_x; + u32 max_y; +}; + +struct wdt87xx_data { + struct i2c_client *client; + struct input_dev *input; + /* Mutex for fw update to prevent concurrent access */ + struct mutex fw_mutex; + struct wdt87xx_sys_param param; + u8 phys[32]; +}; + +static int wdt87xx_i2c_xfer(struct i2c_client *client, + void *txdata, size_t txlen, + void *rxdata, size_t rxlen) +{ + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0, + .len = txlen, + .buf = txdata, + }, + { + .addr = client->addr, + .flags = I2C_M_RD, + .len = rxlen, + .buf = rxdata, + }, + }; + int error; + int ret; + + ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (ret != ARRAY_SIZE(msgs)) { + error = ret < 0 ? ret : -EIO; + dev_err(&client->dev, "%s: i2c transfer failed: %d\n", + __func__, error); + return error; + } + + return 0; +} + +static int wdt87xx_get_string(struct i2c_client *client, u8 str_idx, + u8 *buf, size_t len) +{ + u8 tx_buf[] = { 0x22, 0x00, 0x13, 0x0E, str_idx, 0x23, 0x00 }; + u8 rx_buf[PKT_WRITE_SIZE]; + size_t rx_len = len + 2; + int error; + + if (rx_len > sizeof(rx_buf)) + return -EINVAL; + + error = wdt87xx_i2c_xfer(client, tx_buf, sizeof(tx_buf), + rx_buf, rx_len); + if (error) { + dev_err(&client->dev, "get string failed: %d\n", error); + return error; + } + + if (rx_buf[1] != 0x03) { + dev_err(&client->dev, "unexpected response to get string: %d\n", + rx_buf[1]); + return -EINVAL; + } + + rx_len = min_t(size_t, len, rx_buf[0]); + memcpy(buf, &rx_buf[2], rx_len); + + mdelay(WDT_COMMAND_DELAY_MS); + + return 0; +} + +static int wdt87xx_get_feature(struct i2c_client *client, + u8 *buf, size_t buf_size) +{ + u8 tx_buf[8]; + u8 rx_buf[PKT_WRITE_SIZE]; + size_t tx_len = 0; + size_t rx_len = buf_size + 2; + int error; + + if (rx_len > sizeof(rx_buf)) + return -EINVAL; + + /* Get feature command packet */ + tx_buf[tx_len++] = 0x22; + tx_buf[tx_len++] = 0x00; + if (buf[CMD_REPORT_ID_OFFSET] > 0xF) { + tx_buf[tx_len++] = 0x30; + tx_buf[tx_len++] = 0x02; + tx_buf[tx_len++] = buf[CMD_REPORT_ID_OFFSET]; + } else { + tx_buf[tx_len++] = 0x30 | buf[CMD_REPORT_ID_OFFSET]; + tx_buf[tx_len++] = 0x02; + } + tx_buf[tx_len++] = 0x23; + tx_buf[tx_len++] = 0x00; + + error = wdt87xx_i2c_xfer(client, tx_buf, tx_len, rx_buf, rx_len); + if (error) { + dev_err(&client->dev, "get feature failed: %d\n", error); + return error; + } + + rx_len = min_t(size_t, buf_size, get_unaligned_le16(rx_buf)); + memcpy(buf, &rx_buf[2], rx_len); + + mdelay(WDT_COMMAND_DELAY_MS); + + return 0; +} + +static int wdt87xx_set_feature(struct i2c_client *client, + const u8 *buf, size_t buf_size) +{ + u8 tx_buf[PKT_WRITE_SIZE]; + int tx_len = 0; + int error; + + /* Set feature command packet */ + tx_buf[tx_len++] = 0x22; + tx_buf[tx_len++] = 0x00; + if (buf[CMD_REPORT_ID_OFFSET] > 0xF) { + tx_buf[tx_len++] = 0x30; + tx_buf[tx_len++] = 0x03; + tx_buf[tx_len++] = buf[CMD_REPORT_ID_OFFSET]; + } else { + tx_buf[tx_len++] = 0x30 | buf[CMD_REPORT_ID_OFFSET]; + tx_buf[tx_len++] = 0x03; + } + tx_buf[tx_len++] = 0x23; + tx_buf[tx_len++] = 0x00; + tx_buf[tx_len++] = (buf_size & 0xFF); + tx_buf[tx_len++] = ((buf_size & 0xFF00) >> 8); + + if (tx_len + buf_size > sizeof(tx_buf)) + return -EINVAL; + + memcpy(&tx_buf[tx_len], buf, buf_size); + tx_len += buf_size; + + error = i2c_master_send(client, tx_buf, tx_len); + if (error < 0) { + dev_err(&client->dev, "set feature failed: %d\n", error); + return error; + } + + mdelay(WDT_COMMAND_DELAY_MS); + + return 0; +} + +static int wdt87xx_send_command(struct i2c_client *client, int cmd, int value) +{ + u8 cmd_buf[CMD_BUF_SIZE]; + + /* Set the command packet */ + cmd_buf[CMD_REPORT_ID_OFFSET] = VND_REQ_WRITE; + cmd_buf[CMD_TYPE_OFFSET] = VND_SET_COMMAND_DATA; + put_unaligned_le16((u16)cmd, &cmd_buf[CMD_INDEX_OFFSET]); + + switch (cmd) { + case VND_CMD_START: + case VND_CMD_STOP: + case VND_CMD_RESET: + /* Mode selector */ + put_unaligned_le32((value & 0xFF), &cmd_buf[CMD_LENGTH_OFFSET]); + break; + + case VND_CMD_SFLCK: + put_unaligned_le16(CMD_SFLCK_KEY, &cmd_buf[CMD_KEY_OFFSET]); + break; + + case VND_CMD_SFUNL: + put_unaligned_le16(CMD_SFUNL_KEY, &cmd_buf[CMD_KEY_OFFSET]); + break; + + case VND_CMD_ERASE: + case VND_SET_CHECKSUM_CALC: + case VND_SET_CHECKSUM_LENGTH: + put_unaligned_le32(value, &cmd_buf[CMD_KEY_OFFSET]); + break; + + default: + cmd_buf[CMD_REPORT_ID_OFFSET] = 0; + dev_err(&client->dev, "Invalid command: %d\n", cmd); + return -EINVAL; + } + + return wdt87xx_set_feature(client, cmd_buf, sizeof(cmd_buf)); +} + +static int wdt87xx_sw_reset(struct i2c_client *client) +{ + int error; + + dev_dbg(&client->dev, "resetting device now\n"); + + error = wdt87xx_send_command(client, VND_CMD_RESET, 0); + if (error) { + dev_err(&client->dev, "reset failed\n"); + return error; + } + + /* Wait the device to be ready */ + msleep(200); + + return 0; +} + +static const void *wdt87xx_get_fw_chunk(const struct firmware *fw, u32 id) +{ + size_t pos = FW_PAYLOAD_OFFSET; + u32 chunk_id, chunk_size; + + while (pos < fw->size) { + chunk_id = get_unaligned_le32(fw->data + + pos + FW_CHUNK_ID_OFFSET); + if (chunk_id == id) + return fw->data + pos; + + chunk_size = get_unaligned_le32(fw->data + + pos + FW_CHUNK_SIZE_OFFSET); + pos += chunk_size + 2 * sizeof(u32); /* chunk ID + size */ + } + + return NULL; +} + +static int wdt87xx_get_sysparam(struct i2c_client *client, + struct wdt87xx_sys_param *param) +{ + u8 buf[PKT_READ_SIZE]; + int error; + + error = wdt87xx_get_string(client, STRIDX_PARAMETERS, buf, 34); + if (error) { + dev_err(&client->dev, "failed to get parameters\n"); + return error; + } + + param->xmls_id1 = get_unaligned_le16(buf + CTL_PARAM_OFFSET_XMLS_ID1); + param->xmls_id2 = get_unaligned_le16(buf + CTL_PARAM_OFFSET_XMLS_ID2); + param->phy_ch_x = get_unaligned_le16(buf + CTL_PARAM_OFFSET_PHY_CH_X); + param->phy_ch_y = get_unaligned_le16(buf + CTL_PARAM_OFFSET_PHY_CH_Y); + param->phy_w = get_unaligned_le16(buf + CTL_PARAM_OFFSET_PHY_W) / 10; + param->phy_h = get_unaligned_le16(buf + CTL_PARAM_OFFSET_PHY_H) / 10; + + /* Get the scaling factor of pixel to logical coordinate */ + param->scaling_factor = + get_unaligned_le16(buf + CTL_PARAM_OFFSET_FACTOR); + + param->max_x = MAX_UNIT_AXIS; + param->max_y = DIV_ROUND_CLOSEST(MAX_UNIT_AXIS * param->phy_h, + param->phy_w); + + error = wdt87xx_get_string(client, STRIDX_PLATFORM_ID, buf, 8); + if (error) { + dev_err(&client->dev, "failed to get platform id\n"); + return error; + } + + param->plat_id = buf[1]; + + buf[0] = 0xf2; + error = wdt87xx_get_feature(client, buf, 16); + if (error) { + dev_err(&client->dev, "failed to get firmware id\n"); + return error; + } + + if (buf[0] != 0xf2) { + dev_err(&client->dev, "wrong id of fw response: 0x%x\n", + buf[0]); + return -EINVAL; + } + + param->fw_id = get_unaligned_le16(&buf[1]); + + dev_info(&client->dev, + "fw_id: 0x%x, plat_id: 0x%x, xml_id1: %04x, xml_id2: %04x\n", + param->fw_id, param->plat_id, + param->xmls_id1, param->xmls_id2); + + return 0; +} + +static int wdt87xx_validate_firmware(struct wdt87xx_data *wdt, + const struct firmware *fw) +{ + const void *fw_chunk; + u32 data1, data2; + u32 size; + u8 fw_chip_id; + u8 chip_id; + + data1 = get_unaligned_le32(fw->data + FW_FOURCC1_OFFSET); + data2 = get_unaligned_le32(fw->data + FW_FOURCC2_OFFSET); + if (data1 != FOURCC_ID_RIFF || data2 != FOURCC_ID_WHIF) { + dev_err(&wdt->client->dev, "check fw tag failed\n"); + return -EINVAL; + } + + size = get_unaligned_le32(fw->data + FW_SIZE_OFFSET); + if (size != fw->size) { + dev_err(&wdt->client->dev, + "fw size mismatch: expected %d, actual %zu\n", + size, fw->size); + return -EINVAL; + } + + /* + * Get the chip_id from the firmware. Make sure that it is the + * right controller to do the firmware and config update. + */ + fw_chunk = wdt87xx_get_fw_chunk(fw, CHUNK_ID_FRWR); + if (!fw_chunk) { + dev_err(&wdt->client->dev, + "unable to locate firmware chunk\n"); + return -EINVAL; + } + + fw_chip_id = (get_unaligned_le32(fw_chunk + + FW_CHUNK_VERSION_OFFSET) >> 12) & 0xF; + chip_id = (wdt->param.fw_id >> 12) & 0xF; + + if (fw_chip_id != chip_id) { + dev_err(&wdt->client->dev, + "fw version mismatch: fw %d vs. chip %d\n", + fw_chip_id, chip_id); + return -ENODEV; + } + + return 0; +} + +static int wdt87xx_validate_fw_chunk(const void *data, int id) +{ + if (id == CHUNK_ID_FRWR) { + u32 fw_id; + + fw_id = get_unaligned_le32(data + FW_CHUNK_PAYLOAD_OFFSET); + if (fw_id != WDT_FIRMWARE_ID) + return -EINVAL; + } + + return 0; +} + +static int wdt87xx_write_data(struct i2c_client *client, const char *data, + u32 address, int length) +{ + u16 packet_size; + int count = 0; + int error; + u8 pkt_buf[PKT_BUF_SIZE]; + + /* Address and length should be 4 bytes aligned */ + if ((address & 0x3) != 0 || (length & 0x3) != 0) { + dev_err(&client->dev, + "addr & len must be 4 bytes aligned %x, %x\n", + address, length); + return -EINVAL; + } + + while (length) { + packet_size = min(length, PACKET_SIZE); + + pkt_buf[CMD_REPORT_ID_OFFSET] = VND_REQ_WRITE; + pkt_buf[CMD_TYPE_OFFSET] = VND_SET_DATA; + put_unaligned_le16(packet_size, &pkt_buf[CMD_INDEX_OFFSET]); + put_unaligned_le32(address, &pkt_buf[CMD_LENGTH_OFFSET]); + memcpy(&pkt_buf[CMD_DATA_OFFSET], data, packet_size); + + error = wdt87xx_set_feature(client, pkt_buf, sizeof(pkt_buf)); + if (error) + return error; + + length -= packet_size; + data += packet_size; + address += packet_size; + + /* Wait for the controller to finish the write */ + mdelay(WDT_FLASH_WRITE_DELAY_MS); + + if ((++count % 32) == 0) { + /* Delay for fw to clear watch dog */ + msleep(20); + } + } + + return 0; +} + +static u16 misr(u16 cur_value, u8 new_value) +{ + u32 a, b; + u32 bit0; + u32 y; + + a = cur_value; + b = new_value; + bit0 = a ^ (b & 1); + bit0 ^= a >> 1; + bit0 ^= a >> 2; + bit0 ^= a >> 4; + bit0 ^= a >> 5; + bit0 ^= a >> 7; + bit0 ^= a >> 11; + bit0 ^= a >> 15; + y = (a << 1) ^ b; + y = (y & ~1) | (bit0 & 1); + + return (u16)y; +} + +static u16 wdt87xx_calculate_checksum(const u8 *data, size_t length) +{ + u16 checksum = 0; + size_t i; + + for (i = 0; i < length; i++) + checksum = misr(checksum, data[i]); + + return checksum; +} + +static int wdt87xx_get_checksum(struct i2c_client *client, u16 *checksum, + u32 address, int length) +{ + int error; + int time_delay; + u8 pkt_buf[PKT_BUF_SIZE]; + u8 cmd_buf[CMD_BUF_SIZE]; + + error = wdt87xx_send_command(client, VND_SET_CHECKSUM_LENGTH, length); + if (error) { + dev_err(&client->dev, "failed to set checksum length\n"); + return error; + } + + error = wdt87xx_send_command(client, VND_SET_CHECKSUM_CALC, address); + if (error) { + dev_err(&client->dev, "failed to set checksum address\n"); + return error; + } + + /* Wait the operation to complete */ + time_delay = DIV_ROUND_UP(length, 1024); + msleep(time_delay * 30); + + memset(cmd_buf, 0, sizeof(cmd_buf)); + cmd_buf[CMD_REPORT_ID_OFFSET] = VND_REQ_READ; + cmd_buf[CMD_TYPE_OFFSET] = VND_GET_CHECKSUM; + error = wdt87xx_set_feature(client, cmd_buf, sizeof(cmd_buf)); + if (error) { + dev_err(&client->dev, "failed to request checksum\n"); + return error; + } + + memset(pkt_buf, 0, sizeof(pkt_buf)); + pkt_buf[CMD_REPORT_ID_OFFSET] = VND_READ_DATA; + error = wdt87xx_get_feature(client, pkt_buf, sizeof(pkt_buf)); + if (error) { + dev_err(&client->dev, "failed to read checksum\n"); + return error; + } + + *checksum = get_unaligned_le16(&pkt_buf[CMD_DATA_OFFSET]); + return 0; +} + +static int wdt87xx_write_firmware(struct i2c_client *client, const void *chunk) +{ + u32 start_addr = get_unaligned_le32(chunk + FW_CHUNK_TGT_START_OFFSET); + u32 size = get_unaligned_le32(chunk + FW_CHUNK_PAYLOAD_LEN_OFFSET); + const void *data = chunk + FW_CHUNK_PAYLOAD_OFFSET; + int error; + int err1; + int page_size; + int retry = 0; + u16 device_checksum, firmware_checksum; + + dev_dbg(&client->dev, "start 4k page program\n"); + + error = wdt87xx_send_command(client, VND_CMD_STOP, MODE_STOP); + if (error) { + dev_err(&client->dev, "stop report mode failed\n"); + return error; + } + + error = wdt87xx_send_command(client, VND_CMD_SFUNL, 0); + if (error) { + dev_err(&client->dev, "unlock failed\n"); + goto out_enable_reporting; + } + + mdelay(10); + + while (size) { + dev_dbg(&client->dev, "%s: %x, %x\n", __func__, + start_addr, size); + + page_size = min_t(u32, size, PG_SIZE); + size -= page_size; + + for (retry = 0; retry < MAX_RETRIES; retry++) { + error = wdt87xx_send_command(client, VND_CMD_ERASE, + start_addr); + if (error) { + dev_err(&client->dev, + "erase failed at %#08x\n", start_addr); + break; + } + + msleep(50); + + error = wdt87xx_write_data(client, data, start_addr, + page_size); + if (error) { + dev_err(&client->dev, + "write failed at %#08x (%d bytes)\n", + start_addr, page_size); + break; + } + + error = wdt87xx_get_checksum(client, &device_checksum, + start_addr, page_size); + if (error) { + dev_err(&client->dev, + "failed to retrieve checksum for %#08x (len: %d)\n", + start_addr, page_size); + break; + } + + firmware_checksum = + wdt87xx_calculate_checksum(data, page_size); + + if (device_checksum == firmware_checksum) + break; + + dev_err(&client->dev, + "checksum fail: %d vs %d, retry %d\n", + device_checksum, firmware_checksum, retry); + } + + if (retry == MAX_RETRIES) { + dev_err(&client->dev, "page write failed\n"); + error = -EIO; + goto out_lock_device; + } + + start_addr = start_addr + page_size; + data = data + page_size; + } + +out_lock_device: + err1 = wdt87xx_send_command(client, VND_CMD_SFLCK, 0); + if (err1) + dev_err(&client->dev, "lock failed\n"); + + mdelay(10); + +out_enable_reporting: + err1 = wdt87xx_send_command(client, VND_CMD_START, 0); + if (err1) + dev_err(&client->dev, "start to report failed\n"); + + return error ? error : err1; +} + +static int wdt87xx_load_chunk(struct i2c_client *client, + const struct firmware *fw, u32 ck_id) +{ + const void *chunk; + int error; + + chunk = wdt87xx_get_fw_chunk(fw, ck_id); + if (!chunk) { + dev_err(&client->dev, "unable to locate chunk (type %d)\n", + ck_id); + return -EINVAL; + } + + error = wdt87xx_validate_fw_chunk(chunk, ck_id); + if (error) { + dev_err(&client->dev, "invalid chunk (type %d): %d\n", + ck_id, error); + return error; + } + + error = wdt87xx_write_firmware(client, chunk); + if (error) { + dev_err(&client->dev, + "failed to write fw chunk (type %d): %d\n", + ck_id, error); + return error; + } + + return 0; +} + +static int wdt87xx_do_update_firmware(struct i2c_client *client, + const struct firmware *fw, + unsigned int chunk_id) +{ + struct wdt87xx_data *wdt = i2c_get_clientdata(client); + int error; + + error = wdt87xx_validate_firmware(wdt, fw); + if (error) + return error; + + error = mutex_lock_interruptible(&wdt->fw_mutex); + if (error) + return error; + + disable_irq(client->irq); + + error = wdt87xx_load_chunk(client, fw, chunk_id); + if (error) { + dev_err(&client->dev, + "firmware load failed (type: %d): %d\n", + chunk_id, error); + goto out; + } + + error = wdt87xx_sw_reset(client); + if (error) { + dev_err(&client->dev, "soft reset failed: %d\n", error); + goto out; + } + + /* Refresh the parameters */ + error = wdt87xx_get_sysparam(client, &wdt->param); + if (error) + dev_err(&client->dev, + "failed to refresh system paramaters: %d\n", error); +out: + enable_irq(client->irq); + mutex_unlock(&wdt->fw_mutex); + + return error ? error : 0; +} + +static int wdt87xx_update_firmware(struct device *dev, + const char *fw_name, unsigned int chunk_id) +{ + struct i2c_client *client = to_i2c_client(dev); + const struct firmware *fw; + int error; + + error = request_firmware(&fw, fw_name, dev); + if (error) { + dev_err(&client->dev, "unable to retrieve firmware %s: %d\n", + fw_name, error); + return error; + } + + error = wdt87xx_do_update_firmware(client, fw, chunk_id); + + release_firmware(fw); + + return error ? error : 0; +} + +static ssize_t config_csum_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct wdt87xx_data *wdt = i2c_get_clientdata(client); + u32 cfg_csum; + + cfg_csum = wdt->param.xmls_id1; + cfg_csum = (cfg_csum << 16) | wdt->param.xmls_id2; + + return scnprintf(buf, PAGE_SIZE, "%x\n", cfg_csum); +} + +static ssize_t fw_version_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct wdt87xx_data *wdt = i2c_get_clientdata(client); + + return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.fw_id); +} + +static ssize_t plat_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct i2c_client *client = to_i2c_client(dev); + struct wdt87xx_data *wdt = i2c_get_clientdata(client); + + return scnprintf(buf, PAGE_SIZE, "%x\n", wdt->param.plat_id); +} + +static ssize_t update_config_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int error; + + error = wdt87xx_update_firmware(dev, WDT87XX_CFG_NAME, CHUNK_ID_CNFG); + + return error ? error : count; +} + +static ssize_t update_fw_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int error; + + error = wdt87xx_update_firmware(dev, WDT87XX_FW_NAME, CHUNK_ID_FRWR); + + return error ? error : count; +} + +static DEVICE_ATTR_RO(config_csum); +static DEVICE_ATTR_RO(fw_version); +static DEVICE_ATTR_RO(plat_id); +static DEVICE_ATTR_WO(update_config); +static DEVICE_ATTR_WO(update_fw); + +static struct attribute *wdt87xx_attrs[] = { + &dev_attr_config_csum.attr, + &dev_attr_fw_version.attr, + &dev_attr_plat_id.attr, + &dev_attr_update_config.attr, + &dev_attr_update_fw.attr, + NULL +}; + +static const struct attribute_group wdt87xx_attr_group = { + .attrs = wdt87xx_attrs, +}; + +static void wdt87xx_report_contact(struct input_dev *input, + struct wdt87xx_sys_param *param, + u8 *buf) +{ + int finger_id; + u32 x, y, w; + u8 p; + + finger_id = (buf[FINGER_EV_V1_OFFSET_ID] >> 3) - 1; + if (finger_id < 0) + return; + + /* Check if this is an active contact */ + if (!(buf[FINGER_EV_V1_OFFSET_ID] & 0x1)) + return; + + w = buf[FINGER_EV_V1_OFFSET_W]; + w *= param->scaling_factor; + + p = buf[FINGER_EV_V1_OFFSET_P]; + + x = get_unaligned_le16(buf + FINGER_EV_V1_OFFSET_X); + + y = get_unaligned_le16(buf + FINGER_EV_V1_OFFSET_Y); + y = DIV_ROUND_CLOSEST(y * param->phy_h, param->phy_w); + + /* Refuse incorrect coordinates */ + if (x > param->max_x || y > param->max_y) + return; + + dev_dbg(input->dev.parent, "tip on (%d), x(%d), y(%d)\n", + finger_id, x, y); + + input_mt_slot(input, finger_id); + input_mt_report_slot_state(input, MT_TOOL_FINGER, 1); + input_report_abs(input, ABS_MT_TOUCH_MAJOR, w); + input_report_abs(input, ABS_MT_PRESSURE, p); + input_report_abs(input, ABS_MT_POSITION_X, x); + input_report_abs(input, ABS_MT_POSITION_Y, y); +} + +static irqreturn_t wdt87xx_ts_interrupt(int irq, void *dev_id) +{ + struct wdt87xx_data *wdt = dev_id; + struct i2c_client *client = wdt->client; + int i, fingers; + int error; + u8 raw_buf[WDT_V1_RAW_BUF_COUNT] = {0}; + + error = i2c_master_recv(client, raw_buf, WDT_V1_RAW_BUF_COUNT); + if (error < 0) { + dev_err(&client->dev, "read v1 raw data failed: %d\n", error); + goto irq_exit; + } + + fingers = raw_buf[TOUCH_PK_V1_OFFSET_FNGR_NUM]; + if (!fingers) + goto irq_exit; + + for (i = 0; i < WDT_MAX_FINGER; i++) + wdt87xx_report_contact(wdt->input, + &wdt->param, + &raw_buf[TOUCH_PK_V1_OFFSET_EVENT + + i * FINGER_EV_V1_SIZE]); + + input_mt_sync_frame(wdt->input); + input_sync(wdt->input); + +irq_exit: + return IRQ_HANDLED; +} + +static int wdt87xx_ts_create_input_device(struct wdt87xx_data *wdt) +{ + struct device *dev = &wdt->client->dev; + struct input_dev *input; + unsigned int res = DIV_ROUND_CLOSEST(MAX_UNIT_AXIS, wdt->param.phy_w); + int error; + + input = devm_input_allocate_device(dev); + if (!input) { + dev_err(dev, "failed to allocate input device\n"); + return -ENOMEM; + } + wdt->input = input; + + input->name = "WDT87xx Touchscreen"; + input->id.bustype = BUS_I2C; + input->phys = wdt->phys; + + input_set_abs_params(input, ABS_MT_POSITION_X, 0, + wdt->param.max_x, 0, 0); + input_set_abs_params(input, ABS_MT_POSITION_Y, 0, + wdt->param.max_y, 0, 0); + input_abs_set_res(input, ABS_MT_POSITION_X, res); + input_abs_set_res(input, ABS_MT_POSITION_Y, res); + + input_set_abs_params(input, ABS_MT_TOUCH_MAJOR, + 0, wdt->param.max_x, 0, 0); + input_set_abs_params(input, ABS_MT_PRESSURE, 0, 0xFF, 0, 0); + + input_mt_init_slots(input, WDT_MAX_FINGER, + INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED); + + error = input_register_device(input); + if (error) { + dev_err(dev, "failed to register input device: %d\n", error); + return error; + } + + return 0; +} + +static int wdt87xx_ts_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct wdt87xx_data *wdt; + int error; + + dev_dbg(&client->dev, "adapter=%d, client irq: %d\n", + client->adapter->nr, client->irq); + + /* Check if the I2C function is ok in this adaptor */ + if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) + return -ENXIO; + + wdt = devm_kzalloc(&client->dev, sizeof(*wdt), GFP_KERNEL); + if (!wdt) + return -ENOMEM; + + wdt->client = client; + mutex_init(&wdt->fw_mutex); + i2c_set_clientdata(client, wdt); + + snprintf(wdt->phys, sizeof(wdt->phys), "i2c-%u-%04x/input0", + client->adapter->nr, client->addr); + + error = wdt87xx_get_sysparam(client, &wdt->param); + if (error) + return error; + + error = wdt87xx_ts_create_input_device(wdt); + if (error) + return error; + + error = devm_request_threaded_irq(&client->dev, client->irq, + NULL, wdt87xx_ts_interrupt, + IRQF_ONESHOT, + client->name, wdt); + if (error) { + dev_err(&client->dev, "request irq failed: %d\n", error); + return error; + } + + error = sysfs_create_group(&client->dev.kobj, &wdt87xx_attr_group); + if (error) { + dev_err(&client->dev, "create sysfs failed: %d\n", error); + return error; + } + + return 0; +} + +static int wdt87xx_ts_remove(struct i2c_client *client) +{ + sysfs_remove_group(&client->dev.kobj, &wdt87xx_attr_group); + + return 0; +} + +static int __maybe_unused wdt87xx_suspend(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + int error; + + disable_irq(client->irq); + + error = wdt87xx_send_command(client, VND_CMD_STOP, MODE_IDLE); + if (error) { + enable_irq(client->irq); + dev_err(&client->dev, + "failed to stop device when suspending: %d\n", + error); + return error; + } + + return 0; +} + +static int __maybe_unused wdt87xx_resume(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + int error; + + /* + * The chip may have been reset while system is resuming, + * give it some time to settle. + */ + mdelay(100); + + error = wdt87xx_send_command(client, VND_CMD_START, 0); + if (error) + dev_err(&client->dev, + "failed to start device when resuming: %d\n", + error); + + enable_irq(client->irq); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(wdt87xx_pm_ops, wdt87xx_suspend, wdt87xx_resume); + +static const struct i2c_device_id wdt87xx_dev_id[] = { + { WDT87XX_NAME, 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, wdt87xx_dev_id); + +static const struct acpi_device_id wdt87xx_acpi_id[] = { + { "WDHT0001", 0 }, + { } +}; +MODULE_DEVICE_TABLE(acpi, wdt87xx_acpi_id); + +static struct i2c_driver wdt87xx_driver = { + .probe = wdt87xx_ts_probe, + .remove = wdt87xx_ts_remove, + .id_table = wdt87xx_dev_id, + .driver = { + .name = WDT87XX_NAME, + .pm = &wdt87xx_pm_ops, + .acpi_match_table = ACPI_PTR(wdt87xx_acpi_id), + }, +}; +module_i2c_driver(wdt87xx_driver); + +MODULE_AUTHOR("HN Chen <hn.chen@weidahitech.com>"); +MODULE_DESCRIPTION("WeidaHiTech WDT87XX Touchscreen driver"); +MODULE_VERSION(WDT87XX_DRV_VER); +MODULE_LICENSE("GPL"); diff --git a/drivers/irqchip/irqchip.h b/drivers/irqchip/irqchip.h index 0f6486d4f1b0..0f67ae32464f 100644 --- a/drivers/irqchip/irqchip.h +++ b/drivers/irqchip/irqchip.h @@ -8,21 +8,4 @@ * warranty of any kind, whether express or implied. */ -#ifndef _IRQCHIP_H -#define _IRQCHIP_H - -#include <linux/of.h> - -/* - * This macro must be used by the different irqchip drivers to declare - * the association between their DT compatible string and their - * initialization function. - * - * @name: name that must be unique accross all IRQCHIP_DECLARE of the - * same file. - * @compstr: compatible string of the irqchip driver - * @fn: initialization function - */ -#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn) - -#endif +#include <linux/irqchip.h> diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 019fceffc9e5..b7f31150753d 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -258,6 +258,20 @@ config TUN If you don't know what to use this for, you don't need it. +config TUN_VNET_CROSS_LE + bool "Support for cross-endian vnet headers on little-endian kernels" + default n + ---help--- + This option allows TUN/TAP and MACVTAP device drivers in a + little-endian kernel to parse vnet headers that come from a + big-endian legacy virtio device. + + Userspace programs can control the feature using the TUNSETVNETBE + and TUNGETVNETBE ioctls. + + Unless you have a little-endian system hosting a big-endian virtual + machine with a legacy virtio NIC, you should say N. + config VETH tristate "Virtual ethernet pair device" ---help--- diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 6a64197f5bce..f8370808a018 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -48,15 +48,70 @@ struct macvtap_queue { #define MACVTAP_FEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE) #define MACVTAP_VNET_LE 0x80000000 +#define MACVTAP_VNET_BE 0x40000000 + +#ifdef CONFIG_TUN_VNET_CROSS_LE +static inline bool macvtap_legacy_is_little_endian(struct macvtap_queue *q) +{ + return q->flags & MACVTAP_VNET_BE ? false : + virtio_legacy_is_little_endian(); +} + +static long macvtap_get_vnet_be(struct macvtap_queue *q, int __user *sp) +{ + int s = !!(q->flags & MACVTAP_VNET_BE); + + if (put_user(s, sp)) + return -EFAULT; + + return 0; +} + +static long macvtap_set_vnet_be(struct macvtap_queue *q, int __user *sp) +{ + int s; + + if (get_user(s, sp)) + return -EFAULT; + + if (s) + q->flags |= MACVTAP_VNET_BE; + else + q->flags &= ~MACVTAP_VNET_BE; + + return 0; +} +#else +static inline bool macvtap_legacy_is_little_endian(struct macvtap_queue *q) +{ + return virtio_legacy_is_little_endian(); +} + +static long macvtap_get_vnet_be(struct macvtap_queue *q, int __user *argp) +{ + return -EINVAL; +} + +static long macvtap_set_vnet_be(struct macvtap_queue *q, int __user *argp) +{ + return -EINVAL; +} +#endif /* CONFIG_TUN_VNET_CROSS_LE */ + +static inline bool macvtap_is_little_endian(struct macvtap_queue *q) +{ + return q->flags & MACVTAP_VNET_LE || + macvtap_legacy_is_little_endian(q); +} static inline u16 macvtap16_to_cpu(struct macvtap_queue *q, __virtio16 val) { - return __virtio16_to_cpu(q->flags & MACVTAP_VNET_LE, val); + return __virtio16_to_cpu(macvtap_is_little_endian(q), val); } static inline __virtio16 cpu_to_macvtap16(struct macvtap_queue *q, u16 val) { - return __cpu_to_virtio16(q->flags & MACVTAP_VNET_LE, val); + return __cpu_to_virtio16(macvtap_is_little_endian(q), val); } static struct proto macvtap_proto = { @@ -1085,6 +1140,12 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, q->flags &= ~MACVTAP_VNET_LE; return 0; + case TUNGETVNETBE: + return macvtap_get_vnet_be(q, sp); + + case TUNSETVNETBE: + return macvtap_set_vnet_be(q, sp); + case TUNSETOFFLOAD: /* let the user check for future flags */ if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 1a1c4f7b3ec5..06a039414628 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -111,6 +111,7 @@ do { \ #define TUN_FASYNC IFF_ATTACH_QUEUE /* High bits in flags field are unused. */ #define TUN_VNET_LE 0x80000000 +#define TUN_VNET_BE 0x40000000 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ IFF_MULTI_QUEUE) @@ -205,14 +206,68 @@ struct tun_struct { u32 flow_count; }; +#ifdef CONFIG_TUN_VNET_CROSS_LE +static inline bool tun_legacy_is_little_endian(struct tun_struct *tun) +{ + return tun->flags & TUN_VNET_BE ? false : + virtio_legacy_is_little_endian(); +} + +static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp) +{ + int be = !!(tun->flags & TUN_VNET_BE); + + if (put_user(be, argp)) + return -EFAULT; + + return 0; +} + +static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp) +{ + int be; + + if (get_user(be, argp)) + return -EFAULT; + + if (be) + tun->flags |= TUN_VNET_BE; + else + tun->flags &= ~TUN_VNET_BE; + + return 0; +} +#else +static inline bool tun_legacy_is_little_endian(struct tun_struct *tun) +{ + return virtio_legacy_is_little_endian(); +} + +static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp) +{ + return -EINVAL; +} + +static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp) +{ + return -EINVAL; +} +#endif /* CONFIG_TUN_VNET_CROSS_LE */ + +static inline bool tun_is_little_endian(struct tun_struct *tun) +{ + return tun->flags & TUN_VNET_LE || + tun_legacy_is_little_endian(tun); +} + static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val) { - return __virtio16_to_cpu(tun->flags & TUN_VNET_LE, val); + return __virtio16_to_cpu(tun_is_little_endian(tun), val); } static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val) { - return __cpu_to_virtio16(tun->flags & TUN_VNET_LE, val); + return __cpu_to_virtio16(tun_is_little_endian(tun), val); } static inline u32 tun_hashfn(u32 rxhash) @@ -2044,6 +2099,14 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, tun->flags &= ~TUN_VNET_LE; break; + case TUNGETVNETBE: + ret = tun_get_vnet_be(tun, argp); + break; + + case TUNSETVNETBE: + ret = tun_set_vnet_be(tun, argp); + break; + case TUNATTACHFILTER: /* Can be set only for TAPs */ ret = -EINVAL; diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 5e343bab9458..28c711f0ac6b 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -41,6 +41,19 @@ config STE_MODEM_RPROC This can be either built-in or a loadable module. If unsure say N. +config WKUP_M3_RPROC + tristate "AMx3xx Wakeup M3 remoteproc support" + depends on SOC_AM33XX || SOC_AM43XX + select REMOTEPROC + help + Say y here to support Wakeup M3 remote processor on TI AM33xx + and AM43xx family of SoCs. + + Required for Suspend-to-RAM on AM33xx and AM43xx SoCs. Also needed + for deep CPUIdle states on AM33xx SoCs. Allows for loading of the + firmware onto these remote processors. + If unsure say N. + config DA8XX_REMOTEPROC tristate "DA8xx/OMAP-L13x remoteproc support" depends on ARCH_DAVINCI_DA8XX diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile index ac2ff75686d2..81b04d1e2e58 100644 --- a/drivers/remoteproc/Makefile +++ b/drivers/remoteproc/Makefile @@ -9,4 +9,5 @@ remoteproc-y += remoteproc_virtio.o remoteproc-y += remoteproc_elf_loader.o obj-$(CONFIG_OMAP_REMOTEPROC) += omap_remoteproc.o obj-$(CONFIG_STE_MODEM_RPROC) += ste_modem_rproc.o +obj-$(CONFIG_WKUP_M3_RPROC) += wkup_m3_rproc.o obj-$(CONFIG_DA8XX_REMOTEPROC) += da8xx_remoteproc.o diff --git a/drivers/remoteproc/da8xx_remoteproc.c b/drivers/remoteproc/da8xx_remoteproc.c index f8d6a0661c14..009e56f67de2 100644 --- a/drivers/remoteproc/da8xx_remoteproc.c +++ b/drivers/remoteproc/da8xx_remoteproc.c @@ -26,8 +26,7 @@ static char *da8xx_fw_name; module_param(da8xx_fw_name, charp, S_IRUGO); MODULE_PARM_DESC(da8xx_fw_name, - "\n\t\tName of DSP firmware file in /lib/firmware" - " (if not specified defaults to 'rproc-dsp-fw')"); + "Name of DSP firmware file in /lib/firmware (if not specified defaults to 'rproc-dsp-fw')"); /* * OMAP-L138 Technical References: diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 11cdb119e4f3..8b3130f22b42 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -44,6 +44,9 @@ #include "remoteproc_internal.h" +static DEFINE_MUTEX(rproc_list_mutex); +static LIST_HEAD(rproc_list); + typedef int (*rproc_handle_resources_t)(struct rproc *rproc, struct resource_table *table, int len); typedef int (*rproc_handle_resource_t)(struct rproc *rproc, @@ -132,32 +135,48 @@ static void rproc_disable_iommu(struct rproc *rproc) iommu_detach_device(domain, dev); iommu_domain_free(domain); - - return; } -/* +/** + * rproc_da_to_va() - lookup the kernel virtual address for a remoteproc address + * @rproc: handle of a remote processor + * @da: remoteproc device address to translate + * @len: length of the memory region @da is pointing to + * * Some remote processors will ask us to allocate them physically contiguous * memory regions (which we call "carveouts"), and map them to specific - * device addresses (which are hardcoded in the firmware). + * device addresses (which are hardcoded in the firmware). They may also have + * dedicated memory regions internal to the processors, and use them either + * exclusively or alongside carveouts. * * They may then ask us to copy objects into specific device addresses (e.g. * code/data sections) or expose us certain symbols in other device address * (e.g. their trace buffer). * - * This function is an internal helper with which we can go over the allocated - * carveouts and translate specific device address to kernel virtual addresses - * so we can access the referenced memory. + * This function is a helper function with which we can go over the allocated + * carveouts and translate specific device addresses to kernel virtual addresses + * so we can access the referenced memory. This function also allows to perform + * translations on the internal remoteproc memory regions through a platform + * implementation specific da_to_va ops, if present. + * + * The function returns a valid kernel address on success or NULL on failure. * * Note: phys_to_virt(iommu_iova_to_phys(rproc->domain, da)) will work too, * but only on kernel direct mapped RAM memory. Instead, we're just using - * here the output of the DMA API, which should be more correct. + * here the output of the DMA API for the carveouts, which should be more + * correct. */ void *rproc_da_to_va(struct rproc *rproc, u64 da, int len) { struct rproc_mem_entry *carveout; void *ptr = NULL; + if (rproc->ops->da_to_va) { + ptr = rproc->ops->da_to_va(rproc, da, len); + if (ptr) + goto out; + } + list_for_each_entry(carveout, &rproc->carveouts, node) { int offset = da - carveout->da; @@ -174,6 +193,7 @@ void *rproc_da_to_va(struct rproc *rproc, u64 da, int len) break; } +out: return ptr; } EXPORT_SYMBOL(rproc_da_to_va); @@ -411,10 +431,8 @@ static int rproc_handle_trace(struct rproc *rproc, struct fw_rsc_trace *rsc, } trace = kzalloc(sizeof(*trace), GFP_KERNEL); - if (!trace) { - dev_err(dev, "kzalloc trace failed\n"); + if (!trace) return -ENOMEM; - } /* set the trace buffer dma properties */ trace->len = rsc->len; @@ -489,10 +507,8 @@ static int rproc_handle_devmem(struct rproc *rproc, struct fw_rsc_devmem *rsc, } mapping = kzalloc(sizeof(*mapping), GFP_KERNEL); - if (!mapping) { - dev_err(dev, "kzalloc mapping failed\n"); + if (!mapping) return -ENOMEM; - } ret = iommu_map(rproc->domain, rsc->da, rsc->pa, rsc->len, rsc->flags); if (ret) { @@ -565,10 +581,8 @@ static int rproc_handle_carveout(struct rproc *rproc, rsc->da, rsc->pa, rsc->len, rsc->flags); carveout = kzalloc(sizeof(*carveout), GFP_KERNEL); - if (!carveout) { - dev_err(dev, "kzalloc carveout failed\n"); + if (!carveout) return -ENOMEM; - } va = dma_alloc_coherent(dev->parent, rsc->len, &dma, GFP_KERNEL); if (!va) { @@ -768,7 +782,8 @@ static void rproc_resource_cleanup(struct rproc *rproc) /* clean up carveout allocations */ list_for_each_entry_safe(entry, tmp, &rproc->carveouts, node) { - dma_free_coherent(dev->parent, entry->len, entry->va, entry->dma); + dma_free_coherent(dev->parent, entry->len, entry->va, + entry->dma); list_del(&entry->node); kfree(entry); } @@ -808,9 +823,8 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) /* look for the resource table */ table = rproc_find_rsc_table(rproc, fw, &tablesz); - if (!table) { + if (!table) goto clean_up; - } /* Verify that resource table in loaded fw is unchanged */ if (rproc->table_csum != crc32(0, table, tablesz)) { @@ -911,7 +925,8 @@ static void rproc_fw_config_virtio(const struct firmware *fw, void *context) /* count the number of notify-ids */ rproc->max_notifyid = -1; - ret = rproc_handle_resources(rproc, tablesz, rproc_count_vrings_handler); + ret = rproc_handle_resources(rproc, tablesz, + rproc_count_vrings_handler); if (ret) goto out; @@ -1152,6 +1167,50 @@ out: EXPORT_SYMBOL(rproc_shutdown); /** + * rproc_get_by_phandle() - find a remote processor by phandle + * @phandle: phandle to the rproc + * + * Finds an rproc handle using the remote processor's phandle, and then + * return a handle to the rproc. + * + * This function increments the remote processor's refcount, so always + * use rproc_put() to decrement it back once rproc isn't needed anymore. + * + * Returns the rproc handle on success, and NULL on failure. + */ +#ifdef CONFIG_OF +struct rproc *rproc_get_by_phandle(phandle phandle) +{ + struct rproc *rproc = NULL, *r; + struct device_node *np; + + np = of_find_node_by_phandle(phandle); + if (!np) + return NULL; + + mutex_lock(&rproc_list_mutex); + list_for_each_entry(r, &rproc_list, node) { + if (r->dev.parent && r->dev.parent->of_node == np) { + rproc = r; + get_device(&rproc->dev); + break; + } + } + mutex_unlock(&rproc_list_mutex); + + of_node_put(np); + + return rproc; +} +#else +struct rproc *rproc_get_by_phandle(phandle phandle) +{ + return NULL; +} +#endif +EXPORT_SYMBOL(rproc_get_by_phandle); + +/** * rproc_add() - register a remote processor * @rproc: the remote processor handle to register * @@ -1180,6 +1239,11 @@ int rproc_add(struct rproc *rproc) if (ret < 0) return ret; + /* expose to rproc_get_by_phandle users */ + mutex_lock(&rproc_list_mutex); + list_add(&rproc->node, &rproc_list); + mutex_unlock(&rproc_list_mutex); + dev_info(dev, "%s is available\n", rproc->name); dev_info(dev, "Note: remoteproc is still under development and considered experimental.\n"); @@ -1268,10 +1332,8 @@ struct rproc *rproc_alloc(struct device *dev, const char *name, name_len = strlen(name) + strlen(template) - 2 + 1; rproc = kzalloc(sizeof(struct rproc) + len + name_len, GFP_KERNEL); - if (!rproc) { - dev_err(dev, "%s: kzalloc failed\n", __func__); + if (!rproc) return NULL; - } if (!firmware) { p = (char *)rproc + sizeof(struct rproc) + len; @@ -1369,6 +1431,11 @@ int rproc_del(struct rproc *rproc) /* Free the copy of the resource table */ kfree(rproc->cached_table); + /* the rproc is downref'ed as soon as it's removed from the klist */ + mutex_lock(&rproc_list_mutex); + list_del(&rproc->node); + mutex_unlock(&rproc_list_mutex); + device_del(&rproc->dev); return 0; diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h index 70701a50ddfa..8041b95cb058 100644 --- a/drivers/remoteproc/remoteproc_internal.h +++ b/drivers/remoteproc/remoteproc_internal.h @@ -35,7 +35,7 @@ struct rproc; * @get_boot_addr: get boot address to entry point specified in firmware */ struct rproc_fw_ops { - struct resource_table *(*find_rsc_table) (struct rproc *rproc, + struct resource_table *(*find_rsc_table)(struct rproc *rproc, const struct firmware *fw, int *tablesz); struct resource_table *(*find_loaded_rsc_table)(struct rproc *rproc, diff --git a/drivers/remoteproc/ste_modem_rproc.c b/drivers/remoteproc/ste_modem_rproc.c index dd193f35a1ff..53dc17bdd54e 100644 --- a/drivers/remoteproc/ste_modem_rproc.c +++ b/drivers/remoteproc/ste_modem_rproc.c @@ -67,8 +67,7 @@ static int sproc_load_segments(struct rproc *rproc, const struct firmware *fw) static const struct ste_toc_entry *sproc_find_rsc_entry(const void *data) { int i; - const struct ste_toc *toc; - toc = data; + const struct ste_toc *toc = data; /* Search the table for the resource table */ for (i = 0; i < SPROC_MAX_TOC_ENTRIES && @@ -230,6 +229,7 @@ static int sproc_start(struct rproc *rproc) static int sproc_stop(struct rproc *rproc) { struct sproc *sproc = rproc->priv; + sproc_dbg(sproc, "stop ste-modem\n"); return sproc->mdev->ops.power(sproc->mdev, false); diff --git a/drivers/remoteproc/wkup_m3_rproc.c b/drivers/remoteproc/wkup_m3_rproc.c new file mode 100644 index 000000000000..edf81819cce1 --- /dev/null +++ b/drivers/remoteproc/wkup_m3_rproc.c @@ -0,0 +1,257 @@ +/* + * TI AMx3 Wakeup M3 Remote Processor driver + * + * Copyright (C) 2014-2015 Texas Instruments, Inc. + * + * Dave Gerlach <d-gerlach@ti.com> + * Suman Anna <s-anna@ti.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/remoteproc.h> + +#include <linux/platform_data/wkup_m3.h> + +#include "remoteproc_internal.h" + +#define WKUPM3_MEM_MAX 2 + +/** + * struct wkup_m3_mem - WkupM3 internal memory structure + * @cpu_addr: MPU virtual address of the memory region + * @bus_addr: Bus address used to access the memory region + * @dev_addr: Device address from Wakeup M3 view + * @size: Size of the memory region + */ +struct wkup_m3_mem { + void __iomem *cpu_addr; + phys_addr_t bus_addr; + u32 dev_addr; + size_t size; +}; + +/** + * struct wkup_m3_rproc - WkupM3 remote processor state + * @rproc: rproc handle + * @pdev: pointer to platform device + * @mem: WkupM3 memory information + */ +struct wkup_m3_rproc { + struct rproc *rproc; + struct platform_device *pdev; + struct wkup_m3_mem mem[WKUPM3_MEM_MAX]; +}; + +static int wkup_m3_rproc_start(struct rproc *rproc) +{ + struct wkup_m3_rproc *wkupm3 = rproc->priv; + struct platform_device *pdev = wkupm3->pdev; + struct device *dev = &pdev->dev; + struct wkup_m3_platform_data *pdata = dev_get_platdata(dev); + + if (pdata->deassert_reset(pdev, pdata->reset_name)) { + dev_err(dev, "Unable to reset wkup_m3!\n"); + return -ENODEV; + } + + return 0; +} + +static int wkup_m3_rproc_stop(struct rproc *rproc) +{ + struct wkup_m3_rproc *wkupm3 = rproc->priv; + struct platform_device *pdev = wkupm3->pdev; + struct device *dev = &pdev->dev; + struct wkup_m3_platform_data *pdata = dev_get_platdata(dev); + + if (pdata->assert_reset(pdev, pdata->reset_name)) { + dev_err(dev, "Unable to assert reset of wkup_m3!\n"); + return -ENODEV; + } + + return 0; +} + +static void *wkup_m3_rproc_da_to_va(struct rproc *rproc, u64 da, int len) +{ + struct wkup_m3_rproc *wkupm3 = rproc->priv; + void *va = NULL; + int i; + u32 offset; + + if (len <= 0) + return NULL; + + for (i = 0; i < WKUPM3_MEM_MAX; i++) { + if (da >= wkupm3->mem[i].dev_addr && da + len <= + wkupm3->mem[i].dev_addr + wkupm3->mem[i].size) { + offset = da - wkupm3->mem[i].dev_addr; + /* __force to make sparse happy with type conversion */ + va = (__force void *)(wkupm3->mem[i].cpu_addr + offset); + break; + } + } + + return va; +} + +static struct rproc_ops wkup_m3_rproc_ops = { + .start = wkup_m3_rproc_start, + .stop = wkup_m3_rproc_stop, + .da_to_va = wkup_m3_rproc_da_to_va, +}; + +static const struct of_device_id wkup_m3_rproc_of_match[] = { + { .compatible = "ti,am3352-wkup-m3", }, + { .compatible = "ti,am4372-wkup-m3", }, + {}, +}; + +static int wkup_m3_rproc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct wkup_m3_platform_data *pdata = dev->platform_data; + /* umem always needs to be processed first */ + const char *mem_names[WKUPM3_MEM_MAX] = { "umem", "dmem" }; + struct wkup_m3_rproc *wkupm3; + const char *fw_name; + struct rproc *rproc; + struct resource *res; + const __be32 *addrp; + u32 l4_offset = 0; + u64 size; + int ret; + int i; + + if (!(pdata && pdata->deassert_reset && pdata->assert_reset && + pdata->reset_name)) { + dev_err(dev, "Platform data missing!\n"); + return -ENODEV; + } + + ret = of_property_read_string(dev->of_node, "ti,pm-firmware", + &fw_name); + if (ret) { + dev_err(dev, "No firmware filename given\n"); + return -ENODEV; + } + + pm_runtime_enable(&pdev->dev); + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) { + dev_err(&pdev->dev, "pm_runtime_get_sync() failed\n"); + goto err; + } + + rproc = rproc_alloc(dev, "wkup_m3", &wkup_m3_rproc_ops, + fw_name, sizeof(*wkupm3)); + if (!rproc) { + ret = -ENOMEM; + goto err; + } + + wkupm3 = rproc->priv; + wkupm3->rproc = rproc; + wkupm3->pdev = pdev; + + for (i = 0; i < ARRAY_SIZE(mem_names); i++) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + mem_names[i]); + wkupm3->mem[i].cpu_addr = devm_ioremap_resource(dev, res); + if (IS_ERR(wkupm3->mem[i].cpu_addr)) { + dev_err(&pdev->dev, "devm_ioremap_resource failed for resource %d\n", + i); + ret = PTR_ERR(wkupm3->mem[i].cpu_addr); + goto err; + } + wkupm3->mem[i].bus_addr = res->start; + wkupm3->mem[i].size = resource_size(res); + addrp = of_get_address(dev->of_node, i, &size, NULL); + /* + * The wkupm3 has umem at address 0 in its view, so the device + * addresses for each memory region is computed as a relative + * offset of the bus address for umem, and therefore needs to be + * processed first. + */ + if (!strcmp(mem_names[i], "umem")) + l4_offset = be32_to_cpu(*addrp); + wkupm3->mem[i].dev_addr = be32_to_cpu(*addrp) - l4_offset; + } + + dev_set_drvdata(dev, rproc); + + ret = rproc_add(rproc); + if (ret) { + dev_err(dev, "rproc_add failed\n"); + goto err_put_rproc; + } + + return 0; + +err_put_rproc: + rproc_put(rproc); +err: + pm_runtime_put_noidle(dev); + pm_runtime_disable(dev); + return ret; +} + +static int wkup_m3_rproc_remove(struct platform_device *pdev) +{ + struct rproc *rproc = platform_get_drvdata(pdev); + + rproc_del(rproc); + rproc_put(rproc); + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + return 0; +} + +#ifdef CONFIG_PM +static int wkup_m3_rpm_suspend(struct device *dev) +{ + return -EBUSY; +} + +static int wkup_m3_rpm_resume(struct device *dev) +{ + return 0; +} +#endif + +static const struct dev_pm_ops wkup_m3_rproc_pm_ops = { + SET_RUNTIME_PM_OPS(wkup_m3_rpm_suspend, wkup_m3_rpm_resume, NULL) +}; + +static struct platform_driver wkup_m3_rproc_driver = { + .probe = wkup_m3_rproc_probe, + .remove = wkup_m3_rproc_remove, + .driver = { + .name = "wkup_m3_rproc", + .of_match_table = wkup_m3_rproc_of_match, + .pm = &wkup_m3_rproc_pm_ops, + }, +}; + +module_platform_driver(wkup_m3_rproc_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("TI Wakeup M3 remote processor control driver"); +MODULE_AUTHOR("Dave Gerlach <d-gerlach@ti.com>"); diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig index 017a1e8a8f6f..533eaf04f12f 100644 --- a/drivers/vhost/Kconfig +++ b/drivers/vhost/Kconfig @@ -32,3 +32,18 @@ config VHOST ---help--- This option is selected by any driver which needs to access the core of vhost. + +config VHOST_CROSS_ENDIAN_LEGACY + bool "Cross-endian support for vhost" + default n + ---help--- + This option allows vhost to support guests with a different byte + ordering from host while using legacy virtio. + + Userspace programs can control the feature using the + VHOST_SET_VRING_ENDIAN and VHOST_GET_VRING_ENDIAN ioctls. + + This is only useful on a few platforms (ppc64 and arm64). Since it + adds some overhead, it is disabled by default. + + If unsure, say "N". diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 2ee28266fd07..9e8e004bb1c3 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -36,6 +36,77 @@ enum { #define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num]) #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num]) +#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY +static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq) +{ + vq->user_be = !virtio_legacy_is_little_endian(); +} + +static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp) +{ + struct vhost_vring_state s; + + if (vq->private_data) + return -EBUSY; + + if (copy_from_user(&s, argp, sizeof(s))) + return -EFAULT; + + if (s.num != VHOST_VRING_LITTLE_ENDIAN && + s.num != VHOST_VRING_BIG_ENDIAN) + return -EINVAL; + + vq->user_be = s.num; + + return 0; +} + +static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx, + int __user *argp) +{ + struct vhost_vring_state s = { + .index = idx, + .num = vq->user_be + }; + + if (copy_to_user(argp, &s, sizeof(s))) + return -EFAULT; + + return 0; +} + +static void vhost_init_is_le(struct vhost_virtqueue *vq) +{ + /* Note for legacy virtio: user_be is initialized at reset time + * according to the host endianness. If userspace does not set an + * explicit endianness, the default behavior is native endian, as + * expected by legacy virtio. + */ + vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be; +} +#else +static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq) +{ +} + +static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp) +{ + return -ENOIOCTLCMD; +} + +static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx, + int __user *argp) +{ + return -ENOIOCTLCMD; +} + +static void vhost_init_is_le(struct vhost_virtqueue *vq) +{ + if (vhost_has_feature(vq, VIRTIO_F_VERSION_1)) + vq->is_le = true; +} +#endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */ + static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh, poll_table *pt) { @@ -199,6 +270,8 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->call = NULL; vq->log_ctx = NULL; vq->memory = NULL; + vq->is_le = virtio_legacy_is_little_endian(); + vhost_vq_reset_user_be(vq); } static int vhost_worker(void *data) @@ -806,6 +879,12 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) } else filep = eventfp; break; + case VHOST_SET_VRING_ENDIAN: + r = vhost_set_vring_endian(vq, argp); + break; + case VHOST_GET_VRING_ENDIAN: + r = vhost_get_vring_endian(vq, idx, argp); + break; default: r = -ENOIOCTLCMD; } @@ -1044,8 +1123,12 @@ int vhost_init_used(struct vhost_virtqueue *vq) { __virtio16 last_used_idx; int r; - if (!vq->private_data) + if (!vq->private_data) { + vq->is_le = virtio_legacy_is_little_endian(); return 0; + } + + vhost_init_is_le(vq); r = vhost_update_used_flags(vq); if (r) diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 8c1c792900ba..ce6f6da4b09f 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -106,6 +106,14 @@ struct vhost_virtqueue { /* Log write descriptors */ void __user *log_base; struct vhost_log *log; + + /* Ring endianness. Defaults to legacy native endianness. + * Set to true when starting a modern virtio device. */ + bool is_le; +#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY + /* Ring endianness requested by userspace for cross-endian support. */ + bool user_be; +#endif }; struct vhost_dev { @@ -173,34 +181,39 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) return vq->acked_features & (1ULL << bit); } +static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq) +{ + return vq->is_le; +} + /* Memory accessors */ static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val) { - return __virtio16_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __virtio16_to_cpu(vhost_is_little_endian(vq), val); } static inline __virtio16 cpu_to_vhost16(struct vhost_virtqueue *vq, u16 val) { - return __cpu_to_virtio16(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio16(vhost_is_little_endian(vq), val); } static inline u32 vhost32_to_cpu(struct vhost_virtqueue *vq, __virtio32 val) { - return __virtio32_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __virtio32_to_cpu(vhost_is_little_endian(vq), val); } static inline __virtio32 cpu_to_vhost32(struct vhost_virtqueue *vq, u32 val) { - return __cpu_to_virtio32(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio32(vhost_is_little_endian(vq), val); } static inline u64 vhost64_to_cpu(struct vhost_virtqueue *vq, __virtio64 val) { - return __virtio64_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __virtio64_to_cpu(vhost_is_little_endian(vq), val); } static inline __virtio64 cpu_to_vhost64(struct vhost_virtqueue *vq, u64 val) { - return __cpu_to_virtio64(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio64(vhost_is_little_endian(vq), val); } #endif diff --git a/drivers/video/fbdev/omap2/dss/dss.c b/drivers/video/fbdev/omap2/dss/dss.c index 612b093831d5..9200a8668b49 100644 --- a/drivers/video/fbdev/omap2/dss/dss.c +++ b/drivers/video/fbdev/omap2/dss/dss.c @@ -1225,6 +1225,15 @@ static int dss_add_child_component(struct device *dev, void *data) { struct component_match **match = data; + /* + * HACK + * We don't have a working driver for rfbi, so skip it here always. + * Otherwise dss will never get probed successfully, as it will wait + * for rfbi to get probed. + */ + if (strstr(dev_name(dev), "rfbi")) + return 0; + component_match_add(dev->parent, match, dss_component_compare, dev); return 0; diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 5447b8186332..78f804af6c20 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -507,10 +507,6 @@ static int virtio_pci_probe(struct pci_dev *pci_dev, if (rc) goto err_enable_device; - rc = pci_request_regions(pci_dev, "virtio-pci"); - if (rc) - goto err_request_regions; - if (force_legacy) { rc = virtio_pci_legacy_probe(vp_dev); /* Also try modern mode if we can't map BAR0 (no IO space). */ @@ -540,8 +536,6 @@ err_register: else virtio_pci_modern_remove(vp_dev); err_probe: - pci_release_regions(pci_dev); -err_request_regions: pci_disable_device(pci_dev); err_enable_device: kfree(vp_dev); @@ -559,7 +553,6 @@ static void virtio_pci_remove(struct pci_dev *pci_dev) else virtio_pci_modern_remove(vp_dev); - pci_release_regions(pci_dev); pci_disable_device(pci_dev); } diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 28ee4e56badf..b976d968e793 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -75,6 +75,8 @@ struct virtio_pci_device { /* Multiply queue_notify_off by this value. (non-legacy mode). */ u32 notify_offset_multiplier; + int modern_bars; + /* Legacy only field */ /* the IO mapping for the PCI config space */ void __iomem *ioaddr; diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c index 256a5278a515..48bc9797e530 100644 --- a/drivers/virtio/virtio_pci_legacy.c +++ b/drivers/virtio/virtio_pci_legacy.c @@ -215,6 +215,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev) { struct pci_dev *pci_dev = vp_dev->pci_dev; + int rc; /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */ if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f) @@ -226,9 +227,14 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev) return -ENODEV; } + rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy"); + if (rc) + return rc; + + rc = -ENOMEM; vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0); if (!vp_dev->ioaddr) - return -ENOMEM; + goto err_iomap; vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR; @@ -246,6 +252,10 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev) vp_dev->del_vq = del_vq; return 0; + +err_iomap: + pci_release_region(pci_dev, 0); + return rc; } void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev) @@ -253,4 +263,5 @@ void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev) struct pci_dev *pci_dev = vp_dev->pci_dev; pci_iounmap(pci_dev, vp_dev->ioaddr); + pci_release_region(pci_dev, 0); } diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index e88e0997a889..8e5cf194cc0b 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -499,7 +499,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { * Returns offset of the capability, or 0. */ static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type, - u32 ioresource_types) + u32 ioresource_types, int *bars) { int pos; @@ -520,8 +520,10 @@ static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type, if (type == cfg_type) { if (pci_resource_len(dev, bar) && - pci_resource_flags(dev, bar) & ioresource_types) + pci_resource_flags(dev, bar) & ioresource_types) { + *bars |= (1 << bar); return pos; + } } } return 0; @@ -617,7 +619,8 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) /* check for a common config: if not, use legacy mode (bar 0). */ common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG, - IORESOURCE_IO | IORESOURCE_MEM); + IORESOURCE_IO | IORESOURCE_MEM, + &vp_dev->modern_bars); if (!common) { dev_info(&pci_dev->dev, "virtio_pci: leaving for legacy driver\n"); @@ -626,9 +629,11 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) /* If common is there, these should be too... */ isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG, - IORESOURCE_IO | IORESOURCE_MEM); + IORESOURCE_IO | IORESOURCE_MEM, + &vp_dev->modern_bars); notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG, - IORESOURCE_IO | IORESOURCE_MEM); + IORESOURCE_IO | IORESOURCE_MEM, + &vp_dev->modern_bars); if (!isr || !notify) { dev_err(&pci_dev->dev, "virtio_pci: missing capabilities %i/%i/%i\n", @@ -640,7 +645,13 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) * device-specific configuration. */ device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG, - IORESOURCE_IO | IORESOURCE_MEM); + IORESOURCE_IO | IORESOURCE_MEM, + &vp_dev->modern_bars); + + err = pci_request_selected_regions(pci_dev, vp_dev->modern_bars, + "virtio-pci-modern"); + if (err) + return err; err = -EINVAL; vp_dev->common = map_capability(pci_dev, common, @@ -727,4 +738,5 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev) pci_iounmap(pci_dev, vp_dev->notify_base); pci_iounmap(pci_dev, vp_dev->isr); pci_iounmap(pci_dev, vp_dev->common); + pci_release_selected_regions(pci_dev, vp_dev->modern_bars); } diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 537356742091..a8f3b589a2df 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -129,8 +129,6 @@ void configfs_release_fs(void) } -static struct kobject *config_kobj; - static int __init configfs_init(void) { int err = -ENOMEM; @@ -141,8 +139,8 @@ static int __init configfs_init(void) if (!configfs_dir_cachep) goto out; - config_kobj = kobject_create_and_add("config", kernel_kobj); - if (!config_kobj) + err = sysfs_create_mount_point(kernel_kobj, "config"); + if (err) goto out2; err = register_filesystem(&configfs_fs_type); @@ -152,7 +150,7 @@ static int __init configfs_init(void) return 0; out3: pr_err("Unable to register filesystem!\n"); - kobject_put(config_kobj); + sysfs_remove_mount_point(kernel_kobj, "config"); out2: kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; @@ -163,7 +161,7 @@ out: static void __exit configfs_exit(void) { unregister_filesystem(&configfs_fs_type); - kobject_put(config_kobj); + sysfs_remove_mount_point(kernel_kobj, "config"); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; } diff --git a/fs/dcache.c b/fs/dcache.c index 592c4b582495..910968b4b6bf 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2927,17 +2927,6 @@ restart: vfsmnt = &mnt->mnt; continue; } - /* - * Filesystems needing to implement special "root names" - * should do so with ->d_dname() - */ - if (IS_ROOT(dentry) && - (dentry->d_name.len != 1 || - dentry->d_name.name[0] != '/')) { - WARN(1, "Root dentry has weird name <%.*s>\n", - (int) dentry->d_name.len, - dentry->d_name.name); - } if (!error) error = is_mounted(vfsmnt) ? 1 : 2; break; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 7eaec88ea970..d6d1cf004123 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -716,20 +716,17 @@ bool debugfs_initialized(void) } EXPORT_SYMBOL_GPL(debugfs_initialized); - -static struct kobject *debug_kobj; - static int __init debugfs_init(void) { int retval; - debug_kobj = kobject_create_and_add("debug", kernel_kobj); - if (!debug_kobj) - return -EINVAL; + retval = sysfs_create_mount_point(kernel_kobj, "debug"); + if (retval) + return retval; retval = register_filesystem(&debug_fs_type); if (retval) - kobject_put(debug_kobj); + sysfs_remove_mount_point(kernel_kobj, "debug"); else debugfs_registered = true; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ac81f48ab2f4..2913db2a5b99 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1294,7 +1294,6 @@ static void fuse_fs_cleanup(void) } static struct kobject *fuse_kobj; -static struct kobject *connections_kobj; static int fuse_sysfs_init(void) { @@ -1306,11 +1305,9 @@ static int fuse_sysfs_init(void) goto out_err; } - connections_kobj = kobject_create_and_add("connections", fuse_kobj); - if (!connections_kobj) { - err = -ENOMEM; + err = sysfs_create_mount_point(fuse_kobj, "connections"); + if (err) goto out_fuse_unregister; - } return 0; @@ -1322,7 +1319,7 @@ static int fuse_sysfs_init(void) static void fuse_sysfs_cleanup(void) { - kobject_put(connections_kobj); + sysfs_remove_mount_point(fuse_kobj, "connections"); kobject_put(fuse_kobj); } diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index fffca9517321..2d48d28e1640 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -592,6 +592,9 @@ int kernfs_add_one(struct kernfs_node *kn) goto out_unlock; ret = -ENOENT; + if (parent->flags & KERNFS_EMPTY_DIR) + goto out_unlock; + if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent)) goto out_unlock; @@ -783,6 +786,38 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, return ERR_PTR(rc); } +/** + * kernfs_create_empty_dir - create an always empty directory + * @parent: parent in which to create a new directory + * @name: name of the new directory + * + * Returns the created node on success, ERR_PTR() value on failure. + */ +struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, + const char *name) +{ + struct kernfs_node *kn; + int rc; + + /* allocate */ + kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, KERNFS_DIR); + if (!kn) + return ERR_PTR(-ENOMEM); + + kn->flags |= KERNFS_EMPTY_DIR; + kn->dir.root = parent->dir.root; + kn->ns = NULL; + kn->priv = NULL; + + /* link in */ + rc = kernfs_add_one(kn); + if (!rc) + return kn; + + kernfs_put(kn); + return ERR_PTR(rc); +} + static struct dentry *kernfs_iop_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) @@ -1254,7 +1289,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, mutex_lock(&kernfs_mutex); error = -ENOENT; - if (!kernfs_active(kn) || !kernfs_active(new_parent)) + if (!kernfs_active(kn) || !kernfs_active(new_parent) || + (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; error = 0; diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 2da8493a380b..756dd56aaf60 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -296,6 +296,8 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) case KERNFS_DIR: inode->i_op = &kernfs_dir_iops; inode->i_fop = &kernfs_dir_fops; + if (kn->flags & KERNFS_EMPTY_DIR) + make_empty_dir_inode(inode); break; case KERNFS_FILE: inode->i_size = kn->attr.size; diff --git a/fs/libfs.c b/fs/libfs.c index 65e1feca8b98..88a4cb418756 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1108,3 +1108,98 @@ const struct inode_operations simple_symlink_inode_operations = { .readlink = generic_readlink }; EXPORT_SYMBOL(simple_symlink_inode_operations); + +/* + * Operations for a permanently empty directory. + */ +static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ + return ERR_PTR(-ENOENT); +} + +static int empty_dir_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct inode *inode = d_inode(dentry); + generic_fillattr(inode, stat); + return 0; +} + +static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr) +{ + return -EPERM; +} + +static int empty_dir_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + return -EOPNOTSUPP; +} + +static ssize_t empty_dir_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size) +{ + return -EOPNOTSUPP; +} + +static int empty_dir_removexattr(struct dentry *dentry, const char *name) +{ + return -EOPNOTSUPP; +} + +static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size) +{ + return -EOPNOTSUPP; +} + +static const struct inode_operations empty_dir_inode_operations = { + .lookup = empty_dir_lookup, + .permission = generic_permission, + .setattr = empty_dir_setattr, + .getattr = empty_dir_getattr, + .setxattr = empty_dir_setxattr, + .getxattr = empty_dir_getxattr, + .removexattr = empty_dir_removexattr, + .listxattr = empty_dir_listxattr, +}; + +static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence) +{ + /* An empty directory has two entries . and .. at offsets 0 and 1 */ + return generic_file_llseek_size(file, offset, whence, 2, 2); +} + +static int empty_dir_readdir(struct file *file, struct dir_context *ctx) +{ + dir_emit_dots(file, ctx); + return 0; +} + +static const struct file_operations empty_dir_operations = { + .llseek = empty_dir_llseek, + .read = generic_read_dir, + .iterate = empty_dir_readdir, + .fsync = noop_fsync, +}; + + +void make_empty_dir_inode(struct inode *inode) +{ + set_nlink(inode, 2); + inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + inode->i_rdev = 0; + inode->i_size = 2; + inode->i_blkbits = PAGE_SHIFT; + inode->i_blocks = 0; + + inode->i_op = &empty_dir_inode_operations; + inode->i_fop = &empty_dir_operations; +} + +bool is_empty_dir_inode(struct inode *inode) +{ + return (inode->i_fop == &empty_dir_operations) && + (inode->i_op == &empty_dir_inode_operations); +} diff --git a/fs/namespace.c b/fs/namespace.c index e99f1f4e00cd..c7cb8a526c05 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2343,6 +2343,8 @@ unlock: return err; } +static bool fs_fully_visible(struct file_system_type *fs_type, int *new_mnt_flags); + /* * create a new mount for userspace and request it to be added into the * namespace's tree @@ -2374,6 +2376,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags, flags |= MS_NODEV; mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV; } + if (type->fs_flags & FS_USERNS_VISIBLE) { + if (!fs_fully_visible(type, &mnt_flags)) + return -EPERM; + } } mnt = vfs_kern_mount(type, flags, name, data); @@ -3175,9 +3181,10 @@ bool current_chrooted(void) return chrooted; } -bool fs_fully_visible(struct file_system_type *type) +static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; + int new_flags = *new_mnt_flags; struct mount *mnt; bool visible = false; @@ -3196,16 +3203,36 @@ bool fs_fully_visible(struct file_system_type *type) if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; - /* This mount is not fully visible if there are any child mounts - * that cover anything except for empty directories. + /* Verify the mount flags are equal to or more permissive + * than the proposed new mount. + */ + if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) && + !(new_flags & MNT_READONLY)) + continue; + if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && + !(new_flags & MNT_NODEV)) + continue; + if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) && + ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) + continue; + + /* This mount is not fully visible if there are any + * locked child mounts that cover anything except for + * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; - if (!S_ISDIR(inode->i_mode)) - goto next; - if (inode->i_nlink > 2) + /* Only worry about locked mounts */ + if (!(mnt->mnt.mnt_flags & MNT_LOCKED)) + continue; + /* Is the directory permanetly empty? */ + if (!is_empty_dir_inode(inode)) goto next; } + /* Preserve the locked attributes */ + *new_mnt_flags |= mnt->mnt.mnt_flags & (MNT_LOCK_READONLY | \ + MNT_LOCK_NODEV | \ + MNT_LOCK_ATIME); visible = true; goto found; next: ; diff --git a/fs/proc/base.c b/fs/proc/base.c index 1d540b3f226f..87782e874b6a 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -491,14 +491,17 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, } #endif -#ifdef CONFIG_SCHEDSTATS +#ifdef CONFIG_SCHED_INFO /* * Provides /proc/PID/schedstat */ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - seq_printf(m, "%llu %llu %lu\n", + if (unlikely(!sched_info_on())) + seq_printf(m, "0 0 0\n"); + else + seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); @@ -2787,7 +2790,7 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif -#ifdef CONFIG_SCHEDSTATS +#ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP @@ -3135,7 +3138,7 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_STACKTRACE ONE("stack", S_IRUSR, proc_pid_stack), #endif -#ifdef CONFIG_SCHEDSTATS +#ifdef CONFIG_SCHED_INFO ONE("schedstat", S_IRUGO, proc_pid_schedstat), #endif #ifdef CONFIG_LATENCYTOP diff --git a/fs/proc/generic.c b/fs/proc/generic.c index df6327a2b865..e5dee5c3188e 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -373,6 +373,10 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, WARN(1, "create '/proc/%s' by hand\n", qstr.name); return NULL; } + if (is_empty_pde(*parent)) { + WARN(1, "attempt to add to permanently empty directory"); + return NULL; + } ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL); if (!ent) @@ -455,6 +459,25 @@ struct proc_dir_entry *proc_mkdir(const char *name, } EXPORT_SYMBOL(proc_mkdir); +struct proc_dir_entry *proc_create_mount_point(const char *name) +{ + umode_t mode = S_IFDIR | S_IRUGO | S_IXUGO; + struct proc_dir_entry *ent, *parent = NULL; + + ent = __proc_create(&parent, name, mode, 2); + if (ent) { + ent->data = NULL; + ent->proc_fops = NULL; + ent->proc_iops = NULL; + if (proc_register(parent, ent) < 0) { + kfree(ent); + parent->nlink--; + ent = NULL; + } + } + return ent; +} + struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops, diff --git a/fs/proc/inode.c b/fs/proc/inode.c index afe232b9df6e..bd95b9fdebb0 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -422,6 +422,10 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; PROC_I(inode)->pde = de; + if (is_empty_pde(de)) { + make_empty_dir_inode(inode); + return inode; + } if (de->mode) { inode->i_mode = de->mode; inode->i_uid = de->uid; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index c835b94c0cd3..aa2781095bd1 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -191,6 +191,12 @@ static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde) } extern void pde_put(struct proc_dir_entry *); +static inline bool is_empty_pde(const struct proc_dir_entry *pde) +{ + return S_ISDIR(pde->mode) && !pde->proc_iops; +} +struct proc_dir_entry *proc_create_mount_point(const char *name); + /* * inode.c */ diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index fea2561d773b..fdda62e6115e 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -19,6 +19,28 @@ static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; +/* Support for permanently empty directories */ + +struct ctl_table sysctl_mount_point[] = { + { } +}; + +static bool is_empty_dir(struct ctl_table_header *head) +{ + return head->ctl_table[0].child == sysctl_mount_point; +} + +static void set_empty_dir(struct ctl_dir *dir) +{ + dir->header.ctl_table[0].child = sysctl_mount_point; +} + +static void clear_empty_dir(struct ctl_dir *dir) + +{ + dir->header.ctl_table[0].child = NULL; +} + void proc_sys_poll_notify(struct ctl_table_poll *poll) { if (!poll) @@ -187,6 +209,17 @@ static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header) struct ctl_table *entry; int err; + /* Is this a permanently empty directory? */ + if (is_empty_dir(&dir->header)) + return -EROFS; + + /* Am I creating a permanently empty directory? */ + if (header->ctl_table == sysctl_mount_point) { + if (!RB_EMPTY_ROOT(&dir->root)) + return -EINVAL; + set_empty_dir(dir); + } + dir->header.nreg++; header->parent = dir; err = insert_links(header); @@ -202,6 +235,8 @@ fail: erase_header(header); put_links(header); fail_links: + if (header->ctl_table == sysctl_mount_point) + clear_empty_dir(dir); header->parent = NULL; drop_sysctl_table(&dir->header); return err; @@ -419,6 +454,8 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, inode->i_mode |= S_IFDIR; inode->i_op = &proc_sys_dir_operations; inode->i_fop = &proc_sys_dir_file_operations; + if (is_empty_dir(head)) + make_empty_dir_inode(inode); } out: return inode; diff --git a/fs/proc/root.c b/fs/proc/root.c index b7fa4bfe896a..68feb0f70e63 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -112,9 +112,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, ns = task_active_pid_ns(current); options = data; - if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); - /* Does the mounter have privilege over the pid namespace? */ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -159,7 +156,7 @@ static struct file_system_type proc_fs_type = { .name = "proc", .mount = proc_mount, .kill_sb = proc_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT, }; void __init proc_root_init(void) @@ -182,10 +179,10 @@ void __init proc_root_init(void) #endif proc_mkdir("fs", NULL); proc_mkdir("driver", NULL); - proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */ + proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */ #if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE) /* just give it a mountpoint */ - proc_mkdir("openprom", NULL); + proc_create_mount_point("openprom"); #endif proc_tty_init(); proc_mkdir("bus", NULL); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index dc43b5f29305..3adcc4669fac 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -461,22 +461,18 @@ static struct file_system_type pstore_fs_type = { .kill_sb = pstore_kill_sb, }; -static struct kobject *pstore_kobj; - static int __init init_pstore_fs(void) { - int err = 0; + int err; /* Create a convenient mount point for people to access pstore */ - pstore_kobj = kobject_create_and_add("pstore", fs_kobj); - if (!pstore_kobj) { - err = -ENOMEM; + err = sysfs_create_mount_point(fs_kobj, "pstore"); + if (err) goto out; - } err = register_filesystem(&pstore_fs_type); if (err < 0) - kobject_put(pstore_kobj); + sysfs_remove_mount_point(fs_kobj, "pstore"); out: return err; diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 0b45ff42f374..94374e435025 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -121,3 +121,37 @@ int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, return kernfs_rename_ns(kn, new_parent, kn->name, new_ns); } + +/** + * sysfs_create_mount_point - create an always empty directory + * @parent_kobj: kobject that will contain this always empty directory + * @name: The name of the always empty directory to add + */ +int sysfs_create_mount_point(struct kobject *parent_kobj, const char *name) +{ + struct kernfs_node *kn, *parent = parent_kobj->sd; + + kn = kernfs_create_empty_dir(parent, name); + if (IS_ERR(kn)) { + if (PTR_ERR(kn) == -EEXIST) + sysfs_warn_dup(parent, name); + return PTR_ERR(kn); + } + + return 0; +} +EXPORT_SYMBOL_GPL(sysfs_create_mount_point); + +/** + * sysfs_remove_mount_point - remove an always empty directory. + * @parent_kobj: kobject that will contain this always empty directory + * @name: The name of the always empty directory to remove + * + */ +void sysfs_remove_mount_point(struct kobject *parent_kobj, const char *name) +{ + struct kernfs_node *parent = parent_kobj->sd; + + kernfs_remove_by_name_ns(parent, name, NULL); +} +EXPORT_SYMBOL_GPL(sysfs_remove_mount_point); diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 8a49486bf30c..1c6ac6fcee9f 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -31,9 +31,6 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, bool new_sb; if (!(flags & MS_KERNMOUNT)) { - if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) - return ERR_PTR(-EPERM); - if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET)) return ERR_PTR(-EPERM); } @@ -58,7 +55,7 @@ static struct file_system_type sysfs_fs_type = { .name = "sysfs", .mount = sysfs_mount, .kill_sb = sysfs_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT, }; int __init sysfs_init(void) diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index d92bdf3b079a..a43df11a163f 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -631,14 +631,12 @@ bool tracefs_initialized(void) return tracefs_registered; } -static struct kobject *trace_kobj; - static int __init tracefs_init(void) { int retval; - trace_kobj = kobject_create_and_add("tracing", kernel_kobj); - if (!trace_kobj) + retval = sysfs_create_mount_point(kernel_kobj, "tracing"); + if (retval) return -EINVAL; retval = register_filesystem(&trace_fs_type); diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index a48d90e3bcbb..a23209b43842 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -50,10 +50,10 @@ enum wb_stat_item { */ struct bdi_writeback_congested { unsigned long state; /* WB_[a]sync_congested flags */ + atomic_t refcnt; /* nr of attached wb's and blkg */ #ifdef CONFIG_CGROUP_WRITEBACK struct backing_dev_info *bdi; /* the associated bdi */ - atomic_t refcnt; /* nr of attached wb's and blkg */ int blkcg_id; /* ID of the associated blkcg */ struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ #endif @@ -150,11 +150,12 @@ struct backing_dev_info { atomic_long_t tot_write_bandwidth; struct bdi_writeback wb; /* the root writeback info for this bdi */ - struct bdi_writeback_congested wb_congested; /* its congested state */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */ +#else + struct bdi_writeback_congested *wb_congested; #endif wait_queue_head_t wb_waitq; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0e6d4828a77a..0fe9df983ab7 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -15,6 +15,7 @@ #include <linux/writeback.h> #include <linux/blk-cgroup.h> #include <linux/backing-dev-defs.h> +#include <linux/slab.h> int __must_check bdi_init(struct backing_dev_info *bdi); void bdi_destroy(struct backing_dev_info *bdi); @@ -465,11 +466,14 @@ static inline bool inode_cgwb_enabled(struct inode *inode) static inline struct bdi_writeback_congested * wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) { - return bdi->wb.congested; + atomic_inc(&bdi->wb_congested->refcnt); + return bdi->wb_congested; } static inline void wb_congested_put(struct bdi_writeback_congested *congested) { + if (atomic_dec_and_test(&congested->refcnt)) + kfree(congested); } static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f1a84635da8..8a81fcbb0074 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1917,6 +1917,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ +#define FS_USERNS_VISIBLE 32 /* FS must already be visible */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); @@ -2004,7 +2005,6 @@ extern int vfs_ustat(dev_t, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); extern bool our_mnt(struct vfsmount *mnt); -extern bool fs_fully_visible(struct file_system_type *); extern int current_umask(void); @@ -2816,6 +2816,8 @@ extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned in extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; +extern void make_empty_dir_inode(struct inode *inode); +extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *); diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index 3343298e40e8..859d673d98c8 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -26,6 +26,7 @@ #define HWLOCK_IRQ 0x02 /* Disable interrupts, don't save state */ struct device; +struct device_node; struct hwspinlock; struct hwspinlock_device; struct hwspinlock_ops; @@ -66,6 +67,7 @@ int hwspin_lock_unregister(struct hwspinlock_device *bank); struct hwspinlock *hwspin_lock_request(void); struct hwspinlock *hwspin_lock_request_specific(unsigned int id); int hwspin_lock_free(struct hwspinlock *hwlock); +int of_hwspin_lock_get_id(struct device_node *np, int index); int hwspin_lock_get_id(struct hwspinlock *hwlock); int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int, unsigned long *); @@ -120,6 +122,11 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags) { } +static inline int of_hwspin_lock_get_id(struct device_node *np, int index) +{ + return 0; +} + static inline int hwspin_lock_get_id(struct hwspinlock *hwlock) { return 0; diff --git a/include/linux/input/touchscreen.h b/include/linux/input/touchscreen.h index 08a5ef6e8f25..eecc9ea6cd58 100644 --- a/include/linux/input/touchscreen.h +++ b/include/linux/input/touchscreen.h @@ -12,9 +12,10 @@ #include <linux/input.h> #ifdef CONFIG_OF -void touchscreen_parse_of_params(struct input_dev *dev); +void touchscreen_parse_of_params(struct input_dev *dev, bool multitouch); #else -static inline void touchscreen_parse_of_params(struct input_dev *dev) +static inline void touchscreen_parse_of_params(struct input_dev *dev, + bool multitouch) { } #endif diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 14d79131f53d..638887376e58 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -11,6 +11,20 @@ #ifndef _LINUX_IRQCHIP_H #define _LINUX_IRQCHIP_H +#include <linux/of.h> + +/* + * This macro must be used by the different irqchip drivers to declare + * the association between their DT compatible string and their + * initialization function. + * + * @name: name that must be unique accross all IRQCHIP_DECLARE of the + * same file. + * @compstr: compatible string of the irqchip driver + * @fn: initialization function + */ +#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn) + #ifdef CONFIG_IRQCHIP void irqchip_init(void); #else diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index e6b2f7db9c0c..123be25ea15a 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -45,6 +45,7 @@ enum kernfs_node_flag { KERNFS_LOCKDEP = 0x0100, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, + KERNFS_EMPTY_DIR = 0x1000, }; /* @flags for kernfs_create_root() */ @@ -286,6 +287,8 @@ void kernfs_destroy_root(struct kernfs_root *root); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, void *priv, const void *ns); +struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, + const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, loff_t size, diff --git a/include/linux/platform_data/wkup_m3.h b/include/linux/platform_data/wkup_m3.h new file mode 100644 index 000000000000..3f1d77effd71 --- /dev/null +++ b/include/linux/platform_data/wkup_m3.h @@ -0,0 +1,30 @@ +/* + * TI Wakeup M3 remote processor platform data + * + * Copyright (C) 2014-2015 Texas Instruments, Inc. + * + * Dave Gerlach <d-gerlach@ti.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_PLATFORM_DATA_WKUP_M3_H +#define _LINUX_PLATFORM_DATA_WKUP_M3_H + +struct platform_device; + +struct wkup_m3_platform_data { + const char *reset_name; + + int (*assert_reset)(struct platform_device *pdev, const char *name); + int (*deassert_reset)(struct platform_device *pdev, const char *name); +}; + +#endif /* _LINUX_PLATFORM_DATA_WKUP_M3_H */ diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 78b8a9b9d40a..9c4e1384f636 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -36,11 +36,11 @@ #define REMOTEPROC_H #include <linux/types.h> -#include <linux/klist.h> #include <linux/mutex.h> #include <linux/virtio.h> #include <linux/completion.h> #include <linux/idr.h> +#include <linux/of.h> /** * struct resource_table - firmware resource table header @@ -330,11 +330,13 @@ struct rproc; * @start: power on the device and boot it * @stop: power off the device * @kick: kick a virtqueue (virtqueue id given as a parameter) + * @da_to_va: optional platform hook to perform address translations */ struct rproc_ops { int (*start)(struct rproc *rproc); int (*stop)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); + void * (*da_to_va)(struct rproc *rproc, u64 da, int len); }; /** @@ -375,7 +377,7 @@ enum rproc_crash_type { /** * struct rproc - represents a physical remote processor device - * @node: klist node of this rproc object + * @node: list node of this rproc object * @domain: iommu domain * @name: human readable name of the rproc * @firmware: name of firmware file to be loaded @@ -407,7 +409,7 @@ enum rproc_crash_type { * @has_iommu: flag to indicate if remote processor is behind an MMU */ struct rproc { - struct klist_node node; + struct list_head node; struct iommu_domain *domain; const char *name; const char *firmware; @@ -481,6 +483,7 @@ struct rproc_vdev { u32 rsc_offset; }; +struct rproc *rproc_get_by_phandle(phandle phandle); struct rproc *rproc_alloc(struct device *dev, const char *name, const struct rproc_ops *ops, const char *firmware, int len); diff --git a/include/linux/sched.h b/include/linux/sched.h index 8aa4a251742f..ae21f1591615 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -192,8 +192,6 @@ struct task_group; #ifdef CONFIG_SCHED_DEBUG extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); -extern void -print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); #endif /* @@ -838,7 +836,7 @@ extern struct user_struct root_user; struct backing_dev_info; struct reclaim_state; -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO struct sched_info { /* cumulative counters */ unsigned long pcount; /* # of times run on this cpu */ @@ -848,7 +846,7 @@ struct sched_info { unsigned long long last_arrival,/* when we last ran on a cpu */ last_queued; /* when we were last queued to run */ }; -#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */ +#endif /* CONFIG_SCHED_INFO */ #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { @@ -1397,7 +1395,7 @@ struct task_struct { int rcu_tasks_idle_cpu; #endif /* #ifdef CONFIG_TASKS_RCU */ -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO struct sched_info sched_info; #endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 795d5fea5697..fa7bc29925c9 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -188,6 +188,9 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init(void); + +extern struct ctl_table sysctl_mount_point[]; + #else /* CONFIG_SYSCTL */ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) { diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 99382c0df17e..9f65758311a4 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -210,6 +210,10 @@ int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, int __must_check sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, const void *new_ns); +int __must_check sysfs_create_mount_point(struct kobject *parent_kobj, + const char *name); +void sysfs_remove_mount_point(struct kobject *parent_kobj, + const char *name); int __must_check sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, @@ -298,6 +302,17 @@ static inline int sysfs_move_dir_ns(struct kobject *kobj, return 0; } +static inline int sysfs_create_mount_point(struct kobject *parent_kobj, + const char *name) +{ + return 0; +} + +static inline void sysfs_remove_mount_point(struct kobject *parent_kobj, + const char *name) +{ +} + static inline int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns) diff --git a/include/linux/virtio_byteorder.h b/include/linux/virtio_byteorder.h index 51865d05b267..ce63a2c3a612 100644 --- a/include/linux/virtio_byteorder.h +++ b/include/linux/virtio_byteorder.h @@ -3,17 +3,21 @@ #include <linux/types.h> #include <uapi/linux/virtio_types.h> -/* - * Low-level memory accessors for handling virtio in modern little endian and in - * compatibility native endian format. - */ +static inline bool virtio_legacy_is_little_endian(void) +{ +#ifdef __LITTLE_ENDIAN + return true; +#else + return false; +#endif +} static inline u16 __virtio16_to_cpu(bool little_endian, __virtio16 val) { if (little_endian) return le16_to_cpu((__force __le16)val); else - return (__force u16)val; + return be16_to_cpu((__force __be16)val); } static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val) @@ -21,7 +25,7 @@ static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val) if (little_endian) return (__force __virtio16)cpu_to_le16(val); else - return (__force __virtio16)val; + return (__force __virtio16)cpu_to_be16(val); } static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val) @@ -29,7 +33,7 @@ static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val) if (little_endian) return le32_to_cpu((__force __le32)val); else - return (__force u32)val; + return be32_to_cpu((__force __be32)val); } static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val) @@ -37,7 +41,7 @@ static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val) if (little_endian) return (__force __virtio32)cpu_to_le32(val); else - return (__force __virtio32)val; + return (__force __virtio32)cpu_to_be32(val); } static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val) @@ -45,7 +49,7 @@ static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val) if (little_endian) return le64_to_cpu((__force __le64)val); else - return (__force u64)val; + return be64_to_cpu((__force __be64)val); } static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val) @@ -53,7 +57,7 @@ static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val) if (little_endian) return (__force __virtio64)cpu_to_le64(val); else - return (__force __virtio64)val; + return (__force __virtio64)cpu_to_be64(val); } #endif /* _LINUX_VIRTIO_BYTEORDER */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 1e306f727edc..e5ce8ab0b8b0 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -205,35 +205,41 @@ int virtqueue_set_affinity(struct virtqueue *vq, int cpu) return 0; } +static inline bool virtio_is_little_endian(struct virtio_device *vdev) +{ + return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || + virtio_legacy_is_little_endian(); +} + /* Memory accessors */ static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val) { - return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio16_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val) { - return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio16(virtio_is_little_endian(vdev), val); } static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val) { - return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio32_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val) { - return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio32(virtio_is_little_endian(vdev), val); } static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val) { - return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __virtio64_to_cpu(virtio_is_little_endian(vdev), val); } static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) { - return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } /* Config space accessors. */ diff --git a/include/linux/vringh.h b/include/linux/vringh.h index a3fa537e717a..bc6c28d04263 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -226,33 +226,39 @@ static inline void vringh_notify(struct vringh *vrh) vrh->notify(vrh); } +static inline bool vringh_is_little_endian(const struct vringh *vrh) +{ + return vrh->little_endian || + virtio_legacy_is_little_endian(); +} + static inline u16 vringh16_to_cpu(const struct vringh *vrh, __virtio16 val) { - return __virtio16_to_cpu(vrh->little_endian, val); + return __virtio16_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio16 cpu_to_vringh16(const struct vringh *vrh, u16 val) { - return __cpu_to_virtio16(vrh->little_endian, val); + return __cpu_to_virtio16(vringh_is_little_endian(vrh), val); } static inline u32 vringh32_to_cpu(const struct vringh *vrh, __virtio32 val) { - return __virtio32_to_cpu(vrh->little_endian, val); + return __virtio32_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio32 cpu_to_vringh32(const struct vringh *vrh, u32 val) { - return __cpu_to_virtio32(vrh->little_endian, val); + return __cpu_to_virtio32(vringh_is_little_endian(vrh), val); } static inline u64 vringh64_to_cpu(const struct vringh *vrh, __virtio64 val) { - return __virtio64_to_cpu(vrh->little_endian, val); + return __virtio64_to_cpu(vringh_is_little_endian(vrh), val); } static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val) { - return __cpu_to_virtio64(vrh->little_endian, val); + return __cpu_to_virtio64(vringh_is_little_endian(vrh), val); } #endif /* _LINUX_VRINGH_H */ diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 50ae24335444..3cb5e1d85ddd 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -50,6 +50,12 @@ #define TUNGETFILTER _IOR('T', 219, struct sock_fprog) #define TUNSETVNETLE _IOW('T', 220, int) #define TUNGETVNETLE _IOR('T', 221, int) +/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on + * little-endian hosts. Not all kernel configurations support them, but all + * configurations that support SET also support GET. + */ +#define TUNSETVNETBE _IOW('T', 222, int) +#define TUNGETVNETBE _IOR('T', 223, int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index bb6a5b4cb3c5..ab3731917bac 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -103,6 +103,20 @@ struct vhost_memory { /* Get accessor: reads index, writes value in num */ #define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state) +/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN + * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL). + * The byte order cannot be changed while the device is active: trying to do so + * returns -EBUSY. + * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is + * set. + * Not all kernel configurations support this ioctl, but all configurations that + * support SET also support GET. + */ +#define VHOST_VRING_LITTLE_ENDIAN 0 +#define VHOST_VRING_BIG_ENDIAN 1 +#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state) +#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state) + /* The following ioctls use eventfd file descriptors to signal and poll * for events. */ diff --git a/init/Kconfig b/init/Kconfig index bcc41bd19999..af09b4fb43d2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -435,6 +435,7 @@ config TASKSTATS config TASK_DELAY_ACCT bool "Enable per-task delay accounting" depends on TASKSTATS + select SCHED_INFO help Collect information on time spent by a task waiting for system resources like cpu, synchronous block I/O completion and swapping @@ -820,7 +821,7 @@ config IKCONFIG_PROC config LOG_BUF_SHIFT int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" - range 12 21 + range 12 25 default 17 depends on PRINTK help diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 9ef9fc8a774b..f89d9292eee6 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1939,8 +1939,6 @@ static struct file_system_type cgroup_fs_type = { .kill_sb = cgroup_kill_sb, }; -static struct kobject *cgroup_kobj; - /** * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task @@ -5070,13 +5068,13 @@ int __init cgroup_init(void) ss->bind(init_css_set.subsys[ssid]); } - cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj); - if (!cgroup_kobj) - return -ENOMEM; + err = sysfs_create_mount_point(fs_kobj, "cgroup"); + if (err) + return err; err = register_filesystem(&cgroup_fs_type); if (err < 0) { - kobject_put(cgroup_kobj); + sysfs_remove_mount_point(fs_kobj, "cgroup"); return err; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 552710ab19e0..78b4bad10081 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2164,7 +2164,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) set_task_cpu(p, cpu); raw_spin_unlock_irqrestore(&p->pi_lock, flags); -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 315c68e015d9..4222ec50ab88 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -142,7 +142,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) 0LL, 0L); #endif #ifdef CONFIG_NUMA_BALANCING - SEQ_printf(m, " %d", task_node(p)); + SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p)); #endif #ifdef CONFIG_CGROUP_SCHED SEQ_printf(m, " %s", task_group_path(task_group(p))); @@ -517,11 +517,21 @@ __initcall(init_sched_debug_procfs); SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) +#ifdef CONFIG_NUMA_BALANCING +void print_numa_stats(struct seq_file *m, int node, unsigned long tsf, + unsigned long tpf, unsigned long gsf, unsigned long gpf) +{ + SEQ_printf(m, "numa_faults node=%d ", node); + SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf); + SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf); +} +#endif + + static void sched_show_numa(struct task_struct *p, struct seq_file *m) { #ifdef CONFIG_NUMA_BALANCING struct mempolicy *pol; - int node, i; if (p->mm) P(mm->numa_scan_seq); @@ -533,26 +543,12 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m) mpol_get(pol); task_unlock(p); - SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0)); - - for_each_online_node(node) { - for (i = 0; i < 2; i++) { - unsigned long nr_faults = -1; - int cpu_current, home_node; - - if (p->numa_faults) - nr_faults = p->numa_faults[2*node + i]; - - cpu_current = !i ? (task_node(p) == node) : - (pol && node_isset(node, pol->v.nodes)); - - home_node = (p->numa_preferred_nid == node); - - SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n", - i, node, cpu_current, home_node, nr_faults); - } - } - + P(numa_pages_migrated); + P(numa_preferred_nid); + P(total_numa_faults); + SEQ_printf(m, "current_node=%d, numa_group_id=%d\n", + task_node(p), task_numa_group_id(p)); + show_numa_stats(p, m); mpol_put(pol); #endif } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3d57cc0ca0a6..65c8f3ebdc3c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8473,7 +8473,27 @@ void print_cfs_stats(struct seq_file *m, int cpu) print_cfs_rq(m, cpu, cfs_rq); rcu_read_unlock(); } -#endif + +#ifdef CONFIG_NUMA_BALANCING +void show_numa_stats(struct task_struct *p, struct seq_file *m) +{ + int node; + unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0; + + for_each_online_node(node) { + if (p->numa_faults) { + tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)]; + tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)]; + } + if (p->numa_group) { + gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)], + gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)]; + } + print_numa_stats(m, node, tsf, tpf, gsf, gpf); + } +} +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_SCHED_DEBUG */ __init void init_sched_fair_class(void) { diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 885889190a1f..84d48790bb6d 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1689,9 +1689,22 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq); extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq); + +#ifdef CONFIG_SCHED_DEBUG extern void print_cfs_stats(struct seq_file *m, int cpu); extern void print_rt_stats(struct seq_file *m, int cpu); extern void print_dl_stats(struct seq_file *m, int cpu); +extern void +print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); + +#ifdef CONFIG_NUMA_BALANCING +extern void +show_numa_stats(struct task_struct *p, struct seq_file *m); +extern void +print_numa_stats(struct seq_file *m, int node, unsigned long tsf, + unsigned long tpf, unsigned long gsf, unsigned long gpf); +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_SCHED_DEBUG */ extern void init_cfs_rq(struct cfs_rq *cfs_rq); extern void init_rt_rq(struct rt_rq *rt_rq); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 077ebbd5e10f..b0fbc7632de5 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -47,7 +47,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) # define schedstat_set(var, val) do { } while (0) #endif -#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +#ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { t->sched_info.last_queued = 0; @@ -156,7 +156,7 @@ sched_info_switch(struct rq *rq, #define sched_info_depart(rq, t) do { } while (0) #define sched_info_arrive(rq, next) do { } while (0) #define sched_info_switch(rq, t, next) do { } while (0) -#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ +#endif /* CONFIG_SCHED_INFO */ /* * The following are functions that support scheduler-internal time accounting. diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 812fcc3fd390..19b62b522158 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1538,12 +1538,6 @@ static struct ctl_table vm_table[] = { { } }; -#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) -static struct ctl_table binfmt_misc_table[] = { - { } -}; -#endif - static struct ctl_table fs_table[] = { { .procname = "inode-nr", @@ -1697,7 +1691,7 @@ static struct ctl_table fs_table[] = { { .procname = "binfmt_misc", .mode = 0555, - .child = binfmt_misc_table, + .child = sysctl_mount_point, }, #endif { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index b908048f8d6a..e2894b23efb6 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -841,9 +841,14 @@ config SCHED_DEBUG that can help debug the scheduler. The runtime overhead of this option is minimal. +config SCHED_INFO + bool + default n + config SCHEDSTATS bool "Collect scheduler statistics" depends on DEBUG_KERNEL && PROC_FS + select SCHED_INFO help If you say Y here, additional code will be inserted into the scheduler and related routines to collect statistics about diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7756da31b02b..dac5bf59309d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -287,7 +287,7 @@ void wb_wakeup_delayed(struct bdi_writeback *wb) #define INIT_BW (100 << (20 - PAGE_SHIFT)) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, - gfp_t gfp) + int blkcg_id, gfp_t gfp) { int i, err; @@ -311,21 +311,29 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); + wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp); + if (!wb->congested) + return -ENOMEM; + err = fprop_local_init_percpu(&wb->completions, gfp); if (err) - return err; + goto out_put_cong; for (i = 0; i < NR_WB_STAT_ITEMS; i++) { err = percpu_counter_init(&wb->stat[i], 0, gfp); - if (err) { - while (--i) - percpu_counter_destroy(&wb->stat[i]); - fprop_local_destroy_percpu(&wb->completions); - return err; - } + if (err) + goto out_destroy_stat; } return 0; + +out_destroy_stat: + while (--i) + percpu_counter_destroy(&wb->stat[i]); + fprop_local_destroy_percpu(&wb->completions); +out_put_cong: + wb_congested_put(wb->congested); + return err; } /* @@ -361,6 +369,7 @@ static void wb_exit(struct bdi_writeback *wb) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); + wb_congested_put(wb->congested); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -392,9 +401,6 @@ wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) struct bdi_writeback_congested *new_congested = NULL, *congested; struct rb_node **node, *parent; unsigned long flags; - - if (blkcg_id == 1) - return &bdi->wb_congested; retry: spin_lock_irqsave(&cgwb_lock, flags); @@ -419,7 +425,6 @@ retry: new_congested = NULL; rb_link_node(&congested->rb_node, parent, node); rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree); - atomic_inc(&bdi->usage_cnt); goto found; } @@ -450,24 +455,23 @@ found: */ void wb_congested_put(struct bdi_writeback_congested *congested) { - struct backing_dev_info *bdi = congested->bdi; unsigned long flags; - if (congested->blkcg_id == 1) - return; - local_irq_save(flags); if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) { local_irq_restore(flags); return; } - rb_erase(&congested->rb_node, &congested->bdi->cgwb_congested_tree); + /* bdi might already have been destroyed leaving @congested unlinked */ + if (congested->bdi) { + rb_erase(&congested->rb_node, + &congested->bdi->cgwb_congested_tree); + congested->bdi = NULL; + } + spin_unlock_irqrestore(&cgwb_lock, flags); kfree(congested); - - if (atomic_dec_and_test(&bdi->usage_cnt)) - wake_up_all(&cgwb_release_wait); } static void cgwb_release_workfn(struct work_struct *work) @@ -480,7 +484,6 @@ static void cgwb_release_workfn(struct work_struct *work) css_put(wb->memcg_css); css_put(wb->blkcg_css); - wb_congested_put(wb->congested); fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); @@ -541,7 +544,7 @@ static int cgwb_create(struct backing_dev_info *bdi, if (!wb) return -ENOMEM; - ret = wb_init(wb, bdi, gfp); + ret = wb_init(wb, bdi, blkcg_css->id, gfp); if (ret) goto err_free; @@ -553,12 +556,6 @@ static int cgwb_create(struct backing_dev_info *bdi, if (ret) goto err_ref_exit; - wb->congested = wb_congested_get_create(bdi, blkcg_css->id, gfp); - if (!wb->congested) { - ret = -ENOMEM; - goto err_fprop_exit; - } - wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; INIT_WORK(&wb->release_work, cgwb_release_workfn); @@ -588,12 +585,10 @@ static int cgwb_create(struct backing_dev_info *bdi, if (ret) { if (ret == -EEXIST) ret = 0; - goto err_put_congested; + goto err_fprop_exit; } goto out_put; -err_put_congested: - wb_congested_put(wb->congested); err_fprop_exit: fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: @@ -662,26 +657,41 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, return wb; } -static void cgwb_bdi_init(struct backing_dev_info *bdi) +static int cgwb_bdi_init(struct backing_dev_info *bdi) { - bdi->wb.memcg_css = mem_cgroup_root_css; - bdi->wb.blkcg_css = blkcg_root_css; - bdi->wb_congested.blkcg_id = 1; + int ret; + INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); bdi->cgwb_congested_tree = RB_ROOT; atomic_set(&bdi->usage_cnt, 1); + + ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); + if (!ret) { + bdi->wb.memcg_css = mem_cgroup_root_css; + bdi->wb.blkcg_css = blkcg_root_css; + } + return ret; } static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { struct radix_tree_iter iter; + struct bdi_writeback_congested *congested, *congested_n; void **slot; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); + radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); + + rbtree_postorder_for_each_entry_safe(congested, congested_n, + &bdi->cgwb_congested_tree, rb_node) { + rb_erase(&congested->rb_node, &bdi->cgwb_congested_tree); + congested->bdi = NULL; /* mark @congested unlinked */ + } + spin_unlock_irq(&cgwb_lock); /* @@ -732,15 +742,28 @@ void wb_blkcg_offline(struct blkcg *blkcg) #else /* CONFIG_CGROUP_WRITEBACK */ -static void cgwb_bdi_init(struct backing_dev_info *bdi) { } +static int cgwb_bdi_init(struct backing_dev_info *bdi) +{ + int err; + + bdi->wb_congested = kzalloc(sizeof(*bdi->wb_congested), GFP_KERNEL); + if (!bdi->wb_congested) + return -ENOMEM; + + err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); + if (err) { + kfree(bdi->wb_congested); + return err; + } + return 0; +} + static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { } #endif /* CONFIG_CGROUP_WRITEBACK */ int bdi_init(struct backing_dev_info *bdi) { - int err; - bdi->dev = NULL; bdi->min_ratio = 0; @@ -749,15 +772,7 @@ int bdi_init(struct backing_dev_info *bdi) INIT_LIST_HEAD(&bdi->bdi_list); init_waitqueue_head(&bdi->wb_waitq); - err = wb_init(&bdi->wb, bdi, GFP_KERNEL); - if (err) - return err; - - bdi->wb_congested.state = 0; - bdi->wb.congested = &bdi->wb_congested; - - cgwb_bdi_init(bdi); - return 0; + return cgwb_bdi_init(bdi); } EXPORT_SYMBOL(bdi_init); diff --git a/security/inode.c b/security/inode.c index 91503b79c5f8..0e37e4fba8fa 100644 --- a/security/inode.c +++ b/security/inode.c @@ -215,19 +215,17 @@ void securityfs_remove(struct dentry *dentry) } EXPORT_SYMBOL_GPL(securityfs_remove); -static struct kobject *security_kobj; - static int __init securityfs_init(void) { int retval; - security_kobj = kobject_create_and_add("security", kernel_kobj); - if (!security_kobj) - return -EINVAL; + retval = sysfs_create_mount_point(kernel_kobj, "security"); + if (retval) + return retval; retval = register_filesystem(&fs_type); if (retval) - kobject_put(security_kobj); + sysfs_remove_mount_point(kernel_kobj, "security"); return retval; } diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index d2787cca1fcb..3d2201413028 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1853,7 +1853,6 @@ static struct file_system_type sel_fs_type = { }; struct vfsmount *selinuxfs_mount; -static struct kobject *selinuxfs_kobj; static int __init init_sel_fs(void) { @@ -1862,13 +1861,13 @@ static int __init init_sel_fs(void) if (!selinux_enabled) return 0; - selinuxfs_kobj = kobject_create_and_add("selinux", fs_kobj); - if (!selinuxfs_kobj) - return -ENOMEM; + err = sysfs_create_mount_point(fs_kobj, "selinux"); + if (err) + return err; err = register_filesystem(&sel_fs_type); if (err) { - kobject_put(selinuxfs_kobj); + sysfs_remove_mount_point(fs_kobj, "selinux"); return err; } @@ -1887,7 +1886,7 @@ __initcall(init_sel_fs); #ifdef CONFIG_SECURITY_SELINUX_DISABLE void exit_sel_fs(void) { - kobject_put(selinuxfs_kobj); + sysfs_remove_mount_point(fs_kobj, "selinux"); kern_unmount(selinuxfs_mount); unregister_filesystem(&sel_fs_type); } diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index 5e0a64ebdf23..2716d02119f3 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -2314,16 +2314,16 @@ static const struct file_operations smk_revoke_subj_ops = { .llseek = generic_file_llseek, }; -static struct kset *smackfs_kset; /** * smk_init_sysfs - initialize /sys/fs/smackfs * */ static int smk_init_sysfs(void) { - smackfs_kset = kset_create_and_add("smackfs", NULL, fs_kobj); - if (!smackfs_kset) - return -ENOMEM; + int err; + err = sysfs_create_mount_point(fs_kobj, "smackfs"); + if (err) + return err; return 0; } diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index a51244a8022f..faca2bf6a430 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -25,7 +25,7 @@ build-dir := $(srctree)/tools/build include $(build-dir)/Build.include # do not force detected configuration --include .config-detected +-include $(OUTPUT).config-detected # Init all relevant variables used in build files so # 1) they have correct type diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 04e150d83e7d..47469abdcc1c 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -144,6 +144,10 @@ is a useful mode to detect imbalance between physical cores. To enable this mod use --per-core in addition to -a. (system-wide). The output includes the core number and the number of online logical processors on that physical processor. +--per-thread:: +Aggregate counts per monitored threads, when monitoring threads (-t option) +or processes (-p option). + -D msecs:: --delay msecs:: After starting the program, wait msecs before measuring. This is useful to diff --git a/tools/perf/Makefile b/tools/perf/Makefile index d31a7bbd7cee..480546d5f13b 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -83,8 +83,8 @@ build-test: # # All other targets get passed through: # -%: +%: FORCE $(print_msg) $(make) -.PHONY: tags TAGS +.PHONY: tags TAGS FORCE Makefile diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1af0cfeb7a57..7a4b549214e3 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -110,7 +110,7 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD $(Q)touch $(OUTPUT)PERF-VERSION-FILE CC = $(CROSS_COMPILE)gcc -LD = $(CROSS_COMPILE)ld +LD ?= $(CROSS_COMPILE)ld AR = $(CROSS_COMPILE)ar PKG_CONFIG = $(CROSS_COMPILE)pkg-config @@ -545,7 +545,7 @@ config-clean: clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete - $(Q)$(RM) .config-detected + $(Q)$(RM) $(OUTPUT).config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 52ec66b23607..01b06492bd6a 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -630,12 +630,13 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) if (inject.session == NULL) return -1; - if (symbol__init(&inject.session->header.env) < 0) - return -1; + ret = symbol__init(&inject.session->header.env); + if (ret < 0) + goto out_delete; ret = __cmd_inject(&inject); +out_delete: perf_session__delete(inject.session); - return ret; } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 950f296dfcf7..23b1faaaa4cc 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1916,7 +1916,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (!perf_evlist__find_tracepoint_by_name(session->evlist, "kmem:kmalloc")) { pr_err(errmsg, "slab", "slab"); - return -1; + goto out_delete; } } @@ -1927,7 +1927,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) "kmem:mm_page_alloc"); if (evsel == NULL) { pr_err(errmsg, "page", "page"); - return -1; + goto out_delete; } kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent); diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 74878cd75078..fc1cffb1b7a2 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1061,8 +1061,10 @@ static int read_events(struct perf_kvm_stat *kvm) symbol__init(&kvm->session->header.env); - if (!perf_session__has_traces(kvm->session, "kvm record")) - return -EINVAL; + if (!perf_session__has_traces(kvm->session, "kvm record")) { + ret = -EINVAL; + goto out_delete; + } /* * Do not use 'isa' recorded in kvm_exit tracepoint since it is not @@ -1070,9 +1072,13 @@ static int read_events(struct perf_kvm_stat *kvm) */ ret = cpu_isa_config(kvm); if (ret < 0) - return ret; + goto out_delete; - return perf_session__process_events(kvm->session); + ret = perf_session__process_events(kvm->session); + +out_delete: + perf_session__delete(kvm->session); + return ret; } static int parse_target_str(struct perf_kvm_stat *kvm) diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index da2ec06f0742..80170aace5d4 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -124,7 +124,6 @@ static int report_raw_events(struct perf_mem *mem) .mode = PERF_DATA_MODE_READ, .force = mem->force, }; - int err = -EINVAL; int ret; struct perf_session *session = perf_session__new(&file, false, &mem->tool); @@ -135,24 +134,21 @@ static int report_raw_events(struct perf_mem *mem) if (mem->cpu_list) { ret = perf_session__cpu_bitmap(session, mem->cpu_list, mem->cpu_bitmap); - if (ret) + if (ret < 0) goto out_delete; } - if (symbol__init(&session->header.env) < 0) - return -1; + ret = symbol__init(&session->header.env); + if (ret < 0) + goto out_delete; printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n"); - err = perf_session__process_events(session); - if (err) - return err; - - return 0; + ret = perf_session__process_events(session); out_delete: perf_session__delete(session); - return err; + return ret; } static int report_events(int argc, const char **argv, struct perf_mem *mem) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 32626ea3e227..95a47719aec3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -742,6 +742,17 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) argc = parse_options(argc, argv, options, report_usage, 0); + if (symbol_conf.vmlinux_name && + access(symbol_conf.vmlinux_name, R_OK)) { + pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); + return -EINVAL; + } + if (symbol_conf.kallsyms_name && + access(symbol_conf.kallsyms_name, R_OK)) { + pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name); + return -EINVAL; + } + if (report.use_stdio) use_browser = 0; else if (report.use_tui) @@ -828,8 +839,10 @@ repeat: if (report.header || report.header_only) { perf_session__fprintf_info(session, stdout, report.show_full_info); - if (report.header_only) - return 0; + if (report.header_only) { + ret = 0; + goto error; + } } else if (use_browser == 0) { fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n", stdout); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index fcf99bdeb19e..37e301a32f43 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -67,10 +67,7 @@ #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" -static void print_stat(int argc, const char **argv); -static void print_counter_aggr(struct perf_evsel *counter, char *prefix); -static void print_counter(struct perf_evsel *counter, char *prefix); -static void print_aggr(char *prefix); +static void print_counters(struct timespec *ts, int argc, const char **argv); /* Default events used for perf stat -T */ static const char *transaction_attrs = { @@ -141,96 +138,9 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a, } } -static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +static void perf_stat__reset_stats(void) { - return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus; -} - -static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) -{ - return perf_evsel__cpus(evsel)->nr; -} - -static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) -{ - int i; - struct perf_stat *ps = evsel->priv; - - for (i = 0; i < 3; i++) - init_stats(&ps->res_stats[i]); - - perf_stat_evsel_id_init(evsel); -} - -static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) -{ - evsel->priv = zalloc(sizeof(struct perf_stat)); - if (evsel->priv == NULL) - return -ENOMEM; - perf_evsel__reset_stat_priv(evsel); - return 0; -} - -static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) -{ - zfree(&evsel->priv); -} - -static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel) -{ - struct perf_counts *counts; - - counts = perf_counts__new(perf_evsel__nr_cpus(evsel)); - if (counts) - evsel->prev_raw_counts = counts; - - return counts ? 0 : -ENOMEM; -} - -static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) -{ - perf_counts__delete(evsel->prev_raw_counts); - evsel->prev_raw_counts = NULL; -} - -static void perf_evlist__free_stats(struct perf_evlist *evlist) -{ - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - perf_evsel__free_stat_priv(evsel); - perf_evsel__free_counts(evsel); - perf_evsel__free_prev_raw_counts(evsel); - } -} - -static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) -{ - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - if (perf_evsel__alloc_stat_priv(evsel) < 0 || - perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 || - (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0)) - goto out_free; - } - - return 0; - -out_free: - perf_evlist__free_stats(evlist); - return -1; -} - -static void perf_stat__reset_stats(struct perf_evlist *evlist) -{ - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - perf_evsel__reset_stat_priv(evsel); - perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel)); - } - + perf_evlist__reset_stats(evsel_list); perf_stat__reset_shadow_stats(); } @@ -304,8 +214,9 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip) return 0; } -static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, - struct perf_counts_values *count) +static int +process_counter_values(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count) { struct perf_counts_values *aggr = &evsel->counts->aggr; static struct perf_counts_values zero; @@ -320,13 +231,13 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, count = &zero; switch (aggr_mode) { + case AGGR_THREAD: case AGGR_CORE: case AGGR_SOCKET: case AGGR_NONE: if (!evsel->snapshot) - perf_evsel__compute_deltas(evsel, cpu, count); + perf_evsel__compute_deltas(evsel, cpu, thread, count); perf_counts_values__scale(count, scale, NULL); - evsel->counts->cpu[cpu] = *count; if (aggr_mode == AGGR_NONE) perf_stat__update_shadow_stats(evsel, count->values, cpu); break; @@ -343,26 +254,48 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, return 0; } -static int read_counter(struct perf_evsel *counter); +static int process_counter_maps(struct perf_evsel *counter) +{ + int nthreads = thread_map__nr(counter->threads); + int ncpus = perf_evsel__nr_cpus(counter); + int cpu, thread; -/* - * Read out the results of a single counter: - * aggregate counts across CPUs in system-wide mode - */ -static int read_counter_aggr(struct perf_evsel *counter) + if (counter->system_wide) + nthreads = 1; + + for (thread = 0; thread < nthreads; thread++) { + for (cpu = 0; cpu < ncpus; cpu++) { + if (process_counter_values(counter, cpu, thread, + perf_counts(counter->counts, cpu, thread))) + return -1; + } + } + + return 0; +} + +static int process_counter(struct perf_evsel *counter) { struct perf_counts_values *aggr = &counter->counts->aggr; struct perf_stat *ps = counter->priv; u64 *count = counter->counts->aggr.values; - int i; + int i, ret; aggr->val = aggr->ena = aggr->run = 0; + init_stats(ps->res_stats); - if (read_counter(counter)) - return -1; + if (counter->per_pkg) + zero_per_pkg(counter); + + ret = process_counter_maps(counter); + if (ret) + return ret; + + if (aggr_mode != AGGR_GLOBAL) + return 0; if (!counter->snapshot) - perf_evsel__compute_deltas(counter, -1, aggr); + perf_evsel__compute_deltas(counter, -1, -1, aggr); perf_counts_values__scale(aggr, scale, &counter->counts->scaled); for (i = 0; i < 3; i++) @@ -397,12 +330,12 @@ static int read_counter(struct perf_evsel *counter) if (counter->system_wide) nthreads = 1; - if (counter->per_pkg) - zero_per_pkg(counter); - for (thread = 0; thread < nthreads; thread++) { for (cpu = 0; cpu < ncpus; cpu++) { - if (perf_evsel__read_cb(counter, cpu, thread, read_cb)) + struct perf_counts_values *count; + + count = perf_counts(counter->counts, cpu, thread); + if (perf_evsel__read(counter, cpu, thread, count)) return -1; } } @@ -410,68 +343,34 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void print_interval(void) +static void read_counters(bool close) { - static int num_print_interval; struct perf_evsel *counter; - struct perf_stat *ps; - struct timespec ts, rs; - char prefix[64]; - if (aggr_mode == AGGR_GLOBAL) { - evlist__for_each(evsel_list, counter) { - ps = counter->priv; - memset(ps->res_stats, 0, sizeof(ps->res_stats)); - read_counter_aggr(counter); - } - } else { - evlist__for_each(evsel_list, counter) { - ps = counter->priv; - memset(ps->res_stats, 0, sizeof(ps->res_stats)); - read_counter(counter); - } - } + evlist__for_each(evsel_list, counter) { + if (read_counter(counter)) + pr_warning("failed to read counter %s\n", counter->name); - clock_gettime(CLOCK_MONOTONIC, &ts); - diff_timespec(&rs, &ts, &ref_time); - sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep); + if (process_counter(counter)) + pr_warning("failed to process counter %s\n", counter->name); - if (num_print_interval == 0 && !csv_output) { - switch (aggr_mode) { - case AGGR_SOCKET: - fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit"); - break; - case AGGR_CORE: - fprintf(output, "# time core cpus counts %*s events\n", unit_width, "unit"); - break; - case AGGR_NONE: - fprintf(output, "# time CPU counts %*s events\n", unit_width, "unit"); - break; - case AGGR_GLOBAL: - default: - fprintf(output, "# time counts %*s events\n", unit_width, "unit"); + if (close) { + perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), + thread_map__nr(evsel_list->threads)); } } +} - if (++num_print_interval == 25) - num_print_interval = 0; +static void process_interval(void) +{ + struct timespec ts, rs; - switch (aggr_mode) { - case AGGR_CORE: - case AGGR_SOCKET: - print_aggr(prefix); - break; - case AGGR_NONE: - evlist__for_each(evsel_list, counter) - print_counter(counter, prefix); - break; - case AGGR_GLOBAL: - default: - evlist__for_each(evsel_list, counter) - print_counter_aggr(counter, prefix); - } + read_counters(false); - fflush(output); + clock_gettime(CLOCK_MONOTONIC, &ts); + diff_timespec(&rs, &ts, &ref_time); + + print_counters(&rs, 0, NULL); } static void handle_initial_delay(void) @@ -586,7 +485,7 @@ static int __run_perf_stat(int argc, const char **argv) if (interval) { while (!waitpid(child_pid, &status, WNOHANG)) { nanosleep(&ts, NULL); - print_interval(); + process_interval(); } } wait(&status); @@ -604,7 +503,7 @@ static int __run_perf_stat(int argc, const char **argv) while (!done) { nanosleep(&ts, NULL); if (interval) - print_interval(); + process_interval(); } } @@ -612,18 +511,7 @@ static int __run_perf_stat(int argc, const char **argv) update_stats(&walltime_nsecs_stats, t1 - t0); - if (aggr_mode == AGGR_GLOBAL) { - evlist__for_each(evsel_list, counter) { - read_counter_aggr(counter); - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), - thread_map__nr(evsel_list->threads)); - } - } else { - evlist__for_each(evsel_list, counter) { - read_counter(counter); - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1); - } - } + read_counters(true); return WEXITSTATUS(status); } @@ -715,6 +603,14 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr) csv_output ? 0 : -4, perf_evsel__cpus(evsel)->map[id], csv_sep); break; + case AGGR_THREAD: + fprintf(output, "%*s-%*d%s", + csv_output ? 0 : 16, + thread_map__comm(evsel->threads, id), + csv_output ? 0 : -8, + thread_map__pid(evsel->threads, id), + csv_sep); + break; case AGGR_GLOBAL: default: break; @@ -815,9 +711,9 @@ static void print_aggr(char *prefix) s2 = aggr_get_id(evsel_list->cpus, cpu2); if (s2 != id) continue; - val += counter->counts->cpu[cpu].val; - ena += counter->counts->cpu[cpu].ena; - run += counter->counts->cpu[cpu].run; + val += perf_counts(counter->counts, cpu, 0)->val; + ena += perf_counts(counter->counts, cpu, 0)->ena; + run += perf_counts(counter->counts, cpu, 0)->run; nr++; } if (prefix) @@ -863,6 +759,40 @@ static void print_aggr(char *prefix) } } +static void print_aggr_thread(struct perf_evsel *counter, char *prefix) +{ + int nthreads = thread_map__nr(counter->threads); + int ncpus = cpu_map__nr(counter->cpus); + int cpu, thread; + double uval; + + for (thread = 0; thread < nthreads; thread++) { + u64 ena = 0, run = 0, val = 0; + + for (cpu = 0; cpu < ncpus; cpu++) { + val += perf_counts(counter->counts, cpu, thread)->val; + ena += perf_counts(counter->counts, cpu, thread)->ena; + run += perf_counts(counter->counts, cpu, thread)->run; + } + + if (prefix) + fprintf(output, "%s", prefix); + + uval = val * counter->scale; + + if (nsec_counter(counter)) + nsec_printout(thread, 0, counter, uval); + else + abs_printout(thread, 0, counter, uval); + + if (!csv_output) + print_noise(counter, 1.0); + + print_running(run, ena); + fputc('\n', output); + } +} + /* * Print out the results of a single counter: * aggregated counts in system-wide mode @@ -925,9 +855,9 @@ static void print_counter(struct perf_evsel *counter, char *prefix) int cpu; for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - val = counter->counts->cpu[cpu].val; - ena = counter->counts->cpu[cpu].ena; - run = counter->counts->cpu[cpu].run; + val = perf_counts(counter->counts, cpu, 0)->val; + ena = perf_counts(counter->counts, cpu, 0)->ena; + run = perf_counts(counter->counts, cpu, 0)->run; if (prefix) fprintf(output, "%s", prefix); @@ -972,9 +902,38 @@ static void print_counter(struct perf_evsel *counter, char *prefix) } } -static void print_stat(int argc, const char **argv) +static void print_interval(char *prefix, struct timespec *ts) +{ + static int num_print_interval; + + sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep); + + if (num_print_interval == 0 && !csv_output) { + switch (aggr_mode) { + case AGGR_SOCKET: + fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit"); + break; + case AGGR_CORE: + fprintf(output, "# time core cpus counts %*s events\n", unit_width, "unit"); + break; + case AGGR_NONE: + fprintf(output, "# time CPU counts %*s events\n", unit_width, "unit"); + break; + case AGGR_THREAD: + fprintf(output, "# time comm-pid counts %*s events\n", unit_width, "unit"); + break; + case AGGR_GLOBAL: + default: + fprintf(output, "# time counts %*s events\n", unit_width, "unit"); + } + } + + if (++num_print_interval == 25) + num_print_interval = 0; +} + +static void print_header(int argc, const char **argv) { - struct perf_evsel *counter; int i; fflush(stdout); @@ -1000,36 +959,57 @@ static void print_stat(int argc, const char **argv) fprintf(output, " (%d runs)", run_count); fprintf(output, ":\n\n"); } +} + +static void print_footer(void) +{ + if (!null_run) + fprintf(output, "\n"); + fprintf(output, " %17.9f seconds time elapsed", + avg_stats(&walltime_nsecs_stats)/1e9); + if (run_count > 1) { + fprintf(output, " "); + print_noise_pct(stddev_stats(&walltime_nsecs_stats), + avg_stats(&walltime_nsecs_stats)); + } + fprintf(output, "\n\n"); +} + +static void print_counters(struct timespec *ts, int argc, const char **argv) +{ + struct perf_evsel *counter; + char buf[64], *prefix = NULL; + + if (interval) + print_interval(prefix = buf, ts); + else + print_header(argc, argv); switch (aggr_mode) { case AGGR_CORE: case AGGR_SOCKET: - print_aggr(NULL); + print_aggr(prefix); + break; + case AGGR_THREAD: + evlist__for_each(evsel_list, counter) + print_aggr_thread(counter, prefix); break; case AGGR_GLOBAL: evlist__for_each(evsel_list, counter) - print_counter_aggr(counter, NULL); + print_counter_aggr(counter, prefix); break; case AGGR_NONE: evlist__for_each(evsel_list, counter) - print_counter(counter, NULL); + print_counter(counter, prefix); break; default: break; } - if (!csv_output) { - if (!null_run) - fprintf(output, "\n"); - fprintf(output, " %17.9f seconds time elapsed", - avg_stats(&walltime_nsecs_stats)/1e9); - if (run_count > 1) { - fprintf(output, " "); - print_noise_pct(stddev_stats(&walltime_nsecs_stats), - avg_stats(&walltime_nsecs_stats)); - } - fprintf(output, "\n\n"); - } + if (!interval && !csv_output) + print_footer(); + + fflush(output); } static volatile int signr = -1; @@ -1101,6 +1081,7 @@ static int perf_stat_init_aggr_mode(void) break; case AGGR_NONE: case AGGR_GLOBAL: + case AGGR_THREAD: default: break; } @@ -1325,6 +1306,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-core", &aggr_mode, "aggregate counts per physical processor core", AGGR_CORE), + OPT_SET_UINT(0, "per-thread", &aggr_mode, + "aggregate counts per thread", AGGR_THREAD), OPT_UINTEGER('D', "delay", &initial_delay, "ms to wait before starting measurement after program start"), OPT_END() @@ -1416,8 +1399,19 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) run_count = 1; } - /* no_aggr, cgroup are for system-wide only */ - if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) && + if ((aggr_mode == AGGR_THREAD) && !target__has_task(&target)) { + fprintf(stderr, "The --per-thread option is only available " + "when monitoring via -p -t options.\n"); + parse_options_usage(NULL, options, "p", 1); + parse_options_usage(NULL, options, "t", 1); + goto out; + } + + /* + * no_aggr, cgroup are for system-wide only + * --per-thread is aggregated per thread, we dont mix it with cpu mode + */ + if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_THREAD) || nr_cgroups) && !target__has_cpu(&target)) { fprintf(stderr, "both cgroup and no-aggregation " "modes only available in system-wide mode\n"); @@ -1445,6 +1439,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) } goto out; } + + /* + * Initialize thread_map with comm names, + * so we could print it out on output. + */ + if (aggr_mode == AGGR_THREAD) + thread_map__read_comms(evsel_list->threads); + if (interval && interval < 100) { pr_err("print interval must be >= 100ms\n"); parse_options_usage(stat_usage, options, "I", 1); @@ -1478,13 +1480,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) status = run_perf_stat(argc, argv); if (forever && status != -1) { - print_stat(argc, argv); - perf_stat__reset_stats(evsel_list); + print_counters(NULL, argc, argv); + perf_stat__reset_stats(); } } if (!forever && status != -1 && !interval) - print_stat(argc, argv); + print_counters(NULL, argc, argv); perf_evlist__free_stats(evsel_list); out: diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 619a8696fda7..ecf319728f25 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -586,27 +586,9 @@ static void *display_thread_tui(void *arg) hists->uid_filter_str = top->record_opts.target.uid_str; } - while (true) { - int key = perf_evlist__tui_browse_hists(top->evlist, help, &hbt, - top->min_percent, - &top->session->header.env); - - if (key != 'f') - break; - - perf_evlist__toggle_enable(top->evlist); - /* - * No need to refresh, resort/decay histogram entries - * if we are not collecting samples: - */ - if (top->evlist->enabled) { - hbt.refresh = top->delay_secs; - help = "Press 'f' to disable the events or 'h' to see other hotkeys"; - } else { - help = "Press 'f' again to re-enable the events"; - hbt.refresh = 0; - } - } + perf_evlist__tui_browse_hists(top->evlist, help, &hbt, + top->min_percent, + &top->session->header.env); done = 1; return NULL; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index de5d277d1ad7..39ad4d0ca884 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1617,6 +1617,34 @@ static int trace__read_syscall_info(struct trace *trace, int id) return syscall__set_arg_fmts(sc); } +static int trace__validate_ev_qualifier(struct trace *trace) +{ + int err = 0; + struct str_node *pos; + + strlist__for_each(pos, trace->ev_qualifier) { + const char *sc = pos->s; + + if (audit_name_to_syscall(sc, trace->audit.machine) < 0) { + if (err == 0) { + fputs("Error:\tInvalid syscall ", trace->output); + err = -EINVAL; + } else { + fputs(", ", trace->output); + } + + fputs(sc, trace->output); + } + } + + if (err < 0) { + fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'" + "\nHint:\tand: 'man syscalls'\n", trace->output); + } + + return err; +} + /* * args is to be interpreted as a series of longs but we need to handle * 8-byte unaligned accesses. args points to raw_data within the event @@ -2325,7 +2353,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) */ if (trace->filter_pids.nr > 0) err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries); - else if (evlist->threads->map[0] == -1) + else if (thread_map__pid(evlist->threads, 0) == -1) err = perf_evlist__set_filter_pid(evlist, getpid()); if (err < 0) { @@ -2343,7 +2371,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (forks) perf_evlist__start_workload(evlist); - trace->multiple_threads = evlist->threads->map[0] == -1 || + trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 || evlist->threads->nr > 1 || perf_evlist__first(evlist)->attr.inherit; again: @@ -2862,6 +2890,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) err = -ENOMEM; goto out_close; } + + err = trace__validate_ev_qualifier(&trace); + if (err) + goto out_close; } err = target__validate(&trace.opts.target); diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 317001c94660..094ddaee104c 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -11,9 +11,9 @@ ifneq ($(obj-perf),) obj-perf := $(abspath $(obj-perf))/ endif -$(shell echo -n > .config-detected) -detected = $(shell echo "$(1)=y" >> .config-detected) -detected_var = $(shell echo "$(1)=$($(1))" >> .config-detected) +$(shell echo -n > $(OUTPUT).config-detected) +detected = $(shell echo "$(1)=y" >> $(OUTPUT).config-detected) +detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected) CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index ee41e705b2eb..d20d6e6ab65b 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -31,6 +31,7 @@ perf-y += code-reading.o perf-y += sample-parsing.o perf-y += parse-no-sample-id-all.o perf-y += kmod-path.o +perf-y += thread-map.o perf-$(CONFIG_X86) += perf-time-to-tsc.o diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 87b9961646e4..c1dde733c3a6 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -171,6 +171,10 @@ static struct test { .func = test__kmod_path__parse, }, { + .desc = "Test thread map", + .func = test__thread_map, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 22f8a00446e1..39c784a100a9 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -545,8 +545,8 @@ out_err: if (evlist) { perf_evlist__delete(evlist); } else { - cpu_map__delete(cpus); - thread_map__delete(threads); + cpu_map__put(cpus); + thread_map__put(threads); } machines__destroy_kernel_maps(&machines); machine__delete_threads(machine); diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 5b171d1e338b..4d4b9837b630 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -144,8 +144,8 @@ out_err: perf_evlist__disable(evlist); perf_evlist__delete(evlist); } else { - cpu_map__delete(cpus); - thread_map__delete(threads); + cpu_map__put(cpus); + thread_map__put(threads); } return err; diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 65280d28662e..729112f4cfaa 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -1,5 +1,16 @@ +ifndef MK +ifeq ($(MAKECMDGOALS),) +# no target specified, trigger the whole suite +all: + @echo "Testing Makefile"; $(MAKE) -sf tests/make MK=Makefile + @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf +else +# run only specific test over 'Makefile' +%: + @echo "Testing Makefile"; $(MAKE) -sf tests/make MK=Makefile $@ +endif +else PERF := . -MK := Makefile include config/Makefile.arch @@ -47,6 +58,7 @@ make_install_man := install-man make_install_html := install-html make_install_info := install-info make_install_pdf := install-pdf +make_install_prefix := install prefix=/tmp/krava make_static := LDFLAGS=-static # all the NO_* variable combined @@ -57,7 +69,12 @@ make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 # $(run) contains all available tests run := make_pure +# Targets 'clean all' can be run together only through top level +# Makefile because we detect clean target in Makefile.perf and +# disable features detection +ifeq ($(MK),Makefile) run += make_clean_all +endif run += make_python_perf_so run += make_debug run += make_no_libperl @@ -83,6 +100,7 @@ run += make_util_map_o run += make_util_pmu_bison_o run += make_install run += make_install_bin +run += make_install_prefix # FIXME 'install-*' commented out till they're fixed # run += make_install_doc # run += make_install_man @@ -157,6 +175,12 @@ test_make_install_O := $(call test_dest_files,$(installed_files_all)) test_make_install_bin := $(call test_dest_files,$(installed_files_bin)) test_make_install_bin_O := $(call test_dest_files,$(installed_files_bin)) +# We prefix all installed files for make_install_prefix +# with '/tmp/krava' to match installed/prefix-ed files. +installed_files_all_prefix := $(addprefix /tmp/krava/,$(installed_files_all)) +test_make_install_prefix := $(call test_dest_files,$(installed_files_all_prefix)) +test_make_install_prefix_O := $(call test_dest_files,$(installed_files_all_prefix)) + # FIXME nothing gets installed test_make_install_man := test -f $$TMP_DEST/share/man/man1/perf.1 test_make_install_man_O := $(test_make_install_man) @@ -226,13 +250,13 @@ tarpkg: ( eval $$cmd ) >> $@ 2>&1 make_kernelsrc: - @echo " - make -C <kernelsrc> tools/perf" + @echo "- make -C <kernelsrc> tools/perf" $(call clean); \ (make -C ../.. tools/perf) > $@ 2>&1 && \ test -x perf && rm -f $@ || (cat $@ ; false) make_kernelsrc_tools: - @echo " - make -C <kernelsrc>/tools perf" + @echo "- make -C <kernelsrc>/tools perf" $(call clean); \ (make -C ../../tools perf) > $@ 2>&1 && \ test -x perf && rm -f $@ || (cat $@ ; false) @@ -244,3 +268,4 @@ out: $(run_O) @echo OK .PHONY: all $(run) $(run_O) tarpkg clean +endif # ifndef MK diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 5855cf471210..666b67a4df9d 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -140,8 +140,8 @@ out_delete_evlist: cpus = NULL; threads = NULL; out_free_cpus: - cpu_map__delete(cpus); + cpu_map__put(cpus); out_free_threads: - thread_map__delete(threads); + thread_map__put(threads); return err; } diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 7f48efa7e295..145050e2e544 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -143,7 +143,7 @@ static int synth_process(struct machine *machine) perf_event__process, machine, 0, 500); - thread_map__delete(map); + thread_map__put(map); return err; } diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index 9a7a116e09b8..a572f87e9c8d 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -78,7 +78,7 @@ int test__openat_syscall_event_on_all_cpus(void) * we use the auto allocation it will allocate just for 1 cpu, * as we start by cpu 0. */ - if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) { + if (perf_evsel__alloc_counts(evsel, cpus->nr, 1) < 0) { pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr); goto out_close_fd; } @@ -98,9 +98,9 @@ int test__openat_syscall_event_on_all_cpus(void) } expected = nr_openat_calls + cpu; - if (evsel->counts->cpu[cpu].val != expected) { + if (perf_counts(evsel->counts, cpu, 0)->val != expected) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", - expected, cpus->map[cpu], evsel->counts->cpu[cpu].val); + expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val); err = -1; } } @@ -111,6 +111,6 @@ out_close_fd: out_evsel_delete: perf_evsel__delete(evsel); out_thread_map_delete: - thread_map__delete(threads); + thread_map__put(threads); return err; } diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 6245221479d7..01a19626c846 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -45,7 +45,7 @@ int test__syscall_openat_tp_fields(void) perf_evsel__config(evsel, &opts); - evlist->threads->map[0] = getpid(); + thread_map__set_pid(evlist->threads, 0, getpid()); err = perf_evlist__open(evlist); if (err < 0) { diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index 9f9491bb8e48..c9a37bc6b33a 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -44,9 +44,9 @@ int test__openat_syscall_event(void) goto out_close_fd; } - if (evsel->counts->cpu[0].val != nr_openat_calls) { + if (perf_counts(evsel->counts, 0, 0)->val != nr_openat_calls) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n", - nr_openat_calls, evsel->counts->cpu[0].val); + nr_openat_calls, perf_counts(evsel->counts, 0, 0)->val); goto out_close_fd; } @@ -56,6 +56,6 @@ out_close_fd: out_evsel_delete: perf_evsel__delete(evsel); out_thread_map_delete: - thread_map__delete(threads); + thread_map__put(threads); return err; } diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 0d31403ea593..e698742d4fec 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -560,8 +560,8 @@ out: perf_evlist__disable(evlist); perf_evlist__delete(evlist); } else { - cpu_map__delete(cpus); - thread_map__delete(threads); + cpu_map__put(cpus); + thread_map__put(threads); } return err; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 8e5038b48ba8..ebb47d96bc0b 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -61,6 +61,7 @@ int test__switch_tracking(void); int test__fdarray__filter(void); int test__fdarray__add(void); int test__kmod_path__parse(void); +int test__thread_map(void); #if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c new file mode 100644 index 000000000000..5acf000939ea --- /dev/null +++ b/tools/perf/tests/thread-map.c @@ -0,0 +1,38 @@ +#include <sys/types.h> +#include <unistd.h> +#include "tests.h" +#include "thread_map.h" +#include "debug.h" + +int test__thread_map(void) +{ + struct thread_map *map; + + /* test map on current pid */ + map = thread_map__new_by_pid(getpid()); + TEST_ASSERT_VAL("failed to alloc map", map); + + thread_map__read_comms(map); + + TEST_ASSERT_VAL("wrong nr", map->nr == 1); + TEST_ASSERT_VAL("wrong pid", + thread_map__pid(map, 0) == getpid()); + TEST_ASSERT_VAL("wrong comm", + thread_map__comm(map, 0) && + !strcmp(thread_map__comm(map, 0), "perf")); + thread_map__put(map); + + /* test dummy pid */ + map = thread_map__new_dummy(); + TEST_ASSERT_VAL("failed to alloc map", map); + + thread_map__read_comms(map); + + TEST_ASSERT_VAL("wrong nr", map->nr == 1); + TEST_ASSERT_VAL("wrong pid", thread_map__pid(map, 0) == -1); + TEST_ASSERT_VAL("wrong comm", + thread_map__comm(map, 0) && + !strcmp(thread_map__comm(map, 0), "dummy")); + thread_map__put(map); + return 0; +} diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index c42adb600091..7629bef2fd79 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1902,8 +1902,23 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, case CTRL('c'): goto out_free_stack; case 'f': - if (!is_report_browser(hbt)) - goto out_free_stack; + if (!is_report_browser(hbt)) { + struct perf_top *top = hbt->arg; + + perf_evlist__toggle_enable(top->evlist); + /* + * No need to refresh, resort/decay histogram + * entries if we are not collecting samples: + */ + if (top->evlist->enabled) { + helpline = "Press 'f' to disable the events or 'h' to see other hotkeys"; + hbt->refresh = delay_secs; + } else { + helpline = "Press 'f' again to re-enable the events"; + hbt->refresh = 0; + } + continue; + } /* Fall thru */ default: helpline = "Press '?' for help on key bindings"; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index df66966cfde7..7e7405c9b936 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -119,12 +119,12 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, if (per_cpu) { mp->cpu = evlist->cpus->map[idx]; if (evlist->threads) - mp->tid = evlist->threads->map[0]; + mp->tid = thread_map__pid(evlist->threads, 0); else mp->tid = -1; } else { mp->cpu = -1; - mp->tid = evlist->threads->map[idx]; + mp->tid = thread_map__pid(evlist->threads, idx); } } @@ -1182,6 +1182,13 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm, data2 = NULL; } + if (itr->alignment) { + unsigned int unwanted = len1 % itr->alignment; + + len1 -= unwanted; + size -= unwanted; + } + /* padding must be written by fn() e.g. record__process_auxtrace() */ padding = size & 7; if (padding) diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index a171abbe7301..471aecbc4d68 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -303,6 +303,7 @@ struct auxtrace_record { const char *str); u64 (*reference)(struct auxtrace_record *itr); int (*read_finish)(struct auxtrace_record *itr, int idx); + unsigned int alignment; }; #ifdef HAVE_AUXTRACE_SUPPORT diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 85b523885f9d..2babddaa2481 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -7,11 +7,15 @@ static unsigned long flag = PERF_FLAG_FD_CLOEXEC; +#ifdef __GLIBC_PREREQ +#if !__GLIBC_PREREQ(2, 6) int __weak sched_getcpu(void) { errno = ENOSYS; return -1; } +#endif +#endif static int perf_flag_probe(void) { diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index c4e55b71010c..3667e2123e5b 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -5,6 +5,7 @@ #include <assert.h> #include <stdio.h> #include <stdlib.h> +#include "asm/bug.h" static struct cpu_map *cpu_map__default_new(void) { @@ -22,6 +23,7 @@ static struct cpu_map *cpu_map__default_new(void) cpus->map[i] = i; cpus->nr = nr_cpus; + atomic_set(&cpus->refcnt, 1); } return cpus; @@ -35,6 +37,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) if (cpus != NULL) { cpus->nr = nr_cpus; memcpy(cpus->map, tmp_cpus, payload_size); + atomic_set(&cpus->refcnt, 1); } return cpus; @@ -194,14 +197,32 @@ struct cpu_map *cpu_map__dummy_new(void) if (cpus != NULL) { cpus->nr = 1; cpus->map[0] = -1; + atomic_set(&cpus->refcnt, 1); } return cpus; } -void cpu_map__delete(struct cpu_map *map) +static void cpu_map__delete(struct cpu_map *map) { - free(map); + if (map) { + WARN_ONCE(atomic_read(&map->refcnt) != 0, + "cpu_map refcnt unbalanced\n"); + free(map); + } +} + +struct cpu_map *cpu_map__get(struct cpu_map *map) +{ + if (map) + atomic_inc(&map->refcnt); + return map; +} + +void cpu_map__put(struct cpu_map *map) +{ + if (map && atomic_dec_and_test(&map->refcnt)) + cpu_map__delete(map); } int cpu_map__get_socket(struct cpu_map *map, int idx) @@ -263,6 +284,7 @@ static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, /* ensure we process id in increasing order */ qsort(c->map, c->nr, sizeof(int), cmp_ids); + atomic_set(&cpus->refcnt, 1); *res = c; return 0; } diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 61a654849002..0af9cecb4c51 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -3,18 +3,19 @@ #include <stdio.h> #include <stdbool.h> +#include <linux/atomic.h> #include "perf.h" #include "util/debug.h" struct cpu_map { + atomic_t refcnt; int nr; int map[]; }; struct cpu_map *cpu_map__new(const char *cpu_list); struct cpu_map *cpu_map__dummy_new(void); -void cpu_map__delete(struct cpu_map *map); struct cpu_map *cpu_map__read(FILE *file); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); int cpu_map__get_socket(struct cpu_map *map, int idx); @@ -22,6 +23,9 @@ int cpu_map__get_core(struct cpu_map *map, int idx); int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp); int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep); +struct cpu_map *cpu_map__get(struct cpu_map *map); +void cpu_map__put(struct cpu_map *map); + static inline int cpu_map__socket(struct cpu_map *sock, int s) { if (!sock || s > sock->nr || s < 0) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index d7d986d8f23e..67a977e5d0ab 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -504,7 +504,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, for (thread = 0; thread < threads->nr; ++thread) { if (__event__synthesize_thread(comm_event, mmap_event, fork_event, - threads->map[thread], 0, + thread_map__pid(threads, thread), 0, process, tool, machine, mmap_data, proc_map_timeout)) { err = -1; @@ -515,12 +515,12 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, * comm.pid is set to thread group id by * perf_event__synthesize_comm */ - if ((int) comm_event->comm.pid != threads->map[thread]) { + if ((int) comm_event->comm.pid != thread_map__pid(threads, thread)) { bool need_leader = true; /* is thread group leader in thread_map? */ for (j = 0; j < threads->nr; ++j) { - if ((int) comm_event->comm.pid == threads->map[j]) { + if ((int) comm_event->comm.pid == thread_map__pid(threads, j)) { need_leader = false; break; } diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 8366511b45f8..6cfdee68e763 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -114,8 +114,8 @@ void perf_evlist__delete(struct perf_evlist *evlist) { perf_evlist__munmap(evlist); perf_evlist__close(evlist); - cpu_map__delete(evlist->cpus); - thread_map__delete(evlist->threads); + cpu_map__put(evlist->cpus); + thread_map__put(evlist->threads); evlist->cpus = NULL; evlist->threads = NULL; perf_evlist__purge(evlist); @@ -548,7 +548,7 @@ static void perf_evlist__set_sid_idx(struct perf_evlist *evlist, else sid->cpu = -1; if (!evsel->system_wide && evlist->threads && thread >= 0) - sid->tid = evlist->threads->map[thread]; + sid->tid = thread_map__pid(evlist->threads, thread); else sid->tid = -1; } @@ -1101,6 +1101,31 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false); } +static int perf_evlist__propagate_maps(struct perf_evlist *evlist, + struct target *target) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + /* + * We already have cpus for evsel (via PMU sysfs) so + * keep it, if there's no target cpu list defined. + */ + if (evsel->cpus && target->cpu_list) + cpu_map__put(evsel->cpus); + + if (!evsel->cpus || target->cpu_list) + evsel->cpus = cpu_map__get(evlist->cpus); + + evsel->threads = thread_map__get(evlist->threads); + + if (!evsel->cpus || !evsel->threads) + return -ENOMEM; + } + + return 0; +} + int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) { evlist->threads = thread_map__new_str(target->pid, target->tid, @@ -1117,10 +1142,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target) if (evlist->cpus == NULL) goto out_delete_threads; - return 0; + return perf_evlist__propagate_maps(evlist, target); out_delete_threads: - thread_map__delete(evlist->threads); + thread_map__put(evlist->threads); evlist->threads = NULL; return -1; } @@ -1353,7 +1378,7 @@ static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist) out: return err; out_free_cpus: - cpu_map__delete(evlist->cpus); + cpu_map__put(evlist->cpus); evlist->cpus = NULL; goto out; } @@ -1475,7 +1500,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar __func__, __LINE__); goto out_close_pipes; } - evlist->threads->map[0] = evlist->workload.pid; + thread_map__set_pid(evlist->threads, 0, evlist->workload.pid); } close(child_ready_pipe[1]); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index a8489b9d2812..037633c1da9d 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -289,5 +289,4 @@ void perf_evlist__to_front(struct perf_evlist *evlist, void perf_evlist__set_tracking_event(struct perf_evlist *evlist, struct perf_evsel *tracking_evsel); - #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 33449decf7bd..2936b3080722 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -885,6 +885,8 @@ void perf_evsel__exit(struct perf_evsel *evsel) perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); close_cgroup(evsel->cgrp); + cpu_map__put(evsel->cpus); + thread_map__put(evsel->threads); zfree(&evsel->group_name); zfree(&evsel->name); perf_evsel__object.fini(evsel); @@ -896,7 +898,7 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } -void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, +void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { struct perf_counts_values tmp; @@ -908,8 +910,8 @@ void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, tmp = evsel->prev_raw_counts->aggr; evsel->prev_raw_counts->aggr = *count; } else { - tmp = evsel->prev_raw_counts->cpu[cpu]; - evsel->prev_raw_counts->cpu[cpu] = *count; + tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread); + *perf_counts(evsel->prev_raw_counts, cpu, thread) = *count; } count->val = count->val - tmp.val; @@ -937,20 +939,18 @@ void perf_counts_values__scale(struct perf_counts_values *count, *pscaled = scaled; } -int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread, - perf_evsel__read_cb_t cb) +int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count) { - struct perf_counts_values count; - - memset(&count, 0, sizeof(count)); + memset(count, 0, sizeof(*count)); if (FD(evsel, cpu, thread) < 0) return -EINVAL; - if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0) + if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0) return -errno; - return cb(evsel, cpu, thread, &count); + return 0; } int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, @@ -962,15 +962,15 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, if (FD(evsel, cpu, thread) < 0) return -EINVAL; - if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0) + if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0) return -ENOMEM; if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) return -errno; - perf_evsel__compute_deltas(evsel, cpu, &count); + perf_evsel__compute_deltas(evsel, cpu, thread, &count); perf_counts_values__scale(&count, scale, NULL); - evsel->counts->cpu[cpu] = count; + *perf_counts(evsel->counts, cpu, thread) = count; return 0; } @@ -1167,7 +1167,7 @@ retry_sample_id: int group_fd; if (!evsel->cgrp && !evsel->system_wide) - pid = threads->map[thread]; + pid = thread_map__pid(threads, thread); group_fd = get_group_fd(evsel, cpu, thread); retry_open: diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index bb0579e8a10a..4a7ed5656cf0 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -8,23 +8,8 @@ #include <linux/types.h> #include "xyarray.h" #include "symbol.h" - -struct perf_counts_values { - union { - struct { - u64 val; - u64 ena; - u64 run; - }; - u64 values[3]; - }; -}; - -struct perf_counts { - s8 scaled; - struct perf_counts_values aggr; - struct perf_counts_values cpu[]; -}; +#include "cpumap.h" +#include "stat.h" struct perf_evsel; @@ -82,6 +67,7 @@ struct perf_evsel { struct cgroup_sel *cgrp; void *handler; struct cpu_map *cpus; + struct thread_map *threads; unsigned int sample_size; int id_pos; int is_pos; @@ -113,10 +99,20 @@ struct thread_map; struct perf_evlist; struct record_opts; +static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +{ + return evsel->cpus; +} + +static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) +{ + return perf_evsel__cpus(evsel)->nr; +} + void perf_counts_values__scale(struct perf_counts_values *count, bool scale, s8 *pscaled); -void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, +void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count); int perf_evsel__object_config(size_t object_size, @@ -233,12 +229,8 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1, (a)->attr.type == (b)->attr.type && \ (a)->attr.config == (b)->attr.config) -typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel, - int cpu, int thread, - struct perf_counts_values *count); - -int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread, - perf_evsel__read_cb_t cb); +int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count); int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, int cpu, int thread, bool scale); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 21a77e7a171e..03ace57a800c 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1063,8 +1063,7 @@ out: free(buf); return events; error: - if (events) - free_event_desc(events); + free_event_desc(events); events = NULL; goto out; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 4744673aff1b..7ff682770fdb 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1448,10 +1448,9 @@ int machine__process_event(struct machine *machine, union perf_event *event, case PERF_RECORD_AUX: ret = machine__process_aux_event(machine, event); break; case PERF_RECORD_ITRACE_START: - ret = machine__process_itrace_start_event(machine, event); + ret = machine__process_itrace_start_event(machine, event); break; case PERF_RECORD_LOST_SAMPLES: ret = machine__process_lost_samples_event(machine, event, sample); break; - break; default: ret = -1; break; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 2a4d1ec02846..09f8d2357108 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -17,6 +17,7 @@ #include "parse-events-flex.h" #include "pmu.h" #include "thread_map.h" +#include "cpumap.h" #include "asm/bug.h" #define MAX_NAME_LEN 100 @@ -285,7 +286,9 @@ __add_event(struct list_head *list, int *idx, if (!evsel) return NULL; - evsel->cpus = cpus; + if (cpus) + evsel->cpus = cpu_map__get(cpus); + if (name) evsel->name = strdup(name); list_add_tail(&evsel->node, list); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 09e738fe9ea2..13cef3c65565 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -119,8 +119,8 @@ event [^,{}/]+ num_dec [0-9]+ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ -name [a-zA-Z_*?][a-zA-Z0-9_*?]* -name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?]* +name [a-zA-Z_*?][a-zA-Z0-9_*?.]* +name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.]* /* If you add a modifier you need to update check_modifier() */ modifier_event [ukhpGHSDI]+ modifier_bp [rwx]{1,3} @@ -165,7 +165,6 @@ modifier_bp [rwx]{1,3} return PE_EVENT_NAME; } -. | <<EOF>> { BEGIN(INITIAL); REWIND(0); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 0fcc624eb767..7bcb8c315615 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1,4 +1,5 @@ #include <linux/list.h> +#include <linux/compiler.h> #include <sys/types.h> #include <unistd.h> #include <stdio.h> @@ -205,17 +206,12 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, return 0; } -static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file) +static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, + char *desc __maybe_unused, char *val) { struct perf_pmu_alias *alias; - char buf[256]; int ret; - ret = fread(buf, 1, sizeof(buf), file); - if (ret == 0) - return -EINVAL; - buf[ret] = 0; - alias = malloc(sizeof(*alias)); if (!alias) return -ENOMEM; @@ -225,26 +221,43 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI alias->unit[0] = '\0'; alias->per_pkg = false; - ret = parse_events_terms(&alias->terms, buf); + ret = parse_events_terms(&alias->terms, val); if (ret) { + pr_err("Cannot parse alias %s: %d\n", val, ret); free(alias); return ret; } alias->name = strdup(name); - /* - * load unit name and scale if available - */ - perf_pmu__parse_unit(alias, dir, name); - perf_pmu__parse_scale(alias, dir, name); - perf_pmu__parse_per_pkg(alias, dir, name); - perf_pmu__parse_snapshot(alias, dir, name); + if (dir) { + /* + * load unit name and scale if available + */ + perf_pmu__parse_unit(alias, dir, name); + perf_pmu__parse_scale(alias, dir, name); + perf_pmu__parse_per_pkg(alias, dir, name); + perf_pmu__parse_snapshot(alias, dir, name); + } list_add_tail(&alias->list, list); return 0; } +static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file) +{ + char buf[256]; + int ret; + + ret = fread(buf, 1, sizeof(buf), file); + if (ret == 0) + return -EINVAL; + + buf[ret] = 0; + + return __perf_pmu__new_alias(list, dir, name, NULL, buf); +} + static inline bool pmu_alias_info_file(char *name) { size_t len; @@ -436,7 +449,7 @@ static struct cpu_map *pmu_cpumask(const char *name) return cpus; } -struct perf_event_attr *__attribute__((weak)) +struct perf_event_attr * __weak perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { return NULL; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 076527b639bd..381f23a443c7 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -249,8 +249,12 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs) static bool kprobe_blacklist__listed(unsigned long address); static bool kprobe_warn_out_range(const char *symbol, unsigned long address) { + u64 etext_addr; + /* Get the address of _etext for checking non-probable text symbol */ - if (kernel_get_symbol_address_by_name("_etext", false) < address) + etext_addr = kernel_get_symbol_address_by_name("_etext", false); + + if (etext_addr != 0 && etext_addr < address) pr_warning("%s is out of .text, skip it.\n", symbol); else if (kprobe_blacklist__listed(address)) pr_warning("%s is blacklisted function, skip it.\n", symbol); diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 5925fec90562..e23ded40c79e 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -20,3 +20,4 @@ util/stat.c util/strlist.c util/trace-event.c ../../lib/rbtree.c +util/string.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index d906d0ad5d40..626422eda727 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -384,7 +384,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus) { - cpu_map__delete(pcpus->cpus); + cpu_map__put(pcpus->cpus); pcpus->ob_type->tp_free((PyObject*)pcpus); } @@ -453,7 +453,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads) { - thread_map__delete(pthreads->threads); + thread_map__put(pthreads->threads); pthreads->ob_type->tp_free((PyObject*)pthreads); } diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index d457c523a33d..1f7becbe5e18 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -64,7 +64,7 @@ static bool perf_probe_api(setup_probe_fn_t fn) if (!cpus) return false; cpu = cpus->map[0]; - cpu_map__delete(cpus); + cpu_map__put(cpus); do { ret = perf_do_probe_api(fn, cpu, try[i++]); @@ -226,7 +226,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str) struct cpu_map *cpus = cpu_map__new(NULL); cpu = cpus ? cpus->map[0] : 0; - cpu_map__delete(cpus); + cpu_map__put(cpus); } else { cpu = evlist->cpus->map[0]; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index aa482c10469d..ed9dc2555ec7 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -686,6 +686,8 @@ static int process_finished_round(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct ordered_events *oe) { + if (dump_trace) + fprintf(stdout, "\n"); return ordered_events__flush(oe, OE_FLUSH__ROUND); } @@ -1726,7 +1728,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) if (perf_header__has_feat(&session->header, HEADER_AUXTRACE)) msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)"; - ret = fprintf(fp, "Aggregated stats:%s\n", msg); + ret = fprintf(fp, "\nAggregated stats:%s\n", msg); ret += events_stats__fprintf(&session->evlist->stats, fp); return ret; @@ -1893,7 +1895,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, err = 0; out_delete_map: - cpu_map__delete(map); + cpu_map__put(map); return err; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 4014b709f956..f2a0d1521e26 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,6 +1,8 @@ #include <math.h> #include "stat.h" +#include "evlist.h" #include "evsel.h" +#include "thread_map.h" void update_stats(struct stats *stats, u64 val) { @@ -95,33 +97,46 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -struct perf_counts *perf_counts__new(int ncpus) +struct perf_counts *perf_counts__new(int ncpus, int nthreads) { - int size = sizeof(struct perf_counts) + - ncpus * sizeof(struct perf_counts_values); + struct perf_counts *counts = zalloc(sizeof(*counts)); - return zalloc(size); + if (counts) { + struct xyarray *values; + + values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values)); + if (!values) { + free(counts); + return NULL; + } + + counts->values = values; + } + + return counts; } void perf_counts__delete(struct perf_counts *counts) { - free(counts); + if (counts) { + xyarray__delete(counts->values); + free(counts); + } } -static void perf_counts__reset(struct perf_counts *counts, int ncpus) +static void perf_counts__reset(struct perf_counts *counts) { - memset(counts, 0, (sizeof(*counts) + - (ncpus * sizeof(struct perf_counts_values)))); + xyarray__reset(counts->values); } -void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus) +void perf_evsel__reset_counts(struct perf_evsel *evsel) { - perf_counts__reset(evsel->counts, ncpus); + perf_counts__reset(evsel->counts); } -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads) { - evsel->counts = perf_counts__new(ncpus); + evsel->counts = perf_counts__new(ncpus, nthreads); return evsel->counts != NULL ? 0 : -ENOMEM; } @@ -130,3 +145,96 @@ void perf_evsel__free_counts(struct perf_evsel *evsel) perf_counts__delete(evsel->counts); evsel->counts = NULL; } + +void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) +{ + int i; + struct perf_stat *ps = evsel->priv; + + for (i = 0; i < 3; i++) + init_stats(&ps->res_stats[i]); + + perf_stat_evsel_id_init(evsel); +} + +int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) +{ + evsel->priv = zalloc(sizeof(struct perf_stat)); + if (evsel->priv == NULL) + return -ENOMEM; + perf_evsel__reset_stat_priv(evsel); + return 0; +} + +void perf_evsel__free_stat_priv(struct perf_evsel *evsel) +{ + zfree(&evsel->priv); +} + +int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, + int ncpus, int nthreads) +{ + struct perf_counts *counts; + + counts = perf_counts__new(ncpus, nthreads); + if (counts) + evsel->prev_raw_counts = counts; + + return counts ? 0 : -ENOMEM; +} + +void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) +{ + perf_counts__delete(evsel->prev_raw_counts); + evsel->prev_raw_counts = NULL; +} + +int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw) +{ + int ncpus = perf_evsel__nr_cpus(evsel); + int nthreads = thread_map__nr(evsel->threads); + + if (perf_evsel__alloc_stat_priv(evsel) < 0 || + perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 || + (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0)) + return -ENOMEM; + + return 0; +} + +int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + if (perf_evsel__alloc_stats(evsel, alloc_raw)) + goto out_free; + } + + return 0; + +out_free: + perf_evlist__free_stats(evlist); + return -1; +} + +void perf_evlist__free_stats(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + perf_evsel__free_stat_priv(evsel); + perf_evsel__free_counts(evsel); + perf_evsel__free_prev_raw_counts(evsel); + } +} + +void perf_evlist__reset_stats(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + perf_evsel__reset_stat_priv(evsel); + perf_evsel__reset_counts(evsel); + } +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 093dc3cb28dd..1cfbe0a980ac 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -3,6 +3,7 @@ #include <linux/types.h> #include <stdio.h> +#include "xyarray.h" struct stats { @@ -29,8 +30,32 @@ enum aggr_mode { AGGR_GLOBAL, AGGR_SOCKET, AGGR_CORE, + AGGR_THREAD, }; +struct perf_counts_values { + union { + struct { + u64 val; + u64 ena; + u64 run; + }; + u64 values[3]; + }; +}; + +struct perf_counts { + s8 scaled; + struct perf_counts_values aggr; + struct xyarray *values; +}; + +static inline struct perf_counts_values* +perf_counts(struct perf_counts *counts, int cpu, int thread) +{ + return xyarray__entry(counts->values, cpu, thread); +} + void update_stats(struct stats *stats, u64 val); double avg_stats(struct stats *stats); double stddev_stats(struct stats *stats); @@ -46,6 +71,8 @@ static inline void init_stats(struct stats *stats) } struct perf_evsel; +struct perf_evlist; + bool __perf_evsel_stat__is(struct perf_evsel *evsel, enum perf_stat_evsel_id id); @@ -62,10 +89,24 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, double avg, int cpu, enum aggr_mode aggr); -struct perf_counts *perf_counts__new(int ncpus); +struct perf_counts *perf_counts__new(int ncpus, int nthreads); void perf_counts__delete(struct perf_counts *counts); -void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus); -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); +void perf_evsel__reset_counts(struct perf_evsel *evsel); +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads); void perf_evsel__free_counts(struct perf_evsel *evsel); + +void perf_evsel__reset_stat_priv(struct perf_evsel *evsel); +int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel); +void perf_evsel__free_stat_priv(struct perf_evsel *evsel); + +int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, + int ncpus, int nthreads); +void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel); + +int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw); + +int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); +void perf_evlist__free_stats(struct perf_evlist *evlist); +void perf_evlist__reset_stats(struct perf_evlist *evlist); #endif diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 283d3e73e2f2..eec6c1149f44 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -748,7 +748,7 @@ static int str_to_bitmap(char *s, cpumask_t *b) set_bit(c, cpumask_bits(b)); } - cpu_map__delete(m); + cpu_map__put(m); return ret; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 504f2d73b7ee..48b588c6951a 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1132,8 +1132,11 @@ static int dso__load_kcore(struct dso *dso, struct map *map, INIT_LIST_HEAD(&md.maps); fd = open(kcore_filename, O_RDONLY); - if (fd < 0) + if (fd < 0) { + pr_err("%s requires CAP_SYS_RAWIO capability to access.\n", + kcore_filename); return -EINVAL; + } /* Read new maps into temporary lists */ err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md, diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index f4822bd03709..da7646d767fe 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -8,8 +8,11 @@ #include <unistd.h> #include "strlist.h" #include <string.h> +#include <api/fs/fs.h> +#include "asm/bug.h" #include "thread_map.h" #include "util.h" +#include "debug.h" /* Skip "." and ".." directories */ static int filter(const struct dirent *dir) @@ -20,11 +23,26 @@ static int filter(const struct dirent *dir) return 1; } +static void thread_map__reset(struct thread_map *map, int start, int nr) +{ + size_t size = (nr - start) * sizeof(map->map[0]); + + memset(&map->map[start], 0, size); +} + static struct thread_map *thread_map__realloc(struct thread_map *map, int nr) { - size_t size = sizeof(*map) + sizeof(pid_t) * nr; + size_t size = sizeof(*map) + sizeof(map->map[0]) * nr; + int start = map ? map->nr : 0; + + map = realloc(map, size); + /* + * We only realloc to add more items, let's reset new items. + */ + if (map) + thread_map__reset(map, start, nr); - return realloc(map, size); + return map; } #define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr) @@ -45,8 +63,9 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) threads = thread_map__alloc(items); if (threads != NULL) { for (i = 0; i < items; i++) - threads->map[i] = atoi(namelist[i]->d_name); + thread_map__set_pid(threads, i, atoi(namelist[i]->d_name)); threads->nr = items; + atomic_set(&threads->refcnt, 1); } for (i=0; i<items; i++) @@ -61,8 +80,9 @@ struct thread_map *thread_map__new_by_tid(pid_t tid) struct thread_map *threads = thread_map__alloc(1); if (threads != NULL) { - threads->map[0] = tid; - threads->nr = 1; + thread_map__set_pid(threads, 0, tid); + threads->nr = 1; + atomic_set(&threads->refcnt, 1); } return threads; @@ -84,6 +104,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) goto out_free_threads; threads->nr = 0; + atomic_set(&threads->refcnt, 1); while (!readdir_r(proc, &dirent, &next) && next) { char *end; @@ -123,8 +144,10 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) threads = tmp; } - for (i = 0; i < items; i++) - threads->map[threads->nr + i] = atoi(namelist[i]->d_name); + for (i = 0; i < items; i++) { + thread_map__set_pid(threads, threads->nr + i, + atoi(namelist[i]->d_name)); + } for (i = 0; i < items; i++) zfree(&namelist[i]); @@ -201,7 +224,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) threads = nt; for (i = 0; i < items; i++) { - threads->map[j++] = atoi(namelist[i]->d_name); + thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name)); zfree(&namelist[i]); } threads->nr = total_tasks; @@ -210,6 +233,8 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) out: strlist__delete(slist); + if (threads) + atomic_set(&threads->refcnt, 1); return threads; out_free_namelist: @@ -227,8 +252,9 @@ struct thread_map *thread_map__new_dummy(void) struct thread_map *threads = thread_map__alloc(1); if (threads != NULL) { - threads->map[0] = -1; - threads->nr = 1; + thread_map__set_pid(threads, 0, -1); + threads->nr = 1; + atomic_set(&threads->refcnt, 1); } return threads; } @@ -267,10 +293,12 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) goto out_free_threads; threads = nt; - threads->map[ntasks - 1] = tid; - threads->nr = ntasks; + thread_map__set_pid(threads, ntasks - 1, tid); + threads->nr = ntasks; } out: + if (threads) + atomic_set(&threads->refcnt, 1); return threads; out_free_threads: @@ -290,9 +318,30 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid, return thread_map__new_by_tid_str(tid); } -void thread_map__delete(struct thread_map *threads) +static void thread_map__delete(struct thread_map *threads) { - free(threads); + if (threads) { + int i; + + WARN_ONCE(atomic_read(&threads->refcnt) != 0, + "thread map refcnt unbalanced\n"); + for (i = 0; i < threads->nr; i++) + free(thread_map__comm(threads, i)); + free(threads); + } +} + +struct thread_map *thread_map__get(struct thread_map *map) +{ + if (map) + atomic_inc(&map->refcnt); + return map; +} + +void thread_map__put(struct thread_map *map) +{ + if (map && atomic_dec_and_test(&map->refcnt)) + thread_map__delete(map); } size_t thread_map__fprintf(struct thread_map *threads, FILE *fp) @@ -301,7 +350,60 @@ size_t thread_map__fprintf(struct thread_map *threads, FILE *fp) size_t printed = fprintf(fp, "%d thread%s: ", threads->nr, threads->nr > 1 ? "s" : ""); for (i = 0; i < threads->nr; ++i) - printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]); + printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i)); return printed + fprintf(fp, "\n"); } + +static int get_comm(char **comm, pid_t pid) +{ + char *path; + size_t size; + int err; + + if (asprintf(&path, "%s/%d/comm", procfs__mountpoint(), pid) == -1) + return -ENOMEM; + + err = filename__read_str(path, comm, &size); + if (!err) { + /* + * We're reading 16 bytes, while filename__read_str + * allocates data per BUFSIZ bytes, so we can safely + * mark the end of the string. + */ + (*comm)[size] = 0; + rtrim(*comm); + } + + free(path); + return err; +} + +static void comm_init(struct thread_map *map, int i) +{ + pid_t pid = thread_map__pid(map, i); + char *comm = NULL; + + /* dummy pid comm initialization */ + if (pid == -1) { + map->map[i].comm = strdup("dummy"); + return; + } + + /* + * The comm name is like extra bonus ;-), + * so just warn if we fail for any reason. + */ + if (get_comm(&comm, pid)) + pr_warning("Couldn't resolve comm name for pid %d\n", pid); + + map->map[i].comm = comm; +} + +void thread_map__read_comms(struct thread_map *threads) +{ + int i; + + for (i = 0; i < threads->nr; ++i) + comm_init(threads, i); +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 95313f43cc0f..af679d8a50f8 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -3,10 +3,17 @@ #include <sys/types.h> #include <stdio.h> +#include <linux/atomic.h> + +struct thread_map_data { + pid_t pid; + char *comm; +}; struct thread_map { + atomic_t refcnt; int nr; - pid_t map[]; + struct thread_map_data map[]; }; struct thread_map *thread_map__new_dummy(void); @@ -15,11 +22,12 @@ struct thread_map *thread_map__new_by_tid(pid_t tid); struct thread_map *thread_map__new_by_uid(uid_t uid); struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); +struct thread_map *thread_map__get(struct thread_map *map); +void thread_map__put(struct thread_map *map); + struct thread_map *thread_map__new_str(const char *pid, const char *tid, uid_t uid); -void thread_map__delete(struct thread_map *threads); - size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); static inline int thread_map__nr(struct thread_map *threads) @@ -27,4 +35,21 @@ static inline int thread_map__nr(struct thread_map *threads) return threads ? threads->nr : 1; } +static inline pid_t thread_map__pid(struct thread_map *map, int thread) +{ + return map->map[thread].pid; +} + +static inline void +thread_map__set_pid(struct thread_map *map, int thread, pid_t pid) +{ + map->map[thread].pid = pid; +} + +static inline char *thread_map__comm(struct thread_map *map, int thread) +{ + return map->map[thread].comm; +} + +void thread_map__read_comms(struct thread_map *threads); #endif /* __PERF_THREAD_MAP_H */ |