diff options
author | Gary S. Robertson <gary.robertson@linaro.org> | 2016-01-28 10:57:10 -0600 |
---|---|---|
committer | Gary S. Robertson <gary.robertson@linaro.org> | 2016-01-28 10:57:10 -0600 |
commit | eda0f037f971898a6941ca104e9e00fd3b3ebdf3 (patch) | |
tree | c0374ae2b169aea2ea8325bf80e7c9f5b62c6ca3 | |
parent | 1d10e9e61dedad92bcf380a421d08f021e62ff1b (diff) | |
parent | efab1adba28d9ebbfa86808375fc085c4e84e746 (diff) |
Merge tag 'lsk-v4.1-16.01' of http://git.linaro.org/kernel/linux-linaro-stable into linux-linaro-lng-v4.1
LSK 16.01 v4.1
118 files changed, 1819 insertions, 1438 deletions
diff --git a/Documentation/devicetree/bindings/arm/psci.txt b/Documentation/devicetree/bindings/arm/psci.txt index 5aa40ede0e99..a9adab84e2fe 100644 --- a/Documentation/devicetree/bindings/arm/psci.txt +++ b/Documentation/devicetree/bindings/arm/psci.txt @@ -31,6 +31,10 @@ Main node required properties: support, but are permitted to be present for compatibility with existing software when "arm,psci" is later in the compatible list. + * "arm,psci-1.0" : for implementations complying to PSCI 1.0. PSCI 1.0 is + backward compatible with PSCI 0.2 with minor specification updates, + as defined in the PSCI specification[2]. + - method : The method of calling the PSCI firmware. Permitted values are: @@ -100,3 +104,5 @@ Case 3: PSCI v0.2 and PSCI v0.1. [1] Kernel documentation - ARM idle states bindings Documentation/devicetree/bindings/arm/idle-states.txt +[2] Power State Coordination Interface (PSCI) specification + http://infocenter.arm.com/help/topic/com.arm.doc.den0022c/DEN0022C_Power_State_Coordination_Interface.pdf @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 1 -SUBLEVEL = 14 +SUBLEVEL = 15 EXTRAVERSION = NAME = Series 4800 diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 19f4cc634b0e..3a9d691afe58 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1466,6 +1466,7 @@ config HOTPLUG_CPU config ARM_PSCI bool "Support for the ARM Power State Coordination Interface (PSCI)" depends on CPU_V7 + select ARM_PSCI_FW help Say Y here if you want Linux to communicate with system firmware implementing the PSCI specification for CPU-centric power diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h index c25ef3ec6d1f..68ee3ce17b82 100644 --- a/arch/arm/include/asm/psci.h +++ b/arch/arm/include/asm/psci.h @@ -14,34 +14,11 @@ #ifndef __ASM_ARM_PSCI_H #define __ASM_ARM_PSCI_H -#define PSCI_POWER_STATE_TYPE_STANDBY 0 -#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 - -struct psci_power_state { - u16 id; - u8 type; - u8 affinity_level; -}; - -struct psci_operations { - int (*cpu_suspend)(struct psci_power_state state, - unsigned long entry_point); - int (*cpu_off)(struct psci_power_state state); - int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); - int (*migrate)(unsigned long cpuid); - int (*affinity_info)(unsigned long target_affinity, - unsigned long lowest_affinity_level); - int (*migrate_info_type)(void); -}; - -extern struct psci_operations psci_ops; extern struct smp_operations psci_smp_ops; #ifdef CONFIG_ARM_PSCI -int psci_init(void); bool psci_smp_available(void); #else -static inline int psci_init(void) { return 0; } static inline bool psci_smp_available(void) { return false; } #endif diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 752725dcbf42..2c06383f4d47 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -86,7 +86,7 @@ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o ifeq ($(CONFIG_ARM_PSCI),y) -obj-y += psci.o psci-call.o +obj-y += psci-call.o obj-$(CONFIG_SMP) += psci_smp.o endif diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c deleted file mode 100644 index f90fdf4ce7c7..000000000000 --- a/arch/arm/kernel/psci.c +++ /dev/null @@ -1,299 +0,0 @@ -/* - * 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. - * - * Copyright (C) 2012 ARM Limited - * - * Author: Will Deacon <will.deacon@arm.com> - */ - -#define pr_fmt(fmt) "psci: " fmt - -#include <linux/init.h> -#include <linux/of.h> -#include <linux/reboot.h> -#include <linux/pm.h> -#include <uapi/linux/psci.h> - -#include <asm/compiler.h> -#include <asm/errno.h> -#include <asm/psci.h> -#include <asm/system_misc.h> - -struct psci_operations psci_ops; - -static int (*invoke_psci_fn)(u32, u32, u32, u32); -typedef int (*psci_initcall_t)(const struct device_node *); - -asmlinkage int __invoke_psci_fn_hvc(u32, u32, u32, u32); -asmlinkage int __invoke_psci_fn_smc(u32, u32, u32, u32); - -enum psci_function { - PSCI_FN_CPU_SUSPEND, - PSCI_FN_CPU_ON, - PSCI_FN_CPU_OFF, - PSCI_FN_MIGRATE, - PSCI_FN_AFFINITY_INFO, - PSCI_FN_MIGRATE_INFO_TYPE, - PSCI_FN_MAX, -}; - -static u32 psci_function_id[PSCI_FN_MAX]; - -static int psci_to_linux_errno(int errno) -{ - switch (errno) { - case PSCI_RET_SUCCESS: - return 0; - case PSCI_RET_NOT_SUPPORTED: - return -EOPNOTSUPP; - case PSCI_RET_INVALID_PARAMS: - return -EINVAL; - case PSCI_RET_DENIED: - return -EPERM; - }; - - return -EINVAL; -} - -static u32 psci_power_state_pack(struct psci_power_state state) -{ - return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT) - & PSCI_0_2_POWER_STATE_ID_MASK) | - ((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT) - & PSCI_0_2_POWER_STATE_TYPE_MASK) | - ((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT) - & PSCI_0_2_POWER_STATE_AFFL_MASK); -} - -static int psci_get_version(void) -{ - int err; - - err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0); - return err; -} - -static int psci_cpu_suspend(struct psci_power_state state, - unsigned long entry_point) -{ - int err; - u32 fn, power_state; - - fn = psci_function_id[PSCI_FN_CPU_SUSPEND]; - power_state = psci_power_state_pack(state); - err = invoke_psci_fn(fn, power_state, entry_point, 0); - return psci_to_linux_errno(err); -} - -static int psci_cpu_off(struct psci_power_state state) -{ - int err; - u32 fn, power_state; - - fn = psci_function_id[PSCI_FN_CPU_OFF]; - power_state = psci_power_state_pack(state); - err = invoke_psci_fn(fn, power_state, 0, 0); - return psci_to_linux_errno(err); -} - -static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_CPU_ON]; - err = invoke_psci_fn(fn, cpuid, entry_point, 0); - return psci_to_linux_errno(err); -} - -static int psci_migrate(unsigned long cpuid) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_MIGRATE]; - err = invoke_psci_fn(fn, cpuid, 0, 0); - return psci_to_linux_errno(err); -} - -static int psci_affinity_info(unsigned long target_affinity, - unsigned long lowest_affinity_level) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_AFFINITY_INFO]; - err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0); - return err; -} - -static int psci_migrate_info_type(void) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE]; - err = invoke_psci_fn(fn, 0, 0, 0); - return err; -} - -static int get_set_conduit_method(struct device_node *np) -{ - const char *method; - - pr_info("probing for conduit method from DT.\n"); - - if (of_property_read_string(np, "method", &method)) { - pr_warn("missing \"method\" property\n"); - return -ENXIO; - } - - if (!strcmp("hvc", method)) { - invoke_psci_fn = __invoke_psci_fn_hvc; - } else if (!strcmp("smc", method)) { - invoke_psci_fn = __invoke_psci_fn_smc; - } else { - pr_warn("invalid \"method\" property: %s\n", method); - return -EINVAL; - } - return 0; -} - -static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd) -{ - invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0); -} - -static void psci_sys_poweroff(void) -{ - invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0); -} - -/* - * PSCI Function IDs for v0.2+ are well defined so use - * standard values. - */ -static int psci_0_2_init(struct device_node *np) -{ - int err, ver; - - err = get_set_conduit_method(np); - - if (err) - goto out_put_node; - - ver = psci_get_version(); - - if (ver == PSCI_RET_NOT_SUPPORTED) { - /* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */ - pr_err("PSCI firmware does not comply with the v0.2 spec.\n"); - err = -EOPNOTSUPP; - goto out_put_node; - } else { - pr_info("PSCIv%d.%d detected in firmware.\n", - PSCI_VERSION_MAJOR(ver), - PSCI_VERSION_MINOR(ver)); - - if (PSCI_VERSION_MAJOR(ver) == 0 && - PSCI_VERSION_MINOR(ver) < 2) { - err = -EINVAL; - pr_err("Conflicting PSCI version detected.\n"); - goto out_put_node; - } - } - - pr_info("Using standard PSCI v0.2 function IDs\n"); - psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_CPU_SUSPEND; - psci_ops.cpu_suspend = psci_cpu_suspend; - - psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF; - psci_ops.cpu_off = psci_cpu_off; - - psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_CPU_ON; - psci_ops.cpu_on = psci_cpu_on; - - psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_MIGRATE; - psci_ops.migrate = psci_migrate; - - psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN_AFFINITY_INFO; - psci_ops.affinity_info = psci_affinity_info; - - psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] = - PSCI_0_2_FN_MIGRATE_INFO_TYPE; - psci_ops.migrate_info_type = psci_migrate_info_type; - - arm_pm_restart = psci_sys_reset; - - pm_power_off = psci_sys_poweroff; - -out_put_node: - of_node_put(np); - return err; -} - -/* - * PSCI < v0.2 get PSCI Function IDs via DT. - */ -static int psci_0_1_init(struct device_node *np) -{ - u32 id; - int err; - - err = get_set_conduit_method(np); - - if (err) - goto out_put_node; - - pr_info("Using PSCI v0.1 Function IDs from DT\n"); - - if (!of_property_read_u32(np, "cpu_suspend", &id)) { - psci_function_id[PSCI_FN_CPU_SUSPEND] = id; - psci_ops.cpu_suspend = psci_cpu_suspend; - } - - if (!of_property_read_u32(np, "cpu_off", &id)) { - psci_function_id[PSCI_FN_CPU_OFF] = id; - psci_ops.cpu_off = psci_cpu_off; - } - - if (!of_property_read_u32(np, "cpu_on", &id)) { - psci_function_id[PSCI_FN_CPU_ON] = id; - psci_ops.cpu_on = psci_cpu_on; - } - - if (!of_property_read_u32(np, "migrate", &id)) { - psci_function_id[PSCI_FN_MIGRATE] = id; - psci_ops.migrate = psci_migrate; - } - -out_put_node: - of_node_put(np); - return err; -} - -static const struct of_device_id psci_of_match[] __initconst = { - { .compatible = "arm,psci", .data = psci_0_1_init}, - { .compatible = "arm,psci-0.2", .data = psci_0_2_init}, - {}, -}; - -int __init psci_init(void) -{ - struct device_node *np; - const struct of_device_id *matched_np; - psci_initcall_t init_fn; - - np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np); - if (!np) - return -ENODEV; - - init_fn = (psci_initcall_t)matched_np->data; - return init_fn(np); -} diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c index 28a1db4da704..9d479b2ea40d 100644 --- a/arch/arm/kernel/psci_smp.c +++ b/arch/arm/kernel/psci_smp.c @@ -17,6 +17,8 @@ #include <linux/smp.h> #include <linux/of.h> #include <linux/delay.h> +#include <linux/psci.h> + #include <uapi/linux/psci.h> #include <asm/psci.h> @@ -51,25 +53,37 @@ static int psci_boot_secondary(unsigned int cpu, struct task_struct *idle) { if (psci_ops.cpu_on) return psci_ops.cpu_on(cpu_logical_map(cpu), - __pa(secondary_startup)); + virt_to_idmap(&secondary_startup)); return -ENODEV; } #ifdef CONFIG_HOTPLUG_CPU -void __ref psci_cpu_die(unsigned int cpu) +int psci_cpu_disable(unsigned int cpu) +{ + /* Fail early if we don't have CPU_OFF support */ + if (!psci_ops.cpu_off) + return -EOPNOTSUPP; + + /* Trusted OS will deny CPU_OFF */ + if (psci_tos_resident_on(cpu)) + return -EPERM; + + return 0; +} + +void psci_cpu_die(unsigned int cpu) { - const struct psci_power_state ps = { - .type = PSCI_POWER_STATE_TYPE_POWER_DOWN, - }; + u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << + PSCI_0_2_POWER_STATE_TYPE_SHIFT; - if (psci_ops.cpu_off) - psci_ops.cpu_off(ps); + if (psci_ops.cpu_off) + psci_ops.cpu_off(state); - /* We should never return */ - panic("psci: cpu %d failed to shutdown\n", cpu); + /* We should never return */ + panic("psci: cpu %d failed to shutdown\n", cpu); } -int __ref psci_cpu_kill(unsigned int cpu) +int psci_cpu_kill(unsigned int cpu) { int err, i; @@ -109,6 +123,7 @@ bool __init psci_smp_available(void) struct smp_operations __initdata psci_smp_ops = { .smp_boot_secondary = psci_boot_secondary, #ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = psci_cpu_disable, .cpu_die = psci_cpu_die, .cpu_kill = psci_cpu_kill, #endif diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 6c777e908a24..3224680e44f4 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -31,6 +31,7 @@ #include <linux/bug.h> #include <linux/compiler.h> #include <linux/sort.h> +#include <linux/psci.h> #include <asm/unified.h> #include <asm/cp15.h> @@ -950,7 +951,7 @@ void __init setup_arch(char **cmdline_p) unflatten_device_tree(); arm_dt_init_cpu_maps(); - psci_init(); + psci_dt_init(); #ifdef CONFIG_SMP if (is_smp()) { if (!mdesc->smp_init || !mdesc->smp_init()) { diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 531e922486b2..ad6f6424f1d1 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -24,6 +24,8 @@ #include <asm/kvm_psci.h> #include <asm/kvm_host.h> +#include <uapi/linux/psci.h> + /* * This is an implementation of the Power State Coordination Interface * as described in ARM document number ARM DEN 0022A. @@ -124,7 +126,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) { - int i; + int i, matching_cpus = 0; unsigned long mpidr; unsigned long target_affinity; unsigned long target_affinity_mask; @@ -149,12 +151,16 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) */ kvm_for_each_vcpu(i, tmp, kvm) { mpidr = kvm_vcpu_get_mpidr_aff(tmp); - if (((mpidr & target_affinity_mask) == target_affinity) && - !tmp->arch.pause) { - return PSCI_0_2_AFFINITY_LEVEL_ON; + if ((mpidr & target_affinity_mask) == target_affinity) { + matching_cpus++; + if (!tmp->arch.pause) + return PSCI_0_2_AFFINITY_LEVEL_ON; } } + if (!matching_cpus) + return PSCI_RET_INVALID_PARAMS; + return PSCI_0_2_AFFINITY_LEVEL_OFF; } diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c index 231fba0d03e5..6050a14faee6 100644 --- a/arch/arm/mach-highbank/highbank.c +++ b/arch/arm/mach-highbank/highbank.c @@ -28,8 +28,8 @@ #include <linux/reboot.h> #include <linux/amba/bus.h> #include <linux/platform_device.h> +#include <linux/psci.h> -#include <asm/psci.h> #include <asm/hardware/cache-l2x0.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> diff --git a/arch/arm/mach-highbank/pm.c b/arch/arm/mach-highbank/pm.c index 7f2bd85eb935..400311695548 100644 --- a/arch/arm/mach-highbank/pm.c +++ b/arch/arm/mach-highbank/pm.c @@ -16,19 +16,21 @@ #include <linux/cpu_pm.h> #include <linux/init.h> +#include <linux/psci.h> #include <linux/suspend.h> #include <asm/suspend.h> -#include <asm/psci.h> + +#include <uapi/linux/psci.h> + +#define HIGHBANK_SUSPEND_PARAM \ + ((0 << PSCI_0_2_POWER_STATE_ID_SHIFT) | \ + (1 << PSCI_0_2_POWER_STATE_AFFL_SHIFT) | \ + (PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT)) static int highbank_suspend_finish(unsigned long val) { - const struct psci_power_state ps = { - .type = PSCI_POWER_STATE_TYPE_POWER_DOWN, - .affinity_level = 1, - }; - - return psci_ops.cpu_suspend(ps, __pa(cpu_resume)); + return psci_ops.cpu_suspend(HIGHBANK_SUSPEND_PARAM, __pa(cpu_resume)); } static int highbank_pm_enter(suspend_state_t state) diff --git a/arch/arm/mach-omap2/omap-hotplug.c b/arch/arm/mach-omap2/omap-hotplug.c index 971791fe9a3f..593fec753b28 100644 --- a/arch/arm/mach-omap2/omap-hotplug.c +++ b/arch/arm/mach-omap2/omap-hotplug.c @@ -27,7 +27,7 @@ * platform-specific code to shutdown a CPU * Called with IRQs disabled */ -void __ref omap4_cpu_die(unsigned int cpu) +void omap4_cpu_die(unsigned int cpu) { unsigned int boot_cpu = 0; void __iomem *base = omap_get_wakeupgen_base(); diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index 6833df45d7b1..3e059b215a1d 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -330,7 +330,7 @@ static int irq_cpu_hotplug_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block __refdata irq_hotplug_notifier = { +static struct notifier_block irq_hotplug_notifier = { .notifier_call = irq_cpu_hotplug_notify, }; diff --git a/arch/arm/mach-prima2/hotplug.c b/arch/arm/mach-prima2/hotplug.c index 0ab2f8bae28e..a728c78b996f 100644 --- a/arch/arm/mach-prima2/hotplug.c +++ b/arch/arm/mach-prima2/hotplug.c @@ -32,7 +32,7 @@ static inline void platform_do_lowpower(unsigned int cpu) * * Called with IRQs disabled */ -void __ref sirfsoc_cpu_die(unsigned int cpu) +void sirfsoc_cpu_die(unsigned int cpu) { platform_do_lowpower(cpu); } diff --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c index 5cde63a64b34..9b00123a315d 100644 --- a/arch/arm/mach-qcom/platsmp.c +++ b/arch/arm/mach-qcom/platsmp.c @@ -49,7 +49,7 @@ extern void secondary_startup_arm(void); static DEFINE_SPINLOCK(boot_lock); #ifdef CONFIG_HOTPLUG_CPU -static void __ref qcom_cpu_die(unsigned int cpu) +static void qcom_cpu_die(unsigned int cpu) { wfi(); } diff --git a/arch/arm/mach-realview/hotplug.c b/arch/arm/mach-realview/hotplug.c index ac22dd41b135..968e2d1964f6 100644 --- a/arch/arm/mach-realview/hotplug.c +++ b/arch/arm/mach-realview/hotplug.c @@ -90,7 +90,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious) * * Called with IRQs disabled */ -void __ref realview_cpu_die(unsigned int cpu) +void realview_cpu_die(unsigned int cpu) { int spurious = 0; diff --git a/arch/arm/mach-spear/hotplug.c b/arch/arm/mach-spear/hotplug.c index d97749c642ce..12edd1cf8a12 100644 --- a/arch/arm/mach-spear/hotplug.c +++ b/arch/arm/mach-spear/hotplug.c @@ -80,7 +80,7 @@ static inline void spear13xx_do_lowpower(unsigned int cpu, int *spurious) * * Called with IRQs disabled */ -void __ref spear13xx_cpu_die(unsigned int cpu) +void spear13xx_cpu_die(unsigned int cpu) { int spurious = 0; diff --git a/arch/arm/mach-tegra/hotplug.c b/arch/arm/mach-tegra/hotplug.c index 6fc71f1534b0..1b129899a277 100644 --- a/arch/arm/mach-tegra/hotplug.c +++ b/arch/arm/mach-tegra/hotplug.c @@ -37,7 +37,7 @@ int tegra_cpu_kill(unsigned cpu) * * Called with IRQs disabled */ -void __ref tegra_cpu_die(unsigned int cpu) +void tegra_cpu_die(unsigned int cpu) { if (!tegra_hotplug_shutdown) { WARN(1, "hotplug is not yet initialized\n"); diff --git a/arch/arm/mach-ux500/hotplug.c b/arch/arm/mach-ux500/hotplug.c index 2bc00b085e38..1cbed0331fd3 100644 --- a/arch/arm/mach-ux500/hotplug.c +++ b/arch/arm/mach-ux500/hotplug.c @@ -21,7 +21,7 @@ * * Called with IRQs disabled */ -void __ref ux500_cpu_die(unsigned int cpu) +void ux500_cpu_die(unsigned int cpu) { /* directly enter low power state, skipping secure registers */ for (;;) { diff --git a/arch/arm/mach-vexpress/hotplug.c b/arch/arm/mach-vexpress/hotplug.c index f0ce6b8f5e71..f2fafc10a91d 100644 --- a/arch/arm/mach-vexpress/hotplug.c +++ b/arch/arm/mach-vexpress/hotplug.c @@ -85,7 +85,7 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious) * * Called with IRQs disabled */ -void __ref vexpress_cpu_die(unsigned int cpu) +void vexpress_cpu_die(unsigned int cpu) { int spurious = 0; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index cb71db3d578d..8944f2ab8fd7 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -19,6 +19,7 @@ config ARM64 select ARM_GIC_V2M if PCI_MSI select ARM_GIC_V3 select ARM_GIC_V3_ITS if PCI_MSI + select ARM_PSCI_FW select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select COMMON_CLK @@ -26,7 +27,7 @@ config ARM64 select DCACHE_WORD_ACCESS select GENERIC_ALLOCATOR select GENERIC_CLOCKEVENTS - select GENERIC_CLOCKEVENTS_BROADCAST if SMP + select GENERIC_CLOCKEVENTS_BROADCAST select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP select GENERIC_IRQ_PROBE @@ -138,6 +139,9 @@ config NEED_DMA_MAP_STATE config NEED_SG_DMA_LENGTH def_bool y +config SMP + def_bool y + config SWIOTLB def_bool y @@ -486,22 +490,8 @@ config CPU_BIG_ENDIAN help Say Y if you plan on running a kernel in big-endian mode. -config SMP - bool "Symmetric Multi-Processing" - help - This enables support for systems with more than one CPU. If - you say N here, the kernel will run on single and - multiprocessor machines, but will use only one CPU of a - multiprocessor machine. If you say Y here, the kernel will run - on many, but not all, single processor machines. On a single - processor machine, the kernel will run faster if you say N - here. - - If you don't know what to do here, say N. - config SCHED_MC bool "Multi-core scheduler support" - depends on SMP help Multi-core scheduler support improves the CPU scheduler's decision making when dealing with multi-core CPU chips at a cost of slightly @@ -509,7 +499,6 @@ config SCHED_MC config SCHED_SMT bool "SMT scheduler support" - depends on SMP help Improves the CPU scheduler's decision making when dealing with MultiThreading at a cost of slightly increased overhead in some @@ -518,23 +507,17 @@ config SCHED_SMT config NR_CPUS int "Maximum number of CPUs (2-4096)" range 2 4096 - depends on SMP # These have to remain sorted largest to smallest default "64" config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" - depends on SMP help Say Y here to experiment with turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. source kernel/Kconfig.preempt -config UP_LATE_INIT - def_bool y - depends on !SMP - config HZ int default 100 diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 59c05d8ea4a0..ed7e212c893c 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -12,8 +12,9 @@ #ifndef _ASM_ACPI_H #define _ASM_ACPI_H -#include <linux/mm.h> #include <linux/irqchip/arm-gic-acpi.h> +#include <linux/mm.h> +#include <linux/psci.h> #include <asm/cputype.h> #include <asm/smp_plat.h> @@ -39,18 +40,6 @@ extern int acpi_disabled; extern int acpi_noirq; extern int acpi_pci_disabled; -/* 1 to indicate PSCI 0.2+ is implemented */ -static inline bool acpi_psci_present(void) -{ - return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT; -} - -/* 1 to indicate HVC must be used instead of SMC as the PSCI conduit */ -static inline bool acpi_psci_use_hvc(void) -{ - return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC; -} - static inline void disable_acpi(void) { acpi_disabled = 1; @@ -88,9 +77,11 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { } void __init acpi_init_cpus(void); #else -static inline bool acpi_psci_present(void) { return false; } -static inline bool acpi_psci_use_hvc(void) { return false; } static inline void acpi_init_cpus(void) { } #endif /* CONFIG_ACPI */ +static inline const char *acpi_get_enable_method(int cpu) +{ + return acpi_psci_present() ? "psci" : NULL; +} #endif /*_ASM_ACPI_H*/ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 144b64ad96c3..706ceaf2577a 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -103,9 +103,7 @@ * SMP data memory barrier */ .macro smp_dmb, opt -#ifdef CONFIG_SMP dmb \opt -#endif .endm #define USER(l, x...) \ diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 71f19c4dc0de..2666c9b84ca0 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -35,28 +35,6 @@ #define dma_rmb() dmb(oshld) #define dma_wmb() dmb(oshst) -#ifndef CONFIG_SMP -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() - -#define smp_store_release(p, v) \ -do { \ - compiletime_assert_atomic_type(*p); \ - barrier(); \ - ACCESS_ONCE(*p) = (v); \ -} while (0) - -#define smp_load_acquire(p) \ -({ \ - typeof(*p) ___p1 = ACCESS_ONCE(*p); \ - compiletime_assert_atomic_type(*p); \ - barrier(); \ - ___p1; \ -}) - -#else - #define smp_mb() dmb(ish) #define smp_rmb() dmb(ishld) #define smp_wmb() dmb(ishst) @@ -109,8 +87,6 @@ do { \ ___p1; \ }) -#endif - #define read_barrier_depends() do { } while(0) #define smp_read_barrier_depends() do { } while(0) diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h index 5a31d6716914..8f03446cf89f 100644 --- a/arch/arm64/include/asm/cpu_ops.h +++ b/arch/arm64/include/asm/cpu_ops.h @@ -19,15 +19,15 @@ #include <linux/init.h> #include <linux/threads.h> -struct device_node; - /** * struct cpu_operations - Callback operations for hotplugging CPUs. * * @name: Name of the property as appears in a devicetree cpu node's - * enable-method property. - * @cpu_init: Reads any data necessary for a specific enable-method from the - * devicetree, for a given cpu node and proposed logical id. + * enable-method property. On systems booting with ACPI, @name + * identifies the struct cpu_operations entry corresponding to + * the boot protocol specified in the ACPI MADT table. + * @cpu_init: Reads any data necessary for a specific enable-method for a + * proposed logical id. * @cpu_prepare: Early one-time preparation step for a cpu. If there is a * mechanism for doing so, tests whether it is possible to boot * the given CPU. @@ -40,15 +40,15 @@ struct device_node; * @cpu_die: Makes a cpu leave the kernel. Must not fail. Called from the * cpu being killed. * @cpu_kill: Ensures a cpu has left the kernel. Called from another cpu. - * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from - * devicetree, for a given cpu node and proposed logical id. + * @cpu_init_idle: Reads any data necessary to initialize CPU idle states for + * a proposed logical id. * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing * to wrong parameters or error conditions. Called from the * CPU being suspended. Must be called with IRQs disabled. */ struct cpu_operations { const char *name; - int (*cpu_init)(struct device_node *, unsigned int); + int (*cpu_init)(unsigned int); int (*cpu_prepare)(unsigned int); int (*cpu_boot)(unsigned int); void (*cpu_postboot)(void); @@ -58,14 +58,17 @@ struct cpu_operations { int (*cpu_kill)(unsigned int cpu); #endif #ifdef CONFIG_CPU_IDLE - int (*cpu_init_idle)(struct device_node *, unsigned int); + int (*cpu_init_idle)(unsigned int); int (*cpu_suspend)(unsigned long); #endif }; extern const struct cpu_operations *cpu_ops[NR_CPUS]; -int __init cpu_read_ops(struct device_node *dn, int cpu); -void __init cpu_read_bootcpu_ops(void); -const struct cpu_operations *cpu_get_ops(const char *name); +int __init cpu_read_ops(int cpu); + +static inline void __init cpu_read_bootcpu_ops(void) +{ + cpu_read_ops(0); +} #endif /* ifndef __ASM_CPU_OPS_H */ diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h index 6aae421f4d73..2bb7009bdac7 100644 --- a/arch/arm64/include/asm/hardirq.h +++ b/arch/arm64/include/asm/hardirq.h @@ -24,9 +24,7 @@ typedef struct { unsigned int __softirq_pending; -#ifdef CONFIG_SMP unsigned int ipi_irqs[NR_IPI]; -#endif } ____cacheline_aligned irq_cpustat_t; #include <linux/irq_cpustat.h> /* Standard mappings for irq_cpustat_t above */ @@ -34,10 +32,8 @@ typedef struct { #define __inc_irq_stat(cpu, member) __IRQ_STAT(cpu, member)++ #define __get_irq_stat(cpu, member) __IRQ_STAT(cpu, member) -#ifdef CONFIG_SMP u64 smp_irq_stat_cpu(unsigned int cpu); #define arch_irq_stat_cpu smp_irq_stat_cpu -#endif #define __ARCH_IRQ_EXIT_IRQS_DISABLED 1 diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h index b4f6b19a8a68..8e24ef3f7c82 100644 --- a/arch/arm64/include/asm/irq_work.h +++ b/arch/arm64/include/asm/irq_work.h @@ -1,8 +1,6 @@ #ifndef __ASM_IRQ_WORK_H #define __ASM_IRQ_WORK_H -#ifdef CONFIG_SMP - #include <asm/smp.h> static inline bool arch_irq_work_has_interrupt(void) @@ -10,13 +8,4 @@ static inline bool arch_irq_work_has_interrupt(void) return !!__smp_cross_call; } -#else - -static inline bool arch_irq_work_has_interrupt(void) -{ - return false; -} - -#endif - #endif /* __ASM_IRQ_WORK_H */ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 4fde8c1df97f..0a456bef8c79 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -16,8 +16,6 @@ #ifndef __ASM_PERCPU_H #define __ASM_PERCPU_H -#ifdef CONFIG_SMP - static inline void set_my_cpu_offset(unsigned long off) { asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory"); @@ -38,12 +36,6 @@ static inline unsigned long __my_cpu_offset(void) } #define __my_cpu_offset __my_cpu_offset() -#else /* !CONFIG_SMP */ - -#define set_my_cpu_offset(x) do { } while (0) - -#endif /* CONFIG_SMP */ - #define PERCPU_OP(op, asm_op) \ static inline unsigned long __percpu_##op(void *ptr, \ unsigned long val, int size) \ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index cf7319422768..f35ac429d42b 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -53,13 +53,8 @@ extern void __pmd_error(const char *file, int line, unsigned long val); extern void __pud_error(const char *file, int line, unsigned long val); extern void __pgd_error(const char *file, int line, unsigned long val); -#ifdef CONFIG_SMP #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#else -#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF) -#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF) -#endif #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC)) diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h deleted file mode 100644 index 2454bc59c916..000000000000 --- a/arch/arm64/include/asm/psci.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * 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. - * - * Copyright (C) 2013 ARM Limited - */ - -#ifndef __ASM_PSCI_H -#define __ASM_PSCI_H - -int psci_dt_init(void); -int psci_acpi_init(void); - -#endif /* __ASM_PSCI_H */ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index d4264bb0a409..e9e5467e0bf4 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -183,11 +183,7 @@ static inline int valid_user_regs(struct user_pt_regs *regs) #define instruction_pointer(regs) ((unsigned long)(regs)->pc) -#ifdef CONFIG_SMP extern unsigned long profile_pc(struct pt_regs *regs); -#else -#define profile_pc(regs) instruction_pointer(regs) -#endif #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index bf22650b1a78..d9c3d6a6100a 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -20,10 +20,6 @@ #include <linux/cpumask.h> #include <linux/thread_info.h> -#ifndef CONFIG_SMP -# error "<asm/smp.h> included in non-SMP build" -#endif - #define raw_smp_processor_id() (current_thread_info()->cpu) struct seq_file; @@ -42,7 +38,7 @@ extern void handle_IPI(int ipinr, struct pt_regs *regs); * Discover the set of possible CPUs and determine their * SMP operations. */ -extern void of_smp_init_cpus(void); +extern void smp_init_cpus(void); /* * Provide a function to raise an IPI cross call on CPUs in callmap. diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h index 8dcd61e32176..7abf7570c00f 100644 --- a/arch/arm64/include/asm/smp_plat.h +++ b/arch/arm64/include/asm/smp_plat.h @@ -19,6 +19,8 @@ #ifndef __ASM_SMP_PLAT_H #define __ASM_SMP_PLAT_H +#include <linux/cpumask.h> + #include <asm/types.h> struct mpidr_hash { @@ -39,6 +41,20 @@ static inline u32 mpidr_hash_size(void) */ extern u64 __cpu_logical_map[NR_CPUS]; #define cpu_logical_map(cpu) __cpu_logical_map[cpu] +/* + * Retrieve logical cpu index corresponding to a given MPIDR.Aff* + * - mpidr: MPIDR.Aff* bits to be used for the look-up + * + * Returns the cpu logical index or -EINVAL on look-up error + */ +static inline int get_logical_index(u64 mpidr) +{ + int cpu; + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + if (cpu_logical_map(cpu) == mpidr) + return cpu; + return -EINVAL; +} void __init do_post_cpus_up_work(void); diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 7ebcd31ce51c..65e9c4615664 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -1,8 +1,6 @@ #ifndef __ASM_TOPOLOGY_H #define __ASM_TOPOLOGY_H -#ifdef CONFIG_SMP - #include <linux/cpumask.h> struct cpu_topology { @@ -24,13 +22,6 @@ void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); -#else - -static inline void init_cpu_topology(void) { } -static inline void store_cpu_topology(unsigned int cpuid) { } - -#endif - #include <asm-generic/topology.h> #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 426d0763c81b..c24f5718d484 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -17,7 +17,8 @@ arm64-obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ sys.o stacktrace.o time.o traps.o io.o vdso.o \ hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o \ return_address.o cpuinfo.o cpu_errata.o \ - cpufeature.o alternative.o cacheinfo.o + cpufeature.o alternative.o cacheinfo.o \ + smp.o smp_spin_table.o topology.o arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ sys_compat.o entry32.o \ diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 8b839558838e..19de7537e7d3 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -36,12 +36,6 @@ EXPORT_SYMBOL(acpi_disabled); int acpi_pci_disabled = 1; /* skip ACPI PCI scan and IRQ initialization */ EXPORT_SYMBOL(acpi_pci_disabled); -/* Processors with enabled flag and sane MPIDR */ -static int enabled_cpus; - -/* Boot CPU is valid or not in MADT */ -static bool bootcpu_valid __initdata; - static bool param_acpi_off __initdata; static bool param_acpi_force __initdata; @@ -95,122 +89,15 @@ void __init __acpi_unmap_table(char *map, unsigned long size) early_memunmap(map, size); } -/** - * acpi_map_gic_cpu_interface - generates a logical cpu number - * and map to MPIDR represented by GICC structure - */ -static void __init -acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) +bool __init acpi_psci_present(void) { - int i; - u64 mpidr = processor->arm_mpidr & MPIDR_HWID_BITMASK; - bool enabled = !!(processor->flags & ACPI_MADT_ENABLED); - - if (mpidr == INVALID_HWID) { - pr_info("Skip MADT cpu entry with invalid MPIDR\n"); - return; - } - - total_cpus++; - if (!enabled) - return; - - if (enabled_cpus >= NR_CPUS) { - pr_warn("NR_CPUS limit of %d reached, Processor %d/0x%llx ignored.\n", - NR_CPUS, total_cpus, mpidr); - return; - } - - /* Check if GICC structure of boot CPU is available in the MADT */ - if (cpu_logical_map(0) == mpidr) { - if (bootcpu_valid) { - pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n", - mpidr); - return; - } - - bootcpu_valid = true; - } - - /* - * Duplicate MPIDRs are a recipe for disaster. Scan - * all initialized entries and check for - * duplicates. If any is found just ignore the CPU. - */ - for (i = 1; i < enabled_cpus; i++) { - if (cpu_logical_map(i) == mpidr) { - pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n", - mpidr); - return; - } - } - - if (!acpi_psci_present()) - return; - - cpu_ops[enabled_cpus] = cpu_get_ops("psci"); - /* CPU 0 was already initialized */ - if (enabled_cpus) { - if (!cpu_ops[enabled_cpus]) - return; - - if (cpu_ops[enabled_cpus]->cpu_init(NULL, enabled_cpus)) - return; - - /* map the logical cpu id to cpu MPIDR */ - cpu_logical_map(enabled_cpus) = mpidr; - } - - enabled_cpus++; + return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT; } -static int __init -acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, - const unsigned long end) +/* Whether HVC must be used instead of SMC as the PSCI conduit */ +bool __init acpi_psci_use_hvc(void) { - struct acpi_madt_generic_interrupt *processor; - - processor = (struct acpi_madt_generic_interrupt *)header; - - if (BAD_MADT_ENTRY(processor, end)) - return -EINVAL; - - acpi_table_print_madt_entry(header); - acpi_map_gic_cpu_interface(processor); - return 0; -} - -/* Parse GIC cpu interface entries in MADT for SMP init */ -void __init acpi_init_cpus(void) -{ - int count, i; - - /* - * do a partial walk of MADT to determine how many CPUs - * we have including disabled CPUs, and get information - * we need for SMP init - */ - count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, - acpi_parse_gic_cpu_interface, 0); - - if (!count) { - pr_err("No GIC CPU interface entries present\n"); - return; - } else if (count < 0) { - pr_err("Error parsing GIC CPU interface entry\n"); - return; - } - - if (!bootcpu_valid) { - pr_err("MADT missing boot CPU MPIDR, not enabling secondaries\n"); - return; - } - - for (i = 0; i < enabled_cpus; i++) - set_cpu_possible(i, true); - - /* Make boot-up look pretty */ - pr_info("%d CPUs enabled, %d CPUs total\n", enabled_cpus, total_cpus); + return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC; } /* diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c index fb8ff9ba467a..b6bd7d447768 100644 --- a/arch/arm64/kernel/cpu_ops.c +++ b/arch/arm64/kernel/cpu_ops.c @@ -16,11 +16,13 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ -#include <asm/cpu_ops.h> -#include <asm/smp_plat.h> +#include <linux/acpi.h> #include <linux/errno.h> #include <linux/of.h> #include <linux/string.h> +#include <asm/acpi.h> +#include <asm/cpu_ops.h> +#include <asm/smp_plat.h> extern const struct cpu_operations smp_spin_table_ops; extern const struct cpu_operations cpu_psci_ops; @@ -28,14 +30,12 @@ extern const struct cpu_operations cpu_psci_ops; const struct cpu_operations *cpu_ops[NR_CPUS]; static const struct cpu_operations *supported_cpu_ops[] __initconst = { -#ifdef CONFIG_SMP &smp_spin_table_ops, -#endif &cpu_psci_ops, NULL, }; -const struct cpu_operations * __init cpu_get_ops(const char *name) +static const struct cpu_operations * __init cpu_get_ops(const char *name) { const struct cpu_operations **ops = supported_cpu_ops; @@ -49,39 +49,53 @@ const struct cpu_operations * __init cpu_get_ops(const char *name) return NULL; } +static const char *__init cpu_read_enable_method(int cpu) +{ + const char *enable_method; + + if (acpi_disabled) { + struct device_node *dn = of_get_cpu_node(cpu, NULL); + + if (!dn) { + if (!cpu) + pr_err("Failed to find device node for boot cpu\n"); + return NULL; + } + + enable_method = of_get_property(dn, "enable-method", NULL); + if (!enable_method) { + /* + * The boot CPU may not have an enable method (e.g. + * when spin-table is used for secondaries). + * Don't warn spuriously. + */ + if (cpu != 0) + pr_err("%s: missing enable-method property\n", + dn->full_name); + } + } else { + enable_method = acpi_get_enable_method(cpu); + if (!enable_method) + pr_err("Unsupported ACPI enable-method\n"); + } + + return enable_method; +} /* - * Read a cpu's enable method from the device tree and record it in cpu_ops. + * Read a cpu's enable method and record it in cpu_ops. */ -int __init cpu_read_ops(struct device_node *dn, int cpu) +int __init cpu_read_ops(int cpu) { - const char *enable_method = of_get_property(dn, "enable-method", NULL); - if (!enable_method) { - /* - * The boot CPU may not have an enable method (e.g. when - * spin-table is used for secondaries). Don't warn spuriously. - */ - if (cpu != 0) - pr_err("%s: missing enable-method property\n", - dn->full_name); - return -ENOENT; - } + const char *enable_method = cpu_read_enable_method(cpu); + + if (!enable_method) + return -ENODEV; cpu_ops[cpu] = cpu_get_ops(enable_method); if (!cpu_ops[cpu]) { - pr_warn("%s: unsupported enable-method property: %s\n", - dn->full_name, enable_method); + pr_warn("Unsupported enable-method: %s\n", enable_method); return -EOPNOTSUPP; } return 0; } - -void __init cpu_read_bootcpu_ops(void) -{ - struct device_node *dn = of_get_cpu_node(0, NULL); - if (!dn) { - pr_err("Failed to find device node for boot cpu\n"); - return; - } - cpu_read_ops(dn, 0); -} diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index 2bbd0fee084f..7ce589ca54a4 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -18,15 +18,10 @@ int arm_cpuidle_init(unsigned int cpu) { int ret = -EOPNOTSUPP; - struct device_node *cpu_node = of_cpu_device_node_get(cpu); - - if (!cpu_node) - return -ENODEV; if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle) - ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu); + ret = cpu_ops[cpu]->cpu_init_idle(cpu); - of_node_put(cpu_node); return ret; } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 36aa31ff2c06..e0c458abafb1 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -62,13 +62,8 @@ /* * Initial memory map attributes. */ -#ifndef CONFIG_SMP -#define PTE_FLAGS PTE_TYPE_PAGE | PTE_AF -#define PMD_FLAGS PMD_TYPE_SECT | PMD_SECT_AF -#else #define PTE_FLAGS PTE_TYPE_PAGE | PTE_AF | PTE_SHARED #define PMD_FLAGS PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S -#endif #ifdef CONFIG_ARM64_64K_PAGES #define MM_MMUFLAGS PTE_ATTRINDX(MT_NORMAL) | PTE_FLAGS @@ -382,7 +377,7 @@ __create_page_tables: * Create the identity mapping. */ mov x0, x25 // idmap_pg_dir - adrp x3, KERNEL_START // __pa(KERNEL_START) + adrp x3, __idmap_text_start // __pa(__idmap_text_start) #ifndef CONFIG_ARM64_VA_BITS_48 #define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3) @@ -405,11 +400,11 @@ __create_page_tables: /* * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the - * entire kernel image can be ID mapped. As T0SZ == (64 - #bits used), + * entire ID map region can be mapped. As T0SZ == (64 - #bits used), * this number conveniently equals the number of leading zeroes in - * the physical address of KERNEL_END. + * the physical address of __idmap_text_end. */ - adrp x5, KERNEL_END + adrp x5, __idmap_text_end clz x5, x5 cmp x5, TCR_T0SZ(VA_BITS) // default T0SZ small enough? b.ge 1f // .. then skip additional level @@ -424,8 +419,8 @@ __create_page_tables: #endif create_pgd_entry x0, x3, x5, x6 - mov x5, x3 // __pa(KERNEL_START) - adr_l x6, KERNEL_END // __pa(KERNEL_END) + mov x5, x3 // __pa(__idmap_text_start) + adr_l x6, __idmap_text_end // __pa(__idmap_text_end) create_block_map x0, x7, x3, x5, x6 /* @@ -616,7 +611,6 @@ ENTRY(__boot_cpu_mode) .long BOOT_CPU_MODE_EL1 .popsection -#ifdef CONFIG_SMP /* * This provides a "holding pen" for platforms to hold all secondary * cores are held until we're ready for them to initialise. @@ -664,7 +658,6 @@ ENTRY(__secondary_switched) mov x29, #0 b secondary_start_kernel ENDPROC(__secondary_switched) -#endif /* CONFIG_SMP */ /* * Enable the MMU. @@ -674,6 +667,7 @@ ENDPROC(__secondary_switched) * * other registers depend on the function called upon completion */ + .section ".idmap.text", "ax" __enable_mmu: ldr x5, =vectors msr vbar_el1, x5 diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 240b75c0e94f..de99d4bd31bb 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -33,9 +33,7 @@ unsigned long irq_err_count; int arch_show_interrupts(struct seq_file *p, int prec) { -#ifdef CONFIG_SMP show_ipi_list(p, prec); -#endif seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count); return 0; } diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 24d4733b7e3c..f67f35b6edb1 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -15,183 +15,32 @@ #define pr_fmt(fmt) "psci: " fmt -#include <linux/acpi.h> #include <linux/init.h> #include <linux/of.h> #include <linux/smp.h> -#include <linux/reboot.h> -#include <linux/pm.h> #include <linux/delay.h> +#include <linux/psci.h> #include <linux/slab.h> + #include <uapi/linux/psci.h> -#include <asm/acpi.h> #include <asm/compiler.h> #include <asm/cpu_ops.h> #include <asm/errno.h> -#include <asm/psci.h> #include <asm/smp_plat.h> #include <asm/suspend.h> -#include <asm/system_misc.h> - -#define PSCI_POWER_STATE_TYPE_STANDBY 0 -#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 - -struct psci_power_state { - u16 id; - u8 type; - u8 affinity_level; -}; - -struct psci_operations { - int (*cpu_suspend)(struct psci_power_state state, - unsigned long entry_point); - int (*cpu_off)(struct psci_power_state state); - int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); - int (*migrate)(unsigned long cpuid); - int (*affinity_info)(unsigned long target_affinity, - unsigned long lowest_affinity_level); - int (*migrate_info_type)(void); -}; - -static struct psci_operations psci_ops; - -static int (*invoke_psci_fn)(u64, u64, u64, u64); -typedef int (*psci_initcall_t)(const struct device_node *); - -asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64); -asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64); - -enum psci_function { - PSCI_FN_CPU_SUSPEND, - PSCI_FN_CPU_ON, - PSCI_FN_CPU_OFF, - PSCI_FN_MIGRATE, - PSCI_FN_AFFINITY_INFO, - PSCI_FN_MIGRATE_INFO_TYPE, - PSCI_FN_MAX, -}; - -static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state); - -static u32 psci_function_id[PSCI_FN_MAX]; - -static int psci_to_linux_errno(int errno) -{ - switch (errno) { - case PSCI_RET_SUCCESS: - return 0; - case PSCI_RET_NOT_SUPPORTED: - return -EOPNOTSUPP; - case PSCI_RET_INVALID_PARAMS: - return -EINVAL; - case PSCI_RET_DENIED: - return -EPERM; - }; - - return -EINVAL; -} - -static u32 psci_power_state_pack(struct psci_power_state state) -{ - return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT) - & PSCI_0_2_POWER_STATE_ID_MASK) | - ((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT) - & PSCI_0_2_POWER_STATE_TYPE_MASK) | - ((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT) - & PSCI_0_2_POWER_STATE_AFFL_MASK); -} - -static void psci_power_state_unpack(u32 power_state, - struct psci_power_state *state) -{ - state->id = (power_state & PSCI_0_2_POWER_STATE_ID_MASK) >> - PSCI_0_2_POWER_STATE_ID_SHIFT; - state->type = (power_state & PSCI_0_2_POWER_STATE_TYPE_MASK) >> - PSCI_0_2_POWER_STATE_TYPE_SHIFT; - state->affinity_level = - (power_state & PSCI_0_2_POWER_STATE_AFFL_MASK) >> - PSCI_0_2_POWER_STATE_AFFL_SHIFT; -} - -static int psci_get_version(void) -{ - int err; - - err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0); - return err; -} - -static int psci_cpu_suspend(struct psci_power_state state, - unsigned long entry_point) -{ - int err; - u32 fn, power_state; - - fn = psci_function_id[PSCI_FN_CPU_SUSPEND]; - power_state = psci_power_state_pack(state); - err = invoke_psci_fn(fn, power_state, entry_point, 0); - return psci_to_linux_errno(err); -} -static int psci_cpu_off(struct psci_power_state state) -{ - int err; - u32 fn, power_state; +static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state); - fn = psci_function_id[PSCI_FN_CPU_OFF]; - power_state = psci_power_state_pack(state); - err = invoke_psci_fn(fn, power_state, 0, 0); - return psci_to_linux_errno(err); -} - -static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_CPU_ON]; - err = invoke_psci_fn(fn, cpuid, entry_point, 0); - return psci_to_linux_errno(err); -} - -static int psci_migrate(unsigned long cpuid) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_MIGRATE]; - err = invoke_psci_fn(fn, cpuid, 0, 0); - return psci_to_linux_errno(err); -} - -static int psci_affinity_info(unsigned long target_affinity, - unsigned long lowest_affinity_level) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_AFFINITY_INFO]; - err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0); - return err; -} - -static int psci_migrate_info_type(void) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE]; - err = invoke_psci_fn(fn, 0, 0, 0); - return err; -} - -static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node, - unsigned int cpu) +static int __maybe_unused cpu_psci_cpu_init_idle(unsigned int cpu) { int i, ret, count = 0; - struct psci_power_state *psci_states; - struct device_node *state_node; + u32 *psci_states; + struct device_node *state_node, *cpu_node; + + cpu_node = of_get_cpu_node(cpu, NULL); + if (!cpu_node) + return -ENODEV; /* * If the PSCI cpu_suspend function hook has not been initialized @@ -215,13 +64,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node, return -ENOMEM; for (i = 0; i < count; i++) { - u32 psci_power_state; + u32 state; state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i); ret = of_property_read_u32(state_node, "arm,psci-suspend-param", - &psci_power_state); + &state); if (ret) { pr_warn(" * %s missing arm,psci-suspend-param property\n", state_node->full_name); @@ -230,9 +79,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node, } of_node_put(state_node); - pr_debug("psci-power-state %#x index %d\n", psci_power_state, - i); - psci_power_state_unpack(psci_power_state, &psci_states[i]); + pr_debug("psci-power-state %#x index %d\n", state, i); + if (!psci_power_state_is_valid(state)) { + pr_warn("Invalid PSCI power state %#x\n", state); + ret = -EINVAL; + goto free_mem; + } + psci_states[i] = state; } /* Idle states parsed correctly, initialize per-cpu pointer */ per_cpu(psci_power_state, cpu) = psci_states; @@ -243,208 +96,7 @@ free_mem: return ret; } -static int get_set_conduit_method(struct device_node *np) -{ - const char *method; - - pr_info("probing for conduit method from DT.\n"); - - if (of_property_read_string(np, "method", &method)) { - pr_warn("missing \"method\" property\n"); - return -ENXIO; - } - - if (!strcmp("hvc", method)) { - invoke_psci_fn = __invoke_psci_fn_hvc; - } else if (!strcmp("smc", method)) { - invoke_psci_fn = __invoke_psci_fn_smc; - } else { - pr_warn("invalid \"method\" property: %s\n", method); - return -EINVAL; - } - return 0; -} - -static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd) -{ - invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0); -} - -static void psci_sys_poweroff(void) -{ - invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0); -} - -static void __init psci_0_2_set_functions(void) -{ - pr_info("Using standard PSCI v0.2 function IDs\n"); - psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN64_CPU_SUSPEND; - psci_ops.cpu_suspend = psci_cpu_suspend; - - psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF; - psci_ops.cpu_off = psci_cpu_off; - - psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN64_CPU_ON; - psci_ops.cpu_on = psci_cpu_on; - - psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN64_MIGRATE; - psci_ops.migrate = psci_migrate; - - psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN64_AFFINITY_INFO; - psci_ops.affinity_info = psci_affinity_info; - - psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] = - PSCI_0_2_FN_MIGRATE_INFO_TYPE; - psci_ops.migrate_info_type = psci_migrate_info_type; - - arm_pm_restart = psci_sys_reset; - - pm_power_off = psci_sys_poweroff; -} - -/* - * Probe function for PSCI firmware versions >= 0.2 - */ -static int __init psci_probe(void) -{ - int ver = psci_get_version(); - - if (ver == PSCI_RET_NOT_SUPPORTED) { - /* - * PSCI versions >=0.2 mandates implementation of - * PSCI_VERSION. - */ - pr_err("PSCI firmware does not comply with the v0.2 spec.\n"); - return -EOPNOTSUPP; - } else { - pr_info("PSCIv%d.%d detected in firmware.\n", - PSCI_VERSION_MAJOR(ver), - PSCI_VERSION_MINOR(ver)); - - if (PSCI_VERSION_MAJOR(ver) == 0 && - PSCI_VERSION_MINOR(ver) < 2) { - pr_err("Conflicting PSCI version detected.\n"); - return -EINVAL; - } - } - - psci_0_2_set_functions(); - - return 0; -} - -/* - * PSCI init function for PSCI versions >=0.2 - * - * Probe based on PSCI PSCI_VERSION function - */ -static int __init psci_0_2_init(struct device_node *np) -{ - int err; - - err = get_set_conduit_method(np); - - if (err) - goto out_put_node; - /* - * Starting with v0.2, the PSCI specification introduced a call - * (PSCI_VERSION) that allows probing the firmware version, so - * that PSCI function IDs and version specific initialization - * can be carried out according to the specific version reported - * by firmware - */ - err = psci_probe(); - -out_put_node: - of_node_put(np); - return err; -} - -/* - * PSCI < v0.2 get PSCI Function IDs via DT. - */ -static int __init psci_0_1_init(struct device_node *np) -{ - u32 id; - int err; - - err = get_set_conduit_method(np); - - if (err) - goto out_put_node; - - pr_info("Using PSCI v0.1 Function IDs from DT\n"); - - if (!of_property_read_u32(np, "cpu_suspend", &id)) { - psci_function_id[PSCI_FN_CPU_SUSPEND] = id; - psci_ops.cpu_suspend = psci_cpu_suspend; - } - - if (!of_property_read_u32(np, "cpu_off", &id)) { - psci_function_id[PSCI_FN_CPU_OFF] = id; - psci_ops.cpu_off = psci_cpu_off; - } - - if (!of_property_read_u32(np, "cpu_on", &id)) { - psci_function_id[PSCI_FN_CPU_ON] = id; - psci_ops.cpu_on = psci_cpu_on; - } - - if (!of_property_read_u32(np, "migrate", &id)) { - psci_function_id[PSCI_FN_MIGRATE] = id; - psci_ops.migrate = psci_migrate; - } - -out_put_node: - of_node_put(np); - return err; -} - -static const struct of_device_id psci_of_match[] __initconst = { - { .compatible = "arm,psci", .data = psci_0_1_init}, - { .compatible = "arm,psci-0.2", .data = psci_0_2_init}, - {}, -}; - -int __init psci_dt_init(void) -{ - struct device_node *np; - const struct of_device_id *matched_np; - psci_initcall_t init_fn; - - np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np); - - if (!np) - return -ENODEV; - - init_fn = (psci_initcall_t)matched_np->data; - return init_fn(np); -} - -/* - * We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's - * explicitly clarified in SBBR - */ -int __init psci_acpi_init(void) -{ - if (!acpi_psci_present()) { - pr_info("is not implemented in ACPI.\n"); - return -EOPNOTSUPP; - } - - pr_info("probing for conduit method from ACPI.\n"); - - if (acpi_psci_use_hvc()) - invoke_psci_fn = __invoke_psci_fn_hvc; - else - invoke_psci_fn = __invoke_psci_fn_smc; - - return psci_probe(); -} - -#ifdef CONFIG_SMP - -static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu) +static int __init cpu_psci_cpu_init(unsigned int cpu) { return 0; } @@ -474,6 +126,11 @@ static int cpu_psci_cpu_disable(unsigned int cpu) /* Fail early if we don't have CPU_OFF support */ if (!psci_ops.cpu_off) return -EOPNOTSUPP; + + /* Trusted OS will deny CPU_OFF */ + if (psci_tos_resident_on(cpu)) + return -EPERM; + return 0; } @@ -484,9 +141,8 @@ static void cpu_psci_cpu_die(unsigned int cpu) * There are no known implementations of PSCI actually using the * power state field, pass a sensible default for now. */ - struct psci_power_state state = { - .type = PSCI_POWER_STATE_TYPE_POWER_DOWN, - }; + u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << + PSCI_0_2_POWER_STATE_TYPE_SHIFT; ret = psci_ops.cpu_off(state); @@ -498,7 +154,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu) int err, i; if (!psci_ops.affinity_info) - return 1; + return 0; /* * cpu_kill could race with cpu_die and we can * potentially end up declaring this cpu undead @@ -509,7 +165,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu) err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { pr_info("CPU%d killed.\n", cpu); - return 1; + return 0; } msleep(10); @@ -518,15 +174,13 @@ static int cpu_psci_cpu_kill(unsigned int cpu) pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", cpu, err); - /* Make op_cpu_kill() fail. */ - return 0; + return -ETIMEDOUT; } #endif -#endif static int psci_suspend_finisher(unsigned long index) { - struct psci_power_state *state = __this_cpu_read(psci_power_state); + u32 *state = __this_cpu_read(psci_power_state); return psci_ops.cpu_suspend(state[index - 1], virt_to_phys(cpu_resume)); @@ -535,7 +189,7 @@ static int psci_suspend_finisher(unsigned long index) static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index) { int ret; - struct psci_power_state *state = __this_cpu_read(psci_power_state); + u32 *state = __this_cpu_read(psci_power_state); /* * idle state index 0 corresponds to wfi, should never be called * from the cpu_suspend operations @@ -543,7 +197,7 @@ static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index) if (WARN_ON_ONCE(!index)) return -EINVAL; - if (state[index - 1].type == PSCI_POWER_STATE_TYPE_STANDBY) + if (!psci_power_state_loses_context(state[index - 1])) ret = psci_ops.cpu_suspend(state[index - 1], 0); else ret = cpu_suspend(index, psci_suspend_finisher); @@ -557,7 +211,6 @@ const struct cpu_operations cpu_psci_ops = { .cpu_init_idle = cpu_psci_cpu_init_idle, .cpu_suspend = cpu_psci_cpu_suspend, #endif -#ifdef CONFIG_SMP .cpu_init = cpu_psci_cpu_init, .cpu_prepare = cpu_psci_cpu_prepare, .cpu_boot = cpu_psci_cpu_boot, @@ -566,6 +219,5 @@ const struct cpu_operations cpu_psci_ops = { .cpu_die = cpu_psci_cpu_die, .cpu_kill = cpu_psci_cpu_kill, #endif -#endif }; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 74753132c3ac..e5202836dc64 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -46,6 +46,7 @@ #include <linux/of_platform.h> #include <linux/efi.h> #include <linux/personality.h> +#include <linux/psci.h> #include <asm/acpi.h> #include <asm/fixmap.h> @@ -61,7 +62,6 @@ #include <asm/tlbflush.h> #include <asm/traps.h> #include <asm/memblock.h> -#include <asm/psci.h> #include <asm/efi.h> #include <asm/virt.h> @@ -142,7 +142,6 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id) } struct mpidr_hash mpidr_hash; -#ifdef CONFIG_SMP /** * smp_build_mpidr_hash - Pre-compute shifts required at each affinity * level in order to build a linear index from an @@ -208,7 +207,6 @@ static void __init smp_build_mpidr_hash(void) pr_warn("Large number of MPIDR hash buckets detected\n"); __flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash)); } -#endif static void __init hyp_mode_check(void) { @@ -408,18 +406,13 @@ void __init setup_arch(char **cmdline_p) if (acpi_disabled) { unflatten_device_tree(); psci_dt_init(); - cpu_read_bootcpu_ops(); -#ifdef CONFIG_SMP - of_smp_init_cpus(); -#endif } else { psci_acpi_init(); - acpi_init_cpus(); } -#ifdef CONFIG_SMP + cpu_read_bootcpu_ops(); + smp_init_cpus(); smp_build_mpidr_hash(); -#endif #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) @@ -519,9 +512,7 @@ static int c_show(struct seq_file *m, void *v) * online processors, looking for lines beginning with * "processor". Give glibc what it expects. */ -#ifdef CONFIG_SMP seq_printf(m, "processor\t: %d\n", i); -#endif /* * Dump out the common processor features in a single line. diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index ede186cdd452..5686a3ae3940 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -82,7 +82,6 @@ ENTRY(__cpu_suspend_enter) str x2, [x0, #CPU_CTX_SP] ldr x1, =sleep_save_sp ldr x1, [x1, #SLEEP_SAVE_SP_VIRT] -#ifdef CONFIG_SMP mrs x7, mpidr_el1 ldr x9, =mpidr_hash ldr x10, [x9, #MPIDR_HASH_MASK] @@ -94,7 +93,6 @@ ENTRY(__cpu_suspend_enter) ldp w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)] compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10 add x1, x1, x8, lsl #3 -#endif bl __cpu_suspend_save /* * Grab suspend finisher in x20 and its argument in x19 @@ -130,12 +128,14 @@ ENDPROC(__cpu_suspend_enter) /* * x0 must contain the sctlr value retrieved from restored context */ + .pushsection ".idmap.text", "ax" ENTRY(cpu_resume_mmu) ldr x3, =cpu_resume_after_mmu msr sctlr_el1, x0 // restore sctlr_el1 isb br x3 // global jump to virtual address ENDPROC(cpu_resume_mmu) + .popsection cpu_resume_after_mmu: mov x0, #0 // return zero on success ldp x19, x20, [sp, #16] @@ -149,7 +149,6 @@ ENDPROC(cpu_resume_after_mmu) ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly -#ifdef CONFIG_SMP mrs x1, mpidr_el1 adrp x8, mpidr_hash add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address @@ -159,18 +158,13 @@ ENTRY(cpu_resume) ldp w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)] compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2 /* x7 contains hash index, let's use it to grab context pointer */ -#else mov x7, xzr -#endif - adrp x0, sleep_save_sp - add x0, x0, #:lo12:sleep_save_sp - ldr x0, [x0, #SLEEP_SAVE_SP_PHYS] + ldr_l x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS ldr x0, [x0, x7, lsl #3] /* load sp from context */ ldr x2, [x0, #CPU_CTX_SP] - adrp x1, sleep_idmap_phys /* load physical address of identity map page table in x1 */ - ldr x1, [x1, #:lo12:sleep_idmap_phys] + adrp x1, idmap_pg_dir mov sp, x2 /* * cpu_do_resume expects x0 to contain context physical address diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d3a202b85ba6..a1e6ed5f0d06 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -17,6 +17,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/acpi.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/spinlock.h> @@ -248,7 +249,7 @@ static int op_cpu_kill(unsigned int cpu) * time and hope that it's dead, so let's skip the wait and just hope. */ if (!cpu_ops[cpu]->cpu_kill) - return 1; + return 0; return cpu_ops[cpu]->cpu_kill(cpu); } @@ -261,6 +262,8 @@ static DECLARE_COMPLETION(cpu_died); */ void __cpu_die(unsigned int cpu) { + int err; + if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) { pr_crit("CPU%u: cpu didn't die\n", cpu); return; @@ -273,8 +276,10 @@ void __cpu_die(unsigned int cpu) * verify that it has really left the kernel before we consider * clobbering anything it might still be using. */ - if (!op_cpu_kill(cpu)) - pr_warn("CPU%d may not have shut down cleanly\n", cpu); + err = op_cpu_kill(cpu); + if (err) + pr_warn("CPU%d may not have shut down cleanly: %d\n", + cpu, err); } /* @@ -318,57 +323,158 @@ void __init smp_prepare_boot_cpu(void) set_my_cpu_offset(per_cpu_offset(smp_processor_id())); } +static u64 __init of_get_cpu_mpidr(struct device_node *dn) +{ + const __be32 *cell; + u64 hwid; + + /* + * A cpu node with missing "reg" property is + * considered invalid to build a cpu_logical_map + * entry. + */ + cell = of_get_property(dn, "reg", NULL); + if (!cell) { + pr_err("%s: missing reg property\n", dn->full_name); + return INVALID_HWID; + } + + hwid = of_read_number(cell, of_n_addr_cells(dn)); + /* + * Non affinity bits must be set to 0 in the DT + */ + if (hwid & ~MPIDR_HWID_BITMASK) { + pr_err("%s: invalid reg property\n", dn->full_name); + return INVALID_HWID; + } + return hwid; +} + +/* + * Duplicate MPIDRs are a recipe for disaster. Scan all initialized + * entries and check for duplicates. If any is found just ignore the + * cpu. cpu_logical_map was initialized to INVALID_HWID to avoid + * matching valid MPIDR values. + */ +static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid) +{ + unsigned int i; + + for (i = 1; (i < cpu) && (i < NR_CPUS); i++) + if (cpu_logical_map(i) == hwid) + return true; + return false; +} + +/* + * Initialize cpu operations for a logical cpu and + * set it in the possible mask on success + */ +static int __init smp_cpu_setup(int cpu) +{ + if (cpu_read_ops(cpu)) + return -ENODEV; + + if (cpu_ops[cpu]->cpu_init(cpu)) + return -ENODEV; + + set_cpu_possible(cpu, true); + + return 0; +} + +static bool bootcpu_valid __initdata; +static unsigned int cpu_count = 1; + +#ifdef CONFIG_ACPI +/* + * acpi_map_gic_cpu_interface - parse processor MADT entry + * + * Carry out sanity checks on MADT processor entry and initialize + * cpu_logical_map on success + */ +static void __init +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); + return; + } + + if (!(processor->flags & ACPI_MADT_ENABLED)) { + pr_err("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid); + return; + } + + if (is_mpidr_duplicate(cpu_count, hwid)) { + pr_err("duplicate CPU MPIDR 0x%llx in MADT\n", hwid); + return; + } + + /* Check if GICC structure of boot CPU is available in the MADT */ + if (cpu_logical_map(0) == hwid) { + if (bootcpu_valid) { + pr_err("duplicate boot CPU MPIDR: 0x%llx in MADT\n", + hwid); + return; + } + bootcpu_valid = true; + return; + } + + if (cpu_count >= NR_CPUS) + return; + + /* map the logical cpu id to cpu MPIDR */ + cpu_logical_map(cpu_count) = hwid; + + cpu_count++; +} + +static int __init +acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_generic_interrupt *processor; + + processor = (struct acpi_madt_generic_interrupt *)header; + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + acpi_map_gic_cpu_interface(processor); + + return 0; +} +#else +#define acpi_table_parse_madt(...) do { } while (0) +#endif + /* * Enumerate the possible CPU set from the device tree and build the * cpu logical map array containing MPIDR values related to logical * cpus. Assumes that cpu_logical_map(0) has already been initialized. */ -void __init of_smp_init_cpus(void) +void __init of_parse_and_init_cpus(void) { struct device_node *dn = NULL; - unsigned int i, cpu = 1; - bool bootcpu_valid = false; while ((dn = of_find_node_by_type(dn, "cpu"))) { - const u32 *cell; - u64 hwid; + u64 hwid = of_get_cpu_mpidr(dn); - /* - * A cpu node with missing "reg" property is - * considered invalid to build a cpu_logical_map - * entry. - */ - cell = of_get_property(dn, "reg", NULL); - if (!cell) { - pr_err("%s: missing reg property\n", dn->full_name); + if (hwid == INVALID_HWID) goto next; - } - hwid = of_read_number(cell, of_n_addr_cells(dn)); - /* - * Non affinity bits must be set to 0 in the DT - */ - if (hwid & ~MPIDR_HWID_BITMASK) { - pr_err("%s: invalid reg property\n", dn->full_name); + if (is_mpidr_duplicate(cpu_count, hwid)) { + pr_err("%s: duplicate cpu reg properties in the DT\n", + dn->full_name); goto next; } /* - * Duplicate MPIDRs are a recipe for disaster. Scan - * all initialized entries and check for - * duplicates. If any is found just ignore the cpu. - * cpu_logical_map was initialized to INVALID_HWID to - * avoid matching valid MPIDR values. - */ - for (i = 1; (i < cpu) && (i < NR_CPUS); i++) { - if (cpu_logical_map(i) == hwid) { - pr_err("%s: duplicate cpu reg properties in the DT\n", - dn->full_name); - goto next; - } - } - - /* * The numbering scheme requires that the boot CPU * must be assigned logical id 0. Record it so that * the logical map built from DT is validated and can @@ -392,38 +498,58 @@ void __init of_smp_init_cpus(void) continue; } - if (cpu >= NR_CPUS) - goto next; - - if (cpu_read_ops(dn, cpu) != 0) - goto next; - - if (cpu_ops[cpu]->cpu_init(dn, cpu)) + if (cpu_count >= NR_CPUS) goto next; pr_debug("cpu logical map 0x%llx\n", hwid); - cpu_logical_map(cpu) = hwid; + cpu_logical_map(cpu_count) = hwid; next: - cpu++; + cpu_count++; } +} + +/* + * Enumerate the possible CPU set from the device tree or ACPI and build the + * cpu logical map array containing MPIDR values related to logical + * cpus. Assumes that cpu_logical_map(0) has already been initialized. + */ +void __init smp_init_cpus(void) +{ + int i; - /* sanity check */ - if (cpu > NR_CPUS) - pr_warning("no. of cores (%d) greater than configured maximum of %d - clipping\n", - cpu, NR_CPUS); + if (acpi_disabled) + of_parse_and_init_cpus(); + else + /* + * do a walk of MADT to determine how many CPUs + * we have including disabled CPUs, and get information + * we need for SMP init + */ + acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, + acpi_parse_gic_cpu_interface, 0); + + if (cpu_count > NR_CPUS) + pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n", + cpu_count, NR_CPUS); if (!bootcpu_valid) { - pr_err("DT missing boot CPU MPIDR, not enabling secondaries\n"); + pr_err("missing boot CPU MPIDR, not enabling secondaries\n"); return; } /* - * All the cpus that made it to the cpu_logical_map have been - * validated so set them as possible cpus. + * We need to set the cpu_logical_map entries before enabling + * the cpus so that cpu processor description entries (DT cpu nodes + * and ACPI MADT entries) can be retrieved by matching the cpu hwid + * with entries in cpu_logical_map while initializing the cpus. + * If the cpu set-up fails, invalidate the cpu_logical_map entry. */ - for (i = 0; i < NR_CPUS; i++) - if (cpu_logical_map(i) != INVALID_HWID) - set_cpu_possible(i, true); + for (i = 1; i < NR_CPUS; i++) { + if (cpu_logical_map(i) != INVALID_HWID) { + if (smp_cpu_setup(i)) + cpu_logical_map(i) = INVALID_HWID; + } + } } void __init smp_prepare_cpus(unsigned int max_cpus) diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c index 14944e5b28da..aef3605a8c47 100644 --- a/arch/arm64/kernel/smp_spin_table.c +++ b/arch/arm64/kernel/smp_spin_table.c @@ -49,8 +49,14 @@ static void write_pen_release(u64 val) } -static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu) +static int smp_spin_table_cpu_init(unsigned int cpu) { + struct device_node *dn; + + dn = of_get_cpu_node(cpu, NULL); + if (!dn) + return -ENODEV; + /* * Determine the address from which the CPU is polling. */ diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 53f1f8dccf6c..44ca4143b013 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -122,7 +122,6 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) } struct sleep_save_sp sleep_save_sp; -phys_addr_t sleep_idmap_phys; static int __init cpu_suspend_init(void) { @@ -136,9 +135,7 @@ static int __init cpu_suspend_init(void) sleep_save_sp.save_ptr_stash = ctx_ptr; sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr); - sleep_idmap_phys = virt_to_phys(idmap_pg_dir); __flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp)); - __flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys)); return 0; } diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 42f9195cf2f8..149151fb42bb 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -42,7 +42,6 @@ #include <asm/thread_info.h> #include <asm/stacktrace.h> -#ifdef CONFIG_SMP unsigned long profile_pc(struct pt_regs *regs) { struct stackframe frame; @@ -62,7 +61,6 @@ unsigned long profile_pc(struct pt_regs *regs) return frame.pc; } EXPORT_SYMBOL(profile_pc); -#endif void __init time_init(void) { diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 1ef2940df13c..0a7bc087838e 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -179,11 +179,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) #else #define S_PREEMPT "" #endif -#ifdef CONFIG_SMP #define S_SMP " SMP" -#else -#define S_SMP "" -#endif static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs) diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index aff07bcad882..4d77757b5894 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -38,6 +38,12 @@ jiffies = jiffies_64; *(.hyp.text) \ VMLINUX_SYMBOL(__hyp_text_end) = .; +#define IDMAP_TEXT \ + . = ALIGN(SZ_4K); \ + VMLINUX_SYMBOL(__idmap_text_start) = .; \ + *(.idmap.text) \ + VMLINUX_SYMBOL(__idmap_text_end) = .; + /* * The size of the PE/COFF section that covers the kernel image, which * runs from stext to _edata, must be a round multiple of the PE/COFF @@ -98,6 +104,7 @@ SECTIONS SCHED_TEXT LOCK_TEXT HYPERVISOR_TEXT + IDMAP_TEXT *(.fixup) *(.gnu.warning) . = ALIGN(16); @@ -170,11 +177,13 @@ SECTIONS } /* - * The HYP init code can't be more than a page long, + * The HYP init code and ID map text can't be longer than a page each, * and should not cross a page boundary. */ ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K, "HYP init code too big or misaligned") +ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K, + "ID map text too big or misaligned") /* * If padding is applied before .head.text, virt<->phys conversions will fail. diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index 76c1e6cd36fc..d70ff14dbdbd 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -53,8 +53,6 @@ static void flush_context(void) __flush_icache_all(); } -#ifdef CONFIG_SMP - static void set_mm_context(struct mm_struct *mm, unsigned int asid) { unsigned long flags; @@ -110,23 +108,12 @@ static void reset_context(void *info) cpu_switch_mm(mm->pgd, mm); } -#else - -static inline void set_mm_context(struct mm_struct *mm, unsigned int asid) -{ - mm->context.id = asid; - cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id())); -} - -#endif - void __new_context(struct mm_struct *mm) { unsigned int asid; unsigned int bits = asid_bits(); raw_spin_lock(&cpu_asid_lock); -#ifdef CONFIG_SMP /* * Check the ASID again, in case the change was broadcast from another * CPU before we acquired the lock. @@ -136,7 +123,6 @@ void __new_context(struct mm_struct *mm) raw_spin_unlock(&cpu_asid_lock); return; } -#endif /* * At this point, it is guaranteed that the current mm (with an old * ASID) isn't active on any other CPU since the ASIDs are changed @@ -155,10 +141,8 @@ void __new_context(struct mm_struct *mm) cpu_last_asid = ASID_FIRST_VERSION; asid = cpu_last_asid + smp_processor_id(); flush_context(); -#ifdef CONFIG_SMP smp_wmb(); smp_call_function(reset_context, NULL, 1); -#endif cpu_last_asid += NR_CPUS - 1; } diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index b6f14e8d2121..07844184975b 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -60,14 +60,10 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { -#ifdef CONFIG_SMP preempt_disable(); -#endif memcpy(dst, src, len); flush_ptrace_access(vma, page, uaddr, dst, len); -#ifdef CONFIG_SMP preempt_enable(); -#endif } void __sync_icache_dcache(pte_t pte, unsigned long addr) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index cdd754e19b9b..33322eaea15b 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -34,11 +34,7 @@ #define TCR_TG_FLAGS TCR_TG0_4K | TCR_TG1_4K #endif -#ifdef CONFIG_SMP #define TCR_SMP_FLAGS TCR_SHARED -#else -#define TCR_SMP_FLAGS 0 -#endif /* PTWs cacheable, inner/outer WBWA */ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 1ec6441fe2a5..09138ceba046 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3417,6 +3417,7 @@ static void rbd_queue_workfn(struct work_struct *work) goto err_rq; } img_request->rq = rq; + snapc = NULL; /* img_request consumes a ref */ if (op_type == OBJ_OP_DISCARD) result = rbd_img_request_fill(img_request, OBJ_REQUEST_NODATA, diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c index 9445e6cc02be..1c3242c3e3a7 100644 --- a/drivers/cpuidle/cpuidle-calxeda.c +++ b/drivers/cpuidle/cpuidle-calxeda.c @@ -25,16 +25,21 @@ #include <linux/init.h> #include <linux/mm.h> #include <linux/platform_device.h> +#include <linux/psci.h> + #include <asm/cpuidle.h> #include <asm/suspend.h> -#include <asm/psci.h> + +#include <uapi/linux/psci.h> + +#define CALXEDA_IDLE_PARAM \ + ((0 << PSCI_0_2_POWER_STATE_ID_SHIFT) | \ + (0 << PSCI_0_2_POWER_STATE_AFFL_SHIFT) | \ + (PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT)) static int calxeda_idle_finish(unsigned long val) { - const struct psci_power_state ps = { - .type = PSCI_POWER_STATE_TYPE_POWER_DOWN, - }; - return psci_ops.cpu_suspend(ps, __pa(cpu_resume)); + return psci_ops.cpu_suspend(CALXEDA_IDLE_PARAM, __pa(cpu_resume)); } static int calxeda_pwrdown_idle(struct cpuidle_device *dev, diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index f51d376d10ba..c2f5117fd8cb 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -3675,6 +3675,11 @@ static int pci_probe(struct pci_dev *dev, reg_write(ohci, OHCI1394_IsoXmitIntMaskSet, ~0); ohci->it_context_support = reg_read(ohci, OHCI1394_IsoXmitIntMaskSet); + /* JMicron JMB38x often shows 0 at first read, just ignore it */ + if (!ohci->it_context_support) { + ohci_notice(ohci, "overriding IsoXmitIntMask\n"); + ohci->it_context_support = 0xf; + } reg_write(ohci, OHCI1394_IsoXmitIntMaskClear, ~0); ohci->it_context_mask = ohci->it_context_support; ohci->n_it = hweight32(ohci->it_context_mask); diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 6517132e5d8b..24be7a34b84a 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -5,6 +5,9 @@ menu "Firmware Drivers" +config ARM_PSCI_FW + bool + config EDD tristate "BIOS Enhanced Disk Drive calls determine boot disk" depends on X86 diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index 3fdd3912709a..6b051293e689 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -1,6 +1,7 @@ # # Makefile for the linux kernel. # +obj-$(CONFIG_ARM_PSCI_FW) += psci.o obj-$(CONFIG_DMI) += dmi_scan.o obj-$(CONFIG_DMI_SYSFS) += dmi-sysfs.o obj-$(CONFIG_EDD) += edd.o diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c new file mode 100644 index 000000000000..ae70d2485ca1 --- /dev/null +++ b/drivers/firmware/psci.c @@ -0,0 +1,470 @@ +/* + * 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. + * + * Copyright (C) 2015 ARM Limited + */ + +#define pr_fmt(fmt) "psci: " fmt + +#include <linux/errno.h> +#include <linux/linkage.h> +#include <linux/of.h> +#include <linux/pm.h> +#include <linux/printk.h> +#include <linux/psci.h> +#include <linux/reboot.h> +#include <linux/suspend.h> + +#include <uapi/linux/psci.h> + +#include <asm/cputype.h> +#include <asm/system_misc.h> +#include <asm/smp_plat.h> +#include <asm/suspend.h> + +/* + * While a 64-bit OS can make calls with SMC32 calling conventions, for some + * calls it is necessary to use SMC64 to pass or return 64-bit values. + * For such calls PSCI_FN_NATIVE(version, name) will choose the appropriate + * (native-width) function ID. + */ +#ifdef CONFIG_64BIT +#define PSCI_FN_NATIVE(version, name) PSCI_##version##_FN64_##name +#else +#define PSCI_FN_NATIVE(version, name) PSCI_##version##_FN_##name +#endif + +/* + * The CPU any Trusted OS is resident on. The trusted OS may reject CPU_OFF + * calls to its resident CPU, so we must avoid issuing those. We never migrate + * a Trusted OS even if it claims to be capable of migration -- doing so will + * require cooperation with a Trusted OS driver. + */ +static int resident_cpu = -1; + +bool psci_tos_resident_on(int cpu) +{ + return cpu == resident_cpu; +} + +struct psci_operations psci_ops; + +typedef unsigned long (psci_fn)(unsigned long, unsigned long, + unsigned long, unsigned long); +asmlinkage psci_fn __invoke_psci_fn_hvc; +asmlinkage psci_fn __invoke_psci_fn_smc; +static psci_fn *invoke_psci_fn; + +enum psci_function { + PSCI_FN_CPU_SUSPEND, + PSCI_FN_CPU_ON, + PSCI_FN_CPU_OFF, + PSCI_FN_MIGRATE, + PSCI_FN_MAX, +}; + +static u32 psci_function_id[PSCI_FN_MAX]; + +#define PSCI_0_2_POWER_STATE_MASK \ + (PSCI_0_2_POWER_STATE_ID_MASK | \ + PSCI_0_2_POWER_STATE_TYPE_MASK | \ + PSCI_0_2_POWER_STATE_AFFL_MASK) + +#define PSCI_1_0_EXT_POWER_STATE_MASK \ + (PSCI_1_0_EXT_POWER_STATE_ID_MASK | \ + PSCI_1_0_EXT_POWER_STATE_TYPE_MASK) + +static u32 psci_cpu_suspend_feature; + +static inline bool psci_has_ext_power_state(void) +{ + return psci_cpu_suspend_feature & + PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK; +} + +bool psci_power_state_loses_context(u32 state) +{ + const u32 mask = psci_has_ext_power_state() ? + PSCI_1_0_EXT_POWER_STATE_TYPE_MASK : + PSCI_0_2_POWER_STATE_TYPE_MASK; + + return state & mask; +} + +bool psci_power_state_is_valid(u32 state) +{ + const u32 valid_mask = psci_has_ext_power_state() ? + PSCI_1_0_EXT_POWER_STATE_MASK : + PSCI_0_2_POWER_STATE_MASK; + + return !(state & ~valid_mask); +} + +static int psci_to_linux_errno(int errno) +{ + switch (errno) { + case PSCI_RET_SUCCESS: + return 0; + case PSCI_RET_NOT_SUPPORTED: + return -EOPNOTSUPP; + case PSCI_RET_INVALID_PARAMS: + case PSCI_RET_INVALID_ADDRESS: + return -EINVAL; + case PSCI_RET_DENIED: + return -EPERM; + }; + + return -EINVAL; +} + +static u32 psci_get_version(void) +{ + return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0); +} + +static int psci_cpu_suspend(u32 state, unsigned long entry_point) +{ + int err; + u32 fn; + + fn = psci_function_id[PSCI_FN_CPU_SUSPEND]; + err = invoke_psci_fn(fn, state, entry_point, 0); + return psci_to_linux_errno(err); +} + +static int psci_cpu_off(u32 state) +{ + int err; + u32 fn; + + fn = psci_function_id[PSCI_FN_CPU_OFF]; + err = invoke_psci_fn(fn, state, 0, 0); + return psci_to_linux_errno(err); +} + +static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point) +{ + int err; + u32 fn; + + fn = psci_function_id[PSCI_FN_CPU_ON]; + err = invoke_psci_fn(fn, cpuid, entry_point, 0); + return psci_to_linux_errno(err); +} + +static int psci_migrate(unsigned long cpuid) +{ + int err; + u32 fn; + + fn = psci_function_id[PSCI_FN_MIGRATE]; + err = invoke_psci_fn(fn, cpuid, 0, 0); + return psci_to_linux_errno(err); +} + +static int psci_affinity_info(unsigned long target_affinity, + unsigned long lowest_affinity_level) +{ + return invoke_psci_fn(PSCI_FN_NATIVE(0_2, AFFINITY_INFO), + target_affinity, lowest_affinity_level, 0); +} + +static int psci_migrate_info_type(void) +{ + return invoke_psci_fn(PSCI_0_2_FN_MIGRATE_INFO_TYPE, 0, 0, 0); +} + +static unsigned long psci_migrate_info_up_cpu(void) +{ + return invoke_psci_fn(PSCI_FN_NATIVE(0_2, MIGRATE_INFO_UP_CPU), + 0, 0, 0); +} + +static int get_set_conduit_method(struct device_node *np) +{ + const char *method; + + pr_info("probing for conduit method from DT.\n"); + + if (of_property_read_string(np, "method", &method)) { + pr_warn("missing \"method\" property\n"); + return -ENXIO; + } + + if (!strcmp("hvc", method)) { + invoke_psci_fn = __invoke_psci_fn_hvc; + } else if (!strcmp("smc", method)) { + invoke_psci_fn = __invoke_psci_fn_smc; + } else { + pr_warn("invalid \"method\" property: %s\n", method); + return -EINVAL; + } + return 0; +} + +static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd) +{ + invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0); +} + +static void psci_sys_poweroff(void) +{ + invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0); +} + +static int __init psci_features(u32 psci_func_id) +{ + return invoke_psci_fn(PSCI_1_0_FN_PSCI_FEATURES, + psci_func_id, 0, 0); +} + +static int psci_system_suspend(unsigned long unused) +{ + return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND), + virt_to_phys(cpu_resume), 0, 0); +} + +static int psci_system_suspend_enter(suspend_state_t state) +{ + return cpu_suspend(0, psci_system_suspend); +} + +static const struct platform_suspend_ops psci_suspend_ops = { + .valid = suspend_valid_only_mem, + .enter = psci_system_suspend_enter, +}; + +static void __init psci_init_system_suspend(void) +{ + int ret; + + if (!IS_ENABLED(CONFIG_SUSPEND)) + return; + + ret = psci_features(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND)); + + if (ret != PSCI_RET_NOT_SUPPORTED) + suspend_set_ops(&psci_suspend_ops); +} + +static void __init psci_init_cpu_suspend(void) +{ + int feature = psci_features(psci_function_id[PSCI_FN_CPU_SUSPEND]); + + if (feature != PSCI_RET_NOT_SUPPORTED) + psci_cpu_suspend_feature = feature; +} + +/* + * Detect the presence of a resident Trusted OS which may cause CPU_OFF to + * return DENIED (which would be fatal). + */ +static void __init psci_init_migrate(void) +{ + unsigned long cpuid; + int type, cpu = -1; + + type = psci_ops.migrate_info_type(); + + if (type == PSCI_0_2_TOS_MP) { + pr_info("Trusted OS migration not required\n"); + return; + } + + if (type == PSCI_RET_NOT_SUPPORTED) { + pr_info("MIGRATE_INFO_TYPE not supported.\n"); + return; + } + + if (type != PSCI_0_2_TOS_UP_MIGRATE && + type != PSCI_0_2_TOS_UP_NO_MIGRATE) { + pr_err("MIGRATE_INFO_TYPE returned unknown type (%d)\n", type); + return; + } + + cpuid = psci_migrate_info_up_cpu(); + if (cpuid & ~MPIDR_HWID_BITMASK) { + pr_warn("MIGRATE_INFO_UP_CPU reported invalid physical ID (0x%lx)\n", + cpuid); + return; + } + + cpu = get_logical_index(cpuid); + resident_cpu = cpu >= 0 ? cpu : -1; + + pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid); +} + +static void __init psci_0_2_set_functions(void) +{ + pr_info("Using standard PSCI v0.2 function IDs\n"); + psci_function_id[PSCI_FN_CPU_SUSPEND] = + PSCI_FN_NATIVE(0_2, CPU_SUSPEND); + psci_ops.cpu_suspend = psci_cpu_suspend; + + psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF; + psci_ops.cpu_off = psci_cpu_off; + + psci_function_id[PSCI_FN_CPU_ON] = PSCI_FN_NATIVE(0_2, CPU_ON); + psci_ops.cpu_on = psci_cpu_on; + + psci_function_id[PSCI_FN_MIGRATE] = PSCI_FN_NATIVE(0_2, MIGRATE); + psci_ops.migrate = psci_migrate; + + psci_ops.affinity_info = psci_affinity_info; + + psci_ops.migrate_info_type = psci_migrate_info_type; + + arm_pm_restart = psci_sys_reset; + + pm_power_off = psci_sys_poweroff; +} + +/* + * Probe function for PSCI firmware versions >= 0.2 + */ +static int __init psci_probe(void) +{ + u32 ver = psci_get_version(); + + pr_info("PSCIv%d.%d detected in firmware.\n", + PSCI_VERSION_MAJOR(ver), + PSCI_VERSION_MINOR(ver)); + + if (PSCI_VERSION_MAJOR(ver) == 0 && PSCI_VERSION_MINOR(ver) < 2) { + pr_err("Conflicting PSCI version detected.\n"); + return -EINVAL; + } + + psci_0_2_set_functions(); + + psci_init_migrate(); + + if (PSCI_VERSION_MAJOR(ver) >= 1) { + psci_init_cpu_suspend(); + psci_init_system_suspend(); + } + + return 0; +} + +typedef int (*psci_initcall_t)(const struct device_node *); + +/* + * PSCI init function for PSCI versions >=0.2 + * + * Probe based on PSCI PSCI_VERSION function + */ +static int __init psci_0_2_init(struct device_node *np) +{ + int err; + + err = get_set_conduit_method(np); + + if (err) + goto out_put_node; + /* + * Starting with v0.2, the PSCI specification introduced a call + * (PSCI_VERSION) that allows probing the firmware version, so + * that PSCI function IDs and version specific initialization + * can be carried out according to the specific version reported + * by firmware + */ + err = psci_probe(); + +out_put_node: + of_node_put(np); + return err; +} + +/* + * PSCI < v0.2 get PSCI Function IDs via DT. + */ +static int __init psci_0_1_init(struct device_node *np) +{ + u32 id; + int err; + + err = get_set_conduit_method(np); + + if (err) + goto out_put_node; + + pr_info("Using PSCI v0.1 Function IDs from DT\n"); + + if (!of_property_read_u32(np, "cpu_suspend", &id)) { + psci_function_id[PSCI_FN_CPU_SUSPEND] = id; + psci_ops.cpu_suspend = psci_cpu_suspend; + } + + if (!of_property_read_u32(np, "cpu_off", &id)) { + psci_function_id[PSCI_FN_CPU_OFF] = id; + psci_ops.cpu_off = psci_cpu_off; + } + + if (!of_property_read_u32(np, "cpu_on", &id)) { + psci_function_id[PSCI_FN_CPU_ON] = id; + psci_ops.cpu_on = psci_cpu_on; + } + + if (!of_property_read_u32(np, "migrate", &id)) { + psci_function_id[PSCI_FN_MIGRATE] = id; + psci_ops.migrate = psci_migrate; + } + +out_put_node: + of_node_put(np); + return err; +} + +static const struct of_device_id psci_of_match[] __initconst = { + { .compatible = "arm,psci", .data = psci_0_1_init}, + { .compatible = "arm,psci-0.2", .data = psci_0_2_init}, + { .compatible = "arm,psci-1.0", .data = psci_0_2_init}, + {}, +}; + +int __init psci_dt_init(void) +{ + struct device_node *np; + const struct of_device_id *matched_np; + psci_initcall_t init_fn; + + np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np); + + if (!np) + return -ENODEV; + + init_fn = (psci_initcall_t)matched_np->data; + return init_fn(np); +} + +#ifdef CONFIG_ACPI +/* + * We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's + * explicitly clarified in SBBR + */ +int __init psci_acpi_init(void) +{ + if (!acpi_psci_present()) { + pr_info("is not implemented in ACPI.\n"); + return -EOPNOTSUPP; + } + + pr_info("probing for conduit method from ACPI.\n"); + + if (acpi_psci_use_hvc()) + invoke_psci_fn = __invoke_psci_fn_hvc; + else + invoke_psci_fn = __invoke_psci_fn_smc; + + return psci_probe(); +} +#endif diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 9c71295f2fef..85e640440bd9 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -675,7 +675,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = { { PHY_ID_BCM5461, 0xfffffff0 }, { PHY_ID_BCM54616S, 0xfffffff0 }, { PHY_ID_BCM5464, 0xfffffff0 }, - { PHY_ID_BCM5482, 0xfffffff0 }, + { PHY_ID_BCM5481, 0xfffffff0 }, { PHY_ID_BCM5482, 0xfffffff0 }, { PHY_ID_BCM50610, 0xfffffff0 }, { PHY_ID_BCM50610M, 0xfffffff0 }, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 4e0470d396a3..71190dc1eacf 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -774,6 +774,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ + {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */ {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */ {QMI_FIXED_INTF(0x0b3c, 0xc002, 4)}, /* Olivetti Olicard 140 */ diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index b072e17479aa..2b0d84d32db4 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -756,8 +756,16 @@ next_slot: } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); - if (key.objectid > ino || - key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) + + if (key.objectid > ino) + break; + if (WARN_ON_ONCE(key.objectid < ino) || + key.type < BTRFS_EXTENT_DATA_KEY) { + ASSERT(del_nr == 0); + path->slots[0]++; + goto next_slot; + } + if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end) break; fi = btrfs_item_ptr(leaf, path->slots[0], @@ -776,8 +784,8 @@ next_slot: btrfs_file_extent_inline_len(leaf, path->slots[0], fi); } else { - WARN_ON(1); - extent_end = search_start; + /* can't happen */ + BUG(); } /* diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e3b39f0c4666..5136c73b3dce 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1294,8 +1294,14 @@ next_slot: num_bytes = 0; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); - if (found_key.objectid > ino || - found_key.type > BTRFS_EXTENT_DATA_KEY || + if (found_key.objectid > ino) + break; + if (WARN_ON_ONCE(found_key.objectid < ino) || + found_key.type < BTRFS_EXTENT_DATA_KEY) { + path->slots[0]++; + goto next_slot; + } + if (found_key.type > BTRFS_EXTENT_DATA_KEY || found_key.offset > end) break; @@ -4184,6 +4190,47 @@ static int truncate_space_check(struct btrfs_trans_handle *trans, } +static int truncate_inline_extent(struct inode *inode, + struct btrfs_path *path, + struct btrfs_key *found_key, + const u64 item_end, + const u64 new_size) +{ + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + struct btrfs_file_extent_item *fi; + u32 size = (u32)(new_size - found_key->offset); + struct btrfs_root *root = BTRFS_I(inode)->root; + + fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + + if (btrfs_file_extent_compression(leaf, fi) != BTRFS_COMPRESS_NONE) { + loff_t offset = new_size; + loff_t page_end = ALIGN(offset, PAGE_CACHE_SIZE); + + /* + * Zero out the remaining of the last page of our inline extent, + * instead of directly truncating our inline extent here - that + * would be much more complex (decompressing all the data, then + * compressing the truncated data, which might be bigger than + * the size of the inline extent, resize the extent, etc). + * We release the path because to get the page we might need to + * read the extent item from disk (data not in the page cache). + */ + btrfs_release_path(path); + return btrfs_truncate_page(inode, offset, page_end - offset, 0); + } + + btrfs_set_file_extent_ram_bytes(leaf, fi, size); + size = btrfs_file_extent_calc_inline_size(size); + btrfs_truncate_item(root, path, size, 1); + + if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) + inode_sub_bytes(inode, item_end + 1 - new_size); + + return 0; +} + /* * this can truncate away extent items, csum items and directory items. * It starts at a high offset and removes keys until it can't find @@ -4378,27 +4425,40 @@ search_again: * special encodings */ if (!del_item && - btrfs_file_extent_compression(leaf, fi) == 0 && btrfs_file_extent_encryption(leaf, fi) == 0 && btrfs_file_extent_other_encoding(leaf, fi) == 0) { - u32 size = new_size - found_key.offset; - - if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) - inode_sub_bytes(inode, item_end + 1 - - new_size); /* - * update the ram bytes to properly reflect - * the new size of our item + * Need to release path in order to truncate a + * compressed extent. So delete any accumulated + * extent items so far. */ - btrfs_set_file_extent_ram_bytes(leaf, fi, size); - size = - btrfs_file_extent_calc_inline_size(size); - btrfs_truncate_item(root, path, size, 1); + if (btrfs_file_extent_compression(leaf, fi) != + BTRFS_COMPRESS_NONE && pending_del_nr) { + err = btrfs_del_items(trans, root, path, + pending_del_slot, + pending_del_nr); + if (err) { + btrfs_abort_transaction(trans, + root, + err); + goto error; + } + pending_del_nr = 0; + } + + err = truncate_inline_extent(inode, path, + &found_key, + item_end, + new_size); + if (err) { + btrfs_abort_transaction(trans, + root, err); + goto error; + } } else if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) { - inode_sub_bytes(inode, item_end + 1 - - found_key.offset); + inode_sub_bytes(inode, item_end + 1 - new_size); } } delete: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8b2c82ce36b3..87c720865ebf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3166,6 +3166,150 @@ static void clone_update_extent_map(struct inode *inode, &BTRFS_I(inode)->runtime_flags); } +/* + * Make sure we do not end up inserting an inline extent into a file that has + * already other (non-inline) extents. If a file has an inline extent it can + * not have any other extents and the (single) inline extent must start at the + * file offset 0. Failing to respect these rules will lead to file corruption, + * resulting in EIO errors on read/write operations, hitting BUG_ON's in mm, etc + * + * We can have extents that have been already written to disk or we can have + * dirty ranges still in delalloc, in which case the extent maps and items are + * created only when we run delalloc, and the delalloc ranges might fall outside + * the range we are currently locking in the inode's io tree. So we check the + * inode's i_size because of that (i_size updates are done while holding the + * i_mutex, which we are holding here). + * We also check to see if the inode has a size not greater than "datal" but has + * extents beyond it, due to an fallocate with FALLOC_FL_KEEP_SIZE (and we are + * protected against such concurrent fallocate calls by the i_mutex). + * + * If the file has no extents but a size greater than datal, do not allow the + * copy because we would need turn the inline extent into a non-inline one (even + * with NO_HOLES enabled). If we find our destination inode only has one inline + * extent, just overwrite it with the source inline extent if its size is less + * than the source extent's size, or we could copy the source inline extent's + * data into the destination inode's inline extent if the later is greater then + * the former. + */ +static int clone_copy_inline_extent(struct inode *src, + struct inode *dst, + struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct btrfs_key *new_key, + const u64 drop_start, + const u64 datal, + const u64 skip, + const u64 size, + char *inline_data) +{ + struct btrfs_root *root = BTRFS_I(dst)->root; + const u64 aligned_end = ALIGN(new_key->offset + datal, + root->sectorsize); + int ret; + struct btrfs_key key; + + if (new_key->offset > 0) + return -EOPNOTSUPP; + + key.objectid = btrfs_ino(dst); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = 0; + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) { + return ret; + } else if (ret > 0) { + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) + return ret; + else if (ret > 0) + goto copy_inline_extent; + } + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid == btrfs_ino(dst) && + key.type == BTRFS_EXTENT_DATA_KEY) { + ASSERT(key.offset > 0); + return -EOPNOTSUPP; + } + } else if (i_size_read(dst) <= datal) { + struct btrfs_file_extent_item *ei; + u64 ext_len; + + /* + * If the file size is <= datal, make sure there are no other + * extents following (can happen do to an fallocate call with + * the flag FALLOC_FL_KEEP_SIZE). + */ + ei = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + /* + * If it's an inline extent, it can not have other extents + * following it. + */ + if (btrfs_file_extent_type(path->nodes[0], ei) == + BTRFS_FILE_EXTENT_INLINE) + goto copy_inline_extent; + + ext_len = btrfs_file_extent_num_bytes(path->nodes[0], ei); + if (ext_len > aligned_end) + return -EOPNOTSUPP; + + ret = btrfs_next_item(root, path); + if (ret < 0) { + return ret; + } else if (ret == 0) { + btrfs_item_key_to_cpu(path->nodes[0], &key, + path->slots[0]); + if (key.objectid == btrfs_ino(dst) && + key.type == BTRFS_EXTENT_DATA_KEY) + return -EOPNOTSUPP; + } + } + +copy_inline_extent: + /* + * We have no extent items, or we have an extent at offset 0 which may + * or may not be inlined. All these cases are dealt the same way. + */ + if (i_size_read(dst) > datal) { + /* + * If the destination inode has an inline extent... + * This would require copying the data from the source inline + * extent into the beginning of the destination's inline extent. + * But this is really complex, both extents can be compressed + * or just one of them, which would require decompressing and + * re-compressing data (which could increase the new compressed + * size, not allowing the compressed data to fit anymore in an + * inline extent). + * So just don't support this case for now (it should be rare, + * we are not really saving space when cloning inline extents). + */ + return -EOPNOTSUPP; + } + + btrfs_release_path(path); + ret = btrfs_drop_extents(trans, root, dst, drop_start, aligned_end, 1); + if (ret) + return ret; + ret = btrfs_insert_empty_item(trans, root, path, new_key, size); + if (ret) + return ret; + + if (skip) { + const u32 start = btrfs_file_extent_calc_inline_size(0); + + memmove(inline_data + start, inline_data + start + skip, datal); + } + + write_extent_buffer(path->nodes[0], inline_data, + btrfs_item_ptr_offset(path->nodes[0], + path->slots[0]), + size); + inode_add_bytes(dst, datal); + + return 0; +} + /** * btrfs_clone() - clone a range from inode file to another * @@ -3432,21 +3576,6 @@ process_slot: } else if (type == BTRFS_FILE_EXTENT_INLINE) { u64 skip = 0; u64 trim = 0; - u64 aligned_end = 0; - - /* - * Don't copy an inline extent into an offset - * greater than zero. Having an inline extent - * at such an offset results in chaos as btrfs - * isn't prepared for such cases. Just skip - * this case for the same reasons as commented - * at btrfs_ioctl_clone(). - */ - if (last_dest_end > 0) { - ret = -EOPNOTSUPP; - btrfs_end_transaction(trans, root); - goto out; - } if (off > key.offset) { skip = off - key.offset; @@ -3464,42 +3593,22 @@ process_slot: size -= skip + trim; datal -= skip + trim; - aligned_end = ALIGN(new_key.offset + datal, - root->sectorsize); - ret = btrfs_drop_extents(trans, root, inode, - drop_start, - aligned_end, - 1); + ret = clone_copy_inline_extent(src, inode, + trans, path, + &new_key, + drop_start, + datal, + skip, size, buf); if (ret) { if (ret != -EOPNOTSUPP) btrfs_abort_transaction(trans, - root, ret); - btrfs_end_transaction(trans, root); - goto out; - } - - ret = btrfs_insert_empty_item(trans, root, path, - &new_key, size); - if (ret) { - btrfs_abort_transaction(trans, root, - ret); + root, + ret); btrfs_end_transaction(trans, root); goto out; } - - if (skip) { - u32 start = - btrfs_file_extent_calc_inline_size(0); - memmove(buf+start, buf+start+skip, - datal); - } - leaf = path->nodes[0]; slot = path->slots[0]; - write_extent_buffer(leaf, buf, - btrfs_item_ptr_offset(leaf, slot), - size); - inode_add_bytes(inode, datal); } /* If we have an implicit hole (NO_HOLES feature). */ diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 6f518c90e1c1..1fcd7b6e7564 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -313,8 +313,10 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) /* check to make sure this item is what we want */ if (found_key.objectid != key.objectid) break; - if (found_key.type != BTRFS_XATTR_ITEM_KEY) + if (found_key.type > BTRFS_XATTR_ITEM_KEY) break; + if (found_key.type < BTRFS_XATTR_ITEM_KEY) + goto next; di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); if (verify_dir_item(root, leaf, di)) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 84f37f34f9aa..1e99b29650a9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1905,7 +1905,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, len = sizeof(*head) + pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) + - sizeof(struct timespec); + sizeof(struct ceph_timespec); /* calculate (max) length for cap releases */ len += sizeof(struct ceph_mds_request_release) * diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 12756040ca20..8bec8f1e4b31 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -276,8 +276,12 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) dput(dentry); dentry = ERR_PTR(-EEXIST); } - if (IS_ERR(dentry)) + + if (IS_ERR(dentry)) { mutex_unlock(&d_inode(parent)->i_mutex); + simple_release_fs(&debugfs_mount, &debugfs_mount_count); + } + return dentry; } diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index d41843181818..e770c1ee4613 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -88,13 +88,13 @@ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) return 0; } + err = handle->h_err; if (!handle->h_transaction) { - err = jbd2_journal_stop(handle); - return handle->h_err ? handle->h_err : err; + rc = jbd2_journal_stop(handle); + return err ? err : rc; } sb = handle->h_transaction->t_journal->j_private; - err = handle->h_err; rc = jbd2_journal_stop(handle); if (!err) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 5765f88b3904..8082565c59a9 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -426,6 +426,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, struct buffer_head *bh, *head; int ret = 0; int nr_submitted = 0; + int nr_to_submit = 0; blocksize = 1 << inode->i_blkbits; @@ -478,11 +479,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io, unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); } set_buffer_async_write(bh); + nr_to_submit++; } while ((bh = bh->b_this_page) != head); bh = head = page_buffers(page); - if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { + if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode) && + nr_to_submit) { data_page = ext4_encrypt(inode, page); if (IS_ERR(data_page)) { ret = PTR_ERR(data_page); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ff89971e3ee0..8a3b9f14d198 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -396,9 +396,13 @@ static void ext4_handle_error(struct super_block *sb) smp_wmb(); sb->s_flags |= MS_RDONLY; } - if (test_opt(sb, ERRORS_PANIC)) + if (test_opt(sb, ERRORS_PANIC)) { + if (EXT4_SB(sb)->s_journal && + !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) + return; panic("EXT4-fs (device %s): panic forced after error\n", sb->s_id); + } } #define ext4_error_ratelimit(sb) \ @@ -587,8 +591,12 @@ void __ext4_abort(struct super_block *sb, const char *function, jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); save_error_info(sb, function, line); } - if (test_opt(sb, ERRORS_PANIC)) + if (test_opt(sb, ERRORS_PANIC)) { + if (EXT4_SB(sb)->s_journal && + !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) + return; panic("EXT4-fs panic from previous error\n"); + } } void __ext4_msg(struct super_block *sb, diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 7003c0925760..0469f32918a5 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2086,8 +2086,12 @@ static void __journal_abort_soft (journal_t *journal, int errno) __jbd2_journal_abort_hard(journal); - if (errno) + if (errno) { jbd2_journal_update_sb_errno(journal); + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_REC_ERR; + write_unlock(&journal->j_state_lock); + } } /** diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 976ba792fbc6..7f22b6c6fb50 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1813,7 +1813,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0) nfsi->attr_gencount = fattr->gencount; } - invalid &= ~NFS_INO_INVALID_ATTR; + + /* Don't declare attrcache up to date if there were no attrs! */ + if (fattr->valid != 0) + invalid &= ~NFS_INO_INVALID_ATTR; + /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index e42be52a8c18..5dea913baf46 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -33,7 +33,7 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) return ret; idr_preload(GFP_KERNEL); spin_lock(&nn->nfs_client_lock); - ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT); + ret = idr_alloc(&nn->cb_ident_idr, clp, 1, 0, GFP_NOWAIT); if (ret >= 0) clp->cl_cb_ident = ret; spin_unlock(&nn->nfs_client_lock); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 397798368b1a..bb6c324f1f3d 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -765,16 +765,68 @@ void nfs4_unhash_stid(struct nfs4_stid *s) s->sc_type = 0; } -static void +/** + * nfs4_get_existing_delegation - Discover if this delegation already exists + * @clp: a pointer to the nfs4_client we're granting a delegation to + * @fp: a pointer to the nfs4_file we're granting a delegation on + * + * Return: + * On success: NULL if an existing delegation was not found. + * + * On error: -EAGAIN if one was previously granted to this nfs4_client + * for this nfs4_file. + * + */ + +static int +nfs4_get_existing_delegation(struct nfs4_client *clp, struct nfs4_file *fp) +{ + struct nfs4_delegation *searchdp = NULL; + struct nfs4_client *searchclp = NULL; + + lockdep_assert_held(&state_lock); + lockdep_assert_held(&fp->fi_lock); + + list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) { + searchclp = searchdp->dl_stid.sc_client; + if (clp == searchclp) { + return -EAGAIN; + } + } + return 0; +} + +/** + * hash_delegation_locked - Add a delegation to the appropriate lists + * @dp: a pointer to the nfs4_delegation we are adding. + * @fp: a pointer to the nfs4_file we're granting a delegation on + * + * Return: + * On success: NULL if the delegation was successfully hashed. + * + * On error: -EAGAIN if one was previously granted to this + * nfs4_client for this nfs4_file. Delegation is not hashed. + * + */ + +static int hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) { + int status; + struct nfs4_client *clp = dp->dl_stid.sc_client; + lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); + status = nfs4_get_existing_delegation(clp, fp); + if (status) + return status; + ++fp->fi_delegees; atomic_inc(&dp->dl_stid.sc_count); dp->dl_stid.sc_type = NFS4_DELEG_STID; list_add(&dp->dl_perfile, &fp->fi_delegations); - list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations); + list_add(&dp->dl_perclnt, &clp->cl_delegations); + return 0; } static bool @@ -3351,6 +3403,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, stp->st_access_bmap = 0; stp->st_deny_bmap = 0; stp->st_openstp = NULL; + init_rwsem(&stp->st_rwsem); spin_lock(&oo->oo_owner.so_client->cl_lock); list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids); spin_lock(&fp->fi_lock); @@ -3940,6 +3993,18 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag) return fl; } +/** + * nfs4_setlease - Obtain a delegation by requesting lease from vfs layer + * @dp: a pointer to the nfs4_delegation we're adding. + * + * Return: + * On success: Return code will be 0 on success. + * + * On error: -EAGAIN if there was an existing delegation. + * nonzero if there is an error in other cases. + * + */ + static int nfs4_setlease(struct nfs4_delegation *dp) { struct nfs4_file *fp = dp->dl_stid.sc_file; @@ -3971,16 +4036,19 @@ static int nfs4_setlease(struct nfs4_delegation *dp) goto out_unlock; /* Race breaker */ if (fp->fi_deleg_file) { - status = 0; - ++fp->fi_delegees; - hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); goto out_unlock; } fp->fi_deleg_file = filp; - fp->fi_delegees = 1; - hash_delegation_locked(dp, fp); + fp->fi_delegees = 0; + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); + if (status) { + /* Should never happen, this is a new fi_deleg_file */ + WARN_ON_ONCE(1); + goto out_fput; + } return 0; out_unlock: spin_unlock(&fp->fi_lock); @@ -4000,6 +4068,15 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); + spin_lock(&state_lock); + spin_lock(&fp->fi_lock); + status = nfs4_get_existing_delegation(clp, fp); + spin_unlock(&fp->fi_lock); + spin_unlock(&state_lock); + + if (status) + return ERR_PTR(status); + dp = alloc_init_deleg(clp, fh, odstate); if (!dp) return ERR_PTR(-ENOMEM); @@ -4018,9 +4095,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, status = -EAGAIN; goto out_unlock; } - ++fp->fi_delegees; - hash_delegation_locked(dp, fp); - status = 0; + status = hash_delegation_locked(dp, fp); out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -4181,15 +4256,20 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf */ if (stp) { /* Stateid was found, this is an OPEN upgrade */ + down_read(&stp->st_rwsem); status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); - if (status) + if (status) { + up_read(&stp->st_rwsem); goto out; + } } else { stp = open->op_stp; open->op_stp = NULL; init_open_stateid(stp, fp, open); + down_read(&stp->st_rwsem); status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); if (status) { + up_read(&stp->st_rwsem); release_open_stateid(stp); goto out; } @@ -4201,6 +4281,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf } update_stateid(&stp->st_stid.sc_stateid); memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + up_read(&stp->st_rwsem); if (nfsd4_has_session(&resp->cstate)) { if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { @@ -4777,10 +4858,13 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ * revoked delegations are kept only for free_stateid. */ return nfserr_bad_stateid; + down_write(&stp->st_rwsem); status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); - if (status) - return status; - return nfs4_check_fh(current_fh, &stp->st_stid); + if (status == nfs_ok) + status = nfs4_check_fh(current_fh, &stp->st_stid); + if (status != nfs_ok) + up_write(&stp->st_rwsem); + return status; } /* @@ -4827,6 +4911,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs return status; oo = openowner(stp->st_stateowner); if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); return nfserr_bad_stateid; } @@ -4857,11 +4942,14 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; oo = openowner(stp->st_stateowner); status = nfserr_bad_stateid; - if (oo->oo_flags & NFS4_OO_CONFIRMED) + if (oo->oo_flags & NFS4_OO_CONFIRMED) { + up_write(&stp->st_rwsem); goto put_stateid; + } oo->oo_flags |= NFS4_OO_CONFIRMED; update_stateid(&stp->st_stid.sc_stateid); memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + up_write(&stp->st_rwsem); dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); @@ -4940,6 +5028,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); status = nfs_ok; put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); @@ -4993,6 +5082,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; update_stateid(&stp->st_stid.sc_stateid); memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + up_write(&stp->st_rwsem); nfsd4_close_open_stateid(stp); @@ -5223,6 +5313,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + init_rwsem(&stp->st_rwsem); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); spin_lock(&fp->fi_lock); @@ -5391,6 +5482,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &open_stp, nn); if (status) goto out; + up_write(&open_stp->st_rwsem); open_sop = openowner(open_stp->st_stateowner); status = nfserr_bad_stateid; if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid, @@ -5398,6 +5490,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); + if (status == nfs_ok) + down_write(&lock_stp->st_rwsem); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, @@ -5503,6 +5597,8 @@ out: seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; + up_write(&lock_stp->st_rwsem); + /* * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. @@ -5673,6 +5769,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fput: fput(filp); put_stateid: + up_write(&stp->st_rwsem); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index dbc4f85a5008..67685b6cfef3 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -533,15 +533,16 @@ struct nfs4_file { * Better suggestions welcome. */ struct nfs4_ol_stateid { - struct nfs4_stid st_stid; /* must be first field */ - struct list_head st_perfile; - struct list_head st_perstateowner; - struct list_head st_locks; - struct nfs4_stateowner * st_stateowner; - struct nfs4_clnt_odstate * st_clnt_odstate; - unsigned char st_access_bmap; - unsigned char st_deny_bmap; - struct nfs4_ol_stateid * st_openstp; + struct nfs4_stid st_stid; + struct list_head st_perfile; + struct list_head st_perstateowner; + struct list_head st_locks; + struct nfs4_stateowner *st_stateowner; + struct nfs4_clnt_odstate *st_clnt_odstate; + unsigned char st_access_bmap; + unsigned char st_deny_bmap; + struct nfs4_ol_stateid *st_openstp; + struct rw_semaphore st_rwsem; }; static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 176fe6afd94e..4d5e0a573f4f 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -365,6 +365,8 @@ static int ocfs2_mknod(struct inode *dir, mlog_errno(status); goto leave; } + /* update inode->i_mode after mask with "umask". */ + inode->i_mode = mode; handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 82806c60aa42..e4b464983322 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -224,7 +224,7 @@ struct ipv6_pinfo { struct ipv6_ac_socklist *ipv6_ac_list; struct ipv6_fl_socklist __rcu *ipv6_fl_list; - struct ipv6_txoptions *opt; + struct ipv6_txoptions __rcu *opt; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; struct inet6_cork cork; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index eb1cebed3f36..c90c9b70e568 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1007,6 +1007,7 @@ struct journal_s #define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file * data write error in ordered * mode */ +#define JBD2_REC_ERR 0x080 /* The errno in the sb has been recorded */ /* * Function declarations for the journaling transaction and buffer diff --git a/include/linux/psci.h b/include/linux/psci.h new file mode 100644 index 000000000000..12c4865457ad --- /dev/null +++ b/include/linux/psci.h @@ -0,0 +1,54 @@ +/* + * 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. + * + * Copyright (C) 2015 ARM Limited + */ + +#ifndef __LINUX_PSCI_H +#define __LINUX_PSCI_H + +#include <linux/init.h> +#include <linux/types.h> + +#define PSCI_POWER_STATE_TYPE_STANDBY 0 +#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 + +bool psci_tos_resident_on(int cpu); +bool psci_power_state_loses_context(u32 state); +bool psci_power_state_is_valid(u32 state); + +struct psci_operations { + int (*cpu_suspend)(u32 state, unsigned long entry_point); + int (*cpu_off)(u32 state); + int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); + int (*migrate)(unsigned long cpuid); + int (*affinity_info)(unsigned long target_affinity, + unsigned long lowest_affinity_level); + int (*migrate_info_type)(void); +}; + +extern struct psci_operations psci_ops; + +#if defined(CONFIG_ARM_PSCI_FW) +int __init psci_dt_init(void); +#else +static inline int psci_dt_init(void) { return 0; } +#endif + +#if defined(CONFIG_ARM_PSCI_FW) && defined(CONFIG_ACPI) +int __init psci_acpi_init(void); +bool __init acpi_psci_present(void); +bool __init acpi_psci_use_hvc(void); +#else +static inline int psci_acpi_init(void) { return 0; } +static inline bool acpi_psci_present(void) { return false; } +#endif + +#endif /* __LINUX_PSCI_H */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index dfe4ddfbb43c..e830c3dff61a 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -63,6 +63,7 @@ struct unix_sock { #define UNIX_GC_CANDIDATE 0 #define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; + wait_queue_t peer_wake; }; static inline struct unix_sock *unix_sk(struct sock *sk) diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index b8529aa1dae7..b0f7445c0fdc 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -83,11 +83,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, err = ip6_local_out_sk(sk, skb); if (net_xmit_eval(err) == 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += pkt_len; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else { stats->tx_errors++; stats->tx_aborted_errors++; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index d8214cb88bbc..9c2897e56ee1 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -207,12 +207,13 @@ static inline void iptunnel_xmit_stats(int err, struct pcpu_sw_netstats __percpu *stats) { if (err > 0) { - struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats); + struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += err; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); + put_cpu_ptr(tstats); } else if (err < 0) { err_stats->tx_errors++; err_stats->tx_aborted_errors++; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index eec8ad3c9843..df555ecd4002 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock; */ struct ipv6_txoptions { + atomic_t refcnt; /* Length of this structure */ int tot_len; @@ -217,7 +218,7 @@ struct ipv6_txoptions { struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; - + struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; @@ -250,6 +251,24 @@ struct ipv6_fl_socklist { struct rcu_head rcu; }; +static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) +{ + struct ipv6_txoptions *opt; + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt && !atomic_inc_not_zero(&opt->refcnt)) + opt = NULL; + rcu_read_unlock(); + return opt; +} + +static inline void txopt_put(struct ipv6_txoptions *opt) +{ + if (opt && atomic_dec_and_test(&opt->refcnt)) + kfree_rcu(opt, rcu); +} + struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label); struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, @@ -488,6 +507,7 @@ struct ip6_create_arg { u32 user; const struct in6_addr *src; const struct in6_addr *dst; + int iif; u8 ecn; }; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 6d778efcfdfd..080b657ef8fb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -61,6 +61,9 @@ struct Qdisc { */ #define TCQ_F_WARN_NONWC (1 << 16) #define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */ +#define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : + * qdisc_tree_decrease_qlen() should stop. + */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 310d83e0a91b..3d7a0fc021a7 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -46,6 +46,11 @@ #define PSCI_0_2_FN64_MIGRATE PSCI_0_2_FN64(5) #define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU PSCI_0_2_FN64(7) +#define PSCI_1_0_FN_PSCI_FEATURES PSCI_0_2_FN(10) +#define PSCI_1_0_FN_SYSTEM_SUSPEND PSCI_0_2_FN(14) + +#define PSCI_1_0_FN64_SYSTEM_SUSPEND PSCI_0_2_FN64(14) + /* PSCI v0.2 power state encoding for CPU_SUSPEND function */ #define PSCI_0_2_POWER_STATE_ID_MASK 0xffff #define PSCI_0_2_POWER_STATE_ID_SHIFT 0 @@ -56,6 +61,13 @@ #define PSCI_0_2_POWER_STATE_AFFL_MASK \ (0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT) +/* PSCI extended power state encoding for CPU_SUSPEND function */ +#define PSCI_1_0_EXT_POWER_STATE_ID_MASK 0xfffffff +#define PSCI_1_0_EXT_POWER_STATE_ID_SHIFT 0 +#define PSCI_1_0_EXT_POWER_STATE_TYPE_SHIFT 30 +#define PSCI_1_0_EXT_POWER_STATE_TYPE_MASK \ + (0x1 << PSCI_1_0_EXT_POWER_STATE_TYPE_SHIFT) + /* PSCI v0.2 affinity level state returned by AFFINITY_INFO */ #define PSCI_0_2_AFFINITY_LEVEL_ON 0 #define PSCI_0_2_AFFINITY_LEVEL_OFF 1 @@ -76,6 +88,11 @@ #define PSCI_VERSION_MINOR(ver) \ ((ver) & PSCI_VERSION_MINOR_MASK) +/* PSCI features decoding (>=1.0) */ +#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT 1 +#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK \ + (0x1 << PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT) + /* PSCI return values (inclusive of all PSCI versions) */ #define PSCI_RET_SUCCESS 0 #define PSCI_RET_NOT_SUPPORTED -1 @@ -86,5 +103,6 @@ #define PSCI_RET_INTERNAL_FAILURE -6 #define PSCI_RET_NOT_PRESENT -7 #define PSCI_RET_DISABLED -8 +#define PSCI_RET_INVALID_ADDRESS -9 #endif /* _UAPI_LINUX_PSCI_H */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 8a6616583f38..1c1b8ab34037 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -109,7 +109,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, /* all elements already exist */ return -EEXIST; - memcpy(array->value + array->elem_size * index, value, array->elem_size); + memcpy(array->value + array->elem_size * index, value, map->value_size); return 0; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2237c1b3cdd2..d6e8cfcb6f7c 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2207,7 +2207,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, ndm->ndm_pad2 = 0; ndm->ndm_flags = pn->flags | NTF_PROXY; ndm->ndm_type = RTN_UNICAST; - ndm->ndm_ifindex = pn->dev->ifindex; + ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) @@ -2282,7 +2282,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (h > s_h) s_idx = 0; for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { - if (dev_net(n->dev) != net) + if (pneigh_net(n) != net) continue; if (idx < s_idx) goto next; diff --git a/net/core/scm.c b/net/core/scm.c index 3b6899b7d810..8a1741b14302 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -305,6 +305,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) err = put_user(cmlen, &cm->cmsg_len); if (!err) { cmlen = CMSG_SPACE(i*sizeof(int)); + if (msg->msg_controllen < cmlen) + cmlen = msg->msg_controllen; msg->msg_control += cmlen; msg->msg_controllen -= cmlen; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 5165571f397a..a0490508d213 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -202,7 +202,9 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + rcu_read_lock(); + final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); + rcu_read_unlock(); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { @@ -219,7 +221,10 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) &ireq->ir_v6_loc_addr, &ireq->ir_v6_rmt_addr); fl6.daddr = ireq->ir_v6_rmt_addr; - err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + rcu_read_lock(); + err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt), + np->tclass); + rcu_read_unlock(); err = net_xmit_eval(err); } @@ -415,6 +420,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + struct ipv6_txoptions *opt; struct inet_sock *newinet; struct dccp6_sock *newdp6; struct sock *newsk; @@ -534,13 +540,15 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, * Yes, keeping reference count would be much more clever, but we make * one more one thing there: reattach optmem to newsk. */ - if (np->opt != NULL) - newnp->opt = ipv6_dup_options(newsk, np->opt); - + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + RCU_INIT_POINTER(newnp->opt, opt); + } inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newnp->opt != NULL) - inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + - newnp->opt->opt_flen); + if (opt) + inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + + opt->opt_flen; dccp_sync_mss(newsk, dst_mtu(dst)); @@ -793,6 +801,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_sock *dp = dccp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; + struct ipv6_txoptions *opt; struct flowi6 fl6; struct dst_entry *dst; int addr_type; @@ -892,7 +901,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.fl6_sport = inet->inet_sport; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + final_p = fl6_update_dst(&fl6, opt, &final); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { @@ -912,9 +922,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, __ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; - if (np->opt != NULL) - icsk->icsk_ext_hdr_len = (np->opt->opt_flen + - np->opt->opt_nflen); + if (opt) + icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; inet->inet_dport = usin->sin6_port; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index df28693f32e1..c3bfebd501ed 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd); -static void mroute_clean_tables(struct mr_table *mrt); +static void mroute_clean_tables(struct mr_table *mrt, bool all); static void ipmr_expire_process(unsigned long arg); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES @@ -351,7 +351,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) static void ipmr_free_table(struct mr_table *mrt) { del_timer_sync(&mrt->ipmr_expire_timer); - mroute_clean_tables(mrt); + mroute_clean_tables(mrt, true); kfree(mrt); } @@ -1209,7 +1209,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct mr_table *mrt) +static void mroute_clean_tables(struct mr_table *mrt, bool all) { int i; LIST_HEAD(list); @@ -1218,8 +1218,9 @@ static void mroute_clean_tables(struct mr_table *mrt) /* Shut down all active vif entries */ for (i = 0; i < mrt->maxvif; i++) { - if (!(mrt->vif_table[i].flags & VIFF_STATIC)) - vif_delete(mrt, i, 0, &list); + if (!all && (mrt->vif_table[i].flags & VIFF_STATIC)) + continue; + vif_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); @@ -1227,7 +1228,7 @@ static void mroute_clean_tables(struct mr_table *mrt) for (i = 0; i < MFC_LINES; i++) { list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) { - if (c->mfc_flags & MFC_STATIC) + if (!all && (c->mfc_flags & MFC_STATIC)) continue; list_del_rcu(&c->list); mroute_netlink_event(mrt, c, RTM_DELROUTE); @@ -1262,7 +1263,7 @@ static void mrtsock_destruct(struct sock *sk) NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); RCU_INIT_POINTER(mrt->mroute_sk, NULL); - mroute_clean_tables(mrt); + mroute_clean_tables(mrt, false); } } rtnl_unlock(); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c9ab964189a0..87463c814896 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4438,19 +4438,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_buff *skb; + int err = -ENOMEM; + int data_len = 0; bool fragstolen; if (size == 0) return 0; - skb = alloc_skb(size, sk->sk_allocation); + if (size > PAGE_SIZE) { + int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS); + + data_len = npages << PAGE_SHIFT; + size = data_len + (size & ~PAGE_MASK); + } + skb = alloc_skb_with_frags(size - data_len, data_len, + PAGE_ALLOC_COSTLY_ORDER, + &err, sk->sk_allocation); if (!skb) goto err; + skb_put(skb, size - data_len); + skb->data_len = data_len; + skb->len = size; + if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) goto err_free; - if (memcpy_from_msg(skb_put(skb, size), msg, size)) + err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); + if (err) goto err_free; TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt; @@ -4466,7 +4481,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) err_free: kfree_skb(skb); err: - return -ENOMEM; + return err; + } static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) @@ -5622,6 +5638,7 @@ discard: } tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + tp->copied_seq = tp->rcv_nxt; tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 441ca6f38981..88203e755af8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -922,7 +922,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, } md5sig = rcu_dereference_protected(tp->md5sig_info, - sock_owned_by_user(sk)); + sock_owned_by_user(sk) || + lockdep_is_held(&sk->sk_lock.slock)); if (!md5sig) { md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8c65dc147d8b..c8f97858d6f6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock *sk) syn_set = true; } else { if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) { + /* Some middle-boxes may black-hole Fast Open _after_ + * the handshake. Therefore we conservatively disable + * Fast Open on this path on recurring timeouts with + * few or zero bytes acked after Fast Open. + */ + if (tp->syn_data_acked && + tp->bytes_acked <= tp->rx_opt.mss_clamp) { + tcp_fastopen_cache_set(sk, 0, NULL, true, 0); + if (icsk->icsk_retransmits == sysctl_tcp_retries1) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENACTIVEFAIL); + } /* Black hole detection */ tcp_mtu_probing(icsk, sk); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index eef63b394c5a..2d044d2a2ccf 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -425,9 +425,11 @@ void inet6_destroy_sock(struct sock *sk) /* Free tx options */ - opt = xchg(&np->opt, NULL); - if (opt) - sock_kfree_s(sk, opt, opt->tot_len); + opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL); + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } } EXPORT_SYMBOL_GPL(inet6_destroy_sock); @@ -656,7 +658,10 @@ int inet6_sk_rebuild_header(struct sock *sk) fl6.fl6_sport = inet->inet_sport; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - final_p = fl6_update_dst(&fl6, np->opt, &final); + rcu_read_lock(); + final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), + &final); + rcu_read_unlock(); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); if (IS_ERR(dst)) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index b10a88986a98..13ca4cf5616f 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -167,8 +167,10 @@ ipv4_connected: security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - opt = flowlabel ? flowlabel->opt : np->opt; + rcu_read_lock(); + opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt); final_p = fl6_update_dst(&fl6, opt, &final); + rcu_read_unlock(); dst = ip6_dst_lookup_flow(sk, &fl6, final_p); err = 0; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index a7bbbe45570b..adbd6958c398 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) *((char **)&opt2->srcrt) += dif; + atomic_set(&opt2->refcnt, 1); } return opt2; } @@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, return ERR_PTR(-ENOBUFS); memset(opt2, 0, tot_len); - + atomic_set(&opt2->refcnt, 1); opt2->tot_len = tot_len; p = (char *)(opt2 + 1); diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 6927f3fb5597..9beed302eb36 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -77,7 +77,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = IPPROTO_TCP; fl6->daddr = ireq->ir_v6_rmt_addr; - final_p = fl6_update_dst(fl6, np->opt, &final); + rcu_read_lock(); + final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); + rcu_read_unlock(); fl6->saddr = ireq->ir_v6_loc_addr; fl6->flowi6_oif = ireq->ir_iif; fl6->flowi6_mark = ireq->ir_mark; @@ -207,7 +209,9 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, fl6->fl6_dport = inet->inet_dport; security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); - final_p = fl6_update_dst(fl6, np->opt, &final); + rcu_read_lock(); + final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); + rcu_read_unlock(); dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { @@ -240,7 +244,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused /* Restore final destination back after routing done */ fl6.daddr = sk->sk_v6_daddr; - res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); + res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt), + np->tclass); rcu_read_unlock(); return res; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 5f36266b1f5e..a7aef4b52d65 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -118,7 +118,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc, int cmd); static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb); -static void mroute_clean_tables(struct mr6_table *mrt); +static void mroute_clean_tables(struct mr6_table *mrt, bool all); static void ipmr_expire_process(unsigned long arg); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES @@ -335,7 +335,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id) static void ip6mr_free_table(struct mr6_table *mrt) { del_timer_sync(&mrt->ipmr_expire_timer); - mroute_clean_tables(mrt); + mroute_clean_tables(mrt, true); kfree(mrt); } @@ -1543,7 +1543,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct mr6_table *mrt) +static void mroute_clean_tables(struct mr6_table *mrt, bool all) { int i; LIST_HEAD(list); @@ -1553,8 +1553,9 @@ static void mroute_clean_tables(struct mr6_table *mrt) * Shut down all active vif entries */ for (i = 0; i < mrt->maxvif; i++) { - if (!(mrt->vif6_table[i].flags & VIFF_STATIC)) - mif6_delete(mrt, i, &list); + if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC)) + continue; + mif6_delete(mrt, i, &list); } unregister_netdevice_many(&list); @@ -1563,7 +1564,7 @@ static void mroute_clean_tables(struct mr6_table *mrt) */ for (i = 0; i < MFC6_LINES; i++) { list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) { - if (c->mfc_flags & MFC_STATIC) + if (!all && (c->mfc_flags & MFC_STATIC)) continue; write_lock_bh(&mrt_lock); list_del(&c->list); @@ -1626,7 +1627,7 @@ int ip6mr_sk_done(struct sock *sk) net->ipv6.devconf_all); write_unlock_bh(&mrt_lock); - mroute_clean_tables(mrt); + mroute_clean_tables(mrt, false); err = 0; break; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 63e6956917c9..4449ad1f8114 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); } } - opt = xchg(&inet6_sk(sk)->opt, opt); + opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt, + opt); sk_dst_reset(sk); return opt; @@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sk->sk_socket->ops = &inet_dgram_ops; sk->sk_family = PF_INET; } - opt = xchg(&np->opt, NULL); - if (opt) - sock_kfree_s(sk, opt, opt->tot_len); + opt = xchg((__force struct ipv6_txoptions **)&np->opt, + NULL); + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } pktopt = xchg(&np->pktoptions, NULL); kfree_skb(pktopt); @@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) break; - opt = ipv6_renew_options(sk, np->opt, optname, + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + opt = ipv6_renew_options(sk, opt, optname, (struct ipv6_opt_hdr __user *)optval, optlen); if (IS_ERR(opt)) { @@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; opt = ipv6_update_options(sk, opt); sticky_done: - if (opt) - sock_kfree_s(sk, opt, opt->tot_len); + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } break; } @@ -486,6 +493,7 @@ sticky_done: break; memset(opt, 0, sizeof(*opt)); + atomic_set(&opt->refcnt, 1); opt->tot_len = sizeof(*opt) + optlen; retv = -EFAULT; if (copy_from_user(opt+1, optval, optlen)) @@ -502,8 +510,10 @@ update: retv = 0; opt = ipv6_update_options(sk, opt); done: - if (opt) - sock_kfree_s(sk, opt, opt->tot_len); + if (opt) { + atomic_sub(opt->tot_len, &sk->sk_omem_alloc); + txopt_put(opt); + } break; } case IPV6_UNICAST_HOPS: @@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_RTHDR: case IPV6_DSTOPTS: { + struct ipv6_txoptions *opt; lock_sock(sk); - len = ipv6_getsockopt_sticky(sk, np->opt, - optname, optval, len); + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len); release_sock(sk); /* check if ipv6_getsockopt_sticky() returns err code */ if (len < 0) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 083b2927fc67..41e3b5ee8d0b 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1651,7 +1651,6 @@ out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); } else { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); } @@ -2014,7 +2013,6 @@ out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, full_len); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 6f187c8d8a1b..d235ed7f47ab 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data) /* Creation primitives. */ static inline struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, struct in6_addr *src, - struct in6_addr *dst, u8 ecn) + struct in6_addr *dst, int iif, u8 ecn) { struct inet_frag_queue *q; struct ip6_create_arg arg; @@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id, arg.user = user; arg.src = src; arg.dst = dst; + arg.iif = iif; arg.ecn = ecn; local_bh_disable(); @@ -603,7 +604,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) fhdr = (struct frag_hdr *)skb_transport_header(clone); fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, - ip6_frag_ecn(hdr)); + skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); goto ret_orig; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8072bd4139b7..2c639aee12cb 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -731,6 +731,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { + struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; @@ -837,8 +838,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } - if (!opt) - opt = np->opt; + if (!opt) { + opt = txopt_get(np); + opt_to_free = opt; + } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); @@ -901,6 +904,7 @@ done: dst_release(dst); out: fl6_sock_release(flowlabel); + txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: dst_confirm(dst); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 8ffa2c8cce77..9d1f6a28b284 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a) return fq->id == arg->id && fq->user == arg->user && ipv6_addr_equal(&fq->saddr, arg->src) && - ipv6_addr_equal(&fq->daddr, arg->dst); + ipv6_addr_equal(&fq->daddr, arg->dst) && + (arg->iif == fq->iif || + !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))); } EXPORT_SYMBOL(ip6_frag_match); @@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data) static struct frag_queue * fq_find(struct net *net, __be32 id, const struct in6_addr *src, - const struct in6_addr *dst, u8 ecn) + const struct in6_addr *dst, int iif, u8 ecn) { struct inet_frag_queue *q; struct ip6_create_arg arg; @@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, arg.user = IP6_DEFRAG_LOCAL_DELIVER; arg.src = src; arg.dst = dst; + arg.iif = iif; arg.ecn = ecn; hash = inet6_hash_frag(id, src, dst); @@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) } fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, - ip6_frag_ecn(hdr)); + skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); if (fq) { int ret; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 21bc2eb53c57..a4cf004f44d0 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -242,7 +242,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = ireq->ir_v6_rmt_addr; - final_p = fl6_update_dst(&fl6, np->opt, &final); + final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); fl6.saddr = ireq->ir_v6_loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = ireq->ir_mark; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e541d68dba8b..cfb27f56c62f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -121,6 +121,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; + struct ipv6_txoptions *opt; struct rt6_info *rt; struct flowi6 fl6; struct dst_entry *dst; @@ -237,7 +238,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; - final_p = fl6_update_dst(&fl6, np->opt, &final); + opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); + final_p = fl6_update_dst(&fl6, opt, &final); security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); @@ -266,9 +268,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tcp_fetch_timewait_stamp(sk, dst); icsk->icsk_ext_hdr_len = 0; - if (np->opt) - icsk->icsk_ext_hdr_len = (np->opt->opt_flen + - np->opt->opt_nflen); + if (opt) + icsk->icsk_ext_hdr_len = opt->opt_flen + + opt->opt_nflen; tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); @@ -464,7 +466,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); skb_set_queue_mapping(skb, queue_mapping); - err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass); + err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), + np->tclass); err = net_xmit_eval(err); } @@ -994,6 +997,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct inet_request_sock *ireq; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct tcp6_sock *newtcp6sk; + struct ipv6_txoptions *opt; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; @@ -1129,13 +1133,15 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, but we make one more one thing there: reattach optmem to newsk. */ - if (np->opt) - newnp->opt = ipv6_dup_options(newsk, np->opt); - + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + RCU_INIT_POINTER(newnp->opt, opt); + } inet_csk(newsk)->icsk_ext_hdr_len = 0; - if (newnp->opt) - inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + - newnp->opt->opt_flen); + if (opt) + inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + + opt->opt_flen; tcp_ca_openreq_child(newsk, dst); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e51fc3eee6db..7333f3575fc5 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1107,6 +1107,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_txoptions *opt = NULL; + struct ipv6_txoptions *opt_to_free = NULL; struct ip6_flowlabel *flowlabel = NULL; struct flowi6 fl6; struct dst_entry *dst; @@ -1260,8 +1261,10 @@ do_udp_sendmsg: opt = NULL; connected = 0; } - if (!opt) - opt = np->opt; + if (!opt) { + opt = txopt_get(np); + opt_to_free = opt; + } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); @@ -1370,6 +1373,7 @@ release_dst: out: dst_release(dst); fl6_sock_release(flowlabel); + txopt_put(opt_to_free); if (!err) return len; /* diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index d1ded3777815..0ce9da948ad7 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; @@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) opt = NULL; } - if (opt == NULL) - opt = np->opt; + if (!opt) { + opt = txopt_get(np); + opt_to_free = opt; + } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); @@ -631,6 +634,7 @@ done: dst_release(dst); out: fl6_sock_release(flowlabel); + txopt_put(opt_to_free); return err < 0 ? err : len; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 686e60187401..ebc39e66d704 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1524,6 +1524,20 @@ static void fanout_release(struct sock *sk) mutex_unlock(&fanout_mutex); } +static bool packet_extra_vlan_len_allowed(const struct net_device *dev, + struct sk_buff *skb) +{ + /* Earlier code assumed this would be a VLAN pkt, double-check + * this now that we have the actual packet in hand. We can only + * do this check on Ethernet devices. + */ + if (unlikely(dev->type != ARPHRD_ETHER)) + return false; + + skb_reset_mac_header(skb); + return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); +} + static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; @@ -1685,18 +1699,10 @@ retry: goto retry; } - if (len > (dev->mtu + dev->hard_header_len + extra_len)) { - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ - struct ethhdr *ehdr; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) { - err = -EMSGSIZE; - goto out_unlock; - } + if (len > (dev->mtu + dev->hard_header_len + extra_len) && + !packet_extra_vlan_len_allowed(dev, skb)) { + err = -EMSGSIZE; + goto out_unlock; } skb->protocol = proto; @@ -2115,6 +2121,15 @@ static bool ll_header_truncated(const struct net_device *dev, int len) return false; } +static void tpacket_set_protocol(const struct net_device *dev, + struct sk_buff *skb) +{ + if (dev->type == ARPHRD_ETHER) { + skb_reset_mac_header(skb); + skb->protocol = eth_hdr(skb)->h_proto; + } +} + static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, int size_max, __be16 proto, unsigned char *addr, int hlen) @@ -2151,8 +2166,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb_reserve(skb, hlen); skb_reset_network_header(skb); - if (!packet_use_direct_xmit(po)) - skb_probe_transport_header(skb, 0); if (unlikely(po->tp_tx_has_off)) { int off_min, off_max, off; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); @@ -2198,6 +2211,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, dev->hard_header_len); if (unlikely(err)) return err; + if (!skb->protocol) + tpacket_set_protocol(dev, skb); data += dev->hard_header_len; to_write -= dev->hard_header_len; @@ -2232,6 +2247,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, len = ((to_write > len_max) ? len_max : to_write); } + skb_probe_transport_header(skb, 0); + return tp_len; } @@ -2276,12 +2293,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; - reserve = dev->hard_header_len + VLAN_HLEN; + if (po->sk.sk_socket->type == SOCK_RAW) + reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); - if (size_max > dev->mtu + reserve) - size_max = dev->mtu + reserve; + if (size_max > dev->mtu + reserve + VLAN_HLEN) + size_max = dev->mtu + reserve + VLAN_HLEN; do { ph = packet_current_frame(po, &po->tx_ring, @@ -2308,18 +2326,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, addr, hlen); if (likely(tp_len >= 0) && - tp_len > dev->mtu + dev->hard_header_len) { - struct ethhdr *ehdr; - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ + tp_len > dev->mtu + reserve && + !packet_extra_vlan_len_allowed(dev, skb)) + tp_len = -EMSGSIZE; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) - tp_len = -EMSGSIZE; - } if (unlikely(tp_len < 0)) { if (po->tp_loss) { __packet_set_status(po, ph, @@ -2540,18 +2550,10 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); - if (!gso_type && (len > dev->mtu + reserve + extra_len)) { - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ - struct ethhdr *ehdr; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) { - err = -EMSGSIZE; - goto out_free; - } + if (!gso_type && (len > dev->mtu + reserve + extra_len) && + !packet_extra_vlan_len_allowed(dev, skb)) { + err = -EMSGSIZE; + goto out_free; } skb->protocol = proto; @@ -2582,8 +2584,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) len += vnet_hdr_len; } - if (!packet_use_direct_xmit(po)) - skb_probe_transport_header(skb, reserve); + skb_probe_transport_header(skb, reserve); + if (unlikely(extra_len == 4)) skb->no_fcs = 1; diff --git a/net/rds/connection.c b/net/rds/connection.c index 9d66705f9d41..da6da57e5f36 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -187,12 +187,6 @@ new_conn: } } - if (trans == NULL) { - kmem_cache_free(rds_conn_slab, conn); - conn = ERR_PTR(-ENODEV); - goto out; - } - conn->c_trans = trans; ret = trans->conn_alloc(conn, gfp); diff --git a/net/rds/send.c b/net/rds/send.c index e9430f537f9c..7b30c0f3180d 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -986,11 +986,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) release_sock(sk); } - /* racing with another thread binding seems ok here */ + lock_sock(sk); if (daddr == 0 || rs->rs_bound_addr == 0) { + release_sock(sk); ret = -ENOTCONN; /* XXX not a great errno */ goto out; } + release_sock(sk); /* size of rm including all sgs */ ret = rds_rm_size(msg, payload_len); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1e1c89e51a11..d4b6f3682c14 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -253,7 +253,8 @@ int qdisc_set_default(const char *name) } /* We know handle. Find qdisc among all qdisc's attached to device - (root qdisc, all its children, children of children etc.) + * (root qdisc, all its children, children of children etc.) + * Note: caller either uses rtnl or rcu_read_lock() */ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) @@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) root->handle == handle) return root; - list_for_each_entry(q, &root->list, list) { + list_for_each_entry_rcu(q, &root->list, list) { if (q->handle == handle) return q; } @@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q) struct Qdisc *root = qdisc_dev(q)->qdisc; WARN_ON_ONCE(root == &noop_qdisc); - list_add_tail(&q->list, &root->list); + ASSERT_RTNL(); + list_add_tail_rcu(&q->list, &root->list); } } EXPORT_SYMBOL(qdisc_list_add); void qdisc_list_del(struct Qdisc *q) { - if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) - list_del(&q->list); + if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { + ASSERT_RTNL(); + list_del_rcu(&q->list); + } } EXPORT_SYMBOL(qdisc_list_del); @@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) if (n == 0) return; drops = max_t(int, n, 0); + rcu_read_lock(); while ((parentid = sch->parent)) { if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS)) - return; + break; + if (sch->flags & TCQ_F_NOPARENT) + break; + /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { - WARN_ON(parentid != TC_H_ROOT); - return; + WARN_ON_ONCE(parentid != TC_H_ROOT); + break; } cops = sch->ops->cl_ops; if (cops->qlen_notify) { @@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) sch->q.qlen -= n; __qdisc_qstats_drop(sch, drops); } + rcu_read_unlock(); } EXPORT_SYMBOL(qdisc_tree_decrease_qlen); @@ -941,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, } lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) - sch->flags |= TCQ_F_ONETXQUEUE; + sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } sch->handle = handle; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 6efca30894aa..b453270be3fd 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -743,7 +743,7 @@ static void attach_one_default_qdisc(struct net_device *dev, return; } if (!netif_is_multiqueue(dev)) - qdisc->flags |= TCQ_F_ONETXQUEUE; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } dev_queue->qdisc_sleeping = qdisc; } diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index f3cbaecd283a..3e82f047caaf 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) if (qdisc == NULL) goto err; priv->qdiscs[ntx] = qdisc; - qdisc->flags |= TCQ_F_ONETXQUEUE; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } sch->flags |= TCQ_F_MQROOT; @@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, *old = dev_graft_qdisc(dev_queue, new); if (new) - new->flags |= TCQ_F_ONETXQUEUE; + new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 3811a745452c..ad70ecf57ce7 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) goto err; } priv->qdiscs[i] = qdisc; - qdisc->flags |= TCQ_F_ONETXQUEUE; + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } /* If the mqprio options indicate that hardware should own @@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, *old = dev_graft_qdisc(dev_queue, new); if (new) - new->flags |= TCQ_F_ONETXQUEUE; + new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 4f15b7d730e1..1543e39f47c3 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -809,8 +809,8 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, if (!has_sha1) return -EINVAL; - memcpy(ep->auth_hmacs_list->hmac_ids, &hmacs->shmac_idents[0], - hmacs->shmac_num_idents * sizeof(__u16)); + for (i = 0; i < hmacs->shmac_num_idents; i++) + ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]); ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) + hmacs->shmac_num_idents * sizeof(__u16)); return 0; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 5f6c4e61325b..66d796075050 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -7387,6 +7387,13 @@ struct proto sctp_prot = { #if IS_ENABLED(CONFIG_IPV6) +#include <net/transp_v6.h> +static void sctp_v6_destroy_sock(struct sock *sk) +{ + sctp_destroy_sock(sk); + inet6_destroy_sock(sk); +} + struct proto sctpv6_prot = { .name = "SCTPv6", .owner = THIS_MODULE, @@ -7396,7 +7403,7 @@ struct proto sctpv6_prot = { .accept = sctp_accept, .ioctl = sctp_ioctl, .init = sctp_init_sock, - .destroy = sctp_destroy_sock, + .destroy = sctp_v6_destroy_sock, .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 76e66695621c..1975fd8d1c10 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -316,6 +316,118 @@ found: return s; } +/* Support code for asymmetrically connected dgram sockets + * + * If a datagram socket is connected to a socket not itself connected + * to the first socket (eg, /dev/log), clients may only enqueue more + * messages if the present receive queue of the server socket is not + * "too large". This means there's a second writeability condition + * poll and sendmsg need to test. The dgram recv code will do a wake + * up on the peer_wait wait queue of a socket upon reception of a + * datagram which needs to be propagated to sleeping would-be writers + * since these might not have sent anything so far. This can't be + * accomplished via poll_wait because the lifetime of the server + * socket might be less than that of its clients if these break their + * association with it or if the server socket is closed while clients + * are still connected to it and there's no way to inform "a polling + * implementation" that it should let go of a certain wait queue + * + * In order to propagate a wake up, a wait_queue_t of the client + * socket is enqueued on the peer_wait queue of the server socket + * whose wake function does a wake_up on the ordinary client socket + * wait queue. This connection is established whenever a write (or + * poll for write) hit the flow control condition and broken when the + * association to the server socket is dissolved or after a wake up + * was relayed. + */ + +static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags, + void *key) +{ + struct unix_sock *u; + wait_queue_head_t *u_sleep; + + u = container_of(q, struct unix_sock, peer_wake); + + __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait, + q); + u->peer_wake.private = NULL; + + /* relaying can only happen while the wq still exists */ + u_sleep = sk_sleep(&u->sk); + if (u_sleep) + wake_up_interruptible_poll(u_sleep, key); + + return 0; +} + +static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other) +{ + struct unix_sock *u, *u_other; + int rc; + + u = unix_sk(sk); + u_other = unix_sk(other); + rc = 0; + spin_lock(&u_other->peer_wait.lock); + + if (!u->peer_wake.private) { + u->peer_wake.private = other; + __add_wait_queue(&u_other->peer_wait, &u->peer_wake); + + rc = 1; + } + + spin_unlock(&u_other->peer_wait.lock); + return rc; +} + +static void unix_dgram_peer_wake_disconnect(struct sock *sk, + struct sock *other) +{ + struct unix_sock *u, *u_other; + + u = unix_sk(sk); + u_other = unix_sk(other); + spin_lock(&u_other->peer_wait.lock); + + if (u->peer_wake.private == other) { + __remove_wait_queue(&u_other->peer_wait, &u->peer_wake); + u->peer_wake.private = NULL; + } + + spin_unlock(&u_other->peer_wait.lock); +} + +static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk, + struct sock *other) +{ + unix_dgram_peer_wake_disconnect(sk, other); + wake_up_interruptible_poll(sk_sleep(sk), + POLLOUT | + POLLWRNORM | + POLLWRBAND); +} + +/* preconditions: + * - unix_peer(sk) == other + * - association is stable + */ +static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) +{ + int connected; + + connected = unix_dgram_peer_wake_connect(sk, other); + + if (unix_recvq_full(other)) + return 1; + + if (connected) + unix_dgram_peer_wake_disconnect(sk, other); + + return 0; +} + static inline int unix_writable(struct sock *sk) { return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; @@ -420,6 +532,8 @@ static void unix_release_sock(struct sock *sk, int embrion) skpair->sk_state_change(skpair); sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP); } + + unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ unix_peer(sk) = NULL; } @@ -648,6 +762,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) INIT_LIST_HEAD(&u->link); mutex_init(&u->readlock); /* single task reading lock */ init_waitqueue_head(&u->peer_wait); + init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); unix_insert_socket(unix_sockets_unbound(sk), sk); out: if (sk == NULL) @@ -1015,6 +1130,8 @@ restart: if (unix_peer(sk)) { struct sock *old_peer = unix_peer(sk); unix_peer(sk) = other; + unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer); + unix_state_double_unlock(sk, other); if (other != old_peer) @@ -1453,6 +1570,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, struct scm_cookie scm; int max_level; int data_len = 0; + int sk_locked; wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); @@ -1532,12 +1650,14 @@ restart: goto out_free; } + sk_locked = 0; unix_state_lock(other); +restart_locked: err = -EPERM; if (!unix_may_send(sk, other)) goto out_unlock; - if (sock_flag(other, SOCK_DEAD)) { + if (unlikely(sock_flag(other, SOCK_DEAD))) { /* * Check with 1003.1g - what should * datagram error @@ -1545,10 +1665,14 @@ restart: unix_state_unlock(other); sock_put(other); + if (!sk_locked) + unix_state_lock(sk); + err = 0; - unix_state_lock(sk); if (unix_peer(sk) == other) { unix_peer(sk) = NULL; + unix_dgram_peer_wake_disconnect_wakeup(sk, other); + unix_state_unlock(sk); unix_dgram_disconnected(sk, other); @@ -1574,21 +1698,38 @@ restart: goto out_unlock; } - if (unix_peer(other) != sk && unix_recvq_full(other)) { - if (!timeo) { - err = -EAGAIN; - goto out_unlock; + if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + if (timeo) { + timeo = unix_wait_for_peer(other, timeo); + + err = sock_intr_errno(timeo); + if (signal_pending(current)) + goto out_free; + + goto restart; } - timeo = unix_wait_for_peer(other, timeo); + if (!sk_locked) { + unix_state_unlock(other); + unix_state_double_lock(sk, other); + } - err = sock_intr_errno(timeo); - if (signal_pending(current)) - goto out_free; + if (unix_peer(sk) != other || + unix_dgram_peer_wake_me(sk, other)) { + err = -EAGAIN; + sk_locked = 1; + goto out_unlock; + } - goto restart; + if (!sk_locked) { + sk_locked = 1; + goto restart_locked; + } } + if (unlikely(sk_locked)) + unix_state_unlock(sk); + if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); maybe_add_creds(skb, sock, other); @@ -1602,6 +1743,8 @@ restart: return len; out_unlock: + if (sk_locked) + unix_state_unlock(sk); unix_state_unlock(other); out_free: kfree_skb(skb); @@ -2245,14 +2388,16 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, return mask; writable = unix_writable(sk); - other = unix_peer_get(sk); - if (other) { - if (unix_peer(other) != sk) { - sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); - if (unix_recvq_full(other)) - writable = 0; - } - sock_put(other); + if (writable) { + unix_state_lock(sk); + + other = unix_peer(sk); + if (other && unix_peer(other) != sk && + unix_recvq_full(other) && + unix_dgram_peer_wake_me(sk, other)) + writable = 0; + + unix_state_unlock(sk); } if (writable) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 225b78b4ef12..d02eccd51f6e 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -48,8 +48,9 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info"); #define is_haswell(codec) ((codec)->core.vendor_id == 0x80862807) #define is_broadwell(codec) ((codec)->core.vendor_id == 0x80862808) #define is_skylake(codec) ((codec)->core.vendor_id == 0x80862809) +#define is_broxton(codec) ((codec)->core.vendor_id == 0x8086280a) #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \ - || is_skylake(codec)) + || is_skylake(codec) || is_broxton(codec)) #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882) #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883) diff --git a/tools/net/Makefile b/tools/net/Makefile index ee577ea03ba5..ddf888010652 100644 --- a/tools/net/Makefile +++ b/tools/net/Makefile @@ -4,6 +4,9 @@ CC = gcc LEX = flex YACC = bison +CFLAGS += -Wall -O2 +CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include + %.yacc.c: %.y $(YACC) -o $@ -d $< @@ -12,15 +15,13 @@ YACC = bison all : bpf_jit_disasm bpf_dbg bpf_asm -bpf_jit_disasm : CFLAGS = -Wall -O2 -DPACKAGE='bpf_jit_disasm' +bpf_jit_disasm : CFLAGS += -DPACKAGE='bpf_jit_disasm' bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl bpf_jit_disasm : bpf_jit_disasm.o -bpf_dbg : CFLAGS = -Wall -O2 bpf_dbg : LDLIBS = -lreadline bpf_dbg : bpf_dbg.o -bpf_asm : CFLAGS = -Wall -O2 -I. bpf_asm : LDLIBS = bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o bpf_exp.lex.o : bpf_exp.yacc.c |