From 9ed7d75b2f09d836e71d597cd5879abb1a44e7a9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 27 Feb 2019 09:48:51 +0100 Subject: x86/percpu: Relax smp_processor_id() Nadav reported that since this_cpu_read() became asm-volatile, many smp_processor_id() users generated worse code due to the extra constraints. However since smp_processor_id() is reading a stable value, we can use __this_cpu_read(). While this does reduce text size somewhat, this mostly results in code movement to .text.unlikely as a result of more/larger .cold. subfunctions. Less text on the hotpath is good for I$. $ ./compare.sh defconfig-build1 defconfig-build2 vmlinux.o setup_APIC_ibs 90 98 -12,+20 force_ibs_eilvt_setup 400 413 -57,+70 pci_serr_error 109 104 -54,+49 pci_serr_error 109 104 -54,+49 unknown_nmi_error 125 120 -76,+71 unknown_nmi_error 125 120 -76,+71 io_check_error 125 132 -97,+104 intel_thermal_interrupt 730 822 +92,+0 intel_init_thermal 951 945 -6,+0 generic_get_mtrr 301 294 -7,+0 generic_get_mtrr 301 294 -7,+0 generic_set_all 749 754 -44,+49 get_fixed_ranges 352 360 -41,+49 x86_acpi_suspend_lowlevel 369 363 -6,+0 check_tsc_sync_source 412 412 -71,+71 irq_migrate_all_off_this_cpu 662 674 -14,+26 clocksource_watchdog 748 748 -113,+113 __perf_event_account_interrupt 204 197 -7,+0 attempt_merge 1748 1741 -7,+0 intel_guc_send_ct 1424 1409 -15,+0 __fini_doorbell 235 231 -4,+0 bdw_set_cdclk 928 923 -5,+0 gen11_dsi_disable 1571 1556 -15,+0 gmbus_wait 493 488 -5,+0 md_make_request 376 369 -7,+0 __split_and_process_bio 543 536 -7,+0 delay_tsc 96 89 -7,+0 hsw_disable_pc8 696 691 -5,+0 tsc_verify_tsc_adjust 215 228 -22,+35 cpuidle_driver_unref 56 49 -7,+0 blk_account_io_completion 159 148 -11,+0 mtrr_wrmsr 95 99 -29,+33 __intel_wait_for_register_fw 401 419 +18,+0 cpuidle_driver_ref 43 36 -7,+0 cpuidle_get_driver 15 8 -7,+0 blk_account_io_done 535 528 -7,+0 irq_migrate_all_off_this_cpu 662 674 -14,+26 check_tsc_sync_source 412 412 -71,+71 irq_wait_for_poll 170 163 -7,+0 generic_end_io_acct 329 322 -7,+0 x86_acpi_suspend_lowlevel 369 363 -6,+0 nohz_balance_enter_idle 198 191 -7,+0 generic_start_io_acct 254 247 -7,+0 blk_account_io_start 341 334 -7,+0 perf_event_task_tick 682 675 -7,+0 intel_init_thermal 951 945 -6,+0 amd_e400_c1e_apic_setup 47 51 -28,+32 setup_APIC_eilvt 350 328 -22,+0 hsw_enable_pc8 1611 1605 -6,+0 total 12985947 12985892 -994,+939 Reported-by: Nadav Amit Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/smp.h | 45 +++++++++++++++++++++++++++++++-------------- 1 file changed, 31 insertions(+), 14 deletions(-) (limited to 'include/linux/smp.h') diff --git a/include/linux/smp.h b/include/linux/smp.h index a56f08ff3097..aa9e5e82d8c3 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -181,29 +181,46 @@ static inline int get_boot_cpu_id(void) #endif /* !SMP */ -/* - * smp_processor_id(): get the current CPU ID. +/** + * raw_processor_id() - get the current (unstable) CPU id + * + * For then you know what you are doing and need an unstable + * CPU id. + */ + +/** + * smp_processor_id() - get the current (stable) CPU id + * + * This is the normal accessor to the CPU id and should be used + * whenever possible. + * + * The CPU id is stable when: * - * if DEBUG_PREEMPT is enabled then we check whether it is - * used in a preemption-safe way. (smp_processor_id() is safe - * if it's used in a preemption-off critical section, or in - * a thread that is bound to the current CPU.) + * - IRQs are disabled; + * - preemption is disabled; + * - the task is CPU affine. * - * NOTE: raw_smp_processor_id() is for internal use only - * (smp_processor_id() is the preferred variant), but in rare - * instances it might also be used to turn off false positives - * (i.e. smp_processor_id() use that the debugging code reports but - * which use for some reason is legal). Don't use this to hack around - * the warning message, as your code might not work under PREEMPT. + * When CONFIG_DEBUG_PREEMPT; we verify these assumption and WARN + * when smp_processor_id() is used when the CPU id is not stable. */ + +/* + * Allow the architecture to differentiate between a stable and unstable read. + * For example, x86 uses an IRQ-safe asm-volatile read for the unstable but a + * regular asm read for the stable. + */ +#ifndef __smp_processor_id +#define __smp_processor_id(x) raw_smp_processor_id(x) +#endif + #ifdef CONFIG_DEBUG_PREEMPT extern unsigned int debug_smp_processor_id(void); # define smp_processor_id() debug_smp_processor_id() #else -# define smp_processor_id() raw_smp_processor_id() +# define smp_processor_id() __smp_processor_id() #endif -#define get_cpu() ({ preempt_disable(); smp_processor_id(); }) +#define get_cpu() ({ preempt_disable(); __smp_processor_id(); }) #define put_cpu() preempt_enable() /* -- cgit v1.3-14-g43fede From caa759323c73676b3e48c8d9c86093c88b4aba97 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Wed, 12 Jun 2019 23:48:05 -0700 Subject: smp: Remove smp_call_function() and on_each_cpu() return values The return value is fixed. Remove it and amend the callers. [ tglx: Fixup arm/bL_switcher and powerpc/rtas ] Signed-off-by: Nadav Amit Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Tony Luck Cc: Fenghua Yu Cc: Andrew Morton Link: https://lkml.kernel.org/r/20190613064813.8102-2-namit@vmware.com --- arch/alpha/kernel/smp.c | 19 +++++-------------- arch/alpha/oprofile/common.c | 6 +++--- arch/arm/common/bL_switcher.c | 6 ++---- arch/ia64/kernel/perfmon.c | 12 ++---------- arch/ia64/kernel/uncached.c | 8 ++++---- arch/powerpc/kernel/rtas.c | 3 +-- arch/x86/lib/cache-smp.c | 3 ++- drivers/char/agp/generic.c | 3 +-- include/linux/smp.h | 7 +++---- kernel/smp.c | 10 +++------- kernel/up.c | 3 +-- 11 files changed, 27 insertions(+), 53 deletions(-) (limited to 'include/linux/smp.h') diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index d0dccae53ba9..5f90df30be20 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -614,8 +614,7 @@ void smp_imb(void) { /* Must wait other processors to flush their icache before continue. */ - if (on_each_cpu(ipi_imb, NULL, 1)) - printk(KERN_CRIT "smp_imb: timed out\n"); + on_each_cpu(ipi_imb, NULL, 1); } EXPORT_SYMBOL(smp_imb); @@ -630,9 +629,7 @@ flush_tlb_all(void) { /* Although we don't have any data to pass, we do want to synchronize with the other processors. */ - if (on_each_cpu(ipi_flush_tlb_all, NULL, 1)) { - printk(KERN_CRIT "flush_tlb_all: timed out\n"); - } + on_each_cpu(ipi_flush_tlb_all, NULL, 1); } #define asn_locked() (cpu_data[smp_processor_id()].asn_lock) @@ -667,9 +664,7 @@ flush_tlb_mm(struct mm_struct *mm) } } - if (smp_call_function(ipi_flush_tlb_mm, mm, 1)) { - printk(KERN_CRIT "flush_tlb_mm: timed out\n"); - } + smp_call_function(ipi_flush_tlb_mm, mm, 1); preempt_enable(); } @@ -720,9 +715,7 @@ flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) data.mm = mm; data.addr = addr; - if (smp_call_function(ipi_flush_tlb_page, &data, 1)) { - printk(KERN_CRIT "flush_tlb_page: timed out\n"); - } + smp_call_function(ipi_flush_tlb_page, &data, 1); preempt_enable(); } @@ -772,9 +765,7 @@ flush_icache_user_range(struct vm_area_struct *vma, struct page *page, } } - if (smp_call_function(ipi_flush_icache_page, mm, 1)) { - printk(KERN_CRIT "flush_icache_page: timed out\n"); - } + smp_call_function(ipi_flush_icache_page, mm, 1); preempt_enable(); } diff --git a/arch/alpha/oprofile/common.c b/arch/alpha/oprofile/common.c index 310a4ce1dccc..1b1259c7d7d1 100644 --- a/arch/alpha/oprofile/common.c +++ b/arch/alpha/oprofile/common.c @@ -65,7 +65,7 @@ op_axp_setup(void) model->reg_setup(®, ctr, &sys); /* Configure the registers on all cpus. */ - (void)smp_call_function(model->cpu_setup, ®, 1); + smp_call_function(model->cpu_setup, ®, 1); model->cpu_setup(®); return 0; } @@ -86,7 +86,7 @@ op_axp_cpu_start(void *dummy) static int op_axp_start(void) { - (void)smp_call_function(op_axp_cpu_start, NULL, 1); + smp_call_function(op_axp_cpu_start, NULL, 1); op_axp_cpu_start(NULL); return 0; } @@ -101,7 +101,7 @@ op_axp_cpu_stop(void *dummy) static void op_axp_stop(void) { - (void)smp_call_function(op_axp_cpu_stop, NULL, 1); + smp_call_function(op_axp_cpu_stop, NULL, 1); op_axp_cpu_stop(NULL); } diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c index 57f3b7512636..17bc259729e2 100644 --- a/arch/arm/common/bL_switcher.c +++ b/arch/arm/common/bL_switcher.c @@ -542,16 +542,14 @@ static void bL_switcher_trace_trigger_cpu(void *__always_unused info) int bL_switcher_trace_trigger(void) { - int ret; - preempt_disable(); bL_switcher_trace_trigger_cpu(NULL); - ret = smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true); + smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true); preempt_enable(); - return ret; + return 0; } EXPORT_SYMBOL_GPL(bL_switcher_trace_trigger); diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 58a6337c0690..7c52bd2695a2 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -6390,11 +6390,7 @@ pfm_install_alt_pmu_interrupt(pfm_intr_handler_desc_t *hdl) } /* save the current system wide pmu states */ - ret = on_each_cpu(pfm_alt_save_pmu_state, NULL, 1); - if (ret) { - DPRINT(("on_each_cpu() failed: %d\n", ret)); - goto cleanup_reserve; - } + on_each_cpu(pfm_alt_save_pmu_state, NULL, 1); /* officially change to the alternate interrupt handler */ pfm_alt_intr_handler = hdl; @@ -6421,7 +6417,6 @@ int pfm_remove_alt_pmu_interrupt(pfm_intr_handler_desc_t *hdl) { int i; - int ret; if (hdl == NULL) return -EINVAL; @@ -6435,10 +6430,7 @@ pfm_remove_alt_pmu_interrupt(pfm_intr_handler_desc_t *hdl) pfm_alt_intr_handler = NULL; - ret = on_each_cpu(pfm_alt_restore_pmu_state, NULL, 1); - if (ret) { - DPRINT(("on_each_cpu() failed: %d\n", ret)); - } + on_each_cpu(pfm_alt_restore_pmu_state, NULL, 1); for_each_online_cpu(i) { pfm_unreserve_session(NULL, 1, i); diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c index 583f7ff6b589..c618d0745e22 100644 --- a/arch/ia64/kernel/uncached.c +++ b/arch/ia64/kernel/uncached.c @@ -124,8 +124,8 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid) status = ia64_pal_prefetch_visibility(PAL_VISIBILITY_PHYSICAL); if (status == PAL_VISIBILITY_OK_REMOTE_NEEDED) { atomic_set(&uc_pool->status, 0); - status = smp_call_function(uncached_ipi_visibility, uc_pool, 1); - if (status || atomic_read(&uc_pool->status)) + smp_call_function(uncached_ipi_visibility, uc_pool, 1); + if (atomic_read(&uc_pool->status)) goto failed; } else if (status != PAL_VISIBILITY_OK) goto failed; @@ -146,8 +146,8 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid) if (status != PAL_STATUS_SUCCESS) goto failed; atomic_set(&uc_pool->status, 0); - status = smp_call_function(uncached_ipi_mc_drain, uc_pool, 1); - if (status || atomic_read(&uc_pool->status)) + smp_call_function(uncached_ipi_mc_drain, uc_pool, 1); + if (atomic_read(&uc_pool->status)) goto failed; /* diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index fbc676160adf..64d95eb6ffff 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -994,8 +994,7 @@ int rtas_ibm_suspend_me(u64 handle) /* Call function on all CPUs. One of us will make the * rtas call */ - if (on_each_cpu(rtas_percpu_suspend_me, &data, 0)) - atomic_set(&data.error, -EINVAL); + on_each_cpu(rtas_percpu_suspend_me, &data, 0); wait_for_completion(&done); diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c index 1811fa4a1b1a..7c48ff4ae8d1 100644 --- a/arch/x86/lib/cache-smp.c +++ b/arch/x86/lib/cache-smp.c @@ -15,6 +15,7 @@ EXPORT_SYMBOL(wbinvd_on_cpu); int wbinvd_on_all_cpus(void) { - return on_each_cpu(__wbinvd, NULL, 1); + on_each_cpu(__wbinvd, NULL, 1); + return 0; } EXPORT_SYMBOL(wbinvd_on_all_cpus); diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c index 658664a5a5aa..df1edb5ec0ad 100644 --- a/drivers/char/agp/generic.c +++ b/drivers/char/agp/generic.c @@ -1311,8 +1311,7 @@ static void ipi_handler(void *null) void global_cache_flush(void) { - if (on_each_cpu(ipi_handler, NULL, 1) != 0) - panic(PFX "timed out waiting for the other CPUs!\n"); + on_each_cpu(ipi_handler, NULL, 1); } EXPORT_SYMBOL(global_cache_flush); diff --git a/include/linux/smp.h b/include/linux/smp.h index a56f08ff3097..bb8b451ab01f 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -35,7 +35,7 @@ int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, /* * Call a function on all processors */ -int on_each_cpu(smp_call_func_t func, void *info, int wait); +void on_each_cpu(smp_call_func_t func, void *info, int wait); /* * Call a function on processors specified by mask, which might include @@ -101,7 +101,7 @@ extern void smp_cpus_done(unsigned int max_cpus); /* * Call a function on all other processors */ -int smp_call_function(smp_call_func_t func, void *info, int wait); +void smp_call_function(smp_call_func_t func, void *info, int wait); void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait); @@ -144,9 +144,8 @@ static inline void smp_send_stop(void) { } * These macros fold the SMP functionality into a single CPU system */ #define raw_smp_processor_id() 0 -static inline int up_smp_call_function(smp_call_func_t func, void *info) +static inline void up_smp_call_function(smp_call_func_t func, void *info) { - return 0; } #define smp_call_function(func, info, wait) \ (up_smp_call_function(func, info)) diff --git a/kernel/smp.c b/kernel/smp.c index 220ad142f5dd..616d4d114847 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -487,13 +487,11 @@ EXPORT_SYMBOL(smp_call_function_many); * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ -int smp_call_function(smp_call_func_t func, void *info, int wait) +void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); - - return 0; } EXPORT_SYMBOL(smp_call_function); @@ -594,18 +592,16 @@ void __init smp_init(void) * early_boot_irqs_disabled is set. Use local_irq_save/restore() instead * of local_irq_disable/enable(). */ -int on_each_cpu(void (*func) (void *info), void *info, int wait) +void on_each_cpu(void (*func) (void *info), void *info, int wait) { unsigned long flags; - int ret = 0; preempt_disable(); - ret = smp_call_function(func, info, wait); + smp_call_function(func, info, wait); local_irq_save(flags); func(info); local_irq_restore(flags); preempt_enable(); - return ret; } EXPORT_SYMBOL(on_each_cpu); diff --git a/kernel/up.c b/kernel/up.c index 483c9962c999..862b460ab97a 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -35,14 +35,13 @@ int smp_call_function_single_async(int cpu, call_single_data_t *csd) } EXPORT_SYMBOL(smp_call_function_single_async); -int on_each_cpu(smp_call_func_t func, void *info, int wait) +void on_each_cpu(smp_call_func_t func, void *info, int wait) { unsigned long flags; local_irq_save(flags); func(info); local_irq_restore(flags); - return 0; } EXPORT_SYMBOL(on_each_cpu); -- cgit v1.3-14-g43fede