diff --git a/Documentation/x86/tlb.txt b/Documentation/x86/tlb.txt new file mode 100644 index 000000000000..2b3a82e69151 --- /dev/null +++ b/Documentation/x86/tlb.txt @@ -0,0 +1,75 @@ +When the kernel unmaps or modified the attributes of a range of +memory, it has two choices: + 1. Flush the entire TLB with a two-instruction sequence. This is + a quick operation, but it causes collateral damage: TLB entries + from areas other than the one we are trying to flush will be + destroyed and must be refilled later, at some cost. + 2. Use the invlpg instruction to invalidate a single page at a + time. This could potentialy cost many more instructions, but + it is a much more precise operation, causing no collateral + damage to other TLB entries. + +Which method to do depends on a few things: + 1. The size of the flush being performed. A flush of the entire + address space is obviously better performed by flushing the + entire TLB than doing 2^48/PAGE_SIZE individual flushes. + 2. The contents of the TLB. If the TLB is empty, then there will + be no collateral damage caused by doing the global flush, and + all of the individual flush will have ended up being wasted + work. + 3. The size of the TLB. The larger the TLB, the more collateral + damage we do with a full flush. So, the larger the TLB, the + more attrative an individual flush looks. Data and + instructions have separate TLBs, as do different page sizes. + 4. The microarchitecture. The TLB has become a multi-level + cache on modern CPUs, and the global flushes have become more + expensive relative to single-page flushes. + +There is obviously no way the kernel can know all these things, +especially the contents of the TLB during a given flush. The +sizes of the flush will vary greatly depending on the workload as +well. There is essentially no "right" point to choose. + +You may be doing too many individual invalidations if you see the +invlpg instruction (or instructions _near_ it) show up high in +profiles. If you believe that individual invalidations being +called too often, you can lower the tunable: + + /sys/debug/kernel/x86/tlb_single_page_flush_ceiling + +This will cause us to do the global flush for more cases. +Lowering it to 0 will disable the use of the individual flushes. +Setting it to 1 is a very conservative setting and it should +never need to be 0 under normal circumstances. + +Despite the fact that a single individual flush on x86 is +guaranteed to flush a full 2MB [1], hugetlbfs always uses the full +flushes. THP is treated exactly the same as normal memory. + +You might see invlpg inside of flush_tlb_mm_range() show up in +profiles, or you can use the trace_tlb_flush() tracepoints. to +determine how long the flush operations are taking. + +Essentially, you are balancing the cycles you spend doing invlpg +with the cycles that you spend refilling the TLB later. + +You can measure how expensive TLB refills are by using +performance counters and 'perf stat', like this: + +perf stat -e + cpu/event=0x8,umask=0x84,name=dtlb_load_misses_walk_duration/, + cpu/event=0x8,umask=0x82,name=dtlb_load_misses_walk_completed/, + cpu/event=0x49,umask=0x4,name=dtlb_store_misses_walk_duration/, + cpu/event=0x49,umask=0x2,name=dtlb_store_misses_walk_completed/, + cpu/event=0x85,umask=0x4,name=itlb_misses_walk_duration/, + cpu/event=0x85,umask=0x2,name=itlb_misses_walk_completed/ + +That works on an IvyBridge-era CPU (i5-3320M). Different CPUs +may have differently-named counters, but they should at least +be there in some form. You can use pmu-tools 'ocperf list' +(https://github.com/andikleen/pmu-tools) to find the right +counters for a given CPU. + +1. A footnote in Intel's SDM "4.10.4.2 Recommended Invalidation" + says: "One execution of INVLPG is sufficient even for a page + with size greater than 4 KBytes." diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index be12c534fd59..166af2a8e865 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -3,6 +3,10 @@ #include #include +#include + +#include + #include #include #include @@ -44,6 +48,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Re-load page tables */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ cpumask_clear_cpu(cpu, mm_cpumask(prev)); @@ -71,6 +76,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * to make sure to use no freed page tables. */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); load_LDT_nolock(&next->context); } } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 32cc237f8e20..ee30b9f0b91c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -72,7 +72,6 @@ extern u16 __read_mostly tlb_lld_4k[NR_INFO]; extern u16 __read_mostly tlb_lld_2m[NR_INFO]; extern u16 __read_mostly tlb_lld_4m[NR_INFO]; extern u16 __read_mostly tlb_lld_1g[NR_INFO]; -extern s8 __read_mostly tlb_flushall_shift; /* * CPU type and hardware bug flags. Kept separately for each CPU. diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bc360d3df60e..60e5497681f5 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -724,11 +724,6 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) } #endif -static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) -{ - tlb_flushall_shift = 6; -} - static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) { u32 ebx, eax, ecx, edx; @@ -776,8 +771,6 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) tlb_lli_2m[ENTRIES] = eax & mask; tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; - - cpu_set_tlb_flushall_shift(c); } static const struct cpu_dev amd_cpu_dev = { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 188a8c5cc094..333fd5209336 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -481,26 +481,17 @@ u16 __read_mostly tlb_lld_2m[NR_INFO]; u16 __read_mostly tlb_lld_4m[NR_INFO]; u16 __read_mostly tlb_lld_1g[NR_INFO]; -/* - * tlb_flushall_shift shows the balance point in replacing cr3 write - * with multiple 'invlpg'. It will do this replacement when - * flush_tlb_lines <= active_lines/2^tlb_flushall_shift. - * If tlb_flushall_shift is -1, means the replacement will be disabled. - */ -s8 __read_mostly tlb_flushall_shift = -1; - void cpu_detect_tlb(struct cpuinfo_x86 *c) { if (this_cpu->c_detect_tlb) this_cpu->c_detect_tlb(c); printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" - "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n" - "tlb_flushall_shift: %d\n", + "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n", tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES], tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES], - tlb_lld_1g[ENTRIES], tlb_flushall_shift); + tlb_lld_1g[ENTRIES]); } void detect_ht(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 9483ee5b3991..74e804ddc5c7 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -634,31 +634,6 @@ static void intel_tlb_lookup(const unsigned char desc) } } -static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) -{ - switch ((c->x86 << 8) + c->x86_model) { - case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ - case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ - case 0x617: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ - case 0x61d: /* six-core 45 nm xeon "Dunnington" */ - tlb_flushall_shift = -1; - break; - case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 2; - break; - case 0x61a: /* 45 nm nehalem, "Bloomfield" */ - case 0x61e: /* 45 nm nehalem, "Lynnfield" */ - case 0x625: /* 32 nm nehalem, "Clarkdale" */ - case 0x62c: /* 32 nm nehalem, "Gulftown" */ - case 0x62e: /* 45 nm nehalem-ex, "Beckton" */ - case 0x62f: /* 32 nm Xeon E7 */ - case 0x62a: /* SandyBridge */ - case 0x62d: /* SandyBridge, "Romely-EP" */ - default: - tlb_flushall_shift = 6; - } -} - static void intel_detect_tlb(struct cpuinfo_x86 *c) { int i, j, n; @@ -683,7 +658,6 @@ static void intel_detect_tlb(struct cpuinfo_x86 *c) for (j = 1 ; j < 16 ; j++) intel_tlb_lookup(desc[j]); } - intel_tlb_flushall_shift_set(c); } static const struct cpu_dev intel_cpu_dev = { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 36642793e315..1dbade870f90 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -577,6 +577,8 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address) static const char nx_warning[] = KERN_CRIT "kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n"; +static const char smep_warning[] = KERN_CRIT +"unable to execute userspace code (SMEP?) (uid: %d)\n"; static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, @@ -597,6 +599,10 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, if (pte && pte_present(*pte) && !pte_exec(*pte)) printk(nx_warning, from_kuid(&init_user_ns, current_uid())); + if (pte && pte_present(*pte) && pte_exec(*pte) && + (pgd_flags(*pgd) & _PAGE_USER) && + (read_cr4() & X86_CR4_SMEP)) + printk(smep_warning, from_kuid(&init_user_ns, current_uid())); } printk(KERN_ALERT "BUG: unable to handle kernel "); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index f97130618113..66dba36f2343 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -18,6 +18,13 @@ #include /* for MAX_DMA_PFN */ #include +/* + * We need to define the tracepoints somewhere, and tlb.c + * is only compied when SMP=y. + */ +#define CREATE_TRACE_POINTS +#include + #include "mm_internal.h" static unsigned long __initdata pgt_buf_start; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index dd8dda167a24..1fe33987de02 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -49,6 +49,7 @@ void leave_mm(int cpu) if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) { cpumask_clear_cpu(cpu, mm_cpumask(active_mm)); load_cr3(swapper_pg_dir); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } } EXPORT_SYMBOL_GPL(leave_mm); @@ -102,20 +103,24 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; + if (!f->flush_end) + f->flush_end = f->flush_start + PAGE_SIZE; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { - if (f->flush_end == TLB_FLUSH_ALL) + if (f->flush_end == TLB_FLUSH_ALL) { local_flush_tlb(); - else if (!f->flush_end) - __flush_tlb_single(f->flush_start); - else { + trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL); + } else { unsigned long addr; + unsigned long nr_pages = + f->flush_end - f->flush_start / PAGE_SIZE; addr = f->flush_start; while (addr < f->flush_end) { __flush_tlb_single(addr); addr += PAGE_SIZE; } + trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages); } } else leave_mm(smp_processor_id()); @@ -153,46 +158,45 @@ void flush_tlb_current_task(void) count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); preempt_enable(); } +/* + * See Documentation/x86/tlb.txt for details. We choose 33 + * because it is large enough to cover the vast majority (at + * least 95%) of allocations, and is small enough that we are + * confident it will not cause too much overhead. Each single + * flush is about 100 ns, so this caps the maximum overhead at + * _about_ 3,000 ns. + * + * This is in units of pages. + */ +unsigned long tlb_single_page_flush_ceiling = 33; + void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { unsigned long addr; - unsigned act_entries, tlb_entries = 0; - unsigned long nr_base_pages; + /* do a global flush by default */ + unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); if (current->active_mm != mm) - goto flush_all; + goto out; if (!current->mm) { leave_mm(smp_processor_id()); - goto flush_all; + goto out; } - if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1 - || vmflag & VM_HUGETLB) { - local_flush_tlb(); - goto flush_all; - } + if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) + base_pages_to_flush = (end - start) >> PAGE_SHIFT; - /* In modern CPU, last level tlb used for both data/ins */ - if (vmflag & VM_EXEC) - tlb_entries = tlb_lli_4k[ENTRIES]; - else - tlb_entries = tlb_lld_4k[ENTRIES]; - - /* Assume all of TLB entries was occupied by this task */ - act_entries = tlb_entries >> tlb_flushall_shift; - act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm; - nr_base_pages = (end - start) >> PAGE_SHIFT; - - /* tlb_flushall_shift is on balance point, details in commit log */ - if (nr_base_pages > act_entries) { + if (base_pages_to_flush > tlb_single_page_flush_ceiling) { + base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); } else { @@ -201,17 +205,15 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } - - if (cpumask_any_but(mm_cpumask(mm), - smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, end); - preempt_enable(); - return; } - -flush_all: + trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush); +out: + if (base_pages_to_flush == TLB_FLUSH_ALL) { + start = 0UL; + end = TLB_FLUSH_ALL; + } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); + flush_tlb_others(mm_cpumask(mm), mm, start, end); preempt_enable(); } @@ -260,32 +262,26 @@ static void do_kernel_range_flush(void *info) void flush_tlb_kernel_range(unsigned long start, unsigned long end) { - unsigned act_entries; - struct flush_tlb_info info; - - /* In modern CPU, last level tlb used for both data/ins */ - act_entries = tlb_lld_4k[ENTRIES]; /* Balance as user space task's flush, a bit conservative */ - if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1 || - (end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) - + if (end == TLB_FLUSH_ALL || + (end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) { on_each_cpu(do_flush_tlb_all, NULL, 1); - else { + } else { + struct flush_tlb_info info; info.flush_start = start; info.flush_end = end; on_each_cpu(do_kernel_range_flush, &info, 1); } } -#ifdef CONFIG_DEBUG_TLBFLUSH static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[32]; unsigned int len; - len = sprintf(buf, "%hd\n", tlb_flushall_shift); + len = sprintf(buf, "%ld\n", tlb_single_page_flush_ceiling); return simple_read_from_buffer(user_buf, count, ppos, buf, len); } @@ -294,20 +290,20 @@ static ssize_t tlbflush_write_file(struct file *file, { char buf[32]; ssize_t len; - s8 shift; + int ceiling; len = min(count, sizeof(buf) - 1); if (copy_from_user(buf, user_buf, len)) return -EFAULT; buf[len] = '\0'; - if (kstrtos8(buf, 0, &shift)) + if (kstrtoint(buf, 0, &ceiling)) return -EINVAL; - if (shift < -1 || shift >= BITS_PER_LONG) + if (ceiling < 0) return -EINVAL; - tlb_flushall_shift = shift; + tlb_single_page_flush_ceiling = ceiling; return count; } @@ -317,11 +313,10 @@ static const struct file_operations fops_tlbflush = { .llseek = default_llseek, }; -static int __init create_tlb_flushall_shift(void) +static int __init create_tlb_single_page_flush_ceiling(void) { - debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR, + debugfs_create_file("tlb_single_page_flush_ceiling", S_IRUSR | S_IWUSR, arch_debugfs_dir, NULL, &fops_tlbflush); return 0; } -late_initcall(create_tlb_flushall_shift); -#endif +late_initcall(create_tlb_single_page_flush_ceiling); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 96c5750e3110..796deac19fcf 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -516,4 +516,12 @@ struct vm_special_mapping struct page **pages; }; +enum tlb_flush_reason { + TLB_FLUSH_ON_TASK_SWITCH, + TLB_REMOTE_SHOOTDOWN, + TLB_LOCAL_SHOOTDOWN, + TLB_LOCAL_MM_SHOOTDOWN, + NR_TLB_FLUSH_REASONS, +}; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h new file mode 100644 index 000000000000..13391d288107 --- /dev/null +++ b/include/trace/events/tlb.h @@ -0,0 +1,40 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM tlb + +#if !defined(_TRACE_TLB_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TLB_H + +#include +#include + +#define TLB_FLUSH_REASON \ + { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, \ + { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, \ + { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, \ + { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" } + +TRACE_EVENT(tlb_flush, + + TP_PROTO(int reason, unsigned long pages), + TP_ARGS(reason, pages), + + TP_STRUCT__entry( + __field( int, reason) + __field(unsigned long, pages) + ), + + TP_fast_assign( + __entry->reason = reason; + __entry->pages = pages; + ), + + TP_printk("pages:%ld reason:%s (%d)", + __entry->pages, + __print_symbolic(__entry->reason, TLB_FLUSH_REASON), + __entry->reason) +); + +#endif /* _TRACE_TLB_H */ + +/* This part must be outside protection */ +#include