diff options
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/dump_pagetables.c | 44 | ||||
| -rw-r--r-- | arch/x86/mm/fault.c | 43 | ||||
| -rw-r--r-- | arch/x86/mm/hugetlbpage.c | 10 | ||||
| -rw-r--r-- | arch/x86/mm/init.c | 7 | ||||
| -rw-r--r-- | arch/x86/mm/init_32.c | 3 | ||||
| -rw-r--r-- | arch/x86/mm/init_64.c | 62 | ||||
| -rw-r--r-- | arch/x86/mm/ioremap.c | 32 | ||||
| -rw-r--r-- | arch/x86/mm/numa.c | 6 | ||||
| -rw-r--r-- | arch/x86/mm/pageattr-test.c | 2 | ||||
| -rw-r--r-- | arch/x86/mm/pgtable.c | 27 | ||||
| -rw-r--r-- | arch/x86/mm/tlb.c | 103 |
11 files changed, 210 insertions, 129 deletions
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 20621d753d5f..167ffcac16ed 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -30,12 +30,14 @@ struct pg_state { unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; + unsigned long lines; bool to_dmesg; }; struct addr_marker { unsigned long start_address; const char *name; + unsigned long max_lines; }; /* indices for address_markers; keep sync'd w/ address_markers below */ @@ -46,6 +48,7 @@ enum address_markers_idx { LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, + ESPFIX_START_NR, HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, @@ -68,6 +71,7 @@ static struct addr_marker address_markers[] = { { PAGE_OFFSET, "Low Kernel Mapping" }, { VMALLOC_START, "vmalloc() Area" }, { VMEMMAP_START, "Vmemmap" }, + { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, { __START_KERNEL_map, "High Kernel Mapping" }, { MODULES_VADDR, "Modules" }, { MODULES_END, "End Modules" }, @@ -182,7 +186,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, pgprot_t new_prot, int level) { pgprotval_t prot, cur; - static const char units[] = "KMGTPE"; + static const char units[] = "BKMGTPE"; /* * If we have a "break" in the series, we need to flush the state that @@ -197,6 +201,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->current_prot = new_prot; st->level = level; st->marker = address_markers; + st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); } else if (prot != cur || level != st->level || @@ -208,17 +213,24 @@ static void note_page(struct seq_file *m, struct pg_state *st, /* * Now print the actual finished series */ - pt_dump_seq_printf(m, st->to_dmesg, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, st->current_address); - - delta = (st->current_address - st->start_address) >> 10; - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; + if (!st->marker->max_lines || + st->lines < st->marker->max_lines) { + pt_dump_seq_printf(m, st->to_dmesg, + "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, st->current_address); + + delta = st->current_address - st->start_address; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", + delta, *unit); + printk_prot(m, st->current_prot, st->level, + st->to_dmesg); } - pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", delta, *unit); - printk_prot(m, st->current_prot, st->level, st->to_dmesg); + st->lines++; /* * We print markers for special areas of address space, @@ -226,7 +238,17 @@ static void note_page(struct seq_file *m, struct pg_state *st, * This helps in the interpretation. */ if (st->current_address >= st->marker[1].start_address) { + if (st->marker->max_lines && + st->lines > st->marker->max_lines) { + unsigned long nskip = + st->lines - st->marker->max_lines; + pt_dump_seq_printf(m, st->to_dmesg, + "... %lu entr%s skipped ... \n", + nskip, + nskip == 1 ? "y" : "ies"); + } st->marker++; + st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8e5722992677..a24194681513 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -8,7 +8,7 @@ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/module.h> /* search_exception_table */ #include <linux/bootmem.h> /* max_low_pfn */ -#include <linux/kprobes.h> /* __kprobes, ... */ +#include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ #include <linux/perf_event.h> /* perf_sw_event */ #include <linux/hugetlb.h> /* hstate_index_to_shift */ @@ -18,7 +18,8 @@ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ -#include <asm/fixmap.h> /* VSYSCALL_START */ +#include <asm/fixmap.h> /* VSYSCALL_ADDR */ +#include <asm/vsyscall.h> /* emulate_vsyscall */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -45,7 +46,7 @@ enum x86_pf_error_code { * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ -static inline int __kprobes +static nokprobe_inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) @@ -54,7 +55,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr) return 0; } -static inline int __kprobes kprobes_fault(struct pt_regs *regs) +static nokprobe_inline int kprobes_fault(struct pt_regs *regs) { int ret = 0; @@ -261,7 +262,7 @@ void vmalloc_sync_all(void) * * Handle a fault on the vmalloc or module mapping area */ -static noinline __kprobes int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; @@ -291,6 +292,7 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) return 0; } +NOKPROBE_SYMBOL(vmalloc_fault); /* * Did it hit the DOS screen memory VA from vm86 mode? @@ -358,7 +360,7 @@ void vmalloc_sync_all(void) * * This assumes no large pages in there. */ -static noinline __kprobes int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { pgd_t *pgd, *pgd_ref; pud_t *pud, *pud_ref; @@ -425,6 +427,7 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) return 0; } +NOKPROBE_SYMBOL(vmalloc_fault); #ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = @@ -574,6 +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, @@ -594,6 +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 "); @@ -771,7 +780,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, * emulation. */ if (unlikely((error_code & PF_INSTR) && - ((address & ~0xfff) == VSYSCALL_START))) { + ((address & ~0xfff) == VSYSCALL_ADDR))) { if (emulate_vsyscall(regs, address)) return; } @@ -927,7 +936,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. */ -static noinline __kprobes int +static noinline int spurious_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; @@ -975,6 +984,7 @@ spurious_fault(unsigned long error_code, unsigned long address) return ret; } +NOKPROBE_SYMBOL(spurious_fault); int show_unhandled_signals = 1; @@ -1030,7 +1040,7 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) * {,trace_}do_page_fault() have notrace on. Having this an actual function * guarantees there's a function trace entry. */ -static void __kprobes noinline +static noinline void __do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { @@ -1208,7 +1218,8 @@ good_area: /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo - * the fault: + * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if + * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked. */ fault = handle_mm_fault(mm, vma, address, flags); @@ -1253,8 +1264,9 @@ good_area: up_read(&mm->mmap_sem); } +NOKPROBE_SYMBOL(__do_page_fault); -dotraplinkage void __kprobes notrace +dotraplinkage void notrace do_page_fault(struct pt_regs *regs, unsigned long error_code) { unsigned long address = read_cr2(); /* Get the faulting address */ @@ -1272,10 +1284,12 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code, address); exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_page_fault); #ifdef CONFIG_TRACING -static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs, - unsigned long error_code) +static nokprobe_inline void +trace_page_fault_entries(unsigned long address, struct pt_regs *regs, + unsigned long error_code) { if (user_mode(regs)) trace_page_fault_user(address, regs, error_code); @@ -1283,7 +1297,7 @@ static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs trace_page_fault_kernel(address, regs, error_code); } -dotraplinkage void __kprobes notrace +dotraplinkage void notrace trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) { /* @@ -1300,4 +1314,5 @@ trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code, address); exception_exit(prev_state); } +NOKPROBE_SYMBOL(trace_do_page_fault); #endif /* CONFIG_TRACING */ diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8c9f647ff9e1..8b977ebf9388 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { return NULL; } - -int pmd_huge_support(void) -{ - return 0; -} #else struct page * @@ -80,11 +75,6 @@ int pud_huge(pud_t pud) { return !!(pud_val(pud) & _PAGE_PSE); } - -int pmd_huge_support(void) -{ - return 1; -} #endif #ifdef CONFIG_HUGETLB_PAGE 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 <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/microcode.h> +/* + * We need to define the tracepoints somewhere, and tlb.c + * is only compied when SMP=y. + */ +#define CREATE_TRACE_POINTS +#include <trace/events/tlb.h> + #include "mm_internal.h" static unsigned long __initdata pgt_buf_start; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index e39504878aec..7d05565ba781 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -825,7 +825,8 @@ void __init mem_init(void) int arch_add_memory(int nid, u64 start, u64 size) { struct pglist_data *pgdata = NODE_DATA(nid); - struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM; + struct zone *zone = pgdata->node_zones + + zone_for_memory(nid, start, size, ZONE_HIGHMEM); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f35c66c5959a..5621c47d7a1a 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -691,7 +691,8 @@ static void update_end_of_memory_vars(u64 start, u64 size) int arch_add_memory(int nid, u64 start, u64 size) { struct pglist_data *pgdat = NODE_DATA(nid); - struct zone *zone = pgdat->node_zones + ZONE_NORMAL; + struct zone *zone = pgdat->node_zones + + zone_for_memory(nid, start, size, ZONE_NORMAL); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; @@ -1055,8 +1056,8 @@ void __init mem_init(void) after_bootmem = 1; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, - VSYSCALL_END - VSYSCALL_START, KCORE_OTHER); + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, + PAGE_SIZE, KCORE_OTHER); mem_init_print_info(NULL); } @@ -1185,11 +1186,19 @@ int kern_addr_valid(unsigned long addr) * covers the 64bit vsyscall page now. 32bit has a real VMA now and does * not need special handling anymore: */ +static const char *gate_vma_name(struct vm_area_struct *vma) +{ + return "[vsyscall]"; +} +static struct vm_operations_struct gate_vma_ops = { + .name = gate_vma_name, +}; static struct vm_area_struct gate_vma = { - .vm_start = VSYSCALL_START, - .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE), + .vm_start = VSYSCALL_ADDR, + .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, - .vm_flags = VM_READ | VM_EXEC + .vm_flags = VM_READ | VM_EXEC, + .vm_ops = &gate_vma_ops, }; struct vm_area_struct *get_gate_vma(struct mm_struct *mm) @@ -1218,29 +1227,46 @@ int in_gate_area(struct mm_struct *mm, unsigned long addr) */ int in_gate_area_no_mm(unsigned long addr) { - return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END); + return (addr & PAGE_MASK) == VSYSCALL_ADDR; } -const char *arch_vma_name(struct vm_area_struct *vma) +static unsigned long probe_memory_block_size(void) { - if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) - return "[vdso]"; - if (vma == &gate_vma) - return "[vsyscall]"; - return NULL; -} + /* start from 2g */ + unsigned long bz = 1UL<<31; #ifdef CONFIG_X86_UV -unsigned long memory_block_size_bytes(void) -{ if (is_uv_system()) { printk(KERN_INFO "UV: memory block size 2GB\n"); return 2UL * 1024 * 1024 * 1024; } - return MIN_MEMORY_BLOCK_SIZE; -} #endif + /* less than 64g installed */ + if ((max_pfn << PAGE_SHIFT) < (16UL << 32)) + return MIN_MEMORY_BLOCK_SIZE; + + /* get the tail size */ + while (bz > MIN_MEMORY_BLOCK_SIZE) { + if (!((max_pfn << PAGE_SHIFT) & (bz - 1))) + break; + bz >>= 1; + } + + printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20); + + return bz; +} + +static unsigned long memory_block_size_probed; +unsigned long memory_block_size_bytes(void) +{ + if (!memory_block_size_probed) + memory_block_size_probed = probe_memory_block_size(); + + return memory_block_size_probed; +} + #ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 597ac155c91c..baff1da354e0 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, return err; } +static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, + void *arg) +{ + unsigned long i; + + for (i = 0; i < nr_pages; ++i) + if (pfn_valid(start_pfn + i) && + !PageReserved(pfn_to_page(start_pfn + i))) + return 1; + + WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); + + return 0; +} + /* * Remap an arbitrary physical address space into the kernel virtual * address space. Needed when the kernel wants to access high addresses @@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ + pfn = phys_addr >> PAGE_SHIFT; last_pfn = last_addr >> PAGE_SHIFT; - for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) { - int is_ram = page_is_ram(pfn); - - if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) - return NULL; - WARN_ON_ONCE(is_ram); - } + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) + return NULL; /* * Mappings have to be page-aligned @@ -355,6 +367,12 @@ void __init early_ioremap_init(void) { pmd_t *pmd; +#ifdef CONFIG_X86_64 + BUILD_BUG_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1)); +#else + WARN_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1)); +#endif + early_ioremap_setup(); pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 1d045f9c390f..a32b706c401a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -559,7 +559,7 @@ static void __init numa_clear_kernel_node_hotplug(void) int i, nid; nodemask_t numa_kernel_nodes = NODE_MASK_NONE; unsigned long start, end; - struct memblock_type *type = &memblock.reserved; + struct memblock_region *r; /* * At this time, all memory regions reserved by memblock are @@ -573,8 +573,8 @@ static void __init numa_clear_kernel_node_hotplug(void) } /* Mark all kernel nodes. */ - for (i = 0; i < type->cnt; i++) - node_set(type->regions[i].nid, numa_kernel_nodes); + for_each_memblock(reserved, r) + node_set(r->nid, numa_kernel_nodes); /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ for (i = 0; i < numa_meminfo.nr_blks; i++) { diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 461bc8289024..6629f397b467 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -35,7 +35,7 @@ enum { static int pte_testbit(pte_t pte) { - return pte_flags(pte) & _PAGE_UNUSED1; + return pte_flags(pte) & _PAGE_SOFTW1; } struct split_state { diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c96314abd144..6fb6927f9e76 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - int young; - - young = ptep_test_and_clear_young(vma, address, ptep); - if (young) - flush_tlb_page(vma, address); - - return young; + /* + * On x86 CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -449,9 +456,9 @@ void __init reserve_top_address(unsigned long reserve) { #ifdef CONFIG_X86_32 BUG_ON(fixmaps_set > 0); - printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", - (int)-reserve); - __FIXADDR_TOP = -reserve - PAGE_SIZE; + __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; + printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", + -reserve, __FIXADDR_TOP + PAGE_SIZE); #endif } 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; - } - - /* 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]; + if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) + base_pages_to_flush = (end - start) >> PAGE_SHIFT; - /* 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); |
