diff options
Diffstat (limited to 'include/asm-generic')
| -rw-r--r-- | include/asm-generic/cacheflush.h | 5 | ||||
| -rw-r--r-- | include/asm-generic/pgtable.h | 12 | ||||
| -rw-r--r-- | include/asm-generic/resource.h | 2 | ||||
| -rw-r--r-- | include/asm-generic/tlb.h | 156 | ||||
| -rw-r--r-- | include/asm-generic/vmlinux.lds.h | 95 | ||||
| -rw-r--r-- | include/asm-generic/xor.h | 2 |
6 files changed, 142 insertions, 130 deletions
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index 57b5c3c..87bc536 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -24,7 +24,10 @@ #define flush_cache_vunmap(start, end) do { } while (0) #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ - memcpy(dst, src, len) + do { \ + memcpy(dst, src, len); \ + flush_icache_user_range(vma, page, vaddr, len); \ + } while (0) #define copy_from_user_page(vma, page, vaddr, dst, src, len) \ memcpy(dst, src, len) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index b4bfe33..e9b8e59 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -184,22 +184,18 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif -#ifndef __HAVE_ARCH_PAGE_TEST_DIRTY -#define page_test_dirty(page) (0) +#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY +#define page_test_and_clear_dirty(pfn, mapped) (0) #endif -#ifndef __HAVE_ARCH_PAGE_CLEAR_DIRTY -#define page_clear_dirty(page, mapped) do { } while (0) -#endif - -#ifndef __HAVE_ARCH_PAGE_TEST_DIRTY +#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY #define pte_maybe_dirty(pte) pte_dirty(pte) #else #define pte_maybe_dirty(pte) (1) #endif #ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG -#define page_test_and_clear_young(page) (0) +#define page_test_and_clear_young(pfn) (0) #endif #ifndef __HAVE_ARCH_PGD_OFFSET_GATE diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h index 587566f..61fa862 100644 --- a/include/asm-generic/resource.h +++ b/include/asm-generic/resource.h @@ -78,7 +78,7 @@ [RLIMIT_CORE] = { 0, RLIM_INFINITY }, \ [RLIMIT_RSS] = { RLIM_INFINITY, RLIM_INFINITY }, \ [RLIMIT_NPROC] = { 0, 0 }, \ - [RLIMIT_NOFILE] = { INR_OPEN, INR_OPEN }, \ + [RLIMIT_NOFILE] = { INR_OPEN_CUR, INR_OPEN_MAX }, \ [RLIMIT_MEMLOCK] = { MLOCK_LIMIT, MLOCK_LIMIT }, \ [RLIMIT_AS] = { RLIM_INFINITY, RLIM_INFINITY }, \ [RLIMIT_LOCKS] = { RLIM_INFINITY, RLIM_INFINITY }, \ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index e43f976..e58fa77 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -5,6 +5,8 @@ * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * + * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version @@ -17,97 +19,111 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> +#ifdef CONFIG_HAVE_RCU_TABLE_FREE /* - * For UP we don't need to worry about TLB flush - * and page free order so much.. + * Semi RCU freeing of the page directories. + * + * This is needed by some architectures to implement software pagetable walkers. + * + * gup_fast() and other software pagetable walkers do a lockless page-table + * walk and therefore needs some synchronization with the freeing of the page + * directories. The chosen means to accomplish that is by disabling IRQs over + * the walk. + * + * Architectures that use IPIs to flush TLBs will then automagically DTRT, + * since we unlink the page, flush TLBs, free the page. Since the disabling of + * IRQs delays the completion of the TLB flush we can never observe an already + * freed page. + * + * Architectures that do not have this (PPC) need to delay the freeing by some + * other means, this is that means. + * + * What we do is batch the freed directory pages (tables) and RCU free them. + * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling + * holds off grace periods. + * + * However, in order to batch these pages we need to allocate storage, this + * allocation is deep inside the MM code and can thus easily fail on memory + * pressure. To guarantee progress we fall back to single table freeing, see + * the implementation of tlb_remove_table_one(). + * */ -#ifdef CONFIG_SMP - #ifdef ARCH_FREE_PTR_NR - #define FREE_PTR_NR ARCH_FREE_PTR_NR - #else - #define FREE_PTE_NR 506 - #endif - #define tlb_fast_mode(tlb) ((tlb)->nr == ~0U) -#else - #define FREE_PTE_NR 1 - #define tlb_fast_mode(tlb) 1 +struct mmu_table_batch { + struct rcu_head rcu; + unsigned int nr; + void *tables[0]; +}; + +#define MAX_TABLE_BATCH \ + ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) + +extern void tlb_table_flush(struct mmu_gather *tlb); +extern void tlb_remove_table(struct mmu_gather *tlb, void *table); + #endif -/* struct mmu_gather is an opaque type used by the mm code for passing around - * any data needed by arch specific code for tlb_remove_page. +/* + * If we can't allocate a page to make a big batch of page pointers + * to work on, then just handle a few from the on-stack structure. */ -struct mmu_gather { - struct mm_struct *mm; - unsigned int nr; /* set to ~0U means fast mode */ - unsigned int need_flush;/* Really unmapped some ptes? */ - unsigned int fullmm; /* non-zero means full mm flush */ - struct page * pages[FREE_PTE_NR]; +#define MMU_GATHER_BUNDLE 8 + +struct mmu_gather_batch { + struct mmu_gather_batch *next; + unsigned int nr; + unsigned int max; + struct page *pages[0]; }; -/* Users of the generic TLB shootdown code must declare this storage space. */ -DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); +#define MAX_GATHER_BATCH \ + ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) -/* tlb_gather_mmu - * Return a pointer to an initialized struct mmu_gather. +/* struct mmu_gather is an opaque type used by the mm code for passing around + * any data needed by arch specific code for tlb_remove_page. */ -static inline struct mmu_gather * -tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) -{ - struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); - - tlb->mm = mm; +struct mmu_gather { + struct mm_struct *mm; +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + struct mmu_table_batch *batch; +#endif + unsigned int need_flush : 1, /* Did free PTEs */ + fast_mode : 1; /* No batching */ - /* Use fast mode if only one CPU is online */ - tlb->nr = num_online_cpus() > 1 ? 0U : ~0U; + unsigned int fullmm; - tlb->fullmm = full_mm_flush; + struct mmu_gather_batch *active; + struct mmu_gather_batch local; + struct page *__pages[MMU_GATHER_BUNDLE]; +}; - return tlb; -} +#define HAVE_GENERIC_MMU_GATHER -static inline void -tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) +static inline int tlb_fast_mode(struct mmu_gather *tlb) { - if (!tlb->need_flush) - return; - tlb->need_flush = 0; - tlb_flush(tlb); - if (!tlb_fast_mode(tlb)) { - free_pages_and_swap_cache(tlb->pages, tlb->nr); - tlb->nr = 0; - } +#ifdef CONFIG_SMP + return tlb->fast_mode; +#else + /* + * For UP we don't need to worry about TLB flush + * and page free order so much.. + */ + return 1; +#endif } -/* tlb_finish_mmu - * Called at the end of the shootdown operation to free up any resources - * that were required. - */ -static inline void -tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) -{ - tlb_flush_mmu(tlb, start, end); - - /* keep the page table cache within bounds */ - check_pgt_cache(); - - put_cpu_var(mmu_gathers); -} +void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm); +void tlb_flush_mmu(struct mmu_gather *tlb); +void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end); +int __tlb_remove_page(struct mmu_gather *tlb, struct page *page); /* tlb_remove_page - * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while - * handling the additional races in SMP caused by other CPUs caching valid - * mappings in their TLBs. + * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when + * required. */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { - tlb->need_flush = 1; - if (tlb_fast_mode(tlb)) { - free_page_and_swap_cache(page); - return; - } - tlb->pages[tlb->nr++] = page; - if (tlb->nr >= FREE_PTE_NR) - tlb_flush_mmu(tlb, 0, 0); + if (!__tlb_remove_page(tlb, page)) + tlb_flush_mmu(tlb); } /** diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index bd297a2..db22d13 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -15,7 +15,7 @@ * HEAD_TEXT_SECTION * INIT_TEXT_SECTION(PAGE_SIZE) * INIT_DATA_SECTION(...) - * PERCPU(CACHELINE_SIZE, PAGE_SIZE) + * PERCPU_SECTION(CACHELINE_SIZE) * __init_end = .; * * _stext = .; @@ -170,6 +170,10 @@ STRUCT_ALIGN(); \ *(__tracepoints) \ /* implement dynamic printk debug */ \ + . = ALIGN(8); \ + VMLINUX_SYMBOL(__start___jump_table) = .; \ + *(__jump_table) \ + VMLINUX_SYMBOL(__stop___jump_table) = .; \ . = ALIGN(8); \ VMLINUX_SYMBOL(__start___verbose) = .; \ *(__verbose) \ @@ -228,8 +232,6 @@ \ BUG_TABLE \ \ - JUMP_TABLE \ - \ /* PCI quirks */ \ .pci_fixup : AT(ADDR(.pci_fixup) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start_pci_fixups_early) = .; \ @@ -274,70 +276,70 @@ /* Kernel symbol table: Normal symbols */ \ __ksymtab : AT(ADDR(__ksymtab) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab) = .; \ - *(__ksymtab) \ + *(SORT(___ksymtab+*)) \ VMLINUX_SYMBOL(__stop___ksymtab) = .; \ } \ \ /* Kernel symbol table: GPL-only symbols */ \ __ksymtab_gpl : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_gpl) = .; \ - *(__ksymtab_gpl) \ + *(SORT(___ksymtab_gpl+*)) \ VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .; \ } \ \ /* Kernel symbol table: Normal unused symbols */ \ __ksymtab_unused : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_unused) = .; \ - *(__ksymtab_unused) \ + *(SORT(___ksymtab_unused+*)) \ VMLINUX_SYMBOL(__stop___ksymtab_unused) = .; \ } \ \ /* Kernel symbol table: GPL-only unused symbols */ \ __ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .; \ - *(__ksymtab_unused_gpl) \ + *(SORT(___ksymtab_unused_gpl+*)) \ VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .; \ } \ \ /* Kernel symbol table: GPL-future-only symbols */ \ __ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .; \ - *(__ksymtab_gpl_future) \ + *(SORT(___ksymtab_gpl_future+*)) \ VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .; \ } \ \ /* Kernel symbol table: Normal symbols */ \ __kcrctab : AT(ADDR(__kcrctab) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab) = .; \ - *(__kcrctab) \ + *(SORT(___kcrctab+*)) \ VMLINUX_SYMBOL(__stop___kcrctab) = .; \ } \ \ /* Kernel symbol table: GPL-only symbols */ \ __kcrctab_gpl : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_gpl) = .; \ - *(__kcrctab_gpl) \ + *(SORT(___kcrctab_gpl+*)) \ VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .; \ } \ \ /* Kernel symbol table: Normal unused symbols */ \ __kcrctab_unused : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_unused) = .; \ - *(__kcrctab_unused) \ + *(SORT(___kcrctab_unused+*)) \ VMLINUX_SYMBOL(__stop___kcrctab_unused) = .; \ } \ \ /* Kernel symbol table: GPL-only unused symbols */ \ __kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .; \ - *(__kcrctab_unused_gpl) \ + *(SORT(___kcrctab_unused_gpl+*)) \ VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .; \ } \ \ /* Kernel symbol table: GPL-future-only symbols */ \ __kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .; \ - *(__kcrctab_gpl_future) \ + *(SORT(___kcrctab_gpl_future+*)) \ VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .; \ } \ \ @@ -589,14 +591,6 @@ #define BUG_TABLE #endif -#define JUMP_TABLE \ - . = ALIGN(8); \ - __jump_table : AT(ADDR(__jump_table) - LOAD_OFFSET) { \ - VMLINUX_SYMBOL(__start___jump_table) = .; \ - *(__jump_table) \ - VMLINUX_SYMBOL(__stop___jump_table) = .; \ - } - #ifdef CONFIG_PM_TRACE #define TRACEDATA \ . = ALIGN(4); \ @@ -688,6 +682,28 @@ } /** + * PERCPU_INPUT - the percpu input sections + * @cacheline: cacheline size + * + * The core percpu section names and core symbols which do not rely + * directly upon load addresses. + * + * @cacheline is used to align subsections to avoid false cacheline + * sharing between subsections for different purposes. + */ +#define PERCPU_INPUT(cacheline) \ + VMLINUX_SYMBOL(__per_cpu_start) = .; \ + *(.data..percpu..first) \ + . = ALIGN(PAGE_SIZE); \ + *(.data..percpu..page_aligned) \ + . = ALIGN(cacheline); \ + *(.data..percpu..readmostly) \ + . = ALIGN(cacheline); \ + *(.data..percpu) \ + *(.data..percpu..shared_aligned) \ + VMLINUX_SYMBOL(__per_cpu_end) = .; + +/** * PERCPU_VADDR - define output section for percpu area * @cacheline: cacheline size * @vaddr: explicit base address (optional) @@ -709,52 +725,33 @@ * * Note that this macros defines __per_cpu_load as an absolute symbol. * If there is no need to put the percpu section at a predetermined - * address, use PERCPU(). + * address, use PERCPU_SECTION. */ #define PERCPU_VADDR(cacheline, vaddr, phdr) \ VMLINUX_SYMBOL(__per_cpu_load) = .; \ .data..percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load) \ - LOAD_OFFSET) { \ - VMLINUX_SYMBOL(__per_cpu_start) = .; \ - *(.data..percpu..first) \ - . = ALIGN(PAGE_SIZE); \ - *(.data..percpu..page_aligned) \ - . = ALIGN(cacheline); \ - *(.data..percpu..readmostly) \ - . = ALIGN(cacheline); \ - *(.data..percpu) \ - *(.data..percpu..shared_aligned) \ - VMLINUX_SYMBOL(__per_cpu_end) = .; \ + PERCPU_INPUT(cacheline) \ } phdr \ . = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data..percpu); /** - * PERCPU - define output section for percpu area, simple version + * PERCPU_SECTION - define output section for percpu area, simple version * @cacheline: cacheline size - * @align: required alignment * - * Align to @align and outputs output section for percpu area. This macro - * doesn't manipulate @vaddr or @phdr and __per_cpu_load and + * Align to PAGE_SIZE and outputs output section for percpu area. This + * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and * __per_cpu_start will be identical. * - * This macro is equivalent to ALIGN(@align); PERCPU_VADDR(@cacheline,,) + * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,) * except that __per_cpu_load is defined as a relative symbol against * .data..percpu which is required for relocatable x86_32 configuration. */ -#define PERCPU(cacheline, align) \ - . = ALIGN(align); \ +#define PERCPU_SECTION(cacheline) \ + . = ALIGN(PAGE_SIZE); \ .data..percpu : AT(ADDR(.data..percpu) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__per_cpu_load) = .; \ - VMLINUX_SYMBOL(__per_cpu_start) = .; \ - *(.data..percpu..first) \ - . = ALIGN(PAGE_SIZE); \ - *(.data..percpu..page_aligned) \ - . = ALIGN(cacheline); \ - *(.data..percpu..readmostly) \ - . = ALIGN(cacheline); \ - *(.data..percpu) \ - *(.data..percpu..shared_aligned) \ - VMLINUX_SYMBOL(__per_cpu_end) = .; \ + PERCPU_INPUT(cacheline) \ } diff --git a/include/asm-generic/xor.h b/include/asm-generic/xor.h index aaab875..6028fb8 100644 --- a/include/asm-generic/xor.h +++ b/include/asm-generic/xor.h @@ -13,7 +13,7 @@ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include <asm/processor.h> +#include <linux/prefetch.h> static void xor_8regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) |