diff options
159 files changed, 3217 insertions, 3338 deletions
diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt index e132fb1163b..7eb715e07ed 100644 --- a/Documentation/cachetlb.txt +++ b/Documentation/cachetlb.txt @@ -49,9 +49,6 @@ changes occur: page table operations such as what happens during fork, and exec. - Platform developers note that generic code will always - invoke this interface without mm->page_table_lock held. - 3) void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) @@ -72,9 +69,6 @@ changes occur: call flush_tlb_page (see below) for each entry which may be modified. - Platform developers note that generic code will always - invoke this interface with mm->page_table_lock held. - 4) void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) This time we need to remove the PAGE_SIZE sized translation @@ -93,9 +87,6 @@ changes occur: This is used primarily during fault processing. - Platform developers note that generic code will always - invoke this interface with mm->page_table_lock held. - 5) void flush_tlb_pgtables(struct mm_struct *mm, unsigned long start, unsigned long end) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 90766b75d1b..5dffcfefc3c 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1460,8 +1460,6 @@ running once the system is up. stifb= [HW] Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]] - stram_swap= [HW,M68k] - swiotlb= [IA-64] Number of I/O TLB slabs switches= [HW,M68k] diff --git a/Documentation/m68k/kernel-options.txt b/Documentation/m68k/kernel-options.txt index e191baad830..d5d3f064f55 100644 --- a/Documentation/m68k/kernel-options.txt +++ b/Documentation/m68k/kernel-options.txt @@ -626,7 +626,7 @@ ignored (others aren't affected). can be performed in optimal order. Not all SCSI devices support tagged queuing (:-(). -4.6 switches= +4.5 switches= ------------- Syntax: switches=<list of switches> @@ -661,28 +661,6 @@ correctly. earlier initialization ("ov_"-less) takes precedence. But the switching-off on reset still happens in this case. -4.5) stram_swap= ----------------- - -Syntax: stram_swap=<do_swap>[,<max_swap>] - - This option is available only if the kernel has been compiled with -CONFIG_STRAM_SWAP enabled. Normally, the kernel then determines -dynamically whether to actually use ST-RAM as swap space. (Currently, -the fraction of ST-RAM must be less or equal 1/3 of total memory to -enable this swapping.) You can override the kernel's decision by -specifying this option. 1 for <do_swap> means always enable the swap, -even if you have less alternate RAM. 0 stands for never swap to -ST-RAM, even if it's small enough compared to the rest of memory. - - If ST-RAM swapping is enabled, the kernel usually uses all free -ST-RAM as swap "device". If the kernel resides in ST-RAM, the region -allocated by it is obviously never used for swapping :-) You can also -limit this amount by specifying the second parameter, <max_swap>, if -you want to use parts of ST-RAM as normal system memory. <max_swap> is -in kBytes and the number should be a multiple of 4 (otherwise: rounded -down). - 5) Options for Amiga Only: ========================== diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index c7481d59b6d..6d5251254f6 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -371,6 +371,8 @@ show_mem(void) show_free_areas(); printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); for_each_online_node(nid) { + unsigned long flags; + pgdat_resize_lock(NODE_DATA(nid), &flags); i = node_spanned_pages(nid); while (i-- > 0) { struct page *page = nid_page_nr(nid, i); @@ -384,6 +386,7 @@ show_mem(void) else shared += page_count(page) - 1; } + pgdat_resize_unlock(NODE_DATA(nid), &flags); } printk("%ld pages of RAM\n",total); printk("%ld free pages\n",free); diff --git a/arch/alpha/mm/remap.c b/arch/alpha/mm/remap.c index 19817ad3d89..a78356c3ead 100644 --- a/arch/alpha/mm/remap.c +++ b/arch/alpha/mm/remap.c @@ -2,7 +2,6 @@ #include <asm/pgalloc.h> #include <asm/cacheflush.h> -/* called with the page_table_lock held */ static inline void remap_area_pte(pte_t * pte, unsigned long address, unsigned long size, unsigned long phys_addr, unsigned long flags) @@ -31,7 +30,6 @@ remap_area_pte(pte_t * pte, unsigned long address, unsigned long size, } while (address && (address < end)); } -/* called with the page_table_lock held */ static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size, unsigned long phys_addr, unsigned long flags) @@ -46,7 +44,7 @@ remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size, if (address >= end) BUG(); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, @@ -70,7 +68,6 @@ __alpha_remap_area_pages(unsigned long address, unsigned long phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pmd_t *pmd; pmd = pmd_alloc(&init_mm, dir, address); @@ -84,7 +81,6 @@ __alpha_remap_area_pages(unsigned long address, unsigned long phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); return error; } diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index a94d75fef59..a917e3dd366 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -139,93 +139,33 @@ struct iwmmxt_sigframe { unsigned long storage[0x98/4]; }; -static int page_present(struct mm_struct *mm, void __user *uptr, int wr) -{ - unsigned long addr = (unsigned long)uptr; - pgd_t *pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pmd_t *pmd = pmd_offset(pgd, addr); - if (pmd_present(*pmd)) { - pte_t *pte = pte_offset_map(pmd, addr); - return (pte_present(*pte) && (!wr || pte_write(*pte))); - } - } - return 0; -} - -static int copy_locked(void __user *uptr, void *kptr, size_t size, int write, - void (*copyfn)(void *, void __user *)) -{ - unsigned char v, __user *userptr = uptr; - int err = 0; - - do { - struct mm_struct *mm; - - if (write) { - __put_user_error(0, userptr, err); - __put_user_error(0, userptr + size - 1, err); - } else { - __get_user_error(v, userptr, err); - __get_user_error(v, userptr + size - 1, err); - } - - if (err) - break; - - mm = current->mm; - spin_lock(&mm->page_table_lock); - if (page_present(mm, userptr, write) && - page_present(mm, userptr + size - 1, write)) { - copyfn(kptr, uptr); - } else - err = 1; - spin_unlock(&mm->page_table_lock); - } while (err); - - return err; -} - static int preserve_iwmmxt_context(struct iwmmxt_sigframe *frame) { - int err = 0; + char kbuf[sizeof(*frame) + 8]; + struct iwmmxt_sigframe *kframe; /* the iWMMXt context must be 64 bit aligned */ - WARN_ON((unsigned long)frame & 7); - - __put_user_error(IWMMXT_MAGIC0, &frame->magic0, err); - __put_user_error(IWMMXT_MAGIC1, &frame->magic1, err); - - /* - * iwmmxt_task_copy() doesn't check user permissions. - * Let's do a dummy write on the upper boundary to ensure - * access to user mem is OK all way up. - */ - err |= copy_locked(&frame->storage, current_thread_info(), - sizeof(frame->storage), 1, iwmmxt_task_copy); - return err; + kframe = (struct iwmmxt_sigframe *)((unsigned long)(kbuf + 8) & ~7); + kframe->magic0 = IWMMXT_MAGIC0; + kframe->magic1 = IWMMXT_MAGIC1; + iwmmxt_task_copy(current_thread_info(), &kframe->storage); + return __copy_to_user(frame, kframe, sizeof(*frame)); } static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame) { - unsigned long magic0, magic1; - int err = 0; + char kbuf[sizeof(*frame) + 8]; + struct iwmmxt_sigframe *kframe; - /* the iWMMXt context is 64 bit aligned */ - WARN_ON((unsigned long)frame & 7); - - /* - * Validate iWMMXt context signature. - * Also, iwmmxt_task_restore() doesn't check user permissions. - * Let's do a dummy write on the upper boundary to ensure - * access to user mem is OK all way up. - */ - __get_user_error(magic0, &frame->magic0, err); - __get_user_error(magic1, &frame->magic1, err); - if (!err && magic0 == IWMMXT_MAGIC0 && magic1 == IWMMXT_MAGIC1) - err = copy_locked(&frame->storage, current_thread_info(), - sizeof(frame->storage), 0, iwmmxt_task_restore); - return err; + /* the iWMMXt context must be 64 bit aligned */ + kframe = (struct iwmmxt_sigframe *)((unsigned long)(kbuf + 8) & ~7); + if (__copy_from_user(kframe, frame, sizeof(*frame))) + return -1; + if (kframe->magic0 != IWMMXT_MAGIC0 || + kframe->magic1 != IWMMXT_MAGIC1) + return -1; + iwmmxt_task_restore(current_thread_info(), &kframe->storage); + return 0; } #endif diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index baa09601a64..66e5a0516f2 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -483,29 +483,33 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) unsigned long addr = regs->ARM_r2; struct mm_struct *mm = current->mm; pgd_t *pgd; pmd_t *pmd; pte_t *pte; + spinlock_t *ptl; regs->ARM_cpsr &= ~PSR_C_BIT; - spin_lock(&mm->page_table_lock); + down_read(&mm->mmap_sem); pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) goto bad_access; pmd = pmd_offset(pgd, addr); if (!pmd_present(*pmd)) goto bad_access; - pte = pte_offset_map(pmd, addr); - if (!pte_present(*pte) || !pte_write(*pte)) + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!pte_present(*pte) || !pte_write(*pte)) { + pte_unmap_unlock(pte, ptl); goto bad_access; + } val = *(unsigned long *)addr; val -= regs->ARM_r0; if (val == 0) { *(unsigned long *)addr = regs->ARM_r1; regs->ARM_cpsr |= PSR_C_BIT; } - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(pte, ptl); + up_read(&mm->mmap_sem); return val; bad_access: - spin_unlock(&mm->page_table_lock); + up_read(&mm->mmap_sem); /* simulate a write access fault */ do_DataAbort(addr, 15 + (1 << 11), regs); return -1; diff --git a/arch/arm/mm/consistent.c b/arch/arm/mm/consistent.c index 82f4d5e27c5..47b0b767f08 100644 --- a/arch/arm/mm/consistent.c +++ b/arch/arm/mm/consistent.c @@ -397,8 +397,6 @@ static int __init consistent_init(void) pte_t *pte; int ret = 0; - spin_lock(&init_mm.page_table_lock); - do { pgd = pgd_offset(&init_mm, CONSISTENT_BASE); pmd = pmd_alloc(&init_mm, pgd, CONSISTENT_BASE); @@ -409,7 +407,7 @@ static int __init consistent_init(void) } WARN_ON(!pmd_none(*pmd)); - pte = pte_alloc_kernel(&init_mm, pmd, CONSISTENT_BASE); + pte = pte_alloc_kernel(pmd, CONSISTENT_BASE); if (!pte) { printk(KERN_ERR "%s: no pte tables\n", __func__); ret = -ENOMEM; @@ -419,8 +417,6 @@ static int __init consistent_init(void) consistent_pte = pte; } while (0); - spin_unlock(&init_mm.page_table_lock); - return ret; } diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index be4ab3d73c9..7fc1b35a674 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -26,6 +26,11 @@ static unsigned long shared_pte_mask = L_PTE_CACHEABLE; /* * We take the easy way out of this problem - we make the * PTE uncacheable. However, we leave the write buffer on. + * + * Note that the pte lock held when calling update_mmu_cache must also + * guard the pte (somewhere else in the same mm) that we modify here. + * Therefore those configurations which might call adjust_pte (those + * without CONFIG_CPU_CACHE_VIPT) cannot support split page_table_lock. */ static int adjust_pte(struct vm_area_struct *vma, unsigned long address) { @@ -127,7 +132,7 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page); * 2. If we have multiple shared mappings of the same space in * an object, we need to deal with the cache aliasing issues. * - * Note that the page_table_lock will be held. + * Note that the pte lock will be held. */ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 6fb1258df1b..0f128c28fee 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -75,7 +75,7 @@ remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size, pgprot = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_WRITE | flags); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, pgprot); @@ -97,7 +97,6 @@ remap_area_pages(unsigned long start, unsigned long phys_addr, phys_addr -= address; dir = pgd_offset(&init_mm, address); BUG_ON(address >= end); - spin_lock(&init_mm.page_table_lock); do { pmd_t *pmd = pmd_alloc(&init_mm, dir, address); if (!pmd) { @@ -114,7 +113,6 @@ remap_area_pages(unsigned long start, unsigned long phys_addr, dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_cache_vmap(start, end); return err; } diff --git a/arch/arm/mm/mm-armv.c b/arch/arm/mm/mm-armv.c index 61bc2fa0511..1221fdde176 100644 --- a/arch/arm/mm/mm-armv.c +++ b/arch/arm/mm/mm-armv.c @@ -180,11 +180,6 @@ pgd_t *get_pgd_slow(struct mm_struct *mm) if (!vectors_high()) { /* - * This lock is here just to satisfy pmd_alloc and pte_lock - */ - spin_lock(&mm->page_table_lock); - - /* * On ARM, first page must always be allocated since it * contains the machine vectors. */ @@ -201,23 +196,14 @@ pgd_t *get_pgd_slow(struct mm_struct *mm) set_pte(new_pte, *init_pte); pte_unmap_nested(init_pte); pte_unmap(new_pte); - - spin_unlock(&mm->page_table_lock); } return new_pgd; no_pte: - spin_unlock(&mm->page_table_lock); pmd_free(new_pmd); - free_pages((unsigned long)new_pgd, 2); - return NULL; - no_pmd: - spin_unlock(&mm->page_table_lock); free_pages((unsigned long)new_pgd, 2); - return NULL; - no_pgd: return NULL; } @@ -243,6 +229,7 @@ void free_pgd_slow(pgd_t *pgd) pte = pmd_page(*pmd); pmd_clear(pmd); dec_page_state(nr_page_table_pages); + pte_lock_deinit(pte); pte_free(pte); pmd_free(pmd); free: diff --git a/arch/arm/oprofile/backtrace.c b/arch/arm/oprofile/backtrace.c index df35c452a8b..7c22c12618c 100644 --- a/arch/arm/oprofile/backtrace.c +++ b/arch/arm/oprofile/backtrace.c @@ -49,42 +49,22 @@ static struct frame_tail* kernel_backtrace(struct frame_tail *tail) static struct frame_tail* user_backtrace(struct frame_tail *tail) { - struct frame_tail buftail; + struct frame_tail buftail[2]; - /* hardware pte might not be valid due to dirty/accessed bit emulation - * so we use copy_from_user and benefit from exception fixups */ - if (copy_from_user(&buftail, tail, sizeof(struct frame_tail))) + /* Also check accessibility of one struct frame_tail beyond */ + if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) + return NULL; + if (__copy_from_user_inatomic(buftail, tail, sizeof(buftail))) return NULL; - oprofile_add_trace(buftail.lr); + oprofile_add_trace(buftail[0].lr); /* frame pointers should strictly progress back up the stack * (towards higher addresses) */ - if (tail >= buftail.fp) + if (tail >= buftail[0].fp) return NULL; - return buftail.fp-1; -} - -/* Compare two addresses and see if they're on the same page */ -#define CMP_ADDR_EQUAL(x,y,offset) ((((unsigned long) x) >> PAGE_SHIFT) \ - == ((((unsigned long) y) + offset) >> PAGE_SHIFT)) - -/* check that the page(s) containing the frame tail are present */ -static int pages_present(struct frame_tail *tail) -{ - struct mm_struct * mm = current->mm; - - if (!check_user_page_readable(mm, (unsigned long)tail)) - return 0; - - if (CMP_ADDR_EQUAL(tail, tail, 8)) - return 1; - - if (!check_user_page_readable(mm, ((unsigned long)tail) + 8)) - return 0; - - return 1; + return buftail[0].fp-1; } /* @@ -118,7 +98,6 @@ static int valid_kernel_stack(struct frame_tail *tail, struct pt_regs *regs) void arm_backtrace(struct pt_regs * const regs, unsigned int depth) { struct frame_tail *tail; - unsigned long last_address = 0; tail = ((struct frame_tail *) regs->ARM_fp) - 1; @@ -132,13 +111,6 @@ void arm_backtrace(struct pt_regs * const regs, unsigned int depth) return; } - while (depth-- && tail && !((unsigned long) tail & 3)) { - if ((!CMP_ADDR_EQUAL(last_address, tail, 0) - || !CMP_ADDR_EQUAL(last_address, tail, 8)) - && !pages_present(tail)) - return; - last_address = (unsigned long) tail; + while (depth-- && tail && !((unsigned long) tail & 3)) tail = user_backtrace(tail); - } } - diff --git a/arch/arm26/mm/memc.c b/arch/arm26/mm/memc.c index 8e8a2bb2487..34def6397c3 100644 --- a/arch/arm26/mm/memc.c +++ b/arch/arm26/mm/memc.c @@ -79,12 +79,6 @@ pgd_t *get_pgd_slow(struct mm_struct *mm) goto no_pgd; /* - * This lock is here just to satisfy pmd_alloc and pte_lock - * FIXME: I bet we could avoid taking it pretty much altogether - */ - spin_lock(&mm->page_table_lock); - - /* * On ARM, first page must always be allocated since it contains * the machine vectors. */ @@ -92,7 +86,7 @@ pgd_t *get_pgd_slow(struct mm_struct *mm) if (!new_pmd) goto no_pmd; - new_pte = pte_alloc_kernel(mm, new_pmd, 0); + new_pte = pte_alloc_map(mm, new_pmd, 0); if (!new_pte) goto no_pte; @@ -101,6 +95,7 @@ pgd_t *get_pgd_slow(struct mm_struct *mm) init_pte = pte_offset(init_pmd, 0); set_pte(new_pte, *init_pte); + pte_unmap(new_pte); /* * the page table entries are zeroed @@ -112,23 +107,14 @@ pgd_t *get_pgd_slow(struct mm_struct *mm) memcpy(new_pgd + FIRST_KERNEL_PGD_NR, init_pgd + FIRST_KERNEL_PGD_NR, (PTRS_PER_PGD - FIRST_KERNEL_PGD_NR) * sizeof(pgd_t)); - spin_unlock(&mm->page_table_lock); - /* update MEMC tables */ cpu_memc_update_all(new_pgd); return new_pgd; no_pte: - spin_unlock(&mm->page_table_lock); pmd_free(new_pmd); - free_pgd_slow(new_pgd); - return NULL; - no_pmd: - spin_unlock(&mm->page_table_lock); free_pgd_slow(new_pgd); - return NULL; - no_pgd: return NULL; } diff --git a/arch/cris/arch-v32/mm/tlb.c b/arch/cris/arch-v32/mm/tlb.c index 8233406798d..b08a28bb58a 100644 --- a/arch/cris/arch-v32/mm/tlb.c +++ b/arch/cris/arch-v32/mm/tlb.c @@ -175,6 +175,8 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm) return 0; } +static DEFINE_SPINLOCK(mmu_context_lock); + /* Called in schedule() just before actually doing the switch_to. */ void switch_mm(struct mm_struct *prev, struct mm_struct *next, @@ -183,10 +185,10 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, int cpu = smp_processor_id(); /* Make sure there is a MMU context. */ - spin_lock(&next->page_table_lock); + spin_lock(&mmu_context_lock); get_mmu_context(next); cpu_set(cpu, next->cpu_vm_mask); - spin_unlock(&next->page_table_lock); + spin_unlock(&mmu_context_lock); /* * Remember the pgd for the fault handlers. Keep a seperate copy of it diff --git a/arch/cris/mm/ioremap.c b/arch/cris/mm/ioremap.c index ebba11e270f..a92ac987758 100644 --- a/arch/cris/mm/ioremap.c +++ b/arch/cris/mm/ioremap.c @@ -52,7 +52,7 @@ static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned lo if (address >= end) BUG(); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, prot); @@ -74,7 +74,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pud_t *pud; pmd_t *pmd; @@ -94,7 +93,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return error; } diff --git a/arch/frv/mm/dma-alloc.c b/arch/frv/mm/dma-alloc.c index cfc4f97490c..342823aad75 100644 --- a/arch/frv/mm/dma-alloc.c +++ b/arch/frv/mm/dma-alloc.c @@ -55,21 +55,18 @@ static int map_page(unsigned long va, unsigned long pa, pgprot_t prot) pte_t *pte; int err = -ENOMEM; - spin_lock(&init_mm.page_table_lock); - /* Use upper 10 bits of VA to index the first level map */ pge = pgd_offset_k(va); pue = pud_offset(pge, va); pme = pmd_offset(pue, va); /* Use middle 10 bits of VA to index the second-level map */ - pte = pte_alloc_kernel(&init_mm, pme, va); + pte = pte_alloc_kernel(pme, va); if (pte != 0) { err = 0; set_pte(pte, mk_pte_phys(pa & PAGE_MASK, prot)); } - spin_unlock(&init_mm.page_table_lock); return err; } diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c index 4eaec0f3525..2c67dfe5a6b 100644 --- a/arch/frv/mm/pgalloc.c +++ b/arch/frv/mm/pgalloc.c @@ -87,14 +87,14 @@ static inline void pgd_list_add(pgd_t *pgd) if (pgd_list) pgd_list->private = (unsigned long) &page->index; pgd_list = page; - page->private = (unsigned long) &pgd_list; + set_page_private(page, (unsigned long)&pgd_list); } static inline void pgd_list_del(pgd_t *pgd) { struct page *next, **pprev, *page = virt_to_page(pgd); next = (struct page *) page->index; - pprev = (struct page **) page->private; + pprev = (struct page **)page_private(page); *pprev = next; if (next) next->private = (unsigned long) pprev; diff --git a/arch/i386/kernel/vm86.c b/arch/i386/kernel/vm86.c index 16b48500962..fc1993564f9 100644 --- a/arch/i386/kernel/vm86.c +++ b/arch/i386/kernel/vm86.c @@ -134,17 +134,16 @@ struct pt_regs * fastcall save_v86_state(struct kernel_vm86_regs * regs) return ret; } -static void mark_screen_rdonly(struct task_struct * tsk) +static void mark_screen_rdonly(struct mm_struct *mm) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; - pte_t *pte, *mapped; + pte_t *pte; + spinlock_t *ptl; int i; - preempt_disable(); - spin_lock(&tsk->mm->page_table_lock); - pgd = pgd_offset(tsk->mm, 0xA0000); + pgd = pgd_offset(mm, 0xA0000); if (pgd_none_or_clear_bad(pgd)) goto out; pud = pud_offset(pgd, 0xA0000); @@ -153,16 +152,14 @@ static void mark_screen_rdonly(struct task_struct * tsk) pmd = pmd_offset(pud, 0xA0000); if (pmd_none_or_clear_bad(pmd)) goto out; - pte = mapped = pte_offset_map(pmd, 0xA0000); + pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); for (i = 0; i < 32; i++) { if (pte_present(*pte)) set_pte(pte, pte_wrprotect(*pte)); pte++; } - pte_unmap(mapped); + pte_unmap_unlock(pte, ptl); out: - spin_unlock(&tsk->mm->page_table_lock); - preempt_enable(); flush_tlb(); } @@ -306,7 +303,7 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk tsk->thread.screen_bitmap = info->screen_bitmap; if (info->flags & VM86_SCREEN_BITMAP) - mark_screen_rdonly(tsk); + mark_screen_rdonly(tsk->mm); __asm__ __volatile__( "xorl %%eax,%%eax; movl %%eax,%%fs; movl %%eax,%%gs\n\t" "movl %0,%%esp\n\t" diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index 244d8ec66be..c4af9638dbf 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -98,7 +98,7 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn, extern unsigned long find_max_low_pfn(void); extern void find_max_pfn(void); -extern void one_highpage_init(struct page *, int, int); +extern void add_one_highpage_init(struct page *, int, int); extern struct e820map e820; extern unsigned long init_pg_tables_end; @@ -427,7 +427,7 @@ void __init set_highmem_pages_init(int bad_ppro) if (!pfn_valid(node_pfn)) continue; page = pfn_to_page(node_pfn); - one_highpage_init(page, node_pfn, bad_ppro); + add_one_highpage_init(page, node_pfn, bad_ppro); } } totalram_pages += totalhigh_pages; diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index 2ebaf75f732..542d9298da5 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -27,6 +27,7 @@ #include <linux/slab.h> #include <linux/proc_fs.h> #include <linux/efi.h> +#include <linux/memory_hotplug.h> #include <asm/processor.h> #include <asm/system.h> @@ -266,17 +267,46 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = pte; } -void __init one_highpage_init(struct page *page, int pfn, int bad_ppro) +void __devinit free_new_highpage(struct page *page) +{ + set_page_count(page, 1); + __free_page(page); + totalhigh_pages++; +} + +void __init add_one_highpage_init(struct page *page, int pfn, int bad_ppro) { if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) { ClearPageReserved(page); - set_page_count(page, 1); - __free_page(page); - totalhigh_pages++; + free_new_highpage(page); } else SetPageReserved(page); } +static int add_one_highpage_hotplug(struct page *page, unsigned long pfn) +{ + free_new_highpage(page); + totalram_pages++; +#ifdef CONFIG_FLATMEM + max_mapnr = max(pfn, max_mapnr); +#endif + num_physpages++; + return 0; +} + +/* + * Not currently handling the NUMA case. + * Assuming single node and all memory that + * has been added dynamically that would be + * onlined here is in HIGHMEM + */ +void online_page(struct page *page) +{ + ClearPageReserved(page); + add_one_highpage_hotplug(page, page_to_pfn(page)); +} + + #ifdef CONFIG_NUMA extern void set_highmem_pages_init(int); #else @@ -284,7 +314,7 @@ static void __init set_highmem_pages_init(int bad_ppro) { int pfn; for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) - one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro); + add_one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro); totalram_pages += totalhigh_pages; } #endif /* CONFIG_FLATMEM */ @@ -615,6 +645,28 @@ void __init mem_init(void) #endif } +/* + * this is for the non-NUMA, single node SMP system case. + * Specifically, in the case of x86, we will always add + * memory to the highmem for now. + */ +#ifndef CONFIG_NEED_MULTIPLE_NODES +int add_memory(u64 start, u64 size) +{ + struct pglist_data *pgdata = &contig_page_data; + struct zone *zone = pgdata->node_zones + MAX_NR_ZONES-1; + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + + return __add_pages(zone, start_pfn, nr_pages); +} + +int remove_memory(u64 start, u64 size) +{ + return -EINVAL; +} +#endif + kmem_cache_t *pgd_cache; kmem_cache_t *pmd_cache; diff --git a/arch/i386/mm/ioremap.c b/arch/i386/mm/ioremap.c index f379b8d6755..5d09de8d1c6 100644 --- a/arch/i386/mm/ioremap.c +++ b/arch/i386/mm/ioremap.c @@ -28,7 +28,7 @@ static int ioremap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long pfn; pfn = phys_addr >> PAGE_SHIFT; - pte = pte_alloc_kernel(&init_mm, pmd, addr); + pte = pte_alloc_kernel(pmd, addr); if (!pte) return -ENOMEM; do { @@ -87,14 +87,12 @@ static int ioremap_page_range(unsigned long addr, flush_cache_all(); phys_addr -= addr; pgd = pgd_offset_k(addr); - spin_lock(&init_mm.page_table_lock); do { next = pgd_addr_end(addr, end); err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, flags); if (err) break; } while (pgd++, addr = next, addr != end); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return err; } diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c index dcdce2c6c53..9db3242103b 100644 --- a/arch/i386/mm/pgtable.c +++ b/arch/i386/mm/pgtable.c @@ -31,11 +31,13 @@ void show_mem(void) pg_data_t *pgdat; unsigned long i; struct page_state ps; + unsigned long flags; printk(KERN_INFO "Mem-info:\n"); show_free_areas(); printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); for_each_pgdat(pgdat) { + pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; ++i) { page = pgdat_page_nr(pgdat, i); total++; @@ -48,6 +50,7 @@ void show_mem(void) else if (page_count(page)) shared += page_count(page) - 1; } + pgdat_resize_unlock(pgdat, &flags); } printk(KERN_INFO "%d pages of RAM\n", total); printk(KERN_INFO "%d pages of HIGHMEM\n", highmem); @@ -188,19 +191,19 @@ static inline void pgd_list_add(pgd_t *pgd) struct page *page = virt_to_page(pgd); page->index = (unsigned long)pgd_list; if (pgd_list) - pgd_list->private = (unsigned long)&page->index; + set_page_private(pgd_list, (unsigned long)&page->index); pgd_list = page; - page->private = (unsigned long)&pgd_list; + set_page_private(page, (unsigned long)&pgd_list); } static inline void pgd_list_del(pgd_t *pgd) { struct page *next, **pprev, *page = virt_to_page(pgd); next = (struct page *)page->index; - pprev = (struct page **)page->private; + pprev = (struct page **)page_private(page); *pprev = next; if (next) - next->private = (unsigned long)pprev; + set_page_private(next, (unsigned long)pprev); } void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused) diff --git a/arch/i386/oprofile/backtrace.c b/arch/i386/oprofile/backtrace.c index 65dfd2edb67..21654be3f73 100644 --- a/arch/i386/oprofile/backtrace.c +++ b/arch/i386/oprofile/backtrace.c @@ -12,6 +12,7 @@ #include <linux/sched.h> #include <linux/mm.h> #include <asm/ptrace.h> +#include <asm/uaccess.h> struct frame_head { struct frame_head * ebp; @@ -21,26 +22,22 @@ struct frame_head { static struct frame_head * dump_backtrace(struct frame_head * head) { - oprofile_add_trace(head->ret); + struct frame_head bufhead[2]; - /* frame pointers should strictly progress back up the stack - * (towards higher addresses) */ - if (head >= head->ebp) + /* Also check accessibility of one struct frame_head beyond */ + if (!access_ok(VERIFY_READ, head, sizeof(bufhead))) + return NULL; + if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead))) return NULL; - return head->ebp; -} - -/* check that the page(s) containing the frame head are present */ -static int pages_present(struct frame_head * head) -{ - struct mm_struct * mm = current->mm; + oprofile_add_trace(bufhead[0].ret); - /* FIXME: only necessary once per page */ - if (!check_user_page_readable(mm, (unsigned long)head)) - return 0; + /* frame pointers should strictly progress back up the stack + * (towards higher addresses) */ + if (head >= bufhead[0].ebp) + return NULL; - return check_user_page_readable(mm, (unsigned long)(head + 1)); + return bufhead[0].ebp; } /* @@ -97,15 +94,6 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) return; } -#ifdef CONFIG_SMP - if (!spin_trylock(¤t->mm->page_table_lock)) - return; -#endif - - while (depth-- && head && pages_present(head)) + while (depth-- && head) head = dump_backtrace(head); - -#ifdef CONFIG_SMP - spin_unlock(¤t->mm->page_table_lock); -#endif } diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index d71731ee5b6..f7dfc107cb7 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2352,7 +2352,8 @@ pfm_smpl_buffer_alloc(struct task_struct *task, pfm_context_t *ctx, unsigned lon insert_vm_struct(mm, vma); mm->total_vm += size >> PAGE_SHIFT; - vm_stat_account(vma); + vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, + vma_pages(vma)); up_write(&task->mm->mmap_sem); /* diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index a3788fb8480..a88cdb7232f 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -555,9 +555,13 @@ void show_mem(void) show_free_areas(); printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); for_each_pgdat(pgdat) { - unsigned long present = pgdat->node_present_pages; + unsigned long present; + unsigned long flags; int shared = 0, cached = 0, reserved = 0; + printk("Node ID: %d\n", pgdat->node_id); + pgdat_resize_lock(pgdat, &flags); + present = pgdat->node_present_pages; for(i = 0; i < pgdat->node_spanned_pages; i++) { struct page *page; if (pfn_valid(pgdat->node_start_pfn + i)) @@ -571,6 +575,7 @@ void show_mem(void) else if (page_count(page)) shared += page_count(page)-1; } + pgdat_resize_unlock(pgdat, &flags); total_present += present; total_reserved += reserved; total_cached += cached; diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 3c32af910d6..af7eb087dca 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -20,32 +20,6 @@ extern void die (char *, struct pt_regs *, long); /* - * This routine is analogous to expand_stack() but instead grows the - * register backing store (which grows towards higher addresses). - * Since the register backing store is access sequentially, we - * disallow growing the RBS by more than a page at a time. Note that - * the VM_GROWSUP flag can be set on any VM area but that's fine - * because the total process size is still limited by RLIMIT_STACK and - * RLIMIT_AS. - */ -static inline long -expand_backing_store (struct vm_area_struct *vma, unsigned long address) -{ - unsigned long grow; - - grow = PAGE_SIZE >> PAGE_SHIFT; - if (address - vma->vm_start > current->signal->rlim[RLIMIT_STACK].rlim_cur - || (((vma->vm_mm->total_vm + grow) << PAGE_SHIFT) > current->signal->rlim[RLIMIT_AS].rlim_cur)) - return -ENOMEM; - vma->vm_end += PAGE_SIZE; - vma->vm_mm->total_vm += grow; - if (vma->vm_flags & VM_LOCKED) - vma->vm_mm->locked_vm += grow; - __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, grow); - return 0; -} - -/* * Return TRUE if ADDRESS points at a page in the kernel's mapped segment * (inside region 5, on ia64) and that page is present. */ @@ -185,7 +159,13 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start) || REGION_OFFSET(address) >= RGN_MAP_LIMIT) goto bad_area; - if (expand_backing_store(vma, address)) + /* + * Since the register backing store is accessed sequentially, + * we disallow growing it by more than a page at a time. + */ + if (address > vma->vm_end + PAGE_SIZE - sizeof(long)) + goto bad_area; + if (expand_upwards(vma, address)) goto bad_area; } goto good_area; diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 98246acd499..e3215ba64ff 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -158,7 +158,7 @@ ia64_init_addr_space (void) vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; vma->vm_page_prot = protection_map[VM_DATA_DEFAULT_FLAGS & 0x7]; - vma->vm_flags = VM_DATA_DEFAULT_FLAGS | VM_GROWSUP; + vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; down_write(¤t->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(¤t->mm->mmap_sem); @@ -275,26 +275,21 @@ put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot) pgd = pgd_offset_k(address); /* note: this is NOT pgd_offset()! */ - spin_lock(&init_mm.page_table_lock); { pud = pud_alloc(&init_mm, pgd, address); if (!pud) goto out; - pmd = pmd_alloc(&init_mm, pud, address); if (!pmd) goto out; - pte = pte_alloc_map(&init_mm, pmd, address); + pte = pte_alloc_kernel(pmd, address); if (!pte) goto out; - if (!pte_none(*pte)) { - pte_unmap(pte); + if (!pte_none(*pte)) goto out; - } set_pte(pte, mk_pte(page, pgprot)); - pte_unmap(pte); } - out: spin_unlock(&init_mm.page_table_lock); + out: /* no need for flush_tlb */ return page; } diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index c93e0f2b5fe..c79a9b96d02 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -158,10 +158,12 @@ flush_tlb_range (struct vm_area_struct *vma, unsigned long start, unsigned long # ifdef CONFIG_SMP platform_global_tlb_purge(mm, start, end, nbits); # else + preempt_disable(); do { ia64_ptcl(start, (nbits<<2)); start += (1UL << nbits); } while (start < end); + preempt_enable(); # endif ia64_srlz_i(); /* srlz.i implies srlz.d */ diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c index d9a40b1fe8b..6facf15b04f 100644 --- a/arch/m32r/mm/init.c +++ b/arch/m32r/mm/init.c @@ -48,6 +48,8 @@ void show_mem(void) show_free_areas(); printk("Free swap: %6ldkB\n",nr_swap_pages<<(PAGE_SHIFT-10)); for_each_pgdat(pgdat) { + unsigned long flags; + pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; ++i) { page = pgdat_page_nr(pgdat, i); total++; @@ -60,6 +62,7 @@ void show_mem(void) else if (page_count(page)) shared += page_count(page) - 1; } + pgdat_resize_unlock(pgdat, &flags); } printk("%d pages of RAM\n", total); printk("%d pages of HIGHMEM\n",highmem); @@ -150,10 +153,14 @@ int __init reservedpages_count(void) int reservedpages, nid, i; reservedpages = 0; - for_each_online_node(nid) + for_each_online_node(nid) { + unsigned long flags; + pgdat_resize_lock(NODE_DATA(nid), &flags); for (i = 0 ; i < MAX_LOW_PFN(nid) - START_PFN(nid) ; i++) if (PageReserved(nid_page_nr(nid, i))) reservedpages++; + pgdat_resize_unlock(NODE_DATA(nid), &flags); + } return reservedpages; } diff --git a/arch/m32r/mm/ioremap.c b/arch/m32r/mm/ioremap.c index 70c59055c19..a151849a605 100644 --- a/arch/m32r/mm/ioremap.c +++ b/arch/m32r/mm/ioremap.c @@ -67,7 +67,7 @@ remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned long size, if (address >= end) BUG(); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, flags); @@ -90,7 +90,6 @@ remap_area_pages(unsigned long address, unsigned long phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pmd_t *pmd; pmd = pmd_alloc(&init_mm, dir, address); @@ -104,7 +103,6 @@ remap_area_pages(unsigned long address, unsigned long phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return error; } diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index ba960bbc8e6..1dd5d18b220 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -388,33 +388,11 @@ config AMIGA_PCMCIA Include support in the kernel for pcmcia on Amiga 1200 and Amiga 600. If you intend to use pcmcia cards say Y; otherwise say N. -config STRAM_SWAP - bool "Support for ST-RAM as swap space" - depends on ATARI && BROKEN - ---help--- - Some Atari 68k machines (including the 520STF and 1020STE) divide - their addressable memory into ST and TT sections. The TT section - (up to 512MB) is the main memory; the ST section (up to 4MB) is - accessible to the built-in graphics board, runs slower, and is - present mainly for backward compatibility with older machines. - - This enables support for using (parts of) ST-RAM as swap space, - instead of as normal system memory. This can first enhance system - performance if you have lots of alternate RAM (compared to the size - of ST-RAM), because executable code always will reside in faster - memory. ST-RAM will remain as ultra-fast swap space. On the other - hand, it allows much improved dynamic allocations of ST-RAM buffers - for device driver modules (e.g. floppy, ACSI, SLM printer, DMA - sound). The probability that such allocations at module load time - fail is drastically reduced. - config STRAM_PROC bool "ST-RAM statistics in /proc" depends on ATARI help - Say Y here to report ST-RAM usage statistics in /proc/stram. See - the help for CONFIG_STRAM_SWAP for discussion of ST-RAM and its - uses. + Say Y here to report ST-RAM usage statistics in /proc/stram. config HEARTBEAT bool "Use power LED as a heartbeat" if AMIGA || APOLLO || ATARI || MAC ||Q40 diff --git a/arch/m68k/atari/stram.c b/arch/m68k/atari/stram.c index 5a3c106b40c..22e0481a5f7 100644 --- a/arch/m68k/atari/stram.c +++ b/arch/m68k/atari/stram.c @@ -15,11 +15,9 @@ #include <linux/kdev_t.h> #include <linux/major.h> #include <linux/init.h> -#include <linux/swap.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> -#include <linux/shm.h> #include <linux/bootmem.h> #include <linux/mount.h> #include <linux/blkdev.h> @@ -33,8 +31,6 @@ #include <asm/io.h> #include <asm/semaphore.h> -#include <linux/swapops.h> - #undef DEBUG #ifdef DEBUG @@ -49,8 +45,7 @@ #include <linux/proc_fs.h> #endif -/* Pre-swapping comments: - * +/* * ++roman: * * New version of ST-Ram buffer allocation. Instead of using the @@ -75,76 +70,6 @@ * */ -/* - * New Nov 1997: Use ST-RAM as swap space! - * - * In the past, there were often problems with modules that require ST-RAM - * buffers. Such drivers have to use __get_dma_pages(), which unfortunately - * often isn't very successful in allocating more than 1 page :-( [1] The net - * result was that most of the time you couldn't insmod such modules (ataflop, - * ACSI, SCSI on Falcon, Atari internal framebuffer, not to speak of acsi_slm, - * which needs a 1 MB buffer... :-). - * - * To overcome this limitation, ST-RAM can now be turned into a very - * high-speed swap space. If a request for an ST-RAM buffer comes, the kernel - * now tries to unswap some pages on that swap device to make some free (and - * contiguous) space. This works much better in comparison to - * __get_dma_pages(), since used swap pages can be selectively freed by either - * moving them to somewhere else in swap space, or by reading them back into - * system memory. Ok, there operation of unswapping isn't really cheap (for - * each page, one has to go through the page tables of all processes), but it - * doesn't happen that often (only when allocation ST-RAM, i.e. when loading a - * module that needs ST-RAM). But it at least makes it possible to load such - * modules! - * - * It could also be that overall system performance increases a bit due to - * ST-RAM swapping, since slow ST-RAM isn't used anymore for holding data or - * executing code in. It's then just a (very fast, compared to disk) back - * storage for not-so-often needed data. (But this effect must be compared - * with the loss of total memory...) Don't know if the effect is already - * visible on a TT, where the speed difference between ST- and TT-RAM isn't - * that dramatic, but it should on machines where TT-RAM is really much faster - * (e.g. Afterburner). - * - * [1]: __get_free_pages() does a fine job if you only want one page, but if - * you want more (contiguous) pages, it can give you such a block only if - * there's already a free one. The algorithm can't try to free buffers or swap - * out something in order to make more free space, since all that page-freeing - * mechanisms work "target-less", i.e. they just free something, but not in a - * specific place. I.e., __get_free_pages() can't do anything to free - * *adjacent* pages :-( This situation becomes even worse for DMA memory, - * since the freeing algorithms are also blind to DMA capability of pages. - */ - -/* 1998-10-20: ++andreas - unswap_by_move disabled because it does not handle swapped shm pages. -*/ - -/* 2000-05-01: ++andreas - Integrated with bootmem. Remove all traces of unswap_by_move. -*/ - -#ifdef CONFIG_STRAM_SWAP -#define ALIGN_IF_SWAP(x) PAGE_ALIGN(x) -#else -#define ALIGN_IF_SWAP(x) (x) -#endif - -/* get index of swap page at address 'addr' */ -#define SWAP_NR(addr) (((addr) - swap_start) >> PAGE_SHIFT) - -/* get address of swap page #'nr' */ -#define SWAP_ADDR(nr) (swap_start + ((nr) << PAGE_SHIFT)) - -/* get number of pages for 'n' bytes (already page-aligned) */ -#define N_PAGES(n) ((n) >> PAGE_SHIFT) - -/* The following two numbers define the maximum fraction of ST-RAM in total - * memory, below that the kernel would automatically use ST-RAM as swap - * space. This decision can be overridden with stram_swap= */ -#define MAX_STRAM_FRACTION_NOM 1 -#define MAX_STRAM_FRACTION_DENOM 3 - /* Start and end (virtual) of ST-RAM */ static void *stram_start, *stram_end; @@ -164,10 +89,9 @@ typedef struct stram_block { } BLOCK; /* values for flags field */ -#define BLOCK_FREE 0x01 /* free structure in the BLOCKs pool */ +#define BLOCK_FREE 0x01 /* free structure in the BLOCKs pool */ #define BLOCK_KMALLOCED 0x02 /* structure allocated by kmalloc() */ -#define BLOCK_GFP 0x08 /* block allocated with __get_dma_pages() */ -#define BLOCK_INSWAP 0x10 /* block allocated in swap space */ +#define BLOCK_GFP 0x08 /* block allocated with __get_dma_pages() */ /* list of allocated blocks */ static BLOCK *alloc_list; @@ -179,60 +103,8 @@ static BLOCK *alloc_list; #define N_STATIC_BLOCKS 20 static BLOCK static_blocks[N_STATIC_BLOCKS]; -#ifdef CONFIG_STRAM_SWAP -/* max. number of bytes to use for swapping - * 0 = no ST-RAM swapping - * -1 = do swapping (to whole ST-RAM) if it's less than MAX_STRAM_FRACTION of - * total memory - */ -static int max_swap_size = -1; - -/* start and end of swapping area */ -static void *swap_start, *swap_end; - -/* The ST-RAM's swap info structure */ -static struct swap_info_struct *stram_swap_info; - -/* The ST-RAM's swap type */ -static int stram_swap_type; - -/* Semaphore for get_stram_region. */ -static DECLARE_MUTEX(stram_swap_sem); - -/* major and minor device number of the ST-RAM device; for the major, we use - * the same as Amiga z2ram, which is really similar and impossible on Atari, - * and for the minor a relatively odd number to avoid the user creating and - * using that device. */ -#define STRAM_MAJOR Z2RAM_MAJOR -#define STRAM_MINOR 13 - -/* Some impossible pointer value */ -#define MAGIC_FILE_P (struct file *)0xffffdead - -#ifdef DO_PROC -static unsigned stat_swap_read; -static unsigned stat_swap_write; -static unsigned stat_swap_force; -#endif /* DO_PROC */ - -#endif /* CONFIG_STRAM_SWAP */ - /***************************** Prototypes *****************************/ -#ifdef CONFIG_STRAM_SWAP -static int swap_init(void *start_mem, void *swap_data); -static void *get_stram_region( unsigned long n_pages ); -static void free_stram_region( unsigned long offset, unsigned long n_pages - ); -static int in_some_region(void *addr); -static unsigned long find_free_region( unsigned long n_pages, unsigned long - *total_free, unsigned long - *region_free ); -static void do_stram_request(request_queue_t *); -static int stram_open( struct inode *inode, struct file *filp ); -static int stram_release( struct inode *inode, struct file *filp ); -static void reserve_region(void *start, void *end); -#endif static BLOCK *add_region( void *addr, unsigned long size ); static BLOCK *find_region( void *addr ); static int remove_region( BLOCK *block ); @@ -279,84 +151,11 @@ void __init atari_stram_init(void) */ void __init atari_stram_reserve_pages(void *start_mem) { -#ifdef CONFIG_STRAM_SWAP - /* if max_swap_size is negative (i.e. no stram_swap= option given), - * determine at run time whether to use ST-RAM swapping */ - if (max_swap_size < 0) - /* Use swapping if ST-RAM doesn't make up more than MAX_STRAM_FRACTION - * of total memory. In that case, the max. size is set to 16 MB, - * because ST-RAM can never be bigger than that. - * Also, never use swapping on a Hades, there's no separate ST-RAM in - * that machine. */ - max_swap_size = - (!MACH_IS_HADES && - (N_PAGES(stram_end-stram_start)*MAX_STRAM_FRACTION_DENOM <= - ((unsigned long)high_memory>>PAGE_SHIFT)*MAX_STRAM_FRACTION_NOM)) ? 16*1024*1024 : 0; - DPRINTK( "atari_stram_reserve_pages: max_swap_size = %d\n", max_swap_size ); -#endif - /* always reserve first page of ST-RAM, the first 2 kB are * supervisor-only! */ if (!kernel_in_stram) reserve_bootmem (0, PAGE_SIZE); -#ifdef CONFIG_STRAM_SWAP - { - void *swap_data; - - start_mem = (void *) PAGE_ALIGN ((unsigned long) start_mem); - /* determine first page to use as swap: if the kernel is - in TT-RAM, this is the first page of (usable) ST-RAM; - otherwise just use the end of kernel data (= start_mem) */ - swap_start = !kernel_in_stram ? stram_start + PAGE_SIZE : start_mem; - /* decrement by one page, rest of kernel assumes that first swap page - * is always reserved and maybe doesn't handle swp_entry == 0 - * correctly */ - swap_start -= PAGE_SIZE; - swap_end = stram_end; - if (swap_end-swap_start > max_swap_size) - swap_end = swap_start + max_swap_size; - DPRINTK( "atari_stram_reserve_pages: swapping enabled; " - "swap=%p-%p\n", swap_start, swap_end); - - /* reserve some amount of memory for maintainance of - * swapping itself: one page for each 2048 (PAGE_SIZE/2) - * swap pages. (2 bytes for each page) */ - swap_data = start_mem; - start_mem += ((SWAP_NR(swap_end) + PAGE_SIZE/2 - 1) - >> (PAGE_SHIFT-1)) << PAGE_SHIFT; - /* correct swap_start if necessary */ - if (swap_start + PAGE_SIZE == swap_data) - swap_start = start_mem - PAGE_SIZE; - - if (!swap_init( start_mem, swap_data )) { - printk( KERN_ERR "ST-RAM swap space initialization failed\n" ); - max_swap_size = 0; - return; - } - /* reserve region for swapping meta-data */ - reserve_region(swap_data, start_mem); - /* reserve swapping area itself */ - reserve_region(swap_start + PAGE_SIZE, swap_end); - - /* - * If the whole ST-RAM is used for swapping, there are no allocatable - * dma pages left. But unfortunately, some shared parts of the kernel - * (particularly the SCSI mid-level) call __get_dma_pages() - * unconditionally :-( These calls then fail, and scsi.c even doesn't - * check for NULL return values and just crashes. The quick fix for - * this (instead of doing much clean up work in the SCSI code) is to - * pretend all pages are DMA-able by setting mach_max_dma_address to - * ULONG_MAX. This doesn't change any functionality so far, since - * get_dma_pages() shouldn't be used on Atari anyway anymore (better - * use atari_stram_alloc()), and the Atari SCSI drivers don't need DMA - * memory. But unfortunately there's now no kind of warning (even not - * a NULL return value) if you use get_dma_pages() nevertheless :-( - * You just will get non-DMA-able memory... - */ - mach_max_dma_address = 0xffffffff; - } -#endif } void atari_stram_mem_init_hook (void) @@ -367,7 +166,6 @@ void atari_stram_mem_init_hook (void) /* * This is main public interface: somehow allocate a ST-RAM block - * There are three strategies: * * - If we're before mem_init(), we have to make a static allocation. The * region is taken in the kernel data area (if the kernel is in ST-RAM) or @@ -375,14 +173,9 @@ void atari_stram_mem_init_hook (void) * rsvd_stram_* region. The ST-RAM is somewhere in the middle of kernel * address space in the latter case. * - * - If mem_init() already has been called and ST-RAM swapping is enabled, - * try to get the memory from the (pseudo) swap-space, either free already - * or by moving some other pages out of the swap. - * - * - If mem_init() already has been called, and ST-RAM swapping is not - * enabled, the only possibility is to try with __get_dma_pages(). This has - * the disadvantage that it's very hard to get more than 1 page, and it is - * likely to fail :-( + * - If mem_init() already has been called, try with __get_dma_pages(). + * This has the disadvantage that it's very hard to get more than 1 page, + * and it is likely to fail :-( * */ void *atari_stram_alloc(long size, const char *owner) @@ -393,27 +186,13 @@ void *atari_stram_alloc(long size, const char *owner) DPRINTK("atari_stram_alloc(size=%08lx,owner=%s)\n", size, owner); - size = ALIGN_IF_SWAP(size); - DPRINTK( "atari_stram_alloc: rounded size = %08lx\n", size ); -#ifdef CONFIG_STRAM_SWAP - if (max_swap_size) { - /* If swapping is active: make some free space in the swap - "device". */ - DPRINTK( "atari_stram_alloc: after mem_init, swapping ok, " - "calling get_region\n" ); - addr = get_stram_region( N_PAGES(size) ); - flags = BLOCK_INSWAP; - } - else -#endif if (!mem_init_done) return alloc_bootmem_low(size); else { - /* After mem_init() and no swapping: can only resort to - * __get_dma_pages() */ + /* After mem_init(): can only resort to __get_dma_pages() */ addr = (void *)__get_dma_pages(GFP_KERNEL, get_order(size)); flags = BLOCK_GFP; - DPRINTK( "atari_stram_alloc: after mem_init, swapping off, " + DPRINTK( "atari_stram_alloc: after mem_init, " "get_pages=%p\n", addr ); } @@ -422,12 +201,7 @@ void *atari_stram_alloc(long size, const char *owner) /* out of memory for BLOCK structure :-( */ DPRINTK( "atari_stram_alloc: out of mem for BLOCK -- " "freeing again\n" ); -#ifdef CONFIG_STRAM_SWAP - if (flags == BLOCK_INSWAP) - free_stram_region( SWAP_NR(addr), N_PAGES(size) ); - else -#endif - free_pages((unsigned long)addr, get_order(size)); + free_pages((unsigned long)addr, get_order(size)); return( NULL ); } block->owner = owner; @@ -451,25 +225,12 @@ void atari_stram_free( void *addr ) DPRINTK( "atari_stram_free: found block (%p): size=%08lx, owner=%s, " "flags=%02x\n", block, block->size, block->owner, block->flags ); -#ifdef CONFIG_STRAM_SWAP - if (!max_swap_size) { -#endif - if (block->flags & BLOCK_GFP) { - DPRINTK("atari_stram_free: is kmalloced, order_size=%d\n", - get_order(block->size)); - free_pages((unsigned long)addr, get_order(block->size)); - } - else - goto fail; -#ifdef CONFIG_STRAM_SWAP - } - else if (block->flags & BLOCK_INSWAP) { - DPRINTK( "atari_stram_free: is swap-alloced\n" ); - free_stram_region( SWAP_NR(block->start), N_PAGES(block->size) ); - } - else + if (!(block->flags & BLOCK_GFP)) goto fail; -#endif + + DPRINTK("atari_stram_free: is kmalloced, order_size=%d\n", + get_order(block->size)); + free_pages((unsigned long)addr, get_order(block->size)); remove_region( block ); return; @@ -478,612 +239,6 @@ void atari_stram_free( void *addr ) "(called from %p)\n", addr, __builtin_return_address(0) ); } - -#ifdef CONFIG_STRAM_SWAP - - -/* ------------------------------------------------------------------------ */ -/* Main Swapping Functions */ -/* ------------------------------------------------------------------------ */ - - -/* - * Initialize ST-RAM swap device - * (lots copied and modified from sys_swapon() in mm/swapfile.c) - */ -static int __init swap_init(void *start_mem, void *swap_data) -{ - static struct dentry fake_dentry; - static struct vfsmount fake_vfsmnt; - struct swap_info_struct *p; - struct inode swap_inode; - unsigned int type; - void *addr; - int i, j, k, prev; - - DPRINTK("swap_init(start_mem=%p, swap_data=%p)\n", - start_mem, swap_data); - - /* need at least one page for swapping to (and this also isn't very - * much... :-) */ - if (swap_end - swap_start < 2*PAGE_SIZE) { - printk( KERN_WARNING "stram_swap_init: swap space too small\n" ); - return( 0 ); - } - - /* find free slot in swap_info */ - for( p = swap_info, type = 0; type < nr_swapfiles; type++, p++ ) - if (!(p->flags & SWP_USED)) - break; - if (type >= MAX_SWAPFILES) { - printk( KERN_WARNING "stram_swap_init: max. number of " - "swap devices exhausted\n" ); - return( 0 ); - } - if (type >= nr_swapfiles) - nr_swapfiles = type+1; - - stram_swap_info = p; - stram_swap_type = type; - - /* fake some dir cache entries to give us some name in /dev/swaps */ - fake_dentry.d_parent = &fake_dentry; - fake_dentry.d_name.name = "stram (internal)"; - fake_dentry.d_name.len = 16; - fake_vfsmnt.mnt_parent = &fake_vfsmnt; - - p->flags = SWP_USED; - p->swap_file = &fake_dentry; - p->swap_vfsmnt = &fake_vfsmnt; - p->swap_map = swap_data; - p->cluster_nr = 0; - p->next = -1; - p->prio = 0x7ff0; /* a rather high priority, but not the higest - * to give the user a chance to override */ - - /* call stram_open() directly, avoids at least the overhead in - * constructing a dummy file structure... */ - swap_inode.i_rdev = MKDEV( STRAM_MAJOR, STRAM_MINOR ); - stram_open( &swap_inode, MAGIC_FILE_P ); - p->max = SWAP_NR(swap_end); - - /* initialize swap_map: set regions that are already allocated or belong - * to kernel data space to SWAP_MAP_BAD, otherwise to free */ - j = 0; /* # of free pages */ - k = 0; /* # of already allocated pages (from pre-mem_init stram_alloc()) */ - p->lowest_bit = 0; - p->highest_bit = 0; - for( i = 1, addr = SWAP_ADDR(1); i < p->max; - i++, addr += PAGE_SIZE ) { - if (in_some_region( addr )) { - p->swap_map[i] = SWAP_MAP_BAD; - ++k; - } - else if (kernel_in_stram && addr < start_mem ) { - p->swap_map[i] = SWAP_MAP_BAD; - } - else { - p->swap_map[i] = 0; - ++j; - if (!p->lowest_bit) p->lowest_bit = i; - p->highest_bit = i; - } - } - /* first page always reserved (and doesn't really belong to swap space) */ - p->swap_map[0] = SWAP_MAP_BAD; - - /* now swapping to this device ok */ - p->pages = j + k; - swap_list_lock(); - nr_swap_pages += j; - p->flags = SWP_WRITEOK; - - /* insert swap space into swap_list */ - prev = -1; - for (i = swap_list.head; i >= 0; i = swap_info[i].next) { - if (p->prio >= swap_info[i].prio) { - break; - } - prev = i; - } - p->next = i; - if (prev < 0) { - swap_list.head = swap_list.next = p - swap_info; - } else { - swap_info[prev].next = p - swap_info; - } - swap_list_unlock(); - - printk( KERN_INFO "Using %dk (%d pages) of ST-RAM as swap space.\n", - p->pages << 2, p->pages ); - return( 1 ); -} - - -/* - * The swap entry has been read in advance, and we return 1 to indicate - * that the page has been used or is no longer needed. - * - * Always set the resulting pte to be nowrite (the same as COW pages - * after one process has exited). We don't know just how many PTEs will - * share this swap entry, so be cautious and let do_wp_page work out - * what to do if a write is requested later. - */ -static inline void unswap_pte(struct vm_area_struct * vma, unsigned long - address, pte_t *dir, swp_entry_t entry, - struct page *page) -{ - pte_t pte = *dir; - - if (pte_none(pte)) - return; - if (pte_present(pte)) { - /* If this entry is swap-cached, then page must already - hold the right address for any copies in physical - memory */ - if (pte_page(pte) != page) - return; - /* We will be removing the swap cache in a moment, so... */ - set_pte(dir, pte_mkdirty(pte)); - return; - } - if (pte_val(pte) != entry.val) - return; - - DPRINTK("unswap_pte: replacing entry %08lx by new page %p", - entry.val, page); - set_pte(dir, pte_mkdirty(mk_pte(page, vma->vm_page_prot))); - swap_free(entry); - get_page(page); - inc_mm_counter(vma->vm_mm, rss); -} - -static inline void unswap_pmd(struct vm_area_struct * vma, pmd_t *dir, - unsigned long address, unsigned long size, - unsigned long offset, swp_entry_t entry, - struct page *page) -{ - pte_t * pte; - unsigned long end; - - if (pmd_none(*dir)) - return; - if (pmd_bad(*dir)) { - pmd_ERROR(*dir); - pmd_clear(dir); - return; - } - pte = pte_offset_kernel(dir, address); - offset += address & PMD_MASK; - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - do { - unswap_pte(vma, offset+address-vma->vm_start, pte, entry, page); - address += PAGE_SIZE; - pte++; - } while (address < end); -} - -static inline void unswap_pgd(struct vm_area_struct * vma, pgd_t *dir, - unsigned long address, unsigned long size, - swp_entry_t entry, struct page *page) -{ - pmd_t * pmd; - unsigned long offset, end; - - if (pgd_none(*dir)) - return; - if (pgd_bad(*dir)) { - pgd_ERROR(*dir); - pgd_clear(dir); - return; - } - pmd = pmd_offset(dir, address); - offset = address & PGDIR_MASK; - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - do { - unswap_pmd(vma, pmd, address, end - address, offset, entry, - page); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address < end); -} - -static void unswap_vma(struct vm_area_struct * vma, pgd_t *pgdir, - swp_entry_t entry, struct page *page) -{ - unsigned long start = vma->vm_start, end = vma->vm_end; - - do { - unswap_pgd(vma, pgdir, start, end - start, entry, page); - start = (start + PGDIR_SIZE) & PGDIR_MASK; - pgdir++; - } while (start < end); -} - -static void unswap_process(struct mm_struct * mm, swp_entry_t entry, - struct page *page) -{ - struct vm_area_struct* vma; - - /* - * Go through process' page directory. - */ - if (!mm) - return; - for (vma = mm->mmap; vma; vma = vma->vm_next) { - pgd_t * pgd = pgd_offset(mm, vma->vm_start); - unswap_vma(vma, pgd, entry, page); - } -} - - -static int unswap_by_read(unsigned short *map, unsigned long max, - unsigned long start, unsigned long n_pages) -{ - struct task_struct *p; - struct page *page; - swp_entry_t entry; - unsigned long i; - - DPRINTK( "unswapping %lu..%lu by reading in\n", - start, start+n_pages-1 ); - - for( i = start; i < start+n_pages; ++i ) { - if (map[i] == SWAP_MAP_BAD) { - printk( KERN_ERR "get_stram_region: page %lu already " - "reserved??\n", i ); - continue; - } - - if (map[i]) { - entry = swp_entry(stram_swap_type, i); - DPRINTK("unswap: map[i=%lu]=%u nr_swap=%ld\n", - i, map[i], nr_swap_pages); - - swap_device_lock(stram_swap_info); - map[i]++; - swap_device_unlock(stram_swap_info); - /* Get a page for the entry, using the existing - swap cache page if there is one. Otherwise, - get a clean page and read the swap into it. */ - page = read_swap_cache_async(entry, NULL, 0); - if (!page) { - swap_free(entry); - return -ENOMEM; - } - read_lock(&tasklist_lock); - for_each_process(p) - unswap_process(p->mm, entry, page); - read_unlock(&tasklist_lock); - shmem_unuse(entry, page); - /* Now get rid of the extra reference to the - temporary page we've been using. */ - if (PageSwapCache(page)) - delete_from_swap_cache(page); - __free_page(page); - #ifdef DO_PROC - stat_swap_force++; - #endif - } - - DPRINTK( "unswap: map[i=%lu]=%u nr_swap=%ld\n", - i, map[i], nr_swap_pages ); - swap_list_lock(); - swap_device_lock(stram_swap_info); - map[i] = SWAP_MAP_BAD; - if (stram_swap_info->lowest_bit == i) - stram_swap_info->lowest_bit++; - if (stram_swap_info->highest_bit == i) - stram_swap_info->highest_bit--; - --nr_swap_pages; - swap_device_unlock(stram_swap_info); - swap_list_unlock(); - } - - return 0; -} - -/* - * reserve a region in ST-RAM swap space for an allocation - */ -static void *get_stram_region( unsigned long n_pages ) -{ - unsigned short *map = stram_swap_info->swap_map; - unsigned long max = stram_swap_info->max; - unsigned long start, total_free, region_free; - int err; - void *ret = NULL; - - DPRINTK( "get_stram_region(n_pages=%lu)\n", n_pages ); - - down(&stram_swap_sem); - - /* disallow writing to the swap device now */ - stram_swap_info->flags = SWP_USED; - - /* find a region of n_pages pages in the swap space including as much free - * pages as possible (and excluding any already-reserved pages). */ - if (!(start = find_free_region( n_pages, &total_free, ®ion_free ))) - goto end; - DPRINTK( "get_stram_region: region starts at %lu, has %lu free pages\n", - start, region_free ); - - err = unswap_by_read(map, max, start, n_pages); - if (err) - goto end; - - ret = SWAP_ADDR(start); - end: - /* allow using swap device again */ - stram_swap_info->flags = SWP_WRITEOK; - up(&stram_swap_sem); - DPRINTK( "get_stram_region: returning %p\n", ret ); - return( ret ); -} - - -/* - * free a reserved region in ST-RAM swap space - */ -static void free_stram_region( unsigned long offset, unsigned long n_pages ) -{ - unsigned short *map = stram_swap_info->swap_map; - - DPRINTK( "free_stram_region(offset=%lu,n_pages=%lu)\n", offset, n_pages ); - - if (offset < 1 || offset + n_pages > stram_swap_info->max) { - printk( KERN_ERR "free_stram_region: Trying to free non-ST-RAM\n" ); - return; - } - - swap_list_lock(); - swap_device_lock(stram_swap_info); - /* un-reserve the freed pages */ - for( ; n_pages > 0; ++offset, --n_pages ) { - if (map[offset] != SWAP_MAP_BAD) - printk( KERN_ERR "free_stram_region: Swap page %lu was not " - "reserved\n", offset ); - map[offset] = 0; - } - - /* update swapping meta-data */ - if (offset < stram_swap_info->lowest_bit) - stram_swap_info->lowest_bit = offset; - if (offset+n_pages-1 > stram_swap_info->highest_bit) - stram_swap_info->highest_bit = offset+n_pages-1; - if (stram_swap_info->prio > swap_info[swap_list.next].prio) - swap_list.next = swap_list.head; - nr_swap_pages += n_pages; - swap_device_unlock(stram_swap_info); - swap_list_unlock(); -} - - -/* ------------------------------------------------------------------------ */ -/* Utility Functions for Swapping */ -/* ------------------------------------------------------------------------ */ - - -/* is addr in some of the allocated regions? */ -static int in_some_region(void *addr) -{ - BLOCK *p; - - for( p = alloc_list; p; p = p->next ) { - if (p->start <= addr && addr < p->start + p->size) - return( 1 ); - } - return( 0 ); -} - - -static unsigned long find_free_region(unsigned long n_pages, - unsigned long *total_free, - unsigned long *region_free) -{ - unsigned short *map = stram_swap_info->swap_map; - unsigned long max = stram_swap_info->max; - unsigned long head, tail, max_start; - long nfree, max_free; - - /* first scan the swap space for a suitable place for the allocation */ - head = 1; - max_start = 0; - max_free = -1; - *total_free = 0; - - start_over: - /* increment tail until final window size reached, and count free pages */ - nfree = 0; - for( tail = head; tail-head < n_pages && tail < max; ++tail ) { - if (map[tail] == SWAP_MAP_BAD) { - head = tail+1; - goto start_over; - } - if (!map[tail]) { - ++nfree; - ++*total_free; - } - } - if (tail-head < n_pages) - goto out; - if (nfree > max_free) { - max_start = head; - max_free = nfree; - if (max_free >= n_pages) - /* don't need more free pages... :-) */ - goto out; - } - - /* now shift the window and look for the area where as much pages as - * possible are free */ - while( tail < max ) { - nfree -= (map[head++] == 0); - if (map[tail] == SWAP_MAP_BAD) { - head = tail+1; - goto start_over; - } - if (!map[tail]) { - ++nfree; - ++*total_free; - } - ++tail; - if (nfree > max_free) { - max_start = head; - max_free = nfree; - if (max_free >= n_pages) - /* don't need more free pages... :-) */ - goto out; - } - } - - out: - if (max_free < 0) { - printk( KERN_NOTICE "get_stram_region: ST-RAM too full or fragmented " - "-- can't allocate %lu pages\n", n_pages ); - return( 0 ); - } - - *region_free = max_free; - return( max_start ); -} - - -/* setup parameters from command line */ -void __init stram_swap_setup(char *str, int *ints) -{ - if (ints[0] >= 1) - max_swap_size = ((ints[1] < 0 ? 0 : ints[1]) * 1024) & PAGE_MASK; -} - - -/* ------------------------------------------------------------------------ */ -/* ST-RAM device */ -/* ------------------------------------------------------------------------ */ - -static int refcnt; - -static void do_stram_request(request_queue_t *q) -{ - struct request *req; - - while ((req = elv_next_request(q)) != NULL) { - void *start = swap_start + (req->sector << 9); - unsigned long len = req->current_nr_sectors << 9; - if ((start + len) > swap_end) { - printk( KERN_ERR "stram: bad access beyond end of device: " - "block=%ld, count=%d\n", - req->sector, - req->current_nr_sectors ); - end_request(req, 0); - continue; - } - - if (req->cmd == READ) { - memcpy(req->buffer, start, len); -#ifdef DO_PROC - stat_swap_read += N_PAGES(len); -#endif - } - else { - memcpy(start, req->buffer, len); -#ifdef DO_PROC - stat_swap_write += N_PAGES(len); -#endif - } - end_request(req, 1); - } -} - - -static int stram_open( struct inode *inode, struct file *filp ) -{ - if (filp != MAGIC_FILE_P) { - printk( KERN_NOTICE "Only kernel can open ST-RAM device\n" ); - return( -EPERM ); - } - if (refcnt) - return( -EBUSY ); - ++refcnt; - return( 0 ); -} - -static int stram_release( struct inode *inode, struct file *filp ) -{ - if (filp != MAGIC_FILE_P) { - printk( KERN_NOTICE "Only kernel can close ST-RAM device\n" ); - return( -EPERM ); - } - if (refcnt > 0) - --refcnt; - return( 0 ); -} - - -static struct block_device_operations stram_fops = { - .open = stram_open, - .release = stram_release, -}; - -static struct gendisk *stram_disk; -static struct request_queue *stram_queue; -static DEFINE_SPINLOCK(stram_lock); - -int __init stram_device_init(void) -{ - if (!MACH_IS_ATARI) - /* no point in initializing this, I hope */ - return -ENXIO; - - if (!max_swap_size) - /* swapping not enabled */ - return -ENXIO; - stram_disk = alloc_disk(1); - if (!stram_disk) - return -ENOMEM; - - if (register_blkdev(STRAM_MAJOR, "stram")) { - put_disk(stram_disk); - return -ENXIO; - } - - stram_queue = blk_init_queue(do_stram_request, &stram_lock); - if (!stram_queue) { - unregister_blkdev(STRAM_MAJOR, "stram"); - put_disk(stram_disk); - return -ENOMEM; - } - - stram_disk->major = STRAM_MAJOR; - stram_disk->first_minor = STRAM_MINOR; - stram_disk->fops = &stram_fops; - stram_disk->queue = stram_queue; - sprintf(stram_disk->disk_name, "stram"); - set_capacity(stram_disk, (swap_end - swap_start)/512); - add_disk(stram_disk); - return 0; -} - - - -/* ------------------------------------------------------------------------ */ -/* Misc Utility Functions */ -/* ------------------------------------------------------------------------ */ - -/* reserve a range of pages */ -static void reserve_region(void *start, void *end) -{ - reserve_bootmem (virt_to_phys(start), end - start); -} - -#endif /* CONFIG_STRAM_SWAP */ - /* ------------------------------------------------------------------------ */ /* Region Management */ @@ -1173,50 +328,9 @@ int get_stram_list( char *buf ) { int len = 0; BLOCK *p; -#ifdef CONFIG_STRAM_SWAP - int i; - unsigned short *map = stram_swap_info->swap_map; - unsigned long max = stram_swap_info->max; - unsigned free = 0, used = 0, rsvd = 0; -#endif -#ifdef CONFIG_STRAM_SWAP - if (max_swap_size) { - for( i = 1; i < max; ++i ) { - if (!map[i]) - ++free; - else if (map[i] == SWAP_MAP_BAD) - ++rsvd; - else - ++used; - } - PRINT_PROC( - "Total ST-RAM: %8u kB\n" - "Total ST-RAM swap: %8lu kB\n" - "Free swap: %8u kB\n" - "Used swap: %8u kB\n" - "Allocated swap: %8u kB\n" - "Swap Reads: %8u\n" - "Swap Writes: %8u\n" - "Swap Forced Reads: %8u\n", - (stram_end - stram_start) >> 10, - (max-1) << (PAGE_SHIFT-10), - free << (PAGE_SHIFT-10), - used << (PAGE_SHIFT-10), - rsvd << (PAGE_SHIFT-10), - stat_swap_read, - stat_swap_write, - stat_swap_force ); - } - else { -#endif - PRINT_PROC( "ST-RAM swapping disabled\n" ); - PRINT_PROC("Total ST-RAM: %8u kB\n", + PRINT_PROC("Total ST-RAM: %8u kB\n", (stram_end - stram_start) >> 10); -#ifdef CONFIG_STRAM_SWAP - } -#endif - PRINT_PROC( "Allocated regions:\n" ); for( p = alloc_list; p; p = p->next ) { if (len + 50 >= PAGE_SIZE) @@ -1227,8 +341,6 @@ int get_stram_list( char *buf ) p->owner); if (p->flags & BLOCK_GFP) PRINT_PROC( "page-alloced)\n" ); - else if (p->flags & BLOCK_INSWAP) - PRINT_PROC( "in swap)\n" ); else PRINT_PROC( "??)\n" ); } diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c index 5dcb3fa35ea..fe2383e36b0 100644 --- a/arch/m68k/mm/kmap.c +++ b/arch/m68k/mm/kmap.c @@ -201,7 +201,7 @@ void *__ioremap(unsigned long physaddr, unsigned long size, int cacheflag) virtaddr += PTRTREESIZE; size -= PTRTREESIZE; } else { - pte_dir = pte_alloc_kernel(&init_mm, pmd_dir, virtaddr); + pte_dir = pte_alloc_kernel(pmd_dir, virtaddr); if (!pte_dir) { printk("ioremap: no mem for pte_dir\n"); return NULL; diff --git a/arch/m68k/sun3x/dvma.c b/arch/m68k/sun3x/dvma.c index 32e55adfeb8..117481e8630 100644 --- a/arch/m68k/sun3x/dvma.c +++ b/arch/m68k/sun3x/dvma.c @@ -116,7 +116,7 @@ inline int dvma_map_cpu(unsigned long kaddr, pte_t *pte; unsigned long end3; - if((pte = pte_alloc_kernel(&init_mm, pmd, vaddr)) == NULL) { + if((pte = pte_alloc_kernel(pmd, vaddr)) == NULL) { ret = -ENOMEM; goto out; } diff --git a/arch/mips/kernel/irixelf.c b/arch/mips/kernel/irixelf.c index 99262fe6456..7ce34d4aa22 100644 --- a/arch/mips/kernel/irixelf.c +++ b/arch/mips/kernel/irixelf.c @@ -697,7 +697,6 @@ static int load_irix_binary(struct linux_binprm * bprm, struct pt_regs * regs) /* Do this so that we can load the interpreter, if need be. We will * change some of these later. */ - set_mm_counter(current->mm, rss, 0); setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT); current->mm->start_stack = bprm->p; diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c index 9c44ca70bef..3101d1db559 100644 --- a/arch/mips/mm/ioremap.c +++ b/arch/mips/mm/ioremap.c @@ -55,7 +55,7 @@ static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, if (address >= end) BUG(); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, flags); @@ -77,7 +77,6 @@ static int remap_area_pages(unsigned long address, phys_t phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pud_t *pud; pmd_t *pmd; @@ -96,7 +95,6 @@ static int remap_area_pages(unsigned long address, phys_t phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return error; } diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index e15f09eaed1..a065349aee3 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -270,7 +270,6 @@ void flush_dcache_page(struct page *page) unsigned long offset; unsigned long addr; pgoff_t pgoff; - pte_t *pte; unsigned long pfn = page_to_pfn(page); @@ -301,21 +300,16 @@ void flush_dcache_page(struct page *page) * taking a page fault if the pte doesn't exist. * This is just for speed. If the page translation * isn't there, there's no point exciting the - * nadtlb handler into a nullification frenzy */ - - - if(!(pte = translation_exists(mpnt, addr))) - continue; - - /* make sure we really have this page: the private + * nadtlb handler into a nullification frenzy. + * + * Make sure we really have this page: the private * mappings may cover this area but have COW'd this - * particular page */ - if(pte_pfn(*pte) != pfn) - continue; - - __flush_cache_page(mpnt, addr); - - break; + * particular page. + */ + if (translation_exists(mpnt, addr, pfn)) { + __flush_cache_page(mpnt, addr); + break; + } } flush_dcache_mmap_unlock(mapping); } diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index ae6213d7167..f94a02ef3d9 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -114,7 +114,7 @@ static inline int map_pmd_uncached(pmd_t * pmd, unsigned long vaddr, if (end > PGDIR_SIZE) end = PGDIR_SIZE; do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, vaddr); + pte_t * pte = pte_alloc_kernel(pmd, vaddr); if (!pte) return -ENOMEM; if (map_pte_uncached(pte, orig_vaddr, end - vaddr, paddr_ptr)) diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 2886ad70db4..29b998e430e 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -505,7 +505,9 @@ void show_mem(void) for (j = node_start_pfn(i); j < node_end_pfn(i); j++) { struct page *p; + unsigned long flags; + pgdat_resize_lock(NODE_DATA(i), &flags); p = nid_page_nr(i, j) - node_start_pfn(i); total++; @@ -517,6 +519,7 @@ void show_mem(void) free++; else shared += page_count(p) - 1; + pgdat_resize_unlock(NODE_DATA(i), &flags); } } #endif diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index f2df502cdae..5c7a1b3b932 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -52,7 +52,7 @@ static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned lo if (address >= end) BUG(); do { - pte_t * pte = pte_alloc_kernel(NULL, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, flags); @@ -75,10 +75,9 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pmd_t *pmd; - pmd = pmd_alloc(dir, address); + pmd = pmd_alloc(&init_mm, dir, address); error = -ENOMEM; if (!pmd) break; @@ -89,7 +88,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return error; } diff --git a/arch/ppc/kernel/dma-mapping.c b/arch/ppc/kernel/dma-mapping.c index 0f710d2baec..685fd0defe2 100644 --- a/arch/ppc/kernel/dma-mapping.c +++ b/arch/ppc/kernel/dma-mapping.c @@ -335,8 +335,6 @@ static int __init dma_alloc_init(void) pte_t *pte; int ret = 0; - spin_lock(&init_mm.page_table_lock); - do { pgd = pgd_offset(&init_mm, CONSISTENT_BASE); pmd = pmd_alloc(&init_mm, pgd, CONSISTENT_BASE); @@ -347,7 +345,7 @@ static int __init dma_alloc_init(void) } WARN_ON(!pmd_none(*pmd)); - pte = pte_alloc_kernel(&init_mm, pmd, CONSISTENT_BASE); + pte = pte_alloc_kernel(pmd, CONSISTENT_BASE); if (!pte) { printk(KERN_ERR "%s: no pte tables\n", __func__); ret = -ENOMEM; @@ -357,8 +355,6 @@ static int __init dma_alloc_init(void) consistent_pte = pte; } while (0); - spin_unlock(&init_mm.page_table_lock); - return ret; } diff --git a/arch/ppc/mm/4xx_mmu.c b/arch/ppc/mm/4xx_mmu.c index b7bcbc232f3..4d006aa1a0d 100644 --- a/arch/ppc/mm/4xx_mmu.c +++ b/arch/ppc/mm/4xx_mmu.c @@ -110,13 +110,11 @@ unsigned long __init mmu_mapin_ram(void) pmd_t *pmdp; unsigned long val = p | _PMD_SIZE_16M | _PAGE_HWEXEC | _PAGE_HWWRITE; - spin_lock(&init_mm.page_table_lock); pmdp = pmd_offset(pgd_offset_k(v), v); pmd_val(*pmdp++) = val; pmd_val(*pmdp++) = val; pmd_val(*pmdp++) = val; pmd_val(*pmdp++) = val; - spin_unlock(&init_mm.page_table_lock); v += LARGE_PAGE_SIZE_16M; p += LARGE_PAGE_SIZE_16M; @@ -127,10 +125,8 @@ unsigned long __init mmu_mapin_ram(void) pmd_t *pmdp; unsigned long val = p | _PMD_SIZE_4M | _PAGE_HWEXEC | _PAGE_HWWRITE; - spin_lock(&init_mm.page_table_lock); pmdp = pmd_offset(pgd_offset_k(v), v); pmd_val(*pmdp) = val; - spin_unlock(&init_mm.page_table_lock); v += LARGE_PAGE_SIZE_4M; p += LARGE_PAGE_SIZE_4M; diff --git a/arch/ppc/mm/pgtable.c b/arch/ppc/mm/pgtable.c index 43505b1fc5d..6ea9185fd12 100644 --- a/arch/ppc/mm/pgtable.c +++ b/arch/ppc/mm/pgtable.c @@ -280,18 +280,16 @@ map_page(unsigned long va, phys_addr_t pa, int flags) pte_t *pg; int err = -ENOMEM; - spin_lock(&init_mm.page_table_lock); /* Use upper 10 bits of VA to index the first level map */ pd = pmd_offset(pgd_offset_k(va), va); /* Use middle 10 bits of VA to index the second-level map */ - pg = pte_alloc_kernel(&init_mm, pd, va); + pg = pte_alloc_kernel(pd, va); if (pg != 0) { err = 0; set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT, __pgprot(flags))); if (mem_init_done) flush_HPTE(0, va, pmd_val(*pd)); } - spin_unlock(&init_mm.page_table_lock); return err; } diff --git a/arch/ppc64/kernel/vdso.c b/arch/ppc64/kernel/vdso.c index efa985f05ac..4aacf521e3e 100644 --- a/arch/ppc64/kernel/vdso.c +++ b/arch/ppc64/kernel/vdso.c @@ -176,13 +176,13 @@ static struct page * vdso_vma_nopage(struct vm_area_struct * vma, return NOPAGE_SIGBUS; /* - * Last page is systemcfg, special handling here, no get_page() a - * this is a reserved page + * Last page is systemcfg. */ if ((vma->vm_end - address) <= PAGE_SIZE) - return virt_to_page(systemcfg); + pg = virt_to_page(systemcfg); + else + pg = virt_to_page(vbase + offset); - pg = virt_to_page(vbase + offset); get_page(pg); DBG(" ->page count: %d\n", page_count(pg)); @@ -259,7 +259,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int executable_stack) * gettimeofday will be totally dead. It's fine to use that for setting * breakpoints in the vDSO code pages though */ - vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; + vma->vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | VM_RESERVED; vma->vm_flags |= mm->def_flags; vma->vm_page_prot = protection_map[vma->vm_flags & 0x7]; vma->vm_ops = &vdso_vmops; @@ -603,6 +603,8 @@ void __init vdso_init(void) ClearPageReserved(pg); get_page(pg); } + + get_page(virt_to_page(systemcfg)); } int in_gate_area_no_task(unsigned long addr) diff --git a/arch/ppc64/mm/imalloc.c b/arch/ppc64/mm/imalloc.c index c65b87b9275..f4ca29cf536 100644 --- a/arch/ppc64/mm/imalloc.c +++ b/arch/ppc64/mm/imalloc.c @@ -300,12 +300,7 @@ void im_free(void * addr) for (p = &imlist ; (tmp = *p) ; p = &tmp->next) { if (tmp->addr == addr) { *p = tmp->next; - - /* XXX: do we need the lock? */ - spin_lock(&init_mm.page_table_lock); unmap_vm_area(tmp); - spin_unlock(&init_mm.page_table_lock); - kfree(tmp); up(&imlist_sem); return; diff --git a/arch/ppc64/mm/init.c b/arch/ppc64/mm/init.c index be64b157afc..e2bd7776622 100644 --- a/arch/ppc64/mm/init.c +++ b/arch/ppc64/mm/init.c @@ -104,6 +104,8 @@ void show_mem(void) show_free_areas(); printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); for_each_pgdat(pgdat) { + unsigned long flags; + pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; i++) { page = pgdat_page_nr(pgdat, i); total++; @@ -114,6 +116,7 @@ void show_mem(void) else if (page_count(page)) shared += page_count(page) - 1; } + pgdat_resize_unlock(pgdat, &flags); } printk("%ld pages of RAM\n", total); printk("%ld reserved pages\n", reserved); @@ -155,7 +158,6 @@ static int map_io_page(unsigned long ea, unsigned long pa, int flags) unsigned long vsid; if (mem_init_done) { - spin_lock(&init_mm.page_table_lock); pgdp = pgd_offset_k(ea); pudp = pud_alloc(&init_mm, pgdp, ea); if (!pudp) @@ -163,12 +165,11 @@ static int map_io_page(unsigned long ea, unsigned long pa, int flags) pmdp = pmd_alloc(&init_mm, pudp, ea); if (!pmdp) return -ENOMEM; - ptep = pte_alloc_kernel(&init_mm, pmdp, ea); + ptep = pte_alloc_kernel(pmdp, ea); if (!ptep) return -ENOMEM; set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT, __pgprot(flags))); - spin_unlock(&init_mm.page_table_lock); } else { unsigned long va, vpn, hash, hpteg; @@ -649,11 +650,14 @@ void __init mem_init(void) #endif for_each_pgdat(pgdat) { + unsigned long flags; + pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; i++) { page = pgdat_page_nr(pgdat, i); if (PageReserved(page)) reservedpages++; } + pgdat_resize_unlock(pgdat, &flags); } codesize = (unsigned long)&_etext - (unsigned long)&_stext; @@ -867,3 +871,80 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long addr, return vma_prot; } EXPORT_SYMBOL(phys_mem_access_prot); + +#ifdef CONFIG_MEMORY_HOTPLUG + +void online_page(struct page *page) +{ + ClearPageReserved(page); + free_cold_page(page); + totalram_pages++; + num_physpages++; +} + +/* + * This works only for the non-NUMA case. Later, we'll need a lookup + * to convert from real physical addresses to nid, that doesn't use + * pfn_to_nid(). + */ +int __devinit add_memory(u64 start, u64 size) +{ + struct pglist_data *pgdata = NODE_DATA(0); + struct zone *zone; + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long nr_pages = size >> PAGE_SHIFT; + + /* this should work for most non-highmem platforms */ + zone = pgdata->node_zones; + + return __add_pages(zone, start_pfn, nr_pages); + + return 0; +} + +/* + * First pass at this code will check to determine if the remove + * request is within the RMO. Do not allow removal within the RMO. + */ +int __devinit remove_memory(u64 start, u64 size) +{ + struct zone *zone; + unsigned long start_pfn, end_pfn, nr_pages; + + start_pfn = start >> PAGE_SHIFT; + nr_pages = size >> PAGE_SHIFT; + end_pfn = start_pfn + nr_pages; + + printk("%s(): Attempting to remove memoy in range " + "%lx to %lx\n", __func__, start, start+size); + /* + * check for range within RMO + */ + zone = page_zone(pfn_to_page(start_pfn)); + + printk("%s(): memory will be removed from " + "the %s zone\n", __func__, zone->name); + + /* + * not handling removing memory ranges that + * overlap multiple zones yet + */ + if (end_pfn > (zone->zone_start_pfn + zone->spanned_pages)) + goto overlap; + + /* make sure it is NOT in RMO */ + if ((start < lmb.rmo_size) || ((start+size) < lmb.rmo_size)) { + printk("%s(): range to be removed must NOT be in RMO!\n", + __func__); + goto in_rmo; + } + + return __remove_pages(zone, start_pfn, nr_pages); + +overlap: + printk("%s(): memory range to be removed overlaps " + "multiple zones!!!\n", __func__); +in_rmo: + return -1; +} +#endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/s390/mm/ioremap.c b/arch/s390/mm/ioremap.c index c6c39d868bc..0f6e9ecbefe 100644 --- a/arch/s390/mm/ioremap.c +++ b/arch/s390/mm/ioremap.c @@ -58,7 +58,7 @@ static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned lo if (address >= end) BUG(); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, flags); @@ -80,7 +80,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pmd_t *pmd; pmd = pmd_alloc(&init_mm, dir, address); @@ -94,7 +93,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return 0; } diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 7abba2161da..775f86cd3fe 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -194,10 +194,13 @@ asmlinkage int __do_page_fault(struct pt_regs *regs, unsigned long writeaccess, unsigned long address) { unsigned long addrmax = P4SEG; - pgd_t *dir; + pgd_t *pgd; pmd_t *pmd; pte_t *pte; pte_t entry; + struct mm_struct *mm; + spinlock_t *ptl; + int ret = 1; #ifdef CONFIG_SH_KGDB if (kgdb_nofault && kgdb_bus_err_hook) @@ -208,28 +211,28 @@ asmlinkage int __do_page_fault(struct pt_regs *regs, unsigned long writeaccess, addrmax = P4SEG_STORE_QUE + 0x04000000; #endif - if (address >= P3SEG && address < addrmax) - dir = pgd_offset_k(address); - else if (address >= TASK_SIZE) + if (address >= P3SEG && address < addrmax) { + pgd = pgd_offset_k(address); + mm = NULL; + } else if (address >= TASK_SIZE) return 1; - else if (!current->mm) + else if (!(mm = current->mm)) return 1; else - dir = pgd_offset(current->mm, address); + pgd = pgd_offset(mm, address); - pmd = pmd_offset(dir, address); - if (pmd_none(*pmd)) - return 1; - if (pmd_bad(*pmd)) { - pmd_ERROR(*pmd); - pmd_clear(pmd); + pmd = pmd_offset(pgd, address); + if (pmd_none_or_clear_bad(pmd)) return 1; - } - pte = pte_offset_kernel(pmd, address); + if (mm) + pte = pte_offset_map_lock(mm, pmd, address, &ptl); + else + pte = pte_offset_kernel(pmd, address); + entry = *pte; if (pte_none(entry) || pte_not_present(entry) || (writeaccess && !pte_write(entry))) - return 1; + goto unlock; if (writeaccess) entry = pte_mkdirty(entry); @@ -251,8 +254,11 @@ asmlinkage int __do_page_fault(struct pt_regs *regs, unsigned long writeaccess, set_pte(pte, entry); update_mmu_cache(NULL, address, entry); - - return 0; + ret = 0; +unlock: + if (mm) + pte_unmap_unlock(pte, ptl); + return ret; } void flush_tlb_page(struct vm_area_struct *vma, unsigned long page) diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index 95bb1a6c606..6b7a7688c98 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -54,8 +54,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) return pte; } -#define mk_pte_huge(entry) do { pte_val(entry) |= _PAGE_SZHUGE; } while (0) - void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c index 9f490c2742f..e794e27a72f 100644 --- a/arch/sh/mm/ioremap.c +++ b/arch/sh/mm/ioremap.c @@ -57,7 +57,7 @@ static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, if (address >= end) BUG(); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, flags); @@ -79,7 +79,6 @@ int remap_area_pages(unsigned long address, unsigned long phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pmd_t *pmd; pmd = pmd_alloc(&init_mm, dir, address); @@ -93,7 +92,6 @@ int remap_area_pages(unsigned long address, unsigned long phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return error; } diff --git a/arch/sh64/mm/cache.c b/arch/sh64/mm/cache.c index 3b87e25ea77..c0c1b21350d 100644 --- a/arch/sh64/mm/cache.c +++ b/arch/sh64/mm/cache.c @@ -584,32 +584,36 @@ static void sh64_dcache_purge_phy_page(unsigned long paddr) } } -static void sh64_dcache_purge_user_page(struct mm_struct *mm, unsigned long eaddr) +static void sh64_dcache_purge_user_pages(struct mm_struct *mm, + unsigned long addr, unsigned long end) { pgd_t *pgd; pmd_t *pmd; pte_t *pte; pte_t entry; + spinlock_t *ptl; unsigned long paddr; - /* NOTE : all the callers of this have mm->page_table_lock held, so the - following page table traversal is safe even on SMP/pre-emptible. */ - - if (!mm) return; /* No way to find physical address of page */ - pgd = pgd_offset(mm, eaddr); - if (pgd_bad(*pgd)) return; - - pmd = pmd_offset(pgd, eaddr); - if (pmd_none(*pmd) || pmd_bad(*pmd)) return; - - pte = pte_offset_kernel(pmd, eaddr); - entry = *pte; - if (pte_none(entry) || !pte_present(entry)) return; - - paddr = pte_val(entry) & PAGE_MASK; - - sh64_dcache_purge_coloured_phy_page(paddr, eaddr); - + if (!mm) + return; /* No way to find physical address of page */ + + pgd = pgd_offset(mm, addr); + if (pgd_bad(*pgd)) + return; + + pmd = pmd_offset(pgd, addr); + if (pmd_none(*pmd) || pmd_bad(*pmd)) + return; + + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + do { + entry = *pte; + if (pte_none(entry) || !pte_present(entry)) + continue; + paddr = pte_val(entry) & PAGE_MASK; + sh64_dcache_purge_coloured_phy_page(paddr, addr); + } while (pte++, addr += PAGE_SIZE, addr != end); + pte_unmap_unlock(pte - 1, ptl); } /****************************************************************************/ @@ -668,7 +672,7 @@ static void sh64_dcache_purge_user_range(struct mm_struct *mm, int n_pages; n_pages = ((end - start) >> PAGE_SHIFT); - if (n_pages >= 64) { + if (n_pages >= 64 || ((start ^ (end - 1)) & PMD_MASK)) { #if 1 sh64_dcache_purge_all(); #else @@ -707,20 +711,10 @@ static void sh64_dcache_purge_user_range(struct mm_struct *mm, } #endif } else { - /* 'Small' range */ - unsigned long aligned_start; - unsigned long eaddr; - unsigned long last_page_start; - - aligned_start = start & PAGE_MASK; - /* 'end' is 1 byte beyond the end of the range */ - last_page_start = (end - 1) & PAGE_MASK; - - eaddr = aligned_start; - while (eaddr <= last_page_start) { - sh64_dcache_purge_user_page(mm, eaddr); - eaddr += PAGE_SIZE; - } + /* Small range, covered by a single page table page */ + start &= PAGE_MASK; /* should already be so */ + end = PAGE_ALIGN(end); /* should already be so */ + sh64_dcache_purge_user_pages(mm, start, end); } return; } @@ -880,9 +874,7 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, addresses from the user address space specified by mm, after writing back any dirty data. - Note(1), 'end' is 1 byte beyond the end of the range to flush. - - Note(2), this is called with mm->page_table_lock held.*/ + Note, 'end' is 1 byte beyond the end of the range to flush. */ sh64_dcache_purge_user_range(mm, start, end); sh64_icache_inv_user_page_range(mm, start, end); @@ -898,7 +890,7 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long eaddr, unsigned the I-cache must be searched too in case the page in question is both writable and being executed from (e.g. stack trampolines.) - Note(1), this is called with mm->page_table_lock held. + Note, this is called with pte lock held. */ sh64_dcache_purge_phy_page(pfn << PAGE_SHIFT); diff --git a/arch/sh64/mm/hugetlbpage.c b/arch/sh64/mm/hugetlbpage.c index dcd9c8a8baf..ed6a505b3ee 100644 --- a/arch/sh64/mm/hugetlbpage.c +++ b/arch/sh64/mm/hugetlbpage.c @@ -54,41 +54,31 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) return pte; } -#define mk_pte_huge(entry) do { pte_val(entry) |= _PAGE_SZHUGE; } while (0) - -static void set_huge_pte(struct mm_struct *mm, struct vm_area_struct *vma, - struct page *page, pte_t * page_table, int write_access) +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) { - unsigned long i; - pte_t entry; - - add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE); - - if (write_access) - entry = pte_mkwrite(pte_mkdirty(mk_pte(page, - vma->vm_page_prot))); - else - entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot)); - entry = pte_mkyoung(entry); - mk_pte_huge(entry); + int i; for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - set_pte(page_table, entry); - page_table++; - + set_pte_at(mm, addr, ptep, entry); + ptep++; + addr += PAGE_SIZE; pte_val(entry) += PAGE_SIZE; } } -pte_t huge_ptep_get_and_clear(pte_t *ptep) +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { pte_t entry; + int i; entry = *ptep; for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - pte_clear(pte); - pte++; + pte_clear(mm, addr, ptep); + addr += PAGE_SIZE; + ptep++; } return entry; @@ -106,79 +96,6 @@ int is_aligned_hugepage_range(unsigned long addr, unsigned long len) return 0; } -int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma) -{ - pte_t *src_pte, *dst_pte, entry; - struct page *ptepage; - unsigned long addr = vma->vm_start; - unsigned long end = vma->vm_end; - int i; - - while (addr < end) { - dst_pte = huge_pte_alloc(dst, addr); - if (!dst_pte) - goto nomem; - src_pte = huge_pte_offset(src, addr); - BUG_ON(!src_pte || pte_none(*src_pte)); - entry = *src_pte; - ptepage = pte_page(entry); - get_page(ptepage); - for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - set_pte(dst_pte, entry); - pte_val(entry) += PAGE_SIZE; - dst_pte++; - } - add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE); - addr += HPAGE_SIZE; - } - return 0; - -nomem: - return -ENOMEM; -} - -int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, - struct page **pages, struct vm_area_struct **vmas, - unsigned long *position, int *length, int i) -{ - unsigned long vaddr = *position; - int remainder = *length; - - WARN_ON(!is_vm_hugetlb_page(vma)); - - while (vaddr < vma->vm_end && remainder) { - if (pages) { - pte_t *pte; - struct page *page; - - pte = huge_pte_offset(mm, vaddr); - - /* hugetlb should be locked, and hence, prefaulted */ - BUG_ON(!pte || pte_none(*pte)); - - page = pte_page(*pte); - - WARN_ON(!PageCompound(page)); - - get_page(page); - pages[i] = page; - } - - if (vmas) - vmas[i] = vma; - - vaddr += PAGE_SIZE; - --remainder; - ++i; - } - - *length = remainder; - *position = vaddr; - - return i; -} - struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) { @@ -195,84 +112,3 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, { return NULL; } - -void unmap_hugepage_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - struct mm_struct *mm = vma->vm_mm; - unsigned long address; - pte_t *pte; - struct page *page; - int i; - - BUG_ON(start & (HPAGE_SIZE - 1)); - BUG_ON(end & (HPAGE_SIZE - 1)); - - for (address = start; address < end; address += HPAGE_SIZE) { - pte = huge_pte_offset(mm, address); - BUG_ON(!pte); - if (pte_none(*pte)) - continue; - page = pte_page(*pte); - put_page(page); - for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - pte_clear(mm, address+(i*PAGE_SIZE), pte); - pte++; - } - } - add_mm_counter(mm, rss, -((end - start) >> PAGE_SHIFT)); - flush_tlb_range(vma, start, end); -} - -int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma) -{ - struct mm_struct *mm = current->mm; - unsigned long addr; - int ret = 0; - - BUG_ON(vma->vm_start & ~HPAGE_MASK); - BUG_ON(vma->vm_end & ~HPAGE_MASK); - - spin_lock(&mm->page_table_lock); - for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) { - unsigned long idx; - pte_t *pte = huge_pte_alloc(mm, addr); - struct page *page; - - if (!pte) { - ret = -ENOMEM; - goto out; - } - if (!pte_none(*pte)) - continue; - - idx = ((addr - vma->vm_start) >> HPAGE_SHIFT) - + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); - page = find_get_page(mapping, idx); - if (!page) { - /* charge the fs quota first */ - if (hugetlb_get_quota(mapping)) { - ret = -ENOMEM; - goto out; - } - page = alloc_huge_page(); - if (!page) { - hugetlb_put_quota(mapping); - ret = -ENOMEM; - goto out; - } - ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC); - if (! ret) { - unlock_page(page); - } else { - hugetlb_put_quota(mapping); - free_huge_page(page); - goto out; - } - } - set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE); - } -out: - spin_unlock(&mm->page_table_lock); - return ret; -} diff --git a/arch/sh64/mm/ioremap.c b/arch/sh64/mm/ioremap.c index f4003da556b..fb1866fa2c9 100644 --- a/arch/sh64/mm/ioremap.c +++ b/arch/sh64/mm/ioremap.c @@ -79,7 +79,7 @@ static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned lo BUG(); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, flags); @@ -101,7 +101,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pmd_t *pmd = pmd_alloc(&init_mm, dir, address); error = -ENOMEM; @@ -115,7 +114,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; dir++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return 0; } diff --git a/arch/sparc/mm/generic.c b/arch/sparc/mm/generic.c index 20ccb957fb7..9604893ffdb 100644 --- a/arch/sparc/mm/generic.c +++ b/arch/sparc/mm/generic.c @@ -73,14 +73,16 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, int space = GET_IOSPACE(pfn); unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; + /* See comment in mm/memory.c remap_pfn_range */ + vma->vm_flags |= VM_IO | VM_RESERVED; + prot = __pgprot(pg_iobits); offset -= from; dir = pgd_offset(mm, from); flush_cache_range(vma, beg, end); - spin_lock(&mm->page_table_lock); while (from < end) { - pmd_t *pmd = pmd_alloc(current->mm, dir, from); + pmd_t *pmd = pmd_alloc(mm, dir, from); error = -ENOMEM; if (!pmd) break; @@ -90,7 +92,6 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, from = (from + PGDIR_SIZE) & PGDIR_MASK; dir++; } - spin_unlock(&mm->page_table_lock); flush_tlb_range(vma, beg, end); return error; diff --git a/arch/sparc64/kernel/binfmt_aout32.c b/arch/sparc64/kernel/binfmt_aout32.c index b2854ef221d..edf52d06b28 100644 --- a/arch/sparc64/kernel/binfmt_aout32.c +++ b/arch/sparc64/kernel/binfmt_aout32.c @@ -241,7 +241,6 @@ static int load_aout32_binary(struct linux_binprm * bprm, struct pt_regs * regs) current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - set_mm_counter(current->mm, rss, 0); current->mm->mmap = NULL; compute_creds(bprm); current->flags &= ~PF_FORKNOEXEC; diff --git a/arch/sparc64/mm/generic.c b/arch/sparc64/mm/generic.c index c954d91f01d..112c316e7cd 100644 --- a/arch/sparc64/mm/generic.c +++ b/arch/sparc64/mm/generic.c @@ -127,14 +127,16 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, int space = GET_IOSPACE(pfn); unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; + /* See comment in mm/memory.c remap_pfn_range */ + vma->vm_flags |= VM_IO | VM_RESERVED; + prot = __pgprot(pg_iobits); offset -= from; dir = pgd_offset(mm, from); flush_cache_range(vma, beg, end); - spin_lock(&mm->page_table_lock); while (from < end) { - pud_t *pud = pud_alloc(current->mm, dir, from); + pud_t *pud = pud_alloc(mm, dir, from); error = -ENOMEM; if (!pud) break; @@ -144,8 +146,7 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, from = (from + PGDIR_SIZE) & PGDIR_MASK; dir++; } - flush_tlb_range(vma, beg, end); - spin_unlock(&mm->page_table_lock); + flush_tlb_range(vma, beg, end); return error; } diff --git a/arch/sparc64/mm/tlb.c b/arch/sparc64/mm/tlb.c index 90ca99d0b89..8b104be4662 100644 --- a/arch/sparc64/mm/tlb.c +++ b/arch/sparc64/mm/tlb.c @@ -18,8 +18,7 @@ /* Heavily inspired by the ppc64 code. */ -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers) = - { NULL, 0, 0, 0, 0, 0, { 0 }, { NULL }, }; +DEFINE_PER_CPU(struct mmu_gather, mmu_gathers) = { 0, }; void flush_tlb_pending(void) { @@ -72,7 +71,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t no_cache_flush: - if (mp->tlb_frozen) + if (mp->fullmm) return; nr = mp->tlb_nr; @@ -97,7 +96,7 @@ void flush_tlb_pgtables(struct mm_struct *mm, unsigned long start, unsigned long unsigned long nr = mp->tlb_nr; long s = start, e = end, vpte_base; - if (mp->tlb_frozen) + if (mp->fullmm) return; /* If start is greater than end, that is a real problem. */ diff --git a/arch/um/include/tlb.h b/arch/um/include/tlb.h index 45d7da6c3b2..8efc1e0f1b8 100644 --- a/arch/um/include/tlb.h +++ b/arch/um/include/tlb.h @@ -34,7 +34,6 @@ struct host_vm_op { } u; }; -extern void mprotect_kernel_vm(int w); extern void force_flush_all(void); extern void fix_range_common(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr, int force, diff --git a/arch/um/kernel/process_kern.c b/arch/um/kernel/process_kern.c index 0d73ceeece7..34b54a3e213 100644 --- a/arch/um/kernel/process_kern.c +++ b/arch/um/kernel/process_kern.c @@ -222,6 +222,7 @@ void *um_virt_to_phys(struct task_struct *task, unsigned long addr, pud_t *pud; pmd_t *pmd; pte_t *pte; + pte_t ptent; if(task->mm == NULL) return(ERR_PTR(-EINVAL)); @@ -238,12 +239,13 @@ void *um_virt_to_phys(struct task_struct *task, unsigned long addr, return(ERR_PTR(-EINVAL)); pte = pte_offset_kernel(pmd, addr); - if(!pte_present(*pte)) + ptent = *pte; + if(!pte_present(ptent)) return(ERR_PTR(-EINVAL)); if(pte_out != NULL) - *pte_out = *pte; - return((void *) (pte_val(*pte) & PAGE_MASK) + (addr & ~PAGE_MASK)); + *pte_out = ptent; + return((void *) (pte_val(ptent) & PAGE_MASK) + (addr & ~PAGE_MASK)); } char *current_cmd(void) diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c index 240143b616a..9e5e39cea82 100644 --- a/arch/um/kernel/skas/mmu.c +++ b/arch/um/kernel/skas/mmu.c @@ -28,7 +28,6 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc, pmd_t *pmd; pte_t *pte; - spin_lock(&mm->page_table_lock); pgd = pgd_offset(mm, proc); pud = pud_alloc(mm, pgd, proc); if (!pud) @@ -63,7 +62,6 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc, *pte = mk_pte(virt_to_page(kernel), __pgprot(_PAGE_PRESENT)); *pte = pte_mkexec(*pte); *pte = pte_wrprotect(*pte); - spin_unlock(&mm->page_table_lock); return(0); out_pmd: @@ -71,7 +69,6 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc, out_pte: pmd_free(pmd); out: - spin_unlock(&mm->page_table_lock); return(-ENOMEM); } @@ -147,6 +144,7 @@ void destroy_context_skas(struct mm_struct *mm) if(!proc_mm || !ptrace_faultinfo){ free_page(mmu->id.stack); + pte_lock_deinit(virt_to_page(mmu->last_page_table)); pte_free_kernel((pte_t *) mmu->last_page_table); dec_page_state(nr_page_table_pages); #ifdef CONFIG_3_LEVEL_PGTABLES diff --git a/arch/um/kernel/tt/tlb.c b/arch/um/kernel/tt/tlb.c index f1d85dbb45b..ae6217c8613 100644 --- a/arch/um/kernel/tt/tlb.c +++ b/arch/um/kernel/tt/tlb.c @@ -74,42 +74,6 @@ void flush_tlb_kernel_range_tt(unsigned long start, unsigned long end) atomic_inc(&vmchange_seq); } -static void protect_vm_page(unsigned long addr, int w, int must_succeed) -{ - int err; - - err = protect_memory(addr, PAGE_SIZE, 1, w, 1, must_succeed); - if(err == 0) return; - else if((err == -EFAULT) || (err == -ENOMEM)){ - flush_tlb_kernel_range(addr, addr + PAGE_SIZE); - protect_vm_page(addr, w, 1); - } - else panic("protect_vm_page : protect failed, errno = %d\n", err); -} - -void mprotect_kernel_vm(int w) -{ - struct mm_struct *mm; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - unsigned long addr; - - mm = &init_mm; - for(addr = start_vm; addr < end_vm;){ - pgd = pgd_offset(mm, addr); - pud = pud_offset(pgd, addr); - pmd = pmd_offset(pud, addr); - if(pmd_present(*pmd)){ - pte = pte_offset_kernel(pmd, addr); - if(pte_present(*pte)) protect_vm_page(addr, w, 0); - addr += PAGE_SIZE; - } - else addr += PMD_SIZE; - } -} - void flush_tlb_kernel_vm_tt(void) { flush_tlb_kernel_range(start_vm, end_vm); diff --git a/arch/x86_64/ia32/ia32_aout.c b/arch/x86_64/ia32/ia32_aout.c index 3e6780fa018..93c60f4aa47 100644 --- a/arch/x86_64/ia32/ia32_aout.c +++ b/arch/x86_64/ia32/ia32_aout.c @@ -314,7 +314,6 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) current->mm->free_area_cache = TASK_UNMAPPED_BASE; current->mm->cached_hole_size = 0; - set_mm_counter(current->mm, rss, 0); current->mm->mmap = NULL; compute_creds(bprm); current->flags &= ~PF_FORKNOEXEC; diff --git a/arch/x86_64/mm/ioremap.c b/arch/x86_64/mm/ioremap.c index 6972df480d2..ecf7acb5db9 100644 --- a/arch/x86_64/mm/ioremap.c +++ b/arch/x86_64/mm/ioremap.c @@ -60,7 +60,7 @@ static inline int remap_area_pmd(pmd_t * pmd, unsigned long address, unsigned lo if (address >= end) BUG(); do { - pte_t * pte = pte_alloc_kernel(&init_mm, pmd, address); + pte_t * pte = pte_alloc_kernel(pmd, address); if (!pte) return -ENOMEM; remap_area_pte(pte, address, end - address, address + phys_addr, flags); @@ -105,7 +105,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, flush_cache_all(); if (address >= end) BUG(); - spin_lock(&init_mm.page_table_lock); do { pud_t *pud; pud = pud_alloc(&init_mm, pgd, address); @@ -119,7 +118,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr, address = (address + PGDIR_SIZE) & PGDIR_MASK; pgd++; } while (address && (address < end)); - spin_unlock(&init_mm.page_table_lock); flush_tlb_all(); return error; } diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 01a1bd23926..2143609d293 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -200,8 +200,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) * Note: Assume that this function returns zero on success */ result = add_memory(mem_device->start_addr, - (mem_device->end_addr - mem_device->start_addr) + 1, - mem_device->read_write_attribute); + (mem_device->end_addr - mem_device->start_addr) + 1); if (result) { ACPI_DEBUG_PRINT((ACPI_DB_ERROR, "\nadd_memory failed\n")); mem_device->state = MEMORY_INVALID_STATE; @@ -259,7 +258,7 @@ static int acpi_memory_disable_device(struct acpi_memory_device *mem_device) * Ask the VM to offline this memory range. * Note: Assume that this function returns zero on success */ - result = remove_memory(start, len, attr); + result = remove_memory(start, len); if (result) { ACPI_DEBUG_PRINT((ACPI_DB_ERROR, "Hot-Remove failed.\n")); return_VALUE(result); diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 66d9c4643fc..f12898d5307 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -7,6 +7,7 @@ obj-y := core.o sys.o bus.o dd.o \ obj-y += power/ obj-$(CONFIG_FW_LOADER) += firmware_class.o obj-$(CONFIG_NUMA) += node.o +obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o ifeq ($(CONFIG_DEBUG_DRIVER),y) EXTRA_CFLAGS += -DDEBUG diff --git a/drivers/base/init.c b/drivers/base/init.c index 84e604e25c4..c648914b9cd 100644 --- a/drivers/base/init.c +++ b/drivers/base/init.c @@ -9,6 +9,7 @@ #include <linux/device.h> #include <linux/init.h> +#include <linux/memory.h> #include "base.h" @@ -33,5 +34,6 @@ void __init driver_init(void) platform_bus_init(); system_bus_init(); cpu_dev_init(); + memory_dev_init(); attribute_container_init(); } diff --git a/drivers/base/memory.c b/drivers/base/memory.c new file mode 100644 index 00000000000..b7ddd651d66 --- /dev/null +++ b/drivers/base/memory.c @@ -0,0 +1,452 @@ +/* + * drivers/base/memory.c - basic Memory class support + * + * Written by Matt Tolentino <matthew.e.tolentino@intel.com> + * Dave Hansen <haveblue@us.ibm.com> + * + * This file provides the necessary infrastructure to represent + * a SPARSEMEM-memory-model system's physical memory in /sysfs. + * All arch-independent code that assumes MEMORY_HOTPLUG requires + * SPARSEMEM should be contained here, or in mm/memory_hotplug.c. + */ + +#include <linux/sysdev.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/sched.h> /* capable() */ +#include <linux/topology.h> +#include <linux/device.h> +#include <linux/memory.h> +#include <linux/kobject.h> +#include <linux/memory_hotplug.h> +#include <linux/mm.h> +#include <asm/atomic.h> +#include <asm/uaccess.h> + +#define MEMORY_CLASS_NAME "memory" + +static struct sysdev_class memory_sysdev_class = { + set_kset_name(MEMORY_CLASS_NAME), +}; +EXPORT_SYMBOL(memory_sysdev_class); + +static char *memory_hotplug_name(struct kset *kset, struct kobject *kobj) +{ + return MEMORY_CLASS_NAME; +} + +static int memory_hotplug(struct kset *kset, struct kobject *kobj, char **envp, + int num_envp, char *buffer, int buffer_size) +{ + int retval = 0; + + return retval; +} + +static struct kset_hotplug_ops memory_hotplug_ops = { + .name = memory_hotplug_name, + .hotplug = memory_hotplug, +}; + +static struct notifier_block *memory_chain; + +static int register_memory_notifier(struct notifier_block *nb) +{ + return notifier_chain_register(&memory_chain, nb); +} + +static void unregister_memory_notifier(struct notifier_block *nb) +{ + notifier_chain_unregister(&memory_chain, nb); +} + +/* + * register_memory - Setup a sysfs device for a memory block + */ +static int +register_memory(struct memory_block *memory, struct mem_section *section, + struct node *root) +{ + int error; + + memory->sysdev.cls = &memory_sysdev_class; + memory->sysdev.id = __section_nr(section); + + error = sysdev_register(&memory->sysdev); + + if (root && !error) + error = sysfs_create_link(&root->sysdev.kobj, + &memory->sysdev.kobj, + kobject_name(&memory->sysdev.kobj)); + + return error; +} + +static void +unregister_memory(struct memory_block *memory, struct mem_section *section, + struct node *root) +{ + BUG_ON(memory->sysdev.cls != &memory_sysdev_class); + BUG_ON(memory->sysdev.id != __section_nr(section)); + + sysdev_unregister(&memory->sysdev); + if (root) + sysfs_remove_link(&root->sysdev.kobj, + kobject_name(&memory->sysdev.kobj)); +} + +/* + * use this as the physical section index that this memsection + * uses. + */ + +static ssize_t show_mem_phys_index(struct sys_device *dev, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + return sprintf(buf, "%08lx\n", mem->phys_index); +} + +/* + * online, offline, going offline, etc. + */ +static ssize_t show_mem_state(struct sys_device *dev, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + ssize_t len = 0; + + /* + * We can probably put these states in a nice little array + * so that they're not open-coded + */ + switch (mem->state) { + case MEM_ONLINE: + len = sprintf(buf, "online\n"); + break; + case MEM_OFFLINE: + len = sprintf(buf, "offline\n"); + break; + case MEM_GOING_OFFLINE: + len = sprintf(buf, "going-offline\n"); + break; + default: + len = sprintf(buf, "ERROR-UNKNOWN-%ld\n", + mem->state); + WARN_ON(1); + break; + } + + return len; +} + +static inline int memory_notify(unsigned long val, void *v) +{ + return notifier_call_chain(&memory_chain, val, v); +} + +/* + * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is + * OK to have direct references to sparsemem variables in here. + */ +static int +memory_block_action(struct memory_block *mem, unsigned long action) +{ + int i; + unsigned long psection; + unsigned long start_pfn, start_paddr; + struct page *first_page; + int ret; + int old_state = mem->state; + + psection = mem->phys_index; + first_page = pfn_to_page(psection << PFN_SECTION_SHIFT); + + /* + * The probe routines leave the pages reserved, just + * as the bootmem code does. Make sure they're still + * that way. + */ + if (action == MEM_ONLINE) { + for (i = 0; i < PAGES_PER_SECTION; i++) { + if (PageReserved(first_page+i)) + continue; + + printk(KERN_WARNING "section number %ld page number %d " + "not reserved, was it already online? \n", + psection, i); + return -EBUSY; + } + } + + switch (action) { + case MEM_ONLINE: + start_pfn = page_to_pfn(first_page); + ret = online_pages(start_pfn, PAGES_PER_SECTION); + break; + case MEM_OFFLINE: + mem->state = MEM_GOING_OFFLINE; + memory_notify(MEM_GOING_OFFLINE, NULL); + start_paddr = page_to_pfn(first_page) << PAGE_SHIFT; + ret = remove_memory(start_paddr, + PAGES_PER_SECTION << PAGE_SHIFT); + if (ret) { + mem->state = old_state; + break; + } + memory_notify(MEM_MAPPING_INVALID, NULL); + break; + default: + printk(KERN_WARNING "%s(%p, %ld) unknown action: %ld\n", + __FUNCTION__, mem, action, action); + WARN_ON(1); + ret = -EINVAL; + } + /* + * For now, only notify on successful memory operations + */ + if (!ret) + memory_notify(action, NULL); + + return ret; +} + +static int memory_block_change_state(struct memory_block *mem, + unsigned long to_state, unsigned long from_state_req) +{ + int ret = 0; + down(&mem->state_sem); + + if (mem->state != from_state_req) { + ret = -EINVAL; + goto out; + } + + ret = memory_block_action(mem, to_state); + if (!ret) + mem->state = to_state; + +out: + up(&mem->state_sem); + return ret; +} + +static ssize_t +store_mem_state(struct sys_device *dev, const char *buf, size_t count) +{ + struct memory_block *mem; + unsigned int phys_section_nr; + int ret = -EINVAL; + + mem = container_of(dev, struct memory_block, sysdev); + phys_section_nr = mem->phys_index; + + if (!valid_section_nr(phys_section_nr)) + goto out; + + if (!strncmp(buf, "online", min((int)count, 6))) + ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); + else if(!strncmp(buf, "offline", min((int)count, 7))) + ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); +out: + if (ret) + return ret; + return count; +} + +/* + * phys_device is a bad name for this. What I really want + * is a way to differentiate between memory ranges that + * are part of physical devices that constitute + * a complete removable unit or fru. + * i.e. do these ranges belong to the same physical device, + * s.t. if I offline all of these sections I can then + * remove the physical device? + */ +static ssize_t show_phys_device(struct sys_device *dev, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + return sprintf(buf, "%d\n", mem->phys_device); +} + +static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL); +static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state); +static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL); + +#define mem_create_simple_file(mem, attr_name) \ + sysdev_create_file(&mem->sysdev, &attr_##attr_name) +#define mem_remove_simple_file(mem, attr_name) \ + sysdev_remove_file(&mem->sysdev, &attr_##attr_name) + +/* + * Block size attribute stuff + */ +static ssize_t +print_block_size(struct class *class, char *buf) +{ + return sprintf(buf, "%lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE); +} + +static CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL); + +static int block_size_init(void) +{ + sysfs_create_file(&memory_sysdev_class.kset.kobj, + &class_attr_block_size_bytes.attr); + return 0; +} + +/* + * Some architectures will have custom drivers to do this, and + * will not need to do it from userspace. The fake hot-add code + * as well as ppc64 will do all of their discovery in userspace + * and will require this interface. + */ +#ifdef CONFIG_ARCH_MEMORY_PROBE +static ssize_t +memory_probe_store(struct class *class, const char __user *buf, size_t count) +{ + u64 phys_addr; + int ret; + + phys_addr = simple_strtoull(buf, NULL, 0); + + ret = add_memory(phys_addr, PAGES_PER_SECTION << PAGE_SHIFT); + + if (ret) + count = ret; + + return count; +} +static CLASS_ATTR(probe, 0700, NULL, memory_probe_store); + +static int memory_probe_init(void) +{ + sysfs_create_file(&memory_sysdev_class.kset.kobj, + &class_attr_probe.attr); + return 0; +} +#else +#define memory_probe_init(...) do {} while (0) +#endif + +/* + * Note that phys_device is optional. It is here to allow for + * differentiation between which *physical* devices each + * section belongs to... + */ + +static int add_memory_block(unsigned long node_id, struct mem_section *section, + unsigned long state, int phys_device) +{ + struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL); + int ret = 0; + + if (!mem) + return -ENOMEM; + + mem->phys_index = __section_nr(section); + mem->state = state; + init_MUTEX(&mem->state_sem); + mem->phys_device = phys_device; + + ret = register_memory(mem, section, NULL); + if (!ret) + ret = mem_create_simple_file(mem, phys_index); + if (!ret) + ret = mem_create_simple_file(mem, state); + if (!ret) + ret = mem_create_simple_file(mem, phys_device); + + return ret; +} + +/* + * For now, we have a linear search to go find the appropriate + * memory_block corresponding to a particular phys_index. If + * this gets to be a real problem, we can always use a radix + * tree or something here. + * + * This could be made generic for all sysdev classes. + */ +static struct memory_block *find_memory_block(struct mem_section *section) +{ + struct kobject *kobj; + struct sys_device *sysdev; + struct memory_block *mem; + char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1]; + + /* + * This only works because we know that section == sysdev->id + * slightly redundant with sysdev_register() + */ + sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section)); + + kobj = kset_find_obj(&memory_sysdev_class.kset, name); + if (!kobj) + return NULL; + + sysdev = container_of(kobj, struct sys_device, kobj); + mem = container_of(sysdev, struct memory_block, sysdev); + + return mem; +} + +int remove_memory_block(unsigned long node_id, struct mem_section *section, + int phys_device) +{ + struct memory_block *mem; + + mem = find_memory_block(section); + mem_remove_simple_file(mem, phys_index); + mem_remove_simple_file(mem, state); + mem_remove_simple_file(mem, phys_device); + unregister_memory(mem, section, NULL); + + return 0; +} + +/* + * need an interface for the VM to add new memory regions, + * but without onlining it. + */ +int register_new_memory(struct mem_section *section) +{ + return add_memory_block(0, section, MEM_OFFLINE, 0); +} + +int unregister_memory_section(struct mem_section *section) +{ + if (!valid_section(section)) + return -EINVAL; + + return remove_memory_block(0, section, 0); +} + +/* + * Initialize the sysfs support for memory devices... + */ +int __init memory_dev_init(void) +{ + unsigned int i; + int ret; + + memory_sysdev_class.kset.hotplug_ops = &memory_hotplug_ops; + ret = sysdev_class_register(&memory_sysdev_class); + + /* + * Create entries for memory sections that were found + * during boot and have been initialized + */ + for (i = 0; i < NR_MEM_SECTIONS; i++) { + if (!valid_section_nr(i)) + continue; + add_memory_block(0, __nr_to_section(i), MEM_ONLINE, 0); + } + + memory_probe_init(); + block_size_init(); + + return ret; +} diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 07fee811c09..d86d5c26061 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1887,13 +1887,17 @@ st_unmap_user_pages(struct scatterlist *sgl, const unsigned int nr_pages, int i; for (i=0; i < nr_pages; i++) { - if (dirtied && !PageReserved(sgl[i].page)) - SetPageDirty(sgl[i].page); - /* unlock_page(sgl[i].page); */ + struct page *page = sgl[i].page; + + /* XXX: just for debug. Remove when PageReserved is removed */ + BUG_ON(PageReserved(page)); + if (dirtied) + SetPageDirty(page); + /* unlock_page(page); */ /* FIXME: cache flush missing for rw==READ * FIXME: call the correct reference counting function */ - page_cache_release(sgl[i].page); + page_cache_release(page); } return 0; diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 5eb54d8019b..da9766283bd 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -4526,12 +4526,16 @@ static int sgl_unmap_user_pages(struct scatterlist *sgl, const unsigned int nr_p int i; for (i=0; i < nr_pages; i++) { - if (dirtied && !PageReserved(sgl[i].page)) - SetPageDirty(sgl[i].page); + struct page *page = sgl[i].page; + + /* XXX: just for debug. Remove when PageReserved is removed */ + BUG_ON(PageReserved(page)); + if (dirtied) + SetPageDirty(page); /* FIXME: cache flush missing for rw==READ * FIXME: call the correct reference counting function */ - page_cache_release(sgl[i].page); + page_cache_release(page); } return 0; diff --git a/fs/afs/file.c b/fs/afs/file.c index 0d576987ec6..4975c9c193d 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -291,8 +291,8 @@ static int afs_file_releasepage(struct page *page, gfp_t gfp_flags) cachefs_uncache_page(vnode->cache, page); #endif - pageio = (struct cachefs_page *) page->private; - page->private = 0; + pageio = (struct cachefs_page *) page_private(page); + set_page_private(page, 0); ClearPagePrivate(page); if (pageio) diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index dd9baabaf01..72011826f0c 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -318,7 +318,6 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) current->mm->free_area_cache = current->mm->mmap_base; current->mm->cached_hole_size = 0; - set_mm_counter(current->mm, rss, 0); current->mm->mmap = NULL; compute_creds(bprm); current->flags &= ~PF_FORKNOEXEC; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index d4b15576e58..918ccc267e4 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -773,7 +773,6 @@ static int load_elf_binary(struct linux_binprm * bprm, struct pt_regs * regs) /* Do this so that we can load the interpreter, if need be. We will change some of these later */ - set_mm_counter(current->mm, rss, 0); current->mm->free_area_cache = current->mm->mmap_base; current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP), diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 134c9c0d1f5..dda87c4c82a 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -294,14 +294,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, struct pt_regs *regs &interp_params, ¤t->mm->start_stack, ¤t->mm->start_brk); -#endif - - /* do this so that we can load the interpreter, if need be - * - we will change some of these later - */ - set_mm_counter(current->mm, rss, 0); -#ifdef CONFIG_MMU retval = setup_arg_pages(bprm, current->mm->start_stack, executable_stack); if (retval < 0) { send_sig(SIGKILL, current, 0); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 7974efa107b..9d6625829b9 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -650,7 +650,6 @@ static int load_flat_file(struct linux_binprm * bprm, current->mm->start_brk = datapos + data_len + bss_len; current->mm->brk = (current->mm->start_brk + 3) & ~3; current->mm->context.end_brk = memp + ksize((void *) memp) - stack_len; - set_mm_counter(current->mm, rss, 0); } if (flags & FLAT_FLAG_KTRACE) diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c index 227a2682d2b..00a91dc25d1 100644 --- a/fs/binfmt_som.c +++ b/fs/binfmt_som.c @@ -259,7 +259,6 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs) create_som_tables(bprm); current->mm->start_stack = bprm->p; - set_mm_counter(current->mm, rss, 0); #if 0 printk("(start_brk) %08lx\n" , (unsigned long) current->mm->start_brk); diff --git a/fs/buffer.c b/fs/buffer.c index b1667986442..2066e4cb700 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -96,7 +96,7 @@ static void __clear_page_buffers(struct page *page) { ClearPagePrivate(page); - page->private = 0; + set_page_private(page, 0); page_cache_release(page); } diff --git a/fs/compat.c b/fs/compat.c index a719e158e00..8e71cdbecc7 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1490,7 +1490,6 @@ int compat_do_execve(char * filename, /* execve success */ security_bprm_free(bprm); acct_update_integrals(current); - update_mem_hiwater(current); kfree(bprm); return retval; } diff --git a/fs/direct-io.c b/fs/direct-io.c index 0d06097bc99..3931e7f1e6b 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -162,6 +162,7 @@ static int dio_refill_pages(struct dio *dio) up_read(¤t->mm->mmap_sem); if (ret < 0 && dio->blocks_available && (dio->rw == WRITE)) { + struct page *page = ZERO_PAGE(dio->curr_user_address); /* * A memory fault, but the filesystem has some outstanding * mapped blocks. We need to use those blocks up to avoid @@ -169,7 +170,8 @@ static int dio_refill_pages(struct dio *dio) */ if (dio->page_errors == 0) dio->page_errors = ret; - dio->pages[0] = ZERO_PAGE(dio->curr_user_address); + page_cache_get(page); + dio->pages[0] = page; dio->head = 0; dio->tail = 1; ret = 0; diff --git a/fs/exec.c b/fs/exec.c index d2208f7c87d..ba73797eb4c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -309,40 +309,36 @@ void install_arg_page(struct vm_area_struct *vma, pud_t * pud; pmd_t * pmd; pte_t * pte; + spinlock_t *ptl; if (unlikely(anon_vma_prepare(vma))) - goto out_sig; + goto out; flush_dcache_page(page); pgd = pgd_offset(mm, address); - - spin_lock(&mm->page_table_lock); pud = pud_alloc(mm, pgd, address); if (!pud) goto out; pmd = pmd_alloc(mm, pud, address); if (!pmd) goto out; - pte = pte_alloc_map(mm, pmd, address); + pte = pte_alloc_map_lock(mm, pmd, address, &ptl); if (!pte) goto out; if (!pte_none(*pte)) { - pte_unmap(pte); + pte_unmap_unlock(pte, ptl); goto out; } - inc_mm_counter(mm, rss); + inc_mm_counter(mm, anon_rss); lru_cache_add_active(page); set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte( page, vma->vm_page_prot)))); page_add_anon_rmap(page, vma, address); - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(pte, ptl); /* no need for flush_tlb */ return; out: - spin_unlock(&mm->page_table_lock); -out_sig: __free_page(page); force_sig(SIGKILL, current); } @@ -1207,7 +1203,6 @@ int do_execve(char * filename, /* execve success */ security_bprm_free(bprm); acct_update_integrals(current); - update_mem_hiwater(current); kfree(bprm); return retval; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 3a9b6d179cb..e026c807e6b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -45,10 +45,58 @@ static struct backing_dev_info hugetlbfs_backing_dev_info = { int sysctl_hugetlb_shm_group; +static void huge_pagevec_release(struct pagevec *pvec) +{ + int i; + + for (i = 0; i < pagevec_count(pvec); ++i) + put_page(pvec->pages[i]); + + pagevec_reinit(pvec); +} + +/* + * huge_pages_needed tries to determine the number of new huge pages that + * will be required to fully populate this VMA. This will be equal to + * the size of the VMA in huge pages minus the number of huge pages + * (covered by this VMA) that are found in the page cache. + * + * Result is in bytes to be compatible with is_hugepage_mem_enough() + */ +unsigned long +huge_pages_needed(struct address_space *mapping, struct vm_area_struct *vma) +{ + int i; + struct pagevec pvec; + unsigned long start = vma->vm_start; + unsigned long end = vma->vm_end; + unsigned long hugepages = (end - start) >> HPAGE_SHIFT; + pgoff_t next = vma->vm_pgoff; + pgoff_t endpg = next + ((end - start) >> PAGE_SHIFT); + + pagevec_init(&pvec, 0); + while (next < endpg) { + if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) + break; + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + if (page->index > next) + next = page->index; + if (page->index >= endpg) + break; + next++; + hugepages--; + } + huge_pagevec_release(&pvec); + } + return hugepages << HPAGE_SHIFT; +} + static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file->f_dentry->d_inode; struct address_space *mapping = inode->i_mapping; + unsigned long bytes; loff_t len, vma_len; int ret; @@ -67,6 +115,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) if (vma->vm_end - vma->vm_start < HPAGE_SIZE) return -EINVAL; + bytes = huge_pages_needed(mapping, vma); + if (!is_hugepage_mem_enough(bytes)) + return -ENOMEM; + vma_len = (loff_t)(vma->vm_end - vma->vm_start); down(&inode->i_sem); @@ -79,10 +131,8 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_WRITE) && len > inode->i_size) goto out; - ret = hugetlb_prefault(mapping, vma); - if (ret) - goto out; - + ret = 0; + hugetlb_prefault_arch_hook(vma->vm_mm); if (inode->i_size < len) inode->i_size = len; out: @@ -92,7 +142,7 @@ out: } /* - * Called under down_write(mmap_sem), page_table_lock is not held + * Called under down_write(mmap_sem). */ #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA @@ -171,16 +221,6 @@ static int hugetlbfs_commit_write(struct file *file, return -EINVAL; } -static void huge_pagevec_release(struct pagevec *pvec) -{ - int i; - - for (i = 0; i < pagevec_count(pvec); ++i) - put_page(pvec->pages[i]); - - pagevec_reinit(pvec); -} - static void truncate_huge_page(struct page *page) { clear_page_dirty(page); @@ -224,52 +264,35 @@ static void truncate_hugepages(struct address_space *mapping, loff_t lstart) static void hugetlbfs_delete_inode(struct inode *inode) { - struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(inode->i_sb); - - hlist_del_init(&inode->i_hash); - list_del_init(&inode->i_list); - list_del_init(&inode->i_sb_list); - inode->i_state |= I_FREEING; - inodes_stat.nr_inodes--; - spin_unlock(&inode_lock); - if (inode->i_data.nrpages) truncate_hugepages(&inode->i_data, 0); - - security_inode_delete(inode); - - if (sbinfo->free_inodes >= 0) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); - } - clear_inode(inode); - destroy_inode(inode); } static void hugetlbfs_forget_inode(struct inode *inode) { - struct super_block *super_block = inode->i_sb; - struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(super_block); + struct super_block *sb = inode->i_sb; - if (hlist_unhashed(&inode->i_hash)) - goto out_truncate; - - if (!(inode->i_state & (I_DIRTY|I_LOCK))) { - list_del(&inode->i_list); - list_add(&inode->i_list, &inode_unused); - } - inodes_stat.nr_unused++; - if (!super_block || (super_block->s_flags & MS_ACTIVE)) { + if (!hlist_unhashed(&inode->i_hash)) { + if (!(inode->i_state & (I_DIRTY|I_LOCK))) + list_move(&inode->i_list, &inode_unused); + inodes_stat.nr_unused++; + if (!sb || (sb->s_flags & MS_ACTIVE)) { + spin_unlock(&inode_lock); + return; + } + inode->i_state |= I_WILL_FREE; spin_unlock(&inode_lock); - return; + /* + * write_inode_now is a noop as we set BDI_CAP_NO_WRITEBACK + * in our backing_dev_info. + */ + write_inode_now(inode, 1); + spin_lock(&inode_lock); + inode->i_state &= ~I_WILL_FREE; + inodes_stat.nr_unused--; + hlist_del_init(&inode->i_hash); } - - /* write_inode_now() ? */ - inodes_stat.nr_unused--; - hlist_del_init(&inode->i_hash); -out_truncate: list_del_init(&inode->i_list); list_del_init(&inode->i_sb_list); inode->i_state |= I_FREEING; @@ -277,13 +300,6 @@ out_truncate: spin_unlock(&inode_lock); if (inode->i_data.nrpages) truncate_hugepages(&inode->i_data, 0); - - if (sbinfo->free_inodes >= 0) { - spin_lock(&sbinfo->stat_lock); - sbinfo->free_inodes++; - spin_unlock(&sbinfo->stat_lock); - } - clear_inode(inode); destroy_inode(inode); } @@ -291,7 +307,7 @@ out_truncate: static void hugetlbfs_drop_inode(struct inode *inode) { if (!inode->i_nlink) - hugetlbfs_delete_inode(inode); + generic_delete_inode(inode); else hugetlbfs_forget_inode(inode); } @@ -308,7 +324,6 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff) vma_prio_tree_foreach(vma, &iter, root, h_pgoff, ULONG_MAX) { unsigned long h_vm_pgoff; - unsigned long v_length; unsigned long v_offset; h_vm_pgoff = vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT); @@ -319,11 +334,8 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff) if (h_vm_pgoff >= h_pgoff) v_offset = 0; - v_length = vma->vm_end - vma->vm_start; - - zap_hugepage_range(vma, - vma->vm_start + v_offset, - v_length - v_offset); + unmap_hugepage_range(vma, + vma->vm_start + v_offset, vma->vm_end); } } @@ -379,17 +391,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, gid_t gid, int mode, dev_t dev) { struct inode *inode; - struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb); - - if (sbinfo->free_inodes >= 0) { - spin_lock(&sbinfo->stat_lock); - if (!sbinfo->free_inodes) { - spin_unlock(&sbinfo->stat_lock); - return NULL; - } - sbinfo->free_inodes--; - spin_unlock(&sbinfo->stat_lock); - } inode = new_inode(sb); if (inode) { @@ -531,29 +532,51 @@ static void hugetlbfs_put_super(struct super_block *sb) } } +static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo) +{ + if (sbinfo->free_inodes >= 0) { + spin_lock(&sbinfo->stat_lock); + if (unlikely(!sbinfo->free_inodes)) { + spin_unlock(&sbinfo->stat_lock); + return 0; + } + sbinfo->free_inodes--; + spin_unlock(&sbinfo->stat_lock); + } + + return 1; +} + +static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo) +{ + if (sbinfo->free_inodes >= 0) { + spin_lock(&sbinfo->stat_lock); + sbinfo->free_inodes++; + spin_unlock(&sbinfo->stat_lock); + } +} + + static kmem_cache_t *hugetlbfs_inode_cachep; static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) { + struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb); struct hugetlbfs_inode_info *p; + if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo))) + return NULL; p = kmem_cache_alloc(hugetlbfs_inode_cachep, SLAB_KERNEL); - if (!p) + if (unlikely(!p)) { + hugetlbfs_inc_free_inodes(sbinfo); return NULL; + } return &p->vfs_inode; } -static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags) -{ - struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo; - - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == - SLAB_CTOR_CONSTRUCTOR) - inode_init_once(&ei->vfs_inode); -} - static void hugetlbfs_destroy_inode(struct inode *inode) { + hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb)); mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy); kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode)); } @@ -565,6 +588,16 @@ static struct address_space_operations hugetlbfs_aops = { .set_page_dirty = hugetlbfs_set_page_dirty, }; + +static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags) +{ + struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo; + + if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == + SLAB_CTOR_CONSTRUCTOR) + inode_init_once(&ei->vfs_inode); +} + struct file_operations hugetlbfs_file_operations = { .mmap = hugetlbfs_file_mmap, .fsync = simple_sync_file, @@ -592,6 +625,7 @@ static struct super_operations hugetlbfs_ops = { .alloc_inode = hugetlbfs_alloc_inode, .destroy_inode = hugetlbfs_destroy_inode, .statfs = hugetlbfs_statfs, + .delete_inode = hugetlbfs_delete_inode, .drop_inode = hugetlbfs_drop_inode, .put_super = hugetlbfs_put_super, }; diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 26091a5f88d..8a53981f9f2 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -86,7 +86,7 @@ struct meta_anchor { atomic_t io_count; struct metapage *mp[MPS_PER_PAGE]; }; -#define mp_anchor(page) ((struct meta_anchor *)page->private) +#define mp_anchor(page) ((struct meta_anchor *)page_private(page)) static inline struct metapage *page_to_mp(struct page *page, uint offset) { @@ -108,7 +108,7 @@ static inline int insert_metapage(struct page *page, struct metapage *mp) if (!a) return -ENOMEM; memset(a, 0, sizeof(struct meta_anchor)); - page->private = (unsigned long)a; + set_page_private(page, (unsigned long)a); SetPagePrivate(page); kmap(page); } @@ -136,7 +136,7 @@ static inline void remove_metapage(struct page *page, struct metapage *mp) a->mp[index] = NULL; if (--a->mp_count == 0) { kfree(a); - page->private = 0; + set_page_private(page, 0); ClearPagePrivate(page); kunmap(page); } @@ -156,13 +156,13 @@ static inline void dec_io(struct page *page, void (*handler) (struct page *)) #else static inline struct metapage *page_to_mp(struct page *page, uint offset) { - return PagePrivate(page) ? (struct metapage *)page->private : NULL; + return PagePrivate(page) ? (struct metapage *)page_private(page) : NULL; } static inline int insert_metapage(struct page *page, struct metapage *mp) { if (mp) { - page->private = (unsigned long)mp; + set_page_private(page, (unsigned long)mp); SetPagePrivate(page); kmap(page); } @@ -171,7 +171,7 @@ static inline int insert_metapage(struct page *page, struct metapage *mp) static inline void remove_metapage(struct page *page, struct metapage *mp) { - page->private = 0; + set_page_private(page, 0); ClearPagePrivate(page); kunmap(page); } diff --git a/fs/proc/array.c b/fs/proc/array.c index d84eecacbea..3e1239e4b30 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -438,7 +438,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) jiffies_to_clock_t(it_real_value), start_time, vsize, - mm ? get_mm_counter(mm, rss) : 0, /* you might want to shift this left 3 */ + mm ? get_mm_rss(mm) : 0, rsslim, mm ? mm->start_code : 0, mm ? mm->end_code : 0, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index c7ef3e48e35..d2fa42006d8 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -14,22 +14,41 @@ char *task_mem(struct mm_struct *mm, char *buffer) { unsigned long data, text, lib; + unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; + + /* + * Note: to minimize their overhead, mm maintains hiwater_vm and + * hiwater_rss only when about to *lower* total_vm or rss. Any + * collector of these hiwater stats must therefore get total_vm + * and rss too, which will usually be the higher. Barriers? not + * worth the effort, such snapshots can always be inconsistent. + */ + hiwater_vm = total_vm = mm->total_vm; + if (hiwater_vm < mm->hiwater_vm) + hiwater_vm = mm->hiwater_vm; + hiwater_rss = total_rss = get_mm_rss(mm); + if (hiwater_rss < mm->hiwater_rss) + hiwater_rss = mm->hiwater_rss; data = mm->total_vm - mm->shared_vm - mm->stack_vm; text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10; lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text; buffer += sprintf(buffer, + "VmPeak:\t%8lu kB\n" "VmSize:\t%8lu kB\n" "VmLck:\t%8lu kB\n" + "VmHWM:\t%8lu kB\n" "VmRSS:\t%8lu kB\n" "VmData:\t%8lu kB\n" "VmStk:\t%8lu kB\n" "VmExe:\t%8lu kB\n" "VmLib:\t%8lu kB\n" "VmPTE:\t%8lu kB\n", - (mm->total_vm - mm->reserved_vm) << (PAGE_SHIFT-10), + hiwater_vm << (PAGE_SHIFT-10), + (total_vm - mm->reserved_vm) << (PAGE_SHIFT-10), mm->locked_vm << (PAGE_SHIFT-10), - get_mm_counter(mm, rss) << (PAGE_SHIFT-10), + hiwater_rss << (PAGE_SHIFT-10), + total_rss << (PAGE_SHIFT-10), data << (PAGE_SHIFT-10), mm->stack_vm << (PAGE_SHIFT-10), text, lib, (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10); @@ -44,13 +63,11 @@ unsigned long task_vsize(struct mm_struct *mm) int task_statm(struct mm_struct *mm, int *shared, int *text, int *data, int *resident) { - int rss = get_mm_counter(mm, rss); - - *shared = rss - get_mm_counter(mm, anon_rss); + *shared = get_mm_counter(mm, file_rss); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->total_vm - mm->shared_vm; - *resident = rss; + *resident = *shared + get_mm_counter(mm, anon_rss); return mm->total_vm; } @@ -186,13 +203,14 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd, struct mem_size_stats *mss) { pte_t *pte, ptent; + spinlock_t *ptl; unsigned long pfn; struct page *page; - pte = pte_offset_map(pmd, addr); + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { ptent = *pte; - if (pte_none(ptent) || !pte_present(ptent)) + if (!pte_present(ptent)) continue; mss->resident += PAGE_SIZE; @@ -213,8 +231,8 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd, mss->private_clean += PAGE_SIZE; } } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(pte - 1); - cond_resched_lock(&vma->vm_mm->page_table_lock); + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); } static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud, @@ -268,17 +286,11 @@ static inline void smaps_pgd_range(struct vm_area_struct *vma, static int show_smap(struct seq_file *m, void *v) { struct vm_area_struct *vma = v; - struct mm_struct *mm = vma->vm_mm; struct mem_size_stats mss; memset(&mss, 0, sizeof mss); - - if (mm) { - spin_lock(&mm->page_table_lock); + if (vma->vm_mm) smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss); - spin_unlock(&mm->page_table_lock); - } - return show_map_internal(m, v, &mss); } @@ -407,7 +419,6 @@ static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma) for_each_node(i) md->node[i] =0; - spin_lock(&mm->page_table_lock); for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) { page = follow_page(mm, vaddr, 0); if (page) { @@ -422,8 +433,8 @@ static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma) md->anon++; md->node[page_to_nid(page)]++; } + cond_resched(); } - spin_unlock(&mm->page_table_lock); return md; } @@ -469,7 +480,7 @@ static int show_numa_map(struct seq_file *m, void *v) seq_printf(m, " interleave={"); first = 1; for_each_node(n) { - if (test_bit(n, pol->v.nodes)) { + if (node_isset(n, pol->v.nodes)) { if (!first) seq_putc(m,','); else diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index ba4767c04ad..4cd46abe843 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -181,8 +181,9 @@ set_page_region( size_t offset, size_t length) { - page->private |= page_region_mask(offset, length); - if (page->private == ~0UL) + set_page_private(page, + page_private(page) | page_region_mask(offset, length)); + if (page_private(page) == ~0UL) SetPageUptodate(page); } @@ -194,7 +195,7 @@ test_page_region( { unsigned long mask = page_region_mask(offset, length); - return (mask && (page->private & mask) == mask); + return (mask && (page_private(page) & mask) == mask); } /* diff --git a/include/asm-alpha/barrier.h b/include/asm-alpha/barrier.h index 229c83fe77c..681ff581afa 100644 --- a/include/asm-alpha/barrier.h +++ b/include/asm-alpha/barrier.h @@ -1,6 +1,8 @@ #ifndef __BARRIER_H #define __BARRIER_H +#include <asm/compiler.h> + #define mb() \ __asm__ __volatile__("mb": : :"memory") diff --git a/include/asm-alpha/rwsem.h b/include/asm-alpha/rwsem.h index 8e058a67c9a..fafdd4f7010 100644 --- a/include/asm-alpha/rwsem.h +++ b/include/asm-alpha/rwsem.h @@ -262,5 +262,10 @@ static inline long rwsem_atomic_update(long val, struct rw_semaphore *sem) #endif } +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* __KERNEL__ */ #endif /* _ALPHA_RWSEM_H */ diff --git a/include/asm-arm/tlb.h b/include/asm-arm/tlb.h index 9bb325c5464..f49bfb78c22 100644 --- a/include/asm-arm/tlb.h +++ b/include/asm-arm/tlb.h @@ -27,11 +27,7 @@ */ struct mmu_gather { struct mm_struct *mm; - unsigned int freed; unsigned int fullmm; - - unsigned int flushes; - unsigned int avoided_flushes; }; DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); @@ -39,11 +35,9 @@ DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); static inline struct mmu_gather * tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) { - int cpu = smp_processor_id(); - struct mmu_gather *tlb = &per_cpu(mmu_gathers, cpu); + struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; - tlb->freed = 0; tlb->fullmm = full_mm_flush; return tlb; @@ -52,24 +46,13 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - struct mm_struct *mm = tlb->mm; - unsigned long freed = tlb->freed; - int rss = get_mm_counter(mm, rss); - - if (rss < freed) - freed = rss; - add_mm_counter(mm, rss, -freed); - if (tlb->fullmm) - flush_tlb_mm(mm); + flush_tlb_mm(tlb->mm); /* keep the page table cache within bounds */ check_pgt_cache(); -} -static inline unsigned int tlb_is_full_mm(struct mmu_gather *tlb) -{ - return tlb->fullmm; + put_cpu_var(mmu_gathers); } #define tlb_remove_tlb_entry(tlb,ptep,address) do { } while (0) diff --git a/include/asm-arm26/tlb.h b/include/asm-arm26/tlb.h index 1316352a58f..08ddd85b8d3 100644 --- a/include/asm-arm26/tlb.h +++ b/include/asm-arm26/tlb.h @@ -10,24 +10,20 @@ */ struct mmu_gather { struct mm_struct *mm; - unsigned int freed; - unsigned int fullmm; - - unsigned int flushes; - unsigned int avoided_flushes; + unsigned int need_flush; + unsigned int fullmm; }; -extern struct mmu_gather mmu_gathers[NR_CPUS]; +DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); static inline struct mmu_gather * tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) { - int cpu = smp_processor_id(); - struct mmu_gather *tlb = &mmu_gathers[cpu]; + struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; - tlb->freed = 0; - tlb->fullmm = full_mm_flush; + tlb->need_flush = 0; + tlb->fullmm = full_mm_flush; return tlb; } @@ -35,30 +31,13 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - struct mm_struct *mm = tlb->mm; - unsigned long freed = tlb->freed; - int rss = get_mm_counter(mm, rss); - - if (rss < freed) - freed = rss; - add_mm_counter(mm, rss, -freed); - - if (freed) { - flush_tlb_mm(mm); - tlb->flushes++; - } else { - tlb->avoided_flushes++; - } + if (tlb->need_flush) + flush_tlb_mm(tlb->mm); /* keep the page table cache within bounds */ check_pgt_cache(); -} - -static inline unsigned int -tlb_is_full_mm(struct mmu_gather *tlb) -{ - return tlb->fullmm; + put_cpu_var(mmu_gathers); } #define tlb_remove_tlb_entry(tlb,ptep,address) do { } while (0) @@ -71,7 +50,13 @@ tlb_is_full_mm(struct mmu_gather *tlb) } while (0) #define tlb_end_vma(tlb,vma) do { } while (0) -#define tlb_remove_page(tlb,page) free_page_and_swap_cache(page) +static inline void +tlb_remove_page(struct mmu_gather *tlb, struct page *page) +{ + tlb->need_flush = 1; + free_page_and_swap_cache(page); +} + #define pte_free_tlb(tlb,ptep) pte_free(ptep) #define pmd_free_tlb(tlb,pmdp) pmd_free(pmdp) diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index c20ec257ecc..68c6fea994d 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -10,14 +10,9 @@ #define pud_t pgd_t -#define pmd_alloc(mm, pud, address) \ -({ pmd_t *ret; \ - if (pgd_none(*pud)) \ - ret = __pmd_alloc(mm, pud, address); \ - else \ - ret = pmd_offset(pud, address); \ - ret; \ -}) +#define pmd_alloc(mm, pud, address) \ + ((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \ + NULL: pmd_offset(pud, address)) #define pud_alloc(mm, pgd, address) (pgd) #define pud_offset(pgd, start) (pgd) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index ff28c8b31f5..7dca30a26c5 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -8,7 +8,7 @@ * - update the page tables * - inform the TLB about the new one * - * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock. + * We hold the mm semaphore for reading, and the pte lock. * * Note: the old pte is known to not be writable, so we don't need to * worry about dirty bits etc getting lost. diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 7d0298347ee..cdd4145243c 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -35,16 +35,13 @@ #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. This structure - * can be per-CPU or per-MM as the page table lock is held for the duration of - * TLB shootdown. + * any data needed by arch specific code for tlb_remove_page. */ 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 */ - unsigned long freed; struct page * pages[FREE_PTE_NR]; }; @@ -57,7 +54,7 @@ DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); static inline struct mmu_gather * tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) { - struct mmu_gather *tlb = &per_cpu(mmu_gathers, smp_processor_id()); + struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; @@ -65,7 +62,6 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) tlb->nr = num_online_cpus() > 1 ? 0U : ~0U; tlb->fullmm = full_mm_flush; - tlb->freed = 0; return tlb; } @@ -85,28 +81,17 @@ tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) /* tlb_finish_mmu * Called at the end of the shootdown operation to free up any resources - * that were required. The page table lock is still held at this point. + * that were required. */ static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - int freed = tlb->freed; - struct mm_struct *mm = tlb->mm; - int rss = get_mm_counter(mm, rss); - - if (rss < freed) - freed = rss; - add_mm_counter(mm, rss, -freed); tlb_flush_mmu(tlb, start, end); /* keep the page table cache within bounds */ check_pgt_cache(); -} -static inline unsigned int -tlb_is_full_mm(struct mmu_gather *tlb) -{ - return tlb->fullmm; + put_cpu_var(mmu_gathers); } /* tlb_remove_page diff --git a/include/asm-i386/mmzone.h b/include/asm-i386/mmzone.h index 348fe3a4879..620a90641ea 100644 --- a/include/asm-i386/mmzone.h +++ b/include/asm-i386/mmzone.h @@ -88,12 +88,6 @@ static inline int pfn_to_nid(unsigned long pfn) __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ }) -#define local_mapnr(kvaddr) \ -({ \ - unsigned long __pfn = __pa(kvaddr) >> PAGE_SHIFT; \ - (__pfn - node_start_pfn(pfn_to_nid(__pfn))); \ -}) - /* XXX: FIXME -- wli */ #define kern_addr_valid(kaddr) (0) diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h index d101ac414f0..0e3ec809352 100644 --- a/include/asm-i386/pgtable.h +++ b/include/asm-i386/pgtable.h @@ -203,7 +203,8 @@ extern unsigned long pg0[]; #define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE)) #define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0) -#define pmd_none(x) (!pmd_val(x)) +/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */ +#define pmd_none(x) (!(unsigned long)pmd_val(x)) #define pmd_present(x) (pmd_val(x) & _PAGE_PRESENT) #define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0) #define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) diff --git a/include/asm-i386/rwsem.h b/include/asm-i386/rwsem.h index 7625a675852..be4ab859238 100644 --- a/include/asm-i386/rwsem.h +++ b/include/asm-i386/rwsem.h @@ -284,5 +284,10 @@ LOCK_PREFIX "xadd %0,(%2)" return tmp+delta; } +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* __KERNEL__ */ #endif /* _I386_RWSEM_H */ diff --git a/include/asm-ia64/rwsem.h b/include/asm-ia64/rwsem.h index e18b5ab0cb7..1327c91ea39 100644 --- a/include/asm-ia64/rwsem.h +++ b/include/asm-ia64/rwsem.h @@ -186,4 +186,9 @@ __downgrade_write (struct rw_semaphore *sem) #define rwsem_atomic_add(delta, sem) atomic64_add(delta, (atomic64_t *)(&(sem)->count)) #define rwsem_atomic_update(delta, sem) atomic64_add_return(delta, (atomic64_t *)(&(sem)->count)) +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* _ASM_IA64_RWSEM_H */ diff --git a/include/asm-ia64/tlb.h b/include/asm-ia64/tlb.h index 3a9a6d1be75..834370b9dea 100644 --- a/include/asm-ia64/tlb.h +++ b/include/asm-ia64/tlb.h @@ -60,7 +60,6 @@ struct mmu_gather { unsigned int nr; /* == ~0U => fast mode */ unsigned char fullmm; /* non-zero means full mm flush */ unsigned char need_flush; /* really unmapped some PTEs? */ - unsigned long freed; /* number of pages freed */ unsigned long start_addr; unsigned long end_addr; struct page *pages[FREE_PTE_NR]; @@ -129,7 +128,7 @@ ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long e 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); + struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; /* @@ -147,25 +146,17 @@ tlb_gather_mmu (struct mm_struct *mm, unsigned int full_mm_flush) */ tlb->nr = (num_online_cpus() == 1) ? ~0U : 0; tlb->fullmm = full_mm_flush; - tlb->freed = 0; tlb->start_addr = ~0UL; return tlb; } /* * Called at the end of the shootdown operation to free up any resources that were - * collected. The page table lock is still held at this point. + * collected. */ static inline void tlb_finish_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end) { - unsigned long freed = tlb->freed; - struct mm_struct *mm = tlb->mm; - unsigned long rss = get_mm_counter(mm, rss); - - if (rss < freed) - freed = rss; - add_mm_counter(mm, rss, -freed); /* * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and * tlb->end_addr. @@ -174,12 +165,8 @@ tlb_finish_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end) /* keep the page table cache within bounds */ check_pgt_cache(); -} -static inline unsigned int -tlb_is_full_mm(struct mmu_gather *tlb) -{ - return tlb->fullmm; + put_cpu_var(mmu_gathers); } /* diff --git a/include/asm-m32r/mmzone.h b/include/asm-m32r/mmzone.h index d58878ec899..adc7970a77e 100644 --- a/include/asm-m32r/mmzone.h +++ b/include/asm-m32r/mmzone.h @@ -21,12 +21,6 @@ extern struct pglist_data *node_data[]; __pgdat->node_start_pfn + __pgdat->node_spanned_pages - 1; \ }) -#define local_mapnr(kvaddr) \ -({ \ - unsigned long __pfn = __pa(kvaddr) >> PAGE_SHIFT; \ - (__pfn - node_start_pfn(pfn_to_nid(__pfn))); \ -}) - #define pfn_to_page(pfn) \ ({ \ unsigned long __pfn = pfn; \ diff --git a/include/asm-parisc/cacheflush.h b/include/asm-parisc/cacheflush.h index aa592d8c0e3..1bc3c83ee74 100644 --- a/include/asm-parisc/cacheflush.h +++ b/include/asm-parisc/cacheflush.h @@ -100,30 +100,34 @@ static inline void flush_cache_range(struct vm_area_struct *vma, /* Simple function to work out if we have an existing address translation * for a user space vma. */ -static inline pte_t *__translation_exists(struct mm_struct *mm, - unsigned long addr) +static inline int translation_exists(struct vm_area_struct *vma, + unsigned long addr, unsigned long pfn) { - pgd_t *pgd = pgd_offset(mm, addr); + pgd_t *pgd = pgd_offset(vma->vm_mm, addr); pmd_t *pmd; - pte_t *pte; + pte_t pte; if(pgd_none(*pgd)) - return NULL; + return 0; pmd = pmd_offset(pgd, addr); if(pmd_none(*pmd) || pmd_bad(*pmd)) - return NULL; + return 0; - pte = pte_offset_map(pmd, addr); + /* We cannot take the pte lock here: flush_cache_page is usually + * called with pte lock already held. Whereas flush_dcache_page + * takes flush_dcache_mmap_lock, which is lower in the hierarchy: + * the vma itself is secure, but the pte might come or go racily. + */ + pte = *pte_offset_map(pmd, addr); + /* But pte_unmap() does nothing on this architecture */ - /* The PA flush mappings show up as pte_none, but they're - * valid none the less */ - if(pte_none(*pte) && ((pte_val(*pte) & _PAGE_FLUSH) == 0)) - return NULL; - return pte; -} -#define translation_exists(vma, addr) __translation_exists((vma)->vm_mm, addr) + /* Filter out coincidental file entries and swap entries */ + if (!(pte_val(pte) & (_PAGE_FLUSH|_PAGE_PRESENT))) + return 0; + return pte_pfn(pte) == pfn; +} /* Private function to flush a page from the cache of a non-current * process. cr25 contains the Page Directory of the current user @@ -175,9 +179,8 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long { BUG_ON(!vma->vm_mm->context); - if(likely(translation_exists(vma, vmaddr))) + if (likely(translation_exists(vma, vmaddr, pfn))) __flush_cache_page(vma, vmaddr); } #endif - diff --git a/include/asm-parisc/mmzone.h b/include/asm-parisc/mmzone.h index 595d3dce120..ae039f4fd71 100644 --- a/include/asm-parisc/mmzone.h +++ b/include/asm-parisc/mmzone.h @@ -27,12 +27,6 @@ extern struct node_map_data node_data[]; }) #define node_localnr(pfn, nid) ((pfn) - node_start_pfn(nid)) -#define local_mapnr(kvaddr) \ -({ \ - unsigned long __pfn = __pa(kvaddr) >> PAGE_SHIFT; \ - (__pfn - node_start_pfn(pfn_to_nid(__pfn))); \ -}) - #define pfn_to_page(pfn) \ ({ \ unsigned long __pfn = (pfn); \ diff --git a/include/asm-parisc/tlbflush.h b/include/asm-parisc/tlbflush.h index 84af4ab1fe5..e97aa8d1eff 100644 --- a/include/asm-parisc/tlbflush.h +++ b/include/asm-parisc/tlbflush.h @@ -88,7 +88,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, if (npages >= 512) /* 2MB of space: arbitrary, should be tuned */ flush_tlb_all(); else { - + preempt_disable(); mtsp(vma->vm_mm->context,1); purge_tlb_start(); if (split_tlb) { @@ -102,6 +102,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, pdtlb(start); start += PAGE_SIZE; } + preempt_enable(); } purge_tlb_end(); } diff --git a/include/asm-ppc/rwsem.h b/include/asm-ppc/rwsem.h index 3e738f483c1..3501ea72f88 100644 --- a/include/asm-ppc/rwsem.h +++ b/include/asm-ppc/rwsem.h @@ -168,5 +168,10 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) return atomic_add_return(delta, (atomic_t *)(&sem->count)); } +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* __KERNEL__ */ #endif /* _PPC_RWSEM_XADD_H */ diff --git a/include/asm-ppc64/mmzone.h b/include/asm-ppc64/mmzone.h index ed473f4b015..80a708e7093 100644 --- a/include/asm-ppc64/mmzone.h +++ b/include/asm-ppc64/mmzone.h @@ -67,9 +67,6 @@ static inline int pa_to_nid(unsigned long pa) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) (NODE_DATA(nid)->node_end_pfn) -#define local_mapnr(kvaddr) \ - ( (__pa(kvaddr) >> PAGE_SHIFT) - node_start_pfn(kvaddr_to_nid(kvaddr)) - #ifdef CONFIG_DISCONTIGMEM /* diff --git a/include/asm-ppc64/pgtable.h b/include/asm-ppc64/pgtable.h index c83679c9d2b..2eb1778a3a1 100644 --- a/include/asm-ppc64/pgtable.h +++ b/include/asm-ppc64/pgtable.h @@ -478,10 +478,12 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long addr, #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0) +#define pte_ERROR(e) \ + printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_ERROR(e) \ - printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pud_val(e)) + printk("%s:%d: bad pud %08lx.\n", __FILE__, __LINE__, pud_val(e)) #define pgd_ERROR(e) \ printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) diff --git a/include/asm-ppc64/rwsem.h b/include/asm-ppc64/rwsem.h index bd5c2f09357..7a647fae376 100644 --- a/include/asm-ppc64/rwsem.h +++ b/include/asm-ppc64/rwsem.h @@ -163,5 +163,10 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) return atomic_add_return(delta, (atomic_t *)(&sem->count)); } +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* __KERNEL__ */ #endif /* _PPC_RWSEM_XADD_H */ diff --git a/include/asm-s390/rwsem.h b/include/asm-s390/rwsem.h index 8c0cebbfc03..0422a085dd5 100644 --- a/include/asm-s390/rwsem.h +++ b/include/asm-s390/rwsem.h @@ -351,5 +351,10 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) return new; } +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* __KERNEL__ */ #endif /* _S390_RWSEM_H */ diff --git a/include/asm-sh/rwsem.h b/include/asm-sh/rwsem.h index 1be4337f525..0262d3d1e5e 100644 --- a/include/asm-sh/rwsem.h +++ b/include/asm-sh/rwsem.h @@ -166,5 +166,10 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) return atomic_add_return(delta, (atomic_t *)(&sem->count)); } +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* __KERNEL__ */ #endif /* _ASM_SH_RWSEM_H */ diff --git a/include/asm-sparc64/rwsem.h b/include/asm-sparc64/rwsem.h index 4568ee4022d..cef5e827042 100644 --- a/include/asm-sparc64/rwsem.h +++ b/include/asm-sparc64/rwsem.h @@ -56,6 +56,11 @@ static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem) atomic_add(delta, (atomic_t *)(&sem->count)); } +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* __KERNEL__ */ #endif /* _SPARC64_RWSEM_H */ diff --git a/include/asm-sparc64/tlb.h b/include/asm-sparc64/tlb.h index 9baf57db01d..66138d959df 100644 --- a/include/asm-sparc64/tlb.h +++ b/include/asm-sparc64/tlb.h @@ -25,9 +25,8 @@ struct mmu_gather { struct mm_struct *mm; unsigned int pages_nr; unsigned int need_flush; - unsigned int tlb_frozen; + unsigned int fullmm; unsigned int tlb_nr; - unsigned long freed; unsigned long vaddrs[TLB_BATCH_NR]; struct page *pages[FREE_PTE_NR]; }; @@ -44,14 +43,13 @@ extern void flush_tlb_pending(void); static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) { - struct mmu_gather *mp = &__get_cpu_var(mmu_gathers); + struct mmu_gather *mp = &get_cpu_var(mmu_gathers); BUG_ON(mp->tlb_nr); mp->mm = mm; mp->pages_nr = num_online_cpus() > 1 ? 0U : ~0U; - mp->tlb_frozen = full_mm_flush; - mp->freed = 0; + mp->fullmm = full_mm_flush; return mp; } @@ -78,30 +76,19 @@ extern void smp_flush_tlb_mm(struct mm_struct *mm); static inline void tlb_finish_mmu(struct mmu_gather *mp, unsigned long start, unsigned long end) { - unsigned long freed = mp->freed; - struct mm_struct *mm = mp->mm; - unsigned long rss = get_mm_counter(mm, rss); - - if (rss < freed) - freed = rss; - add_mm_counter(mm, rss, -freed); - tlb_flush_mmu(mp); - if (mp->tlb_frozen) { - if (CTX_VALID(mm->context)) - do_flush_tlb_mm(mm); - mp->tlb_frozen = 0; + if (mp->fullmm) { + if (CTX_VALID(mp->mm->context)) + do_flush_tlb_mm(mp->mm); + mp->fullmm = 0; } else flush_tlb_pending(); /* keep the page table cache within bounds */ check_pgt_cache(); -} -static inline unsigned int tlb_is_full_mm(struct mmu_gather *mp) -{ - return mp->tlb_frozen; + put_cpu_var(mmu_gathers); } static inline void tlb_remove_page(struct mmu_gather *mp, struct page *page) diff --git a/include/asm-um/pgtable.h b/include/asm-um/pgtable.h index 616d02b57ea..ac64eb95586 100644 --- a/include/asm-um/pgtable.h +++ b/include/asm-um/pgtable.h @@ -138,7 +138,7 @@ extern unsigned long pg0[1024]; #define pte_clear(mm,addr,xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEWPAGE)) -#define pmd_none(x) (!(pmd_val(x) & ~_PAGE_NEWPAGE)) +#define pmd_none(x) (!((unsigned long)pmd_val(x) & ~_PAGE_NEWPAGE)) #define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE) #define pmd_present(x) (pmd_val(x) & _PAGE_PRESENT) #define pmd_clear(xp) do { pmd_val(*(xp)) = _PAGE_NEWPAGE; } while (0) diff --git a/include/asm-x86_64/rwsem.h b/include/asm-x86_64/rwsem.h index c002175b6e8..46077e9c191 100644 --- a/include/asm-x86_64/rwsem.h +++ b/include/asm-x86_64/rwsem.h @@ -274,5 +274,10 @@ LOCK_PREFIX "xaddl %0,(%2)" return tmp+delta; } +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->count != 0); +} + #endif /* __KERNEL__ */ #endif /* _X8664_RWSEM_H */ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 88af42f5e04..c937d6e6550 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -126,8 +126,8 @@ BUFFER_FNS(Eopnotsupp, eopnotsupp) /* If we *know* page->private refers to buffer_heads */ #define page_buffers(page) \ ({ \ - BUG_ON(!PagePrivate(page)); \ - ((struct buffer_head *)(page)->private); \ + BUG_ON(!PagePrivate(page)); \ + ((struct buffer_head *)page_private(page)); \ }) #define page_has_buffers(page) PagePrivate(page) @@ -219,7 +219,7 @@ static inline void attach_page_buffers(struct page *page, { page_cache_get(page); SetPagePrivate(page); - page->private = (unsigned long)head; + set_page_private(page, (unsigned long)head); } static inline void get_bh(struct buffer_head *bh) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d664330d900..0cea162b08c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -16,7 +16,6 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int); -void zap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); int hugetlb_prefault(struct address_space *, struct vm_area_struct *); int hugetlb_report_meminfo(char *); @@ -87,7 +86,6 @@ static inline unsigned long hugetlb_total_pages(void) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) #define hugetlb_prefault(mapping, vma) ({ BUG(); 0; }) -#define zap_hugepage_range(vma, start, len) BUG() #define unmap_hugepage_range(vma, start, end) BUG() #define is_hugepage_mem_enough(size) 0 #define hugetlb_report_meminfo(buf) 0 diff --git a/include/linux/memory.h b/include/linux/memory.h new file mode 100644 index 00000000000..0def328ab5c --- /dev/null +++ b/include/linux/memory.h @@ -0,0 +1,94 @@ +/* + * include/linux/memory.h - generic memory definition + * + * This is mainly for topological representation. We define the + * basic "struct memory_block" here, which can be embedded in per-arch + * definitions or NUMA information. + * + * Basic handling of the devices is done in drivers/base/memory.c + * and system devices are handled in drivers/base/sys.c. + * + * Memory block are exported via sysfs in the class/memory/devices/ + * directory. + * + */ +#ifndef _LINUX_MEMORY_H_ +#define _LINUX_MEMORY_H_ + +#include <linux/sysdev.h> +#include <linux/node.h> +#include <linux/compiler.h> + +#include <asm/semaphore.h> + +struct memory_block { + unsigned long phys_index; + unsigned long state; + /* + * This serializes all state change requests. It isn't + * held during creation because the control files are + * created long after the critical areas during + * initialization. + */ + struct semaphore state_sem; + int phys_device; /* to which fru does this belong? */ + void *hw; /* optional pointer to fw/hw data */ + int (*phys_callback)(struct memory_block *); + struct sys_device sysdev; +}; + +/* These states are exposed to userspace as text strings in sysfs */ +#define MEM_ONLINE (1<<0) /* exposed to userspace */ +#define MEM_GOING_OFFLINE (1<<1) /* exposed to userspace */ +#define MEM_OFFLINE (1<<2) /* exposed to userspace */ + +/* + * All of these states are currently kernel-internal for notifying + * kernel components and architectures. + * + * For MEM_MAPPING_INVALID, all notifier chains with priority >0 + * are called before pfn_to_page() becomes invalid. The priority=0 + * entry is reserved for the function that actually makes + * pfn_to_page() stop working. Any notifiers that want to be called + * after that should have priority <0. + */ +#define MEM_MAPPING_INVALID (1<<3) + +#ifndef CONFIG_MEMORY_HOTPLUG +static inline int memory_dev_init(void) +{ + return 0; +} +static inline int register_memory_notifier(struct notifier_block *nb) +{ + return 0; +} +static inline void unregister_memory_notifier(struct notifier_block *nb) +{ +} +#else +extern int register_memory(struct memory_block *, struct mem_section *section, struct node *); +extern int register_new_memory(struct mem_section *); +extern int unregister_memory_section(struct mem_section *); +extern int memory_dev_init(void); +extern int register_memory_notifier(struct notifier_block *nb); +extern void unregister_memory_notifier(struct notifier_block *nb); + +#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT) + +extern int invalidate_phys_mapping(unsigned long, unsigned long); +struct notifier_block; + +extern int register_memory_notifier(struct notifier_block *nb); +extern void unregister_memory_notifier(struct notifier_block *nb); + +extern struct sysdev_class memory_sysdev_class; +#endif /* CONFIG_MEMORY_HOTPLUG */ + +#define hotplug_memory_notifier(fn, pri) { \ + static struct notifier_block fn##_mem_nb = \ + { .notifier_call = fn, .priority = pri }; \ + register_memory_notifier(&fn##_mem_nb); \ +} + +#endif /* _LINUX_MEMORY_H_ */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h new file mode 100644 index 00000000000..01f03bc06ef --- /dev/null +++ b/include/linux/memory_hotplug.h @@ -0,0 +1,104 @@ +#ifndef __LINUX_MEMORY_HOTPLUG_H +#define __LINUX_MEMORY_HOTPLUG_H + +#include <linux/mmzone.h> +#include <linux/spinlock.h> +#include <linux/mmzone.h> +#include <linux/notifier.h> + +#ifdef CONFIG_MEMORY_HOTPLUG +/* + * pgdat resizing functions + */ +static inline +void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags) +{ + spin_lock_irqsave(&pgdat->node_size_lock, *flags); +} +static inline +void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags) +{ + spin_unlock_irqrestore(&pgdat->node_size_lock, *flags); +} +static inline +void pgdat_resize_init(struct pglist_data *pgdat) +{ + spin_lock_init(&pgdat->node_size_lock); +} +/* + * Zone resizing functions + */ +static inline unsigned zone_span_seqbegin(struct zone *zone) +{ + return read_seqbegin(&zone->span_seqlock); +} +static inline int zone_span_seqretry(struct zone *zone, unsigned iv) +{ + return read_seqretry(&zone->span_seqlock, iv); +} +static inline void zone_span_writelock(struct zone *zone) +{ + write_seqlock(&zone->span_seqlock); +} +static inline void zone_span_writeunlock(struct zone *zone) +{ + write_sequnlock(&zone->span_seqlock); +} +static inline void zone_seqlock_init(struct zone *zone) +{ + seqlock_init(&zone->span_seqlock); +} +extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); +extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); +extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); +/* need some defines for these for archs that don't support it */ +extern void online_page(struct page *page); +/* VM interface that may be used by firmware interface */ +extern int add_memory(u64 start, u64 size); +extern int remove_memory(u64 start, u64 size); +extern int online_pages(unsigned long, unsigned long); + +/* reasonably generic interface to expand the physical pages in a zone */ +extern int __add_pages(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages); +#else /* ! CONFIG_MEMORY_HOTPLUG */ +/* + * Stub functions for when hotplug is off + */ +static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {} +static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {} +static inline void pgdat_resize_init(struct pglist_data *pgdat) {} + +static inline unsigned zone_span_seqbegin(struct zone *zone) +{ + return 0; +} +static inline int zone_span_seqretry(struct zone *zone, unsigned iv) +{ + return 0; +} +static inline void zone_span_writelock(struct zone *zone) {} +static inline void zone_span_writeunlock(struct zone *zone) {} +static inline void zone_seqlock_init(struct zone *zone) {} + +static inline int mhp_notimplemented(const char *func) +{ + printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func); + dump_stack(); + return -ENOSYS; +} + +static inline int __add_pages(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages) +{ + return mhp_notimplemented(__FUNCTION__); +} +#endif /* ! CONFIG_MEMORY_HOTPLUG */ +static inline int __remove_pages(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages) +{ + printk(KERN_WARNING "%s() called, not yet supported\n", __FUNCTION__); + dump_stack(); + return -ENOSYS; +} +#endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 58385ee1c0a..7af8cb836e7 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -27,10 +27,10 @@ #include <linux/config.h> #include <linux/mmzone.h> -#include <linux/bitmap.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> +#include <linux/nodemask.h> struct vm_area_struct; @@ -47,8 +47,7 @@ struct vm_area_struct; * Locking policy for interlave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on - * mmap_sem. For allocating in the interleave policy the page_table_lock - * must be also aquired to protect il_next. + * mmap_sem. * * Freeing policy: * When policy is MPOL_BIND v.zonelist is kmalloc'ed and must be kfree'd. @@ -63,7 +62,7 @@ struct mempolicy { union { struct zonelist *zonelist; /* bind */ short preferred_node; /* preferred */ - DECLARE_BITMAP(nodes, MAX_NUMNODES); /* interleave */ + nodemask_t nodes; /* interleave */ /* undefined for default */ } v; }; diff --git a/include/linux/mm.h b/include/linux/mm.h index e1649578fb0..5c1fb0a2e80 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -157,7 +157,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ -#define VM_RESERVED 0x00080000 /* Don't unmap it from swap_out */ +#define VM_RESERVED 0x00080000 /* Pages managed in a special way */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ @@ -226,13 +226,18 @@ struct page { * to show when page is mapped * & limit reverse map searches. */ - unsigned long private; /* Mapping-private opaque data: + union { + unsigned long private; /* Mapping-private opaque data: * usually used for buffer_heads * if PagePrivate set; used for * swp_entry_t if PageSwapCache * When page is free, this indicates * order in the buddy system. */ +#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS + spinlock_t ptl; +#endif + } u; struct address_space *mapping; /* If low bit clear, points to * inode address_space, or NULL. * If page mapped as anonymous @@ -260,6 +265,9 @@ struct page { #endif /* WANT_PAGE_VIRTUAL */ }; +#define page_private(page) ((page)->u.private) +#define set_page_private(page, v) ((page)->u.private = (v)) + /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) @@ -311,17 +319,17 @@ extern void FASTCALL(__page_cache_release(struct page *)); #ifdef CONFIG_HUGETLB_PAGE -static inline int page_count(struct page *p) +static inline int page_count(struct page *page) { - if (PageCompound(p)) - p = (struct page *)p->private; - return atomic_read(&(p)->_count) + 1; + if (PageCompound(page)) + page = (struct page *)page_private(page); + return atomic_read(&page->_count) + 1; } static inline void get_page(struct page *page) { if (unlikely(PageCompound(page))) - page = (struct page *)page->private; + page = (struct page *)page_private(page); atomic_inc(&page->_count); } @@ -338,7 +346,7 @@ static inline void get_page(struct page *page) static inline void put_page(struct page *page) { - if (!PageReserved(page) && put_page_testzero(page)) + if (put_page_testzero(page)) __page_cache_release(page); } @@ -587,7 +595,7 @@ static inline int PageAnon(struct page *page) static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) - return page->private; + return page_private(page); return page->index; } @@ -682,7 +690,7 @@ struct zap_details { unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); -unsigned long unmap_vmas(struct mmu_gather **tlb, struct mm_struct *mm, +unsigned long unmap_vmas(struct mmu_gather **tlb, struct vm_area_struct *start_vma, unsigned long start_addr, unsigned long end_addr, unsigned long *nr_accounted, struct zap_details *); @@ -704,10 +712,6 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, } extern int vmtruncate(struct inode * inode, loff_t offset); -extern pud_t *FASTCALL(__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)); -extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)); -extern pte_t *FASTCALL(pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address)); -extern pte_t *FASTCALL(pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address)); extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot); extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot); extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access); @@ -723,6 +727,7 @@ void install_arg_page(struct vm_area_struct *, struct page *, unsigned long); int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); +void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long); int __set_page_dirty_buffers(struct page *page); int __set_page_dirty_nobuffers(struct page *page); @@ -759,38 +764,83 @@ struct shrinker; extern struct shrinker *set_shrinker(int, shrinker_t); extern void remove_shrinker(struct shrinker *shrinker); -/* - * On a two-level or three-level page table, this ends up being trivial. Thus - * the inlining and the symmetry break with pte_alloc_map() that does all - * of this out-of-line. - */ +int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); +int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); +int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address); +int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); + /* * The following ifdef needed to get the 4level-fixup.h header to work. * Remove it when 4level-fixup.h has been removed. */ -#ifdef CONFIG_MMU -#ifndef __ARCH_HAS_4LEVEL_HACK +#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { - if (pgd_none(*pgd)) - return __pud_alloc(mm, pgd, address); - return pud_offset(pgd, address); + return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))? + NULL: pud_offset(pgd, address); } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { - if (pud_none(*pud)) - return __pmd_alloc(mm, pud, address); - return pmd_offset(pud, address); + return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? + NULL: pmd_offset(pud, address); } -#endif -#endif /* CONFIG_MMU */ +#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ + +#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS +/* + * We tuck a spinlock to guard each pagetable page into its struct page, + * at page->private, with BUILD_BUG_ON to make sure that this will not + * overflow into the next struct page (as it might with DEBUG_SPINLOCK). + * When freeing, reset page->mapping so free_pages_check won't complain. + */ +#define __pte_lockptr(page) &((page)->u.ptl) +#define pte_lock_init(_page) do { \ + spin_lock_init(__pte_lockptr(_page)); \ +} while (0) +#define pte_lock_deinit(page) ((page)->mapping = NULL) +#define pte_lockptr(mm, pmd) ({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));}) +#else +/* + * We use mm->page_table_lock to guard all pagetable pages of the mm. + */ +#define pte_lock_init(page) do {} while (0) +#define pte_lock_deinit(page) do {} while (0) +#define pte_lockptr(mm, pmd) ({(void)(pmd); &(mm)->page_table_lock;}) +#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ + +#define pte_offset_map_lock(mm, pmd, address, ptlp) \ +({ \ + spinlock_t *__ptl = pte_lockptr(mm, pmd); \ + pte_t *__pte = pte_offset_map(pmd, address); \ + *(ptlp) = __ptl; \ + spin_lock(__ptl); \ + __pte; \ +}) + +#define pte_unmap_unlock(pte, ptl) do { \ + spin_unlock(ptl); \ + pte_unmap(pte); \ +} while (0) + +#define pte_alloc_map(mm, pmd, address) \ + ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ + NULL: pte_offset_map(pmd, address)) + +#define pte_alloc_map_lock(mm, pmd, address, ptlp) \ + ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ + NULL: pte_offset_map_lock(mm, pmd, address, ptlp)) + +#define pte_alloc_kernel(pmd, address) \ + ((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ + NULL: pte_offset_kernel(pmd, address)) extern void free_area_init(unsigned long * zones_size); extern void free_area_init_node(int nid, pg_data_t *pgdat, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long); +extern void setup_per_zone_pages_min(void); extern void mem_init(void); extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); @@ -834,6 +884,7 @@ extern int split_vma(struct mm_struct *, extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, struct rb_node **, struct rb_node *); +extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff); extern void exit_mmap(struct mm_struct *); @@ -894,7 +945,8 @@ void handle_ra_miss(struct address_space *mapping, unsigned long max_sane_readahead(unsigned long nr); /* Do stack extension */ -extern int expand_stack(struct vm_area_struct * vma, unsigned long address); +extern int expand_stack(struct vm_area_struct *vma, unsigned long address); +extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); @@ -917,40 +969,28 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma) return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } -extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr); +struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); +struct page *vmalloc_to_page(void *addr); +unsigned long vmalloc_to_pfn(void *addr); +int remap_pfn_range(struct vm_area_struct *, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t); -extern struct page * vmalloc_to_page(void *addr); -extern unsigned long vmalloc_to_pfn(void *addr); -extern struct page * follow_page(struct mm_struct *mm, unsigned long address, - int write); -extern int check_user_page_readable(struct mm_struct *mm, unsigned long address); -int remap_pfn_range(struct vm_area_struct *, unsigned long, - unsigned long, unsigned long, pgprot_t); +struct page *follow_page(struct mm_struct *, unsigned long address, + unsigned int foll_flags); +#define FOLL_WRITE 0x01 /* check pte is writable */ +#define FOLL_TOUCH 0x02 /* mark page accessed */ +#define FOLL_GET 0x04 /* do get_page on page */ +#define FOLL_ANON 0x08 /* give ZERO_PAGE if no pgtable */ #ifdef CONFIG_PROC_FS -void __vm_stat_account(struct mm_struct *, unsigned long, struct file *, long); +void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long); #else -static inline void __vm_stat_account(struct mm_struct *mm, +static inline void vm_stat_account(struct mm_struct *mm, unsigned long flags, struct file *file, long pages) { } #endif /* CONFIG_PROC_FS */ -static inline void vm_stat_account(struct vm_area_struct *vma) -{ - __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, - vma_pages(vma)); -} - -static inline void vm_stat_unaccount(struct vm_area_struct *vma) -{ - __vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, - -vma_pages(vma)); -} - -/* update per process rss and vm hiwater data */ -extern void update_mem_hiwater(struct task_struct *tsk); - #ifndef CONFIG_DEBUG_PAGEALLOC static inline void kernel_map_pages(struct page *page, int numpages, int enable) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7519eb4191e..f5fa3082fd6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -12,6 +12,7 @@ #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> +#include <linux/seqlock.h> #include <asm/atomic.h> /* Free memory management - zoned buddy allocator. */ @@ -137,6 +138,10 @@ struct zone { * free areas of different sizes */ spinlock_t lock; +#ifdef CONFIG_MEMORY_HOTPLUG + /* see spanned/present_pages for more description */ + seqlock_t span_seqlock; +#endif struct free_area free_area[MAX_ORDER]; @@ -220,6 +225,16 @@ struct zone { /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; + /* + * zone_start_pfn, spanned_pages and present_pages are all + * protected by span_seqlock. It is a seqlock because it has + * to be read outside of zone->lock, and it is done in the main + * allocator path. But, it is written quite infrequently. + * + * The lock is declared along with zone->lock because it is + * frequently read in proximity to zone->lock. It's good to + * give them a chance of being in the same cacheline. + */ unsigned long spanned_pages; /* total size, including holes */ unsigned long present_pages; /* amount of memory (excluding holes) */ @@ -273,6 +288,16 @@ typedef struct pglist_data { struct page *node_mem_map; #endif struct bootmem_data *bdata; +#ifdef CONFIG_MEMORY_HOTPLUG + /* + * Must be held any time you expect node_start_pfn, node_present_pages + * or node_spanned_pages stay constant. Holding this will also + * guarantee that any pfn_valid() stays that way. + * + * Nests above zone->lock and zone->size_seqlock. + */ + spinlock_t node_size_lock; +#endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page @@ -293,6 +318,8 @@ typedef struct pglist_data { #endif #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) +#include <linux/memory_hotplug.h> + extern struct pglist_data *pgdat_list; void __get_zone_counts(unsigned long *active, unsigned long *inactive, @@ -509,6 +536,7 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) return NULL; return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; } +extern int __section_nr(struct mem_section* ms); /* * We use the lower bits of the mem_map pointer to store diff --git a/include/linux/rmap.h b/include/linux/rmap.h index e80fb7ee6ef..35b30e6c8cf 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -95,8 +95,8 @@ int try_to_unmap(struct page *); /* * Called from mm/filemap_xip.c to unmap empty zero page */ -pte_t *page_check_address(struct page *, struct mm_struct *, unsigned long); - +pte_t *page_check_address(struct page *, struct mm_struct *, + unsigned long, spinlock_t **); /* * Used by swapoff to help locate where page is expected in vma. diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index b52a2af25f1..f30f805080a 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -61,5 +61,10 @@ extern void FASTCALL(__up_read(struct rw_semaphore *sem)); extern void FASTCALL(__up_write(struct rw_semaphore *sem)); extern void FASTCALL(__downgrade_write(struct rw_semaphore *sem)); +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return (sem->activity != 0); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_RWSEM_SPINLOCK_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 27519df0f98..1c30bc308ef 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -249,6 +249,36 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, extern void arch_unmap_area(struct mm_struct *, unsigned long); extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); +#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS +/* + * The mm counters are not protected by its page_table_lock, + * so must be incremented atomically. + */ +#ifdef ATOMIC64_INIT +#define set_mm_counter(mm, member, value) atomic64_set(&(mm)->_##member, value) +#define get_mm_counter(mm, member) ((unsigned long)atomic64_read(&(mm)->_##member)) +#define add_mm_counter(mm, member, value) atomic64_add(value, &(mm)->_##member) +#define inc_mm_counter(mm, member) atomic64_inc(&(mm)->_##member) +#define dec_mm_counter(mm, member) atomic64_dec(&(mm)->_##member) +typedef atomic64_t mm_counter_t; +#else /* !ATOMIC64_INIT */ +/* + * The counters wrap back to 0 at 2^32 * PAGE_SIZE, + * that is, at 16TB if using 4kB page size. + */ +#define set_mm_counter(mm, member, value) atomic_set(&(mm)->_##member, value) +#define get_mm_counter(mm, member) ((unsigned long)atomic_read(&(mm)->_##member)) +#define add_mm_counter(mm, member, value) atomic_add(value, &(mm)->_##member) +#define inc_mm_counter(mm, member) atomic_inc(&(mm)->_##member) +#define dec_mm_counter(mm, member) atomic_dec(&(mm)->_##member) +typedef atomic_t mm_counter_t; +#endif /* !ATOMIC64_INIT */ + +#else /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ +/* + * The mm counters are protected by its page_table_lock, + * so can be incremented directly. + */ #define set_mm_counter(mm, member, value) (mm)->_##member = (value) #define get_mm_counter(mm, member) ((mm)->_##member) #define add_mm_counter(mm, member, value) (mm)->_##member += (value) @@ -256,6 +286,20 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); #define dec_mm_counter(mm, member) (mm)->_##member-- typedef unsigned long mm_counter_t; +#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ + +#define get_mm_rss(mm) \ + (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss)) +#define update_hiwater_rss(mm) do { \ + unsigned long _rss = get_mm_rss(mm); \ + if ((mm)->hiwater_rss < _rss) \ + (mm)->hiwater_rss = _rss; \ +} while (0) +#define update_hiwater_vm(mm) do { \ + if ((mm)->hiwater_vm < (mm)->total_vm) \ + (mm)->hiwater_vm = (mm)->total_vm; \ +} while (0) + struct mm_struct { struct vm_area_struct * mmap; /* list of VMAs */ struct rb_root mm_rb; @@ -279,15 +323,20 @@ struct mm_struct { * by mmlist_lock */ + /* Special counters, in some configurations protected by the + * page_table_lock, in other configurations by being atomic. + */ + mm_counter_t _file_rss; + mm_counter_t _anon_rss; + + unsigned long hiwater_rss; /* High-watermark of RSS usage */ + unsigned long hiwater_vm; /* High-water virtual memory usage */ + + unsigned long total_vm, locked_vm, shared_vm, exec_vm; + unsigned long stack_vm, reserved_vm, def_flags, nr_ptes; unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; - unsigned long total_vm, locked_vm, shared_vm; - unsigned long exec_vm, stack_vm, reserved_vm, def_flags, nr_ptes; - - /* Special counters protected by the page_table_lock */ - mm_counter_t _rss; - mm_counter_t _anon_rss; unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ @@ -308,11 +357,7 @@ struct mm_struct { /* aio bits */ rwlock_t ioctx_list_lock; struct kioctx *ioctx_list; - struct kioctx default_kioctx; - - unsigned long hiwater_rss; /* High-water RSS usage */ - unsigned long hiwater_vm; /* High-water virtual memory usage */ }; struct sighand_struct { diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3701a0673d2..1d5577b2b75 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -32,10 +32,14 @@ struct vm_struct { * Highlevel APIs for driver use */ extern void *vmalloc(unsigned long size); +extern void *vmalloc_node(unsigned long size, int node); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot); -extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot); +extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, + pgprot_t prot); +extern void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, + pgprot_t prot, int node); extern void vfree(void *addr); extern void *vmap(struct page **pages, unsigned int count, @@ -48,6 +52,8 @@ extern void vunmap(void *addr); extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end); +extern struct vm_struct *get_vm_area_node(unsigned long size, + unsigned long flags, int node); extern struct vm_struct *remove_vm_area(void *addr); extern struct vm_struct *__remove_vm_area(void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, diff --git a/ipc/shm.c b/ipc/shm.c index dca90489e3b..b58c651d31a 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -233,10 +233,11 @@ static int newseg (key_t key, int shmflg, size_t size) shp->id = shm_buildid(id,shp->shm_perm.seq); shp->shm_file = file; file->f_dentry->d_inode->i_ino = shp->id; - if (shmflg & SHM_HUGETLB) - set_file_hugepages(file); - else + + /* Hugetlb ops would have already been assigned. */ + if (!(shmflg & SHM_HUGETLB)) file->f_op = &shm_file_operations; + shm_tot += numpages; shm_unlock(shp); return shp->id; diff --git a/kernel/acct.c b/kernel/acct.c index b756f527497..2e3f4a47e7d 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -553,7 +553,7 @@ void acct_update_integrals(struct task_struct *tsk) if (delta == 0) return; tsk->acct_stimexpd = tsk->stime; - tsk->acct_rss_mem1 += delta * get_mm_counter(tsk->mm, rss); + tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; } } diff --git a/kernel/exit.c b/kernel/exit.c index 3b25b182d2b..79f52b85d6e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -839,7 +839,10 @@ fastcall NORET_TYPE void do_exit(long code) preempt_count()); acct_update_integrals(tsk); - update_mem_hiwater(tsk); + if (tsk->mm) { + update_hiwater_rss(tsk->mm); + update_hiwater_vm(tsk->mm); + } group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { del_timer_sync(&tsk->signal->real_timer); diff --git a/kernel/fork.c b/kernel/fork.c index 280bd44ac44..8a069612eac 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -182,37 +182,37 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) } #ifdef CONFIG_MMU -static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm) +static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { - struct vm_area_struct * mpnt, *tmp, **pprev; + struct vm_area_struct *mpnt, *tmp, **pprev; struct rb_node **rb_link, *rb_parent; int retval; unsigned long charge; struct mempolicy *pol; down_write(&oldmm->mmap_sem); - flush_cache_mm(current->mm); + flush_cache_mm(oldmm); + down_write(&mm->mmap_sem); + mm->locked_vm = 0; mm->mmap = NULL; mm->mmap_cache = NULL; mm->free_area_cache = oldmm->mmap_base; mm->cached_hole_size = ~0UL; mm->map_count = 0; - set_mm_counter(mm, rss, 0); - set_mm_counter(mm, anon_rss, 0); cpus_clear(mm->cpu_vm_mask); mm->mm_rb = RB_ROOT; rb_link = &mm->mm_rb.rb_node; rb_parent = NULL; pprev = &mm->mmap; - for (mpnt = current->mm->mmap ; mpnt ; mpnt = mpnt->vm_next) { + for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { long pages = vma_pages(mpnt); mm->total_vm -= pages; - __vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, + vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, -pages); continue; } @@ -253,12 +253,8 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm) } /* - * Link in the new vma and copy the page table entries: - * link in first so that swapoff can see swap entries. - * Note that, exceptionally, here the vma is inserted - * without holding mm->mmap_sem. + * Link in the new vma and copy the page table entries. */ - spin_lock(&mm->page_table_lock); *pprev = tmp; pprev = &tmp->vm_next; @@ -267,8 +263,7 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm) rb_parent = &tmp->vm_rb; mm->map_count++; - retval = copy_page_range(mm, current->mm, tmp); - spin_unlock(&mm->page_table_lock); + retval = copy_page_range(mm, oldmm, tmp); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); @@ -277,9 +272,9 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm) goto out; } retval = 0; - out: - flush_tlb_mm(current->mm); + up_write(&mm->mmap_sem); + flush_tlb_mm(oldmm); up_write(&oldmm->mmap_sem); return retval; fail_nomem_policy: @@ -323,6 +318,8 @@ static struct mm_struct * mm_init(struct mm_struct * mm) INIT_LIST_HEAD(&mm->mmlist); mm->core_waiters = 0; mm->nr_ptes = 0; + set_mm_counter(mm, file_rss, 0); + set_mm_counter(mm, anon_rss, 0); spin_lock_init(&mm->page_table_lock); rwlock_init(&mm->ioctx_list_lock); mm->ioctx_list = NULL; @@ -499,7 +496,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) if (retval) goto free_pt; - mm->hiwater_rss = get_mm_counter(mm,rss); + mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; good_mm: diff --git a/kernel/futex.c b/kernel/futex.c index ca05fe6a70b..3b4d5ad44cc 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -205,15 +205,13 @@ static int get_futex_key(unsigned long uaddr, union futex_key *key) /* * Do a quick atomic lookup first - this is the fastpath. */ - spin_lock(¤t->mm->page_table_lock); - page = follow_page(mm, uaddr, 0); + page = follow_page(mm, uaddr, FOLL_TOUCH|FOLL_GET); if (likely(page != NULL)) { key->shared.pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - spin_unlock(¤t->mm->page_table_lock); + put_page(page); return 0; } - spin_unlock(¤t->mm->page_table_lock); /* * Do it the general way. diff --git a/kernel/kexec.c b/kernel/kexec.c index 36c5d9cd4cc..2c95848fbce 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -334,7 +334,7 @@ static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order) if (pages) { unsigned int count, i; pages->mapping = NULL; - pages->private = order; + set_page_private(pages, order); count = 1 << order; for (i = 0; i < count; i++) SetPageReserved(pages + i); @@ -347,7 +347,7 @@ static void kimage_free_pages(struct page *page) { unsigned int order, count, i; - order = page->private; + order = page_private(page); count = 1 << order; for (i = 0; i < count; i++) ClearPageReserved(page + i); diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c index 10bc5ec496d..016504ccfcc 100644 --- a/kernel/power/swsusp.c +++ b/kernel/power/swsusp.c @@ -578,15 +578,23 @@ static int save_highmem_zone(struct zone *zone) continue; page = pfn_to_page(pfn); /* - * This condition results from rvmalloc() sans vmalloc_32() - * and architectural memory reservations. This should be - * corrected eventually when the cases giving rise to this - * are better understood. + * PageReserved results from rvmalloc() sans vmalloc_32() + * and architectural memory reservations. + * + * rvmalloc should not cause this, because all implementations + * appear to always be using vmalloc_32 on architectures with + * highmem. This is a good thing, because we would like to save + * rvmalloc pages. + * + * It appears to be triggered by pages which do not point to + * valid memory (see arch/i386/mm/init.c:one_highpage_init(), + * which sets PageReserved if the page does not point to valid + * RAM. + * + * XXX: must remove usage of PageReserved! */ - if (PageReserved(page)) { - printk("highmem reserved page?!\n"); + if (PageReserved(page)) continue; - } BUG_ON(PageNosave(page)); if (PageNosaveFree(page)) continue; @@ -672,10 +680,9 @@ static int saveable(struct zone * zone, unsigned long * zone_pfn) return 0; page = pfn_to_page(pfn); - BUG_ON(PageReserved(page) && PageNosave(page)); if (PageNosave(page)) return 0; - if (PageReserved(page) && pfn_is_nosave(pfn)) { + if (pfn_is_nosave(pfn)) { pr_debug("[nosave pfn 0x%lx]", pfn); return 0; } diff --git a/kernel/sched.c b/kernel/sched.c index 1e5cafdf4e2..4f26c544d02 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2511,8 +2511,6 @@ void account_system_time(struct task_struct *p, int hardirq_offset, cpustat->idle = cputime64_add(cpustat->idle, tmp); /* Account for system time used */ acct_update_integrals(p); - /* Update rss highwater mark */ - update_mem_hiwater(p); } /* diff --git a/kernel/timer.c b/kernel/timer.c index 3ba10fa35b6..6a2e5f8dc72 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -752,6 +752,15 @@ static void second_overflow(void) else time_adj += (time_adj >> 2) + (time_adj >> 5); #endif +#if HZ == 250 + /* Compensate for (HZ==250) != (1 << SHIFT_HZ). + * Add 1.5625% and 0.78125% to get 255.85938; => only 0.05% error (p. 14) + */ + if (time_adj < 0) + time_adj -= (-time_adj >> 6) + (-time_adj >> 7); + else + time_adj += (time_adj >> 6) + (time_adj >> 7); +#endif #if HZ == 1000 /* Compensate for (HZ==1000) != (1 << SHIFT_HZ). * Add 1.5625% and 0.78125% to get 1023.4375; => only 0.05% error (p. 14) diff --git a/mm/Kconfig b/mm/Kconfig index 391ffc54d13..1a4473fcb2c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -111,3 +111,24 @@ config SPARSEMEM_STATIC config SPARSEMEM_EXTREME def_bool y depends on SPARSEMEM && !SPARSEMEM_STATIC + +# eventually, we can have this option just 'select SPARSEMEM' +config MEMORY_HOTPLUG + bool "Allow for memory hot-add" + depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND + +comment "Memory hotplug is currently incompatible with Software Suspend" + depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND + +# Heavily threaded applications may benefit from splitting the mm-wide +# page_table_lock, so that faults on different parts of the user address +# space can be handled with less contention: split it at this NR_CPUS. +# Default to 4 for wider testing, though 8 might be more appropriate. +# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. +# PA-RISC's debug spinlock_t is too large for the 32-bit struct page. +# +config SPLIT_PTLOCK_CPUS + int + default "4096" if ARM && !CPU_CACHE_VIPT + default "4096" if PARISC && DEBUG_SPINLOCK && !64BIT + default "4" diff --git a/mm/Makefile b/mm/Makefile index 4cd69e3ce42..2fa6d2ca9f2 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -18,5 +18,5 @@ obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SHMEM) += shmem.o obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o - +obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-$(CONFIG_FS_XIP) += filemap_xip.o diff --git a/mm/bootmem.c b/mm/bootmem.c index a58699b6579..e8c567177dc 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -305,6 +305,7 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat) if (j + 16 < BITS_PER_LONG) prefetchw(page + j + 16); __ClearPageReserved(page + j); + set_page_count(page + j, 0); } __free_pages(page, order); i += BITS_PER_LONG; diff --git a/mm/filemap.c b/mm/filemap.c index 1c31b2fd2ca..768687f1d46 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -66,7 +66,7 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * * ->mmap_sem * ->i_mmap_lock - * ->page_table_lock (various places, mainly in mmap.c) + * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->mapping->tree_lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_sem @@ -86,9 +86,9 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * ->anon_vma.lock (vma_adjust) * * ->anon_vma.lock - * ->page_table_lock (anon_vma_prepare and various) + * ->page_table_lock or pte_lock (anon_vma_prepare and various) * - * ->page_table_lock + * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->tree_lock (try_to_unmap_one) @@ -152,7 +152,7 @@ static int sync_page(void *word) * in the ->sync_page() methods make essential use of the * page_mapping(), merely passing the page down to the backing * device's unplug functions when it's non-NULL, which in turn - * ignore it for all cases but swap, where only page->private is + * ignore it for all cases but swap, where only page_private(page) is * of interest. When page_mapping() does go NULL, the entire * call stack gracefully ignores the page and returns. * -- wli @@ -1520,7 +1520,7 @@ repeat: page_cache_release(page); return err; } - } else { + } else if (vma->vm_flags & VM_NONLINEAR) { /* No page was found just because we can't read it in now (being * here implies nonblock != 0), but the page may exist, so set * the PTE to fault it in later. */ @@ -1537,6 +1537,7 @@ repeat: return 0; } +EXPORT_SYMBOL(filemap_populate); struct vm_operations_struct generic_file_vm_ops = { .nopage = filemap_nopage, @@ -1555,7 +1556,6 @@ int generic_file_mmap(struct file * file, struct vm_area_struct * vma) vma->vm_ops = &generic_file_vm_ops; return 0; } -EXPORT_SYMBOL(filemap_populate); /* * This is for filesystems which do not implement ->writepage. diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 8c199f53773..9cf687e4a29 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -174,6 +174,8 @@ __xip_unmap (struct address_space * mapping, unsigned long address; pte_t *pte; pte_t pteval; + spinlock_t *ptl; + struct page *page; spin_lock(&mapping->i_mmap_lock); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { @@ -181,19 +183,17 @@ __xip_unmap (struct address_space * mapping, address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); BUG_ON(address < vma->vm_start || address >= vma->vm_end); - /* - * We need the page_table_lock to protect us from page faults, - * munmap, fork, etc... - */ - pte = page_check_address(ZERO_PAGE(address), mm, - address); - if (!IS_ERR(pte)) { + page = ZERO_PAGE(address); + pte = page_check_address(page, mm, address, &ptl); + if (pte) { /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pte)); pteval = ptep_clear_flush(vma, address, pte); + page_remove_rmap(page); + dec_mm_counter(mm, file_rss); BUG_ON(pte_dirty(pteval)); - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(pte, ptl); + page_cache_release(page); } } spin_unlock(&mapping->i_mmap_lock); @@ -228,7 +228,7 @@ xip_file_nopage(struct vm_area_struct * area, page = mapping->a_ops->get_xip_page(mapping, pgoff*(PAGE_SIZE/512), 0); if (!IS_ERR(page)) { - return page; + goto out; } if (PTR_ERR(page) != -ENODATA) return NULL; @@ -249,6 +249,8 @@ xip_file_nopage(struct vm_area_struct * area, page = ZERO_PAGE(address); } +out: + page_cache_get(page); return page; } diff --git a/mm/fremap.c b/mm/fremap.c index ab23a0673c3..d862be3bc3e 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -20,33 +20,32 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> -static inline void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, +static int zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte = *ptep; + struct page *page = NULL; - if (pte_none(pte)) - return; if (pte_present(pte)) { unsigned long pfn = pte_pfn(pte); - flush_cache_page(vma, addr, pfn); pte = ptep_clear_flush(vma, addr, ptep); - if (pfn_valid(pfn)) { - struct page *page = pfn_to_page(pfn); - if (!PageReserved(page)) { - if (pte_dirty(pte)) - set_page_dirty(page); - page_remove_rmap(page); - page_cache_release(page); - dec_mm_counter(mm, rss); - } + if (unlikely(!pfn_valid(pfn))) { + print_bad_pte(vma, pte, addr); + goto out; } + page = pfn_to_page(pfn); + if (pte_dirty(pte)) + set_page_dirty(page); + page_remove_rmap(page); + page_cache_release(page); } else { if (!pte_file(pte)) free_swap_and_cache(pte_to_swp_entry(pte)); pte_clear(mm, addr, ptep); } +out: + return !!page; } /* @@ -64,21 +63,20 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma, pud_t *pud; pgd_t *pgd; pte_t pte_val; + spinlock_t *ptl; + + BUG_ON(vma->vm_flags & VM_RESERVED); pgd = pgd_offset(mm, addr); - spin_lock(&mm->page_table_lock); - pud = pud_alloc(mm, pgd, addr); if (!pud) - goto err_unlock; - + goto out; pmd = pmd_alloc(mm, pud, addr); if (!pmd) - goto err_unlock; - - pte = pte_alloc_map(mm, pmd, addr); + goto out; + pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) - goto err_unlock; + goto out; /* * This page may have been truncated. Tell the @@ -88,29 +86,27 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma, inode = vma->vm_file->f_mapping->host; size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; if (!page->mapping || page->index >= size) - goto err_unlock; + goto unlock; err = -ENOMEM; if (page_mapcount(page) > INT_MAX/2) - goto err_unlock; + goto unlock; - zap_pte(mm, vma, addr, pte); + if (pte_none(*pte) || !zap_pte(mm, vma, addr, pte)) + inc_mm_counter(mm, file_rss); - inc_mm_counter(mm,rss); flush_icache_page(vma, page); set_pte_at(mm, addr, pte, mk_pte(page, prot)); page_add_file_rmap(page); pte_val = *pte; - pte_unmap(pte); update_mmu_cache(vma, addr, pte_val); - err = 0; -err_unlock: - spin_unlock(&mm->page_table_lock); +unlock: + pte_unmap_unlock(pte, ptl); +out: return err; } EXPORT_SYMBOL(install_page); - /* * Install a file pte to a given virtual memory address, release any * previously existing mapping. @@ -124,37 +120,35 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, pud_t *pud; pgd_t *pgd; pte_t pte_val; + spinlock_t *ptl; + + BUG_ON(vma->vm_flags & VM_RESERVED); pgd = pgd_offset(mm, addr); - spin_lock(&mm->page_table_lock); - pud = pud_alloc(mm, pgd, addr); if (!pud) - goto err_unlock; - + goto out; pmd = pmd_alloc(mm, pud, addr); if (!pmd) - goto err_unlock; - - pte = pte_alloc_map(mm, pmd, addr); + goto out; + pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) - goto err_unlock; + goto out; - zap_pte(mm, vma, addr, pte); + if (!pte_none(*pte) && zap_pte(mm, vma, addr, pte)) { + update_hiwater_rss(mm); + dec_mm_counter(mm, file_rss); + } set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff)); pte_val = *pte; - pte_unmap(pte); update_mmu_cache(vma, addr, pte_val); - spin_unlock(&mm->page_table_lock); - return 0; - -err_unlock: - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(pte, ptl); + err = 0; +out: return err; } - /*** * sys_remap_file_pages - remap arbitrary pages of a shared backing store * file within an existing vma. diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 61d38067803..c9b43360fd3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -277,19 +277,23 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, unsigned long addr; for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) { + src_pte = huge_pte_offset(src, addr); + if (!src_pte) + continue; dst_pte = huge_pte_alloc(dst, addr); if (!dst_pte) goto nomem; + spin_lock(&dst->page_table_lock); spin_lock(&src->page_table_lock); - src_pte = huge_pte_offset(src, addr); - if (src_pte && !pte_none(*src_pte)) { + if (!pte_none(*src_pte)) { entry = *src_pte; ptepage = pte_page(entry); get_page(ptepage); - add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE); + add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE); set_huge_pte_at(dst, addr, dst_pte, entry); } spin_unlock(&src->page_table_lock); + spin_unlock(&dst->page_table_lock); } return 0; @@ -310,12 +314,14 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, BUG_ON(start & ~HPAGE_MASK); BUG_ON(end & ~HPAGE_MASK); + spin_lock(&mm->page_table_lock); + + /* Update high watermark before we lower rss */ + update_hiwater_rss(mm); + for (address = start; address < end; address += HPAGE_SIZE) { ptep = huge_pte_offset(mm, address); - if (! ptep) - /* This can happen on truncate, or if an - * mmap() is aborted due to an error before - * the prefault */ + if (!ptep) continue; pte = huge_ptep_get_and_clear(mm, address, ptep); @@ -324,96 +330,99 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, page = pte_page(pte); put_page(page); - add_mm_counter(mm, rss, - (HPAGE_SIZE / PAGE_SIZE)); + add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE)); } - flush_tlb_range(vma, start, end); -} - -void zap_hugepage_range(struct vm_area_struct *vma, - unsigned long start, unsigned long length) -{ - struct mm_struct *mm = vma->vm_mm; - spin_lock(&mm->page_table_lock); - unmap_hugepage_range(vma, start, start + length); spin_unlock(&mm->page_table_lock); + flush_tlb_range(vma, start, end); } -int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma) +static struct page *find_lock_huge_page(struct address_space *mapping, + unsigned long idx) { - struct mm_struct *mm = current->mm; - unsigned long addr; - int ret = 0; - - WARN_ON(!is_vm_hugetlb_page(vma)); - BUG_ON(vma->vm_start & ~HPAGE_MASK); - BUG_ON(vma->vm_end & ~HPAGE_MASK); - - hugetlb_prefault_arch_hook(mm); - - spin_lock(&mm->page_table_lock); - for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) { - unsigned long idx; - pte_t *pte = huge_pte_alloc(mm, addr); - struct page *page; - - if (!pte) { - ret = -ENOMEM; - goto out; - } + struct page *page; + int err; + struct inode *inode = mapping->host; + unsigned long size; + +retry: + page = find_lock_page(mapping, idx); + if (page) + goto out; + + /* Check to make sure the mapping hasn't been truncated */ + size = i_size_read(inode) >> HPAGE_SHIFT; + if (idx >= size) + goto out; + + if (hugetlb_get_quota(mapping)) + goto out; + page = alloc_huge_page(); + if (!page) { + hugetlb_put_quota(mapping); + goto out; + } - idx = ((addr - vma->vm_start) >> HPAGE_SHIFT) - + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); - page = find_get_page(mapping, idx); - if (!page) { - /* charge the fs quota first */ - if (hugetlb_get_quota(mapping)) { - ret = -ENOMEM; - goto out; - } - page = alloc_huge_page(); - if (!page) { - hugetlb_put_quota(mapping); - ret = -ENOMEM; - goto out; - } - ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC); - if (! ret) { - unlock_page(page); - } else { - hugetlb_put_quota(mapping); - free_huge_page(page); - goto out; - } - } - add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE); - set_huge_pte_at(mm, addr, pte, make_huge_pte(vma, page)); + err = add_to_page_cache(page, mapping, idx, GFP_KERNEL); + if (err) { + put_page(page); + hugetlb_put_quota(mapping); + if (err == -EEXIST) + goto retry; + page = NULL; } out: - spin_unlock(&mm->page_table_lock); - return ret; + return page; } -/* - * On ia64 at least, it is possible to receive a hugetlb fault from a - * stale zero entry left in the TLB from earlier hardware prefetching. - * Low-level arch code should already have flushed the stale entry as - * part of its fault handling, but we do need to accept this minor fault - * and return successfully. Whereas the "normal" case is that this is - * an access to a hugetlb page which has been truncated off since mmap. - */ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access) { int ret = VM_FAULT_SIGBUS; + unsigned long idx; + unsigned long size; pte_t *pte; + struct page *page; + struct address_space *mapping; + + pte = huge_pte_alloc(mm, address); + if (!pte) + goto out; + + mapping = vma->vm_file->f_mapping; + idx = ((address - vma->vm_start) >> HPAGE_SHIFT) + + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); + + /* + * Use page lock to guard against racing truncation + * before we get page_table_lock. + */ + page = find_lock_huge_page(mapping, idx); + if (!page) + goto out; spin_lock(&mm->page_table_lock); - pte = huge_pte_offset(mm, address); - if (pte && !pte_none(*pte)) - ret = VM_FAULT_MINOR; + size = i_size_read(mapping->host) >> HPAGE_SHIFT; + if (idx >= size) + goto backout; + + ret = VM_FAULT_MINOR; + if (!pte_none(*pte)) + goto backout; + + add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE); + set_huge_pte_at(mm, address, pte, make_huge_pte(vma, page)); spin_unlock(&mm->page_table_lock); + unlock_page(page); +out: return ret; + +backout: + spin_unlock(&mm->page_table_lock); + hugetlb_put_quota(mapping); + unlock_page(page); + put_page(page); + goto out; } int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, @@ -423,34 +432,36 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long vpfn, vaddr = *position; int remainder = *length; - BUG_ON(!is_vm_hugetlb_page(vma)); - vpfn = vaddr/PAGE_SIZE; spin_lock(&mm->page_table_lock); while (vaddr < vma->vm_end && remainder) { + pte_t *pte; + struct page *page; - if (pages) { - pte_t *pte; - struct page *page; - - /* Some archs (sparc64, sh*) have multiple - * pte_ts to each hugepage. We have to make - * sure we get the first, for the page - * indexing below to work. */ - pte = huge_pte_offset(mm, vaddr & HPAGE_MASK); - - /* the hugetlb file might have been truncated */ - if (!pte || pte_none(*pte)) { - remainder = 0; - if (!i) - i = -EFAULT; - break; - } + /* + * Some archs (sparc64, sh*) have multiple pte_ts to + * each hugepage. We have to make * sure we get the + * first, for the page indexing below to work. + */ + pte = huge_pte_offset(mm, vaddr & HPAGE_MASK); - page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)]; + if (!pte || pte_none(*pte)) { + int ret; - WARN_ON(!PageCompound(page)); + spin_unlock(&mm->page_table_lock); + ret = hugetlb_fault(mm, vma, vaddr, 0); + spin_lock(&mm->page_table_lock); + if (ret == VM_FAULT_MINOR) + continue; + + remainder = 0; + if (!i) + i = -EFAULT; + break; + } + if (pages) { + page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)]; get_page(page); pages[i] = page; } diff --git a/mm/madvise.c b/mm/madvise.c index 20e075d1c64..17aaf3e1644 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -126,7 +126,7 @@ static long madvise_dontneed(struct vm_area_struct * vma, unsigned long start, unsigned long end) { *prev = vma; - if ((vma->vm_flags & VM_LOCKED) || is_vm_hugetlb_page(vma)) + if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_RESERVED)) return -EINVAL; if (unlikely(vma->vm_flags & VM_NONLINEAR)) { diff --git a/mm/memory.c b/mm/memory.c index 1db40e935e5..0f60baf6f69 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -114,6 +114,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd) { struct page *page = pmd_page(*pmd); pmd_clear(pmd); + pte_lock_deinit(page); pte_free_tlb(tlb, page); dec_page_state(nr_page_table_pages); tlb->mm->nr_ptes--; @@ -249,7 +250,7 @@ void free_pgd_range(struct mmu_gather **tlb, free_pud_range(*tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); - if (!tlb_is_full_mm(*tlb)) + if (!(*tlb)->fullmm) flush_tlb_pgtables((*tlb)->mm, start, end); } @@ -260,6 +261,12 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, struct vm_area_struct *next = vma->vm_next; unsigned long addr = vma->vm_start; + /* + * Hide vma from rmap and vmtruncate before freeing pgtables + */ + anon_vma_unlink(vma); + unlink_file_vma(vma); + if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next? next->vm_start: ceiling); @@ -272,6 +279,8 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, HPAGE_SIZE)) { vma = next; next = vma->vm_next; + anon_vma_unlink(vma); + unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, floor, next? next->vm_start: ceiling); @@ -280,72 +289,78 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma, } } -pte_t fastcall *pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, - unsigned long address) +int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { - if (!pmd_present(*pmd)) { - struct page *new; - - spin_unlock(&mm->page_table_lock); - new = pte_alloc_one(mm, address); - spin_lock(&mm->page_table_lock); - if (!new) - return NULL; - /* - * Because we dropped the lock, we should re-check the - * entry, as somebody else could have populated it.. - */ - if (pmd_present(*pmd)) { - pte_free(new); - goto out; - } + struct page *new = pte_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + pte_lock_init(new); + spin_lock(&mm->page_table_lock); + if (pmd_present(*pmd)) { /* Another has populated it */ + pte_lock_deinit(new); + pte_free(new); + } else { mm->nr_ptes++; inc_page_state(nr_page_table_pages); pmd_populate(mm, pmd, new); } -out: - return pte_offset_map(pmd, address); + spin_unlock(&mm->page_table_lock); + return 0; } -pte_t fastcall * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address) +int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) { - if (!pmd_present(*pmd)) { - pte_t *new; + pte_t *new = pte_alloc_one_kernel(&init_mm, address); + if (!new) + return -ENOMEM; - spin_unlock(&mm->page_table_lock); - new = pte_alloc_one_kernel(mm, address); - spin_lock(&mm->page_table_lock); - if (!new) - return NULL; + spin_lock(&init_mm.page_table_lock); + if (pmd_present(*pmd)) /* Another has populated it */ + pte_free_kernel(new); + else + pmd_populate_kernel(&init_mm, pmd, new); + spin_unlock(&init_mm.page_table_lock); + return 0; +} - /* - * Because we dropped the lock, we should re-check the - * entry, as somebody else could have populated it.. - */ - if (pmd_present(*pmd)) { - pte_free_kernel(new); - goto out; - } - pmd_populate_kernel(mm, pmd, new); - } -out: - return pte_offset_kernel(pmd, address); +static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) +{ + if (file_rss) + add_mm_counter(mm, file_rss, file_rss); + if (anon_rss) + add_mm_counter(mm, anon_rss, anon_rss); +} + +/* + * This function is called to print an error when a pte in a + * !VM_RESERVED region is found pointing to an invalid pfn (which + * is an error. + * + * The calling function must still handle the error. + */ +void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr) +{ + printk(KERN_ERR "Bad pte = %08llx, process = %s, " + "vm_flags = %lx, vaddr = %lx\n", + (long long)pte_val(pte), + (vma->vm_mm == current->mm ? current->comm : "???"), + vma->vm_flags, vaddr); + dump_stack(); } /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. - * - * dst->page_table_lock is held on entry and exit, - * but may be dropped within p[mg]d_alloc() and pte_alloc_map(). */ static inline void copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pte_t *dst_pte, pte_t *src_pte, unsigned long vm_flags, - unsigned long addr) + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, + unsigned long addr, int *rss) { + unsigned long vm_flags = vma->vm_flags; pte_t pte = *src_pte; struct page *page; unsigned long pfn; @@ -357,29 +372,32 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); - list_add(&dst_mm->mmlist, &src_mm->mmlist); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); spin_unlock(&mmlist_lock); } } - set_pte_at(dst_mm, addr, dst_pte, pte); - return; + goto out_set_pte; } - pfn = pte_pfn(pte); - /* the pte points outside of valid memory, the - * mapping is assumed to be good, meaningful - * and not mapped via rmap - duplicate the - * mapping as is. + /* If the region is VM_RESERVED, the mapping is not + * mapped via rmap - duplicate the pte as is. */ - page = NULL; - if (pfn_valid(pfn)) - page = pfn_to_page(pfn); + if (vm_flags & VM_RESERVED) + goto out_set_pte; - if (!page || PageReserved(page)) { - set_pte_at(dst_mm, addr, dst_pte, pte); - return; + pfn = pte_pfn(pte); + /* If the pte points outside of valid memory but + * the region is not VM_RESERVED, we have a problem. + */ + if (unlikely(!pfn_valid(pfn))) { + print_bad_pte(vma, pte, addr); + goto out_set_pte; /* try to do something sane */ } + page = pfn_to_page(pfn); + /* * If it's a COW mapping, write protect it both * in the parent and the child @@ -397,11 +415,11 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte = pte_mkclean(pte); pte = pte_mkold(pte); get_page(page); - inc_mm_counter(dst_mm, rss); - if (PageAnon(page)) - inc_mm_counter(dst_mm, anon_rss); - set_pte_at(dst_mm, addr, dst_pte, pte); page_dup_rmap(page); + rss[!!PageAnon(page)]++; + +out_set_pte: + set_pte_at(dst_mm, addr, dst_pte, pte); } static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, @@ -409,38 +427,44 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long addr, unsigned long end) { pte_t *src_pte, *dst_pte; - unsigned long vm_flags = vma->vm_flags; - int progress; + spinlock_t *src_ptl, *dst_ptl; + int progress = 0; + int rss[2]; again: - dst_pte = pte_alloc_map(dst_mm, dst_pmd, addr); + rss[1] = rss[0] = 0; + dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) return -ENOMEM; src_pte = pte_offset_map_nested(src_pmd, addr); + src_ptl = pte_lockptr(src_mm, src_pmd); + spin_lock(src_ptl); - progress = 0; - spin_lock(&src_mm->page_table_lock); do { /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ - if (progress >= 32 && (need_resched() || - need_lockbreak(&src_mm->page_table_lock) || - need_lockbreak(&dst_mm->page_table_lock))) - break; + if (progress >= 32) { + progress = 0; + if (need_resched() || + need_lockbreak(src_ptl) || + need_lockbreak(dst_ptl)) + break; + } if (pte_none(*src_pte)) { progress++; continue; } - copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vm_flags, addr); + copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss); progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); - spin_unlock(&src_mm->page_table_lock); + spin_unlock(src_ptl); pte_unmap_nested(src_pte - 1); - pte_unmap(dst_pte - 1); - cond_resched_lock(&dst_mm->page_table_lock); + add_mm_rss(dst_mm, rss[0], rss[1]); + pte_unmap_unlock(dst_pte - 1, dst_ptl); + cond_resched(); if (addr != end) goto again; return 0; @@ -525,24 +549,30 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, return 0; } -static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd, +static void zap_pte_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { + struct mm_struct *mm = tlb->mm; pte_t *pte; + spinlock_t *ptl; + int file_rss = 0; + int anon_rss = 0; - pte = pte_offset_map(pmd, addr); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); do { pte_t ptent = *pte; if (pte_none(ptent)) continue; if (pte_present(ptent)) { struct page *page = NULL; - unsigned long pfn = pte_pfn(ptent); - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (PageReserved(page)) - page = NULL; + if (!(vma->vm_flags & VM_RESERVED)) { + unsigned long pfn = pte_pfn(ptent); + if (unlikely(!pfn_valid(pfn))) + print_bad_pte(vma, ptent, addr); + else + page = pfn_to_page(pfn); } if (unlikely(details) && page) { /* @@ -562,7 +592,7 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd, page->index > details->last_index)) continue; } - ptent = ptep_get_and_clear_full(tlb->mm, addr, pte, + ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) @@ -570,15 +600,17 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd, if (unlikely(details) && details->nonlinear_vma && linear_page_index(details->nonlinear_vma, addr) != page->index) - set_pte_at(tlb->mm, addr, pte, + set_pte_at(mm, addr, pte, pgoff_to_pte(page->index)); - if (pte_dirty(ptent)) - set_page_dirty(page); if (PageAnon(page)) - dec_mm_counter(tlb->mm, anon_rss); - else if (pte_young(ptent)) - mark_page_accessed(page); - tlb->freed++; + anon_rss--; + else { + if (pte_dirty(ptent)) + set_page_dirty(page); + if (pte_young(ptent)) + mark_page_accessed(page); + file_rss--; + } page_remove_rmap(page); tlb_remove_page(tlb, page); continue; @@ -591,12 +623,15 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd, continue; if (!pte_file(ptent)) free_swap_and_cache(pte_to_swp_entry(ptent)); - pte_clear_full(tlb->mm, addr, pte, tlb->fullmm); + pte_clear_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(pte - 1); + + add_mm_rss(mm, file_rss, anon_rss); + pte_unmap_unlock(pte - 1, ptl); } -static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud, +static inline void zap_pmd_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { @@ -608,11 +643,12 @@ static inline void zap_pmd_range(struct mmu_gather *tlb, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; - zap_pte_range(tlb, pmd, addr, next, details); + zap_pte_range(tlb, vma, pmd, addr, next, details); } while (pmd++, addr = next, addr != end); } -static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd, +static inline void zap_pud_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { @@ -624,7 +660,7 @@ static inline void zap_pud_range(struct mmu_gather *tlb, pgd_t *pgd, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - zap_pmd_range(tlb, pud, addr, next, details); + zap_pmd_range(tlb, vma, pud, addr, next, details); } while (pud++, addr = next, addr != end); } @@ -645,7 +681,7 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - zap_pud_range(tlb, pgd, addr, next, details); + zap_pud_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } @@ -660,7 +696,6 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlbp: address of the caller's struct mmu_gather - * @mm: the controlling mm_struct * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping @@ -669,10 +704,10 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * * Returns the end address of the unmapping (restart addr if interrupted). * - * Unmap all pages in the vma list. Called under page_table_lock. + * Unmap all pages in the vma list. * - * We aim to not hold page_table_lock for too long (for scheduling latency - * reasons). So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to + * We aim to not hold locks for too long (for scheduling latency reasons). + * So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to * return the ending mmu_gather to the caller. * * Only addresses between `start' and `end' will be unmapped. @@ -684,7 +719,7 @@ static void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ -unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm, +unsigned long unmap_vmas(struct mmu_gather **tlbp, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, unsigned long *nr_accounted, struct zap_details *details) @@ -694,7 +729,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm, int tlb_start_valid = 0; unsigned long start = start_addr; spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; - int fullmm = tlb_is_full_mm(*tlbp); + int fullmm = (*tlbp)->fullmm; for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { unsigned long end; @@ -734,19 +769,15 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, struct mm_struct *mm, tlb_finish_mmu(*tlbp, tlb_start, start); if (need_resched() || - need_lockbreak(&mm->page_table_lock) || (i_mmap_lock && need_lockbreak(i_mmap_lock))) { if (i_mmap_lock) { - /* must reset count of rss freed */ - *tlbp = tlb_gather_mmu(mm, fullmm); + *tlbp = NULL; goto out; } - spin_unlock(&mm->page_table_lock); cond_resched(); - spin_lock(&mm->page_table_lock); } - *tlbp = tlb_gather_mmu(mm, fullmm); + *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm); tlb_start_valid = 0; zap_bytes = ZAP_BLOCK_SIZE; } @@ -770,123 +801,93 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long end = address + size; unsigned long nr_accounted = 0; - if (is_vm_hugetlb_page(vma)) { - zap_hugepage_range(vma, address, size); - return end; - } - lru_add_drain(); - spin_lock(&mm->page_table_lock); tlb = tlb_gather_mmu(mm, 0); - end = unmap_vmas(&tlb, mm, vma, address, end, &nr_accounted, details); - tlb_finish_mmu(tlb, address, end); - spin_unlock(&mm->page_table_lock); + update_hiwater_rss(mm); + end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details); + if (tlb) + tlb_finish_mmu(tlb, address, end); return end; } /* * Do a quick page-table lookup for a single page. - * mm->page_table_lock must be held. */ -static struct page *__follow_page(struct mm_struct *mm, unsigned long address, - int read, int write, int accessed) +struct page *follow_page(struct mm_struct *mm, unsigned long address, + unsigned int flags) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; + spinlock_t *ptl; unsigned long pfn; struct page *page; - page = follow_huge_addr(mm, address, write); - if (! IS_ERR(page)) - return page; + page = follow_huge_addr(mm, address, flags & FOLL_WRITE); + if (!IS_ERR(page)) { + BUG_ON(flags & FOLL_GET); + goto out; + } + page = NULL; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - goto out; + goto no_page_table; pud = pud_offset(pgd, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) - goto out; + goto no_page_table; pmd = pmd_offset(pud, address); if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + goto no_page_table; + + if (pmd_huge(*pmd)) { + BUG_ON(flags & FOLL_GET); + page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); goto out; - if (pmd_huge(*pmd)) - return follow_huge_pmd(mm, address, pmd, write); + } - ptep = pte_offset_map(pmd, address); + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) goto out; pte = *ptep; - pte_unmap(ptep); - if (pte_present(pte)) { - if (write && !pte_write(pte)) - goto out; - if (read && !pte_read(pte)) - goto out; - pfn = pte_pfn(pte); - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (accessed) { - if (write && !pte_dirty(pte) &&!PageDirty(page)) - set_page_dirty(page); - mark_page_accessed(page); - } - return page; - } + if (!pte_present(pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + pfn = pte_pfn(pte); + if (!pfn_valid(pfn)) + goto unlock; + + page = pfn_to_page(pfn); + if (flags & FOLL_GET) + get_page(page); + if (flags & FOLL_TOUCH) { + if ((flags & FOLL_WRITE) && + !pte_dirty(pte) && !PageDirty(page)) + set_page_dirty(page); + mark_page_accessed(page); } - +unlock: + pte_unmap_unlock(ptep, ptl); out: - return NULL; -} - -inline struct page * -follow_page(struct mm_struct *mm, unsigned long address, int write) -{ - return __follow_page(mm, address, 0, write, 1); -} - -/* - * check_user_page_readable() can be called frm niterrupt context by oprofile, - * so we need to avoid taking any non-irq-safe locks - */ -int check_user_page_readable(struct mm_struct *mm, unsigned long address) -{ - return __follow_page(mm, address, 1, 0, 0) != NULL; -} -EXPORT_SYMBOL(check_user_page_readable); - -static inline int -untouched_anonymous_page(struct mm_struct* mm, struct vm_area_struct *vma, - unsigned long address) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - - /* Check if the vma is for an anonymous mapping. */ - if (vma->vm_ops && vma->vm_ops->nopage) - return 0; - - /* Check if page directory entry exists. */ - pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return 1; - - pud = pud_offset(pgd, address); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) - return 1; - - /* Check if page middle directory entry exists. */ - pmd = pmd_offset(pud, address); - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) - return 1; + return page; - /* There is a pte slot for 'address' in 'mm'. */ - return 0; +no_page_table: + /* + * When core dumping an enormous anonymous area that nobody + * has touched so far, we don't want to allocate page tables. + */ + if (flags & FOLL_ANON) { + page = ZERO_PAGE(address); + if (flags & FOLL_GET) + get_page(page); + BUG_ON(flags & FOLL_WRITE); + } + return page; } int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, @@ -894,18 +895,19 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, struct page **pages, struct vm_area_struct **vmas) { int i; - unsigned int flags; + unsigned int vm_flags; /* * Require read or write permissions. * If 'force' is set, we only require the "MAY" flags. */ - flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); - flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); + vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); + vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); i = 0; do { - struct vm_area_struct * vma; + struct vm_area_struct *vma; + unsigned int foll_flags; vma = find_extend_vma(mm, start); if (!vma && in_gate_area(tsk, start)) { @@ -945,8 +947,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, continue; } - if (!vma || (vma->vm_flags & VM_IO) - || !(flags & vma->vm_flags)) + if (!vma || (vma->vm_flags & (VM_IO | VM_RESERVED)) + || !(vm_flags & vma->vm_flags)) return i ? : -EFAULT; if (is_vm_hugetlb_page(vma)) { @@ -954,29 +956,25 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, &start, &len, i); continue; } - spin_lock(&mm->page_table_lock); + + foll_flags = FOLL_TOUCH; + if (pages) + foll_flags |= FOLL_GET; + if (!write && !(vma->vm_flags & VM_LOCKED) && + (!vma->vm_ops || !vma->vm_ops->nopage)) + foll_flags |= FOLL_ANON; + do { - int write_access = write; struct page *page; - cond_resched_lock(&mm->page_table_lock); - while (!(page = follow_page(mm, start, write_access))) { - int ret; - - /* - * Shortcut for anonymous pages. We don't want - * to force the creation of pages tables for - * insanely big anonymously mapped areas that - * nobody touched so far. This is important - * for doing a core dump for these mappings. - */ - if (!write && untouched_anonymous_page(mm,vma,start)) { - page = ZERO_PAGE(start); - break; - } - spin_unlock(&mm->page_table_lock); - ret = __handle_mm_fault(mm, vma, start, write_access); + if (write) + foll_flags |= FOLL_WRITE; + cond_resched(); + while (!(page = follow_page(mm, start, foll_flags))) { + int ret; + ret = __handle_mm_fault(mm, vma, start, + foll_flags & FOLL_WRITE); /* * The VM_FAULT_WRITE bit tells us that do_wp_page has * broken COW when necessary, even if maybe_mkwrite @@ -984,7 +982,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, * subsequent page lookups as if they were reads. */ if (ret & VM_FAULT_WRITE) - write_access = 0; + foll_flags &= ~FOLL_WRITE; switch (ret & ~VM_FAULT_WRITE) { case VM_FAULT_MINOR: @@ -1000,13 +998,10 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, default: BUG(); } - spin_lock(&mm->page_table_lock); } if (pages) { pages[i] = page; flush_dcache_page(page); - if (!PageReserved(page)) - page_cache_get(page); } if (vmas) vmas[i] = vma; @@ -1014,7 +1009,6 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, start += PAGE_SIZE; len--; } while (len && start < vma->vm_end); - spin_unlock(&mm->page_table_lock); } while (len); return i; } @@ -1024,16 +1018,21 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot) { pte_t *pte; + spinlock_t *ptl; - pte = pte_alloc_map(mm, pmd, addr); + pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; do { - pte_t zero_pte = pte_wrprotect(mk_pte(ZERO_PAGE(addr), prot)); + struct page *page = ZERO_PAGE(addr); + pte_t zero_pte = pte_wrprotect(mk_pte(page, prot)); + page_cache_get(page); + page_add_file_rmap(page); + inc_mm_counter(mm, file_rss); BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, zero_pte); } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(pte - 1); + pte_unmap_unlock(pte - 1, ptl); return 0; } @@ -1083,14 +1082,12 @@ int zeromap_page_range(struct vm_area_struct *vma, BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); - spin_lock(&mm->page_table_lock); do { next = pgd_addr_end(addr, end); err = zeromap_pud_range(mm, pgd, addr, next, prot); if (err) break; } while (pgd++, addr = next, addr != end); - spin_unlock(&mm->page_table_lock); return err; } @@ -1104,17 +1101,17 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long pfn, pgprot_t prot) { pte_t *pte; + spinlock_t *ptl; - pte = pte_alloc_map(mm, pmd, addr); + pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; do { BUG_ON(!pte_none(*pte)); - if (!pfn_valid(pfn) || PageReserved(pfn_to_page(pfn))) - set_pte_at(mm, addr, pte, pfn_pte(pfn, prot)); + set_pte_at(mm, addr, pte, pfn_pte(pfn, prot)); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(pte - 1); + pte_unmap_unlock(pte - 1, ptl); return 0; } @@ -1173,8 +1170,8 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). - * VM_RESERVED tells swapout not to try to touch - * this region. + * VM_RESERVED tells the core MM not to "manage" these pages + * (e.g. refcount, mapcount, try to swap them out). */ vma->vm_flags |= VM_IO | VM_RESERVED; @@ -1182,7 +1179,6 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); - spin_lock(&mm->page_table_lock); do { next = pgd_addr_end(addr, end); err = remap_pud_range(mm, pgd, addr, next, @@ -1190,12 +1186,36 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, if (err) break; } while (pgd++, addr = next, addr != end); - spin_unlock(&mm->page_table_lock); return err; } EXPORT_SYMBOL(remap_pfn_range); /* + * handle_pte_fault chooses page fault handler according to an entry + * which was read non-atomically. Before making any commitment, on + * those architectures or configurations (e.g. i386 with PAE) which + * might give a mix of unmatched parts, do_swap_page and do_file_page + * must check under lock before unmapping the pte and proceeding + * (but do_wp_page is only called after already making such a check; + * and do_anonymous_page and do_no_page can safely check later on). + */ +static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, + pte_t *page_table, pte_t orig_pte) +{ + int same = 1; +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) + if (sizeof(pte_t) > sizeof(unsigned long)) { + spinlock_t *ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + same = pte_same(*page_table, orig_pte); + spin_unlock(ptl); + } +#endif + pte_unmap(page_table); + return same; +} + +/* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings @@ -1209,28 +1229,10 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) } /* - * We hold the mm semaphore for reading and vma->vm_mm->page_table_lock - */ -static inline void break_cow(struct vm_area_struct * vma, struct page * new_page, unsigned long address, - pte_t *page_table) -{ - pte_t entry; - - entry = maybe_mkwrite(pte_mkdirty(mk_pte(new_page, vma->vm_page_prot)), - vma); - ptep_establish(vma, address, page_table, entry); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); -} - -/* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. * - * Goto-purists beware: the only reason for goto's here is that it results - * in better assembly code.. The "default" path will see no jumps at all. - * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus we can safely just mark it writable once we've done any necessary @@ -1240,28 +1242,28 @@ static inline void break_cow(struct vm_area_struct * vma, struct page * new_page * change only once the write actually happens. This avoids a few races, * and potentially makes it more efficient. * - * We hold the mm semaphore and the page_table_lock on entry and exit - * with the page_table_lock released. + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), with pte both mapped and locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, pte_t pte) +static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + spinlock_t *ptl, pte_t orig_pte) { struct page *old_page, *new_page; - unsigned long pfn = pte_pfn(pte); + unsigned long pfn = pte_pfn(orig_pte); pte_t entry; - int ret; + int ret = VM_FAULT_MINOR; + + BUG_ON(vma->vm_flags & VM_RESERVED); if (unlikely(!pfn_valid(pfn))) { /* - * This should really halt the system so it can be debugged or - * at least the kernel stops what it's doing before it corrupts - * data, but for the moment just pretend this is OOM. + * Page table corrupted: show pte and kill process. */ - pte_unmap(page_table); - printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n", - address); - spin_unlock(&mm->page_table_lock); - return VM_FAULT_OOM; + print_bad_pte(vma, orig_pte, address); + ret = VM_FAULT_OOM; + goto unlock; } old_page = pfn_to_page(pfn); @@ -1270,52 +1272,51 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma, unlock_page(old_page); if (reuse) { flush_cache_page(vma, address, pfn); - entry = maybe_mkwrite(pte_mkyoung(pte_mkdirty(pte)), - vma); + entry = pte_mkyoung(orig_pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); ptep_set_access_flags(vma, address, page_table, entry, 1); update_mmu_cache(vma, address, entry); lazy_mmu_prot_update(entry); - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); - return VM_FAULT_MINOR|VM_FAULT_WRITE; + ret |= VM_FAULT_WRITE; + goto unlock; } } - pte_unmap(page_table); /* * Ok, we need to copy. Oh, well.. */ - if (!PageReserved(old_page)) - page_cache_get(old_page); - spin_unlock(&mm->page_table_lock); + page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); if (unlikely(anon_vma_prepare(vma))) - goto no_new_page; + goto oom; if (old_page == ZERO_PAGE(address)) { new_page = alloc_zeroed_user_highpage(vma, address); if (!new_page) - goto no_new_page; + goto oom; } else { new_page = alloc_page_vma(GFP_HIGHUSER, vma, address); if (!new_page) - goto no_new_page; + goto oom; copy_user_highpage(new_page, old_page, address); } + /* * Re-check the pte - we dropped the lock */ - ret = VM_FAULT_MINOR; - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, address); - if (likely(pte_same(*page_table, pte))) { - if (PageAnon(old_page)) - dec_mm_counter(mm, anon_rss); - if (PageReserved(old_page)) - inc_mm_counter(mm, rss); - else - page_remove_rmap(old_page); + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (likely(pte_same(*page_table, orig_pte))) { + page_remove_rmap(old_page); + if (!PageAnon(old_page)) { + inc_mm_counter(mm, anon_rss); + dec_mm_counter(mm, file_rss); + } flush_cache_page(vma, address, pfn); - break_cow(vma, new_page, address, page_table); + entry = mk_pte(new_page, vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + ptep_establish(vma, address, page_table, entry); + update_mmu_cache(vma, address, entry); + lazy_mmu_prot_update(entry); lru_cache_add_active(new_page); page_add_anon_rmap(new_page, vma, address); @@ -1323,13 +1324,12 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma, new_page = old_page; ret |= VM_FAULT_WRITE; } - pte_unmap(page_table); page_cache_release(new_page); page_cache_release(old_page); - spin_unlock(&mm->page_table_lock); +unlock: + pte_unmap_unlock(page_table, ptl); return ret; - -no_new_page: +oom: page_cache_release(old_page); return VM_FAULT_OOM; } @@ -1399,13 +1399,6 @@ again: restart_addr = zap_page_range(vma, start_addr, end_addr - start_addr, details); - - /* - * We cannot rely on the break test in unmap_vmas: - * on the one hand, we don't want to restart our loop - * just because that broke out for the page_table_lock; - * on the other hand, it does no test when vma is small. - */ need_break = need_resched() || need_lockbreak(details->i_mmap_lock); @@ -1654,38 +1647,37 @@ void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struc } /* - * We hold the mm semaphore and the page_table_lock on entry and - * should release the pagetable lock on exit.. + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static int do_swap_page(struct mm_struct * mm, - struct vm_area_struct * vma, unsigned long address, - pte_t *page_table, pmd_t *pmd, pte_t orig_pte, int write_access) +static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access, pte_t orig_pte) { + spinlock_t *ptl; struct page *page; - swp_entry_t entry = pte_to_swp_entry(orig_pte); + swp_entry_t entry; pte_t pte; int ret = VM_FAULT_MINOR; - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) + goto out; + + entry = pte_to_swp_entry(orig_pte); page = lookup_swap_cache(entry); if (!page) { swapin_readahead(entry, address, vma); page = read_swap_cache_async(entry, vma, address); if (!page) { /* - * Back out if somebody else faulted in this pte while - * we released the page table lock. + * Back out if somebody else faulted in this pte + * while we released the pte lock. */ - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, address); + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); if (likely(pte_same(*page_table, orig_pte))) ret = VM_FAULT_OOM; - else - ret = VM_FAULT_MINOR; - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); - goto out; + goto unlock; } /* Had to read the page from swap area: Major fault */ @@ -1698,15 +1690,11 @@ static int do_swap_page(struct mm_struct * mm, lock_page(page); /* - * Back out if somebody else faulted in this pte while we - * released the page table lock. + * Back out if somebody else already faulted in this pte. */ - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, address); - if (unlikely(!pte_same(*page_table, orig_pte))) { - ret = VM_FAULT_MINOR; + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*page_table, orig_pte))) goto out_nomap; - } if (unlikely(!PageUptodate(page))) { ret = VM_FAULT_SIGBUS; @@ -1715,7 +1703,7 @@ static int do_swap_page(struct mm_struct * mm, /* The page isn't present yet, go ahead with the fault. */ - inc_mm_counter(mm, rss); + inc_mm_counter(mm, anon_rss); pte = mk_pte(page, vma->vm_page_prot); if (write_access && can_share_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); @@ -1733,7 +1721,7 @@ static int do_swap_page(struct mm_struct * mm, if (write_access) { if (do_wp_page(mm, vma, address, - page_table, pmd, pte) == VM_FAULT_OOM) + page_table, pmd, ptl, pte) == VM_FAULT_OOM) ret = VM_FAULT_OOM; goto out; } @@ -1741,74 +1729,76 @@ static int do_swap_page(struct mm_struct * mm, /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, address, pte); lazy_mmu_prot_update(pte); - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); +unlock: + pte_unmap_unlock(page_table, ptl); out: return ret; out_nomap: - pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(page_table, ptl); unlock_page(page); page_cache_release(page); - goto out; + return ret; } /* - * We are called with the MM semaphore and page_table_lock - * spinlock held to protect against concurrent faults in - * multithreaded programs. + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static int -do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, - pte_t *page_table, pmd_t *pmd, int write_access, - unsigned long addr) +static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access) { + struct page *page; + spinlock_t *ptl; pte_t entry; - struct page * page = ZERO_PAGE(addr); - - /* Read-only mapping of ZERO_PAGE. */ - entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot)); - /* ..except if it's a write access */ if (write_access) { /* Allocate our own private page. */ pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); if (unlikely(anon_vma_prepare(vma))) - goto no_mem; - page = alloc_zeroed_user_highpage(vma, addr); + goto oom; + page = alloc_zeroed_user_highpage(vma, address); if (!page) - goto no_mem; + goto oom; - spin_lock(&mm->page_table_lock); - page_table = pte_offset_map(pmd, addr); + entry = mk_pte(page, vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (!pte_none(*page_table)) { - pte_unmap(page_table); - page_cache_release(page); - spin_unlock(&mm->page_table_lock); - goto out; - } - inc_mm_counter(mm, rss); - entry = maybe_mkwrite(pte_mkdirty(mk_pte(page, - vma->vm_page_prot)), - vma); + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (!pte_none(*page_table)) + goto release; + inc_mm_counter(mm, anon_rss); lru_cache_add_active(page); SetPageReferenced(page); - page_add_anon_rmap(page, vma, addr); + page_add_anon_rmap(page, vma, address); + } else { + /* Map the ZERO_PAGE - vm_page_prot is readonly */ + page = ZERO_PAGE(address); + page_cache_get(page); + entry = mk_pte(page, vma->vm_page_prot); + + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (!pte_none(*page_table)) + goto release; + inc_mm_counter(mm, file_rss); + page_add_file_rmap(page); } - set_pte_at(mm, addr, page_table, entry); - pte_unmap(page_table); + set_pte_at(mm, address, page_table, entry); /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, addr, entry); + update_mmu_cache(vma, address, entry); lazy_mmu_prot_update(entry); - spin_unlock(&mm->page_table_lock); -out: +unlock: + pte_unmap_unlock(page_table, ptl); return VM_FAULT_MINOR; -no_mem: +release: + page_cache_release(page); + goto unlock; +oom: return VM_FAULT_OOM; } @@ -1821,25 +1811,23 @@ no_mem: * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * - * This is called with the MM semaphore held and the page table - * spinlock held. Exit with the spinlock released. + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static int -do_no_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, int write_access, pte_t *page_table, pmd_t *pmd) +static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access) { - struct page * new_page; + spinlock_t *ptl; + struct page *new_page; struct address_space *mapping = NULL; pte_t entry; unsigned int sequence = 0; int ret = VM_FAULT_MINOR; int anon = 0; - if (!vma->vm_ops || !vma->vm_ops->nopage) - return do_anonymous_page(mm, vma, page_table, - pmd, write_access, address); pte_unmap(page_table); - spin_unlock(&mm->page_table_lock); if (vma->vm_file) { mapping = vma->vm_file->f_mapping; @@ -1847,7 +1835,6 @@ do_no_page(struct mm_struct *mm, struct vm_area_struct *vma, smp_rmb(); /* serializes i_size against truncate_count */ } retry: - cond_resched(); new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret); /* * No smp_rmb is needed here as long as there's a full @@ -1880,19 +1867,20 @@ retry: anon = 1; } - spin_lock(&mm->page_table_lock); + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); /* * For a file-backed vma, someone could have truncated or otherwise * invalidated this page. If unmap_mapping_range got called, * retry getting the page. */ if (mapping && unlikely(sequence != mapping->truncate_count)) { - sequence = mapping->truncate_count; - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(page_table, ptl); page_cache_release(new_page); + cond_resched(); + sequence = mapping->truncate_count; + smp_rmb(); goto retry; } - page_table = pte_offset_map(pmd, address); /* * This silly early PAGE_DIRTY setting removes a race @@ -1906,68 +1894,67 @@ retry: */ /* Only go through if we didn't race with anybody else... */ if (pte_none(*page_table)) { - if (!PageReserved(new_page)) - inc_mm_counter(mm, rss); - flush_icache_page(vma, new_page); entry = mk_pte(new_page, vma->vm_page_prot); if (write_access) entry = maybe_mkwrite(pte_mkdirty(entry), vma); set_pte_at(mm, address, page_table, entry); if (anon) { + inc_mm_counter(mm, anon_rss); lru_cache_add_active(new_page); page_add_anon_rmap(new_page, vma, address); - } else + } else if (!(vma->vm_flags & VM_RESERVED)) { + inc_mm_counter(mm, file_rss); page_add_file_rmap(new_page); - pte_unmap(page_table); + } } else { /* One of our sibling threads was faster, back out. */ - pte_unmap(page_table); page_cache_release(new_page); - spin_unlock(&mm->page_table_lock); - goto out; + goto unlock; } /* no need to invalidate: a not-present page shouldn't be cached */ update_mmu_cache(vma, address, entry); lazy_mmu_prot_update(entry); - spin_unlock(&mm->page_table_lock); -out: +unlock: + pte_unmap_unlock(page_table, ptl); return ret; oom: page_cache_release(new_page); - ret = VM_FAULT_OOM; - goto out; + return VM_FAULT_OOM; } /* * Fault of a previously existing named mapping. Repopulate the pte * from the encoded file_pte if possible. This enables swappable * nonlinear vmas. + * + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. */ -static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma, - unsigned long address, int write_access, pte_t *pte, pmd_t *pmd) +static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access, pte_t orig_pte) { - unsigned long pgoff; + pgoff_t pgoff; int err; - BUG_ON(!vma->vm_ops || !vma->vm_ops->nopage); - /* - * Fall back to the linear mapping if the fs does not support - * ->populate: - */ - if (!vma->vm_ops->populate || - (write_access && !(vma->vm_flags & VM_SHARED))) { - pte_clear(mm, address, pte); - return do_no_page(mm, vma, address, write_access, pte, pmd); - } - - pgoff = pte_to_pgoff(*pte); + if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) + return VM_FAULT_MINOR; - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); + if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { + /* + * Page table corrupted: show pte and kill process. + */ + print_bad_pte(vma, orig_pte, address); + return VM_FAULT_OOM; + } + /* We can then assume vm->vm_ops && vma->vm_ops->populate */ - err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, vma->vm_page_prot, pgoff, 0); + pgoff = pte_to_pgoff(orig_pte); + err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE, + vma->vm_page_prot, pgoff, 0); if (err == -ENOMEM) return VM_FAULT_OOM; if (err) @@ -1984,56 +1971,68 @@ static int do_file_page(struct mm_struct * mm, struct vm_area_struct * vma, * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * - * Note the "page_table_lock". It is to protect against kswapd removing - * pages from under us. Note that kswapd only ever _removes_ pages, never - * adds them. As such, once we have noticed that the page is not present, - * we can drop the lock early. - * - * The adding of pages is protected by the MM semaphore (which we hold), - * so we don't need to worry about a page being suddenly been added into - * our VM. - * - * We enter with the pagetable spinlock held, we are supposed to - * release it when done. + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. */ static inline int handle_pte_fault(struct mm_struct *mm, - struct vm_area_struct * vma, unsigned long address, - int write_access, pte_t *pte, pmd_t *pmd) + struct vm_area_struct *vma, unsigned long address, + pte_t *pte, pmd_t *pmd, int write_access) { pte_t entry; + pte_t old_entry; + spinlock_t *ptl; - entry = *pte; + old_entry = entry = *pte; if (!pte_present(entry)) { - /* - * If it truly wasn't present, we know that kswapd - * and the PTE updates will not touch it later. So - * drop the lock. - */ - if (pte_none(entry)) - return do_no_page(mm, vma, address, write_access, pte, pmd); + if (pte_none(entry)) { + if (!vma->vm_ops || !vma->vm_ops->nopage) + return do_anonymous_page(mm, vma, address, + pte, pmd, write_access); + return do_no_page(mm, vma, address, + pte, pmd, write_access); + } if (pte_file(entry)) - return do_file_page(mm, vma, address, write_access, pte, pmd); - return do_swap_page(mm, vma, address, pte, pmd, entry, write_access); + return do_file_page(mm, vma, address, + pte, pmd, write_access, entry); + return do_swap_page(mm, vma, address, + pte, pmd, write_access, entry); } + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (unlikely(!pte_same(*pte, entry))) + goto unlock; if (write_access) { if (!pte_write(entry)) - return do_wp_page(mm, vma, address, pte, pmd, entry); + return do_wp_page(mm, vma, address, + pte, pmd, ptl, entry); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); - ptep_set_access_flags(vma, address, pte, entry, write_access); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); + if (!pte_same(old_entry, entry)) { + ptep_set_access_flags(vma, address, pte, entry, write_access); + update_mmu_cache(vma, address, entry); + lazy_mmu_prot_update(entry); + } else { + /* + * This is needed only for protection faults but the arch code + * is not yet telling us if this is a protection fault or not. + * This still avoids useless tlb flushes for .text page faults + * with threads. + */ + if (write_access) + flush_tlb_page(vma, address); + } +unlock: + pte_unmap_unlock(pte, ptl); return VM_FAULT_MINOR; } /* * By the time we get here, we already hold the mm semaphore */ -int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma, +int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access) { pgd_t *pgd; @@ -2048,100 +2047,66 @@ int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma, if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, write_access); - /* - * We need the page table lock to synchronize with kswapd - * and the SMP-safe atomic PTE updates. - */ pgd = pgd_offset(mm, address); - spin_lock(&mm->page_table_lock); - pud = pud_alloc(mm, pgd, address); if (!pud) - goto oom; - + return VM_FAULT_OOM; pmd = pmd_alloc(mm, pud, address); if (!pmd) - goto oom; - + return VM_FAULT_OOM; pte = pte_alloc_map(mm, pmd, address); if (!pte) - goto oom; - - return handle_pte_fault(mm, vma, address, write_access, pte, pmd); + return VM_FAULT_OOM; - oom: - spin_unlock(&mm->page_table_lock); - return VM_FAULT_OOM; + return handle_pte_fault(mm, vma, address, pte, pmd, write_access); } #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. - * - * We've already handled the fast-path in-line, and we own the - * page table lock. + * We've already handled the fast-path in-line. */ -pud_t fastcall *__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { - pud_t *new; - - spin_unlock(&mm->page_table_lock); - new = pud_alloc_one(mm, address); - spin_lock(&mm->page_table_lock); + pud_t *new = pud_alloc_one(mm, address); if (!new) - return NULL; + return -ENOMEM; - /* - * Because we dropped the lock, we should re-check the - * entry, as somebody else could have populated it.. - */ - if (pgd_present(*pgd)) { + spin_lock(&mm->page_table_lock); + if (pgd_present(*pgd)) /* Another has populated it */ pud_free(new); - goto out; - } - pgd_populate(mm, pgd, new); - out: - return pud_offset(pgd, address); + else + pgd_populate(mm, pgd, new); + spin_unlock(&mm->page_table_lock); + return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. - * - * We've already handled the fast-path in-line, and we own the - * page table lock. + * We've already handled the fast-path in-line. */ -pmd_t fastcall *__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) +int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { - pmd_t *new; - - spin_unlock(&mm->page_table_lock); - new = pmd_alloc_one(mm, address); - spin_lock(&mm->page_table_lock); + pmd_t *new = pmd_alloc_one(mm, address); if (!new) - return NULL; + return -ENOMEM; - /* - * Because we dropped the lock, we should re-check the - * entry, as somebody else could have populated it.. - */ + spin_lock(&mm->page_table_lock); #ifndef __ARCH_HAS_4LEVEL_HACK - if (pud_present(*pud)) { + if (pud_present(*pud)) /* Another has populated it */ pmd_free(new); - goto out; - } - pud_populate(mm, pud, new); + else + pud_populate(mm, pud, new); #else - if (pgd_present(*pud)) { + if (pgd_present(*pud)) /* Another has populated it */ pmd_free(new); - goto out; - } - pgd_populate(mm, pud, new); + else + pgd_populate(mm, pud, new); #endif /* __ARCH_HAS_4LEVEL_HACK */ - - out: - return pmd_offset(pud, address); + spin_unlock(&mm->page_table_lock); + return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ @@ -2206,22 +2171,6 @@ unsigned long vmalloc_to_pfn(void * vmalloc_addr) EXPORT_SYMBOL(vmalloc_to_pfn); -/* - * update_mem_hiwater - * - update per process rss and vm high water data - */ -void update_mem_hiwater(struct task_struct *tsk) -{ - if (tsk->mm) { - unsigned long rss = get_mm_counter(tsk->mm, rss); - - if (tsk->mm->hiwater_rss < rss) - tsk->mm->hiwater_rss = rss; - if (tsk->mm->hiwater_vm < tsk->mm->total_vm) - tsk->mm->hiwater_vm = tsk->mm->total_vm; - } -} - #if !defined(__HAVE_ARCH_GATE_AREA) #if defined(AT_SYSINFO_EHDR) @@ -2233,7 +2182,7 @@ static int __init gate_vma_init(void) gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_page_prot = PAGE_READONLY; - gate_vma.vm_flags = 0; + gate_vma.vm_flags = VM_RESERVED; return 0; } __initcall(gate_vma_init); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c new file mode 100644 index 00000000000..431a64f021c --- /dev/null +++ b/mm/memory_hotplug.c @@ -0,0 +1,138 @@ +/* + * linux/mm/memory_hotplug.c + * + * Copyright (C) + */ + +#include <linux/config.h> +#include <linux/stddef.h> +#include <linux/mm.h> +#include <linux/swap.h> +#include <linux/interrupt.h> +#include <linux/pagemap.h> +#include <linux/bootmem.h> +#include <linux/compiler.h> +#include <linux/module.h> +#include <linux/pagevec.h> +#include <linux/slab.h> +#include <linux/sysctl.h> +#include <linux/cpu.h> +#include <linux/memory.h> +#include <linux/memory_hotplug.h> +#include <linux/highmem.h> +#include <linux/vmalloc.h> + +#include <asm/tlbflush.h> + +extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn, + unsigned long size); +static void __add_zone(struct zone *zone, unsigned long phys_start_pfn) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + int nr_pages = PAGES_PER_SECTION; + int nid = pgdat->node_id; + int zone_type; + + zone_type = zone - pgdat->node_zones; + memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn); + zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages); +} + +extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, + int nr_pages); +static int __add_section(struct zone *zone, unsigned long phys_start_pfn) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + int nr_pages = PAGES_PER_SECTION; + int ret; + + ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages); + + if (ret < 0) + return ret; + + __add_zone(zone, phys_start_pfn); + return register_new_memory(__pfn_to_section(phys_start_pfn)); +} + +/* + * Reasonably generic function for adding memory. It is + * expected that archs that support memory hotplug will + * call this function after deciding the zone to which to + * add the new pages. + */ +int __add_pages(struct zone *zone, unsigned long phys_start_pfn, + unsigned long nr_pages) +{ + unsigned long i; + int err = 0; + + for (i = 0; i < nr_pages; i += PAGES_PER_SECTION) { + err = __add_section(zone, phys_start_pfn + i); + + if (err) + break; + } + + return err; +} + +static void grow_zone_span(struct zone *zone, + unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long old_zone_end_pfn; + + zone_span_writelock(zone); + + old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; + if (start_pfn < zone->zone_start_pfn) + zone->zone_start_pfn = start_pfn; + + if (end_pfn > old_zone_end_pfn) + zone->spanned_pages = end_pfn - zone->zone_start_pfn; + + zone_span_writeunlock(zone); +} + +static void grow_pgdat_span(struct pglist_data *pgdat, + unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long old_pgdat_end_pfn = + pgdat->node_start_pfn + pgdat->node_spanned_pages; + + if (start_pfn < pgdat->node_start_pfn) + pgdat->node_start_pfn = start_pfn; + + if (end_pfn > old_pgdat_end_pfn) + pgdat->node_spanned_pages = end_pfn - pgdat->node_spanned_pages; +} + +int online_pages(unsigned long pfn, unsigned long nr_pages) +{ + unsigned long i; + unsigned long flags; + unsigned long onlined_pages = 0; + struct zone *zone; + + /* + * This doesn't need a lock to do pfn_to_page(). + * The section can't be removed here because of the + * memory_block->state_sem. + */ + zone = page_zone(pfn_to_page(pfn)); + pgdat_resize_lock(zone->zone_pgdat, &flags); + grow_zone_span(zone, pfn, pfn + nr_pages); + grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages); + pgdat_resize_unlock(zone->zone_pgdat, &flags); + + for (i = 0; i < nr_pages; i++) { + struct page *page = pfn_to_page(pfn + i); + online_page(page); + onlined_pages++; + } + zone->present_pages += onlined_pages; + + setup_per_zone_pages_min(); + + return 0; +} diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 1d5c64df165..2076b1542b8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2,6 +2,7 @@ * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. + * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * Subject to the GNU Public License, version 2. * * NUMA policy allows the user to give hints in which node(s) memory should @@ -17,13 +18,19 @@ * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. + * * bind Only allocate memory on a specific set of nodes, * no fallback. + * FIXME: memory is allocated starting with the first node + * to the last. It would be better if bind would truly restrict + * the allocation to memory nodes instead + * * preferred Try a specific node first before normal fallback. * As a special case node -1 here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. + * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. @@ -93,23 +100,10 @@ struct mempolicy default_policy = { .policy = MPOL_DEFAULT, }; -/* Check if all specified nodes are online */ -static int nodes_online(unsigned long *nodes) -{ - DECLARE_BITMAP(online2, MAX_NUMNODES); - - bitmap_copy(online2, nodes_addr(node_online_map), MAX_NUMNODES); - if (bitmap_empty(online2, MAX_NUMNODES)) - set_bit(0, online2); - if (!bitmap_subset(nodes, online2, MAX_NUMNODES)) - return -EINVAL; - return 0; -} - /* Do sanity checking on a policy */ -static int mpol_check_policy(int mode, unsigned long *nodes) +static int mpol_check_policy(int mode, nodemask_t *nodes) { - int empty = bitmap_empty(nodes, MAX_NUMNODES); + int empty = nodes_empty(*nodes); switch (mode) { case MPOL_DEFAULT: @@ -124,71 +118,20 @@ static int mpol_check_policy(int mode, unsigned long *nodes) return -EINVAL; break; } - return nodes_online(nodes); -} - -/* Copy a node mask from user space. */ -static int get_nodes(unsigned long *nodes, unsigned long __user *nmask, - unsigned long maxnode, int mode) -{ - unsigned long k; - unsigned long nlongs; - unsigned long endmask; - - --maxnode; - bitmap_zero(nodes, MAX_NUMNODES); - if (maxnode == 0 || !nmask) - return 0; - - nlongs = BITS_TO_LONGS(maxnode); - if ((maxnode % BITS_PER_LONG) == 0) - endmask = ~0UL; - else - endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1; - - /* When the user specified more nodes than supported just check - if the non supported part is all zero. */ - if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) { - if (nlongs > PAGE_SIZE/sizeof(long)) - return -EINVAL; - for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) { - unsigned long t; - if (get_user(t, nmask + k)) - return -EFAULT; - if (k == nlongs - 1) { - if (t & endmask) - return -EINVAL; - } else if (t) - return -EINVAL; - } - nlongs = BITS_TO_LONGS(MAX_NUMNODES); - endmask = ~0UL; - } - - if (copy_from_user(nodes, nmask, nlongs*sizeof(unsigned long))) - return -EFAULT; - nodes[nlongs-1] &= endmask; - /* Update current mems_allowed */ - cpuset_update_current_mems_allowed(); - /* Ignore nodes not set in current->mems_allowed */ - cpuset_restrict_to_mems_allowed(nodes); - return mpol_check_policy(mode, nodes); + return nodes_subset(*nodes, node_online_map) ? 0 : -EINVAL; } - /* Generate a custom zonelist for the BIND policy. */ -static struct zonelist *bind_zonelist(unsigned long *nodes) +static struct zonelist *bind_zonelist(nodemask_t *nodes) { struct zonelist *zl; int num, max, nd; - max = 1 + MAX_NR_ZONES * bitmap_weight(nodes, MAX_NUMNODES); + max = 1 + MAX_NR_ZONES * nodes_weight(*nodes); zl = kmalloc(sizeof(void *) * max, GFP_KERNEL); if (!zl) return NULL; num = 0; - for (nd = find_first_bit(nodes, MAX_NUMNODES); - nd < MAX_NUMNODES; - nd = find_next_bit(nodes, MAX_NUMNODES, 1+nd)) { + for_each_node_mask(nd, *nodes) { int k; for (k = MAX_NR_ZONES-1; k >= 0; k--) { struct zone *z = &NODE_DATA(nd)->node_zones[k]; @@ -199,17 +142,16 @@ static struct zonelist *bind_zonelist(unsigned long *nodes) policy_zone = k; } } - BUG_ON(num >= max); zl->zones[num] = NULL; return zl; } /* Create a new policy */ -static struct mempolicy *mpol_new(int mode, unsigned long *nodes) +static struct mempolicy *mpol_new(int mode, nodemask_t *nodes) { struct mempolicy *policy; - PDprintk("setting mode %d nodes[0] %lx\n", mode, nodes[0]); + PDprintk("setting mode %d nodes[0] %lx\n", mode, nodes_addr(*nodes)[0]); if (mode == MPOL_DEFAULT) return NULL; policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); @@ -218,10 +160,10 @@ static struct mempolicy *mpol_new(int mode, unsigned long *nodes) atomic_set(&policy->refcnt, 1); switch (mode) { case MPOL_INTERLEAVE: - bitmap_copy(policy->v.nodes, nodes, MAX_NUMNODES); + policy->v.nodes = *nodes; break; case MPOL_PREFERRED: - policy->v.preferred_node = find_first_bit(nodes, MAX_NUMNODES); + policy->v.preferred_node = first_node(*nodes); if (policy->v.preferred_node >= MAX_NUMNODES) policy->v.preferred_node = -1; break; @@ -238,14 +180,14 @@ static struct mempolicy *mpol_new(int mode, unsigned long *nodes) } /* Ensure all existing pages follow the policy. */ -static int check_pte_range(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr, unsigned long end, unsigned long *nodes) +static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, nodemask_t *nodes) { pte_t *orig_pte; pte_t *pte; + spinlock_t *ptl; - spin_lock(&mm->page_table_lock); - orig_pte = pte = pte_offset_map(pmd, addr); + orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { unsigned long pfn; unsigned int nid; @@ -253,19 +195,20 @@ static int check_pte_range(struct mm_struct *mm, pmd_t *pmd, if (!pte_present(*pte)) continue; pfn = pte_pfn(*pte); - if (!pfn_valid(pfn)) + if (!pfn_valid(pfn)) { + print_bad_pte(vma, *pte, addr); continue; + } nid = pfn_to_nid(pfn); - if (!test_bit(nid, nodes)) + if (!node_isset(nid, *nodes)) break; } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(orig_pte); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(orig_pte, ptl); return addr != end; } -static inline int check_pmd_range(struct mm_struct *mm, pud_t *pud, - unsigned long addr, unsigned long end, unsigned long *nodes) +static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, + unsigned long addr, unsigned long end, nodemask_t *nodes) { pmd_t *pmd; unsigned long next; @@ -275,14 +218,14 @@ static inline int check_pmd_range(struct mm_struct *mm, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; - if (check_pte_range(mm, pmd, addr, next, nodes)) + if (check_pte_range(vma, pmd, addr, next, nodes)) return -EIO; } while (pmd++, addr = next, addr != end); return 0; } -static inline int check_pud_range(struct mm_struct *mm, pgd_t *pgd, - unsigned long addr, unsigned long end, unsigned long *nodes) +static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, nodemask_t *nodes) { pud_t *pud; unsigned long next; @@ -292,24 +235,24 @@ static inline int check_pud_range(struct mm_struct *mm, pgd_t *pgd, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - if (check_pmd_range(mm, pud, addr, next, nodes)) + if (check_pmd_range(vma, pud, addr, next, nodes)) return -EIO; } while (pud++, addr = next, addr != end); return 0; } -static inline int check_pgd_range(struct mm_struct *mm, - unsigned long addr, unsigned long end, unsigned long *nodes) +static inline int check_pgd_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long end, nodemask_t *nodes) { pgd_t *pgd; unsigned long next; - pgd = pgd_offset(mm, addr); + pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - if (check_pud_range(mm, pgd, addr, next, nodes)) + if (check_pud_range(vma, pgd, addr, next, nodes)) return -EIO; } while (pgd++, addr = next, addr != end); return 0; @@ -318,7 +261,7 @@ static inline int check_pgd_range(struct mm_struct *mm, /* Step 1: check the range */ static struct vm_area_struct * check_range(struct mm_struct *mm, unsigned long start, unsigned long end, - unsigned long *nodes, unsigned long flags) + nodemask_t *nodes, unsigned long flags) { int err; struct vm_area_struct *first, *vma, *prev; @@ -326,6 +269,8 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, first = find_vma(mm, start); if (!first) return ERR_PTR(-EFAULT); + if (first->vm_flags & VM_RESERVED) + return ERR_PTR(-EACCES); prev = NULL; for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) { if (!vma->vm_next && vma->vm_end < end) @@ -338,8 +283,7 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, endvma = end; if (vma->vm_start > start) start = vma->vm_start; - err = check_pgd_range(vma->vm_mm, - start, endvma, nodes); + err = check_pgd_range(vma, start, endvma, nodes); if (err) { first = ERR_PTR(err); break; @@ -393,17 +337,25 @@ static int mbind_range(struct vm_area_struct *vma, unsigned long start, return err; } -/* Change policy for a memory range */ -asmlinkage long sys_mbind(unsigned long start, unsigned long len, - unsigned long mode, - unsigned long __user *nmask, unsigned long maxnode, - unsigned flags) +static int contextualize_policy(int mode, nodemask_t *nodes) +{ + if (!nodes) + return 0; + + /* Update current mems_allowed */ + cpuset_update_current_mems_allowed(); + /* Ignore nodes not set in current->mems_allowed */ + cpuset_restrict_to_mems_allowed(nodes->bits); + return mpol_check_policy(mode, nodes); +} + +long do_mbind(unsigned long start, unsigned long len, + unsigned long mode, nodemask_t *nmask, unsigned long flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; - DECLARE_BITMAP(nodes, MAX_NUMNODES); int err; if ((flags & ~(unsigned long)(MPOL_MF_STRICT)) || mode > MPOL_MAX) @@ -418,20 +370,17 @@ asmlinkage long sys_mbind(unsigned long start, unsigned long len, return -EINVAL; if (end == start) return 0; - - err = get_nodes(nodes, nmask, maxnode, mode); - if (err) - return err; - - new = mpol_new(mode, nodes); + if (mpol_check_policy(mode, nmask)) + return -EINVAL; + new = mpol_new(mode, nmask); if (IS_ERR(new)) return PTR_ERR(new); PDprintk("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len, - mode,nodes[0]); + mode,nodes_addr(nodes)[0]); down_write(&mm->mmap_sem); - vma = check_range(mm, start, end, nodes, flags); + vma = check_range(mm, start, end, nmask, flags); err = PTR_ERR(vma); if (!IS_ERR(vma)) err = mbind_range(vma, start, end, new); @@ -441,50 +390,45 @@ asmlinkage long sys_mbind(unsigned long start, unsigned long len, } /* Set the process memory policy */ -asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask, - unsigned long maxnode) +long do_set_mempolicy(int mode, nodemask_t *nodes) { - int err; struct mempolicy *new; - DECLARE_BITMAP(nodes, MAX_NUMNODES); - if (mode < 0 || mode > MPOL_MAX) + if (contextualize_policy(mode, nodes)) return -EINVAL; - err = get_nodes(nodes, nmask, maxnode, mode); - if (err) - return err; new = mpol_new(mode, nodes); if (IS_ERR(new)) return PTR_ERR(new); mpol_free(current->mempolicy); current->mempolicy = new; if (new && new->policy == MPOL_INTERLEAVE) - current->il_next = find_first_bit(new->v.nodes, MAX_NUMNODES); + current->il_next = first_node(new->v.nodes); return 0; } /* Fill a zone bitmap for a policy */ -static void get_zonemask(struct mempolicy *p, unsigned long *nodes) +static void get_zonemask(struct mempolicy *p, nodemask_t *nodes) { int i; - bitmap_zero(nodes, MAX_NUMNODES); + nodes_clear(*nodes); switch (p->policy) { case MPOL_BIND: for (i = 0; p->v.zonelist->zones[i]; i++) - __set_bit(p->v.zonelist->zones[i]->zone_pgdat->node_id, nodes); + node_set(p->v.zonelist->zones[i]->zone_pgdat->node_id, + *nodes); break; case MPOL_DEFAULT: break; case MPOL_INTERLEAVE: - bitmap_copy(nodes, p->v.nodes, MAX_NUMNODES); + *nodes = p->v.nodes; break; case MPOL_PREFERRED: /* or use current node instead of online map? */ if (p->v.preferred_node < 0) - bitmap_copy(nodes, nodes_addr(node_online_map), MAX_NUMNODES); + *nodes = node_online_map; else - __set_bit(p->v.preferred_node, nodes); + node_set(p->v.preferred_node, *nodes); break; default: BUG(); @@ -504,37 +448,17 @@ static int lookup_node(struct mm_struct *mm, unsigned long addr) return err; } -/* Copy a kernel node mask to user space */ -static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, - void *nodes, unsigned nbytes) -{ - unsigned long copy = ALIGN(maxnode-1, 64) / 8; - - if (copy > nbytes) { - if (copy > PAGE_SIZE) - return -EINVAL; - if (clear_user((char __user *)mask + nbytes, copy - nbytes)) - return -EFAULT; - copy = nbytes; - } - return copy_to_user(mask, nodes, copy) ? -EFAULT : 0; -} - /* Retrieve NUMA policy */ -asmlinkage long sys_get_mempolicy(int __user *policy, - unsigned long __user *nmask, - unsigned long maxnode, - unsigned long addr, unsigned long flags) +long do_get_mempolicy(int *policy, nodemask_t *nmask, + unsigned long addr, unsigned long flags) { - int err, pval; + int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; - if (nmask != NULL && maxnode < MAX_NUMNODES) - return -EINVAL; if (flags & MPOL_F_ADDR) { down_read(&mm->mmap_sem); vma = find_vma_intersection(mm, addr, addr+1); @@ -557,31 +481,25 @@ asmlinkage long sys_get_mempolicy(int __user *policy, err = lookup_node(mm, addr); if (err < 0) goto out; - pval = err; + *policy = err; } else if (pol == current->mempolicy && pol->policy == MPOL_INTERLEAVE) { - pval = current->il_next; + *policy = current->il_next; } else { err = -EINVAL; goto out; } } else - pval = pol->policy; + *policy = pol->policy; if (vma) { up_read(¤t->mm->mmap_sem); vma = NULL; } - if (policy && put_user(pval, policy)) - return -EFAULT; - err = 0; - if (nmask) { - DECLARE_BITMAP(nodes, MAX_NUMNODES); - get_zonemask(pol, nodes); - err = copy_nodes_to_user(nmask, maxnode, nodes, sizeof(nodes)); - } + if (nmask) + get_zonemask(pol, nmask); out: if (vma) @@ -589,6 +507,126 @@ asmlinkage long sys_get_mempolicy(int __user *policy, return err; } +/* + * User space interface with variable sized bitmaps for nodelists. + */ + +/* Copy a node mask from user space. */ +static int get_nodes(nodemask_t *nodes, unsigned long __user *nmask, + unsigned long maxnode) +{ + unsigned long k; + unsigned long nlongs; + unsigned long endmask; + + --maxnode; + nodes_clear(*nodes); + if (maxnode == 0 || !nmask) + return 0; + + nlongs = BITS_TO_LONGS(maxnode); + if ((maxnode % BITS_PER_LONG) == 0) + endmask = ~0UL; + else + endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1; + + /* When the user specified more nodes than supported just check + if the non supported part is all zero. */ + if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) { + if (nlongs > PAGE_SIZE/sizeof(long)) + return -EINVAL; + for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) { + unsigned long t; + if (get_user(t, nmask + k)) + return -EFAULT; + if (k == nlongs - 1) { + if (t & endmask) + return -EINVAL; + } else if (t) + return -EINVAL; + } + nlongs = BITS_TO_LONGS(MAX_NUMNODES); + endmask = ~0UL; + } + + if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long))) + return -EFAULT; + nodes_addr(*nodes)[nlongs-1] &= endmask; + return 0; +} + +/* Copy a kernel node mask to user space */ +static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, + nodemask_t *nodes) +{ + unsigned long copy = ALIGN(maxnode-1, 64) / 8; + const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long); + + if (copy > nbytes) { + if (copy > PAGE_SIZE) + return -EINVAL; + if (clear_user((char __user *)mask + nbytes, copy - nbytes)) + return -EFAULT; + copy = nbytes; + } + return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; +} + +asmlinkage long sys_mbind(unsigned long start, unsigned long len, + unsigned long mode, + unsigned long __user *nmask, unsigned long maxnode, + unsigned flags) +{ + nodemask_t nodes; + int err; + + err = get_nodes(&nodes, nmask, maxnode); + if (err) + return err; + return do_mbind(start, len, mode, &nodes, flags); +} + +/* Set the process memory policy */ +asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask, + unsigned long maxnode) +{ + int err; + nodemask_t nodes; + + if (mode < 0 || mode > MPOL_MAX) + return -EINVAL; + err = get_nodes(&nodes, nmask, maxnode); + if (err) + return err; + return do_set_mempolicy(mode, &nodes); +} + +/* Retrieve NUMA policy */ +asmlinkage long sys_get_mempolicy(int __user *policy, + unsigned long __user *nmask, + unsigned long maxnode, + unsigned long addr, unsigned long flags) +{ + int err, pval; + nodemask_t nodes; + + if (nmask != NULL && maxnode < MAX_NUMNODES) + return -EINVAL; + + err = do_get_mempolicy(&pval, &nodes, addr, flags); + + if (err) + return err; + + if (policy && put_user(pval, policy)) + return -EFAULT; + + if (nmask) + err = copy_nodes_to_user(nmask, maxnode, &nodes); + + return err; +} + #ifdef CONFIG_COMPAT asmlinkage long compat_sys_get_mempolicy(int __user *policy, @@ -649,15 +687,15 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len, long err = 0; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; - DECLARE_BITMAP(bm, MAX_NUMNODES); + nodemask_t bm; nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { - err = compat_get_bitmap(bm, nmask, nr_bits); + err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits); nm = compat_alloc_user_space(alloc_size); - err |= copy_to_user(nm, bm, alloc_size); + err |= copy_to_user(nm, nodes_addr(bm), alloc_size); } if (err) @@ -676,7 +714,7 @@ get_vma_policy(struct task_struct *task, struct vm_area_struct *vma, unsigned lo if (vma) { if (vma->vm_ops && vma->vm_ops->get_policy) - pol = vma->vm_ops->get_policy(vma, addr); + pol = vma->vm_ops->get_policy(vma, addr); else if (vma->vm_policy && vma->vm_policy->policy != MPOL_DEFAULT) pol = vma->vm_policy; @@ -722,10 +760,9 @@ static unsigned interleave_nodes(struct mempolicy *policy) struct task_struct *me = current; nid = me->il_next; - BUG_ON(nid >= MAX_NUMNODES); - next = find_next_bit(policy->v.nodes, MAX_NUMNODES, 1+nid); + next = next_node(nid, policy->v.nodes); if (next >= MAX_NUMNODES) - next = find_first_bit(policy->v.nodes, MAX_NUMNODES); + next = first_node(policy->v.nodes); me->il_next = next; return nid; } @@ -734,29 +771,27 @@ static unsigned interleave_nodes(struct mempolicy *policy) static unsigned offset_il_node(struct mempolicy *pol, struct vm_area_struct *vma, unsigned long off) { - unsigned nnodes = bitmap_weight(pol->v.nodes, MAX_NUMNODES); + unsigned nnodes = nodes_weight(pol->v.nodes); unsigned target = (unsigned)off % nnodes; int c; int nid = -1; c = 0; do { - nid = find_next_bit(pol->v.nodes, MAX_NUMNODES, nid+1); + nid = next_node(nid, pol->v.nodes); c++; } while (c <= target); - BUG_ON(nid >= MAX_NUMNODES); - BUG_ON(!test_bit(nid, pol->v.nodes)); return nid; } /* Allocate a page in interleaved policy. Own path because it needs to do special accounting. */ -static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, unsigned nid) +static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, + unsigned nid) { struct zonelist *zl; struct page *page; - BUG_ON(!node_online(nid)); zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp); page = __alloc_pages(gfp, order, zl); if (page && page_zone(page) == zl->zones[0]) { @@ -799,8 +834,6 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) unsigned nid; if (vma) { unsigned long off; - BUG_ON(addr >= vma->vm_end); - BUG_ON(addr < vma->vm_start); off = vma->vm_pgoff; off += (addr - vma->vm_start) >> PAGE_SHIFT; nid = offset_il_node(pol, vma, off); @@ -878,7 +911,7 @@ int __mpol_equal(struct mempolicy *a, struct mempolicy *b) case MPOL_DEFAULT: return 1; case MPOL_INTERLEAVE: - return bitmap_equal(a->v.nodes, b->v.nodes, MAX_NUMNODES); + return nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: return a->v.preferred_node == b->v.preferred_node; case MPOL_BIND: { @@ -1117,7 +1150,7 @@ int mpol_set_shared_policy(struct shared_policy *info, PDprintk("set_shared_policy %lx sz %lu %d %lx\n", vma->vm_pgoff, sz, npol? npol->policy : -1, - npol ? npol->v.nodes[0] : -1); + npol ? nodes_addr(npol->v.nodes)[0] : -1); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); @@ -1164,14 +1197,12 @@ void __init numa_policy_init(void) /* Set interleaving policy for system init. This way not all the data structures allocated at system boot end up in node zero. */ - if (sys_set_mempolicy(MPOL_INTERLEAVE, nodes_addr(node_online_map), - MAX_NUMNODES) < 0) + if (do_set_mempolicy(MPOL_INTERLEAVE, &node_online_map)) printk("numa_policy_init: interleaving failed\n"); } -/* Reset policy of current process to default. - * Assumes fs == KERNEL_DS */ +/* Reset policy of current process to default */ void numa_default_policy(void) { - sys_set_mempolicy(MPOL_DEFAULT, NULL, 0); + do_set_mempolicy(MPOL_DEFAULT, NULL); } diff --git a/mm/mmap.c b/mm/mmap.c index fa11d91242e..5ecc2cf3e1d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -181,26 +181,36 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, } /* - * Remove one vm structure and free it. + * Unlink a file-based vm structure from its prio_tree, to hide + * vma from rmap and vmtruncate before freeing its page tables. */ -static void remove_vm_struct(struct vm_area_struct *vma) +void unlink_file_vma(struct vm_area_struct *vma) { struct file *file = vma->vm_file; - might_sleep(); if (file) { struct address_space *mapping = file->f_mapping; spin_lock(&mapping->i_mmap_lock); __remove_shared_vm_struct(vma, file, mapping); spin_unlock(&mapping->i_mmap_lock); } +} + +/* + * Close a vm structure and free it, returning the next. + */ +static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) +{ + struct vm_area_struct *next = vma->vm_next; + + might_sleep(); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); - if (file) - fput(file); - anon_vma_unlink(vma); + if (vma->vm_file) + fput(vma->vm_file); mpol_free(vma_policy(vma)); kmem_cache_free(vm_area_cachep, vma); + return next; } asmlinkage unsigned long sys_brk(unsigned long brk) @@ -832,7 +842,7 @@ none: } #ifdef CONFIG_PROC_FS -void __vm_stat_account(struct mm_struct *mm, unsigned long flags, +void vm_stat_account(struct mm_struct *mm, unsigned long flags, struct file *file, long pages) { const unsigned long stack_flags @@ -1070,6 +1080,17 @@ munmap_back: error = file->f_op->mmap(file, vma); if (error) goto unmap_and_free_vma; + if ((vma->vm_flags & (VM_SHARED | VM_WRITE | VM_RESERVED)) + == (VM_WRITE | VM_RESERVED)) { + printk(KERN_WARNING "program %s is using MAP_PRIVATE, " + "PROT_WRITE mmap of VM_RESERVED memory, which " + "is deprecated. Please report this to " + "linux-kernel@vger.kernel.org\n",current->comm); + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); + error = -EACCES; + goto unmap_and_free_vma; + } } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) @@ -1110,7 +1131,7 @@ munmap_back: } out: mm->total_vm += len >> PAGE_SHIFT; - __vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); + vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { mm->locked_vm += len >> PAGE_SHIFT; make_pages_present(addr, addr + len); @@ -1475,15 +1496,19 @@ static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, un mm->total_vm += grow; if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; - __vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow); + vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow); return 0; } -#ifdef CONFIG_STACK_GROWSUP +#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) /* - * vma is the first one with address > vma->vm_end. Have to extend vma. + * PA-RISC uses this for its stack; IA64 for its Register Backing Store. + * vma is the last one with address > vma->vm_end. Have to extend vma. */ -int expand_stack(struct vm_area_struct * vma, unsigned long address) +#ifdef CONFIG_STACK_GROWSUP +static inline +#endif +int expand_upwards(struct vm_area_struct *vma, unsigned long address) { int error; @@ -1521,6 +1546,13 @@ int expand_stack(struct vm_area_struct * vma, unsigned long address) anon_vma_unlock(vma); return error; } +#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ + +#ifdef CONFIG_STACK_GROWSUP +int expand_stack(struct vm_area_struct *vma, unsigned long address) +{ + return expand_upwards(vma, address); +} struct vm_area_struct * find_extend_vma(struct mm_struct *mm, unsigned long addr) @@ -1603,36 +1635,24 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr) } #endif -/* Normal function to fix up a mapping - * This function is the default for when an area has no specific - * function. This may be used as part of a more specific routine. - * - * By the time this function is called, the area struct has been - * removed from the process mapping list. - */ -static void unmap_vma(struct mm_struct *mm, struct vm_area_struct *area) -{ - size_t len = area->vm_end - area->vm_start; - - area->vm_mm->total_vm -= len >> PAGE_SHIFT; - if (area->vm_flags & VM_LOCKED) - area->vm_mm->locked_vm -= len >> PAGE_SHIFT; - vm_stat_unaccount(area); - remove_vm_struct(area); -} - /* - * Update the VMA and inode share lists. - * - * Ok - we have the memory areas we should free on the 'free' list, + * Ok - we have the memory areas we should free on the vma list, * so release them, and do the vma updates. + * + * Called with the mm semaphore held. */ -static void unmap_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) +static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) { + /* Update high watermark before we lower total_vm */ + update_hiwater_vm(mm); do { - struct vm_area_struct *next = vma->vm_next; - unmap_vma(mm, vma); - vma = next; + long nrpages = vma_pages(vma); + + mm->total_vm -= nrpages; + if (vma->vm_flags & VM_LOCKED) + mm->locked_vm -= nrpages; + vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages); + vma = remove_vma(vma); } while (vma); validate_mm(mm); } @@ -1651,14 +1671,13 @@ static void unmap_region(struct mm_struct *mm, unsigned long nr_accounted = 0; lru_add_drain(); - spin_lock(&mm->page_table_lock); tlb = tlb_gather_mmu(mm, 0); - unmap_vmas(&tlb, mm, vma, start, end, &nr_accounted, NULL); + update_hiwater_rss(mm); + unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL); vm_unacct_memory(nr_accounted); free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS, next? next->vm_start: 0); tlb_finish_mmu(tlb, start, end); - spin_unlock(&mm->page_table_lock); } /* @@ -1799,7 +1818,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) unmap_region(mm, vma, prev, start, end); /* Fix up all other VM information */ - unmap_vma_list(mm, vma); + remove_vma_list(mm, vma); return 0; } @@ -1933,34 +1952,21 @@ void exit_mmap(struct mm_struct *mm) unsigned long end; lru_add_drain(); - - spin_lock(&mm->page_table_lock); - flush_cache_mm(mm); tlb = tlb_gather_mmu(mm, 1); + /* Don't update_hiwater_rss(mm) here, do_exit already did */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ - end = unmap_vmas(&tlb, mm, vma, 0, -1, &nr_accounted, NULL); + end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL); vm_unacct_memory(nr_accounted); free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); tlb_finish_mmu(tlb, 0, end); - mm->mmap = mm->mmap_cache = NULL; - mm->mm_rb = RB_ROOT; - set_mm_counter(mm, rss, 0); - mm->total_vm = 0; - mm->locked_vm = 0; - - spin_unlock(&mm->page_table_lock); - /* - * Walk the list again, actually closing and freeing it - * without holding any MM locks. + * Walk the list again, actually closing and freeing it, + * with preemption enabled, without holding any MM locks. */ - while (vma) { - struct vm_area_struct *next = vma->vm_next; - remove_vm_struct(vma); - vma = next; - } + while (vma) + vma = remove_vma(vma); BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 57577f63b30..17a2b52b753 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -29,8 +29,9 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot) { pte_t *pte; + spinlock_t *ptl; - pte = pte_offset_map(pmd, addr); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); do { if (pte_present(*pte)) { pte_t ptent; @@ -44,7 +45,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, lazy_mmu_prot_update(ptent); } } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(pte - 1); + pte_unmap_unlock(pte - 1, ptl); } static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud, @@ -88,7 +89,6 @@ static void change_protection(struct vm_area_struct *vma, BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); - spin_lock(&mm->page_table_lock); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) @@ -96,7 +96,6 @@ static void change_protection(struct vm_area_struct *vma, change_pud_range(mm, pgd, addr, next, newprot); } while (pgd++, addr = next, addr != end); flush_tlb_range(vma, start, end); - spin_unlock(&mm->page_table_lock); } static int @@ -125,6 +124,14 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, * a MAP_NORESERVE private mapping to writable will now reserve. */ if (newflags & VM_WRITE) { + if (oldflags & VM_RESERVED) { + BUG_ON(oldflags & VM_WRITE); + printk(KERN_WARNING "program %s is using MAP_PRIVATE, " + "PROT_WRITE mprotect of VM_RESERVED memory, " + "which is deprecated. Please report this to " + "linux-kernel@vger.kernel.org\n",current->comm); + return -EACCES; + } if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED|VM_HUGETLB))) { charged = nrpages; if (security_vm_enough_memory(charged)) @@ -168,8 +175,8 @@ success: vma->vm_flags = newflags; vma->vm_page_prot = newprot; change_protection(vma, start, end, newprot); - __vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); - __vm_stat_account(mm, newflags, vma->vm_file, nrpages); + vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); + vm_stat_account(mm, newflags, vma->vm_file, nrpages); return 0; fail: diff --git a/mm/mremap.c b/mm/mremap.c index f343fc73a8b..b535438c363 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -22,35 +22,7 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> -static pte_t *get_one_pte_map_nested(struct mm_struct *mm, unsigned long addr) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte = NULL; - - pgd = pgd_offset(mm, addr); - if (pgd_none_or_clear_bad(pgd)) - goto end; - - pud = pud_offset(pgd, addr); - if (pud_none_or_clear_bad(pud)) - goto end; - - pmd = pmd_offset(pud, addr); - if (pmd_none_or_clear_bad(pmd)) - goto end; - - pte = pte_offset_map_nested(pmd, addr); - if (pte_none(*pte)) { - pte_unmap_nested(pte); - pte = NULL; - } -end: - return pte; -} - -static pte_t *get_one_pte_map(struct mm_struct *mm, unsigned long addr) +static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; pud_t *pud; @@ -68,35 +40,39 @@ static pte_t *get_one_pte_map(struct mm_struct *mm, unsigned long addr) if (pmd_none_or_clear_bad(pmd)) return NULL; - return pte_offset_map(pmd, addr); + return pmd; } -static inline pte_t *alloc_one_pte_map(struct mm_struct *mm, unsigned long addr) +static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; - pte_t *pte = NULL; pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); if (!pud) return NULL; + pmd = pmd_alloc(mm, pud, addr); - if (pmd) - pte = pte_alloc_map(mm, pmd, addr); - return pte; + if (!pmd) + return NULL; + + if (!pmd_present(*pmd) && __pte_alloc(mm, pmd, addr)) + return NULL; + + return pmd; } -static int -move_one_page(struct vm_area_struct *vma, unsigned long old_addr, - struct vm_area_struct *new_vma, unsigned long new_addr) +static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, + unsigned long old_addr, unsigned long old_end, + struct vm_area_struct *new_vma, pmd_t *new_pmd, + unsigned long new_addr) { struct address_space *mapping = NULL; struct mm_struct *mm = vma->vm_mm; - int error = 0; - pte_t *src, *dst; + pte_t *old_pte, *new_pte, pte; + spinlock_t *old_ptl, *new_ptl; if (vma->vm_file) { /* @@ -111,74 +87,69 @@ move_one_page(struct vm_area_struct *vma, unsigned long old_addr, new_vma->vm_truncate_count != vma->vm_truncate_count) new_vma->vm_truncate_count = 0; } - spin_lock(&mm->page_table_lock); - src = get_one_pte_map_nested(mm, old_addr); - if (src) { - /* - * Look to see whether alloc_one_pte_map needs to perform a - * memory allocation. If it does then we need to drop the - * atomic kmap - */ - dst = get_one_pte_map(mm, new_addr); - if (unlikely(!dst)) { - pte_unmap_nested(src); - if (mapping) - spin_unlock(&mapping->i_mmap_lock); - dst = alloc_one_pte_map(mm, new_addr); - if (mapping && !spin_trylock(&mapping->i_mmap_lock)) { - spin_unlock(&mm->page_table_lock); - spin_lock(&mapping->i_mmap_lock); - spin_lock(&mm->page_table_lock); - } - src = get_one_pte_map_nested(mm, old_addr); - } - /* - * Since alloc_one_pte_map can drop and re-acquire - * page_table_lock, we should re-check the src entry... - */ - if (src) { - if (dst) { - pte_t pte; - pte = ptep_clear_flush(vma, old_addr, src); - - /* ZERO_PAGE can be dependant on virtual addr */ - pte = move_pte(pte, new_vma->vm_page_prot, - old_addr, new_addr); - set_pte_at(mm, new_addr, dst, pte); - } else - error = -ENOMEM; - pte_unmap_nested(src); - } - if (dst) - pte_unmap(dst); + /* + * We don't have to worry about the ordering of src and dst + * pte locks because exclusive mmap_sem prevents deadlock. + */ + old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); + new_pte = pte_offset_map_nested(new_pmd, new_addr); + new_ptl = pte_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock(new_ptl); + + for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, + new_pte++, new_addr += PAGE_SIZE) { + if (pte_none(*old_pte)) + continue; + pte = ptep_clear_flush(vma, old_addr, old_pte); + /* ZERO_PAGE can be dependant on virtual addr */ + pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); + set_pte_at(mm, new_addr, new_pte, pte); } - spin_unlock(&mm->page_table_lock); + + if (new_ptl != old_ptl) + spin_unlock(new_ptl); + pte_unmap_nested(new_pte - 1); + pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) spin_unlock(&mapping->i_mmap_lock); - return error; } +#define LATENCY_LIMIT (64 * PAGE_SIZE) + static unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len) { - unsigned long offset; + unsigned long extent, next, old_end; + pmd_t *old_pmd, *new_pmd; - flush_cache_range(vma, old_addr, old_addr + len); + old_end = old_addr + len; + flush_cache_range(vma, old_addr, old_end); - /* - * This is not the clever way to do this, but we're taking the - * easy way out on the assumption that most remappings will be - * only a few pages.. This also makes error recovery easier. - */ - for (offset = 0; offset < len; offset += PAGE_SIZE) { - if (move_one_page(vma, old_addr + offset, - new_vma, new_addr + offset) < 0) - break; + for (; old_addr < old_end; old_addr += extent, new_addr += extent) { cond_resched(); + next = (old_addr + PMD_SIZE) & PMD_MASK; + if (next - 1 > old_end) + next = old_end; + extent = next - old_addr; + old_pmd = get_old_pmd(vma->vm_mm, old_addr); + if (!old_pmd) + continue; + new_pmd = alloc_new_pmd(vma->vm_mm, new_addr); + if (!new_pmd) + break; + next = (new_addr + PMD_SIZE) & PMD_MASK; + if (extent > next - new_addr) + extent = next - new_addr; + if (extent > LATENCY_LIMIT) + extent = LATENCY_LIMIT; + move_ptes(vma, old_pmd, old_addr, old_addr + extent, + new_vma, new_pmd, new_addr); } - return offset; + + return len + old_addr - old_end; /* how much done */ } static unsigned long move_vma(struct vm_area_struct *vma, @@ -191,6 +162,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, unsigned long new_pgoff; unsigned long moved_len; unsigned long excess = 0; + unsigned long hiwater_vm; int split = 0; /* @@ -229,17 +201,24 @@ static unsigned long move_vma(struct vm_area_struct *vma, } /* - * if we failed to move page tables we still do total_vm increment - * since do_munmap() will decrement it by old_len == new_len + * If we failed to move page tables we still do total_vm increment + * since do_munmap() will decrement it by old_len == new_len. + * + * Since total_vm is about to be raised artificially high for a + * moment, we need to restore high watermark afterwards: if stats + * are taken meanwhile, total_vm and hiwater_vm appear too high. + * If this were a serious issue, we'd add a flag to do_munmap(). */ + hiwater_vm = mm->hiwater_vm; mm->total_vm += new_len >> PAGE_SHIFT; - __vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); + vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); if (do_munmap(mm, old_addr, old_len) < 0) { /* OOM: unable to split vma, just get accounts right */ vm_unacct_memory(excess >> PAGE_SHIFT); excess = 0; } + mm->hiwater_vm = hiwater_vm; /* Restore VM_ACCOUNT if one or two pieces of vma left */ if (excess) { @@ -269,6 +248,7 @@ unsigned long do_mremap(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr) { + struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long ret = -EINVAL; unsigned long charged = 0; @@ -309,7 +289,7 @@ unsigned long do_mremap(unsigned long addr, if ((addr <= new_addr) && (addr+old_len) > new_addr) goto out; - ret = do_munmap(current->mm, new_addr, new_len); + ret = do_munmap(mm, new_addr, new_len); if (ret) goto out; } @@ -320,7 +300,7 @@ unsigned long do_mremap(unsigned long addr, * do_munmap does all the needed commit accounting */ if (old_len >= new_len) { - ret = do_munmap(current->mm, addr+new_len, old_len - new_len); + ret = do_munmap(mm, addr+new_len, old_len - new_len); if (ret && old_len != new_len) goto out; ret = addr; @@ -333,7 +313,7 @@ unsigned long do_mremap(unsigned long addr, * Ok, we need to grow.. or relocate. */ ret = -EFAULT; - vma = find_vma(current->mm, addr); + vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) goto out; if (is_vm_hugetlb_page(vma)) { @@ -349,14 +329,14 @@ unsigned long do_mremap(unsigned long addr, } if (vma->vm_flags & VM_LOCKED) { unsigned long locked, lock_limit; - locked = current->mm->locked_vm << PAGE_SHIFT; + locked = mm->locked_vm << PAGE_SHIFT; lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur; locked += new_len - old_len; ret = -EAGAIN; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) goto out; } - if (!may_expand_vm(current->mm, (new_len - old_len) >> PAGE_SHIFT)) { + if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) { ret = -ENOMEM; goto out; } @@ -383,11 +363,10 @@ unsigned long do_mremap(unsigned long addr, vma_adjust(vma, vma->vm_start, addr + new_len, vma->vm_pgoff, NULL); - current->mm->total_vm += pages; - __vm_stat_account(vma->vm_mm, vma->vm_flags, - vma->vm_file, pages); + mm->total_vm += pages; + vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); if (vma->vm_flags & VM_LOCKED) { - current->mm->locked_vm += pages; + mm->locked_vm += pages; make_pages_present(addr + old_len, addr + new_len); } diff --git a/mm/msync.c b/mm/msync.c index d0f5a1bce7c..0e040e9c39d 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -17,40 +17,48 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> -/* - * Called with mm->page_table_lock held to protect against other - * threads/the swapper from ripping pte's out from under us. - */ - -static void sync_pte_range(struct vm_area_struct *vma, pmd_t *pmd, +static void msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end) { pte_t *pte; + spinlock_t *ptl; + int progress = 0; - pte = pte_offset_map(pmd, addr); +again: + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { unsigned long pfn; struct page *page; + if (progress >= 64) { + progress = 0; + if (need_resched() || need_lockbreak(ptl)) + break; + } + progress++; if (!pte_present(*pte)) continue; if (!pte_maybe_dirty(*pte)) continue; pfn = pte_pfn(*pte); - if (!pfn_valid(pfn)) + if (unlikely(!pfn_valid(pfn))) { + print_bad_pte(vma, *pte, addr); continue; + } page = pfn_to_page(pfn); - if (PageReserved(page)) - continue; if (ptep_clear_flush_dirty(vma, addr, pte) || page_test_and_clear_dirty(page)) set_page_dirty(page); + progress += 3; } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(pte - 1); + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); + if (addr != end) + goto again; } -static inline void sync_pmd_range(struct vm_area_struct *vma, pud_t *pud, +static inline void msync_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end) { pmd_t *pmd; @@ -61,11 +69,11 @@ static inline void sync_pmd_range(struct vm_area_struct *vma, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; - sync_pte_range(vma, pmd, addr, next); + msync_pte_range(vma, pmd, addr, next); } while (pmd++, addr = next, addr != end); } -static inline void sync_pud_range(struct vm_area_struct *vma, pgd_t *pgd, +static inline void msync_pud_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end) { pud_t *pud; @@ -76,58 +84,34 @@ static inline void sync_pud_range(struct vm_area_struct *vma, pgd_t *pgd, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - sync_pmd_range(vma, pud, addr, next); + msync_pmd_range(vma, pud, addr, next); } while (pud++, addr = next, addr != end); } -static void sync_page_range(struct vm_area_struct *vma, +static void msync_page_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { - struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; unsigned long next; /* For hugepages we can't go walking the page table normally, * but that's ok, hugetlbfs is memory based, so we don't need - * to do anything more on an msync() */ - if (is_vm_hugetlb_page(vma)) + * to do anything more on an msync(). + * Can't do anything with VM_RESERVED regions either. + */ + if (vma->vm_flags & (VM_HUGETLB|VM_RESERVED)) return; BUG_ON(addr >= end); - pgd = pgd_offset(mm, addr); + pgd = pgd_offset(vma->vm_mm, addr); flush_cache_range(vma, addr, end); - spin_lock(&mm->page_table_lock); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - sync_pud_range(vma, pgd, addr, next); + msync_pud_range(vma, pgd, addr, next); } while (pgd++, addr = next, addr != end); - spin_unlock(&mm->page_table_lock); -} - -#ifdef CONFIG_PREEMPT -static inline void filemap_sync(struct vm_area_struct *vma, - unsigned long addr, unsigned long end) -{ - const size_t chunk = 64 * 1024; /* bytes */ - unsigned long next; - - do { - next = addr + chunk; - if (next > end || next < addr) - next = end; - sync_page_range(vma, addr, next); - cond_resched(); - } while (addr = next, addr != end); -} -#else -static inline void filemap_sync(struct vm_area_struct *vma, - unsigned long addr, unsigned long end) -{ - sync_page_range(vma, addr, end); } -#endif /* * MS_SYNC syncs the entire file - including mappings. @@ -150,7 +134,7 @@ static int msync_interval(struct vm_area_struct *vma, return -EBUSY; if (file && (vma->vm_flags & VM_SHARED)) { - filemap_sync(vma, addr, end); + msync_page_range(vma, addr, end); if (flags & MS_SYNC) { struct address_space *mapping = file->f_mapping; diff --git a/mm/nommu.c b/mm/nommu.c index 0ef241ae376..d1e076a487c 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -931,6 +931,8 @@ int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len) realalloc -= kobjsize(vml); askedalloc -= sizeof(*vml); kfree(vml); + + update_hiwater_vm(mm); mm->total_vm -= len >> PAGE_SHIFT; #ifdef DEBUG @@ -1047,7 +1049,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) EXPORT_SYMBOL(find_vma); -struct page * follow_page(struct mm_struct *mm, unsigned long addr, int write) +struct page *follow_page(struct mm_struct *mm, unsigned long address, + unsigned int foll_flags) { return NULL; } @@ -1078,19 +1081,6 @@ void arch_unmap_area(struct mm_struct *mm, unsigned long addr) { } -void update_mem_hiwater(struct task_struct *tsk) -{ - unsigned long rss; - - if (likely(tsk->mm)) { - rss = get_mm_counter(tsk->mm, rss); - if (tsk->mm->hiwater_rss < rss) - tsk->mm->hiwater_rss = rss; - if (tsk->mm->hiwater_vm < tsk->mm->total_vm) - tsk->mm->hiwater_vm = tsk->mm->total_vm; - } -} - void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 94c864eac9c..2dbdd98426f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -33,6 +33,7 @@ #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/cpuset.h> +#include <linux/memory_hotplug.h> #include <linux/nodemask.h> #include <linux/vmalloc.h> @@ -78,21 +79,44 @@ int min_free_kbytes = 1024; unsigned long __initdata nr_kernel_pages; unsigned long __initdata nr_all_pages; +static int page_outside_zone_boundaries(struct zone *zone, struct page *page) +{ + int ret = 0; + unsigned seq; + unsigned long pfn = page_to_pfn(page); + + do { + seq = zone_span_seqbegin(zone); + if (pfn >= zone->zone_start_pfn + zone->spanned_pages) + ret = 1; + else if (pfn < zone->zone_start_pfn) + ret = 1; + } while (zone_span_seqretry(zone, seq)); + + return ret; +} + +static int page_is_consistent(struct zone *zone, struct page *page) +{ +#ifdef CONFIG_HOLES_IN_ZONE + if (!pfn_valid(page_to_pfn(page))) + return 0; +#endif + if (zone != page_zone(page)) + return 0; + + return 1; +} /* * Temporary debugging check for pages not lying within a given zone. */ static int bad_range(struct zone *zone, struct page *page) { - if (page_to_pfn(page) >= zone->zone_start_pfn + zone->spanned_pages) + if (page_outside_zone_boundaries(zone, page)) return 1; - if (page_to_pfn(page) < zone->zone_start_pfn) - return 1; -#ifdef CONFIG_HOLES_IN_ZONE - if (!pfn_valid(page_to_pfn(page))) - return 1; -#endif - if (zone != page_zone(page)) + if (!page_is_consistent(zone, page)) return 1; + return 0; } @@ -114,7 +138,8 @@ static void bad_page(const char *function, struct page *page) 1 << PG_reclaim | 1 << PG_slab | 1 << PG_swapcache | - 1 << PG_writeback); + 1 << PG_writeback | + 1 << PG_reserved ); set_page_count(page, 0); reset_page_mapcount(page); page->mapping = NULL; @@ -153,7 +178,7 @@ static void prep_compound_page(struct page *page, unsigned long order) struct page *p = page + i; SetPageCompound(p); - p->private = (unsigned long)page; + set_page_private(p, (unsigned long)page); } } @@ -173,7 +198,7 @@ static void destroy_compound_page(struct page *page, unsigned long order) if (!PageCompound(p)) bad_page(__FUNCTION__, page); - if (p->private != (unsigned long)page) + if (page_private(p) != (unsigned long)page) bad_page(__FUNCTION__, page); ClearPageCompound(p); } @@ -186,18 +211,18 @@ static void destroy_compound_page(struct page *page, unsigned long order) * So, we don't need atomic page->flags operations here. */ static inline unsigned long page_order(struct page *page) { - return page->private; + return page_private(page); } static inline void set_page_order(struct page *page, int order) { - page->private = order; + set_page_private(page, order); __SetPagePrivate(page); } static inline void rmv_page_order(struct page *page) { __ClearPagePrivate(page); - page->private = 0; + set_page_private(page, 0); } /* @@ -237,14 +262,13 @@ __find_combined_index(unsigned long page_idx, unsigned int order) * (a) the buddy is free && * (b) the buddy is on the buddy system && * (c) a page and its buddy have the same order. - * for recording page's order, we use page->private and PG_private. + * for recording page's order, we use page_private(page) and PG_private. * */ static inline int page_is_buddy(struct page *page, int order) { if (PagePrivate(page) && (page_order(page) == order) && - !PageReserved(page) && page_count(page) == 0) return 1; return 0; @@ -264,7 +288,7 @@ static inline int page_is_buddy(struct page *page, int order) * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous * free pages of length of (1 << order) and marked with PG_Private.Page's - * order is recorded in page->private field. + * order is recorded in page_private(page) field. * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were * free, the remainder of the region must be split into blocks. @@ -327,7 +351,8 @@ static inline void free_pages_check(const char *function, struct page *page) 1 << PG_reclaim | 1 << PG_slab | 1 << PG_swapcache | - 1 << PG_writeback ))) + 1 << PG_writeback | + 1 << PG_reserved ))) bad_page(function, page); if (PageDirty(page)) __ClearPageDirty(page); @@ -455,13 +480,14 @@ static void prep_new_page(struct page *page, int order) 1 << PG_reclaim | 1 << PG_slab | 1 << PG_swapcache | - 1 << PG_writeback ))) + 1 << PG_writeback | + 1 << PG_reserved ))) bad_page(__FUNCTION__, page); page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_referenced | 1 << PG_arch_1 | 1 << PG_checked | 1 << PG_mappedtodisk); - page->private = 0; + set_page_private(page, 0); set_page_refs(page, order); kernel_map_pages(page, 1 << order, 1); } @@ -1016,7 +1042,7 @@ void __pagevec_free(struct pagevec *pvec) fastcall void __free_pages(struct page *page, unsigned int order) { - if (!PageReserved(page) && put_page_testzero(page)) { + if (put_page_testzero(page)) { if (order == 0) free_hot_page(page); else @@ -1305,12 +1331,9 @@ void show_free_areas(void) } else printk("\n"); - for (cpu = 0; cpu < NR_CPUS; ++cpu) { + for_each_cpu(cpu) { struct per_cpu_pageset *pageset; - if (!cpu_possible(cpu)) - continue; - pageset = zone_pcp(zone, cpu); for (temperature = 0; temperature < 2; temperature++) @@ -1660,7 +1683,7 @@ static void __init calculate_zone_totalpages(struct pglist_data *pgdat, * up by free_all_bootmem() once the early boot process is * done. Non-atomic initialization, single-pass. */ -void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone, +void __devinit memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { struct page *page; @@ -1674,7 +1697,7 @@ void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone, continue; page = pfn_to_page(pfn); set_page_links(page, zone, nid, pfn); - set_page_count(page, 0); + set_page_count(page, 1); reset_page_mapcount(page); SetPageReserved(page); INIT_LIST_HEAD(&page->lru); @@ -1721,29 +1744,29 @@ static int __devinit zone_batchsize(struct zone *zone) /* * The per-cpu-pages pools are set to around 1000th of the - * size of the zone. But no more than 1/4 of a meg - there's - * no point in going beyond the size of L2 cache. + * size of the zone. But no more than 1/2 of a meg. * * OK, so we don't know how big the cache is. So guess. */ batch = zone->present_pages / 1024; - if (batch * PAGE_SIZE > 256 * 1024) - batch = (256 * 1024) / PAGE_SIZE; + if (batch * PAGE_SIZE > 512 * 1024) + batch = (512 * 1024) / PAGE_SIZE; batch /= 4; /* We effectively *= 4 below */ if (batch < 1) batch = 1; /* - * Clamp the batch to a 2^n - 1 value. Having a power - * of 2 value was found to be more likely to have - * suboptimal cache aliasing properties in some cases. + * We will be trying to allcoate bigger chunks of contiguous + * memory of the order of fls(batch). This should result in + * better cache coloring. * - * For example if 2 tasks are alternately allocating - * batches of pages, one task can end up with a lot - * of pages of one half of the possible page colors - * and the other with pages of the other colors. + * A sanity check also to ensure that batch is still in limits. */ - batch = (1 << fls(batch + batch/2)) - 1; + batch = (1 << fls(batch + batch/2)); + + if (fls(batch) >= (PAGE_SHIFT + MAX_ORDER - 2)) + batch = PAGE_SHIFT + ((MAX_ORDER - 1 - PAGE_SHIFT)/2); + return batch; } @@ -1755,7 +1778,7 @@ inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) pcp = &p->pcp[0]; /* hot */ pcp->count = 0; - pcp->low = 2 * batch; + pcp->low = 0; pcp->high = 6 * batch; pcp->batch = max(1UL, 1 * batch); INIT_LIST_HEAD(&pcp->list); @@ -1764,7 +1787,7 @@ inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) pcp->count = 0; pcp->low = 0; pcp->high = 2 * batch; - pcp->batch = max(1UL, 1 * batch); + pcp->batch = max(1UL, batch/2); INIT_LIST_HEAD(&pcp->list); } @@ -1873,6 +1896,60 @@ void __init setup_per_cpu_pageset() #endif +static __devinit +void zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) +{ + int i; + struct pglist_data *pgdat = zone->zone_pgdat; + + /* + * The per-page waitqueue mechanism uses hashed waitqueues + * per zone. + */ + zone->wait_table_size = wait_table_size(zone_size_pages); + zone->wait_table_bits = wait_table_bits(zone->wait_table_size); + zone->wait_table = (wait_queue_head_t *) + alloc_bootmem_node(pgdat, zone->wait_table_size + * sizeof(wait_queue_head_t)); + + for(i = 0; i < zone->wait_table_size; ++i) + init_waitqueue_head(zone->wait_table + i); +} + +static __devinit void zone_pcp_init(struct zone *zone) +{ + int cpu; + unsigned long batch = zone_batchsize(zone); + + for (cpu = 0; cpu < NR_CPUS; cpu++) { +#ifdef CONFIG_NUMA + /* Early boot. Slab allocator not functional yet */ + zone->pageset[cpu] = &boot_pageset[cpu]; + setup_pageset(&boot_pageset[cpu],0); +#else + setup_pageset(zone_pcp(zone,cpu), batch); +#endif + } + printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n", + zone->name, zone->present_pages, batch); +} + +static __devinit void init_currently_empty_zone(struct zone *zone, + unsigned long zone_start_pfn, unsigned long size) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + + zone_wait_table_init(zone, size); + pgdat->nr_zones = zone_idx(zone) + 1; + + zone->zone_mem_map = pfn_to_page(zone_start_pfn); + zone->zone_start_pfn = zone_start_pfn; + + memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn); + + zone_init_free_lists(pgdat, zone, zone->spanned_pages); +} + /* * Set up the zone data structures: * - mark all pages reserved @@ -1882,10 +1959,11 @@ void __init setup_per_cpu_pageset() static void __init free_area_init_core(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) { - unsigned long i, j; - int cpu, nid = pgdat->node_id; + unsigned long j; + int nid = pgdat->node_id; unsigned long zone_start_pfn = pgdat->node_start_pfn; + pgdat_resize_init(pgdat); pgdat->nr_zones = 0; init_waitqueue_head(&pgdat->kswapd_wait); pgdat->kswapd_max_order = 0; @@ -1893,7 +1971,6 @@ static void __init free_area_init_core(struct pglist_data *pgdat, for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; unsigned long size, realsize; - unsigned long batch; realsize = size = zones_size[j]; if (zholes_size) @@ -1908,24 +1985,13 @@ static void __init free_area_init_core(struct pglist_data *pgdat, zone->name = zone_names[j]; spin_lock_init(&zone->lock); spin_lock_init(&zone->lru_lock); + zone_seqlock_init(zone); zone->zone_pgdat = pgdat; zone->free_pages = 0; zone->temp_priority = zone->prev_priority = DEF_PRIORITY; - batch = zone_batchsize(zone); - - for (cpu = 0; cpu < NR_CPUS; cpu++) { -#ifdef CONFIG_NUMA - /* Early boot. Slab allocator not functional yet */ - zone->pageset[cpu] = &boot_pageset[cpu]; - setup_pageset(&boot_pageset[cpu],0); -#else - setup_pageset(zone_pcp(zone,cpu), batch); -#endif - } - printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n", - zone_names[j], realsize, batch); + zone_pcp_init(zone); INIT_LIST_HEAD(&zone->active_list); INIT_LIST_HEAD(&zone->inactive_list); zone->nr_scan_active = 0; @@ -1936,32 +2002,9 @@ static void __init free_area_init_core(struct pglist_data *pgdat, if (!size) continue; - /* - * The per-page waitqueue mechanism uses hashed waitqueues - * per zone. - */ - zone->wait_table_size = wait_table_size(size); - zone->wait_table_bits = - wait_table_bits(zone->wait_table_size); - zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node(pgdat, zone->wait_table_size - * sizeof(wait_queue_head_t)); - - for(i = 0; i < zone->wait_table_size; ++i) - init_waitqueue_head(zone->wait_table + i); - - pgdat->nr_zones = j+1; - - zone->zone_mem_map = pfn_to_page(zone_start_pfn); - zone->zone_start_pfn = zone_start_pfn; - - memmap_init(size, nid, j, zone_start_pfn); - zonetable_add(zone, nid, j, zone_start_pfn, size); - + init_currently_empty_zone(zone, zone_start_pfn, size); zone_start_pfn += size; - - zone_init_free_lists(pgdat, zone, zone->spanned_pages); } } @@ -2361,7 +2404,7 @@ static void setup_per_zone_lowmem_reserve(void) * that the pages_{min,low,high} values for each zone are set correctly * with respect to min_free_kbytes. */ -static void setup_per_zone_pages_min(void) +void setup_per_zone_pages_min(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; diff --git a/mm/page_io.c b/mm/page_io.c index 330e00d6db0..bb2b0d53889 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -91,7 +91,8 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) unlock_page(page); goto out; } - bio = get_swap_bio(GFP_NOIO, page->private, page, end_swap_bio_write); + bio = get_swap_bio(GFP_NOIO, page_private(page), page, + end_swap_bio_write); if (bio == NULL) { set_page_dirty(page); unlock_page(page); @@ -115,7 +116,8 @@ int swap_readpage(struct file *file, struct page *page) BUG_ON(!PageLocked(page)); ClearPageUptodate(page); - bio = get_swap_bio(GFP_KERNEL, page->private, page, end_swap_bio_read); + bio = get_swap_bio(GFP_KERNEL, page_private(page), page, + end_swap_bio_read); if (bio == NULL) { unlock_page(page); ret = -ENOMEM; diff --git a/mm/rmap.c b/mm/rmap.c index 450f5241b5a..914d04b98be 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -32,7 +32,7 @@ * page->flags PG_locked (lock_page) * mapping->i_mmap_lock * anon_vma->lock - * mm->page_table_lock + * mm->page_table_lock or pte_lock * zone->lru_lock (in mark_page_accessed) * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) @@ -244,37 +244,44 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) /* * Check that @page is mapped at @address into @mm. * - * On success returns with mapped pte and locked mm->page_table_lock. + * On success returns with pte mapped and locked. */ pte_t *page_check_address(struct page *page, struct mm_struct *mm, - unsigned long address) + unsigned long address, spinlock_t **ptlp) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; + spinlock_t *ptl; - /* - * We need the page_table_lock to protect us from page faults, - * munmap, fork, etc... - */ - spin_lock(&mm->page_table_lock); pgd = pgd_offset(mm, address); - if (likely(pgd_present(*pgd))) { - pud = pud_offset(pgd, address); - if (likely(pud_present(*pud))) { - pmd = pmd_offset(pud, address); - if (likely(pmd_present(*pmd))) { - pte = pte_offset_map(pmd, address); - if (likely(pte_present(*pte) && - page_to_pfn(page) == pte_pfn(*pte))) - return pte; - pte_unmap(pte); - } - } + if (!pgd_present(*pgd)) + return NULL; + + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return NULL; + + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) + return NULL; + + pte = pte_offset_map(pmd, address); + /* Make a quick check before getting the lock */ + if (!pte_present(*pte)) { + pte_unmap(pte); + return NULL; + } + + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) { + *ptlp = ptl; + return pte; } - spin_unlock(&mm->page_table_lock); - return ERR_PTR(-ENOENT); + pte_unmap_unlock(pte, ptl); + return NULL; } /* @@ -287,24 +294,28 @@ static int page_referenced_one(struct page *page, struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *pte; + spinlock_t *ptl; int referenced = 0; address = vma_address(page, vma); if (address == -EFAULT) goto out; - pte = page_check_address(page, mm, address); - if (!IS_ERR(pte)) { - if (ptep_clear_flush_young(vma, address, pte)) - referenced++; + pte = page_check_address(page, mm, address, &ptl); + if (!pte) + goto out; - if (mm != current->mm && !ignore_token && has_swap_token(mm)) - referenced++; + if (ptep_clear_flush_young(vma, address, pte)) + referenced++; - (*mapcount)--; - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); - } + /* Pretend the page is referenced if the task has the + swap token and is in the middle of a page fault. */ + if (mm != current->mm && !ignore_token && has_swap_token(mm) && + rwsem_is_locked(&mm->mmap_sem)) + referenced++; + + (*mapcount)--; + pte_unmap_unlock(pte, ptl); out: return referenced; } @@ -434,15 +445,11 @@ int page_referenced(struct page *page, int is_locked, int ignore_token) * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * - * The caller needs to hold the mm->page_table_lock. + * The caller needs to hold the pte lock. */ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { - BUG_ON(PageReserved(page)); - - inc_mm_counter(vma->vm_mm, anon_rss); - if (atomic_inc_and_test(&page->_mapcount)) { struct anon_vma *anon_vma = vma->anon_vma; @@ -461,13 +468,12 @@ void page_add_anon_rmap(struct page *page, * page_add_file_rmap - add pte mapping to a file page * @page: the page to add the mapping to * - * The caller needs to hold the mm->page_table_lock. + * The caller needs to hold the pte lock. */ void page_add_file_rmap(struct page *page) { BUG_ON(PageAnon(page)); - if (!pfn_valid(page_to_pfn(page)) || PageReserved(page)) - return; + BUG_ON(!pfn_valid(page_to_pfn(page))); if (atomic_inc_and_test(&page->_mapcount)) inc_page_state(nr_mapped); @@ -477,12 +483,10 @@ void page_add_file_rmap(struct page *page) * page_remove_rmap - take down pte mapping from a page * @page: page to remove mapping from * - * Caller needs to hold the mm->page_table_lock. + * The caller needs to hold the pte lock. */ void page_remove_rmap(struct page *page) { - BUG_ON(PageReserved(page)); - if (atomic_add_negative(-1, &page->_mapcount)) { BUG_ON(page_mapcount(page) < 0); /* @@ -510,14 +514,15 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma) unsigned long address; pte_t *pte; pte_t pteval; + spinlock_t *ptl; int ret = SWAP_AGAIN; address = vma_address(page, vma); if (address == -EFAULT) goto out; - pte = page_check_address(page, mm, address); - if (IS_ERR(pte)) + pte = page_check_address(page, mm, address, &ptl); + if (!pte) goto out; /* @@ -541,8 +546,11 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma) if (pte_dirty(pteval)) set_page_dirty(page); + /* Update high watermark before we lower rss */ + update_hiwater_rss(mm); + if (PageAnon(page)) { - swp_entry_t entry = { .val = page->private }; + swp_entry_t entry = { .val = page_private(page) }; /* * Store the swap location in the pte. * See handle_pte_fault() ... @@ -551,21 +559,21 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma) swap_duplicate(entry); if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); - list_add(&mm->mmlist, &init_mm.mmlist); + if (list_empty(&mm->mmlist)) + list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); BUG_ON(pte_file(*pte)); dec_mm_counter(mm, anon_rss); - } + } else + dec_mm_counter(mm, file_rss); - dec_mm_counter(mm, rss); page_remove_rmap(page); page_cache_release(page); out_unmap: - pte_unmap(pte); - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(pte, ptl); out: return ret; } @@ -599,19 +607,14 @@ static void try_to_unmap_cluster(unsigned long cursor, pgd_t *pgd; pud_t *pud; pmd_t *pmd; - pte_t *pte, *original_pte; + pte_t *pte; pte_t pteval; + spinlock_t *ptl; struct page *page; unsigned long address; unsigned long end; unsigned long pfn; - /* - * We need the page_table_lock to protect us from page faults, - * munmap, fork, etc... - */ - spin_lock(&mm->page_table_lock); - address = (vma->vm_start + cursor) & CLUSTER_MASK; end = address + CLUSTER_SIZE; if (address < vma->vm_start) @@ -621,30 +624,33 @@ static void try_to_unmap_cluster(unsigned long cursor, pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) - goto out_unlock; + return; pud = pud_offset(pgd, address); if (!pud_present(*pud)) - goto out_unlock; + return; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) - goto out_unlock; + return; + + pte = pte_offset_map_lock(mm, pmd, address, &ptl); - for (original_pte = pte = pte_offset_map(pmd, address); - address < end; pte++, address += PAGE_SIZE) { + /* Update high watermark before we lower rss */ + update_hiwater_rss(mm); + for (; address < end; pte++, address += PAGE_SIZE) { if (!pte_present(*pte)) continue; pfn = pte_pfn(*pte); - if (!pfn_valid(pfn)) + if (unlikely(!pfn_valid(pfn))) { + print_bad_pte(vma, *pte, address); continue; + } page = pfn_to_page(pfn); BUG_ON(PageAnon(page)); - if (PageReserved(page)) - continue; if (ptep_clear_flush_young(vma, address, pte)) continue; @@ -663,13 +669,10 @@ static void try_to_unmap_cluster(unsigned long cursor, page_remove_rmap(page); page_cache_release(page); - dec_mm_counter(mm, rss); + dec_mm_counter(mm, file_rss); (*mapcount)--; } - - pte_unmap(original_pte); -out_unlock: - spin_unlock(&mm->page_table_lock); + pte_unmap_unlock(pte - 1, ptl); } static int try_to_unmap_anon(struct page *page) @@ -806,7 +809,6 @@ int try_to_unmap(struct page *page) { int ret; - BUG_ON(PageReserved(page)); BUG_ON(!PageLocked(page)); if (PageAnon(page)) diff --git a/mm/shmem.c b/mm/shmem.c index 55e04a0734c..dc25565a61e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -71,9 +71,6 @@ /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 -/* Keep swapped page count in private field of indirect struct page */ -#define nr_swapped private - /* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */ enum sgp_type { SGP_QUICK, /* don't try more than file page cache lookup */ @@ -324,8 +321,10 @@ static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, uns entry->val = value; info->swapped += incdec; - if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) - kmap_atomic_to_page(entry)->nr_swapped += incdec; + if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) { + struct page *page = kmap_atomic_to_page(entry); + set_page_private(page, page_private(page) + incdec); + } } /* @@ -368,9 +367,8 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long spin_unlock(&info->lock); page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO); - if (page) { - page->nr_swapped = 0; - } + if (page) + set_page_private(page, 0); spin_lock(&info->lock); if (!page) { @@ -561,7 +559,7 @@ static void shmem_truncate(struct inode *inode) diroff = 0; } subdir = dir[diroff]; - if (subdir && subdir->nr_swapped) { + if (subdir && page_private(subdir)) { size = limit - idx; if (size > ENTRIES_PER_PAGE) size = ENTRIES_PER_PAGE; @@ -572,10 +570,10 @@ static void shmem_truncate(struct inode *inode) nr_swaps_freed += freed; if (offset) spin_lock(&info->lock); - subdir->nr_swapped -= freed; + set_page_private(subdir, page_private(subdir) - freed); if (offset) spin_unlock(&info->lock); - BUG_ON(subdir->nr_swapped > offset); + BUG_ON(page_private(subdir) > offset); } if (offset) offset = 0; @@ -743,7 +741,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s dir = shmem_dir_map(subdir); } subdir = *dir; - if (subdir && subdir->nr_swapped) { + if (subdir && page_private(subdir)) { ptr = shmem_swp_map(subdir); size = limit - idx; if (size > ENTRIES_PER_PAGE) @@ -1201,7 +1199,7 @@ static int shmem_populate(struct vm_area_struct *vma, page_cache_release(page); return err; } - } else { + } else if (vma->vm_flags & VM_NONLINEAR) { /* No page was found just because we can't read it in * now (being here implies nonblock != 0), but the page * may exist, so set the PTE to fault it in later. */ @@ -1506,8 +1504,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ */ if (!offset) mark_page_accessed(page); - } else + } else { page = ZERO_PAGE(0); + page_cache_get(page); + } /* * Ok, we have the page, and it's up-to-date, so diff --git a/mm/slab.c b/mm/slab.c index d30423f167a..22bfb0b2ac8 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2419,6 +2419,7 @@ retry: next = slab_bufctl(slabp)[slabp->free]; #if DEBUG slab_bufctl(slabp)[slabp->free] = BUFCTL_FREE; + WARN_ON(numa_node_id() != slabp->nodeid); #endif slabp->free = next; } @@ -2633,8 +2634,10 @@ static void free_block(kmem_cache_t *cachep, void **objpp, int nr_objects, int n check_spinlock_acquired_node(cachep, node); check_slabp(cachep, slabp); - #if DEBUG + /* Verify that the slab belongs to the intended node */ + WARN_ON(slabp->nodeid != node); + if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) { printk(KERN_ERR "slab: double free detected in cache " "'%s', objp %p\n", cachep->name, objp); diff --git a/mm/sparse.c b/mm/sparse.c index 347249a4917..72079b538e2 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -5,8 +5,10 @@ #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/bootmem.h> +#include <linux/highmem.h> #include <linux/module.h> #include <linux/spinlock.h> +#include <linux/vmalloc.h> #include <asm/dma.h> /* @@ -72,6 +74,31 @@ static inline int sparse_index_init(unsigned long section_nr, int nid) } #endif +/* + * Although written for the SPARSEMEM_EXTREME case, this happens + * to also work for the flat array case becase + * NR_SECTION_ROOTS==NR_MEM_SECTIONS. + */ +int __section_nr(struct mem_section* ms) +{ + unsigned long root_nr; + struct mem_section* root; + + for (root_nr = 0; + root_nr < NR_MEM_SECTIONS; + root_nr += SECTIONS_PER_ROOT) { + root = __nr_to_section(root_nr); + + if (!root) + continue; + + if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT))) + break; + } + + return (root_nr * SECTIONS_PER_ROOT) + (ms - root); +} + /* Record a memory area against a node. */ void memory_present(int nid, unsigned long start, unsigned long end) { @@ -162,6 +189,45 @@ static struct page *sparse_early_mem_map_alloc(unsigned long pnum) return NULL; } +static struct page *__kmalloc_section_memmap(unsigned long nr_pages) +{ + struct page *page, *ret; + unsigned long memmap_size = sizeof(struct page) * nr_pages; + + page = alloc_pages(GFP_KERNEL, get_order(memmap_size)); + if (page) + goto got_map_page; + + ret = vmalloc(memmap_size); + if (ret) + goto got_map_ptr; + + return NULL; +got_map_page: + ret = (struct page *)pfn_to_kaddr(page_to_pfn(page)); +got_map_ptr: + memset(ret, 0, memmap_size); + + return ret; +} + +static int vaddr_in_vmalloc_area(void *addr) +{ + if (addr >= (void *)VMALLOC_START && + addr < (void *)VMALLOC_END) + return 1; + return 0; +} + +static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) +{ + if (vaddr_in_vmalloc_area(memmap)) + vfree(memmap); + else + free_pages((unsigned long)memmap, + get_order(sizeof(struct page) * nr_pages)); +} + /* * Allocate the accumulated non-linear sections, allocate a mem_map * for each and record the physical to section mapping. @@ -187,14 +253,37 @@ void sparse_init(void) * set. If this is <=0, then that means that the passed-in * map was not consumed and must be freed. */ -int sparse_add_one_section(unsigned long start_pfn, int nr_pages, struct page *map) +int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, + int nr_pages) { - struct mem_section *ms = __pfn_to_section(start_pfn); + unsigned long section_nr = pfn_to_section_nr(start_pfn); + struct pglist_data *pgdat = zone->zone_pgdat; + struct mem_section *ms; + struct page *memmap; + unsigned long flags; + int ret; - if (ms->section_mem_map & SECTION_MARKED_PRESENT) - return -EEXIST; + /* + * no locking for this, because it does its own + * plus, it does a kmalloc + */ + sparse_index_init(section_nr, pgdat->node_id); + memmap = __kmalloc_section_memmap(nr_pages); + + pgdat_resize_lock(pgdat, &flags); + ms = __pfn_to_section(start_pfn); + if (ms->section_mem_map & SECTION_MARKED_PRESENT) { + ret = -EEXIST; + goto out; + } ms->section_mem_map |= SECTION_MARKED_PRESENT; - return sparse_init_one_section(ms, pfn_to_section_nr(start_pfn), map); + ret = sparse_init_one_section(ms, section_nr, memmap); + + if (ret <= 0) + __kfree_section_memmap(memmap, nr_pages); +out: + pgdat_resize_unlock(pgdat, &flags); + return ret; } diff --git a/mm/swap.c b/mm/swap.c index 7771d2803f6..b89512877ec 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -39,7 +39,7 @@ int page_cluster; void put_page(struct page *page) { if (unlikely(PageCompound(page))) { - page = (struct page *)page->private; + page = (struct page *)page_private(page); if (put_page_testzero(page)) { void (*dtor)(struct page *page); @@ -48,7 +48,7 @@ void put_page(struct page *page) } return; } - if (!PageReserved(page) && put_page_testzero(page)) + if (put_page_testzero(page)) __page_cache_release(page); } EXPORT_SYMBOL(put_page); @@ -215,7 +215,7 @@ void release_pages(struct page **pages, int nr, int cold) struct page *page = pages[i]; struct zone *pagezone; - if (PageReserved(page) || !put_page_testzero(page)) + if (!put_page_testzero(page)) continue; pagezone = page_zone(page); diff --git a/mm/swap_state.c b/mm/swap_state.c index 132164f7d0a..dfd9a46755b 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -83,7 +83,7 @@ static int __add_to_swap_cache(struct page *page, swp_entry_t entry, page_cache_get(page); SetPageLocked(page); SetPageSwapCache(page); - page->private = entry.val; + set_page_private(page, entry.val); total_swapcache_pages++; pagecache_acct(1); } @@ -126,8 +126,8 @@ void __delete_from_swap_cache(struct page *page) BUG_ON(PageWriteback(page)); BUG_ON(PagePrivate(page)); - radix_tree_delete(&swapper_space.page_tree, page->private); - page->private = 0; + radix_tree_delete(&swapper_space.page_tree, page_private(page)); + set_page_private(page, 0); ClearPageSwapCache(page); total_swapcache_pages--; pagecache_acct(-1); @@ -197,7 +197,7 @@ void delete_from_swap_cache(struct page *page) { swp_entry_t entry; - entry.val = page->private; + entry.val = page_private(page); write_lock_irq(&swapper_space.tree_lock); __delete_from_swap_cache(page); @@ -259,8 +259,7 @@ static inline void free_swap_cache(struct page *page) /* * Perform a free_page(), also freeing any swap cache associated with - * this page if it is the last user of the page. Can not do a lock_page, - * as we are holding the page_table_lock spinlock. + * this page if it is the last user of the page. */ void free_page_and_swap_cache(struct page *page) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 1dcaeda039f..8970c0b7419 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -61,7 +61,7 @@ void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) swp_entry_t entry; down_read(&swap_unplug_sem); - entry.val = page->private; + entry.val = page_private(page); if (PageSwapCache(page)) { struct block_device *bdev = swap_info[swp_type(entry)].bdev; struct backing_dev_info *bdi; @@ -69,8 +69,8 @@ void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page) /* * If the page is removed from swapcache from under us (with a * racy try_to_unuse/swapoff) we need an additional reference - * count to avoid reading garbage from page->private above. If - * the WARN_ON triggers during a swapoff it maybe the race + * count to avoid reading garbage from page_private(page) above. + * If the WARN_ON triggers during a swapoff it maybe the race * condition and it's harmless. However if it triggers without * swapoff it signals a problem. */ @@ -294,7 +294,7 @@ static inline int page_swapcount(struct page *page) struct swap_info_struct *p; swp_entry_t entry; - entry.val = page->private; + entry.val = page_private(page); p = swap_info_get(entry); if (p) { /* Subtract the 1 for the swap cache itself */ @@ -339,7 +339,7 @@ int remove_exclusive_swap_page(struct page *page) if (page_count(page) != 2) /* 2: us + cache */ return 0; - entry.val = page->private; + entry.val = page_private(page); p = swap_info_get(entry); if (!p) return 0; @@ -398,17 +398,14 @@ void free_swap_and_cache(swp_entry_t entry) } /* - * Always set the resulting pte to be nowrite (the same as COW pages - * after one process has exited). We don't know just how many PTEs will - * share this swap entry, so be cautious and let do_wp_page work out - * what to do if a write is requested later. - * - * vma->vm_mm->page_table_lock is held. + * No need to decide whether this PTE shares the swap entry with others, + * just let do_wp_page work it out if a write is requested later - to + * force COW, vm_page_prot omits write permission from any private vma. */ static void unuse_pte(struct vm_area_struct *vma, pte_t *pte, unsigned long addr, swp_entry_t entry, struct page *page) { - inc_mm_counter(vma->vm_mm, rss); + inc_mm_counter(vma->vm_mm, anon_rss); get_page(page); set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); @@ -425,23 +422,25 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { - pte_t *pte; pte_t swp_pte = swp_entry_to_pte(entry); + pte_t *pte; + spinlock_t *ptl; + int found = 0; - pte = pte_offset_map(pmd, addr); + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { /* * swapoff spends a _lot_ of time in this loop! * Test inline before going to call unuse_pte. */ if (unlikely(pte_same(*pte, swp_pte))) { - unuse_pte(vma, pte, addr, entry, page); - pte_unmap(pte); - return 1; + unuse_pte(vma, pte++, addr, entry, page); + found = 1; + break; } } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap(pte - 1); - return 0; + pte_unmap_unlock(pte - 1, ptl); + return found; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, @@ -523,12 +522,10 @@ static int unuse_mm(struct mm_struct *mm, down_read(&mm->mmap_sem); lock_page(page); } - spin_lock(&mm->page_table_lock); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma && unuse_vma(vma, entry, page)) break; } - spin_unlock(&mm->page_table_lock); up_read(&mm->mmap_sem); /* * Currently unuse_mm cannot fail, but leave error handling @@ -1045,7 +1042,7 @@ int page_queue_congested(struct page *page) BUG_ON(!PageLocked(page)); /* It pins the swap_info_struct */ if (PageSwapCache(page)) { - swp_entry_t entry = { .val = page->private }; + swp_entry_t entry = { .val = page_private(page) }; struct swap_info_struct *sis; sis = get_swap_info_struct(swp_type(entry)); diff --git a/mm/thrash.c b/mm/thrash.c index 11461f7ad83..eff3c18c33a 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -19,7 +19,7 @@ static unsigned long swap_token_check; struct mm_struct * swap_token_mm = &init_mm; #define SWAP_TOKEN_CHECK_INTERVAL (HZ * 2) -#define SWAP_TOKEN_TIMEOUT 0 +#define SWAP_TOKEN_TIMEOUT (300 * HZ) /* * Currently disabled; Needs further code to work at HZ * 300. */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1150229b636..54a90e83cb3 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -5,6 +5,7 @@ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 + * Numa awareness, Christoph Lameter, SGI, June 2005 */ #include <linux/mm.h> @@ -88,7 +89,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, { pte_t *pte; - pte = pte_alloc_kernel(&init_mm, pmd, addr); + pte = pte_alloc_kernel(pmd, addr); if (!pte) return -ENOMEM; do { @@ -146,20 +147,18 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) BUG_ON(addr >= end); pgd = pgd_offset_k(addr); - spin_lock(&init_mm.page_table_lock); do { next = pgd_addr_end(addr, end); err = vmap_pud_range(pgd, addr, next, prot, pages); if (err) break; } while (pgd++, addr = next, addr != end); - spin_unlock(&init_mm.page_table_lock); flush_cache_vmap((unsigned long) area->addr, end); return err; } -struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, - unsigned long start, unsigned long end) +struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, + unsigned long start, unsigned long end, int node) { struct vm_struct **p, *tmp, *area; unsigned long align = 1; @@ -178,7 +177,7 @@ struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, addr = ALIGN(start, align); size = PAGE_ALIGN(size); - area = kmalloc(sizeof(*area), GFP_KERNEL); + area = kmalloc_node(sizeof(*area), GFP_KERNEL, node); if (unlikely(!area)) return NULL; @@ -231,6 +230,12 @@ out: return NULL; } +struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, + unsigned long start, unsigned long end) +{ + return __get_vm_area_node(size, flags, start, end, -1); +} + /** * get_vm_area - reserve a contingous kernel virtual area * @@ -246,6 +251,11 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) return __get_vm_area(size, flags, VMALLOC_START, VMALLOC_END); } +struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int node) +{ + return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node); +} + /* Caller must hold vmlist_lock */ struct vm_struct *__remove_vm_area(void *addr) { @@ -342,7 +352,6 @@ void vfree(void *addr) BUG_ON(in_interrupt()); __vunmap(addr, 1); } - EXPORT_SYMBOL(vfree); /** @@ -360,7 +369,6 @@ void vunmap(void *addr) BUG_ON(in_interrupt()); __vunmap(addr, 0); } - EXPORT_SYMBOL(vunmap); /** @@ -392,10 +400,10 @@ void *vmap(struct page **pages, unsigned int count, return area->addr; } - EXPORT_SYMBOL(vmap); -void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) +void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, + pgprot_t prot, int node) { struct page **pages; unsigned int nr_pages, array_size, i; @@ -406,9 +414,9 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) area->nr_pages = nr_pages; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) - pages = __vmalloc(array_size, gfp_mask, PAGE_KERNEL); + pages = __vmalloc_node(array_size, gfp_mask, PAGE_KERNEL, node); else - pages = kmalloc(array_size, (gfp_mask & ~__GFP_HIGHMEM)); + pages = kmalloc_node(array_size, (gfp_mask & ~__GFP_HIGHMEM), node); area->pages = pages; if (!area->pages) { remove_vm_area(area->addr); @@ -418,7 +426,10 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) memset(area->pages, 0, array_size); for (i = 0; i < area->nr_pages; i++) { - area->pages[i] = alloc_page(gfp_mask); + if (node < 0) + area->pages[i] = alloc_page(gfp_mask); + else + area->pages[i] = alloc_pages_node(node, gfp_mask, 0); if (unlikely(!area->pages[i])) { /* Successfully allocated i pages, free them in __vunmap() */ area->nr_pages = i; @@ -435,18 +446,25 @@ fail: return NULL; } +void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) +{ + return __vmalloc_area_node(area, gfp_mask, prot, -1); +} + /** - * __vmalloc - allocate virtually contiguous memory + * __vmalloc_node - allocate virtually contiguous memory * * @size: allocation size * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages + * @node node to use for allocation or -1 * * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. */ -void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) +void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, + int node) { struct vm_struct *area; @@ -454,13 +472,18 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) if (!size || (size >> PAGE_SHIFT) > num_physpages) return NULL; - area = get_vm_area(size, VM_ALLOC); + area = get_vm_area_node(size, VM_ALLOC, node); if (!area) return NULL; - return __vmalloc_area(area, gfp_mask, prot); + return __vmalloc_area_node(area, gfp_mask, prot, node); } +EXPORT_SYMBOL(__vmalloc_node); +void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) +{ + return __vmalloc_node(size, gfp_mask, prot, -1); +} EXPORT_SYMBOL(__vmalloc); /** @@ -478,9 +501,26 @@ void *vmalloc(unsigned long size) { return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL); } - EXPORT_SYMBOL(vmalloc); +/** + * vmalloc_node - allocate memory on a specific node + * + * @size: allocation size + * @node; numa node + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * + * For tight cotrol over page level allocator and protection flags + * use __vmalloc() instead. + */ +void *vmalloc_node(unsigned long size, int node) +{ + return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node); +} +EXPORT_SYMBOL(vmalloc_node); + #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif @@ -515,7 +555,6 @@ void *vmalloc_32(unsigned long size) { return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL); } - EXPORT_SYMBOL(vmalloc_32); long vread(char *buf, char *addr, unsigned long count) diff --git a/mm/vmscan.c b/mm/vmscan.c index 843c87d1e61..135bf8ca96e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -417,7 +417,9 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc) * Anonymous process memory has backing store? * Try to allocate it some swap space here. */ - if (PageAnon(page) && !PageSwapCache(page) && sc->may_swap) { + if (PageAnon(page) && !PageSwapCache(page)) { + if (!sc->may_swap) + goto keep_locked; if (!add_to_swap(page)) goto activate_locked; } @@ -519,7 +521,7 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc) #ifdef CONFIG_SWAP if (PageSwapCache(page)) { - swp_entry_t swap = { .val = page->private }; + swp_entry_t swap = { .val = page_private(page) }; __delete_from_swap_cache(page); write_unlock_irq(&mapping->tree_lock); swap_free(swap); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 67abebabf83..e97b2d162cc 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -2949,8 +2949,7 @@ static struct page * snd_pcm_mmap_status_nopage(struct vm_area_struct *area, uns return NOPAGE_OOM; runtime = substream->runtime; page = virt_to_page(runtime->status); - if (!PageReserved(page)) - get_page(page); + get_page(page); if (type) *type = VM_FAULT_MINOR; return page; @@ -2992,8 +2991,7 @@ static struct page * snd_pcm_mmap_control_nopage(struct vm_area_struct *area, un return NOPAGE_OOM; runtime = substream->runtime; page = virt_to_page(runtime->control); - if (!PageReserved(page)) - get_page(page); + get_page(page); if (type) *type = VM_FAULT_MINOR; return page; @@ -3066,8 +3064,7 @@ static struct page *snd_pcm_mmap_data_nopage(struct vm_area_struct *area, unsign vaddr = runtime->dma_area + offset; page = virt_to_page(vaddr); } - if (!PageReserved(page)) - get_page(page); + get_page(page); if (type) *type = VM_FAULT_MINOR; return page; |