From a1e78772d72b2616ed20e54896e68e0e7044854e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 23 Jul 2008 21:27:23 -0700 Subject: hugetlb: reserve huge pages for reliable MAP_PRIVATE hugetlbfs mappings until fork() This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman Acked-by: Adam Litke Cc: Andy Whitcroft Cc: William Lee Irwin III Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a79e80b689d8..185b14c9f021 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -17,6 +17,7 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) return vma->vm_flags & VM_HUGETLB; } +void reset_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); @@ -30,7 +31,8 @@ int hugetlb_report_node_meminfo(int, char *); unsigned long hugetlb_total_pages(void); int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access); -int hugetlb_reserve_pages(struct inode *inode, long from, long to); +int hugetlb_reserve_pages(struct inode *inode, long from, long to, + struct vm_area_struct *vma); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long max_huge_pages; @@ -58,6 +60,11 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) { return 0; } + +static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) +{ +} + static inline unsigned long hugetlb_total_pages(void) { return 0; -- cgit v1.2.3 From 04f2cbe35699d22dbf428373682ead85ca1240f5 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 23 Jul 2008 21:27:25 -0700 Subject: hugetlb: guarantee that COW faults for a process that called mmap(MAP_PRIVATE) on hugetlbfs will succeed After patch 2 in this series, a process that successfully calls mmap() for a MAP_PRIVATE mapping will be guaranteed to successfully fault until a process calls fork(). At that point, the next write fault from the parent could fail due to COW if the child still has a reference. We only reserve pages for the parent but a copy must be made to avoid leaking data from the parent to the child after fork(). Reserves could be taken for both parent and child at fork time to guarantee faults but if the mapping is large it is highly likely we will not have sufficient pages for the reservation, and it is common to fork only to exec() immediatly after. A failure here would be very undesirable. Note that the current behaviour of mainline with MAP_PRIVATE pages is pretty bad. The following situation is allowed to occur today. 1. Process calls mmap(MAP_PRIVATE) 2. Process calls mlock() to fault all pages and makes sure it succeeds 3. Process forks() 4. Process writes to MAP_PRIVATE mapping while child still exists 5. If the COW fails at this point, the process gets SIGKILLed even though it had taken care to ensure the pages existed This patch improves the situation by guaranteeing the reliability of the process that successfully calls mmap(). When the parent performs COW, it will try to satisfy the allocation without using reserves. If that fails the parent will steal the page leaving any children without a page. Faults from the child after that point will result in failure. If the child COW happens first, an attempt will be made to allocate the page without reserves and the child will get SIGKILLed on failure. To summarise the new behaviour: 1. If the original mapper performs COW on a private mapping with multiple references, it will attempt to allocate a hugepage from the pool or the buddy allocator without using the existing reserves. On fail, VMAs mapping the same area are traversed and the page being COW'd is unmapped where found. It will then steal the original page as the last mapper in the normal way. 2. The VMAs the pages were unmapped from are flagged to note that pages with data no longer exist. Future no-page faults on those VMAs will terminate the process as otherwise it would appear that data was corrupted. A warning is printed to the console that this situation occured. 2. If the child performs COW first, it will attempt to satisfy the COW from the pool if there are enough pages or via the buddy allocator if overcommit is allowed and the buddy allocator can satisfy the request. If it fails, the child will be killed. If the pool is large enough, existing applications will not notice that the reserves were a factor. Existing applications depending on the no-reserves been set are unlikely to exist as for much of the history of hugetlbfs, pages were prefaulted at mmap(), allocating the pages at that point or failing the mmap(). [npiggin@suse.de: fix CONFIG_HUGETLB=n build] Signed-off-by: Mel Gorman Acked-by: Adam Litke Cc: Andy Whitcroft Cc: William Lee Irwin III Cc: Hugh Dickins Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 +- include/linux/hugetlb.h | 8 +- mm/hugetlb.c | 201 +++++++++++++++++++++++++++++++++++++++++++----- mm/memory.c | 2 +- 4 files changed, 190 insertions(+), 23 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 1576bbecd084..428eff5b73f3 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -441,7 +441,7 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff) v_offset = 0; __unmap_hugepage_range(vma, - vma->vm_start + v_offset, vma->vm_end); + vma->vm_start + v_offset, vma->vm_end, NULL); } } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 185b14c9f021..abbc187193a1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -23,8 +23,10 @@ int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __us int hugetlb_treat_movable_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, int); -void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); -void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long); +void unmap_hugepage_range(struct vm_area_struct *, + unsigned long, unsigned long, struct page *); +void __unmap_hugepage_range(struct vm_area_struct *, + unsigned long, unsigned long, struct page *); int hugetlb_prefault(struct address_space *, struct vm_area_struct *); int hugetlb_report_meminfo(char *); int hugetlb_report_node_meminfo(int, char *); @@ -74,7 +76,7 @@ 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 unmap_hugepage_range(vma, start, end) BUG() +#define unmap_hugepage_range(vma, start, end, page) BUG() #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0af500db3632..a2d29b84501f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -40,6 +40,9 @@ static int hugetlb_next_nid; */ static DEFINE_SPINLOCK(hugetlb_lock); +#define HPAGE_RESV_OWNER (1UL << (BITS_PER_LONG - 1)) +#define HPAGE_RESV_UNMAPPED (1UL << (BITS_PER_LONG - 2)) +#define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() @@ -54,17 +57,32 @@ static unsigned long vma_resv_huge_pages(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); if (!(vma->vm_flags & VM_SHARED)) - return (unsigned long)vma->vm_private_data; + return (unsigned long)vma->vm_private_data & ~HPAGE_RESV_MASK; return 0; } static void set_vma_resv_huge_pages(struct vm_area_struct *vma, unsigned long reserve) { + unsigned long flags; VM_BUG_ON(!is_vm_hugetlb_page(vma)); VM_BUG_ON(vma->vm_flags & VM_SHARED); - vma->vm_private_data = (void *)reserve; + flags = (unsigned long)vma->vm_private_data & HPAGE_RESV_MASK; + vma->vm_private_data = (void *)(reserve | flags); +} + +static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) +{ + unsigned long reserveflags = (unsigned long)vma->vm_private_data; + VM_BUG_ON(!is_vm_hugetlb_page(vma)); + vma->vm_private_data = (void *)(reserveflags | flags); +} + +static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) +{ + VM_BUG_ON(!is_vm_hugetlb_page(vma)); + return ((unsigned long)vma->vm_private_data & flag) != 0; } /* Decrement the reserved pages in the hugepage pool by one */ @@ -78,14 +96,18 @@ static void decrement_hugepage_resv_vma(struct vm_area_struct *vma) * Only the process that called mmap() has reserves for * private mappings. */ - if (vma_resv_huge_pages(vma)) { + if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + unsigned long flags, reserve; resv_huge_pages--; + flags = (unsigned long)vma->vm_private_data & + HPAGE_RESV_MASK; reserve = (unsigned long)vma->vm_private_data - 1; - vma->vm_private_data = (void *)reserve; + vma->vm_private_data = (void *)(reserve | flags); } } } +/* Reset counters to 0 and clear all HPAGE_RESV_* flags */ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); @@ -153,7 +175,7 @@ static struct page *dequeue_huge_page(void) } static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, - unsigned long address) + unsigned long address, int avoid_reserve) { int nid; struct page *page = NULL; @@ -173,6 +195,10 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, free_huge_pages - resv_huge_pages == 0) return NULL; + /* If reserves cannot be used, ensure enough pages are in the pool */ + if (avoid_reserve && free_huge_pages - resv_huge_pages == 0) + return NULL; + for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { nid = zone_to_nid(zone); @@ -183,7 +209,9 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, list_del(&page->lru); free_huge_pages--; free_huge_pages_node[nid]--; - decrement_hugepage_resv_vma(vma); + + if (!avoid_reserve) + decrement_hugepage_resv_vma(vma); break; } @@ -534,7 +562,7 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages) } static struct page *alloc_huge_page(struct vm_area_struct *vma, - unsigned long addr) + unsigned long addr, int avoid_reserve) { struct page *page; struct address_space *mapping = vma->vm_file->f_mapping; @@ -546,14 +574,15 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, * will not have accounted against quota. Check that the quota can be * made before satisfying the allocation */ - if (!vma_has_private_reserves(vma)) { + if (!(vma->vm_flags & VM_SHARED) && + !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { chg = 1; if (hugetlb_get_quota(inode->i_mapping, chg)) return ERR_PTR(-ENOSPC); } spin_lock(&hugetlb_lock); - page = dequeue_huge_page_vma(vma, addr); + page = dequeue_huge_page_vma(vma, addr, avoid_reserve); spin_unlock(&hugetlb_lock); if (!page) { @@ -909,7 +938,7 @@ nomem: } void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) + unsigned long end, struct page *ref_page) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -937,6 +966,27 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, if (huge_pmd_unshare(mm, &address, ptep)) continue; + /* + * If a reference page is supplied, it is because a specific + * page is being unmapped, not a range. Ensure the page we + * are about to unmap is the actual page of interest. + */ + if (ref_page) { + pte = huge_ptep_get(ptep); + if (huge_pte_none(pte)) + continue; + page = pte_page(pte); + if (page != ref_page) + continue; + + /* + * Mark the VMA as having unmapped its page so that + * future faults in this VMA will fail rather than + * looking like data was lost + */ + set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); + } + pte = huge_ptep_get_and_clear(mm, address, ptep); if (huge_pte_none(pte)) continue; @@ -955,7 +1005,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) + unsigned long end, struct page *ref_page) { /* * It is undesirable to test vma->vm_file as it should be non-null @@ -967,19 +1017,68 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, */ if (vma->vm_file) { spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); - __unmap_hugepage_range(vma, start, end); + __unmap_hugepage_range(vma, start, end, ref_page); spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); } } +/* + * This is called when the original mapper is failing to COW a MAP_PRIVATE + * mappping it owns the reserve page for. The intention is to unmap the page + * from other VMAs and let the children be SIGKILLed if they are faulting the + * same region. + */ +int unmap_ref_private(struct mm_struct *mm, + struct vm_area_struct *vma, + struct page *page, + unsigned long address) +{ + struct vm_area_struct *iter_vma; + struct address_space *mapping; + struct prio_tree_iter iter; + pgoff_t pgoff; + + /* + * vm_pgoff is in PAGE_SIZE units, hence the different calculation + * from page cache lookup which is in HPAGE_SIZE units. + */ + address = address & huge_page_mask(hstate_vma(vma)); + pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + + (vma->vm_pgoff >> PAGE_SHIFT); + mapping = (struct address_space *)page_private(page); + + vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + /* Do not unmap the current VMA */ + if (iter_vma == vma) + continue; + + /* + * Unmap the page from other VMAs without their own reserves. + * They get marked to be SIGKILLed if they fault in these + * areas. This is because a future no-page fault on this VMA + * could insert a zeroed page instead of the data existing + * from the time of fork. This would look like data corruption + */ + if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) + unmap_hugepage_range(iter_vma, + address, address + HPAGE_SIZE, + page); + } + + return 1; +} + static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, pte_t pte) + unsigned long address, pte_t *ptep, pte_t pte, + struct page *pagecache_page) { struct page *old_page, *new_page; int avoidcopy; + int outside_reserve = 0; old_page = pte_page(pte); +retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ avoidcopy = (page_count(old_page) == 1); @@ -988,11 +1087,43 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } + /* + * If the process that created a MAP_PRIVATE mapping is about to + * perform a COW due to a shared page count, attempt to satisfy + * the allocation without using the existing reserves. The pagecache + * page is used to determine if the reserve at this address was + * consumed or not. If reserves were used, a partial faulted mapping + * at the time of fork() could consume its reserves on COW instead + * of the full address range. + */ + if (!(vma->vm_flags & VM_SHARED) && + is_vma_resv_set(vma, HPAGE_RESV_OWNER) && + old_page != pagecache_page) + outside_reserve = 1; + page_cache_get(old_page); - new_page = alloc_huge_page(vma, address); + new_page = alloc_huge_page(vma, address, outside_reserve); if (IS_ERR(new_page)) { page_cache_release(old_page); + + /* + * If a process owning a MAP_PRIVATE mapping fails to COW, + * it is due to references held by a child and an insufficient + * huge page pool. To guarantee the original mappers + * reliability, unmap the page from child processes. The child + * may get SIGKILLed if it later faults. + */ + if (outside_reserve) { + BUG_ON(huge_pte_none(pte)); + if (unmap_ref_private(mm, vma, old_page, address)) { + BUG_ON(page_count(old_page) != 1); + BUG_ON(huge_pte_none(pte)); + goto retry_avoidcopy; + } + WARN_ON_ONCE(1); + } + return -PTR_ERR(new_page); } @@ -1015,6 +1146,20 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } +/* Return the pagecache page at a given address within a VMA */ +static struct page *hugetlbfs_pagecache_page(struct vm_area_struct *vma, + unsigned long address) +{ + struct address_space *mapping; + unsigned long idx; + + mapping = vma->vm_file->f_mapping; + idx = ((address - vma->vm_start) >> HPAGE_SHIFT) + + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); + + return find_lock_page(mapping, idx); +} + static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, int write_access) { @@ -1025,6 +1170,18 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping; pte_t new_pte; + /* + * Currently, we are forced to kill the process in the event the + * original mapper has unmapped pages from the child due to a failed + * COW. Warn that such a situation has occured as it may not be obvious + */ + if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { + printk(KERN_WARNING + "PID %d killed due to inadequate hugepage pool\n", + current->pid); + return ret; + } + mapping = vma->vm_file->f_mapping; idx = ((address - vma->vm_start) >> HPAGE_SHIFT) + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); @@ -1039,7 +1196,7 @@ retry: size = i_size_read(mapping->host) >> HPAGE_SHIFT; if (idx >= size) goto out; - page = alloc_huge_page(vma, address); + page = alloc_huge_page(vma, address, 0); if (IS_ERR(page)) { ret = -PTR_ERR(page); goto out; @@ -1081,7 +1238,7 @@ retry: if (write_access && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_cow(mm, vma, address, ptep, new_pte); + ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page); } spin_unlock(&mm->page_table_lock); @@ -1126,8 +1283,15 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, spin_lock(&mm->page_table_lock); /* Check for a racing update before calling hugetlb_cow */ if (likely(pte_same(entry, huge_ptep_get(ptep)))) - if (write_access && !pte_write(entry)) - ret = hugetlb_cow(mm, vma, address, ptep, entry); + if (write_access && !pte_write(entry)) { + struct page *page; + page = hugetlbfs_pagecache_page(vma, address); + ret = hugetlb_cow(mm, vma, address, ptep, entry, page); + if (page) { + unlock_page(page); + put_page(page); + } + } spin_unlock(&mm->page_table_lock); mutex_unlock(&hugetlb_instantiation_mutex); @@ -1371,6 +1535,7 @@ int hugetlb_reserve_pages(struct inode *inode, else { chg = to - from; set_vma_resv_huge_pages(vma, chg); + set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) diff --git a/mm/memory.c b/mm/memory.c index 82f3f1c5cf17..72932489a082 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -901,7 +901,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, } if (unlikely(is_vm_hugetlb_page(vma))) { - unmap_hugepage_range(vma, start, end); + unmap_hugepage_range(vma, start, end, NULL); zap_work -= (end - start) / (HPAGE_SIZE / PAGE_SIZE); start = end; -- cgit v1.2.3 From a5516438959d90b071ff0a484ce4f3f523dc3152 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:41 -0700 Subject: hugetlb: modular state for hugetlb page size The goal of this patchset is to support multiple hugetlb page sizes. This is achieved by introducing a new struct hstate structure, which encapsulates the important hugetlb state and constants (eg. huge page size, number of huge pages currently allocated, etc). The hstate structure is then passed around the code which requires these fields, they will do the right thing regardless of the exact hstate they are operating on. This patch adds the hstate structure, with a single global instance of it (default_hstate), and does the basic work of converting hugetlb to use the hstate. Future patches will add more hstate structures to allow for different hugetlbfs mounts to have different page sizes. [akpm@linux-foundation.org: coding-style fixes] Acked-by: Adam Litke Acked-by: Nishanth Aravamudan Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/hugetlbpage.c | 7 +- arch/powerpc/mm/hugetlbpage.c | 3 +- arch/s390/mm/hugetlbpage.c | 3 +- arch/sh/mm/hugetlbpage.c | 3 +- arch/sparc64/mm/hugetlbpage.c | 5 +- arch/x86/mm/hugetlbpage.c | 5 +- fs/hugetlbfs/inode.c | 52 +++--- include/asm-ia64/hugetlb.h | 3 +- include/asm-powerpc/hugetlb.h | 3 +- include/asm-s390/hugetlb.h | 3 +- include/asm-sh/hugetlb.h | 3 +- include/asm-sparc/hugetlb.h | 3 +- include/asm-x86/hugetlb.h | 8 +- include/linux/hugetlb.h | 88 +++++++++- ipc/shm.c | 3 +- mm/hugetlb.c | 368 +++++++++++++++++++++++------------------- mm/memory.c | 2 +- mm/mempolicy.c | 9 +- mm/mmap.c | 3 +- 19 files changed, 356 insertions(+), 218 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index cd49e2860eef..6170f097d255 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -24,7 +24,7 @@ unsigned int hpage_shift=HPAGE_SHIFT_DEFAULT; pte_t * -huge_pte_alloc (struct mm_struct *mm, unsigned long addr) +huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { unsigned long taddr = htlbpage_to_page(addr); pgd_t *pgd; @@ -75,7 +75,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) * Don't actually need to do any preparation, but need to make sure * the address is in the right region. */ -int prepare_hugepage_range(unsigned long addr, unsigned long len) +int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; @@ -149,7 +150,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, u /* Handle MAP_FIXED */ if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 1a96cc891cf5..c94dc71af989 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -128,7 +128,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) return NULL; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pg; pud_t *pu; diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index f4b6124fdb75..9162dc84f77f 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -72,7 +72,8 @@ void arch_release_hugepage(struct page *page) page[1].index = 0; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgdp; pud_t *pudp; diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index ae8c321d6e2a..2f9dbe0ef4ac 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -22,7 +22,8 @@ #include #include -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; diff --git a/arch/sparc64/mm/hugetlbpage.c b/arch/sparc64/mm/hugetlbpage.c index ebefd2a14375..1307b23f6a76 100644 --- a/arch/sparc64/mm/hugetlbpage.c +++ b/arch/sparc64/mm/hugetlbpage.c @@ -175,7 +175,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } @@ -195,7 +195,8 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, pgoff, flags); } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 0b3d567e686d..52476fde8996 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 1; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; @@ -368,7 +369,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 428eff5b73f3..516c581b5371 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -80,6 +80,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) struct inode *inode = file->f_path.dentry->d_inode; loff_t len, vma_len; int ret; + struct hstate *h = hstate_file(file); /* * vma address alignment (but not the pgoff alignment) has @@ -92,7 +93,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags |= VM_HUGETLB | VM_RESERVED; vma->vm_ops = &hugetlb_vm_ops; - if (vma->vm_pgoff & ~(HPAGE_MASK >> PAGE_SHIFT)) + if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; vma_len = (loff_t)(vma->vm_end - vma->vm_start); @@ -104,8 +105,8 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); if (hugetlb_reserve_pages(inode, - vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT), - len >> HPAGE_SHIFT, vma)) + vma->vm_pgoff >> huge_page_order(h), + len >> huge_page_shift(h), vma)) goto out; ret = 0; @@ -130,20 +131,21 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; + struct hstate *h = hstate_file(file); - if (len & ~HPAGE_MASK) + if (len & ~huge_page_mask(h)) return -EINVAL; if (len > TASK_SIZE) return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } if (addr) { - addr = ALIGN(addr, HPAGE_SIZE); + addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && (!vma || addr + len <= vma->vm_start)) @@ -156,7 +158,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, start_addr = TASK_UNMAPPED_BASE; full_search: - addr = ALIGN(start_addr, HPAGE_SIZE); + addr = ALIGN(start_addr, huge_page_size(h)); for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { /* At this point: (!vma || addr < vma->vm_end). */ @@ -174,7 +176,7 @@ full_search: if (!vma || addr + len <= vma->vm_start) return addr; - addr = ALIGN(vma->vm_end, HPAGE_SIZE); + addr = ALIGN(vma->vm_end, huge_page_size(h)); } } #endif @@ -225,10 +227,11 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset, static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { + struct hstate *h = hstate_file(filp); struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; - unsigned long index = *ppos >> HPAGE_SHIFT; - unsigned long offset = *ppos & ~HPAGE_MASK; + unsigned long index = *ppos >> huge_page_shift(h); + unsigned long offset = *ppos & ~huge_page_mask(h); unsigned long end_index; loff_t isize; ssize_t retval = 0; @@ -243,17 +246,17 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, if (!isize) goto out; - end_index = (isize - 1) >> HPAGE_SHIFT; + end_index = (isize - 1) >> huge_page_shift(h); for (;;) { struct page *page; - int nr, ret; + unsigned long nr, ret; /* nr is the maximum number of bytes to copy from this page */ - nr = HPAGE_SIZE; + nr = huge_page_size(h); if (index >= end_index) { if (index > end_index) goto out; - nr = ((isize - 1) & ~HPAGE_MASK) + 1; + nr = ((isize - 1) & ~huge_page_mask(h)) + 1; if (nr <= offset) { goto out; } @@ -287,8 +290,8 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, offset += ret; retval += ret; len -= ret; - index += offset >> HPAGE_SHIFT; - offset &= ~HPAGE_MASK; + index += offset >> huge_page_shift(h); + offset &= ~huge_page_mask(h); if (page) page_cache_release(page); @@ -298,7 +301,7 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf, break; } out: - *ppos = ((loff_t)index << HPAGE_SHIFT) + offset; + *ppos = ((loff_t)index << huge_page_shift(h)) + offset; mutex_unlock(&inode->i_mutex); return retval; } @@ -339,8 +342,9 @@ static void truncate_huge_page(struct page *page) static void truncate_hugepages(struct inode *inode, loff_t lstart) { + struct hstate *h = hstate_inode(inode); struct address_space *mapping = &inode->i_data; - const pgoff_t start = lstart >> HPAGE_SHIFT; + const pgoff_t start = lstart >> huge_page_shift(h); struct pagevec pvec; pgoff_t next; int i, freed = 0; @@ -449,8 +453,9 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) { pgoff_t pgoff; struct address_space *mapping = inode->i_mapping; + struct hstate *h = hstate_inode(inode); - BUG_ON(offset & ~HPAGE_MASK); + BUG_ON(offset & ~huge_page_mask(h)); pgoff = offset >> PAGE_SHIFT; i_size_write(inode, offset); @@ -465,6 +470,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; + struct hstate *h = hstate_inode(inode); int error; unsigned int ia_valid = attr->ia_valid; @@ -476,7 +482,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) if (ia_valid & ATTR_SIZE) { error = -EINVAL; - if (!(attr->ia_size & ~HPAGE_MASK)) + if (!(attr->ia_size & ~huge_page_mask(h))) error = hugetlb_vmtruncate(inode, attr->ia_size); if (error) goto out; @@ -610,9 +616,10 @@ static int hugetlbfs_set_page_dirty(struct page *page) static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); + struct hstate *h = hstate_inode(dentry->d_inode); buf->f_type = HUGETLBFS_MAGIC; - buf->f_bsize = HPAGE_SIZE; + buf->f_bsize = huge_page_size(h); if (sbinfo) { spin_lock(&sbinfo->stat_lock); /* If no limits set, just report 0 for max/free/used @@ -942,7 +949,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size) goto out_dentry; error = -ENOMEM; - if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT, NULL)) + if (hugetlb_reserve_pages(inode, 0, + size >> huge_page_shift(hstate_inode(inode)), NULL)) goto out_inode; d_instantiate(dentry, inode); diff --git a/include/asm-ia64/hugetlb.h b/include/asm-ia64/hugetlb.h index e9d1e5e2382d..da55c63728e0 100644 --- a/include/asm-ia64/hugetlb.h +++ b/include/asm-ia64/hugetlb.h @@ -8,7 +8,8 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -int prepare_hugepage_range(unsigned long addr, unsigned long len); +int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len); static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/include/asm-powerpc/hugetlb.h b/include/asm-powerpc/hugetlb.h index 0a37aa5ecaa5..ca37c4af27b1 100644 --- a/include/asm-powerpc/hugetlb.h +++ b/include/asm-powerpc/hugetlb.h @@ -21,7 +21,8 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; diff --git a/include/asm-s390/hugetlb.h b/include/asm-s390/hugetlb.h index 600a776f8f75..670a1d1745d2 100644 --- a/include/asm-s390/hugetlb.h +++ b/include/asm-s390/hugetlb.h @@ -22,7 +22,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; diff --git a/include/asm-sh/hugetlb.h b/include/asm-sh/hugetlb.h index fb30018938c7..967068fb79ac 100644 --- a/include/asm-sh/hugetlb.h +++ b/include/asm-sh/hugetlb.h @@ -14,7 +14,8 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; diff --git a/include/asm-sparc/hugetlb.h b/include/asm-sparc/hugetlb.h index aeb92374ca3d..177061064ee6 100644 --- a/include/asm-sparc/hugetlb.h +++ b/include/asm-sparc/hugetlb.h @@ -22,7 +22,8 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { if (len & ~HPAGE_MASK) return -EINVAL; diff --git a/include/asm-x86/hugetlb.h b/include/asm-x86/hugetlb.h index 7eed6e0883bf..439a9acc132d 100644 --- a/include/asm-x86/hugetlb.h +++ b/include/asm-x86/hugetlb.h @@ -14,11 +14,13 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ -static inline int prepare_hugepage_range(unsigned long addr, unsigned long len) +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) { - if (len & ~HPAGE_MASK) + struct hstate *h = hstate_file(file); + if (len & ~huge_page_mask(h)) return -EINVAL; - if (addr & ~HPAGE_MASK) + if (addr & ~huge_page_mask(h)) return -EINVAL; return 0; } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index abbc187193a1..ad2271e11f9b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -8,7 +8,6 @@ #include #include #include -#include struct ctl_table; @@ -45,7 +44,8 @@ extern int sysctl_hugetlb_shm_group; /* arch callbacks */ -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr); +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, @@ -80,7 +80,7 @@ static inline unsigned long hugetlb_total_pages(void) #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL -#define prepare_hugepage_range(addr,len) (-EINVAL) +#define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) @@ -134,8 +134,6 @@ struct file *hugetlb_file_setup(const char *name, size_t); int hugetlb_get_quota(struct address_space *mapping, long delta); void hugetlb_put_quota(struct address_space *mapping, long delta); -#define BLOCKS_PER_HUGEPAGE (HPAGE_SIZE / 512) - static inline int is_file_hugepages(struct file *file) { if (file->f_op == &hugetlbfs_file_operations) @@ -164,4 +162,84 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +#ifdef CONFIG_HUGETLB_PAGE + +/* Defines one hugetlb page size */ +struct hstate { + int hugetlb_next_nid; + unsigned int order; + unsigned long mask; + unsigned long max_huge_pages; + unsigned long nr_huge_pages; + unsigned long free_huge_pages; + unsigned long resv_huge_pages; + unsigned long surplus_huge_pages; + unsigned long nr_overcommit_huge_pages; + struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int nr_huge_pages_node[MAX_NUMNODES]; + unsigned int free_huge_pages_node[MAX_NUMNODES]; + unsigned int surplus_huge_pages_node[MAX_NUMNODES]; +}; + +extern struct hstate default_hstate; + +static inline struct hstate *hstate_vma(struct vm_area_struct *vma) +{ + return &default_hstate; +} + +static inline struct hstate *hstate_file(struct file *f) +{ + return &default_hstate; +} + +static inline struct hstate *hstate_inode(struct inode *i) +{ + return &default_hstate; +} + +static inline unsigned long huge_page_size(struct hstate *h) +{ + return (unsigned long)PAGE_SIZE << h->order; +} + +static inline unsigned long huge_page_mask(struct hstate *h) +{ + return h->mask; +} + +static inline unsigned int huge_page_order(struct hstate *h) +{ + return h->order; +} + +static inline unsigned huge_page_shift(struct hstate *h) +{ + return h->order + PAGE_SHIFT; +} + +static inline unsigned int pages_per_huge_page(struct hstate *h) +{ + return 1 << h->order; +} + +static inline unsigned int blocks_per_huge_page(struct hstate *h) +{ + return huge_page_size(h) / 512; +} + +#include + +#else +struct hstate {}; +#define hstate_file(f) NULL +#define hstate_vma(v) NULL +#define hstate_inode(i) NULL +#define huge_page_size(h) PAGE_SIZE +#define huge_page_mask(h) PAGE_MASK +#define huge_page_order(h) 0 +#define huge_page_shift(h) PAGE_SHIFT +#define pages_per_huge_page(h) 1 +#endif + #endif /* _LINUX_HUGETLB_H */ diff --git a/ipc/shm.c b/ipc/shm.c index 790240cd067f..a726aebce7d7 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -577,7 +577,8 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, if (is_file_hugepages(shp->shm_file)) { struct address_space *mapping = inode->i_mapping; - *rss += (HPAGE_SIZE/PAGE_SIZE)*mapping->nrpages; + struct hstate *h = hstate_file(shp->shm_file); + *rss += pages_per_huge_page(h) * mapping->nrpages; } else { struct shmem_inode_info *info = SHMEM_I(inode); spin_lock(&info->lock); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 32dff4290c66..0d8153e25f09 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -22,18 +22,12 @@ #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; -static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages; -static unsigned long surplus_huge_pages; -static unsigned long nr_overcommit_huge_pages; unsigned long max_huge_pages; unsigned long sysctl_overcommit_huge_pages; -static struct list_head hugepage_freelists[MAX_NUMNODES]; -static unsigned int nr_huge_pages_node[MAX_NUMNODES]; -static unsigned int free_huge_pages_node[MAX_NUMNODES]; -static unsigned int surplus_huge_pages_node[MAX_NUMNODES]; static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; -static int hugetlb_next_nid; + +struct hstate default_hstate; /* * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages @@ -203,11 +197,11 @@ static long region_count(struct list_head *head, long f, long t) * Convert the address within this vma to the page offset within * the mapping, in pagecache page units; huge pages here. */ -static pgoff_t vma_hugecache_offset(struct vm_area_struct *vma, - unsigned long address) +static pgoff_t vma_hugecache_offset(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { - return ((address - vma->vm_start) >> HPAGE_SHIFT) + - (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); + return ((address - vma->vm_start) >> huge_page_shift(h)) + + (vma->vm_pgoff >> huge_page_order(h)); } /* @@ -309,20 +303,21 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) } /* Decrement the reserved pages in the hugepage pool by one */ -static void decrement_hugepage_resv_vma(struct vm_area_struct *vma) +static void decrement_hugepage_resv_vma(struct hstate *h, + struct vm_area_struct *vma) { if (vma->vm_flags & VM_NORESERVE) return; if (vma->vm_flags & VM_SHARED) { /* Shared mappings always use reserves */ - resv_huge_pages--; + h->resv_huge_pages--; } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Only the process that called mmap() has reserves for * private mappings. */ - resv_huge_pages--; + h->resv_huge_pages--; } } @@ -344,12 +339,13 @@ static int vma_has_private_reserves(struct vm_area_struct *vma) return 1; } -static void clear_huge_page(struct page *page, unsigned long addr) +static void clear_huge_page(struct page *page, + unsigned long addr, unsigned long sz) { int i; might_sleep(); - for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) { + for (i = 0; i < sz/PAGE_SIZE; i++) { cond_resched(); clear_user_highpage(page + i, addr + i * PAGE_SIZE); } @@ -359,41 +355,43 @@ static void copy_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma) { int i; + struct hstate *h = hstate_vma(vma); might_sleep(); - for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) { + for (i = 0; i < pages_per_huge_page(h); i++) { cond_resched(); copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); } } -static void enqueue_huge_page(struct page *page) +static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); - list_add(&page->lru, &hugepage_freelists[nid]); - free_huge_pages++; - free_huge_pages_node[nid]++; + list_add(&page->lru, &h->hugepage_freelists[nid]); + h->free_huge_pages++; + h->free_huge_pages_node[nid]++; } -static struct page *dequeue_huge_page(void) +static struct page *dequeue_huge_page(struct hstate *h) { int nid; struct page *page = NULL; for (nid = 0; nid < MAX_NUMNODES; ++nid) { - if (!list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, + if (!list_empty(&h->hugepage_freelists[nid])) { + page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_del(&page->lru); - free_huge_pages--; - free_huge_pages_node[nid]--; + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; break; } } return page; } -static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, +static struct page *dequeue_huge_page_vma(struct hstate *h, + struct vm_area_struct *vma, unsigned long address, int avoid_reserve) { int nid; @@ -411,26 +409,26 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, * not "stolen". The child may still get SIGKILLed */ if (!vma_has_private_reserves(vma) && - free_huge_pages - resv_huge_pages == 0) + h->free_huge_pages - h->resv_huge_pages == 0) return NULL; /* If reserves cannot be used, ensure enough pages are in the pool */ - if (avoid_reserve && free_huge_pages - resv_huge_pages == 0) + if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) return NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, MAX_NR_ZONES - 1, nodemask) { nid = zone_to_nid(zone); if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) && - !list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, + !list_empty(&h->hugepage_freelists[nid])) { + page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_del(&page->lru); - free_huge_pages--; - free_huge_pages_node[nid]--; + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; if (!avoid_reserve) - decrement_hugepage_resv_vma(vma); + decrement_hugepage_resv_vma(h, vma); break; } @@ -439,12 +437,13 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma, return page; } -static void update_and_free_page(struct page *page) +static void update_and_free_page(struct hstate *h, struct page *page) { int i; - nr_huge_pages--; - nr_huge_pages_node[page_to_nid(page)]--; - for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) { + + h->nr_huge_pages--; + h->nr_huge_pages_node[page_to_nid(page)]--; + for (i = 0; i < pages_per_huge_page(h); i++) { page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_reserved | 1 << PG_private | 1<< PG_writeback); @@ -452,11 +451,16 @@ static void update_and_free_page(struct page *page) set_compound_page_dtor(page, NULL); set_page_refcounted(page); arch_release_hugepage(page); - __free_pages(page, HUGETLB_PAGE_ORDER); + __free_pages(page, huge_page_order(h)); } static void free_huge_page(struct page *page) { + /* + * Can't pass hstate in here because it is called from the + * compound page destructor. + */ + struct hstate *h = &default_hstate; int nid = page_to_nid(page); struct address_space *mapping; @@ -466,12 +470,12 @@ static void free_huge_page(struct page *page) INIT_LIST_HEAD(&page->lru); spin_lock(&hugetlb_lock); - if (surplus_huge_pages_node[nid]) { - update_and_free_page(page); - surplus_huge_pages--; - surplus_huge_pages_node[nid]--; + if (h->surplus_huge_pages_node[nid]) { + update_and_free_page(h, page); + h->surplus_huge_pages--; + h->surplus_huge_pages_node[nid]--; } else { - enqueue_huge_page(page); + enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); if (mapping) @@ -483,7 +487,7 @@ static void free_huge_page(struct page *page) * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ -static int adjust_pool_surplus(int delta) +static int adjust_pool_surplus(struct hstate *h, int delta) { static int prev_nid; int nid = prev_nid; @@ -496,15 +500,15 @@ static int adjust_pool_surplus(int delta) nid = first_node(node_online_map); /* To shrink on this node, there must be a surplus page */ - if (delta < 0 && !surplus_huge_pages_node[nid]) + if (delta < 0 && !h->surplus_huge_pages_node[nid]) continue; /* Surplus cannot exceed the total number of pages */ - if (delta > 0 && surplus_huge_pages_node[nid] >= - nr_huge_pages_node[nid]) + if (delta > 0 && h->surplus_huge_pages_node[nid] >= + h->nr_huge_pages_node[nid]) continue; - surplus_huge_pages += delta; - surplus_huge_pages_node[nid] += delta; + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[nid] += delta; ret = 1; break; } while (nid != prev_nid); @@ -513,46 +517,46 @@ static int adjust_pool_surplus(int delta) return ret; } -static void prep_new_huge_page(struct page *page, int nid) +static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { set_compound_page_dtor(page, free_huge_page); spin_lock(&hugetlb_lock); - nr_huge_pages++; - nr_huge_pages_node[nid]++; + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; spin_unlock(&hugetlb_lock); put_page(page); /* free it into the hugepage allocator */ } -static struct page *alloc_fresh_huge_page_node(int nid) +static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; page = alloc_pages_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, - HUGETLB_PAGE_ORDER); + huge_page_order(h)); if (page) { if (arch_prepare_hugepage(page)) { __free_pages(page, HUGETLB_PAGE_ORDER); return NULL; } - prep_new_huge_page(page, nid); + prep_new_huge_page(h, page, nid); } return page; } -static int alloc_fresh_huge_page(void) +static int alloc_fresh_huge_page(struct hstate *h) { struct page *page; int start_nid; int next_nid; int ret = 0; - start_nid = hugetlb_next_nid; + start_nid = h->hugetlb_next_nid; do { - page = alloc_fresh_huge_page_node(hugetlb_next_nid); + page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid); if (page) ret = 1; /* @@ -566,11 +570,11 @@ static int alloc_fresh_huge_page(void) * if we just successfully allocated a hugepage so that * the next caller gets hugepages on the next node. */ - next_nid = next_node(hugetlb_next_nid, node_online_map); + next_nid = next_node(h->hugetlb_next_nid, node_online_map); if (next_nid == MAX_NUMNODES) next_nid = first_node(node_online_map); - hugetlb_next_nid = next_nid; - } while (!page && hugetlb_next_nid != start_nid); + h->hugetlb_next_nid = next_nid; + } while (!page && h->hugetlb_next_nid != start_nid); if (ret) count_vm_event(HTLB_BUDDY_PGALLOC); @@ -580,8 +584,8 @@ static int alloc_fresh_huge_page(void) return ret; } -static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, - unsigned long address) +static struct page *alloc_buddy_huge_page(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { struct page *page; unsigned int nid; @@ -610,18 +614,18 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, * per-node value is checked there. */ spin_lock(&hugetlb_lock); - if (surplus_huge_pages >= nr_overcommit_huge_pages) { + if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { spin_unlock(&hugetlb_lock); return NULL; } else { - nr_huge_pages++; - surplus_huge_pages++; + h->nr_huge_pages++; + h->surplus_huge_pages++; } spin_unlock(&hugetlb_lock); page = alloc_pages(htlb_alloc_mask|__GFP_COMP| __GFP_REPEAT|__GFP_NOWARN, - HUGETLB_PAGE_ORDER); + huge_page_order(h)); spin_lock(&hugetlb_lock); if (page) { @@ -636,12 +640,12 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, /* * We incremented the global counters already */ - nr_huge_pages_node[nid]++; - surplus_huge_pages_node[nid]++; + h->nr_huge_pages_node[nid]++; + h->surplus_huge_pages_node[nid]++; __count_vm_event(HTLB_BUDDY_PGALLOC); } else { - nr_huge_pages--; - surplus_huge_pages--; + h->nr_huge_pages--; + h->surplus_huge_pages--; __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); } spin_unlock(&hugetlb_lock); @@ -653,16 +657,16 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma, * Increase the hugetlb pool such that it can accomodate a reservation * of size 'delta'. */ -static int gather_surplus_pages(int delta) +static int gather_surplus_pages(struct hstate *h, int delta) { struct list_head surplus_list; struct page *page, *tmp; int ret, i; int needed, allocated; - needed = (resv_huge_pages + delta) - free_huge_pages; + needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { - resv_huge_pages += delta; + h->resv_huge_pages += delta; return 0; } @@ -673,7 +677,7 @@ static int gather_surplus_pages(int delta) retry: spin_unlock(&hugetlb_lock); for (i = 0; i < needed; i++) { - page = alloc_buddy_huge_page(NULL, 0); + page = alloc_buddy_huge_page(h, NULL, 0); if (!page) { /* * We were not able to allocate enough pages to @@ -694,7 +698,8 @@ retry: * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock(&hugetlb_lock); - needed = (resv_huge_pages + delta) - (free_huge_pages + allocated); + needed = (h->resv_huge_pages + delta) - + (h->free_huge_pages + allocated); if (needed > 0) goto retry; @@ -707,7 +712,7 @@ retry: * before they are reserved. */ needed += allocated; - resv_huge_pages += delta; + h->resv_huge_pages += delta; ret = 0; free: /* Free the needed pages to the hugetlb pool */ @@ -715,7 +720,7 @@ free: if ((--needed) < 0) break; list_del(&page->lru); - enqueue_huge_page(page); + enqueue_huge_page(h, page); } /* Free unnecessary surplus pages to the buddy allocator */ @@ -743,7 +748,8 @@ free: * allocated to satisfy the reservation must be explicitly freed if they were * never used. */ -static void return_unused_surplus_pages(unsigned long unused_resv_pages) +static void return_unused_surplus_pages(struct hstate *h, + unsigned long unused_resv_pages) { static int nid = -1; struct page *page; @@ -758,27 +764,27 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages) unsigned long remaining_iterations = num_online_nodes(); /* Uncommit the reservation */ - resv_huge_pages -= unused_resv_pages; + h->resv_huge_pages -= unused_resv_pages; - nr_pages = min(unused_resv_pages, surplus_huge_pages); + nr_pages = min(unused_resv_pages, h->surplus_huge_pages); while (remaining_iterations-- && nr_pages) { nid = next_node(nid, node_online_map); if (nid == MAX_NUMNODES) nid = first_node(node_online_map); - if (!surplus_huge_pages_node[nid]) + if (!h->surplus_huge_pages_node[nid]) continue; - if (!list_empty(&hugepage_freelists[nid])) { - page = list_entry(hugepage_freelists[nid].next, + if (!list_empty(&h->hugepage_freelists[nid])) { + page = list_entry(h->hugepage_freelists[nid].next, struct page, lru); list_del(&page->lru); - update_and_free_page(page); - free_huge_pages--; - free_huge_pages_node[nid]--; - surplus_huge_pages--; - surplus_huge_pages_node[nid]--; + update_and_free_page(h, page); + h->free_huge_pages--; + h->free_huge_pages_node[nid]--; + h->surplus_huge_pages--; + h->surplus_huge_pages_node[nid]--; nr_pages--; remaining_iterations = num_online_nodes(); } @@ -794,13 +800,14 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages) * an instantiated the change should be committed via vma_commit_reservation. * No action is required on failure. */ -static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr) +static int vma_needs_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; if (vma->vm_flags & VM_SHARED) { - pgoff_t idx = vma_hugecache_offset(vma, addr); + pgoff_t idx = vma_hugecache_offset(h, vma, addr); return region_chg(&inode->i_mapping->private_list, idx, idx + 1); @@ -809,7 +816,7 @@ static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr) } else { int err; - pgoff_t idx = vma_hugecache_offset(vma, addr); + pgoff_t idx = vma_hugecache_offset(h, vma, addr); struct resv_map *reservations = vma_resv_map(vma); err = region_chg(&reservations->regions, idx, idx + 1); @@ -818,18 +825,18 @@ static int vma_needs_reservation(struct vm_area_struct *vma, unsigned long addr) return 0; } } -static void vma_commit_reservation(struct vm_area_struct *vma, - unsigned long addr) +static void vma_commit_reservation(struct hstate *h, + struct vm_area_struct *vma, unsigned long addr) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; if (vma->vm_flags & VM_SHARED) { - pgoff_t idx = vma_hugecache_offset(vma, addr); + pgoff_t idx = vma_hugecache_offset(h, vma, addr); region_add(&inode->i_mapping->private_list, idx, idx + 1); } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { - pgoff_t idx = vma_hugecache_offset(vma, addr); + pgoff_t idx = vma_hugecache_offset(h, vma, addr); struct resv_map *reservations = vma_resv_map(vma); /* Mark this page used in the map. */ @@ -840,6 +847,7 @@ static void vma_commit_reservation(struct vm_area_struct *vma, static struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { + struct hstate *h = hstate_vma(vma); struct page *page; struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; @@ -852,7 +860,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, * MAP_NORESERVE mappings may also need pages and quota allocated * if no reserve mapping overlaps. */ - chg = vma_needs_reservation(vma, addr); + chg = vma_needs_reservation(h, vma, addr); if (chg < 0) return ERR_PTR(chg); if (chg) @@ -860,11 +868,11 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return ERR_PTR(-ENOSPC); spin_lock(&hugetlb_lock); - page = dequeue_huge_page_vma(vma, addr, avoid_reserve); + page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve); spin_unlock(&hugetlb_lock); if (!page) { - page = alloc_buddy_huge_page(vma, addr); + page = alloc_buddy_huge_page(h, vma, addr); if (!page) { hugetlb_put_quota(inode->i_mapping, chg); return ERR_PTR(-VM_FAULT_OOM); @@ -874,7 +882,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, set_page_refcounted(page); set_page_private(page, (unsigned long) mapping); - vma_commit_reservation(vma, addr); + vma_commit_reservation(h, vma, addr); return page; } @@ -882,21 +890,28 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, static int __init hugetlb_init(void) { unsigned long i; + struct hstate *h = &default_hstate; if (HPAGE_SHIFT == 0) return 0; + if (!h->order) { + h->order = HPAGE_SHIFT - PAGE_SHIFT; + h->mask = HPAGE_MASK; + } + for (i = 0; i < MAX_NUMNODES; ++i) - INIT_LIST_HEAD(&hugepage_freelists[i]); + INIT_LIST_HEAD(&h->hugepage_freelists[i]); - hugetlb_next_nid = first_node(node_online_map); + h->hugetlb_next_nid = first_node(node_online_map); for (i = 0; i < max_huge_pages; ++i) { - if (!alloc_fresh_huge_page()) + if (!alloc_fresh_huge_page(h)) break; } - max_huge_pages = free_huge_pages = nr_huge_pages = i; - printk("Total HugeTLB memory allocated, %ld\n", free_huge_pages); + max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i; + printk(KERN_INFO "Total HugeTLB memory allocated, %ld\n", + h->free_huge_pages); return 0; } module_init(hugetlb_init); @@ -922,34 +937,36 @@ static unsigned int cpuset_mems_nr(unsigned int *array) #ifdef CONFIG_SYSCTL #ifdef CONFIG_HIGHMEM -static void try_to_free_low(unsigned long count) +static void try_to_free_low(struct hstate *h, unsigned long count) { int i; for (i = 0; i < MAX_NUMNODES; ++i) { struct page *page, *next; - list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) { - if (count >= nr_huge_pages) + struct list_head *freel = &h->hugepage_freelists[i]; + list_for_each_entry_safe(page, next, freel, lru) { + if (count >= h->nr_huge_pages) return; if (PageHighMem(page)) continue; list_del(&page->lru); update_and_free_page(page); - free_huge_pages--; - free_huge_pages_node[page_to_nid(page)]--; + h->free_huge_pages--; + h->free_huge_pages_node[page_to_nid(page)]--; } } } #else -static inline void try_to_free_low(unsigned long count) +static inline void try_to_free_low(struct hstate *h, unsigned long count) { } #endif -#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages) +#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static unsigned long set_max_huge_pages(unsigned long count) { unsigned long min_count, ret; + struct hstate *h = &default_hstate; /* * Increase the pool size @@ -963,19 +980,19 @@ static unsigned long set_max_huge_pages(unsigned long count) * within all the constraints specified by the sysctls. */ spin_lock(&hugetlb_lock); - while (surplus_huge_pages && count > persistent_huge_pages) { - if (!adjust_pool_surplus(-1)) + while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { + if (!adjust_pool_surplus(h, -1)) break; } - while (count > persistent_huge_pages) { + while (count > persistent_huge_pages(h)) { /* * If this allocation races such that we no longer need the * page, free_huge_page will handle it by freeing the page * and reducing the surplus. */ spin_unlock(&hugetlb_lock); - ret = alloc_fresh_huge_page(); + ret = alloc_fresh_huge_page(h); spin_lock(&hugetlb_lock); if (!ret) goto out; @@ -997,21 +1014,21 @@ static unsigned long set_max_huge_pages(unsigned long count) * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. */ - min_count = resv_huge_pages + nr_huge_pages - free_huge_pages; + min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); - try_to_free_low(min_count); - while (min_count < persistent_huge_pages) { - struct page *page = dequeue_huge_page(); + try_to_free_low(h, min_count); + while (min_count < persistent_huge_pages(h)) { + struct page *page = dequeue_huge_page(h); if (!page) break; - update_and_free_page(page); + update_and_free_page(h, page); } - while (count < persistent_huge_pages) { - if (!adjust_pool_surplus(1)) + while (count < persistent_huge_pages(h)) { + if (!adjust_pool_surplus(h, 1)) break; } out: - ret = persistent_huge_pages; + ret = persistent_huge_pages(h); spin_unlock(&hugetlb_lock); return ret; } @@ -1041,9 +1058,10 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { + struct hstate *h = &default_hstate; proc_doulongvec_minmax(table, write, file, buffer, length, ppos); spin_lock(&hugetlb_lock); - nr_overcommit_huge_pages = sysctl_overcommit_huge_pages; + h->nr_overcommit_huge_pages = sysctl_overcommit_huge_pages; spin_unlock(&hugetlb_lock); return 0; } @@ -1052,37 +1070,40 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, int hugetlb_report_meminfo(char *buf) { + struct hstate *h = &default_hstate; return sprintf(buf, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %5lu kB\n", - nr_huge_pages, - free_huge_pages, - resv_huge_pages, - surplus_huge_pages, - HPAGE_SIZE/1024); + h->nr_huge_pages, + h->free_huge_pages, + h->resv_huge_pages, + h->surplus_huge_pages, + 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); } int hugetlb_report_node_meminfo(int nid, char *buf) { + struct hstate *h = &default_hstate; return sprintf(buf, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", - nid, nr_huge_pages_node[nid], - nid, free_huge_pages_node[nid], - nid, surplus_huge_pages_node[nid]); + nid, h->nr_huge_pages_node[nid], + nid, h->free_huge_pages_node[nid], + nid, h->surplus_huge_pages_node[nid]); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { - return nr_huge_pages * (HPAGE_SIZE / PAGE_SIZE); + struct hstate *h = &default_hstate; + return h->nr_huge_pages * pages_per_huge_page(h); } -static int hugetlb_acct_memory(long delta) +static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; @@ -1105,18 +1126,18 @@ static int hugetlb_acct_memory(long delta) * semantics that cpuset has. */ if (delta > 0) { - if (gather_surplus_pages(delta) < 0) + if (gather_surplus_pages(h, delta) < 0) goto out; - if (delta > cpuset_mems_nr(free_huge_pages_node)) { - return_unused_surplus_pages(delta); + if (delta > cpuset_mems_nr(h->free_huge_pages_node)) { + return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) - return_unused_surplus_pages((unsigned long) -delta); + return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock(&hugetlb_lock); @@ -1141,14 +1162,15 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) static void hugetlb_vm_op_close(struct vm_area_struct *vma) { + struct hstate *h = hstate_vma(vma); struct resv_map *reservations = vma_resv_map(vma); unsigned long reserve; unsigned long start; unsigned long end; if (reservations) { - start = vma_hugecache_offset(vma, vma->vm_start); - end = vma_hugecache_offset(vma, vma->vm_end); + start = vma_hugecache_offset(h, vma, vma->vm_start); + end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(&reservations->regions, start, end); @@ -1156,7 +1178,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) kref_put(&reservations->refs, resv_map_release); if (reserve) - hugetlb_acct_memory(-reserve); + hugetlb_acct_memory(h, -reserve); } } @@ -1214,14 +1236,16 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct page *ptepage; unsigned long addr; int cow; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; - for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) { + for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { src_pte = huge_pte_offset(src, addr); if (!src_pte) continue; - dst_pte = huge_pte_alloc(dst, addr); + dst_pte = huge_pte_alloc(dst, addr, sz); if (!dst_pte) goto nomem; @@ -1257,6 +1281,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, pte_t pte; struct page *page; struct page *tmp; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); + /* * A page gathering list, protected by per file i_mmap_lock. The * lock is used to avoid list corruption from multiple unmapping @@ -1265,11 +1292,11 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, LIST_HEAD(page_list); WARN_ON(!is_vm_hugetlb_page(vma)); - BUG_ON(start & ~HPAGE_MASK); - BUG_ON(end & ~HPAGE_MASK); + BUG_ON(start & ~huge_page_mask(h)); + BUG_ON(end & ~huge_page_mask(h)); spin_lock(&mm->page_table_lock); - for (address = start; address < end; address += HPAGE_SIZE) { + for (address = start; address < end; address += sz) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; @@ -1383,6 +1410,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t pte, struct page *pagecache_page) { + struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; int avoidcopy; int outside_reserve = 0; @@ -1443,7 +1471,7 @@ retry_avoidcopy: __SetPageUptodate(new_page); spin_lock(&mm->page_table_lock); - ptep = huge_pte_offset(mm, address & HPAGE_MASK); + ptep = huge_pte_offset(mm, address & huge_page_mask(h)); if (likely(pte_same(huge_ptep_get(ptep), pte))) { /* Break COW */ huge_ptep_clear_flush(vma, address, ptep); @@ -1458,14 +1486,14 @@ retry_avoidcopy: } /* Return the pagecache page at a given address within a VMA */ -static struct page *hugetlbfs_pagecache_page(struct vm_area_struct *vma, - unsigned long address) +static struct page *hugetlbfs_pagecache_page(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping; pgoff_t idx; mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(vma, address); + idx = vma_hugecache_offset(h, vma, address); return find_lock_page(mapping, idx); } @@ -1473,6 +1501,7 @@ static struct page *hugetlbfs_pagecache_page(struct vm_area_struct *vma, static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, int write_access) { + struct hstate *h = hstate_vma(vma); int ret = VM_FAULT_SIGBUS; pgoff_t idx; unsigned long size; @@ -1493,7 +1522,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, } mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(vma, address); + idx = vma_hugecache_offset(h, vma, address); /* * Use page lock to guard against racing truncation @@ -1502,7 +1531,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, retry: page = find_lock_page(mapping, idx); if (!page) { - size = i_size_read(mapping->host) >> HPAGE_SHIFT; + size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; page = alloc_huge_page(vma, address, 0); @@ -1510,7 +1539,7 @@ retry: ret = -PTR_ERR(page); goto out; } - clear_huge_page(page, address); + clear_huge_page(page, address, huge_page_size(h)); __SetPageUptodate(page); if (vma->vm_flags & VM_SHARED) { @@ -1526,14 +1555,14 @@ retry: } spin_lock(&inode->i_lock); - inode->i_blocks += BLOCKS_PER_HUGEPAGE; + inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); } else lock_page(page); } spin_lock(&mm->page_table_lock); - size = i_size_read(mapping->host) >> HPAGE_SHIFT; + size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto backout; @@ -1569,8 +1598,9 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_t entry; int ret; static DEFINE_MUTEX(hugetlb_instantiation_mutex); + struct hstate *h = hstate_vma(vma); - ptep = huge_pte_alloc(mm, address); + ptep = huge_pte_alloc(mm, address, huge_page_size(h)); if (!ptep) return VM_FAULT_OOM; @@ -1594,7 +1624,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (likely(pte_same(entry, huge_ptep_get(ptep)))) if (write_access && !pte_write(entry)) { struct page *page; - page = hugetlbfs_pagecache_page(vma, address); + page = hugetlbfs_pagecache_page(h, vma, address); ret = hugetlb_cow(mm, vma, address, ptep, entry, page); if (page) { unlock_page(page); @@ -1615,6 +1645,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long pfn_offset; unsigned long vaddr = *position; int remainder = *length; + struct hstate *h = hstate_vma(vma); spin_lock(&mm->page_table_lock); while (vaddr < vma->vm_end && remainder) { @@ -1626,7 +1657,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * 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); + pte = huge_pte_offset(mm, vaddr & huge_page_mask(h)); if (!pte || huge_pte_none(huge_ptep_get(pte)) || (write && !pte_write(huge_ptep_get(pte)))) { @@ -1644,7 +1675,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } - pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT; + pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); same_page: if (pages) { @@ -1660,7 +1691,7 @@ same_page: --remainder; ++i; if (vaddr < vma->vm_end && remainder && - pfn_offset < HPAGE_SIZE/PAGE_SIZE) { + pfn_offset < pages_per_huge_page(h)) { /* * We use pfn_offset to avoid touching the pageframes * of this compound page. @@ -1682,13 +1713,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long start = address; pte_t *ptep; pte_t pte; + struct hstate *h = hstate_vma(vma); BUG_ON(address >= end); flush_cache_range(vma, address, end); spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); spin_lock(&mm->page_table_lock); - for (; address < end; address += HPAGE_SIZE) { + for (; address < end; address += huge_page_size(h)) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; @@ -1711,6 +1743,7 @@ int hugetlb_reserve_pages(struct inode *inode, struct vm_area_struct *vma) { long ret, chg; + struct hstate *h = hstate_inode(inode); if (vma && vma->vm_flags & VM_NORESERVE) return 0; @@ -1739,7 +1772,7 @@ int hugetlb_reserve_pages(struct inode *inode, if (hugetlb_get_quota(inode->i_mapping, chg)) return -ENOSPC; - ret = hugetlb_acct_memory(chg); + ret = hugetlb_acct_memory(h, chg); if (ret < 0) { hugetlb_put_quota(inode->i_mapping, chg); return ret; @@ -1751,12 +1784,13 @@ int hugetlb_reserve_pages(struct inode *inode, void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) { + struct hstate *h = hstate_inode(inode); long chg = region_truncate(&inode->i_mapping->private_list, offset); spin_lock(&inode->i_lock); - inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed; + inode->i_blocks -= blocks_per_huge_page(h); spin_unlock(&inode->i_lock); hugetlb_put_quota(inode->i_mapping, (chg - freed)); - hugetlb_acct_memory(-(chg - freed)); + hugetlb_acct_memory(h, -(chg - freed)); } diff --git a/mm/memory.c b/mm/memory.c index 72932489a082..c1c1d6d8c22b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -903,7 +903,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, if (unlikely(is_vm_hugetlb_page(vma))) { unmap_hugepage_range(vma, start, end, NULL); zap_work -= (end - start) / - (HPAGE_SIZE / PAGE_SIZE); + pages_per_huge_page(hstate_vma(vma)); start = end; } else start = unmap_page_range(*tlbp, vma, diff --git a/mm/mempolicy.c b/mm/mempolicy.c index c94e58b192c3..e550bec20582 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1481,7 +1481,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) { zl = node_zonelist(interleave_nid(*mpol, vma, addr, - HPAGE_SHIFT), gfp_flags); + huge_page_shift(hstate_vma(vma))), gfp_flags); } else { zl = policy_zonelist(gfp_flags, *mpol); if ((*mpol)->mode == MPOL_BIND) @@ -2220,9 +2220,12 @@ static void check_huge_range(struct vm_area_struct *vma, { unsigned long addr; struct page *page; + struct hstate *h = hstate_vma(vma); + unsigned long sz = huge_page_size(h); - for (addr = start; addr < end; addr += HPAGE_SIZE) { - pte_t *ptep = huge_pte_offset(vma->vm_mm, addr & HPAGE_MASK); + for (addr = start; addr < end; addr += sz) { + pte_t *ptep = huge_pte_offset(vma->vm_mm, + addr & huge_page_mask(h)); pte_t pte; if (!ptep) diff --git a/mm/mmap.c b/mm/mmap.c index 57d3b6097deb..5e0cc99e9cd5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1812,7 +1812,8 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma, struct mempolicy *pol; struct vm_area_struct *new; - if (is_vm_hugetlb_page(vma) && (addr & ~HPAGE_MASK)) + if (is_vm_hugetlb_page(vma) && (addr & + ~(huge_page_mask(hstate_vma(vma))))) return -EINVAL; if (mm->map_count >= sysctl_max_map_count) -- cgit v1.2.3 From e5ff215941d59f8ae6bf58f6428dc5c26745a612 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:42 -0700 Subject: hugetlb: multiple hstates for multiple page sizes Add basic support for more than one hstate in hugetlbfs. This is the key to supporting multiple hugetlbfs page sizes at once. - Rather than a single hstate, we now have an array, with an iterator - default_hstate continues to be the struct hstate which we use by default - Add functions for architectures to register new hstates [akpm@linux-foundation.org: coding-style fixes] Acked-by: Adam Litke Acked-by: Nishanth Aravamudan Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 ++++++- kernel/sysctl.c | 8 ++- mm/hugetlb.c | 148 +++++++++++++++++++++++++++++++++++++++--------- 3 files changed, 142 insertions(+), 33 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ad2271e11f9b..b75bdb4deba3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -36,8 +36,6 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma); void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); -extern unsigned long max_huge_pages; -extern unsigned long sysctl_overcommit_huge_pages; extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; @@ -181,7 +179,17 @@ struct hstate { unsigned int surplus_huge_pages_node[MAX_NUMNODES]; }; -extern struct hstate default_hstate; +void __init hugetlb_add_hstate(unsigned order); +struct hstate *size_to_hstate(unsigned long size); + +#ifndef HUGE_MAX_HSTATE +#define HUGE_MAX_HSTATE 1 +#endif + +extern struct hstate hstates[HUGE_MAX_HSTATE]; +extern unsigned int default_hstate_idx; + +#define default_hstate (hstates[default_hstate_idx]) static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { @@ -230,6 +238,11 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h) #include +static inline struct hstate *page_hstate(struct page *page) +{ + return size_to_hstate(PAGE_SIZE << compound_order(page)); +} + #else struct hstate {}; #define hstate_file(f) NULL diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 1f7b3b76a166..1a8299d1fe59 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -959,7 +959,7 @@ static struct ctl_table vm_table[] = { #ifdef CONFIG_HUGETLB_PAGE { .procname = "nr_hugepages", - .data = &max_huge_pages, + .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_sysctl_handler, @@ -985,10 +985,12 @@ static struct ctl_table vm_table[] = { { .ctl_name = CTL_UNNUMBERED, .procname = "nr_overcommit_hugepages", - .data = &sysctl_overcommit_huge_pages, - .maxlen = sizeof(sysctl_overcommit_huge_pages), + .data = NULL, + .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_overcommit_handler, + .extra1 = (void *)&hugetlb_zero, + .extra2 = (void *)&hugetlb_infinity, }, #endif { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0d8153e25f09..82378d44a0c5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -22,12 +22,19 @@ #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; -unsigned long max_huge_pages; -unsigned long sysctl_overcommit_huge_pages; static gfp_t htlb_alloc_mask = GFP_HIGHUSER; unsigned long hugepages_treat_as_movable; -struct hstate default_hstate; +static int max_hstate; +unsigned int default_hstate_idx; +struct hstate hstates[HUGE_MAX_HSTATE]; + +/* for command line parsing */ +static struct hstate * __initdata parsed_hstate; +static unsigned long __initdata default_hstate_max_huge_pages; + +#define for_each_hstate(h) \ + for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++) /* * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages @@ -454,13 +461,24 @@ static void update_and_free_page(struct hstate *h, struct page *page) __free_pages(page, huge_page_order(h)); } +struct hstate *size_to_hstate(unsigned long size) +{ + struct hstate *h; + + for_each_hstate(h) { + if (huge_page_size(h) == size) + return h; + } + return NULL; +} + static void free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the * compound page destructor. */ - struct hstate *h = &default_hstate; + struct hstate *h = page_hstate(page); int nid = page_to_nid(page); struct address_space *mapping; @@ -887,39 +905,94 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return page; } -static int __init hugetlb_init(void) +static void __init hugetlb_init_one_hstate(struct hstate *h) { unsigned long i; - struct hstate *h = &default_hstate; - - if (HPAGE_SHIFT == 0) - return 0; - - if (!h->order) { - h->order = HPAGE_SHIFT - PAGE_SHIFT; - h->mask = HPAGE_MASK; - } for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); h->hugetlb_next_nid = first_node(node_online_map); - for (i = 0; i < max_huge_pages; ++i) { + for (i = 0; i < h->max_huge_pages; ++i) { if (!alloc_fresh_huge_page(h)) break; } - max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i; - printk(KERN_INFO "Total HugeTLB memory allocated, %ld\n", - h->free_huge_pages); + h->max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i; +} + +static void __init hugetlb_init_hstates(void) +{ + struct hstate *h; + + for_each_hstate(h) { + hugetlb_init_one_hstate(h); + } +} + +static void __init report_hugepages(void) +{ + struct hstate *h; + + for_each_hstate(h) { + printk(KERN_INFO "Total HugeTLB memory allocated, " + "%ld %dMB pages\n", + h->free_huge_pages, + 1 << (h->order + PAGE_SHIFT - 20)); + } +} + +static int __init hugetlb_init(void) +{ + BUILD_BUG_ON(HPAGE_SHIFT == 0); + + if (!size_to_hstate(HPAGE_SIZE)) { + hugetlb_add_hstate(HUGETLB_PAGE_ORDER); + parsed_hstate->max_huge_pages = default_hstate_max_huge_pages; + } + default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates; + + hugetlb_init_hstates(); + + report_hugepages(); + return 0; } module_init(hugetlb_init); +/* Should be called on processing a hugepagesz=... option */ +void __init hugetlb_add_hstate(unsigned order) +{ + struct hstate *h; + if (size_to_hstate(PAGE_SIZE << order)) { + printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); + return; + } + BUG_ON(max_hstate >= HUGE_MAX_HSTATE); + BUG_ON(order == 0); + h = &hstates[max_hstate++]; + h->order = order; + h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); + hugetlb_init_one_hstate(h); + parsed_hstate = h; +} + static int __init hugetlb_setup(char *s) { - if (sscanf(s, "%lu", &max_huge_pages) <= 0) - max_huge_pages = 0; + unsigned long *mhp; + + /* + * !max_hstate means we haven't parsed a hugepagesz= parameter yet, + * so this hugepages= parameter goes to the "default hstate". + */ + if (!max_hstate) + mhp = &default_hstate_max_huge_pages; + else + mhp = &parsed_hstate->max_huge_pages; + + if (sscanf(s, "%lu", mhp) <= 0) + *mhp = 0; + return 1; } __setup("hugepages=", hugetlb_setup); @@ -950,7 +1023,7 @@ static void try_to_free_low(struct hstate *h, unsigned long count) if (PageHighMem(page)) continue; list_del(&page->lru); - update_and_free_page(page); + update_and_free_page(h, page); h->free_huge_pages--; h->free_huge_pages_node[page_to_nid(page)]--; } @@ -963,10 +1036,9 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count) #endif #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) -static unsigned long set_max_huge_pages(unsigned long count) +static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count) { unsigned long min_count, ret; - struct hstate *h = &default_hstate; /* * Increase the pool size @@ -1037,8 +1109,19 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { + struct hstate *h = &default_hstate; + unsigned long tmp; + + if (!write) + tmp = h->max_huge_pages; + + table->data = &tmp; + table->maxlen = sizeof(unsigned long); proc_doulongvec_minmax(table, write, file, buffer, length, ppos); - max_huge_pages = set_max_huge_pages(max_huge_pages); + + if (write) + h->max_huge_pages = set_max_huge_pages(h, tmp); + return 0; } @@ -1059,10 +1142,21 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; + unsigned long tmp; + + if (!write) + tmp = h->nr_overcommit_huge_pages; + + table->data = &tmp; + table->maxlen = sizeof(unsigned long); proc_doulongvec_minmax(table, write, file, buffer, length, ppos); - spin_lock(&hugetlb_lock); - h->nr_overcommit_huge_pages = sysctl_overcommit_huge_pages; - spin_unlock(&hugetlb_lock); + + if (write) { + spin_lock(&hugetlb_lock); + h->nr_overcommit_huge_pages = tmp; + spin_unlock(&hugetlb_lock); + } + return 0; } -- cgit v1.2.3 From a137e1cc6d6e7d315fef03962a2a5a113348b13b Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:43 -0700 Subject: hugetlbfs: per mount huge page sizes Add the ability to configure the hugetlb hstate used on a per mount basis. - Add a new pagesize= option to the hugetlbfs mount that allows setting the page size - This option causes the mount code to find the hstate corresponding to the specified size, and sets up a pointer to the hstate in the mount's superblock. - Change the hstate accessors to use this information rather than the global_hstate they were using (requires a slight change in mm/memory.c so we don't NULL deref in the error-unmap path -- see comments). [np: take hstate out of hugetlbfs inode and vma->vm_private_data] Acked-by: Adam Litke Acked-by: Nishanth Aravamudan Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 45 ++++++++++++++++++++++++++++++++++++--------- include/linux/hugetlb.h | 14 +++++++++----- mm/hugetlb.c | 16 +++------------- mm/memory.c | 18 ++++++++++++++++-- 4 files changed, 64 insertions(+), 29 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 516c581b5371..dbd01d262ca4 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -53,6 +53,7 @@ int sysctl_hugetlb_shm_group; enum { Opt_size, Opt_nr_inodes, Opt_mode, Opt_uid, Opt_gid, + Opt_pagesize, Opt_err, }; @@ -62,6 +63,7 @@ static match_table_t tokens = { {Opt_mode, "mode=%o"}, {Opt_uid, "uid=%u"}, {Opt_gid, "gid=%u"}, + {Opt_pagesize, "pagesize=%s"}, {Opt_err, NULL}, }; @@ -750,6 +752,8 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) char *p, *rest; substring_t args[MAX_OPT_ARGS]; int option; + unsigned long long size = 0; + enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = NO_SIZE; if (!options) return 0; @@ -780,17 +784,13 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) break; case Opt_size: { - unsigned long long size; /* memparse() will accept a K/M/G without a digit */ if (!isdigit(*args[0].from)) goto bad_val; size = memparse(args[0].from, &rest); - if (*rest == '%') { - size <<= HPAGE_SHIFT; - size *= max_huge_pages; - do_div(size, 100); - } - pconfig->nr_blocks = (size >> HPAGE_SHIFT); + setsize = SIZE_STD; + if (*rest == '%') + setsize = SIZE_PERCENT; break; } @@ -801,6 +801,19 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) pconfig->nr_inodes = memparse(args[0].from, &rest); break; + case Opt_pagesize: { + unsigned long ps; + ps = memparse(args[0].from, &rest); + pconfig->hstate = size_to_hstate(ps); + if (!pconfig->hstate) { + printk(KERN_ERR + "hugetlbfs: Unsupported page size %lu MB\n", + ps >> 20); + return -EINVAL; + } + break; + } + default: printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n", p); @@ -808,6 +821,18 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) break; } } + + /* Do size after hstate is set up */ + if (setsize > NO_SIZE) { + struct hstate *h = pconfig->hstate; + if (setsize == SIZE_PERCENT) { + size <<= huge_page_shift(h); + size *= h->max_huge_pages; + do_div(size, 100); + } + pconfig->nr_blocks = (size >> huge_page_shift(h)); + } + return 0; bad_val: @@ -832,6 +857,7 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) config.uid = current->fsuid; config.gid = current->fsgid; config.mode = 0755; + config.hstate = &default_hstate; ret = hugetlbfs_parse_options(data, &config); if (ret) return ret; @@ -840,14 +866,15 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) if (!sbinfo) return -ENOMEM; sb->s_fs_info = sbinfo; + sbinfo->hstate = config.hstate; spin_lock_init(&sbinfo->stat_lock); sbinfo->max_blocks = config.nr_blocks; sbinfo->free_blocks = config.nr_blocks; sbinfo->max_inodes = config.nr_inodes; sbinfo->free_inodes = config.nr_inodes; sb->s_maxbytes = MAX_LFS_FILESIZE; - sb->s_blocksize = HPAGE_SIZE; - sb->s_blocksize_bits = HPAGE_SHIFT; + sb->s_blocksize = huge_page_size(config.hstate); + sb->s_blocksize_bits = huge_page_shift(config.hstate); sb->s_magic = HUGETLBFS_MAGIC; sb->s_op = &hugetlbfs_ops; sb->s_time_gran = 1; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b75bdb4deba3..ba9263e631b9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -100,6 +100,7 @@ struct hugetlbfs_config { umode_t mode; long nr_blocks; long nr_inodes; + struct hstate *hstate; }; struct hugetlbfs_sb_info { @@ -108,6 +109,7 @@ struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; + struct hstate *hstate; }; @@ -191,19 +193,21 @@ extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) -static inline struct hstate *hstate_vma(struct vm_area_struct *vma) +static inline struct hstate *hstate_inode(struct inode *i) { - return &default_hstate; + struct hugetlbfs_sb_info *hsb; + hsb = HUGETLBFS_SB(i->i_sb); + return hsb->hstate; } static inline struct hstate *hstate_file(struct file *f) { - return &default_hstate; + return hstate_inode(f->f_dentry->d_inode); } -static inline struct hstate *hstate_inode(struct inode *i) +static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { - return &default_hstate; + return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(struct hstate *h) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 82378d44a0c5..4cf7a90e9140 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1439,19 +1439,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { - /* - * It is undesirable to test vma->vm_file as it should be non-null - * for valid hugetlb area. However, vm_file will be NULL in the error - * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails, - * do_mmap_pgoff() nullifies vma->vm_file before calling this function - * to clean up. Since no pte has actually been setup, it is safe to - * do nothing in this case. - */ - if (vma->vm_file) { - spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); - __unmap_hugepage_range(vma, start, end, ref_page); - spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); - } + spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); + __unmap_hugepage_range(vma, start, end, ref_page); + spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); } /* diff --git a/mm/memory.c b/mm/memory.c index c1c1d6d8c22b..02fc6b1047b0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -901,9 +901,23 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp, } if (unlikely(is_vm_hugetlb_page(vma))) { - unmap_hugepage_range(vma, start, end, NULL); - zap_work -= (end - start) / + /* + * It is undesirable to test vma->vm_file as it + * should be non-null for valid hugetlb area. + * However, vm_file will be NULL in the error + * cleanup path of do_mmap_pgoff. When + * hugetlbfs ->mmap method fails, + * do_mmap_pgoff() nullifies vma->vm_file + * before calling this function to clean up. + * Since no pte has actually been setup, it is + * safe to do nothing in this case. + */ + if (vma->vm_file) { + unmap_hugepage_range(vma, start, end, NULL); + zap_work -= (end - start) / pages_per_huge_page(hstate_vma(vma)); + } + start = end; } else start = unmap_page_range(*tlbp, vma, -- cgit v1.2.3 From a3437870160cf2caaac6bdd76c7377a5a4145a8c Mon Sep 17 00:00:00 2001 From: Nishanth Aravamudan Date: Wed, 23 Jul 2008 21:27:44 -0700 Subject: hugetlb: new sysfs interface Provide new hugepages user APIs that are more suited to multiple hstates in sysfs. There is a new directory, /sys/kernel/hugepages. Underneath that directory there will be a directory per-supported hugepage size, e.g.: /sys/kernel/hugepages/hugepages-64kB /sys/kernel/hugepages/hugepages-16384kB /sys/kernel/hugepages/hugepages-16777216kB corresponding to 64k, 16m and 16g respectively. Within each hugepages-size directory there are a number of files, corresponding to the tracked counters in the hstate, e.g.: /sys/kernel/hugepages/hugepages-64/nr_hugepages /sys/kernel/hugepages/hugepages-64/nr_overcommit_hugepages /sys/kernel/hugepages/hugepages-64/free_hugepages /sys/kernel/hugepages/hugepages-64/resv_hugepages /sys/kernel/hugepages/hugepages-64/surplus_hugepages Of these files, the first two are read-write and the latter three are read-only. The size of the hugepage being manipulated is trivially deducible from the enclosing directory and is always expressed in kB (to match meminfo). [dave@linux.vnet.ibm.com: fix build] [nacc@us.ibm.com: hugetlb: hang off of /sys/kernel/mm rather than /sys/kernel] [nacc@us.ibm.com: hugetlb: remove CONFIG_SYSFS dependency] Acked-by: Greg Kroah-Hartman Signed-off-by: Nishanth Aravamudan Signed-off-by: Nick Piggin Cc: Dave Hansen Signed-off-by: Nishanth Aravamudan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../ABI/testing/sysfs-kernel-mm-hugepages | 15 ++ Documentation/vm/hugetlbpage.txt | 23 ++ include/linux/hugetlb.h | 2 + mm/hugetlb.c | 288 ++++++++++++++++----- 4 files changed, 262 insertions(+), 66 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm-hugepages (limited to 'include/linux/hugetlb.h') diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages new file mode 100644 index 000000000000..e21c00571cf4 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages @@ -0,0 +1,15 @@ +What: /sys/kernel/mm/hugepages/ +Date: June 2008 +Contact: Nishanth Aravamudan , hugetlb maintainers +Description: + /sys/kernel/mm/hugepages/ contains a number of subdirectories + of the form hugepages-kB, where is the page size + of the hugepages supported by the kernel/CPU combination. + + Under these directories are a number of files: + nr_hugepages + nr_overcommit_hugepages + free_hugepages + surplus_hugepages + resv_hugepages + See Documentation/vm/hugetlbpage.txt for details. diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt index 3102b81bef88..8a5b5763f0fe 100644 --- a/Documentation/vm/hugetlbpage.txt +++ b/Documentation/vm/hugetlbpage.txt @@ -95,6 +95,29 @@ this condition holds, however, no more surplus huge pages will be allowed on the system until one of the two sysctls are increased sufficiently, or the surplus huge pages go out of use and are freed. +With support for multiple hugepage pools at run-time available, much of +the hugepage userspace interface has been duplicated in sysfs. The above +information applies to the default hugepage size (which will be +controlled by the proc interfaces for backwards compatibility). The root +hugepage control directory is + + /sys/kernel/mm/hugepages + +For each hugepage size supported by the running kernel, a subdirectory +will exist, of the form + + hugepages-${size}kB + +Inside each of these directories, the same set of files will exist: + + nr_hugepages + nr_overcommit_hugepages + free_hugepages + resv_hugepages + surplus_hugepages + +which function as described above for the default hugepage-sized case. + If the user applications are going to request hugepages using mmap system call, then it is required that system administrator mount a file system of type hugetlbfs: diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ba9263e631b9..58c0de32e7f0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -164,6 +164,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #ifdef CONFIG_HUGETLB_PAGE +#define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { int hugetlb_next_nid; @@ -179,6 +180,7 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; + char name[HSTATE_NAME_LEN]; }; void __init hugetlb_add_hstate(unsigned order); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4cf7a90e9140..bb49ce5d0067 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -942,72 +943,6 @@ static void __init report_hugepages(void) } } -static int __init hugetlb_init(void) -{ - BUILD_BUG_ON(HPAGE_SHIFT == 0); - - if (!size_to_hstate(HPAGE_SIZE)) { - hugetlb_add_hstate(HUGETLB_PAGE_ORDER); - parsed_hstate->max_huge_pages = default_hstate_max_huge_pages; - } - default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates; - - hugetlb_init_hstates(); - - report_hugepages(); - - return 0; -} -module_init(hugetlb_init); - -/* Should be called on processing a hugepagesz=... option */ -void __init hugetlb_add_hstate(unsigned order) -{ - struct hstate *h; - if (size_to_hstate(PAGE_SIZE << order)) { - printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); - return; - } - BUG_ON(max_hstate >= HUGE_MAX_HSTATE); - BUG_ON(order == 0); - h = &hstates[max_hstate++]; - h->order = order; - h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); - hugetlb_init_one_hstate(h); - parsed_hstate = h; -} - -static int __init hugetlb_setup(char *s) -{ - unsigned long *mhp; - - /* - * !max_hstate means we haven't parsed a hugepagesz= parameter yet, - * so this hugepages= parameter goes to the "default hstate". - */ - if (!max_hstate) - mhp = &default_hstate_max_huge_pages; - else - mhp = &parsed_hstate->max_huge_pages; - - if (sscanf(s, "%lu", mhp) <= 0) - *mhp = 0; - - return 1; -} -__setup("hugepages=", hugetlb_setup); - -static unsigned int cpuset_mems_nr(unsigned int *array) -{ - int node; - unsigned int nr = 0; - - for_each_node_mask(node, cpuset_current_mems_allowed) - nr += array[node]; - - return nr; -} - #ifdef CONFIG_SYSCTL #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count) @@ -1105,6 +1040,227 @@ out: return ret; } +#define HSTATE_ATTR_RO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +#define HSTATE_ATTR(_name) \ + static struct kobj_attribute _name##_attr = \ + __ATTR(_name, 0644, _name##_show, _name##_store) + +static struct kobject *hugepages_kobj; +static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; + +static struct hstate *kobj_to_hstate(struct kobject *kobj) +{ + int i; + for (i = 0; i < HUGE_MAX_HSTATE; i++) + if (hstate_kobjs[i] == kobj) + return &hstates[i]; + BUG(); + return NULL; +} + +static ssize_t nr_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->nr_huge_pages); +} +static ssize_t nr_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int err; + unsigned long input; + struct hstate *h = kobj_to_hstate(kobj); + + err = strict_strtoul(buf, 10, &input); + if (err) + return 0; + + h->max_huge_pages = set_max_huge_pages(h, input); + + return count; +} +HSTATE_ATTR(nr_hugepages); + +static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages); +} +static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int err; + unsigned long input; + struct hstate *h = kobj_to_hstate(kobj); + + err = strict_strtoul(buf, 10, &input); + if (err) + return 0; + + spin_lock(&hugetlb_lock); + h->nr_overcommit_huge_pages = input; + spin_unlock(&hugetlb_lock); + + return count; +} +HSTATE_ATTR(nr_overcommit_hugepages); + +static ssize_t free_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->free_huge_pages); +} +HSTATE_ATTR_RO(free_hugepages); + +static ssize_t resv_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->resv_huge_pages); +} +HSTATE_ATTR_RO(resv_hugepages); + +static ssize_t surplus_hugepages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct hstate *h = kobj_to_hstate(kobj); + return sprintf(buf, "%lu\n", h->surplus_huge_pages); +} +HSTATE_ATTR_RO(surplus_hugepages); + +static struct attribute *hstate_attrs[] = { + &nr_hugepages_attr.attr, + &nr_overcommit_hugepages_attr.attr, + &free_hugepages_attr.attr, + &resv_hugepages_attr.attr, + &surplus_hugepages_attr.attr, + NULL, +}; + +static struct attribute_group hstate_attr_group = { + .attrs = hstate_attrs, +}; + +static int __init hugetlb_sysfs_add_hstate(struct hstate *h) +{ + int retval; + + hstate_kobjs[h - hstates] = kobject_create_and_add(h->name, + hugepages_kobj); + if (!hstate_kobjs[h - hstates]) + return -ENOMEM; + + retval = sysfs_create_group(hstate_kobjs[h - hstates], + &hstate_attr_group); + if (retval) + kobject_put(hstate_kobjs[h - hstates]); + + return retval; +} + +static void __init hugetlb_sysfs_init(void) +{ + struct hstate *h; + int err; + + hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); + if (!hugepages_kobj) + return; + + for_each_hstate(h) { + err = hugetlb_sysfs_add_hstate(h); + if (err) + printk(KERN_ERR "Hugetlb: Unable to add hstate %s", + h->name); + } +} + +static void __exit hugetlb_exit(void) +{ + struct hstate *h; + + for_each_hstate(h) { + kobject_put(hstate_kobjs[h - hstates]); + } + + kobject_put(hugepages_kobj); +} +module_exit(hugetlb_exit); + +static int __init hugetlb_init(void) +{ + BUILD_BUG_ON(HPAGE_SHIFT == 0); + + if (!size_to_hstate(HPAGE_SIZE)) { + hugetlb_add_hstate(HUGETLB_PAGE_ORDER); + parsed_hstate->max_huge_pages = default_hstate_max_huge_pages; + } + default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates; + + hugetlb_init_hstates(); + + report_hugepages(); + + hugetlb_sysfs_init(); + + return 0; +} +module_init(hugetlb_init); + +/* Should be called on processing a hugepagesz=... option */ +void __init hugetlb_add_hstate(unsigned order) +{ + struct hstate *h; + if (size_to_hstate(PAGE_SIZE << order)) { + printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n"); + return; + } + BUG_ON(max_hstate >= HUGE_MAX_HSTATE); + BUG_ON(order == 0); + h = &hstates[max_hstate++]; + h->order = order; + h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); + snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", + huge_page_size(h)/1024); + hugetlb_init_one_hstate(h); + parsed_hstate = h; +} + +static int __init hugetlb_setup(char *s) +{ + unsigned long *mhp; + + /* + * !max_hstate means we haven't parsed a hugepagesz= parameter yet, + * so this hugepages= parameter goes to the "default hstate". + */ + if (!max_hstate) + mhp = &default_hstate_max_huge_pages; + else + mhp = &parsed_hstate->max_huge_pages; + + if (sscanf(s, "%lu", mhp) <= 0) + *mhp = 0; + + return 1; +} +__setup("hugepages=", hugetlb_setup); + +static unsigned int cpuset_mems_nr(unsigned int *array) +{ + int node; + unsigned int nr = 0; + + for_each_node_mask(node, cpuset_current_mems_allowed) + nr += array[node]; + + return nr; +} + int hugetlb_sysctl_handler(struct ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) -- cgit v1.2.3 From ceb868796181dc95ea01a110e123afd391639873 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 23 Jul 2008 21:27:50 -0700 Subject: hugetlb: introduce pud_huge Straight forward extensions for huge pages located in the PUD instead of PMDs. Signed-off-by: Andi Kleen Signed-off-by: Nick Piggin Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/hugetlbpage.c | 6 ++++++ arch/powerpc/mm/hugetlbpage.c | 5 +++++ arch/s390/mm/hugetlbpage.c | 5 +++++ arch/sh/mm/hugetlbpage.c | 5 +++++ arch/sparc64/mm/hugetlbpage.c | 5 +++++ arch/x86/mm/hugetlbpage.c | 25 ++++++++++++++++++++++++- include/linux/hugetlb.h | 5 +++++ mm/hugetlb.c | 9 +++++++++ mm/memory.c | 15 +++++++++++---- 9 files changed, 75 insertions(+), 5 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 6170f097d255..c45fc7f5a979 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -107,6 +107,12 @@ int pmd_huge(pmd_t pmd) { return 0; } + +int pud_huge(pud_t pud) +{ + return 0; +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index c94dc71af989..63db7adce717 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -369,6 +369,11 @@ int pmd_huge(pmd_t pmd) return 0; } +int pud_huge(pud_t pud) +{ + return 0; +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 9162dc84f77f..f28c43d2f61d 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -120,6 +120,11 @@ int pmd_huge(pmd_t pmd) return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE); } +int pud_huge(pud_t pud) +{ + return 0; +} + struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmdp, int write) { diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index 2f9dbe0ef4ac..9304117039c4 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -79,6 +79,11 @@ int pmd_huge(pmd_t pmd) return 0; } +int pud_huge(pud_t pud) +{ + return 0; +} + struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/sparc64/mm/hugetlbpage.c b/arch/sparc64/mm/hugetlbpage.c index 1307b23f6a76..f27d10369e0c 100644 --- a/arch/sparc64/mm/hugetlbpage.c +++ b/arch/sparc64/mm/hugetlbpage.c @@ -295,6 +295,11 @@ int pmd_huge(pmd_t pmd) return 0; } +int pud_huge(pud_t pud) +{ + return 0; +} + struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) { diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 52476fde8996..a4789e87a315 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -189,6 +189,11 @@ int pmd_huge(pmd_t pmd) return 0; } +int pud_huge(pud_t pud) +{ + return 0; +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) @@ -209,6 +214,11 @@ int pmd_huge(pmd_t pmd) return !!(pmd_val(pmd) & _PAGE_PSE); } +int pud_huge(pud_t pud) +{ + return 0; +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) @@ -217,9 +227,22 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, page = pte_page(*(pte_t *)pmd); if (page) - page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT); + page += ((address & ~PMD_MASK) >> PAGE_SHIFT); return page; } + +struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pud); + if (page) + page += ((address & ~PUD_MASK) >> PAGE_SHIFT); + return page; +} + #endif /* x86_64 also uses this file */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 58c0de32e7f0..b2c17f62cacb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -50,7 +50,10 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write); +struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write); int pmd_huge(pmd_t pmd); +int pud_huge(pud_t pmd); void hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot); @@ -78,8 +81,10 @@ static inline unsigned long hugetlb_total_pages(void) #define hugetlb_report_meminfo(buf) 0 #define hugetlb_report_node_meminfo(n, buf) 0 #define follow_huge_pmd(mm, addr, pmd, write) NULL +#define follow_huge_pud(mm, addr, pud, write) NULL #define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 +#define pud_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, write) ({ BUG(); 0; }) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0c74c14dd2f7..107c1ce223cb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1996,6 +1996,15 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, return ret; } +/* Can be overriden by architectures */ +__attribute__((weak)) struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + BUG(); + return NULL; +} + 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, diff --git a/mm/memory.c b/mm/memory.c index 02fc6b1047b0..262e3eb6601a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -998,19 +998,24 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, goto no_page_table; pud = pud_offset(pgd, address); - if (pud_none(*pud) || unlikely(pud_bad(*pud))) + if (pud_none(*pud)) + goto no_page_table; + if (pud_huge(*pud)) { + BUG_ON(flags & FOLL_GET); + page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); + goto out; + } + if (unlikely(pud_bad(*pud))) goto no_page_table; - + pmd = pmd_offset(pud, address); if (pmd_none(*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 (unlikely(pmd_bad(*pmd))) goto no_page_table; @@ -1567,6 +1572,8 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long next; int err; + BUG_ON(pud_huge(*pud)); + pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; -- cgit v1.2.3 From 53ba51d21d6e048424ab8aadfebdb1f25ae07b60 Mon Sep 17 00:00:00 2001 From: Jon Tollefson Date: Wed, 23 Jul 2008 21:27:52 -0700 Subject: hugetlb: allow arch overridden hugepage allocation Allow alloc_bootmem_huge_page() to be overridden by architectures that can't always use bootmem. This requires huge_boot_pages to be available for use by this function. This is required for powerpc 16G pages, which have to be reserved prior to boot-time. The location of these pages are indicated in the device tree. Acked-by: Adam Litke Signed-off-by: Jon Tollefson Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ++++++++++ mm/hugetlb.c | 11 +++-------- 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b2c17f62cacb..9a71d4cc88c8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -39,6 +39,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); extern unsigned long hugepages_treat_as_movable; extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; +extern struct list_head huge_boot_pages; /* arch callbacks */ @@ -188,6 +189,14 @@ struct hstate { char name[HSTATE_NAME_LEN]; }; +struct huge_bootmem_page { + struct list_head list; + struct hstate *hstate; +}; + +/* arch callback */ +int __init alloc_bootmem_huge_page(struct hstate *h); + void __init hugetlb_add_hstate(unsigned order); struct hstate *size_to_hstate(unsigned long size); @@ -256,6 +265,7 @@ static inline struct hstate *page_hstate(struct page *page) #else struct hstate {}; +#define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL #define hstate_vma(v) NULL #define hstate_inode(i) NULL diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2a2f6e869401..3e1506b808a3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -31,6 +31,8 @@ static int max_hstate; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; +__initdata LIST_HEAD(huge_boot_pages); + /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; @@ -925,14 +927,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, return page; } -static __initdata LIST_HEAD(huge_boot_pages); - -struct huge_bootmem_page { - struct list_head list; - struct hstate *hstate; -}; - -static int __init alloc_bootmem_huge_page(struct hstate *h) +__attribute__((weak)) int alloc_bootmem_huge_page(struct hstate *h) { struct huge_bootmem_page *m; int nr_nodes = nodes_weight(node_online_map); -- cgit v1.2.3 From 510a35d4a47802f4a0028aa6bd2ca2170da5e32f Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Sat, 26 Jul 2008 15:22:27 -0700 Subject: hugetlb: remove unused variable warning Remove the following warning when CONFIG_HUGETLB_PAGE is not set: ipc/shm.c: In function `shm_get_stat': ipc/shm.c:565: warning: unused variable `h' [akpm@linux-foundation.org: use tabs, not spaces] Signed-off-by: Andrea Righi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/hugetlb.h') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9a71d4cc88c8..32e0ef0f6e1f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -273,7 +273,10 @@ struct hstate {}; #define huge_page_mask(h) PAGE_MASK #define huge_page_order(h) 0 #define huge_page_shift(h) PAGE_SHIFT -#define pages_per_huge_page(h) 1 +static inline unsigned int pages_per_huge_page(struct hstate *h) +{ + return 1; +} #endif #endif /* _LINUX_HUGETLB_H */ -- cgit v1.2.3