From 0d71d10a4252a3938e6b70189bc776171c02e076 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 23 Jul 2008 21:27:05 -0700 Subject: mm: remove nopfn There are no users of nopfn in the tree. Remove it. [hugh@veritas.com: fix build error] Signed-off-by: Nick Piggin Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2128ef7780c6..eb815cfc1b35 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -166,8 +166,6 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); - unsigned long (*nopfn)(struct vm_area_struct *area, - unsigned long address); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ @@ -674,13 +672,6 @@ static inline int page_mapped(struct page *page) return atomic_read(&(page)->_mapcount) >= 0; } -/* - * Error return values for the *_nopfn functions - */ -#define NOPFN_SIGBUS ((unsigned long) -1) -#define NOPFN_OOM ((unsigned long) -2) -#define NOPFN_REFAULT ((unsigned long) -3) - /* * Different kinds of faults, as returned by handle_mm_fault(). * Used to decide whether a process gets delivered SIGBUS or -- cgit v1.2.3 From 28b2ee20c7cba812b6f2ccf6d722cf86d00a84dc Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 23 Jul 2008 21:27:05 -0700 Subject: access_process_vm device memory infrastructure In order to be able to debug things like the X server and programs using the PPC Cell SPUs, the debugger needs to be able to access device memory through ptrace and /proc/pid/mem. This patch: Add the generic_access_phys access function and put the hooks in place to allow access_process_vm to access device or PPC Cell SPU memory. [riel@redhat.com: Add documentation for the vm_ops->access function] Signed-off-by: Rik van Riel Signed-off-by: Benjamin Herrensmidt Cc: Dave Airlie Cc: Hugh Dickins Cc: Paul Mackerras Cc: Arnd Bergmann Acked-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index eb815cfc1b35..5c7f8f64f70e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -170,6 +170,12 @@ struct vm_operations_struct { /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); + + /* called by access_process_vm when get_user_pages() fails, typically + * for use by special VMAs that can switch between memory and hardware + */ + int (*access)(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy @@ -771,6 +777,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) -- cgit v1.2.3 From 42b7772812d15b86543a23b82bd6070eef9a08b1 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 23 Jul 2008 21:27:10 -0700 Subject: mm: remove double indirection on tlb parameter to free_pgd_range() & Co The double indirection here is not needed anywhere and hence (at least) confusing. Signed-off-by: Jan Beulich Cc: Hugh Dickins Cc: Nick Piggin Cc: Christoph Lameter Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Luck, Tony" Cc: Paul Mundt Cc: "David S. Miller" Acked-by: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5c7f8f64f70e..f8071097302a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -769,10 +769,8 @@ struct mm_walk { int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk); -void free_pgd_range(struct mmu_gather **tlb, unsigned long addr, +void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma, - unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, -- cgit v1.2.3 From 9109fb7b3520de187ebc3646c209d66a233f7169 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 23 Jul 2008 21:27:20 -0700 Subject: mm: drop unneeded pgdat argument from free_area_init_node() free_area_init_node() gets passed in the node id as well as the node descriptor. This is redundant as the function can trivially get the node descriptor itself by means of NODE_DATA() and the node's id. I checked all the users and NODE_DATA() seems to be usable everywhere from where this function is called. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index f8071097302a..196924b657bc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -962,9 +962,8 @@ static inline void pgtable_page_dtor(struct page *page) NULL: pte_offset_kernel(pmd, address)) extern void free_area_init(unsigned long * zones_size); -extern void free_area_init_node(int nid, pg_data_t *pgdat, - unsigned long * zones_size, unsigned long zone_start_pfn, - unsigned long *zholes_size); +extern void free_area_init_node(int nid, unsigned long * zones_size, + unsigned long zone_start_pfn, unsigned long *zholes_size); #ifdef CONFIG_ARCH_POPULATES_NODE_MAP /* * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its -- cgit v1.2.3 From cdfd4325c0d878679bd6a3ba8285b71d9980e3c0 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 23 Jul 2008 21:27:28 -0700 Subject: mm: record MAP_NORESERVE status on vmas and fix small page mprotect reservations With Mel's hugetlb private reservation support patches applied, strict overcommit semantics are applied to both shared and private huge page mappings. This can be a problem if an application relied on unlimited overcommit semantics for private mappings. An example of this would be an application which maps a huge area with the intention of using it very sparsely. These application would benefit from being able to opt-out of the strict overcommit. It should be noted that prior to hugetlb supporting demand faulting all mappings were fully populated and so applications of this type should be rare. This patch stack implements the MAP_NORESERVE mmap() flag for huge page mappings. This flag has the same meaning as for small page mappings, suppressing reservations for that mapping. Thanks to Mel Gorman for reviewing a number of early versions of these patches. This patch: When a small page mapping is created with mmap() reservations are created by default for any memory pages required. When the region is read/write the reservation is increased for every page, no reservation is needed for read-only regions (as they implicitly share the zero page). Reservations are tracked via the VM_ACCOUNT vma flag which is present when the region has reservation backing it. When we convert a region from read-only to read-write new reservations are aquired and VM_ACCOUNT is set. However, when a read-only map is created with MAP_NORESERVE it is indistinguishable from a normal mapping. When we then convert that to read/write we are forced to incorrectly create reservations for it as we have no record of the original MAP_NORESERVE. This patch introduces a new vma flag VM_NORESERVE which records the presence of the original MAP_NORESERVE flag. This allows us to distinguish these two circumstances and correctly account the reserve. As well as fixing this FIXME in the code, this makes it much easier to introduce MAP_NORESERVE support for huge pages as this flag is available consistantly for the life of the mapping. VM_ACCOUNT on the other hand is heavily used at the generic level in association with small pages. Signed-off-by: Andy Whitcroft Cc: Mel Gorman Cc: Adam Litke Cc: Johannes Weiner Cc: Andy Whitcroft Cc: William Lee Irwin III Cc: Hugh Dickins Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 196924b657bc..df322fb4df31 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -100,6 +100,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_RESERVED 0x00080000 /* Count as reserved_vm like IO */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ +#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ -- cgit v1.2.3 From 27ac792ca0b0a1e7e65f20342260650516c95864 Mon Sep 17 00:00:00 2001 From: Andrea Righi Date: Wed, 23 Jul 2008 21:28:13 -0700 Subject: PAGE_ALIGN(): correctly handle 64-bit values on 32-bit architectures On 32-bit architectures PAGE_ALIGN() truncates 64-bit values to the 32-bit boundary. For example: u64 val = PAGE_ALIGN(size); always returns a value < 4GB even if size is greater than 4GB. The problem resides in PAGE_MASK definition (from include/asm-x86/page.h for example): #define PAGE_SHIFT 12 #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) ... #define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) The "~" is performed on a 32-bit value, so everything in "and" with PAGE_MASK greater than 4GB will be truncated to the 32-bit boundary. Using the ALIGN() macro seems to be the right way, because it uses typeof(addr) for the mask. Also move the PAGE_ALIGN() definitions out of include/asm-*/page.h in include/linux/mm.h. See also lkml discussion: http://lkml.org/lkml/2008/6/11/237 [akpm@linux-foundation.org: fix drivers/media/video/uvc/uvc_queue.c] [akpm@linux-foundation.org: fix v850] [akpm@linux-foundation.org: fix powerpc] [akpm@linux-foundation.org: fix arm] [akpm@linux-foundation.org: fix mips] [akpm@linux-foundation.org: fix drivers/media/video/pvrusb2/pvrusb2-dvb.c] [akpm@linux-foundation.org: fix drivers/mtd/maps/uclinux.c] [akpm@linux-foundation.org: fix powerpc] Signed-off-by: Andrea Righi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index df322fb4df31..d87a5a5fe87d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -41,6 +41,9 @@ extern unsigned long mmap_min_addr; #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +/* to align the pointer to the (next) page boundary */ +#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) + /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way -- cgit v1.2.3 From 21cc199baa815d7b3f1ace4be20b9558cbddc00f Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 25 Jul 2008 19:45:22 -0700 Subject: mm: introduce get_user_pages_fast Introduce a new get_user_pages_fast mm API, which is basically a get_user_pages with a less general API (but still tends to be suited to the common case): - task and mm are always current and current->mm - force is always 0 - pages is always non-NULL - don't pass back vmas This restricted API can be implemented in a much more scalable way on many architectures when the ptes are present, by walking the page tables locklessly (no mmap_sem or page table locks). When the ptes are not populated, get_user_pages_fast() could be slower. This is implemented locklessly on x86, and used in some key direct IO call sites, in later patches, which provides nearly 10% performance improvement on a threaded database workload. Lots of other code could use this too, depending on use cases (eg. grep drivers/). And it might inspire some new and clever ways to use it. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Nick Piggin Cc: Dave Kleikamp Cc: Andy Whitcroft Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Andi Kleen Cc: Dave Kleikamp Cc: Badari Pulavarty Cc: Zach Brown Cc: Jens Axboe Reviewed-by: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index d87a5a5fe87d..f3fd70d6029f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -833,6 +833,39 @@ extern int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); +#ifdef CONFIG_HAVE_GET_USER_PAGES_FAST +/* + * get_user_pages_fast provides equivalent functionality to get_user_pages, + * operating on current and current->mm (force=0 and doesn't return any vmas). + * + * get_user_pages_fast may take mmap_sem and page tables, so no assumptions + * can be made about locking. get_user_pages_fast is to be implemented in a + * way that is advantageous (vs get_user_pages()) when the user memory area is + * already faulted in and present in ptes. However if the pages have to be + * faulted in, it may turn out to be slightly slower). + */ +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages); + +#else +/* + * Should probably be moved to asm-generic, and architectures can include it if + * they don't implement their own get_user_pages_fast. + */ +#define get_user_pages_fast(start, nr_pages, write, pages) \ +({ \ + struct mm_struct *mm = current->mm; \ + int ret; \ + \ + down_read(&mm->mmap_sem); \ + ret = get_user_pages(current, mm, start, nr_pages, \ + write, 0, pages, NULL); \ + up_read(&mm->mmap_sem); \ + \ + ret; \ +}) +#endif + /* * A callback you can register to apply pressure to ageable caches. * -- cgit v1.2.3 From 15f59adae001766a2c7f7fe4f196387bb04bcff5 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 25 Jul 2008 19:46:23 -0700 Subject: make mm/memory.c:print_bad_pte() static This patch makes the needlessly global print_bad_pte() static. Signed-off-by: Adrian Bunk Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index f3fd70d6029f..6e695eaab4ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -810,7 +810,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); -void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned long offset); -- cgit v1.2.3