From 0f8053a509ceba4a077a50ea7b77039b5559b428 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:33 -0800 Subject: [PATCH] mm: make __put_page internal Remove __put_page from outside the core mm/. It is dangerous because it does not handle compound pages nicely, and misses 1->0 transitions. If a user later appears that really needs the extra speed we can reevaluate. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 44da3d47699..e8f58f7dd7a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -30,6 +30,8 @@ #include #include #include "filemap.h" +#include "internal.h" + /* * FIXME: remove all knowledge of the buffer layer from the core VM */ -- cgit v1.2.3-70-g09d2 From 44110fe385af23ca5eee8a6ad4ff55d50339097a Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Fri, 24 Mar 2006 03:16:04 -0800 Subject: [PATCH] cpuset memory spread page cache implementation and hooks Change the page cache allocation calls to support cpuset memory spreading. See the previous patch, cpuset_mem_spread, for an explanation of cpuset memory spreading. On systems without cpusets configured in the kernel, this is no change. On systems with cpusets configured in the kernel, but the "memory_spread" cpuset option not enabled for the current tasks cpuset, this adds a call to a cpuset routine and failed bit test of the processor state flag PF_SPREAD_PAGE. On tasks in cpusets with "memory_spread" enabled, this adds a call to a cpuset routine that computes which of the tasks mems_allowed nodes should be preferred for this allocation. If memory spreading applies to a particular allocation, then any other NUMA mempolicy does not apply. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 5 +++++ mm/filemap.c | 23 +++++++++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'mm/filemap.c') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee700c6eb44..839f0b3c23a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -51,6 +51,10 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_release(page) put_page(page) void release_pages(struct page **pages, int nr, int cold); +#ifdef CONFIG_NUMA +extern struct page *page_cache_alloc(struct address_space *x); +extern struct page *page_cache_alloc_cold(struct address_space *x); +#else static inline struct page *page_cache_alloc(struct address_space *x) { return alloc_pages(mapping_gfp_mask(x), 0); @@ -60,6 +64,7 @@ static inline struct page *page_cache_alloc_cold(struct address_space *x) { return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); } +#endif typedef int filler_t(void *, struct page *); diff --git a/mm/filemap.c b/mm/filemap.c index e8f58f7dd7a..d4ff48ec269 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "filemap.h" #include "internal.h" @@ -427,6 +428,28 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, return ret; } +#ifdef CONFIG_NUMA +struct page *page_cache_alloc(struct address_space *x) +{ + if (cpuset_do_page_mem_spread()) { + int n = cpuset_mem_spread_node(); + return alloc_pages_node(n, mapping_gfp_mask(x), 0); + } + return alloc_pages(mapping_gfp_mask(x), 0); +} +EXPORT_SYMBOL(page_cache_alloc); + +struct page *page_cache_alloc_cold(struct address_space *x) +{ + if (cpuset_do_page_mem_spread()) { + int n = cpuset_mem_spread_node(); + return alloc_pages_node(n, mapping_gfp_mask(x)|__GFP_COLD, 0); + } + return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); +} +EXPORT_SYMBOL(page_cache_alloc_cold); +#endif + /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of -- cgit v1.2.3-70-g09d2 From 469eb4d03878b676418f853011ebfb54ccf83a5e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 24 Mar 2006 03:17:45 -0800 Subject: [PATCH] filemap_fdatawrite_range() api: clarify -end parameter I had trouble understanding working out whether filemap_fdatawrite_range()'s `end' parameter describes the last-byte-to-be-written or the last-plus-one. Clarify that in comments. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index d4ff48ec269..c1b1708cc95 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -175,7 +175,7 @@ static int sync_page(void *word) * dirty pages that lie within the byte offsets * @mapping: address space structure to write * @start: offset in bytes where the range starts - * @end: offset in bytes where the range ends + * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as @@ -368,6 +368,12 @@ int filemap_write_and_wait(struct address_space *mapping) } EXPORT_SYMBOL(filemap_write_and_wait); +/* + * Write out and wait upon file offsets lstart->lend, inclusive. + * + * Note that `lend' is inclusive (describes the last byte to be written) so + * that this function can be used to write to the very end-of-file (end = -1). + */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { -- cgit v1.2.3-70-g09d2 From ebcf28e1c7a295f3321249dd235ad2e45938fdd9 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 24 Mar 2006 03:18:04 -0800 Subject: [PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fadvise.h | 6 ++++++ include/linux/fs.h | 5 +++++ mm/fadvise.c | 46 +++++++++++++++++++++++++++++++++++++++++----- mm/filemap.c | 10 +++++----- 4 files changed, 57 insertions(+), 10 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/fadvise.h b/include/linux/fadvise.h index e8e747139b9..b2913bba35d 100644 --- a/include/linux/fadvise.h +++ b/include/linux/fadvise.h @@ -18,4 +18,10 @@ #define POSIX_FADV_NOREUSE 5 /* Data will be accessed once. */ #endif +/* + * Linux-specific fadvise() extensions: + */ +#define LINUX_FADV_ASYNC_WRITE 32 /* Start writeout on range */ +#define LINUX_FADV_WRITE_WAIT 33 /* Wait upon writeout to range */ + #endif /* FADVISE_H_INCLUDED */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 65e6df247ea..0ad70c1e5e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1473,6 +1473,11 @@ extern int filemap_fdatawait(struct address_space *); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); +extern int wait_on_page_writeback_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +extern int __filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end, int sync_mode); + extern void sync_supers(void); extern void sync_filesystems(int wait); extern void emergency_sync(void); diff --git a/mm/fadvise.c b/mm/fadvise.c index d257c89e770..907c39257ca 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -22,13 +23,36 @@ /* * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could * deactivate the pages and clear PG_Referenced. + * + * LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file + * offsets `offset' and `offset+len' inclusive. Any pages which are currently + * under writeout are skipped, whether or not they are dirty. + * + * LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file + * offsets `offset' and `offset+len'. + * + * By combining these two operations the application may do several things: + * + * LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. + * + * LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently + * dirty pages at the disk. + * + * LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push + * all of the currently dirty pages at the disk, wait until they have been + * written. + * + * It should be noted that none of these operations write out the file's + * metadata. So unless the application is strictly performing overwrites of + * already-instantiated disk blocks, there are no guarantees here that the data + * will be available after a crash. */ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) { struct file *file = fget(fd); struct address_space *mapping; struct backing_dev_info *bdi; - loff_t endbyte; + loff_t endbyte; /* inclusive */ pgoff_t start_index; pgoff_t end_index; unsigned long nrpages; @@ -56,6 +80,8 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) endbyte = offset + len; if (!len || endbyte < len) endbyte = -1; + else + endbyte--; /* inclusive */ bdi = mapping->backing_dev_info; @@ -78,7 +104,7 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) /* First and last PARTIAL page! */ start_index = offset >> PAGE_CACHE_SHIFT; - end_index = (endbyte-1) >> PAGE_CACHE_SHIFT; + end_index = endbyte >> PAGE_CACHE_SHIFT; /* Careful about overflow on the "+1" */ nrpages = end_index - start_index + 1; @@ -96,11 +122,21 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) filemap_flush(mapping); /* First and last FULL page! */ - start_index = (offset + (PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT; + start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT; end_index = (endbyte >> PAGE_CACHE_SHIFT); - if (end_index > start_index) - invalidate_mapping_pages(mapping, start_index, end_index-1); + if (end_index >= start_index) + invalidate_mapping_pages(mapping, start_index, + end_index); + break; + case LINUX_FADV_ASYNC_WRITE: + ret = __filemap_fdatawrite_range(mapping, offset, endbyte, + WB_SYNC_NONE); + break; + case LINUX_FADV_WRITE_WAIT: + ret = wait_on_page_writeback_range(mapping, + offset >> PAGE_CACHE_SHIFT, + endbyte >> PAGE_CACHE_SHIFT); break; default: ret = -EINVAL; diff --git a/mm/filemap.c b/mm/filemap.c index c1b1708cc95..3ef20739e72 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -183,8 +183,8 @@ static int sync_page(void *word) * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. */ -static int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode) +int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, + loff_t end, int sync_mode) { int ret; struct writeback_control wbc = { @@ -213,8 +213,8 @@ int filemap_fdatawrite(struct address_space *mapping) } EXPORT_SYMBOL(filemap_fdatawrite); -static int filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end) +static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, + loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } @@ -233,7 +233,7 @@ EXPORT_SYMBOL(filemap_flush); * Wait for writeback to complete against pages indexed by start->end * inclusive */ -static int wait_on_page_writeback_range(struct address_space *mapping, +int wait_on_page_writeback_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { struct pagevec pvec; -- cgit v1.2.3-70-g09d2