From e2b371f00a6f529f6362654239bdec8dcd510760 Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Fri, 3 Apr 2009 16:43:35 +0200 Subject: mm, x86, ptrace, bts: defer branch trace stopping When a ptraced task is unlinked, we need to stop branch tracing for that task. Since the unlink is called with interrupts disabled, and we need interrupts enabled to stop branch tracing, we defer the work. Collect all branch tracing related stuff in a branch tracing context. Reviewed-by: Oleg Nesterov Signed-off-by: Markus Metzger Cc: Andrew Morton Cc: Peter Zijlstra Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: juan.villacis@intel.com Cc: ak@linux.jf.intel.com LKML-Reference: <20090403144550.712401000@intel.com> Signed-off-by: Ingo Molnar --- mm/mlock.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/mm/mlock.c b/mm/mlock.c index cbe9e0581b75..749383b442c7 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -660,21 +660,20 @@ void *alloc_locked_buffer(size_t size) return buffer; } -void release_locked_buffer(void *buffer, size_t size) +void refund_locked_buffer_memory(struct mm_struct *mm, size_t size) { unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; - down_write(¤t->mm->mmap_sem); + down_write(&mm->mmap_sem); - current->mm->total_vm -= pgsz; - current->mm->locked_vm -= pgsz; + mm->total_vm -= pgsz; + mm->locked_vm -= pgsz; - up_write(¤t->mm->mmap_sem); + up_write(&mm->mmap_sem); } void free_locked_buffer(void *buffer, size_t size) { - release_locked_buffer(buffer, size); - + refund_locked_buffer_memory(current->mm, size); kfree(buffer); } -- cgit From a34b50ddc265bae058c66661b096ef6384c5a8b1 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 8 Apr 2009 10:56:54 +0200 Subject: mm, x86, ptrace, bts: defer branch trace stopping, remove dead code Remove the unused free_locked_buffer() API. Signed-off-by: Ingo Molnar --- mm/mlock.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'mm') diff --git a/mm/mlock.c b/mm/mlock.c index 749383b442c7..28be15ead9c1 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -671,9 +671,3 @@ void refund_locked_buffer_memory(struct mm_struct *mm, size_t size) up_write(&mm->mmap_sem); } - -void free_locked_buffer(void *buffer, size_t size) -{ - refund_locked_buffer_memory(current->mm, size); - kfree(buffer); -} -- cgit From ae9e6bc9f74f8247cbca50a6a93c80e0d686fa19 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 2 Apr 2009 13:19:54 +0900 Subject: percpu: don't put the first chunk in reverse-map rbtree Impact: both first chunks don't use rbtree, no functional change There can be two first chunks - reserved and dynamic with the former one being optional. Dynamic first chunk was linked on reverse-mapping rbtree while the reserved one was mapped manually using the start address and reserved offset limit. This patch makes both first chunks to be looked up manually without using the rbtree. This is to help getting rid of the rbtree. Signed-off-by: Tejun Heo Cc: Martin Schwidefsky Cc: rusty@rustcorp.com.au Cc: Paul Mundt Cc: rmk@arm.linux.org.uk Cc: starvik@axis.com Cc: ralf@linux-mips.org Cc: davem@davemloft.net Cc: cooloney@kernel.org Cc: kyle@mcmartin.ca Cc: matthew@wil.cx Cc: grundler@parisc-linux.org Cc: takata@linux-m32r.org Cc: benh@kernel.crashing.org Cc: rth@twiddle.net Cc: ink@jurassic.park.msu.ru Cc: heiko.carstens@de.ibm.com Cc: Linus Torvalds Cc: Nick Piggin Cc: Christoph Lameter LKML-Reference: <49D43CEA.3040609@kernel.org> Signed-off-by: Ingo Molnar --- mm/percpu.c | 41 ++++++++++++++++++++++++----------------- 1 file changed, 24 insertions(+), 17 deletions(-) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index 1aa5d8fbca12..bf1bf1f4a729 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -110,9 +110,21 @@ static size_t pcpu_chunk_struct_size __read_mostly; void *pcpu_base_addr __read_mostly; EXPORT_SYMBOL_GPL(pcpu_base_addr); -/* optional reserved chunk, only accessible for reserved allocations */ +/* + * The first chunk which always exists. Note that unlike other + * chunks, this one can be allocated and mapped in several different + * ways and thus often doesn't live in the vmalloc area. + */ +static struct pcpu_chunk *pcpu_first_chunk; + +/* + * Optional reserved chunk. This chunk reserves part of the first + * chunk and serves it for reserved allocations. The amount of + * reserved offset is in pcpu_reserved_chunk_limit. When reserved + * area doesn't exist, the following variables contain NULL and 0 + * respectively. + */ static struct pcpu_chunk *pcpu_reserved_chunk; -/* offset limit of the reserved chunk */ static int pcpu_reserved_chunk_limit; /* @@ -297,15 +309,16 @@ static struct rb_node **pcpu_chunk_rb_search(void *addr, */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { + void *first_start = pcpu_first_chunk->vm->addr; struct rb_node *n, *parent; struct pcpu_chunk *chunk; - /* is it in the reserved chunk? */ - if (pcpu_reserved_chunk) { - void *start = pcpu_reserved_chunk->vm->addr; - - if (addr >= start && addr < start + pcpu_reserved_chunk_limit) + /* is it in the first chunk? */ + if (addr >= first_start && addr < first_start + pcpu_chunk_size) { + /* is it in the reserved area? */ + if (addr < first_start + pcpu_reserved_chunk_limit) return pcpu_reserved_chunk; + return pcpu_first_chunk; } /* nah... search the regular ones */ @@ -1147,7 +1160,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, if (reserved_size) { schunk->free_size = reserved_size; - pcpu_reserved_chunk = schunk; /* not for dynamic alloc */ + pcpu_reserved_chunk = schunk; + pcpu_reserved_chunk_limit = static_size + reserved_size; } else { schunk->free_size = dyn_size; dyn_size = 0; /* dynamic area covered */ @@ -1158,8 +1172,6 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, if (schunk->free_size) schunk->map[schunk->map_used++] = schunk->free_size; - pcpu_reserved_chunk_limit = static_size + schunk->free_size; - /* init dynamic chunk if necessary */ if (dyn_size) { dchunk = alloc_bootmem(sizeof(struct pcpu_chunk)); @@ -1226,13 +1238,8 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn, } /* link the first chunk in */ - if (!dchunk) { - pcpu_chunk_relocate(schunk, -1); - pcpu_chunk_addr_insert(schunk); - } else { - pcpu_chunk_relocate(dchunk, -1); - pcpu_chunk_addr_insert(dchunk); - } + pcpu_first_chunk = dchunk ?: schunk; + pcpu_chunk_relocate(pcpu_first_chunk, -1); /* we're done */ pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0); -- cgit From e1b9aa3f47242e757c776a3771bb6613e675bf9c Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 2 Apr 2009 13:21:44 +0900 Subject: percpu: remove rbtree and use page->index instead Impact: use page->index for addr to chunk mapping instead of dedicated rbtree The rbtree is used to determine the chunk from the virtual address. However, we can already determine the page struct from a virtual address and there are several unused fields in page struct used by vmalloc. Use the index field to store a pointer to the chunk. Then there is no need anymore for an rbtree. tj: * s/(set|get)_chunk/pcpu_\1_page_chunk/ * Drop inline from the above two functions and moved them upwards so that they are with other simple helpers. * Initial pages might not (actually most of the time don't) live in the vmalloc area. With the previous patch to manually reverse-map both first chunks, this is no longer an issue. Removed pcpu_set_chunk() call on initial pages. Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo Cc: Martin Schwidefsky Cc: rusty@rustcorp.com.au Cc: Paul Mundt Cc: rmk@arm.linux.org.uk Cc: starvik@axis.com Cc: ralf@linux-mips.org Cc: davem@davemloft.net Cc: cooloney@kernel.org Cc: kyle@mcmartin.ca Cc: matthew@wil.cx Cc: grundler@parisc-linux.org Cc: takata@linux-m32r.org Cc: benh@kernel.crashing.org Cc: rth@twiddle.net Cc: ink@jurassic.park.msu.ru Cc: heiko.carstens@de.ibm.com Cc: Linus Torvalds Cc: Nick Piggin LKML-Reference: <49D43D58.4050102@kernel.org> Signed-off-by: Ingo Molnar --- mm/percpu.c | 100 ++++++++++++------------------------------------------------ 1 file changed, 20 insertions(+), 80 deletions(-) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index bf1bf1f4a729..c0b2c1a76e81 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -23,7 +23,7 @@ * Allocation is done in offset-size areas of single unit space. Ie, * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0, * c1:u1, c1:u2 and c1:u3. Percpu access can be done by configuring - * percpu base registers UNIT_SIZE apart. + * percpu base registers pcpu_unit_size apart. * * There are usually many small percpu allocations many of them as * small as 4 bytes. The allocator organizes chunks into lists @@ -38,8 +38,8 @@ * region and negative allocated. Allocation inside a chunk is done * by scanning this map sequentially and serving the first matching * entry. This is mostly copied from the percpu_modalloc() allocator. - * Chunks are also linked into a rb tree to ease address to chunk - * mapping during free. + * Chunks can be determined from the address using the index field + * in the page struct. The index field contains a pointer to the chunk. * * To use this allocator, arch code should do the followings. * @@ -61,7 +61,6 @@ #include #include #include -#include #include #include #include @@ -88,7 +87,6 @@ struct pcpu_chunk { struct list_head list; /* linked to pcpu_slot lists */ - struct rb_node rb_node; /* key is chunk->vm->addr */ int free_size; /* free bytes in the chunk */ int contig_hint; /* max contiguous size hint */ struct vm_struct *vm; /* mapped vmalloc region */ @@ -133,7 +131,7 @@ static int pcpu_reserved_chunk_limit; * There are two locks - pcpu_alloc_mutex and pcpu_lock. The former * protects allocation/reclaim paths, chunks and chunk->page arrays. * The latter is a spinlock and protects the index data structures - - * chunk slots, rbtree, chunks and area maps in chunks. + * chunk slots, chunks and area maps in chunks. * * During allocation, pcpu_alloc_mutex is kept locked all the time and * pcpu_lock is grabbed and released as necessary. All actual memory @@ -152,7 +150,6 @@ static DEFINE_MUTEX(pcpu_alloc_mutex); /* protects whole alloc and reclaim */ static DEFINE_SPINLOCK(pcpu_lock); /* protects index data structures */ static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */ -static struct rb_root pcpu_addr_root = RB_ROOT; /* chunks by address */ /* reclaim work to release fully free chunks, scheduled from free path */ static void pcpu_reclaim(struct work_struct *work); @@ -203,6 +200,18 @@ static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk, return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL; } +/* set the pointer to a chunk in a page struct */ +static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) +{ + page->index = (unsigned long)pcpu; +} + +/* obtain pointer to a chunk from a page struct */ +static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) +{ + return (struct pcpu_chunk *)page->index; +} + /** * pcpu_mem_alloc - allocate memory * @size: bytes to allocate @@ -269,40 +278,9 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) } } -static struct rb_node **pcpu_chunk_rb_search(void *addr, - struct rb_node **parentp) -{ - struct rb_node **p = &pcpu_addr_root.rb_node; - struct rb_node *parent = NULL; - struct pcpu_chunk *chunk; - - while (*p) { - parent = *p; - chunk = rb_entry(parent, struct pcpu_chunk, rb_node); - - if (addr < chunk->vm->addr) - p = &(*p)->rb_left; - else if (addr > chunk->vm->addr) - p = &(*p)->rb_right; - else - break; - } - - if (parentp) - *parentp = parent; - return p; -} - /** - * pcpu_chunk_addr_search - search for chunk containing specified address - * @addr: address to search for - * - * Look for chunk which might contain @addr. More specifically, it - * searchs for the chunk with the highest start address which isn't - * beyond @addr. - * - * CONTEXT: - * pcpu_lock. + * pcpu_chunk_addr_search - determine chunk containing specified address + * @addr: address for which the chunk needs to be determined. * * RETURNS: * The address of the found chunk. @@ -310,8 +288,6 @@ static struct rb_node **pcpu_chunk_rb_search(void *addr, static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { void *first_start = pcpu_first_chunk->vm->addr; - struct rb_node *n, *parent; - struct pcpu_chunk *chunk; /* is it in the first chunk? */ if (addr >= first_start && addr < first_start + pcpu_chunk_size) { @@ -321,42 +297,7 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) return pcpu_first_chunk; } - /* nah... search the regular ones */ - n = *pcpu_chunk_rb_search(addr, &parent); - if (!n) { - /* no exactly matching chunk, the parent is the closest */ - n = parent; - BUG_ON(!n); - } - chunk = rb_entry(n, struct pcpu_chunk, rb_node); - - if (addr < chunk->vm->addr) { - /* the parent was the next one, look for the previous one */ - n = rb_prev(n); - BUG_ON(!n); - chunk = rb_entry(n, struct pcpu_chunk, rb_node); - } - - return chunk; -} - -/** - * pcpu_chunk_addr_insert - insert chunk into address rb tree - * @new: chunk to insert - * - * Insert @new into address rb tree. - * - * CONTEXT: - * pcpu_lock. - */ -static void pcpu_chunk_addr_insert(struct pcpu_chunk *new) -{ - struct rb_node **p, *parent; - - p = pcpu_chunk_rb_search(new->vm->addr, &parent); - BUG_ON(*p); - rb_link_node(&new->rb_node, parent, p); - rb_insert_color(&new->rb_node, &pcpu_addr_root); + return pcpu_get_page_chunk(vmalloc_to_page(addr)); } /** @@ -768,6 +709,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size) alloc_mask, 0); if (!*pagep) goto err; + pcpu_set_page_chunk(*pagep, chunk); } } @@ -892,7 +834,6 @@ restart: spin_lock_irq(&pcpu_lock); pcpu_chunk_relocate(chunk, -1); - pcpu_chunk_addr_insert(chunk); goto restart; area_found: @@ -981,7 +922,6 @@ static void pcpu_reclaim(struct work_struct *work) if (chunk == list_first_entry(head, struct pcpu_chunk, list)) continue; - rb_erase(&chunk->rb_node, &pcpu_addr_root); list_move(&chunk->list, &todo); } -- cgit From 02af61bb50f5d5f0322dbe5ab2a0d75808d25c7b Mon Sep 17 00:00:00 2001 From: Zhaolei Date: Fri, 10 Apr 2009 14:26:18 +0800 Subject: tracing, kmemtrace: Separate include/trace/kmemtrace.h to kmemtrace part and tracepoint part Impact: refactor code for future changes Current kmemtrace.h is used both as header file of kmemtrace and kmem's tracepoints definition. Tracepoints' definition file may be used by other code, and should only have definition of tracepoint. We can separate include/trace/kmemtrace.h into 2 files: include/linux/kmemtrace.h: header file for kmemtrace include/trace/kmem.h: definition of kmem tracepoints Signed-off-by: Zhao Lei Acked-by: Eduard - Gabriel Munteanu Acked-by: Pekka Enberg Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Tom Zanussi LKML-Reference: <49DEE68A.5040902@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- mm/slab.c | 2 +- mm/slob.c | 2 +- mm/slub.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/slab.c b/mm/slab.c index 9a90b00d2f91..f85831da9080 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -102,7 +102,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/mm/slob.c b/mm/slob.c index a2d4ab32198d..494f05f19417 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -65,7 +65,7 @@ #include #include #include -#include +#include #include /* diff --git a/mm/slub.c b/mm/slub.c index 7ab54ecbd3f3..ea9e7160e2e7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include -- cgit From a8d154b009168337494fbf345671bab74d3e4b8b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 10 Apr 2009 09:36:00 -0400 Subject: tracing: create automated trace defines This patch lowers the number of places a developer must modify to add new tracepoints. The current method to add a new tracepoint into an existing system is to write the trace point macro in the trace header with one of the macros TRACE_EVENT, TRACE_FORMAT or DECLARE_TRACE, then they must add the same named item into the C file with the macro DEFINE_TRACE(name) and then add the trace point. This change cuts out the needing to add the DEFINE_TRACE(name). Every file that uses the tracepoint must still include the trace/.h file, but the one C file must also add a define before the including of that file. #define CREATE_TRACE_POINTS #include This will cause the trace/mytrace.h file to also produce the C code necessary to implement the trace point. Note, if more than one trace/.h is used to create the C code it is best to list them all together. #define CREATE_TRACE_POINTS #include #include #include Thanks to Mathieu Desnoyers and Christoph Hellwig for coming up with the cleaner solution of the define above the includes over my first design to have the C code include a "special" header. This patch converts sched, irq and lockdep and skb to use this new method. Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Neil Horman Cc: Zhao Lei Cc: Eduard - Gabriel Munteanu Cc: Pekka Enberg Signed-off-by: Steven Rostedt --- mm/util.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/util.c b/mm/util.c index 2599e83eea17..0e74a22791cb 100644 --- a/mm/util.c +++ b/mm/util.c @@ -4,9 +4,11 @@ #include #include #include -#include #include +#define CREATE_TRACE_POINTS +#include + /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate @@ -239,13 +241,6 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start, EXPORT_SYMBOL_GPL(get_user_pages_fast); /* Tracepoints definitions. */ -DEFINE_TRACE(kmalloc); -DEFINE_TRACE(kmem_cache_alloc); -DEFINE_TRACE(kmalloc_node); -DEFINE_TRACE(kmem_cache_alloc_node); -DEFINE_TRACE(kfree); -DEFINE_TRACE(kmem_cache_free); - EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); EXPORT_TRACEPOINT_SYMBOL(kmalloc_node); -- cgit From ad8d75fff811a6a230f7f43b05a6483099349533 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 14 Apr 2009 19:39:12 -0400 Subject: tracing/events: move trace point headers into include/trace/events Impact: clean up Create a sub directory in include/trace called events to keep the trace point headers in their own separate directory. Only headers that declare trace points should be defined in this directory. Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Neil Horman Cc: Zhao Lei Cc: Eduard - Gabriel Munteanu Cc: Pekka Enberg Signed-off-by: Steven Rostedt --- mm/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/util.c b/mm/util.c index 0e74a22791cb..6794a336e9af 100644 --- a/mm/util.c +++ b/mm/util.c @@ -7,7 +7,7 @@ #include #define CREATE_TRACE_POINTS -#include +#include /** * kstrdup - allocate space for and copy an existing string -- cgit From 1cb81b143fa8f0e4629f10690862e2e52ca792ff Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Fri, 24 Apr 2009 09:51:43 +0200 Subject: x86, bts, mm: clean up buffer allocation The current mm interface is asymetric. One function allocates a locked buffer, another function only refunds the memory. Change this to have two functions for accounting and refunding locked memory, respectively; and do the actual buffer allocation in ptrace. [ Impact: refactor BTS buffer allocation code ] Signed-off-by: Markus Metzger Acked-by: Andrew Morton Cc: Peter Zijlstra LKML-Reference: <20090424095143.A30265@sedona.ch.intel.com> Signed-off-by: Ingo Molnar --- mm/mlock.c | 36 +++++++++++++++++------------------- 1 file changed, 17 insertions(+), 19 deletions(-) (limited to 'mm') diff --git a/mm/mlock.c b/mm/mlock.c index 28be15ead9c1..ac130433c7d3 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -629,38 +629,36 @@ void user_shm_unlock(size_t size, struct user_struct *user) free_uid(user); } -void *alloc_locked_buffer(size_t size) +int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, + size_t size) { - unsigned long rlim, vm, pgsz; - void *buffer = NULL; + unsigned long lim, vm, pgsz; + int error = -ENOMEM; pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; - down_write(¤t->mm->mmap_sem); - - rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; - vm = current->mm->total_vm + pgsz; - if (rlim < vm) - goto out; + down_write(&mm->mmap_sem); - rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; - vm = current->mm->locked_vm + pgsz; - if (rlim < vm) + lim = rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT; + vm = mm->total_vm + pgsz; + if (lim < vm) goto out; - buffer = kzalloc(size, GFP_KERNEL); - if (!buffer) + lim = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT; + vm = mm->locked_vm + pgsz; + if (lim < vm) goto out; - current->mm->total_vm += pgsz; - current->mm->locked_vm += pgsz; + mm->total_vm += pgsz; + mm->locked_vm += pgsz; + error = 0; out: - up_write(¤t->mm->mmap_sem); - return buffer; + up_write(&mm->mmap_sem); + return error; } -void refund_locked_buffer_memory(struct mm_struct *mm, size_t size) +void refund_locked_memory(struct mm_struct *mm, size_t size) { unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT; -- cgit From 888a589f6be07d624e21e2174d98375e9f95911b Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 15 May 2009 13:59:37 -0700 Subject: mm, x86: remove MEMORY_HOTPLUG_RESERVE related code after: | commit b263295dbffd33b0fbff670720fa178c30e3392a | Author: Christoph Lameter | Date: Wed Jan 30 13:30:47 2008 +0100 | | x86: 64-bit, make sparsemem vmemmap the only memory model we don't have MEMORY_HOTPLUG_RESERVE anymore. Historically, x86-64 had an architecture-specific method for memory hotplug whereby it scanned the SRAT for physical memory ranges that could be potentially used for memory hot-add later. By reserving those ranges without physical memory, the memmap would be allocated and left dormant until needed. This depended on the DISCONTIG memory model which has been removed so the code implementing HOTPLUG_RESERVE is now dead. This patch removes the dead code used by MEMORY_HOTPLUG_RESERVE. (Changelog authored by Mel.) v2: updated changelog, and remove hotadd= in doc [ Impact: remove dead code ] Signed-off-by: Yinghai Lu Reviewed-by: Christoph Lameter Reviewed-by: Mel Gorman Workflow-found-OK-by: Andrew Morton LKML-Reference: <4A0C4910.7090508@kernel.org> Signed-off-by: Ingo Molnar --- mm/page_alloc.c | 69 --------------------------------------------------------- 1 file changed, 69 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fe753ecf2aa5..474c7e9dd51a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -149,10 +149,6 @@ static unsigned long __meminitdata dma_reserve; static int __meminitdata nr_nodemap_entries; static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; -#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE - static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES]; - static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES]; -#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */ static unsigned long __initdata required_kernelcore; static unsigned long __initdata required_movablecore; static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES]; @@ -3102,64 +3098,6 @@ void __init sparse_memory_present_with_active_regions(int nid) early_node_map[i].end_pfn); } -/** - * push_node_boundaries - Push node boundaries to at least the requested boundary - * @nid: The nid of the node to push the boundary for - * @start_pfn: The start pfn of the node - * @end_pfn: The end pfn of the node - * - * In reserve-based hot-add, mem_map is allocated that is unused until hotadd - * time. Specifically, on x86_64, SRAT will report ranges that can potentially - * be hotplugged even though no physical memory exists. This function allows - * an arch to push out the node boundaries so mem_map is allocated that can - * be used later. - */ -#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE -void __init push_node_boundaries(unsigned int nid, - unsigned long start_pfn, unsigned long end_pfn) -{ - mminit_dprintk(MMINIT_TRACE, "zoneboundary", - "Entering push_node_boundaries(%u, %lu, %lu)\n", - nid, start_pfn, end_pfn); - - /* Initialise the boundary for this node if necessary */ - if (node_boundary_end_pfn[nid] == 0) - node_boundary_start_pfn[nid] = -1UL; - - /* Update the boundaries */ - if (node_boundary_start_pfn[nid] > start_pfn) - node_boundary_start_pfn[nid] = start_pfn; - if (node_boundary_end_pfn[nid] < end_pfn) - node_boundary_end_pfn[nid] = end_pfn; -} - -/* If necessary, push the node boundary out for reserve hotadd */ -static void __meminit account_node_boundary(unsigned int nid, - unsigned long *start_pfn, unsigned long *end_pfn) -{ - mminit_dprintk(MMINIT_TRACE, "zoneboundary", - "Entering account_node_boundary(%u, %lu, %lu)\n", - nid, *start_pfn, *end_pfn); - - /* Return if boundary information has not been provided */ - if (node_boundary_end_pfn[nid] == 0) - return; - - /* Check the boundaries and update if necessary */ - if (node_boundary_start_pfn[nid] < *start_pfn) - *start_pfn = node_boundary_start_pfn[nid]; - if (node_boundary_end_pfn[nid] > *end_pfn) - *end_pfn = node_boundary_end_pfn[nid]; -} -#else -void __init push_node_boundaries(unsigned int nid, - unsigned long start_pfn, unsigned long end_pfn) {} - -static void __meminit account_node_boundary(unsigned int nid, - unsigned long *start_pfn, unsigned long *end_pfn) {} -#endif - - /** * get_pfn_range_for_nid - Return the start and end page frames for a node * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned. @@ -3185,9 +3123,6 @@ void __meminit get_pfn_range_for_nid(unsigned int nid, if (*start_pfn == -1UL) *start_pfn = 0; - - /* Push the node boundaries out if requested */ - account_node_boundary(nid, start_pfn, end_pfn); } /* @@ -3793,10 +3728,6 @@ void __init remove_all_active_ranges(void) { memset(early_node_map, 0, sizeof(early_node_map)); nr_nodemap_entries = 0; -#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE - memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn)); - memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn)); -#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */ } /* Compare two active node_active_regions */ -- cgit From 98f32602d42951e61a059685f842aa7d778ffab0 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 21 May 2009 20:33:58 +0100 Subject: hugh: update email address My old address will shut down in a few days time: remove it from the tree, and add a tmpfs (shmem filesystem) maintainer entry with the new address. Signed-off-by: Hugh Dickins Signed-off-by: Hugh Dickins Signed-off-by: Linus Torvalds --- mm/rmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/rmap.c b/mm/rmap.c index 16521664010d..23122af32611 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -14,7 +14,7 @@ * Original design by Rik van Riel 2001 * File methods by Dave McCracken 2003, 2004 * Anonymous methods by Andrea Arcangeli 2004 - * Contributions by Hugh Dickins 2003, 2004 + * Contributions by Hugh Dickins 2003, 2004 */ /* -- cgit From 6d2661ede5f20f968422e790af3334908c3bc857 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 28 May 2009 14:34:19 -0700 Subject: oom: fix possible oom_dump_tasks NULL pointer When /proc/sys/vm/oom_dump_tasks is enabled, it is possible to get a NULL pointer for tasks that have detached mm's since task_lock() is not held during the tasklist scan. Add the task_lock(). Acked-by: Nick Piggin Acked-by: Mel Gorman Cc: Rik van Riel Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 92bcf1db16b2..a7b2460e922b 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -284,22 +284,28 @@ static void dump_tasks(const struct mem_cgroup *mem) printk(KERN_INFO "[ pid ] uid tgid total_vm rss cpu oom_adj " "name\n"); do_each_thread(g, p) { - /* - * total_vm and rss sizes do not exist for tasks with a - * detached mm so there's no need to report them. - */ - if (!p->mm) - continue; + struct mm_struct *mm; + if (mem && !task_in_mem_cgroup(p, mem)) continue; if (!thread_group_leader(p)) continue; task_lock(p); + mm = p->mm; + if (!mm) { + /* + * total_vm and rss sizes do not exist for tasks with no + * mm so there's no need to report them; they can't be + * oom killed anyway. + */ + task_unlock(p); + continue; + } printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", - p->pid, __task_cred(p)->uid, p->tgid, - p->mm->total_vm, get_mm_rss(p->mm), (int)task_cpu(p), - p->oomkilladj, p->comm); + p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm, + get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj, + p->comm); task_unlock(p); } while_each_thread(g, p); } -- cgit From e767e0561d7fd2333df1921f1ab4176211f9036b Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Thu, 28 May 2009 14:34:28 -0700 Subject: memcg: fix deadlock between lock_page_cgroup and mapping tree_lock mapping->tree_lock can be acquired from interrupt context. Then, following dead lock can occur. Assume "A" as a page. CPU0: lock_page_cgroup(A) interrupted -> take mapping->tree_lock. CPU1: take mapping->tree_lock -> lock_page_cgroup(A) This patch tries to fix above deadlock by moving memcg's hook to out of mapping->tree_lock. charge/uncharge of pagecache/swapcache is protected by page lock, not tree_lock. After this patch, lock_page_cgroup() is not called under mapping->tree_lock. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Daisuke Nishimura Cc: Balbir Singh Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 6 +++--- mm/memcontrol.c | 4 +++- mm/swap_state.c | 4 +--- mm/truncate.c | 1 + mm/vmscan.c | 2 ++ 5 files changed, 10 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 379ff0bcbf6e..1b60f30cebfa 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -121,7 +121,6 @@ void __remove_from_page_cache(struct page *page) mapping->nrpages--; __dec_zone_page_state(page, NR_FILE_PAGES); BUG_ON(page_mapped(page)); - mem_cgroup_uncharge_cache_page(page); /* * Some filesystems seem to re-dirty the page even after @@ -145,6 +144,7 @@ void remove_from_page_cache(struct page *page) spin_lock_irq(&mapping->tree_lock); __remove_from_page_cache(page); spin_unlock_irq(&mapping->tree_lock); + mem_cgroup_uncharge_cache_page(page); } static int sync_page(void *word) @@ -476,13 +476,13 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, if (likely(!error)) { mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); + spin_unlock_irq(&mapping->tree_lock); } else { page->mapping = NULL; + spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); page_cache_release(page); } - - spin_unlock_irq(&mapping->tree_lock); radix_tree_preload_end(); } else mem_cgroup_uncharge_cache_page(page); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 01c2d8f14685..4a747a27a22f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1488,8 +1488,9 @@ void mem_cgroup_uncharge_cache_page(struct page *page) __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE); } +#ifdef CONFIG_SWAP /* - * called from __delete_from_swap_cache() and drop "page" account. + * called after __delete_from_swap_cache() and drop "page" account. * memcg information is recorded to swap_cgroup of "ent" */ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) @@ -1506,6 +1507,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) if (memcg) css_put(&memcg->css); } +#endif #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP /* diff --git a/mm/swap_state.c b/mm/swap_state.c index 3ecea98ecb45..1416e7e9e02d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -109,8 +109,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) */ void __delete_from_swap_cache(struct page *page) { - swp_entry_t ent = {.val = page_private(page)}; - VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(!PageSwapCache(page)); VM_BUG_ON(PageWriteback(page)); @@ -121,7 +119,6 @@ void __delete_from_swap_cache(struct page *page) total_swapcache_pages--; __dec_zone_page_state(page, NR_FILE_PAGES); INC_CACHE_INFO(del_total); - mem_cgroup_uncharge_swapcache(page, ent); } /** @@ -191,6 +188,7 @@ void delete_from_swap_cache(struct page *page) __delete_from_swap_cache(page); spin_unlock_irq(&swapper_space.tree_lock); + mem_cgroup_uncharge_swapcache(page, entry); swap_free(entry); page_cache_release(page); } diff --git a/mm/truncate.c b/mm/truncate.c index 55206fab7b99..12e1579f9165 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -359,6 +359,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) BUG_ON(page_has_private(page)); __remove_from_page_cache(page); spin_unlock_irq(&mapping->tree_lock); + mem_cgroup_uncharge_cache_page(page); page_cache_release(page); /* pagecache ref */ return 1; failed: diff --git a/mm/vmscan.c b/mm/vmscan.c index 5fa3eda1f03f..d254306562cd 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -470,10 +470,12 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) swp_entry_t swap = { .val = page_private(page) }; __delete_from_swap_cache(page); spin_unlock_irq(&mapping->tree_lock); + mem_cgroup_uncharge_swapcache(page, swap); swap_free(swap); } else { __remove_from_page_cache(page); spin_unlock_irq(&mapping->tree_lock); + mem_cgroup_uncharge_cache_page(page); } return 1; -- cgit From f83a275dbc5ca1721143698e844243fcadfabf6a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 May 2009 14:34:40 -0700 Subject: mm: account for MAP_SHARED mappings using VM_MAYSHARE and not VM_SHARED in hugetlbfs Addresses http://bugzilla.kernel.org/show_bug.cgi?id=13302 hugetlbfs reserves huge pages but does not fault them at mmap() time to ensure that future faults succeed. The reservation behaviour differs depending on whether the mapping was mapped MAP_SHARED or MAP_PRIVATE. For MAP_SHARED mappings, hugepages are reserved when mmap() is first called and are tracked based on information associated with the inode. Other processes mapping MAP_SHARED use the same reservation. MAP_PRIVATE track the reservations based on the VMA created as part of the mmap() operation. Each process mapping MAP_PRIVATE must make its own reservation. hugetlbfs currently checks if a VMA is MAP_SHARED with the VM_SHARED flag and not VM_MAYSHARE. For file-backed mappings, such as hugetlbfs, VM_SHARED is set only if the mapping is MAP_SHARED and the file was opened read-write. If a shared memory mapping was mapped shared-read-write for populating of data and mapped shared-read-only by other processes, then hugetlbfs would account for the mapping as if it was MAP_PRIVATE. This causes processes to fail to map the file MAP_SHARED even though it should succeed as the reservation is there. This patch alters mm/hugetlb.c and replaces VM_SHARED with VM_MAYSHARE when the intent of the code was to check whether the VMA was mapped MAP_SHARED or MAP_PRIVATE. Signed-off-by: Mel Gorman Cc: Hugh Dickins Cc: Ingo Molnar Cc: Cc: Lee Schermerhorn Cc: KOSAKI Motohiro Cc: Cc: Eric B Munson Cc: Adam Litke Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 28c655ba9353..e83ad2c9228c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -316,7 +316,7 @@ static void resv_map_release(struct kref *ref) static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - if (!(vma->vm_flags & VM_SHARED)) + if (!(vma->vm_flags & VM_MAYSHARE)) return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); return NULL; @@ -325,7 +325,7 @@ static struct resv_map *vma_resv_map(struct vm_area_struct *vma) static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - VM_BUG_ON(vma->vm_flags & VM_SHARED); + VM_BUG_ON(vma->vm_flags & VM_MAYSHARE); set_vma_private_data(vma, (get_vma_private_data(vma) & HPAGE_RESV_MASK) | (unsigned long)map); @@ -334,7 +334,7 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - VM_BUG_ON(vma->vm_flags & VM_SHARED); + VM_BUG_ON(vma->vm_flags & VM_MAYSHARE); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } @@ -353,7 +353,7 @@ static void decrement_hugepage_resv_vma(struct hstate *h, if (vma->vm_flags & VM_NORESERVE) return; - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { /* Shared mappings always use reserves */ h->resv_huge_pages--; } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { @@ -369,14 +369,14 @@ static void decrement_hugepage_resv_vma(struct hstate *h, void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { VM_BUG_ON(!is_vm_hugetlb_page(vma)); - if (!(vma->vm_flags & VM_SHARED)) + if (!(vma->vm_flags & VM_MAYSHARE)) vma->vm_private_data = (void *)0; } /* Returns true if the VMA has associated reserve pages */ static int vma_has_reserves(struct vm_area_struct *vma) { - if (vma->vm_flags & VM_SHARED) + if (vma->vm_flags & VM_MAYSHARE) return 1; if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return 1; @@ -924,7 +924,7 @@ static long vma_needs_reservation(struct hstate *h, struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { pgoff_t idx = vma_hugecache_offset(h, vma, addr); return region_chg(&inode->i_mapping->private_list, idx, idx + 1); @@ -949,7 +949,7 @@ static void vma_commit_reservation(struct hstate *h, struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { pgoff_t idx = vma_hugecache_offset(h, vma, addr); region_add(&inode->i_mapping->private_list, idx, idx + 1); @@ -1893,7 +1893,7 @@ retry_avoidcopy: * at the time of fork() could consume its reserves on COW instead * of the full address range. */ - if (!(vma->vm_flags & VM_SHARED) && + if (!(vma->vm_flags & VM_MAYSHARE) && is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_page != pagecache_page) outside_reserve = 1; @@ -2000,7 +2000,7 @@ retry: clear_huge_page(page, address, huge_page_size(h)); __SetPageUptodate(page); - if (vma->vm_flags & VM_SHARED) { + if (vma->vm_flags & VM_MAYSHARE) { int err; struct inode *inode = mapping->host; @@ -2104,7 +2104,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, goto out_mutex; } - if (!(vma->vm_flags & VM_SHARED)) + if (!(vma->vm_flags & VM_MAYSHARE)) pagecache_page = hugetlbfs_pagecache_page(h, vma, address); } @@ -2289,7 +2289,7 @@ int hugetlb_reserve_pages(struct inode *inode, * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ - if (!vma || vma->vm_flags & VM_SHARED) + if (!vma || vma->vm_flags & VM_MAYSHARE) chg = region_chg(&inode->i_mapping->private_list, from, to); else { struct resv_map *resv_map = resv_map_alloc(); @@ -2330,7 +2330,7 @@ int hugetlb_reserve_pages(struct inode *inode, * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ - if (!vma || vma->vm_flags & VM_SHARED) + if (!vma || vma->vm_flags & VM_MAYSHARE) region_add(&inode->i_mapping->private_list, from, to); return 0; } -- cgit From 46f7e602fb32e02145ef14f8c0ca6d399f0a96b9 Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Thu, 28 May 2009 14:34:41 -0700 Subject: memcg: fix build warning and avoid checking for mem != null again and again Fix build warning, "mem_cgroup_is_obsolete defined but not used" when CONFIG_DEBUG_VM is not set. Also avoid checking for !mem again and again. Signed-off-by: Nikanth Karthikesan Acked-by: Pekka Enberg Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4a747a27a22f..78eb8552818b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -314,14 +314,6 @@ static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) return mem; } -static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem) -{ - if (!mem) - return true; - return css_is_removed(&mem->css); -} - - /* * Call callback function against all cgroup under hierarchy tree. */ @@ -932,7 +924,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, if (unlikely(!mem)) return 0; - VM_BUG_ON(!mem || mem_cgroup_is_obsolete(mem)); + VM_BUG_ON(css_is_removed(&mem->css)); while (1) { int ret; -- cgit From 55782138e47d9baf2f7d3a7af9e7cf42adf72c56 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 9 Jun 2009 13:43:05 +0800 Subject: tracing/events: convert block trace points to TRACE_EVENT() TRACE_EVENT is a more generic way to define tracepoints. Doing so adds these new capabilities to this tracepoint: - zero-copy and per-cpu splice() tracing - binary tracing without printf overhead - structured logging records exposed under /debug/tracing/events - trace events embedded in function tracer output and other plugins - user-defined, per tracepoint filter expressions ... Cons: - no dev_t info for the output of plug, unplug_timer and unplug_io events. no dev_t info for getrq and sleeprq events if bio == NULL. no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL. This is mainly because we can't get the deivce from a request queue. But this may change in the future. - A packet command is converted to a string in TP_assign, not TP_print. While blktrace do the convertion just before output. Since pc requests should be rather rare, this is not a big issue. - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT has a unique format, which means we have some unused data in a trace entry. The overhead is minimized by using __dynamic_array() instead of __array(). I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing: dd dd + ioctl blktrace dd + TRACE_EVENT (splice) 1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s 2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s 3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s So the overhead of tracing is very small, and no regression when using those trace events vs blktrace. And the binary output of TRACE_EVENT is much smaller than blktrace: # ls -l -h -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out Following are some comparisons between TRACE_EVENT and blktrace: plug: kjournald-480 [000] 303.084981: block_plug: [kjournald] kjournald-480 [000] 303.084981: 8,0 P N [kjournald] unplug_io: kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1 kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1 remap: kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384 kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384 bio_backmerge: kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald] kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald] getrq: kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald] kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald] bash-2066 [001] 1072.953770: 8,0 G N [bash] bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash] rq_complete: konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0] konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0] ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0] ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0] rq_insert: kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald] kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald] Changelog from v2 -> v3: - use the newly introduced __dynamic_array(). Changelog from v1 -> v2: - use __string() instead of __array() to minimize the memory required to store hex dump of rq->cmd(). - support large pc requests. - add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT. - some cleanups. Signed-off-by: Li Zefan LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- mm/bounce.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/bounce.c b/mm/bounce.c index e590272fe7a8..65f5e17e411a 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -14,16 +14,15 @@ #include #include #include -#include #include +#include + #define POOL_SIZE 64 #define ISA_POOL_SIZE 16 static mempool_t *page_pool, *isa_page_pool; -DEFINE_TRACE(block_bio_bounce); - #ifdef CONFIG_HIGHMEM static __init int init_emergency_pool(void) { -- cgit