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 --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index bff1f0d475c..64d8ed2538a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -13,6 +13,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -1321,6 +1322,6 @@ void vmemmap_populate_print_last(void); extern void *alloc_locked_buffer(size_t size); extern void free_locked_buffer(void *buffer, size_t size); -extern void release_locked_buffer(void *buffer, size_t size); +extern void refund_locked_buffer_memory(struct mm_struct *mm, size_t size); #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.3-70-g09d2 From 44bc9dc729e33a4ec6ebed4d0b6c08e8d20b42cf Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 8 Apr 2009 10:47:17 +0200 Subject: mm, x86, ptrace, bts: defer branch trace stopping, cleanup Andrew Morton noticed that mm.h needlessly includes sched.h - remove it. Reported-by: Andrew Morton Signed-off-by: Ingo Molnar --- 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 64d8ed2538a..776b641f37e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -13,7 +13,6 @@ #include #include #include -#include struct mempolicy; struct anon_vma; -- cgit v1.2.3-70-g09d2 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 --- include/linux/mm.h | 1 - mm/mlock.c | 6 ------ 2 files changed, 7 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 776b641f37e..a3963ba23a6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1320,7 +1320,6 @@ int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); extern void *alloc_locked_buffer(size_t size); -extern void free_locked_buffer(void *buffer, size_t size); extern void refund_locked_buffer_memory(struct mm_struct *mm, size_t size); #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/mm/mlock.c b/mm/mlock.c index 749383b442c..28be15ead9c 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 v1.2.3-70-g09d2 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 --- arch/x86/kernel/ptrace.c | 39 ++++++++++++++++++++++++++------------- include/linux/mm.h | 6 ++++-- mm/mlock.c | 36 +++++++++++++++++------------------- 3 files changed, 47 insertions(+), 34 deletions(-) (limited to 'include/linux/mm.h') diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index d5252ae6c52..09ecbde91c1 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -617,17 +617,28 @@ struct bts_context { struct work_struct work; }; -static inline void alloc_bts_buffer(struct bts_context *context, - unsigned int size) +static int alloc_bts_buffer(struct bts_context *context, unsigned int size) { - void *buffer; + void *buffer = NULL; + int err = -ENOMEM; - buffer = alloc_locked_buffer(size); - if (buffer) { - context->buffer = buffer; - context->size = size; - context->mm = get_task_mm(current); - } + err = account_locked_memory(current->mm, current->signal->rlim, size); + if (err < 0) + return err; + + buffer = kzalloc(size, GFP_KERNEL); + if (!buffer) + goto out_refund; + + context->buffer = buffer; + context->size = size; + context->mm = get_task_mm(current); + + return 0; + + out_refund: + refund_locked_memory(current->mm, size); + return err; } static inline void free_bts_buffer(struct bts_context *context) @@ -638,7 +649,7 @@ static inline void free_bts_buffer(struct bts_context *context) kfree(context->buffer); context->buffer = NULL; - refund_locked_buffer_memory(context->mm, context->size); + refund_locked_memory(context->mm, context->size); context->size = 0; mmput(context->mm); @@ -786,13 +797,15 @@ static int ptrace_bts_config(struct task_struct *child, context->tracer = NULL; if ((cfg.flags & PTRACE_BTS_O_ALLOC) && (cfg.size != context->size)) { + int err; + free_bts_buffer(context); if (!cfg.size) return 0; - alloc_bts_buffer(context, cfg.size); - if (!context->buffer) - return -ENOMEM; + err = alloc_bts_buffer(context, cfg.size); + if (err < 0) + return err; } if (cfg.flags & PTRACE_BTS_O_TRACE) diff --git a/include/linux/mm.h b/include/linux/mm.h index a3963ba23a6..009eabd3c21 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -19,6 +19,7 @@ struct anon_vma; struct file_ra_state; struct user_struct; struct writeback_control; +struct rlimit; #ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; @@ -1319,7 +1320,8 @@ int vmemmap_populate_basepages(struct page *start_page, int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); -extern void *alloc_locked_buffer(size_t size); -extern void refund_locked_buffer_memory(struct mm_struct *mm, size_t size); +extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, + size_t size); +extern void refund_locked_memory(struct mm_struct *mm, size_t size); #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/mm/mlock.c b/mm/mlock.c index 28be15ead9c..ac130433c7d 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 v1.2.3-70-g09d2 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 --- Documentation/x86/x86_64/boot-options.txt | 5 --- arch/x86/include/asm/numa_64.h | 3 -- arch/x86/mm/numa_64.c | 5 --- arch/x86/mm/srat_64.c | 63 ++++++---------------------- include/linux/mm.h | 2 - mm/page_alloc.c | 69 ------------------------------- 6 files changed, 12 insertions(+), 135 deletions(-) (limited to 'include/linux/mm.h') diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt index 34c13040a71..2db5893d6c9 100644 --- a/Documentation/x86/x86_64/boot-options.txt +++ b/Documentation/x86/x86_64/boot-options.txt @@ -150,11 +150,6 @@ NUMA Otherwise, the remaining system RAM is allocated to an additional node. - numa=hotadd=percent - Only allow hotadd memory to preallocate page structures upto - percent of already available memory. - numa=hotadd=0 will disable hotadd memory. - ACPI acpi=off Don't enable ACPI diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h index 064ed6df4cb..7feff0648d7 100644 --- a/arch/x86/include/asm/numa_64.h +++ b/arch/x86/include/asm/numa_64.h @@ -17,9 +17,6 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks, extern void numa_init_array(void); extern int numa_off; -extern void srat_reserve_add_area(int nodeid); -extern int hotadd_percent; - extern s16 apicid_to_node[MAX_LOCAL_APIC]; extern unsigned long numa_free_all_bootmem(void); diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index fb61d81a656..a6a93c39523 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -272,9 +272,6 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, bootmap_pages<> PAGE_SHIFT; unsigned long e_pfn = end >> PAGE_SHIFT; - int ret = 0, changed = 0; + int changed = 0; struct bootnode *nd = &nodes_add[node]; /* I had some trouble with strange memory hotadd regions breaking @@ -210,7 +201,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end) mistakes */ if ((signed long)(end - start) < NODE_MIN_SIZE) { printk(KERN_ERR "SRAT: Hotplug area too small\n"); - return -1; + return; } /* This check might be a bit too strict, but I'm keeping it for now. */ @@ -218,12 +209,7 @@ reserve_hotadd(int node, unsigned long start, unsigned long end) printk(KERN_ERR "SRAT: Hotplug area %lu -> %lu has existing memory\n", s_pfn, e_pfn); - return -1; - } - - if (!hotadd_enough_memory(&nodes_add[node])) { - printk(KERN_ERR "SRAT: Hotplug area too large\n"); - return -1; + return; } /* Looks good */ @@ -245,11 +231,9 @@ reserve_hotadd(int node, unsigned long start, unsigned long end) printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n"); } - ret = update_end_of_memory(nd->end); - if (changed) - printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end); - return ret; + printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", + nd->start, nd->end); } /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ @@ -310,13 +294,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) start, end); e820_register_active_regions(node, start >> PAGE_SHIFT, end >> PAGE_SHIFT); - push_node_boundaries(node, nd->start >> PAGE_SHIFT, - nd->end >> PAGE_SHIFT); - if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && - (reserve_hotadd(node, start, end) < 0)) { - /* Ignore hotadd region. Undo damage */ - printk(KERN_NOTICE "SRAT: Hotplug region ignored\n"); + if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) { + update_nodes_add(node, start, end); + /* restore nodes[node] */ *nd = oldnode; if ((nd->start | nd->end) == 0) node_clear(node, nodes_parsed); @@ -510,26 +491,6 @@ static int null_slit_node_compare(int a, int b) } #endif /* CONFIG_NUMA_EMU */ -void __init srat_reserve_add_area(int nodeid) -{ - if (found_add_area && nodes_add[nodeid].end) { - u64 total_mb; - - printk(KERN_INFO "SRAT: Reserving hot-add memory space " - "for node %d at %Lx-%Lx\n", - nodeid, nodes_add[nodeid].start, nodes_add[nodeid].end); - total_mb = (nodes_add[nodeid].end - nodes_add[nodeid].start) - >> PAGE_SHIFT; - total_mb *= sizeof(struct page); - total_mb >>= 20; - printk(KERN_INFO "SRAT: This will cost you %Lu MB of " - "pre-allocated memory.\n", (unsigned long long)total_mb); - reserve_bootmem_node(NODE_DATA(nodeid), nodes_add[nodeid].start, - nodes_add[nodeid].end - nodes_add[nodeid].start, - BOOTMEM_DEFAULT); - } -} - int __node_distance(int a, int b) { int index; diff --git a/include/linux/mm.h b/include/linux/mm.h index bff1f0d475c..511b0986709 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1031,8 +1031,6 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); extern void remove_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); -extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn, - unsigned long end_pfn); extern void remove_all_active_ranges(void); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fe753ecf2aa..474c7e9dd51 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 v1.2.3-70-g09d2 From e0a94c2a63f2644826069044649669b5e7ca75d3 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 3 Jun 2009 16:04:31 -0400 Subject: security: use mmap_min_addr indepedently of security models This patch removes the dependency of mmap_min_addr on CONFIG_SECURITY. It also sets a default mmap_min_addr of 4096. mmapping of addresses below 4096 will only be possible for processes with CAP_SYS_RAWIO. Signed-off-by: Christoph Lameter Acked-by: Eric Paris Looks-ok-by: Linus Torvalds Signed-off-by: James Morris --- include/linux/mm.h | 2 -- include/linux/security.h | 2 ++ kernel/sysctl.c | 2 -- mm/Kconfig | 19 +++++++++++++++++++ mm/mmap.c | 3 +++ security/Kconfig | 22 +--------------------- security/security.c | 3 --- 7 files changed, 25 insertions(+), 28 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index bff1f0d475c..0c21af6abff 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -580,12 +580,10 @@ static inline void set_page_links(struct page *page, enum zone_type zone, */ static inline unsigned long round_hint_to_min(unsigned long hint) { -#ifdef CONFIG_SECURITY hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); -#endif return hint; } diff --git a/include/linux/security.h b/include/linux/security.h index d5fd6163606..5eff459b383 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2197,6 +2197,8 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot, unsigned long addr, unsigned long addr_only) { + if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO)) + return -EACCES; return 0; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 149581fb48a..45bd711a242 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1237,7 +1237,6 @@ static struct ctl_table vm_table[] = { .strategy = &sysctl_jiffies, }, #endif -#ifdef CONFIG_SECURITY { .ctl_name = CTL_UNNUMBERED, .procname = "mmap_min_addr", @@ -1246,7 +1245,6 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &proc_doulongvec_minmax, }, -#endif #ifdef CONFIG_NUMA { .ctl_name = CTL_UNNUMBERED, diff --git a/mm/Kconfig b/mm/Kconfig index c2b57d81e15..71830ba7b98 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -226,6 +226,25 @@ config HAVE_MLOCKED_PAGE_BIT config MMU_NOTIFIER bool +config DEFAULT_MMAP_MIN_ADDR + int "Low address space to protect from user allocation" + default 4096 + help + This is the portion of low virtual memory which should be protected + from userspace allocation. Keeping a user from writing to low pages + can help reduce the impact of kernel NULL pointer bugs. + + For most ia64, ppc64 and x86 users with lots of address space + a value of 65536 is reasonable and should cause no problems. + On arm and other archs it should not be higher than 32768. + Programs which use vm86 functionality would either need additional + permissions from either the LSM or the capabilities module or have + this protection disabled. + + This value can be changed after boot using the + /proc/sys/vm/mmap_min_addr tunable. + + config NOMMU_INITIAL_TRIM_EXCESS int "Turn on mmap() excess space trimming before booting" depends on !MMU diff --git a/mm/mmap.c b/mm/mmap.c index 6b7b1a95944..2b43fa1aa3c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -87,6 +87,9 @@ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; struct percpu_counter vm_committed_as; +/* amount of vm to protect from userspace access */ +unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; + /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to diff --git a/security/Kconfig b/security/Kconfig index bb244774e9d..d23c839038f 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -110,28 +110,8 @@ config SECURITY_ROOTPLUG See for more information about this module. - - If you are unsure how to answer this question, answer N. - -config SECURITY_DEFAULT_MMAP_MIN_ADDR - int "Low address space to protect from user allocation" - depends on SECURITY - default 0 - help - This is the portion of low virtual memory which should be protected - from userspace allocation. Keeping a user from writing to low pages - can help reduce the impact of kernel NULL pointer bugs. - - For most ia64, ppc64 and x86 users with lots of address space - a value of 65536 is reasonable and should cause no problems. - On arm and other archs it should not be higher than 32768. - Programs which use vm86 functionality would either need additional - permissions from either the LSM or the capabilities module or have - this protection disabled. - - This value can be changed after boot using the - /proc/sys/vm/mmap_min_addr tunable. + If you are unsure how to answer this question, answer N. source security/selinux/Kconfig source security/smack/Kconfig diff --git a/security/security.c b/security/security.c index 5284255c5cd..dc7674fbfc7 100644 --- a/security/security.c +++ b/security/security.c @@ -26,9 +26,6 @@ extern void security_fixup_ops(struct security_operations *ops); struct security_operations *security_ops; /* Initialized to NULL */ -/* amount of vm to protect from userspace access */ -unsigned long mmap_min_addr = CONFIG_SECURITY_DEFAULT_MMAP_MIN_ADDR; - static inline int verify(struct security_operations *ops) { /* verify the security_operations structure exists */ -- cgit v1.2.3-70-g09d2 From 465a454f254ee2ff7acc4aececbe31f8af046bc0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Jun 2009 12:31:37 +0200 Subject: x86, mm: Add __get_user_pages_fast() Introduce a gup_fast() variant which is usable from IRQ/NMI context. Signed-off-by: Peter Zijlstra CC: Nick Piggin Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/mm/gup.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm.h | 6 ++++++ 2 files changed, 62 insertions(+) (limited to 'include/linux/mm.h') diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 6340cef6798..697d5727c11 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -219,6 +219,62 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +/* + * Like get_user_pages_fast() except its IRQ-safe in that it won't fall + * back to the regular GUP. + */ +int __get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next; + unsigned long flags; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, + (void __user *)start, len))) + return 0; + + /* + * XXX: batch / limit 'nr', to avoid large irq off latency + * needs some instrumenting to determine the common sizes used by + * important workloads (eg. DB2), and whether limiting the batch size + * will decrease performance. + * + * It seems like we're in the clear for the moment. Direct-IO is + * the main guy that batches up lots of get_user_pages, and even + * they are limited to 64-at-a-time which is not so many. + */ + /* + * This doesn't prevent pagetable teardown, but does prevent + * the pagetables and pages from being freed on x86. + * + * So long as we atomically load page table pointers versus teardown + * (which we do on x86, with the above PAE exception), we can follow the + * address down to the the page and take a ref on it. + */ + local_irq_save(flags); + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + break; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + break; + } while (pgdp++, addr = next, addr != end); + local_irq_restore(flags); + + return nr; +} + /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address diff --git a/include/linux/mm.h b/include/linux/mm.h index ad613ed66ab..b457bc047ab 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -862,6 +862,12 @@ extern int mprotect_fixup(struct vm_area_struct *vma, int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); +/* + * doesn't attempt to fault and will return short. + */ +int __get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages); + /* * A callback you can register to apply pressure to ageable caches. * -- cgit v1.2.3-70-g09d2 From d30a11004e3411909f2448546f036a011978062e Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Tue, 16 Jun 2009 15:31:30 -0700 Subject: readahead: record mmap read-around states in file_ra_state Mmap read-around now shares the same code style and data structure with readahead code. This also removes do_page_cache_readahead(). Its last user, mmap read-around, has been changed to call ra_submit(). The no-readahead-if-congested logic is dumped by the way. Users will be pretty sensitive about the slow loading of executables. So it's unfavorable to disabled mmap read-around on a congested queue. [akpm@linux-foundation.org: coding-style fixes] Cc: Nick Piggin Signed-off-by: Fengguang Wu Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +++-- mm/filemap.c | 12 +++++++----- mm/readahead.c | 23 ++--------------------- 3 files changed, 12 insertions(+), 28 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index ad613ed66ab..33da7f53884 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1178,8 +1178,6 @@ void task_dirty_inc(struct task_struct *tsk); #define VM_MAX_READAHEAD 128 /* kbytes */ #define VM_MIN_READAHEAD 16 /* kbytes (includes current page) */ -int do_page_cache_readahead(struct address_space *mapping, struct file *filp, - pgoff_t offset, unsigned long nr_to_read); int force_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read); @@ -1197,6 +1195,9 @@ void page_cache_async_readahead(struct address_space *mapping, unsigned long size); unsigned long max_sane_readahead(unsigned long nr); +unsigned long ra_submit(struct file_ra_state *ra, + struct address_space *mapping, + struct file *filp); /* Do stack extension */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); diff --git a/mm/filemap.c b/mm/filemap.c index 5c0c6518f34..734891d0663 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1488,13 +1488,15 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma, if (ra->mmap_miss > MMAP_LOTSAMISS) return; + /* + * mmap read-around + */ ra_pages = max_sane_readahead(ra->ra_pages); if (ra_pages) { - pgoff_t start = 0; - - if (offset > ra_pages / 2) - start = offset - ra_pages / 2; - do_page_cache_readahead(mapping, file, start, ra_pages); + ra->start = max_t(long, 0, offset - ra_pages/2); + ra->size = ra_pages; + ra->async_size = 0; + ra_submit(ra, mapping, file); } } diff --git a/mm/readahead.c b/mm/readahead.c index d7c6e143a12..a7f01fcce9e 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -133,15 +133,12 @@ out: } /* - * do_page_cache_readahead actually reads a chunk of disk. It allocates all + * __do_page_cache_readahead() actually reads a chunk of disk. It allocates all * the pages first, then submits them all for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. * * Returns the number of pages requested, or the maximum amount of I/O allowed. - * - * do_page_cache_readahead() returns -1 if it encountered request queue - * congestion. */ static int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, @@ -231,22 +228,6 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, return ret; } -/* - * This version skips the IO if the queue is read-congested, and will tell the - * block layer to abandon the readahead if request allocation would block. - * - * force_page_cache_readahead() will ignore queue congestion and will block on - * request queues. - */ -int do_page_cache_readahead(struct address_space *mapping, struct file *filp, - pgoff_t offset, unsigned long nr_to_read) -{ - if (bdi_read_congested(mapping->backing_dev_info)) - return -1; - - return __do_page_cache_readahead(mapping, filp, offset, nr_to_read, 0); -} - /* * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a * sensible upper limit. @@ -260,7 +241,7 @@ unsigned long max_sane_readahead(unsigned long nr) /* * Submit IO for the read-ahead request in file_ra_state. */ -static unsigned long ra_submit(struct file_ra_state *ra, +unsigned long ra_submit(struct file_ra_state *ra, struct address_space *mapping, struct file *filp) { int actual; -- cgit v1.2.3-70-g09d2 From d2bf6be8ab63aa84e6149aac934649aadf3828b1 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 16 Jun 2009 15:31:39 -0700 Subject: mm: clean up get_user_pages_fast() documentation Move more documentation for get_user_pages_fast into the new kerneldoc comment. Add some comments for get_user_pages as well. Also, move get_user_pages_fast declaration up to get_user_pages. It wasn't there initially because it was once a static inline function. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Nick Piggin Cc: Andy Grover Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 20 +++++--------------- mm/memory.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ mm/util.c | 16 ++++++++++++---- 3 files changed, 67 insertions(+), 19 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 33da7f53884..a880161a385 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -824,8 +824,11 @@ static inline int handle_mm_fault(struct mm_struct *mm, extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); -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); +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); +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned long offset); @@ -849,19 +852,6 @@ extern int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); -/* - * 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); - /* * A callback you can register to apply pressure to ageable caches. * diff --git a/mm/memory.c b/mm/memory.c index 4126dd16778..891bad0613f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1360,6 +1360,56 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, return i; } +/** + * get_user_pages() - pin user pages in memory + * @tsk: task_struct of target task + * @mm: mm_struct of target mm + * @start: starting user address + * @len: number of pages from start to pin + * @write: whether pages will be written to by the caller + * @force: whether to force write access even if user mapping is + * readonly. This will result in the page being COWed even + * in MAP_SHARED mappings. You do not want this. + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. Or NULL, if caller + * only intends to ensure the pages are faulted in. + * @vmas: array of pointers to vmas corresponding to each page. + * Or NULL if the caller does not require them. + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If len is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. Each page returned must be released + * with a put_page() call when it is finished with. vmas will only + * remain valid while mmap_sem is held. + * + * Must be called with mmap_sem held for read or write. + * + * get_user_pages walks a process's page tables and takes a reference to + * each struct page that each user address corresponds to at a given + * instant. That is, it takes the page that would be accessed if a user + * thread accesses the given user virtual address at that instant. + * + * This does not guarantee that the page exists in the user mappings when + * get_user_pages returns, and there may even be a completely different + * page there in some cases (eg. if mmapped pagecache has been invalidated + * and subsequently re faulted). However it does guarantee that the page + * won't be freed completely. And mostly callers simply care that the page + * contains data that was valid *at some point in time*. Typically, an IO + * or similar operation cannot guarantee anything stronger anyway because + * locks can't be held over the syscall boundary. + * + * If write=0, the page must not be written to. If the page is written to, + * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called + * after the page is finished with, and before put_page is called. + * + * get_user_pages is typically used for fewer-copy IO operations, to get a + * handle on the memory by some means other than accesses via the user virtual + * addresses. The pages may be submitted for DMA to devices or accessed via + * their kernel linear mapping (via the kmap APIs). Care should be taken to + * use the correct cache flushing APIs. + * + * See also get_user_pages_fast, for performance critical applications. + */ 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) diff --git a/mm/util.c b/mm/util.c index abc65aa7cdf..d5d2213728c 100644 --- a/mm/util.c +++ b/mm/util.c @@ -233,13 +233,21 @@ void arch_pick_mmap_layout(struct mm_struct *mm) * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * * Returns number of pages pinned. This may be fewer than the number * requested. If nr_pages is 0 or negative, returns 0. If no pages * were pinned, returns -errno. + * + * get_user_pages_fast provides equivalent functionality to get_user_pages, + * operating on current and current->mm, with force=0 and vma=NULL. However + * unlike get_user_pages, it must be called without mmap_sem held. + * + * get_user_pages_fast may take mmap_sem and page table locks, so no + * assumptions can be made about lack of 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 so + * callers need to carefully consider what to use. On many architectures, + * get_user_pages_fast simply falls back to get_user_pages. */ int __attribute__((weak)) get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) -- cgit v1.2.3-70-g09d2 From 6484eb3e2a81807722c5f28efef94d8338b7b996 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 16 Jun 2009 15:31:54 -0700 Subject: page allocator: do not check NUMA node ID when the caller knows the node is valid Callers of alloc_pages_node() can optionally specify -1 as a node to mean "allocate from the current node". However, a number of the callers in fast paths know for a fact their node is valid. To avoid a comparison and branch, this patch adds alloc_pages_exact_node() that only checks the nid with VM_BUG_ON(). Callers that know their node is valid are then converted. Signed-off-by: Mel Gorman Reviewed-by: Christoph Lameter Reviewed-by: KOSAKI Motohiro Reviewed-by: Pekka Enberg Acked-by: Paul Mundt [for the SLOB NUMA bits] Cc: Peter Zijlstra Cc: Nick Piggin Cc: Dave Hansen Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/hp/common/sba_iommu.c | 2 +- arch/ia64/kernel/mca.c | 3 +-- arch/ia64/kernel/uncached.c | 3 ++- arch/ia64/sn/pci/pci_dma.c | 3 ++- arch/powerpc/platforms/cell/ras.c | 4 ++-- arch/x86/kvm/vmx.c | 2 +- drivers/misc/sgi-gru/grufile.c | 2 +- drivers/misc/sgi-xp/xpc_uv.c | 2 +- include/linux/gfp.h | 9 +++++++++ include/linux/mm.h | 1 - kernel/profile.c | 8 ++++---- mm/filemap.c | 2 +- mm/hugetlb.c | 4 ++-- mm/mempolicy.c | 2 +- mm/migrate.c | 2 +- mm/slab.c | 4 ++-- mm/slob.c | 4 ++-- 17 files changed, 33 insertions(+), 24 deletions(-) (limited to 'include/linux/mm.h') diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 56ceb68eb99..fe63b2dc9d0 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -1131,7 +1131,7 @@ sba_alloc_coherent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp #ifdef CONFIG_NUMA { struct page *page; - page = alloc_pages_node(ioc->node == MAX_NUMNODES ? + page = alloc_pages_exact_node(ioc->node == MAX_NUMNODES ? numa_node_id() : ioc->node, flags, get_order(size)); diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 8f33a884042..5b17bd40227 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -1829,8 +1829,7 @@ ia64_mca_cpu_init(void *cpu_data) data = mca_bootmem(); first_time = 0; } else - data = page_address(alloc_pages_node(numa_node_id(), - GFP_KERNEL, get_order(sz))); + data = __get_free_pages(GFP_KERNEL, get_order(sz)); if (!data) panic("Could not allocate MCA memory for cpu %d\n", cpu); diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c index 8eff8c1d40a..6ba72ab42fc 100644 --- a/arch/ia64/kernel/uncached.c +++ b/arch/ia64/kernel/uncached.c @@ -98,7 +98,8 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid) /* attempt to allocate a granule's worth of cached memory pages */ - page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + page = alloc_pages_exact_node(nid, + GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, IA64_GRANULE_SHIFT-PAGE_SHIFT); if (!page) { mutex_unlock(&uc_pool->add_chunk_mutex); diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index d876423e4e7..98b684928e1 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -90,7 +90,8 @@ static void *sn_dma_alloc_coherent(struct device *dev, size_t size, */ node = pcibus_to_node(pdev->bus); if (likely(node >=0)) { - struct page *p = alloc_pages_node(node, flags, get_order(size)); + struct page *p = alloc_pages_exact_node(node, + flags, get_order(size)); if (likely(p)) cpuaddr = page_address(p); diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c index 296b5268754..5e0a191764f 100644 --- a/arch/powerpc/platforms/cell/ras.c +++ b/arch/powerpc/platforms/cell/ras.c @@ -122,8 +122,8 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order) area->nid = nid; area->order = order; - area->pages = alloc_pages_node(area->nid, GFP_KERNEL | GFP_THISNODE, - area->order); + area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE, + area->order); if (!area->pages) { printk(KERN_WARNING "%s: no page on node %d\n", diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 32d6ae8fb60..e770bf349ec 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1277,7 +1277,7 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) struct page *pages; struct vmcs *vmcs; - pages = alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); + pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order); if (!pages) return NULL; vmcs = page_address(pages); diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c index bbefe77c67a..3ce2920e2bf 100644 --- a/drivers/misc/sgi-gru/grufile.c +++ b/drivers/misc/sgi-gru/grufile.c @@ -302,7 +302,7 @@ static int gru_init_tables(unsigned long gru_base_paddr, void *gru_base_vaddr) pnode = uv_node_to_pnode(nid); if (bid < 0 || gru_base[bid]) continue; - page = alloc_pages_node(nid, GFP_KERNEL, order); + page = alloc_pages_exact_node(nid, GFP_KERNEL, order); if (!page) goto fail; gru_base[bid] = page_address(page); diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 9172fcdee4e..c76677afda1 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -232,7 +232,7 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name, mq->mmr_blade = uv_cpu_to_blade_id(cpu); nid = cpu_to_node(cpu); - page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, + page = alloc_pages_exact_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, pg_order); if (page == NULL) { dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d " diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c2d3fe03b5d..4efa33088a8 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -5,6 +5,7 @@ #include #include #include +#include struct vm_area_struct; @@ -192,6 +193,14 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); } +static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask, + unsigned int order) +{ + VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); + + return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); +} + #ifdef CONFIG_NUMA extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order); diff --git a/include/linux/mm.h b/include/linux/mm.h index a880161a385..7b548e7cfbd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -7,7 +7,6 @@ #include #include -#include #include #include #include diff --git a/kernel/profile.c b/kernel/profile.c index 28cf26ad2d2..69911b5745e 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -365,7 +365,7 @@ static int __cpuinit profile_cpu_callback(struct notifier_block *info, node = cpu_to_node(cpu); per_cpu(cpu_profile_flip, cpu) = 0; if (!per_cpu(cpu_profile_hits, cpu)[1]) { - page = alloc_pages_node(node, + page = alloc_pages_exact_node(node, GFP_KERNEL | __GFP_ZERO, 0); if (!page) @@ -373,7 +373,7 @@ static int __cpuinit profile_cpu_callback(struct notifier_block *info, per_cpu(cpu_profile_hits, cpu)[1] = page_address(page); } if (!per_cpu(cpu_profile_hits, cpu)[0]) { - page = alloc_pages_node(node, + page = alloc_pages_exact_node(node, GFP_KERNEL | __GFP_ZERO, 0); if (!page) @@ -564,14 +564,14 @@ static int create_hash_tables(void) int node = cpu_to_node(cpu); struct page *page; - page = alloc_pages_node(node, + page = alloc_pages_exact_node(node, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, 0); if (!page) goto out_cleanup; per_cpu(cpu_profile_hits, cpu)[1] = (struct profile_hit *)page_address(page); - page = alloc_pages_node(node, + page = alloc_pages_exact_node(node, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE, 0); if (!page) diff --git a/mm/filemap.c b/mm/filemap.c index 6846a902f5c..22396713feb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -521,7 +521,7 @@ struct page *__page_cache_alloc(gfp_t gfp) { if (cpuset_do_page_mem_spread()) { int n = cpuset_mem_spread_node(); - return alloc_pages_node(n, gfp, 0); + return alloc_pages_exact_node(n, gfp, 0); } return alloc_pages(gfp, 0); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e83ad2c9228..2f8241f300f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -630,7 +630,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) if (h->order >= MAX_ORDER) return NULL; - page = alloc_pages_node(nid, + page = alloc_pages_exact_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); @@ -649,7 +649,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) * Use a helper variable to find the next node and then * copy it back to hugetlb_next_nid afterwards: * otherwise there's a window in which a racer might - * pass invalid nid MAX_NUMNODES to alloc_pages_node. + * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node. * But we don't need to use a spin_lock here: it really * doesn't matter if occasionally a racer chooses the * same nid as we do. Move nid forward in the mask even diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 46bdf9ddf2b..e08e2c4da63 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -803,7 +803,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, static struct page *new_node_page(struct page *page, unsigned long node, int **x) { - return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0); + return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0); } /* diff --git a/mm/migrate.c b/mm/migrate.c index 068655d8f88..5a24923e7fd 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -802,7 +802,7 @@ static struct page *new_page_node(struct page *p, unsigned long private, *result = &pm->status; - return alloc_pages_node(pm->node, + return alloc_pages_exact_node(pm->node, GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0); } diff --git a/mm/slab.c b/mm/slab.c index 18e3164de09..bb3254c95cd 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1707,7 +1707,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) if (cachep->flags & SLAB_RECLAIM_ACCOUNT) flags |= __GFP_RECLAIMABLE; - page = alloc_pages_node(nodeid, flags, cachep->gfporder); + page = alloc_pages_exact_node(nodeid, flags, cachep->gfporder); if (!page) return NULL; @@ -3261,7 +3261,7 @@ retry: if (local_flags & __GFP_WAIT) local_irq_enable(); kmem_flagcheck(cache, flags); - obj = kmem_getpages(cache, local_flags, -1); + obj = kmem_getpages(cache, local_flags, numa_node_id()); if (local_flags & __GFP_WAIT) local_irq_disable(); if (obj) { diff --git a/mm/slob.c b/mm/slob.c index 12f26149992..64f6db1943b 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -46,7 +46,7 @@ * NUMA support in SLOB is fairly simplistic, pushing most of the real * logic down to the page allocator, and simply doing the node accounting * on the upper levels. In the event that a node id is explicitly - * provided, alloc_pages_node() with the specified node id is used + * provided, alloc_pages_exact_node() with the specified node id is used * instead. The common case (or when the node id isn't explicitly provided) * will default to the current node, as per numa_node_id(). * @@ -244,7 +244,7 @@ static void *slob_new_pages(gfp_t gfp, int order, int node) #ifdef CONFIG_NUMA if (node != -1) - page = alloc_pages_node(node, gfp, order); + page = alloc_pages_exact_node(node, gfp, order); else #endif page = alloc_pages(gfp, order); -- cgit v1.2.3-70-g09d2 From 3b6748e2dd69906af3835db4dc9d1c8a3ee4c68c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 16 Jun 2009 15:32:35 -0700 Subject: mm: introduce follow_pfn() Analoguous to follow_phys(), add a helper that looks up the PFN at a user virtual address in an IO mapping or a raw PFN mapping. Signed-off-by: Johannes Weiner Cc: Christoph Hellwig Acked-by: Magnus Damm Cc: Hans Verkuil Cc: Paul Mundt Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/memory.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b548e7cfbd..c80dbd4a62c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -792,6 +792,8 @@ 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 follow_pfn(struct vm_area_struct *vma, unsigned long address, + unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, diff --git a/mm/memory.c b/mm/memory.c index 24ff20480bb..d5d1653d60a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3140,6 +3140,35 @@ out: return -EINVAL; } +/** + * follow_pfn - look up PFN at a user virtual address + * @vma: memory mapping + * @address: user virtual address + * @pfn: location to store found PFN + * + * Only IO mappings and raw PFN mappings are allowed. + * + * Returns zero and the pfn at @pfn on success, -ve otherwise. + */ +int follow_pfn(struct vm_area_struct *vma, unsigned long address, + unsigned long *pfn) +{ + int ret = -EINVAL; + spinlock_t *ptl; + pte_t *ptep; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return ret; + + ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); + if (ret) + return ret; + *pfn = pte_pfn(*ptep); + pte_unmap_unlock(ptep, ptl); + return 0; +} +EXPORT_SYMBOL(follow_pfn); + #ifdef CONFIG_HAVE_IOREMAP_PROT int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, -- cgit v1.2.3-70-g09d2 From bc75d33f0fc1d56e734db1f56d3cfc8097b8e0cf Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 16 Jun 2009 15:32:48 -0700 Subject: page-allocator: clean up functions related to pages_min Change the names of two functions. It doesn't affect behavior. Presently, setup_per_zone_pages_min() changes low, high of zone as well as min. So a better name is setup_per_zone_wmarks(). That's because Mel changed zone->pages_[hig/low/min] to zone->watermark array in "page allocator: replace the watermark-related union in struct zone with a watermark[] array". * setup_per_zone_pages_min => setup_per_zone_wmarks Of course, we have to change init_per_zone_pages_min, too. There are not pages_min any more. * init_per_zone_pages_min => init_per_zone_wmark_min [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Minchan Kim Acked-by: Mel Gorman Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- mm/memory_hotplug.c | 2 +- mm/page_alloc.c | 17 +++++++++-------- 3 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index c80dbd4a62c..6e11cda1ba0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1052,7 +1052,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn); extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context); -extern void setup_per_zone_pages_min(void); +extern void setup_per_zone_wmarks(void); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(void); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c083cf5fd6d..037291e15b2 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -422,7 +422,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) zone->present_pages += onlined_pages; zone->zone_pgdat->node_present_pages += onlined_pages; - setup_per_zone_pages_min(); + setup_per_zone_wmarks(); if (onlined_pages) { kswapd_run(zone_to_nid(zone)); node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5b09488d0f5..8629c84fd9b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4396,12 +4396,13 @@ static void setup_per_zone_lowmem_reserve(void) } /** - * setup_per_zone_pages_min - called when min_free_kbytes changes. + * setup_per_zone_wmarks - called when min_free_kbytes changes + * or when memory is hot-added * - * Ensures that the pages_{min,low,high} values for each zone are set correctly - * with respect to min_free_kbytes. + * Ensures that the watermark[min,low,high] values for each zone are set + * correctly with respect to min_free_kbytes. */ -void setup_per_zone_pages_min(void) +void setup_per_zone_wmarks(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; @@ -4519,7 +4520,7 @@ static void __init setup_per_zone_inactive_ratio(void) * 8192MB: 11584k * 16384MB: 16384k */ -static int __init init_per_zone_pages_min(void) +static int __init init_per_zone_wmark_min(void) { unsigned long lowmem_kbytes; @@ -4530,12 +4531,12 @@ static int __init init_per_zone_pages_min(void) min_free_kbytes = 128; if (min_free_kbytes > 65536) min_free_kbytes = 65536; - setup_per_zone_pages_min(); + setup_per_zone_wmarks(); setup_per_zone_lowmem_reserve(); setup_per_zone_inactive_ratio(); return 0; } -module_init(init_per_zone_pages_min) +module_init(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so @@ -4547,7 +4548,7 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, { proc_dointvec(table, write, file, buffer, length, ppos); if (write) - setup_per_zone_pages_min(); + setup_per_zone_wmarks(); return 0; } -- cgit v1.2.3-70-g09d2 From 96cb4df5ddf5e6d5785b5acd4003e3689b87f896 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 16 Jun 2009 15:32:49 -0700 Subject: page-allocator: add inactive ratio calculation function of each zone Factor the per-zone arithemetic inside setup_per_zone_inactive_ratio()'s loop into a a separate function, calculate_zone_inactive_ratio(). This function will be used in a later patch [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Minchan Kim Reviewed-by: KOSAKI Motohiro Cc: Rik van Riel Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + mm/page_alloc.c | 28 ++++++++++++++++------------ 2 files changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e11cda1ba0..f0473a88ca2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1053,6 +1053,7 @@ extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context); extern void setup_per_zone_wmarks(void); +extern void calculate_zone_inactive_ratio(struct zone *zone); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(void); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8629c84fd9b..303607f1d32 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4478,22 +4478,26 @@ void setup_per_zone_wmarks(void) * 1TB 101 10GB * 10TB 320 32GB */ -static void __init setup_per_zone_inactive_ratio(void) +void calculate_zone_inactive_ratio(struct zone *zone) { - struct zone *zone; + unsigned int gb, ratio; - for_each_zone(zone) { - unsigned int gb, ratio; + /* Zone size in gigabytes */ + gb = zone->present_pages >> (30 - PAGE_SHIFT); + if (gb) + ratio = int_sqrt(10 * gb); + else + ratio = 1; - /* Zone size in gigabytes */ - gb = zone->present_pages >> (30 - PAGE_SHIFT); - if (gb) - ratio = int_sqrt(10 * gb); - else - ratio = 1; + zone->inactive_ratio = ratio; +} - zone->inactive_ratio = ratio; - } +static void __init setup_per_zone_inactive_ratio(void) +{ + struct zone *zone; + + for_each_zone(zone) + calculate_zone_inactive_ratio(zone); } /* -- cgit v1.2.3-70-g09d2 From 168f5ac668f63dfb64439766e3ef9e866b83719d Mon Sep 17 00:00:00 2001 From: Sergei Trofimovich Date: Tue, 16 Jun 2009 15:33:02 -0700 Subject: mm cleanup: shmem_file_setup: 'char *' -> 'const char *' for name argument As function shmem_file_setup does not modify/allocate/free/pass given filename - mark it as const. Signed-off-by: Sergei Trofimovich Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- mm/shmem.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/mm.h') diff --git a/include/linux/mm.h b/include/linux/mm.h index f0473a88ca2..d88d6fc530a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -724,7 +724,7 @@ static inline int shmem_lock(struct file *file, int lock, return 0; } #endif -struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags); +struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); int shmem_zero_setup(struct vm_area_struct *); diff --git a/mm/shmem.c b/mm/shmem.c index 47ab1918228..e89d7ec18ed 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2612,7 +2612,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page) * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ -struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) +struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) { int error; struct file *file; -- cgit v1.2.3-70-g09d2 From d06063cc221fdefcab86589e79ddfdb7c0e14b63 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 10 Apr 2009 09:01:23 -0700 Subject: Move FAULT_FLAG_xyz into handle_mm_fault() callers This allows the callers to now pass down the full set of FAULT_FLAG_xyz flags to handle_mm_fault(). All callers have been (mechanically) converted to the new calling convention, there's almost certainly room for architectures to clean up their code and then add FAULT_FLAG_RETRY when that support is added. Signed-off-by: Linus Torvalds --- arch/alpha/mm/fault.c | 2 +- arch/arm/mm/fault.c | 2 +- arch/avr32/mm/fault.c | 2 +- arch/cris/mm/fault.c | 2 +- arch/frv/mm/fault.c | 2 +- arch/ia64/mm/fault.c | 2 +- arch/m32r/mm/fault.c | 2 +- arch/m68k/mm/fault.c | 2 +- arch/microblaze/mm/fault.c | 2 +- arch/mips/mm/fault.c | 2 +- arch/mn10300/mm/fault.c | 2 +- arch/parisc/mm/fault.c | 2 +- arch/powerpc/mm/fault.c | 2 +- arch/powerpc/platforms/cell/spu_fault.c | 2 +- arch/s390/lib/uaccess_pt.c | 2 +- arch/s390/mm/fault.c | 2 +- arch/sh/mm/fault_32.c | 2 +- arch/sh/mm/tlbflush_64.c | 2 +- arch/sparc/mm/fault_32.c | 4 ++-- arch/sparc/mm/fault_64.c | 2 +- arch/um/kernel/trap.c | 2 +- arch/x86/mm/fault.c | 2 +- arch/xtensa/mm/fault.c | 2 +- include/linux/mm.h | 4 ++-- mm/memory.c | 8 ++++---- 25 files changed, 30 insertions(+), 30 deletions(-) (limited to 'include/linux/mm.h') diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 4829f96585b..00a31deaa96 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -146,7 +146,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, /* If for any reason at all we couldn't handle the fault, make sure we exit gracefully rather than endlessly redo the fault. */ - fault = handle_mm_fault(mm, vma, address, cause > 0); + fault = handle_mm_fault(mm, vma, address, cause > 0 ? FAULT_FLAG_WRITE : 0); up_read(&mm->mmap_sem); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 0455557a289..6fdcbb70982 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -208,7 +208,7 @@ good_area: * than endlessly redo the fault. */ survive: - fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, fsr & (1 << 11)); + fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, (fsr & (1 << 11)) ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index 62d4abbaa65..b61d86d3deb 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -133,7 +133,7 @@ good_area: * fault. */ survive: - fault = handle_mm_fault(mm, vma, address, writeaccess); + fault = handle_mm_fault(mm, vma, address, writeaccess ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index c4c76db90f9..f925115e325 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -163,7 +163,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs, * the fault. */ - fault = handle_mm_fault(mm, vma, address, writeaccess & 1); + fault = handle_mm_fault(mm, vma, address, (writeaccess & 1) ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 05093d41d98..30f5d100a81 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -163,7 +163,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, ear0, write); + fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 23088bed111..19261a99e62 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -154,7 +154,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re * sure we exit gracefully rather than endlessly redo the * fault. */ - fault = handle_mm_fault(mm, vma, address, (mask & VM_WRITE) != 0); + fault = handle_mm_fault(mm, vma, address, (mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { /* * We ran out of memory, or some other thing happened diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index 4a71df4c1b3..7274b47f4c2 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -196,7 +196,7 @@ survive: */ addr = (address & PAGE_MASK); set_thread_fault_code(error_code); - fault = handle_mm_fault(mm, vma, addr, write); + fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index f493f03231d..d0e35cf99fc 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -155,7 +155,7 @@ good_area: */ survive: - fault = handle_mm_fault(mm, vma, address, write); + fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); #ifdef DEBUG printk("handle_mm_fault returns %d\n",fault); #endif diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index 5e67cd1fab4..956607a63f4 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -232,7 +232,7 @@ good_area: * the fault. */ survive: - fault = handle_mm_fault(mm, vma, address, is_write); + fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 55767ad9f00..6751ce9ede9 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -102,7 +102,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, write); + fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 33cf25025da..a62e1e138bc 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -258,7 +258,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, write); + fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 92c7fa4ecc3..bfb6dd6ab38 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -202,7 +202,7 @@ good_area: * fault. */ - fault = handle_mm_fault(mm, vma, address, (acc_type & VM_WRITE) != 0); + fault = handle_mm_fault(mm, vma, address, (acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { /* * We hit a shared mapping outside of the file, or some diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 5beffc8f481..830bef0a113 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -302,7 +302,7 @@ good_area: * the fault. */ survive: - ret = handle_mm_fault(mm, vma, address, is_write); + ret = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0); if (unlikely(ret & VM_FAULT_ERROR)) { if (ret & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/platforms/cell/spu_fault.c index 95d8dadf2d8..d06ba87f1a1 100644 --- a/arch/powerpc/platforms/cell/spu_fault.c +++ b/arch/powerpc/platforms/cell/spu_fault.c @@ -70,7 +70,7 @@ int spu_handle_mm_fault(struct mm_struct *mm, unsigned long ea, } ret = 0; - *flt = handle_mm_fault(mm, vma, ea, is_write); + *flt = handle_mm_fault(mm, vma, ea, is_write ? FAULT_FLAG_WRITE : 0); if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index b0b84c35b0a..cb5d59eab0e 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -66,7 +66,7 @@ static int __handle_fault(struct mm_struct *mm, unsigned long address, } survive: - fault = handle_mm_fault(mm, vma, address, write_access); + fault = handle_mm_fault(mm, vma, address, write_access ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 220a152c836..74eb26bf197 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -352,7 +352,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, write); + fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { up_read(&mm->mmap_sem); diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c index 2c50f80fc33..cc8ddbdf3d7 100644 --- a/arch/sh/mm/fault_32.c +++ b/arch/sh/mm/fault_32.c @@ -133,7 +133,7 @@ good_area: * the fault. */ survive: - fault = handle_mm_fault(mm, vma, address, writeaccess); + fault = handle_mm_fault(mm, vma, address, writeaccess ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sh/mm/tlbflush_64.c b/arch/sh/mm/tlbflush_64.c index 7876997ba19..fcbb6e135ce 100644 --- a/arch/sh/mm/tlbflush_64.c +++ b/arch/sh/mm/tlbflush_64.c @@ -187,7 +187,7 @@ good_area: * the fault. */ survive: - fault = handle_mm_fault(mm, vma, address, writeaccess); + fault = handle_mm_fault(mm, vma, address, writeaccess ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 12e447fc854..a5e30c642ee 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -241,7 +241,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, write); + fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -484,7 +484,7 @@ good_area: if(!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; } - switch (handle_mm_fault(mm, vma, address, write)) { + switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) { case VM_FAULT_SIGBUS: case VM_FAULT_OOM: goto do_sigbus; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 4ab8993b086..e5620b27c8b 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -398,7 +398,7 @@ good_area: goto bad_area; } - fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE)); + fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 7384d8accfe..637c6505dc0 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -65,7 +65,7 @@ good_area: do { int fault; - fault = handle_mm_fault(mm, vma, address, is_write); + fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) { goto out_of_memory; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index c403526d5d1..78a5fff857b 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1113,7 +1113,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault: */ - fault = handle_mm_fault(mm, vma, address, write); + fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { mm_fault_error(regs, error_code, address, fault); diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index bdd860d93f7..bc0733359a8 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -106,7 +106,7 @@ good_area: * the fault. */ survive: - fault = handle_mm_fault(mm, vma, address, is_write); + fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/include/linux/mm.h b/include/linux/mm.h index cf260d848eb..d006e93d5c9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -810,11 +810,11 @@ extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); #ifdef CONFIG_MMU extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, int write_access); + unsigned long address, unsigned int flags); #else static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, - int write_access) + unsigned int flags) { /* should never happen if there's no MMU */ BUG(); diff --git a/mm/memory.c b/mm/memory.c index e6a9700359d..98bcb90d595 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1310,8 +1310,9 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, cond_resched(); while (!(page = follow_page(vma, start, foll_flags))) { int ret; - ret = handle_mm_fault(mm, vma, start, - foll_flags & FOLL_WRITE); + + /* FOLL_WRITE matches FAULT_FLAG_WRITE! */ + ret = handle_mm_fault(mm, vma, start, foll_flags & FOLL_WRITE); if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) return i ? i : -ENOMEM; @@ -2958,13 +2959,12 @@ unlock: * By the time we get here, we already hold the mm semaphore */ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, int write_access) + unsigned long address, unsigned int flags) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - unsigned int flags = write_access ? FAULT_FLAG_WRITE : 0; __set_current_state(TASK_RUNNING); -- cgit v1.2.3-70-g09d2