diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-16 19:50:13 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-16 19:50:13 -0700 |
| commit | 517d08699b250021303f9a7cf0d758b6dc0748ed (patch) | |
| tree | 5e5b0134c3fffb78fe9d8b1641a64ff28fdd7bbc | |
| parent | 8eeee4e2f04fc551f50c9d9847da2d73d7d33728 (diff) | |
| parent | a34601c5d84134055782ee031d58d82f5440e918 (diff) | |
Merge branch 'akpm'
* akpm: (182 commits)
fbdev: bf54x-lq043fb: use kzalloc over kmalloc/memset
fbdev: *bfin*: fix __dev{init,exit} markings
fbdev: *bfin*: drop unnecessary calls to memset
fbdev: bfin-t350mcqb-fb: drop unused local variables
fbdev: blackfin has __raw I/O accessors, so use them in fb.h
fbdev: s1d13xxxfb: add accelerated bitblt functions
tcx: use standard fields for framebuffer physical address and length
fbdev: add support for handoff from firmware to hw framebuffers
intelfb: fix a bug when changing video timing
fbdev: use framebuffer_release() for freeing fb_info structures
radeon: P2G2CLK_ALWAYS_ONb tested twice, should 2nd be P2G2CLK_DAC_ALWAYS_ONb?
s3c-fb: CPUFREQ frequency scaling support
s3c-fb: fix resource releasing on error during probing
carminefb: fix possible access beyond end of carmine_modedb[]
acornfb: remove fb_mmap function
mb862xxfb: use CONFIG_OF instead of CONFIG_PPC_OF
mb862xxfb: restrict compliation of platform driver to PPC
Samsung SoC Framebuffer driver: add Alpha Channel support
atmel-lcdc: fix pixclock upper bound detection
offb: use framebuffer_alloc() to allocate fb_info struct
...
Manually fix up conflicts due to kmemcheck in mm/slab.c
247 files changed, 5666 insertions, 2683 deletions
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c index 7ea231172c8..aa73e72fd79 100644 --- a/Documentation/accounting/getdelays.c +++ b/Documentation/accounting/getdelays.c @@ -246,7 +246,8 @@ void print_ioacct(struct taskstats *t) int main(int argc, char *argv[]) { - int c, rc, rep_len, aggr_len, len2, cmd_type; + int c, rc, rep_len, aggr_len, len2; + int cmd_type = TASKSTATS_CMD_ATTR_UNSPEC; __u16 id; __u32 mypid; diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt index 4ef24501045..396bec3b74e 100644 --- a/Documentation/atomic_ops.txt +++ b/Documentation/atomic_ops.txt @@ -229,10 +229,10 @@ kernel. It is the use of atomic counters to implement reference counting, and it works such that once the counter falls to zero it can be guaranteed that no other entity can be accessing the object: -static void obj_list_add(struct obj *obj) +static void obj_list_add(struct obj *obj, struct list_head *head) { obj->active = 1; - list_add(&obj->list); + list_add(&obj->list, head); } static void obj_list_del(struct obj *obj) diff --git a/Documentation/fb/vesafb.txt b/Documentation/fb/vesafb.txt index ee277dd204b..950d5a658cb 100644 --- a/Documentation/fb/vesafb.txt +++ b/Documentation/fb/vesafb.txt @@ -95,7 +95,7 @@ There is no way to change the vesafb video mode and/or timings after booting linux. If you are not happy with the 60 Hz refresh rate, you have these options: - * configure and load the DOS-Tools for your the graphics board (if + * configure and load the DOS-Tools for the graphics board (if available) and boot linux with loadlin. * use a native driver (matroxfb/atyfb) instead if vesafb. If none is available, write a new one! diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index cd8717a3627..ebff3c10a07 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -1003,11 +1003,13 @@ CHAPTER 3: PER-PROCESS PARAMETERS 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score ------------------------------------------------------ -This file can be used to adjust the score used to select which processes -should be killed in an out-of-memory situation. Giving it a high score will -increase the likelihood of this process being killed by the oom-killer. Valid -values are in the range -16 to +15, plus the special value -17, which disables -oom-killing altogether for this process. +This file can be used to adjust the score used to select which processes should +be killed in an out-of-memory situation. The oom_adj value is a characteristic +of the task's mm, so all threads that share an mm with pid will have the same +oom_adj value. A high value will increase the likelihood of this process being +killed by the oom-killer. Valid values are in the range -16 to +15 as +explained below and a special value of -17, which disables oom-killing +altogether for threads sharing pid's mm. The process to be killed in an out-of-memory situation is selected among all others based on its badness score. This value equals the original memory size of the process @@ -1021,6 +1023,9 @@ the parent's score if they do not share the same memory. Thus forking servers are the prime candidates to be killed. Having only one 'hungry' child will make parent less preferable than the child. +/proc/<pid>/oom_adj cannot be changed for kthreads since they are immune from +oom-killing already. + /proc/<pid>/oom_score shows process' current badness score. The following heuristics are then applied: diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index ad380063077..5578248c18a 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -546,6 +546,10 @@ and is between 256 and 4096 characters. It is defined in the file console=brl,ttyS0 For now, only VisioBraille is supported. + consoleblank= [KNL] The console blank (screen saver) timeout in + seconds. Defaults to 10*60 = 10mins. A value of 0 + disables the blank timer. + coredump_filter= [KNL] Change the default value for /proc/<pid>/coredump_filter. diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 6fab2dcbb4d..c4de6359d44 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -233,8 +233,8 @@ These protections are added to score to judge whether this zone should be used for page allocation or should be reclaimed. In this example, if normal pages (index=2) are required to this DMA zone and -pages_high is used for watermark, the kernel judges this zone should not be -used because pages_free(1355) is smaller than watermark + protection[2] +watermark[WMARK_HIGH] is used for watermark, the kernel judges this zone should +not be used because pages_free(1355) is smaller than watermark + protection[2] (4 + 2004 = 2008). If this protection value is 0, this zone would be used for normal page requirement. If requirement is DMA zone(index=0), protection[0] (=0) is used. @@ -280,9 +280,10 @@ The default value is 65536. min_free_kbytes: This is used to force the Linux VM to keep a minimum number -of kilobytes free. The VM uses this number to compute a pages_min -value for each lowmem zone in the system. Each lowmem zone gets -a number of reserved free pages based proportionally on its size. +of kilobytes free. The VM uses this number to compute a +watermark[WMARK_MIN] value for each lowmem zone in the system. +Each lowmem zone gets a number of reserved free pages based +proportionally on its size. Some minimal amount of memory is needed to satisfy PF_MEMALLOC allocations; if you set this to lower than 1024KB, your system will @@ -314,10 +315,14 @@ min_unmapped_ratio: This is available only on NUMA kernels. -A percentage of the total pages in each zone. Zone reclaim will only -occur if more than this percentage of pages are file backed and unmapped. -This is to insure that a minimal amount of local pages is still available for -file I/O even if the node is overallocated. +This is a percentage of the total pages in each zone. Zone reclaim will +only occur if more than this percentage of pages are in a state that +zone_reclaim_mode allows to be reclaimed. + +If zone_reclaim_mode has the value 4 OR'd, then the percentage is compared +against all file-backed unmapped pages including swapcache pages and tmpfs +files. Otherwise, only unmapped pages backed by normal files but not tmpfs +files and similar are considered. The default is 1 percent. diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile index 6f562f778b2..27479d43a9b 100644 --- a/Documentation/vm/Makefile +++ b/Documentation/vm/Makefile @@ -2,7 +2,7 @@ obj- := dummy.o # List of programs to build -hostprogs-y := slabinfo +hostprogs-y := slabinfo slqbinfo page-types # Tell kbuild to always build the programs always := $(hostprogs-y) diff --git a/Documentation/vm/balance b/Documentation/vm/balance index bd3d31bc491..c46e68cf934 100644 --- a/Documentation/vm/balance +++ b/Documentation/vm/balance @@ -75,15 +75,15 @@ Page stealing from process memory and shm is done if stealing the page would alleviate memory pressure on any zone in the page's node that has fallen below its watermark. -pages_min/pages_low/pages_high/low_on_memory/zone_wake_kswapd: These are -per-zone fields, used to determine when a zone needs to be balanced. When -the number of pages falls below pages_min, the hysteric field low_on_memory -gets set. This stays set till the number of free pages becomes pages_high. -When low_on_memory is set, page allocation requests will try to free some -pages in the zone (providing GFP_WAIT is set in the request). Orthogonal -to this, is the decision to poke kswapd to free some zone pages. That -decision is not hysteresis based, and is done when the number of free -pages is below pages_low; in which case zone_wake_kswapd is also set. +watemark[WMARK_MIN/WMARK_LOW/WMARK_HIGH]/low_on_memory/zone_wake_kswapd: These +are per-zone fields, used to determine when a zone needs to be balanced. When +the number of pages falls below watermark[WMARK_MIN], the hysteric field +low_on_memory gets set. This stays set till the number of free pages becomes +watermark[WMARK_HIGH]. When low_on_memory is set, page allocation requests will +try to free some pages in the zone (providing GFP_WAIT is set in the request). +Orthogonal to this, is the decision to poke kswapd to free some zone pages. +That decision is not hysteresis based, and is done when the number of free +pages is below watermark[WMARK_LOW]; in which case zone_wake_kswapd is also set. (Good) Ideas that I have heard: diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c new file mode 100644 index 00000000000..0833f44ba16 --- /dev/null +++ b/Documentation/vm/page-types.c @@ -0,0 +1,698 @@ +/* + * page-types: Tool for querying page flags + * + * Copyright (C) 2009 Intel corporation + * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com> + */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdint.h> +#include <stdarg.h> +#include <string.h> +#include <getopt.h> +#include <limits.h> +#include <sys/types.h> +#include <sys/errno.h> +#include <sys/fcntl.h> + + +/* + * kernel page flags + */ + +#define KPF_BYTES 8 +#define PROC_KPAGEFLAGS "/proc/kpageflags" + +/* copied from kpageflags_read() */ +#define KPF_LOCKED 0 +#define KPF_ERROR 1 +#define KPF_REFERENCED 2 +#define KPF_UPTODATE 3 +#define KPF_DIRTY 4 +#define KPF_LRU 5 +#define KPF_ACTIVE 6 +#define KPF_SLAB 7 +#define KPF_WRITEBACK 8 +#define KPF_RECLAIM 9 +#define KPF_BUDDY 10 + +/* [11-20] new additions in 2.6.31 */ +#define KPF_MMAP 11 +#define KPF_ANON 12 +#define KPF_SWAPCACHE 13 +#define KPF_SWAPBACKED 14 +#define KPF_COMPOUND_HEAD 15 +#define KPF_COMPOUND_TAIL 16 +#define KPF_HUGE 17 +#define KPF_UNEVICTABLE 18 +#define KPF_NOPAGE 20 + +/* [32-] kernel hacking assistances */ +#define KPF_RESERVED 32 +#define KPF_MLOCKED 33 +#define KPF_MAPPEDTODISK 34 +#define KPF_PRIVATE 35 +#define KPF_PRIVATE_2 36 +#define KPF_OWNER_PRIVATE 37 +#define KPF_ARCH 38 +#define KPF_UNCACHED 39 + +/* [48-] take some arbitrary free slots for expanding overloaded flags + * not part of kernel API + */ +#define KPF_READAHEAD 48 +#define KPF_SLOB_FREE 49 +#define KPF_SLUB_FROZEN 50 +#define KPF_SLUB_DEBUG 51 + +#define KPF_ALL_BITS ((uint64_t)~0ULL) +#define KPF_HACKERS_BITS (0xffffULL << 32) +#define KPF_OVERLOADED_BITS (0xffffULL << 48) +#define BIT(name) (1ULL << KPF_##name) +#define BITS_COMPOUND (BIT(COMPOUND_HEAD) | BIT(COMPOUND_TAIL)) + +static char *page_flag_names[] = { + [KPF_LOCKED] = "L:locked", + [KPF_ERROR] = "E:error", + [KPF_REFERENCED] = "R:referenced", + [KPF_UPTODATE] = "U:uptodate", + [KPF_DIRTY] = "D:dirty", + [KPF_LRU] = "l:lru", + [KPF_ACTIVE] = "A:active", + [KPF_SLAB] = "S:slab", + [KPF_WRITEBACK] = "W:writeback", + [KPF_RECLAIM] = "I:reclaim", + [KPF_BUDDY] = "B:buddy", + + [KPF_MMAP] = "M:mmap", + [KPF_ANON] = "a:anonymous", + [KPF_SWAPCACHE] = "s:swapcache", + [KPF_SWAPBACKED] = "b:swapbacked", + [KPF_COMPOUND_HEAD] = "H:compound_head", + [KPF_COMPOUND_TAIL] = "T:compound_tail", + [KPF_HUGE] = "G:huge", + [KPF_UNEVICTABLE] = "u:unevictable", + [KPF_NOPAGE] = "n:nopage", + + [KPF_RESERVED] = "r:reserved", + [KPF_MLOCKED] = "m:mlocked", + [KPF_MAPPEDTODISK] = "d:mappedtodisk", + [KPF_PRIVATE] = "P:private", + [KPF_PRIVATE_2] = "p:private_2", + [KPF_OWNER_PRIVATE] = "O:owner_private", + [KPF_ARCH] = "h:arch", + [KPF_UNCACHED] = "c:uncached", + + [KPF_READAHEAD] = "I:readahead", + [KPF_SLOB_FREE] = "P:slob_free", + [KPF_SLUB_FROZEN] = "A:slub_frozen", + [KPF_SLUB_DEBUG] = "E:slub_debug", +}; + + +/* + * data structures + */ + +static int opt_raw; /* for kernel developers */ +static int opt_list; /* list pages (in ranges) */ +static int opt_no_summary; /* don't show summary */ +static pid_t opt_pid; /* process to walk */ + +#define MAX_ADDR_RANGES 1024 +static int nr_addr_ranges; +static unsigned long opt_offset[MAX_ADDR_RANGES]; +static unsigned long opt_size[MAX_ADDR_RANGES]; + +#define MAX_BIT_FILTERS 64 +static int nr_bit_filters; +static uint64_t opt_mask[MAX_BIT_FILTERS]; +static uint64_t opt_bits[MAX_BIT_FILTERS]; + +static int page_size; + +#define PAGES_BATCH (64 << 10) /* 64k pages */ +static int kpageflags_fd; +static uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH]; + +#define HASH_SHIFT 13 +#define HASH_SIZE (1 << HASH_SHIFT) +#define HASH_MASK (HASH_SIZE - 1) +#define HASH_KEY(flags) (flags & HASH_MASK) + +static unsigned long total_pages; +static unsigned long nr_pages[HASH_SIZE]; +static uint64_t page_flags[HASH_SIZE]; + + +/* + * helper functions + */ + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +#define min_t(type, x, y) ({ \ + type __min1 = (x); \ + type __min2 = (y); \ + __min1 < __min2 ? __min1 : __min2; }) + +unsigned long pages2mb(unsigned long pages) +{ + return (pages * page_size) >> 20; +} + +void fatal(const char *x, ...) +{ + va_list ap; + + va_start(ap, x); + vfprintf(stderr, x, ap); + va_end(ap); + exit(EXIT_FAILURE); +} + + +/* + * page flag names + */ + +char *page_flag_name(uint64_t flags) +{ + static char buf[65]; + int present; + int i, j; + + for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) { + present = (flags >> i) & 1; + if (!page_flag_names[i]) { + if (present) + fatal("unkown flag bit %d\n", i); + continue; + } + buf[j++] = present ? page_flag_names[i][0] : '_'; + } + + return buf; +} + +char *page_flag_longname(uint64_t flags) +{ + static char buf[1024]; + int i, n; + + for (i = 0, n = 0; i < ARRAY_SIZE(page_flag_names); i++) { + if (!page_flag_names[i]) + continue; + if ((flags >> i) & 1) + n += snprintf(buf + n, sizeof(buf) - n, "%s,", + page_flag_names[i] + 2); + } + if (n) + n--; + buf[n] = '\0'; + + return buf; +} + + +/* + * page list and summary + */ + +void show_page_range(unsigned long offset, uint64_t flags) +{ + static uint64_t flags0; + static unsigned long index; + static unsigned long count; + + if (flags == flags0 && offset == index + count) { + count++; + return; + } + + if (count) + printf("%lu\t%lu\t%s\n", + index, count, page_flag_name(flags0)); + + flags0 = flags; + index = offset; + count = 1; +} + +void show_page(unsigned long offset, uint64_t flags) +{ + printf("%lu\t%s\n", offset, page_flag_name(flags)); +} + +void show_summary(void) +{ + int i; + + printf(" flags\tpage-count MB" + " symbolic-flags\t\t\tlong-symbolic-flags\n"); + + for (i = 0; i < ARRAY_SIZE(nr_pages); i++) { + if (nr_pages[i]) + printf("0x%016llx\t%10lu %8lu %s\t%s\n", + (unsigned long long)page_flags[i], + nr_pages[i], + pages2mb(nr_pages[i]), + page_flag_name(page_flags[i]), + page_flag_longname(page_flags[i])); + } + + printf(" total\t%10lu %8lu\n", + total_pages, pages2mb(total_pages)); +} + + +/* + * page flag filters + */ + +int bit_mask_ok(uint64_t flags) +{ + int i; + + for (i = 0; i < nr_bit_filters; i++) { + if (opt_bits[i] == KPF_ALL_BITS) { + if ((flags & opt_mask[i]) == 0) + return 0; + } else { + if ((flags & opt_mask[i]) != opt_bits[i]) + return 0; + } + } + + return 1; +} + +uint64_t expand_overloaded_flags(uint64_t flags) +{ + /* SLOB/SLUB overload several page flags */ + if (flags & BIT(SLAB)) { + if (flags & BIT(PRIVATE)) + flags ^= BIT(PRIVATE) | BIT(SLOB_FREE); + if (flags & BIT(ACTIVE)) + flags ^= BIT(ACTIVE) | BIT(SLUB_FROZEN); + if (flags & BIT(ERROR)) + flags ^= BIT(ERROR) | BIT(SLUB_DEBUG); + } + + /* PG_reclaim is overloaded as PG_readahead in the read path */ + if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM)) + flags ^= BIT(RECLAIM) | BIT(READAHEAD); + + return flags; +} + +uint64_t well_known_flags(uint64_t flags) +{ + /* hide flags intended only for kernel hacker */ + flags &= ~KPF_HACKERS_BITS; + + /* hide non-hugeTLB compound pages */ + if ((flags & BITS_COMPOUND) && !(flags & BIT(HUGE))) + flags &= ~BITS_COMPOUND; + + return flags; +} + + +/* + * page frame walker + */ + +int hash_slot(uint64_t flags) +{ + int k = HASH_KEY(flags); + int i; + + /* Explicitly reserve slot 0 for flags 0: the following logic + * cannot distinguish an unoccupied slot from slot (flags==0). + */ + if (flags == 0) + return 0; + + /* search through the remaining (HASH_SIZE-1) slots */ + for (i = 1; i < ARRAY_SIZE(page_flags); i++, k++) { + if (!k || k >= ARRAY_SIZE(page_flags)) + k = 1; + if (page_flags[k] == 0) { + page_flags[k] = flags; + return k; + } + if (page_flags[k] == flags) + return k; + } + + fatal("hash table full: bump up HASH_SHIFT?\n"); + exit(EXIT_FAILURE); +} + +void add_page(unsigned long offset, uint64_t flags) +{ + flags = expand_overloaded_flags(flags); + + if (!opt_raw) + flags = well_known_flags(flags); + + if (!bit_mask_ok(flags)) + return; + + if (opt_list == 1) + show_page_range(offset, flags); + else if (opt_list == 2) + show_page(offset, flags); + + nr_pages[hash_slot(flags)]++; + total_pages++; +} + +void walk_pfn(unsigned long index, unsigned long count) +{ + unsigned long batch; + unsigned long n; + unsigned long i; + + if (index > ULONG_MAX / KPF_BYTES) + fatal("index overflow: %lu\n", index); + + lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET); + + while (count) { + batch = min_t(unsigned long, count, PAGES_BATCH); + n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES); + if (n == 0) + break; + if (n < 0) { + perror(PROC_KPAGEFLAGS); + exit(EXIT_FAILURE); + } + + if (n % KPF_BYTES != 0) + fatal("partial read: %lu bytes\n", n); + n = n / KPF_BYTES; + + for (i = 0; i < n; i++) + add_page(index + i, kpageflags_buf[i]); + + index += batch; + count -= batch; + } +} + +void walk_addr_ranges(void) +{ + int i; + + kpageflags_fd = open(PROC_KPAGEFLAGS, O_RDONLY); + if (kpageflags_fd < 0) { + perror(PROC_KPAGEFLAGS); + exit(EXIT_FAILURE); + } + + if (!nr_addr_ranges) + walk_pfn(0, ULONG_MAX); + + for (i = 0; i < nr_addr_ranges; i++) + walk_pfn(opt_offset[i], opt_size[i]); + + close(kpageflags_fd); +} + + +/* + * user interface + */ + +const char *page_flag_type(uint64_t flag) +{ + if (flag & KPF_HACKERS_BITS) + return "(r)"; + if (flag & KPF_OVERLOADED_BITS) + return "(o)"; + return " "; +} + +void usage(void) +{ + int i, j; + + printf( +"page-types [options]\n" +" -r|--raw Raw mode, for kernel developers\n" +" -a|--addr addr-spec Walk a range of pages\n" +" -b|--bits bits-spec Walk pages with specified bits\n" +#if 0 /* planned features */ +" -p|--pid pid Walk process address space\n" +" -f|--file filename Walk file address space\n" +#endif +" -l|--list Show page details in ranges\n" +" -L|--list-each Show page details one by one\n" +" -N|--no-summary Don't show summay info\n" +" -h|--help Show this usage message\n" +"addr-spec:\n" +" N one page at offset N (unit: pages)\n" +" N+M pages range from N to N+M-1\n" +" N,M pages range from N to M-1\n" +" N, pages range from N to end\n" +" ,M pages range from 0 to M\n" +"bits-spec:\n" +" bit1,bit2 (flags & (bit1|bit2)) != 0\n" +" bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1\n" +" bit1,~bit2 (flags & (bit1|bit2)) == bit1\n" +" =bit1,bit2 flags == (bit1|bit2)\n" +"bit-names:\n" + ); + + for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) { + if (!page_flag_names[i]) + continue; + printf("%16s%s", page_flag_names[i] + 2, + page_flag_type(1ULL << i)); + if (++j > 3) { + j = 0; + putchar('\n'); + } + } + printf("\n " + "(r) raw mode bits (o) overloaded bits\n"); +} + +unsigned long long parse_number(const char *str) +{ + unsigned long long n; + + n = strtoll(str, NULL, 0); + + if (n == 0 && str[0] != '0') + fatal("invalid name or number: %s\n", str); + + return n; +} + +void parse_pid(const char *str) +{ + opt_pid = parse_number(str); +} + +void parse_file(const char *name) +{ +} + +void add_addr_range(unsigned long offset, unsigned long size) +{ + if (nr_addr_ranges >= MAX_ADDR_RANGES) + fatal("too much addr ranges\n"); + + opt_offset[nr_addr_ranges] = offset; + opt_size[nr_addr_ranges] = size; + nr_addr_ranges++; +} + +void parse_addr_range(const char *optarg) +{ + unsigned long offset; + unsigned long size; + char *p; + + p = strchr(optarg, ','); + if (!p) + p = strchr(optarg, '+'); + + if (p == optarg) { + offset = 0; + size = parse_number(p + 1); + } else if (p) { + offset = parse_number(optarg); + if (p[1] == '\0') + size = ULONG_MAX; + else { + size = parse_number(p + 1); + if (*p == ',') { + if (size < offset) + fatal("invalid range: %lu,%lu\n", + offset, size); + size -= offset; + } + } + } else { + offset = parse_number(optarg); + size = 1; + } + + add_addr_range(offset, size); +} + +void add_bits_filter(uint64_t mask, uint64_t bits) +{ + if (nr_bit_filters >= MAX_BIT_FILTERS) + fatal("too much bit filters\n"); + + opt_mask[nr_bit_filters] = mask; + opt_bits[nr_bit_filters] = bits; + nr_bit_filters++; +} + +uint64_t parse_flag_name(const char *str, int len) +{ + int i; + + if (!*str || !len) + return 0; + + if (len <= 8 && !strncmp(str, "compound", len)) + return BITS_COMPOUND; + + for (i = 0; i < ARRAY_SIZE(page_flag_names); i++) { + if (!page_flag_names[i]) + continue; + if (!strncmp(str, page_flag_names[i] + 2, len)) + return 1ULL << i; + } + + return parse_number(str); +} + +uint64_t parse_flag_names(const char *str, int all) +{ + const char *p = str; + uint64_t flags = 0; + + while (1) { + if (*p == ',' || *p == '=' || *p == '\0') { + if ((*str != '~') || (*str == '~' && all && *++str)) + flags |= parse_flag_name(str, p - str); + if (*p != ',') + break; + str = p + 1; + } + p++; + } + + return flags; +} + +void parse_bits_mask(const char *optarg) +{ + uint64_t mask; + uint64_t bits; + const char *p; + + p = strchr(optarg, '='); + if (p == optarg) { + mask = KPF_ALL_BITS; + bits = parse_flag_names(p + 1, 0); + } else if (p) { + mask = parse_flag_names(optarg, 0); + bits = parse_flag_names(p + 1, 0); + } else if (strchr(optarg, '~')) { + mask = parse_flag_names(optarg, 1); + bits = parse_flag_names(optarg, 0); + } else { + mask = parse_flag_names(optarg, 0); + bits = KPF_ALL_BITS; + } + + add_bits_filter(mask, bits); +} + + +struct option opts[] = { + { "raw" , 0, NULL, 'r' }, + { "pid" , 1, NULL, 'p' }, + { "file" , 1, NULL, 'f' }, + { "addr" , 1, NULL, 'a' }, + { "bits" , 1, NULL, 'b' }, + { "list" , 0, NULL, 'l' }, + { "list-each" , 0, NULL, 'L' }, + { "no-summary", 0, NULL, 'N' }, + { "help" , 0, NULL, 'h' }, + { NULL , 0, NULL, 0 } +}; + +int main(int argc, char *argv[]) +{ + int c; + + page_size = getpagesize(); + + while ((c = getopt_long(argc, argv, + "rp:f:a:b:lLNh", opts, NULL)) != -1) { + switch (c) { + case 'r': + opt_raw = 1; + break; + case 'p': + parse_pid(optarg); + break; + case 'f': + parse_file(optarg); + break; + case 'a': + parse_addr_range(optarg); + break; + case 'b': + parse_bits_mask(optarg); + break; + case 'l': + opt_list = 1; + break; + case 'L': + opt_list = 2; + break; + case 'N': + opt_no_summary = 1; + break; + case 'h': + usage(); + exit(0); + default: + usage(); + exit(1); + } + } + + if (opt_list == 1) + printf("offset\tcount\tflags\n"); + if (opt_list == 2) + printf("offset\tflags\n"); + + walk_addr_ranges(); + + if (opt_list == 1) + show_page_range(0, 0); /* drain the buffer */ + + if (opt_no_summary) + return 0; + + if (opt_list) + printf("\n\n"); + + show_summary(); + + return 0; +} diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt index ce72c0fe617..600a304a828 100644 --- a/Documentation/vm/pagemap.txt +++ b/Documentation/vm/pagemap.txt @@ -12,9 +12,9 @@ There are three components to pagemap: value for each virtual page, containing the following data (from fs/proc/task_mmu.c, above pagemap_read): - * Bits 0-55 page frame number (PFN) if present + * Bits 0-54 page frame number (PFN) if present * Bits 0-4 swap type if swapped - * Bits 5-55 swap offset if swapped + * Bits 5-54 swap offset if swapped * Bits 55-60 page shift (page size = 1<<page shift) * Bit 61 reserved for future use * Bit 62 page swapped @@ -36,7 +36,7 @@ There are three components to pagemap: * /proc/kpageflags. This file contains a 64-bit set of flags for each page, indexed by PFN. - The flags are (from fs/proc/proc_misc, above kpageflags_read): + The flags are (from fs/proc/page.c, above kpageflags_read): 0. LOCKED 1. ERROR @@ -49,6 +49,68 @@ There are three components to pagemap: 8. WRITEBACK 9. RECLAIM 10. BUDDY + 11. MMAP + 12. ANON + 13. SWAPCACHE + 14. SWAPBACKED + 15. COMPOUND_HEAD + 16. COMPOUND_TAIL + 16. HUGE + 18. UNEVICTABLE + 20. NOPAGE + +Short descriptions to the page flags: + + 0. LOCKED + page is being locked for exclusive access, eg. by undergoing read/write IO + + 7. SLAB + page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator + When compound page is used, SLUB/SLQB will only set this flag on the head + page; SLOB will not flag it at all. + +10. BUDDY + a free memory block managed by the buddy system allocator + The buddy system organizes free memory in blocks of various orders. + An order N block has 2^N physically contiguous pages, with the BUDDY flag + set for and _only_ for the first page. + +15. COMPOUND_HEAD +16. COMPOUND_TAIL + A compound page with order N consists of 2^N physically contiguous pages. + A compound page with order 2 takes the form of "HTTT", where H donates its + head page and T donates its tail page(s). The major consumers of compound + pages are hugeTLB pages (Documentation/vm/hugetlbpage.txt), the SLUB etc. + memory allocators and various device drivers. However in this interface, + only huge/giga pages are made visible to end users. +17. HUGE + this is an integral part of a HugeTLB page + +20. NOPAGE + no page frame exists at the requested address + + [IO related page flags] + 1. ERROR IO error occurred + 3. UPTODATE page has up-to-date data + ie. for file backed page: (in-memory data revision >= on-disk one) + 4. DIRTY page has been written to, hence contains new data + ie. for file backed page: (in-memory data revision > on-disk one) + 8. WRITEBACK page is being synced to disk + + [LRU related page flags] + 5. LRU page is in one of the LRU lists + 6. ACTIVE page is in the active LRU list +18. UNEVICTABLE page is in the unevictable (non-)LRU list + It is somehow pinned and not a candidate for LRU page reclaims, + eg. ramfs pages, shmctl(SHM_LOCK) and mlock() memory segments + 2. REFERENCED page has been referenced since last LRU list enqueue/requeue + 9. RECLAIM page will be reclaimed soon after its pageout IO completed +11. MMAP a memory mapped page +12. ANON a memory mapped page that is not part of a file +13. SWAPCACHE page is mapped to swap space, ie. has an associated swap entry +14. SWAPBACKED page is backed by swap/RAM + +The page-types tool in this directory can be used to query the above flags. Using pagemap to do something useful: diff --git a/MAINTAINERS b/MAINTAINERS index af8ef6527f2..fb94addb34d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -36,6 +36,12 @@ trivial patch so apply some common sense. (scripts/checkpatch.pl) to catch trival style violations. See Documentation/CodingStyle for guidance here. + PLEASE CC: the maintainers and mailing lists that are generated + by scripts/get_maintainer.pl. The results returned by the + script will be best if you have git installed and are making + your changes in a branch derived from Linus' latest git tree. + See Documentation/SubmittingPatches for details. + PLEASE try to include any credit lines you want added with the patch. It avoids people being missed off by mistake and makes it easier to know who wants adding and who doesn't. @@ -489,7 +495,7 @@ AOA (Apple Onboard Audio) ALSA DRIVER P: Johannes Berg M: johannes@sipsolutions.net L: linuxppc-dev@ozlabs.org -L: alsa-devel@alsa-project.org (subscribers-only) +L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained F: sound/aoa/ @@ -912,7 +918,6 @@ P: Dan Williams M: dan.j.williams@intel.com P: Maciej Sosnowski M: maciej.sosnowski@intel.com -L: linux-kernel@vger.kernel.org W: http://sourceforge.net/projects/xscaleiop S: Supported F: Documentation/crypto/async-tx-api.txt @@ -1008,7 +1013,6 @@ F: drivers/mmc/host/at91_mci.c ATMEL AT91 / AT32 SERIAL DRIVER P: Haavard Skinnemoen M: hskinnemoen@atmel.com -L: linux-kernel@vger.kernel.org S: Supported F: drivers/serial/atmel_serial.c @@ -1064,7 +1068,6 @@ F: kernel/audit* AUXILIARY DISPLAY DRIVERS P: Miguel Ojeda Sandonis M: miguel.ojeda.sandonis@gmail.com -L: linux-kernel@vger.kernel.org W: http://miguelojeda.es/auxdisplay.htm W: http://jair.lab.fi.uva.es/~migojed/auxdisplay.htm S: Maintained @@ -1134,7 +1137,6 @@ F: drivers/net/hamradio/baycom* BEFS FILE SYSTEM P: Sergey S. Kostyliov M: rathamahata@php4.ru -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/befs.txt F: fs/befs/ @@ -1142,7 +1144,6 @@ F: fs/befs/ BFS FILE SYSTEM P: Tigran A. Aivazian M: tigran@aivazian.fsnet.co.uk -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/bfs.txt F: fs/bfs/ @@ -1199,7 +1200,6 @@ F: drivers/i2c/busses/i2c-bfin-twi.c BLOCK LAYER P: Jens Axboe M: axboe@kernel.dk -L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git S: Maintained F: block/ @@ -1326,7 +1326,6 @@ P: Muli Ben-Yehuda M: muli@il.ibm.com P: Jon D. Mason M: jdmason@kudzu.us -L: linux-kernel@vger.kernel.org L: discuss@x86-64.org S: Maintained F: arch/x86/kernel/pci-calgary_64.c @@ -1378,7 +1377,6 @@ F: include/linux/usb/wusb* CFAG12864B LCD DRIVER P: Miguel Ojeda Sandonis M: miguel.ojeda.sandonis@gmail.com -L: linux-kernel@vger.kernel.org W: http://miguelojeda.es/auxdisplay.htm W: http://jair.lab.fi.uva.es/~migojed/auxdisplay.htm S: Maintained @@ -1388,7 +1386,6 @@ F: include/linux/cfag12864b.h CFAG12864BFB LCD FRAMEBUFFER DRIVER P: Miguel Ojeda Sandonis M: miguel.ojeda.sandonis@gmail.com -L: linux-kernel@vger.kernel.org W: http://miguelojeda.es/auxdisplay.htm W: http://jair.lab.fi.uva.es/~migojed/auxdisplay.htm S: Maintained @@ -1408,7 +1405,6 @@ X: net/wireless/wext* CHECKPATCH P: Andy Whitcroft M: apw@canonical.com -L: linux-kernel@vger.kernel.org S: Supported F: scripts/checkpatch.pl @@ -1437,7 +1433,7 @@ F: drivers/usb/host/ohci-ep93xx.c CIRRUS LOGIC CS4270 SOUND DRIVER P: Timur Tabi M: timur@freescale.com -L: alsa-devel@alsa-project.org +L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: sound/soc/codecs/cs4270* @@ -1462,6 +1458,7 @@ P: Joe Eykholt M: jeykholt@cisco.com L: linux-scsi@vger.kernel.org S: Supported +F: drivers/scsi/fnic/ CODA FILE SYSTEM P: Jan Harkes @@ -1534,7 +1531,6 @@ F: drivers/usb/atm/cxacru.c CONFIGFS P: Joel Becker M: joel.becker@oracle.com -L: linux-kernel@vger.kernel.org S: Supported F: fs/configfs/ F: include/linux/configfs.h @@ -1592,7 +1588,6 @@ F: arch/x86/kernel/msr.c CPUSETS P: Paul Menage M: menage@google.com -L: linux-kernel@vger.kernel.org W: http://www.bullopensource.org/cpuset/ W: http://oss.sgi.com/projects/cpusets/ S: Supported @@ -1799,7 +1794,6 @@ DEVICE NUMBER REGISTRY P: Torben Mathiasen M: device@lanana.org W: http://lanana.org/docs/device-list/index.html -L: linux-kernel@vger.kernel.org S: Maintained DEVICE-MAPPER (LVM) @@ -1825,7 +1819,6 @@ F: drivers/char/digi* DIRECTORY NOTIFICATION (DNOTIFY) P: Eric Paris M: eparis@parisplace.org -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/dnotify.txt F: fs/notify/dnotify/ @@ -1842,7 +1835,6 @@ S: Maintained DISKQUOTA P: Jan Kara M: jack@suse.cz -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/quota.txt F: fs/quota/ @@ -1864,7 +1856,6 @@ P: Maciej Sosnowski M: maciej.sosnowski@intel.com P: Dan Williams M: dan.j.williams@intel.com -L: linux-kernel@vger.kernel.org S: Supported F: drivers/dma/ F: include/linux/dma* @@ -1916,7 +1907,6 @@ F: drivers/scsi/dpt/ DRIVER CORE, KOBJECTS, AND SYSFS P: Greg Kroah-Hartman M: gregkh@suse.de -L: linux-kernel@vger.kernel.org T: quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/ S: Supported F: Documentation/kobject.txt @@ -1982,8 +1972,8 @@ F: net/bridge/netfilter/ebt*.c ECRYPT FILE SYSTEM P: Tyler Hicks M: tyhicks@linux.vnet.ibm.com -M: Dustin Kirkland -P: kirkland@canonical.com +P: Dustin Kirkland +M: kirkland@canonical.com L: ecryptfs-devel@lists.launchpad.net W: https://launchpad.net/ecryptfs S: Supported @@ -2263,7 +2253,6 @@ F: drivers/firewire/ F: include/linux/firewire*.h FIRMWARE LOADER (request_firmware) -L: linux-kernel@vger.kernel.org S: Orphan F: Documentation/firmware_class/ F: drivers/base/firmware*.c @@ -2300,7 +2289,6 @@ M: leoli@freescale.com P: Zhang Wei M: zw@zh-kernel.org L: linuxppc-dev@ozlabs.org -L: linux-kernel@vger.kernel.org S: Maintained F: drivers/dma/fsldma.* @@ -2366,7 +2354,7 @@ F: drivers/serial/ucc_uart.c FREESCALE SOC SOUND DRIVERS P: Timur Tabi M: timur@freescale.com -L: alsa-devel@alsa-project.org +L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: linuxppc-dev@ozlabs.org S: Supported F: sound/soc/fsl/fsl* @@ -2500,7 +2488,6 @@ F: drivers/hwmon/hdaps.c HYPERVISOR VIRTUAL CONSOLE DRIVER L: linuxppc-dev@ozlabs.org -L: linux-kernel@vger.kernel.org S: Odd Fixes F: drivers/char/hvc_* @@ -2567,7 +2554,6 @@ F: sound/parisc/harmony.* HAYES ESP SERIAL DRIVER P: Andrew J. Robinson M: arobinso@nyx.net -L: linux-kernel@vger.kernel.org W: http://www.nyx.net/~arobinso S: Maintained F: Documentation/serial/hayes-esp.txt @@ -2593,7 +2579,6 @@ F: include/linux/cciss_ioctl.h HFS FILESYSTEM P: Roman Zippel M: zippel@linux-m68k.org -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/hfs.txt F: fs/hfs/ @@ -2633,7 +2618,6 @@ F: include/linux/hid* HIGH-RESOLUTION TIMERS, CLOCKEVENTS, DYNTICKS P: Thomas Gleixner M: tglx@linutronix.de -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/timers/ F: kernel/hrtimer.c @@ -2772,7 +2756,6 @@ F: drivers/i2c/busses/i2c-tiny-usb.c i386 BOOT CODE P: H. Peter Anvin M: hpa@zytor.com -L: Linux-Kernel@vger.kernel.org S: Maintained F: arch/x86/boot/ @@ -2902,7 +2885,6 @@ P: Robert Love M: rlove@rlove.org P: Eric Paris M: eparis@parisplace.org -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/inotify.txt F: fs/notify/inotify/ @@ -2950,7 +2932,6 @@ F: arch/x86/kernel/microcode_intel.c INTEL I/OAT DMA DRIVER P: Maciej Sosnowski M: maciej.sosnowski@intel.com -L: linux-kernel@vger.kernel.org S: Supported F: drivers/dma/ioat* @@ -2966,7 +2947,6 @@ F: include/linux/intel-iommu.h INTEL IOP-ADMA DMA DRIVER P: Dan Williams M: dan.j.williams@intel.com -L: linux-kernel@vger.kernel.org S: Supported F: drivers/dma/iop-adma.c @@ -3279,7 +3259,6 @@ M: vgoyal@redhat.com P: Haren Myneni M: hbabu@us.ibm.com L: kexec@lists.infradead.org -L: linux-kernel@vger.kernel.org W: http://lse.sourceforge.net/kdump/ S: Maintained F: Documentation/kdump/ @@ -3389,7 +3368,6 @@ KEXEC P: Eric Biederman M: ebiederm@xmission.com W: http://ftp.kernel.org/pub/linux/kernel/people/horms/kexec-tools/ -L: linux-kernel@vger.kernel.org L: kexec@lists.infradead.org S: Maintained F: include/linux/kexec.h @@ -3427,7 +3405,6 @@ F: mm/kmemleak-test.c KMEMTRACE P: Eduard - Gabriel Munteanu M: eduard.munteanu@linux360.ro -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/trace/kmemtrace.txt F: include/trace/kmemtrace.h @@ -3442,7 +3419,6 @@ P: David S. Miller M: davem@davemloft.net P: Masami Hiramatsu M: mhiramat@redhat.com -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/kprobes.txt F: include/linux/kprobes.h @@ -3451,7 +3427,6 @@ F: kernel/kprobes.c KS0108 LCD CONTROLLER DRIVER P: Miguel Ojeda Sandonis M: miguel.ojeda.sandonis@gmail.com -L: linux-kernel@vger.kernel.org W: http://miguelojeda.es/auxdisplay.htm W: http://jair.lab.fi.uva.es/~migojed/auxdisplay.htm S: Maintained @@ -3615,7 +3590,6 @@ P: Peter Zijlstra M: peterz@infradead.org P: Ingo Molnar M: mingo@redhat.com -L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-lockdep.git S: Maintained F: Documentation/lockdep*.txt @@ -3667,7 +3641,6 @@ L: linux-m32r-ja@ml.linux-m32r.org (in Japanese) W: http://www.linux-m32r.org/ S: Maintained F: arch/m32r/ -F: include/asm-m32r/ M68K ARCHITECTURE P: Geert Uytterhoeven @@ -3751,7 +3724,6 @@ F: include/linux/mv643xx.h MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER P: Nicolas Pitre M: nico@cam.org -L: linux-kernel@vger.kernel.org S: Maintained MARVELL YUKON / SYSKONNECT DRIVER @@ -3805,7 +3777,6 @@ F: drivers/scsi/megaraid/ MEMORY MANAGEMENT L: linux-mm@kvack.org -L: linux-kernel@vger.kernel.org W: http://www.linux-mm.org S: Maintained F: include/linux/mm.h @@ -3819,7 +3790,6 @@ M: xemul@openvz.org P: KAMEZAWA Hiroyuki M: kamezawa.hiroyu@jp.fujitsu.com L: linux-mm@kvack.org -L: linux-kernel@vger.kernel.org S: Maintained F: mm/memcontrol.c @@ -3862,7 +3832,6 @@ F: arch/mips/ MISCELLANEOUS MCA-SUPPORT P: James Bottomley M: James.Bottomley@HansenPartnership.com -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/ia64/mca.txt F: Documentation/mca.txt @@ -3872,7 +3841,6 @@ F: include/linux/mca* MODULE SUPPORT P: Rusty Russell M: rusty@rustcorp.com.au -L: linux-kernel@vger.kernel.org S: Maintained F: include/linux/module.h F: kernel/module.c @@ -3896,7 +3864,6 @@ F: drivers/mmc/host/imxmmc.* MOUSE AND MISC DEVICES [GENERAL] P: Alessandro Rubini M: rubini@ipvvis.unipv.it -L: linux-kernel@vger.kernel.org S: Maintained F: drivers/input/mouse/ F: include/linux/gpio_mouse.h @@ -3904,7 +3871,6 @@ F: include/linux/gpio_mouse.h MOXA SMARTIO/INDUSTIO/INTELLIO SERIAL CARD P: Jiri Slaby M: jirislaby@gmail.com -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/serial/moxa-smartio F: drivers/char/mxser.* @@ -3920,7 +3886,6 @@ F: drivers/platform/x86/msi-laptop.c MULTIFUNCTION DEVICES (MFD) P: Samuel Ortiz M: sameo@linux.intel.com -L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/sameo/mfd-2.6.git S: Supported F: drivers/mfd/ @@ -3928,7 +3893,6 @@ F: drivers/mfd/ MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM P: Pierre Ossman M: pierre@ossman.eu -L: linux-kernel@vger.kernel.org S: Maintained F: drivers/mmc/ F: include/linux/mmc/ @@ -3936,7 +3900,6 @@ F: include/linux/mmc/ MULTIMEDIA CARD (MMC) ETC. OVER SPI P: David Brownell M: dbrownell@users.sourceforge.net -L: linux-kernel@vger.kernel.org S: Odd Fixes F: drivers/mmc/host/mmc_spi.c F: include/linux/spi/mmc_spi.h @@ -3951,7 +3914,6 @@ F: sound/oss/msnd* MULTITECH MULTIPORT CARD (ISICOM) P: Jiri Slaby M: jirislaby@gmail.com -L: linux-kernel@vger.kernel.org S: Maintained F: drivers/char/isicom.c F: include/linux/isicom.h @@ -4195,7 +4157,6 @@ NTFS FILESYSTEM P: Anton Altaparmakov M: aia21@cantab.net L: linux-ntfs-dev@lists.sourceforge.net -L: linux-kernel@vger.kernel.org W: http://www.linux-ntfs.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/aia21/ntfs-2.6.git S: Maintained @@ -4429,7 +4390,6 @@ M: akataria@vmware.com P: Rusty Russell M: rusty@rustcorp.com.au L: virtualization@lists.osdl.org -L: linux-kernel@vger.kernel.org S: Supported F: Documentation/ia64/paravirt_ops.txt F: arch/*/kernel/paravirt* @@ -4480,7 +4440,6 @@ F: include/linux/leds-pca9532.h PCI ERROR RECOVERY P: Linas Vepstas M: linas@austin.ibm.com -L: linux-kernel@vger.kernel.org L: linux-pci@vger.kernel.org S: Supported F: Documentation/PCI/pci-error-recovery.txt @@ -4489,7 +4448,6 @@ F: Documentation/powerpc/eeh-pci-error-recovery.txt PCI SUBSYSTEM P: Jesse Barnes M: jbarnes@virtuousgeek.org -L: linux-kernel@vger.kernel.org L: linux-pci@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6.git S: Supported @@ -4524,7 +4482,6 @@ F: drivers/net/pcnet32.c PER-TASK DELAY ACCOUNTING P: Balbir Singh M: balbir@linux.vnet.ibm.com -L: linux-kernel@vger.kernel.org S: Maintained F: include/linux/delayacct.h F: kernel/delayacct.c @@ -4556,7 +4513,6 @@ F: drivers/mtd/devices/phram.c PKTCDVD DRIVER P: Peter Osterlund M: petero2@telia.com -L: linux-kernel@vger.kernel.org S: Maintained F: drivers/block/pktcdvd.c F: include/linux/pktcdvd.h @@ -4564,7 +4520,6 @@ F: include/linux/pktcdvd.h POSIX CLOCKS and TIMERS P: Thomas Gleixner M: tglx@linutronix.de -L: linux-kernel@vger.kernel.org S: Supported F: fs/timerfd.c F: include/linux/timer* @@ -4575,7 +4530,6 @@ P: Anton Vorontsov M: cbou@mail.ru P: David Woodhouse M: dwmw2@infradead.org -L: linux-kernel@vger.kernel.org T: git git://git.infradead.org/battery-2.6.git S: Maintained F: include/linux/power_supply.h @@ -4627,7 +4581,6 @@ F: include/linux/if_pppol2tp.h PREEMPTIBLE KERNEL P: Robert Love M: rml@tech9.net -L: linux-kernel@vger.kernel.org L: kpreempt-tech@lists.sourceforge.net W: ftp://ftp.kernel.org/pub/linux/kernel/people/rml/preempt-kernel S: Supported @@ -4690,7 +4643,6 @@ P: Roland McGrath M: roland@redhat.com P: Oleg Nesterov M: oleg@redhat.com -L: linux-kernel@vger.kernel.org S: Maintained F: include/asm-generic/syscall.h F: include/linux/ptrace.h @@ -4776,7 +4728,6 @@ F: drivers/net/qlge/ QNX4 FILESYSTEM P: Anders Larsen M: al@alarsen.net -L: linux-kernel@vger.kernel.org W: http://www.alarsen.net/linux/qnx4fs/ S: Maintained F: fs/qnx4/ @@ -4823,7 +4774,6 @@ F: drivers/char/random.c RAPIDIO SUBSYSTEM P: Matt Porter M: mporter@kernel.crashing.org -L: linux-kernel@vger.kernel.org S: Maintained F: drivers/rapidio/ @@ -4837,7 +4787,8 @@ F: drivers/net/wireless/ray* RCUTORTURE MODULE P: Josh Triplett M: josh@freedesktop.org -L: linux-kernel@vger.kernel.org +P: Paul E. McKenney +M: paulmck@linux.vnet.ibm.com S: Maintained F: Documentation/RCU/torture.txt F: kernel/rcutorture.c @@ -4845,7 +4796,6 @@ F: kernel/rcutorture.c RDC R-321X SoC P: Florian Fainelli M: florian@openwrt.org -L: linux-kernel@vger.kernel.org S: Maintained RDC R6040 FAST ETHERNET DRIVER @@ -4865,8 +4815,9 @@ F: net/rds/ READ-COPY UPDATE (RCU) P: Dipankar Sarma M: dipankar@in.ibm.com +P: Paul E. McKenney +M: paulmck@linux.vnet.ibm.com W: http://www.rdrop.com/users/paulmck/rclock/ -L: linux-kernel@vger.kernel.org S: Supported F: Documentation/RCU/rcu.txt F: Documentation/RCU/rcuref.txt @@ -4877,7 +4828,6 @@ F: kernel/rcupdate.c REAL TIME CLOCK DRIVER P: Paul Gortmaker M: p_gortmaker@yahoo.com -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/rtc.txt F: drivers/rtc/ @@ -5015,7 +4965,6 @@ S3C24XX SD/MMC Driver P: Ben Dooks M: ben-linux@fluff.org L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) -L: linux-kernel@vger.kernel.org S: Supported F: drivers/mmc/host/s3cmci.* @@ -5041,7 +4990,6 @@ P: Ingo Molnar M: mingo@elte.hu P: Peter Zijlstra M: peterz@infradead.org -L: linux-kernel@vger.kernel.org S: Maintained F: kernel/sched* F: include/linux/sched.h @@ -5143,7 +5091,6 @@ F: drivers/mmc/host/sdhci.* SECURITY SUBSYSTEM P: James Morris M: jmorris@namei.org -L: linux-kernel@vger.kernel.org L: linux-security-module@vger.kernel.org (suggested Cc:) T: git git://www.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6.git W: http://security.wiki.kernel.org/ @@ -5162,7 +5109,6 @@ P: James Morris M: jmorris@namei.org P: Eric Paris M: eparis@parisplace.org -L: linux-kernel@vger.kernel.org (kernel issues) L: selinux@tycho.nsa.gov (subscribers-only, general discussion) W: http://selinuxproject.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6.git @@ -5425,7 +5371,6 @@ F: include/linux/sony-laptop.h SONY MEMORYSTICK CARD SUPPORT P: Alex Dubov M: oakad@yahoo.com -L: linux-kernel@vger.kernel.org W: http://tifmxx.berlios.de/ S: Maintained F: drivers/memstick/host/tifm_ms.c @@ -5435,7 +5380,7 @@ P: Jaroslav Kysela M: perex@perex.cz P: Takashi Iwai M: tiwai@suse.de -L: alsa-devel@alsa-project.org (subscribers-only) +L: alsa-devel@alsa-project.org (moderated for non-subscribers) W: http://www.alsa-project.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6.git T: git git://git.alsa-project.org/alsa-kernel.git @@ -5450,7 +5395,7 @@ M: lrg@slimlogic.co.uk P: Mark Brown M: broonie@opensource.wolfsonmicro.com T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound-2.6.git -L: alsa-devel@alsa-project.org (subscribers-only) +L: alsa-devel@alsa-project.org (moderated for non-subscribers) W: http://alsa-project.org/main/index.php/ASoC S: Supported F: sound/soc/ @@ -5468,7 +5413,6 @@ F: arch/sparc/ SPECIALIX IO8+ MULTIPORT SERIAL CARD DRIVER P: Roger Wolff M: R.E.Wolff@BitWizard.nl -L: linux-kernel@vger.kernel.org S: Supported F: Documentation/serial/specialix.txt F: drivers/char/specialix* @@ -5514,7 +5458,6 @@ F: fs/squashfs/ SRM (Alpha) environment access P: Jan-Benedict Glaw M: jbglaw@lug-owl.de -L: linux-kernel@vger.kernel.org S: Maintained F: arch/alpha/kernel/srm_env.c @@ -5529,7 +5472,6 @@ S: Maintained STAGING SUBSYSTEM P: Greg Kroah-Hartman M: gregkh@suse.de -L: linux-kernel@vger.kernel.org T: quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/ S: Maintained F: drivers/staging/ @@ -5609,7 +5551,6 @@ F: include/linux/sysv_fs.h TASKSTATS STATISTICS INTERFACE P: Balbir Singh M: balbir@linux.vnet.ibm.com -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/accounting/taskstats* F: include/linux/taskstats* @@ -5702,7 +5643,6 @@ P: Kentaro Takeda M: takedakn@nttdata.co.jp P: Tetsuo Handa M: penguin-kernel@I-love.SAKURA.ne.jp -L: linux-kernel@vger.kernel.org (kernel issues) L: tomoyo-users-en@lists.sourceforge.jp (subscribers-only, for developers and users in English) L: tomoyo-dev@lists.sourceforge.jp (subscribers-only, for developers in Japanese) L: tomoyo-users@lists.sourceforge.jp (subscribers-only, for users in Japanese) @@ -5754,14 +5694,17 @@ F: drivers/char/tpm/ TRIVIAL PATCHES P: Jiri Kosina M: trivial@kernel.org -L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial.git S: Maintained +F: drivers/char/tty_* +F: drivers/serial/serial_core.c +F: include/linux/serial_core.h +F: include/linux/serial.h +F: include/linux/tty.h TTY LAYER P: Alan Cox M: alan@lxorguk.ukuu.org.uk -L: linux-kernel@vger.kernel.org S: Maintained T: stgit http://zeniv.linux.org.uk/~alan/ttydev/ @@ -5834,7 +5777,6 @@ F: fs/udf/ UFS FILESYSTEM P: Evgeniy Dushistov M: dushistov@mail.ru -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/ufs.txt F: fs/ufs/ @@ -5851,7 +5793,6 @@ F: include/linux/uwb/ UNIFORM CDROM DRIVER P: Jens Axboe M: axboe@kernel.dk -L: linux-kernel@vger.kernel.org W: http://www.kernel.dk S: Maintained F: Documentation/cdrom/ @@ -5880,7 +5821,6 @@ F: drivers/usb/class/cdc-acm.* USB BLOCK DRIVER (UB ub) P: Pete Zaitcev M: zaitcev@redhat.com -L: linux-kernel@vger.kernel.org L: linux-usb@vger.kernel.org S: Supported F: drivers/block/ub.c @@ -6226,7 +6166,6 @@ P: Hans J. Koch M: hjk@linutronix.de P: Greg Kroah-Hartman M: gregkh@suse.de -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/DocBook/uio-howto.tmpl F: drivers/uio/ @@ -6252,7 +6191,6 @@ F: drivers/video/uvesafb.* VFAT/FAT/MSDOS FILESYSTEM P: OGAWA Hirofumi M: hirofumi@mail.parknet.co.jp -L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/filesystems/vfat.txt F: fs/fat/ @@ -6296,6 +6234,14 @@ F: drivers/net/macvlan.c F: include/linux/if_*vlan.h F: net/8021q/ +VLYNQ BUS +P: Florian Fainelli +M: florian@openwrt.org +L: openwrt-devel@lists.openwrt.org +S: Maintained +F: drivers/vlynq/vlynq.c +F: include/linux/vlynq.h + VOLTAGE AND CURRENT REGULATOR FRAMEWORK P: Liam Girdwood M: lrg@slimlogic.co.uk @@ -6349,7 +6295,6 @@ F: drivers/hwmon/w83793.c W83L51xD SD/MMC CARD INTERFACE DRIVER P: Pierre Ossman M: pierre@ossman.eu -L: linux-kernel@vger.kernel.org S: Maintained F: drivers/mmc/host/wbsd.* @@ -6436,7 +6381,6 @@ M: mingo@redhat.com P: H. Peter Anvin M: hpa@zytor.com M: x86@kernel.org -L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git S: Maintained F: Documentation/x86/ @@ -6472,7 +6416,6 @@ XILINX SYSTEMACE DRIVER P: Grant Likely M: grant.likely@secretlab.ca W: http://www.secretlab.ca/ -L: linux-kernel@vger.kernel.org S: Maintained F: drivers/block/xsysace.c @@ -6537,5 +6480,9 @@ F: drivers/serial/zs.* THE REST P: Linus Torvalds +M: torvalds@linux-foundation.org +L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git S: Buried alive in reporters +F: * +F: */ diff --git a/arch/alpha/include/asm/8253pit.h b/arch/alpha/include/asm/8253pit.h index fef5c1450e4..a71c9c1455a 100644 --- a/arch/alpha/include/asm/8253pit.h +++ b/arch/alpha/include/asm/8253pit.h @@ -1,10 +1,3 @@ /* * 8253/8254 Programmable Interval Timer */ - -#ifndef _8253PIT_H -#define _8253PIT_H - -#define PIT_TICK_RATE 1193180UL - -#endif diff --git a/arch/alpha/include/asm/kmap_types.h b/arch/alpha/include/asm/kmap_types.h index 3e6735a34c5..a8d4ec8ea4b 100644 --- a/arch/alpha/include/asm/kmap_types.h +++ b/arch/alpha/include/asm/kmap_types.h @@ -3,30 +3,12 @@ /* Dummy header just to define km_type. */ - #ifdef CONFIG_DEBUG_HIGHMEM -# define D(n) __KM_FENCE_##n , -#else -# define D(n) +#define __WITH_KM_FENCE #endif -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_IRQ0, -D(10) KM_IRQ1, -D(11) KM_SOFTIRQ0, -D(12) KM_SOFTIRQ1, -D(13) KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> -#undef D +#undef __WITH_KM_FENCE #endif diff --git a/arch/alpha/kernel/init_task.c b/arch/alpha/kernel/init_task.c index c2938e574a4..19b86328ffd 100644 --- a/arch/alpha/kernel/init_task.c +++ b/arch/alpha/kernel/init_task.c @@ -10,10 +10,7 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); struct task_struct init_task = INIT_TASK(init_task); - -EXPORT_SYMBOL(init_mm); EXPORT_SYMBOL(init_task); union thread_union init_thread_union diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 67c19f8a994..38c805dfc54 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -227,7 +227,7 @@ struct irqaction timer_irqaction = { .name = "timer", }; -static struct hw_interrupt_type rtc_irq_type = { +static struct irq_chip rtc_irq_type = { .typename = "RTC", .startup = rtc_startup, .shutdown = rtc_enable_disable, diff --git a/arch/alpha/kernel/irq_i8259.c b/arch/alpha/kernel/irq_i8259.c index 9405bee9894..50bfec9b588 100644 --- a/arch/alpha/kernel/irq_i8259.c +++ b/arch/alpha/kernel/irq_i8259.c @@ -83,7 +83,7 @@ i8259a_end_irq(unsigned int irq) i8259a_enable_irq(irq); } -struct hw_interrupt_type i8259a_irq_type = { +struct irq_chip i8259a_irq_type = { .typename = "XT-PIC", .startup = i8259a_startup_irq, .shutdown = i8259a_disable_irq, diff --git a/arch/alpha/kernel/irq_impl.h b/arch/alpha/kernel/irq_impl.h index cc9a8a7aa27..b63ccd7386f 100644 --- a/arch/alpha/kernel/irq_impl.h +++ b/arch/alpha/kernel/irq_impl.h @@ -36,7 +36,7 @@ extern void i8259a_disable_irq(unsigned int); extern void i8259a_mask_and_ack_irq(unsigned int); extern unsigned int i8259a_startup_irq(unsigned int); extern void i8259a_end_irq(unsigned int); -extern struct hw_interrupt_type i8259a_irq_type; +extern struct irq_chip i8259a_irq_type; extern void init_i8259a_irqs(void); extern void handle_irq(int irq); diff --git a/arch/alpha/kernel/irq_pyxis.c b/arch/alpha/kernel/irq_pyxis.c index d53edbccbfe..69199a76ec4 100644 --- a/arch/alpha/kernel/irq_pyxis.c +++ b/arch/alpha/kernel/irq_pyxis.c @@ -70,7 +70,7 @@ pyxis_mask_and_ack_irq(unsigned int irq) *(vulp)PYXIS_INT_MASK; } -static struct hw_interrupt_type pyxis_irq_type = { +static struct irq_chip pyxis_irq_type = { .typename = "PYXIS", .startup = pyxis_startup_irq, .shutdown = pyxis_disable_irq, diff --git a/arch/alpha/kernel/irq_srm.c b/arch/alpha/kernel/irq_srm.c index a03fbca4940..85229369a1f 100644 --- a/arch/alpha/kernel/irq_srm.c +++ b/arch/alpha/kernel/irq_srm.c @@ -48,7 +48,7 @@ srm_end_irq(unsigned int irq) } /* Handle interrupts from the SRM, assuming no additional weirdness. */ -static struct hw_interrupt_type srm_irq_type = { +static struct irq_chip srm_irq_type = { .typename = "SRM", .startup = srm_startup_irq, .shutdown = srm_disable_irq, diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 80df86cd746..d2634e4476b 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -252,9 +252,9 @@ reserve_std_resources(void) } #define PFN_MAX PFN_DOWN(0x80000000) -#define for_each_mem_cluster(memdesc, cluster, i) \ - for ((cluster) = (memdesc)->cluster, (i) = 0; \ - (i) < (memdesc)->numclusters; (i)++, (cluster)++) +#define for_each_mem_cluster(memdesc, _cluster, i) \ + for ((_cluster) = (memdesc)->cluster, (i) = 0; \ + (i) < (memdesc)->numclusters; (i)++, (_cluster)++) static unsigned long __init get_mem_size_limit(char *s) diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c index e53a1e1c2f2..382035ef739 100644 --- a/arch/alpha/kernel/sys_alcor.c +++ b/arch/alpha/kernel/sys_alcor.c @@ -89,7 +89,7 @@ alcor_end_irq(unsigned int irq) alcor_enable_irq(irq); } -static struct hw_interrupt_type alcor_irq_type = { +static struct irq_chip alcor_irq_type = { .typename = "ALCOR", .startup = alcor_startup_irq, .shutdown = alcor_disable_irq, diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index ace475c124f..ed349436732 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -71,7 +71,7 @@ cabriolet_end_irq(unsigned int irq) cabriolet_enable_irq(irq); } -static struct hw_interrupt_type cabriolet_irq_type = { +static struct irq_chip cabriolet_irq_type = { .typename = "CABRIOLET", .startup = cabriolet_startup_irq, .shutdown = cabriolet_disable_irq, diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c index 5bd5259324b..46e70ece517 100644 --- a/arch/alpha/kernel/sys_dp264.c +++ b/arch/alpha/kernel/sys_dp264.c @@ -198,7 +198,7 @@ clipper_set_affinity(unsigned int irq, const struct cpumask *affinity) return 0; } -static struct hw_interrupt_type dp264_irq_type = { +static struct irq_chip dp264_irq_type = { .typename = "DP264", .startup = dp264_startup_irq, .shutdown = dp264_disable_irq, @@ -209,7 +209,7 @@ static struct hw_interrupt_type dp264_irq_type = { .set_affinity = dp264_set_affinity, }; -static struct hw_interrupt_type clipper_irq_type = { +static struct irq_chip clipper_irq_type = { .typename = "CLIPPER", .startup = clipper_startup_irq, .shutdown = clipper_disable_irq, @@ -298,7 +298,7 @@ clipper_srm_device_interrupt(unsigned long vector) } static void __init -init_tsunami_irqs(struct hw_interrupt_type * ops, int imin, int imax) +init_tsunami_irqs(struct irq_chip * ops, int imin, int imax) { long i; for (i = imin; i <= imax; ++i) { diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c index 9c5a306dc0e..660c23ef661 100644 --- a/arch/alpha/kernel/sys_eb64p.c +++ b/arch/alpha/kernel/sys_eb64p.c @@ -69,7 +69,7 @@ eb64p_end_irq(unsigned int irq) eb64p_enable_irq(irq); } -static struct hw_interrupt_type eb64p_irq_type = { +static struct irq_chip eb64p_irq_type = { .typename = "EB64P", .startup = eb64p_startup_irq, .shutdown = eb64p_disable_irq, diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c index baf60f36cbd..b99ea488d84 100644 --- a/arch/alpha/kernel/sys_eiger.c +++ b/arch/alpha/kernel/sys_eiger.c @@ -80,7 +80,7 @@ eiger_end_irq(unsigned int irq) eiger_enable_irq(irq); } -static struct hw_interrupt_type eiger_irq_type = { +static struct irq_chip eiger_irq_type = { .typename = "EIGER", .startup = eiger_startup_irq, .shutdown = eiger_disable_irq, diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c index 2b5caf3d9b1..ef0b83a070a 100644 --- a/arch/alpha/kernel/sys_jensen.c +++ b/arch/alpha/kernel/sys_jensen.c @@ -118,7 +118,7 @@ jensen_local_end(unsigned int irq) i8259a_end_irq(1); } -static struct hw_interrupt_type jensen_local_irq_type = { +static struct irq_chip jensen_local_irq_type = { .typename = "LOCAL", .startup = jensen_local_startup, .shutdown = jensen_local_shutdown, diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index c5a1a2438c6..bbfc4f20ca7 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -169,7 +169,7 @@ marvel_irq_noop_return(unsigned int irq) return 0; } -static struct hw_interrupt_type marvel_legacy_irq_type = { +static struct irq_chip marvel_legacy_irq_type = { .typename = "LEGACY", .startup = marvel_irq_noop_return, .shutdown = marvel_irq_noop, @@ -179,7 +179,7 @@ static struct hw_interrupt_type marvel_legacy_irq_type = { .end = marvel_irq_noop, }; -static struct hw_interrupt_type io7_lsi_irq_type = { +static struct irq_chip io7_lsi_irq_type = { .typename = "LSI", .startup = io7_startup_irq, .shutdown = io7_disable_irq, @@ -189,7 +189,7 @@ static struct hw_interrupt_type io7_lsi_irq_type = { .end = io7_end_irq, }; -static struct hw_interrupt_type io7_msi_irq_type = { +static struct irq_chip io7_msi_irq_type = { .typename = "MSI", .startup = io7_startup_irq, .shutdown = io7_disable_irq, @@ -273,8 +273,8 @@ init_one_io7_msi(struct io7 *io7, unsigned int which, unsigned int where) static void __init init_io7_irqs(struct io7 *io7, - struct hw_interrupt_type *lsi_ops, - struct hw_interrupt_type *msi_ops) + struct irq_chip *lsi_ops, + struct irq_chip *msi_ops) { long base = (io7->pe << MARVEL_IRQ_VEC_PE_SHIFT) + 16; long i; diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c index 8d3e9429c5e..4e366641a08 100644 --- a/arch/alpha/kernel/sys_mikasa.c +++ b/arch/alpha/kernel/sys_mikasa.c @@ -68,7 +68,7 @@ mikasa_end_irq(unsigned int irq) mikasa_enable_irq(irq); } -static struct hw_interrupt_type mikasa_irq_type = { +static struct irq_chip mikasa_irq_type = { .typename = "MIKASA", .startup = mikasa_startup_irq, .shutdown = mikasa_disable_irq, diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c index 538876b6244..35753a173ba 100644 --- a/arch/alpha/kernel/sys_noritake.c +++ b/arch/alpha/kernel/sys_noritake.c @@ -73,7 +73,7 @@ noritake_end_irq(unsigned int irq) noritake_enable_irq(irq); } -static struct hw_interrupt_type noritake_irq_type = { +static struct irq_chip noritake_irq_type = { .typename = "NORITAKE", .startup = noritake_startup_irq, .shutdown = noritake_disable_irq, diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c index 672cb2df53d..f3aec7e085c 100644 --- a/arch/alpha/kernel/sys_rawhide.c +++ b/arch/alpha/kernel/sys_rawhide.c @@ -135,7 +135,7 @@ rawhide_end_irq(unsigned int irq) rawhide_enable_irq(irq); } -static struct hw_interrupt_type rawhide_irq_type = { +static struct irq_chip rawhide_irq_type = { .typename = "RAWHIDE", .startup = rawhide_startup_irq, .shutdown = rawhide_disable_irq, diff --git a/arch/alpha/kernel/sys_ruffian.c b/arch/alpha/kernel/sys_ruffian.c index f15a329b601..d9f9cfeb993 100644 --- a/arch/alpha/kernel/sys_ruffian.c +++ b/arch/alpha/kernel/sys_ruffian.c @@ -14,6 +14,7 @@ #include <linux/sched.h> #include <linux/pci.h> #include <linux/ioport.h> +#include <linux/timex.h> #include <linux/init.h> #include <asm/ptrace.h> diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c index ce1faa6f1df..fc924637345 100644 --- a/arch/alpha/kernel/sys_rx164.c +++ b/arch/alpha/kernel/sys_rx164.c @@ -72,7 +72,7 @@ rx164_end_irq(unsigned int irq) rx164_enable_irq(irq); } -static struct hw_interrupt_type rx164_irq_type = { +static struct irq_chip rx164_irq_type = { .typename = "RX164", .startup = rx164_startup_irq, .shutdown = rx164_disable_irq, diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c index 9e263256a42..426eb6906d0 100644 --- a/arch/alpha/kernel/sys_sable.c +++ b/arch/alpha/kernel/sys_sable.c @@ -501,7 +501,7 @@ sable_lynx_mask_and_ack_irq(unsigned int irq) spin_unlock(&sable_lynx_irq_lock); } -static struct hw_interrupt_type sable_lynx_irq_type = { +static struct irq_chip sable_lynx_irq_type = { .typename = "SABLE/LYNX", .startup = sable_lynx_startup_irq, .shutdown = sable_lynx_disable_irq, diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index 9bd9a31450c..830318c2166 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -74,7 +74,7 @@ takara_end_irq(unsigned int irq) takara_enable_irq(irq); } -static struct hw_interrupt_type takara_irq_type = { +static struct irq_chip takara_irq_type = { .typename = "TAKARA", .startup = takara_startup_irq, .shutdown = takara_disable_irq, diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c index 8dd239ebdb9..88978fc60f8 100644 --- a/arch/alpha/kernel/sys_titan.c +++ b/arch/alpha/kernel/sys_titan.c @@ -185,7 +185,7 @@ titan_srm_device_interrupt(unsigned long vector) static void __init -init_titan_irqs(struct hw_interrupt_type * ops, int imin, int imax) +init_titan_irqs(struct irq_chip * ops, int imin, int imax) { long i; for (i = imin; i <= imax; ++i) { @@ -194,7 +194,7 @@ init_titan_irqs(struct hw_interrupt_type * ops, int imin, int imax) } } -static struct hw_interrupt_type titan_irq_type = { +static struct irq_chip titan_irq_type = { .typename = "TITAN", .startup = titan_startup_irq, .shutdown = titan_disable_irq, diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index 42c3eede4d0..e91b4c3838a 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -157,7 +157,7 @@ wildfire_end_irq(unsigned int irq) wildfire_enable_irq(irq); } -static struct hw_interrupt_type wildfire_irq_type = { +static struct irq_chip wildfire_irq_type = { .typename = "WILDFIRE", .startup = wildfire_startup_irq, .shutdown = wildfire_disable_irq, diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index a13de49d126..0eab5574942 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -28,9 +28,9 @@ EXPORT_SYMBOL(node_data); #define DBGDCONT(args...) #endif -#define for_each_mem_cluster(memdesc, cluster, i) \ - for ((cluster) = (memdesc)->cluster, (i) = 0; \ - (i) < (memdesc)->numclusters; (i)++, (cluster)++) +#define for_each_mem_cluster(memdesc, _cluster, i) \ + for ((_cluster) = (memdesc)->cluster, (i) = 0; \ + (i) < (memdesc)->numclusters; (i)++, (_cluster)++) static void __init show_mem_layout(void) { diff --git a/arch/arm/kernel/init_task.c b/arch/arm/kernel/init_task.c index e859af34946..3f470866bb8 100644 --- a/arch/arm/kernel/init_task.c +++ b/arch/arm/kernel/init_task.c @@ -14,10 +14,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/avr32/kernel/init_task.c b/arch/avr32/kernel/init_task.c index 993d56ee3cf..57ec9f2dcd9 100644 --- a/arch/avr32/kernel/init_task.c +++ b/arch/avr32/kernel/init_task.c @@ -15,10 +15,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. Must be aligned on an 8192-byte boundary. */ diff --git a/arch/blackfin/include/asm/kmap_types.h b/arch/blackfin/include/asm/kmap_types.h index e215f710497..0a88622339e 100644 --- a/arch/blackfin/include/asm/kmap_types.h +++ b/arch/blackfin/include/asm/kmap_types.h @@ -1,21 +1,6 @@ #ifndef _ASM_KMAP_TYPES_H #define _ASM_KMAP_TYPES_H -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif diff --git a/arch/blackfin/kernel/init_task.c b/arch/blackfin/kernel/init_task.c index 2c228c02097..c26c34de9f3 100644 --- a/arch/blackfin/kernel/init_task.c +++ b/arch/blackfin/kernel/init_task.c @@ -35,10 +35,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); - -struct mm_struct init_mm = INIT_MM(init_mm); -EXPORT_SYMBOL(init_mm); - /* * Initial task structure. * diff --git a/arch/cris/include/asm/kmap_types.h b/arch/cris/include/asm/kmap_types.h index 492988cb907..d2d643c4ea5 100644 --- a/arch/cris/include/asm/kmap_types.h +++ b/arch/cris/include/asm/kmap_types.h @@ -5,21 +5,6 @@ * is actually used on cris. */ -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index 4df0b320d52..51dcd04d277 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -38,10 +38,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/frv/kernel/init_task.c b/arch/frv/kernel/init_task.c index 29429a8b7f6..1d3df1d9495 100644 --- a/arch/frv/kernel/init_task.c +++ b/arch/frv/kernel/init_task.c @@ -12,10 +12,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/h8300/include/asm/kmap_types.h b/arch/h8300/include/asm/kmap_types.h index 1ec8a342712..be12a716011 100644 --- a/arch/h8300/include/asm/kmap_types.h +++ b/arch/h8300/include/asm/kmap_types.h @@ -1,21 +1,6 @@ #ifndef _ASM_H8300_KMAP_TYPES_H #define _ASM_H8300_KMAP_TYPES_H -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif diff --git a/arch/h8300/kernel/init_task.c b/arch/h8300/kernel/init_task.c index cb5dc552da9..089c65ed6eb 100644 --- a/arch/h8300/kernel/init_task.c +++ b/arch/h8300/kernel/init_task.c @@ -14,10 +14,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial task structure. * 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/include/asm/kmap_types.h b/arch/ia64/include/asm/kmap_types.h index 5d1658aa2b3..05d5f999610 100644 --- a/arch/ia64/include/asm/kmap_types.h +++ b/arch/ia64/include/asm/kmap_types.h @@ -1,30 +1,12 @@ #ifndef _ASM_IA64_KMAP_TYPES_H #define _ASM_IA64_KMAP_TYPES_H - #ifdef CONFIG_DEBUG_HIGHMEM -# define D(n) __KM_FENCE_##n , -#else -# define D(n) +#define __WITH_KM_FENCE #endif -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_IRQ0, -D(10) KM_IRQ1, -D(11) KM_SOFTIRQ0, -D(12) KM_SOFTIRQ1, -D(13) KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> -#undef D +#undef __WITH_KM_FENCE #endif /* _ASM_IA64_KMAP_TYPES_H */ diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c index 5b0e830c6f3..c475fc281be 100644 --- a/arch/ia64/kernel/init_task.c +++ b/arch/ia64/kernel/init_task.c @@ -19,10 +19,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial task structure. * 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/perfmon.c b/arch/ia64/kernel/perfmon.c index 8a06dc48059..bdc176cb5e8 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -5595,7 +5595,7 @@ pfm_interrupt_handler(int irq, void *arg) (*pfm_alt_intr_handler->handler)(irq, arg, regs); } - put_cpu_no_resched(); + put_cpu(); return IRQ_HANDLED; } 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/m32r/include/asm/kmap_types.h b/arch/m32r/include/asm/kmap_types.h index fa94dc6410e..4cdb5e3a06b 100644 --- a/arch/m32r/include/asm/kmap_types.h +++ b/arch/m32r/include/asm/kmap_types.h @@ -2,28 +2,11 @@ #define __M32R_KMAP_TYPES_H #ifdef CONFIG_DEBUG_HIGHMEM -# define D(n) __KM_FENCE_##n , -#else -# define D(n) +#define __WITH_KM_FENCE #endif -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_IRQ0, -D(10) KM_IRQ1, -D(11) KM_SOFTIRQ0, -D(12) KM_SOFTIRQ1, -D(13) KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> -#undef D +#undef __WITH_KM_FENCE #endif /* __M32R_KMAP_TYPES_H */ diff --git a/arch/m32r/kernel/init_task.c b/arch/m32r/kernel/init_task.c index 016885c6f26..fce57e5d3f9 100644 --- a/arch/m32r/kernel/init_task.c +++ b/arch/m32r/kernel/init_task.c @@ -13,10 +13,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/m32r/mm/discontig.c b/arch/m32r/mm/discontig.c index 7daf897292c..b7a78ad429b 100644 --- a/arch/m32r/mm/discontig.c +++ b/arch/m32r/mm/discontig.c @@ -154,9 +154,9 @@ unsigned long __init zone_sizes_init(void) * Use all area of internal RAM. * see __alloc_pages() */ - NODE_DATA(1)->node_zones->pages_min = 0; - NODE_DATA(1)->node_zones->pages_low = 0; - NODE_DATA(1)->node_zones->pages_high = 0; + NODE_DATA(1)->node_zones->watermark[WMARK_MIN] = 0; + NODE_DATA(1)->node_zones->watermark[WMARK_LOW] = 0; + NODE_DATA(1)->node_zones->watermark[WMARK_HIGH] = 0; return holes; } diff --git a/arch/m32r/platforms/m32104ut/setup.c b/arch/m32r/platforms/m32104ut/setup.c index 98138b4e922..922fdfdadea 100644 --- a/arch/m32r/platforms/m32104ut/setup.c +++ b/arch/m32r/platforms/m32104ut/setup.c @@ -63,7 +63,7 @@ static void shutdown_m32104ut_irq(unsigned int irq) outl(M32R_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type m32104ut_irq_type = +static struct irq_chip m32104ut_irq_type = { .typename = "M32104UT-IRQ", .startup = startup_m32104ut_irq, diff --git a/arch/m32r/platforms/m32700ut/setup.c b/arch/m32r/platforms/m32700ut/setup.c index 77b0ae9379e..9c1bc7487c1 100644 --- a/arch/m32r/platforms/m32700ut/setup.c +++ b/arch/m32r/platforms/m32700ut/setup.c @@ -69,7 +69,7 @@ static void shutdown_m32700ut_irq(unsigned int irq) outl(M32R_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type m32700ut_irq_type = +static struct irq_chip m32700ut_irq_type = { .typename = "M32700UT-IRQ", .startup = startup_m32700ut_irq, @@ -146,7 +146,7 @@ static void shutdown_m32700ut_pld_irq(unsigned int irq) outw(PLD_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type m32700ut_pld_irq_type = +static struct irq_chip m32700ut_pld_irq_type = { .typename = "M32700UT-PLD-IRQ", .startup = startup_m32700ut_pld_irq, @@ -215,7 +215,7 @@ static void shutdown_m32700ut_lanpld_irq(unsigned int irq) outw(PLD_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type m32700ut_lanpld_irq_type = +static struct irq_chip m32700ut_lanpld_irq_type = { .typename = "M32700UT-PLD-LAN-IRQ", .startup = startup_m32700ut_lanpld_irq, @@ -284,7 +284,7 @@ static void shutdown_m32700ut_lcdpld_irq(unsigned int irq) outw(PLD_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type m32700ut_lcdpld_irq_type = +static struct irq_chip m32700ut_lcdpld_irq_type = { .typename = "M32700UT-PLD-LCD-IRQ", .startup = startup_m32700ut_lcdpld_irq, diff --git a/arch/m32r/platforms/mappi/setup.c b/arch/m32r/platforms/mappi/setup.c index 3ec087ff221..fb4b17799b6 100644 --- a/arch/m32r/platforms/mappi/setup.c +++ b/arch/m32r/platforms/mappi/setup.c @@ -63,7 +63,7 @@ static void shutdown_mappi_irq(unsigned int irq) outl(M32R_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type mappi_irq_type = +static struct irq_chip mappi_irq_type = { .typename = "MAPPI-IRQ", .startup = startup_mappi_irq, diff --git a/arch/m32r/platforms/mappi2/setup.c b/arch/m32r/platforms/mappi2/setup.c index d87969c6356..6a65eda0a05 100644 --- a/arch/m32r/platforms/mappi2/setup.c +++ b/arch/m32r/platforms/mappi2/setup.c @@ -70,7 +70,7 @@ static void shutdown_mappi2_irq(unsigned int irq) outl(M32R_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type mappi2_irq_type = +static struct irq_chip mappi2_irq_type = { .typename = "MAPPI2-IRQ", .startup = startup_mappi2_irq, diff --git a/arch/m32r/platforms/mappi3/setup.c b/arch/m32r/platforms/mappi3/setup.c index 785b4bd6d9f..9c337aeac94 100644 --- a/arch/m32r/platforms/mappi3/setup.c +++ b/arch/m32r/platforms/mappi3/setup.c @@ -70,7 +70,7 @@ static void shutdown_mappi3_irq(unsigned int irq) outl(M32R_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type mappi3_irq_type = +static struct irq_chip mappi3_irq_type = { .typename = "MAPPI3-IRQ", .startup = startup_mappi3_irq, diff --git a/arch/m32r/platforms/oaks32r/setup.c b/arch/m32r/platforms/oaks32r/setup.c index 6faa5db68e9..ed865741c38 100644 --- a/arch/m32r/platforms/oaks32r/setup.c +++ b/arch/m32r/platforms/oaks32r/setup.c @@ -61,7 +61,7 @@ static void shutdown_oaks32r_irq(unsigned int irq) outl(M32R_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type oaks32r_irq_type = +static struct irq_chip oaks32r_irq_type = { .typename = "OAKS32R-IRQ", .startup = startup_oaks32r_irq, diff --git a/arch/m32r/platforms/opsput/setup.c b/arch/m32r/platforms/opsput/setup.c index fab13fd8542..80d68065701 100644 --- a/arch/m32r/platforms/opsput/setup.c +++ b/arch/m32r/platforms/opsput/setup.c @@ -70,7 +70,7 @@ static void shutdown_opsput_irq(unsigned int irq) outl(M32R_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type opsput_irq_type = +static struct irq_chip opsput_irq_type = { .typename = "OPSPUT-IRQ", .startup = startup_opsput_irq, @@ -147,7 +147,7 @@ static void shutdown_opsput_pld_irq(unsigned int irq) outw(PLD_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type opsput_pld_irq_type = +static struct irq_chip opsput_pld_irq_type = { .typename = "OPSPUT-PLD-IRQ", .startup = startup_opsput_pld_irq, @@ -216,7 +216,7 @@ static void shutdown_opsput_lanpld_irq(unsigned int irq) outw(PLD_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type opsput_lanpld_irq_type = +static struct irq_chip opsput_lanpld_irq_type = { .typename = "OPSPUT-PLD-LAN-IRQ", .startup = startup_opsput_lanpld_irq, @@ -285,7 +285,7 @@ static void shutdown_opsput_lcdpld_irq(unsigned int irq) outw(PLD_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type opsput_lcdpld_irq_type = +static struct irq_chip opsput_lcdpld_irq_type = { "OPSPUT-PLD-LCD-IRQ", startup_opsput_lcdpld_irq, diff --git a/arch/m32r/platforms/usrv/setup.c b/arch/m32r/platforms/usrv/setup.c index 89588d649eb..757302660af 100644 --- a/arch/m32r/platforms/usrv/setup.c +++ b/arch/m32r/platforms/usrv/setup.c @@ -61,7 +61,7 @@ static void shutdown_mappi_irq(unsigned int irq) outl(M32R_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type mappi_irq_type = +static struct irq_chip mappi_irq_type = { .typename = "M32700-IRQ", .startup = startup_mappi_irq, @@ -134,7 +134,7 @@ static void shutdown_m32700ut_pld_irq(unsigned int irq) outw(PLD_ICUCR_ILEVEL7, port); } -static struct hw_interrupt_type m32700ut_pld_irq_type = +static struct irq_chip m32700ut_pld_irq_type = { .typename = "USRV-PLD-IRQ", .startup = startup_m32700ut_pld_irq, diff --git a/arch/m68k/include/asm/kmap_types.h b/arch/m68k/include/asm/kmap_types.h index c843c63d380..3413cc1390e 100644 --- a/arch/m68k/include/asm/kmap_types.h +++ b/arch/m68k/include/asm/kmap_types.h @@ -1,21 +1,6 @@ #ifndef __ASM_M68K_KMAP_TYPES_H #define __ASM_M68K_KMAP_TYPES_H -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif /* __ASM_M68K_KMAP_TYPES_H */ diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index ec37fb56c12..72bad65dba3 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -42,10 +42,6 @@ */ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - union thread_union init_thread_union __attribute__((section(".data.init_task"), aligned(THREAD_SIZE))) = { INIT_THREAD_INFO(init_task) }; diff --git a/arch/m68knommu/kernel/init_task.c b/arch/m68knommu/kernel/init_task.c index fe282de1d59..45e97a207fe 100644 --- a/arch/m68knommu/kernel/init_task.c +++ b/arch/m68knommu/kernel/init_task.c @@ -14,10 +14,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial task structure. * diff --git a/arch/microblaze/include/asm/kmap_types.h b/arch/microblaze/include/asm/kmap_types.h index 4d7e222f5dd..25975252d83 100644 --- a/arch/microblaze/include/asm/kmap_types.h +++ b/arch/microblaze/include/asm/kmap_types.h @@ -1,29 +1,6 @@ -/* - * Copyright (C) 2006 Atmark Techno, Inc. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - #ifndef _ASM_MICROBLAZE_KMAP_TYPES_H #define _ASM_MICROBLAZE_KMAP_TYPES_H -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR, -}; +#include <asm-generic/kmap_types.h> #endif /* _ASM_MICROBLAZE_KMAP_TYPES_H */ diff --git a/arch/mips/include/asm/i8253.h b/arch/mips/include/asm/i8253.h index 5dabc870b32..032ca73f181 100644 --- a/arch/mips/include/asm/i8253.h +++ b/arch/mips/include/asm/i8253.h @@ -12,8 +12,6 @@ #define PIT_CH0 0x40 #define PIT_CH2 0x42 -#define PIT_TICK_RATE 1193182UL - extern spinlock_t i8253_lock; extern void setup_pit_timer(void); diff --git a/arch/mips/include/asm/kmap_types.h b/arch/mips/include/asm/kmap_types.h index 806aae3c533..58e91ed0388 100644 --- a/arch/mips/include/asm/kmap_types.h +++ b/arch/mips/include/asm/kmap_types.h @@ -1,30 +1,12 @@ #ifndef _ASM_KMAP_TYPES_H #define _ASM_KMAP_TYPES_H - #ifdef CONFIG_DEBUG_HIGHMEM -# define D(n) __KM_FENCE_##n , -#else -# define D(n) +#define __WITH_KM_FENCE #endif -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_IRQ0, -D(10) KM_IRQ1, -D(11) KM_SOFTIRQ0, -D(12) KM_SOFTIRQ1, -D(13) KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> -#undef D +#undef __WITH_KM_FENCE #endif diff --git a/arch/mips/kernel/init_task.c b/arch/mips/kernel/init_task.c index 149cd914526..5b457a40c78 100644 --- a/arch/mips/kernel/init_task.c +++ b/arch/mips/kernel/init_task.c @@ -11,10 +11,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/mn10300/include/asm/kmap_types.h b/arch/mn10300/include/asm/kmap_types.h index 3398f9f3560..76d093b58d4 100644 --- a/arch/mn10300/include/asm/kmap_types.h +++ b/arch/mn10300/include/asm/kmap_types.h @@ -1,31 +1,6 @@ -/* MN10300 kmap_atomic() slot IDs - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ #ifndef _ASM_KMAP_TYPES_H #define _ASM_KMAP_TYPES_H -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif /* _ASM_KMAP_TYPES_H */ diff --git a/arch/mn10300/kernel/init_task.c b/arch/mn10300/kernel/init_task.c index 5ac3566f8c9..80d423b80af 100644 --- a/arch/mn10300/kernel/init_task.c +++ b/arch/mn10300/kernel/init_task.c @@ -20,9 +20,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/parisc/include/asm/kmap_types.h b/arch/parisc/include/asm/kmap_types.h index 806aae3c533..58e91ed0388 100644 --- a/arch/parisc/include/asm/kmap_types.h +++ b/arch/parisc/include/asm/kmap_types.h @@ -1,30 +1,12 @@ #ifndef _ASM_KMAP_TYPES_H #define _ASM_KMAP_TYPES_H - #ifdef CONFIG_DEBUG_HIGHMEM -# define D(n) __KM_FENCE_##n , -#else -# define D(n) +#define __WITH_KM_FENCE #endif -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_IRQ0, -D(10) KM_IRQ1, -D(11) KM_SOFTIRQ0, -D(12) KM_SOFTIRQ1, -D(13) KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> -#undef D +#undef __WITH_KM_FENCE #endif diff --git a/arch/parisc/kernel/init_task.c b/arch/parisc/kernel/init_task.c index 1e25a45d64c..82974b20fc1 100644 --- a/arch/parisc/kernel/init_task.c +++ b/arch/parisc/kernel/init_task.c @@ -36,10 +36,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial task structure. * diff --git a/arch/powerpc/include/asm/8253pit.h b/arch/powerpc/include/asm/8253pit.h index b70d6e53b30..a71c9c1455a 100644 --- a/arch/powerpc/include/asm/8253pit.h +++ b/arch/powerpc/include/asm/8253pit.h @@ -1,10 +1,3 @@ -#ifndef _ASM_POWERPC_8253PIT_H -#define _ASM_POWERPC_8253PIT_H - /* * 8253/8254 Programmable Interval Timer */ - -#define PIT_TICK_RATE 1193182UL - -#endif /* _ASM_POWERPC_8253PIT_H */ diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c index 688b329800b..ffc4253fef5 100644 --- a/arch/powerpc/kernel/init_task.c +++ b/arch/powerpc/kernel/init_task.c @@ -9,10 +9,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 2f0e64b5364..ef6f64950e9 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -44,10 +44,7 @@ #include <asm/sections.h> #include <asm/machdep.h> -#ifdef CONFIG_LOGO_LINUX_CLUT224 #include <linux/linux_logo.h> -extern const struct linux_logo logo_linux_clut224; -#endif /* * Properties whose value is longer than this get excluded from our 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/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index 9abd210d87c..8547e86bfb4 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -752,17 +752,8 @@ static int __init init_spu_base(void) goto out_unregister_sysdev_class; } - if (ret > 0) { - /* - * We cannot put the forward declaration in - * <linux/linux_logo.h> because of conflicting session type - * conflicts for const and __initdata with different compiler - * versions - */ - extern const struct linux_logo logo_spe_clut224; - + if (ret > 0) fb_append_extra_logo(&logo_spe_clut224, ret); - } mutex_lock(&spu_full_list_mutex); xmon_register_spus(&spu_full_list); diff --git a/arch/s390/include/asm/kmap_types.h b/arch/s390/include/asm/kmap_types.h index fd157464822..94ec3ee0798 100644 --- a/arch/s390/include/asm/kmap_types.h +++ b/arch/s390/include/asm/kmap_types.h @@ -2,22 +2,7 @@ #ifndef _ASM_KMAP_TYPES_H #define _ASM_KMAP_TYPES_H -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif #endif /* __KERNEL__ */ diff --git a/arch/s390/kernel/init_task.c b/arch/s390/kernel/init_task.c index 7db95c0b869..fe787f9e5f3 100644 --- a/arch/s390/kernel/init_task.c +++ b/arch/s390/kernel/init_task.c @@ -18,10 +18,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/sh/include/asm/kmap_types.h b/arch/sh/include/asm/kmap_types.h index 84d565c696b..5962b08b6dd 100644 --- a/arch/sh/include/asm/kmap_types.h +++ b/arch/sh/include/asm/kmap_types.h @@ -3,30 +3,12 @@ /* Dummy header just to define km_type. */ - #ifdef CONFIG_DEBUG_HIGHMEM -# define D(n) __KM_FENCE_##n , -#else -# define D(n) +#define __WITH_KM_FENCE #endif -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_IRQ0, -D(10) KM_IRQ1, -D(11) KM_SOFTIRQ0, -D(12) KM_SOFTIRQ1, -D(13) KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> -#undef D +#undef __WITH_KM_FENCE #endif diff --git a/arch/sh/kernel/init_task.c b/arch/sh/kernel/init_task.c index 80c35ff71d5..1719957c0a6 100644 --- a/arch/sh/kernel/init_task.c +++ b/arch/sh/kernel/init_task.c @@ -10,9 +10,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); struct pt_regs fake_swapper_regs; -struct mm_struct init_mm = INIT_MM(init_mm); -EXPORT_SYMBOL(init_mm); - /* * Initial thread structure. * diff --git a/arch/sparc/include/asm/kmap_types.h b/arch/sparc/include/asm/kmap_types.h index 602f5e034f7..aad21745fbb 100644 --- a/arch/sparc/include/asm/kmap_types.h +++ b/arch/sparc/include/asm/kmap_types.h @@ -5,21 +5,6 @@ * is actually used on sparc. -DaveM */ -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif diff --git a/arch/sparc/kernel/init_task.c b/arch/sparc/kernel/init_task.c index f28cb8278e9..28125c5b3d3 100644 --- a/arch/sparc/kernel/init_task.c +++ b/arch/sparc/kernel/init_task.c @@ -10,10 +10,7 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); struct task_struct init_task = INIT_TASK(init_task); - -EXPORT_SYMBOL(init_mm); EXPORT_SYMBOL(init_task); /* .text section in head.S is aligned at 8k boundary and this gets linked diff --git a/arch/um/include/shared/init.h b/arch/um/include/shared/init.h index 37dd097c16c..b3906f860a8 100644 --- a/arch/um/include/shared/init.h +++ b/arch/um/include/shared/init.h @@ -27,7 +27,7 @@ * sign followed by value, e.g.: * * static int init_variable __initdata = 0; - * static char linux_logo[] __initdata = { 0x32, 0x36, ... }; + * static const char linux_logo[] __initconst = { 0x32, 0x36, ... }; * * Don't forget to initialize data not at file scope, i.e. within a function, * as gcc otherwise puts the data into the bss section and not into the init diff --git a/arch/um/include/shared/net_user.h b/arch/um/include/shared/net_user.h index 63bee158cd8..3dabbe128e4 100644 --- a/arch/um/include/shared/net_user.h +++ b/arch/um/include/shared/net_user.h @@ -8,7 +8,7 @@ #define ETH_ADDR_LEN (6) #define ETH_HEADER_ETHERTAP (16) -#define ETH_HEADER_OTHER (14) +#define ETH_HEADER_OTHER (26) /* 14 for ethernet + VLAN + MPLS for crazy people */ #define ETH_MAX_PACKET (1500) #define UML_NET_VERSION (4) diff --git a/arch/um/kernel/init_task.c b/arch/um/kernel/init_task.c index 806d381947b..b25121b537d 100644 --- a/arch/um/kernel/init_task.c +++ b/arch/um/kernel/init_task.c @@ -10,11 +10,8 @@ #include "linux/mqueue.h" #include "asm/uaccess.h" -struct mm_struct init_mm = INIT_MM(init_mm); static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -EXPORT_SYMBOL(init_mm); - /* * Initial task structure. * diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 336b6156907..454cdb43e35 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -358,7 +358,7 @@ EXPORT_SYMBOL(um_request_irq); EXPORT_SYMBOL(reactivate_fd); /* - * hw_interrupt_type must define (startup || enable) && + * irq_chip must define (startup || enable) && * (shutdown || disable) && end */ static void dummy(unsigned int irq) @@ -366,7 +366,7 @@ static void dummy(unsigned int irq) } /* This is used for everything else than the timer. */ -static struct hw_interrupt_type normal_irq_type = { +static struct irq_chip normal_irq_type = { .typename = "SIGIO", .release = free_irq_by_irq_and_dev, .disable = dummy, @@ -375,7 +375,7 @@ static struct hw_interrupt_type normal_irq_type = { .end = dummy }; -static struct hw_interrupt_type SIGVTALRM_irq_type = { +static struct irq_chip SIGVTALRM_irq_type = { .typename = "SIGVTALRM", .release = free_irq_by_irq_and_dev, .shutdown = dummy, /* never called */ diff --git a/arch/um/sys-i386/stub.S b/arch/um/sys-i386/stub.S index c41b04bf5fa..54a36ec20cb 100644 --- a/arch/um/sys-i386/stub.S +++ b/arch/um/sys-i386/stub.S @@ -1,7 +1,7 @@ #include "as-layout.h" .globl syscall_stub -.section .__syscall_stub, "x" +.section .__syscall_stub, "ax" .globl batch_syscall_stub batch_syscall_stub: diff --git a/arch/um/sys-x86_64/asm/elf.h b/arch/um/sys-x86_64/asm/elf.h index 6e8a9195e95..04b9e87c8da 100644 --- a/arch/um/sys-x86_64/asm/elf.h +++ b/arch/um/sys-x86_64/asm/elf.h @@ -66,28 +66,28 @@ typedef struct user_i387_struct elf_fpregset_t; PT_REGS_R15(regs) = 0; \ } while (0) -#define ELF_CORE_COPY_REGS(pr_reg, regs) \ - (pr_reg)[0] = (regs)->regs.gp[0]; \ - (pr_reg)[1] = (regs)->regs.gp[1]; \ - (pr_reg)[2] = (regs)->regs.gp[2]; \ - (pr_reg)[3] = (regs)->regs.gp[3]; \ - (pr_reg)[4] = (regs)->regs.gp[4]; \ - (pr_reg)[5] = (regs)->regs.gp[5]; \ - (pr_reg)[6] = (regs)->regs.gp[6]; \ - (pr_reg)[7] = (regs)->regs.gp[7]; \ - (pr_reg)[8] = (regs)->regs.gp[8]; \ - (pr_reg)[9] = (regs)->regs.gp[9]; \ - (pr_reg)[10] = (regs)->regs.gp[10]; \ - (pr_reg)[11] = (regs)->regs.gp[11]; \ - (pr_reg)[12] = (regs)->regs.gp[12]; \ - (pr_reg)[13] = (regs)->regs.gp[13]; \ - (pr_reg)[14] = (regs)->regs.gp[14]; \ - (pr_reg)[15] = (regs)->regs.gp[15]; \ - (pr_reg)[16] = (regs)->regs.gp[16]; \ - (pr_reg)[17] = (regs)->regs.gp[17]; \ - (pr_reg)[18] = (regs)->regs.gp[18]; \ - (pr_reg)[19] = (regs)->regs.gp[19]; \ - (pr_reg)[20] = (regs)->regs.gp[20]; \ +#define ELF_CORE_COPY_REGS(pr_reg, _regs) \ + (pr_reg)[0] = (_regs)->regs.gp[0]; \ + (pr_reg)[1] = (_regs)->regs.gp[1]; \ + (pr_reg)[2] = (_regs)->regs.gp[2]; \ + (pr_reg)[3] = (_regs)->regs.gp[3]; \ + (pr_reg)[4] = (_regs)->regs.gp[4]; \ + (pr_reg)[5] = (_regs)->regs.gp[5]; \ + (pr_reg)[6] = (_regs)->regs.gp[6]; \ + (pr_reg)[7] = (_regs)->regs.gp[7]; \ + (pr_reg)[8] = (_regs)->regs.gp[8]; \ + (pr_reg)[9] = (_regs)->regs.gp[9]; \ + (pr_reg)[10] = (_regs)->regs.gp[10]; \ + (pr_reg)[11] = (_regs)->regs.gp[11]; \ + (pr_reg)[12] = (_regs)->regs.gp[12]; \ + (pr_reg)[13] = (_regs)->regs.gp[13]; \ + (pr_reg)[14] = (_regs)->regs.gp[14]; \ + (pr_reg)[15] = (_regs)->regs.gp[15]; \ + (pr_reg)[16] = (_regs)->regs.gp[16]; \ + (pr_reg)[17] = (_regs)->regs.gp[17]; \ + (pr_reg)[18] = (_regs)->regs.gp[18]; \ + (pr_reg)[19] = (_regs)->regs.gp[19]; \ + (pr_reg)[20] = (_regs)->regs.gp[20]; \ (pr_reg)[21] = current->thread.arch.fs; \ (pr_reg)[22] = 0; \ (pr_reg)[23] = 0; \ diff --git a/arch/um/sys-x86_64/stub.S b/arch/um/sys-x86_64/stub.S index 6d9edf9fabc..20e4a96a6dc 100644 --- a/arch/um/sys-x86_64/stub.S +++ b/arch/um/sys-x86_64/stub.S @@ -1,7 +1,7 @@ #include "as-layout.h" .globl syscall_stub -.section .__syscall_stub, "x" +.section .__syscall_stub, "ax" syscall_stub: syscall /* We don't have 64-bit constants, so this constructs the address diff --git a/arch/x86/include/asm/kmap_types.h b/arch/x86/include/asm/kmap_types.h index 5759c165a5c..9e00a731a7f 100644 --- a/arch/x86/include/asm/kmap_types.h +++ b/arch/x86/include/asm/kmap_types.h @@ -2,28 +2,11 @@ #define _ASM_X86_KMAP_TYPES_H #if defined(CONFIG_X86_32) && defined(CONFIG_DEBUG_HIGHMEM) -# define D(n) __KM_FENCE_##n , -#else -# define D(n) +#define __WITH_KM_FENCE #endif -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_IRQ0, -D(10) KM_IRQ1, -D(11) KM_SOFTIRQ0, -D(12) KM_SOFTIRQ1, -D(13) KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> -#undef D +#undef __WITH_KM_FENCE #endif /* _ASM_X86_KMAP_TYPES_H */ diff --git a/arch/x86/include/asm/timex.h b/arch/x86/include/asm/timex.h index b5c9d45c981..1375cfc9396 100644 --- a/arch/x86/include/asm/timex.h +++ b/arch/x86/include/asm/timex.h @@ -4,9 +4,7 @@ #include <asm/processor.h> #include <asm/tsc.h> -/* The PIT ticks at this frequency (in HZ): */ -#define PIT_TICK_RATE 1193182 - +/* Assume we use the PIT time source for the clock tick */ #define CLOCK_TICK_RATE PIT_TICK_RATE #define ARCH_HAS_READ_CURRENT_TIMER diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3ffdcfa9abd..9fa33886c0d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -487,7 +487,6 @@ out: static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; - static int printed; int i; for (i = 0; i < X86_VENDOR_NUM; i++) { @@ -504,13 +503,9 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) } } - if (!printed) { - printed++; - printk(KERN_ERR - "CPU: vendor_id '%s' unknown, using generic init.\n", v); - - printk(KERN_ERR "CPU: Your system may be unstable.\n"); - } + printk_once(KERN_ERR + "CPU: vendor_id '%s' unknown, using generic init.\n" \ + "CPU: Your system may be unstable.\n", v); c->x86_vendor = X86_VENDOR_UNKNOWN; this_cpu = &default_cpu; diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index c2e0bb0890d..5cf36c053ac 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -7,6 +7,7 @@ #include <linux/spinlock.h> #include <linux/jiffies.h> #include <linux/module.h> +#include <linux/timex.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/io.h> diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c index df3bf269bea..270ff83efc1 100644 --- a/arch/x86/kernel/init_task.c +++ b/arch/x86/kernel/init_task.c @@ -12,7 +12,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); /* * Initial thread structure. diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 3e1c057e98f..ae3180c506a 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -9,6 +9,7 @@ #include <linux/delay.h> #include <linux/clocksource.h> #include <linux/percpu.h> +#include <linux/timex.h> #include <asm/hpet.h> #include <asm/timer.h> 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/arch/xtensa/include/asm/kmap_types.h b/arch/xtensa/include/asm/kmap_types.h index 9e822d2e3bc..11c687e527f 100644 --- a/arch/xtensa/include/asm/kmap_types.h +++ b/arch/xtensa/include/asm/kmap_types.h @@ -1,31 +1,6 @@ -/* - * include/asm-xtensa/kmap_types.h - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2001 - 2005 Tensilica Inc. - */ - #ifndef _XTENSA_KMAP_TYPES_H #define _XTENSA_KMAP_TYPES_H -enum km_type { - KM_BOUNCE_READ, - KM_SKB_SUNRPC_DATA, - KM_SKB_DATA_SOFTIRQ, - KM_USER0, - KM_USER1, - KM_BIO_SRC_IRQ, - KM_BIO_DST_IRQ, - KM_PTE0, - KM_PTE1, - KM_IRQ0, - KM_IRQ1, - KM_SOFTIRQ0, - KM_SOFTIRQ1, - KM_TYPE_NR -}; +#include <asm-generic/kmap_types.h> #endif /* _XTENSA_KMAP_TYPES_H */ diff --git a/arch/xtensa/kernel/init_task.c b/arch/xtensa/kernel/init_task.c index e07f5c9fcd3..c4302f0e4ba 100644 --- a/arch/xtensa/kernel/init_task.c +++ b/arch/xtensa/kernel/init_task.c @@ -23,10 +23,6 @@ static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - union thread_union init_thread_union __attribute__((__section__(".data.init_task"))) = { INIT_THREAD_INFO(init_task) }; diff --git a/drivers/Kconfig b/drivers/Kconfig index 00cf9553f74..a442c8f29fc 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -104,6 +104,8 @@ source "drivers/auxdisplay/Kconfig" source "drivers/uio/Kconfig" +source "drivers/vlynq/Kconfig" + source "drivers/xen/Kconfig" source "drivers/staging/Kconfig" diff --git a/drivers/Makefile b/drivers/Makefile index 9e7d4e56c85..00b44f4ccf0 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -105,6 +105,7 @@ obj-$(CONFIG_PPC_PS3) += ps3/ obj-$(CONFIG_OF) += of/ obj-$(CONFIG_SSB) += ssb/ obj-$(CONFIG_VIRTIO) += virtio/ +obj-$(CONFIG_VLYNQ) += vlynq/ obj-$(CONFIG_STAGING) += staging/ obj-y += platform/ obj-y += ieee802154/ diff --git a/drivers/base/node.c b/drivers/base/node.c index 40b809742a1..91d4087b403 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -72,10 +72,8 @@ static ssize_t node_read_meminfo(struct sys_device * dev, "Node %d Inactive(anon): %8lu kB\n" "Node %d Active(file): %8lu kB\n" "Node %d Inactive(file): %8lu kB\n" -#ifdef CONFIG_UNEVICTABLE_LRU "Node %d Unevictable: %8lu kB\n" "Node %d Mlocked: %8lu kB\n" -#endif #ifdef CONFIG_HIGHMEM "Node %d HighTotal: %8lu kB\n" "Node %d HighFree: %8lu kB\n" @@ -105,10 +103,8 @@ static ssize_t node_read_meminfo(struct sys_device * dev, nid, K(node_page_state(nid, NR_INACTIVE_ANON)), nid, K(node_page_state(nid, NR_ACTIVE_FILE)), nid, K(node_page_state(nid, NR_INACTIVE_FILE)), -#ifdef CONFIG_UNEVICTABLE_LRU nid, K(node_page_state(nid, NR_UNEVICTABLE)), nid, K(node_page_state(nid, NR_MLOCK)), -#endif #ifdef CONFIG_HIGHMEM nid, K(i.totalhigh), nid, K(i.freehigh), diff --git a/drivers/char/vt.c b/drivers/char/vt.c index c796a86ab7f..d9113b4c76e 100644 --- a/drivers/char/vt.c +++ b/drivers/char/vt.c @@ -171,8 +171,9 @@ int do_poke_blanked_console; int console_blanked; static int vesa_blank_mode; /* 0:none 1:suspendV 2:suspendH 3:powerdown */ -static int blankinterval = 10*60*HZ; static int vesa_off_interval; +static int blankinterval = 10*60; +core_param(consoleblank, blankinterval, int, 0444); static DECLARE_WORK(console_work, console_callback); @@ -1485,7 +1486,7 @@ static void setterm_command(struct vc_data *vc) update_attr(vc); break; case 9: /* set blanking interval */ - blankinterval = ((vc->vc_par[1] < 60) ? vc->vc_par[1] : 60) * 60 * HZ; + blankinterval = ((vc->vc_par[1] < 60) ? vc->vc_par[1] : 60) * 60; poke_blanked_console(); break; case 10: /* set bell frequency in Hz */ @@ -2871,7 +2872,7 @@ static int __init con_init(void) if (blankinterval) { blank_state = blank_normal_wait; - mod_timer(&console_timer, jiffies + blankinterval); + mod_timer(&console_timer, jiffies + (blankinterval * HZ)); } for (currcons = 0; currcons < MIN_NR_CONSOLES; currcons++) { @@ -3677,7 +3678,7 @@ void do_unblank_screen(int leaving_gfx) return; /* but leave console_blanked != 0 */ if (blankinterval) { - mod_timer(&console_timer, jiffies + blankinterval); + mod_timer(&console_timer, jiffies + (blankinterval * HZ)); blank_state = blank_normal_wait; } @@ -3711,7 +3712,7 @@ void unblank_screen(void) static void blank_screen_t(unsigned long dummy) { if (unlikely(!keventd_up())) { - mod_timer(&console_timer, jiffies + blankinterval); + mod_timer(&console_timer, jiffies + (blankinterval * HZ)); return; } blank_timer_expired = 1; @@ -3741,7 +3742,7 @@ void poke_blanked_console(void) if (console_blanked) unblank_screen(); else if (blankinterval) { - mod_timer(&console_timer, jiffies + blankinterval); + mod_timer(&console_timer, jiffies + (blankinterval * HZ)); blank_state = blank_normal_wait; } } diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index 40bd8c61c7d..72a633a6ec9 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -18,6 +18,7 @@ #include <linux/acpi_pmtmr.h> #include <linux/clocksource.h> +#include <linux/timex.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/pci.h> diff --git a/drivers/eisa/eisa.ids b/drivers/eisa/eisa.ids index ed69837d8b7..6cbb7a51443 100644 --- a/drivers/eisa/eisa.ids +++ b/drivers/eisa/eisa.ids @@ -1140,6 +1140,11 @@ NON0301 "c't Universale Graphic Adapter" NON0401 "c't Universal Ethernet Adapter" NON0501 "c't Universal 16-Bit Sound Adapter" NON0601 "c't Universal 8-Bit Adapter" +NPI0120 "Network Peripherals NP-EISA-1 FDDI Interface" +NPI0221 "Network Peripherals NP-EISA-2 FDDI Interface" +NPI0223 "Network Peripherals NP-EISA-2E Enhanced FDDI Interface" +NPI0301 "Network Peripherals NP-EISA-3 FDDI Interface" +NPI0303 "Network Peripherals NP-EISA-3E Enhanced FDDI Interface" NSS0011 "Newport Systems Solutions WNIC Adapter" NVL0701 "Novell NE3200 Bus Master Ethernet" NVL0702 "Novell NE3200T Bus Master Ethernet" diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 05aa2d406ac..d5ea8a68d33 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -31,8 +31,12 @@ * information is necessary as for the resource tree. */ struct firmware_map_entry { - resource_size_t start; /* start of the memory range */ - resource_size_t end; /* end of the memory range (incl.) */ + /* + * start and end must be u64 rather than resource_size_t, because e820 + * resources can lie at addresses above 4G. + */ + u64 start; /* start of the memory range */ + u64 end; /* end of the memory range (incl.) */ const char *type; /* type of the memory range */ struct list_head list; /* entry for the linked list */ struct kobject kobj; /* kobject for each entry */ @@ -101,7 +105,7 @@ static LIST_HEAD(map_entries); * Common implementation of firmware_map_add() and firmware_map_add_early() * which expects a pre-allocated struct firmware_map_entry. **/ -static int firmware_map_add_entry(resource_size_t start, resource_size_t end, +static int firmware_map_add_entry(u64 start, u64 end, const char *type, struct firmware_map_entry *entry) { @@ -132,8 +136,7 @@ static int firmware_map_add_entry(resource_size_t start, resource_size_t end, * * Returns 0 on success, or -ENOMEM if no memory could be allocated. **/ -int firmware_map_add(resource_size_t start, resource_size_t end, - const char *type) +int firmware_map_add(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; @@ -157,8 +160,7 @@ int firmware_map_add(resource_size_t start, resource_size_t end, * * Returns 0 on success, or -ENOMEM if no memory could be allocated. **/ -int __init firmware_map_add_early(resource_size_t start, resource_size_t end, - const char *type) +int __init firmware_map_add_early(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index 0ecf6b76a40..8e28e5993df 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -504,6 +504,14 @@ static int intelfb_create(struct drm_device *dev, uint32_t fb_width, info->fbops = &intelfb_ops; info->fix.line_length = fb->pitch; + + /* setup aperture base/size for vesafb takeover */ + info->aperture_base = dev->mode_config.fb_base; + if (IS_I9XX(dev)) + info->aperture_size = pci_resource_len(dev->pdev, 2); + else + info->aperture_size = pci_resource_len(dev->pdev, 0); + info->fix.smem_start = dev->mode_config.fb_base + obj_priv->gtt_offset; info->fix.smem_len = size; diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index f8090e137fe..2d5016691d4 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -950,6 +950,7 @@ config SENSORS_HDAPS config SENSORS_LIS3LV02D tristate "STMicroeletronics LIS3LV02Dx three-axis digital accelerometer" depends on ACPI && INPUT + select INPUT_POLLDEV select NEW_LEDS select LEDS_CLASS default n @@ -977,6 +978,7 @@ config SENSORS_LIS3LV02D config SENSORS_LIS3_SPI tristate "STMicroeletronics LIS3LV02Dx three-axis digital accelerometer (SPI)" depends on !ACPI && SPI_MASTER && INPUT + select INPUT_POLLDEV default n help This driver provides support for the LIS3LV02Dx accelerometer connected diff --git a/drivers/hwmon/hp_accel.c b/drivers/hwmon/hp_accel.c index abca7e9f953..6679854c85b 100644 --- a/drivers/hwmon/hp_accel.c +++ b/drivers/hwmon/hp_accel.c @@ -27,9 +27,6 @@ #include <linux/types.h> #include <linux/platform_device.h> #include <linux/interrupt.h> -#include <linux/input.h> -#include <linux/kthread.h> -#include <linux/semaphore.h> #include <linux/delay.h> #include <linux/wait.h> #include <linux/poll.h> @@ -161,6 +158,7 @@ static struct axis_conversion lis3lv02d_axis_normal = {1, 2, 3}; static struct axis_conversion lis3lv02d_axis_y_inverted = {1, -2, 3}; static struct axis_conversion lis3lv02d_axis_x_inverted = {-1, 2, 3}; static struct axis_conversion lis3lv02d_axis_z_inverted = {1, 2, -3}; +static struct axis_conversion lis3lv02d_axis_xy_swap = {2, 1, 3}; static struct axis_conversion lis3lv02d_axis_xy_rotated_left = {-2, 1, 3}; static struct axis_conversion lis3lv02d_axis_xy_rotated_left_usd = {-2, 1, -3}; static struct axis_conversion lis3lv02d_axis_xy_swap_inverted = {-2, -1, 3}; @@ -194,13 +192,16 @@ static struct dmi_system_id lis3lv02d_dmi_ids[] = { AXIS_DMI_MATCH("NX9420", "HP Compaq nx9420", x_inverted), AXIS_DMI_MATCH("NW9440", "HP Compaq nw9440", x_inverted), AXIS_DMI_MATCH("NC2510", "HP Compaq 2510", y_inverted), + AXIS_DMI_MATCH("NC2710", "HP Compaq 2710", xy_swap), AXIS_DMI_MATCH("NC8510", "HP Compaq 8510", xy_swap_inverted), AXIS_DMI_MATCH("HP2133", "HP 2133", xy_rotated_left), AXIS_DMI_MATCH("HP2140", "HP 2140", xy_swap_inverted), AXIS_DMI_MATCH("NC653x", "HP Compaq 653", xy_rotated_left_usd), AXIS_DMI_MATCH("NC673x", "HP Compaq 673", xy_rotated_left_usd), AXIS_DMI_MATCH("NC651xx", "HP Compaq 651", xy_rotated_right), - AXIS_DMI_MATCH("NC671xx", "HP Compaq 671", xy_swap_yz_inverted), + AXIS_DMI_MATCH("NC6710x", "HP Compaq 6710", xy_swap_yz_inverted), + AXIS_DMI_MATCH("NC6715x", "HP Compaq 6715", y_inverted), + AXIS_DMI_MATCH("NC693xx", "HP EliteBook 693", xy_rotated_right), /* Intel-based HP Pavilion dv5 */ AXIS_DMI_MATCH2("HPDV5_I", PRODUCT_NAME, "HP Pavilion dv5", @@ -216,7 +217,6 @@ static struct dmi_system_id lis3lv02d_dmi_ids[] = { { NULL, } /* Laptop models without axis info (yet): * "NC6910" "HP Compaq 6910" - * HP Compaq 8710x Notebook PC / Mobile Workstation * "NC2400" "HP Compaq nc2400" * "NX74x0" "HP Compaq nx74" * "NX6325" "HP Compaq nx6325" @@ -324,7 +324,7 @@ static int lis3lv02d_remove(struct acpi_device *device, int type) flush_work(&hpled_led.work); led_classdev_unregister(&hpled_led.led_classdev); - return lis3lv02d_remove_fs(); + return lis3lv02d_remove_fs(&lis3_dev); } @@ -338,13 +338,7 @@ static int lis3lv02d_suspend(struct acpi_device *device, pm_message_t state) static int lis3lv02d_resume(struct acpi_device *device) { - /* put back the device in the right state (ACPI might turn it on) */ - mutex_lock(&lis3_dev.lock); - if (lis3_dev.usage > 0) - lis3lv02d_poweron(&lis3_dev); - else - lis3lv02d_poweroff(&lis3_dev); - mutex_unlock(&lis3_dev.lock); + lis3lv02d_poweron(&lis3_dev); return 0; } #else diff --git a/drivers/hwmon/lis3lv02d.c b/drivers/hwmon/lis3lv02d.c index 778eb779598..271338bdb6b 100644 --- a/drivers/hwmon/lis3lv02d.c +++ b/drivers/hwmon/lis3lv02d.c @@ -27,9 +27,7 @@ #include <linux/types.h> #include <linux/platform_device.h> #include <linux/interrupt.h> -#include <linux/input.h> -#include <linux/kthread.h> -#include <linux/semaphore.h> +#include <linux/input-polldev.h> #include <linux/delay.h> #include <linux/wait.h> #include <linux/poll.h> @@ -105,56 +103,39 @@ static void lis3lv02d_get_xyz(struct lis3lv02d *lis3, int *x, int *y, int *z) { int position[3]; - position[0] = lis3_dev.read_data(lis3, OUTX); - position[1] = lis3_dev.read_data(lis3, OUTY); - position[2] = lis3_dev.read_data(lis3, OUTZ); + position[0] = lis3->read_data(lis3, OUTX); + position[1] = lis3->read_data(lis3, OUTY); + position[2] = lis3->read_data(lis3, OUTZ); - *x = lis3lv02d_get_axis(lis3_dev.ac.x, position); - *y = lis3lv02d_get_axis(lis3_dev.ac.y, position); - *z = lis3lv02d_get_axis(lis3_dev.ac.z, position); + *x = lis3lv02d_get_axis(lis3->ac.x, position); + *y = lis3lv02d_get_axis(lis3->ac.y, position); + *z = lis3lv02d_get_axis(lis3->ac.z, position); } void lis3lv02d_poweroff(struct lis3lv02d *lis3) { - lis3_dev.is_on = 0; + /* disable X,Y,Z axis and power down */ + lis3->write(lis3, CTRL_REG1, 0x00); } EXPORT_SYMBOL_GPL(lis3lv02d_poweroff); void lis3lv02d_poweron(struct lis3lv02d *lis3) { - lis3_dev.is_on = 1; - lis3_dev.init(lis3); -} -EXPORT_SYMBOL_GPL(lis3lv02d_poweron); + u8 reg; -/* - * To be called before starting to use the device. It makes sure that the - * device will always be on until a call to lis3lv02d_decrease_use(). Not to be - * used from interrupt context. - */ -static void lis3lv02d_increase_use(struct lis3lv02d *dev) -{ - mutex_lock(&dev->lock); - dev->usage++; - if (dev->usage == 1) { - if (!dev->is_on) - lis3lv02d_poweron(dev); - } - mutex_unlock(&dev->lock); -} + lis3->init(lis3); -/* - * To be called whenever a usage of the device is stopped. - * It will make sure to turn off the device when there is not usage. - */ -static void lis3lv02d_decrease_use(struct lis3lv02d *dev) -{ - mutex_lock(&dev->lock); - dev->usage--; - if (dev->usage == 0) - lis3lv02d_poweroff(dev); - mutex_unlock(&dev->lock); + /* + * Common configuration + * BDU: LSB and MSB values are not updated until both have been read. + * So the value read will always be correct. + */ + lis3->read(lis3, CTRL_REG2, ®); + reg |= CTRL2_BDU; + lis3->write(lis3, CTRL_REG2, reg); } +EXPORT_SYMBOL_GPL(lis3lv02d_poweron); + static irqreturn_t lis302dl_interrupt(int irq, void *dummy) { @@ -198,15 +179,12 @@ static int lis3lv02d_misc_open(struct inode *inode, struct file *file) printk(KERN_ERR DRIVER_NAME ": IRQ%d allocation failed\n", lis3_dev.irq); return -EBUSY; } - lis3lv02d_increase_use(&lis3_dev); - printk("lis3: registered interrupt %d\n", lis3_dev.irq); return 0; } static int lis3lv02d_misc_release(struct inode *inode, struct file *file) { fasync_helper(-1, file, 0, &lis3_dev.async_queue); - lis3lv02d_decrease_use(&lis3_dev); free_irq(lis3_dev.irq, &lis3_dev); clear_bit(0, &lis3_dev.misc_opened); /* release the device */ return 0; @@ -290,46 +268,16 @@ static struct miscdevice lis3lv02d_misc_device = { .fops = &lis3lv02d_misc_fops, }; -/** - * lis3lv02d_joystick_kthread - Kthread polling function - * @data: unused - here to conform to threadfn prototype - */ -static int lis3lv02d_joystick_kthread(void *data) +static void lis3lv02d_joystick_poll(struct input_polled_dev *pidev) { int x, y, z; - while (!kthread_should_stop()) { - lis3lv02d_get_xyz(&lis3_dev, &x, &y, &z); - input_report_abs(lis3_dev.idev, ABS_X, x - lis3_dev.xcalib); - input_report_abs(lis3_dev.idev, ABS_Y, y - lis3_dev.ycalib); - input_report_abs(lis3_dev.idev, ABS_Z, z - lis3_dev.zcalib); - - input_sync(lis3_dev.idev); - - try_to_freeze(); - msleep_interruptible(MDPS_POLL_INTERVAL); - } - - return 0; -} - -static int lis3lv02d_joystick_open(struct input_dev *input) -{ - lis3lv02d_increase_use(&lis3_dev); - lis3_dev.kthread = kthread_run(lis3lv02d_joystick_kthread, NULL, "klis3lv02d"); - if (IS_ERR(lis3_dev.kthread)) { - lis3lv02d_decrease_use(&lis3_dev); - return PTR_ERR(lis3_dev.kthread); - } - - return 0; + lis3lv02d_get_xyz(&lis3_dev, &x, &y, &z); + input_report_abs(pidev->input, ABS_X, x - lis3_dev.xcalib); + input_report_abs(pidev->input, ABS_Y, y - lis3_dev.ycalib); + input_report_abs(pidev->input, ABS_Z, z - lis3_dev.zcalib); } -static void lis3lv02d_joystick_close(struct input_dev *input) -{ - kthread_stop(lis3_dev.kthread); - lis3lv02d_decrease_use(&lis3_dev); -} static inline void lis3lv02d_calibrate_joystick(void) { @@ -339,33 +287,36 @@ static inline void lis3lv02d_calibrate_joystick(void) int lis3lv02d_joystick_enable(void) { + struct input_dev *input_dev; int err; if (lis3_dev.idev) return -EINVAL; - lis3_dev.idev = input_allocate_device(); + lis3_dev.idev = input_allocate_polled_device(); if (!lis3_dev.idev) return -ENOMEM; + lis3_dev.idev->poll = lis3lv02d_joystick_poll; + lis3_dev.idev->poll_interval = MDPS_POLL_INTERVAL; + input_dev = lis3_dev.idev->input; + lis3lv02d_calibrate_joystick(); - lis3_dev.idev->name = "ST LIS3LV02DL Accelerometer"; - lis3_dev.idev->phys = DRIVER_NAME "/input0"; - lis3_dev.idev->id.bustype = BUS_HOST; - lis3_dev.idev->id.vendor = 0; - lis3_dev.idev->dev.parent = &lis3_dev.pdev->dev; - lis3_dev.idev->open = lis3lv02d_joystick_open; - lis3_dev.idev->close = lis3lv02d_joystick_close; + input_dev->name = "ST LIS3LV02DL Accelerometer"; + input_dev->phys = DRIVER_NAME "/input0"; + input_dev->id.bustype = BUS_HOST; + input_dev->id.vendor = 0; + input_dev->dev.parent = &lis3_dev.pdev->dev; - set_bit(EV_ABS, lis3_dev.idev->evbit); - input_set_abs_params(lis3_dev.idev, ABS_X, -lis3_dev.mdps_max_val, lis3_dev.mdps_max_val, 3, 3); - input_set_abs_params(lis3_dev.idev, ABS_Y, -lis3_dev.mdps_max_val, lis3_dev.mdps_max_val, 3, 3); - input_set_abs_params(lis3_dev.idev, ABS_Z, -lis3_dev.mdps_max_val, lis3_dev.mdps_max_val, 3, 3); + set_bit(EV_ABS, input_dev->evbit); + input_set_abs_params(input_dev, ABS_X, -lis3_dev.mdps_max_val, lis3_dev.mdps_max_val, 3, 3); + input_set_abs_params(input_dev, ABS_Y, -lis3_dev.mdps_max_val, lis3_dev.mdps_max_val, 3, 3); + input_set_abs_params(input_dev, ABS_Z, -lis3_dev.mdps_max_val, lis3_dev.mdps_max_val, 3, 3); - err = input_register_device(lis3_dev.idev); + err = input_register_polled_device(lis3_dev.idev); if (err) { - input_free_device(lis3_dev.idev); + input_free_polled_device(lis3_dev.idev); lis3_dev.idev = NULL; } @@ -378,8 +329,9 @@ void lis3lv02d_joystick_disable(void) if (!lis3_dev.idev) return; - misc_deregister(&lis3lv02d_misc_device); - input_unregister_device(lis3_dev.idev); + if (lis3_dev.irq) + misc_deregister(&lis3lv02d_misc_device); + input_unregister_polled_device(lis3_dev.idev); lis3_dev.idev = NULL; } EXPORT_SYMBOL_GPL(lis3lv02d_joystick_disable); @@ -390,9 +342,7 @@ static ssize_t lis3lv02d_position_show(struct device *dev, { int x, y, z; - lis3lv02d_increase_use(&lis3_dev); lis3lv02d_get_xyz(&lis3_dev, &x, &y, &z); - lis3lv02d_decrease_use(&lis3_dev); return sprintf(buf, "(%d,%d,%d)\n", x, y, z); } @@ -406,9 +356,7 @@ static ssize_t lis3lv02d_calibrate_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - lis3lv02d_increase_use(&lis3_dev); lis3lv02d_calibrate_joystick(); - lis3lv02d_decrease_use(&lis3_dev); return count; } @@ -420,9 +368,7 @@ static ssize_t lis3lv02d_rate_show(struct device *dev, u8 ctrl; int val; - lis3lv02d_increase_use(&lis3_dev); lis3_dev.read(&lis3_dev, CTRL_REG1, &ctrl); - lis3lv02d_decrease_use(&lis3_dev); val = (ctrl & (CTRL1_DF0 | CTRL1_DF1)) >> 4; return sprintf(buf, "%d\n", lis3lv02dl_df_val[val]); } @@ -446,17 +392,17 @@ static struct attribute_group lis3lv02d_attribute_group = { static int lis3lv02d_add_fs(struct lis3lv02d *lis3) { - lis3_dev.pdev = platform_device_register_simple(DRIVER_NAME, -1, NULL, 0); - if (IS_ERR(lis3_dev.pdev)) - return PTR_ERR(lis3_dev.pdev); + lis3->pdev = platform_device_register_simple(DRIVER_NAME, -1, NULL, 0); + if (IS_ERR(lis3->pdev)) + return PTR_ERR(lis3->pdev); - return sysfs_create_group(&lis3_dev.pdev->dev.kobj, &lis3lv02d_attribute_group); + return sysfs_create_group(&lis3->pdev->dev.kobj, &lis3lv02d_attribute_group); } -int lis3lv02d_remove_fs(void) +int lis3lv02d_remove_fs(struct lis3lv02d *lis3) { - sysfs_remove_group(&lis3_dev.pdev->dev.kobj, &lis3lv02d_attribute_group); - platform_device_unregister(lis3_dev.pdev); + sysfs_remove_group(&lis3->pdev->dev.kobj, &lis3lv02d_attribute_group); + platform_device_unregister(lis3->pdev); return 0; } EXPORT_SYMBOL_GPL(lis3lv02d_remove_fs); @@ -482,18 +428,35 @@ int lis3lv02d_init_device(struct lis3lv02d *dev) break; default: printk(KERN_ERR DRIVER_NAME - ": unknown sensor type 0x%X\n", lis3_dev.whoami); + ": unknown sensor type 0x%X\n", dev->whoami); return -EINVAL; } - mutex_init(&dev->lock); lis3lv02d_add_fs(dev); - lis3lv02d_increase_use(dev); + lis3lv02d_poweron(dev); if (lis3lv02d_joystick_enable()) printk(KERN_ERR DRIVER_NAME ": joystick initialization failed\n"); - printk("lis3_init_device: irq %d\n", dev->irq); + /* passing in platform specific data is purely optional and only + * used by the SPI transport layer at the moment */ + if (dev->pdata) { + struct lis3lv02d_platform_data *p = dev->pdata; + + if (p->click_flags && (dev->whoami == LIS_SINGLE_ID)) { + dev->write(dev, CLICK_CFG, p->click_flags); + dev->write(dev, CLICK_TIMELIMIT, p->click_time_limit); + dev->write(dev, CLICK_LATENCY, p->click_latency); + dev->write(dev, CLICK_WINDOW, p->click_window); + dev->write(dev, CLICK_THSZ, p->click_thresh_z & 0xf); + dev->write(dev, CLICK_THSY_X, + (p->click_thresh_x & 0xf) | + (p->click_thresh_y << 4)); + } + + if (p->irq_cfg) + dev->write(dev, CTRL_REG3, p->irq_cfg); + } /* bail if we did not get an IRQ from the bus layer */ if (!dev->irq) { @@ -502,11 +465,9 @@ int lis3lv02d_init_device(struct lis3lv02d *dev) goto out; } - printk("lis3: registering device\n"); if (misc_register(&lis3lv02d_misc_device)) printk(KERN_ERR DRIVER_NAME ": misc_register failed\n"); out: - lis3lv02d_decrease_use(dev); return 0; } EXPORT_SYMBOL_GPL(lis3lv02d_init_device); diff --git a/drivers/hwmon/lis3lv02d.h b/drivers/hwmon/lis3lv02d.h index 745ec96806d..e320e2f511f 100644 --- a/drivers/hwmon/lis3lv02d.h +++ b/drivers/hwmon/lis3lv02d.h @@ -18,6 +18,8 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include <linux/platform_device.h> +#include <linux/input-polldev.h> /* * The actual chip is STMicroelectronics LIS3LV02DL or LIS3LV02DQ that seems to @@ -27,12 +29,14 @@ * They can also be connected via I²C. */ +#include <linux/lis3lv02d.h> + /* 2-byte registers */ #define LIS_DOUBLE_ID 0x3A /* LIS3LV02D[LQ] */ /* 1-byte registers */ #define LIS_SINGLE_ID 0x3B /* LIS[32]02DL and others */ -enum lis3lv02d_reg { +enum lis3_reg { WHO_AM_I = 0x0F, OFFSET_X = 0x16, OFFSET_Y = 0x17, @@ -60,6 +64,19 @@ enum lis3lv02d_reg { FF_WU_THS_L = 0x34, FF_WU_THS_H = 0x35, FF_WU_DURATION = 0x36, +}; + +enum lis302d_reg { + CLICK_CFG = 0x38, + CLICK_SRC = 0x39, + CLICK_THSY_X = 0x3B, + CLICK_THSZ = 0x3C, + CLICK_TIMELIMIT = 0x3D, + CLICK_LATENCY = 0x3E, + CLICK_WINDOW = 0x3F, +}; + +enum lis3lv02d_reg { DD_CFG = 0x38, DD_SRC = 0x39, DD_ACK = 0x3A, @@ -169,22 +186,20 @@ struct lis3lv02d { s16 (*read_data) (struct lis3lv02d *lis3, int reg); int mdps_max_val; - struct input_dev *idev; /* input device */ - struct task_struct *kthread; /* kthread for input */ - struct mutex lock; + struct input_polled_dev *idev; /* input device */ struct platform_device *pdev; /* platform device */ atomic_t count; /* interrupt count after last read */ int xcalib; /* calibrated null value for x */ int ycalib; /* calibrated null value for y */ int zcalib; /* calibrated null value for z */ - unsigned char is_on; /* whether the device is on or off */ - unsigned char usage; /* usage counter */ struct axis_conversion ac; /* hw -> logical axis */ u32 irq; /* IRQ number */ struct fasync_struct *async_queue; /* queue for the misc device */ wait_queue_head_t misc_wait; /* Wait queue for the misc device */ unsigned long misc_opened; /* bit0: whether the device is open */ + + struct lis3lv02d_platform_data *pdata; /* for passing board config */ }; int lis3lv02d_init_device(struct lis3lv02d *lis3); @@ -192,6 +207,6 @@ int lis3lv02d_joystick_enable(void); void lis3lv02d_joystick_disable(void); void lis3lv02d_poweroff(struct lis3lv02d *lis3); void lis3lv02d_poweron(struct lis3lv02d *lis3); -int lis3lv02d_remove_fs(void); +int lis3lv02d_remove_fs(struct lis3lv02d *lis3); extern struct lis3lv02d lis3_dev; diff --git a/drivers/hwmon/lis3lv02d_spi.c b/drivers/hwmon/lis3lv02d_spi.c index 07ae74b0e19..3827ff04485 100644 --- a/drivers/hwmon/lis3lv02d_spi.c +++ b/drivers/hwmon/lis3lv02d_spi.c @@ -72,6 +72,7 @@ static int __devinit lis302dl_spi_probe(struct spi_device *spi) lis3_dev.write = lis3_spi_write; lis3_dev.irq = spi->irq; lis3_dev.ac = lis3lv02d_axis_normal; + lis3_dev.pdata = spi->dev.platform_data; spi_set_drvdata(spi, &lis3_dev); ret = lis3lv02d_init_device(&lis3_dev); diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c index 356b3a25efa..1c0b529c06a 100644 --- a/drivers/input/joystick/analog.c +++ b/drivers/input/joystick/analog.c @@ -35,7 +35,7 @@ #include <linux/input.h> #include <linux/gameport.h> #include <linux/jiffies.h> -#include <asm/timex.h> +#include <linux/timex.h> #define DRIVER_DESC "Analog joystick and gamepad driver" diff --git a/drivers/input/misc/pcspkr.c b/drivers/input/misc/pcspkr.c index d6a30cee7bc..6d67af5387a 100644 --- a/drivers/input/misc/pcspkr.c +++ b/drivers/input/misc/pcspkr.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/input.h> #include <linux/platform_device.h> +#include <linux/timex.h> #include <asm/io.h> MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>"); diff --git a/drivers/media/video/videobuf-dma-contig.c b/drivers/media/video/videobuf-dma-contig.c index 6109fb5f34e..0c29a019bc8 100644 --- a/drivers/media/video/videobuf-dma-contig.c +++ b/drivers/media/video/videobuf-dma-contig.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> +#include <linux/pagemap.h> #include <linux/dma-mapping.h> #include <media/videobuf-dma-contig.h> @@ -25,6 +26,7 @@ struct videobuf_dma_contig_memory { void *vaddr; dma_addr_t dma_handle; unsigned long size; + int is_userptr; }; #define MAGIC_DC_MEM 0x0733ac61 @@ -108,6 +110,82 @@ static struct vm_operations_struct videobuf_vm_ops = { .close = videobuf_vm_close, }; +/** + * videobuf_dma_contig_user_put() - reset pointer to user space buffer + * @mem: per-buffer private videobuf-dma-contig data + * + * This function resets the user space pointer + */ +static void videobuf_dma_contig_user_put(struct videobuf_dma_contig_memory *mem) +{ + mem->is_userptr = 0; + mem->dma_handle = 0; + mem->size = 0; +} + +/** + * videobuf_dma_contig_user_get() - setup user space memory pointer + * @mem: per-buffer private videobuf-dma-contig data + * @vb: video buffer to map + * + * This function validates and sets up a pointer to user space memory. + * Only physically contiguous pfn-mapped memory is accepted. + * + * Returns 0 if successful. + */ +static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem, + struct videobuf_buffer *vb) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long prev_pfn, this_pfn; + unsigned long pages_done, user_address; + int ret; + + mem->size = PAGE_ALIGN(vb->size); + mem->is_userptr = 0; + ret = -EINVAL; + + down_read(&mm->mmap_sem); + + vma = find_vma(mm, vb->baddr); + if (!vma) + goto out_up; + + if ((vb->baddr + mem->size) > vma->vm_end) + goto out_up; + + pages_done = 0; + prev_pfn = 0; /* kill warning */ + user_address = vb->baddr; + + while (pages_done < (mem->size >> PAGE_SHIFT)) { + ret = follow_pfn(vma, user_address, &this_pfn); + if (ret) + break; + + if (pages_done == 0) + mem->dma_handle = this_pfn << PAGE_SHIFT; + else if (this_pfn != (prev_pfn + 1)) + ret = -EFAULT; + + if (ret) + break; + + prev_pfn = this_pfn; + user_address += PAGE_SIZE; + pages_done++; + } + + if (!ret) + mem->is_userptr = 1; + + out_up: + up_read(¤t->mm->mmap_sem); + + return ret; +} + static void *__videobuf_alloc(size_t size) { struct videobuf_dma_contig_memory *mem; @@ -154,12 +232,11 @@ static int __videobuf_iolock(struct videobuf_queue *q, case V4L2_MEMORY_USERPTR: dev_dbg(q->dev, "%s memory method USERPTR\n", __func__); - /* The only USERPTR currently supported is the one needed for - read() method. - */ + /* handle pointer from user space */ if (vb->baddr) - return -EINVAL; + return videobuf_dma_contig_user_get(mem, vb); + /* allocate memory for the read() method */ mem->size = PAGE_ALIGN(vb->size); mem->vaddr = dma_alloc_coherent(q->dev, mem->size, &mem->dma_handle, GFP_KERNEL); @@ -400,7 +477,7 @@ void videobuf_dma_contig_free(struct videobuf_queue *q, So, it should free memory only if the memory were allocated for read() operation. */ - if ((buf->memory != V4L2_MEMORY_USERPTR) || buf->baddr) + if (buf->memory != V4L2_MEMORY_USERPTR) return; if (!mem) @@ -408,6 +485,13 @@ void videobuf_dma_contig_free(struct videobuf_queue *q, MAGIC_CHECK(mem->magic, MAGIC_DC_MEM); + /* handle user space pointer case */ + if (buf->baddr) { + videobuf_dma_contig_user_put(mem); + return; + } + + /* read() method */ dma_free_coherent(q->dev, mem->size, mem->vaddr, mem->dma_handle); mem->vaddr = NULL; } 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/drivers/pcmcia/pcmcia_ioctl.c b/drivers/pcmcia/pcmcia_ioctl.c index 1703b20cad5..6095f8daecd 100644 --- a/drivers/pcmcia/pcmcia_ioctl.c +++ b/drivers/pcmcia/pcmcia_ioctl.c @@ -915,12 +915,9 @@ static int ds_ioctl(struct inode * inode, struct file * file, err = -EPERM; goto free_out; } else { - static int printed = 0; - if (!printed) { - printk(KERN_WARNING "2.6. kernels use pcmciamtd instead of memory_cs.c and do not require special\n"); - printk(KERN_WARNING "MTD handling any more.\n"); - printed++; - } + printk_once(KERN_WARNING + "2.6. kernels use pcmciamtd instead of memory_cs.c and do not require special\n"); + printk_once(KERN_WARNING "MTD handling any more.\n"); } err = -EINVAL; goto free_out; diff --git a/drivers/spi/spi_mpc83xx.c b/drivers/spi/spi_mpc83xx.c index f4573a96af2..a32ccb44065 100644 --- a/drivers/spi/spi_mpc83xx.c +++ b/drivers/spi/spi_mpc83xx.c @@ -711,12 +711,12 @@ static int of_mpc83xx_spi_get_chipselects(struct device *dev) return 0; } - pinfo->gpios = kmalloc(ngpios * sizeof(pinfo->gpios), GFP_KERNEL); + pinfo->gpios = kmalloc(ngpios * sizeof(*pinfo->gpios), GFP_KERNEL); if (!pinfo->gpios) return -ENOMEM; - memset(pinfo->gpios, -1, ngpios * sizeof(pinfo->gpios)); + memset(pinfo->gpios, -1, ngpios * sizeof(*pinfo->gpios)); - pinfo->alow_flags = kzalloc(ngpios * sizeof(pinfo->alow_flags), + pinfo->alow_flags = kzalloc(ngpios * sizeof(*pinfo->alow_flags), GFP_KERNEL); if (!pinfo->alow_flags) { ret = -ENOMEM; diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index 2b5a691064b..932ffdbf86d 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -2104,6 +2104,7 @@ config FB_MB862XX_LIME bool "Lime GDC" depends on FB_MB862XX depends on OF && !FB_MB862XX_PCI_GDC + depends on PPC select FB_FOREIGN_ENDIAN select FB_LITTLE_ENDIAN ---help--- diff --git a/drivers/video/acornfb.c b/drivers/video/acornfb.c index 6995fe1e86d..0bcc59eb37f 100644 --- a/drivers/video/acornfb.c +++ b/drivers/video/acornfb.c @@ -859,43 +859,6 @@ acornfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) return 0; } -/* - * Note that we are entered with the kernel locked. - */ -static int -acornfb_mmap(struct fb_info *info, struct vm_area_struct *vma) -{ - unsigned long off, start; - u32 len; - - off = vma->vm_pgoff << PAGE_SHIFT; - - start = info->fix.smem_start; - len = PAGE_ALIGN(start & ~PAGE_MASK) + info->fix.smem_len; - start &= PAGE_MASK; - if ((vma->vm_end - vma->vm_start + off) > len) - return -EINVAL; - off += start; - vma->vm_pgoff = off >> PAGE_SHIFT; - - /* This is an IO map - tell maydump to skip this VMA */ - vma->vm_flags |= VM_IO; - - vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot); - - /* - * Don't alter the page protection flags; we want to keep the area - * cached for better performance. This does mean that we may miss - * some updates to the screen occasionally, but process switches - * should cause the caches and buffers to be flushed often enough. - */ - if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, - vma->vm_page_prot)) - return -EAGAIN; - return 0; -} - static struct fb_ops acornfb_ops = { .owner = THIS_MODULE, .fb_check_var = acornfb_check_var, @@ -905,7 +868,6 @@ static struct fb_ops acornfb_ops = { .fb_fillrect = cfb_fillrect, .fb_copyarea = cfb_copyarea, .fb_imageblit = cfb_imageblit, - .fb_mmap = acornfb_mmap, }; /* diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c index 2fb63f6ea2f..5afd64482f5 100644 --- a/drivers/video/atmel_lcdfb.c +++ b/drivers/video/atmel_lcdfb.c @@ -345,7 +345,7 @@ static int atmel_lcdfb_check_var(struct fb_var_screeninfo *var, dev_dbg(dev, " bpp: %u\n", var->bits_per_pixel); dev_dbg(dev, " clk: %lu KHz\n", clk_value_khz); - if ((PICOS2KHZ(var->pixclock) * var->bits_per_pixel / 8) > clk_value_khz) { + if (PICOS2KHZ(var->pixclock) > clk_value_khz) { dev_err(dev, "%lu KHz pixel clock is too fast\n", PICOS2KHZ(var->pixclock)); return -EINVAL; } diff --git a/drivers/video/aty/radeon_pm.c b/drivers/video/aty/radeon_pm.c index 97a1f095f32..515cf1978d1 100644 --- a/drivers/video/aty/radeon_pm.c +++ b/drivers/video/aty/radeon_pm.c @@ -213,7 +213,6 @@ static void radeon_pm_disable_dynamic_mode(struct radeonfb_info *rinfo) PIXCLKS_CNTL__R300_PIXCLK_TRANS_ALWAYS_ONb | PIXCLKS_CNTL__R300_PIXCLK_TVO_ALWAYS_ONb | PIXCLKS_CNTL__R300_P2G2CLK_ALWAYS_ONb | - PIXCLKS_CNTL__R300_P2G2CLK_ALWAYS_ONb | PIXCLKS_CNTL__R300_DISP_DAC_PIXCLK_DAC2_BLANK_OFF); OUTPLL(pllPIXCLKS_CNTL, tmp); @@ -395,7 +394,7 @@ static void radeon_pm_enable_dynamic_mode(struct radeonfb_info *rinfo) PIXCLKS_CNTL__R300_PIXCLK_TRANS_ALWAYS_ONb | PIXCLKS_CNTL__R300_PIXCLK_TVO_ALWAYS_ONb | PIXCLKS_CNTL__R300_P2G2CLK_ALWAYS_ONb | - PIXCLKS_CNTL__R300_P2G2CLK_ALWAYS_ONb); + PIXCLKS_CNTL__R300_P2G2CLK_DAC_ALWAYS_ONb); OUTPLL(pllPIXCLKS_CNTL, tmp); tmp = INPLL(pllMCLK_MISC); diff --git a/drivers/video/bf54x-lq043fb.c b/drivers/video/bf54x-lq043fb.c index 37e60b1d2ed..e49ae5edcc0 100644 --- a/drivers/video/bf54x-lq043fb.c +++ b/drivers/video/bf54x-lq043fb.c @@ -323,7 +323,6 @@ static int bfin_bf54x_fb_release(struct fb_info *info, int user) bfin_write_EPPI0_CONTROL(0); SSYNC(); disable_dma(CH_EPPI0); - memset(fbi->fb_buffer, 0, info->fix.smem_len); } spin_unlock(&fbi->lock); @@ -530,7 +529,7 @@ static irqreturn_t bfin_bf54x_irq_error(int irq, void *dev_id) return IRQ_HANDLED; } -static int __init bfin_bf54x_probe(struct platform_device *pdev) +static int __devinit bfin_bf54x_probe(struct platform_device *pdev) { struct bfin_bf54xfb_info *info; struct fb_info *fbinfo; @@ -626,14 +625,12 @@ static int __init bfin_bf54x_probe(struct platform_device *pdev) goto out3; } - memset(info->fb_buffer, 0, fbinfo->fix.smem_len); - fbinfo->screen_base = (void *)info->fb_buffer; fbinfo->fix.smem_start = (int)info->fb_buffer; fbinfo->fbops = &bfin_bf54x_fb_ops; - fbinfo->pseudo_palette = kmalloc(sizeof(u32) * 16, GFP_KERNEL); + fbinfo->pseudo_palette = kzalloc(sizeof(u32) * 16, GFP_KERNEL); if (!fbinfo->pseudo_palette) { printk(KERN_ERR DRIVER_NAME "Fail to allocate pseudo_palette\n"); @@ -642,8 +639,6 @@ static int __init bfin_bf54x_probe(struct platform_device *pdev) goto out4; } - memset(fbinfo->pseudo_palette, 0, sizeof(u32) * 16); - if (fb_alloc_cmap(&fbinfo->cmap, BFIN_LCD_NBR_PALETTE_ENTRIES, 0) < 0) { printk(KERN_ERR DRIVER_NAME @@ -712,7 +707,7 @@ out1: return ret; } -static int bfin_bf54x_remove(struct platform_device *pdev) +static int __devexit bfin_bf54x_remove(struct platform_device *pdev) { struct fb_info *fbinfo = platform_get_drvdata(pdev); @@ -781,7 +776,7 @@ static int bfin_bf54x_resume(struct platform_device *pdev) static struct platform_driver bfin_bf54x_driver = { .probe = bfin_bf54x_probe, - .remove = bfin_bf54x_remove, + .remove = __devexit_p(bfin_bf54x_remove), .suspend = bfin_bf54x_suspend, .resume = bfin_bf54x_resume, .driver = { @@ -790,7 +785,7 @@ static struct platform_driver bfin_bf54x_driver = { }, }; -static int __devinit bfin_bf54x_driver_init(void) +static int __init bfin_bf54x_driver_init(void) { return platform_driver_register(&bfin_bf54x_driver); } diff --git a/drivers/video/bfin-t350mcqb-fb.c b/drivers/video/bfin-t350mcqb-fb.c index 90cfddabf1f..5cc36cfbf07 100644 --- a/drivers/video/bfin-t350mcqb-fb.c +++ b/drivers/video/bfin-t350mcqb-fb.c @@ -242,7 +242,6 @@ static int bfin_t350mcqb_fb_release(struct fb_info *info, int user) SSYNC(); disable_dma(CH_PPI); bfin_t350mcqb_stop_timers(); - memset(fbi->fb_buffer, 0, info->fix.smem_len); } spin_unlock(&fbi->lock); @@ -527,8 +526,6 @@ static int __devinit bfin_t350mcqb_probe(struct platform_device *pdev) goto out3; } - memset(info->fb_buffer, 0, fbinfo->fix.smem_len); - fbinfo->screen_base = (void *)info->fb_buffer + ACTIVE_VIDEO_MEM_OFFSET; fbinfo->fix.smem_start = (int)info->fb_buffer + ACTIVE_VIDEO_MEM_OFFSET; @@ -602,7 +599,7 @@ out1: return ret; } -static int bfin_t350mcqb_remove(struct platform_device *pdev) +static int __devexit bfin_t350mcqb_remove(struct platform_device *pdev) { struct fb_info *fbinfo = platform_get_drvdata(pdev); @@ -637,9 +634,6 @@ static int bfin_t350mcqb_remove(struct platform_device *pdev) #ifdef CONFIG_PM static int bfin_t350mcqb_suspend(struct platform_device *pdev, pm_message_t state) { - struct fb_info *fbinfo = platform_get_drvdata(pdev); - struct bfin_t350mcqbfb_info *info = fbinfo->par; - bfin_t350mcqb_disable_ppi(); disable_dma(CH_PPI); bfin_write_PPI_STATUS(0xFFFF); @@ -649,9 +643,6 @@ static int bfin_t350mcqb_suspend(struct platform_device *pdev, pm_message_t stat static int bfin_t350mcqb_resume(struct platform_device *pdev) { - struct fb_info *fbinfo = platform_get_drvdata(pdev); - struct bfin_t350mcqbfb_info *info = fbinfo->par; - enable_dma(CH_PPI); bfin_t350mcqb_enable_ppi(); @@ -664,7 +655,7 @@ static int bfin_t350mcqb_resume(struct platform_device *pdev) static struct platform_driver bfin_t350mcqb_driver = { .probe = bfin_t350mcqb_probe, - .remove = bfin_t350mcqb_remove, + .remove = __devexit_p(bfin_t350mcqb_remove), .suspend = bfin_t350mcqb_suspend, .resume = bfin_t350mcqb_resume, .driver = { @@ -673,7 +664,7 @@ static struct platform_driver bfin_t350mcqb_driver = { }, }; -static int __devinit bfin_t350mcqb_driver_init(void) +static int __init bfin_t350mcqb_driver_init(void) { return platform_driver_register(&bfin_t350mcqb_driver); } diff --git a/drivers/video/carminefb.c b/drivers/video/carminefb.c index c7ff3c1a266..0c02f8ec4bf 100644 --- a/drivers/video/carminefb.c +++ b/drivers/video/carminefb.c @@ -562,7 +562,7 @@ static int __devinit alloc_carmine_fb(void __iomem *regs, void __iomem *smem_bas if (ret < 0) goto err_free_fb; - if (fb_mode > ARRAY_SIZE(carmine_modedb)) + if (fb_mode >= ARRAY_SIZE(carmine_modedb)) fb_mode = CARMINEFB_DEFAULT_VIDEO_MODE; par->cur_mode = par->new_mode = ~0; diff --git a/drivers/video/chipsfb.c b/drivers/video/chipsfb.c index 777389c4098..57b9d276497 100644 --- a/drivers/video/chipsfb.c +++ b/drivers/video/chipsfb.c @@ -414,7 +414,6 @@ chipsfb_pci_init(struct pci_dev *dp, const struct pci_device_id *ent) } pci_set_drvdata(dp, p); - p->device = &dp->dev; init_chips(p, addr); diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c index 8dea2bc9270..eb12182b205 100644 --- a/drivers/video/efifb.c +++ b/drivers/video/efifb.c @@ -280,6 +280,9 @@ static int __init efifb_probe(struct platform_device *dev) info->pseudo_palette = info->par; info->par = NULL; + info->aperture_base = efifb_fix.smem_start; + info->aperture_size = size_total; + info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len); if (!info->screen_base) { printk(KERN_ERR "efifb: abort, cannot ioremap video memory " @@ -337,7 +340,7 @@ static int __init efifb_probe(struct platform_device *dev) info->fbops = &efifb_ops; info->var = efifb_defined; info->fix = efifb_fix; - info->flags = FBINFO_FLAG_DEFAULT; + info->flags = FBINFO_FLAG_DEFAULT | FBINFO_MISC_FIRMWARE; if ((err = fb_alloc_cmap(&info->cmap, 256, 0)) < 0) { printk(KERN_ERR "efifb: cannot allocate colormap\n"); diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c index d412a1ddc12..f8a09bf8d0c 100644 --- a/drivers/video/fbmem.c +++ b/drivers/video/fbmem.c @@ -1462,6 +1462,16 @@ static int fb_check_foreignness(struct fb_info *fi) return 0; } +static bool fb_do_apertures_overlap(struct fb_info *gen, struct fb_info *hw) +{ + /* is the generic aperture base the same as the HW one */ + if (gen->aperture_base == hw->aperture_base) + return true; + /* is the generic aperture base inside the hw base->hw base+size */ + if (gen->aperture_base > hw->aperture_base && gen->aperture_base <= hw->aperture_base + hw->aperture_size) + return true; + return false; +} /** * register_framebuffer - registers a frame buffer device * @fb_info: frame buffer info structure @@ -1485,6 +1495,23 @@ register_framebuffer(struct fb_info *fb_info) if (fb_check_foreignness(fb_info)) return -ENOSYS; + /* check all firmware fbs and kick off if the base addr overlaps */ + for (i = 0 ; i < FB_MAX; i++) { + if (!registered_fb[i]) + continue; + + if (registered_fb[i]->flags & FBINFO_MISC_FIRMWARE) { + if (fb_do_apertures_overlap(registered_fb[i], fb_info)) { + printk(KERN_ERR "fb: conflicting fb hw usage " + "%s vs %s - removing generic driver\n", + fb_info->fix.id, + registered_fb[i]->fix.id); + unregister_framebuffer(registered_fb[i]); + break; + } + } + } + num_registered_fb++; for (i = 0 ; i < FB_MAX; i++) if (!registered_fb[i]) @@ -1586,6 +1613,10 @@ unregister_framebuffer(struct fb_info *fb_info) device_destroy(fb_class, MKDEV(FB_MAJOR, i)); event.info = fb_info; fb_notifier_call_chain(FB_EVENT_FB_UNREGISTERED, &event); + + /* this may free fb info */ + if (fb_info->fbops->fb_destroy) + fb_info->fbops->fb_destroy(fb_info); done: return ret; } diff --git a/drivers/video/igafb.c b/drivers/video/igafb.c index 3a81060137a..15d20010944 100644 --- a/drivers/video/igafb.c +++ b/drivers/video/igafb.c @@ -395,17 +395,16 @@ int __init igafb_init(void) /* We leak a reference here but as it cannot be unloaded this is fine. If you write unload code remember to free it in unload */ - size = sizeof(struct fb_info) + sizeof(struct iga_par) + sizeof(u32)*16; + size = sizeof(struct iga_par) + sizeof(u32)*16; - info = kzalloc(size, GFP_ATOMIC); + info = framebuffer_alloc(size, &pdev->dev); if (!info) { printk("igafb_init: can't alloc fb_info\n"); pci_dev_put(pdev); return -ENOMEM; } - par = (struct iga_par *) (info + 1); - + par = info->par; if ((addr = pdev->resource[0].start) == 0) { printk("igafb_init: no memory start\n"); @@ -526,7 +525,6 @@ int __init igafb_init(void) info->var = default_var; info->fix = igafb_fix; info->pseudo_palette = (void *)(par + 1); - info->device = &pdev->dev; if (!iga_init(info, par)) { iounmap((void *)par->io_base); diff --git a/drivers/video/intelfb/intelfbdrv.c b/drivers/video/intelfb/intelfbdrv.c index ace14fe02fc..0cafd642fbc 100644 --- a/drivers/video/intelfb/intelfbdrv.c +++ b/drivers/video/intelfb/intelfbdrv.c @@ -1365,6 +1365,11 @@ static int intelfb_set_par(struct fb_info *info) DBG_MSG("intelfb_set_par (%dx%d-%d)\n", info->var.xres, info->var.yres, info->var.bits_per_pixel); + /* + * Disable VCO prior to timing register change. + */ + OUTREG(DPLL_A, INREG(DPLL_A) & ~DPLL_VCO_ENABLE); + intelfb_blank(FB_BLANK_POWERDOWN, info); if (ACCEL(dinfo, info)) diff --git a/drivers/video/logo/Makefile b/drivers/video/logo/Makefile index b91251d1fe4..3b437813584 100644 --- a/drivers/video/logo/Makefile +++ b/drivers/video/logo/Makefile @@ -37,22 +37,24 @@ extra-y += $(call logo-cfiles,_clut224,ppm) # Gray 256 extra-y += $(call logo-cfiles,_gray256,pgm) +pnmtologo := scripts/pnmtologo + # Create commands like "pnmtologo -t mono -n logo_mac_mono -o ..." quiet_cmd_logo = LOGO $@ - cmd_logo = scripts/pnmtologo \ + cmd_logo = $(pnmtologo) \ -t $(patsubst $*_%,%,$(notdir $(basename $<))) \ -n $(notdir $(basename $<)) -o $@ $< -$(obj)/%_mono.c: $(src)/%_mono.pbm FORCE +$(obj)/%_mono.c: $(src)/%_mono.pbm $(pnmtologo) FORCE $(call if_changed,logo) -$(obj)/%_vga16.c: $(src)/%_vga16.ppm FORCE +$(obj)/%_vga16.c: $(src)/%_vga16.ppm $(pnmtologo) FORCE $(call if_changed,logo) -$(obj)/%_clut224.c: $(src)/%_clut224.ppm FORCE +$(obj)/%_clut224.c: $(src)/%_clut224.ppm $(pnmtologo) FORCE $(call if_changed,logo) -$(obj)/%_gray256.c: $(src)/%_gray256.pgm FORCE +$(obj)/%_gray256.c: $(src)/%_gray256.pgm $(pnmtologo) FORCE $(call if_changed,logo) # Files generated that shall be removed upon make clean diff --git a/drivers/video/logo/logo.c b/drivers/video/logo/logo.c index 2e85a2b52d0..ea7a8ccc830 100644 --- a/drivers/video/logo/logo.c +++ b/drivers/video/logo/logo.c @@ -21,21 +21,6 @@ #include <asm/bootinfo.h> #endif -extern const struct linux_logo logo_linux_mono; -extern const struct linux_logo logo_linux_vga16; -extern const struct linux_logo logo_linux_clut224; -extern const struct linux_logo logo_blackfin_vga16; -extern const struct linux_logo logo_blackfin_clut224; -extern const struct linux_logo logo_dec_clut224; -extern const struct linux_logo logo_mac_clut224; -extern const struct linux_logo logo_parisc_clut224; -extern const struct linux_logo logo_sgi_clut224; -extern const struct linux_logo logo_sun_clut224; -extern const struct linux_logo logo_superh_mono; -extern const struct linux_logo logo_superh_vga16; -extern const struct linux_logo logo_superh_clut224; -extern const struct linux_logo logo_m32r_clut224; - static int nologo; module_param(nologo, bool, 0); MODULE_PARM_DESC(nologo, "Disables startup logo"); diff --git a/drivers/video/mb862xx/mb862xxfb.c b/drivers/video/mb862xx/mb862xxfb.c index fb64234a382..a28e3cfbbf7 100644 --- a/drivers/video/mb862xx/mb862xxfb.c +++ b/drivers/video/mb862xx/mb862xxfb.c @@ -19,7 +19,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/pci.h> -#if defined(CONFIG_PPC_OF) +#if defined(CONFIG_OF) #include <linux/of_platform.h> #endif #include "mb862xxfb.h" diff --git a/drivers/video/modedb.c b/drivers/video/modedb.c index 16186240c5f..34e4e799516 100644 --- a/drivers/video/modedb.c +++ b/drivers/video/modedb.c @@ -264,6 +264,14 @@ static const struct fb_videomode modedb[] = { /* 1280x800, 60 Hz, 47.403 kHz hsync, WXGA 16:10 aspect ratio */ NULL, 60, 1280, 800, 12048, 200, 64, 24, 1, 136, 3, 0, FB_VMODE_NONINTERLACED + }, { + /* 720x576i @ 50 Hz, 15.625 kHz hsync (PAL RGB) */ + NULL, 50, 720, 576, 74074, 64, 16, 39, 5, 64, 5, + 0, FB_VMODE_INTERLACED + }, { + /* 800x520i @ 50 Hz, 15.625 kHz hsync (PAL RGB) */ + NULL, 50, 800, 520, 58823, 144, 64, 72, 28, 80, 5, + 0, FB_VMODE_INTERLACED }, }; diff --git a/drivers/video/offb.c b/drivers/video/offb.c index e1d9eeb1aea..4d8c54c23dd 100644 --- a/drivers/video/offb.c +++ b/drivers/video/offb.c @@ -378,7 +378,6 @@ static void __init offb_init_fb(const char *name, const char *full_name, struct fb_fix_screeninfo *fix; struct fb_var_screeninfo *var; struct fb_info *info; - int size; if (!request_mem_region(res_start, res_size, "offb")) return; @@ -393,15 +392,12 @@ static void __init offb_init_fb(const char *name, const char *full_name, return; } - size = sizeof(struct fb_info) + sizeof(u32) * 16; - - info = kmalloc(size, GFP_ATOMIC); + info = framebuffer_alloc(sizeof(u32) * 16, NULL); if (info == 0) { release_mem_region(res_start, res_size); return; } - memset(info, 0, size); fix = &info->fix; var = &info->var; @@ -497,7 +493,7 @@ static void __init offb_init_fb(const char *name, const char *full_name, iounmap(par->cmap_adr); par->cmap_adr = NULL; iounmap(info->screen_base); - kfree(info); + framebuffer_release(info); release_mem_region(res_start, res_size); return; } diff --git a/drivers/video/pm2fb.c b/drivers/video/pm2fb.c index c6dd924976a..36436ee6c1a 100644 --- a/drivers/video/pm2fb.c +++ b/drivers/video/pm2fb.c @@ -1748,7 +1748,7 @@ static void __devexit pm2fb_remove(struct pci_dev *pdev) pci_set_drvdata(pdev, NULL); fb_dealloc_cmap(&info->cmap); kfree(info->pixmap.addr); - kfree(info); + framebuffer_release(info); } static struct pci_device_id pm2fb_id_table[] = { diff --git a/drivers/video/s1d13xxxfb.c b/drivers/video/s1d13xxxfb.c index 0726aecf3b7..0deb0a8867b 100644 --- a/drivers/video/s1d13xxxfb.c +++ b/drivers/video/s1d13xxxfb.c @@ -2,6 +2,7 @@ * * (c) 2004 Simtec Electronics * (c) 2005 Thibaut VARENE <varenet@parisc-linux.org> + * (c) 2009 Kristoffer Ericson <kristoffer.ericson@gmail.com> * * Driver for Epson S1D13xxx series framebuffer chips * @@ -10,18 +11,10 @@ * linux/drivers/video/epson1355fb.c * linux/drivers/video/epson/s1d13xxxfb.c (2.4 driver by Epson) * - * Note, currently only tested on S1D13806 with 16bit CRT. - * As such, this driver might still contain some hardcoded bits relating to - * S1D13806. - * Making it work on other S1D13XXX chips should merely be a matter of adding - * a few switch()s, some missing glue here and there maybe, and split header - * files. - * * TODO: - handle dual screen display (CRT and LCD at the same time). * - check_var(), mode change, etc. - * - PM untested. - * - Accelerated interfaces. - * - Probably not SMP safe :) + * - probably not SMP safe :) + * - support all bitblt operations on all cards * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive for @@ -31,19 +24,24 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/delay.h> - #include <linux/types.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/fb.h> +#include <linux/spinlock_types.h> +#include <linux/spinlock.h> #include <asm/io.h> #include <video/s1d13xxxfb.h> -#define PFX "s1d13xxxfb: " +#define PFX "s1d13xxxfb: " +#define BLIT "s1d13xxxfb_bitblt: " +/* + * set this to enable debugging on general functions + */ #if 0 #define dbg(fmt, args...) do { printk(KERN_INFO fmt, ## args); } while(0) #else @@ -51,7 +49,21 @@ #endif /* - * List of card production ids + * set this to enable debugging on 2D acceleration + */ +#if 0 +#define dbg_blit(fmt, args...) do { printk(KERN_INFO BLIT fmt, ## args); } while (0) +#else +#define dbg_blit(fmt, args...) do { } while (0) +#endif + +/* + * we make sure only one bitblt operation is running + */ +static DEFINE_SPINLOCK(s1d13xxxfb_bitblt_lock); + +/* + * list of card production ids */ static const int s1d13xxxfb_prod_ids[] = { S1D13505_PROD_ID, @@ -69,7 +81,7 @@ static const char *s1d13xxxfb_prod_names[] = { }; /* - * Here we define the default struct fb_fix_screeninfo + * here we define the default struct fb_fix_screeninfo */ static struct fb_fix_screeninfo __devinitdata s1d13xxxfb_fix = { .id = S1D_FBID, @@ -145,8 +157,10 @@ crt_enable(struct s1d13xxxfb_par *par, int enable) s1d13xxxfb_writereg(par, S1DREG_COM_DISP_MODE, mode); } -/* framebuffer control routines */ +/************************************************************* + framebuffer control functions + *************************************************************/ static inline void s1d13xxxfb_setup_pseudocolour(struct fb_info *info) { @@ -242,13 +256,13 @@ s1d13xxxfb_set_par(struct fb_info *info) } /** - * s1d13xxxfb_setcolreg - sets a color register. - * @regno: Which register in the CLUT we are programming - * @red: The red value which can be up to 16 bits wide + * s1d13xxxfb_setcolreg - sets a color register. + * @regno: Which register in the CLUT we are programming + * @red: The red value which can be up to 16 bits wide * @green: The green value which can be up to 16 bits wide * @blue: The blue value which can be up to 16 bits wide. * @transp: If supported the alpha value which can be up to 16 bits wide. - * @info: frame buffer info structure + * @info: frame buffer info structure * * Returns negative errno on error, or zero on success. */ @@ -351,15 +365,15 @@ s1d13xxxfb_blank(int blank_mode, struct fb_info *info) } /** - * s1d13xxxfb_pan_display - Pans the display. - * @var: frame buffer variable screen structure - * @info: frame buffer structure that represents a single frame buffer + * s1d13xxxfb_pan_display - Pans the display. + * @var: frame buffer variable screen structure + * @info: frame buffer structure that represents a single frame buffer * * Pan (or wrap, depending on the `vmode' field) the display using the - * `yoffset' field of the `var' structure (`xoffset' not yet supported). - * If the values don't fit, return -EINVAL. + * `yoffset' field of the `var' structure (`xoffset' not yet supported). + * If the values don't fit, return -EINVAL. * - * Returns negative errno on error, or zero on success. + * Returns negative errno on error, or zero on success. */ static int s1d13xxxfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) @@ -390,8 +404,259 @@ s1d13xxxfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) return 0; } -/* framebuffer information structures */ +/************************************************************ + functions to handle bitblt acceleration + ************************************************************/ + +/** + * bltbit_wait_bitset - waits for change in register value + * @info : framebuffer structure + * @bit : value expected in register + * @timeout : ... + * + * waits until value changes INTO bit + */ +static u8 +bltbit_wait_bitset(struct fb_info *info, u8 bit, int timeout) +{ + while (!(s1d13xxxfb_readreg(info->par, S1DREG_BBLT_CTL0) & bit)) { + udelay(10); + if (!--timeout) { + dbg_blit("wait_bitset timeout\n"); + break; + } + } + + return timeout; +} + +/** + * bltbit_wait_bitclear - waits for change in register value + * @info : frambuffer structure + * @bit : value currently in register + * @timeout : ... + * + * waits until value changes FROM bit + * + */ +static u8 +bltbit_wait_bitclear(struct fb_info *info, u8 bit, int timeout) +{ + while (s1d13xxxfb_readreg(info->par, S1DREG_BBLT_CTL0) & bit) { + udelay(10); + if (!--timeout) { + dbg_blit("wait_bitclear timeout\n"); + break; + } + } + + return timeout; +} + +/** + * bltbit_fifo_status - checks the current status of the fifo + * @info : framebuffer structure + * + * returns number of free words in buffer + */ +static u8 +bltbit_fifo_status(struct fb_info *info) +{ + u8 status; + status = s1d13xxxfb_readreg(info->par, S1DREG_BBLT_CTL0); + + /* its empty so room for 16 words */ + if (status & BBLT_FIFO_EMPTY) + return 16; + + /* its full so we dont want to add */ + if (status & BBLT_FIFO_FULL) + return 0; + + /* its atleast half full but we can add one atleast */ + if (status & BBLT_FIFO_NOT_FULL) + return 1; + + return 0; +} + +/* + * s1d13xxxfb_bitblt_copyarea - accelerated copyarea function + * @info : framebuffer structure + * @area : fb_copyarea structure + * + * supports (atleast) S1D13506 + * + */ +static void +s1d13xxxfb_bitblt_copyarea(struct fb_info *info, const struct fb_copyarea *area) +{ + u32 dst, src; + u32 stride; + u16 reverse = 0; + u16 sx = area->sx, sy = area->sy; + u16 dx = area->dx, dy = area->dy; + u16 width = area->width, height = area->height; + u16 bpp; + + spin_lock(&s1d13xxxfb_bitblt_lock); + + /* bytes per xres line */ + bpp = (info->var.bits_per_pixel >> 3); + stride = bpp * info->var.xres; + + /* reverse, calculate the last pixel in rectangle */ + if ((dy > sy) || ((dy == sy) && (dx >= sx))) { + dst = (((dy + height - 1) * stride) + (bpp * (dx + width - 1))); + src = (((sy + height - 1) * stride) + (bpp * (sx + width - 1))); + reverse = 1; + /* not reverse, calculate the first pixel in rectangle */ + } else { /* (y * xres) + (bpp * x) */ + dst = (dy * stride) + (bpp * dx); + src = (sy * stride) + (bpp * sx); + } + + /* set source adress */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_SRC_START0, (src & 0xff)); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_SRC_START1, (src >> 8) & 0x00ff); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_SRC_START2, (src >> 16) & 0x00ff); + + /* set destination adress */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_DST_START0, (dst & 0xff)); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_DST_START1, (dst >> 8) & 0x00ff); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_DST_START2, (dst >> 16) & 0x00ff); + + /* program height and width */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_WIDTH0, (width & 0xff) - 1); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_WIDTH1, (width >> 8)); + + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_HEIGHT0, (height & 0xff) - 1); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_HEIGHT1, (height >> 8)); + + /* negative direction ROP */ + if (reverse == 1) { + dbg_blit("(copyarea) negative rop\n"); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_OP, 0x03); + } else /* positive direction ROP */ { + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_OP, 0x02); + dbg_blit("(copyarea) positive rop\n"); + } + + /* set for rectangel mode and not linear */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_CTL0, 0x0); + + /* setup the bpp 1 = 16bpp, 0 = 8bpp*/ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_CTL1, (bpp >> 1)); + + /* set words per xres */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_MEM_OFF0, (stride >> 1) & 0xff); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_MEM_OFF1, (stride >> 9)); + + dbg_blit("(copyarea) dx=%d, dy=%d\n", dx, dy); + dbg_blit("(copyarea) sx=%d, sy=%d\n", sx, sy); + dbg_blit("(copyarea) width=%d, height=%d\n", width - 1, height - 1); + dbg_blit("(copyarea) stride=%d\n", stride); + dbg_blit("(copyarea) bpp=%d=0x0%d, mem_offset1=%d, mem_offset2=%d\n", bpp, (bpp >> 1), + (stride >> 1) & 0xff, stride >> 9); + + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_CC_EXP, 0x0c); + + /* initialize the engine */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_CTL0, 0x80); + + /* wait to complete */ + bltbit_wait_bitclear(info, 0x80, 8000); + + spin_unlock(&s1d13xxxfb_bitblt_lock); +} + +/** + * + * s1d13xxxfb_bitblt_solidfill - accelerated solidfill function + * @info : framebuffer structure + * @rect : fb_fillrect structure + * + * supports (atleast 13506) + * + **/ +static void +s1d13xxxfb_bitblt_solidfill(struct fb_info *info, const struct fb_fillrect *rect) +{ + u32 screen_stride, dest; + u32 fg; + u16 bpp = (info->var.bits_per_pixel >> 3); + + /* grab spinlock */ + spin_lock(&s1d13xxxfb_bitblt_lock); + + /* bytes per x width */ + screen_stride = (bpp * info->var.xres); + + /* bytes to starting point */ + dest = ((rect->dy * screen_stride) + (bpp * rect->dx)); + + dbg_blit("(solidfill) dx=%d, dy=%d, stride=%d, dest=%d\n" + "(solidfill) : rect_width=%d, rect_height=%d\n", + rect->dx, rect->dy, screen_stride, dest, + rect->width - 1, rect->height - 1); + + dbg_blit("(solidfill) : xres=%d, yres=%d, bpp=%d\n", + info->var.xres, info->var.yres, + info->var.bits_per_pixel); + dbg_blit("(solidfill) : rop=%d\n", rect->rop); + + /* We split the destination into the three registers */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_DST_START0, (dest & 0x00ff)); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_DST_START1, ((dest >> 8) & 0x00ff)); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_DST_START2, ((dest >> 16) & 0x00ff)); + + /* give information regarding rectangel width */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_WIDTH0, ((rect->width) & 0x00ff) - 1); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_WIDTH1, (rect->width >> 8)); + + /* give information regarding rectangel height */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_HEIGHT0, ((rect->height) & 0x00ff) - 1); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_HEIGHT1, (rect->height >> 8)); + + if (info->fix.visual == FB_VISUAL_TRUECOLOR || + info->fix.visual == FB_VISUAL_DIRECTCOLOR) { + fg = ((u32 *)info->pseudo_palette)[rect->color]; + dbg_blit("(solidfill) truecolor/directcolor\n"); + dbg_blit("(solidfill) pseudo_palette[%d] = %d\n", rect->color, fg); + } else { + fg = rect->color; + dbg_blit("(solidfill) color = %d\n", rect->color); + } + + /* set foreground color */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_FGC0, (fg & 0xff)); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_FGC1, (fg >> 8) & 0xff); + + /* set rectangual region of memory (rectangle and not linear) */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_CTL0, 0x0); + + /* set operation mode SOLID_FILL */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_OP, BBLT_SOLID_FILL); + + /* set bits per pixel (1 = 16bpp, 0 = 8bpp) */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_CTL1, (info->var.bits_per_pixel >> 4)); + + /* set the memory offset for the bblt in word sizes */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_MEM_OFF0, (screen_stride >> 1) & 0x00ff); + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_MEM_OFF1, (screen_stride >> 9)); + + /* and away we go.... */ + s1d13xxxfb_writereg(info->par, S1DREG_BBLT_CTL0, 0x80); + + /* wait until its done */ + bltbit_wait_bitclear(info, 0x80, 8000); + + /* let others play */ + spin_unlock(&s1d13xxxfb_bitblt_lock); +} + +/* framebuffer information structures */ static struct fb_ops s1d13xxxfb_fbops = { .owner = THIS_MODULE, .fb_set_par = s1d13xxxfb_set_par, @@ -400,7 +665,7 @@ static struct fb_ops s1d13xxxfb_fbops = { .fb_pan_display = s1d13xxxfb_pan_display, - /* to be replaced by any acceleration we can */ + /* gets replaced at chip detection time */ .fb_fillrect = cfb_fillrect, .fb_copyarea = cfb_copyarea, .fb_imageblit = cfb_imageblit, @@ -412,9 +677,9 @@ static int s1d13xxxfb_width_tab[2][4] __devinitdata = { }; /** - * s1d13xxxfb_fetch_hw_state - Configure the framebuffer according to + * s1d13xxxfb_fetch_hw_state - Configure the framebuffer according to * hardware setup. - * @info: frame buffer structure + * @info: frame buffer structure * * We setup the framebuffer structures according to the current * hardware setup. On some machines, the BIOS will have filled @@ -569,7 +834,6 @@ s1d13xxxfb_probe(struct platform_device *pdev) if (pdata && pdata->platform_init_video) pdata->platform_init_video(); - if (pdev->num_resources != 2) { dev_err(&pdev->dev, "invalid num_resources: %i\n", pdev->num_resources); @@ -655,16 +919,27 @@ s1d13xxxfb_probe(struct platform_device *pdev) info->fix = s1d13xxxfb_fix; info->fix.mmio_start = pdev->resource[1].start; - info->fix.mmio_len = pdev->resource[1].end - pdev->resource[1].start +1; + info->fix.mmio_len = pdev->resource[1].end - pdev->resource[1].start + 1; info->fix.smem_start = pdev->resource[0].start; - info->fix.smem_len = pdev->resource[0].end - pdev->resource[0].start +1; + info->fix.smem_len = pdev->resource[0].end - pdev->resource[0].start + 1; printk(KERN_INFO PFX "regs mapped at 0x%p, fb %d KiB mapped at 0x%p\n", default_par->regs, info->fix.smem_len / 1024, info->screen_base); info->par = default_par; - info->fbops = &s1d13xxxfb_fbops; info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_YPAN; + info->fbops = &s1d13xxxfb_fbops; + + switch(prod_id) { + case S1D13506_PROD_ID: /* activate acceleration */ + s1d13xxxfb_fbops.fb_fillrect = s1d13xxxfb_bitblt_solidfill; + s1d13xxxfb_fbops.fb_copyarea = s1d13xxxfb_bitblt_copyarea; + info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_YPAN | + FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_COPYAREA; + break; + default: + break; + } /* perform "manual" chip initialization, if needed */ if (pdata && pdata->initregs) diff --git a/drivers/video/s3c-fb.c b/drivers/video/s3c-fb.c index d3a568e6b16..43680e54542 100644 --- a/drivers/video/s3c-fb.c +++ b/drivers/video/s3c-fb.c @@ -358,9 +358,16 @@ static int s3c_fb_set_par(struct fb_info *info) writel(data, regs + VIDOSD_B(win_no)); data = var->xres * var->yres; + + u32 osdc_data = 0; + + osdc_data = VIDISD14C_ALPHA1_R(0xf) | + VIDISD14C_ALPHA1_G(0xf) | + VIDISD14C_ALPHA1_B(0xf); + if (s3c_fb_has_osd_d(win_no)) { writel(data, regs + VIDOSD_D(win_no)); - writel(0, regs + VIDOSD_C(win_no)); + writel(osdc_data, regs + VIDOSD_C(win_no)); } else writel(data, regs + VIDOSD_C(win_no)); @@ -409,8 +416,12 @@ static int s3c_fb_set_par(struct fb_info *info) data |= WINCON1_BPPMODE_19BPP_A1666; else data |= WINCON1_BPPMODE_18BPP_666; - } else if (var->transp.length != 0) - data |= WINCON1_BPPMODE_25BPP_A1888; + } else if (var->transp.length == 1) + data |= WINCON1_BPPMODE_25BPP_A1888 + | WINCON1_BLD_PIX; + else if (var->transp.length == 4) + data |= WINCON1_BPPMODE_28BPP_A4888 + | WINCON1_BLD_PIX | WINCON1_ALPHA_SEL; else data |= WINCON0_BPPMODE_24BPP_888; @@ -418,6 +429,20 @@ static int s3c_fb_set_par(struct fb_info *info) break; } + /* It has no color key control register for window0 */ + if (win_no > 0) { + u32 keycon0_data = 0, keycon1_data = 0; + + keycon0_data = ~(WxKEYCON0_KEYBL_EN | + WxKEYCON0_KEYEN_F | + WxKEYCON0_DIRCON) | WxKEYCON0_COMPKEY(0); + + keycon1_data = WxKEYCON1_COLVAL(0xffffff); + + writel(keycon0_data, regs + WxKEYCONy(win_no-1, 0)); + writel(keycon1_data, regs + WxKEYCONy(win_no-1, 1)); + } + writel(data, regs + WINCON(win_no)); writel(0x0, regs + WINxMAP(win_no)); @@ -700,9 +725,12 @@ static void s3c_fb_free_memory(struct s3c_fb *sfb, struct s3c_fb_win *win) */ static void s3c_fb_release_win(struct s3c_fb *sfb, struct s3c_fb_win *win) { - fb_dealloc_cmap(&win->fbinfo->cmap); - unregister_framebuffer(win->fbinfo); - s3c_fb_free_memory(sfb, win); + if (win->fbinfo) { + unregister_framebuffer(win->fbinfo); + fb_dealloc_cmap(&win->fbinfo->cmap); + s3c_fb_free_memory(sfb, win); + framebuffer_release(win->fbinfo); + } } /** @@ -753,7 +781,7 @@ static int __devinit s3c_fb_probe_win(struct s3c_fb *sfb, unsigned int win_no, ret = s3c_fb_alloc_memory(sfb, win); if (ret) { dev_err(sfb->dev, "failed to allocate display memory\n"); - goto err_framebuffer; + return ret; } /* setup the r/b/g positions for the window's palette */ @@ -776,7 +804,7 @@ static int __devinit s3c_fb_probe_win(struct s3c_fb *sfb, unsigned int win_no, ret = s3c_fb_check_var(&fbinfo->var, fbinfo); if (ret < 0) { dev_err(sfb->dev, "check_var failed on initial video params\n"); - goto err_alloc_mem; + return ret; } /* create initial colour map */ @@ -796,20 +824,13 @@ static int __devinit s3c_fb_probe_win(struct s3c_fb *sfb, unsigned int win_no, ret = register_framebuffer(fbinfo); if (ret < 0) { dev_err(sfb->dev, "failed to register framebuffer\n"); - goto err_alloc_mem; + return ret; } *res = win; dev_info(sfb->dev, "window %d: fb %s\n", win_no, fbinfo->fix.id); return 0; - -err_alloc_mem: - s3c_fb_free_memory(sfb, win); - -err_framebuffer: - unregister_framebuffer(fbinfo); - return ret; } /** diff --git a/drivers/video/s3c2410fb.c b/drivers/video/s3c2410fb.c index b0b4513ba53..7da0027e240 100644 --- a/drivers/video/s3c2410fb.c +++ b/drivers/video/s3c2410fb.c @@ -24,6 +24,7 @@ #include <linux/interrupt.h> #include <linux/platform_device.h> #include <linux/clk.h> +#include <linux/cpufreq.h> #include <asm/io.h> #include <asm/div64.h> @@ -89,7 +90,7 @@ static void s3c2410fb_set_lcdaddr(struct fb_info *info) static unsigned int s3c2410fb_calc_pixclk(struct s3c2410fb_info *fbi, unsigned long pixclk) { - unsigned long clk = clk_get_rate(fbi->clk); + unsigned long clk = fbi->clk_rate; unsigned long long div; /* pixclk is in picoseconds, our clock is in Hz @@ -758,6 +759,57 @@ static irqreturn_t s3c2410fb_irq(int irq, void *dev_id) return IRQ_HANDLED; } +#ifdef CONFIG_CPU_FREQ + +static int s3c2410fb_cpufreq_transition(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct cpufreq_freqs *freqs = data; + struct s3c2410fb_info *info; + struct fb_info *fbinfo; + long delta_f; + + info = container_of(nb, struct s3c2410fb_info, freq_transition); + fbinfo = platform_get_drvdata(to_platform_device(info->dev)); + + /* work out change, <0 for speed-up */ + delta_f = info->clk_rate - clk_get_rate(info->clk); + + if ((val == CPUFREQ_POSTCHANGE && delta_f > 0) || + (val == CPUFREQ_PRECHANGE && delta_f < 0)) { + info->clk_rate = clk_get_rate(info->clk); + s3c2410fb_activate_var(fbinfo); + } + + return 0; +} + +static inline int s3c2410fb_cpufreq_register(struct s3c2410fb_info *info) +{ + info->freq_transition.notifier_call = s3c2410fb_cpufreq_transition; + + return cpufreq_register_notifier(&info->freq_transition, + CPUFREQ_TRANSITION_NOTIFIER); +} + +static inline void s3c2410fb_cpufreq_deregister(struct s3c2410fb_info *info) +{ + cpufreq_unregister_notifier(&info->freq_transition, + CPUFREQ_TRANSITION_NOTIFIER); +} + +#else +static inline int s3c2410fb_cpufreq_register(struct s3c2410fb_info *info) +{ + return 0; +} + +static inline void s3c2410fb_cpufreq_deregister(struct s3c2410fb_info *info) +{ +} +#endif + + static char driver_name[] = "s3c2410fb"; static int __init s3c24xxfb_probe(struct platform_device *pdev, @@ -875,6 +927,8 @@ static int __init s3c24xxfb_probe(struct platform_device *pdev, msleep(1); + info->clk_rate = clk_get_rate(info->clk); + /* find maximum required memory size for display */ for (i = 0; i < mach_info->num_displays; i++) { unsigned long smem_len = mach_info->displays[i].xres; @@ -904,11 +958,17 @@ static int __init s3c24xxfb_probe(struct platform_device *pdev, s3c2410fb_check_var(&fbinfo->var, fbinfo); + ret = s3c2410fb_cpufreq_register(info); + if (ret < 0) { + dev_err(&pdev->dev, "Failed to register cpufreq\n"); + goto free_video_memory; + } + ret = register_framebuffer(fbinfo); if (ret < 0) { printk(KERN_ERR "Failed to register framebuffer device: %d\n", ret); - goto free_video_memory; + goto free_cpufreq; } /* create device files */ @@ -922,6 +982,8 @@ static int __init s3c24xxfb_probe(struct platform_device *pdev, return 0; + free_cpufreq: + s3c2410fb_cpufreq_deregister(info); free_video_memory: s3c2410fb_unmap_video_memory(fbinfo); release_clock: @@ -961,6 +1023,7 @@ static int s3c2410fb_remove(struct platform_device *pdev) int irq; unregister_framebuffer(fbinfo); + s3c2410fb_cpufreq_deregister(info); s3c2410fb_lcd_enable(info, 0); msleep(1); diff --git a/drivers/video/s3c2410fb.h b/drivers/video/s3c2410fb.h index 9a6ba3e9d1b..47a17bd2301 100644 --- a/drivers/video/s3c2410fb.h +++ b/drivers/video/s3c2410fb.h @@ -29,8 +29,13 @@ struct s3c2410fb_info { enum s3c_drv_type drv_type; struct s3c2410fb_hw regs; + unsigned long clk_rate; unsigned int palette_ready; +#ifdef CONFIG_CPU_FREQ + struct notifier_block freq_transition; +#endif + /* keep these registers in case we need to re-write palette */ u32 palette_buffer[256]; u32 pseudo_pal[16]; diff --git a/drivers/video/sis/sis_main.c b/drivers/video/sis/sis_main.c index 7e17ee95a97..7072d19080d 100644 --- a/drivers/video/sis/sis_main.c +++ b/drivers/video/sis/sis_main.c @@ -5928,7 +5928,7 @@ sisfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if(pci_enable_device(pdev)) { if(ivideo->nbridge) pci_dev_put(ivideo->nbridge); pci_set_drvdata(pdev, NULL); - kfree(sis_fb_info); + framebuffer_release(sis_fb_info); return -EIO; } } @@ -6134,7 +6134,7 @@ error_3: vfree(ivideo->bios_abase); pci_set_drvdata(pdev, NULL); if(!ivideo->sisvga_enabled) pci_disable_device(pdev); - kfree(sis_fb_info); + framebuffer_release(sis_fb_info); return ret; } diff --git a/drivers/video/stifb.c b/drivers/video/stifb.c index eabaad765ae..eec9dcb7f59 100644 --- a/drivers/video/stifb.c +++ b/drivers/video/stifb.c @@ -1380,7 +1380,7 @@ stifb_cleanup(void) if (info->screen_base) iounmap(info->screen_base); fb_dealloc_cmap(&info->cmap); - kfree(info); + framebuffer_release(info); } sti->info = NULL; } diff --git a/drivers/video/tcx.c b/drivers/video/tcx.c index 643afbfe827..45b883598bf 100644 --- a/drivers/video/tcx.c +++ b/drivers/video/tcx.c @@ -116,17 +116,16 @@ struct tcx_par { u32 flags; #define TCX_FLAG_BLANKED 0x00000001 - unsigned long physbase; unsigned long which_io; - unsigned long fbsize; struct sbus_mmap_map mmap_map[TCX_MMAP_ENTRIES]; int lowdepth; }; /* Reset control plane so that WID is 8-bit plane. */ -static void __tcx_set_control_plane(struct tcx_par *par) +static void __tcx_set_control_plane(struct fb_info *info) { + struct tcx_par *par = info->par; u32 __iomem *p, *pend; if (par->lowdepth) @@ -135,7 +134,7 @@ static void __tcx_set_control_plane(struct tcx_par *par) p = par->cplane; if (p == NULL) return; - for (pend = p + par->fbsize; p < pend; p++) { + for (pend = p + info->fix.smem_len; p < pend; p++) { u32 tmp = sbus_readl(p); tmp &= 0xffffff; @@ -149,7 +148,7 @@ static void tcx_reset(struct fb_info *info) unsigned long flags; spin_lock_irqsave(&par->lock, flags); - __tcx_set_control_plane(par); + __tcx_set_control_plane(info); spin_unlock_irqrestore(&par->lock, flags); } @@ -304,7 +303,7 @@ static int tcx_mmap(struct fb_info *info, struct vm_area_struct *vma) struct tcx_par *par = (struct tcx_par *)info->par; return sbusfb_mmap_helper(par->mmap_map, - par->physbase, par->fbsize, + info->fix.smem_start, info->fix.smem_len, par->which_io, vma); } @@ -316,7 +315,7 @@ static int tcx_ioctl(struct fb_info *info, unsigned int cmd, return sbusfb_ioctl_helper(cmd, arg, info, FBTYPE_TCXCOLOR, (par->lowdepth ? 8 : 24), - par->fbsize); + info->fix.smem_len); } /* @@ -358,10 +357,10 @@ static void tcx_unmap_regs(struct of_device *op, struct fb_info *info, par->bt, sizeof(struct bt_regs)); if (par->cplane) of_iounmap(&op->resource[4], - par->cplane, par->fbsize * sizeof(u32)); + par->cplane, info->fix.smem_len * sizeof(u32)); if (info->screen_base) of_iounmap(&op->resource[0], - info->screen_base, par->fbsize); + info->screen_base, info->fix.smem_len); } static int __devinit tcx_probe(struct of_device *op, @@ -391,7 +390,7 @@ static int __devinit tcx_probe(struct of_device *op, linebytes = of_getintprop_default(dp, "linebytes", info->var.xres); - par->fbsize = PAGE_ALIGN(linebytes * info->var.yres); + info->fix.smem_len = PAGE_ALIGN(linebytes * info->var.yres); par->tec = of_ioremap(&op->resource[7], 0, sizeof(struct tcx_tec), "tcx tec"); @@ -400,7 +399,7 @@ static int __devinit tcx_probe(struct of_device *op, par->bt = of_ioremap(&op->resource[8], 0, sizeof(struct bt_regs), "tcx dac"); info->screen_base = of_ioremap(&op->resource[0], 0, - par->fbsize, "tcx ram"); + info->fix.smem_len, "tcx ram"); if (!par->tec || !par->thc || !par->bt || !info->screen_base) goto out_unmap_regs; @@ -408,7 +407,7 @@ static int __devinit tcx_probe(struct of_device *op, memcpy(&par->mmap_map, &__tcx_mmap_map, sizeof(par->mmap_map)); if (!par->lowdepth) { par->cplane = of_ioremap(&op->resource[4], 0, - par->fbsize * sizeof(u32), + info->fix.smem_len * sizeof(u32), "tcx cplane"); if (!par->cplane) goto out_unmap_regs; @@ -419,7 +418,7 @@ static int __devinit tcx_probe(struct of_device *op, par->mmap_map[6].size = SBUS_MMAP_EMPTY; } - par->physbase = op->resource[0].start; + info->fix.smem_start = op->resource[0].start; par->which_io = op->resource[0].flags & IORESOURCE_BITS; for (i = 0; i < TCX_MMAP_ENTRIES; i++) { @@ -473,7 +472,7 @@ static int __devinit tcx_probe(struct of_device *op, printk(KERN_INFO "%s: TCX at %lx:%lx, %s\n", dp->full_name, par->which_io, - par->physbase, + info->fix.smem_start, par->lowdepth ? "8-bit only" : "24-bit depth"); return 0; diff --git a/drivers/video/vesafb.c b/drivers/video/vesafb.c index d6856f43d24..bd37ee1f6a2 100644 --- a/drivers/video/vesafb.c +++ b/drivers/video/vesafb.c @@ -174,8 +174,17 @@ static int vesafb_setcolreg(unsigned regno, unsigned red, unsigned green, return err; } +static void vesafb_destroy(struct fb_info *info) +{ + if (info->screen_base) + iounmap(info->screen_base); + release_mem_region(info->aperture_base, info->aperture_size); + framebuffer_release(info); +} + static struct fb_ops vesafb_ops = { .owner = THIS_MODULE, + .fb_destroy = vesafb_destroy, .fb_setcolreg = vesafb_setcolreg, .fb_pan_display = vesafb_pan_display, .fb_fillrect = cfb_fillrect, @@ -286,6 +295,10 @@ static int __init vesafb_probe(struct platform_device *dev) info->pseudo_palette = info->par; info->par = NULL; + /* set vesafb aperture size for generic probing */ + info->aperture_base = screen_info.lfb_base; + info->aperture_size = size_total; + info->screen_base = ioremap(vesafb_fix.smem_start, vesafb_fix.smem_len); if (!info->screen_base) { printk(KERN_ERR @@ -437,7 +450,7 @@ static int __init vesafb_probe(struct platform_device *dev) info->fbops = &vesafb_ops; info->var = vesafb_defined; info->fix = vesafb_fix; - info->flags = FBINFO_FLAG_DEFAULT | + info->flags = FBINFO_FLAG_DEFAULT | FBINFO_MISC_FIRMWARE | (ypan ? FBINFO_HWACCEL_YPAN : 0); if (!ypan) diff --git a/drivers/vlynq/Kconfig b/drivers/vlynq/Kconfig new file mode 100644 index 00000000000..f6542211db4 --- /dev/null +++ b/drivers/vlynq/Kconfig @@ -0,0 +1,20 @@ +menu "TI VLYNQ" + +config VLYNQ + bool "TI VLYNQ bus support" + depends on AR7 && EXPERIMENTAL + help + Support for Texas Instruments(R) VLYNQ bus. + The VLYNQ bus is a high-speed, serial and packetized + data bus which allows external peripherals of a SoC + to appear into the system's main memory. + + If unsure, say N + +config VLYNQ_DEBUG + bool "VLYNQ bus debug" + depends on VLYNQ && KERNEL_DEBUG + help + Turn on VLYNQ bus debugging. + +endmenu diff --git a/drivers/vlynq/Makefile b/drivers/vlynq/Makefile new file mode 100644 index 00000000000..b3f61149b59 --- /dev/null +++ b/drivers/vlynq/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for kernel vlynq drivers +# + +obj-$(CONFIG_VLYNQ) += vlynq.o diff --git a/drivers/vlynq/vlynq.c b/drivers/vlynq/vlynq.c new file mode 100644 index 00000000000..7335433b067 --- /dev/null +++ b/drivers/vlynq/vlynq.c @@ -0,0 +1,814 @@ +/* + * Copyright (C) 2006, 2007 Eugene Konev <ejka@openwrt.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + * + * Parts of the VLYNQ specification can be found here: + * http://www.ti.com/litv/pdf/sprue36a + */ + +#include <linux/init.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/errno.h> +#include <linux/platform_device.h> +#include <linux/interrupt.h> +#include <linux/device.h> +#include <linux/delay.h> +#include <linux/io.h> + +#include <linux/vlynq.h> + +#define VLYNQ_CTRL_PM_ENABLE 0x80000000 +#define VLYNQ_CTRL_CLOCK_INT 0x00008000 +#define VLYNQ_CTRL_CLOCK_DIV(x) (((x) & 7) << 16) +#define VLYNQ_CTRL_INT_LOCAL 0x00004000 +#define VLYNQ_CTRL_INT_ENABLE 0x00002000 +#define VLYNQ_CTRL_INT_VECTOR(x) (((x) & 0x1f) << 8) +#define VLYNQ_CTRL_INT2CFG 0x00000080 +#define VLYNQ_CTRL_RESET 0x00000001 + +#define VLYNQ_CTRL_CLOCK_MASK (0x7 << 16) + +#define VLYNQ_INT_OFFSET 0x00000014 +#define VLYNQ_REMOTE_OFFSET 0x00000080 + +#define VLYNQ_STATUS_LINK 0x00000001 +#define VLYNQ_STATUS_LERROR 0x00000080 +#define VLYNQ_STATUS_RERROR 0x00000100 + +#define VINT_ENABLE 0x00000100 +#define VINT_TYPE_EDGE 0x00000080 +#define VINT_LEVEL_LOW 0x00000040 +#define VINT_VECTOR(x) ((x) & 0x1f) +#define VINT_OFFSET(irq) (8 * ((irq) % 4)) + +#define VLYNQ_AUTONEGO_V2 0x00010000 + +struct vlynq_regs { + u32 revision; + u32 control; + u32 status; + u32 int_prio; + u32 int_status; + u32 int_pending; + u32 int_ptr; + u32 tx_offset; + struct vlynq_mapping rx_mapping[4]; + u32 chip; + u32 autonego; + u32 unused[6]; + u32 int_device[8]; +}; + +#ifdef VLYNQ_DEBUG +static void vlynq_dump_regs(struct vlynq_device *dev) +{ + int i; + + printk(KERN_DEBUG "VLYNQ local=%p remote=%p\n", + dev->local, dev->remote); + for (i = 0; i < 32; i++) { + printk(KERN_DEBUG "VLYNQ: local %d: %08x\n", + i + 1, ((u32 *)dev->local)[i]); + printk(KERN_DEBUG "VLYNQ: remote %d: %08x\n", + i + 1, ((u32 *)dev->remote)[i]); + } +} + +static void vlynq_dump_mem(u32 *base, int count) +{ + int i; + + for (i = 0; i < (count + 3) / 4; i++) { + if (i % 4 == 0) + printk(KERN_DEBUG "\nMEM[0x%04x]:", i * 4); + printk(KERN_DEBUG " 0x%08x", *(base + i)); + } + printk(KERN_DEBUG "\n"); +} +#endif + +/* Check the VLYNQ link status with a given device */ +static int vlynq_linked(struct vlynq_device *dev) +{ + int i; + + for (i = 0; i < 100; i++) + if (readl(&dev->local->status) & VLYNQ_STATUS_LINK) + return 1; + else + cpu_relax(); + + return 0; +} + +static void vlynq_reset(struct vlynq_device *dev) +{ + writel(readl(&dev->local->control) | VLYNQ_CTRL_RESET, + &dev->local->control); + + /* Wait for the devices to finish resetting */ + msleep(5); + + /* Remove reset bit */ + writel(readl(&dev->local->control) & ~VLYNQ_CTRL_RESET, + &dev->local->control); + + /* Give some time for the devices to settle */ + msleep(5); +} + +static void vlynq_irq_unmask(unsigned int irq) +{ + u32 val; + struct vlynq_device *dev = get_irq_chip_data(irq); + int virq; + + BUG_ON(!dev); + virq = irq - dev->irq_start; + val = readl(&dev->remote->int_device[virq >> 2]); + val |= (VINT_ENABLE | virq) << VINT_OFFSET(virq); + writel(val, &dev->remote->int_device[virq >> 2]); +} + +static void vlynq_irq_mask(unsigned int irq) +{ + u32 val; + struct vlynq_device *dev = get_irq_chip_data(irq); + int virq; + + BUG_ON(!dev); + virq = irq - dev->irq_start; + val = readl(&dev->remote->int_device[virq >> 2]); + val &= ~(VINT_ENABLE << VINT_OFFSET(virq)); + writel(val, &dev->remote->int_device[virq >> 2]); +} + +static int vlynq_irq_type(unsigned int irq, unsigned int flow_type) +{ + u32 val; + struct vlynq_device *dev = get_irq_chip_data(irq); + int virq; + + BUG_ON(!dev); + virq = irq - dev->irq_start; + val = readl(&dev->remote->int_device[virq >> 2]); + switch (flow_type & IRQ_TYPE_SENSE_MASK) { + case IRQ_TYPE_EDGE_RISING: + case IRQ_TYPE_EDGE_FALLING: + case IRQ_TYPE_EDGE_BOTH: + val |= VINT_TYPE_EDGE << VINT_OFFSET(virq); + val &= ~(VINT_LEVEL_LOW << VINT_OFFSET(virq)); + break; + case IRQ_TYPE_LEVEL_HIGH: + val &= ~(VINT_TYPE_EDGE << VINT_OFFSET(virq)); + val &= ~(VINT_LEVEL_LOW << VINT_OFFSET(virq)); + break; + case IRQ_TYPE_LEVEL_LOW: + val &= ~(VINT_TYPE_EDGE << VINT_OFFSET(virq)); + val |= VINT_LEVEL_LOW << VINT_OFFSET(virq); + break; + default: + return -EINVAL; + } + writel(val, &dev->remote->int_device[virq >> 2]); + return 0; +} + +static void vlynq_local_ack(unsigned int irq) +{ + struct vlynq_device *dev = get_irq_chip_data(irq); + + u32 status = readl(&dev->local->status); + + pr_debug("%s: local status: 0x%08x\n", + dev_name(&dev->dev), status); + writel(status, &dev->local->status); +} + +static void vlynq_remote_ack(unsigned int irq) +{ + struct vlynq_device *dev = get_irq_chip_data(irq); + + u32 status = readl(&dev->remote->status); + + pr_debug("%s: remote status: 0x%08x\n", + dev_name(&dev->dev), status); + writel(status, &dev->remote->status); +} + +static irqreturn_t vlynq_irq(int irq, void *dev_id) +{ + struct vlynq_device *dev = dev_id; + u32 status; + int virq = 0; + + status = readl(&dev->local->int_status); + writel(status, &dev->local->int_status); + + if (unlikely(!status)) + spurious_interrupt(); + + while (status) { + if (status & 1) + do_IRQ(dev->irq_start + virq); + status >>= 1; + virq++; + } + + return IRQ_HANDLED; +} + +static struct irq_chip vlynq_irq_chip = { + .name = "vlynq", + .unmask = vlynq_irq_unmask, + .mask = vlynq_irq_mask, + .set_type = vlynq_irq_type, +}; + +static struct irq_chip vlynq_local_chip = { + .name = "vlynq local error", + .unmask = vlynq_irq_unmask, + .mask = vlynq_irq_mask, + .ack = vlynq_local_ack, +}; + +static struct irq_chip vlynq_remote_chip = { + .name = "vlynq local error", + .unmask = vlynq_irq_unmask, + .mask = vlynq_irq_mask, + .ack = vlynq_remote_ack, +}; + +static int vlynq_setup_irq(struct vlynq_device *dev) +{ + u32 val; + int i, virq; + + if (dev->local_irq == dev->remote_irq) { + printk(KERN_ERR + "%s: local vlynq irq should be different from remote\n", + dev_name(&dev->dev)); + return -EINVAL; + } + + /* Clear local and remote error bits */ + writel(readl(&dev->local->status), &dev->local->status); + writel(readl(&dev->remote->status), &dev->remote->status); + + /* Now setup interrupts */ + val = VLYNQ_CTRL_INT_VECTOR(dev->local_irq); + val |= VLYNQ_CTRL_INT_ENABLE | VLYNQ_CTRL_INT_LOCAL | + VLYNQ_CTRL_INT2CFG; + val |= readl(&dev->local->control); + writel(VLYNQ_INT_OFFSET, &dev->local->int_ptr); + writel(val, &dev->local->control); + + val = VLYNQ_CTRL_INT_VECTOR(dev->remote_irq); + val |= VLYNQ_CTRL_INT_ENABLE; + val |= readl(&dev->remote->control); + writel(VLYNQ_INT_OFFSET, &dev->remote->int_ptr); + writel(val, &dev->remote->int_ptr); + writel(val, &dev->remote->control); + + for (i = dev->irq_start; i <= dev->irq_end; i++) { + virq = i - dev->irq_start; + if (virq == dev->local_irq) { + set_irq_chip_and_handler(i, &vlynq_local_chip, + handle_level_irq); + set_irq_chip_data(i, dev); + } else if (virq == dev->remote_irq) { + set_irq_chip_and_handler(i, &vlynq_remote_chip, + handle_level_irq); + set_irq_chip_data(i, dev); + } else { + set_irq_chip_and_handler(i, &vlynq_irq_chip, + handle_simple_irq); + set_irq_chip_data(i, dev); + writel(0, &dev->remote->int_device[virq >> 2]); + } + } + + if (request_irq(dev->irq, vlynq_irq, IRQF_SHARED, "vlynq", dev)) { + printk(KERN_ERR "%s: request_irq failed\n", + dev_name(&dev->dev)); + return -EAGAIN; + } + + return 0; +} + +static void vlynq_device_release(struct device *dev) +{ + struct vlynq_device *vdev = to_vlynq_device(dev); + kfree(vdev); +} + +static int vlynq_device_match(struct device *dev, + struct device_driver *drv) +{ + struct vlynq_device *vdev = to_vlynq_device(dev); + struct vlynq_driver *vdrv = to_vlynq_driver(drv); + struct vlynq_device_id *ids = vdrv->id_table; + + while (ids->id) { + if (ids->id == vdev->dev_id) { + vdev->divisor = ids->divisor; + vlynq_set_drvdata(vdev, ids); + printk(KERN_INFO "Driver found for VLYNQ " + "device: %08x\n", vdev->dev_id); + return 1; + } + printk(KERN_DEBUG "Not using the %08x VLYNQ device's driver" + " for VLYNQ device: %08x\n", ids->id, vdev->dev_id); + ids++; + } + return 0; +} + +static int vlynq_device_probe(struct device *dev) +{ + struct vlynq_device *vdev = to_vlynq_device(dev); + struct vlynq_driver *drv = to_vlynq_driver(dev->driver); + struct vlynq_device_id *id = vlynq_get_drvdata(vdev); + int result = -ENODEV; + + if (drv->probe) + result = drv->probe(vdev, id); + if (result) + put_device(dev); + return result; +} + +static int vlynq_device_remove(struct device *dev) +{ + struct vlynq_driver *drv = to_vlynq_driver(dev->driver); + + if (drv->remove) + drv->remove(to_vlynq_device(dev)); + + return 0; +} + +int __vlynq_register_driver(struct vlynq_driver *driver, struct module *owner) +{ + driver->driver.name = driver->name; + driver->driver.bus = &vlynq_bus_type; + return driver_register(&driver->driver); +} +EXPORT_SYMBOL(__vlynq_register_driver); + +void vlynq_unregister_driver(struct vlynq_driver *driver) +{ + driver_unregister(&driver->driver); +} +EXPORT_SYMBOL(vlynq_unregister_driver); + +/* + * A VLYNQ remote device can clock the VLYNQ bus master + * using a dedicated clock line. In that case, both the + * remove device and the bus master should have the same + * serial clock dividers configured. Iterate through the + * 8 possible dividers until we actually link with the + * device. + */ +static int __vlynq_try_remote(struct vlynq_device *dev) +{ + int i; + + vlynq_reset(dev); + for (i = dev->dev_id ? vlynq_rdiv2 : vlynq_rdiv8; dev->dev_id ? + i <= vlynq_rdiv8 : i >= vlynq_rdiv2; + dev->dev_id ? i++ : i--) { + + if (!vlynq_linked(dev)) + break; + + writel((readl(&dev->remote->control) & + ~VLYNQ_CTRL_CLOCK_MASK) | + VLYNQ_CTRL_CLOCK_INT | + VLYNQ_CTRL_CLOCK_DIV(i - vlynq_rdiv1), + &dev->remote->control); + writel((readl(&dev->local->control) + & ~(VLYNQ_CTRL_CLOCK_INT | + VLYNQ_CTRL_CLOCK_MASK)) | + VLYNQ_CTRL_CLOCK_DIV(i - vlynq_rdiv1), + &dev->local->control); + + if (vlynq_linked(dev)) { + printk(KERN_DEBUG + "%s: using remote clock divisor %d\n", + dev_name(&dev->dev), i - vlynq_rdiv1 + 1); + dev->divisor = i; + return 0; + } else { + vlynq_reset(dev); + } + } + + return -ENODEV; +} + +/* + * A VLYNQ remote device can be clocked by the VLYNQ bus + * master using a dedicated clock line. In that case, only + * the bus master configures the serial clock divider. + * Iterate through the 8 possible dividers until we + * actually get a link with the device. + */ +static int __vlynq_try_local(struct vlynq_device *dev) +{ + int i; + + vlynq_reset(dev); + + for (i = dev->dev_id ? vlynq_ldiv2 : vlynq_ldiv8; dev->dev_id ? + i <= vlynq_ldiv8 : i >= vlynq_ldiv2; + dev->dev_id ? i++ : i--) { + + writel((readl(&dev->local->control) & + ~VLYNQ_CTRL_CLOCK_MASK) | + VLYNQ_CTRL_CLOCK_INT | + VLYNQ_CTRL_CLOCK_DIV(i - vlynq_ldiv1), + &dev->local->control); + + if (vlynq_linked(dev)) { + printk(KERN_DEBUG + "%s: using local clock divisor %d\n", + dev_name(&dev->dev), i - vlynq_ldiv1 + 1); + dev->divisor = i; + return 0; + } else { + vlynq_reset(dev); + } + } + + return -ENODEV; +} + +/* + * When using external clocking method, serial clock + * is supplied by an external oscillator, therefore we + * should mask the local clock bit in the clock control + * register for both the bus master and the remote device. + */ +static int __vlynq_try_external(struct vlynq_device *dev) +{ + vlynq_reset(dev); + if (!vlynq_linked(dev)) + return -ENODEV; + + writel((readl(&dev->remote->control) & + ~VLYNQ_CTRL_CLOCK_INT), + &dev->remote->control); + + writel((readl(&dev->local->control) & + ~VLYNQ_CTRL_CLOCK_INT), + &dev->local->control); + + if (vlynq_linked(dev)) { + printk(KERN_DEBUG "%s: using external clock\n", + dev_name(&dev->dev)); + dev->divisor = vlynq_div_external; + return 0; + } + + return -ENODEV; +} + +static int __vlynq_enable_device(struct vlynq_device *dev) +{ + int result; + struct plat_vlynq_ops *ops = dev->dev.platform_data; + + result = ops->on(dev); + if (result) + return result; + + switch (dev->divisor) { + case vlynq_div_external: + case vlynq_div_auto: + /* When the device is brought from reset it should have clock + * generation negotiated by hardware. + * Check which device is generating clocks and perform setup + * accordingly */ + if (vlynq_linked(dev) && readl(&dev->remote->control) & + VLYNQ_CTRL_CLOCK_INT) { + if (!__vlynq_try_remote(dev) || + !__vlynq_try_local(dev) || + !__vlynq_try_external(dev)) + return 0; + } else { + if (!__vlynq_try_external(dev) || + !__vlynq_try_local(dev) || + !__vlynq_try_remote(dev)) + return 0; + } + break; + case vlynq_ldiv1: + case vlynq_ldiv2: + case vlynq_ldiv3: + case vlynq_ldiv4: + case vlynq_ldiv5: + case vlynq_ldiv6: + case vlynq_ldiv7: + case vlynq_ldiv8: + writel(VLYNQ_CTRL_CLOCK_INT | + VLYNQ_CTRL_CLOCK_DIV(dev->divisor - + vlynq_ldiv1), &dev->local->control); + writel(0, &dev->remote->control); + if (vlynq_linked(dev)) { + printk(KERN_DEBUG + "%s: using local clock divisor %d\n", + dev_name(&dev->dev), + dev->divisor - vlynq_ldiv1 + 1); + return 0; + } + break; + case vlynq_rdiv1: + case vlynq_rdiv2: + case vlynq_rdiv3: + case vlynq_rdiv4: + case vlynq_rdiv5: + case vlynq_rdiv6: + case vlynq_rdiv7: + case vlynq_rdiv8: + writel(0, &dev->local->control); + writel(VLYNQ_CTRL_CLOCK_INT | + VLYNQ_CTRL_CLOCK_DIV(dev->divisor - + vlynq_rdiv1), &dev->remote->control); + if (vlynq_linked(dev)) { + printk(KERN_DEBUG + "%s: using remote clock divisor %d\n", + dev_name(&dev->dev), + dev->divisor - vlynq_rdiv1 + 1); + return 0; + } + break; + } + + ops->off(dev); + return -ENODEV; +} + +int vlynq_enable_device(struct vlynq_device *dev) +{ + struct plat_vlynq_ops *ops = dev->dev.platform_data; + int result = -ENODEV; + + result = __vlynq_enable_device(dev); + if (result) + return result; + + result = vlynq_setup_irq(dev); + if (result) + ops->off(dev); + + dev->enabled = !result; + return result; +} +EXPORT_SYMBOL(vlynq_enable_device); + + +void vlynq_disable_device(struct vlynq_device *dev) +{ + struct plat_vlynq_ops *ops = dev->dev.platform_data; + + dev->enabled = 0; + free_irq(dev->irq, dev); + ops->off(dev); +} +EXPORT_SYMBOL(vlynq_disable_device); + +int vlynq_set_local_mapping(struct vlynq_device *dev, u32 tx_offset, + struct vlynq_mapping *mapping) +{ + int i; + + if (!dev->enabled) + return -ENXIO; + + writel(tx_offset, &dev->local->tx_offset); + for (i = 0; i < 4; i++) { + writel(mapping[i].offset, &dev->local->rx_mapping[i].offset); + writel(mapping[i].size, &dev->local->rx_mapping[i].size); + } + return 0; +} +EXPORT_SYMBOL(vlynq_set_local_mapping); + +int vlynq_set_remote_mapping(struct vlynq_device *dev, u32 tx_offset, + struct vlynq_mapping *mapping) +{ + int i; + + if (!dev->enabled) + return -ENXIO; + + writel(tx_offset, &dev->remote->tx_offset); + for (i = 0; i < 4; i++) { + writel(mapping[i].offset, &dev->remote->rx_mapping[i].offset); + writel(mapping[i].size, &dev->remote->rx_mapping[i].size); + } + return 0; +} +EXPORT_SYMBOL(vlynq_set_remote_mapping); + +int vlynq_set_local_irq(struct vlynq_device *dev, int virq) +{ + int irq = dev->irq_start + virq; + if (dev->enabled) + return -EBUSY; + + if ((irq < dev->irq_start) || (irq > dev->irq_end)) + return -EINVAL; + + if (virq == dev->remote_irq) + return -EINVAL; + + dev->local_irq = virq; + + return 0; +} +EXPORT_SYMBOL(vlynq_set_local_irq); + +int vlynq_set_remote_irq(struct vlynq_device *dev, int virq) +{ + int irq = dev->irq_start + virq; + if (dev->enabled) + return -EBUSY; + + if ((irq < dev->irq_start) || (irq > dev->irq_end)) + return -EINVAL; + + if (virq == dev->local_irq) + return -EINVAL; + + dev->remote_irq = virq; + + return 0; +} +EXPORT_SYMBOL(vlynq_set_remote_irq); + +static int vlynq_probe(struct platform_device *pdev) +{ + struct vlynq_device *dev; + struct resource *regs_res, *mem_res, *irq_res; + int len, result; + + regs_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); + if (!regs_res) + return -ENODEV; + + mem_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mem"); + if (!mem_res) + return -ENODEV; + + irq_res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "devirq"); + if (!irq_res) + return -ENODEV; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) { + printk(KERN_ERR + "vlynq: failed to allocate device structure\n"); + return -ENOMEM; + } + + dev->id = pdev->id; + dev->dev.bus = &vlynq_bus_type; + dev->dev.parent = &pdev->dev; + dev_set_name(&dev->dev, "vlynq%d", dev->id); + dev->dev.platform_data = pdev->dev.platform_data; + dev->dev.release = vlynq_device_release; + + dev->regs_start = regs_res->start; + dev->regs_end = regs_res->end; + dev->mem_start = mem_res->start; + dev->mem_end = mem_res->end; + + len = regs_res->end - regs_res->start; + if (!request_mem_region(regs_res->start, len, dev_name(&dev->dev))) { + printk(KERN_ERR "%s: Can't request vlynq registers\n", + dev_name(&dev->dev)); + result = -ENXIO; + goto fail_request; + } + + dev->local = ioremap(regs_res->start, len); + if (!dev->local) { + printk(KERN_ERR "%s: Can't remap vlynq registers\n", + dev_name(&dev->dev)); + result = -ENXIO; + goto fail_remap; + } + + dev->remote = (struct vlynq_regs *)((void *)dev->local + + VLYNQ_REMOTE_OFFSET); + + dev->irq = platform_get_irq_byname(pdev, "irq"); + dev->irq_start = irq_res->start; + dev->irq_end = irq_res->end; + dev->local_irq = dev->irq_end - dev->irq_start; + dev->remote_irq = dev->local_irq - 1; + + if (device_register(&dev->dev)) + goto fail_register; + platform_set_drvdata(pdev, dev); + + printk(KERN_INFO "%s: regs 0x%p, irq %d, mem 0x%p\n", + dev_name(&dev->dev), (void *)dev->regs_start, dev->irq, + (void *)dev->mem_start); + + dev->dev_id = 0; + dev->divisor = vlynq_div_auto; + result = __vlynq_enable_device(dev); + if (result == 0) { + dev->dev_id = readl(&dev->remote->chip); + ((struct plat_vlynq_ops *)(dev->dev.platform_data))->off(dev); + } + if (dev->dev_id) + printk(KERN_INFO "Found a VLYNQ device: %08x\n", dev->dev_id); + + return 0; + +fail_register: + iounmap(dev->local); +fail_remap: +fail_request: + release_mem_region(regs_res->start, len); + kfree(dev); + return result; +} + +static int vlynq_remove(struct platform_device *pdev) +{ + struct vlynq_device *dev = platform_get_drvdata(pdev); + + device_unregister(&dev->dev); + iounmap(dev->local); + release_mem_region(dev->regs_start, dev->regs_end - dev->regs_start); + + kfree(dev); + + return 0; +} + +static struct platform_driver vlynq_platform_driver = { + .driver.name = "vlynq", + .probe = vlynq_probe, + .remove = __devexit_p(vlynq_remove), +}; + +struct bus_type vlynq_bus_type = { + .name = "vlynq", + .match = vlynq_device_match, + .probe = vlynq_device_probe, + .remove = vlynq_device_remove, +}; +EXPORT_SYMBOL(vlynq_bus_type); + +static int __devinit vlynq_init(void) +{ + int res = 0; + + res = bus_register(&vlynq_bus_type); + if (res) + goto fail_bus; + + res = platform_driver_register(&vlynq_platform_driver); + if (res) + goto fail_platform; + + return 0; + +fail_platform: + bus_unregister(&vlynq_bus_type); +fail_bus: + return res; +} + +static void __devexit vlynq_exit(void) +{ + platform_driver_unregister(&vlynq_platform_driver); + bus_unregister(&vlynq_bus_type); +} + +module_init(vlynq_init); +module_exit(vlynq_exit); diff --git a/fs/Kconfig b/fs/Kconfig index 525da2e8f73..4044f163035 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -39,6 +39,13 @@ config FS_POSIX_ACL bool default n +source "fs/xfs/Kconfig" +source "fs/gfs2/Kconfig" +source "fs/ocfs2/Kconfig" +source "fs/btrfs/Kconfig" + +endif # BLOCK + config FILE_LOCKING bool "Enable POSIX file locking API" if EMBEDDED default y @@ -47,13 +54,6 @@ config FILE_LOCKING for filesystems like NFS and for the flock() system call. Disabling this option saves about 11k. -source "fs/xfs/Kconfig" -source "fs/gfs2/Kconfig" -source "fs/ocfs2/Kconfig" -source "fs/btrfs/Kconfig" - -endif # BLOCK - source "fs/notify/Kconfig" source "fs/quota/Kconfig" diff --git a/fs/drop_caches.c b/fs/drop_caches.c index b6a719a909f..a2edb791344 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -24,7 +24,7 @@ static void drop_pagecache_sb(struct super_block *sb) continue; __iget(inode); spin_unlock(&inode_lock); - __invalidate_mapping_pages(inode->i_mapping, 0, -1, true); + invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; spin_lock(&inode_lock); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 40308e98c6a..caf049146ca 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -321,7 +321,7 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc) spin_lock(&inode_lock); inode->i_state &= ~I_SYNC; - if (!(inode->i_state & I_FREEING)) { + if (!(inode->i_state & (I_FREEING | I_CLEAR))) { if (!(inode->i_state & I_DIRTY) && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { /* @@ -492,7 +492,7 @@ void generic_sync_sb_inodes(struct super_block *sb, break; } - if (inode->i_state & I_NEW) { + if (inode->i_state & (I_NEW | I_WILL_FREE)) { requeue_io(inode); continue; } @@ -523,7 +523,7 @@ void generic_sync_sb_inodes(struct super_block *sb, if (current_is_pdflush() && !writeback_acquire(bdi)) break; - BUG_ON(inode->i_state & I_FREEING); + BUG_ON(inode->i_state & (I_FREEING | I_CLEAR)); __iget(inode); pages_skipped = wbc->pages_skipped; __writeback_single_inode(inode, wbc); diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h index a2ab2529b5c..ceda50aad73 100644 --- a/fs/nfs/iostat.h +++ b/fs/nfs/iostat.h @@ -31,7 +31,7 @@ static inline void nfs_inc_server_stats(const struct nfs_server *server, cpu = get_cpu(); iostats = per_cpu_ptr(server->io_stats, cpu); iostats->events[stat]++; - put_cpu_no_resched(); + put_cpu(); } static inline void nfs_inc_stats(const struct inode *inode, @@ -50,7 +50,7 @@ static inline void nfs_add_server_stats(const struct nfs_server *server, cpu = get_cpu(); iostats = per_cpu_ptr(server->io_stats, cpu); iostats->bytes[stat] += addend; - put_cpu_no_resched(); + put_cpu(); } static inline void nfs_add_stats(const struct inode *inode, @@ -71,7 +71,7 @@ static inline void nfs_add_fscache_stats(struct inode *inode, cpu = get_cpu(); iostats = per_cpu_ptr(NFS_SERVER(inode)->io_stats, cpu); iostats->fscache[stat] += addend; - put_cpu_no_resched(); + put_cpu(); } #endif diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 82c5085559c..9938034762c 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -27,6 +27,7 @@ #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/slab.h> +#include <linux/log2.h> #include "aops.h" #include "attrib.h" @@ -1570,7 +1571,7 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) ntfs_debug("Index collation rule is 0x%x.", le32_to_cpu(ir->collation_rule)); ni->itype.index.block_size = le32_to_cpu(ir->index_block_size); - if (ni->itype.index.block_size & (ni->itype.index.block_size - 1)) { + if (!is_power_of_2(ni->itype.index.block_size)) { ntfs_error(vi->i_sb, "Index block size (%u) is not a power of " "two.", ni->itype.index.block_size); goto unm_err_out; diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c index d7932e95b1f..89b02985c05 100644 --- a/fs/ntfs/logfile.c +++ b/fs/ntfs/logfile.c @@ -26,6 +26,7 @@ #include <linux/highmem.h> #include <linux/buffer_head.h> #include <linux/bitops.h> +#include <linux/log2.h> #include "attrib.h" #include "aops.h" @@ -65,7 +66,7 @@ static bool ntfs_check_restart_page_header(struct inode *vi, logfile_log_page_size < NTFS_BLOCK_SIZE || logfile_system_page_size & (logfile_system_page_size - 1) || - logfile_log_page_size & (logfile_log_page_size - 1)) { + !is_power_of_2(logfile_log_page_size)) { ntfs_error(vi->i_sb, "$LogFile uses unsupported page size."); return false; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 1539e630c47..3ce5ae9e3d2 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1006,7 +1006,12 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf, if (!task) return -ESRCH; - oom_adjust = task->oomkilladj; + task_lock(task); + if (task->mm) + oom_adjust = task->mm->oom_adj; + else + oom_adjust = OOM_DISABLE; + task_unlock(task); put_task_struct(task); len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust); @@ -1035,11 +1040,19 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, task = get_proc_task(file->f_path.dentry->d_inode); if (!task) return -ESRCH; - if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) { + task_lock(task); + if (!task->mm) { + task_unlock(task); + put_task_struct(task); + return -EINVAL; + } + if (oom_adjust < task->mm->oom_adj && !capable(CAP_SYS_RESOURCE)) { + task_unlock(task); put_task_struct(task); return -EACCES; } - task->oomkilladj = oom_adjust; + task->mm->oom_adj = oom_adjust; + task_unlock(task); put_task_struct(task); if (end - buffer == 0) return -EIO; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index c6b0302af4c..d5c410d47fa 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -64,10 +64,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v) "Inactive(anon): %8lu kB\n" "Active(file): %8lu kB\n" "Inactive(file): %8lu kB\n" -#ifdef CONFIG_UNEVICTABLE_LRU "Unevictable: %8lu kB\n" "Mlocked: %8lu kB\n" -#endif #ifdef CONFIG_HIGHMEM "HighTotal: %8lu kB\n" "HighFree: %8lu kB\n" @@ -109,10 +107,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(pages[LRU_INACTIVE_ANON]), K(pages[LRU_ACTIVE_FILE]), K(pages[LRU_INACTIVE_FILE]), -#ifdef CONFIG_UNEVICTABLE_LRU K(pages[LRU_UNEVICTABLE]), K(global_page_state(NR_MLOCK)), -#endif #ifdef CONFIG_HIGHMEM K(i.totalhigh), K(i.freehigh), diff --git a/fs/proc/page.c b/fs/proc/page.c index e9983837d08..2707c6c7a20 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -6,11 +6,13 @@ #include <linux/mmzone.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/hugetlb.h> #include <asm/uaccess.h> #include "internal.h" #define KPMSIZE sizeof(u64) #define KPMMASK (KPMSIZE - 1) + /* /proc/kpagecount - an array exposing page counts * * Each entry is a u64 representing the corresponding @@ -32,20 +34,22 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - ppage = NULL; if (pfn_valid(pfn)) ppage = pfn_to_page(pfn); - pfn++; + else + ppage = NULL; if (!ppage) pcount = 0; else pcount = page_mapcount(ppage); - if (put_user(pcount, out++)) { + if (put_user(pcount, out)) { ret = -EFAULT; break; } + pfn++; + out++; count -= KPMSIZE; } @@ -68,19 +72,122 @@ static const struct file_operations proc_kpagecount_operations = { /* These macros are used to decouple internal flags from exported ones */ -#define KPF_LOCKED 0 -#define KPF_ERROR 1 -#define KPF_REFERENCED 2 -#define KPF_UPTODATE 3 -#define KPF_DIRTY 4 -#define KPF_LRU 5 -#define KPF_ACTIVE 6 -#define KPF_SLAB 7 -#define KPF_WRITEBACK 8 -#define KPF_RECLAIM 9 -#define KPF_BUDDY 10 +#define KPF_LOCKED 0 +#define KPF_ERROR 1 +#define KPF_REFERENCED 2 +#define KPF_UPTODATE 3 +#define KPF_DIRTY 4 +#define KPF_LRU 5 +#define KPF_ACTIVE 6 +#define KPF_SLAB 7 +#define KPF_WRITEBACK 8 +#define KPF_RECLAIM 9 +#define KPF_BUDDY 10 + +/* 11-20: new additions in 2.6.31 */ +#define KPF_MMAP 11 +#define KPF_ANON 12 +#define KPF_SWAPCACHE 13 +#define KPF_SWAPBACKED 14 +#define KPF_COMPOUND_HEAD 15 +#define KPF_COMPOUND_TAIL 16 +#define KPF_HUGE 17 +#define KPF_UNEVICTABLE 18 +#define KPF_NOPAGE 20 + +/* kernel hacking assistances + * WARNING: subject to change, never rely on them! + */ +#define KPF_RESERVED 32 +#define KPF_MLOCKED 33 +#define KPF_MAPPEDTODISK 34 +#define KPF_PRIVATE 35 +#define KPF_PRIVATE_2 36 +#define KPF_OWNER_PRIVATE 37 +#define KPF_ARCH 38 +#define KPF_UNCACHED 39 + +static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit) +{ + return ((kflags >> kbit) & 1) << ubit; +} -#define kpf_copy_bit(flags, dstpos, srcpos) (((flags >> srcpos) & 1) << dstpos) +static u64 get_uflags(struct page *page) +{ + u64 k; + u64 u; + + /* + * pseudo flag: KPF_NOPAGE + * it differentiates a memory hole from a page with no flags + */ + if (!page) + return 1 << KPF_NOPAGE; + + k = page->flags; + u = 0; + + /* + * pseudo flags for the well known (anonymous) memory mapped pages + * + * Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the + * simple test in page_mapped() is not enough. + */ + if (!PageSlab(page) && page_mapped(page)) + u |= 1 << KPF_MMAP; + if (PageAnon(page)) + u |= 1 << KPF_ANON; + + /* + * compound pages: export both head/tail info + * they together define a compound page's start/end pos and order + */ + if (PageHead(page)) + u |= 1 << KPF_COMPOUND_HEAD; + if (PageTail(page)) + u |= 1 << KPF_COMPOUND_TAIL; + if (PageHuge(page)) + u |= 1 << KPF_HUGE; + + u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); + + /* + * Caveats on high order pages: + * PG_buddy will only be set on the head page; SLUB/SLQB do the same + * for PG_slab; SLOB won't set PG_slab at all on compound pages. + */ + u |= kpf_copy_bit(k, KPF_SLAB, PG_slab); + u |= kpf_copy_bit(k, KPF_BUDDY, PG_buddy); + + u |= kpf_copy_bit(k, KPF_ERROR, PG_error); + u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty); + u |= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate); + u |= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback); + + u |= kpf_copy_bit(k, KPF_LRU, PG_lru); + u |= kpf_copy_bit(k, KPF_REFERENCED, PG_referenced); + u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active); + u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim); + + u |= kpf_copy_bit(k, KPF_SWAPCACHE, PG_swapcache); + u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked); + + u |= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable); + u |= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked); + +#ifdef CONFIG_IA64_UNCACHED_ALLOCATOR + u |= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached); +#endif + + u |= kpf_copy_bit(k, KPF_RESERVED, PG_reserved); + u |= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk); + u |= kpf_copy_bit(k, KPF_PRIVATE, PG_private); + u |= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2); + u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1); + u |= kpf_copy_bit(k, KPF_ARCH, PG_arch_1); + + return u; +}; static ssize_t kpageflags_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) @@ -90,7 +197,6 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, unsigned long src = *ppos; unsigned long pfn; ssize_t ret = 0; - u64 kflags, uflags; pfn = src / KPMSIZE; count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); @@ -98,32 +204,18 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - ppage = NULL; if (pfn_valid(pfn)) ppage = pfn_to_page(pfn); - pfn++; - if (!ppage) - kflags = 0; else - kflags = ppage->flags; - - uflags = kpf_copy_bit(kflags, KPF_LOCKED, PG_locked) | - kpf_copy_bit(kflags, KPF_ERROR, PG_error) | - kpf_copy_bit(kflags, KPF_REFERENCED, PG_referenced) | - kpf_copy_bit(kflags, KPF_UPTODATE, PG_uptodate) | - kpf_copy_bit(kflags, KPF_DIRTY, PG_dirty) | - kpf_copy_bit(kflags, KPF_LRU, PG_lru) | - kpf_copy_bit(kflags, KPF_ACTIVE, PG_active) | - kpf_copy_bit(kflags, KPF_SLAB, PG_slab) | - kpf_copy_bit(kflags, KPF_WRITEBACK, PG_writeback) | - kpf_copy_bit(kflags, KPF_RECLAIM, PG_reclaim) | - kpf_copy_bit(kflags, KPF_BUDDY, PG_buddy); - - if (put_user(uflags, out++)) { + ppage = NULL; + + if (put_user(get_uflags(ppage), out)) { ret = -EFAULT; break; } + pfn++; + out++; count -= KPMSIZE; } diff --git a/fs/select.c b/fs/select.c index 0fe0e1469df..d870237e42c 100644 --- a/fs/select.c +++ b/fs/select.c @@ -168,7 +168,7 @@ static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) return table->entry++; } -static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) { struct poll_wqueues *pwq = wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); @@ -194,6 +194,16 @@ static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) return default_wake_function(&dummy_wait, mode, sync, key); } +static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + struct poll_table_entry *entry; + + entry = container_of(wait, struct poll_table_entry, wait); + if (key && !((unsigned long)key & entry->key)) + return 0; + return __pollwake(wait, mode, sync, key); +} + /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) @@ -205,6 +215,7 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, get_file(filp); entry->filp = filp; entry->wait_address = wait_address; + entry->key = p->key; init_waitqueue_func_entry(&entry->wait, pollwake); entry->wait.private = pwq; add_wait_queue(wait_address, &entry->wait); @@ -362,6 +373,18 @@ get_max: #define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR) #define POLLEX_SET (POLLPRI) +static inline void wait_key_set(poll_table *wait, unsigned long in, + unsigned long out, unsigned long bit) +{ + if (wait) { + wait->key = POLLEX_SET; + if (in & bit) + wait->key |= POLLIN_SET; + if (out & bit) + wait->key |= POLLOUT_SET; + } +} + int do_select(int n, fd_set_bits *fds, struct timespec *end_time) { ktime_t expire, *to = NULL; @@ -418,20 +441,25 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) if (file) { f_op = file->f_op; mask = DEFAULT_POLLMASK; - if (f_op && f_op->poll) - mask = (*f_op->poll)(file, retval ? NULL : wait); + if (f_op && f_op->poll) { + wait_key_set(wait, in, out, bit); + mask = (*f_op->poll)(file, wait); + } fput_light(file, fput_needed); if ((mask & POLLIN_SET) && (in & bit)) { res_in |= bit; retval++; + wait = NULL; } if ((mask & POLLOUT_SET) && (out & bit)) { res_out |= bit; retval++; + wait = NULL; } if ((mask & POLLEX_SET) && (ex & bit)) { res_ex |= bit; retval++; + wait = NULL; } } } @@ -685,8 +713,12 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait) mask = POLLNVAL; if (file != NULL) { mask = DEFAULT_POLLMASK; - if (file->f_op && file->f_op->poll) + if (file->f_op && file->f_op->poll) { + if (pwait) + pwait->key = pollfd->events | + POLLERR | POLLHUP; mask = file->f_op->poll(file, pwait); + } /* Mask out unneeded events. */ mask &= pollfd->events | POLLERR | POLLHUP; fput_light(file, fput_needed); diff --git a/include/asm-generic/kmap_types.h b/include/asm-generic/kmap_types.h index 58c33055c30..54e8b3d956b 100644 --- a/include/asm-generic/kmap_types.h +++ b/include/asm-generic/kmap_types.h @@ -1,7 +1,7 @@ #ifndef _ASM_GENERIC_KMAP_TYPES_H #define _ASM_GENERIC_KMAP_TYPES_H -#ifdef CONFIG_DEBUG_HIGHMEM +#ifdef __WITH_KM_FENCE # define D(n) __KM_FENCE_##n , #else # define D(n) diff --git a/include/linux/bug.h b/include/linux/bug.h index 54398d2c6d8..d276b5510c8 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -1,7 +1,6 @@ #ifndef _LINUX_BUG_H #define _LINUX_BUG_H -#include <linux/module.h> #include <asm/bug.h> enum bug_trap_type { @@ -24,10 +23,6 @@ const struct bug_entry *find_bug(unsigned long bugaddr); enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs); -int module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, - struct module *); -void module_bug_cleanup(struct module *); - /* These are defined by the architecture */ int is_valid_bugaddr(unsigned long addr); @@ -38,13 +33,6 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr, { return BUG_TRAP_TYPE_BUG; } -static inline int module_bug_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - struct module *mod) -{ - return 0; -} -static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ #endif /* _LINUX_BUG_H */ diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 05ea1dd7d68..a5740fc4d04 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -18,7 +18,6 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ -extern int cpuset_init_early(void); extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); @@ -27,7 +26,6 @@ extern void cpuset_cpus_allowed_locked(struct task_struct *p, extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); -void cpuset_update_task_memory_state(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask); @@ -92,9 +90,13 @@ extern void rebuild_sched_domains(void); extern void cpuset_print_task_mems_allowed(struct task_struct *p); +static inline void set_mems_allowed(nodemask_t nodemask) +{ + current->mems_allowed = nodemask; +} + #else /* !CONFIG_CPUSETS */ -static inline int cpuset_init_early(void) { return 0; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} @@ -116,7 +118,6 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) #define cpuset_current_mems_allowed (node_states[N_HIGH_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} -static inline void cpuset_update_task_memory_state(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { @@ -188,6 +189,10 @@ static inline void cpuset_print_task_mems_allowed(struct task_struct *p) { } +static inline void set_mems_allowed(nodemask_t nodemask) +{ +} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/include/linux/fb.h b/include/linux/fb.h index 330c4b1bfca..dd68358996b 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -677,6 +677,9 @@ struct fb_ops { /* get capability given var */ void (*fb_get_caps)(struct fb_info *info, struct fb_blit_caps *caps, struct fb_var_screeninfo *var); + + /* teardown any resources to do with this framebuffer */ + void (*fb_destroy)(struct fb_info *info); }; #ifdef CONFIG_FB_TILEBLITTING @@ -786,6 +789,8 @@ struct fb_tile_ops { #define FBINFO_MISC_USEREVENT 0x10000 /* event request from userspace */ #define FBINFO_MISC_TILEBLITTING 0x20000 /* use tile blitting */ +#define FBINFO_MISC_FIRMWARE 0x40000 /* a replaceable firmware + inited framebuffer */ /* A driver may set this flag to indicate that it does want a set_par to be * called every time when fbcon_switch is executed. The advantage is that with @@ -854,7 +859,12 @@ struct fb_info { u32 state; /* Hardware state i.e suspend */ void *fbcon_par; /* fbcon use-only private area */ /* From here on everything is device dependent */ - void *par; + void *par; + /* we need the PCI or similiar aperture base/size not + smem_start/size as smem_start may just be an object + allocated inside the aperture so may not actually overlap */ + resource_size_t aperture_base; + resource_size_t aperture_size; }; #ifdef MODULE @@ -893,7 +903,7 @@ struct fb_info { #define fb_writeq sbus_writeq #define fb_memset sbus_memset_io -#elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || defined(__avr32__) +#elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || defined(__avr32__) || defined(__bfin__) #define fb_readb __raw_readb #define fb_readw __raw_readw diff --git a/include/linux/firmware-map.h b/include/linux/firmware-map.h index cca686b3912..875451f1373 100644 --- a/include/linux/firmware-map.h +++ b/include/linux/firmware-map.h @@ -24,21 +24,17 @@ */ #ifdef CONFIG_FIRMWARE_MEMMAP -int firmware_map_add(resource_size_t start, resource_size_t end, - const char *type); -int firmware_map_add_early(resource_size_t start, resource_size_t end, - const char *type); +int firmware_map_add(u64 start, u64 end, const char *type); +int firmware_map_add_early(u64 start, u64 end, const char *type); #else /* CONFIG_FIRMWARE_MEMMAP */ -static inline int firmware_map_add(resource_size_t start, resource_size_t end, - const char *type) +static inline int firmware_map_add(u64 start, u64 end, const char *type) { return 0; } -static inline int firmware_map_add_early(resource_size_t start, - resource_size_t end, const char *type) +static inline int firmware_map_add_early(u64 start, u64 end, const char *type) { return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 6d12174fbe1..74a57938c88 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -879,7 +879,7 @@ struct file_ra_state { there are only # of pages ahead */ unsigned int ra_pages; /* Maximum readahead window */ - int mmap_miss; /* Cache miss stat for mmap accesses */ + unsigned int mmap_miss; /* Cache miss stat for mmap accesses */ loff_t prev_pos; /* Cache last read() position */ }; @@ -2037,9 +2037,6 @@ extern int __invalidate_device(struct block_device *); extern int invalidate_partition(struct gendisk *, int); #endif extern int invalidate_inodes(struct super_block *); -unsigned long __invalidate_mapping_pages(struct address_space *mapping, - pgoff_t start, pgoff_t end, - bool be_atomic); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 80e14b8c2e7..cfdb35d71bc 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -5,6 +5,7 @@ #include <linux/stddef.h> #include <linux/linkage.h> #include <linux/topology.h> +#include <linux/mmdebug.h> struct vm_area_struct; @@ -20,7 +21,8 @@ struct vm_area_struct; #define __GFP_DMA ((__force gfp_t)0x01u) #define __GFP_HIGHMEM ((__force gfp_t)0x02u) #define __GFP_DMA32 ((__force gfp_t)0x04u) - +#define __GFP_MOVABLE ((__force gfp_t)0x08u) /* Page is movable */ +#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) /* * Action modifiers - doesn't change the zoning * @@ -50,7 +52,6 @@ struct vm_area_struct; #define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */ #define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */ #define __GFP_RECLAIMABLE ((__force gfp_t)0x80000u) /* Page is reclaimable */ -#define __GFP_MOVABLE ((__force gfp_t)0x100000u) /* Page is movable */ #ifdef CONFIG_KMEMCHECK #define __GFP_NOTRACK ((__force gfp_t)0x200000u) /* Don't track with kmemcheck */ @@ -127,24 +128,105 @@ static inline int allocflags_to_migratetype(gfp_t gfp_flags) ((gfp_flags & __GFP_RECLAIMABLE) != 0); } -static inline enum zone_type gfp_zone(gfp_t flags) -{ +#ifdef CONFIG_HIGHMEM +#define OPT_ZONE_HIGHMEM ZONE_HIGHMEM +#else +#define OPT_ZONE_HIGHMEM ZONE_NORMAL +#endif + #ifdef CONFIG_ZONE_DMA - if (flags & __GFP_DMA) - return ZONE_DMA; +#define OPT_ZONE_DMA ZONE_DMA +#else +#define OPT_ZONE_DMA ZONE_NORMAL #endif + #ifdef CONFIG_ZONE_DMA32 - if (flags & __GFP_DMA32) - return ZONE_DMA32; +#define OPT_ZONE_DMA32 ZONE_DMA32 +#else +#define OPT_ZONE_DMA32 ZONE_NORMAL #endif - if ((flags & (__GFP_HIGHMEM | __GFP_MOVABLE)) == - (__GFP_HIGHMEM | __GFP_MOVABLE)) - return ZONE_MOVABLE; -#ifdef CONFIG_HIGHMEM - if (flags & __GFP_HIGHMEM) - return ZONE_HIGHMEM; + +/* + * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the + * zone to use given the lowest 4 bits of gfp_t. Entries are ZONE_SHIFT long + * and there are 16 of them to cover all possible combinations of + * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM + * + * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. + * But GFP_MOVABLE is not only a zone specifier but also an allocation + * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. + * Only 1bit of the lowest 3 bit (DMA,DMA32,HIGHMEM) can be set to "1". + * + * bit result + * ================= + * 0x0 => NORMAL + * 0x1 => DMA or NORMAL + * 0x2 => HIGHMEM or NORMAL + * 0x3 => BAD (DMA+HIGHMEM) + * 0x4 => DMA32 or DMA or NORMAL + * 0x5 => BAD (DMA+DMA32) + * 0x6 => BAD (HIGHMEM+DMA32) + * 0x7 => BAD (HIGHMEM+DMA32+DMA) + * 0x8 => NORMAL (MOVABLE+0) + * 0x9 => DMA or NORMAL (MOVABLE+DMA) + * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) + * 0xb => BAD (MOVABLE+HIGHMEM+DMA) + * 0xc => DMA32 (MOVABLE+HIGHMEM+DMA32) + * 0xd => BAD (MOVABLE+DMA32+DMA) + * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) + * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) + * + * ZONES_SHIFT must be <= 2 on 32 bit platforms. + */ + +#if 16 * ZONES_SHIFT > BITS_PER_LONG +#error ZONES_SHIFT too large to create GFP_ZONE_TABLE integer +#endif + +#define GFP_ZONE_TABLE ( \ + (ZONE_NORMAL << 0 * ZONES_SHIFT) \ + | (OPT_ZONE_DMA << __GFP_DMA * ZONES_SHIFT) \ + | (OPT_ZONE_HIGHMEM << __GFP_HIGHMEM * ZONES_SHIFT) \ + | (OPT_ZONE_DMA32 << __GFP_DMA32 * ZONES_SHIFT) \ + | (ZONE_NORMAL << __GFP_MOVABLE * ZONES_SHIFT) \ + | (OPT_ZONE_DMA << (__GFP_MOVABLE | __GFP_DMA) * ZONES_SHIFT) \ + | (ZONE_MOVABLE << (__GFP_MOVABLE | __GFP_HIGHMEM) * ZONES_SHIFT)\ + | (OPT_ZONE_DMA32 << (__GFP_MOVABLE | __GFP_DMA32) * ZONES_SHIFT)\ +) + +/* + * GFP_ZONE_BAD is a bitmap for all combination of __GFP_DMA, __GFP_DMA32 + * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per + * entry starting with bit 0. Bit is set if the combination is not + * allowed. + */ +#define GFP_ZONE_BAD ( \ + 1 << (__GFP_DMA | __GFP_HIGHMEM) \ + | 1 << (__GFP_DMA | __GFP_DMA32) \ + | 1 << (__GFP_DMA32 | __GFP_HIGHMEM) \ + | 1 << (__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM) \ + | 1 << (__GFP_MOVABLE | __GFP_HIGHMEM | __GFP_DMA) \ + | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_DMA) \ + | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_HIGHMEM) \ + | 1 << (__GFP_MOVABLE | __GFP_DMA32 | __GFP_DMA | __GFP_HIGHMEM)\ +) + +static inline enum zone_type gfp_zone(gfp_t flags) +{ + enum zone_type z; + int bit = flags & GFP_ZONEMASK; + + z = (GFP_ZONE_TABLE >> (bit * ZONES_SHIFT)) & + ((1 << ZONES_SHIFT) - 1); + + if (__builtin_constant_p(bit)) + BUILD_BUG_ON((GFP_ZONE_BAD >> bit) & 1); + else { +#ifdef CONFIG_DEBUG_VM + BUG_ON((GFP_ZONE_BAD >> bit) & 1); #endif - return ZONE_NORMAL; + } + return z; } /* @@ -184,30 +266,19 @@ static inline void arch_alloc_page(struct page *page, int order) { } #endif struct page * -__alloc_pages_internal(gfp_t gfp_mask, unsigned int order, +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, nodemask_t *nodemask); static inline struct page * __alloc_pages(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist) { - return __alloc_pages_internal(gfp_mask, order, zonelist, NULL); + return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL); } -static inline struct page * -__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, nodemask_t *nodemask) -{ - return __alloc_pages_internal(gfp_mask, order, zonelist, nodemask); -} - - static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { - if (unlikely(order >= MAX_ORDER)) - return NULL; - /* Unknown node is current node */ if (nid < 0) nid = numa_node_id(); @@ -215,15 +286,20 @@ 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); static inline struct page * alloc_pages(gfp_t gfp_mask, unsigned int order) { - if (unlikely(order >= MAX_ORDER)) - return NULL; - return alloc_pages_current(gfp_mask, order); } extern struct page *alloc_page_vma(gfp_t gfp_mask, @@ -260,4 +336,16 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(void); void drain_local_pages(void *dummy); +extern bool oom_killer_disabled; + +static inline void oom_killer_disable(void) +{ + oom_killer_disabled = true; +} + +static inline void oom_killer_enable(void) +{ + oom_killer_disabled = false; +} + #endif /* __LINUX_GFP_H */ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 1fcb7126a01..211ff449726 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -55,7 +55,9 @@ static inline void *kmap(struct page *page) return page_address(page); } -#define kunmap(page) do { (void) (page); } while (0) +static inline void kunmap(struct page *page) +{ +} static inline void *kmap_atomic(struct page *page, enum km_type idx) { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 03be7f29ca0..a05a5ef3339 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -11,6 +11,8 @@ struct ctl_table; +int PageHuge(struct page *page); + static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) { return vma->vm_flags & VM_HUGETLB; @@ -61,6 +63,11 @@ void hugetlb_change_protection(struct vm_area_struct *vma, #else /* !CONFIG_HUGETLB_PAGE */ +static inline int PageHuge(struct page *page) +{ + return 0; +} + static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) { return 0; diff --git a/include/linux/init.h b/include/linux/init.h index b2189803f19..8c2c9989626 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -29,7 +29,7 @@ * sign followed by value, e.g.: * * static int init_variable __initdata = 0; - * static char linux_logo[] __initdata = { 0x32, 0x36, ... }; + * static const char linux_logo[] __initconst = { 0x32, 0x36, ... }; * * Don't forget to initialize data not at file scope, i.e. within a function, * as gcc otherwise puts the data into the bss section and not into the init diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 28b1f30601b..5368fbdc780 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -15,18 +15,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; -#define INIT_MM(name) \ -{ \ - .mm_rb = RB_ROOT, \ - .pgd = swapper_pg_dir, \ - .mm_users = ATOMIC_INIT(2), \ - .mm_count = ATOMIC_INIT(1), \ - .mmap_sem = __RWSEM_INITIALIZER(name.mmap_sem), \ - .page_table_lock = __SPIN_LOCK_UNLOCKED(name.page_table_lock), \ - .mmlist = LIST_HEAD_INIT(name.mmlist), \ - .cpu_vm_mask = CPU_MASK_ALL, \ -} - #define INIT_SIGNALS(sig) { \ .count = ATOMIC_INIT(1), \ .wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\ diff --git a/include/linux/linux_logo.h b/include/linux/linux_logo.h index 08a92969c76..ca5bd91d12e 100644 --- a/include/linux/linux_logo.h +++ b/include/linux/linux_logo.h @@ -32,6 +32,22 @@ struct linux_logo { const unsigned char *data; }; +extern const struct linux_logo logo_linux_mono; +extern const struct linux_logo logo_linux_vga16; +extern const struct linux_logo logo_linux_clut224; +extern const struct linux_logo logo_blackfin_vga16; +extern const struct linux_logo logo_blackfin_clut224; +extern const struct linux_logo logo_dec_clut224; +extern const struct linux_logo logo_mac_clut224; +extern const struct linux_logo logo_parisc_clut224; +extern const struct linux_logo logo_sgi_clut224; +extern const struct linux_logo logo_sun_clut224; +extern const struct linux_logo logo_superh_mono; +extern const struct linux_logo logo_superh_vga16; +extern const struct linux_logo logo_superh_clut224; +extern const struct linux_logo logo_m32r_clut224; +extern const struct linux_logo logo_spe_clut224; + extern const struct linux_logo *fb_find_logo(int depth); #ifdef CONFIG_FB_LOGO_EXTRA extern void fb_append_extra_logo(const struct linux_logo *logo, diff --git a/include/linux/lis3lv02d.h b/include/linux/lis3lv02d.h new file mode 100644 index 00000000000..ad651f4e45a --- /dev/null +++ b/include/linux/lis3lv02d.h @@ -0,0 +1,39 @@ +#ifndef __LIS3LV02D_H_ +#define __LIS3LV02D_H_ + +struct lis3lv02d_platform_data { + /* please note: the 'click' feature is only supported for + * LIS[32]02DL variants of the chip and will be ignored for + * others */ +#define LIS3_CLICK_SINGLE_X (1 << 0) +#define LIS3_CLICK_DOUBLE_X (1 << 1) +#define LIS3_CLICK_SINGLE_Y (1 << 2) +#define LIS3_CLICK_DOUBLE_Y (1 << 3) +#define LIS3_CLICK_SINGLE_Z (1 << 4) +#define LIS3_CLICK_DOUBLE_Z (1 << 5) + unsigned char click_flags; + unsigned char click_thresh_x; + unsigned char click_thresh_y; + unsigned char click_thresh_z; + unsigned char click_time_limit; + unsigned char click_latency; + unsigned char click_window; + +#define LIS3_IRQ1_DISABLE (0 << 0) +#define LIS3_IRQ1_FF_WU_1 (1 << 0) +#define LIS3_IRQ1_FF_WU_2 (2 << 0) +#define LIS3_IRQ1_FF_WU_12 (3 << 0) +#define LIS3_IRQ1_DATA_READY (4 << 0) +#define LIS3_IRQ1_CLICK (7 << 0) +#define LIS3_IRQ2_DISABLE (0 << 3) +#define LIS3_IRQ2_FF_WU_1 (1 << 3) +#define LIS3_IRQ2_FF_WU_2 (2 << 3) +#define LIS3_IRQ2_FF_WU_12 (3 << 3) +#define LIS3_IRQ2_DATA_READY (4 << 3) +#define LIS3_IRQ2_CLICK (7 << 3) +#define LIS3_IRQ_OPEN_DRAIN (1 << 6) +#define LIS3_IRQ_ACTIVE_HIGH (1 << 7) + unsigned char irq_cfg; +}; + +#endif /* __LIS3LV02D_H_ */ diff --git a/include/linux/major.h b/include/linux/major.h index 058ec15dd06..6a8ca98c9a9 100644 --- a/include/linux/major.h +++ b/include/linux/major.h @@ -145,6 +145,7 @@ #define UNIX98_PTY_MAJOR_COUNT 8 #define UNIX98_PTY_SLAVE_MAJOR (UNIX98_PTY_MASTER_MAJOR+UNIX98_PTY_MAJOR_COUNT) +#define DRBD_MAJOR 147 #define RTF_MAJOR 150 #define RAW_MAJOR 162 diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 25b9ca93d23..45add35dda1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -94,6 +94,7 @@ extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority); int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg); +int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg); unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone, enum lru_list lru); @@ -239,6 +240,12 @@ mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg) return 1; } +static inline int +mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg) +{ + return 1; +} + static inline unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone, enum lru_list lru) diff --git a/include/linux/mm.h b/include/linux/mm.h index ad613ed66ab..d88d6fc530a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -7,7 +7,6 @@ #include <linux/gfp.h> #include <linux/list.h> -#include <linux/mmdebug.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/prio_tree.h> @@ -725,7 +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 *); @@ -793,6 +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, @@ -824,8 +825,11 @@ 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); @@ -850,19 +854,6 @@ extern int mprotect_fixup(struct vm_area_struct *vma, 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. * * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'. It should @@ -1061,7 +1052,8 @@ 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 calculate_zone_inactive_ratio(struct zone *zone); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(void); @@ -1178,8 +1170,6 @@ 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 +1187,9 @@ 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/include/linux/mm_types.h b/include/linux/mm_types.h index 0042090a4d7..7acc8439d9b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,6 +240,8 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + s8 oom_adj; /* OOM kill score adjustment (bit shift) */ + cpumask_t cpu_vm_mask; /* Architecture-specific MM context */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a47c879e130..88959853737 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -50,9 +50,6 @@ extern int page_group_by_mobility_disabled; static inline int get_pageblock_migratetype(struct page *page) { - if (unlikely(page_group_by_mobility_disabled)) - return MIGRATE_UNMOVABLE; - return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end); } @@ -86,13 +83,8 @@ enum zone_stat_item { NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ -#ifdef CONFIG_UNEVICTABLE_LRU NR_UNEVICTABLE, /* " " " " " */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ -#else - NR_UNEVICTABLE = NR_ACTIVE_FILE, /* avoid compiler errors in dead code */ - NR_MLOCK = NR_ACTIVE_FILE, -#endif NR_ANON_PAGES, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ @@ -135,11 +127,7 @@ enum lru_list { LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, -#ifdef CONFIG_UNEVICTABLE_LRU LRU_UNEVICTABLE, -#else - LRU_UNEVICTABLE = LRU_ACTIVE_FILE, /* avoid compiler errors in dead code */ -#endif NR_LRU_LISTS }; @@ -159,13 +147,20 @@ static inline int is_active_lru(enum lru_list l) static inline int is_unevictable_lru(enum lru_list l) { -#ifdef CONFIG_UNEVICTABLE_LRU return (l == LRU_UNEVICTABLE); -#else - return 0; -#endif } +enum zone_watermarks { + WMARK_MIN, + WMARK_LOW, + WMARK_HIGH, + NR_WMARK +}; + +#define min_wmark_pages(z) (z->watermark[WMARK_MIN]) +#define low_wmark_pages(z) (z->watermark[WMARK_LOW]) +#define high_wmark_pages(z) (z->watermark[WMARK_HIGH]) + struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ @@ -278,7 +273,10 @@ struct zone_reclaim_stat { struct zone { /* Fields commonly accessed by the page allocator */ - unsigned long pages_min, pages_low, pages_high; + + /* zone watermarks, access with *_wmark_pages(zone) macros */ + unsigned long watermark[NR_WMARK]; + /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several @@ -323,9 +321,9 @@ struct zone { /* Fields commonly accessed by the page reclaim scanner */ spinlock_t lru_lock; - struct { + struct zone_lru { struct list_head list; - unsigned long nr_scan; + unsigned long nr_saved_scan; /* accumulated for batching */ } lru[NR_LRU_LISTS]; struct zone_reclaim_stat reclaim_stat; diff --git a/include/linux/module.h b/include/linux/module.h index a7bc6e7b43a..505f20dcc1c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -697,4 +697,21 @@ static inline void module_remove_modinfo_attrs(struct module *mod) #define __MODULE_STRING(x) __stringify(x) + +#ifdef CONFIG_GENERIC_BUG +int module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, + struct module *); +void module_bug_cleanup(struct module *); + +#else /* !CONFIG_GENERIC_BUG */ + +static inline int module_bug_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod) +{ + return 0; +} +static inline void module_bug_cleanup(struct module *mod) {} +#endif /* CONFIG_GENERIC_BUG */ + #endif /* _LINUX_MODULE_H */ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 848025cd708..829b94b156f 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -408,6 +408,19 @@ static inline int num_node_state(enum node_states state) #define next_online_node(nid) next_node((nid), node_states[N_ONLINE]) extern int nr_node_ids; +extern int nr_online_nodes; + +static inline void node_set_online(int nid) +{ + node_set_state(nid, N_ONLINE); + nr_online_nodes = num_node_state(N_ONLINE); +} + +static inline void node_set_offline(int nid) +{ + node_clear_state(nid, N_ONLINE); + nr_online_nodes = num_node_state(N_ONLINE); +} #else static inline int node_state(int node, enum node_states state) @@ -434,7 +447,10 @@ static inline int num_node_state(enum node_states state) #define first_online_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define nr_node_ids 1 +#define nr_online_nodes 1 +#define node_set_online(node) node_set_state((node), N_ONLINE) +#define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif #define node_online_map node_states[N_ONLINE] @@ -454,9 +470,6 @@ static inline int num_node_state(enum node_states state) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) -#define node_set_online(node) node_set_state((node), N_ONLINE) -#define node_set_offline(node) node_clear_state((node), N_ONLINE) - #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 62214c7d2d9..d6792f88a17 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -95,9 +95,7 @@ enum pageflags { PG_reclaim, /* To be reclaimed asap */ PG_buddy, /* Page is free, on buddy lists */ PG_swapbacked, /* Page is backed by RAM/swap */ -#ifdef CONFIG_UNEVICTABLE_LRU PG_unevictable, /* Page is "unevictable" */ -#endif #ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT PG_mlocked, /* Page is vma mlocked */ #endif @@ -248,14 +246,8 @@ PAGEFLAG_FALSE(SwapCache) SETPAGEFLAG_NOOP(SwapCache) CLEARPAGEFLAG_NOOP(SwapCache) #endif -#ifdef CONFIG_UNEVICTABLE_LRU PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable) TESTCLEARFLAG(Unevictable, unevictable) -#else -PAGEFLAG_FALSE(Unevictable) TESTCLEARFLAG_FALSE(Unevictable) - SETPAGEFLAG_NOOP(Unevictable) CLEARPAGEFLAG_NOOP(Unevictable) - __CLEARPAGEFLAG_NOOP(Unevictable) -#endif #ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT #define MLOCK_PAGES 1 @@ -382,12 +374,6 @@ static inline void __ClearPageTail(struct page *page) #endif /* !PAGEFLAGS_EXTENDED */ -#ifdef CONFIG_UNEVICTABLE_LRU -#define __PG_UNEVICTABLE (1 << PG_unevictable) -#else -#define __PG_UNEVICTABLE 0 -#endif - #ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT #define __PG_MLOCKED (1 << PG_mlocked) #else @@ -403,7 +389,7 @@ static inline void __ClearPageTail(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - __PG_UNEVICTABLE | __PG_MLOCKED) + 1 << PG_unevictable | __PG_MLOCKED) /* * Flags checked when a page is prepped for return by the page allocator. diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 34da5230faa..aec3252afcf 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -22,9 +22,7 @@ enum mapping_flags { AS_EIO = __GFP_BITS_SHIFT + 0, /* IO error on async write */ AS_ENOSPC = __GFP_BITS_SHIFT + 1, /* ENOSPC on async write */ AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */ -#ifdef CONFIG_UNEVICTABLE_LRU AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */ -#endif }; static inline void mapping_set_error(struct address_space *mapping, int error) @@ -37,8 +35,6 @@ static inline void mapping_set_error(struct address_space *mapping, int error) } } -#ifdef CONFIG_UNEVICTABLE_LRU - static inline void mapping_set_unevictable(struct address_space *mapping) { set_bit(AS_UNEVICTABLE, &mapping->flags); @@ -55,14 +51,6 @@ static inline int mapping_unevictable(struct address_space *mapping) return test_bit(AS_UNEVICTABLE, &mapping->flags); return !!mapping; } -#else -static inline void mapping_set_unevictable(struct address_space *mapping) { } -static inline void mapping_clear_unevictable(struct address_space *mapping) { } -static inline int mapping_unevictable(struct address_space *mapping) -{ - return 0; -} -#endif static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { diff --git a/include/linux/poll.h b/include/linux/poll.h index 8c24ef8d997..fa287f25138 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -32,6 +32,7 @@ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_ typedef struct poll_table_struct { poll_queue_proc qproc; + unsigned long key; } poll_table; static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) @@ -43,10 +44,12 @@ static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_addres static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) { pt->qproc = qproc; + pt->key = ~0UL; /* all events enabled */ } struct poll_table_entry { struct file *filp; + unsigned long key; wait_queue_t wait; wait_queue_head_t *wait_address; }; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 355f6e80db0..c5da7491809 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -167,6 +167,8 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, unsigned long first_index, unsigned int max_items); unsigned long radix_tree_next_hole(struct radix_tree_root *root, unsigned long index, unsigned long max_scan); +unsigned long radix_tree_prev_hole(struct radix_tree_root *root, + unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b35bc0e19cd..216d024f830 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -83,7 +83,8 @@ static inline void page_dup_rmap(struct page *page, struct vm_area_struct *vma, /* * Called from mm/vmscan.c to handle paging out */ -int page_referenced(struct page *, int is_locked, struct mem_cgroup *cnt); +int page_referenced(struct page *, int is_locked, + struct mem_cgroup *cnt, unsigned long *vm_flags); int try_to_unmap(struct page *, int ignore_refs); /* @@ -105,18 +106,11 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int page_mkclean(struct page *); -#ifdef CONFIG_UNEVICTABLE_LRU /* * called in munlock()/munmap() path to check for other vmas holding * the page mlocked. */ int try_to_munlock(struct page *); -#else -static inline int try_to_munlock(struct page *page) -{ - return 0; /* a.k.a. SWAP_SUCCESS */ -} -#endif #else /* !CONFIG_MMU */ @@ -124,7 +118,7 @@ static inline int try_to_munlock(struct page *page) #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) -#define page_referenced(page,l,cnt) TestClearPageReferenced(page) +#define page_referenced(page, locked, cnt, flags) TestClearPageReferenced(page) #define try_to_unmap(page, refs) SWAP_FAIL static inline int page_mkclean(struct page *page) diff --git a/include/linux/sched.h b/include/linux/sched.h index 7531b1c2820..02042e7f219 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1178,7 +1178,6 @@ struct task_struct { * a short time */ unsigned char fpu_counter; - s8 oomkilladj; /* OOM kill score adjustment (bit shift). */ #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif @@ -1318,7 +1317,8 @@ struct task_struct { /* Thread group tracking */ u32 parent_exec_id; u32 self_exec_id; -/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */ +/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, + * mempolicy */ spinlock_t alloc_lock; #ifdef CONFIG_GENERIC_HARDIRQS @@ -1386,8 +1386,7 @@ struct task_struct { cputime_t acct_timexpd; /* stime + utime since last update */ #endif #ifdef CONFIG_CPUSETS - nodemask_t mems_allowed; - int cpuset_mems_generation; + nodemask_t mems_allowed; /* Protected by alloc_lock */ int cpuset_mem_spread_rotor; #endif #ifdef CONFIG_CGROUPS @@ -1410,7 +1409,7 @@ struct task_struct { struct list_head perf_counter_list; #endif #ifdef CONFIG_NUMA - struct mempolicy *mempolicy; + struct mempolicy *mempolicy; /* Protected by alloc_lock */ short il_next; #endif atomic_t fs_excl; /* holding fs exclusive resources */ diff --git a/include/linux/smp.h b/include/linux/smp.h index a69db820eed..9e3d8af0920 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -177,7 +177,6 @@ static inline void init_call_single_data(void) #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) #define put_cpu() preempt_enable() -#define put_cpu_no_resched() preempt_enable_no_resched() /* * Callback to arch code if there's nosmp or maxcpus=0 on the diff --git a/include/linux/swap.h b/include/linux/swap.h index d476aad3ff5..0cedf31af0b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -129,9 +129,10 @@ enum { #define SWAP_CLUSTER_MAX 32 -#define SWAP_MAP_MAX 0x7fff -#define SWAP_MAP_BAD 0x8000 - +#define SWAP_MAP_MAX 0x7ffe +#define SWAP_MAP_BAD 0x7fff +#define SWAP_HAS_CACHE 0x8000 /* There is a swap cache of entry. */ +#define SWAP_COUNT_MASK (~SWAP_HAS_CACHE) /* * The in-memory structure used to track swap areas. */ @@ -235,7 +236,6 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order) } #endif -#ifdef CONFIG_UNEVICTABLE_LRU extern int page_evictable(struct page *page, struct vm_area_struct *vma); extern void scan_mapping_unevictable_pages(struct address_space *); @@ -244,24 +244,6 @@ extern int scan_unevictable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); extern int scan_unevictable_register_node(struct node *node); extern void scan_unevictable_unregister_node(struct node *node); -#else -static inline int page_evictable(struct page *page, - struct vm_area_struct *vma) -{ - return 1; -} - -static inline void scan_mapping_unevictable_pages(struct address_space *mapping) -{ -} - -static inline int scan_unevictable_register_node(struct node *node) -{ - return 0; -} - -static inline void scan_unevictable_unregister_node(struct node *node) { } -#endif extern int kswapd_run(int nid); @@ -274,7 +256,7 @@ extern void swap_unplug_io_fn(struct backing_dev_info *, struct page *); #ifdef CONFIG_SWAP /* linux/mm/page_io.c */ -extern int swap_readpage(struct file *, struct page *); +extern int swap_readpage(struct page *); extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_read(struct bio *bio, int err); @@ -300,9 +282,11 @@ extern long total_swap_pages; extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); extern swp_entry_t get_swap_page_of_type(int); -extern int swap_duplicate(swp_entry_t); +extern void swap_duplicate(swp_entry_t); +extern int swapcache_prepare(swp_entry_t); extern int valid_swaphandles(swp_entry_t, unsigned long *); extern void swap_free(swp_entry_t); +extern void swapcache_free(swp_entry_t, struct page *page); extern int free_swap_and_cache(swp_entry_t); extern int swap_type_of(dev_t, sector_t, struct block_device **); extern unsigned int count_swap_pages(int, int); @@ -370,12 +354,20 @@ static inline void show_swap_cache_info(void) } #define free_swap_and_cache(swp) is_migration_entry(swp) -#define swap_duplicate(swp) is_migration_entry(swp) +#define swapcache_prepare(swp) is_migration_entry(swp) + +static inline void swap_duplicate(swp_entry_t swp) +{ +} static inline void swap_free(swp_entry_t swp) { } +static inline void swapcache_free(swp_entry_t swp, struct page *page) +{ +} + static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 418d90f5eff..fa4242cdade 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -434,6 +434,7 @@ asmlinkage long sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg); asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg); #endif +asmlinkage long sys_pipe(int __user *fildes); asmlinkage long sys_pipe2(int __user *fildes, int flags); asmlinkage long sys_dup(unsigned int fildes); asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd); @@ -751,8 +752,6 @@ asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int, struct timespec __user *, const sigset_t __user *, size_t); -asmlinkage long sys_pipe2(int __user *, int); -asmlinkage long sys_pipe(int __user *); int kernel_execve(const char *filename, char *const argv[], char *const envp[]); diff --git a/include/linux/timex.h b/include/linux/timex.h index 9910e3bd5b3..e6967d10d9e 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -280,6 +280,9 @@ extern int do_adjtimex(struct timex *); int read_current_timer(unsigned long *timer_val); +/* The clock frequency of the i8253/i8254 PIT */ +#define PIT_TICK_RATE 1193182ul + #endif /* KERNEL */ #endif /* LINUX_TIMEX_H */ diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 11232676bff..3656b300de3 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -22,12 +22,12 @@ struct old_utsname { }; struct new_utsname { - char sysname[65]; - char nodename[65]; - char release[65]; - char version[65]; - char machine[65]; - char domainname[65]; + char sysname[__NEW_UTS_LEN + 1]; + char nodename[__NEW_UTS_LEN + 1]; + char release[__NEW_UTS_LEN + 1]; + char version[__NEW_UTS_LEN + 1]; + char machine[__NEW_UTS_LEN + 1]; + char domainname[__NEW_UTS_LEN + 1]; }; #ifdef __KERNEL__ diff --git a/include/linux/vlynq.h b/include/linux/vlynq.h new file mode 100644 index 00000000000..8f6a95882b0 --- /dev/null +++ b/include/linux/vlynq.h @@ -0,0 +1,161 @@ +/* + * Copyright (C) 2006, 2007 Eugene Konev <ejka@openwrt.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#ifndef __VLYNQ_H__ +#define __VLYNQ_H__ + +#include <linux/device.h> +#include <linux/module.h> +#include <linux/types.h> + +#define VLYNQ_NUM_IRQS 32 + +struct vlynq_mapping { + u32 size; + u32 offset; +}; + +enum vlynq_divisor { + vlynq_div_auto = 0, + vlynq_ldiv1, + vlynq_ldiv2, + vlynq_ldiv3, + vlynq_ldiv4, + vlynq_ldiv5, + vlynq_ldiv6, + vlynq_ldiv7, + vlynq_ldiv8, + vlynq_rdiv1, + vlynq_rdiv2, + vlynq_rdiv3, + vlynq_rdiv4, + vlynq_rdiv5, + vlynq_rdiv6, + vlynq_rdiv7, + vlynq_rdiv8, + vlynq_div_external +}; + +struct vlynq_device_id { + u32 id; + enum vlynq_divisor divisor; + unsigned long driver_data; +}; + +struct vlynq_regs; +struct vlynq_device { + u32 id, dev_id; + int local_irq; + int remote_irq; + enum vlynq_divisor divisor; + u32 regs_start, regs_end; + u32 mem_start, mem_end; + u32 irq_start, irq_end; + int irq; + int enabled; + struct vlynq_regs *local; + struct vlynq_regs *remote; + struct device dev; +}; + +struct vlynq_driver { + char *name; + struct vlynq_device_id *id_table; + int (*probe)(struct vlynq_device *dev, struct vlynq_device_id *id); + void (*remove)(struct vlynq_device *dev); + struct device_driver driver; +}; + +struct plat_vlynq_ops { + int (*on)(struct vlynq_device *dev); + void (*off)(struct vlynq_device *dev); +}; + +static inline struct vlynq_driver *to_vlynq_driver(struct device_driver *drv) +{ + return container_of(drv, struct vlynq_driver, driver); +} + +static inline struct vlynq_device *to_vlynq_device(struct device *device) +{ + return container_of(device, struct vlynq_device, dev); +} + +extern struct bus_type vlynq_bus_type; + +extern int __vlynq_register_driver(struct vlynq_driver *driver, + struct module *owner); + +static inline int vlynq_register_driver(struct vlynq_driver *driver) +{ + return __vlynq_register_driver(driver, THIS_MODULE); +} + +static inline void *vlynq_get_drvdata(struct vlynq_device *dev) +{ + return dev_get_drvdata(&dev->dev); +} + +static inline void vlynq_set_drvdata(struct vlynq_device *dev, void *data) +{ + dev_set_drvdata(&dev->dev, data); +} + +static inline u32 vlynq_mem_start(struct vlynq_device *dev) +{ + return dev->mem_start; +} + +static inline u32 vlynq_mem_end(struct vlynq_device *dev) +{ + return dev->mem_end; +} + +static inline u32 vlynq_mem_len(struct vlynq_device *dev) +{ + return dev->mem_end - dev->mem_start + 1; +} + +static inline int vlynq_virq_to_irq(struct vlynq_device *dev, int virq) +{ + int irq = dev->irq_start + virq; + if ((irq < dev->irq_start) || (irq > dev->irq_end)) + return -EINVAL; + + return irq; +} + +static inline int vlynq_irq_to_virq(struct vlynq_device *dev, int irq) +{ + if ((irq < dev->irq_start) || (irq > dev->irq_end)) + return -EINVAL; + + return irq - dev->irq_start; +} + +extern void vlynq_unregister_driver(struct vlynq_driver *driver); +extern int vlynq_enable_device(struct vlynq_device *dev); +extern void vlynq_disable_device(struct vlynq_device *dev); +extern int vlynq_set_local_mapping(struct vlynq_device *dev, u32 tx_offset, + struct vlynq_mapping *mapping); +extern int vlynq_set_remote_mapping(struct vlynq_device *dev, u32 tx_offset, + struct vlynq_mapping *mapping); +extern int vlynq_set_local_irq(struct vlynq_device *dev, int virq); +extern int vlynq_set_remote_irq(struct vlynq_device *dev, int virq); + +#endif /* __VLYNQ_H__ */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 524cd1b28ec..81a97cf8f0a 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -36,12 +36,14 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGSTEAL), FOR_ALL_ZONES(PGSCAN_KSWAPD), FOR_ALL_ZONES(PGSCAN_DIRECT), +#ifdef CONFIG_NUMA + PGSCAN_ZONE_RECLAIM_FAILED, +#endif PGINODESTEAL, SLABS_SCANNED, KSWAPD_STEAL, KSWAPD_INODESTEAL, PAGEOUTRUN, ALLOCSTALL, PGROTATED, #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, #endif -#ifdef CONFIG_UNEVICTABLE_LRU UNEVICTABLE_PGCULLED, /* culled to noreclaim list */ UNEVICTABLE_PGSCANNED, /* scanned for reclaimability */ UNEVICTABLE_PGRESCUED, /* rescued from noreclaim list */ @@ -50,7 +52,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, UNEVICTABLE_PGCLEARED, /* on COW, page truncate */ UNEVICTABLE_PGSTRANDED, /* unable to isolate on unlock */ UNEVICTABLE_MLOCKFREED, -#endif NR_VM_EVENT_ITEMS }; diff --git a/include/video/s1d13xxxfb.h b/include/video/s1d13xxxfb.h index c3b2a2aa714..f0736cff2ca 100644 --- a/include/video/s1d13xxxfb.h +++ b/include/video/s1d13xxxfb.h @@ -136,6 +136,15 @@ #define S1DREG_DELAYOFF 0xFFFE #define S1DREG_DELAYON 0xFFFF +#define BBLT_FIFO_EMPTY 0x00 +#define BBLT_FIFO_NOT_EMPTY 0x40 +#define BBLT_FIFO_NOT_FULL 0x30 +#define BBLT_FIFO_HALF_FULL 0x20 +#define BBLT_FIFO_FULL 0x10 + +#define BBLT_SOLID_FILL 0x0c + + /* Note: all above defines should go in separate header files when implementing other S1D13xxx chip support. */ diff --git a/init/main.c b/init/main.c index 7becd8b5c5b..7756ddad3c8 100644 --- a/init/main.c +++ b/init/main.c @@ -671,7 +671,6 @@ asmlinkage void __init start_kernel(void) initrd_start = 0; } #endif - cpuset_init_early(); page_cgroup_init(); enable_debug_pagealloc(); cpu_hotplug_init(); @@ -868,6 +867,11 @@ static noinline int init_post(void) static int __init kernel_init(void * unused) { lock_kernel(); + + /* + * init can allocate pages on any node + */ + set_mems_allowed(node_possible_map); /* * init can run on any cpu. */ diff --git a/kernel/Makefile b/kernel/Makefile index 90b53f6dc22..9df4501cb92 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,6 +11,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ async.o +obj-y += groups.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files diff --git a/kernel/cpuset.c b/kernel/cpuset.c index d5a7e17474e..7e75a41bd50 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -97,12 +97,6 @@ struct cpuset { struct cpuset *parent; /* my parent */ - /* - * Copy of global cpuset_mems_generation as of the most - * recent time this cpuset changed its mems_allowed. - */ - int mems_generation; - struct fmeter fmeter; /* memory_pressure filter */ /* partition number for rebuild_sched_domains() */ @@ -176,27 +170,6 @@ static inline int is_spread_slab(const struct cpuset *cs) return test_bit(CS_SPREAD_SLAB, &cs->flags); } -/* - * Increment this integer everytime any cpuset changes its - * mems_allowed value. Users of cpusets can track this generation - * number, and avoid having to lock and reload mems_allowed unless - * the cpuset they're using changes generation. - * - * A single, global generation is needed because cpuset_attach_task() could - * reattach a task to a different cpuset, which must not have its - * generation numbers aliased with those of that tasks previous cpuset. - * - * Generations are needed for mems_allowed because one task cannot - * modify another's memory placement. So we must enable every task, - * on every visit to __alloc_pages(), to efficiently check whether - * its current->cpuset->mems_allowed has changed, requiring an update - * of its current->mems_allowed. - * - * Since writes to cpuset_mems_generation are guarded by the cgroup lock - * there is no need to mark it atomic. - */ -static int cpuset_mems_generation; - static struct cpuset top_cpuset = { .flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), }; @@ -228,8 +201,9 @@ static struct cpuset top_cpuset = { * If a task is only holding callback_mutex, then it has read-only * access to cpusets. * - * The task_struct fields mems_allowed and mems_generation may only - * be accessed in the context of that task, so require no locks. + * Now, the task_struct fields mems_allowed and mempolicy may be changed + * by other task, we use alloc_lock in the task_struct fields to protect + * them. * * The cpuset_common_file_read() handlers only hold callback_mutex across * small pieces of code, such as when reading out possibly multi-word @@ -331,75 +305,22 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask) BUG_ON(!nodes_intersects(*pmask, node_states[N_HIGH_MEMORY])); } -/** - * cpuset_update_task_memory_state - update task memory placement - * - * If the current tasks cpusets mems_allowed changed behind our - * backs, update current->mems_allowed, mems_generation and task NUMA - * mempolicy to the new value. - * - * Task mempolicy is updated by rebinding it relative to the - * current->cpuset if a task has its memory placement changed. - * Do not call this routine if in_interrupt(). - * - * Call without callback_mutex or task_lock() held. May be - * called with or without cgroup_mutex held. Thanks in part to - * 'the_top_cpuset_hack', the task's cpuset pointer will never - * be NULL. This routine also might acquire callback_mutex during - * call. - * - * Reading current->cpuset->mems_generation doesn't need task_lock - * to guard the current->cpuset derefence, because it is guarded - * from concurrent freeing of current->cpuset using RCU. - * - * The rcu_dereference() is technically probably not needed, - * as I don't actually mind if I see a new cpuset pointer but - * an old value of mems_generation. However this really only - * matters on alpha systems using cpusets heavily. If I dropped - * that rcu_dereference(), it would save them a memory barrier. - * For all other arch's, rcu_dereference is a no-op anyway, and for - * alpha systems not using cpusets, another planned optimization, - * avoiding the rcu critical section for tasks in the root cpuset - * which is statically allocated, so can't vanish, will make this - * irrelevant. Better to use RCU as intended, than to engage in - * some cute trick to save a memory barrier that is impossible to - * test, for alpha systems using cpusets heavily, which might not - * even exist. - * - * This routine is needed to update the per-task mems_allowed data, - * within the tasks context, when it is trying to allocate memory - * (in various mm/mempolicy.c routines) and notices that some other - * task has been modifying its cpuset. +/* + * update task's spread flag if cpuset's page/slab spread flag is set + * + * Called with callback_mutex/cgroup_mutex held */ - -void cpuset_update_task_memory_state(void) +static void cpuset_update_task_spread_flag(struct cpuset *cs, + struct task_struct *tsk) { - int my_cpusets_mem_gen; - struct task_struct *tsk = current; - struct cpuset *cs; - - rcu_read_lock(); - my_cpusets_mem_gen = task_cs(tsk)->mems_generation; - rcu_read_unlock(); - - if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) { - mutex_lock(&callback_mutex); - task_lock(tsk); - cs = task_cs(tsk); /* Maybe changed when task not locked */ - guarantee_online_mems(cs, &tsk->mems_allowed); - tsk->cpuset_mems_generation = cs->mems_generation; - if (is_spread_page(cs)) - tsk->flags |= PF_SPREAD_PAGE; - else - tsk->flags &= ~PF_SPREAD_PAGE; - if (is_spread_slab(cs)) - tsk->flags |= PF_SPREAD_SLAB; - else - tsk->flags &= ~PF_SPREAD_SLAB; - task_unlock(tsk); - mutex_unlock(&callback_mutex); - mpol_rebind_task(tsk, &tsk->mems_allowed); - } + if (is_spread_page(cs)) + tsk->flags |= PF_SPREAD_PAGE; + else + tsk->flags &= ~PF_SPREAD_PAGE; + if (is_spread_slab(cs)) + tsk->flags |= PF_SPREAD_SLAB; + else + tsk->flags &= ~PF_SPREAD_SLAB; } /* @@ -1007,14 +928,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * other task, the task_struct mems_allowed that we are hacking * is for our current task, which must allocate new pages for that * migrating memory region. - * - * We call cpuset_update_task_memory_state() before hacking - * our tasks mems_allowed, so that we are assured of being in - * sync with our tasks cpuset, and in particular, callbacks to - * cpuset_update_task_memory_state() from nested page allocations - * won't see any mismatch of our cpuset and task mems_generation - * values, so won't overwrite our hacked tasks mems_allowed - * nodemask. */ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, @@ -1022,22 +935,37 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, { struct task_struct *tsk = current; - cpuset_update_task_memory_state(); - - mutex_lock(&callback_mutex); tsk->mems_allowed = *to; - mutex_unlock(&callback_mutex); do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); - mutex_lock(&callback_mutex); guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed); - mutex_unlock(&callback_mutex); } /* - * Rebind task's vmas to cpuset's new mems_allowed, and migrate pages to new - * nodes if memory_migrate flag is set. Called with cgroup_mutex held. + * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy + * @tsk: the task to change + * @newmems: new nodes that the task will be set + * + * In order to avoid seeing no nodes if the old and new nodes are disjoint, + * we structure updates as setting all new allowed nodes, then clearing newly + * disallowed ones. + * + * Called with task's alloc_lock held + */ +static void cpuset_change_task_nodemask(struct task_struct *tsk, + nodemask_t *newmems) +{ + nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); + mpol_rebind_task(tsk, &tsk->mems_allowed); + mpol_rebind_task(tsk, newmems); + tsk->mems_allowed = *newmems; +} + +/* + * Update task's mems_allowed and rebind its mempolicy and vmas' mempolicy + * of it to cpuset's new mems_allowed, and migrate pages to new nodes if + * memory_migrate flag is set. Called with cgroup_mutex held. */ static void cpuset_change_nodemask(struct task_struct *p, struct cgroup_scanner *scan) @@ -1046,12 +974,19 @@ static void cpuset_change_nodemask(struct task_struct *p, struct cpuset *cs; int migrate; const nodemask_t *oldmem = scan->data; + nodemask_t newmems; + + cs = cgroup_cs(scan->cg); + guarantee_online_mems(cs, &newmems); + + task_lock(p); + cpuset_change_task_nodemask(p, &newmems); + task_unlock(p); mm = get_task_mm(p); if (!mm) return; - cs = cgroup_cs(scan->cg); migrate = is_memory_migrate(cs); mpol_rebind_mm(mm, &cs->mems_allowed); @@ -1104,10 +1039,10 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem, /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the - * cpusets mems_allowed and mems_generation, and for each - * task in the cpuset, rebind any vma mempolicies and if - * the cpuset is marked 'memory_migrate', migrate the tasks - * pages to the new memory. + * cpusets mems_allowed, and for each task in the cpuset, + * update mems_allowed and rebind task's mempolicy and any vma + * mempolicies and if the cpuset is marked 'memory_migrate', + * migrate the tasks pages to the new memory. * * Call with cgroup_mutex held. May take callback_mutex during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, @@ -1160,7 +1095,6 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, mutex_lock(&callback_mutex); cs->mems_allowed = trialcs->mems_allowed; - cs->mems_generation = cpuset_mems_generation++; mutex_unlock(&callback_mutex); update_tasks_nodemask(cs, &oldmem, &heap); @@ -1193,6 +1127,46 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) } /* + * cpuset_change_flag - make a task's spread flags the same as its cpuset's + * @tsk: task to be updated + * @scan: struct cgroup_scanner containing the cgroup of the task + * + * Called by cgroup_scan_tasks() for each task in a cgroup. + * + * We don't need to re-check for the cgroup/cpuset membership, since we're + * holding cgroup_lock() at this point. + */ +static void cpuset_change_flag(struct task_struct *tsk, + struct cgroup_scanner *scan) +{ + cpuset_update_task_spread_flag(cgroup_cs(scan->cg), tsk); +} + +/* + * update_tasks_flags - update the spread flags of tasks in the cpuset. + * @cs: the cpuset in which each task's spread flags needs to be changed + * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks() + * + * Called with cgroup_mutex held + * + * The cgroup_scan_tasks() function will scan all the tasks in a cgroup, + * calling callback functions for each. + * + * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0 + * if @heap != NULL. + */ +static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap) +{ + struct cgroup_scanner scan; + + scan.cg = cs->css.cgroup; + scan.test_task = NULL; + scan.process_task = cpuset_change_flag; + scan.heap = heap; + cgroup_scan_tasks(&scan); +} + +/* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update @@ -1205,8 +1179,10 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; - int err; int balance_flag_changed; + int spread_flag_changed; + struct ptr_heap heap; + int err; trialcs = alloc_trial_cpuset(cs); if (!trialcs) @@ -1221,9 +1197,16 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, if (err < 0) goto out; + err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); + if (err < 0) + goto out; + balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); + spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) + || (is_spread_page(cs) != is_spread_page(trialcs))); + mutex_lock(&callback_mutex); cs->flags = trialcs->flags; mutex_unlock(&callback_mutex); @@ -1231,6 +1214,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) async_rebuild_sched_domains(); + if (spread_flag_changed) + update_tasks_flags(cs, &heap); + heap_free(&heap); out: free_trial_cpuset(trialcs); return err; @@ -1372,15 +1358,20 @@ static void cpuset_attach(struct cgroup_subsys *ss, if (cs == &top_cpuset) { cpumask_copy(cpus_attach, cpu_possible_mask); + to = node_possible_map; } else { - mutex_lock(&callback_mutex); guarantee_online_cpus(cs, cpus_attach); - mutex_unlock(&callback_mutex); + guarantee_online_mems(cs, &to); } err = set_cpus_allowed_ptr(tsk, cpus_attach); if (err) return; + task_lock(tsk); + cpuset_change_task_nodemask(tsk, &to); + task_unlock(tsk); + cpuset_update_task_spread_flag(cs, tsk); + from = oldcs->mems_allowed; to = cs->mems_allowed; mm = get_task_mm(tsk); @@ -1442,11 +1433,9 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val) break; case FILE_SPREAD_PAGE: retval = update_flag(CS_SPREAD_PAGE, cs, val); - cs->mems_generation = cpuset_mems_generation++; break; case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); - cs->mems_generation = cpuset_mems_generation++; break; default: retval = -EINVAL; @@ -1786,8 +1775,6 @@ static struct cgroup_subsys_state *cpuset_create( struct cpuset *parent; if (!cont->parent) { - /* This is early initialization for the top cgroup */ - top_cpuset.mems_generation = cpuset_mems_generation++; return &top_cpuset.css; } parent = cgroup_cs(cont->parent); @@ -1799,7 +1786,6 @@ static struct cgroup_subsys_state *cpuset_create( return ERR_PTR(-ENOMEM); } - cpuset_update_task_memory_state(); cs->flags = 0; if (is_spread_page(parent)) set_bit(CS_SPREAD_PAGE, &cs->flags); @@ -1808,7 +1794,6 @@ static struct cgroup_subsys_state *cpuset_create( set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpumask_clear(cs->cpus_allowed); nodes_clear(cs->mems_allowed); - cs->mems_generation = cpuset_mems_generation++; fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; @@ -1827,8 +1812,6 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont) { struct cpuset *cs = cgroup_cs(cont); - cpuset_update_task_memory_state(); - if (is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); @@ -1849,21 +1832,6 @@ struct cgroup_subsys cpuset_subsys = { .early_init = 1, }; -/* - * cpuset_init_early - just enough so that the calls to - * cpuset_update_task_memory_state() in early init code - * are harmless. - */ - -int __init cpuset_init_early(void) -{ - alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_NOWAIT); - - top_cpuset.mems_generation = cpuset_mems_generation++; - return 0; -} - - /** * cpuset_init - initialize cpusets at system boot * @@ -1874,11 +1842,13 @@ int __init cpuset_init(void) { int err = 0; + if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)) + BUG(); + cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); fmeter_init(&top_cpuset.fmeter); - top_cpuset.mems_generation = cpuset_mems_generation++; set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); top_cpuset.relax_domain_level = -1; diff --git a/kernel/groups.c b/kernel/groups.c new file mode 100644 index 00000000000..2b45b2ee396 --- /dev/null +++ b/kernel/groups.c @@ -0,0 +1,288 @@ +/* + * Supplementary group IDs + */ +#include <linux/cred.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/security.h> +#include <linux/syscalls.h> +#include <asm/uaccess.h> + +/* init to 2 - one for init_task, one to ensure it is never freed */ +struct group_info init_groups = { .usage = ATOMIC_INIT(2) }; + +struct group_info *groups_alloc(int gidsetsize) +{ + struct group_info *group_info; + int nblocks; + int i; + + nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK; + /* Make sure we always allocate at least one indirect block pointer */ + nblocks = nblocks ? : 1; + group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER); + if (!group_info) + return NULL; + group_info->ngroups = gidsetsize; + group_info->nblocks = nblocks; + atomic_set(&group_info->usage, 1); + + if (gidsetsize <= NGROUPS_SMALL) + group_info->blocks[0] = group_info->small_block; + else { + for (i = 0; i < nblocks; i++) { + gid_t *b; + b = (void *)__get_free_page(GFP_USER); + if (!b) + goto out_undo_partial_alloc; + group_info->blocks[i] = b; + } + } + return group_info; + +out_undo_partial_alloc: + while (--i >= 0) { + free_page((unsigned long)group_info->blocks[i]); + } + kfree(group_info); + return NULL; +} + +EXPORT_SYMBOL(groups_alloc); + +void groups_free(struct group_info *group_info) +{ + if (group_info->blocks[0] != group_info->small_block) { + int i; + for (i = 0; i < group_info->nblocks; i++) + free_page((unsigned long)group_info->blocks[i]); + } + kfree(group_info); +} + +EXPORT_SYMBOL(groups_free); + +/* export the group_info to a user-space array */ +static int groups_to_user(gid_t __user *grouplist, + const struct group_info *group_info) +{ + int i; + unsigned int count = group_info->ngroups; + + for (i = 0; i < group_info->nblocks; i++) { + unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); + unsigned int len = cp_count * sizeof(*grouplist); + + if (copy_to_user(grouplist, group_info->blocks[i], len)) + return -EFAULT; + + grouplist += NGROUPS_PER_BLOCK; + count -= cp_count; + } + return 0; +} + +/* fill a group_info from a user-space array - it must be allocated already */ +static int groups_from_user(struct group_info *group_info, + gid_t __user *grouplist) +{ + int i; + unsigned int count = group_info->ngroups; + + for (i = 0; i < group_info->nblocks; i++) { + unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); + unsigned int len = cp_count * sizeof(*grouplist); + + if (copy_from_user(group_info->blocks[i], grouplist, len)) + return -EFAULT; + + grouplist += NGROUPS_PER_BLOCK; + count -= cp_count; + } + return 0; +} + +/* a simple Shell sort */ +static void groups_sort(struct group_info *group_info) +{ + int base, max, stride; + int gidsetsize = group_info->ngroups; + + for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1) + ; /* nothing */ + stride /= 3; + + while (stride) { + max = gidsetsize - stride; + for (base = 0; base < max; base++) { + int left = base; + int right = left + stride; + gid_t tmp = GROUP_AT(group_info, right); + + while (left >= 0 && GROUP_AT(group_info, left) > tmp) { + GROUP_AT(group_info, right) = + GROUP_AT(group_info, left); + right = left; + left -= stride; + } + GROUP_AT(group_info, right) = tmp; + } + stride /= 3; + } +} + +/* a simple bsearch */ +int groups_search(const struct group_info *group_info, gid_t grp) +{ + unsigned int left, right; + + if (!group_info) + return 0; + + left = 0; + right = group_info->ngroups; + while (left < right) { + unsigned int mid = (left+right)/2; + int cmp = grp - GROUP_AT(group_info, mid); + if (cmp > 0) + left = mid + 1; + else if (cmp < 0) + right = mid; + else + return 1; + } + return 0; +} + +/** + * set_groups - Change a group subscription in a set of credentials + * @new: The newly prepared set of credentials to alter + * @group_info: The group list to install + * + * Validate a group subscription and, if valid, insert it into a set + * of credentials. + */ +int set_groups(struct cred *new, struct group_info *group_info) +{ + int retval; + + retval = security_task_setgroups(group_info); + if (retval) + return retval; + + put_group_info(new->group_info); + groups_sort(group_info); + get_group_info(group_info); + new->group_info = group_info; + return 0; +} + +EXPORT_SYMBOL(set_groups); + +/** + * set_current_groups - Change current's group subscription + * @group_info: The group list to impose + * + * Validate a group subscription and, if valid, impose it upon current's task + * security record. + */ +int set_current_groups(struct group_info *group_info) +{ + struct cred *new; + int ret; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + ret = set_groups(new, group_info); + if (ret < 0) { + abort_creds(new); + return ret; + } + + return commit_creds(new); +} + +EXPORT_SYMBOL(set_current_groups); + +SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) +{ + const struct cred *cred = current_cred(); + int i; + + if (gidsetsize < 0) + return -EINVAL; + + /* no need to grab task_lock here; it cannot change */ + i = cred->group_info->ngroups; + if (gidsetsize) { + if (i > gidsetsize) { + i = -EINVAL; + goto out; + } + if (groups_to_user(grouplist, cred->group_info)) { + i = -EFAULT; + goto out; + } + } +out: + return i; +} + +/* + * SMP: Our groups are copy-on-write. We can set them safely + * without another task interfering. + */ + +SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) +{ + struct group_info *group_info; + int retval; + + if (!capable(CAP_SETGID)) + return -EPERM; + if ((unsigned)gidsetsize > NGROUPS_MAX) + return -EINVAL; + + group_info = groups_alloc(gidsetsize); + if (!group_info) + return -ENOMEM; + retval = groups_from_user(group_info, grouplist); + if (retval) { + put_group_info(group_info); + return retval; + } + + retval = set_current_groups(group_info); + put_group_info(group_info); + + return retval; +} + +/* + * Check whether we're fsgid/egid or in the supplemental group.. + */ +int in_group_p(gid_t grp) +{ + const struct cred *cred = current_cred(); + int retval = 1; + + if (grp != cred->fsgid) + retval = groups_search(cred->group_info, grp); + return retval; +} + +EXPORT_SYMBOL(in_group_p); + +int in_egroup_p(gid_t grp) +{ + const struct cred *cred = current_cred(); + int retval = 1; + + if (grp != cred->egid) + retval = groups_search(cred->group_info, grp); + return retval; +} + +EXPORT_SYMBOL(in_egroup_p); diff --git a/kernel/kfifo.c b/kernel/kfifo.c index bc41ad0f24f..26539e3228e 100644 --- a/kernel/kfifo.c +++ b/kernel/kfifo.c @@ -72,9 +72,9 @@ struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock) /* * round up to the next power of 2, since our 'let the indices - * wrap' tachnique works only in this case. + * wrap' technique works only in this case. */ - if (size & (size - 1)) { + if (!is_power_of_2(size)) { BUG_ON(size > 0x80000000); size = roundup_pow_of_two(size); } diff --git a/kernel/kthread.c b/kernel/kthread.c index 41c88fe4050..7fa44133352 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -9,6 +9,7 @@ #include <linux/kthread.h> #include <linux/completion.h> #include <linux/err.h> +#include <linux/cpuset.h> #include <linux/unistd.h> #include <linux/file.h> #include <linux/module.h> @@ -236,6 +237,7 @@ int kthreadd(void *unused) ignore_signals(tsk); set_user_nice(tsk, KTHREAD_NICE_LEVEL); set_cpus_allowed_ptr(tsk, cpu_all_mask); + set_mems_allowed(node_possible_map); current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG; diff --git a/kernel/power/process.c b/kernel/power/process.c index ca634019497..da2072d7381 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -117,9 +117,12 @@ int freeze_processes(void) if (error) goto Exit; printk("done."); + + oom_killer_disable(); Exit: BUG_ON(in_atomic()); printk("\n"); + return error; } @@ -145,6 +148,8 @@ static void thaw_tasks(bool nosig_only) void thaw_processes(void) { + oom_killer_enable(); + printk("Restarting tasks ... "); thaw_tasks(true); thaw_tasks(false); 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/kernel/slow-work.c b/kernel/slow-work.c index 521ed2004d6..09d7519557d 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -319,6 +319,15 @@ cant_get_ref: EXPORT_SYMBOL(slow_work_enqueue); /* + * Schedule a cull of the thread pool at some time in the near future + */ +static void slow_work_schedule_cull(void) +{ + mod_timer(&slow_work_cull_timer, + round_jiffies(jiffies + SLOW_WORK_CULL_TIMEOUT)); +} + +/* * Worker thread culling algorithm */ static bool slow_work_cull_thread(void) @@ -335,8 +344,7 @@ static bool slow_work_cull_thread(void) list_empty(&vslow_work_queue) && atomic_read(&slow_work_thread_count) > slow_work_min_threads) { - mod_timer(&slow_work_cull_timer, - jiffies + SLOW_WORK_CULL_TIMEOUT); + slow_work_schedule_cull(); do_cull = true; } } @@ -393,8 +401,7 @@ static int slow_work_thread(void *_data) list_empty(&vslow_work_queue) && atomic_read(&slow_work_thread_count) > slow_work_min_threads) - mod_timer(&slow_work_cull_timer, - jiffies + SLOW_WORK_CULL_TIMEOUT); + slow_work_schedule_cull(); continue; } @@ -458,7 +465,7 @@ static void slow_work_new_thread_execute(struct slow_work *work) if (atomic_dec_and_test(&slow_work_thread_count)) BUG(); /* we're running on a slow work thread... */ mod_timer(&slow_work_oom_timer, - jiffies + SLOW_WORK_OOM_TIMEOUT); + round_jiffies(jiffies + SLOW_WORK_OOM_TIMEOUT)); } else { /* ratelimit the starting of new threads */ mod_timer(&slow_work_oom_timer, jiffies + 1); @@ -502,8 +509,7 @@ static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, if (n < 0 && !slow_work_may_not_start_new_thread) slow_work_enqueue(&slow_work_new_thread); else if (n > 0) - mod_timer(&slow_work_cull_timer, - jiffies + SLOW_WORK_CULL_TIMEOUT); + slow_work_schedule_cull(); } mutex_unlock(&slow_work_user_lock); } @@ -529,8 +535,7 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, atomic_read(&slow_work_thread_count); if (n < 0) - mod_timer(&slow_work_cull_timer, - jiffies + SLOW_WORK_CULL_TIMEOUT); + slow_work_schedule_cull(); } mutex_unlock(&slow_work_user_lock); } diff --git a/kernel/sys.c b/kernel/sys.c index 438d99a38c8..b3f1097c76f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1113,289 +1113,6 @@ out: return err; } -/* - * Supplementary group IDs - */ - -/* init to 2 - one for init_task, one to ensure it is never freed */ -struct group_info init_groups = { .usage = ATOMIC_INIT(2) }; - -struct group_info *groups_alloc(int gidsetsize) -{ - struct group_info *group_info; - int nblocks; - int i; - - nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK; - /* Make sure we always allocate at least one indirect block pointer */ - nblocks = nblocks ? : 1; - group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER); - if (!group_info) - return NULL; - group_info->ngroups = gidsetsize; - group_info->nblocks = nblocks; - atomic_set(&group_info->usage, 1); - - if (gidsetsize <= NGROUPS_SMALL) - group_info->blocks[0] = group_info->small_block; - else { - for (i = 0; i < nblocks; i++) { - gid_t *b; - b = (void *)__get_free_page(GFP_USER); - if (!b) - goto out_undo_partial_alloc; - group_info->blocks[i] = b; - } - } - return group_info; - -out_undo_partial_alloc: - while (--i >= 0) { - free_page((unsigned long)group_info->blocks[i]); - } - kfree(group_info); - return NULL; -} - -EXPORT_SYMBOL(groups_alloc); - -void groups_free(struct group_info *group_info) -{ - if (group_info->blocks[0] != group_info->small_block) { - int i; - for (i = 0; i < group_info->nblocks; i++) - free_page((unsigned long)group_info->blocks[i]); - } - kfree(group_info); -} - -EXPORT_SYMBOL(groups_free); - -/* export the group_info to a user-space array */ -static int groups_to_user(gid_t __user *grouplist, - const struct group_info *group_info) -{ - int i; - unsigned int count = group_info->ngroups; - - for (i = 0; i < group_info->nblocks; i++) { - unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); - unsigned int len = cp_count * sizeof(*grouplist); - - if (copy_to_user(grouplist, group_info->blocks[i], len)) - return -EFAULT; - - grouplist += NGROUPS_PER_BLOCK; - count -= cp_count; - } - return 0; -} - -/* fill a group_info from a user-space array - it must be allocated already */ -static int groups_from_user(struct group_info *group_info, - gid_t __user *grouplist) -{ - int i; - unsigned int count = group_info->ngroups; - - for (i = 0; i < group_info->nblocks; i++) { - unsigned int cp_count = min(NGROUPS_PER_BLOCK, count); - unsigned int len = cp_count * sizeof(*grouplist); - - if (copy_from_user(group_info->blocks[i], grouplist, len)) - return -EFAULT; - - grouplist += NGROUPS_PER_BLOCK; - count -= cp_count; - } - return 0; -} - -/* a simple Shell sort */ -static void groups_sort(struct group_info *group_info) -{ - int base, max, stride; - int gidsetsize = group_info->ngroups; - - for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1) - ; /* nothing */ - stride /= 3; - - while (stride) { - max = gidsetsize - stride; - for (base = 0; base < max; base++) { - int left = base; - int right = left + stride; - gid_t tmp = GROUP_AT(group_info, right); - - while (left >= 0 && GROUP_AT(group_info, left) > tmp) { - GROUP_AT(group_info, right) = - GROUP_AT(group_info, left); - right = left; - left -= stride; - } - GROUP_AT(group_info, right) = tmp; - } - stride /= 3; - } -} - -/* a simple bsearch */ -int groups_search(const struct group_info *group_info, gid_t grp) -{ - unsigned int left, right; - - if (!group_info) - return 0; - - left = 0; - right = group_info->ngroups; - while (left < right) { - unsigned int mid = (left+right)/2; - int cmp = grp - GROUP_AT(group_info, mid); - if (cmp > 0) - left = mid + 1; - else if (cmp < 0) - right = mid; - else - return 1; - } - return 0; -} - -/** - * set_groups - Change a group subscription in a set of credentials - * @new: The newly prepared set of credentials to alter - * @group_info: The group list to install - * - * Validate a group subscription and, if valid, insert it into a set - * of credentials. - */ -int set_groups(struct cred *new, struct group_info *group_info) -{ - int retval; - - retval = security_task_setgroups(group_info); - if (retval) - return retval; - - put_group_info(new->group_info); - groups_sort(group_info); - get_group_info(group_info); - new->group_info = group_info; - return 0; -} - -EXPORT_SYMBOL(set_groups); - -/** - * set_current_groups - Change current's group subscription - * @group_info: The group list to impose - * - * Validate a group subscription and, if valid, impose it upon current's task - * security record. - */ -int set_current_groups(struct group_info *group_info) -{ - struct cred *new; - int ret; - - new = prepare_creds(); - if (!new) - return -ENOMEM; - - ret = set_groups(new, group_info); - if (ret < 0) { - abort_creds(new); - return ret; - } - - return commit_creds(new); -} - -EXPORT_SYMBOL(set_current_groups); - -SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) -{ - const struct cred *cred = current_cred(); - int i; - - if (gidsetsize < 0) - return -EINVAL; - - /* no need to grab task_lock here; it cannot change */ - i = cred->group_info->ngroups; - if (gidsetsize) { - if (i > gidsetsize) { - i = -EINVAL; - goto out; - } - if (groups_to_user(grouplist, cred->group_info)) { - i = -EFAULT; - goto out; - } - } -out: - return i; -} - -/* - * SMP: Our groups are copy-on-write. We can set them safely - * without another task interfering. - */ - -SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) -{ - struct group_info *group_info; - int retval; - - if (!capable(CAP_SETGID)) - return -EPERM; - if ((unsigned)gidsetsize > NGROUPS_MAX) - return -EINVAL; - - group_info = groups_alloc(gidsetsize); - if (!group_info) - return -ENOMEM; - retval = groups_from_user(group_info, grouplist); - if (retval) { - put_group_info(group_info); - return retval; - } - - retval = set_current_groups(group_info); - put_group_info(group_info); - - return retval; -} - -/* - * Check whether we're fsgid/egid or in the supplemental group.. - */ -int in_group_p(gid_t grp) -{ - const struct cred *cred = current_cred(); - int retval = 1; - - if (grp != cred->fsgid) - retval = groups_search(cred->group_info, grp); - return retval; -} - -EXPORT_SYMBOL(in_group_p); - -int in_egroup_p(gid_t grp) -{ - const struct cred *cred = current_cred(); - int retval = 1; - - if (grp != cred->egid) - retval = groups_search(cred->group_info, grp); - return retval; -} - -EXPORT_SYMBOL(in_egroup_p); - DECLARE_RWSEM(uts_sem); SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f5c76b6cd61..ab462b9968d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1337,7 +1337,6 @@ static struct ctl_table vm_table[] = { .extra2 = &one, }, #endif -#ifdef CONFIG_UNEVICTABLE_LRU { .ctl_name = CTL_UNNUMBERED, .procname = "scan_unevictable_pages", @@ -1346,7 +1345,6 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &scan_unevictable_handler, }, -#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c index a65c3145554..e73822aa6e9 100644 --- a/lib/dec_and_lock.c +++ b/lib/dec_and_lock.c @@ -19,11 +19,10 @@ */ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) { -#ifdef CONFIG_SMP /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; -#endif + /* Otherwise do it the slow way */ spin_lock(lock); if (atomic_dec_and_test(atomic)) diff --git a/lib/genalloc.c b/lib/genalloc.c index f6d276db2d5..eed2bdb865e 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -85,7 +85,6 @@ void gen_pool_destroy(struct gen_pool *pool) int bit, end_bit; - write_lock(&pool->lock); list_for_each_safe(_chunk, _next_chunk, &pool->chunks) { chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk); list_del(&chunk->next_chunk); diff --git a/lib/hexdump.c b/lib/hexdump.c index f07c0db81d2..39af2560f76 100644 --- a/lib/hexdump.c +++ b/lib/hexdump.c @@ -65,7 +65,8 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize, for (j = 0; j < ngroups; j++) lx += scnprintf(linebuf + lx, linebuflen - lx, - "%16.16llx ", (unsigned long long)*(ptr8 + j)); + "%s%16.16llx", j ? " " : "", + (unsigned long long)*(ptr8 + j)); ascii_column = 17 * ngroups + 2; break; } @@ -76,7 +77,7 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize, for (j = 0; j < ngroups; j++) lx += scnprintf(linebuf + lx, linebuflen - lx, - "%8.8x ", *(ptr4 + j)); + "%s%8.8x", j ? " " : "", *(ptr4 + j)); ascii_column = 9 * ngroups + 2; break; } @@ -87,19 +88,21 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize, for (j = 0; j < ngroups; j++) lx += scnprintf(linebuf + lx, linebuflen - lx, - "%4.4x ", *(ptr2 + j)); + "%s%4.4x", j ? " " : "", *(ptr2 + j)); ascii_column = 5 * ngroups + 2; break; } default: - for (j = 0; (j < rowsize) && (j < len) && (lx + 4) < linebuflen; - j++) { + for (j = 0; (j < len) && (lx + 3) <= linebuflen; j++) { ch = ptr[j]; linebuf[lx++] = hex_asc_hi(ch); linebuf[lx++] = hex_asc_lo(ch); linebuf[lx++] = ' '; } + if (j) + lx--; + ascii_column = 3 * rowsize + 2; break; } @@ -108,7 +111,7 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize, while (lx < (linebuflen - 1) && lx < (ascii_column - 1)) linebuf[lx++] = ' '; - for (j = 0; (j < rowsize) && (j < len) && (lx + 2) < linebuflen; j++) + for (j = 0; (j < len) && (lx + 2) < linebuflen; j++) linebuf[lx++] = (isascii(ptr[j]) && isprint(ptr[j])) ? ptr[j] : '.'; nil: diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 4bb42a0344e..23abbd93cae 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -351,20 +351,12 @@ int radix_tree_insert(struct radix_tree_root *root, } EXPORT_SYMBOL(radix_tree_insert); -/** - * radix_tree_lookup_slot - lookup a slot in a radix tree - * @root: radix tree root - * @index: index key - * - * Returns: the slot corresponding to the position @index in the - * radix tree @root. This is useful for update-if-exists operations. - * - * This function can be called under rcu_read_lock iff the slot is not - * modified by radix_tree_replace_slot, otherwise it must be called - * exclusive from other writers. Any dereference of the slot must be done - * using radix_tree_deref_slot. +/* + * is_slot == 1 : search for the slot. + * is_slot == 0 : search for the node. */ -void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) +static void *radix_tree_lookup_element(struct radix_tree_root *root, + unsigned long index, int is_slot) { unsigned int height, shift; struct radix_tree_node *node, **slot; @@ -376,7 +368,7 @@ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) if (!radix_tree_is_indirect_ptr(node)) { if (index > 0) return NULL; - return (void **)&root->rnode; + return is_slot ? (void *)&root->rnode : node; } node = radix_tree_indirect_to_ptr(node); @@ -397,7 +389,25 @@ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) height--; } while (height > 0); - return (void **)slot; + return is_slot ? (void *)slot:node; +} + +/** + * radix_tree_lookup_slot - lookup a slot in a radix tree + * @root: radix tree root + * @index: index key + * + * Returns: the slot corresponding to the position @index in the + * radix tree @root. This is useful for update-if-exists operations. + * + * This function can be called under rcu_read_lock iff the slot is not + * modified by radix_tree_replace_slot, otherwise it must be called + * exclusive from other writers. Any dereference of the slot must be done + * using radix_tree_deref_slot. + */ +void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index) +{ + return (void **)radix_tree_lookup_element(root, index, 1); } EXPORT_SYMBOL(radix_tree_lookup_slot); @@ -415,38 +425,7 @@ EXPORT_SYMBOL(radix_tree_lookup_slot); */ void *radix_tree_lookup(struct radix_tree_root *root, unsigned long index) { - unsigned int height, shift; - struct radix_tree_node *node, **slot; - - node = rcu_dereference(root->rnode); - if (node == NULL) - return NULL; - - if (!radix_tree_is_indirect_ptr(node)) { - if (index > 0) - return NULL; - return node; - } - node = radix_tree_indirect_to_ptr(node); - - height = node->height; - if (index > radix_tree_maxindex(height)) - return NULL; - - shift = (height-1) * RADIX_TREE_MAP_SHIFT; - - do { - slot = (struct radix_tree_node **) - (node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK)); - node = rcu_dereference(*slot); - if (node == NULL) - return NULL; - - shift -= RADIX_TREE_MAP_SHIFT; - height--; - } while (height > 0); - - return node; + return radix_tree_lookup_element(root, index, 0); } EXPORT_SYMBOL(radix_tree_lookup); @@ -666,6 +645,43 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root, } EXPORT_SYMBOL(radix_tree_next_hole); +/** + * radix_tree_prev_hole - find the prev hole (not-present entry) + * @root: tree root + * @index: index key + * @max_scan: maximum range to search + * + * Search backwards in the range [max(index-max_scan+1, 0), index] + * for the first hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'index - return >= max_scan' + * will be true). In rare cases of wrap-around, LONG_MAX will be returned. + * + * radix_tree_next_hole may be called under rcu_read_lock. However, like + * radix_tree_gang_lookup, this will not atomically search a snapshot of + * the tree at a single point in time. For example, if a hole is created + * at index 10, then subsequently a hole is created at index 5, + * radix_tree_prev_hole covering both indexes may return 5 if called under + * rcu_read_lock. + */ +unsigned long radix_tree_prev_hole(struct radix_tree_root *root, + unsigned long index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + if (!radix_tree_lookup(root, index)) + break; + index--; + if (index == LONG_MAX) + break; + } + + return index; +} +EXPORT_SYMBOL(radix_tree_prev_hole); + static unsigned int __lookup(struct radix_tree_node *slot, void ***results, unsigned long index, unsigned int max_items, unsigned long *next_index) diff --git a/lib/rbtree.c b/lib/rbtree.c index f653659e0bc..e2aa3be2985 100644 --- a/lib/rbtree.c +++ b/lib/rbtree.c @@ -231,34 +231,34 @@ void rb_erase(struct rb_node *node, struct rb_root *root) node = node->rb_right; while ((left = node->rb_left) != NULL) node = left; + + if (rb_parent(old)) { + if (rb_parent(old)->rb_left == old) + rb_parent(old)->rb_left = node; + else + rb_parent(old)->rb_right = node; + } else + root->rb_node = node; + child = node->rb_right; parent = rb_parent(node); color = rb_color(node); - if (child) - rb_set_parent(child, parent); if (parent == old) { - parent->rb_right = child; parent = node; - } else + } else { + if (child) + rb_set_parent(child, parent); parent->rb_left = child; + node->rb_right = old->rb_right; + rb_set_parent(old->rb_right, node); + } + node->rb_parent_color = old->rb_parent_color; - node->rb_right = old->rb_right; node->rb_left = old->rb_left; - - if (rb_parent(old)) - { - if (rb_parent(old)->rb_left == old) - rb_parent(old)->rb_left = node; - else - rb_parent(old)->rb_right = node; - } else - root->rb_node = node; - rb_set_parent(old->rb_left, node); - if (old->rb_right) - rb_set_parent(old->rb_right, node); + goto color; } diff --git a/mm/Kconfig b/mm/Kconfig index 6f4610a9ce5..c948d4ca8bd 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -203,25 +203,13 @@ config VIRT_TO_BUS def_bool y depends on !ARCH_NO_VIRT_TO_BUS -config UNEVICTABLE_LRU - bool "Add LRU list to track non-evictable pages" - default y - help - Keeps unevictable pages off of the active and inactive pageout - lists, so kswapd will not waste CPU time or have its balancing - algorithms thrown off by scanning these pages. Selecting this - will use one page flag and increase the code size a little, - say Y unless you know what you are doing. - - See Documentation/vm/unevictable-lru.txt for more information. - config HAVE_MLOCK bool default y if MMU=y config HAVE_MLOCKED_PAGE_BIT bool - default y if HAVE_MLOCK=y && UNEVICTABLE_LRU=y + default y if HAVE_MLOCK=y config MMU_NOTIFIER bool diff --git a/mm/Makefile b/mm/Makefile index c379ce08354..5e0bd642669 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -12,6 +12,7 @@ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o $(mmu-y) +obj-y += init-mm.o obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o obj-$(CONFIG_BOUNCE) += bounce.o diff --git a/mm/fadvise.c b/mm/fadvise.c index 54a0f8040af..e43359214f6 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -101,7 +101,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice) ret = force_page_cache_readahead(mapping, file, start_index, - max_sane_readahead(nrpages)); + nrpages); if (ret > 0) ret = 0; break; diff --git a/mm/filemap.c b/mm/filemap.c index 1b60f30cebf..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); } @@ -1004,9 +1004,6 @@ EXPORT_SYMBOL(grab_cache_page_nowait); static void shrink_readahead_size_eio(struct file *filp, struct file_ra_state *ra) { - if (!ra->ra_pages) - return; - ra->ra_pages /= 4; } @@ -1390,8 +1387,7 @@ do_readahead(struct address_space *mapping, struct file *filp, if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage) return -EINVAL; - force_page_cache_readahead(mapping, filp, index, - max_sane_readahead(nr)); + force_page_cache_readahead(mapping, filp, index, nr); return 0; } @@ -1457,6 +1453,73 @@ static int page_cache_read(struct file *file, pgoff_t offset) #define MMAP_LOTSAMISS (100) +/* + * Synchronous readahead happens when we don't even find + * a page in the page cache at all. + */ +static void do_sync_mmap_readahead(struct vm_area_struct *vma, + struct file_ra_state *ra, + struct file *file, + pgoff_t offset) +{ + unsigned long ra_pages; + struct address_space *mapping = file->f_mapping; + + /* If we don't want any read-ahead, don't bother */ + if (VM_RandomReadHint(vma)) + return; + + if (VM_SequentialReadHint(vma) || + offset - 1 == (ra->prev_pos >> PAGE_CACHE_SHIFT)) { + page_cache_sync_readahead(mapping, ra, file, offset, + ra->ra_pages); + return; + } + + if (ra->mmap_miss < INT_MAX) + ra->mmap_miss++; + + /* + * Do we miss much more than hit in this file? If so, + * stop bothering with read-ahead. It will only hurt. + */ + if (ra->mmap_miss > MMAP_LOTSAMISS) + return; + + /* + * mmap read-around + */ + ra_pages = max_sane_readahead(ra->ra_pages); + if (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); + } +} + +/* + * Asynchronous readahead happens when we find the page and PG_readahead, + * so we want to possibly extend the readahead further.. + */ +static void do_async_mmap_readahead(struct vm_area_struct *vma, + struct file_ra_state *ra, + struct file *file, + struct page *page, + pgoff_t offset) +{ + struct address_space *mapping = file->f_mapping; + + /* If we don't want any read-ahead, don't bother */ + if (VM_RandomReadHint(vma)) + return; + if (ra->mmap_miss > 0) + ra->mmap_miss--; + if (PageReadahead(page)) + page_cache_async_readahead(mapping, ra, file, + page, offset, ra->ra_pages); +} + /** * filemap_fault - read in file data for page fault handling * @vma: vma in which the fault was taken @@ -1476,78 +1539,44 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct address_space *mapping = file->f_mapping; struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; + pgoff_t offset = vmf->pgoff; struct page *page; pgoff_t size; - int did_readaround = 0; int ret = 0; size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (vmf->pgoff >= size) + if (offset >= size) return VM_FAULT_SIGBUS; - /* If we don't want any read-ahead, don't bother */ - if (VM_RandomReadHint(vma)) - goto no_cached_page; - /* * Do we have something in the page cache already? */ -retry_find: - page = find_lock_page(mapping, vmf->pgoff); - /* - * For sequential accesses, we use the generic readahead logic. - */ - if (VM_SequentialReadHint(vma)) { - if (!page) { - page_cache_sync_readahead(mapping, ra, file, - vmf->pgoff, 1); - page = find_lock_page(mapping, vmf->pgoff); - if (!page) - goto no_cached_page; - } - if (PageReadahead(page)) { - page_cache_async_readahead(mapping, ra, file, page, - vmf->pgoff, 1); - } - } - - if (!page) { - unsigned long ra_pages; - - ra->mmap_miss++; - + page = find_get_page(mapping, offset); + if (likely(page)) { /* - * Do we miss much more than hit in this file? If so, - * stop bothering with read-ahead. It will only hurt. + * We found the page, so try async readahead before + * waiting for the lock. */ - if (ra->mmap_miss > MMAP_LOTSAMISS) - goto no_cached_page; + do_async_mmap_readahead(vma, ra, file, page, offset); + lock_page(page); - /* - * To keep the pgmajfault counter straight, we need to - * check did_readaround, as this is an inner loop. - */ - if (!did_readaround) { - ret = VM_FAULT_MAJOR; - count_vm_event(PGMAJFAULT); - } - did_readaround = 1; - ra_pages = max_sane_readahead(file->f_ra.ra_pages); - if (ra_pages) { - pgoff_t start = 0; - - if (vmf->pgoff > ra_pages / 2) - start = vmf->pgoff - ra_pages / 2; - do_page_cache_readahead(mapping, file, start, ra_pages); + /* Did it get truncated? */ + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + put_page(page); + goto no_cached_page; } - page = find_lock_page(mapping, vmf->pgoff); + } else { + /* No page in the page cache at all */ + do_sync_mmap_readahead(vma, ra, file, offset); + count_vm_event(PGMAJFAULT); + ret = VM_FAULT_MAJOR; +retry_find: + page = find_lock_page(mapping, offset); if (!page) goto no_cached_page; } - if (!did_readaround) - ra->mmap_miss--; - /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. @@ -1555,18 +1584,18 @@ retry_find: if (unlikely(!PageUptodate(page))) goto page_not_uptodate; - /* Must recheck i_size under page lock */ + /* + * Found the page and have a reference on it. + * We must recheck i_size under page lock. + */ size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (unlikely(vmf->pgoff >= size)) { + if (unlikely(offset >= size)) { unlock_page(page); page_cache_release(page); return VM_FAULT_SIGBUS; } - /* - * Found the page and have a reference on it. - */ - ra->prev_pos = (loff_t)page->index << PAGE_CACHE_SHIFT; + ra->prev_pos = (loff_t)offset << PAGE_CACHE_SHIFT; vmf->page = page; return ret | VM_FAULT_LOCKED; @@ -1575,7 +1604,7 @@ no_cached_page: * We're only likely to ever get here if MADV_RANDOM is in * effect. */ - error = page_cache_read(file, vmf->pgoff); + error = page_cache_read(file, offset); /* * The page we want has now been added to the page cache. @@ -1595,12 +1624,6 @@ no_cached_page: return VM_FAULT_SIGBUS; page_not_uptodate: - /* IO error path */ - if (!did_readaround) { - ret = VM_FAULT_MAJOR; - count_vm_event(PGMAJFAULT); - } - /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e83ad2c9228..a56e6f3ce97 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -578,41 +578,6 @@ static void free_huge_page(struct page *page) hugetlb_put_quota(mapping, 1); } -/* - * Increment or decrement surplus_huge_pages. Keep node-specific counters - * balanced by operating on them in a round-robin fashion. - * Returns 1 if an adjustment was made. - */ -static int adjust_pool_surplus(struct hstate *h, int delta) -{ - static int prev_nid; - int nid = prev_nid; - int ret = 0; - - VM_BUG_ON(delta != -1 && delta != 1); - do { - nid = next_node(nid, node_online_map); - if (nid == MAX_NUMNODES) - nid = first_node(node_online_map); - - /* To shrink on this node, there must be a surplus page */ - if (delta < 0 && !h->surplus_huge_pages_node[nid]) - continue; - /* Surplus cannot exceed the total number of pages */ - if (delta > 0 && h->surplus_huge_pages_node[nid] >= - h->nr_huge_pages_node[nid]) - continue; - - h->surplus_huge_pages += delta; - h->surplus_huge_pages_node[nid] += delta; - ret = 1; - break; - } while (nid != prev_nid); - - prev_nid = nid; - return ret; -} - static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { set_compound_page_dtor(page, free_huge_page); @@ -623,6 +588,34 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) put_page(page); /* free it into the hugepage allocator */ } +static void prep_compound_gigantic_page(struct page *page, unsigned long order) +{ + int i; + int nr_pages = 1 << order; + struct page *p = page + 1; + + /* we rely on prep_new_huge_page to set the destructor */ + set_compound_order(page, order); + __SetPageHead(page); + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { + __SetPageTail(p); + p->first_page = page; + } +} + +int PageHuge(struct page *page) +{ + compound_page_dtor *dtor; + + if (!PageCompound(page)) + return 0; + + page = compound_head(page); + dtor = get_compound_page_dtor(page); + + return dtor == free_huge_page; +} + static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; @@ -630,7 +623,7 @@ 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 +642,7 @@ 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 @@ -875,7 +868,7 @@ static void return_unused_surplus_pages(struct hstate *h, * can no longer free unreserved surplus pages. This occurs when * the nodes with surplus pages have no free pages. */ - unsigned long remaining_iterations = num_online_nodes(); + unsigned long remaining_iterations = nr_online_nodes; /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; @@ -904,7 +897,7 @@ static void return_unused_surplus_pages(struct hstate *h, h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; nr_pages--; - remaining_iterations = num_online_nodes(); + remaining_iterations = nr_online_nodes; } } } @@ -1140,6 +1133,41 @@ static inline void try_to_free_low(struct hstate *h, unsigned long count) } #endif +/* + * Increment or decrement surplus_huge_pages. Keep node-specific counters + * balanced by operating on them in a round-robin fashion. + * Returns 1 if an adjustment was made. + */ +static int adjust_pool_surplus(struct hstate *h, int delta) +{ + static int prev_nid; + int nid = prev_nid; + int ret = 0; + + VM_BUG_ON(delta != -1 && delta != 1); + do { + nid = next_node(nid, node_online_map); + if (nid == MAX_NUMNODES) + nid = first_node(node_online_map); + + /* To shrink on this node, there must be a surplus page */ + if (delta < 0 && !h->surplus_huge_pages_node[nid]) + continue; + /* Surplus cannot exceed the total number of pages */ + if (delta > 0 && h->surplus_huge_pages_node[nid] >= + h->nr_huge_pages_node[nid]) + continue; + + h->surplus_huge_pages += delta; + h->surplus_huge_pages_node[nid] += delta; + ret = 1; + break; + } while (nid != prev_nid); + + prev_nid = nid; + return ret; +} + #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count) { diff --git a/mm/init-mm.c b/mm/init-mm.c new file mode 100644 index 00000000000..57aba0da966 --- /dev/null +++ b/mm/init-mm.c @@ -0,0 +1,20 @@ +#include <linux/mm_types.h> +#include <linux/rbtree.h> +#include <linux/rwsem.h> +#include <linux/spinlock.h> +#include <linux/list.h> +#include <linux/cpumask.h> + +#include <asm/atomic.h> +#include <asm/pgtable.h> + +struct mm_struct init_mm = { + .mm_rb = RB_ROOT, + .pgd = swapper_pg_dir, + .mm_users = ATOMIC_INIT(2), + .mm_count = ATOMIC_INIT(1), + .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), + .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), + .mmlist = LIST_HEAD_INIT(init_mm.mmlist), + .cpu_vm_mask = CPU_MASK_ALL, +}; diff --git a/mm/internal.h b/mm/internal.h index 987bb03fbdd..f290c4db528 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -16,9 +16,6 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); -extern void prep_compound_page(struct page *page, unsigned long order); -extern void prep_compound_gigantic_page(struct page *page, unsigned long order); - static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_count, v); @@ -51,6 +48,8 @@ extern void putback_lru_page(struct page *page); */ extern unsigned long highest_memmap_pfn; extern void __free_pages_bootmem(struct page *page, unsigned int order); +extern void prep_compound_page(struct page *page, unsigned long order); + /* * function for dealing with page's order in buddy system. @@ -74,7 +73,6 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma) } #endif -#ifdef CONFIG_UNEVICTABLE_LRU /* * unevictable_migrate_page() called only from migrate_page_copy() to * migrate unevictable flag to new page. @@ -86,11 +84,6 @@ static inline void unevictable_migrate_page(struct page *new, struct page *old) if (TestClearPageUnevictable(old)) SetPageUnevictable(new); } -#else -static inline void unevictable_migrate_page(struct page *new, struct page *old) -{ -} -#endif #ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT /* @@ -150,23 +143,6 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) } } -/* - * free_page_mlock() -- clean up attempts to free and mlocked() page. - * Page should not be on lru, so no need to fix that up. - * free_pages_check() will verify... - */ -static inline void free_page_mlock(struct page *page) -{ - if (unlikely(TestClearPageMlocked(page))) { - unsigned long flags; - - local_irq_save(flags); - __dec_zone_page_state(page, NR_MLOCK); - __count_vm_event(UNEVICTABLE_MLOCKFREED); - local_irq_restore(flags); - } -} - #else /* CONFIG_HAVE_MLOCKED_PAGE_BIT */ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p) { @@ -175,7 +151,6 @@ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p) static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void mlock_migrate_page(struct page *new, struct page *old) { } -static inline void free_page_mlock(struct page *page) { } #endif /* CONFIG_HAVE_MLOCKED_PAGE_BIT */ @@ -284,4 +259,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int flags, struct page **pages, struct vm_area_struct **vmas); +#define ZONE_RECLAIM_NOSCAN -2 +#define ZONE_RECLAIM_FULL -1 +#define ZONE_RECLAIM_SOME 0 +#define ZONE_RECLAIM_SUCCESS 1 #endif diff --git a/mm/madvise.c b/mm/madvise.c index b9ce574827c..76eb4193acd 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -123,8 +123,7 @@ static long madvise_willneed(struct vm_area_struct * vma, end = vma->vm_end; end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - force_page_cache_readahead(file->f_mapping, - file, start, max_sane_readahead(end - start)); + force_page_cache_readahead(file->f_mapping, file, start, end - start); return 0; } @@ -239,12 +238,30 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, break; default: - error = -EINVAL; + BUG(); break; } return error; } +static int +madvise_behavior_valid(int behavior) +{ + switch (behavior) { + case MADV_DOFORK: + case MADV_DONTFORK: + case MADV_NORMAL: + case MADV_SEQUENTIAL: + case MADV_RANDOM: + case MADV_REMOVE: + case MADV_WILLNEED: + case MADV_DONTNEED: + return 1; + + default: + return 0; + } +} /* * The madvise(2) system call. * @@ -290,6 +307,9 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) int write; size_t len; + if (!madvise_behavior_valid(behavior)) + return error; + write = madvise_need_mmap_write(behavior); if (write) down_write(¤t->mm->mmap_sem); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 78eb8552818..70db6e0a5ee 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -570,6 +570,17 @@ int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg) return 0; } +int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg) +{ + unsigned long active; + unsigned long inactive; + + inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_FILE); + active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_FILE); + + return (active > inactive); +} + unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone, enum lru_list lru) diff --git a/mm/memory.c b/mm/memory.c index 4126dd16778..d5d1653d60a 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) @@ -3053,22 +3103,13 @@ int in_gate_area_no_task(unsigned long addr) #endif /* __HAVE_ARCH_GATE_AREA */ -#ifdef CONFIG_HAVE_IOREMAP_PROT -int follow_phys(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned long *prot, resource_size_t *phys) +static int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; - pte_t *ptep, pte; - spinlock_t *ptl; - resource_size_t phys_addr = 0; - struct mm_struct *mm = vma->vm_mm; - int ret = -EINVAL; - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - goto out; + pte_t *ptep; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) @@ -3086,22 +3127,71 @@ int follow_phys(struct vm_area_struct *vma, if (pmd_huge(*pmd)) goto out; - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!ptep) goto out; + if (!pte_present(*ptep)) + goto unlock; + *ptepp = ptep; + return 0; +unlock: + pte_unmap_unlock(ptep, *ptlp); +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, + unsigned long *prot, resource_size_t *phys) +{ + int ret = -EINVAL; + pte_t *ptep, pte; + spinlock_t *ptl; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; + + if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) + goto out; pte = *ptep; - if (!pte_present(pte)) - goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; - phys_addr = pte_pfn(pte); - phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */ *prot = pgprot_val(pte_pgprot(pte)); - *phys = phys_addr; - ret = 0; + *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c083cf5fd6d..e4412a676c8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -422,7 +422,8 @@ 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(); + calculate_zone_inactive_ratio(zone); if (onlined_pages) { kswapd_run(zone_to_nid(zone)); node_set_state(zone_to_nid(zone), N_HIGH_MEMORY); @@ -832,6 +833,9 @@ repeat: totalram_pages -= offlined_pages; num_physpages -= offlined_pages; + setup_per_zone_wmarks(); + calculate_zone_inactive_ratio(zone); + vm_total_pages = nr_free_pagecache_pages(); writeback_set_ratelimit(); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3eb4a6fdc04..e08e2c4da63 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -182,13 +182,54 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) return 0; } -/* Create a new policy */ +/* + * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if + * any, for the new policy. mpol_new() has already validated the nodes + * parameter with respect to the policy mode and flags. But, we need to + * handle an empty nodemask with MPOL_PREFERRED here. + * + * Must be called holding task's alloc_lock to protect task's mems_allowed + * and mempolicy. May also be called holding the mmap_semaphore for write. + */ +static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes) +{ + nodemask_t cpuset_context_nmask; + int ret; + + /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ + if (pol == NULL) + return 0; + + VM_BUG_ON(!nodes); + if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) + nodes = NULL; /* explicit local allocation */ + else { + if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&cpuset_context_nmask, nodes, + &cpuset_current_mems_allowed); + else + nodes_and(cpuset_context_nmask, *nodes, + cpuset_current_mems_allowed); + if (mpol_store_user_nodemask(pol)) + pol->w.user_nodemask = *nodes; + else + pol->w.cpuset_mems_allowed = + cpuset_current_mems_allowed; + } + + ret = mpol_ops[pol->mode].create(pol, + nodes ? &cpuset_context_nmask : NULL); + return ret; +} + +/* + * This function just creates a new policy, does some check and simple + * initialization. You must invoke mpol_set_nodemask() to set nodes. + */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; - nodemask_t cpuset_context_nmask; - int ret; pr_debug("setting mode %d flags %d nodes[0] %lx\n", mode, flags, nodes ? nodes_addr(*nodes)[0] : -1); @@ -210,7 +251,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); - nodes = NULL; /* flag local alloc */ } } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); @@ -221,30 +261,6 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, policy->mode = mode; policy->flags = flags; - if (nodes) { - /* - * cpuset related setup doesn't apply to local allocation - */ - cpuset_update_task_memory_state(); - if (flags & MPOL_F_RELATIVE_NODES) - mpol_relative_nodemask(&cpuset_context_nmask, nodes, - &cpuset_current_mems_allowed); - else - nodes_and(cpuset_context_nmask, *nodes, - cpuset_current_mems_allowed); - if (mpol_store_user_nodemask(policy)) - policy->w.user_nodemask = *nodes; - else - policy->w.cpuset_mems_allowed = - cpuset_mems_allowed(current); - } - - ret = mpol_ops[mode].create(policy, - nodes ? &cpuset_context_nmask : NULL); - if (ret < 0) { - kmem_cache_free(policy_cache, policy); - return ERR_PTR(ret); - } return policy; } @@ -324,6 +340,8 @@ static void mpol_rebind_policy(struct mempolicy *pol, /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. + * + * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) @@ -600,8 +618,9 @@ static void mpol_set_task_struct_flag(void) static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { - struct mempolicy *new; + struct mempolicy *new, *old; struct mm_struct *mm = current->mm; + int ret; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) @@ -615,20 +634,33 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, */ if (mm) down_write(&mm->mmap_sem); - mpol_put(current->mempolicy); + task_lock(current); + ret = mpol_set_nodemask(new, nodes); + if (ret) { + task_unlock(current); + if (mm) + up_write(&mm->mmap_sem); + mpol_put(new); + return ret; + } + old = current->mempolicy; current->mempolicy = new; mpol_set_task_struct_flag(); if (new && new->mode == MPOL_INTERLEAVE && nodes_weight(new->v.nodes)) current->il_next = first_node(new->v.nodes); + task_unlock(current); if (mm) up_write(&mm->mmap_sem); + mpol_put(old); return 0; } /* * Return nodemask for policy for get_mempolicy() query + * + * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) { @@ -674,7 +706,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy; - cpuset_update_task_memory_state(); if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; @@ -683,7 +714,9 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ + task_lock(current); *nmask = cpuset_current_mems_allowed; + task_unlock(current); return 0; } @@ -738,8 +771,11 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } err = 0; - if (nmask) + if (nmask) { + task_lock(current); get_policy_nodemask(pol, nmask); + task_unlock(current); + } out: mpol_cond_put(pol); @@ -767,7 +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); } /* @@ -979,6 +1015,14 @@ static long do_mbind(unsigned long start, unsigned long len, return err; } down_write(&mm->mmap_sem); + task_lock(current); + err = mpol_set_nodemask(new, nmask); + task_unlock(current); + if (err) { + up_write(&mm->mmap_sem); + mpol_put(new); + return err; + } vma = check_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); @@ -1545,8 +1589,6 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) struct mempolicy *pol = get_vma_policy(current, vma, addr); struct zonelist *zl; - cpuset_update_task_memory_state(); - if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; @@ -1593,8 +1635,6 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) { struct mempolicy *pol = current->mempolicy; - if ((gfp & __GFP_WAIT) && !in_interrupt()) - cpuset_update_task_memory_state(); if (!pol || in_interrupt() || (gfp & __GFP_THISNODE)) pol = &default_policy; @@ -1854,6 +1894,8 @@ restart: */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { + int ret; + sp->root = RB_ROOT; /* empty tree == default mempolicy */ spin_lock_init(&sp->lock); @@ -1863,9 +1905,19 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) /* contextualize the tmpfs mount point mempolicy */ new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); - mpol_put(mpol); /* drop our ref on sb mpol */ - if (IS_ERR(new)) + if (IS_ERR(new)) { + mpol_put(mpol); /* drop our ref on sb mpol */ return; /* no valid nodemask intersection */ + } + + task_lock(current); + ret = mpol_set_nodemask(new, &mpol->w.user_nodemask); + task_unlock(current); + mpol_put(mpol); /* drop our ref on sb mpol */ + if (ret) { + mpol_put(new); + return; + } /* Create pseudo-vma that contains just the policy */ memset(&pvma, 0, sizeof(struct vm_area_struct)); @@ -2086,8 +2138,19 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) err = 1; - else if (no_context) - new->w.user_nodemask = nodes; /* save for contextualization */ + else { + int ret; + + task_lock(current); + ret = mpol_set_nodemask(new, &nodes); + task_unlock(current); + if (ret) + err = 1; + else if (no_context) { + /* save for contextualization */ + new->w.user_nodemask = nodes; + } + } out: /* Restore string for error message */ diff --git a/mm/migrate.c b/mm/migrate.c index 068655d8f88..939888f9dda 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); } @@ -820,7 +820,6 @@ static int do_move_page_to_node_array(struct mm_struct *mm, struct page_to_node *pp; LIST_HEAD(pagelist); - migrate_prep(); down_read(&mm->mmap_sem); /* @@ -907,6 +906,9 @@ static int do_pages_move(struct mm_struct *mm, struct task_struct *task, pm = (struct page_to_node *)__get_free_page(GFP_KERNEL); if (!pm) goto out; + + migrate_prep(); + /* * Store a chunk of page_to_node array in a page, * but keep the last one as a marker diff --git a/mm/mlock.c b/mm/mlock.c index ac130433c7d..45eb650b965 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -31,7 +31,6 @@ int can_do_mlock(void) } EXPORT_SYMBOL(can_do_mlock); -#ifdef CONFIG_UNEVICTABLE_LRU /* * Mlocked pages are marked with PageMlocked() flag for efficient testing * in vmscan and, possibly, the fault path; and to support semi-accurate @@ -261,27 +260,6 @@ static int __mlock_posix_error_return(long retval) return retval; } -#else /* CONFIG_UNEVICTABLE_LRU */ - -/* - * Just make pages present if VM_LOCKED. No-op if unlocking. - */ -static long __mlock_vma_pages_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - int mlock) -{ - if (mlock && (vma->vm_flags & VM_LOCKED)) - return make_pages_present(start, end); - return 0; -} - -static inline int __mlock_posix_error_return(long retval) -{ - return 0; -} - -#endif /* CONFIG_UNEVICTABLE_LRU */ - /** * mlock_vma_pages_range() - mlock pages in specified vma range. * @vma - the vma containing the specfied address range diff --git a/mm/oom_kill.c b/mm/oom_kill.c index a7b2460e922..175a67a78a9 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -58,6 +58,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) unsigned long points, cpu_time, run_time; struct mm_struct *mm; struct task_struct *child; + int oom_adj; task_lock(p); mm = p->mm; @@ -65,6 +66,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) task_unlock(p); return 0; } + oom_adj = mm->oom_adj; + if (oom_adj == OOM_DISABLE) { + task_unlock(p); + return 0; + } /* * The memory size of the process is the basis for the badness. @@ -148,15 +154,15 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) points /= 8; /* - * Adjust the score by oomkilladj. + * Adjust the score by oom_adj. */ - if (p->oomkilladj) { - if (p->oomkilladj > 0) { + if (oom_adj) { + if (oom_adj > 0) { if (!points) points = 1; - points <<= p->oomkilladj; + points <<= oom_adj; } else - points >>= -(p->oomkilladj); + points >>= -(oom_adj); } #ifdef DEBUG @@ -251,11 +257,8 @@ static struct task_struct *select_bad_process(unsigned long *ppoints, *ppoints = ULONG_MAX; } - if (p->oomkilladj == OOM_DISABLE) - continue; - points = badness(p, uptime.tv_sec); - if (points > *ppoints || !chosen) { + if (points > *ppoints) { chosen = p; *ppoints = points; } @@ -304,8 +307,7 @@ static void dump_tasks(const struct mem_cgroup *mem) } printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", p->pid, __task_cred(p)->uid, p->tgid, mm->total_vm, - get_mm_rss(mm), (int)task_cpu(p), p->oomkilladj, - p->comm); + get_mm_rss(mm), (int)task_cpu(p), mm->oom_adj, p->comm); task_unlock(p); } while_each_thread(g, p); } @@ -323,11 +325,8 @@ static void __oom_kill_task(struct task_struct *p, int verbose) return; } - if (!p->mm) { - WARN_ON(1); - printk(KERN_WARNING "tried to kill an mm-less task!\n"); + if (!p->mm) return; - } if (verbose) printk(KERN_ERR "Killed process %d (%s)\n", @@ -349,28 +348,13 @@ static int oom_kill_task(struct task_struct *p) struct mm_struct *mm; struct task_struct *g, *q; + task_lock(p); mm = p->mm; - - /* WARNING: mm may not be dereferenced since we did not obtain its - * value from get_task_mm(p). This is OK since all we need to do is - * compare mm to q->mm below. - * - * Furthermore, even if mm contains a non-NULL value, p->mm may - * change to NULL at any time since we do not hold task_lock(p). - * However, this is of no concern to us. - */ - - if (mm == NULL) + if (!mm || mm->oom_adj == OOM_DISABLE) { + task_unlock(p); return 1; - - /* - * Don't kill the process if any threads are set to OOM_DISABLE - */ - do_each_thread(g, q) { - if (q->mm == mm && q->oomkilladj == OOM_DISABLE) - return 1; - } while_each_thread(g, q); - + } + task_unlock(p); __oom_kill_task(p, 1); /* @@ -393,10 +377,11 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, struct task_struct *c; if (printk_ratelimit()) { - printk(KERN_WARNING "%s invoked oom-killer: " - "gfp_mask=0x%x, order=%d, oomkilladj=%d\n", - current->comm, gfp_mask, order, current->oomkilladj); task_lock(current); + printk(KERN_WARNING "%s invoked oom-killer: " + "gfp_mask=0x%x, order=%d, oom_adj=%d\n", + current->comm, gfp_mask, order, + current->mm ? current->mm->oom_adj : OOM_DISABLE); cpuset_print_task_mems_allowed(current); task_unlock(current); dump_stack(); @@ -409,8 +394,9 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* * If the task is already exiting, don't alarm the sysadmin or kill * its children or threads, just set TIF_MEMDIE so it can die quickly + * if its mm is still attached. */ - if (p->flags & PF_EXITING) { + if (p->mm && (p->flags & PF_EXITING)) { __oom_kill_task(p, 0); return 0; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index bb553c3e955..7b0dcea4935 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -265,18 +265,19 @@ static void bdi_writeout_fraction(struct backing_dev_info *bdi, * This avoids exceeding the total dirty_limit when the floating averages * fluctuate too quickly. */ -static void -clip_bdi_dirty_limit(struct backing_dev_info *bdi, long dirty, long *pbdi_dirty) +static void clip_bdi_dirty_limit(struct backing_dev_info *bdi, + unsigned long dirty, unsigned long *pbdi_dirty) { - long avail_dirty; + unsigned long avail_dirty; - avail_dirty = dirty - - (global_page_state(NR_FILE_DIRTY) + + avail_dirty = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_WRITEBACK) + global_page_state(NR_UNSTABLE_NFS) + - global_page_state(NR_WRITEBACK_TEMP)); + global_page_state(NR_WRITEBACK_TEMP); - if (avail_dirty < 0) + if (avail_dirty < dirty) + avail_dirty = dirty - avail_dirty; + else avail_dirty = 0; avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) + @@ -299,10 +300,10 @@ static inline void task_dirties_fraction(struct task_struct *tsk, * * dirty -= (dirty/8) * p_{t} */ -static void task_dirty_limit(struct task_struct *tsk, long *pdirty) +static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty) { long numerator, denominator; - long dirty = *pdirty; + unsigned long dirty = *pdirty; u64 inv = dirty >> 3; task_dirties_fraction(tsk, &numerator, &denominator); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0727896a88a..a5f3c278c57 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -162,17 +162,25 @@ static unsigned long __meminitdata dma_reserve; #if MAX_NUMNODES > 1 int nr_node_ids __read_mostly = MAX_NUMNODES; +int nr_online_nodes __read_mostly = 1; EXPORT_SYMBOL(nr_node_ids); +EXPORT_SYMBOL(nr_online_nodes); #endif int page_group_by_mobility_disabled __read_mostly; static void set_pageblock_migratetype(struct page *page, int migratetype) { + + if (unlikely(page_group_by_mobility_disabled)) + migratetype = MIGRATE_UNMOVABLE; + set_pageblock_flags_group(page, (unsigned long)migratetype, PB_migrate, PB_migrate_end); } +bool oom_killer_disabled __read_mostly; + #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) { @@ -295,23 +303,6 @@ void prep_compound_page(struct page *page, unsigned long order) } } -#ifdef CONFIG_HUGETLBFS -void prep_compound_gigantic_page(struct page *page, unsigned long order) -{ - int i; - int nr_pages = 1 << order; - struct page *p = page + 1; - - set_compound_page_dtor(page, free_compound_page); - set_compound_order(page, order); - __SetPageHead(page); - for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { - __SetPageTail(p); - p->first_page = page; - } -} -#endif - static int destroy_compound_page(struct page *page, unsigned long order) { int i; @@ -418,7 +409,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; if (PageBuddy(buddy) && page_order(buddy) == order) { - BUG_ON(page_count(buddy) != 0); + VM_BUG_ON(page_count(buddy) != 0); return 1; } return 0; @@ -449,22 +440,22 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, */ static inline void __free_one_page(struct page *page, - struct zone *zone, unsigned int order) + struct zone *zone, unsigned int order, + int migratetype) { unsigned long page_idx; - int order_size = 1 << order; - int migratetype = get_pageblock_migratetype(page); if (unlikely(PageCompound(page))) if (unlikely(destroy_compound_page(page, order))) return; + VM_BUG_ON(migratetype == -1); + page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); - VM_BUG_ON(page_idx & (order_size - 1)); + VM_BUG_ON(page_idx & ((1 << order) - 1)); VM_BUG_ON(bad_range(zone, page)); - __mod_zone_page_state(zone, NR_FREE_PAGES, order_size); while (order < MAX_ORDER-1) { unsigned long combined_idx; struct page *buddy; @@ -488,12 +479,27 @@ static inline void __free_one_page(struct page *page, zone->free_area[order].nr_free++; } +#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT +/* + * free_page_mlock() -- clean up attempts to free and mlocked() page. + * Page should not be on lru, so no need to fix that up. + * free_pages_check() will verify... + */ +static inline void free_page_mlock(struct page *page) +{ + __ClearPageMlocked(page); + __dec_zone_page_state(page, NR_MLOCK); + __count_vm_event(UNEVICTABLE_MLOCKFREED); +} +#else +static void free_page_mlock(struct page *page) { } +#endif + static inline int free_pages_check(struct page *page) { - free_page_mlock(page); if (unlikely(page_mapcount(page) | (page->mapping != NULL) | - (page_count(page) != 0) | + (atomic_read(&page->_count) != 0) | (page->flags & PAGE_FLAGS_CHECK_AT_FREE))) { bad_page(page); return 1; @@ -520,6 +526,8 @@ static void free_pages_bulk(struct zone *zone, int count, spin_lock(&zone->lock); zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE); zone->pages_scanned = 0; + + __mod_zone_page_state(zone, NR_FREE_PAGES, count << order); while (count--) { struct page *page; @@ -527,17 +535,20 @@ static void free_pages_bulk(struct zone *zone, int count, page = list_entry(list->prev, struct page, lru); /* have to delete it as __free_one_page list manipulates */ list_del(&page->lru); - __free_one_page(page, zone, order); + __free_one_page(page, zone, order, page_private(page)); } spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order) +static void free_one_page(struct zone *zone, struct page *page, int order, + int migratetype) { spin_lock(&zone->lock); zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE); zone->pages_scanned = 0; - __free_one_page(page, zone, order); + + __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order); + __free_one_page(page, zone, order, migratetype); spin_unlock(&zone->lock); } @@ -546,6 +557,7 @@ static void __free_pages_ok(struct page *page, unsigned int order) unsigned long flags; int i; int bad = 0; + int clearMlocked = PageMlocked(page); kmemcheck_free_shadow(page, order); @@ -563,8 +575,11 @@ static void __free_pages_ok(struct page *page, unsigned int order) kernel_map_pages(page, 1 << order, 0); local_irq_save(flags); + if (unlikely(clearMlocked)) + free_page_mlock(page); __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, order); + free_one_page(page_zone(page), page, order, + get_pageblock_migratetype(page)); local_irq_restore(flags); } @@ -635,7 +650,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) { if (unlikely(page_mapcount(page) | (page->mapping != NULL) | - (page_count(page) != 0) | + (atomic_read(&page->_count) != 0) | (page->flags & PAGE_FLAGS_CHECK_AT_PREP))) { bad_page(page); return 1; @@ -660,7 +675,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) * Go through the free lists for the given migratetype and remove * the smallest available page from the freelists */ -static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, +static inline +struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, int migratetype) { unsigned int current_order; @@ -678,7 +694,6 @@ static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, list_del(&page->lru); rmv_page_order(page); area->nr_free--; - __mod_zone_page_state(zone, NR_FREE_PAGES, - (1UL << order)); expand(zone, page, order, current_order, area, migratetype); return page; } @@ -769,8 +784,8 @@ static int move_freepages_block(struct zone *zone, struct page *page, } /* Remove an element from the buddy allocator from the fallback list */ -static struct page *__rmqueue_fallback(struct zone *zone, int order, - int start_migratetype) +static inline struct page * +__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) { struct free_area * area; int current_order; @@ -818,8 +833,6 @@ static struct page *__rmqueue_fallback(struct zone *zone, int order, /* Remove the page from the freelists */ list_del(&page->lru); rmv_page_order(page); - __mod_zone_page_state(zone, NR_FREE_PAGES, - -(1UL << order)); if (current_order == pageblock_order) set_pageblock_migratetype(page, @@ -830,8 +843,7 @@ static struct page *__rmqueue_fallback(struct zone *zone, int order, } } - /* Use MIGRATE_RESERVE rather than fail an allocation */ - return __rmqueue_smallest(zone, order, MIGRATE_RESERVE); + return NULL; } /* @@ -843,11 +855,23 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order, { struct page *page; +retry_reserve: page = __rmqueue_smallest(zone, order, migratetype); - if (unlikely(!page)) + if (unlikely(!page) && migratetype != MIGRATE_RESERVE) { page = __rmqueue_fallback(zone, order, migratetype); + /* + * Use MIGRATE_RESERVE rather than fail an allocation. goto + * is used because __rmqueue_smallest is an inline function + * and we want just one call site + */ + if (!page) { + migratetype = MIGRATE_RESERVE; + goto retry_reserve; + } + } + return page; } @@ -881,6 +905,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, set_page_private(page, migratetype); list = &page->lru; } + __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock(&zone->lock); return i; } @@ -996,6 +1021,7 @@ static void free_hot_cold_page(struct page *page, int cold) struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + int clearMlocked = PageMlocked(page); kmemcheck_free_shadow(page, 0); @@ -1012,13 +1038,16 @@ static void free_hot_cold_page(struct page *page, int cold) kernel_map_pages(page, 1, 0); pcp = &zone_pcp(zone, get_cpu())->pcp; + set_page_private(page, get_pageblock_migratetype(page)); local_irq_save(flags); + if (unlikely(clearMlocked)) + free_page_mlock(page); __count_vm_event(PGFREE); + if (cold) list_add_tail(&page->lru, &pcp->list); else list_add(&page->lru, &pcp->list); - set_page_private(page, get_pageblock_migratetype(page)); pcp->count++; if (pcp->count >= pcp->high) { free_pages_bulk(zone, pcp->batch, &pcp->list, 0); @@ -1071,14 +1100,15 @@ void split_page(struct page *page, unsigned int order) * we cheat by calling it from here, in the order > 0 path. Saves a branch * or two. */ -static struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags) +static inline +struct page *buffered_rmqueue(struct zone *preferred_zone, + struct zone *zone, int order, gfp_t gfp_flags, + int migratetype) { unsigned long flags; struct page *page; int cold = !!(gfp_flags & __GFP_COLD); int cpu; - int migratetype = allocflags_to_migratetype(gfp_flags); again: cpu = get_cpu(); @@ -1115,8 +1145,22 @@ again: list_del(&page->lru); pcp->count--; } else { + if (unlikely(gfp_flags & __GFP_NOFAIL)) { + /* + * __GFP_NOFAIL is not to be used in new code. + * + * All __GFP_NOFAIL callers should be fixed so that they + * properly detect and handle allocation failures. + * + * We most definitely don't want callers attempting to + * allocate greater than single-page units with + * __GFP_NOFAIL. + */ + WARN_ON_ONCE(order > 0); + } spin_lock_irqsave(&zone->lock, flags); page = __rmqueue(zone, order, migratetype); + __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order)); spin_unlock(&zone->lock); if (!page) goto failed; @@ -1138,10 +1182,15 @@ failed: return NULL; } -#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */ -#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */ -#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */ -#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */ +/* The ALLOC_WMARK bits are used as an index to zone->watermark */ +#define ALLOC_WMARK_MIN WMARK_MIN +#define ALLOC_WMARK_LOW WMARK_LOW +#define ALLOC_WMARK_HIGH WMARK_HIGH +#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ + +/* Mask to get the watermark bits */ +#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) + #define ALLOC_HARDER 0x10 /* try to alloc harder */ #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ @@ -1399,23 +1448,18 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) */ static struct page * get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, - struct zonelist *zonelist, int high_zoneidx, int alloc_flags) + struct zonelist *zonelist, int high_zoneidx, int alloc_flags, + struct zone *preferred_zone, int migratetype) { struct zoneref *z; struct page *page = NULL; int classzone_idx; - struct zone *zone, *preferred_zone; + struct zone *zone; nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ int zlc_active = 0; /* set if using zonelist_cache */ int did_zlc_setup = 0; /* just call zlc_setup() one time */ - (void)first_zones_zonelist(zonelist, high_zoneidx, nodemask, - &preferred_zone); - if (!preferred_zone) - return NULL; - classzone_idx = zone_idx(preferred_zone); - zonelist_scan: /* * Scan zonelist, looking for a zone with enough free. @@ -1430,31 +1474,49 @@ zonelist_scan: !cpuset_zone_allowed_softwall(zone, gfp_mask)) goto try_next_zone; + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { unsigned long mark; - if (alloc_flags & ALLOC_WMARK_MIN) - mark = zone->pages_min; - else if (alloc_flags & ALLOC_WMARK_LOW) - mark = zone->pages_low; - else - mark = zone->pages_high; - if (!zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) { - if (!zone_reclaim_mode || - !zone_reclaim(zone, gfp_mask, order)) + int ret; + + mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; + if (zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) + goto try_this_zone; + + if (zone_reclaim_mode == 0) + goto this_zone_full; + + ret = zone_reclaim(zone, gfp_mask, order); + switch (ret) { + case ZONE_RECLAIM_NOSCAN: + /* did not scan */ + goto try_next_zone; + case ZONE_RECLAIM_FULL: + /* scanned but unreclaimable */ + goto this_zone_full; + default: + /* did we reclaim enough */ + if (!zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) goto this_zone_full; } } - page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask); +try_this_zone: + page = buffered_rmqueue(preferred_zone, zone, order, + gfp_mask, migratetype); if (page) break; this_zone_full: if (NUMA_BUILD) zlc_mark_zone_full(zonelist, z); try_next_zone: - if (NUMA_BUILD && !did_zlc_setup) { - /* we do zlc_setup after the first zone is tried */ + if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) { + /* + * we do zlc_setup after the first zone is tried but only + * if there are multiple nodes make it worthwhile + */ allowednodes = zlc_setup(zonelist, alloc_flags); zlc_active = 1; did_zlc_setup = 1; @@ -1469,47 +1531,217 @@ try_next_zone: return page; } +static inline int +should_alloc_retry(gfp_t gfp_mask, unsigned int order, + unsigned long pages_reclaimed) +{ + /* Do not loop if specifically requested */ + if (gfp_mask & __GFP_NORETRY) + return 0; + + /* + * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER + * means __GFP_NOFAIL, but that may not be true in other + * implementations. + */ + if (order <= PAGE_ALLOC_COSTLY_ORDER) + return 1; + + /* + * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is + * specified, then we retry until we no longer reclaim any pages + * (above), or we've reclaimed an order of pages at least as + * large as the allocation's order. In both cases, if the + * allocation still fails, we stop retrying. + */ + if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order)) + return 1; + + /* + * Don't let big-order allocations loop unless the caller + * explicitly requests that. + */ + if (gfp_mask & __GFP_NOFAIL) + return 1; + + return 0; +} + +static inline struct page * +__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, struct zone *preferred_zone, + int migratetype) +{ + struct page *page; + + /* Acquire the OOM killer lock for the zones in zonelist */ + if (!try_set_zone_oom(zonelist, gfp_mask)) { + schedule_timeout_uninterruptible(1); + return NULL; + } + + /* + * Go through the zonelist yet one more time, keep very high watermark + * here, this is only to catch a parallel oom killing, we must fail if + * we're still under heavy pressure. + */ + page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, + order, zonelist, high_zoneidx, + ALLOC_WMARK_HIGH|ALLOC_CPUSET, + preferred_zone, migratetype); + if (page) + goto out; + + /* The OOM killer will not help higher order allocs */ + if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_NOFAIL)) + goto out; + + /* Exhausted what can be done so it's blamo time */ + out_of_memory(zonelist, gfp_mask, order); + +out: + clear_zonelist_oom(zonelist, gfp_mask); + return page; +} + +/* The really slow allocator path where we enter direct reclaim */ +static inline struct page * +__alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, + int migratetype, unsigned long *did_some_progress) +{ + struct page *page = NULL; + struct reclaim_state reclaim_state; + struct task_struct *p = current; + + cond_resched(); + + /* We now go into synchronous reclaim */ + cpuset_memory_pressure_bump(); + + /* + * The task's cpuset might have expanded its set of allowable nodes + */ + p->flags |= PF_MEMALLOC; + lockdep_set_current_reclaim_state(gfp_mask); + reclaim_state.reclaimed_slab = 0; + p->reclaim_state = &reclaim_state; + + *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); + + p->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); + p->flags &= ~PF_MEMALLOC; + + cond_resched(); + + if (order != 0) + drain_all_pages(); + + if (likely(*did_some_progress)) + page = get_page_from_freelist(gfp_mask, nodemask, order, + zonelist, high_zoneidx, + alloc_flags, preferred_zone, + migratetype); + return page; +} + /* - * This is the 'heart' of the zoned buddy allocator. + * This is called in the allocator slow-path if the allocation request is of + * sufficient urgency to ignore watermarks and take other desperate measures */ -struct page * -__alloc_pages_internal(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, nodemask_t *nodemask) +static inline struct page * +__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, struct zone *preferred_zone, + int migratetype) +{ + struct page *page; + + do { + page = get_page_from_freelist(gfp_mask, nodemask, order, + zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, + preferred_zone, migratetype); + + if (!page && gfp_mask & __GFP_NOFAIL) + congestion_wait(WRITE, HZ/50); + } while (!page && (gfp_mask & __GFP_NOFAIL)); + + return page; +} + +static inline +void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, + enum zone_type high_zoneidx) { - const gfp_t wait = gfp_mask & __GFP_WAIT; - enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zoneref *z; struct zone *zone; - struct page *page; - struct reclaim_state reclaim_state; - struct task_struct *p = current; - int do_retry; - int alloc_flags; - unsigned long did_some_progress; - unsigned long pages_reclaimed = 0; - lockdep_trace_alloc(gfp_mask); + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) + wakeup_kswapd(zone, order); +} - might_sleep_if(wait); +static inline int +gfp_to_alloc_flags(gfp_t gfp_mask) +{ + struct task_struct *p = current; + int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; + const gfp_t wait = gfp_mask & __GFP_WAIT; - if (should_fail_alloc_page(gfp_mask, order)) - return NULL; + /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ + BUILD_BUG_ON(__GFP_HIGH != ALLOC_HIGH); -restart: - z = zonelist->_zonerefs; /* the list of zones suitable for gfp_mask */ + /* + * The caller may dip into page reserves a bit more if the caller + * cannot run direct reclaim, or if the caller has realtime scheduling + * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will + * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + */ + alloc_flags |= (gfp_mask & __GFP_HIGH); - if (unlikely(!z->zone)) { + if (!wait) { + alloc_flags |= ALLOC_HARDER; /* - * Happens if we have an empty zonelist as a result of - * GFP_THISNODE being used on a memoryless node + * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. + * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ - return NULL; + alloc_flags &= ~ALLOC_CPUSET; + } else if (unlikely(rt_task(p))) + alloc_flags |= ALLOC_HARDER; + + if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { + if (!in_interrupt() && + ((p->flags & PF_MEMALLOC) || + unlikely(test_thread_flag(TIF_MEMDIE)))) + alloc_flags |= ALLOC_NO_WATERMARKS; } - page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, - zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET); - if (page) - goto got_pg; + return alloc_flags; +} + +static inline struct page * +__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, enum zone_type high_zoneidx, + nodemask_t *nodemask, struct zone *preferred_zone, + int migratetype) +{ + const gfp_t wait = gfp_mask & __GFP_WAIT; + struct page *page = NULL; + int alloc_flags; + unsigned long pages_reclaimed = 0; + unsigned long did_some_progress; + struct task_struct *p = current; + + /* + * In the slowpath, we sanity check order to avoid ever trying to + * reclaim >= MAX_ORDER areas which will never succeed. Callers may + * be using allocators in order of preference for an area that is + * too large. + */ + if (WARN_ON_ONCE(order >= MAX_ORDER)) + return NULL; /* * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and @@ -1522,154 +1754,83 @@ restart: if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - wakeup_kswapd(zone, order); + wake_all_kswapd(order, zonelist, high_zoneidx); /* * OK, we're below the kswapd watermark and have kicked background * reclaim. Now things get more complex, so set up alloc_flags according * to how we want to proceed. - * - * The caller may dip into page reserves a bit more if the caller - * cannot run direct reclaim, or if the caller has realtime scheduling - * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). */ - alloc_flags = ALLOC_WMARK_MIN; - if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait) - alloc_flags |= ALLOC_HARDER; - if (gfp_mask & __GFP_HIGH) - alloc_flags |= ALLOC_HIGH; - if (wait) - alloc_flags |= ALLOC_CPUSET; + alloc_flags = gfp_to_alloc_flags(gfp_mask); - /* - * Go through the zonelist again. Let __GFP_HIGH and allocations - * coming from realtime tasks go deeper into reserves. - * - * This is the last chance, in general, before the goto nopage. - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. - */ +restart: + /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, - high_zoneidx, alloc_flags); + high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, + preferred_zone, migratetype); if (page) goto got_pg; - /* This allocation should allow future memory freeing. */ - rebalance: - if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE))) - && !in_interrupt()) { - if (!(gfp_mask & __GFP_NOMEMALLOC)) { -nofail_alloc: - /* go through the zonelist yet again, ignoring mins */ - page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, ALLOC_NO_WATERMARKS); - if (page) - goto got_pg; - if (gfp_mask & __GFP_NOFAIL) { - congestion_wait(WRITE, HZ/50); - goto nofail_alloc; - } - } - goto nopage; + /* Allocate without watermarks if the context allows */ + if (alloc_flags & ALLOC_NO_WATERMARKS) { + page = __alloc_pages_high_priority(gfp_mask, order, + zonelist, high_zoneidx, nodemask, + preferred_zone, migratetype); + if (page) + goto got_pg; } /* Atomic allocations - we can't balance anything */ if (!wait) goto nopage; - cond_resched(); + /* Avoid recursion of direct reclaim */ + if (p->flags & PF_MEMALLOC) + goto nopage; + + /* Try direct reclaim and then allocating */ + page = __alloc_pages_direct_reclaim(gfp_mask, order, + zonelist, high_zoneidx, + nodemask, + alloc_flags, preferred_zone, + migratetype, &did_some_progress); + if (page) + goto got_pg; - /* We now go into synchronous reclaim */ - cpuset_memory_pressure_bump(); /* - * The task's cpuset might have expanded its set of allowable nodes + * If we failed to make any progress reclaiming, then we are + * running out of options and have to consider going OOM */ - cpuset_update_task_memory_state(); - p->flags |= PF_MEMALLOC; - - lockdep_set_current_reclaim_state(gfp_mask); - reclaim_state.reclaimed_slab = 0; - p->reclaim_state = &reclaim_state; - - did_some_progress = try_to_free_pages(zonelist, order, - gfp_mask, nodemask); - - p->reclaim_state = NULL; - lockdep_clear_current_reclaim_state(); - p->flags &= ~PF_MEMALLOC; - - cond_resched(); + if (!did_some_progress) { + if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { + if (oom_killer_disabled) + goto nopage; + page = __alloc_pages_may_oom(gfp_mask, order, + zonelist, high_zoneidx, + nodemask, preferred_zone, + migratetype); + if (page) + goto got_pg; - if (order != 0) - drain_all_pages(); + /* + * The OOM killer does not trigger for high-order + * ~__GFP_NOFAIL allocations so if no progress is being + * made, there are no other options and retrying is + * unlikely to help. + */ + if (order > PAGE_ALLOC_COSTLY_ORDER && + !(gfp_mask & __GFP_NOFAIL)) + goto nopage; - if (likely(did_some_progress)) { - page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, alloc_flags); - if (page) - goto got_pg; - } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { - if (!try_set_zone_oom(zonelist, gfp_mask)) { - schedule_timeout_uninterruptible(1); goto restart; } - - /* - * Go through the zonelist yet one more time, keep - * very high watermark here, this is only to catch - * a parallel oom killing, we must fail if we're still - * under heavy pressure. - */ - page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, - order, zonelist, high_zoneidx, - ALLOC_WMARK_HIGH|ALLOC_CPUSET); - if (page) { - clear_zonelist_oom(zonelist, gfp_mask); - goto got_pg; - } - - /* The OOM killer will not help higher order allocs so fail */ - if (order > PAGE_ALLOC_COSTLY_ORDER) { - clear_zonelist_oom(zonelist, gfp_mask); - goto nopage; - } - - out_of_memory(zonelist, gfp_mask, order); - clear_zonelist_oom(zonelist, gfp_mask); - goto restart; } - /* - * Don't let big-order allocations loop unless the caller explicitly - * requests that. Wait for some write requests to complete then retry. - * - * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER - * means __GFP_NOFAIL, but that may not be true in other - * implementations. - * - * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is - * specified, then we retry until we no longer reclaim any pages - * (above), or we've reclaimed an order of pages at least as - * large as the allocation's order. In both cases, if the - * allocation still fails, we stop retrying. - */ + /* Check if we should retry the allocation */ pages_reclaimed += did_some_progress; - do_retry = 0; - if (!(gfp_mask & __GFP_NORETRY)) { - if (order <= PAGE_ALLOC_COSTLY_ORDER) { - do_retry = 1; - } else { - if (gfp_mask & __GFP_REPEAT && - pages_reclaimed < (1 << order)) - do_retry = 1; - } - if (gfp_mask & __GFP_NOFAIL) - do_retry = 1; - } - if (do_retry) { + if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) { + /* Wait for some write requests to complete then retry */ congestion_wait(WRITE, HZ/50); goto rebalance; } @@ -1687,8 +1848,53 @@ got_pg: if (kmemcheck_enabled) kmemcheck_pagealloc_alloc(page, order, gfp_mask); return page; + +} + +/* + * This is the 'heart' of the zoned buddy allocator. + */ +struct page * +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, nodemask_t *nodemask) +{ + enum zone_type high_zoneidx = gfp_zone(gfp_mask); + struct zone *preferred_zone; + struct page *page; + int migratetype = allocflags_to_migratetype(gfp_mask); + + lockdep_trace_alloc(gfp_mask); + + might_sleep_if(gfp_mask & __GFP_WAIT); + + if (should_fail_alloc_page(gfp_mask, order)) + return NULL; + + /* + * Check the zones suitable for the gfp_mask contain at least one + * valid zone. It's possible to have an empty zonelist as a result + * of GFP_THISNODE and a memoryless node + */ + if (unlikely(!zonelist->_zonerefs->zone)) + return NULL; + + /* The preferred zone is used for statistics later */ + first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone); + if (!preferred_zone) + return NULL; + + /* First allocation attempt */ + page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, + zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET, + preferred_zone, migratetype); + if (unlikely(!page)) + page = __alloc_pages_slowpath(gfp_mask, order, + zonelist, high_zoneidx, nodemask, + preferred_zone, migratetype); + + return page; } -EXPORT_SYMBOL(__alloc_pages_internal); +EXPORT_SYMBOL(__alloc_pages_nodemask); /* * Common helper functions. @@ -1817,7 +2023,7 @@ static unsigned int nr_free_zone_pages(int offset) for_each_zone_zonelist(zone, z, zonelist, offset) { unsigned long size = zone->present_pages; - unsigned long high = zone->pages_high; + unsigned long high = high_wmark_pages(zone); if (size > high) sum += size - high; } @@ -1909,19 +2115,14 @@ void show_free_areas(void) printk("Active_anon:%lu active_file:%lu inactive_anon:%lu\n" " inactive_file:%lu" -//TODO: check/adjust line lengths -#ifdef CONFIG_UNEVICTABLE_LRU " unevictable:%lu" -#endif " dirty:%lu writeback:%lu unstable:%lu\n" " free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n", global_page_state(NR_ACTIVE_ANON), global_page_state(NR_ACTIVE_FILE), global_page_state(NR_INACTIVE_ANON), global_page_state(NR_INACTIVE_FILE), -#ifdef CONFIG_UNEVICTABLE_LRU global_page_state(NR_UNEVICTABLE), -#endif global_page_state(NR_FILE_DIRTY), global_page_state(NR_WRITEBACK), global_page_state(NR_UNSTABLE_NFS), @@ -1945,25 +2146,21 @@ void show_free_areas(void) " inactive_anon:%lukB" " active_file:%lukB" " inactive_file:%lukB" -#ifdef CONFIG_UNEVICTABLE_LRU " unevictable:%lukB" -#endif " present:%lukB" " pages_scanned:%lu" " all_unreclaimable? %s" "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), - K(zone->pages_min), - K(zone->pages_low), - K(zone->pages_high), + K(min_wmark_pages(zone)), + K(low_wmark_pages(zone)), + K(high_wmark_pages(zone)), K(zone_page_state(zone, NR_ACTIVE_ANON)), K(zone_page_state(zone, NR_INACTIVE_ANON)), K(zone_page_state(zone, NR_ACTIVE_FILE)), K(zone_page_state(zone, NR_INACTIVE_FILE)), -#ifdef CONFIG_UNEVICTABLE_LRU K(zone_page_state(zone, NR_UNEVICTABLE)), -#endif K(zone->present_pages), zone->pages_scanned, (zone_is_all_unreclaimable(zone) ? "yes" : "no") @@ -2121,7 +2318,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write, } -#define MAX_NODE_LOAD (num_online_nodes()) +#define MAX_NODE_LOAD (nr_online_nodes) static int node_load[MAX_NUMNODES]; /** @@ -2330,7 +2527,7 @@ static void build_zonelists(pg_data_t *pgdat) /* NUMA-aware ordering of nodes */ local_node = pgdat->node_id; - load = num_online_nodes(); + load = nr_online_nodes; prev_node = local_node; nodes_clear(used_mask); @@ -2481,7 +2678,7 @@ void build_all_zonelists(void) printk("Built %i zonelists in %s order, mobility grouping %s. " "Total pages: %ld\n", - num_online_nodes(), + nr_online_nodes, zonelist_order_name[current_zonelist_order], page_group_by_mobility_disabled ? "off" : "on", vm_total_pages); @@ -2560,8 +2757,8 @@ static inline unsigned long wait_table_bits(unsigned long size) /* * Mark a number of pageblocks as MIGRATE_RESERVE. The number - * of blocks reserved is based on zone->pages_min. The memory within the - * reserve will tend to store contiguous free pages. Setting min_free_kbytes + * of blocks reserved is based on min_wmark_pages(zone). The memory within + * the reserve will tend to store contiguous free pages. Setting min_free_kbytes * higher will lead to a bigger reserve which will get freed as contiguous * blocks as reclaim kicks in */ @@ -2574,7 +2771,7 @@ static void setup_zone_migrate_reserve(struct zone *zone) /* Get the start pfn, end pfn and the number of blocks to reserve */ start_pfn = zone->zone_start_pfn; end_pfn = start_pfn + zone->spanned_pages; - reserve = roundup(zone->pages_min, pageblock_nr_pages) >> + reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >> pageblock_order; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { @@ -3506,7 +3703,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, zone_pcp_init(zone); for_each_lru(l) { INIT_LIST_HEAD(&zone->lru[l].list); - zone->lru[l].nr_scan = 0; + zone->lru[l].nr_saved_scan = 0; } zone->reclaim_stat.recent_rotated[0] = 0; zone->reclaim_stat.recent_rotated[1] = 0; @@ -4043,6 +4240,11 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) early_node_map[i].start_pfn, early_node_map[i].end_pfn); + /* + * find_zone_movable_pfns_for_nodes/early_calculate_totalpages init + * that node_mask, clear it at first + */ + nodes_clear(node_states[N_HIGH_MEMORY]); /* Initialise every node */ mminit_verify_pageflags_layout(); setup_nr_node_ids(); @@ -4177,8 +4379,8 @@ static void calculate_totalreserve_pages(void) max = zone->lowmem_reserve[j]; } - /* we treat pages_high as reserved pages. */ - max += zone->pages_high; + /* we treat the high watermark as reserved pages. */ + max += high_wmark_pages(zone); if (max > zone->present_pages) max = zone->present_pages; @@ -4228,12 +4430,13 @@ 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|removed} * - * 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; @@ -4258,7 +4461,7 @@ void setup_per_zone_pages_min(void) * need highmem pages, so cap pages_min to a small * value here. * - * The (pages_high-pages_low) and (pages_low-pages_min) + * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) * deltas controls asynch page reclaim, and so should * not be capped for highmem. */ @@ -4269,17 +4472,17 @@ void setup_per_zone_pages_min(void) min_pages = SWAP_CLUSTER_MAX; if (min_pages > 128) min_pages = 128; - zone->pages_min = min_pages; + zone->watermark[WMARK_MIN] = min_pages; } else { /* * If it's a lowmem zone, reserve a number of pages * proportionate to the zone's size. */ - zone->pages_min = tmp; + zone->watermark[WMARK_MIN] = tmp; } - zone->pages_low = zone->pages_min + (tmp >> 2); - zone->pages_high = zone->pages_min + (tmp >> 1); + zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); + zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -4289,8 +4492,6 @@ void setup_per_zone_pages_min(void) } /** - * setup_per_zone_inactive_ratio - called when min_free_kbytes changes. - * * The inactive anon list should be small enough that the VM never has to * do too much work, but large enough that each inactive page has a chance * to be referenced again before it is swapped out. @@ -4311,21 +4512,26 @@ void setup_per_zone_pages_min(void) * 1TB 101 10GB * 10TB 320 32GB */ -static void setup_per_zone_inactive_ratio(void) +void calculate_zone_inactive_ratio(struct zone *zone) { - struct zone *zone; - - for_each_zone(zone) { - unsigned int gb, ratio; + unsigned int gb, ratio; - /* Zone size in gigabytes */ - gb = zone->present_pages >> (30 - PAGE_SHIFT); + /* Zone size in gigabytes */ + gb = zone->present_pages >> (30 - PAGE_SHIFT); + if (gb) ratio = int_sqrt(10 * gb); - if (!ratio) - ratio = 1; + 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); } /* @@ -4352,7 +4558,7 @@ static void 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; @@ -4363,12 +4569,12 @@ 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 @@ -4380,7 +4586,7 @@ 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; } @@ -4424,7 +4630,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, * whenever sysctl_lowmem_reserve_ratio changes. * * The reserve ratio obviously has absolutely no relation with the - * pages_min watermarks. The lowmem reserve ratio can only make sense + * minimum watermarks. The lowmem reserve ratio can only make sense * if in function of the boot time zone sizes. */ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, @@ -4531,23 +4737,13 @@ void *__init alloc_large_system_hash(const char *tablename, else if (hashdist) table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL); else { - unsigned long order = get_order(size); - table = (void*) __get_free_pages(GFP_ATOMIC, order); /* * If bucketsize is not a power-of-two, we may free - * some pages at the end of hash table. + * some pages at the end of hash table which + * alloc_pages_exact() automatically does */ - if (table) { - unsigned long alloc_end = (unsigned long)table + - (PAGE_SIZE << order); - unsigned long used = (unsigned long)table + - PAGE_ALIGN(size); - split_page(virt_to_page(table), order); - while (used < alloc_end) { - free_page(used); - used += PAGE_SIZE; - } - } + if (get_order(size) < MAX_ORDER) + table = alloc_pages_exact(size, GFP_ATOMIC); } } while (!table && size > PAGE_SIZE && --log2qty); diff --git a/mm/page_io.c b/mm/page_io.c index 3023c475e04..c6f3e5071de 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -120,7 +120,7 @@ out: return ret; } -int swap_readpage(struct file *file, struct page *page) +int swap_readpage(struct page *page) { struct bio *bio; int ret = 0; diff --git a/mm/readahead.c b/mm/readahead.c index 133b6d52551..aa1aa234523 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, @@ -210,6 +207,7 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages)) return -EINVAL; + nr_to_read = max_sane_readahead(nr_to_read); while (nr_to_read) { int err; @@ -231,22 +229,6 @@ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, } /* - * 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. */ @@ -259,7 +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; @@ -348,6 +330,59 @@ static unsigned long get_next_ra_size(struct file_ra_state *ra, */ /* + * Count contiguously cached pages from @offset-1 to @offset-@max, + * this count is a conservative estimation of + * - length of the sequential read sequence, or + * - thrashing threshold in memory tight systems + */ +static pgoff_t count_history_pages(struct address_space *mapping, + struct file_ra_state *ra, + pgoff_t offset, unsigned long max) +{ + pgoff_t head; + + rcu_read_lock(); + head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max); + rcu_read_unlock(); + + return offset - 1 - head; +} + +/* + * page cache context based read-ahead + */ +static int try_context_readahead(struct address_space *mapping, + struct file_ra_state *ra, + pgoff_t offset, + unsigned long req_size, + unsigned long max) +{ + pgoff_t size; + + size = count_history_pages(mapping, ra, offset, max); + + /* + * no history pages: + * it could be a random read + */ + if (!size) + return 0; + + /* + * starts from beginning of file: + * it is a strong indication of long-run stream (or whole-file-read) + */ + if (size >= offset) + size *= 2; + + ra->start = offset; + ra->size = get_init_ra_size(size + req_size, max); + ra->async_size = ra->size; + + return 1; +} + +/* * A minimal readahead algorithm for trivial sequential/random reads. */ static unsigned long @@ -356,34 +391,26 @@ ondemand_readahead(struct address_space *mapping, bool hit_readahead_marker, pgoff_t offset, unsigned long req_size) { - int max = ra->ra_pages; /* max readahead pages */ - pgoff_t prev_offset; - int sequential; + unsigned long max = max_sane_readahead(ra->ra_pages); + + /* + * start of file + */ + if (!offset) + goto initial_readahead; /* * It's the expected callback offset, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ - if (offset && (offset == (ra->start + ra->size - ra->async_size) || - offset == (ra->start + ra->size))) { + if ((offset == (ra->start + ra->size - ra->async_size) || + offset == (ra->start + ra->size))) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max); ra->async_size = ra->size; goto readit; } - prev_offset = ra->prev_pos >> PAGE_CACHE_SHIFT; - sequential = offset - prev_offset <= 1UL || req_size > max; - - /* - * Standalone, small read. - * Read as is, and do not pollute the readahead state. - */ - if (!hit_readahead_marker && !sequential) { - return __do_page_cache_readahead(mapping, filp, - offset, req_size, 0); - } - /* * Hit a marked page without valid readahead state. * E.g. interleaved reads. @@ -394,7 +421,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = radix_tree_next_hole(&mapping->page_tree, offset,max+1); + start = radix_tree_next_hole(&mapping->page_tree, offset+1,max); rcu_read_unlock(); if (!start || start - offset > max) @@ -402,23 +429,53 @@ ondemand_readahead(struct address_space *mapping, ra->start = start; ra->size = start - offset; /* old async_size */ + ra->size += req_size; ra->size = get_next_ra_size(ra, max); ra->async_size = ra->size; goto readit; } /* - * It may be one of - * - first read on start of file - * - sequential cache miss - * - oversize random read - * Start readahead for it. + * oversize read + */ + if (req_size > max) + goto initial_readahead; + + /* + * sequential cache miss + */ + if (offset - (ra->prev_pos >> PAGE_CACHE_SHIFT) <= 1UL) + goto initial_readahead; + + /* + * Query the page cache and look for the traces(cached history pages) + * that a sequential stream would leave behind. + */ + if (try_context_readahead(mapping, ra, offset, req_size, max)) + goto readit; + + /* + * standalone, small random read + * Read as is, and do not pollute the readahead state. */ + return __do_page_cache_readahead(mapping, filp, offset, req_size, 0); + +initial_readahead: ra->start = offset; ra->size = get_init_ra_size(req_size, max); ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size; readit: + /* + * Will this read hit the readahead marker made by itself? + * If so, trigger the readahead marker hit now, and merge + * the resulted next readahead window into the current one. + */ + if (offset == ra->start && ra->size == ra->async_size) { + ra->async_size = get_next_ra_size(ra, max); + ra->size += ra->async_size; + } + return ra_submit(ra, mapping, filp); } diff --git a/mm/rmap.c b/mm/rmap.c index 23122af3261..c9ccc1a72dc 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -333,7 +333,9 @@ static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) * repeatedly from either page_referenced_anon or page_referenced_file. */ static int page_referenced_one(struct page *page, - struct vm_area_struct *vma, unsigned int *mapcount) + struct vm_area_struct *vma, + unsigned int *mapcount, + unsigned long *vm_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -381,11 +383,14 @@ out_unmap: (*mapcount)--; pte_unmap_unlock(pte, ptl); out: + if (referenced) + *vm_flags |= vma->vm_flags; return referenced; } static int page_referenced_anon(struct page *page, - struct mem_cgroup *mem_cont) + struct mem_cgroup *mem_cont, + unsigned long *vm_flags) { unsigned int mapcount; struct anon_vma *anon_vma; @@ -405,7 +410,8 @@ static int page_referenced_anon(struct page *page, */ if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont)) continue; - referenced += page_referenced_one(page, vma, &mapcount); + referenced += page_referenced_one(page, vma, + &mapcount, vm_flags); if (!mapcount) break; } @@ -418,6 +424,7 @@ static int page_referenced_anon(struct page *page, * page_referenced_file - referenced check for object-based rmap * @page: the page we're checking references on. * @mem_cont: target memory controller + * @vm_flags: collect encountered vma->vm_flags who actually referenced the page * * For an object-based mapped page, find all the places it is mapped and * check/clear the referenced flag. This is done by following the page->mapping @@ -427,7 +434,8 @@ static int page_referenced_anon(struct page *page, * This function is only called from page_referenced for object-based pages. */ static int page_referenced_file(struct page *page, - struct mem_cgroup *mem_cont) + struct mem_cgroup *mem_cont, + unsigned long *vm_flags) { unsigned int mapcount; struct address_space *mapping = page->mapping; @@ -467,7 +475,8 @@ static int page_referenced_file(struct page *page, */ if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont)) continue; - referenced += page_referenced_one(page, vma, &mapcount); + referenced += page_referenced_one(page, vma, + &mapcount, vm_flags); if (!mapcount) break; } @@ -481,29 +490,35 @@ static int page_referenced_file(struct page *page, * @page: the page to test * @is_locked: caller holds lock on the page * @mem_cont: target memory controller + * @vm_flags: collect encountered vma->vm_flags who actually referenced the page * * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ -int page_referenced(struct page *page, int is_locked, - struct mem_cgroup *mem_cont) +int page_referenced(struct page *page, + int is_locked, + struct mem_cgroup *mem_cont, + unsigned long *vm_flags) { int referenced = 0; if (TestClearPageReferenced(page)) referenced++; + *vm_flags = 0; if (page_mapped(page) && page->mapping) { if (PageAnon(page)) - referenced += page_referenced_anon(page, mem_cont); + referenced += page_referenced_anon(page, mem_cont, + vm_flags); else if (is_locked) - referenced += page_referenced_file(page, mem_cont); + referenced += page_referenced_file(page, mem_cont, + vm_flags); else if (!trylock_page(page)) referenced++; else { if (page->mapping) - referenced += - page_referenced_file(page, mem_cont); + referenced += page_referenced_file(page, + mem_cont, vm_flags); unlock_page(page); } } @@ -1202,7 +1217,6 @@ int try_to_unmap(struct page *page, int migration) return ret; } -#ifdef CONFIG_UNEVICTABLE_LRU /** * try_to_munlock - try to munlock a page * @page: the page to be munlocked @@ -1226,4 +1240,4 @@ int try_to_munlock(struct page *page) else return try_to_unmap_file(page, 1, 0); } -#endif + diff --git a/mm/shmem.c b/mm/shmem.c index 0132fbd45a2..e89d7ec18ed 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1097,7 +1097,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) shmem_swp_unmap(entry); unlock: spin_unlock(&info->lock); - swap_free(swap); + swapcache_free(swap, NULL); redirty: set_page_dirty(page); if (wbc->for_reclaim) @@ -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; diff --git a/mm/slab.c b/mm/slab.c index af3376d0a83..f257d4dd474 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -818,7 +818,6 @@ static void __slab_error(const char *function, struct kmem_cache *cachep, */ static int use_alien_caches __read_mostly = 1; -static int numa_platform __read_mostly = 1; static int __init noaliencache_setup(char *s) { use_alien_caches = 0; @@ -1377,10 +1376,8 @@ void __init kmem_cache_init(void) int order; int node; - if (num_possible_nodes() == 1) { + if (num_possible_nodes() == 1) use_alien_caches = 0; - numa_platform = 0; - } for (i = 0; i < NUM_INIT_LISTS; i++) { kmem_list3_init(&initkmem_list3[i]); @@ -1627,7 +1624,7 @@ 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 | __GFP_NOTRACK, cachep->gfporder); + page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder); if (!page) return NULL; @@ -3193,7 +3190,7 @@ 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) { @@ -3530,7 +3527,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp) * variable to skip the call, which is mostly likely to be present in * the cache. */ - if (numa_platform && cache_free_alien(cachep, objp)) + if (nr_online_nodes > 1 && cache_free_alien(cachep, objp)) return; if (likely(ac->avail < ac->limit)) { 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); diff --git a/mm/slub.c b/mm/slub.c index 15960a09abb..2701419b0ad 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3765,7 +3765,7 @@ static int list_locations(struct kmem_cache *s, char *buf, to_cpumask(l->cpus)); } - if (num_online_nodes() > 1 && !nodes_empty(l->nodes) && + if (nr_online_nodes > 1 && !nodes_empty(l->nodes) && len < PAGE_SIZE - 60) { len += sprintf(buf + len, " nodes="); len += nodelist_scnprintf(buf + len, PAGE_SIZE - len - 50, diff --git a/mm/swap_state.c b/mm/swap_state.c index 1416e7e9e02..42cd38eba79 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -124,7 +124,6 @@ void __delete_from_swap_cache(struct page *page) /** * add_to_swap - allocate swap space for a page * @page: page we want to move to swap - * @gfp_mask: memory allocation flags * * Allocate swap space for the page and add the page to the * swap cache. Caller needs to hold the page lock. @@ -162,11 +161,11 @@ int add_to_swap(struct page *page) return 1; case -EEXIST: /* Raced with "speculative" read_swap_cache_async */ - swap_free(entry); + swapcache_free(entry, NULL); continue; default: /* -ENOMEM radix-tree allocation failure */ - swap_free(entry); + swapcache_free(entry, NULL); return 0; } } @@ -188,8 +187,7 @@ 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); + swapcache_free(entry, page); page_cache_release(page); } @@ -293,7 +291,10 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * Swap entry may have been freed since our caller observed it. */ - if (!swap_duplicate(entry)) + err = swapcache_prepare(entry); + if (err == -EEXIST) /* seems racy */ + continue; + if (err) /* swp entry is obsolete ? */ break; /* @@ -312,12 +313,12 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * Initiate read into locked page and return. */ lru_cache_add_anon(new_page); - swap_readpage(NULL, new_page); + swap_readpage(new_page); return new_page; } ClearPageSwapBacked(new_page); __clear_page_locked(new_page); - swap_free(entry); + swapcache_free(entry, NULL); } while (err != -ENOMEM); if (new_page) diff --git a/mm/swapfile.c b/mm/swapfile.c index 312fafe0ab6..28faa01cf57 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -53,6 +53,59 @@ static struct swap_info_struct swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); +/* For reference count accounting in swap_map */ +/* enum for swap_map[] handling. internal use only */ +enum { + SWAP_MAP = 0, /* ops for reference from swap users */ + SWAP_CACHE, /* ops for reference from swap cache */ +}; + +static inline int swap_count(unsigned short ent) +{ + return ent & SWAP_COUNT_MASK; +} + +static inline bool swap_has_cache(unsigned short ent) +{ + return !!(ent & SWAP_HAS_CACHE); +} + +static inline unsigned short encode_swapmap(int count, bool has_cache) +{ + unsigned short ret = count; + + if (has_cache) + return SWAP_HAS_CACHE | ret; + return ret; +} + +/* returnes 1 if swap entry is freed */ +static int +__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) +{ + int type = si - swap_info; + swp_entry_t entry = swp_entry(type, offset); + struct page *page; + int ret = 0; + + page = find_get_page(&swapper_space, entry.val); + if (!page) + return 0; + /* + * This function is called from scan_swap_map() and it's called + * by vmscan.c at reclaiming pages. So, we hold a lock on a page, here. + * We have to use trylock for avoiding deadlock. This is a special + * case and you should use try_to_free_swap() with explicit lock_page() + * in usual operations. + */ + if (trylock_page(page)) { + ret = try_to_free_swap(page); + unlock_page(page); + } + page_cache_release(page); + return ret; +} + /* * We need this because the bdev->unplug_fn can sleep and we cannot * hold swap_lock while calling the unplug_fn. And swap_lock @@ -167,7 +220,8 @@ static int wait_for_discard(void *word) #define SWAPFILE_CLUSTER 256 #define LATENCY_LIMIT 256 -static inline unsigned long scan_swap_map(struct swap_info_struct *si) +static inline unsigned long scan_swap_map(struct swap_info_struct *si, + int cache) { unsigned long offset; unsigned long scan_base; @@ -273,6 +327,19 @@ checks: goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; + + /* reuse swap entry of cache-only swap if not busy. */ + if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + int swap_was_freed; + spin_unlock(&swap_lock); + swap_was_freed = __try_to_reclaim_swap(si, offset); + spin_lock(&swap_lock); + /* entry was freed successfully, try to use this again */ + if (swap_was_freed) + goto checks; + goto scan; /* check next one */ + } + if (si->swap_map[offset]) goto scan; @@ -285,7 +352,10 @@ checks: si->lowest_bit = si->max; si->highest_bit = 0; } - si->swap_map[offset] = 1; + if (cache == SWAP_CACHE) /* at usual swap-out via vmscan.c */ + si->swap_map[offset] = encode_swapmap(0, true); + else /* at suspend */ + si->swap_map[offset] = encode_swapmap(1, false); si->cluster_next = offset + 1; si->flags -= SWP_SCANNING; @@ -351,6 +421,10 @@ scan: spin_lock(&swap_lock); goto checks; } + if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + spin_lock(&swap_lock); + goto checks; + } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; @@ -362,6 +436,10 @@ scan: spin_lock(&swap_lock); goto checks; } + if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { + spin_lock(&swap_lock); + goto checks; + } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; @@ -401,7 +479,8 @@ swp_entry_t get_swap_page(void) continue; swap_list.next = next; - offset = scan_swap_map(si); + /* This is called for allocating swap entry for cache */ + offset = scan_swap_map(si, SWAP_CACHE); if (offset) { spin_unlock(&swap_lock); return swp_entry(type, offset); @@ -415,6 +494,7 @@ noswap: return (swp_entry_t) {0}; } +/* The only caller of this function is now susupend routine */ swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si; @@ -424,7 +504,8 @@ swp_entry_t get_swap_page_of_type(int type) si = swap_info + type; if (si->flags & SWP_WRITEOK) { nr_swap_pages--; - offset = scan_swap_map(si); + /* This is called for allocating swap entry, not cache */ + offset = scan_swap_map(si, SWAP_MAP); if (offset) { spin_unlock(&swap_lock); return swp_entry(type, offset); @@ -471,25 +552,38 @@ out: return NULL; } -static int swap_entry_free(struct swap_info_struct *p, swp_entry_t ent) +static int swap_entry_free(struct swap_info_struct *p, + swp_entry_t ent, int cache) { unsigned long offset = swp_offset(ent); - int count = p->swap_map[offset]; - - if (count < SWAP_MAP_MAX) { - count--; - p->swap_map[offset] = count; - if (!count) { - if (offset < p->lowest_bit) - p->lowest_bit = offset; - if (offset > p->highest_bit) - p->highest_bit = offset; - if (p->prio > swap_info[swap_list.next].prio) - swap_list.next = p - swap_info; - nr_swap_pages++; - p->inuse_pages--; - mem_cgroup_uncharge_swap(ent); + int count = swap_count(p->swap_map[offset]); + bool has_cache; + + has_cache = swap_has_cache(p->swap_map[offset]); + + if (cache == SWAP_MAP) { /* dropping usage count of swap */ + if (count < SWAP_MAP_MAX) { + count--; + p->swap_map[offset] = encode_swapmap(count, has_cache); } + } else { /* dropping swap cache flag */ + VM_BUG_ON(!has_cache); + p->swap_map[offset] = encode_swapmap(count, false); + + } + /* return code. */ + count = p->swap_map[offset]; + /* free if no reference */ + if (!count) { + if (offset < p->lowest_bit) + p->lowest_bit = offset; + if (offset > p->highest_bit) + p->highest_bit = offset; + if (p->prio > swap_info[swap_list.next].prio) + swap_list.next = p - swap_info; + nr_swap_pages++; + p->inuse_pages--; + mem_cgroup_uncharge_swap(ent); } return count; } @@ -504,9 +598,26 @@ void swap_free(swp_entry_t entry) p = swap_info_get(entry); if (p) { - swap_entry_free(p, entry); + swap_entry_free(p, entry, SWAP_MAP); + spin_unlock(&swap_lock); + } +} + +/* + * Called after dropping swapcache to decrease refcnt to swap entries. + */ +void swapcache_free(swp_entry_t entry, struct page *page) +{ + struct swap_info_struct *p; + + if (page) + mem_cgroup_uncharge_swapcache(page, entry); + p = swap_info_get(entry); + if (p) { + swap_entry_free(p, entry, SWAP_CACHE); spin_unlock(&swap_lock); } + return; } /* @@ -521,8 +632,7 @@ static inline int page_swapcount(struct page *page) entry.val = page_private(page); p = swap_info_get(entry); if (p) { - /* Subtract the 1 for the swap cache itself */ - count = p->swap_map[swp_offset(entry)] - 1; + count = swap_count(p->swap_map[swp_offset(entry)]); spin_unlock(&swap_lock); } return count; @@ -584,7 +694,7 @@ int free_swap_and_cache(swp_entry_t entry) p = swap_info_get(entry); if (p) { - if (swap_entry_free(p, entry) == 1) { + if (swap_entry_free(p, entry, SWAP_MAP) == SWAP_HAS_CACHE) { page = find_get_page(&swapper_space, entry.val); if (page && !trylock_page(page)) { page_cache_release(page); @@ -891,7 +1001,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, i = 1; } count = si->swap_map[i]; - if (count && count != SWAP_MAP_BAD) + if (count && swap_count(count) != SWAP_MAP_BAD) break; } return i; @@ -995,13 +1105,13 @@ static int try_to_unuse(unsigned int type) */ shmem = 0; swcount = *swap_map; - if (swcount > 1) { + if (swap_count(swcount)) { if (start_mm == &init_mm) shmem = shmem_unuse(entry, page); else retval = unuse_mm(start_mm, entry, page); } - if (*swap_map > 1) { + if (swap_count(*swap_map)) { int set_start_mm = (*swap_map >= swcount); struct list_head *p = &start_mm->mmlist; struct mm_struct *new_start_mm = start_mm; @@ -1011,7 +1121,7 @@ static int try_to_unuse(unsigned int type) atomic_inc(&new_start_mm->mm_users); atomic_inc(&prev_mm->mm_users); spin_lock(&mmlist_lock); - while (*swap_map > 1 && !retval && !shmem && + while (swap_count(*swap_map) && !retval && !shmem && (p = p->next) != &start_mm->mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!atomic_inc_not_zero(&mm->mm_users)) @@ -1023,14 +1133,16 @@ static int try_to_unuse(unsigned int type) cond_resched(); swcount = *swap_map; - if (swcount <= 1) + if (!swap_count(swcount)) /* any usage ? */ ; else if (mm == &init_mm) { set_start_mm = 1; shmem = shmem_unuse(entry, page); } else retval = unuse_mm(mm, entry, page); - if (set_start_mm && *swap_map < swcount) { + + if (set_start_mm && + swap_count(*swap_map) < swcount) { mmput(new_start_mm); atomic_inc(&mm->mm_users); new_start_mm = mm; @@ -1057,21 +1169,25 @@ static int try_to_unuse(unsigned int type) } /* - * How could swap count reach 0x7fff when the maximum - * pid is 0x7fff, and there's no way to repeat a swap - * page within an mm (except in shmem, where it's the - * shared object which takes the reference count)? - * We believe SWAP_MAP_MAX cannot occur in Linux 2.4. - * + * How could swap count reach 0x7ffe ? + * There's no way to repeat a swap page within an mm + * (except in shmem, where it's the shared object which takes + * the reference count)? + * We believe SWAP_MAP_MAX cannot occur.(if occur, unsigned + * short is too small....) * If that's wrong, then we should worry more about * exit_mmap() and do_munmap() cases described above: * we might be resetting SWAP_MAP_MAX too early here. * We know "Undead"s can happen, they're okay, so don't * report them; but do report if we reset SWAP_MAP_MAX. */ - if (*swap_map == SWAP_MAP_MAX) { + /* We might release the lock_page() in unuse_mm(). */ + if (!PageSwapCache(page) || page_private(page) != entry.val) + goto retry; + + if (swap_count(*swap_map) == SWAP_MAP_MAX) { spin_lock(&swap_lock); - *swap_map = 1; + *swap_map = encode_swapmap(0, true); spin_unlock(&swap_lock); reset_overflow = 1; } @@ -1089,7 +1205,8 @@ static int try_to_unuse(unsigned int type) * pages would be incorrect if swap supported "shared * private" pages, but they are handled by tmpfs files. */ - if ((*swap_map > 1) && PageDirty(page) && PageSwapCache(page)) { + if (swap_count(*swap_map) && + PageDirty(page) && PageSwapCache(page)) { struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, }; @@ -1116,6 +1233,7 @@ static int try_to_unuse(unsigned int type) * mark page dirty so shrink_page_list will preserve it. */ SetPageDirty(page); +retry: unlock_page(page); page_cache_release(page); @@ -1942,15 +2060,23 @@ void si_swapinfo(struct sysinfo *val) * * Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as * "permanent", but will be reclaimed by the next swapoff. + * Returns error code in following case. + * - success -> 0 + * - swp_entry is invalid -> EINVAL + * - swp_entry is migration entry -> EINVAL + * - swap-cache reference is requested but there is already one. -> EEXIST + * - swap-cache reference is requested but the entry is not used. -> ENOENT */ -int swap_duplicate(swp_entry_t entry) +static int __swap_duplicate(swp_entry_t entry, bool cache) { struct swap_info_struct * p; unsigned long offset, type; - int result = 0; + int result = -EINVAL; + int count; + bool has_cache; if (is_migration_entry(entry)) - return 1; + return -EINVAL; type = swp_type(entry); if (type >= nr_swapfiles) @@ -1959,17 +2085,40 @@ int swap_duplicate(swp_entry_t entry) offset = swp_offset(entry); spin_lock(&swap_lock); - if (offset < p->max && p->swap_map[offset]) { - if (p->swap_map[offset] < SWAP_MAP_MAX - 1) { - p->swap_map[offset]++; - result = 1; - } else if (p->swap_map[offset] <= SWAP_MAP_MAX) { + + if (unlikely(offset >= p->max)) + goto unlock_out; + + count = swap_count(p->swap_map[offset]); + has_cache = swap_has_cache(p->swap_map[offset]); + + if (cache == SWAP_CACHE) { /* called for swapcache/swapin-readahead */ + + /* set SWAP_HAS_CACHE if there is no cache and entry is used */ + if (!has_cache && count) { + p->swap_map[offset] = encode_swapmap(count, true); + result = 0; + } else if (has_cache) /* someone added cache */ + result = -EEXIST; + else if (!count) /* no users */ + result = -ENOENT; + + } else if (count || has_cache) { + if (count < SWAP_MAP_MAX - 1) { + p->swap_map[offset] = encode_swapmap(count + 1, + has_cache); + result = 0; + } else if (count <= SWAP_MAP_MAX) { if (swap_overflow++ < 5) - printk(KERN_WARNING "swap_dup: swap entry overflow\n"); - p->swap_map[offset] = SWAP_MAP_MAX; - result = 1; + printk(KERN_WARNING + "swap_dup: swap entry overflow\n"); + p->swap_map[offset] = encode_swapmap(SWAP_MAP_MAX, + has_cache); + result = 0; } - } + } else + result = -ENOENT; /* unused swap entry */ +unlock_out: spin_unlock(&swap_lock); out: return result; @@ -1978,6 +2127,27 @@ bad_file: printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val); goto out; } +/* + * increase reference count of swap entry by 1. + */ +void swap_duplicate(swp_entry_t entry) +{ + __swap_duplicate(entry, SWAP_MAP); +} + +/* + * @entry: swap entry for which we allocate swap cache. + * + * Called when allocating swap cache for exising swap entry, + * This can return error codes. Returns 0 at success. + * -EBUSY means there is a swap cache. + * Note: return code is different from swap_duplicate(). + */ +int swapcache_prepare(swp_entry_t entry) +{ + return __swap_duplicate(entry, SWAP_CACHE); +} + struct swap_info_struct * get_swap_info_struct(unsigned type) @@ -2016,7 +2186,7 @@ int valid_swaphandles(swp_entry_t entry, unsigned long *offset) /* Don't read in free or bad pages */ if (!si->swap_map[toff]) break; - if (si->swap_map[toff] == SWAP_MAP_BAD) + if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD) break; } /* Count contiguous allocated slots below our target */ @@ -2024,7 +2194,7 @@ int valid_swaphandles(swp_entry_t entry, unsigned long *offset) /* Don't read in free or bad pages */ if (!si->swap_map[toff]) break; - if (si->swap_map[toff] == SWAP_MAP_BAD) + if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD) break; } spin_unlock(&swap_lock); diff --git a/mm/truncate.c b/mm/truncate.c index 12e1579f916..ccc3ecf7cb9 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -267,8 +267,21 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) } EXPORT_SYMBOL(truncate_inode_pages); -unsigned long __invalidate_mapping_pages(struct address_space *mapping, - pgoff_t start, pgoff_t end, bool be_atomic) +/** + * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode + * @mapping: the address_space which holds the pages to invalidate + * @start: the offset 'from' which to invalidate + * @end: the offset 'to' which to invalidate (inclusive) + * + * This function only removes the unlocked pages, if you want to + * remove all the pages of one inode, you must call truncate_inode_pages. + * + * invalidate_mapping_pages() will not block on IO activity. It will not + * invalidate pages which are dirty, locked, under writeback or mapped into + * pagetables. + */ +unsigned long invalidate_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t end) { struct pagevec pvec; pgoff_t next = start; @@ -309,30 +322,10 @@ unlock: break; } pagevec_release(&pvec); - if (likely(!be_atomic)) - cond_resched(); + cond_resched(); } return ret; } - -/** - * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode - * @mapping: the address_space which holds the pages to invalidate - * @start: the offset 'from' which to invalidate - * @end: the offset 'to' which to invalidate (inclusive) - * - * This function only removes the unlocked pages, if you want to - * remove all the pages of one inode, you must call truncate_inode_pages. - * - * invalidate_mapping_pages() will not block on IO activity. It will not - * invalidate pages which are dirty, locked, under writeback or mapped into - * pagetables. - */ -unsigned long invalidate_mapping_pages(struct address_space *mapping, - pgoff_t start, pgoff_t end) -{ - return __invalidate_mapping_pages(mapping, start, end, false); -} EXPORT_SYMBOL(invalidate_mapping_pages); /* 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) diff --git a/mm/vmscan.c b/mm/vmscan.c index 95c08a8cc2b..4139aa52b94 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -470,8 +470,7 @@ 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); + swapcache_free(swap, page); } else { __remove_from_page_cache(page); spin_unlock_irq(&mapping->tree_lock); @@ -514,7 +513,6 @@ int remove_mapping(struct address_space *mapping, struct page *page) * * lru_lock must not be held, interrupts must be enabled. */ -#ifdef CONFIG_UNEVICTABLE_LRU void putback_lru_page(struct page *page) { int lru; @@ -568,20 +566,6 @@ redo: put_page(page); /* drop ref from isolate */ } -#else /* CONFIG_UNEVICTABLE_LRU */ - -void putback_lru_page(struct page *page) -{ - int lru; - VM_BUG_ON(PageLRU(page)); - - lru = !!TestClearPageActive(page) + page_is_file_cache(page); - lru_cache_add_lru(page, lru); - put_page(page); -} -#endif /* CONFIG_UNEVICTABLE_LRU */ - - /* * shrink_page_list() returns the number of reclaimed pages */ @@ -593,6 +577,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, struct pagevec freed_pvec; int pgactivate = 0; unsigned long nr_reclaimed = 0; + unsigned long vm_flags; cond_resched(); @@ -643,7 +628,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep_locked; } - referenced = page_referenced(page, 1, sc->mem_cgroup); + referenced = page_referenced(page, 1, + sc->mem_cgroup, &vm_flags); /* In active use or really unfreeable? Activate it. */ if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced && page_mapping_inuse(page)) @@ -943,18 +929,10 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, /* Check that we have not crossed a zone boundary. */ if (unlikely(page_zone_id(cursor_page) != zone_id)) continue; - switch (__isolate_lru_page(cursor_page, mode, file)) { - case 0: + if (__isolate_lru_page(cursor_page, mode, file) == 0) { list_move(&cursor_page->lru, dst); nr_taken++; scan++; - break; - - case -EBUSY: - /* else it is being freed elsewhere */ - list_move(&cursor_page->lru, src); - default: - break; /* ! on LRU or wrong list */ } } } @@ -1061,6 +1039,19 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, unsigned long nr_scanned = 0; unsigned long nr_reclaimed = 0; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); + int lumpy_reclaim = 0; + + /* + * If we need a large contiguous chunk of memory, or have + * trouble getting a small set of contiguous pages, we + * will reclaim both active and inactive pages. + * + * We use the same threshold as pageout congestion_wait below. + */ + if (sc->order > PAGE_ALLOC_COSTLY_ORDER) + lumpy_reclaim = 1; + else if (sc->order && priority < DEF_PRIORITY - 2) + lumpy_reclaim = 1; pagevec_init(&pvec, 1); @@ -1073,19 +1064,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, unsigned long nr_freed; unsigned long nr_active; unsigned int count[NR_LRU_LISTS] = { 0, }; - int mode = ISOLATE_INACTIVE; - - /* - * If we need a large contiguous chunk of memory, or have - * trouble getting a small set of contiguous pages, we - * will reclaim both active and inactive pages. - * - * We use the same threshold as pageout congestion_wait below. - */ - if (sc->order > PAGE_ALLOC_COSTLY_ORDER) - mode = ISOLATE_BOTH; - else if (sc->order && priority < DEF_PRIORITY - 2) - mode = ISOLATE_BOTH; + int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE; nr_taken = sc->isolate_pages(sc->swap_cluster_max, &page_list, &nr_scan, sc->order, mode, @@ -1122,7 +1101,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan, * but that should be acceptable to the caller */ if (nr_freed < nr_taken && !current_is_kswapd() && - sc->order > PAGE_ALLOC_COSTLY_ORDER) { + lumpy_reclaim) { congestion_wait(WRITE, HZ/10); /* @@ -1217,18 +1196,54 @@ static inline void note_zone_scanning_priority(struct zone *zone, int priority) * But we had to alter page->flags anyway. */ +static void move_active_pages_to_lru(struct zone *zone, + struct list_head *list, + enum lru_list lru) +{ + unsigned long pgmoved = 0; + struct pagevec pvec; + struct page *page; + + pagevec_init(&pvec, 1); + + while (!list_empty(list)) { + page = lru_to_page(list); + prefetchw_prev_lru_page(page, list, flags); + + VM_BUG_ON(PageLRU(page)); + SetPageLRU(page); + + VM_BUG_ON(!PageActive(page)); + if (!is_active_lru(lru)) + ClearPageActive(page); /* we are de-activating */ + + list_move(&page->lru, &zone->lru[lru].list); + mem_cgroup_add_lru_list(page, lru); + pgmoved++; + + if (!pagevec_add(&pvec, page) || list_empty(list)) { + spin_unlock_irq(&zone->lru_lock); + if (buffer_heads_over_limit) + pagevec_strip(&pvec); + __pagevec_release(&pvec); + spin_lock_irq(&zone->lru_lock); + } + } + __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved); + if (!is_active_lru(lru)) + __count_vm_events(PGDEACTIVATE, pgmoved); +} static void shrink_active_list(unsigned long nr_pages, struct zone *zone, struct scan_control *sc, int priority, int file) { unsigned long pgmoved; - int pgdeactivate = 0; unsigned long pgscanned; + unsigned long vm_flags; LIST_HEAD(l_hold); /* The pages which were snipped off */ + LIST_HEAD(l_active); LIST_HEAD(l_inactive); struct page *page; - struct pagevec pvec; - enum lru_list lru; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); lru_add_drain(); @@ -1245,13 +1260,14 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, } reclaim_stat->recent_scanned[!!file] += pgmoved; + __count_zone_vm_events(PGREFILL, zone, pgscanned); if (file) __mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved); else __mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved); spin_unlock_irq(&zone->lru_lock); - pgmoved = 0; + pgmoved = 0; /* count referenced (mapping) mapped pages */ while (!list_empty(&l_hold)) { cond_resched(); page = lru_to_page(&l_hold); @@ -1264,58 +1280,44 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, /* page_referenced clears PageReferenced */ if (page_mapping_inuse(page) && - page_referenced(page, 0, sc->mem_cgroup)) + page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) { pgmoved++; + /* + * Identify referenced, file-backed active pages and + * give them one more trip around the active list. So + * that executable code get better chances to stay in + * memory under moderate memory pressure. Anon pages + * are not likely to be evicted by use-once streaming + * IO, plus JVM can create lots of anon VM_EXEC pages, + * so we ignore them here. + */ + if ((vm_flags & VM_EXEC) && !PageAnon(page)) { + list_add(&page->lru, &l_active); + continue; + } + } list_add(&page->lru, &l_inactive); } /* - * Move the pages to the [file or anon] inactive list. + * Move pages back to the lru list. */ - pagevec_init(&pvec, 1); - lru = LRU_BASE + file * LRU_FILE; - spin_lock_irq(&zone->lru_lock); /* - * Count referenced pages from currently used mappings as - * rotated, even though they are moved to the inactive list. - * This helps balance scan pressure between file and anonymous - * pages in get_scan_ratio. + * Count referenced pages from currently used mappings as rotated, + * even though only some of them are actually re-activated. This + * helps balance scan pressure between file and anonymous pages in + * get_scan_ratio. */ reclaim_stat->recent_rotated[!!file] += pgmoved; - pgmoved = 0; - while (!list_empty(&l_inactive)) { - page = lru_to_page(&l_inactive); - prefetchw_prev_lru_page(page, &l_inactive, flags); - VM_BUG_ON(PageLRU(page)); - SetPageLRU(page); - VM_BUG_ON(!PageActive(page)); - ClearPageActive(page); + move_active_pages_to_lru(zone, &l_active, + LRU_ACTIVE + file * LRU_FILE); + move_active_pages_to_lru(zone, &l_inactive, + LRU_BASE + file * LRU_FILE); - list_move(&page->lru, &zone->lru[lru].list); - mem_cgroup_add_lru_list(page, lru); - pgmoved++; - if (!pagevec_add(&pvec, page)) { - __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved); - spin_unlock_irq(&zone->lru_lock); - pgdeactivate += pgmoved; - pgmoved = 0; - if (buffer_heads_over_limit) - pagevec_strip(&pvec); - __pagevec_release(&pvec); - spin_lock_irq(&zone->lru_lock); - } - } - __mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved); - pgdeactivate += pgmoved; - __count_zone_vm_events(PGREFILL, zone, pgscanned); - __count_vm_events(PGDEACTIVATE, pgdeactivate); spin_unlock_irq(&zone->lru_lock); - if (buffer_heads_over_limit) - pagevec_strip(&pvec); - pagevec_release(&pvec); } static int inactive_anon_is_low_global(struct zone *zone) @@ -1350,12 +1352,48 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc) return low; } +static int inactive_file_is_low_global(struct zone *zone) +{ + unsigned long active, inactive; + + active = zone_page_state(zone, NR_ACTIVE_FILE); + inactive = zone_page_state(zone, NR_INACTIVE_FILE); + + return (active > inactive); +} + +/** + * inactive_file_is_low - check if file pages need to be deactivated + * @zone: zone to check + * @sc: scan control of this context + * + * When the system is doing streaming IO, memory pressure here + * ensures that active file pages get deactivated, until more + * than half of the file pages are on the inactive list. + * + * Once we get to that situation, protect the system's working + * set from being evicted by disabling active file page aging. + * + * This uses a different ratio than the anonymous pages, because + * the page cache uses a use-once replacement algorithm. + */ +static int inactive_file_is_low(struct zone *zone, struct scan_control *sc) +{ + int low; + + if (scanning_global_lru(sc)) + low = inactive_file_is_low_global(zone); + else + low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup); + return low; +} + static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct zone *zone, struct scan_control *sc, int priority) { int file = is_file_lru(lru); - if (lru == LRU_ACTIVE_FILE) { + if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) { shrink_active_list(nr_to_scan, zone, sc, priority, file); return 0; } @@ -1384,13 +1422,6 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc, unsigned long ap, fp; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc); - /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || (nr_swap_pages <= 0)) { - percent[0] = 0; - percent[1] = 100; - return; - } - anon = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) + zone_nr_pages(zone, sc, LRU_INACTIVE_ANON); file = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) + @@ -1400,7 +1431,7 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc, free = zone_page_state(zone, NR_FREE_PAGES); /* If we have very few page cache pages, force-scan anon pages. */ - if (unlikely(file + free <= zone->pages_high)) { + if (unlikely(file + free <= high_wmark_pages(zone))) { percent[0] = 100; percent[1] = 0; return; @@ -1455,6 +1486,26 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc, percent[1] = 100 - percent[0]; } +/* + * Smallish @nr_to_scan's are deposited in @nr_saved_scan, + * until we collected @swap_cluster_max pages to scan. + */ +static unsigned long nr_scan_try_batch(unsigned long nr_to_scan, + unsigned long *nr_saved_scan, + unsigned long swap_cluster_max) +{ + unsigned long nr; + + *nr_saved_scan += nr_to_scan; + nr = *nr_saved_scan; + + if (nr >= swap_cluster_max) + *nr_saved_scan = 0; + else + nr = 0; + + return nr; +} /* * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. @@ -1468,26 +1519,30 @@ static void shrink_zone(int priority, struct zone *zone, enum lru_list l; unsigned long nr_reclaimed = sc->nr_reclaimed; unsigned long swap_cluster_max = sc->swap_cluster_max; + int noswap = 0; - get_scan_ratio(zone, sc, percent); + /* If we have no swap space, do not bother scanning anon pages. */ + if (!sc->may_swap || (nr_swap_pages <= 0)) { + noswap = 1; + percent[0] = 0; + percent[1] = 100; + } else + get_scan_ratio(zone, sc, percent); for_each_evictable_lru(l) { int file = is_file_lru(l); unsigned long scan; scan = zone_nr_pages(zone, sc, l); - if (priority) { + if (priority || noswap) { scan >>= priority; scan = (scan * percent[file]) / 100; } - if (scanning_global_lru(sc)) { - zone->lru[l].nr_scan += scan; - nr[l] = zone->lru[l].nr_scan; - if (nr[l] >= swap_cluster_max) - zone->lru[l].nr_scan = 0; - else - nr[l] = 0; - } else + if (scanning_global_lru(sc)) + nr[l] = nr_scan_try_batch(scan, + &zone->lru[l].nr_saved_scan, + swap_cluster_max); + else nr[l] = scan; } @@ -1521,7 +1576,7 @@ static void shrink_zone(int priority, struct zone *zone, * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (inactive_anon_is_low(zone, sc)) + if (inactive_anon_is_low(zone, sc) && nr_swap_pages > 0) shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0); throttle_vm_writeout(sc->gfp_mask); @@ -1532,11 +1587,13 @@ static void shrink_zone(int priority, struct zone *zone, * try to reclaim pages from zones which will satisfy the caller's allocation * request. * - * We reclaim from a zone even if that zone is over pages_high. Because: + * We reclaim from a zone even if that zone is over high_wmark_pages(zone). + * Because: * a) The caller may be trying to free *extra* pages to satisfy a higher-order * allocation or - * b) The zones may be over pages_high but they must go *over* pages_high to - * satisfy the `incremental min' zone defense algorithm. + * b) The target zone may be at high_wmark_pages(zone) but the lower zones + * must go *over* high_wmark_pages(zone) to satisfy the `incremental min' + * zone defense algorithm. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. @@ -1742,7 +1799,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, /* * For kswapd, balance_pgdat() will work across all this node's zones until - * they are all at pages_high. + * they are all at high_wmark_pages(zone). * * Returns the number of pages which were actually freed. * @@ -1755,11 +1812,11 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont, * the zone for when the problem goes away. * * kswapd scans the zones in the highmem->normal->dma direction. It skips - * zones which have free_pages > pages_high, but once a zone is found to have - * free_pages <= pages_high, we scan that zone and the lower zones regardless - * of the number of free pages in the lower zones. This interoperates with - * the page allocator fallback scheme to ensure that aging of pages is balanced - * across the zones. + * zones which have free_pages > high_wmark_pages(zone), but once a zone is + * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the + * lower zones regardless of the number of free pages in the lower zones. This + * interoperates with the page allocator fallback scheme to ensure that aging + * of pages is balanced across the zones. */ static unsigned long balance_pgdat(pg_data_t *pgdat, int order) { @@ -1780,7 +1837,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order) }; /* * temp_priority is used to remember the scanning priority at which - * this zone was successfully refilled to free_pages == pages_high. + * this zone was successfully refilled to + * free_pages == high_wmark_pages(zone). */ int temp_priority[MAX_NR_ZONES]; @@ -1825,8 +1883,8 @@ loop_again: shrink_active_list(SWAP_CLUSTER_MAX, zone, &sc, priority, 0); - if (!zone_watermark_ok(zone, order, zone->pages_high, - 0, 0)) { + if (!zone_watermark_ok(zone, order, + high_wmark_pages(zone), 0, 0)) { end_zone = i; break; } @@ -1860,8 +1918,8 @@ loop_again: priority != DEF_PRIORITY) continue; - if (!zone_watermark_ok(zone, order, zone->pages_high, - end_zone, 0)) + if (!zone_watermark_ok(zone, order, + high_wmark_pages(zone), end_zone, 0)) all_zones_ok = 0; temp_priority[i] = priority; sc.nr_scanned = 0; @@ -1870,8 +1928,8 @@ loop_again: * We put equal pressure on every zone, unless one * zone has way too many pages free already. */ - if (!zone_watermark_ok(zone, order, 8*zone->pages_high, - end_zone, 0)) + if (!zone_watermark_ok(zone, order, + 8*high_wmark_pages(zone), end_zone, 0)) shrink_zone(priority, zone, &sc); reclaim_state->reclaimed_slab = 0; nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL, @@ -2037,7 +2095,7 @@ void wakeup_kswapd(struct zone *zone, int order) return; pgdat = zone->zone_pgdat; - if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0)) + if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0)) return; if (pgdat->kswapd_max_order < order) pgdat->kswapd_max_order = order; @@ -2084,11 +2142,11 @@ static void shrink_all_zones(unsigned long nr_pages, int prio, l == LRU_ACTIVE_FILE)) continue; - zone->lru[l].nr_scan += (lru_pages >> prio) + 1; - if (zone->lru[l].nr_scan >= nr_pages || pass > 3) { + zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1; + if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) { unsigned long nr_to_scan; - zone->lru[l].nr_scan = 0; + zone->lru[l].nr_saved_scan = 0; nr_to_scan = min(nr_pages, lru_pages); nr_reclaimed += shrink_list(l, nr_to_scan, zone, sc, prio); @@ -2290,6 +2348,48 @@ int sysctl_min_unmapped_ratio = 1; */ int sysctl_min_slab_ratio = 5; +static inline unsigned long zone_unmapped_file_pages(struct zone *zone) +{ + unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED); + unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) + + zone_page_state(zone, NR_ACTIVE_FILE); + + /* + * It's possible for there to be more file mapped pages than + * accounted for by the pages on the file LRU lists because + * tmpfs pages accounted for as ANON can also be FILE_MAPPED + */ + return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; +} + +/* Work out how many page cache pages we can reclaim in this reclaim_mode */ +static long zone_pagecache_reclaimable(struct zone *zone) +{ + long nr_pagecache_reclaimable; + long delta = 0; + + /* + * If RECLAIM_SWAP is set, then all file pages are considered + * potentially reclaimable. Otherwise, we have to worry about + * pages like swapcache and zone_unmapped_file_pages() provides + * a better estimate + */ + if (zone_reclaim_mode & RECLAIM_SWAP) + nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES); + else + nr_pagecache_reclaimable = zone_unmapped_file_pages(zone); + + /* If we can't clean pages, remove dirty pages from consideration */ + if (!(zone_reclaim_mode & RECLAIM_WRITE)) + delta += zone_page_state(zone, NR_FILE_DIRTY); + + /* Watch for any possible underflows due to delta */ + if (unlikely(delta > nr_pagecache_reclaimable)) + delta = nr_pagecache_reclaimable; + + return nr_pagecache_reclaimable - delta; +} + /* * Try to free up some pages from this zone through reclaim. */ @@ -2324,9 +2424,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - if (zone_page_state(zone, NR_FILE_PAGES) - - zone_page_state(zone, NR_FILE_MAPPED) > - zone->min_unmapped_pages) { + if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) { /* * Free memory by calling shrink zone with increasing * priorities until we have enough memory freed. @@ -2384,20 +2482,18 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * if less than a specified percentage of the zone is used by * unmapped file backed pages. */ - if (zone_page_state(zone, NR_FILE_PAGES) - - zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages - && zone_page_state(zone, NR_SLAB_RECLAIMABLE) - <= zone->min_slab_pages) - return 0; + if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages && + zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages) + return ZONE_RECLAIM_FULL; if (zone_is_all_unreclaimable(zone)) - return 0; + return ZONE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC)) - return 0; + return ZONE_RECLAIM_NOSCAN; /* * Only run zone reclaim on the local zone or on zones that do not @@ -2407,18 +2503,21 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) */ node_id = zone_to_nid(zone); if (node_state(node_id, N_CPU) && node_id != numa_node_id()) - return 0; + return ZONE_RECLAIM_NOSCAN; if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED)) - return 0; + return ZONE_RECLAIM_NOSCAN; + ret = __zone_reclaim(zone, gfp_mask, order); zone_clear_flag(zone, ZONE_RECLAIM_LOCKED); + if (!ret) + count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); + return ret; } #endif -#ifdef CONFIG_UNEVICTABLE_LRU /* * page_evictable - test whether a page is evictable * @page: the page to test @@ -2665,4 +2764,3 @@ void scan_unevictable_unregister_node(struct node *node) sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages); } -#endif diff --git a/mm/vmstat.c b/mm/vmstat.c index 74d66dba0cb..138bed53706 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -629,10 +629,8 @@ static const char * const vmstat_text[] = { "nr_active_anon", "nr_inactive_file", "nr_active_file", -#ifdef CONFIG_UNEVICTABLE_LRU "nr_unevictable", "nr_mlock", -#endif "nr_anon_pages", "nr_mapped", "nr_file_pages", @@ -675,6 +673,9 @@ static const char * const vmstat_text[] = { TEXTS_FOR_ZONES("pgscan_kswapd") TEXTS_FOR_ZONES("pgscan_direct") +#ifdef CONFIG_NUMA + "zone_reclaim_failed", +#endif "pginodesteal", "slabs_scanned", "kswapd_steal", @@ -687,7 +688,6 @@ static const char * const vmstat_text[] = { "htlb_buddy_alloc_success", "htlb_buddy_alloc_fail", #endif -#ifdef CONFIG_UNEVICTABLE_LRU "unevictable_pgs_culled", "unevictable_pgs_scanned", "unevictable_pgs_rescued", @@ -697,7 +697,6 @@ static const char * const vmstat_text[] = { "unevictable_pgs_stranded", "unevictable_pgs_mlockfreed", #endif -#endif }; static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, @@ -710,18 +709,14 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n min %lu" "\n low %lu" "\n high %lu" - "\n scanned %lu (aa: %lu ia: %lu af: %lu if: %lu)" + "\n scanned %lu" "\n spanned %lu" "\n present %lu", zone_page_state(zone, NR_FREE_PAGES), - zone->pages_min, - zone->pages_low, - zone->pages_high, + min_wmark_pages(zone), + low_wmark_pages(zone), + high_wmark_pages(zone), zone->pages_scanned, - zone->lru[LRU_ACTIVE_ANON].nr_scan, - zone->lru[LRU_INACTIVE_ANON].nr_scan, - zone->lru[LRU_ACTIVE_FILE].nr_scan, - zone->lru[LRU_INACTIVE_FILE].nr_scan, zone->spanned_pages, zone->present_pages); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 8847add6ca1..5ed8931dfe9 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -124,7 +124,7 @@ svc_pool_map_choose_mode(void) { unsigned int node; - if (num_online_nodes() > 1) { + if (nr_online_nodes > 1) { /* * Actually have multiple NUMA nodes, * so split pools on NUMA node boundaries diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 60dc0c48c92..3e733146cd5 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -13,7 +13,7 @@ use strict; my $P = $0; -my $V = '0.15'; +my $V = '0.16'; use Getopt::Long qw(:config no_auto_abbrev); @@ -55,6 +55,10 @@ foreach my $chief (@penguin_chief) { } my $penguin_chiefs = "\(" . join("|",@penguin_chief_names) . "\)"; +# rfc822 email address - preloaded methods go here. +my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])"; +my $rfc822_char = '[\\000-\\377]'; + if (!GetOptions( 'email!' => \$email, 'git!' => \$email_git, @@ -161,7 +165,7 @@ foreach my $file (@ARGV) { } close(PATCH); if ($file_cnt == @files) { - die "$P: file '${file}' doesn't appear to be a patch. " + warn "$P: file '${file}' doesn't appear to be a patch. " . "Add -f to options?\n"; } @files = sort_and_uniq(@files); @@ -169,6 +173,7 @@ foreach my $file (@ARGV) { } my @email_to = (); +my @list_to = (); my @scm = (); my @web = (); my @subsystem = (); @@ -182,7 +187,7 @@ foreach my $file (@files) { my $exclude = 0; foreach my $line (@typevalue) { - if ($line =~ m/^(\C):(.*)/) { + if ($line =~ m/^(\C):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'X') { @@ -196,7 +201,7 @@ foreach my $file (@files) { if (!$exclude) { my $tvi = 0; foreach my $line (@typevalue) { - if ($line =~ m/^(\C):(.*)/) { + if ($line =~ m/^(\C):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'F') { @@ -215,29 +220,33 @@ foreach my $file (@files) { } -if ($email_git_penguin_chiefs) { +if ($email) { foreach my $chief (@penguin_chief) { if ($chief =~ m/^(.*):(.*)/) { - my $chief_name = $1; - my $chief_addr = $2; + my $email_address; if ($email_usename) { - push(@email_to, format_email($chief_name, $chief_addr)); + $email_address = format_email($1, $2); + } else { + $email_address = $2; + } + if ($email_git_penguin_chiefs) { + push(@email_to, $email_address); } else { - push(@email_to, $chief_addr); + @email_to = grep(!/${email_address}/, @email_to); } } } } -if ($email) { - my $address_cnt = @email_to; - if ($address_cnt == 0 && $email_list) { - push(@email_to, "linux-kernel\@vger.kernel.org"); +if ($email || $email_list) { + my @to = (); + if ($email) { + @to = (@to, @email_to); } - -#Don't sort email address list, but do remove duplicates - @email_to = uniq(@email_to); - output(@email_to); + if ($email_list) { + @to = (@to, @list_to); + } + output(uniq(@to)); } if ($scm) { @@ -307,10 +316,10 @@ Output type options: --multiline => print 1 entry per line Default options: - [--email --git --m --l --multiline] + [--email --git --m --n --l --multiline] Other options: - --version -> show version + --version => show version --help => show this help information EOT @@ -347,6 +356,7 @@ sub format_email { my ($name, $email) = @_; $name =~ s/^\s+|\s+$//g; + $name =~ s/^\"|\"$//g; $email =~ s/^\s+|\s+$//g; my $formatted_email = ""; @@ -366,36 +376,41 @@ sub add_categories { $index = $index - 1; while ($index >= 0) { my $tv = $typevalue[$index]; - if ($tv =~ m/^(\C):(.*)/) { + if ($tv =~ m/^(\C):\s*(.*)/) { my $ptype = $1; my $pvalue = $2; if ($ptype eq "L") { - my $subscr = $pvalue; - if ($subscr =~ m/\s*\(subscribers-only\)/) { + my $list_address = $pvalue; + my $list_additional = ""; + if ($list_address =~ m/([^\s]+)\s+(.*)$/) { + $list_address = $1; + $list_additional = $2; + } + if ($list_additional =~ m/subscribers-only/) { if ($email_subscriber_list) { - $subscr =~ s/\s*\(subscribers-only\)//g; - push(@email_to, $subscr); + push(@list_to, $list_address); } } else { if ($email_list) { - push(@email_to, $pvalue); + push(@list_to, $list_address); } } } elsif ($ptype eq "M") { - if ($email_maintainer) { - if ($index >= 0) { - my $tv = $typevalue[$index - 1]; - if ($tv =~ m/^(\C):(.*)/) { - if ($1 eq "P" && $email_usename) { - push(@email_to, format_email($2, $pvalue)); - } else { - push(@email_to, $pvalue); + my $p_used = 0; + if ($index >= 0) { + my $tv = $typevalue[$index - 1]; + if ($tv =~ m/^(\C):\s*(.*)/) { + if ($1 eq "P") { + if ($email_usename) { + push_email_address(format_email($2, $pvalue)); + $p_used = 1; } } - } else { - push(@email_to, $pvalue); } } + if (!$p_used) { + push_email_addresses($pvalue); + } } elsif ($ptype eq "T") { push(@scm, $pvalue); } elsif ($ptype eq "W") { @@ -412,10 +427,45 @@ sub add_categories { } } +sub push_email_address { + my ($email_address) = @_; + + my $email_name = ""; + if ($email_address =~ m/([^<]+)<(.*\@.*)>$/) { + $email_name = $1; + $email_address = $2; + } + + if ($email_maintainer) { + if ($email_usename && $email_name) { + push(@email_to, format_email($email_name, $email_address)); + } else { + push(@email_to, $email_address); + } + } +} + +sub push_email_addresses { + my ($address) = @_; + + my @address_list = (); + + if (rfc822_valid($address)) { + push_email_address($address); + } elsif (@address_list = rfc822_validlist($address)) { + my $array_count = shift(@address_list); + while (my $entry = shift(@address_list)) { + push_email_address($entry); + } + } else { + warn("Invalid MAINTAINERS address: '" . $address . "'\n"); + } +} + sub which { my ($bin) = @_; - foreach my $path (split /:/, $ENV{PATH}) { + foreach my $path (split(/:/, $ENV{PATH})) { if (-e "$path/$bin") { return "$path/$bin"; } @@ -434,16 +484,21 @@ sub recent_git_signoffs { my @lines = (); if (which("git") eq "") { - die("$P: git not found. Add --nogit to options?\n"); + warn("$P: git not found. Add --nogit to options?\n"); + return; + } + if (!(-d ".git")) { + warn("$P: .git directory not found. Use a git repository for better results.\n"); + warn("$P: perhaps 'git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git'\n"); + return; } $cmd = "git log --since=${email_git_since} -- ${file}"; - $cmd .= " | grep -Pi \"^[-_ a-z]+by:.*\\\@\""; + $cmd .= " | grep -Ei \"^[-_ a-z]+by:.*\\\@.*\$\""; if (!$email_git_penguin_chiefs) { - $cmd .= " | grep -Pv \"${penguin_chiefs}\""; + $cmd .= " | grep -Ev \"${penguin_chiefs}\""; } $cmd .= " | cut -f2- -d\":\""; - $cmd .= " | sed -e \"s/^\\s+//g\""; $cmd .= " | sort | uniq -c | sort -rn"; $output = `${cmd}`; @@ -465,10 +520,6 @@ sub recent_git_signoffs { if ($line =~ m/(.+)<(.+)>/) { my $git_name = $1; my $git_addr = $2; - $git_name =~ tr/^\"//; - $git_name =~ tr/^\\s*//; - $git_name =~ tr/\"$//; - $git_name =~ tr/\\s*$//; if ($email_usename) { push(@email_to, format_email($git_name, $git_addr)); } else { @@ -481,7 +532,6 @@ sub recent_git_signoffs { push(@email_to, $line); } } - return $output; } sub uniq { @@ -513,3 +563,97 @@ sub output { print("\n"); } } + +my $rfc822re; + +sub make_rfc822re { +# Basic lexical tokens are specials, domain_literal, quoted_string, atom, and +# comment. We must allow for rfc822_lwsp (or comments) after each of these. +# This regexp will only work on addresses which have had comments stripped +# and replaced with rfc822_lwsp. + + my $specials = '()<>@,;:\\\\".\\[\\]'; + my $controls = '\\000-\\037\\177'; + + my $dtext = "[^\\[\\]\\r\\\\]"; + my $domain_literal = "\\[(?:$dtext|\\\\.)*\\]$rfc822_lwsp*"; + + my $quoted_string = "\"(?:[^\\\"\\r\\\\]|\\\\.|$rfc822_lwsp)*\"$rfc822_lwsp*"; + +# Use zero-width assertion to spot the limit of an atom. A simple +# $rfc822_lwsp* causes the regexp engine to hang occasionally. + my $atom = "[^$specials $controls]+(?:$rfc822_lwsp+|\\Z|(?=[\\[\"$specials]))"; + my $word = "(?:$atom|$quoted_string)"; + my $localpart = "$word(?:\\.$rfc822_lwsp*$word)*"; + + my $sub_domain = "(?:$atom|$domain_literal)"; + my $domain = "$sub_domain(?:\\.$rfc822_lwsp*$sub_domain)*"; + + my $addr_spec = "$localpart\@$rfc822_lwsp*$domain"; + + my $phrase = "$word*"; + my $route = "(?:\@$domain(?:,\@$rfc822_lwsp*$domain)*:$rfc822_lwsp*)"; + my $route_addr = "\\<$rfc822_lwsp*$route?$addr_spec\\>$rfc822_lwsp*"; + my $mailbox = "(?:$addr_spec|$phrase$route_addr)"; + + my $group = "$phrase:$rfc822_lwsp*(?:$mailbox(?:,\\s*$mailbox)*)?;\\s*"; + my $address = "(?:$mailbox|$group)"; + + return "$rfc822_lwsp*$address"; +} + +sub rfc822_strip_comments { + my $s = shift; +# Recursively remove comments, and replace with a single space. The simpler +# regexps in the Email Addressing FAQ are imperfect - they will miss escaped +# chars in atoms, for example. + + while ($s =~ s/^((?:[^"\\]|\\.)* + (?:"(?:[^"\\]|\\.)*"(?:[^"\\]|\\.)*)*) + \((?:[^()\\]|\\.)*\)/$1 /osx) {} + return $s; +} + +# valid: returns true if the parameter is an RFC822 valid address +# +sub rfc822_valid ($) { + my $s = rfc822_strip_comments(shift); + + if (!$rfc822re) { + $rfc822re = make_rfc822re(); + } + + return $s =~ m/^$rfc822re$/so && $s =~ m/^$rfc822_char*$/; +} + +# validlist: In scalar context, returns true if the parameter is an RFC822 +# valid list of addresses. +# +# In list context, returns an empty list on failure (an invalid +# address was found); otherwise a list whose first element is the +# number of addresses found and whose remaining elements are the +# addresses. This is needed to disambiguate failure (invalid) +# from success with no addresses found, because an empty string is +# a valid list. + +sub rfc822_validlist ($) { + my $s = rfc822_strip_comments(shift); + + if (!$rfc822re) { + $rfc822re = make_rfc822re(); + } + # * null list items are valid according to the RFC + # * the '1' business is to aid in distinguishing failure from no results + + my @r; + if ($s =~ m/^(?:$rfc822re)?(?:,(?:$rfc822re)?)*$/so && + $s =~ m/^$rfc822_char*$/) { + while ($s =~ m/(?:^|,$rfc822_lwsp*)($rfc822re)/gos) { + push @r, $1; + } + return wantarray ? (scalar(@r), @r) : 1; + } + else { + return wantarray ? () : 0; + } +} diff --git a/scripts/gfp-translate b/scripts/gfp-translate new file mode 100644 index 00000000000..073cb6d152a --- /dev/null +++ b/scripts/gfp-translate @@ -0,0 +1,81 @@ +#!/bin/bash +# Translate the bits making up a GFP mask +# (c) 2009, Mel Gorman <mel@csn.ul.ie> +# Licensed under the terms of the GNU GPL License version 2 +SOURCE= +GFPMASK=none + +# Helper function to report failures and exit +die() { + echo ERROR: $@ + if [ "$TMPFILE" != "" ]; then + rm -f $TMPFILE + fi + exit -1 +} + +usage() { + echo "usage: gfp-translate [-h] [ --source DIRECTORY ] gfpmask" + exit 0 +} + +# Parse command-line arguements +while [ $# -gt 0 ]; do + case $1 in + --source) + SOURCE=$2 + shift 2 + ;; + -h) + usage + ;; + --help) + usage + ;; + *) + GFPMASK=$1 + shift + ;; + esac +done + +# Guess the kernel source directory if it's not set. Preference is in order of +# o current directory +# o /usr/src/linux +if [ "$SOURCE" = "" ]; then + if [ -r "/usr/src/linux/Makefile" ]; then + SOURCE=/usr/src/linux + fi + if [ -r "`pwd`/Makefile" ]; then + SOURCE=`pwd` + fi +fi + +# Confirm that a source directory exists +if [ ! -r "$SOURCE/Makefile" ]; then + die "Could not locate kernel source directory or it is invalid" +fi + +# Confirm that a GFP mask has been specified +if [ "$GFPMASK" = "none" ]; then + usage +fi + +# Extract GFP flags from the kernel source +TMPFILE=`mktemp -t gfptranslate-XXXXXX` || exit 1 +grep "^#define __GFP" $SOURCE/include/linux/gfp.h | sed -e 's/(__force gfp_t)//' | sed -e 's/u)/)/' | grep -v GFP_BITS | sed -e 's/)\//) \//' > $TMPFILE + +# Parse the flags +IFS=" +" +echo Source: $SOURCE +echo Parsing: $GFPMASK +for LINE in `cat $TMPFILE`; do + MASK=`echo $LINE | awk '{print $3}'` + if [ $(($GFPMASK&$MASK)) -ne 0 ]; then + echo $LINE + fi +done + +rm -f $TMPFILE +exit 0 diff --git a/scripts/pnmtologo.c b/scripts/pnmtologo.c index 6aa2a2483f8..64f5ddb09ea 100644 --- a/scripts/pnmtologo.c +++ b/scripts/pnmtologo.c @@ -237,22 +237,22 @@ static void write_header(void) fprintf(out, " * Linux logo %s\n", logoname); fputs(" */\n\n", out); fputs("#include <linux/linux_logo.h>\n\n", out); - fprintf(out, "static unsigned char %s_data[] __initdata = {\n", + fprintf(out, "static const unsigned char %s_data[] __initconst = {\n", logoname); } static void write_footer(void) { fputs("\n};\n\n", out); - fprintf(out, "struct linux_logo %s __initdata = {\n", logoname); - fprintf(out, " .type\t= %s,\n", logo_types[logo_type]); - fprintf(out, " .width\t= %d,\n", logo_width); - fprintf(out, " .height\t= %d,\n", logo_height); + fprintf(out, "const struct linux_logo %s __initconst = {\n", logoname); + fprintf(out, "\t.type\t\t= %s,\n", logo_types[logo_type]); + fprintf(out, "\t.width\t\t= %d,\n", logo_width); + fprintf(out, "\t.height\t\t= %d,\n", logo_height); if (logo_type == LINUX_LOGO_CLUT224) { - fprintf(out, " .clutsize\t= %d,\n", logo_clutsize); - fprintf(out, " .clut\t= %s_clut,\n", logoname); + fprintf(out, "\t.clutsize\t= %d,\n", logo_clutsize); + fprintf(out, "\t.clut\t\t= %s_clut,\n", logoname); } - fprintf(out, " .data\t= %s_data\n", logoname); + fprintf(out, "\t.data\t\t= %s_data\n", logoname); fputs("};\n\n", out); /* close logo file */ @@ -374,7 +374,7 @@ static void write_logo_clut224(void) fputs("\n};\n\n", out); /* write logo clut */ - fprintf(out, "static unsigned char %s_clut[] __initdata = {\n", + fprintf(out, "static const unsigned char %s_clut[] __initconst = {\n", logoname); write_hex_cnt = 0; for (i = 0; i < logo_clutsize; i++) { diff --git a/sound/drivers/pcsp/pcsp.h b/sound/drivers/pcsp/pcsp.h index cdef2664218..174dd2ff0f2 100644 --- a/sound/drivers/pcsp/pcsp.h +++ b/sound/drivers/pcsp/pcsp.h @@ -10,6 +10,7 @@ #define __PCSP_H__ #include <linux/hrtimer.h> +#include <linux/timex.h> #if defined(CONFIG_MIPS) || defined(CONFIG_X86) /* Use the global PIT lock ! */ #include <asm/i8253.h> diff --git a/sound/oss/pas2_pcm.c b/sound/oss/pas2_pcm.c index 36c3ea62086..8f7d175767a 100644 --- a/sound/oss/pas2_pcm.c +++ b/sound/oss/pas2_pcm.c @@ -17,7 +17,7 @@ #include <linux/init.h> #include <linux/spinlock.h> -#include <asm/timex.h> +#include <linux/timex.h> #include "sound_config.h" #include "pas2.h" |