From c3811711a6fd3965bfd8c782fa5c014aecaeeffc Mon Sep 17 00:00:00 2001 From: Loc Ho Date: Fri, 6 Jun 2014 14:35:40 -0700 Subject: Documentation/devicetree/bindings: add documentation for the APM X-Gene SoC RTC DTS binding Signed-off-by: Rameshwar Prasad Sahu Signed-off-by: Loc Ho Cc: Jon Masters Cc: Alessandro Zummo Cc: Catalin Marinas Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../devicetree/bindings/rtc/xgene-rtc.txt | 28 ++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 Documentation/devicetree/bindings/rtc/xgene-rtc.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/rtc/xgene-rtc.txt b/Documentation/devicetree/bindings/rtc/xgene-rtc.txt new file mode 100644 index 000000000000..fd195c358446 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/xgene-rtc.txt @@ -0,0 +1,28 @@ +* APM X-Gene Real Time Clock + +RTC controller for the APM X-Gene Real Time Clock + +Required properties: +- compatible : Should be "apm,xgene-rtc" +- reg: physical base address of the controller and length of memory mapped + region. +- interrupts: IRQ line for the RTC. +- #clock-cells: Should be 1. +- clocks: Reference to the clock entry. + +Example: + +rtcclk: rtcclk { + compatible = "fixed-clock"; + #clock-cells = <1>; + clock-frequency = <100000000>; + clock-output-names = "rtcclk"; +}; + +rtc: rtc@10510000 { + compatible = "apm,xgene-rtc"; + reg = <0x0 0x10510000 0x0 0x400>; + interrupts = <0x0 0x46 0x4>; + #clock-cells = <1>; + clocks = <&rtcclk 0>; +}; -- cgit v1.2.3 From 68164a73b1055191975419f5da7180294902f461 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Fri, 6 Jun 2014 14:36:08 -0700 Subject: drivers/rtc/rtc-hym8563.c: add optional clock-output-names property This enables the setting of a custom clock name for the clock provided by the hym8563 rtc. Signed-off-by: Heiko Stuebner Reviewed-by: Mike Turquette Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/devicetree/bindings/rtc/haoyu,hym8563.txt | 3 +++ drivers/rtc/rtc-hym8563.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/rtc/haoyu,hym8563.txt b/Documentation/devicetree/bindings/rtc/haoyu,hym8563.txt index 31406fd4a43e..5c199ee044cb 100644 --- a/Documentation/devicetree/bindings/rtc/haoyu,hym8563.txt +++ b/Documentation/devicetree/bindings/rtc/haoyu,hym8563.txt @@ -9,6 +9,9 @@ Required properties: - interrupts: rtc alarm/event interrupt - #clock-cells: the value should be 0 +Optional properties: +- clock-output-names: From common clock binding + Example: hym8563: hym8563@51 { diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c index e3290abbb03e..b936bb4096b5 100644 --- a/drivers/rtc/rtc-hym8563.c +++ b/drivers/rtc/rtc-hym8563.c @@ -418,6 +418,9 @@ static struct clk *hym8563_clkout_register_clk(struct hym8563 *hym8563) init.num_parents = 0; hym8563->clkout_hw.init = &init; + /* optional override of the clockname */ + of_property_read_string(node, "clock-output-names", &init.name); + /* register the clock */ clk = clk_register(&client->dev, &hym8563->clkout_hw); -- cgit v1.2.3 From 190a8843ded231638d0e7ae7d8ca6a712472d114 Mon Sep 17 00:00:00 2001 From: Conrad Meyer Date: Fri, 6 Jun 2014 14:36:37 -0700 Subject: fs/fat/: add support for DOS 1.x formatted volumes Add structure for parsed BPB information, struct fat_bios_param_block, and move all of the deserialization and validation logic from fat_fill_super() into fat_read_bpb(). Add a 'dos1xfloppy' mount option to infer DOS 2.x BIOS Parameter Block defaults from block device geometry for ancient floppies and floppy images, as a fall-back from the default BPB parsing logic. When fat_read_bpb() finds an invalid FAT filesystem and dos1xfloppy is set, fall back to fat_read_static_bpb(). fat_read_static_bpb() validates that the entire BPB is zero, and that the floppy has a DOS-style 8086 code bootstrapping header. Then it fills in default BPB values from media size and a table.[0] Media size is assumed to be static for archaic FAT volumes. See also: [1]. Fixes kernel.org bug #42617. [0]: https://en.wikipedia.org/wiki/File_Allocation_Table#Exceptions [1]: http://www.win.tue.nl/~aeb/linux/fs/fat/fat-1.html [hirofumi@mail.parknet.co.jp: fix missed error code] Signed-off-by: Conrad Meyer Acked-by: OGAWA Hirofumi Signed-off-by: OGAWA Hirofumi Tested-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/vfat.txt | 5 + fs/fat/fat.h | 3 +- fs/fat/inode.c | 343 +++++++++++++++++++++++++++++-------- 3 files changed, 274 insertions(+), 77 deletions(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt index 4a93e98b290a..ce1126aceed8 100644 --- a/Documentation/filesystems/vfat.txt +++ b/Documentation/filesystems/vfat.txt @@ -172,6 +172,11 @@ nfs=stale_rw|nostale_ro To maintain backward compatibility, '-o nfs' is also accepted, defaulting to stale_rw +dos1xfloppy -- If set, use a fallback default BIOS Parameter Block + configuration, determined by backing device size. These static + parameters match defaults assumed by DOS 1.x for 160 kiB, + 180 kiB, 320 kiB, and 360 kiB floppies and floppy images. + : 0,1,yes,no,true,false diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 7c31f4bc74a9..e0c4ba39a377 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -52,7 +52,8 @@ struct fat_mount_options { usefree:1, /* Use free_clusters for FAT32 */ tz_set:1, /* Filesystem timestamps' offset set */ rodir:1, /* allow ATTR_RO for directory */ - discard:1; /* Issue discard requests on deletions */ + discard:1, /* Issue discard requests on deletions */ + dos1xfloppy:1; /* Assume default BPB for DOS 1.x floppies */ }; #define FAT_HASH_BITS 8 diff --git a/fs/fat/inode.c b/fs/fat/inode.c index b3361fe2bcb5..babff0f40696 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -35,9 +35,71 @@ #define CONFIG_FAT_DEFAULT_IOCHARSET "" #endif +#define KB_IN_SECTORS 2 + +/* + * A deserialized copy of the on-disk structure laid out in struct + * fat_boot_sector. + */ +struct fat_bios_param_block { + u16 fat_sector_size; + u8 fat_sec_per_clus; + u16 fat_reserved; + u8 fat_fats; + u16 fat_dir_entries; + u16 fat_sectors; + u16 fat_fat_length; + u32 fat_total_sect; + + u8 fat16_state; + u32 fat16_vol_id; + + u32 fat32_length; + u32 fat32_root_cluster; + u16 fat32_info_sector; + u8 fat32_state; + u32 fat32_vol_id; +}; + static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE; static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET; +static struct fat_floppy_defaults { + unsigned nr_sectors; + unsigned sec_per_clus; + unsigned dir_entries; + unsigned media; + unsigned fat_length; +} floppy_defaults[] = { +{ + .nr_sectors = 160 * KB_IN_SECTORS, + .sec_per_clus = 1, + .dir_entries = 64, + .media = 0xFE, + .fat_length = 1, +}, +{ + .nr_sectors = 180 * KB_IN_SECTORS, + .sec_per_clus = 1, + .dir_entries = 64, + .media = 0xFC, + .fat_length = 2, +}, +{ + .nr_sectors = 320 * KB_IN_SECTORS, + .sec_per_clus = 2, + .dir_entries = 112, + .media = 0xFF, + .fat_length = 1, +}, +{ + .nr_sectors = 360 * KB_IN_SECTORS, + .sec_per_clus = 2, + .dir_entries = 112, + .media = 0xFD, + .fat_length = 2, +}, +}; static int fat_add_cluster(struct inode *inode) { @@ -853,6 +915,8 @@ static int fat_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",nfs=stale_rw"); if (opts->discard) seq_puts(m, ",discard"); + if (opts->dos1xfloppy) + seq_puts(m, ",dos1xfloppy"); return 0; } @@ -867,7 +931,7 @@ enum { Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes, Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont, Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset, - Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err, + Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err, Opt_dos1xfloppy, }; static const match_table_t fat_tokens = { @@ -900,6 +964,7 @@ static const match_table_t fat_tokens = { {Opt_nfs_stale_rw, "nfs"}, {Opt_nfs_stale_rw, "nfs=stale_rw"}, {Opt_nfs_nostale_ro, "nfs=nostale_ro"}, + {Opt_dos1xfloppy, "dos1xfloppy"}, {Opt_obsolete, "conv=binary"}, {Opt_obsolete, "conv=text"}, {Opt_obsolete, "conv=auto"}, @@ -1102,6 +1167,9 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, case Opt_nfs_nostale_ro: opts->nfs = FAT_NFS_NOSTALE_RO; break; + case Opt_dos1xfloppy: + opts->dos1xfloppy = 1; + break; /* msdos specific */ case Opt_dots: @@ -1247,6 +1315,169 @@ static unsigned long calc_fat_clusters(struct super_block *sb) return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; } +static bool fat_bpb_is_zero(struct fat_boot_sector *b) +{ + if (get_unaligned_le16(&b->sector_size)) + return false; + if (b->sec_per_clus) + return false; + if (b->reserved) + return false; + if (b->fats) + return false; + if (get_unaligned_le16(&b->dir_entries)) + return false; + if (get_unaligned_le16(&b->sectors)) + return false; + if (b->media) + return false; + if (b->fat_length) + return false; + if (b->secs_track) + return false; + if (b->heads) + return false; + return true; +} + +static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b, + int silent, struct fat_bios_param_block *bpb) +{ + int error = -EINVAL; + + /* Read in BPB ... */ + memset(bpb, 0, sizeof(*bpb)); + bpb->fat_sector_size = get_unaligned_le16(&b->sector_size); + bpb->fat_sec_per_clus = b->sec_per_clus; + bpb->fat_reserved = le16_to_cpu(b->reserved); + bpb->fat_fats = b->fats; + bpb->fat_dir_entries = get_unaligned_le16(&b->dir_entries); + bpb->fat_sectors = get_unaligned_le16(&b->sectors); + bpb->fat_fat_length = le16_to_cpu(b->fat_length); + bpb->fat_total_sect = le32_to_cpu(b->total_sect); + + bpb->fat16_state = b->fat16.state; + bpb->fat16_vol_id = get_unaligned_le32(b->fat16.vol_id); + + bpb->fat32_length = le32_to_cpu(b->fat32.length); + bpb->fat32_root_cluster = le32_to_cpu(b->fat32.root_cluster); + bpb->fat32_info_sector = le16_to_cpu(b->fat32.info_sector); + bpb->fat32_state = b->fat32.state; + bpb->fat32_vol_id = get_unaligned_le32(b->fat32.vol_id); + + /* Validate this looks like a FAT filesystem BPB */ + if (!bpb->fat_reserved) { + if (!silent) + fat_msg(sb, KERN_ERR, + "bogus number of reserved sectors"); + goto out; + } + if (!bpb->fat_fats) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus number of FAT structure"); + goto out; + } + + /* + * Earlier we checked here that b->secs_track and b->head are nonzero, + * but it turns out valid FAT filesystems can have zero there. + */ + + if (!fat_valid_media(b->media)) { + if (!silent) + fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)", + (unsigned)b->media); + goto out; + } + + if (!is_power_of_2(bpb->fat_sector_size) + || (bpb->fat_sector_size < 512) + || (bpb->fat_sector_size > 4096)) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus logical sector size %u", + (unsigned)bpb->fat_sector_size); + goto out; + } + + if (!is_power_of_2(bpb->fat_sec_per_clus)) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u", + (unsigned)bpb->fat_sec_per_clus); + goto out; + } + + error = 0; + +out: + return error; +} + +static int fat_read_static_bpb(struct super_block *sb, + struct fat_boot_sector *b, int silent, + struct fat_bios_param_block *bpb) +{ + static const char *notdos1x = "This doesn't look like a DOS 1.x volume"; + + struct fat_floppy_defaults *fdefaults = NULL; + int error = -EINVAL; + sector_t bd_sects; + unsigned i; + + bd_sects = i_size_read(sb->s_bdev->bd_inode) / SECTOR_SIZE; + + /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */ + if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) { + if (!silent) + fat_msg(sb, KERN_ERR, + "%s; no bootstrapping code", notdos1x); + goto out; + } + + /* + * If any value in this region is non-zero, it isn't archaic + * DOS. + */ + if (!fat_bpb_is_zero(b)) { + if (!silent) + fat_msg(sb, KERN_ERR, + "%s; DOS 2.x BPB is non-zero", notdos1x); + goto out; + } + + for (i = 0; i < ARRAY_SIZE(floppy_defaults); i++) { + if (floppy_defaults[i].nr_sectors == bd_sects) { + fdefaults = &floppy_defaults[i]; + break; + } + } + + if (fdefaults == NULL) { + if (!silent) + fat_msg(sb, KERN_WARNING, + "This looks like a DOS 1.x volume, but isn't a recognized floppy size (%llu sectors)", + (u64)bd_sects); + goto out; + } + + if (!silent) + fat_msg(sb, KERN_INFO, + "This looks like a DOS 1.x volume; assuming default BPB values"); + + memset(bpb, 0, sizeof(*bpb)); + bpb->fat_sector_size = SECTOR_SIZE; + bpb->fat_sec_per_clus = fdefaults->sec_per_clus; + bpb->fat_reserved = 1; + bpb->fat_fats = 2; + bpb->fat_dir_entries = fdefaults->dir_entries; + bpb->fat_sectors = fdefaults->nr_sectors; + bpb->fat_fat_length = fdefaults->fat_length; + + error = 0; + +out: + return error; +} + /* * Read the super block of an MS-DOS FS. */ @@ -1256,12 +1487,11 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, struct inode *root_inode = NULL, *fat_inode = NULL; struct inode *fsinfo_inode = NULL; struct buffer_head *bh; - struct fat_boot_sector *b; + struct fat_bios_param_block bpb; struct msdos_sb_info *sbi; u16 logical_sector_size; u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors; int debug; - unsigned int media; long error; char buf[50]; @@ -1298,100 +1528,72 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, goto out_fail; } - b = (struct fat_boot_sector *) bh->b_data; - if (!b->reserved) { - if (!silent) - fat_msg(sb, KERN_ERR, "bogus number of reserved sectors"); - brelse(bh); - goto out_invalid; - } - if (!b->fats) { - if (!silent) - fat_msg(sb, KERN_ERR, "bogus number of FAT structure"); - brelse(bh); - goto out_invalid; - } - - /* - * Earlier we checked here that b->secs_track and b->head are nonzero, - * but it turns out valid FAT filesystems can have zero there. - */ + error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, + &bpb); + if (error == -EINVAL && sbi->options.dos1xfloppy) + error = fat_read_static_bpb(sb, + (struct fat_boot_sector *)bh->b_data, silent, &bpb); + brelse(bh); - media = b->media; - if (!fat_valid_media(media)) { - if (!silent) - fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)", - media); - brelse(bh); - goto out_invalid; - } - logical_sector_size = get_unaligned_le16(&b->sector_size); - if (!is_power_of_2(logical_sector_size) - || (logical_sector_size < 512) - || (logical_sector_size > 4096)) { - if (!silent) - fat_msg(sb, KERN_ERR, "bogus logical sector size %u", - logical_sector_size); - brelse(bh); - goto out_invalid; - } - sbi->sec_per_clus = b->sec_per_clus; - if (!is_power_of_2(sbi->sec_per_clus)) { - if (!silent) - fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u", - sbi->sec_per_clus); - brelse(bh); + if (error == -EINVAL) goto out_invalid; - } + else if (error) + goto out_fail; + + logical_sector_size = bpb.fat_sector_size; + sbi->sec_per_clus = bpb.fat_sec_per_clus; + error = -EIO; if (logical_sector_size < sb->s_blocksize) { fat_msg(sb, KERN_ERR, "logical sector size too small for device" " (logical sector size = %u)", logical_sector_size); - brelse(bh); goto out_fail; } + if (logical_sector_size > sb->s_blocksize) { - brelse(bh); + struct buffer_head *bh_resize; if (!sb_set_blocksize(sb, logical_sector_size)) { fat_msg(sb, KERN_ERR, "unable to set blocksize %u", logical_sector_size); goto out_fail; } - bh = sb_bread(sb, 0); - if (bh == NULL) { + + /* Verify that the larger boot sector is fully readable */ + bh_resize = sb_bread(sb, 0); + if (bh_resize == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector" " (logical sector size = %lu)", sb->s_blocksize); goto out_fail; } - b = (struct fat_boot_sector *) bh->b_data; + brelse(bh_resize); } mutex_init(&sbi->s_lock); sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus; sbi->cluster_bits = ffs(sbi->cluster_size) - 1; - sbi->fats = b->fats; + sbi->fats = bpb.fat_fats; sbi->fat_bits = 0; /* Don't know yet */ - sbi->fat_start = le16_to_cpu(b->reserved); - sbi->fat_length = le16_to_cpu(b->fat_length); + sbi->fat_start = bpb.fat_reserved; + sbi->fat_length = bpb.fat_fat_length; sbi->root_cluster = 0; sbi->free_clusters = -1; /* Don't know yet */ sbi->free_clus_valid = 0; sbi->prev_free = FAT_START_ENT; sb->s_maxbytes = 0xffffffff; - if (!sbi->fat_length && b->fat32.length) { + if (!sbi->fat_length && bpb.fat32_length) { struct fat_boot_fsinfo *fsinfo; struct buffer_head *fsinfo_bh; /* Must be FAT32 */ sbi->fat_bits = 32; - sbi->fat_length = le32_to_cpu(b->fat32.length); - sbi->root_cluster = le32_to_cpu(b->fat32.root_cluster); + sbi->fat_length = bpb.fat32_length; + sbi->root_cluster = bpb.fat32_root_cluster; /* MC - if info_sector is 0, don't multiply by 0 */ - sbi->fsinfo_sector = le16_to_cpu(b->fat32.info_sector); + sbi->fsinfo_sector = bpb.fat32_info_sector; if (sbi->fsinfo_sector == 0) sbi->fsinfo_sector = 1; @@ -1399,7 +1601,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, if (fsinfo_bh == NULL) { fat_msg(sb, KERN_ERR, "bread failed, FSINFO block" " (sector = %lu)", sbi->fsinfo_sector); - brelse(bh); goto out_fail; } @@ -1422,35 +1623,28 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, /* interpret volume ID as a little endian 32 bit integer */ if (sbi->fat_bits == 32) - sbi->vol_id = (((u32)b->fat32.vol_id[0]) | - ((u32)b->fat32.vol_id[1] << 8) | - ((u32)b->fat32.vol_id[2] << 16) | - ((u32)b->fat32.vol_id[3] << 24)); + sbi->vol_id = bpb.fat32_vol_id; else /* fat 16 or 12 */ - sbi->vol_id = (((u32)b->fat16.vol_id[0]) | - ((u32)b->fat16.vol_id[1] << 8) | - ((u32)b->fat16.vol_id[2] << 16) | - ((u32)b->fat16.vol_id[3] << 24)); + sbi->vol_id = bpb.fat16_vol_id; sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry); sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1; sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length; - sbi->dir_entries = get_unaligned_le16(&b->dir_entries); + sbi->dir_entries = bpb.fat_dir_entries; if (sbi->dir_entries & (sbi->dir_per_block - 1)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus directory-entries per block" " (%u)", sbi->dir_entries); - brelse(bh); goto out_invalid; } rootdir_sectors = sbi->dir_entries * sizeof(struct msdos_dir_entry) / sb->s_blocksize; sbi->data_start = sbi->dir_start + rootdir_sectors; - total_sectors = get_unaligned_le16(&b->sectors); + total_sectors = bpb.fat_sectors; if (total_sectors == 0) - total_sectors = le32_to_cpu(b->total_sect); + total_sectors = bpb.fat_total_sect; total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; @@ -1459,9 +1653,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ if (sbi->fat_bits == 32) - sbi->dirty = b->fat32.state & FAT_STATE_DIRTY; + sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY; else /* fat 16 or 12 */ - sbi->dirty = b->fat16.state & FAT_STATE_DIRTY; + sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY; /* check that FAT table does not overflow */ fat_clusters = calc_fat_clusters(sb); @@ -1470,7 +1664,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, if (!silent) fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", total_clusters); - brelse(bh); goto out_invalid; } @@ -1483,8 +1676,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, if (sbi->prev_free < FAT_START_ENT) sbi->prev_free = FAT_START_ENT; - brelse(bh); - /* set up enough so that it can read an inode */ fat_hash_init(sb); dir_hash_init(sb); -- cgit v1.2.3 From 8401aa1f59975c03eeebd3ac6d264cbdfe9af5de Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 6 Jun 2014 14:36:39 -0700 Subject: Documentation/SubmittingPatches: describe the Fixes: tag Update the SubmittingPatches process to include howto about the new 'Fixes:' tag to be used when a patch fixes an issue in a previous commit (found by git-bisect for example). Signed-off-by: Jacob Keller Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/SubmittingPatches | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 2a8e89e13e45..7e9abb8a276b 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -132,6 +132,20 @@ Example: platform_set_drvdata(), but left the variable "dev" unused, delete it. +If your patch fixes a bug in a specific commit, e.g. you found an issue using +git-bisect, please use the 'Fixes:' tag with the first 12 characters of the +SHA-1 ID, and the one line summary. +Example: + + Fixes: e21d2170f366 ("video: remove unnecessary platform_set_drvdata()") + +The following git-config settings can be used to add a pretty format for +outputting the above style in the git log or git show commands + + [core] + abbrev = 12 + [pretty] + fixes = Fixes: %h (\"%s\") 3) Separate your changes. @@ -443,7 +457,7 @@ person it names. This tag documents that potentially interested parties have been included in the discussion -14) Using Reported-by:, Tested-by:, Reviewed-by: and Suggested-by: +14) Using Reported-by:, Tested-by:, Reviewed-by:, Suggested-by: and Fixes: If this patch fixes a problem reported by somebody else, consider adding a Reported-by: tag to credit the reporter for their contribution. Please @@ -498,6 +512,12 @@ idea was not posted in a public forum. That said, if we diligently credit our idea reporters, they will, hopefully, be inspired to help us again in the future. +A Fixes: tag indicates that the patch fixes an issue in a previous commit. It +is used to make it easy to determine where a bug originated, which can help +review a bug fix. This tag also assists the stable kernel team in determining +which stable kernel versions should receive your fix. This is the preferred +method for indicating a bug fixed by the patch. See #2 above for more details. + 15) The canonical patch format -- cgit v1.2.3 From 0b07cb8271507ca99cca79222a1dc92ba415f06b Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Fri, 6 Jun 2014 14:36:40 -0700 Subject: Documentation/filesystems/seq_file.txt: create_proc_entry deprecated Linked article in seq_file.txt still uses create_proc_entry which was removed in commit 80e928f7ebb9 ("proc: Kill create_proc_entry()"). This patch adds information for kernel 3.10 and above Signed-off-by: Fabian Frederick Cc: Jonathan Corbet Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/seq_file.txt | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'Documentation') diff --git a/Documentation/filesystems/seq_file.txt b/Documentation/filesystems/seq_file.txt index a1e2e0dda907..1fe0ccb1af55 100644 --- a/Documentation/filesystems/seq_file.txt +++ b/Documentation/filesystems/seq_file.txt @@ -54,6 +54,15 @@ how the mechanism works without getting lost in other details. (Those wanting to see the full source for this module can find it at http://lwn.net/Articles/22359/). +Deprecated create_proc_entry + +Note that the above article uses create_proc_entry which was removed in +kernel 3.10. Current versions require the following update + +- entry = create_proc_entry("sequence", 0, NULL); +- if (entry) +- entry->proc_fops = &ct_file_ops; ++ entry = proc_create("sequence", 0, NULL, &ct_file_ops); The iterator interface -- cgit v1.2.3 From 615cc2c9cf9529846fbc342560d6787c2ccaaeea Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 6 Jun 2014 14:36:41 -0700 Subject: Documentation/memory-barriers.txt: fix important typo re memory barriers Examples introducing neccesity of RMB+WMP pair reads as A=3 READ B www rrrrrr B=4 READ A Note the opposite order of reads vs writes. But the first example without barriers reads as A=3 READ A B=4 READ B There are 4 outcomes in the first example. But if someone new to the concept tries to insert barriers like this: A=3 READ A www rrrrrr B=4 READ B he will still get all 4 possible outcomes, because "READ A" is first. All this can be utterly confusing because barrier pair seems to be superfluous. In short, fixup first example to match latter examples with barriers. Signed-off-by: Alexey Dobriyan Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/memory-barriers.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 46412bded104..f1dc4a215593 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -115,8 +115,8 @@ For example, consider the following sequence of events: CPU 1 CPU 2 =============== =============== { A == 1; B == 2 } - A = 3; x = A; - B = 4; y = B; + A = 3; x = B; + B = 4; y = A; The set of accesses as seen by the memory system in the middle can be arranged in 24 different combinations: -- cgit v1.2.3 From f06e5153f4ae2e2f3b0300f0e260e40cb7fefd45 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Jun 2014 14:37:07 -0700 Subject: kernel/panic.c: add "crash_kexec_post_notifiers" option for kdump after panic_notifers Add a "crash_kexec_post_notifiers" boot option to run kdump after running panic_notifiers and dump kmsg. This can help rare situations where kdump fails because of unstable crashed kernel or hardware failure (memory corruption on critical data/code), or the 2nd kernel is already broken by the 1st kernel (it's a broken behavior, but who can guarantee that the "crashed" kernel works correctly?). Usage: add "crash_kexec_post_notifiers" to kernel boot option. Note that this actually increases risks of the failure of kdump. This option should be set only if you worry about the rare case of kdump failure rather than increasing the chance of success. Signed-off-by: Masami Hiramatsu Acked-by: Motohiro Kosaki Acked-by: Vivek Goyal Cc: Eric Biederman Cc: Yoshihiro YUNOMAE Cc: Satoru MORIYA Cc: Tomoki Sekiyama Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 8 ++++++++ kernel/panic.c | 23 +++++++++++++++++++++-- 2 files changed, 29 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 9973a7e2e0ac..b9f67781c577 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2361,6 +2361,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted. timeout < 0: reboot immediately Format: + crash_kexec_post_notifiers + Run kdump after running panic-notifiers and dumping + kmsg. This only for the users who doubt kdump always + succeeds in any situation. + Note that this also increases risks of kdump failure, + because some panic notifiers can make the crashed + kernel more unstable. + parkbd.port= [HW] Parallel port number the keyboard adapter is connected to, default is 0. Format: diff --git a/kernel/panic.c b/kernel/panic.c index d02fa9fef46a..62e16cef9cc2 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -32,6 +32,7 @@ static unsigned long tainted_mask; static int pause_on_oops; static int pause_on_oops_flag; static DEFINE_SPINLOCK(pause_on_oops_lock); +static bool crash_kexec_post_notifiers; int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -112,9 +113,11 @@ void panic(const char *fmt, ...) /* * If we have crashed and we have a crash kernel loaded let it handle * everything else. - * Do we want to call this before we try to display a message? + * If we want to run this after calling panic_notifiers, pass + * the "crash_kexec_post_notifiers" option to the kernel. */ - crash_kexec(NULL); + if (!crash_kexec_post_notifiers) + crash_kexec(NULL); /* * Note smp_send_stop is the usual smp shutdown function, which @@ -131,6 +134,15 @@ void panic(const char *fmt, ...) kmsg_dump(KMSG_DUMP_PANIC); + /* + * If you doubt kdump always works fine in any situation, + * "crash_kexec_post_notifiers" offers you a chance to run + * panic_notifiers and dumping kmsg before kdump. + * Note: since some panic_notifiers can make crashed kernel + * more unstable, it can increase risks of the kdump failure too. + */ + crash_kexec(NULL); + bust_spinlocks(0); if (!panic_blink) @@ -472,6 +484,13 @@ EXPORT_SYMBOL(__stack_chk_fail); core_param(panic, panic_timeout, int, 0644); core_param(pause_on_oops, pause_on_oops, int, 0644); +static int __init setup_crash_kexec_post_notifiers(char *s) +{ + crash_kexec_post_notifiers = true; + return 0; +} +early_param("crash_kexec_post_notifiers", setup_crash_kexec_post_notifiers); + static int __init oops_setup(char *s) { if (!s) -- cgit v1.2.3 From f4aacea2f5d1a5f7e3154e967d70cf3f711bcd61 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 6 Jun 2014 14:37:19 -0700 Subject: sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/kernel.txt | 21 +++++++++++++ kernel/sysctl.c | 69 +++++++++++++++++++++++++++++++++++++++-- 2 files changed, 88 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 9886c3d57fc2..708bb7f1b7e0 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -77,6 +77,7 @@ show up in /proc/sys/kernel: - shmmni - stop-a [ SPARC only ] - sysrq ==> Documentation/sysrq.txt +- sysctl_writes_strict - tainted - threads-max - unknown_nmi_panic @@ -762,6 +763,26 @@ without users and with a dead originative process will be destroyed. ============================================================== +sysctl_writes_strict: + +Control how file position affects the behavior of updating sysctl values +via the /proc/sys interface: + + -1 - Legacy per-write sysctl value handling, with no printk warnings. + Each write syscall must fully contain the sysctl value to be + written, and multiple writes on the same sysctl file descriptor + will rewrite the sysctl value, regardless of file position. + 0 - (default) Same behavior as above, but warn about processes that + perform writes to a sysctl file descriptor when the file position + is not 0. + 1 - Respect file position when writing sysctl strings. Multiple writes + will append to the sysctl value buffer. Anything past the max length + of the sysctl value buffer will be ignored. Writes to numeric sysctl + entries must always be at file position 0 and the value must be + fully contained in the buffer sent in the write syscall. + +============================================================== + tainted: Non-zero if the kernel has been tainted. Numeric values, which diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ac6847feaa83..7a910b9081e8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -173,6 +173,13 @@ extern int no_unaligned_warning; #endif #ifdef CONFIG_PROC_SYSCTL + +#define SYSCTL_WRITES_LEGACY -1 +#define SYSCTL_WRITES_WARN 0 +#define SYSCTL_WRITES_STRICT 1 + +static int sysctl_writes_strict = SYSCTL_WRITES_WARN; + static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); static int proc_taint(struct ctl_table *table, int write, @@ -495,6 +502,15 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_taint, }, + { + .procname = "sysctl_writes_strict", + .data = &sysctl_writes_strict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &neg_one, + .extra2 = &one, + }, #endif #ifdef CONFIG_LATENCYTOP { @@ -1717,8 +1733,20 @@ static int _proc_do_string(char *data, int maxlen, int write, } if (write) { - /* Start writing from beginning of buffer. */ - len = 0; + if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) { + /* Only continue writes not past the end of buffer. */ + len = strlen(data); + if (len > maxlen - 1) + len = maxlen - 1; + + if (*ppos > len) + return 0; + len = *ppos; + } else { + /* Start writing from beginning of buffer. */ + len = 0; + } + *ppos += *lenp; p = buffer; while ((p - buffer) < *lenp && len < maxlen - 1) { @@ -1758,6 +1786,14 @@ static int _proc_do_string(char *data, int maxlen, int write, return 0; } +static void warn_sysctl_write(struct ctl_table *table) +{ + pr_warn_once("%s wrote to %s when file position was not 0!\n" + "This will not be supported in the future. To silence this\n" + "warning, set kernel.sysctl_writes_strict = -1\n", + current->comm, table->procname); +} + /** * proc_dostring - read a string sysctl * @table: the sysctl table @@ -1778,6 +1814,9 @@ static int _proc_do_string(char *data, int maxlen, int write, int proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN) + warn_sysctl_write(table); + return _proc_do_string((char *)(table->data), table->maxlen, write, (char __user *)buffer, lenp, ppos); } @@ -1953,6 +1992,18 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, conv = do_proc_dointvec_conv; if (write) { + if (*ppos) { + switch (sysctl_writes_strict) { + case SYSCTL_WRITES_STRICT: + goto out; + case SYSCTL_WRITES_WARN: + warn_sysctl_write(table); + break; + default: + break; + } + } + if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; page = __get_free_page(GFP_TEMPORARY); @@ -2010,6 +2061,7 @@ free: return err ? : -EINVAL; } *lenp -= left; +out: *ppos += *lenp; return err; } @@ -2202,6 +2254,18 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int left = *lenp; if (write) { + if (*ppos) { + switch (sysctl_writes_strict) { + case SYSCTL_WRITES_STRICT: + goto out; + case SYSCTL_WRITES_WARN: + warn_sysctl_write(table); + break; + default: + break; + } + } + if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; page = __get_free_page(GFP_TEMPORARY); @@ -2257,6 +2321,7 @@ free: return err ? : -EINVAL; } *lenp -= left; +out: *ppos += *lenp; return err; } -- cgit v1.2.3 From 688eb988d15af55c1d1b70b1ca9f6ce58f277c20 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 6 Jun 2014 14:38:15 -0700 Subject: vmscan: memcg: always use swappiness of the reclaimed memcg Memory reclaim always uses swappiness of the reclaim target memcg (origin of the memory pressure) or vm_swappiness for global memory reclaim. This behavior was consistent (except for difference between global and hard limit reclaim) because swappiness was enforced to be consistent within each memcg hierarchy. After "mm: memcontrol: remove hierarchy restrictions for swappiness and oom_control" each memcg can have its own swappiness independent of hierarchical parents, though, so the consistency guarantee is gone. This can lead to an unexpected behavior. Say that a group is explicitly configured to not swapout by memory.swappiness=0 but its memory gets swapped out anyway when the memory pressure comes from its parent with a It is also unexpected that the knob is meaningless without setting the hard limit which would trigger the reclaim and enforce the swappiness. There are setups where the hard limit is configured higher in the hierarchy by an administrator and children groups are under control of somebody else who is interested in the swapout behavior but not necessarily about the memory limit. From a semantic point of view swappiness is an attribute defining anon vs. file proportional scanning of LRU which is memcg specific (unlike charges which are propagated up the hierarchy) so it should be applied to the particular memcg's LRU regardless where the memory pressure comes from. This patch removes vmscan_swappiness() and stores the swappiness into the scan_control structure. mem_cgroup_swappiness is then used to provide the correct value before shrink_lruvec is called. The global vm_swappiness is used for the root memcg. [hughd@google.com: oopses immediately when booted with cgroup_disable=memory] Signed-off-by: Michal Hocko Acked-by: Johannes Weiner Cc: Tejun Heo Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memory.txt | 15 +++++++-------- mm/memcontrol.c | 2 +- mm/vmscan.c | 18 ++++++++---------- 3 files changed, 16 insertions(+), 19 deletions(-) (limited to 'Documentation') diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 4937e6fff9b4..b3429aec444c 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -540,14 +540,13 @@ Note: 5.3 swappiness -Similar to /proc/sys/vm/swappiness, but only affecting reclaim that is -triggered by this cgroup's hard limit. The tunable in the root cgroup -corresponds to the global swappiness setting. - -Please note that unlike the global swappiness, memcg knob set to 0 -really prevents from any swapping even if there is a swap storage -available. This might lead to memcg OOM killer if there are no file -pages to reclaim. +Overrides /proc/sys/vm/swappiness for the particular group. The tunable +in the root cgroup corresponds to the global swappiness setting. + +Please note that unlike during the global reclaim, limit reclaim +enforces that 0 swappiness really prevents from any swapping even if +there is a swap storage available. This might lead to memcg OOM killer +if there are no file pages to reclaim. 5.4 failcnt diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a500cb0594c4..9bf8a84bcaae 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1550,7 +1550,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* root ? */ - if (!css_parent(&memcg->css)) + if (mem_cgroup_disabled() || !css_parent(&memcg->css)) return vm_swappiness; return memcg->swappiness; diff --git a/mm/vmscan.c b/mm/vmscan.c index 05d41c0d7f6c..f44476a41544 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -83,6 +83,9 @@ struct scan_control { /* Scan (total_size >> priority) pages at once */ int priority; + /* anon vs. file LRUs scanning "ratio" */ + int swappiness; + /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. @@ -1845,13 +1848,6 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } -static int vmscan_swappiness(struct scan_control *sc) -{ - if (global_reclaim(sc)) - return vm_swappiness; - return mem_cgroup_swappiness(sc->target_mem_cgroup); -} - enum scan_balance { SCAN_EQUAL, SCAN_FRACT, @@ -1912,7 +1908,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * using the memory controller's swap limit feature would be * too expensive. */ - if (!global_reclaim(sc) && !vmscan_swappiness(sc)) { + if (!global_reclaim(sc) && !sc->swappiness) { scan_balance = SCAN_FILE; goto out; } @@ -1922,7 +1918,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ - if (!sc->priority && vmscan_swappiness(sc)) { + if (!sc->priority && sc->swappiness) { scan_balance = SCAN_EQUAL; goto out; } @@ -1965,7 +1961,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ - anon_prio = vmscan_swappiness(sc); + anon_prio = sc->swappiness; file_prio = 200 - anon_prio; /* @@ -2265,6 +2261,7 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) lruvec = mem_cgroup_zone_lruvec(zone, memcg); + sc->swappiness = mem_cgroup_swappiness(memcg); shrink_lruvec(lruvec, sc); /* @@ -2731,6 +2728,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, .may_swap = !noswap, .order = 0, .priority = 0, + .swappiness = mem_cgroup_swappiness(memcg), .target_mem_cgroup = memcg, }; struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); -- cgit v1.2.3 From ffe2c748e283c5dc1b9b9ac116299dbfc11a609b Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Fri, 6 Jun 2014 14:38:17 -0700 Subject: mm: introduce kmemleak_update_trace() The memory allocation stack trace is not always useful for debugging a memory leak (e.g. radix_tree_preload). This function, when called, updates the stack trace for an already allocated object. Signed-off-by: Catalin Marinas Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kmemleak.txt | 1 + include/linux/kmemleak.h | 4 ++++ mm/kmemleak.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 39 insertions(+) (limited to 'Documentation') diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt index a7563ec4ea7b..b772418bf064 100644 --- a/Documentation/kmemleak.txt +++ b/Documentation/kmemleak.txt @@ -142,6 +142,7 @@ kmemleak_alloc_percpu - notify of a percpu memory block allocation kmemleak_free - notify of a memory block freeing kmemleak_free_part - notify of a partial memory block freeing kmemleak_free_percpu - notify of a percpu memory block freeing +kmemleak_update_trace - update object allocation stack trace kmemleak_not_leak - mark an object as not a leak kmemleak_ignore - do not scan or report an object as leak kmemleak_scan_area - add scan areas inside a memory block diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 5bb424659c04..057e95971014 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -30,6 +30,7 @@ extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) __ref; extern void kmemleak_free(const void *ptr) __ref; extern void kmemleak_free_part(const void *ptr, size_t size) __ref; extern void kmemleak_free_percpu(const void __percpu *ptr) __ref; +extern void kmemleak_update_trace(const void *ptr) __ref; extern void kmemleak_not_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; @@ -83,6 +84,9 @@ static inline void kmemleak_free_recursive(const void *ptr, unsigned long flags) static inline void kmemleak_free_percpu(const void __percpu *ptr) { } +static inline void kmemleak_update_trace(const void *ptr) +{ +} static inline void kmemleak_not_leak(const void *ptr) { } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 5d4aec44982e..3cda50c1e394 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -989,6 +989,40 @@ void __ref kmemleak_free_percpu(const void __percpu *ptr) } EXPORT_SYMBOL_GPL(kmemleak_free_percpu); +/** + * kmemleak_update_trace - update object allocation stack trace + * @ptr: pointer to beginning of the object + * + * Override the object allocation stack trace for cases where the actual + * allocation place is not always useful. + */ +void __ref kmemleak_update_trace(const void *ptr) +{ + struct kmemleak_object *object; + unsigned long flags; + + pr_debug("%s(0x%p)\n", __func__, ptr); + + if (!kmemleak_enabled || IS_ERR_OR_NULL(ptr)) + return; + + object = find_and_get_object((unsigned long)ptr, 1); + if (!object) { +#ifdef DEBUG + kmemleak_warn("Updating stack trace for unknown object at %p\n", + ptr); +#endif + return; + } + + spin_lock_irqsave(&object->lock, flags); + object->trace_len = __save_stack_trace(object->trace); + spin_unlock_irqrestore(&object->lock, flags); + + put_object(object); +} +EXPORT_SYMBOL(kmemleak_update_trace); + /** * kmemleak_not_leak - mark an allocated object as false positive * @ptr: pointer to beginning of the object -- cgit v1.2.3 From 33041a0d76d3c3e0aff28ac95a2ffdedf1282dbc Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 6 Jun 2014 14:38:23 -0700 Subject: mm: mark remap_file_pages() syscall as deprecated The remap_file_pages() system call is used to create a nonlinear mapping, that is, a mapping in which the pages of the file are mapped into a nonsequential order in memory. The advantage of using remap_file_pages() over using repeated calls to mmap(2) is that the former approach does not require the kernel to create additional VMA (Virtual Memory Area) data structures. Supporting of nonlinear mapping requires significant amount of non-trivial code in kernel virtual memory subsystem including hot paths. Also to get nonlinear mapping work kernel need a way to distinguish normal page table entries from entries with file offset (pte_file). Kernel reserves flag in PTE for this purpose. PTE flags are scarce resource especially on some CPU architectures. It would be nice to free up the flag for other usage. Fortunately, there are not many users of remap_file_pages() in the wild. It's only known that one enterprise RDBMS implementation uses the syscall on 32-bit systems to map files bigger than can linearly fit into 32-bit virtual address space. This use-case is not critical anymore since 64-bit systems are widely available. The plan is to deprecate the syscall and replace it with an emulation. The emulation will create new VMAs instead of nonlinear mappings. It's going to work slower for rare users of remap_file_pages() but ABI is preserved. One side effect of emulation (apart from performance) is that user can hit vm.max_map_count limit more easily due to additional VMAs. See comment for DEFAULT_MAX_MAP_COUNT for more details on the limit. [akpm@linux-foundation.org: fix spello] Signed-off-by: Kirill A. Shutemov Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Dave Jones Cc: Armin Rigo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/remap_file_pages.txt | 28 ++++++++++++++++++++++++++++ mm/fremap.c | 4 ++++ 2 files changed, 32 insertions(+) create mode 100644 Documentation/vm/remap_file_pages.txt (limited to 'Documentation') diff --git a/Documentation/vm/remap_file_pages.txt b/Documentation/vm/remap_file_pages.txt new file mode 100644 index 000000000000..560e4363a55d --- /dev/null +++ b/Documentation/vm/remap_file_pages.txt @@ -0,0 +1,28 @@ +The remap_file_pages() system call is used to create a nonlinear mapping, +that is, a mapping in which the pages of the file are mapped into a +nonsequential order in memory. The advantage of using remap_file_pages() +over using repeated calls to mmap(2) is that the former approach does not +require the kernel to create additional VMA (Virtual Memory Area) data +structures. + +Supporting of nonlinear mapping requires significant amount of non-trivial +code in kernel virtual memory subsystem including hot paths. Also to get +nonlinear mapping work kernel need a way to distinguish normal page table +entries from entries with file offset (pte_file). Kernel reserves flag in +PTE for this purpose. PTE flags are scarce resource especially on some CPU +architectures. It would be nice to free up the flag for other usage. + +Fortunately, there are not many users of remap_file_pages() in the wild. +It's only known that one enterprise RDBMS implementation uses the syscall +on 32-bit systems to map files bigger than can linearly fit into 32-bit +virtual address space. This use-case is not critical anymore since 64-bit +systems are widely available. + +The plan is to deprecate the syscall and replace it with an emulation. +The emulation will create new VMAs instead of nonlinear mappings. It's +going to work slower for rare users of remap_file_pages() but ABI is +preserved. + +One side effect of emulation (apart from performance) is that user can hit +vm.max_map_count limit more easily due to additional VMAs. See comment for +DEFAULT_MAX_MAP_COUNT for more details on the limit. diff --git a/mm/fremap.c b/mm/fremap.c index 2c5646f11f41..72b8fa361433 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -149,6 +149,10 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, int has_write_lock = 0; vm_flags_t vm_flags = 0; + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " + "See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); + if (prot) return err; /* -- cgit v1.2.3