From 7eaceaccab5f40bbfda044629a6298616aeaed50 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2011 08:52:07 +0100 Subject: block: remove per-queue plugging Code has been converted over to the new explicit on-stack plugging, and delay users have been converted to use the new API for that. So lets kill off the old plugging along with aops->sync_page(). Signed-off-by: Jens Axboe --- fs/logfs/dev_bdev.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs/logfs') diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index 723bc5bca09a..1adc8d455f0e 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -39,7 +39,6 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw) bio.bi_end_io = request_complete; submit_bio(rw, &bio); - generic_unplug_device(bdev_get_queue(bdev)); wait_for_completion(&complete); return test_bit(BIO_UPTODATE, &bio.bi_flags) ? 0 : -EIO; } @@ -168,7 +167,6 @@ static void bdev_writeseg(struct super_block *sb, u64 ofs, size_t len) } len = PAGE_ALIGN(len); __bdev_writeseg(sb, ofs, ofs >> PAGE_SHIFT, len >> PAGE_SHIFT); - generic_unplug_device(bdev_get_queue(logfs_super(sb)->s_bdev)); } -- cgit v1.2.3 From 565d76cb7d5fd7cb010fd690602280a69ab116ef Mon Sep 17 00:00:00 2001 From: Jim Keniston Date: Tue, 22 Mar 2011 16:35:12 -0700 Subject: zlib: slim down zlib_deflate() workspace when possible Instead of always creating a huge (268K) deflate_workspace with the maximum compression parameters (windowBits=15, memLevel=8), allow the caller to obtain a smaller workspace by specifying smaller parameter values. For example, when capturing oops and panic reports to a medium with limited capacity, such as NVRAM, compression may be the only way to capture the whole report. In this case, a small workspace (24K works fine) is a win, whether you allocate the workspace when you need it (i.e., during an oops or panic) or at boot time. I've verified that this patch works with all accepted values of windowBits (positive and negative), memLevel, and compression level. Signed-off-by: Jim Keniston Cc: Herbert Xu Cc: David Miller Cc: Chris Mason Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- crypto/deflate.c | 3 ++- crypto/zlib.c | 18 +++++++++++------- drivers/net/ppp_deflate.c | 2 +- fs/btrfs/zlib.c | 3 ++- fs/jffs2/compr_zlib.c | 7 ++++--- fs/logfs/compr.c | 2 +- include/linux/zlib.h | 11 ++++++++--- lib/zlib_deflate/deflate.c | 31 +++++++++++++++++++++++++++++-- lib/zlib_deflate/defutil.h | 17 +++++++++++++---- 9 files changed, 71 insertions(+), 23 deletions(-) (limited to 'fs/logfs') diff --git a/crypto/deflate.c b/crypto/deflate.c index cbc7a33a9600..b5ccae29be74 100644 --- a/crypto/deflate.c +++ b/crypto/deflate.c @@ -48,7 +48,8 @@ static int deflate_comp_init(struct deflate_ctx *ctx) int ret = 0; struct z_stream_s *stream = &ctx->comp_stream; - stream->workspace = vzalloc(zlib_deflate_workspacesize()); + stream->workspace = vzalloc(zlib_deflate_workspacesize( + -DEFLATE_DEF_WINBITS, DEFLATE_DEF_MEMLEVEL)); if (!stream->workspace) { ret = -ENOMEM; goto out; diff --git a/crypto/zlib.c b/crypto/zlib.c index 739b8fca4cea..d11d761a5e41 100644 --- a/crypto/zlib.c +++ b/crypto/zlib.c @@ -85,6 +85,7 @@ static int zlib_compress_setup(struct crypto_pcomp *tfm, void *params, struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm)); struct z_stream_s *stream = &ctx->comp_stream; struct nlattr *tb[ZLIB_COMP_MAX + 1]; + int window_bits, mem_level; size_t workspacesize; int ret; @@ -94,7 +95,14 @@ static int zlib_compress_setup(struct crypto_pcomp *tfm, void *params, zlib_comp_exit(ctx); - workspacesize = zlib_deflate_workspacesize(); + window_bits = tb[ZLIB_COMP_WINDOWBITS] + ? nla_get_u32(tb[ZLIB_COMP_WINDOWBITS]) + : MAX_WBITS; + mem_level = tb[ZLIB_COMP_MEMLEVEL] + ? nla_get_u32(tb[ZLIB_COMP_MEMLEVEL]) + : DEF_MEM_LEVEL; + + workspacesize = zlib_deflate_workspacesize(window_bits, mem_level); stream->workspace = vzalloc(workspacesize); if (!stream->workspace) return -ENOMEM; @@ -106,12 +114,8 @@ static int zlib_compress_setup(struct crypto_pcomp *tfm, void *params, tb[ZLIB_COMP_METHOD] ? nla_get_u32(tb[ZLIB_COMP_METHOD]) : Z_DEFLATED, - tb[ZLIB_COMP_WINDOWBITS] - ? nla_get_u32(tb[ZLIB_COMP_WINDOWBITS]) - : MAX_WBITS, - tb[ZLIB_COMP_MEMLEVEL] - ? nla_get_u32(tb[ZLIB_COMP_MEMLEVEL]) - : DEF_MEM_LEVEL, + window_bits, + mem_level, tb[ZLIB_COMP_STRATEGY] ? nla_get_u32(tb[ZLIB_COMP_STRATEGY]) : Z_DEFAULT_STRATEGY); diff --git a/drivers/net/ppp_deflate.c b/drivers/net/ppp_deflate.c index 43583309a65d..31e9407a0739 100644 --- a/drivers/net/ppp_deflate.c +++ b/drivers/net/ppp_deflate.c @@ -129,7 +129,7 @@ static void *z_comp_alloc(unsigned char *options, int opt_len) state->strm.next_in = NULL; state->w_size = w_size; - state->strm.workspace = vmalloc(zlib_deflate_workspacesize()); + state->strm.workspace = vmalloc(zlib_deflate_workspacesize(-w_size, 8)); if (state->strm.workspace == NULL) goto out_free; diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index f5ec2d44150d..faccd47c6c46 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -57,7 +57,8 @@ static struct list_head *zlib_alloc_workspace(void) if (!workspace) return ERR_PTR(-ENOMEM); - workspace->def_strm.workspace = vmalloc(zlib_deflate_workspacesize()); + workspace->def_strm.workspace = vmalloc(zlib_deflate_workspacesize( + MAX_WBITS, MAX_MEM_LEVEL)); workspace->inf_strm.workspace = vmalloc(zlib_inflate_workspacesize()); workspace->buf = kmalloc(PAGE_CACHE_SIZE, GFP_NOFS); if (!workspace->def_strm.workspace || diff --git a/fs/jffs2/compr_zlib.c b/fs/jffs2/compr_zlib.c index fd05a0b9431d..5a001020c542 100644 --- a/fs/jffs2/compr_zlib.c +++ b/fs/jffs2/compr_zlib.c @@ -40,12 +40,13 @@ static z_stream inf_strm, def_strm; static int __init alloc_workspaces(void) { - def_strm.workspace = vmalloc(zlib_deflate_workspacesize()); + def_strm.workspace = vmalloc(zlib_deflate_workspacesize(MAX_WBITS, + MAX_MEM_LEVEL)); if (!def_strm.workspace) { - printk(KERN_WARNING "Failed to allocate %d bytes for deflate workspace\n", zlib_deflate_workspacesize()); + printk(KERN_WARNING "Failed to allocate %d bytes for deflate workspace\n", zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL)); return -ENOMEM; } - D1(printk(KERN_DEBUG "Allocated %d bytes for deflate workspace\n", zlib_deflate_workspacesize())); + D1(printk(KERN_DEBUG "Allocated %d bytes for deflate workspace\n", zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL))); inf_strm.workspace = vmalloc(zlib_inflate_workspacesize()); if (!inf_strm.workspace) { printk(KERN_WARNING "Failed to allocate %d bytes for inflate workspace\n", zlib_inflate_workspacesize()); diff --git a/fs/logfs/compr.c b/fs/logfs/compr.c index 44bbfd249abc..961f02b86d97 100644 --- a/fs/logfs/compr.c +++ b/fs/logfs/compr.c @@ -81,7 +81,7 @@ error: int __init logfs_compr_init(void) { - size_t size = max(zlib_deflate_workspacesize(), + size_t size = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); stream.workspace = vmalloc(size); if (!stream.workspace) diff --git a/include/linux/zlib.h b/include/linux/zlib.h index 40c49cb3eb51..9c5a6b4de0a3 100644 --- a/include/linux/zlib.h +++ b/include/linux/zlib.h @@ -179,11 +179,16 @@ typedef z_stream *z_streamp; /* basic functions */ -extern int zlib_deflate_workspacesize (void); +extern int zlib_deflate_workspacesize (int windowBits, int memLevel); /* Returns the number of bytes that needs to be allocated for a per- - stream workspace. A pointer to this number of bytes should be - returned in stream->workspace before calling zlib_deflateInit(). + stream workspace with the specified parameters. A pointer to this + number of bytes should be returned in stream->workspace before + you call zlib_deflateInit() or zlib_deflateInit2(). If you call + zlib_deflateInit(), specify windowBits = MAX_WBITS and memLevel = + MAX_MEM_LEVEL here. If you call zlib_deflateInit2(), the windowBits + and memLevel parameters passed to zlib_deflateInit2() must not + exceed those passed here. */ /* diff --git a/lib/zlib_deflate/deflate.c b/lib/zlib_deflate/deflate.c index 46a31e5f49c3..d63381e8e333 100644 --- a/lib/zlib_deflate/deflate.c +++ b/lib/zlib_deflate/deflate.c @@ -176,6 +176,7 @@ int zlib_deflateInit2( deflate_state *s; int noheader = 0; deflate_workspace *mem; + char *next; ush *overlay; /* We overlay pending_buf and d_buf+l_buf. This works since the average @@ -199,6 +200,21 @@ int zlib_deflateInit2( strategy < 0 || strategy > Z_HUFFMAN_ONLY) { return Z_STREAM_ERROR; } + + /* + * Direct the workspace's pointers to the chunks that were allocated + * along with the deflate_workspace struct. + */ + next = (char *) mem; + next += sizeof(*mem); + mem->window_memory = (Byte *) next; + next += zlib_deflate_window_memsize(windowBits); + mem->prev_memory = (Pos *) next; + next += zlib_deflate_prev_memsize(windowBits); + mem->head_memory = (Pos *) next; + next += zlib_deflate_head_memsize(memLevel); + mem->overlay_memory = next; + s = (deflate_state *) &(mem->deflate_memory); strm->state = (struct internal_state *)s; s->strm = strm; @@ -1247,7 +1263,18 @@ static block_state deflate_slow( return flush == Z_FINISH ? finish_done : block_done; } -int zlib_deflate_workspacesize(void) +int zlib_deflate_workspacesize(int windowBits, int memLevel) { - return sizeof(deflate_workspace); + if (windowBits < 0) /* undocumented feature: suppress zlib header */ + windowBits = -windowBits; + + /* Since the return value is typically passed to vmalloc() unchecked... */ + BUG_ON(memLevel < 1 || memLevel > MAX_MEM_LEVEL || windowBits < 9 || + windowBits > 15); + + return sizeof(deflate_workspace) + + zlib_deflate_window_memsize(windowBits) + + zlib_deflate_prev_memsize(windowBits) + + zlib_deflate_head_memsize(memLevel) + + zlib_deflate_overlay_memsize(memLevel); } diff --git a/lib/zlib_deflate/defutil.h b/lib/zlib_deflate/defutil.h index 6b15a909ca3f..b640b6402e99 100644 --- a/lib/zlib_deflate/defutil.h +++ b/lib/zlib_deflate/defutil.h @@ -241,12 +241,21 @@ typedef struct deflate_state { typedef struct deflate_workspace { /* State memory for the deflator */ deflate_state deflate_memory; - Byte window_memory[2 * (1 << MAX_WBITS)]; - Pos prev_memory[1 << MAX_WBITS]; - Pos head_memory[1 << (MAX_MEM_LEVEL + 7)]; - char overlay_memory[(1 << (MAX_MEM_LEVEL + 6)) * (sizeof(ush)+2)]; + Byte *window_memory; + Pos *prev_memory; + Pos *head_memory; + char *overlay_memory; } deflate_workspace; +#define zlib_deflate_window_memsize(windowBits) \ + (2 * (1 << (windowBits)) * sizeof(Byte)) +#define zlib_deflate_prev_memsize(windowBits) \ + ((1 << (windowBits)) * sizeof(Pos)) +#define zlib_deflate_head_memsize(memLevel) \ + ((1 << ((memLevel)+7)) * sizeof(Pos)) +#define zlib_deflate_overlay_memsize(memLevel) \ + ((1 << ((memLevel)+6)) * (sizeof(ush)+2)) + /* Output a byte on the stream. * IN assertion: there is enough room in pending_buf. */ -- cgit v1.2.3 From 2e1496707560ecf98e9b0604622c0990f94861d3 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:26 -0700 Subject: userns: rename is_owner_or_cap to inode_owner_or_capable And give it a kernel-doc comment. [akpm@linux-foundation.org: btrfs changed in linux-next] Signed-off-by: Serge E. Hallyn Cc: "Eric W. Biederman" Cc: Daniel Lezcano Acked-by: David Howells Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/acl.c | 2 +- fs/attr.c | 4 ++-- fs/btrfs/acl.c | 2 +- fs/btrfs/ioctl.c | 4 ++-- fs/ext2/acl.c | 2 +- fs/ext2/ioctl.c | 6 +++--- fs/ext3/acl.c | 2 +- fs/ext3/ioctl.c | 6 +++--- fs/ext4/acl.c | 2 +- fs/ext4/ioctl.c | 8 ++++---- fs/fcntl.c | 2 +- fs/generic_acl.c | 2 +- fs/gfs2/file.c | 2 +- fs/hfsplus/ioctl.c | 2 +- fs/inode.c | 13 ++++++++----- fs/jffs2/acl.c | 2 +- fs/jfs/ioctl.c | 2 +- fs/jfs/xattr.c | 2 +- fs/logfs/file.c | 2 +- fs/namei.c | 2 +- fs/nilfs2/ioctl.c | 2 +- fs/ocfs2/acl.c | 2 +- fs/ocfs2/ioctl.c | 2 +- fs/reiserfs/ioctl.c | 4 ++-- fs/reiserfs/xattr_acl.c | 2 +- fs/ubifs/ioctl.c | 2 +- fs/utimes.c | 2 +- fs/xattr.c | 2 +- include/linux/fs.h | 2 +- security/selinux/hooks.c | 2 +- 30 files changed, 47 insertions(+), 44 deletions(-) (limited to 'fs/logfs') diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 33aa116732c8..535ab6eccb1a 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -323,7 +323,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; if (value) { /* update the cached acl value */ diff --git a/fs/attr.c b/fs/attr.c index 7ca41811afa1..1007ed616314 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -59,7 +59,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; /* Also check the setgid bit! */ if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : @@ -69,7 +69,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; } diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 9c949348510b..de34bfad9ec3 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -170,7 +170,7 @@ static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name, int ret; struct posix_acl *acl = NULL; - if (!is_owner_or_cap(dentry->d_inode)) + if (!inode_owner_or_capable(dentry->d_inode)) return -EPERM; if (!IS_POSIXACL(dentry->d_inode)) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5fdb2abc4fa7..d1bace3df9b6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -158,7 +158,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) FS_SYNC_FL | FS_DIRSYNC_FL)) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; mutex_lock(&inode->i_mutex); @@ -1077,7 +1077,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, if (flags & ~BTRFS_SUBVOL_RDONLY) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; down_write(&root->fs_info->subvol_sem); diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 7b4180554a62..abea5a17c764 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -406,7 +406,7 @@ ext2_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, return -EINVAL; if (!test_opt(dentry->d_sb, POSIX_ACL)) return -EOPNOTSUPP; - if (!is_owner_or_cap(dentry->d_inode)) + if (!inode_owner_or_capable(dentry->d_inode)) return -EPERM; if (value) { diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index e7431309bdca..f81e250ac5c4 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -39,7 +39,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (ret) return ret; - if (!is_owner_or_cap(inode)) { + if (!inode_owner_or_capable(inode)) { ret = -EACCES; goto setflags_out; } @@ -89,7 +89,7 @@ setflags_out: case EXT2_IOC_GETVERSION: return put_user(inode->i_generation, (int __user *) arg); case EXT2_IOC_SETVERSION: - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; ret = mnt_want_write(filp->f_path.mnt); if (ret) @@ -115,7 +115,7 @@ setflags_out: if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode)) return -ENOTTY; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; if (get_user(rsv_window_size, (int __user *)arg)) diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index e4fa49e6c539..9d021c0d472a 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -435,7 +435,7 @@ ext3_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, return -EINVAL; if (!test_opt(inode->i_sb, POSIX_ACL)) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; if (value) { diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c index fc080dd561f7..f4090bd2f345 100644 --- a/fs/ext3/ioctl.c +++ b/fs/ext3/ioctl.c @@ -38,7 +38,7 @@ long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) unsigned int oldflags; unsigned int jflag; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) @@ -123,7 +123,7 @@ flags_out: __u32 generation; int err; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; err = mnt_want_write(filp->f_path.mnt); @@ -192,7 +192,7 @@ setversion_out: if (err) return err; - if (!is_owner_or_cap(inode)) { + if (!inode_owner_or_capable(inode)) { err = -EACCES; goto setrsvsz_out; } diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index e0270d1f8d82..21eacd7b7d79 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -433,7 +433,7 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value, return -EINVAL; if (!test_opt(inode->i_sb, POSIX_ACL)) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; if (value) { diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index eb3bc2fe647e..a84faa110bcd 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -38,7 +38,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) unsigned int oldflags; unsigned int jflag; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) @@ -146,7 +146,7 @@ flags_out: __u32 generation; int err; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; err = mnt_want_write(filp->f_path.mnt); @@ -298,7 +298,7 @@ mext_out: case EXT4_IOC_MIGRATE: { int err; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; err = mnt_want_write(filp->f_path.mnt); @@ -320,7 +320,7 @@ mext_out: case EXT4_IOC_ALLOC_DA_BLKS: { int err; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; err = mnt_want_write(filp->f_path.mnt); diff --git a/fs/fcntl.c b/fs/fcntl.c index 6c82e5bac039..22764c7c8382 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -159,7 +159,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg) /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; /* required for strict SunOS emulation */ diff --git a/fs/generic_acl.c b/fs/generic_acl.c index 06c48a891832..8f26d1a58912 100644 --- a/fs/generic_acl.c +++ b/fs/generic_acl.c @@ -74,7 +74,7 @@ generic_acl_set(struct dentry *dentry, const char *name, const void *value, return -EINVAL; if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; if (value) { acl = posix_acl_from_xattr(value, size); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 4074b952b059..b2682e073eee 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -221,7 +221,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) goto out_drop_write; error = -EACCES; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) goto out; error = 0; diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index 508ce662ce12..fbaa6690c8e0 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -47,7 +47,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) if (err) goto out; - if (!is_owner_or_cap(inode)) { + if (!inode_owner_or_capable(inode)) { err = -EACCES; goto out_drop_write; } diff --git a/fs/inode.c b/fs/inode.c index a21d5a938a17..0b3da4a77704 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1735,11 +1735,14 @@ void inode_init_owner(struct inode *inode, const struct inode *dir, } EXPORT_SYMBOL(inode_init_owner); -/* - * return true if current either has CAP_FOWNER to the - * file, or owns the file. +/** + * inode_owner_or_capable - check current task permissions to inode + * @inode: inode being checked + * + * Return true if current either has CAP_FOWNER to the inode, or + * owns the file. */ -bool is_owner_or_cap(const struct inode *inode) +bool inode_owner_or_capable(const struct inode *inode) { struct user_namespace *ns = inode_userns(inode); @@ -1749,4 +1752,4 @@ bool is_owner_or_cap(const struct inode *inode) return true; return false; } -EXPORT_SYMBOL(is_owner_or_cap); +EXPORT_SYMBOL(inode_owner_or_capable); diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 95b79672150a..828a0e1ea438 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -402,7 +402,7 @@ static int jffs2_acl_setxattr(struct dentry *dentry, const char *name, if (name[0] != '\0') return -EINVAL; - if (!is_owner_or_cap(dentry->d_inode)) + if (!inode_owner_or_capable(dentry->d_inode)) return -EPERM; if (value) { diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index afe222bf300f..6f98a1866776 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -72,7 +72,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (err) return err; - if (!is_owner_or_cap(inode)) { + if (!inode_owner_or_capable(inode)) { err = -EACCES; goto setflags_out; } diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 3fa4c32272df..24838f1eeee5 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -678,7 +678,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name, struct posix_acl *acl; int rc; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; /* diff --git a/fs/logfs/file.c b/fs/logfs/file.c index e86376b87af1..c2ad7028def4 100644 --- a/fs/logfs/file.c +++ b/fs/logfs/file.c @@ -196,7 +196,7 @@ long logfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (IS_RDONLY(inode)) return -EROFS; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; err = get_user(flags, (int __user *)arg); diff --git a/fs/namei.c b/fs/namei.c index dbb45a652ae3..fc858b1124c2 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2036,7 +2036,7 @@ static int may_open(struct path *path, int acc_mode, int flag) } /* O_NOATIME can only be set by the owner or superuser */ - if (flag & O_NOATIME && !is_owner_or_cap(inode)) + if (flag & O_NOATIME && !inode_owner_or_capable(inode)) return -EPERM; /* diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 95c04c2f2b3e..f2469ba6246b 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -113,7 +113,7 @@ static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp, unsigned int flags, oldflags; int ret; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; if (get_user(flags, (int __user *)argp)) diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 704f6b1742f3..90f2729b7a5b 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -497,7 +497,7 @@ static int ocfs2_xattr_set_acl(struct dentry *dentry, const char *name, if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; if (value) { diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 7a4868196152..09de77ce002a 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -82,7 +82,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, } status = -EACCES; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) goto bail_unlock; if (!S_ISDIR(inode->i_mode)) diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 79265fdc317a..4e153051bc75 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -59,7 +59,7 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (err) break; - if (!is_owner_or_cap(inode)) { + if (!inode_owner_or_capable(inode)) { err = -EPERM; goto setflags_out; } @@ -103,7 +103,7 @@ setflags_out: err = put_user(inode->i_generation, (int __user *)arg); break; case REISERFS_IOC_SETVERSION: - if (!is_owner_or_cap(inode)) { + if (!inode_owner_or_capable(inode)) { err = -EPERM; break; } diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 90d2fcb67a31..3dc38f1206fc 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -26,7 +26,7 @@ posix_acl_set(struct dentry *dentry, const char *name, const void *value, size_t jcreate_blocks; if (!reiserfs_posixacl(inode->i_sb)) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; if (value) { diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 8aacd64957a2..548acf494afd 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -160,7 +160,7 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (IS_RDONLY(inode)) return -EROFS; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EACCES; if (get_user(flags, (int __user *) arg)) diff --git a/fs/utimes.c b/fs/utimes.c index 179b58690657..ba653f3dc1bc 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -95,7 +95,7 @@ static int utimes_common(struct path *path, struct timespec *times) if (IS_IMMUTABLE(inode)) goto mnt_drop_write_and_out; - if (!is_owner_or_cap(inode)) { + if (!inode_owner_or_capable(inode)) { error = inode_permission(inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; diff --git a/fs/xattr.c b/fs/xattr.c index 01bb8135e14a..a19acdb81cd1 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -59,7 +59,7 @@ xattr_permission(struct inode *inode, const char *name, int mask) if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EPERM; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && - (mask & MAY_WRITE) && !is_owner_or_cap(inode)) + (mask & MAY_WRITE) && !inode_owner_or_capable(inode)) return -EPERM; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 9eebc646d14a..4dda076c24a1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1463,7 +1463,7 @@ enum { */ extern struct user_namespace init_user_ns; #define inode_userns(inode) (&init_user_ns) -extern bool is_owner_or_cap(const struct inode *inode); +extern bool inode_owner_or_capable(const struct inode *inode); /* not quite ready to be deprecated, but... */ extern void lock_super(struct super_block *); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index c67f863d3546..f9c3764e4859 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2725,7 +2725,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name, if (!(sbsec->flags & SE_SBLABELSUPP)) return -EOPNOTSUPP; - if (!is_owner_or_cap(inode)) + if (!inode_owner_or_capable(inode)) return -EPERM; COMMON_AUDIT_DATA_INIT(&ad, FS); -- cgit v1.2.3 From f283c86afe6aa70b733d1ecebad5d9464943b774 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 22 Mar 2011 22:23:39 +1100 Subject: fs: remove inode_lock from iput_final and prune_icache Now that inode state changes are protected by the inode->i_lock and the inode LRU manipulations by the inode_lru_lock, we can remove the inode_lock from prune_icache and the initial part of iput_final(). instead of using the inode_lock to protect the inode during iput_final, use the inode->i_lock instead. This protects the inode against new references being taken while we change the inode state to I_FREEING, as well as preventing prune_icache from grabbing the inode while we are manipulating it. Hence we no longer need the inode_lock in iput_final prior to setting I_FREEING on the inode. For prune_icache, we no longer need the inode_lock to protect the LRU list, and the inodes themselves are protected against freeing races by the inode->i_lock. Hence we can lift the inode_lock from prune_icache as well. Signed-off-by: Dave Chinner Signed-off-by: Al Viro --- Documentation/filesystems/Locking | 2 +- Documentation/filesystems/porting | 16 +++++++++++----- Documentation/filesystems/vfs.txt | 2 +- fs/inode.c | 17 +++-------------- fs/logfs/inode.c | 2 +- 5 files changed, 17 insertions(+), 22 deletions(-) (limited to 'fs/logfs') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 2e994efe12cb..61b31acb9176 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -128,7 +128,7 @@ alloc_inode: destroy_inode: dirty_inode: (must not sleep) write_inode: -drop_inode: !!!inode_lock!!! +drop_inode: !!!inode->i_lock!!! evict_inode: put_super: write write_super: read diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 0c986c9e8519..6e29954851a2 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -298,11 +298,14 @@ be used instead. It gets called whenever the inode is evicted, whether it has remaining links or not. Caller does *not* evict the pagecache or inode-associated metadata buffers; getting rid of those is responsibility of method, as it had been for ->delete_inode(). - ->drop_inode() returns int now; it's called on final iput() with inode_lock -held and it returns true if filesystems wants the inode to be dropped. As before, -generic_drop_inode() is still the default and it's been updated appropriately. -generic_delete_inode() is also alive and it consists simply of return 1. Note that -all actual eviction work is done by caller after ->drop_inode() returns. + + ->drop_inode() returns int now; it's called on final iput() with +inode->i_lock held and it returns true if filesystems wants the inode to be +dropped. As before, generic_drop_inode() is still the default and it's been +updated appropriately. generic_delete_inode() is also alive and it consists +simply of return 1. Note that all actual eviction work is done by caller after +->drop_inode() returns. + clear_inode() is gone; use end_writeback() instead. As before, it must be called exactly once on each call of ->evict_inode() (as it used to be for each call of ->delete_inode()). Unlike before, if you are using inode-associated @@ -395,6 +398,9 @@ Currently you can only have FALLOC_FL_PUNCH_HOLE with FALLOC_FL_KEEP_SIZE set, so the i_size should not change when hole punching, even when puching the end of a file off. +-- +[mandatory] + -- [mandatory] ->get_sb() is gone. Switch to use of ->mount(). Typically it's just diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 306f0ae8df09..80815ed654cb 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -254,7 +254,7 @@ or bottom half). should be synchronous or not, not all filesystems check this flag. drop_inode: called when the last access to the inode is dropped, - with the inode_lock spinlock held. + with the inode->i_lock spinlock held. This method should be either NULL (normal UNIX filesystem semantics) or "generic_delete_inode" (for filesystems that do not diff --git a/fs/inode.c b/fs/inode.c index b19cb6ee6ca3..389f5a247599 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -650,7 +650,6 @@ static void prune_icache(int nr_to_scan) unsigned long reap = 0; down_read(&iprune_sem); - spin_lock(&inode_lock); spin_lock(&inode_lru_lock); for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) { struct inode *inode; @@ -676,8 +675,8 @@ static void prune_icache(int nr_to_scan) */ if (atomic_read(&inode->i_count) || (inode->i_state & ~I_REFERENCED)) { - spin_unlock(&inode->i_lock); list_del_init(&inode->i_lru); + spin_unlock(&inode->i_lock); inodes_stat.nr_unused--; continue; } @@ -685,20 +684,18 @@ static void prune_icache(int nr_to_scan) /* recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; - spin_unlock(&inode->i_lock); list_move(&inode->i_lru, &inode_lru); + spin_unlock(&inode->i_lock); continue; } if (inode_has_buffers(inode) || inode->i_data.nrpages) { __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&inode_lru_lock); - spin_unlock(&inode_lock); if (remove_inode_buffers(inode)) reap += invalidate_mapping_pages(&inode->i_data, 0, -1); iput(inode); - spin_lock(&inode_lock); spin_lock(&inode_lru_lock); if (inode != list_entry(inode_lru.next, @@ -724,7 +721,6 @@ static void prune_icache(int nr_to_scan) else __count_vm_events(PGINODESTEAL, reap); spin_unlock(&inode_lru_lock); - spin_unlock(&inode_lock); dispose_list(&freeable); up_read(&iprune_sem); @@ -1082,7 +1078,6 @@ EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { - spin_lock(&inode_lock); spin_lock(&inode->i_lock); if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { __iget(inode); @@ -1096,7 +1091,6 @@ struct inode *igrab(struct inode *inode) */ inode = NULL; } - spin_unlock(&inode_lock); return inode; } EXPORT_SYMBOL(igrab); @@ -1439,7 +1433,6 @@ static void iput_final(struct inode *inode) const struct super_operations *op = inode->i_sb->s_op; int drop; - spin_lock(&inode->i_lock); WARN_ON(inode->i_state & I_NEW); if (op && op->drop_inode) @@ -1452,16 +1445,13 @@ static void iput_final(struct inode *inode) if (!(inode->i_state & (I_DIRTY|I_SYNC))) inode_lru_list_add(inode); spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); return; } if (!drop) { inode->i_state |= I_WILL_FREE; spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); write_inode_now(inode, 1); - spin_lock(&inode_lock); spin_lock(&inode->i_lock); WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_WILL_FREE; @@ -1470,7 +1460,6 @@ static void iput_final(struct inode *inode) inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); evict(inode); } @@ -1489,7 +1478,7 @@ void iput(struct inode *inode) if (inode) { BUG_ON(inode->i_state & I_CLEAR); - if (atomic_dec_and_lock(&inode->i_count, &inode_lock)) + if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) iput_final(inode); } } diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index 03b8c240aeda..edfea7a3a747 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -293,7 +293,7 @@ static int logfs_write_inode(struct inode *inode, struct writeback_control *wbc) return ret; } -/* called with inode_lock held */ +/* called with inode->i_lock held */ static int logfs_drop_inode(struct inode *inode) { struct logfs_super *super = logfs_super(inode->i_sb); -- cgit v1.2.3