diff options
Diffstat (limited to 'fs')
66 files changed, 2520 insertions, 696 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index e54be7058359e0..5e817902cb3b40 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -382,10 +382,8 @@ config QUOTA usage (also called disk quotas). Currently, it works for the ext2, ext3, and reiserfs file system. ext3 also supports journalled quotas for which you don't need to run quotacheck(8) after an unclean - shutdown. You need additional software in order to use quota support - (you can download sources from - <http://www.sf.net/projects/linuxquota/>). For further details, read - the Quota mini-HOWTO, available from + shutdown. + For further details, read the Quota mini-HOWTO, available from <http://www.tldp.org/docs.html#howto>, or the documentation provided with the quota tools. Probably the quota support is only useful for multi user systems. If unsure, say N. @@ -403,8 +401,7 @@ config QFMT_V2 depends on QUOTA help This quota format allows using quotas with 32-bit UIDs/GIDs. If you - need this functionality say Y here. Note that you will need recent - quota utilities (>= 3.01) for new quota format with this kernel. + need this functionality say Y here. config QUOTACTL bool @@ -783,28 +780,6 @@ config SYSFS Designers of embedded systems may wish to say N here to conserve space. -config DEVPTS_FS_XATTR - bool "/dev/pts Extended Attributes" - depends on UNIX98_PTYS - help - Extended attributes are name:value pairs associated with inodes by - the kernel or by users (see the attr(5) manual page, or visit - <http://acl.bestbits.at/> for details). - - If unsure, say N. - -config DEVPTS_FS_SECURITY - bool "/dev/pts Security Labels" - depends on DEVPTS_FS_XATTR - help - Security labels support alternative access control models - implemented by security modules like SELinux. This option - enables an extended attribute handler for file security - labels in the /dev/pts filesystem. - - If you are not using a security module that requires using - extended attributes for file security labels, say N. - config TMPFS bool "Virtual memory file system support (former shm fs)" help @@ -817,27 +792,6 @@ config TMPFS See <file:Documentation/filesystems/tmpfs.txt> for details. -config TMPFS_XATTR - bool "tmpfs Extended Attributes" - depends on TMPFS - help - Extended attributes are name:value pairs associated with inodes by - the kernel or by users (see the attr(5) manual page, or visit - <http://acl.bestbits.at/> for details). - - If unsure, say N. - -config TMPFS_SECURITY - bool "tmpfs Security Labels" - depends on TMPFS_XATTR - help - Security labels support alternative access control models - implemented by security modules like SELinux. This option - enables an extended attribute handler for file security - labels in the tmpfs filesystem. - If you are not using a security module that requires using - extended attributes for file security labels, say N. - config HUGETLBFS bool "HugeTLB file system support" depends X86 || IA64 || PPC64 || SPARC64 || SUPERH || X86_64 || BROKEN @@ -859,6 +813,18 @@ config RAMFS To compile this as a module, choose M here: the module will be called ramfs. +config RELAYFS_FS + tristate "Relayfs file system support" + ---help--- + Relayfs is a high-speed data relay filesystem designed to provide + an efficient mechanism for tools and facilities to relay large + amounts of data from kernel space to user space. + + To compile this code as a module, choose M here: the module will be + called relayfs. + + If unsure, say N. + endmenu menu "Miscellaneous filesystems" diff --git a/fs/Makefile b/fs/Makefile index cf95eb894fd537..15158309dee4ae 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -90,6 +90,7 @@ obj-$(CONFIG_AUTOFS_FS) += autofs/ obj-$(CONFIG_AUTOFS4_FS) += autofs4/ obj-$(CONFIG_ADFS_FS) += adfs/ obj-$(CONFIG_UDF_FS) += udf/ +obj-$(CONFIG_RELAYFS_FS) += relayfs/ obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/ obj-$(CONFIG_JFS_FS) += jfs/ obj-$(CONFIG_XFS_FS) += xfs/ diff --git a/fs/aio.c b/fs/aio.c index 06d7d4390fe7dd..4f641abac3c092 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -567,6 +567,10 @@ static void use_mm(struct mm_struct *mm) atomic_inc(&mm->mm_count); tsk->mm = mm; tsk->active_mm = mm; + /* + * Note that on UML this *requires* PF_BORROWED_MM to be set, otherwise + * it won't work. Update it accordingly if you change it here + */ activate_mm(active_mm, mm); task_unlock(tsk); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index c8998dc668824d..7974efa107bce1 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -520,7 +520,7 @@ static int load_flat_file(struct linux_binprm * bprm, DBG_FLT("BINFMT_FLAT: ROM mapping of file (we hope)\n"); down_write(¤t->mm->mmap_sem); - textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, MAP_SHARED, 0); + textpos = do_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, MAP_PRIVATE, 0); up_write(¤t->mm->mmap_sem); if (!textpos || textpos >= (unsigned long) -4096) { if (!textpos) diff --git a/fs/bio.c b/fs/bio.c index 1f2d4649b18801..bf3ec9d2b54c6d 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -104,18 +104,22 @@ static inline struct bio_vec *bvec_alloc_bs(unsigned int __nocast gfp_mask, int return bvl; } -/* - * default destructor for a bio allocated with bio_alloc_bioset() - */ -static void bio_destructor(struct bio *bio) +void bio_free(struct bio *bio, struct bio_set *bio_set) { const int pool_idx = BIO_POOL_IDX(bio); - struct bio_set *bs = bio->bi_set; BIO_BUG_ON(pool_idx >= BIOVEC_NR_POOLS); - mempool_free(bio->bi_io_vec, bs->bvec_pools[pool_idx]); - mempool_free(bio, bs->bio_pool); + mempool_free(bio->bi_io_vec, bio_set->bvec_pools[pool_idx]); + mempool_free(bio, bio_set->bio_pool); +} + +/* + * default destructor for a bio allocated with bio_alloc_bioset() + */ +static void bio_fs_destructor(struct bio *bio) +{ + bio_free(bio, fs_bio_set); } inline void bio_init(struct bio *bio) @@ -171,8 +175,6 @@ struct bio *bio_alloc_bioset(unsigned int __nocast gfp_mask, int nr_iovecs, stru bio->bi_max_vecs = bvec_slabs[idx].nr_vecs; } bio->bi_io_vec = bvl; - bio->bi_destructor = bio_destructor; - bio->bi_set = bs; } out: return bio; @@ -180,7 +182,12 @@ out: struct bio *bio_alloc(unsigned int __nocast gfp_mask, int nr_iovecs) { - return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set); + struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set); + + if (bio) + bio->bi_destructor = bio_fs_destructor; + + return bio; } void zero_fill_bio(struct bio *bio) @@ -273,8 +280,10 @@ struct bio *bio_clone(struct bio *bio, unsigned int __nocast gfp_mask) { struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set); - if (b) + if (b) { + b->bi_destructor = bio_fs_destructor; __bio_clone(b, bio); + } return b; } @@ -1075,6 +1084,7 @@ subsys_initcall(init_bio); EXPORT_SYMBOL(bio_alloc); EXPORT_SYMBOL(bio_put); +EXPORT_SYMBOL(bio_free); EXPORT_SYMBOL(bio_endio); EXPORT_SYMBOL(bio_init); EXPORT_SYMBOL(__bio_clone); diff --git a/fs/buffer.c b/fs/buffer.c index 6a25d7df89b176..1c62203a4906ec 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -917,8 +917,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * contents - it is a noop if I/O is still in * flight on potentially older contents. */ - wait_on_buffer(bh); - ll_rw_block(WRITE, 1, &bh); + ll_rw_block(SWRITE, 1, &bh); brelse(bh); spin_lock(lock); } @@ -2793,21 +2792,22 @@ int submit_bh(int rw, struct buffer_head * bh) /** * ll_rw_block: low-level access to block devices (DEPRECATED) - * @rw: whether to %READ or %WRITE or maybe %READA (readahead) + * @rw: whether to %READ or %WRITE or %SWRITE or maybe %READA (readahead) * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * - * ll_rw_block() takes an array of pointers to &struct buffer_heads, - * and requests an I/O operation on them, either a %READ or a %WRITE. - * The third %READA option is described in the documentation for - * generic_make_request() which ll_rw_block() calls. + * ll_rw_block() takes an array of pointers to &struct buffer_heads, and + * requests an I/O operation on them, either a %READ or a %WRITE. The third + * %SWRITE is like %WRITE only we make sure that the *current* data in buffers + * are sent to disk. The fourth %READA option is described in the documentation + * for generic_make_request() which ll_rw_block() calls. * * This function drops any buffer that it cannot get a lock on (with the - * BH_Lock state bit), any buffer that appears to be clean when doing a - * write request, and any buffer that appears to be up-to-date when doing - * read request. Further it marks as clean buffers that are processed for - * writing (the buffer cache won't assume that they are actually clean until - * the buffer gets unlocked). + * BH_Lock state bit) unless SWRITE is required, any buffer that appears to be + * clean when doing a write request, and any buffer that appears to be + * up-to-date when doing read request. Further it marks as clean buffers that + * are processed for writing (the buffer cache won't assume that they are + * actually clean until the buffer gets unlocked). * * ll_rw_block sets b_end_io to simple completion handler that marks * the buffer up-to-date (if approriate), unlocks the buffer and wakes @@ -2823,11 +2823,13 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; - if (test_set_buffer_locked(bh)) + if (rw == SWRITE) + lock_buffer(bh); + else if (test_set_buffer_locked(bh)) continue; get_bh(bh); - if (rw == WRITE) { + if (rw == WRITE || rw == SWRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; submit_bh(WRITE, bh); @@ -3046,10 +3048,9 @@ struct buffer_head *alloc_buffer_head(unsigned int __nocast gfp_flags) { struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags); if (ret) { - preempt_disable(); - __get_cpu_var(bh_accounting).nr++; + get_cpu_var(bh_accounting).nr++; recalc_bh_state(); - preempt_enable(); + put_cpu_var(bh_accounting); } return ret; } @@ -3059,10 +3060,9 @@ void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); - preempt_disable(); - __get_cpu_var(bh_accounting).nr--; + get_cpu_var(bh_accounting).nr--; recalc_bh_state(); - preempt_enable(); + put_cpu_var(bh_accounting); } EXPORT_SYMBOL(free_buffer_head); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index e568cc47a7f930..3217ac5f6bd7aa 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -836,7 +836,7 @@ cifs_parse_mount_options(char *options, const char *devname,struct smb_vol *vol) /* go from value to value + temp_len condensing double commas to singles. Note that this ends up allocating a few bytes too many, which is ok */ - vol->password = kcalloc(1, temp_len, GFP_KERNEL); + vol->password = kzalloc(temp_len, GFP_KERNEL); if(vol->password == NULL) { printk("CIFS: no memory for pass\n"); return 1; @@ -851,7 +851,7 @@ cifs_parse_mount_options(char *options, const char *devname,struct smb_vol *vol) } vol->password[j] = 0; } else { - vol->password = kcalloc(1, temp_len+1, GFP_KERNEL); + vol->password = kzalloc(temp_len+1, GFP_KERNEL); if(vol->password == NULL) { printk("CIFS: no memory for pass\n"); return 1; @@ -1317,7 +1317,7 @@ ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket, sessinit is sent but no second negprot */ struct rfc1002_session_packet * ses_init_buf; struct smb_hdr * smb_buf; - ses_init_buf = kcalloc(1, sizeof(struct rfc1002_session_packet), GFP_KERNEL); + ses_init_buf = kzalloc(sizeof(struct rfc1002_session_packet), GFP_KERNEL); if(ses_init_buf) { ses_init_buf->trailer.session_req.called_len = 32; rfc1002mangle(ses_init_buf->trailer.session_req.called_name, @@ -1964,7 +1964,7 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, /* We look for obvious messed up bcc or strings in response so we do not go off the end since (at least) WIN2K and Windows XP have a major bug in not null terminating last Unicode string in response */ - ses->serverOS = kcalloc(1, 2 * (len + 1), GFP_KERNEL); + ses->serverOS = kzalloc(2 * (len + 1), GFP_KERNEL); if(ses->serverOS == NULL) goto sesssetup_nomem; cifs_strfromUCS_le(ses->serverOS, @@ -1976,7 +1976,7 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, if (remaining_words > 0) { len = UniStrnlen((wchar_t *)bcc_ptr, remaining_words-1); - ses->serverNOS = kcalloc(1, 2 * (len + 1),GFP_KERNEL); + ses->serverNOS = kzalloc(2 * (len + 1),GFP_KERNEL); if(ses->serverNOS == NULL) goto sesssetup_nomem; cifs_strfromUCS_le(ses->serverNOS, @@ -1994,7 +1994,7 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, len = UniStrnlen((wchar_t *) bcc_ptr, remaining_words); /* last string is not always null terminated (for e.g. for Windows XP & 2000) */ ses->serverDomain = - kcalloc(1, 2*(len+1),GFP_KERNEL); + kzalloc(2*(len+1),GFP_KERNEL); if(ses->serverDomain == NULL) goto sesssetup_nomem; cifs_strfromUCS_le(ses->serverDomain, @@ -2005,22 +2005,22 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, } /* else no more room so create dummy domain string */ else ses->serverDomain = - kcalloc(1, 2, GFP_KERNEL); + kzalloc(2, GFP_KERNEL); } else { /* no room so create dummy domain and NOS string */ /* if these kcallocs fail not much we can do, but better to not fail the sesssetup itself */ ses->serverDomain = - kcalloc(1, 2, GFP_KERNEL); + kzalloc(2, GFP_KERNEL); ses->serverNOS = - kcalloc(1, 2, GFP_KERNEL); + kzalloc(2, GFP_KERNEL); } } else { /* ASCII */ len = strnlen(bcc_ptr, 1024); if (((long) bcc_ptr + len) - (long) pByteArea(smb_buffer_response) <= BCC(smb_buffer_response)) { - ses->serverOS = kcalloc(1, len + 1,GFP_KERNEL); + ses->serverOS = kzalloc(len + 1,GFP_KERNEL); if(ses->serverOS == NULL) goto sesssetup_nomem; strncpy(ses->serverOS,bcc_ptr, len); @@ -2030,7 +2030,7 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, bcc_ptr++; len = strnlen(bcc_ptr, 1024); - ses->serverNOS = kcalloc(1, len + 1,GFP_KERNEL); + ses->serverNOS = kzalloc(len + 1,GFP_KERNEL); if(ses->serverNOS == NULL) goto sesssetup_nomem; strncpy(ses->serverNOS, bcc_ptr, len); @@ -2039,7 +2039,7 @@ CIFSSessSetup(unsigned int xid, struct cifsSesInfo *ses, bcc_ptr++; len = strnlen(bcc_ptr, 1024); - ses->serverDomain = kcalloc(1, len + 1,GFP_KERNEL); + ses->serverDomain = kzalloc(len + 1,GFP_KERNEL); if(ses->serverDomain == NULL) goto sesssetup_nomem; strncpy(ses->serverDomain, bcc_ptr, len); @@ -2240,7 +2240,7 @@ CIFSSpnegoSessSetup(unsigned int xid, struct cifsSesInfo *ses, the end since (at least) WIN2K and Windows XP have a major bug in not null terminating last Unicode string in response */ ses->serverOS = - kcalloc(1, 2 * (len + 1), GFP_KERNEL); + kzalloc(2 * (len + 1), GFP_KERNEL); cifs_strfromUCS_le(ses->serverOS, (wchar_t *) bcc_ptr, len, @@ -2254,7 +2254,7 @@ CIFSSpnegoSessSetup(unsigned int xid, struct cifsSesInfo *ses, remaining_words - 1); ses->serverNOS = - kcalloc(1, 2 * (len + 1), + kzalloc(2 * (len + 1), GFP_KERNEL); cifs_strfromUCS_le(ses->serverNOS, (wchar_t *)bcc_ptr, @@ -2267,7 +2267,7 @@ CIFSSpnegoSessSetup(unsigned int xid, struct cifsSesInfo *ses, if (remaining_words > 0) { len = UniStrnlen((wchar_t *) bcc_ptr, remaining_words); /* last string is not always null terminated (for e.g. for Windows XP & 2000) */ - ses->serverDomain = kcalloc(1, 2*(len+1),GFP_KERNEL); + ses->serverDomain = kzalloc(2*(len+1),GFP_KERNEL); cifs_strfromUCS_le(ses->serverDomain, (wchar_t *)bcc_ptr, len, @@ -2278,10 +2278,10 @@ CIFSSpnegoSessSetup(unsigned int xid, struct cifsSesInfo *ses, } /* else no more room so create dummy domain string */ else ses->serverDomain = - kcalloc(1, 2,GFP_KERNEL); + kzalloc(2,GFP_KERNEL); } else { /* no room so create dummy domain and NOS string */ - ses->serverDomain = kcalloc(1, 2, GFP_KERNEL); - ses->serverNOS = kcalloc(1, 2, GFP_KERNEL); + ses->serverDomain = kzalloc(2, GFP_KERNEL); + ses->serverNOS = kzalloc(2, GFP_KERNEL); } } else { /* ASCII */ @@ -2289,7 +2289,7 @@ CIFSSpnegoSessSetup(unsigned int xid, struct cifsSesInfo *ses, if (((long) bcc_ptr + len) - (long) pByteArea(smb_buffer_response) <= BCC(smb_buffer_response)) { - ses->serverOS = kcalloc(1, len + 1, GFP_KERNEL); + ses->serverOS = kzalloc(len + 1, GFP_KERNEL); strncpy(ses->serverOS, bcc_ptr, len); bcc_ptr += len; @@ -2297,14 +2297,14 @@ CIFSSpnegoSessSetup(unsigned int xid, struct cifsSesInfo *ses, bcc_ptr++; len = strnlen(bcc_ptr, 1024); - ses->serverNOS = kcalloc(1, len + 1,GFP_KERNEL); + ses->serverNOS = kzalloc(len + 1,GFP_KERNEL); strncpy(ses->serverNOS, bcc_ptr, len); bcc_ptr += len; bcc_ptr[0] = 0; bcc_ptr++; len = strnlen(bcc_ptr, 1024); - ses->serverDomain = kcalloc(1, len + 1, GFP_KERNEL); + ses->serverDomain = kzalloc(len + 1, GFP_KERNEL); strncpy(ses->serverDomain, bcc_ptr, len); bcc_ptr += len; bcc_ptr[0] = 0; @@ -2554,7 +2554,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, the end since (at least) WIN2K and Windows XP have a major bug in not null terminating last Unicode string in response */ ses->serverOS = - kcalloc(1, 2 * (len + 1), GFP_KERNEL); + kzalloc(2 * (len + 1), GFP_KERNEL); cifs_strfromUCS_le(ses->serverOS, (wchar_t *) bcc_ptr, len, @@ -2569,7 +2569,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, remaining_words - 1); ses->serverNOS = - kcalloc(1, 2 * (len + 1), + kzalloc(2 * (len + 1), GFP_KERNEL); cifs_strfromUCS_le(ses-> serverNOS, @@ -2586,7 +2586,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, len = UniStrnlen((wchar_t *) bcc_ptr, remaining_words); /* last string is not always null terminated (for e.g. for Windows XP & 2000) */ ses->serverDomain = - kcalloc(1, 2 * + kzalloc(2 * (len + 1), GFP_KERNEL); @@ -2612,13 +2612,13 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, } /* else no more room so create dummy domain string */ else ses->serverDomain = - kcalloc(1, 2, + kzalloc(2, GFP_KERNEL); } else { /* no room so create dummy domain and NOS string */ ses->serverDomain = - kcalloc(1, 2, GFP_KERNEL); + kzalloc(2, GFP_KERNEL); ses->serverNOS = - kcalloc(1, 2, GFP_KERNEL); + kzalloc(2, GFP_KERNEL); } } else { /* ASCII */ len = strnlen(bcc_ptr, 1024); @@ -2626,7 +2626,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, pByteArea(smb_buffer_response) <= BCC(smb_buffer_response)) { ses->serverOS = - kcalloc(1, len + 1, + kzalloc(len + 1, GFP_KERNEL); strncpy(ses->serverOS, bcc_ptr, len); @@ -2637,7 +2637,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, len = strnlen(bcc_ptr, 1024); ses->serverNOS = - kcalloc(1, len + 1, + kzalloc(len + 1, GFP_KERNEL); strncpy(ses->serverNOS, bcc_ptr, len); bcc_ptr += len; @@ -2646,7 +2646,7 @@ CIFSNTLMSSPNegotiateSessSetup(unsigned int xid, len = strnlen(bcc_ptr, 1024); ses->serverDomain = - kcalloc(1, len + 1, + kzalloc(len + 1, GFP_KERNEL); strncpy(ses->serverDomain, bcc_ptr, len); bcc_ptr += len; @@ -2948,7 +2948,7 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, the end since (at least) WIN2K and Windows XP have a major bug in not null terminating last Unicode string in response */ ses->serverOS = - kcalloc(1, 2 * (len + 1), GFP_KERNEL); + kzalloc(2 * (len + 1), GFP_KERNEL); cifs_strfromUCS_le(ses->serverOS, (wchar_t *) bcc_ptr, len, @@ -2963,7 +2963,7 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, remaining_words - 1); ses->serverNOS = - kcalloc(1, 2 * (len + 1), + kzalloc(2 * (len + 1), GFP_KERNEL); cifs_strfromUCS_le(ses-> serverNOS, @@ -2979,7 +2979,7 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, len = UniStrnlen((wchar_t *) bcc_ptr, remaining_words); /* last string not always null terminated (e.g. for Windows XP & 2000) */ ses->serverDomain = - kcalloc(1, 2 * + kzalloc(2 * (len + 1), GFP_KERNEL); @@ -3004,17 +3004,17 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, = 0; } /* else no more room so create dummy domain string */ else - ses->serverDomain = kcalloc(1, 2,GFP_KERNEL); + ses->serverDomain = kzalloc(2,GFP_KERNEL); } else { /* no room so create dummy domain and NOS string */ - ses->serverDomain = kcalloc(1, 2, GFP_KERNEL); - ses->serverNOS = kcalloc(1, 2, GFP_KERNEL); + ses->serverDomain = kzalloc(2, GFP_KERNEL); + ses->serverNOS = kzalloc(2, GFP_KERNEL); } } else { /* ASCII */ len = strnlen(bcc_ptr, 1024); if (((long) bcc_ptr + len) - (long) pByteArea(smb_buffer_response) <= BCC(smb_buffer_response)) { - ses->serverOS = kcalloc(1, len + 1,GFP_KERNEL); + ses->serverOS = kzalloc(len + 1,GFP_KERNEL); strncpy(ses->serverOS,bcc_ptr, len); bcc_ptr += len; @@ -3022,14 +3022,14 @@ CIFSNTLMSSPAuthSessSetup(unsigned int xid, struct cifsSesInfo *ses, bcc_ptr++; len = strnlen(bcc_ptr, 1024); - ses->serverNOS = kcalloc(1, len+1,GFP_KERNEL); + ses->serverNOS = kzalloc(len+1,GFP_KERNEL); strncpy(ses->serverNOS, bcc_ptr, len); bcc_ptr += len; bcc_ptr[0] = 0; bcc_ptr++; len = strnlen(bcc_ptr, 1024); - ses->serverDomain = kcalloc(1, len+1,GFP_KERNEL); + ses->serverDomain = kzalloc(len+1,GFP_KERNEL); strncpy(ses->serverDomain, bcc_ptr, len); bcc_ptr += len; bcc_ptr[0] = 0; @@ -3141,7 +3141,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, if(tcon->nativeFileSystem) kfree(tcon->nativeFileSystem); tcon->nativeFileSystem = - kcalloc(1, length + 2, GFP_KERNEL); + kzalloc(length + 2, GFP_KERNEL); cifs_strfromUCS_le(tcon->nativeFileSystem, (wchar_t *) bcc_ptr, length, nls_codepage); @@ -3159,7 +3159,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, if(tcon->nativeFileSystem) kfree(tcon->nativeFileSystem); tcon->nativeFileSystem = - kcalloc(1, length + 1, GFP_KERNEL); + kzalloc(length + 1, GFP_KERNEL); strncpy(tcon->nativeFileSystem, bcc_ptr, length); } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 3f3538d4a1fad1..d335269bd91cfe 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -145,24 +145,23 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, return -ENOMEM; } - if(nd) { - if ((nd->intent.open.flags & O_ACCMODE) == O_RDONLY) - desiredAccess = GENERIC_READ; - else if ((nd->intent.open.flags & O_ACCMODE) == O_WRONLY) { - desiredAccess = GENERIC_WRITE; - write_only = TRUE; - } else if ((nd->intent.open.flags & O_ACCMODE) == O_RDWR) { - /* GENERIC_ALL is too much permission to request */ - /* can cause unnecessary access denied on create */ - /* desiredAccess = GENERIC_ALL; */ - desiredAccess = GENERIC_READ | GENERIC_WRITE; + if(nd && (nd->flags & LOOKUP_OPEN)) { + int oflags = nd->intent.open.flags; + + desiredAccess = 0; + if (oflags & FMODE_READ) + desiredAccess |= GENERIC_READ; + if (oflags & FMODE_WRITE) { + desiredAccess |= GENERIC_WRITE; + if (!(oflags & FMODE_READ)) + write_only = TRUE; } - if((nd->intent.open.flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) + if((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) disposition = FILE_CREATE; - else if((nd->intent.open.flags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC)) + else if((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC)) disposition = FILE_OVERWRITE_IF; - else if((nd->intent.open.flags & O_CREAT) == O_CREAT) + else if((oflags & O_CREAT) == O_CREAT) disposition = FILE_OPEN_IF; else { cFYI(1,("Create flag not set in create function")); diff --git a/fs/compat.c b/fs/compat.c index 6b06b6bae35e52..8c665705c6a07b 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -310,96 +310,6 @@ static int __init init_sys32_ioctl(void) __initcall(init_sys32_ioctl); -int register_ioctl32_conversion(unsigned int cmd, - ioctl_trans_handler_t handler) -{ - struct ioctl_trans *t; - struct ioctl_trans *new_t; - unsigned long hash = ioctl32_hash(cmd); - - new_t = kmalloc(sizeof(*new_t), GFP_KERNEL); - if (!new_t) - return -ENOMEM; - - down_write(&ioctl32_sem); - for (t = ioctl32_hash_table[hash]; t; t = t->next) { - if (t->cmd == cmd) { - printk(KERN_ERR "Trying to register duplicated ioctl32 " - "handler %x\n", cmd); - up_write(&ioctl32_sem); - kfree(new_t); - return -EINVAL; - } - } - new_t->next = NULL; - new_t->cmd = cmd; - new_t->handler = handler; - ioctl32_insert_translation(new_t); - - up_write(&ioctl32_sem); - return 0; -} -EXPORT_SYMBOL(register_ioctl32_conversion); - -static inline int builtin_ioctl(struct ioctl_trans *t) -{ - return t >= ioctl_start && t < (ioctl_start + ioctl_table_size); -} - -/* Problem: - This function cannot unregister duplicate ioctls, because they are not - unique. - When they happen we need to extend the prototype to pass the handler too. */ - -int unregister_ioctl32_conversion(unsigned int cmd) -{ - unsigned long hash = ioctl32_hash(cmd); - struct ioctl_trans *t, *t1; - - down_write(&ioctl32_sem); - - t = ioctl32_hash_table[hash]; - if (!t) { - up_write(&ioctl32_sem); - return -EINVAL; - } - - if (t->cmd == cmd) { - if (builtin_ioctl(t)) { - printk("%p tried to unregister builtin ioctl %x\n", - __builtin_return_address(0), cmd); - } else { - ioctl32_hash_table[hash] = t->next; - up_write(&ioctl32_sem); - kfree(t); - return 0; - } - } - while (t->next) { - t1 = t->next; - if (t1->cmd == cmd) { - if (builtin_ioctl(t1)) { - printk("%p tried to unregister builtin " - "ioctl %x\n", - __builtin_return_address(0), cmd); - goto out; - } else { - t->next = t1->next; - up_write(&ioctl32_sem); - kfree(t1); - return 0; - } - } - t = t1; - } - printk(KERN_ERR "Trying to free unknown 32bit ioctl handler %x\n", - cmd); -out: - up_write(&ioctl32_sem); - return -EINVAL; -} -EXPORT_SYMBOL(unregister_ioctl32_conversion); - static void compat_ioctl_error(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg) { @@ -720,14 +630,14 @@ compat_sys_io_submit(aio_context_t ctx_id, int nr, u32 __user *iocb) struct compat_ncp_mount_data { compat_int_t version; compat_uint_t ncp_fd; - compat_uid_t mounted_uid; + __compat_uid_t mounted_uid; compat_pid_t wdog_pid; unsigned char mounted_vol[NCP_VOLNAME_LEN + 1]; compat_uint_t time_out; compat_uint_t retry_count; compat_uint_t flags; - compat_uid_t uid; - compat_gid_t gid; + __compat_uid_t uid; + __compat_gid_t gid; compat_mode_t file_mode; compat_mode_t dir_mode; }; @@ -784,9 +694,9 @@ static void *do_ncp_super_data_conv(void *raw_data) struct compat_smb_mount_data { compat_int_t version; - compat_uid_t mounted_uid; - compat_uid_t uid; - compat_gid_t gid; + __compat_uid_t mounted_uid; + __compat_uid_t uid; + __compat_gid_t gid; compat_mode_t file_mode; compat_mode_t dir_mode; }; @@ -1365,6 +1275,16 @@ out: } /* + * Exactly like fs/open.c:sys_open(), except that it doesn't set the + * O_LARGEFILE flag. + */ +asmlinkage long +compat_sys_open(const char __user *filename, int flags, int mode) +{ + return do_sys_open(filename, flags, mode); +} + +/* * compat_count() counts the number of arguments/envelopes. It is basically * a copy of count() from fs/exec.c, except that it works with 32 bit argv * and envp pointers. @@ -1808,8 +1728,8 @@ struct compat_nfsctl_export { compat_dev_t ex32_dev; compat_ino_t ex32_ino; compat_int_t ex32_flags; - compat_uid_t ex32_anon_uid; - compat_gid_t ex32_anon_gid; + __compat_uid_t ex32_anon_uid; + __compat_gid_t ex32_anon_gid; }; struct compat_nfsctl_fdparm { diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 6c285efa20043c..7fe85415ae7c2d 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -39,12 +39,47 @@ static DECLARE_MUTEX(read_mutex); #define CRAMINO(x) ((x)->offset?(x)->offset<<2:1) #define OFFSET(x) ((x)->i_ino) -static struct inode *get_cramfs_inode(struct super_block *sb, struct cramfs_inode * cramfs_inode) + +static int cramfs_iget5_test(struct inode *inode, void *opaque) +{ + struct cramfs_inode *cramfs_inode = opaque; + + if (inode->i_ino != CRAMINO(cramfs_inode)) + return 0; /* does not match */ + + if (inode->i_ino != 1) + return 1; + + /* all empty directories, char, block, pipe, and sock, share inode #1 */ + + if ((inode->i_mode != cramfs_inode->mode) || + (inode->i_gid != cramfs_inode->gid) || + (inode->i_uid != cramfs_inode->uid)) + return 0; /* does not match */ + + if ((S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) && + (inode->i_rdev != old_decode_dev(cramfs_inode->size))) + return 0; /* does not match */ + + return 1; /* matches */ +} + +static int cramfs_iget5_set(struct inode *inode, void *opaque) +{ + struct cramfs_inode *cramfs_inode = opaque; + inode->i_ino = CRAMINO(cramfs_inode); + return 0; +} + +static struct inode *get_cramfs_inode(struct super_block *sb, + struct cramfs_inode * cramfs_inode) { - struct inode * inode = new_inode(sb); + struct inode *inode = iget5_locked(sb, CRAMINO(cramfs_inode), + cramfs_iget5_test, cramfs_iget5_set, + cramfs_inode); static struct timespec zerotime; - if (inode) { + if (inode && (inode->i_state & I_NEW)) { inode->i_mode = cramfs_inode->mode; inode->i_uid = cramfs_inode->uid; inode->i_size = cramfs_inode->size; @@ -58,7 +93,6 @@ static struct inode *get_cramfs_inode(struct super_block *sb, struct cramfs_inod but it's the best we can do without reading the directory contents. 1 yields the right result in GNU find, even without -noleaf option. */ - insert_inode_hash(inode); if (S_ISREG(inode->i_mode)) { inode->i_fop = &generic_ro_fops; inode->i_data.a_ops = &cramfs_aops; @@ -74,6 +108,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb, struct cramfs_inod init_special_inode(inode, inode->i_mode, old_decode_dev(cramfs_inode->size)); } + unlock_new_inode(inode); } return inode; } diff --git a/fs/devpts/Makefile b/fs/devpts/Makefile index 5800df2e50c8e6..236696efcbac7b 100644 --- a/fs/devpts/Makefile +++ b/fs/devpts/Makefile @@ -5,4 +5,3 @@ obj-$(CONFIG_UNIX98_PTYS) += devpts.o devpts-$(CONFIG_UNIX98_PTYS) := inode.o -devpts-$(CONFIG_DEVPTS_FS_SECURITY) += xattr_security.o diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 1571c8d6c23223..f2be44d4491ffc 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -18,28 +18,9 @@ #include <linux/mount.h> #include <linux/tty.h> #include <linux/devpts_fs.h> -#include <linux/xattr.h> #define DEVPTS_SUPER_MAGIC 0x1cd1 -extern struct xattr_handler devpts_xattr_security_handler; - -static struct xattr_handler *devpts_xattr_handlers[] = { -#ifdef CONFIG_DEVPTS_FS_SECURITY - &devpts_xattr_security_handler, -#endif - NULL -}; - -static struct inode_operations devpts_file_inode_operations = { -#ifdef CONFIG_DEVPTS_FS_XATTR - .setxattr = generic_setxattr, - .getxattr = generic_getxattr, - .listxattr = generic_listxattr, - .removexattr = generic_removexattr, -#endif -}; - static struct vfsmount *devpts_mnt; static struct dentry *devpts_root; @@ -102,7 +83,6 @@ devpts_fill_super(struct super_block *s, void *data, int silent) s->s_blocksize_bits = 10; s->s_magic = DEVPTS_SUPER_MAGIC; s->s_op = &devpts_sops; - s->s_xattr = devpts_xattr_handlers; s->s_time_gran = 1; inode = new_inode(s); @@ -175,7 +155,6 @@ int devpts_pty_new(struct tty_struct *tty) inode->i_gid = config.setgid ? config.gid : current->fsgid; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; init_special_inode(inode, S_IFCHR|config.mode, device); - inode->i_op = &devpts_file_inode_operations; inode->u.generic_ip = tty; dentry = get_node(number); diff --git a/fs/devpts/xattr_security.c b/fs/devpts/xattr_security.c deleted file mode 100644 index 864cb5c79baaf7..00000000000000 --- a/fs/devpts/xattr_security.c +++ /dev/null @@ -1,47 +0,0 @@ -/* - * Security xattr support for devpts. - * - * Author: Stephen Smalley <sds@epoch.ncsc.mil> - * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> - * - * 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. - */ -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/security.h> -#include <linux/xattr.h> - -static size_t -devpts_xattr_security_list(struct inode *inode, char *list, size_t list_len, - const char *name, size_t name_len) -{ - return security_inode_listsecurity(inode, list, list_len); -} - -static int -devpts_xattr_security_get(struct inode *inode, const char *name, - void *buffer, size_t size) -{ - if (strcmp(name, "") == 0) - return -EINVAL; - return security_inode_getsecurity(inode, name, buffer, size); -} - -static int -devpts_xattr_security_set(struct inode *inode, const char *name, - const void *value, size_t size, int flags) -{ - if (strcmp(name, "") == 0) - return -EINVAL; - return security_inode_setsecurity(inode, name, value, size, flags); -} - -struct xattr_handler devpts_xattr_security_handler = { - .prefix = XATTR_SECURITY_PREFIX, - .list = devpts_xattr_security_list, - .get = devpts_xattr_security_get, - .set = devpts_xattr_security_set, -}; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index dcfe331dc4c481..3c0c7c6a5b4400 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -19,6 +19,7 @@ #include <linux/config.h> #include <linux/module.h> #include <linux/string.h> +#include <linux/fs.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> @@ -27,6 +28,8 @@ #include <linux/buffer_head.h> #include <linux/smp_lock.h> #include <linux/vfs.h> +#include <linux/seq_file.h> +#include <linux/mount.h> #include <asm/uaccess.h> #include "ext2.h" #include "xattr.h" @@ -201,6 +204,26 @@ static void ext2_clear_inode(struct inode *inode) #endif } +static int ext2_show_options(struct seq_file *seq, struct vfsmount *vfs) +{ + struct ext2_sb_info *sbi = EXT2_SB(vfs->mnt_sb); + + if (sbi->s_mount_opt & EXT2_MOUNT_GRPID) + seq_puts(seq, ",grpid"); + else + seq_puts(seq, ",nogrpid"); + +#if defined(CONFIG_QUOTA) + if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA) + seq_puts(seq, ",usrquota"); + + if (sbi->s_mount_opt & EXT2_MOUNT_GRPQUOTA) + seq_puts(seq, ",grpquota"); +#endif + + return 0; +} + #ifdef CONFIG_QUOTA static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); @@ -218,6 +241,7 @@ static struct super_operations ext2_sops = { .statfs = ext2_statfs, .remount_fs = ext2_remount, .clear_inode = ext2_clear_inode, + .show_options = ext2_show_options, #ifdef CONFIG_QUOTA .quota_read = ext2_quota_read, .quota_write = ext2_quota_write, @@ -256,10 +280,11 @@ static unsigned long get_sb_block(void **data) enum { Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, - Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro, - Opt_nouid32, Opt_check, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov, Opt_nobh, - Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl, Opt_xip, - Opt_ignore, Opt_err, + Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, + Opt_err_ro, Opt_nouid32, Opt_check, Opt_nocheck, Opt_debug, + Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr, + Opt_acl, Opt_noacl, Opt_xip, Opt_ignore, Opt_err, Opt_quota, + Opt_usrquota, Opt_grpquota }; static match_table_t tokens = { @@ -288,10 +313,10 @@ static match_table_t tokens = { {Opt_acl, "acl"}, {Opt_noacl, "noacl"}, {Opt_xip, "xip"}, - {Opt_ignore, "grpquota"}, + {Opt_grpquota, "grpquota"}, {Opt_ignore, "noquota"}, - {Opt_ignore, "quota"}, - {Opt_ignore, "usrquota"}, + {Opt_quota, "quota"}, + {Opt_usrquota, "usrquota"}, {Opt_err, NULL} }; @@ -406,6 +431,26 @@ static int parse_options (char * options, printk("EXT2 xip option not supported\n"); #endif break; + +#if defined(CONFIG_QUOTA) + case Opt_quota: + case Opt_usrquota: + set_opt(sbi->s_mount_opt, USRQUOTA); + break; + + case Opt_grpquota: + set_opt(sbi->s_mount_opt, GRPQUOTA); + break; +#else + case Opt_quota: + case Opt_usrquota: + case Opt_grpquota: + printk(KERN_ERR + "EXT2-fs: quota operations not supported.\n"); + + break; +#endif + case Opt_ignore: break; default: diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 3c3c6e399fb3df..a93c3609025de9 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -35,6 +35,7 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/quotaops.h> +#include <linux/seq_file.h> #include <asm/uaccess.h> #include "xattr.h" #include "acl.h" @@ -509,8 +510,41 @@ static void ext3_clear_inode(struct inode *inode) kfree(rsv); } -#ifdef CONFIG_QUOTA +static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs) +{ + struct ext3_sb_info *sbi = EXT3_SB(vfs->mnt_sb); + + if (sbi->s_mount_opt & EXT3_MOUNT_JOURNAL_DATA) + seq_puts(seq, ",data=journal"); + + if (sbi->s_mount_opt & EXT3_MOUNT_ORDERED_DATA) + seq_puts(seq, ",data=ordered"); + + if (sbi->s_mount_opt & EXT3_MOUNT_WRITEBACK_DATA) + seq_puts(seq, ",data=writeback"); + +#if defined(CONFIG_QUOTA) + if (sbi->s_jquota_fmt) + seq_printf(seq, ",jqfmt=%s", + (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0"); + + if (sbi->s_qf_names[USRQUOTA]) + seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]); + + if (sbi->s_qf_names[GRPQUOTA]) + seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]); + if (sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA) + seq_puts(seq, ",usrquota"); + + if (sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA) + seq_puts(seq, ",grpquota"); +#endif + + return 0; +} + +#ifdef CONFIG_QUOTA #define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group") #define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA)) @@ -569,6 +603,7 @@ static struct super_operations ext3_sops = { .statfs = ext3_statfs, .remount_fs = ext3_remount, .clear_inode = ext3_clear_inode, + .show_options = ext3_show_options, #ifdef CONFIG_QUOTA .quota_read = ext3_quota_read, .quota_write = ext3_quota_write, @@ -590,7 +625,8 @@ enum { Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota, - Opt_ignore, Opt_barrier, Opt_err, Opt_resize, + Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota, + Opt_grpquota }; static match_table_t tokens = { @@ -634,10 +670,10 @@ static match_table_t tokens = { {Opt_grpjquota, "grpjquota=%s"}, {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, - {Opt_quota, "grpquota"}, + {Opt_grpquota, "grpquota"}, {Opt_noquota, "noquota"}, {Opt_quota, "quota"}, - {Opt_quota, "usrquota"}, + {Opt_usrquota, "usrquota"}, {Opt_barrier, "barrier=%u"}, {Opt_err, NULL}, {Opt_resize, "resize"}, @@ -903,7 +939,13 @@ clear_qf_name: sbi->s_jquota_fmt = QFMT_VFS_V0; break; case Opt_quota: + case Opt_usrquota: set_opt(sbi->s_mount_opt, QUOTA); + set_opt(sbi->s_mount_opt, USRQUOTA); + break; + case Opt_grpquota: + set_opt(sbi->s_mount_opt, QUOTA); + set_opt(sbi->s_mount_opt, GRPQUOTA); break; case Opt_noquota: if (sb_any_quota_enabled(sb)) { @@ -912,8 +954,13 @@ clear_qf_name: return 0; } clear_opt(sbi->s_mount_opt, QUOTA); + clear_opt(sbi->s_mount_opt, USRQUOTA); + clear_opt(sbi->s_mount_opt, GRPQUOTA); break; #else + case Opt_quota: + case Opt_usrquota: + case Opt_grpquota: case Opt_usrjquota: case Opt_grpjquota: case Opt_offusrjquota: @@ -924,7 +971,6 @@ clear_qf_name: "EXT3-fs: journalled quota options not " "supported.\n"); break; - case Opt_quota: case Opt_noquota: break; #endif @@ -962,14 +1008,38 @@ clear_qf_name: } } #ifdef CONFIG_QUOTA - if (!sbi->s_jquota_fmt && (sbi->s_qf_names[USRQUOTA] || - sbi->s_qf_names[GRPQUOTA])) { - printk(KERN_ERR - "EXT3-fs: journalled quota format not specified.\n"); - return 0; + if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) { + if ((sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA) && + sbi->s_qf_names[USRQUOTA]) + clear_opt(sbi->s_mount_opt, USRQUOTA); + + if ((sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA) && + sbi->s_qf_names[GRPQUOTA]) + clear_opt(sbi->s_mount_opt, GRPQUOTA); + + if ((sbi->s_qf_names[USRQUOTA] && + (sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)) || + (sbi->s_qf_names[GRPQUOTA] && + (sbi->s_mount_opt & EXT3_MOUNT_USRQUOTA))) { + printk(KERN_ERR "EXT3-fs: old and new quota " + "format mixing.\n"); + return 0; + } + + if (!sbi->s_jquota_fmt) { + printk(KERN_ERR "EXT3-fs: journalled quota format " + "not specified.\n"); + return 0; + } + } else { + if (sbi->s_jquota_fmt) { + printk(KERN_ERR "EXT3-fs: journalled quota format " + "specified with no journalling " + "enabled.\n"); + return 0; + } } #endif - return 1; } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index e5ae1b720dde8b..895049b2ac9cb6 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -30,6 +30,29 @@ static inline loff_t fat_make_i_pos(struct super_block *sb, | (de - (struct msdos_dir_entry *)bh->b_data); } +static inline void fat_dir_readahead(struct inode *dir, sector_t iblock, + sector_t phys) +{ + struct super_block *sb = dir->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct buffer_head *bh; + int sec; + + /* This is not a first sector of cluster, or sec_per_clus == 1 */ + if ((iblock & (sbi->sec_per_clus - 1)) || sbi->sec_per_clus == 1) + return; + /* root dir of FAT12/FAT16 */ + if ((sbi->fat_bits != 32) && (dir->i_ino == MSDOS_ROOT_INO)) + return; + + bh = sb_getblk(sb, phys); + if (bh && !buffer_uptodate(bh)) { + for (sec = 0; sec < sbi->sec_per_clus; sec++) + sb_breadahead(sb, phys + sec); + } + brelse(bh); +} + /* Returns the inode number of the directory entry at offset pos. If bh is non-NULL, it is brelse'd before. Pos is incremented. The buffer header is returned in bh. @@ -58,6 +81,8 @@ next: if (err || !phys) return -1; /* beyond EOF or error */ + fat_dir_readahead(dir, iblock, phys); + *bh = sb_bread(sb, phys); if (*bh == NULL) { printk(KERN_ERR "FAT: Directory bread(block %llu) failed\n", @@ -635,8 +660,7 @@ RecEnd: EODir: filp->f_pos = cpos; FillFailed: - if (bh) - brelse(bh); + brelse(bh); if (unicode) free_page((unsigned long)unicode); out: diff --git a/fs/file_table.c b/fs/file_table.c index 1d3de78e6bc960..43e9e1737de2cb 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -89,7 +89,6 @@ struct file *get_empty_filp(void) rwlock_init(&f->f_owner.lock); /* f->f_version: 0 */ INIT_LIST_HEAD(&f->f_list); - f->f_maxcount = INT_MAX; return f; over: diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c index 27f66d3e8a0413..6aa6fbe4f8ee9a 100644 --- a/fs/freevxfs/vxfs_super.c +++ b/fs/freevxfs/vxfs_super.c @@ -155,7 +155,7 @@ static int vxfs_fill_super(struct super_block *sbp, void *dp, int silent) sbp->s_flags |= MS_RDONLY; - infp = kcalloc(1, sizeof(*infp), GFP_KERNEL); + infp = kzalloc(sizeof(*infp), GFP_KERNEL); if (!infp) { printk(KERN_WARNING "vxfs: unable to allocate incore superblock\n"); return -ENOMEM; diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index a096c5a5666442..3d5cdc6847c06f 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -13,8 +13,6 @@ #include "btree.h" -#define REF_PAGES 0 - void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { @@ -289,9 +287,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) page_cache_release(page); goto fail; } -#if !REF_PAGES page_cache_release(page); -#endif node->page[i] = page; } @@ -449,13 +445,6 @@ void hfs_bnode_get(struct hfs_bnode *node) { if (node) { atomic_inc(&node->refcnt); -#if REF_PAGES - { - int i; - for (i = 0; i < node->tree->pages_per_bnode; i++) - get_page(node->page[i]); - } -#endif dprint(DBG_BNODE_REFS, "get_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); } @@ -472,20 +461,12 @@ void hfs_bnode_put(struct hfs_bnode *node) node->tree->cnid, node->this, atomic_read(&node->refcnt)); if (!atomic_read(&node->refcnt)) BUG(); - if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock)) { -#if REF_PAGES - for (i = 0; i < tree->pages_per_bnode; i++) - put_page(node->page[i]); -#endif + if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock)) return; - } for (i = 0; i < tree->pages_per_bnode; i++) { if (!node->page[i]) continue; mark_page_accessed(node->page[i]); -#if REF_PAGES - put_page(node->page[i]); -#endif } if (test_bit(HFS_BNODE_DELETED, &node->flags)) { diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c index 65dedefcabfc5f..2fcd679f023833 100644 --- a/fs/hfs/catalog.c +++ b/fs/hfs/catalog.c @@ -20,12 +20,12 @@ * * Given the ID of the parent and the name build a search key. */ -void hfs_cat_build_key(btree_key *key, u32 parent, struct qstr *name) +void hfs_cat_build_key(struct super_block *sb, btree_key *key, u32 parent, struct qstr *name) { key->cat.reserved = 0; key->cat.ParID = cpu_to_be32(parent); if (name) { - hfs_triv2mac(&key->cat.CName, name); + hfs_asc2mac(sb, &key->cat.CName, name); key->key_len = 6 + key->cat.CName.len; } else { memset(&key->cat.CName, 0, sizeof(struct hfs_name)); @@ -62,13 +62,14 @@ static int hfs_cat_build_record(hfs_cat_rec *rec, u32 cnid, struct inode *inode) } } -static int hfs_cat_build_thread(hfs_cat_rec *rec, int type, +static int hfs_cat_build_thread(struct super_block *sb, + hfs_cat_rec *rec, int type, u32 parentid, struct qstr *name) { rec->type = type; memset(rec->thread.reserved, 0, sizeof(rec->thread.reserved)); rec->thread.ParID = cpu_to_be32(parentid); - hfs_triv2mac(&rec->thread.CName, name); + hfs_asc2mac(sb, &rec->thread.CName, name); return sizeof(struct hfs_cat_thread); } @@ -93,8 +94,8 @@ int hfs_cat_create(u32 cnid, struct inode *dir, struct qstr *str, struct inode * sb = dir->i_sb; hfs_find_init(HFS_SB(sb)->cat_tree, &fd); - hfs_cat_build_key(fd.search_key, cnid, NULL); - entry_size = hfs_cat_build_thread(&entry, S_ISDIR(inode->i_mode) ? + hfs_cat_build_key(sb, fd.search_key, cnid, NULL); + entry_size = hfs_cat_build_thread(sb, &entry, S_ISDIR(inode->i_mode) ? HFS_CDR_THD : HFS_CDR_FTH, dir->i_ino, str); err = hfs_brec_find(&fd); @@ -107,7 +108,7 @@ int hfs_cat_create(u32 cnid, struct inode *dir, struct qstr *str, struct inode * if (err) goto err2; - hfs_cat_build_key(fd.search_key, dir->i_ino, str); + hfs_cat_build_key(sb, fd.search_key, dir->i_ino, str); entry_size = hfs_cat_build_record(&entry, cnid, inode); err = hfs_brec_find(&fd); if (err != -ENOENT) { @@ -127,7 +128,7 @@ int hfs_cat_create(u32 cnid, struct inode *dir, struct qstr *str, struct inode * return 0; err1: - hfs_cat_build_key(fd.search_key, cnid, NULL); + hfs_cat_build_key(sb, fd.search_key, cnid, NULL); if (!hfs_brec_find(&fd)) hfs_brec_remove(&fd); err2: @@ -176,7 +177,7 @@ int hfs_cat_find_brec(struct super_block *sb, u32 cnid, hfs_cat_rec rec; int res, len, type; - hfs_cat_build_key(fd->search_key, cnid, NULL); + hfs_cat_build_key(sb, fd->search_key, cnid, NULL); res = hfs_brec_read(fd, &rec, sizeof(rec)); if (res) return res; @@ -211,7 +212,7 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str) sb = dir->i_sb; hfs_find_init(HFS_SB(sb)->cat_tree, &fd); - hfs_cat_build_key(fd.search_key, dir->i_ino, str); + hfs_cat_build_key(sb, fd.search_key, dir->i_ino, str); res = hfs_brec_find(&fd); if (res) goto out; @@ -239,7 +240,7 @@ int hfs_cat_delete(u32 cnid, struct inode *dir, struct qstr *str) if (res) goto out; - hfs_cat_build_key(fd.search_key, cnid, NULL); + hfs_cat_build_key(sb, fd.search_key, cnid, NULL); res = hfs_brec_find(&fd); if (!res) { res = hfs_brec_remove(&fd); @@ -280,7 +281,7 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, struct qstr *src_name, dst_fd = src_fd; /* find the old dir entry and read the data */ - hfs_cat_build_key(src_fd.search_key, src_dir->i_ino, src_name); + hfs_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); err = hfs_brec_find(&src_fd); if (err) goto out; @@ -289,7 +290,7 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, struct qstr *src_name, src_fd.entrylength); /* create new dir entry with the data from the old entry */ - hfs_cat_build_key(dst_fd.search_key, dst_dir->i_ino, dst_name); + hfs_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name); err = hfs_brec_find(&dst_fd); if (err != -ENOENT) { if (!err) @@ -305,7 +306,7 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, struct qstr *src_name, mark_inode_dirty(dst_dir); /* finally remove the old entry */ - hfs_cat_build_key(src_fd.search_key, src_dir->i_ino, src_name); + hfs_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name); err = hfs_brec_find(&src_fd); if (err) goto out; @@ -321,7 +322,7 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, struct qstr *src_name, goto out; /* remove old thread entry */ - hfs_cat_build_key(src_fd.search_key, cnid, NULL); + hfs_cat_build_key(sb, src_fd.search_key, cnid, NULL); err = hfs_brec_find(&src_fd); if (err) goto out; @@ -330,8 +331,8 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, struct qstr *src_name, goto out; /* create new thread entry */ - hfs_cat_build_key(dst_fd.search_key, cnid, NULL); - entry_size = hfs_cat_build_thread(&entry, type == HFS_CDR_FIL ? HFS_CDR_FTH : HFS_CDR_THD, + hfs_cat_build_key(sb, dst_fd.search_key, cnid, NULL); + entry_size = hfs_cat_build_thread(sb, &entry, type == HFS_CDR_FIL ? HFS_CDR_FTH : HFS_CDR_THD, dst_dir->i_ino, dst_name); err = hfs_brec_find(&dst_fd); if (err != -ENOENT) { diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index c55998262aed51..e1f24befba58b2 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -28,7 +28,7 @@ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_op = &hfs_dentry_operations; hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd); - hfs_cat_build_key(fd.search_key, dir->i_ino, &dentry->d_name); + hfs_cat_build_key(dir->i_sb, fd.search_key, dir->i_ino, &dentry->d_name); res = hfs_brec_read(&fd, &rec, sizeof(rec)); if (res) { hfs_find_exit(&fd); @@ -56,7 +56,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) struct inode *inode = filp->f_dentry->d_inode; struct super_block *sb = inode->i_sb; int len, err; - char strbuf[HFS_NAMELEN + 1]; + char strbuf[HFS_MAX_NAMELEN]; union hfs_cat_rec entry; struct hfs_find_data fd; struct hfs_readdir_data *rd; @@ -66,7 +66,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) return 0; hfs_find_init(HFS_SB(sb)->cat_tree, &fd); - hfs_cat_build_key(fd.search_key, inode->i_ino, NULL); + hfs_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); err = hfs_brec_find(&fd); if (err) goto out; @@ -111,7 +111,7 @@ static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir) } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); type = entry.type; - len = hfs_mac2triv(strbuf, &fd.key->cat.CName); + len = hfs_mac2asc(sb, strbuf, &fd.key->cat.CName); if (type == HFS_CDR_DIR) { if (fd.entrylength < sizeof(struct hfs_cat_dir)) { printk("HFS: small dir entry\n"); @@ -307,7 +307,8 @@ static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry, old_dir, &old_dentry->d_name, new_dir, &new_dentry->d_name); if (!res) - hfs_cat_build_key((btree_key *)&HFS_I(old_dentry->d_inode)->cat_key, + hfs_cat_build_key(old_dir->i_sb, + (btree_key *)&HFS_I(old_dentry->d_inode)->cat_key, new_dir->i_ino, &new_dentry->d_name); return res; } diff --git a/fs/hfs/hfs.h b/fs/hfs/hfs.h index df6b33adee3bbd..88099ab1a18012 100644 --- a/fs/hfs/hfs.h +++ b/fs/hfs/hfs.h @@ -25,6 +25,7 @@ #define HFS_SECTOR_SIZE 512 /* size of an HFS sector */ #define HFS_SECTOR_SIZE_BITS 9 /* log_2(HFS_SECTOR_SIZE) */ #define HFS_NAMELEN 31 /* maximum length of an HFS filename */ +#define HFS_MAX_NAMELEN 128 #define HFS_MAX_VALENCE 32767U /* Meanings of the drAtrb field of the MDB, diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 0dc8ef8e14de67..aae019aadf8865 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -141,6 +141,8 @@ struct hfs_sb_info { int session, part; + struct nls_table *nls_io, *nls_disk; + struct semaphore bitmap_lock; unsigned long flags; @@ -168,7 +170,7 @@ extern int hfs_cat_create(u32, struct inode *, struct qstr *, struct inode *); extern int hfs_cat_delete(u32, struct inode *, struct qstr *); extern int hfs_cat_move(u32, struct inode *, struct qstr *, struct inode *, struct qstr *); -extern void hfs_cat_build_key(btree_key *, u32, struct qstr *); +extern void hfs_cat_build_key(struct super_block *, btree_key *, u32, struct qstr *); /* dir.c */ extern struct file_operations hfs_dir_operations; @@ -222,8 +224,8 @@ extern int hfs_strcmp(const unsigned char *, unsigned int, extern int hfs_compare_dentry(struct dentry *, struct qstr *, struct qstr *); /* trans.c */ -extern void hfs_triv2mac(struct hfs_name *, struct qstr *); -extern int hfs_mac2triv(char *, const struct hfs_name *); +extern void hfs_asc2mac(struct super_block *, struct hfs_name *, struct qstr *); +extern int hfs_mac2asc(struct super_block *, char *, const struct hfs_name *); extern struct timezone sys_tz; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 75191232609454..f1570b9f9de304 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -160,7 +160,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, int mode) init_MUTEX(&HFS_I(inode)->extents_lock); INIT_LIST_HEAD(&HFS_I(inode)->open_dir_list); - hfs_cat_build_key((btree_key *)&HFS_I(inode)->cat_key, dir->i_ino, name); + hfs_cat_build_key(sb, (btree_key *)&HFS_I(inode)->cat_key, dir->i_ino, name); inode->i_ino = HFS_SB(sb)->next_id++; inode->i_mode = mode; inode->i_uid = current->fsuid; diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 217e32f37e0be7..0a473f79c89feb 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -10,6 +10,7 @@ #include <linux/cdrom.h> #include <linux/genhd.h> +#include <linux/nls.h> #include "hfs_fs.h" #include "btree.h" @@ -343,6 +344,11 @@ void hfs_mdb_put(struct super_block *sb) brelse(HFS_SB(sb)->mdb_bh); brelse(HFS_SB(sb)->alt_mdb_bh); + if (HFS_SB(sb)->nls_io) + unload_nls(HFS_SB(sb)->nls_io); + if (HFS_SB(sb)->nls_disk) + unload_nls(HFS_SB(sb)->nls_disk); + kfree(HFS_SB(sb)); sb->s_fs_info = NULL; } diff --git a/fs/hfs/super.c b/fs/hfs/super.c index ab783f6afa3b08..c5074aeafcae7e 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -15,8 +15,11 @@ #include <linux/config.h> #include <linux/module.h> #include <linux/blkdev.h> +#include <linux/mount.h> #include <linux/init.h> +#include <linux/nls.h> #include <linux/parser.h> +#include <linux/seq_file.h> #include <linux/vfs.h> #include "hfs_fs.h" @@ -111,6 +114,32 @@ static int hfs_remount(struct super_block *sb, int *flags, char *data) return 0; } +static int hfs_show_options(struct seq_file *seq, struct vfsmount *mnt) +{ + struct hfs_sb_info *sbi = HFS_SB(mnt->mnt_sb); + + if (sbi->s_creator != cpu_to_be32(0x3f3f3f3f)) + seq_printf(seq, ",creator=%.4s", (char *)&sbi->s_creator); + if (sbi->s_type != cpu_to_be32(0x3f3f3f3f)) + seq_printf(seq, ",type=%.4s", (char *)&sbi->s_type); + seq_printf(seq, ",uid=%u,gid=%u", sbi->s_uid, sbi->s_gid); + if (sbi->s_file_umask != 0133) + seq_printf(seq, ",file_umask=%o", sbi->s_file_umask); + if (sbi->s_dir_umask != 0022) + seq_printf(seq, ",dir_umask=%o", sbi->s_dir_umask); + if (sbi->part >= 0) + seq_printf(seq, ",part=%u", sbi->part); + if (sbi->session >= 0) + seq_printf(seq, ",session=%u", sbi->session); + if (sbi->nls_disk) + seq_printf(seq, ",codepage=%s", sbi->nls_disk->charset); + if (sbi->nls_io) + seq_printf(seq, ",iocharset=%s", sbi->nls_io->charset); + if (sbi->s_quiet) + seq_printf(seq, ",quiet"); + return 0; +} + static struct inode *hfs_alloc_inode(struct super_block *sb) { struct hfs_inode_info *i; @@ -133,11 +162,13 @@ static struct super_operations hfs_super_operations = { .write_super = hfs_write_super, .statfs = hfs_statfs, .remount_fs = hfs_remount, + .show_options = hfs_show_options, }; enum { opt_uid, opt_gid, opt_umask, opt_file_umask, opt_dir_umask, opt_part, opt_session, opt_type, opt_creator, opt_quiet, + opt_codepage, opt_iocharset, opt_err }; @@ -152,6 +183,8 @@ static match_table_t tokens = { { opt_type, "type=%s" }, { opt_creator, "creator=%s" }, { opt_quiet, "quiet" }, + { opt_codepage, "codepage=%s" }, + { opt_iocharset, "iocharset=%s" }, { opt_err, NULL } }; @@ -257,11 +290,46 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) case opt_quiet: hsb->s_quiet = 1; break; + case opt_codepage: + if (hsb->nls_disk) { + printk("HFS+-fs: unable to change codepage\n"); + return 0; + } + p = match_strdup(&args[0]); + hsb->nls_disk = load_nls(p); + if (!hsb->nls_disk) { + printk("HFS+-fs: unable to load codepage \"%s\"\n", p); + kfree(p); + return 0; + } + kfree(p); + break; + case opt_iocharset: + if (hsb->nls_io) { + printk("HFS: unable to change iocharset\n"); + return 0; + } + p = match_strdup(&args[0]); + hsb->nls_io = load_nls(p); + if (!hsb->nls_io) { + printk("HFS: unable to load iocharset \"%s\"\n", p); + kfree(p); + return 0; + } + kfree(p); + break; default: return 0; } } + if (hsb->nls_disk && !hsb->nls_io) { + hsb->nls_io = load_nls_default(); + if (!hsb->nls_io) { + printk("HFS: unable to load default iocharset\n"); + return 0; + } + } hsb->s_dir_umask &= 0777; hsb->s_file_umask &= 0577; diff --git a/fs/hfs/trans.c b/fs/hfs/trans.c index fb9720abbadd64..e673a88b8ae756 100644 --- a/fs/hfs/trans.c +++ b/fs/hfs/trans.c @@ -9,12 +9,15 @@ * with ':' vs. '/' as the path-element separator. */ +#include <linux/types.h> +#include <linux/nls.h> + #include "hfs_fs.h" /*================ Global functions ================*/ /* - * hfs_mac2triv() + * hfs_mac2asc() * * Given a 'Pascal String' (a string preceded by a length byte) in * the Macintosh character set produce the corresponding filename using @@ -27,23 +30,58 @@ * by ':' which never appears in HFS filenames. All other characters * are passed unchanged from input to output. */ -int hfs_mac2triv(char *out, const struct hfs_name *in) +int hfs_mac2asc(struct super_block *sb, char *out, const struct hfs_name *in) { - const char *p; - char c; - int i, len; + struct nls_table *nls_disk = HFS_SB(sb)->nls_disk; + struct nls_table *nls_io = HFS_SB(sb)->nls_io; + const char *src; + char *dst; + int srclen, dstlen, size; + + src = in->name; + srclen = in->len; + dst = out; + dstlen = HFS_MAX_NAMELEN; + if (nls_io) { + wchar_t ch; - len = in->len; - p = in->name; - for (i = 0; i < len; i++) { - c = *p++; - *out++ = c == '/' ? ':' : c; + while (srclen > 0) { + if (nls_disk) { + size = nls_disk->char2uni(src, srclen, &ch); + if (size <= 0) { + ch = '?'; + size = 1; + } + src += size; + srclen -= size; + } else { + ch = *src++; + srclen--; + } + if (ch == '/') + ch = ':'; + size = nls_io->uni2char(ch, dst, dstlen); + if (size < 0) { + if (size == -ENAMETOOLONG) + goto out; + *dst = '?'; + size = 1; + } + dst += size; + dstlen -= size; + } + } else { + char ch; + + while (--srclen >= 0) + *dst++ = (ch = *src++) == '/' ? ':' : ch; } - return i; +out: + return dst - out; } /* - * hfs_triv2mac() + * hfs_asc2mac() * * Given an ASCII string (not null-terminated) and its length, * generate the corresponding filename in the Macintosh character set @@ -54,19 +92,57 @@ int hfs_mac2triv(char *out, const struct hfs_name *in) * This routine is a inverse to hfs_mac2triv(). * A ':' is replaced by a '/'. */ -void hfs_triv2mac(struct hfs_name *out, struct qstr *in) +void hfs_asc2mac(struct super_block *sb, struct hfs_name *out, struct qstr *in) { + struct nls_table *nls_disk = HFS_SB(sb)->nls_disk; + struct nls_table *nls_io = HFS_SB(sb)->nls_io; const char *src; - char *dst, c; - int i, len; + char *dst; + int srclen, dstlen, size; - out->len = len = min((unsigned int)HFS_NAMELEN, in->len); src = in->name; + srclen = in->len; dst = out->name; - for (i = 0; i < len; i++) { - c = *src++; - *dst++ = c == ':' ? '/' : c; + dstlen = HFS_NAMELEN; + if (nls_io) { + wchar_t ch; + + while (srclen > 0) { + size = nls_io->char2uni(src, srclen, &ch); + if (size < 0) { + ch = '?'; + size = 1; + } + src += size; + srclen -= size; + if (ch == ':') + ch = '/'; + if (nls_disk) { + size = nls_disk->uni2char(ch, dst, dstlen); + if (size < 0) { + if (size == -ENAMETOOLONG) + goto out; + *dst = '?'; + size = 1; + } + dst += size; + dstlen -= size; + } else { + *dst++ = ch > 0xff ? '?' : ch; + dstlen--; + } + } + } else { + char ch; + + if (dstlen > srclen) + dstlen = srclen; + while (--dstlen >= 0) + *dst++ = (ch = *src++) == ':' ? '/' : ch; } - for (; i < HFS_NAMELEN; i++) +out: + out->len = dst - (char *)out->name; + dstlen = HFS_NAMELEN - out->len; + while (--dstlen >= 0) *dst++ = 0; } diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 8868d3b766fd46..b85abc6e6f83b3 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -18,8 +18,6 @@ #include "hfsplus_fs.h" #include "hfsplus_raw.h" -#define REF_PAGES 0 - /* Copy a specified range of bytes from the raw data of a node */ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { @@ -450,9 +448,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) page_cache_release(page); goto fail; } -#if !REF_PAGES page_cache_release(page); -#endif node->page[i] = page; } @@ -612,13 +608,6 @@ void hfs_bnode_get(struct hfs_bnode *node) { if (node) { atomic_inc(&node->refcnt); -#if REF_PAGES - { - int i; - for (i = 0; i < node->tree->pages_per_bnode; i++) - get_page(node->page[i]); - } -#endif dprint(DBG_BNODE_REFS, "get_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); } @@ -635,20 +624,12 @@ void hfs_bnode_put(struct hfs_bnode *node) node->tree->cnid, node->this, atomic_read(&node->refcnt)); if (!atomic_read(&node->refcnt)) BUG(); - if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock)) { -#if REF_PAGES - for (i = 0; i < tree->pages_per_bnode; i++) - put_page(node->page[i]); -#endif + if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock)) return; - } for (i = 0; i < tree->pages_per_bnode; i++) { if (!node->page[i]) continue; mark_page_accessed(node->page[i]); -#if REF_PAGES - put_page(node->page[i]); -#endif } if (test_bit(HFS_BNODE_DELETED, &node->flags)) { diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 533094a570df30..2bc0cdd30e5656 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -343,8 +343,9 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size); /* options.c */ -int parse_options(char *, struct hfsplus_sb_info *); -void fill_defaults(struct hfsplus_sb_info *); +int hfsplus_parse_options(char *, struct hfsplus_sb_info *); +void hfsplus_fill_defaults(struct hfsplus_sb_info *); +int hfsplus_show_options(struct seq_file *, struct vfsmount *); /* tables.c */ extern u16 hfsplus_case_fold_table[]; diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index 1cca0102c98d30..cca0818aa4ca3d 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -13,6 +13,8 @@ #include <linux/sched.h> #include <linux/parser.h> #include <linux/nls.h> +#include <linux/mount.h> +#include <linux/seq_file.h> #include "hfsplus_fs.h" enum { @@ -38,7 +40,7 @@ static match_table_t tokens = { }; /* Initialize an options object to reasonable defaults */ -void fill_defaults(struct hfsplus_sb_info *opts) +void hfsplus_fill_defaults(struct hfsplus_sb_info *opts) { if (!opts) return; @@ -63,7 +65,7 @@ static inline int match_fourchar(substring_t *arg, u32 *result) /* Parse options from mount. Returns 0 on failure */ /* input is the options passed to mount() as a string */ -int parse_options(char *input, struct hfsplus_sb_info *sbi) +int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) { char *p; substring_t args[MAX_OPT_ARGS]; @@ -160,3 +162,23 @@ done: return 1; } + +int hfsplus_show_options(struct seq_file *seq, struct vfsmount *mnt) +{ + struct hfsplus_sb_info *sbi = &HFSPLUS_SB(mnt->mnt_sb); + + if (sbi->creator != HFSPLUS_DEF_CR_TYPE) + seq_printf(seq, ",creator=%.4s", (char *)&sbi->creator); + if (sbi->type != HFSPLUS_DEF_CR_TYPE) + seq_printf(seq, ",type=%.4s", (char *)&sbi->type); + seq_printf(seq, ",umask=%o,uid=%u,gid=%u", sbi->umask, sbi->uid, sbi->gid); + if (sbi->part >= 0) + seq_printf(seq, ",part=%u", sbi->part); + if (sbi->session >= 0) + seq_printf(seq, ",session=%u", sbi->session); + if (sbi->nls) + seq_printf(seq, ",nls=%s", sbi->nls->charset); + if (sbi->flags & HFSPLUS_SB_NODECOMPOSE) + seq_printf(seq, ",nodecompose"); + return 0; +} diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index d55ad67b8e4238..fd0f0f050e1d5f 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -217,8 +217,7 @@ static void hfsplus_put_super(struct super_block *sb) vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_UNMNT); vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_INCNSTNT); mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh); - ll_rw_block(WRITE, 1, &HFSPLUS_SB(sb).s_vhbh); - wait_on_buffer(HFSPLUS_SB(sb).s_vhbh); + sync_dirty_buffer(HFSPLUS_SB(sb).s_vhbh); } hfs_btree_close(HFSPLUS_SB(sb).cat_tree); @@ -277,6 +276,7 @@ static struct super_operations hfsplus_sops = { .write_super = hfsplus_write_super, .statfs = hfsplus_statfs, .remount_fs = hfsplus_remount, + .show_options = hfsplus_show_options, }; static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) @@ -297,8 +297,8 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) memset(sbi, 0, sizeof(HFSPLUS_SB(sb))); sb->s_fs_info = sbi; INIT_HLIST_HEAD(&sbi->rsrc_inodes); - fill_defaults(sbi); - if (!parse_options(data, sbi)) { + hfsplus_fill_defaults(sbi); + if (!hfsplus_parse_options(data, sbi)) { if (!silent) printk("HFS+-fs: unable to parse mount options\n"); err = -EINVAL; @@ -415,8 +415,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT); vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT); mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh); - ll_rw_block(WRITE, 1, &HFSPLUS_SB(sb).s_vhbh); - wait_on_buffer(HFSPLUS_SB(sb).s_vhbh); + sync_dirty_buffer(HFSPLUS_SB(sb).s_vhbh); if (!HFSPLUS_SB(sb).hidden_dir) { printk("HFS+: create hidden dir...\n"); diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h index 67bca0d4a33ba5..cca3fb693f9905 100644 --- a/fs/hostfs/hostfs.h +++ b/fs/hostfs/hostfs.h @@ -49,7 +49,6 @@ struct hostfs_iattr { struct timespec ia_atime; struct timespec ia_mtime; struct timespec ia_ctime; - unsigned int ia_attr_flags; }; extern int stat_file(const char *path, unsigned long long *inode_out, diff --git a/fs/inode.c b/fs/inode.c index e57f1724db3e89..71df1b1e8f75a8 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1195,9 +1195,6 @@ void update_atime(struct inode *inode) if (!timespec_equal(&inode->i_atime, &now)) { inode->i_atime = now; mark_inode_dirty_sync(inode); - } else { - if (!timespec_equal(&inode->i_atime, &now)) - inode->i_atime = now; } } diff --git a/fs/inotify.c b/fs/inotify.c index 2e4e2a57708cf9..a37e9fb1da589f 100644 --- a/fs/inotify.c +++ b/fs/inotify.c @@ -37,6 +37,7 @@ #include <asm/ioctls.h> static atomic_t inotify_cookie; +static atomic_t inotify_watches; static kmem_cache_t *watch_cachep; static kmem_cache_t *event_cachep; @@ -422,6 +423,7 @@ static struct inotify_watch *create_watch(struct inotify_device *dev, get_inotify_watch(watch); atomic_inc(&dev->user->inotify_watches); + atomic_inc(&inotify_watches); return watch; } @@ -454,6 +456,7 @@ static void remove_watch_no_event(struct inotify_watch *watch, list_del(&watch->d_list); atomic_dec(&dev->user->inotify_watches); + atomic_dec(&inotify_watches); idr_remove(&dev->idr, watch->wd); put_inotify_watch(watch); } @@ -532,6 +535,9 @@ void inotify_dentry_parent_queue_event(struct dentry *dentry, u32 mask, struct dentry *parent; struct inode *inode; + if (!atomic_read (&inotify_watches)) + return; + spin_lock(&dentry->d_lock); parent = dentry->d_parent; inode = parent->d_inode; @@ -925,6 +931,7 @@ asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask) struct nameidata nd; struct file *filp; int ret, fput_needed; + int mask_add = 0; filp = fget_light(fd, &fput_needed); if (unlikely(!filp)) @@ -947,6 +954,9 @@ asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask) down(&inode->inotify_sem); down(&dev->sem); + if (mask & IN_MASK_ADD) + mask_add = 1; + /* don't let user-space set invalid bits: we don't want flags set */ mask &= IN_ALL_EVENTS; if (unlikely(!mask)) { @@ -960,7 +970,10 @@ asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask) */ old = inode_find_dev(inode, dev); if (unlikely(old)) { - old->mask = mask; + if (mask_add) + old->mask |= mask; + else + old->mask = mask; ret = old->wd; goto out; } @@ -1043,6 +1056,7 @@ static int __init inotify_setup(void) inotify_max_user_watches = 8192; atomic_set(&inotify_cookie, 0); + atomic_set(&inotify_watches, 0); watch_cachep = kmem_cache_create("inotify_watch_cache", sizeof(struct inotify_watch), diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 5a97e346bd95a2..014a51fd00d776 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -204,7 +204,7 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count) int i; spin_unlock(&journal->j_list_lock); - ll_rw_block(WRITE, *batch_count, bhs); + ll_rw_block(SWRITE, *batch_count, bhs); spin_lock(&journal->j_list_lock); for (i = 0; i < *batch_count; i++) { struct buffer_head *bh = bhs[i]; diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index dac720c837abf0..2a3e310f79efa7 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -358,7 +358,7 @@ write_out_data: jbd_debug(2, "submit %d writes\n", bufs); spin_unlock(&journal->j_list_lock); - ll_rw_block(WRITE, bufs, wbuf); + ll_rw_block(SWRITE, bufs, wbuf); journal_brelse_array(wbuf, bufs); bufs = 0; goto write_out_data; @@ -381,7 +381,7 @@ write_out_data: if (bufs) { spin_unlock(&journal->j_list_lock); - ll_rw_block(WRITE, bufs, wbuf); + ll_rw_block(SWRITE, bufs, wbuf); journal_brelse_array(wbuf, bufs); spin_lock(&journal->j_list_lock); } @@ -720,11 +720,17 @@ wait_for_iobuf: J_ASSERT(commit_transaction->t_log_list == NULL); restart_loop: + /* + * As there are other places (journal_unmap_buffer()) adding buffers + * to this list we have to be careful and hold the j_list_lock. + */ + spin_lock(&journal->j_list_lock); while (commit_transaction->t_forget) { transaction_t *cp_transaction; struct buffer_head *bh; jh = commit_transaction->t_forget; + spin_unlock(&journal->j_list_lock); bh = jh2bh(jh); jbd_lock_bh_state(bh); J_ASSERT_JH(jh, jh->b_transaction == commit_transaction || @@ -792,9 +798,25 @@ restart_loop: journal_remove_journal_head(bh); /* needs a brelse */ release_buffer_page(bh); } + cond_resched_lock(&journal->j_list_lock); + } + spin_unlock(&journal->j_list_lock); + /* + * This is a bit sleazy. We borrow j_list_lock to protect + * journal->j_committing_transaction in __journal_remove_checkpoint. + * Really, __journal_remove_checkpoint should be using j_state_lock but + * it's a bit hassle to hold that across __journal_remove_checkpoint + */ + spin_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + /* + * Now recheck if some buffers did not get attached to the transaction + * while the lock was dropped... + */ + if (commit_transaction->t_forget) { spin_unlock(&journal->j_list_lock); - if (cond_resched()) - goto restart_loop; + spin_unlock(&journal->j_state_lock); + goto restart_loop; } /* Done with this transaction! */ @@ -803,14 +825,6 @@ restart_loop: J_ASSERT(commit_transaction->t_state == T_COMMIT); - /* - * This is a bit sleazy. We borrow j_list_lock to protect - * journal->j_committing_transaction in __journal_remove_checkpoint. - * Really, __jornal_remove_checkpoint should be using j_state_lock but - * it's a bit hassle to hold that across __journal_remove_checkpoint - */ - spin_lock(&journal->j_state_lock); - spin_lock(&journal->j_list_lock); commit_transaction->t_state = T_FINISHED; J_ASSERT(commit_transaction == journal->j_committing_transaction); journal->j_commit_sequence = commit_transaction->t_tid; diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 5e7b439495171c..7ae2c4fe506bb5 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -65,7 +65,6 @@ EXPORT_SYMBOL(journal_set_features); EXPORT_SYMBOL(journal_create); EXPORT_SYMBOL(journal_load); EXPORT_SYMBOL(journal_destroy); -EXPORT_SYMBOL(journal_recover); EXPORT_SYMBOL(journal_update_superblock); EXPORT_SYMBOL(journal_abort); EXPORT_SYMBOL(journal_errno); @@ -81,6 +80,7 @@ EXPORT_SYMBOL(journal_try_to_free_buffers); EXPORT_SYMBOL(journal_force_commit); static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); +static void __journal_abort_soft (journal_t *journal, int errno); /* * Helper function used to manage commit timeouts @@ -93,16 +93,6 @@ static void commit_timeout(unsigned long __data) wake_up_process(p); } -/* Static check for data structure consistency. There's no code - * invoked --- we'll just get a linker failure if things aren't right. - */ -void __journal_internal_check(void) -{ - extern void journal_bad_superblock_size(void); - if (sizeof(struct journal_superblock_s) != 1024) - journal_bad_superblock_size(); -} - /* * kjournald: The main thread function used to manage a logging device * journal. @@ -119,16 +109,12 @@ void __journal_internal_check(void) * known as checkpointing, and this thread is responsible for that job. */ -journal_t *current_journal; // AKPM: debug - -int kjournald(void *arg) +static int kjournald(void *arg) { journal_t *journal = (journal_t *) arg; transaction_t *transaction; struct timer_list timer; - current_journal = journal; - daemonize("kjournald"); /* Set up an interval timer which can be used to trigger a @@ -193,6 +179,8 @@ loop: if (transaction && time_after_eq(jiffies, transaction->t_expires)) should_sleep = 0; + if (journal->j_flags & JFS_UNMOUNT) + should_sleep = 0; if (should_sleep) { spin_unlock(&journal->j_state_lock); schedule(); @@ -969,7 +957,7 @@ void journal_update_superblock(journal_t *journal, int wait) if (wait) sync_dirty_buffer(bh); else - ll_rw_block(WRITE, 1, &bh); + ll_rw_block(SWRITE, 1, &bh); out: /* If we have just flushed the log (by marking s_start==0), then @@ -1439,7 +1427,7 @@ int journal_wipe(journal_t *journal, int write) * device this journal is present. */ -const char *journal_dev_name(journal_t *journal, char *buffer) +static const char *journal_dev_name(journal_t *journal, char *buffer) { struct block_device *bdev; @@ -1485,7 +1473,7 @@ void __journal_abort_hard(journal_t *journal) /* Soft abort: record the abort error status in the journal superblock, * but don't do any other IO. */ -void __journal_abort_soft (journal_t *journal, int errno) +static void __journal_abort_soft (journal_t *journal, int errno) { if (journal->j_flags & JFS_ABORT) return; @@ -1880,7 +1868,7 @@ EXPORT_SYMBOL(journal_enable_debug); static struct proc_dir_entry *proc_jbd_debug; -int read_jbd_debug(char *page, char **start, off_t off, +static int read_jbd_debug(char *page, char **start, off_t off, int count, int *eof, void *data) { int ret; @@ -1890,7 +1878,7 @@ int read_jbd_debug(char *page, char **start, off_t off, return ret; } -int write_jbd_debug(struct file *file, const char __user *buffer, +static int write_jbd_debug(struct file *file, const char __user *buffer, unsigned long count, void *data) { char buf[32]; @@ -1979,6 +1967,14 @@ static int __init journal_init(void) { int ret; +/* Static check for data structure consistency. There's no code + * invoked --- we'll just get a linker failure if things aren't right. + */ + extern void journal_bad_superblock_size(void); + if (sizeof(struct journal_superblock_s) != 1024) + journal_bad_superblock_size(); + + ret = journal_init_caches(); if (ret != 0) journal_destroy_caches(); diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c index d327a598f86128..a56144183462e2 100644 --- a/fs/jbd/revoke.c +++ b/fs/jbd/revoke.c @@ -116,7 +116,8 @@ static inline int hash(journal_t *journal, unsigned long block) (block << (hash_shift - 12))) & (table->hash_size - 1); } -int insert_revoke_hash(journal_t *journal, unsigned long blocknr, tid_t seq) +static int insert_revoke_hash(journal_t *journal, unsigned long blocknr, + tid_t seq) { struct list_head *hash_list; struct jbd_revoke_record_s *record; @@ -613,7 +614,7 @@ static void flush_descriptor(journal_t *journal, set_buffer_jwrite(bh); BUFFER_TRACE(bh, "write"); set_buffer_dirty(bh); - ll_rw_block(WRITE, 1, &bh); + ll_rw_block(SWRITE, 1, &bh); } #endif diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 77b7662b840b48..c6ec66fd876682 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -490,23 +490,21 @@ void journal_unlock_updates (journal_t *journal) */ static void jbd_unexpected_dirty_buffer(struct journal_head *jh) { - struct buffer_head *bh = jh2bh(jh); int jlist; - if (buffer_dirty(bh)) { - /* If this buffer is one which might reasonably be dirty - * --- ie. data, or not part of this journal --- then - * we're OK to leave it alone, but otherwise we need to - * move the dirty bit to the journal's own internal - * JBDDirty bit. */ - jlist = jh->b_jlist; - - if (jlist == BJ_Metadata || jlist == BJ_Reserved || - jlist == BJ_Shadow || jlist == BJ_Forget) { - if (test_clear_buffer_dirty(jh2bh(jh))) { - set_bit(BH_JBDDirty, &jh2bh(jh)->b_state); - } - } + /* If this buffer is one which might reasonably be dirty + * --- ie. data, or not part of this journal --- then + * we're OK to leave it alone, but otherwise we need to + * move the dirty bit to the journal's own internal + * JBDDirty bit. */ + jlist = jh->b_jlist; + + if (jlist == BJ_Metadata || jlist == BJ_Reserved || + jlist == BJ_Shadow || jlist == BJ_Forget) { + struct buffer_head *bh = jh2bh(jh); + + if (test_clear_buffer_dirty(bh)) + set_buffer_jbddirty(bh); } } @@ -574,9 +572,14 @@ repeat: if (jh->b_next_transaction) J_ASSERT_JH(jh, jh->b_next_transaction == transaction); - JBUFFER_TRACE(jh, "Unexpected dirty buffer"); - jbd_unexpected_dirty_buffer(jh); - } + } + /* + * In any case we need to clean the dirty flag and we must + * do it under the buffer lock to be sure we don't race + * with running write-out. + */ + JBUFFER_TRACE(jh, "Unexpected dirty buffer"); + jbd_unexpected_dirty_buffer(jh); } unlock_buffer(bh); diff --git a/fs/jffs/inode-v23.c b/fs/jffs/inode-v23.c index bfbeb4c86e03af..777b90057b8939 100644 --- a/fs/jffs/inode-v23.c +++ b/fs/jffs/inode-v23.c @@ -1629,9 +1629,6 @@ static int jffs_fsync(struct file *f, struct dentry *d, int datasync) } -extern int generic_file_open(struct inode *, struct file *) __attribute__((weak)); -extern loff_t generic_file_llseek(struct file *, loff_t, int) __attribute__((weak)); - static struct file_operations jffs_file_operations = { .open = generic_file_open, diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index bd9ed9b0247b1d..8279bf0133ff57 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -21,9 +21,6 @@ #include <linux/jffs2.h> #include "nodelist.h" -extern int generic_file_open(struct inode *, struct file *) __attribute__((weak)); -extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin) __attribute__((weak)); - static int jffs2_commit_write (struct file *filp, struct page *pg, unsigned start, unsigned end); static int jffs2_prepare_write (struct file *filp, struct page *pg, diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index 86ccac80f0abc1..72a5588faecac5 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -37,6 +37,9 @@ #define JFS_ERR_CONTINUE 0x00000004 /* continue */ #define JFS_ERR_PANIC 0x00000008 /* panic */ +#define JFS_USRQUOTA 0x00000010 +#define JFS_GRPQUOTA 0x00000020 + /* platform option (conditional compilation) */ #define JFS_AIX 0x80000000 /* AIX support */ /* POSIX name/directory support */ diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 9ff89720f93bab..71bc34b96b2b89 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -23,9 +23,11 @@ #include <linux/parser.h> #include <linux/completion.h> #include <linux/vfs.h> +#include <linux/mount.h> #include <linux/moduleparam.h> #include <linux/posix_acl.h> #include <asm/uaccess.h> +#include <linux/seq_file.h> #include "jfs_incore.h" #include "jfs_filsys.h" @@ -192,7 +194,8 @@ static void jfs_put_super(struct super_block *sb) enum { Opt_integrity, Opt_nointegrity, Opt_iocharset, Opt_resize, - Opt_resize_nosize, Opt_errors, Opt_ignore, Opt_err, + Opt_resize_nosize, Opt_errors, Opt_ignore, Opt_err, Opt_quota, + Opt_usrquota, Opt_grpquota }; static match_table_t tokens = { @@ -204,8 +207,8 @@ static match_table_t tokens = { {Opt_errors, "errors=%s"}, {Opt_ignore, "noquota"}, {Opt_ignore, "quota"}, - {Opt_ignore, "usrquota"}, - {Opt_ignore, "grpquota"}, + {Opt_usrquota, "usrquota"}, + {Opt_grpquota, "grpquota"}, {Opt_err, NULL} }; @@ -293,6 +296,24 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize, } break; } + +#if defined(CONFIG_QUOTA) + case Opt_quota: + case Opt_usrquota: + *flag |= JFS_USRQUOTA; + break; + case Opt_grpquota: + *flag |= JFS_GRPQUOTA; + break; +#else + case Opt_usrquota: + case Opt_grpquota: + case Opt_quota: + printk(KERN_ERR + "JFS: quota operations not supported\n"); + break; +#endif + default: printk("jfs: Unrecognized mount option \"%s\" " " or missing value\n", p); @@ -539,6 +560,26 @@ static int jfs_sync_fs(struct super_block *sb, int wait) return 0; } +static int jfs_show_options(struct seq_file *seq, struct vfsmount *vfs) +{ + struct jfs_sb_info *sbi = JFS_SBI(vfs->mnt_sb); + + if (sbi->flag & JFS_NOINTEGRITY) + seq_puts(seq, ",nointegrity"); + else + seq_puts(seq, ",integrity"); + +#if defined(CONFIG_QUOTA) + if (sbi->flag & JFS_USRQUOTA) + seq_puts(seq, ",usrquota"); + + if (sbi->flag & JFS_GRPQUOTA) + seq_puts(seq, ",grpquota"); +#endif + + return 0; +} + static struct super_operations jfs_super_operations = { .alloc_inode = jfs_alloc_inode, .destroy_inode = jfs_destroy_inode, @@ -552,6 +593,7 @@ static struct super_operations jfs_super_operations = { .unlockfs = jfs_unlockfs, .statfs = jfs_statfs, .remount_fs = jfs_remount, + .show_options = jfs_show_options }; static struct export_operations jfs_export_operations = { diff --git a/fs/namei.c b/fs/namei.c index 6ec1f0fefc5b01..145e852c4bd02d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -525,6 +525,22 @@ static inline int __do_follow_link(struct path *path, struct nameidata *nd) return error; } +static inline void dput_path(struct path *path, struct nameidata *nd) +{ + dput(path->dentry); + if (path->mnt != nd->mnt) + mntput(path->mnt); +} + +static inline void path_to_nameidata(struct path *path, struct nameidata *nd) +{ + dput(nd->dentry); + if (nd->mnt != path->mnt) + mntput(nd->mnt); + nd->mnt = path->mnt; + nd->dentry = path->dentry; +} + /* * This limits recursive symlink follows to 8, while * limiting consecutive symlinks to 40. @@ -552,9 +568,7 @@ static inline int do_follow_link(struct path *path, struct nameidata *nd) nd->depth--; return err; loop: - dput(path->dentry); - if (path->mnt != nd->mnt) - mntput(path->mnt); + dput_path(path, nd); path_release(nd); return err; } @@ -813,13 +827,8 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) err = -ENOTDIR; if (!inode->i_op) break; - } else { - dput(nd->dentry); - if (nd->mnt != next.mnt) - mntput(nd->mnt); - nd->mnt = next.mnt; - nd->dentry = next.dentry; - } + } else + path_to_nameidata(&next, nd); err = -ENOTDIR; if (!inode->i_op->lookup) break; @@ -859,13 +868,8 @@ last_component: if (err) goto return_err; inode = nd->dentry->d_inode; - } else { - dput(nd->dentry); - if (nd->mnt != next.mnt) - mntput(nd->mnt); - nd->mnt = next.mnt; - nd->dentry = next.dentry; - } + } else + path_to_nameidata(&next, nd); err = -ENOENT; if (!inode) break; @@ -901,9 +905,7 @@ return_reval: return_base: return 0; out_dput: - dput(next.dentry); - if (nd->mnt != next.mnt) - mntput(next.mnt); + dput_path(&next, nd); break; } path_release(nd); @@ -1507,11 +1509,7 @@ do_last: if (path.dentry->d_inode->i_op && path.dentry->d_inode->i_op->follow_link) goto do_link; - dput(nd->dentry); - nd->dentry = path.dentry; - if (nd->mnt != path.mnt) - mntput(nd->mnt); - nd->mnt = path.mnt; + path_to_nameidata(&path, nd); error = -EISDIR; if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode)) goto exit; @@ -1522,9 +1520,7 @@ ok: return 0; exit_dput: - dput(path.dentry); - if (nd->mnt != path.mnt) - mntput(path.mnt); + dput_path(&path, nd); exit: path_release(nd); return error; diff --git a/fs/namespace.c b/fs/namespace.c index 79bd8a46e1e729..34156260c9b658 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -40,7 +40,7 @@ static inline int sysfs_init(void) __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); static struct list_head *mount_hashtable; -static int hash_mask, hash_bits; +static int hash_mask __read_mostly, hash_bits __read_mostly; static kmem_cache_t *mnt_cache; static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) @@ -1334,8 +1334,12 @@ asmlinkage long sys_pivot_root(const char __user *new_root, const char __user *p error = -EINVAL; if (user_nd.mnt->mnt_root != user_nd.dentry) goto out2; /* not a mountpoint */ + if (user_nd.mnt->mnt_parent == user_nd.mnt) + goto out2; /* not attached */ if (new_nd.mnt->mnt_root != new_nd.dentry) goto out2; /* not a mountpoint */ + if (new_nd.mnt->mnt_parent == new_nd.mnt) + goto out2; /* not attached */ tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */ spin_lock(&vfsmount_lock); if (tmp != new_nd.mnt) { diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 9a11aa39e2e4e8..057aff745506da 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -26,6 +26,7 @@ #include <linux/namei.h> #include <linux/mount.h> #include <linux/hash.h> +#include <linux/module.h> #include <linux/sunrpc/svc.h> #include <linux/nfsd/nfsd.h> @@ -221,6 +222,7 @@ static int expkey_show(struct seq_file *m, } struct cache_detail svc_expkey_cache = { + .owner = THIS_MODULE, .hash_size = EXPKEY_HASHMAX, .hash_table = expkey_table, .name = "nfsd.fh", @@ -456,6 +458,7 @@ static int svc_export_show(struct seq_file *m, return 0; } struct cache_detail svc_export_cache = { + .owner = THIS_MODULE, .hash_size = EXPORT_HASHMAX, .hash_table = export_table, .name = "nfsd.export", diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 5605a26efc57d9..13369650cdf9b8 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -187,6 +187,7 @@ static int idtoname_parse(struct cache_detail *, char *, int); static struct ent *idtoname_lookup(struct ent *, int); static struct cache_detail idtoname_cache = { + .owner = THIS_MODULE, .hash_size = ENT_HASHMAX, .hash_table = idtoname_table, .name = "nfs4.idtoname", @@ -320,6 +321,7 @@ static struct ent *nametoid_lookup(struct ent *, int); static int nametoid_parse(struct cache_detail *, char *, int); static struct cache_detail nametoid_cache = { + .owner = THIS_MODULE, .hash_size = ENT_HASHMAX, .hash_table = nametoid_table, .name = "nfs4.nametoid", @@ -404,8 +406,10 @@ nfsd_idmap_init(void) void nfsd_idmap_shutdown(void) { - cache_unregister(&idtoname_cache); - cache_unregister(&nametoid_cache); + if (cache_unregister(&idtoname_cache)) + printk(KERN_ERR "nfsd: failed to unregister idtoname cache\n"); + if (cache_unregister(&nametoid_cache)) + printk(KERN_ERR "nfsd: failed to unregister nametoid cache\n"); } /* diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 57ed50fe7f8568..954cf893d50c34 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -93,7 +93,7 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname) dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n", clname->len, clname->data); - tfm = crypto_alloc_tfm("md5", 0); + tfm = crypto_alloc_tfm("md5", CRYPTO_TFM_REQ_MAY_SLEEP); if (tfm == NULL) goto out; cksum.len = crypto_tfm_alg_digestsize(tfm); @@ -114,8 +114,7 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname) kfree(cksum.data); status = nfs_ok; out: - if (tfm) - crypto_free_tfm(tfm); + crypto_free_tfm(tfm); return status; } diff --git a/fs/open.c b/fs/open.c index 32bf05e2996d80..4ee2dcc31c285d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -933,16 +933,11 @@ void fastcall fd_install(unsigned int fd, struct file * file) EXPORT_SYMBOL(fd_install); -asmlinkage long sys_open(const char __user * filename, int flags, int mode) +long do_sys_open(const char __user *filename, int flags, int mode) { - char * tmp; - int fd; + char *tmp = getname(filename); + int fd = PTR_ERR(tmp); - if (force_o_largefile()) - flags |= O_LARGEFILE; - - tmp = getname(filename); - fd = PTR_ERR(tmp); if (!IS_ERR(tmp)) { fd = get_unused_fd(); if (fd >= 0) { @@ -959,6 +954,14 @@ asmlinkage long sys_open(const char __user * filename, int flags, int mode) } return fd; } + +asmlinkage long sys_open(const char __user *filename, int flags, int mode) +{ + if (force_o_largefile()) + flags |= O_LARGEFILE; + + return do_sys_open(filename, flags, mode); +} EXPORT_SYMBOL_GPL(sys_open); #ifndef __alpha__ diff --git a/fs/pipe.c b/fs/pipe.c index 25aa09f9d09d08..2c7a23dde2d83f 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -415,6 +415,10 @@ pipe_poll(struct file *filp, poll_table *wait) if (filp->f_mode & FMODE_WRITE) { mask |= (nrbufs < PIPE_BUFFERS) ? POLLOUT | POLLWRNORM : 0; + /* + * Most Unices do not set POLLERR for FIFOs but on Linux they + * behave exactly like pipes for poll(). + */ if (!PIPE_READERS(*inode)) mask |= POLLERR; } @@ -422,9 +426,6 @@ pipe_poll(struct file *filp, poll_table *wait) return mask; } -/* FIXME: most Unices do not set POLLERR for fifos */ -#define fifo_poll pipe_poll - static int pipe_release(struct inode *inode, int decr, int decw) { @@ -568,7 +569,7 @@ struct file_operations read_fifo_fops = { .read = pipe_read, .readv = pipe_readv, .write = bad_pipe_w, - .poll = fifo_poll, + .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_read_open, .release = pipe_read_release, @@ -580,7 +581,7 @@ struct file_operations write_fifo_fops = { .read = bad_pipe_r, .write = pipe_write, .writev = pipe_writev, - .poll = fifo_poll, + .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_write_open, .release = pipe_write_release, @@ -593,7 +594,7 @@ struct file_operations rdwr_fifo_fops = { .readv = pipe_readv, .write = pipe_write, .writev = pipe_writev, - .poll = fifo_poll, + .poll = pipe_poll, .ioctl = pipe_ioctl, .open = pipe_rdwr_open, .release = pipe_rdwr_release, diff --git a/fs/proc/base.c b/fs/proc/base.c index 491f2d9f89acd9..84751f3f52d530 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -11,6 +11,40 @@ * go into icache. We cache the reference to task_struct upon lookup too. * Eventually it should become a filesystem in its own. We don't use the * rest of procfs anymore. + * + * + * Changelog: + * 17-Jan-2005 + * Allan Bezerra + * Bruna Moreira <bruna.moreira@indt.org.br> + * Edjard Mota <edjard.mota@indt.org.br> + * Ilias Biris <ilias.biris@indt.org.br> + * Mauricio Lin <mauricio.lin@indt.org.br> + * + * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT + * + * A new process specific entry (smaps) included in /proc. It shows the + * size of rss for each memory area. The maps entry lacks information + * about physical memory size (rss) for each mapped file, i.e., + * rss information for executables and library files. + * This additional information is useful for any tools that need to know + * about physical memory consumption for a process specific library. + * + * Changelog: + * 21-Feb-2005 + * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT + * Pud inclusion in the page table walking. + * + * ChangeLog: + * 10-Mar-2005 + * 10LE Instituto Nokia de Tecnologia - INdT: + * A better way to walks through the page table as suggested by Hugh Dickins. + * + * Simo Piiroinen <simo.piiroinen@nokia.com>: + * Smaps information related to shared, private, clean and dirty pages. + * + * Paul Mundt <paul.mundt@nokia.com>: + * Overall revision about smaps. */ #include <asm/uaccess.h> @@ -65,8 +99,10 @@ enum pid_directory_inos { PROC_TGID_STAT, PROC_TGID_STATM, PROC_TGID_MAPS, + PROC_TGID_NUMA_MAPS, PROC_TGID_MOUNTS, PROC_TGID_WCHAN, + PROC_TGID_SMAPS, #ifdef CONFIG_SCHEDSTATS PROC_TGID_SCHEDSTAT, #endif @@ -83,7 +119,6 @@ enum pid_directory_inos { #ifdef CONFIG_AUDITSYSCALL PROC_TGID_LOGINUID, #endif - PROC_TGID_FD_DIR, PROC_TGID_OOM_SCORE, PROC_TGID_OOM_ADJUST, PROC_TID_INO, @@ -102,8 +137,10 @@ enum pid_directory_inos { PROC_TID_STAT, PROC_TID_STATM, PROC_TID_MAPS, + PROC_TID_NUMA_MAPS, PROC_TID_MOUNTS, PROC_TID_WCHAN, + PROC_TID_SMAPS, #ifdef CONFIG_SCHEDSTATS PROC_TID_SCHEDSTAT, #endif @@ -120,9 +157,11 @@ enum pid_directory_inos { #ifdef CONFIG_AUDITSYSCALL PROC_TID_LOGINUID, #endif - PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ PROC_TID_OOM_SCORE, PROC_TID_OOM_ADJUST, + + /* Add new entries before this */ + PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ }; struct pid_entry { @@ -144,6 +183,9 @@ static struct pid_entry tgid_base_stuff[] = { E(PROC_TGID_STAT, "stat", S_IFREG|S_IRUGO), E(PROC_TGID_STATM, "statm", S_IFREG|S_IRUGO), E(PROC_TGID_MAPS, "maps", S_IFREG|S_IRUGO), +#ifdef CONFIG_NUMA + E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), +#endif E(PROC_TGID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), #ifdef CONFIG_SECCOMP E(PROC_TGID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), @@ -152,6 +194,7 @@ static struct pid_entry tgid_base_stuff[] = { E(PROC_TGID_ROOT, "root", S_IFLNK|S_IRWXUGO), E(PROC_TGID_EXE, "exe", S_IFLNK|S_IRWXUGO), E(PROC_TGID_MOUNTS, "mounts", S_IFREG|S_IRUGO), + E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUGO), #ifdef CONFIG_SECURITY E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), #endif @@ -180,6 +223,9 @@ static struct pid_entry tid_base_stuff[] = { E(PROC_TID_STAT, "stat", S_IFREG|S_IRUGO), E(PROC_TID_STATM, "statm", S_IFREG|S_IRUGO), E(PROC_TID_MAPS, "maps", S_IFREG|S_IRUGO), +#ifdef CONFIG_NUMA + E(PROC_TID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), +#endif E(PROC_TID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), #ifdef CONFIG_SECCOMP E(PROC_TID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), @@ -188,6 +234,7 @@ static struct pid_entry tid_base_stuff[] = { E(PROC_TID_ROOT, "root", S_IFLNK|S_IRWXUGO), E(PROC_TID_EXE, "exe", S_IFLNK|S_IRWXUGO), E(PROC_TID_MOUNTS, "mounts", S_IFREG|S_IRUGO), + E(PROC_TID_SMAPS, "smaps", S_IFREG|S_IRUGO), #ifdef CONFIG_SECURITY E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), #endif @@ -251,15 +298,21 @@ static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsm return -ENOENT; } -static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +static struct fs_struct *get_fs_struct(struct task_struct *task) { struct fs_struct *fs; - int result = -ENOENT; - task_lock(proc_task(inode)); - fs = proc_task(inode)->fs; + task_lock(task); + fs = task->fs; if(fs) atomic_inc(&fs->count); - task_unlock(proc_task(inode)); + task_unlock(task); + return fs; +} + +static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +{ + struct fs_struct *fs = get_fs_struct(proc_task(inode)); + int result = -ENOENT; if (fs) { read_lock(&fs->lock); *mnt = mntget(fs->pwdmnt); @@ -273,13 +326,8 @@ static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfs static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) { - struct fs_struct *fs; + struct fs_struct *fs = get_fs_struct(proc_task(inode)); int result = -ENOENT; - task_lock(proc_task(inode)); - fs = proc_task(inode)->fs; - if(fs) - atomic_inc(&fs->count); - task_unlock(proc_task(inode)); if (fs) { read_lock(&fs->lock); *mnt = mntget(fs->rootmnt); @@ -298,33 +346,6 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \ security_ptrace(current,task) == 0)) -static int may_ptrace_attach(struct task_struct *task) -{ - int retval = 0; - - task_lock(task); - - if (!task->mm) - goto out; - if (((current->uid != task->euid) || - (current->uid != task->suid) || - (current->uid != task->uid) || - (current->gid != task->egid) || - (current->gid != task->sgid) || - (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE)) - goto out; - rmb(); - if (task->mm->dumpable != 1 && !capable(CAP_SYS_PTRACE)) - goto out; - if (security_ptrace(current, task)) - goto out; - - retval = 1; -out: - task_unlock(task); - return retval; -} - static int proc_pid_environ(struct task_struct *task, char * buffer) { int res = 0; @@ -334,7 +355,7 @@ static int proc_pid_environ(struct task_struct *task, char * buffer) if (len > PAGE_SIZE) len = PAGE_SIZE; res = access_process_vm(task, mm->env_start, buffer, len, 0); - if (!may_ptrace_attach(task)) + if (!ptrace_may_attach(task)) res = -ESRCH; mmput(mm); } @@ -515,6 +536,46 @@ static struct file_operations proc_maps_operations = { .release = seq_release, }; +#ifdef CONFIG_NUMA +extern struct seq_operations proc_pid_numa_maps_op; +static int numa_maps_open(struct inode *inode, struct file *file) +{ + struct task_struct *task = proc_task(inode); + int ret = seq_open(file, &proc_pid_numa_maps_op); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = task; + } + return ret; +} + +static struct file_operations proc_numa_maps_operations = { + .open = numa_maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; +#endif + +extern struct seq_operations proc_pid_smaps_op; +static int smaps_open(struct inode *inode, struct file *file) +{ + struct task_struct *task = proc_task(inode); + int ret = seq_open(file, &proc_pid_smaps_op); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = task; + } + return ret; +} + +static struct file_operations proc_smaps_operations = { + .open = smaps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + extern struct seq_operations mounts_op; static int mounts_open(struct inode *inode, struct file *file) { @@ -597,7 +658,7 @@ static ssize_t mem_read(struct file * file, char __user * buf, int ret = -ESRCH; struct mm_struct *mm; - if (!MAY_PTRACE(task) || !may_ptrace_attach(task)) + if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) goto out; ret = -ENOMEM; @@ -623,7 +684,7 @@ static ssize_t mem_read(struct file * file, char __user * buf, this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; retval = access_process_vm(task, src, page, this_len, 0); - if (!retval || !MAY_PTRACE(task) || !may_ptrace_attach(task)) { + if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) { if (!ret) ret = -EIO; break; @@ -661,7 +722,7 @@ static ssize_t mem_write(struct file * file, const char * buf, struct task_struct *task = proc_task(file->f_dentry->d_inode); unsigned long dst = *ppos; - if (!MAY_PTRACE(task) || !may_ptrace_attach(task)) + if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) return -ESRCH; page = (char *)__get_free_page(GFP_USER); @@ -1524,6 +1585,12 @@ static struct dentry *proc_pident_lookup(struct inode *dir, case PROC_TGID_MAPS: inode->i_fop = &proc_maps_operations; break; +#ifdef CONFIG_NUMA + case PROC_TID_NUMA_MAPS: + case PROC_TGID_NUMA_MAPS: + inode->i_fop = &proc_numa_maps_operations; + break; +#endif case PROC_TID_MEM: case PROC_TGID_MEM: inode->i_op = &proc_mem_inode_operations; @@ -1539,6 +1606,10 @@ static struct dentry *proc_pident_lookup(struct inode *dir, case PROC_TGID_MOUNTS: inode->i_fop = &proc_mounts_operations; break; + case PROC_TID_SMAPS: + case PROC_TGID_SMAPS: + inode->i_fop = &proc_smaps_operations; + break; #ifdef CONFIG_SECURITY case PROC_TID_ATTR: inode->i_nlink = 2; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index abe8920313fb32..8a8c34461d481c 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -249,6 +249,18 @@ out: return error; } +static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct proc_dir_entry *de = PROC_I(inode)->pde; + if (de && de->nlink) + inode->i_nlink = de->nlink; + + generic_fillattr(inode, stat); + return 0; +} + static struct inode_operations proc_file_inode_operations = { .setattr = proc_notify_change, }; @@ -475,6 +487,7 @@ static struct file_operations proc_dir_operations = { */ static struct inode_operations proc_dir_inode_operations = { .lookup = proc_lookup, + .getattr = proc_getattr, .setattr = proc_notify_change, }; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 28b4a0253a9216..c7ef3e48e35bae 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -2,8 +2,13 @@ #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/seq_file.h> +#include <linux/highmem.h> +#include <linux/pagemap.h> +#include <linux/mempolicy.h> + #include <asm/elf.h> #include <asm/uaccess.h> +#include <asm/tlbflush.h> #include "internal.h" char *task_mem(struct mm_struct *mm, char *buffer) @@ -87,49 +92,58 @@ static void pad_len_spaces(struct seq_file *m, int len) seq_printf(m, "%*c", len, ' '); } -static int show_map(struct seq_file *m, void *v) +struct mem_size_stats +{ + unsigned long resident; + unsigned long shared_clean; + unsigned long shared_dirty; + unsigned long private_clean; + unsigned long private_dirty; +}; + +static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss) { struct task_struct *task = m->private; - struct vm_area_struct *map = v; - struct mm_struct *mm = map->vm_mm; - struct file *file = map->vm_file; - int flags = map->vm_flags; + struct vm_area_struct *vma = v; + struct mm_struct *mm = vma->vm_mm; + struct file *file = vma->vm_file; + int flags = vma->vm_flags; unsigned long ino = 0; dev_t dev = 0; int len; if (file) { - struct inode *inode = map->vm_file->f_dentry->d_inode; + struct inode *inode = vma->vm_file->f_dentry->d_inode; dev = inode->i_sb->s_dev; ino = inode->i_ino; } seq_printf(m, "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", - map->vm_start, - map->vm_end, + vma->vm_start, + vma->vm_end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? 's' : 'p', - map->vm_pgoff << PAGE_SHIFT, + vma->vm_pgoff << PAGE_SHIFT, MAJOR(dev), MINOR(dev), ino, &len); /* * Print the dentry name for named mappings, and a * special [heap] marker for the heap: */ - if (map->vm_file) { + if (file) { pad_len_spaces(m, len); - seq_path(m, file->f_vfsmnt, file->f_dentry, ""); + seq_path(m, file->f_vfsmnt, file->f_dentry, "\n"); } else { if (mm) { - if (map->vm_start <= mm->start_brk && - map->vm_end >= mm->brk) { + if (vma->vm_start <= mm->start_brk && + vma->vm_end >= mm->brk) { pad_len_spaces(m, len); seq_puts(m, "[heap]"); } else { - if (map->vm_start <= mm->start_stack && - map->vm_end >= mm->start_stack) { + if (vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack) { pad_len_spaces(m, len); seq_puts(m, "[stack]"); @@ -141,24 +155,146 @@ static int show_map(struct seq_file *m, void *v) } } seq_putc(m, '\n'); - if (m->count < m->size) /* map is copied successfully */ - m->version = (map != get_gate_vma(task))? map->vm_start: 0; + + if (mss) + seq_printf(m, + "Size: %8lu kB\n" + "Rss: %8lu kB\n" + "Shared_Clean: %8lu kB\n" + "Shared_Dirty: %8lu kB\n" + "Private_Clean: %8lu kB\n" + "Private_Dirty: %8lu kB\n", + (vma->vm_end - vma->vm_start) >> 10, + mss->resident >> 10, + mss->shared_clean >> 10, + mss->shared_dirty >> 10, + mss->private_clean >> 10, + mss->private_dirty >> 10); + + if (m->count < m->size) /* vma is copied successfully */ + m->version = (vma != get_gate_vma(task))? vma->vm_start: 0; return 0; } +static int show_map(struct seq_file *m, void *v) +{ + return show_map_internal(m, v, 0); +} + +static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, + struct mem_size_stats *mss) +{ + pte_t *pte, ptent; + unsigned long pfn; + struct page *page; + + pte = pte_offset_map(pmd, addr); + do { + ptent = *pte; + if (pte_none(ptent) || !pte_present(ptent)) + continue; + + mss->resident += PAGE_SIZE; + pfn = pte_pfn(ptent); + if (!pfn_valid(pfn)) + continue; + + page = pfn_to_page(pfn); + if (page_count(page) >= 2) { + if (pte_dirty(ptent)) + mss->shared_dirty += PAGE_SIZE; + else + mss->shared_clean += PAGE_SIZE; + } else { + if (pte_dirty(ptent)) + mss->private_dirty += PAGE_SIZE; + else + mss->private_clean += PAGE_SIZE; + } + } while (pte++, addr += PAGE_SIZE, addr != end); + pte_unmap(pte - 1); + cond_resched_lock(&vma->vm_mm->page_table_lock); +} + +static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud, + unsigned long addr, unsigned long end, + struct mem_size_stats *mss) +{ + pmd_t *pmd; + unsigned long next; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(pmd)) + continue; + smaps_pte_range(vma, pmd, addr, next, mss); + } while (pmd++, addr = next, addr != end); +} + +static inline void smaps_pud_range(struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + struct mem_size_stats *mss) +{ + pud_t *pud; + unsigned long next; + + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + smaps_pmd_range(vma, pud, addr, next, mss); + } while (pud++, addr = next, addr != end); +} + +static inline void smaps_pgd_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + struct mem_size_stats *mss) +{ + pgd_t *pgd; + unsigned long next; + + pgd = pgd_offset(vma->vm_mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + smaps_pud_range(vma, pgd, addr, next, mss); + } while (pgd++, addr = next, addr != end); +} + +static int show_smap(struct seq_file *m, void *v) +{ + struct vm_area_struct *vma = v; + struct mm_struct *mm = vma->vm_mm; + struct mem_size_stats mss; + + memset(&mss, 0, sizeof mss); + + if (mm) { + spin_lock(&mm->page_table_lock); + smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss); + spin_unlock(&mm->page_table_lock); + } + + return show_map_internal(m, v, &mss); +} + static void *m_start(struct seq_file *m, loff_t *pos) { struct task_struct *task = m->private; unsigned long last_addr = m->version; struct mm_struct *mm; - struct vm_area_struct *map, *tail_map; + struct vm_area_struct *vma, *tail_vma; loff_t l = *pos; /* * We remember last_addr rather than next_addr to hit with * mmap_cache most of the time. We have zero last_addr at - * the begining and also after lseek. We will have -1 last_addr - * after the end of the maps. + * the beginning and also after lseek. We will have -1 last_addr + * after the end of the vmas. */ if (last_addr == -1UL) @@ -168,47 +304,47 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!mm) return NULL; - tail_map = get_gate_vma(task); + tail_vma = get_gate_vma(task); down_read(&mm->mmap_sem); /* Start with last addr hint */ - if (last_addr && (map = find_vma(mm, last_addr))) { - map = map->vm_next; + if (last_addr && (vma = find_vma(mm, last_addr))) { + vma = vma->vm_next; goto out; } /* - * Check the map index is within the range and do + * Check the vma index is within the range and do * sequential scan until m_index. */ - map = NULL; + vma = NULL; if ((unsigned long)l < mm->map_count) { - map = mm->mmap; - while (l-- && map) - map = map->vm_next; + vma = mm->mmap; + while (l-- && vma) + vma = vma->vm_next; goto out; } if (l != mm->map_count) - tail_map = NULL; /* After gate map */ + tail_vma = NULL; /* After gate vma */ out: - if (map) - return map; + if (vma) + return vma; - /* End of maps has reached */ - m->version = (tail_map != NULL)? 0: -1UL; + /* End of vmas has been reached */ + m->version = (tail_vma != NULL)? 0: -1UL; up_read(&mm->mmap_sem); mmput(mm); - return tail_map; + return tail_vma; } static void m_stop(struct seq_file *m, void *v) { struct task_struct *task = m->private; - struct vm_area_struct *map = v; - if (map && map != get_gate_vma(task)) { - struct mm_struct *mm = map->vm_mm; + struct vm_area_struct *vma = v; + if (vma && vma != get_gate_vma(task)) { + struct mm_struct *mm = vma->vm_mm; up_read(&mm->mmap_sem); mmput(mm); } @@ -217,14 +353,14 @@ static void m_stop(struct seq_file *m, void *v) static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct task_struct *task = m->private; - struct vm_area_struct *map = v; - struct vm_area_struct *tail_map = get_gate_vma(task); + struct vm_area_struct *vma = v; + struct vm_area_struct *tail_vma = get_gate_vma(task); (*pos)++; - if (map && (map != tail_map) && map->vm_next) - return map->vm_next; + if (vma && (vma != tail_vma) && vma->vm_next) + return vma->vm_next; m_stop(m, v); - return (map != tail_map)? tail_map: NULL; + return (vma != tail_vma)? tail_vma: NULL; } struct seq_operations proc_pid_maps_op = { @@ -233,3 +369,140 @@ struct seq_operations proc_pid_maps_op = { .stop = m_stop, .show = show_map }; + +struct seq_operations proc_pid_smaps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_smap +}; + +#ifdef CONFIG_NUMA + +struct numa_maps { + unsigned long pages; + unsigned long anon; + unsigned long mapped; + unsigned long mapcount_max; + unsigned long node[MAX_NUMNODES]; +}; + +/* + * Calculate numa node maps for a vma + */ +static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma) +{ + struct page *page; + unsigned long vaddr; + struct mm_struct *mm = vma->vm_mm; + int i; + struct numa_maps *md = kmalloc(sizeof(struct numa_maps), GFP_KERNEL); + + if (!md) + return NULL; + md->pages = 0; + md->anon = 0; + md->mapped = 0; + md->mapcount_max = 0; + for_each_node(i) + md->node[i] =0; + + spin_lock(&mm->page_table_lock); + for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) { + page = follow_page(mm, vaddr, 0); + if (page) { + int count = page_mapcount(page); + + if (count) + md->mapped++; + if (count > md->mapcount_max) + md->mapcount_max = count; + md->pages++; + if (PageAnon(page)) + md->anon++; + md->node[page_to_nid(page)]++; + } + } + spin_unlock(&mm->page_table_lock); + return md; +} + +static int show_numa_map(struct seq_file *m, void *v) +{ + struct task_struct *task = m->private; + struct vm_area_struct *vma = v; + struct mempolicy *pol; + struct numa_maps *md; + struct zone **z; + int n; + int first; + + if (!vma->vm_mm) + return 0; + + md = get_numa_maps(vma); + if (!md) + return 0; + + seq_printf(m, "%08lx", vma->vm_start); + pol = get_vma_policy(task, vma, vma->vm_start); + /* Print policy */ + switch (pol->policy) { + case MPOL_PREFERRED: + seq_printf(m, " prefer=%d", pol->v.preferred_node); + break; + case MPOL_BIND: + seq_printf(m, " bind={"); + first = 1; + for (z = pol->v.zonelist->zones; *z; z++) { + + if (!first) + seq_putc(m, ','); + else + first = 0; + seq_printf(m, "%d/%s", (*z)->zone_pgdat->node_id, + (*z)->name); + } + seq_putc(m, '}'); + break; + case MPOL_INTERLEAVE: + seq_printf(m, " interleave={"); + first = 1; + for_each_node(n) { + if (test_bit(n, pol->v.nodes)) { + if (!first) + seq_putc(m,','); + else + first = 0; + seq_printf(m, "%d",n); + } + } + seq_putc(m, '}'); + break; + default: + seq_printf(m," default"); + break; + } + seq_printf(m, " MaxRef=%lu Pages=%lu Mapped=%lu", + md->mapcount_max, md->pages, md->mapped); + if (md->anon) + seq_printf(m," Anon=%lu",md->anon); + + for_each_online_node(n) { + if (md->node[n]) + seq_printf(m, " N%d=%lu", n, md->node[n]); + } + seq_putc(m, '\n'); + kfree(md); + if (m->count < m->size) /* vma is copied successfully */ + m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0; + return 0; +} + +struct seq_operations proc_pid_numa_maps_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_numa_map +}; +#endif diff --git a/fs/read_write.c b/fs/read_write.c index 563abd09b5c84b..b60324aaa2b673 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -188,7 +188,7 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count struct inode *inode; loff_t pos; - if (unlikely(count > file->f_maxcount)) + if (unlikely(count > INT_MAX)) goto Einval; pos = *ppos; if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index ca7989b04be349..a8e29e9bbbd08e 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -1034,7 +1034,7 @@ static int flush_commit_list(struct super_block *s, SB_ONDISK_JOURNAL_SIZE(s); tbh = journal_find_get_block(s, bn); if (buffer_dirty(tbh)) /* redundant, ll_rw_block() checks */ - ll_rw_block(WRITE, 1, &tbh); + ll_rw_block(SWRITE, 1, &tbh); put_bh(tbh); } atomic_dec(&journal->j_async_throttle); @@ -2172,7 +2172,7 @@ static int journal_read_transaction(struct super_block *p_s_sb, /* flush out the real blocks */ for (i = 0; i < get_desc_trans_len(desc); i++) { set_buffer_dirty(real_blocks[i]); - ll_rw_block(WRITE, 1, real_blocks + i); + ll_rw_block(SWRITE, 1, real_blocks + i); } for (i = 0; i < get_desc_trans_len(desc); i++) { wait_on_buffer(real_blocks[i]); diff --git a/fs/relayfs/Makefile b/fs/relayfs/Makefile new file mode 100644 index 00000000000000..e76e182cdb3894 --- /dev/null +++ b/fs/relayfs/Makefile @@ -0,0 +1,4 @@ +obj-$(CONFIG_RELAYFS_FS) += relayfs.o + +relayfs-y := relay.o inode.o buffers.o + diff --git a/fs/relayfs/buffers.c b/fs/relayfs/buffers.c new file mode 100644 index 00000000000000..2aa8e27199999d --- /dev/null +++ b/fs/relayfs/buffers.c @@ -0,0 +1,189 @@ +/* + * RelayFS buffer management code. + * + * Copyright (C) 2002-2005 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp + * Copyright (C) 1999-2005 - Karim Yaghmour (karim@opersys.com) + * + * This file is released under the GPL. + */ + +#include <linux/module.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> +#include <linux/relayfs_fs.h> +#include "relay.h" +#include "buffers.h" + +/* + * close() vm_op implementation for relayfs file mapping. + */ +static void relay_file_mmap_close(struct vm_area_struct *vma) +{ + struct rchan_buf *buf = vma->vm_private_data; + buf->chan->cb->buf_unmapped(buf, vma->vm_file); +} + +/* + * nopage() vm_op implementation for relayfs file mapping. + */ +static struct page *relay_buf_nopage(struct vm_area_struct *vma, + unsigned long address, + int *type) +{ + struct page *page; + struct rchan_buf *buf = vma->vm_private_data; + unsigned long offset = address - vma->vm_start; + + if (address > vma->vm_end) + return NOPAGE_SIGBUS; /* Disallow mremap */ + if (!buf) + return NOPAGE_OOM; + + page = vmalloc_to_page(buf->start + offset); + if (!page) + return NOPAGE_OOM; + get_page(page); + + if (type) + *type = VM_FAULT_MINOR; + + return page; +} + +/* + * vm_ops for relay file mappings. + */ +static struct vm_operations_struct relay_file_mmap_ops = { + .nopage = relay_buf_nopage, + .close = relay_file_mmap_close, +}; + +/** + * relay_mmap_buf: - mmap channel buffer to process address space + * @buf: relay channel buffer + * @vma: vm_area_struct describing memory to be mapped + * + * Returns 0 if ok, negative on error + * + * Caller should already have grabbed mmap_sem. + */ +int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma) +{ + unsigned long length = vma->vm_end - vma->vm_start; + struct file *filp = vma->vm_file; + + if (!buf) + return -EBADF; + + if (length != (unsigned long)buf->chan->alloc_size) + return -EINVAL; + + vma->vm_ops = &relay_file_mmap_ops; + vma->vm_private_data = buf; + buf->chan->cb->buf_mapped(buf, filp); + + return 0; +} + +/** + * relay_alloc_buf - allocate a channel buffer + * @buf: the buffer struct + * @size: total size of the buffer + * + * Returns a pointer to the resulting buffer, NULL if unsuccessful + */ +static void *relay_alloc_buf(struct rchan_buf *buf, unsigned long size) +{ + void *mem; + unsigned int i, j, n_pages; + + size = PAGE_ALIGN(size); + n_pages = size >> PAGE_SHIFT; + + buf->page_array = kcalloc(n_pages, sizeof(struct page *), GFP_KERNEL); + if (!buf->page_array) + return NULL; + + for (i = 0; i < n_pages; i++) { + buf->page_array[i] = alloc_page(GFP_KERNEL); + if (unlikely(!buf->page_array[i])) + goto depopulate; + } + mem = vmap(buf->page_array, n_pages, GFP_KERNEL, PAGE_KERNEL); + if (!mem) + goto depopulate; + + memset(mem, 0, size); + buf->page_count = n_pages; + return mem; + +depopulate: + for (j = 0; j < i; j++) + __free_page(buf->page_array[j]); + kfree(buf->page_array); + return NULL; +} + +/** + * relay_create_buf - allocate and initialize a channel buffer + * @alloc_size: size of the buffer to allocate + * @n_subbufs: number of sub-buffers in the channel + * + * Returns channel buffer if successful, NULL otherwise + */ +struct rchan_buf *relay_create_buf(struct rchan *chan) +{ + struct rchan_buf *buf = kcalloc(1, sizeof(struct rchan_buf), GFP_KERNEL); + if (!buf) + return NULL; + + buf->padding = kmalloc(chan->n_subbufs * sizeof(size_t *), GFP_KERNEL); + if (!buf->padding) + goto free_buf; + + buf->start = relay_alloc_buf(buf, chan->alloc_size); + if (!buf->start) + goto free_buf; + + buf->chan = chan; + kref_get(&buf->chan->kref); + return buf; + +free_buf: + kfree(buf->padding); + kfree(buf); + return NULL; +} + +/** + * relay_destroy_buf - destroy an rchan_buf struct and associated buffer + * @buf: the buffer struct + */ +void relay_destroy_buf(struct rchan_buf *buf) +{ + struct rchan *chan = buf->chan; + unsigned int i; + + if (likely(buf->start)) { + vunmap(buf->start); + for (i = 0; i < buf->page_count; i++) + __free_page(buf->page_array[i]); + kfree(buf->page_array); + } + kfree(buf->padding); + kfree(buf); + kref_put(&chan->kref, relay_destroy_channel); +} + +/** + * relay_remove_buf - remove a channel buffer + * + * Removes the file from the relayfs fileystem, which also frees the + * rchan_buf_struct and the channel buffer. Should only be called from + * kref_put(). + */ +void relay_remove_buf(struct kref *kref) +{ + struct rchan_buf *buf = container_of(kref, struct rchan_buf, kref); + relayfs_remove(buf->dentry); +} diff --git a/fs/relayfs/buffers.h b/fs/relayfs/buffers.h new file mode 100644 index 00000000000000..37a12493f641df --- /dev/null +++ b/fs/relayfs/buffers.h @@ -0,0 +1,12 @@ +#ifndef _BUFFERS_H +#define _BUFFERS_H + +/* This inspired by rtai/shmem */ +#define FIX_SIZE(x) (((x) - 1) & PAGE_MASK) + PAGE_SIZE + +extern int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma); +extern struct rchan_buf *relay_create_buf(struct rchan *chan); +extern void relay_destroy_buf(struct rchan_buf *buf); +extern void relay_remove_buf(struct kref *kref); + +#endif/* _BUFFERS_H */ diff --git a/fs/relayfs/inode.c b/fs/relayfs/inode.c new file mode 100644 index 00000000000000..0f7f88d067adad --- /dev/null +++ b/fs/relayfs/inode.c @@ -0,0 +1,609 @@ +/* + * VFS-related code for RelayFS, a high-speed data relay filesystem. + * + * Copyright (C) 2003-2005 - Tom Zanussi <zanussi@us.ibm.com>, IBM Corp + * Copyright (C) 2003-2005 - Karim Yaghmour <karim@opersys.com> + * + * Based on ramfs, Copyright (C) 2002 - Linus Torvalds + * + * This file is released under the GPL. + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/pagemap.h> +#include <linux/init.h> +#include <linux/string.h> +#include <linux/backing-dev.h> +#include <linux/namei.h> +#include <linux/poll.h> +#include <linux/relayfs_fs.h> +#include "relay.h" +#include "buffers.h" + +#define RELAYFS_MAGIC 0xF0B4A981 + +static struct vfsmount * relayfs_mount; +static int relayfs_mount_count; +static kmem_cache_t * relayfs_inode_cachep; + +static struct backing_dev_info relayfs_backing_dev_info = { + .ra_pages = 0, /* No readahead */ + .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK, +}; + +static struct inode *relayfs_get_inode(struct super_block *sb, int mode, + struct rchan *chan) +{ + struct rchan_buf *buf = NULL; + struct inode *inode; + + if (S_ISREG(mode)) { + BUG_ON(!chan); + buf = relay_create_buf(chan); + if (!buf) + return NULL; + } + + inode = new_inode(sb); + if (!inode) { + relay_destroy_buf(buf); + return NULL; + } + + inode->i_mode = mode; + inode->i_uid = 0; + inode->i_gid = 0; + inode->i_blksize = PAGE_CACHE_SIZE; + inode->i_blocks = 0; + inode->i_mapping->backing_dev_info = &relayfs_backing_dev_info; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + switch (mode & S_IFMT) { + case S_IFREG: + inode->i_fop = &relayfs_file_operations; + RELAYFS_I(inode)->buf = buf; + break; + case S_IFDIR: + inode->i_op = &simple_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inode->i_nlink++; + break; + default: + break; + } + + return inode; +} + +/** + * relayfs_create_entry - create a relayfs directory or file + * @name: the name of the file to create + * @parent: parent directory + * @mode: mode + * @chan: relay channel associated with the file + * + * Returns the new dentry, NULL on failure + * + * Creates a file or directory with the specifed permissions. + */ +static struct dentry *relayfs_create_entry(const char *name, + struct dentry *parent, + int mode, + struct rchan *chan) +{ + struct dentry *d; + struct inode *inode; + int error = 0; + + BUG_ON(!name || !(S_ISREG(mode) || S_ISDIR(mode))); + + error = simple_pin_fs("relayfs", &relayfs_mount, &relayfs_mount_count); + if (error) { + printk(KERN_ERR "Couldn't mount relayfs: errcode %d\n", error); + return NULL; + } + + if (!parent && relayfs_mount && relayfs_mount->mnt_sb) + parent = relayfs_mount->mnt_sb->s_root; + + if (!parent) { + simple_release_fs(&relayfs_mount, &relayfs_mount_count); + return NULL; + } + + parent = dget(parent); + down(&parent->d_inode->i_sem); + d = lookup_one_len(name, parent, strlen(name)); + if (IS_ERR(d)) { + d = NULL; + goto release_mount; + } + + if (d->d_inode) { + d = NULL; + goto release_mount; + } + + inode = relayfs_get_inode(parent->d_inode->i_sb, mode, chan); + if (!inode) { + d = NULL; + goto release_mount; + } + + d_instantiate(d, inode); + dget(d); /* Extra count - pin the dentry in core */ + + if (S_ISDIR(mode)) + parent->d_inode->i_nlink++; + + goto exit; + +release_mount: + simple_release_fs(&relayfs_mount, &relayfs_mount_count); + +exit: + up(&parent->d_inode->i_sem); + dput(parent); + return d; +} + +/** + * relayfs_create_file - create a file in the relay filesystem + * @name: the name of the file to create + * @parent: parent directory + * @mode: mode, if not specied the default perms are used + * @chan: channel associated with the file + * + * Returns file dentry if successful, NULL otherwise. + * + * The file will be created user r on behalf of current user. + */ +struct dentry *relayfs_create_file(const char *name, struct dentry *parent, + int mode, struct rchan *chan) +{ + if (!mode) + mode = S_IRUSR; + mode = (mode & S_IALLUGO) | S_IFREG; + + return relayfs_create_entry(name, parent, mode, chan); +} + +/** + * relayfs_create_dir - create a directory in the relay filesystem + * @name: the name of the directory to create + * @parent: parent directory, NULL if parent should be fs root + * + * Returns directory dentry if successful, NULL otherwise. + * + * The directory will be created world rwx on behalf of current user. + */ +struct dentry *relayfs_create_dir(const char *name, struct dentry *parent) +{ + int mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + return relayfs_create_entry(name, parent, mode, NULL); +} + +/** + * relayfs_remove - remove a file or directory in the relay filesystem + * @dentry: file or directory dentry + * + * Returns 0 if successful, negative otherwise. + */ +int relayfs_remove(struct dentry *dentry) +{ + struct dentry *parent; + int error = 0; + + if (!dentry) + return -EINVAL; + parent = dentry->d_parent; + if (!parent) + return -EINVAL; + + parent = dget(parent); + down(&parent->d_inode->i_sem); + if (dentry->d_inode) { + if (S_ISDIR(dentry->d_inode->i_mode)) + error = simple_rmdir(parent->d_inode, dentry); + else + error = simple_unlink(parent->d_inode, dentry); + if (!error) + d_delete(dentry); + } + if (!error) + dput(dentry); + up(&parent->d_inode->i_sem); + dput(parent); + + if (!error) + simple_release_fs(&relayfs_mount, &relayfs_mount_count); + + return error; +} + +/** + * relayfs_remove_dir - remove a directory in the relay filesystem + * @dentry: directory dentry + * + * Returns 0 if successful, negative otherwise. + */ +int relayfs_remove_dir(struct dentry *dentry) +{ + return relayfs_remove(dentry); +} + +/** + * relayfs_open - open file op for relayfs files + * @inode: the inode + * @filp: the file + * + * Increments the channel buffer refcount. + */ +static int relayfs_open(struct inode *inode, struct file *filp) +{ + struct rchan_buf *buf = RELAYFS_I(inode)->buf; + kref_get(&buf->kref); + + return 0; +} + +/** + * relayfs_mmap - mmap file op for relayfs files + * @filp: the file + * @vma: the vma describing what to map + * + * Calls upon relay_mmap_buf to map the file into user space. + */ +static int relayfs_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct inode *inode = filp->f_dentry->d_inode; + return relay_mmap_buf(RELAYFS_I(inode)->buf, vma); +} + +/** + * relayfs_poll - poll file op for relayfs files + * @filp: the file + * @wait: poll table + * + * Poll implemention. + */ +static unsigned int relayfs_poll(struct file *filp, poll_table *wait) +{ + unsigned int mask = 0; + struct inode *inode = filp->f_dentry->d_inode; + struct rchan_buf *buf = RELAYFS_I(inode)->buf; + + if (buf->finalized) + return POLLERR; + + if (filp->f_mode & FMODE_READ) { + poll_wait(filp, &buf->read_wait, wait); + if (!relay_buf_empty(buf)) + mask |= POLLIN | POLLRDNORM; + } + + return mask; +} + +/** + * relayfs_release - release file op for relayfs files + * @inode: the inode + * @filp: the file + * + * Decrements the channel refcount, as the filesystem is + * no longer using it. + */ +static int relayfs_release(struct inode *inode, struct file *filp) +{ + struct rchan_buf *buf = RELAYFS_I(inode)->buf; + kref_put(&buf->kref, relay_remove_buf); + + return 0; +} + +/** + * relayfs_read_consume - update the consumed count for the buffer + */ +static void relayfs_read_consume(struct rchan_buf *buf, + size_t read_pos, + size_t bytes_consumed) +{ + size_t subbuf_size = buf->chan->subbuf_size; + size_t n_subbufs = buf->chan->n_subbufs; + size_t read_subbuf; + + if (buf->bytes_consumed + bytes_consumed > subbuf_size) { + relay_subbufs_consumed(buf->chan, buf->cpu, 1); + buf->bytes_consumed = 0; + } + + buf->bytes_consumed += bytes_consumed; + read_subbuf = read_pos / buf->chan->subbuf_size; + if (buf->bytes_consumed + buf->padding[read_subbuf] == subbuf_size) { + if ((read_subbuf == buf->subbufs_produced % n_subbufs) && + (buf->offset == subbuf_size)) + return; + relay_subbufs_consumed(buf->chan, buf->cpu, 1); + buf->bytes_consumed = 0; + } +} + +/** + * relayfs_read_avail - boolean, are there unconsumed bytes available? + */ +static int relayfs_read_avail(struct rchan_buf *buf, size_t read_pos) +{ + size_t bytes_produced, bytes_consumed, write_offset; + size_t subbuf_size = buf->chan->subbuf_size; + size_t n_subbufs = buf->chan->n_subbufs; + size_t produced = buf->subbufs_produced % n_subbufs; + size_t consumed = buf->subbufs_consumed % n_subbufs; + + write_offset = buf->offset > subbuf_size ? subbuf_size : buf->offset; + + if (consumed > produced) { + if ((produced > n_subbufs) && + (produced + n_subbufs - consumed <= n_subbufs)) + produced += n_subbufs; + } else if (consumed == produced) { + if (buf->offset > subbuf_size) { + produced += n_subbufs; + if (buf->subbufs_produced == buf->subbufs_consumed) + consumed += n_subbufs; + } + } + + if (buf->offset > subbuf_size) + bytes_produced = (produced - 1) * subbuf_size + write_offset; + else + bytes_produced = produced * subbuf_size + write_offset; + bytes_consumed = consumed * subbuf_size + buf->bytes_consumed; + + if (bytes_produced == bytes_consumed) + return 0; + + relayfs_read_consume(buf, read_pos, 0); + + return 1; +} + +/** + * relayfs_read_subbuf_avail - return bytes available in sub-buffer + */ +static size_t relayfs_read_subbuf_avail(size_t read_pos, + struct rchan_buf *buf) +{ + size_t padding, avail = 0; + size_t read_subbuf, read_offset, write_subbuf, write_offset; + size_t subbuf_size = buf->chan->subbuf_size; + + write_subbuf = (buf->data - buf->start) / subbuf_size; + write_offset = buf->offset > subbuf_size ? subbuf_size : buf->offset; + read_subbuf = read_pos / subbuf_size; + read_offset = read_pos % subbuf_size; + padding = buf->padding[read_subbuf]; + + if (read_subbuf == write_subbuf) { + if (read_offset + padding < write_offset) + avail = write_offset - (read_offset + padding); + } else + avail = (subbuf_size - padding) - read_offset; + + return avail; +} + +/** + * relayfs_read_start_pos - find the first available byte to read + * + * If the read_pos is in the middle of padding, return the + * position of the first actually available byte, otherwise + * return the original value. + */ +static size_t relayfs_read_start_pos(size_t read_pos, + struct rchan_buf *buf) +{ + size_t read_subbuf, padding, padding_start, padding_end; + size_t subbuf_size = buf->chan->subbuf_size; + size_t n_subbufs = buf->chan->n_subbufs; + + read_subbuf = read_pos / subbuf_size; + padding = buf->padding[read_subbuf]; + padding_start = (read_subbuf + 1) * subbuf_size - padding; + padding_end = (read_subbuf + 1) * subbuf_size; + if (read_pos >= padding_start && read_pos < padding_end) { + read_subbuf = (read_subbuf + 1) % n_subbufs; + read_pos = read_subbuf * subbuf_size; + } + + return read_pos; +} + +/** + * relayfs_read_end_pos - return the new read position + */ +static size_t relayfs_read_end_pos(struct rchan_buf *buf, + size_t read_pos, + size_t count) +{ + size_t read_subbuf, padding, end_pos; + size_t subbuf_size = buf->chan->subbuf_size; + size_t n_subbufs = buf->chan->n_subbufs; + + read_subbuf = read_pos / subbuf_size; + padding = buf->padding[read_subbuf]; + if (read_pos % subbuf_size + count + padding == subbuf_size) + end_pos = (read_subbuf + 1) * subbuf_size; + else + end_pos = read_pos + count; + if (end_pos >= subbuf_size * n_subbufs) + end_pos = 0; + + return end_pos; +} + +/** + * relayfs_read - read file op for relayfs files + * @filp: the file + * @buffer: the userspace buffer + * @count: number of bytes to read + * @ppos: position to read from + * + * Reads count bytes or the number of bytes available in the + * current sub-buffer being read, whichever is smaller. + */ +static ssize_t relayfs_read(struct file *filp, + char __user *buffer, + size_t count, + loff_t *ppos) +{ + struct inode *inode = filp->f_dentry->d_inode; + struct rchan_buf *buf = RELAYFS_I(inode)->buf; + size_t read_start, avail; + ssize_t ret = 0; + void *from; + + down(&inode->i_sem); + if(!relayfs_read_avail(buf, *ppos)) + goto out; + + read_start = relayfs_read_start_pos(*ppos, buf); + avail = relayfs_read_subbuf_avail(read_start, buf); + if (!avail) + goto out; + + from = buf->start + read_start; + ret = count = min(count, avail); + if (copy_to_user(buffer, from, count)) { + ret = -EFAULT; + goto out; + } + relayfs_read_consume(buf, read_start, count); + *ppos = relayfs_read_end_pos(buf, read_start, count); +out: + up(&inode->i_sem); + return ret; +} + +/** + * relayfs alloc_inode() implementation + */ +static struct inode *relayfs_alloc_inode(struct super_block *sb) +{ + struct relayfs_inode_info *p = kmem_cache_alloc(relayfs_inode_cachep, SLAB_KERNEL); + if (!p) + return NULL; + p->buf = NULL; + + return &p->vfs_inode; +} + +/** + * relayfs destroy_inode() implementation + */ +static void relayfs_destroy_inode(struct inode *inode) +{ + if (RELAYFS_I(inode)->buf) + relay_destroy_buf(RELAYFS_I(inode)->buf); + + kmem_cache_free(relayfs_inode_cachep, RELAYFS_I(inode)); +} + +static void init_once(void *p, kmem_cache_t *cachep, unsigned long flags) +{ + struct relayfs_inode_info *i = p; + if ((flags & (SLAB_CTOR_VERIFY | SLAB_CTOR_CONSTRUCTOR)) == SLAB_CTOR_CONSTRUCTOR) + inode_init_once(&i->vfs_inode); +} + +struct file_operations relayfs_file_operations = { + .open = relayfs_open, + .poll = relayfs_poll, + .mmap = relayfs_mmap, + .read = relayfs_read, + .llseek = no_llseek, + .release = relayfs_release, +}; + +static struct super_operations relayfs_ops = { + .statfs = simple_statfs, + .drop_inode = generic_delete_inode, + .alloc_inode = relayfs_alloc_inode, + .destroy_inode = relayfs_destroy_inode, +}; + +static int relayfs_fill_super(struct super_block * sb, void * data, int silent) +{ + struct inode *inode; + struct dentry *root; + int mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; + + sb->s_blocksize = PAGE_CACHE_SIZE; + sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_magic = RELAYFS_MAGIC; + sb->s_op = &relayfs_ops; + inode = relayfs_get_inode(sb, mode, NULL); + + if (!inode) + return -ENOMEM; + + root = d_alloc_root(inode); + if (!root) { + iput(inode); + return -ENOMEM; + } + sb->s_root = root; + + return 0; +} + +static struct super_block * relayfs_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data) +{ + return get_sb_single(fs_type, flags, data, relayfs_fill_super); +} + +static struct file_system_type relayfs_fs_type = { + .owner = THIS_MODULE, + .name = "relayfs", + .get_sb = relayfs_get_sb, + .kill_sb = kill_litter_super, +}; + +static int __init init_relayfs_fs(void) +{ + int err; + + relayfs_inode_cachep = kmem_cache_create("relayfs_inode_cache", + sizeof(struct relayfs_inode_info), 0, + 0, init_once, NULL); + if (!relayfs_inode_cachep) + return -ENOMEM; + + err = register_filesystem(&relayfs_fs_type); + if (err) + kmem_cache_destroy(relayfs_inode_cachep); + + return err; +} + +static void __exit exit_relayfs_fs(void) +{ + unregister_filesystem(&relayfs_fs_type); + kmem_cache_destroy(relayfs_inode_cachep); +} + +module_init(init_relayfs_fs) +module_exit(exit_relayfs_fs) + +EXPORT_SYMBOL_GPL(relayfs_file_operations); +EXPORT_SYMBOL_GPL(relayfs_create_dir); +EXPORT_SYMBOL_GPL(relayfs_remove_dir); + +MODULE_AUTHOR("Tom Zanussi <zanussi@us.ibm.com> and Karim Yaghmour <karim@opersys.com>"); +MODULE_DESCRIPTION("Relay Filesystem"); +MODULE_LICENSE("GPL"); + diff --git a/fs/relayfs/relay.c b/fs/relayfs/relay.c new file mode 100644 index 00000000000000..16446a15c96d95 --- /dev/null +++ b/fs/relayfs/relay.c @@ -0,0 +1,431 @@ +/* + * Public API and common code for RelayFS. + * + * See Documentation/filesystems/relayfs.txt for an overview of relayfs. + * + * Copyright (C) 2002-2005 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp + * Copyright (C) 1999-2005 - Karim Yaghmour (karim@opersys.com) + * + * This file is released under the GPL. + */ + +#include <linux/errno.h> +#include <linux/stddef.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/string.h> +#include <linux/relayfs_fs.h> +#include "relay.h" +#include "buffers.h" + +/** + * relay_buf_empty - boolean, is the channel buffer empty? + * @buf: channel buffer + * + * Returns 1 if the buffer is empty, 0 otherwise. + */ +int relay_buf_empty(struct rchan_buf *buf) +{ + return (buf->subbufs_produced - buf->subbufs_consumed) ? 0 : 1; +} + +/** + * relay_buf_full - boolean, is the channel buffer full? + * @buf: channel buffer + * + * Returns 1 if the buffer is full, 0 otherwise. + */ +int relay_buf_full(struct rchan_buf *buf) +{ + size_t ready = buf->subbufs_produced - buf->subbufs_consumed; + return (ready >= buf->chan->n_subbufs) ? 1 : 0; +} + +/* + * High-level relayfs kernel API and associated functions. + */ + +/* + * rchan_callback implementations defining default channel behavior. Used + * in place of corresponding NULL values in client callback struct. + */ + +/* + * subbuf_start() default callback. Does nothing. + */ +static int subbuf_start_default_callback (struct rchan_buf *buf, + void *subbuf, + void *prev_subbuf, + size_t prev_padding) +{ + if (relay_buf_full(buf)) + return 0; + + return 1; +} + +/* + * buf_mapped() default callback. Does nothing. + */ +static void buf_mapped_default_callback(struct rchan_buf *buf, + struct file *filp) +{ +} + +/* + * buf_unmapped() default callback. Does nothing. + */ +static void buf_unmapped_default_callback(struct rchan_buf *buf, + struct file *filp) +{ +} + +/* relay channel default callbacks */ +static struct rchan_callbacks default_channel_callbacks = { + .subbuf_start = subbuf_start_default_callback, + .buf_mapped = buf_mapped_default_callback, + .buf_unmapped = buf_unmapped_default_callback, +}; + +/** + * wakeup_readers - wake up readers waiting on a channel + * @private: the channel buffer + * + * This is the work function used to defer reader waking. The + * reason waking is deferred is that calling directly from write + * causes problems if you're writing from say the scheduler. + */ +static void wakeup_readers(void *private) +{ + struct rchan_buf *buf = private; + wake_up_interruptible(&buf->read_wait); +} + +/** + * __relay_reset - reset a channel buffer + * @buf: the channel buffer + * @init: 1 if this is a first-time initialization + * + * See relay_reset for description of effect. + */ +static inline void __relay_reset(struct rchan_buf *buf, unsigned int init) +{ + size_t i; + + if (init) { + init_waitqueue_head(&buf->read_wait); + kref_init(&buf->kref); + INIT_WORK(&buf->wake_readers, NULL, NULL); + } else { + cancel_delayed_work(&buf->wake_readers); + flush_scheduled_work(); + } + + buf->subbufs_produced = 0; + buf->subbufs_consumed = 0; + buf->bytes_consumed = 0; + buf->finalized = 0; + buf->data = buf->start; + buf->offset = 0; + + for (i = 0; i < buf->chan->n_subbufs; i++) + buf->padding[i] = 0; + + buf->chan->cb->subbuf_start(buf, buf->data, NULL, 0); +} + +/** + * relay_reset - reset the channel + * @chan: the channel + * + * This has the effect of erasing all data from all channel buffers + * and restarting the channel in its initial state. The buffers + * are not freed, so any mappings are still in effect. + * + * NOTE: Care should be taken that the channel isn't actually + * being used by anything when this call is made. + */ +void relay_reset(struct rchan *chan) +{ + unsigned int i; + + if (!chan) + return; + + for (i = 0; i < NR_CPUS; i++) { + if (!chan->buf[i]) + continue; + __relay_reset(chan->buf[i], 0); + } +} + +/** + * relay_open_buf - create a new channel buffer in relayfs + * + * Internal - used by relay_open(). + */ +static struct rchan_buf *relay_open_buf(struct rchan *chan, + const char *filename, + struct dentry *parent) +{ + struct rchan_buf *buf; + struct dentry *dentry; + + /* Create file in fs */ + dentry = relayfs_create_file(filename, parent, S_IRUSR, chan); + if (!dentry) + return NULL; + + buf = RELAYFS_I(dentry->d_inode)->buf; + buf->dentry = dentry; + __relay_reset(buf, 1); + + return buf; +} + +/** + * relay_close_buf - close a channel buffer + * @buf: channel buffer + * + * Marks the buffer finalized and restores the default callbacks. + * The channel buffer and channel buffer data structure are then freed + * automatically when the last reference is given up. + */ +static inline void relay_close_buf(struct rchan_buf *buf) +{ + buf->finalized = 1; + buf->chan->cb = &default_channel_callbacks; + cancel_delayed_work(&buf->wake_readers); + flush_scheduled_work(); + kref_put(&buf->kref, relay_remove_buf); +} + +static inline void setup_callbacks(struct rchan *chan, + struct rchan_callbacks *cb) +{ + if (!cb) { + chan->cb = &default_channel_callbacks; + return; + } + + if (!cb->subbuf_start) + cb->subbuf_start = subbuf_start_default_callback; + if (!cb->buf_mapped) + cb->buf_mapped = buf_mapped_default_callback; + if (!cb->buf_unmapped) + cb->buf_unmapped = buf_unmapped_default_callback; + chan->cb = cb; +} + +/** + * relay_open - create a new relayfs channel + * @base_filename: base name of files to create + * @parent: dentry of parent directory, NULL for root directory + * @subbuf_size: size of sub-buffers + * @n_subbufs: number of sub-buffers + * @cb: client callback functions + * + * Returns channel pointer if successful, NULL otherwise. + * + * Creates a channel buffer for each cpu using the sizes and + * attributes specified. The created channel buffer files + * will be named base_filename0...base_filenameN-1. File + * permissions will be S_IRUSR. + */ +struct rchan *relay_open(const char *base_filename, + struct dentry *parent, + size_t subbuf_size, + size_t n_subbufs, + struct rchan_callbacks *cb) +{ + unsigned int i; + struct rchan *chan; + char *tmpname; + + if (!base_filename) + return NULL; + + if (!(subbuf_size && n_subbufs)) + return NULL; + + chan = kcalloc(1, sizeof(struct rchan), GFP_KERNEL); + if (!chan) + return NULL; + + chan->version = RELAYFS_CHANNEL_VERSION; + chan->n_subbufs = n_subbufs; + chan->subbuf_size = subbuf_size; + chan->alloc_size = FIX_SIZE(subbuf_size * n_subbufs); + setup_callbacks(chan, cb); + kref_init(&chan->kref); + + tmpname = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!tmpname) + goto free_chan; + + for_each_online_cpu(i) { + sprintf(tmpname, "%s%d", base_filename, i); + chan->buf[i] = relay_open_buf(chan, tmpname, parent); + chan->buf[i]->cpu = i; + if (!chan->buf[i]) + goto free_bufs; + } + + kfree(tmpname); + return chan; + +free_bufs: + for (i = 0; i < NR_CPUS; i++) { + if (!chan->buf[i]) + break; + relay_close_buf(chan->buf[i]); + } + kfree(tmpname); + +free_chan: + kref_put(&chan->kref, relay_destroy_channel); + return NULL; +} + +/** + * relay_switch_subbuf - switch to a new sub-buffer + * @buf: channel buffer + * @length: size of current event + * + * Returns either the length passed in or 0 if full. + + * Performs sub-buffer-switch tasks such as invoking callbacks, + * updating padding counts, waking up readers, etc. + */ +size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) +{ + void *old, *new; + size_t old_subbuf, new_subbuf; + + if (unlikely(length > buf->chan->subbuf_size)) + goto toobig; + + if (buf->offset != buf->chan->subbuf_size + 1) { + buf->prev_padding = buf->chan->subbuf_size - buf->offset; + old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; + buf->padding[old_subbuf] = buf->prev_padding; + buf->subbufs_produced++; + if (waitqueue_active(&buf->read_wait)) { + PREPARE_WORK(&buf->wake_readers, wakeup_readers, buf); + schedule_delayed_work(&buf->wake_readers, 1); + } + } + + old = buf->data; + new_subbuf = buf->subbufs_produced % buf->chan->n_subbufs; + new = buf->start + new_subbuf * buf->chan->subbuf_size; + buf->offset = 0; + if (!buf->chan->cb->subbuf_start(buf, new, old, buf->prev_padding)) { + buf->offset = buf->chan->subbuf_size + 1; + return 0; + } + buf->data = new; + buf->padding[new_subbuf] = 0; + + if (unlikely(length + buf->offset > buf->chan->subbuf_size)) + goto toobig; + + return length; + +toobig: + printk(KERN_WARNING "relayfs: event too large (%Zd)\n", length); + WARN_ON(1); + return 0; +} + +/** + * relay_subbufs_consumed - update the buffer's sub-buffers-consumed count + * @chan: the channel + * @cpu: the cpu associated with the channel buffer to update + * @subbufs_consumed: number of sub-buffers to add to current buf's count + * + * Adds to the channel buffer's consumed sub-buffer count. + * subbufs_consumed should be the number of sub-buffers newly consumed, + * not the total consumed. + * + * NOTE: kernel clients don't need to call this function if the channel + * mode is 'overwrite'. + */ +void relay_subbufs_consumed(struct rchan *chan, + unsigned int cpu, + size_t subbufs_consumed) +{ + struct rchan_buf *buf; + + if (!chan) + return; + + if (cpu >= NR_CPUS || !chan->buf[cpu]) + return; + + buf = chan->buf[cpu]; + buf->subbufs_consumed += subbufs_consumed; + if (buf->subbufs_consumed > buf->subbufs_produced) + buf->subbufs_consumed = buf->subbufs_produced; +} + +/** + * relay_destroy_channel - free the channel struct + * + * Should only be called from kref_put(). + */ +void relay_destroy_channel(struct kref *kref) +{ + struct rchan *chan = container_of(kref, struct rchan, kref); + kfree(chan); +} + +/** + * relay_close - close the channel + * @chan: the channel + * + * Closes all channel buffers and frees the channel. + */ +void relay_close(struct rchan *chan) +{ + unsigned int i; + + if (!chan) + return; + + for (i = 0; i < NR_CPUS; i++) { + if (!chan->buf[i]) + continue; + relay_close_buf(chan->buf[i]); + } + + kref_put(&chan->kref, relay_destroy_channel); +} + +/** + * relay_flush - close the channel + * @chan: the channel + * + * Flushes all channel buffers i.e. forces buffer switch. + */ +void relay_flush(struct rchan *chan) +{ + unsigned int i; + + if (!chan) + return; + + for (i = 0; i < NR_CPUS; i++) { + if (!chan->buf[i]) + continue; + relay_switch_subbuf(chan->buf[i], 0); + } +} + +EXPORT_SYMBOL_GPL(relay_open); +EXPORT_SYMBOL_GPL(relay_close); +EXPORT_SYMBOL_GPL(relay_flush); +EXPORT_SYMBOL_GPL(relay_reset); +EXPORT_SYMBOL_GPL(relay_subbufs_consumed); +EXPORT_SYMBOL_GPL(relay_switch_subbuf); +EXPORT_SYMBOL_GPL(relay_buf_full); diff --git a/fs/relayfs/relay.h b/fs/relayfs/relay.h new file mode 100644 index 00000000000000..703503fa22b6f3 --- /dev/null +++ b/fs/relayfs/relay.h @@ -0,0 +1,12 @@ +#ifndef _RELAY_H +#define _RELAY_H + +struct dentry *relayfs_create_file(const char *name, + struct dentry *parent, + int mode, + struct rchan *chan); +extern int relayfs_remove(struct dentry *dentry); +extern int relay_buf_empty(struct rchan_buf *buf); +extern void relay_destroy_channel(struct kref *kref); + +#endif /* _RELAY_H */ diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index 997640c99c7d88..faf1512173eb23 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -114,8 +114,7 @@ void ufs_free_fragments (struct inode * inode, unsigned fragment, unsigned count ubh_mark_buffer_dirty (USPI_UBH); ubh_mark_buffer_dirty (UCPI_UBH); if (sb->s_flags & MS_SYNCHRONOUS) { - ubh_wait_on_buffer (UCPI_UBH); - ubh_ll_rw_block (WRITE, 1, (struct ufs_buffer_head **)&ucpi); + ubh_ll_rw_block (SWRITE, 1, (struct ufs_buffer_head **)&ucpi); ubh_wait_on_buffer (UCPI_UBH); } sb->s_dirt = 1; @@ -200,8 +199,7 @@ do_more: ubh_mark_buffer_dirty (USPI_UBH); ubh_mark_buffer_dirty (UCPI_UBH); if (sb->s_flags & MS_SYNCHRONOUS) { - ubh_wait_on_buffer (UCPI_UBH); - ubh_ll_rw_block (WRITE, 1, (struct ufs_buffer_head **)&ucpi); + ubh_ll_rw_block (SWRITE, 1, (struct ufs_buffer_head **)&ucpi); ubh_wait_on_buffer (UCPI_UBH); } @@ -459,8 +457,7 @@ ufs_add_fragments (struct inode * inode, unsigned fragment, ubh_mark_buffer_dirty (USPI_UBH); ubh_mark_buffer_dirty (UCPI_UBH); if (sb->s_flags & MS_SYNCHRONOUS) { - ubh_wait_on_buffer (UCPI_UBH); - ubh_ll_rw_block (WRITE, 1, (struct ufs_buffer_head **)&ucpi); + ubh_ll_rw_block (SWRITE, 1, (struct ufs_buffer_head **)&ucpi); ubh_wait_on_buffer (UCPI_UBH); } sb->s_dirt = 1; @@ -585,8 +582,7 @@ succed: ubh_mark_buffer_dirty (USPI_UBH); ubh_mark_buffer_dirty (UCPI_UBH); if (sb->s_flags & MS_SYNCHRONOUS) { - ubh_wait_on_buffer (UCPI_UBH); - ubh_ll_rw_block (WRITE, 1, (struct ufs_buffer_head **)&ucpi); + ubh_ll_rw_block (SWRITE, 1, (struct ufs_buffer_head **)&ucpi); ubh_wait_on_buffer (UCPI_UBH); } sb->s_dirt = 1; diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 61a6b1542fc5f0..0938945b9cbc2c 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -124,8 +124,7 @@ void ufs_free_inode (struct inode * inode) ubh_mark_buffer_dirty (USPI_UBH); ubh_mark_buffer_dirty (UCPI_UBH); if (sb->s_flags & MS_SYNCHRONOUS) { - ubh_wait_on_buffer (UCPI_UBH); - ubh_ll_rw_block (WRITE, 1, (struct ufs_buffer_head **) &ucpi); + ubh_ll_rw_block (SWRITE, 1, (struct ufs_buffer_head **) &ucpi); ubh_wait_on_buffer (UCPI_UBH); } @@ -249,8 +248,7 @@ cg_found: ubh_mark_buffer_dirty (USPI_UBH); ubh_mark_buffer_dirty (UCPI_UBH); if (sb->s_flags & MS_SYNCHRONOUS) { - ubh_wait_on_buffer (UCPI_UBH); - ubh_ll_rw_block (WRITE, 1, (struct ufs_buffer_head **) &ucpi); + ubh_ll_rw_block (SWRITE, 1, (struct ufs_buffer_head **) &ucpi); ubh_wait_on_buffer (UCPI_UBH); } sb->s_dirt = 1; diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index e312bf8bad9fd5..61d2e35012a462 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -285,8 +285,7 @@ next:; } } if (IS_SYNC(inode) && ind_ubh && ubh_buffer_dirty(ind_ubh)) { - ubh_wait_on_buffer (ind_ubh); - ubh_ll_rw_block (WRITE, 1, &ind_ubh); + ubh_ll_rw_block (SWRITE, 1, &ind_ubh); ubh_wait_on_buffer (ind_ubh); } ubh_brelse (ind_ubh); @@ -353,8 +352,7 @@ static int ufs_trunc_dindirect (struct inode *inode, unsigned offset, __fs32 *p) } } if (IS_SYNC(inode) && dind_bh && ubh_buffer_dirty(dind_bh)) { - ubh_wait_on_buffer (dind_bh); - ubh_ll_rw_block (WRITE, 1, &dind_bh); + ubh_ll_rw_block (SWRITE, 1, &dind_bh); ubh_wait_on_buffer (dind_bh); } ubh_brelse (dind_bh); @@ -418,8 +416,7 @@ static int ufs_trunc_tindirect (struct inode * inode) } } if (IS_SYNC(inode) && tind_bh && ubh_buffer_dirty(tind_bh)) { - ubh_wait_on_buffer (tind_bh); - ubh_ll_rw_block (WRITE, 1, &tind_bh); + ubh_ll_rw_block (SWRITE, 1, &tind_bh); ubh_wait_on_buffer (tind_bh); } ubh_brelse (tind_bh); diff --git a/fs/umsdos/notes b/fs/umsdos/notes deleted file mode 100644 index 3c47d1f4fc4732..00000000000000 --- a/fs/umsdos/notes +++ /dev/null @@ -1,17 +0,0 @@ -This file contain idea and things I don't want to forget - -Possible bug in fs/read_write.c -Function sys_readdir() - - There is a call the verify_area that does not take in account - the count parameter. I guess it should read - - error = verify_area(VERIFY_WRITE, dirent, count*sizeof (*dirent)); - - instead of - - error = verify_area(VERIFY_WRITE, dirent, sizeof (*dirent)); - - Of course, now , count is always 1 - - diff --git a/fs/xattr.c b/fs/xattr.c index 6acd5c63da9113..3f9c64bea151fd 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -51,20 +51,29 @@ setxattr(struct dentry *d, char __user *name, void __user *value, } } + down(&d->d_inode->i_sem); + error = security_inode_setxattr(d, kname, kvalue, size, flags); + if (error) + goto out; error = -EOPNOTSUPP; if (d->d_inode->i_op && d->d_inode->i_op->setxattr) { - down(&d->d_inode->i_sem); - error = security_inode_setxattr(d, kname, kvalue, size, flags); - if (error) - goto out; - error = d->d_inode->i_op->setxattr(d, kname, kvalue, size, flags); + error = d->d_inode->i_op->setxattr(d, kname, kvalue, + size, flags); if (!error) { fsnotify_xattr(d); - security_inode_post_setxattr(d, kname, kvalue, size, flags); + security_inode_post_setxattr(d, kname, kvalue, + size, flags); } -out: - up(&d->d_inode->i_sem); + } else if (!strncmp(kname, XATTR_SECURITY_PREFIX, + sizeof XATTR_SECURITY_PREFIX - 1)) { + const char *suffix = kname + sizeof XATTR_SECURITY_PREFIX - 1; + error = security_inode_setsecurity(d->d_inode, suffix, kvalue, + size, flags); + if (!error) + fsnotify_xattr(d); } +out: + up(&d->d_inode->i_sem); if (kvalue) kfree(kvalue); return error; @@ -139,20 +148,25 @@ getxattr(struct dentry *d, char __user *name, void __user *value, size_t size) return -ENOMEM; } + error = security_inode_getxattr(d, kname); + if (error) + goto out; error = -EOPNOTSUPP; - if (d->d_inode->i_op && d->d_inode->i_op->getxattr) { - error = security_inode_getxattr(d, kname); - if (error) - goto out; + if (d->d_inode->i_op && d->d_inode->i_op->getxattr) error = d->d_inode->i_op->getxattr(d, kname, kvalue, size); - if (error > 0) { - if (size && copy_to_user(value, kvalue, error)) - error = -EFAULT; - } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { - /* The file system tried to returned a value bigger - than XATTR_SIZE_MAX bytes. Not possible. */ - error = -E2BIG; - } + else if (!strncmp(kname, XATTR_SECURITY_PREFIX, + sizeof XATTR_SECURITY_PREFIX - 1)) { + const char *suffix = kname + sizeof XATTR_SECURITY_PREFIX - 1; + error = security_inode_getsecurity(d->d_inode, suffix, kvalue, + size); + } + if (error > 0) { + if (size && copy_to_user(value, kvalue, error)) + error = -EFAULT; + } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { + /* The file system tried to returned a value bigger + than XATTR_SIZE_MAX bytes. Not possible. */ + error = -E2BIG; } out: if (kvalue) @@ -221,20 +235,24 @@ listxattr(struct dentry *d, char __user *list, size_t size) return -ENOMEM; } + error = security_inode_listxattr(d); + if (error) + goto out; error = -EOPNOTSUPP; if (d->d_inode->i_op && d->d_inode->i_op->listxattr) { - error = security_inode_listxattr(d); - if (error) - goto out; error = d->d_inode->i_op->listxattr(d, klist, size); - if (error > 0) { - if (size && copy_to_user(list, klist, error)) - error = -EFAULT; - } else if (error == -ERANGE && size >= XATTR_LIST_MAX) { - /* The file system tried to returned a list bigger - than XATTR_LIST_MAX bytes. Not possible. */ - error = -E2BIG; - } + } else { + error = security_inode_listsecurity(d->d_inode, klist, size); + if (size && error >= size) + error = -ERANGE; + } + if (error > 0) { + if (size && copy_to_user(list, klist, error)) + error = -EFAULT; + } else if (error == -ERANGE && size >= XATTR_LIST_MAX) { + /* The file system tried to returned a list bigger + than XATTR_LIST_MAX bytes. Not possible. */ + error = -E2BIG; } out: if (klist) @@ -307,6 +325,8 @@ removexattr(struct dentry *d, char __user *name) down(&d->d_inode->i_sem); error = d->d_inode->i_op->removexattr(d, kname); up(&d->d_inode->i_sem); + if (!error) + fsnotify_xattr(d); } out: return error; |