diff options
Diffstat (limited to 'fs')
53 files changed, 655 insertions, 223 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index bc57ae9e2963..cce9ace651a2 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -35,8 +35,9 @@ * @page: structure to page * */ -static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) +static int v9fs_fid_readpage(void *data, struct page *page) { + struct p9_fid *fid = data; struct inode *inode = page->mapping->host; struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE}; struct iov_iter to; @@ -107,7 +108,8 @@ static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) return ret; - ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp); + ret = read_cache_pages(mapping, pages, v9fs_fid_readpage, + filp->private_data); p9_debug(P9_DEBUG_VFS, " = %d\n", ret); return ret; } @@ -425,7 +425,7 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, BUG_ON(PageWriteback(old)); get_page(new); - rc = migrate_page_move_mapping(mapping, new, old, mode, 1); + rc = migrate_page_move_mapping(mapping, new, old, 1); if (rc != MIGRATEPAGE_SUCCESS) { put_page(new); goto out_unlock; @@ -2096,6 +2096,7 @@ SYSCALL_DEFINE6(io_pgetevents, struct __aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 ts; + bool interrupted; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) @@ -2109,8 +2110,10 @@ SYSCALL_DEFINE6(io_pgetevents, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2129,6 +2132,7 @@ SYSCALL_DEFINE6(io_pgetevents_time32, struct __aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 ts; + bool interrupted; int ret; if (timeout && unlikely(get_old_timespec32(&ts, timeout))) @@ -2143,8 +2147,10 @@ SYSCALL_DEFINE6(io_pgetevents_time32, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2194,6 +2200,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, struct __compat_aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 t; + bool interrupted; int ret; if (timeout && get_old_timespec32(&t, timeout)) @@ -2207,8 +2214,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2227,6 +2236,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, struct __compat_aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 t; + bool interrupted; int ret; if (timeout && get_timespec64(&t, timeout)) @@ -2240,8 +2250,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 8264b468f283..d4e11b2e04f6 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1127,7 +1127,6 @@ out_free_interp: load_addr, interp_load_addr); if (retval < 0) goto out; - /* N.B. passed_fileno might not be initialized? */ current->mm->end_code = end_code; current->mm->start_code = start_code; current->mm->start_data = start_data; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 82a48e830018..7562d6aefbe4 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -416,7 +416,6 @@ static int load_flat_file(struct linux_binprm *bprm, u32 text_len, data_len, bss_len, stack_len, full_data, flags; unsigned long len, memp, memp_size, extra, rlim; u32 __user *reloc, *rp; - struct inode *inode; int i, rev, relocs; loff_t fpos; unsigned long start_code, end_code; @@ -424,7 +423,6 @@ static int load_flat_file(struct linux_binprm *bprm, int ret; hdr = ((struct flat_hdr *) bprm->buf); /* exec-header */ - inode = file_inode(bprm->file); text_len = ntohl(hdr->data_start); data_len = ntohl(hdr->data_end) - ntohl(hdr->data_start); @@ -856,9 +854,14 @@ err: static int load_flat_shared_library(int id, struct lib_info *libs) { + /* + * This is a fake bprm struct; only the members "buf", "file" and + * "filename" are actually used. + */ struct linux_binprm bprm; int res; char buf[16]; + loff_t pos = 0; memset(&bprm, 0, sizeof(bprm)); @@ -872,25 +875,11 @@ static int load_flat_shared_library(int id, struct lib_info *libs) if (IS_ERR(bprm.file)) return res; - bprm.cred = prepare_exec_creds(); - res = -ENOMEM; - if (!bprm.cred) - goto out; - - /* We don't really care about recalculating credentials at this point - * as we're past the point of no return and are dealing with shared - * libraries. - */ - bprm.called_set_creds = 1; + res = kernel_read(bprm.file, bprm.buf, BINPRM_BUF_SIZE, &pos); - res = prepare_binprm(&bprm); - - if (!res) + if (res >= 0) res = load_flat_file(&bprm, libs, id, NULL); - abort_creds(bprm.cred); - -out: allow_write_access(bprm.file); fput(bprm.file); diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index 3837ca180d52..6c0044255e69 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -27,15 +27,17 @@ /* 307s to avoid pathologically clashing with transaction commit */ #define ZSTD_BTRFS_RECLAIM_JIFFIES (307 * HZ) -static ZSTD_parameters zstd_get_btrfs_parameters(unsigned int level, +static ZSTD_parameters *zstd_get_btrfs_parameters(unsigned int level, size_t src_len) { - ZSTD_parameters params = ZSTD_getParams(level, src_len, 0); + static ZSTD_parameters params; + + params = ZSTD_getParams(level, src_len, 0); if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG) params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG; WARN_ON(src_len > ZSTD_BTRFS_MAX_INPUT); - return params; + return ¶ms; } struct workspace { @@ -155,11 +157,12 @@ static void zstd_calc_ws_mem_sizes(void) unsigned int level; for (level = 1; level <= ZSTD_BTRFS_MAX_LEVEL; level++) { - ZSTD_parameters params = - zstd_get_btrfs_parameters(level, ZSTD_BTRFS_MAX_INPUT); - size_t level_size = - max_t(size_t, - ZSTD_CStreamWorkspaceBound(params.cParams), + ZSTD_parameters *params; + size_t level_size; + + params = zstd_get_btrfs_parameters(level, ZSTD_BTRFS_MAX_INPUT); + level_size = max_t(size_t, + ZSTD_CStreamWorkspaceBound(params->cParams), ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT)); max_size = max_t(size_t, max_size, level_size); @@ -385,8 +388,9 @@ static int zstd_compress_pages(struct list_head *ws, unsigned long len = *total_out; const unsigned long nr_dest_pages = *out_pages; unsigned long max_out = nr_dest_pages * PAGE_SIZE; - ZSTD_parameters params = zstd_get_btrfs_parameters(workspace->req_level, - len); + ZSTD_parameters *params; + + params = zstd_get_btrfs_parameters(workspace->req_level, len); *out_pages = 0; *total_out = 0; diff --git a/fs/buffer.c b/fs/buffer.c index e450c55f6434..f85b6e12da5d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -956,10 +956,20 @@ grow_dev_page(struct block_device *bdev, sector_t block, end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x01; +#endif goto done; } - if (!try_to_free_buffers(page)) + if (!try_to_free_buffers(page)) { +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x02; +#endif goto failed; + } +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x04; +#endif } /* @@ -979,6 +989,9 @@ grow_dev_page(struct block_device *bdev, sector_t block, spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x08; +#endif failed: unlock_page(page); put_page(page); @@ -1034,6 +1047,12 @@ __getblk_slow(struct block_device *bdev, sector_t block, return NULL; } +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_stamp = jiffies; + current->getblk_executed = 0; + current->getblk_bh_count = 0; + current->getblk_bh_state = 0; +#endif for (;;) { struct buffer_head *bh; int ret; @@ -1045,6 +1064,24 @@ __getblk_slow(struct block_device *bdev, sector_t block, ret = grow_buffers(bdev, block, size, gfp); if (ret < 0) return NULL; + +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + if (!time_after(jiffies, current->getblk_stamp + 3 * HZ)) + continue; + printk(KERN_ERR "%s(%u): getblk(): executed=%x bh_count=%d bh_state=%lx bdev_super_blocksize=%ld size=%u bdev_super_blocksize_bits=%d bdev_inode_blkbits=%d\n", + current->comm, current->pid, current->getblk_executed, + current->getblk_bh_count, current->getblk_bh_state, + IS_ERR_OR_NULL(bdev->bd_super) ? -1L : + bdev->bd_super->s_blocksize, size, + IS_ERR_OR_NULL(bdev->bd_super) ? -1 : + bdev->bd_super->s_blocksize_bits, + IS_ERR_OR_NULL(bdev->bd_inode) ? -1 : + bdev->bd_inode->i_blkbits); + current->getblk_executed = 0; + current->getblk_bh_count = 0; + current->getblk_bh_state = 0; + current->getblk_stamp = jiffies; +#endif } } @@ -3227,6 +3264,11 @@ EXPORT_SYMBOL(sync_dirty_buffer); */ static inline int buffer_busy(struct buffer_head *bh) { +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x80; + current->getblk_bh_count = atomic_read(&bh->b_count); + current->getblk_bh_state = bh->b_state; +#endif return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } @@ -3265,11 +3307,18 @@ int try_to_free_buffers(struct page *page) int ret = 0; BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) + if (PageWriteback(page)) { +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x10; +#endif return 0; + } if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(page, &buffers_to_free); +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x20; +#endif goto out; } @@ -3293,6 +3342,9 @@ int try_to_free_buffers(struct page *page) if (ret) cancel_dirty_page(page); spin_unlock(&mapping->private_lock); +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x40; +#endif out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; diff --git a/fs/coda/Makefile b/fs/coda/Makefile index 1ce66819da2a..78befb8369c9 100644 --- a/fs/coda/Makefile +++ b/fs/coda/Makefile @@ -6,7 +6,8 @@ obj-$(CONFIG_CODA_FS) += coda.o coda-objs := psdev.o cache.o cnode.o inode.o dir.o file.o upcall.o \ - coda_linux.o symlink.o pioctl.o sysctl.o + coda_linux.o symlink.o pioctl.o +coda-$(CONFIG_SYSCTL) += sysctl.o # If you want debugging output, please uncomment the following line. diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 201fc08a8b4f..3b8c4513118f 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -21,7 +21,7 @@ #include <linux/spinlock.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> +#include "coda_psdev.h" #include "coda_linux.h" #include "coda_cache.h" diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c index 845b5a66952a..06855f6c7902 100644 --- a/fs/coda/cnode.c +++ b/fs/coda/cnode.c @@ -8,8 +8,8 @@ #include <linux/time.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> #include <linux/pagemap.h> +#include "coda_psdev.h" #include "coda_linux.h" static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2) @@ -137,11 +137,6 @@ struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb) struct inode *inode; unsigned long hash = coda_f2i(fid); - if ( !sb ) { - pr_warn("%s: no sb!\n", __func__); - return NULL; - } - inode = ilookup5(sb, hash, coda_test_inode, fid); if ( !inode ) return NULL; @@ -153,6 +148,16 @@ struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb) return inode; } +struct coda_file_info *coda_ftoc(struct file *file) +{ + struct coda_file_info *cfi = file->private_data; + + BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); + + return cfi; + +} + /* the CONTROL inode is made without asking attributes from Venus */ struct inode *coda_cnode_makectl(struct super_block *sb) { diff --git a/fs/coda/coda_fs_i.h b/fs/coda/coda_fs_i.h index d702ba1a2bf9..c99d574d1c43 100644 --- a/fs/coda/coda_fs_i.h +++ b/fs/coda/coda_fs_i.h @@ -42,8 +42,6 @@ struct coda_file_info { unsigned int cfi_mapcount; /* nr of times this file is mapped */ }; -#define CODA_FTOC(file) ((struct coda_file_info *)((file)->private_data)) - /* flags */ #define C_VATTR 0x1 /* Validity of vattr in inode */ #define C_FLUSH 0x2 /* used after a flush */ @@ -54,6 +52,7 @@ struct inode *coda_cnode_make(struct CodaFid *, struct super_block *); struct inode *coda_iget(struct super_block *sb, struct CodaFid *fid, struct coda_vattr *attr); struct inode *coda_cnode_makectl(struct super_block *sb); struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb); +struct coda_file_info *coda_ftoc(struct file *file); void coda_replace_fid(struct inode *, struct CodaFid *, struct CodaFid *); #endif diff --git a/fs/coda/coda_int.h b/fs/coda/coda_int.h index bb0b3e0ed6c2..f82b59c9dd28 100644 --- a/fs/coda/coda_int.h +++ b/fs/coda/coda_int.h @@ -13,9 +13,19 @@ extern int coda_fake_statfs; void coda_destroy_inodecache(void); int __init coda_init_inodecache(void); int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync); + +#ifdef CONFIG_SYSCTL void coda_sysctl_init(void); void coda_sysctl_clean(void); +#else +static inline void coda_sysctl_init(void) +{ +} +static inline void coda_sysctl_clean(void) +{ +} +#endif #endif /* _CODA_INT_ */ diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c index f3d543dd9a98..2e1a5a192074 100644 --- a/fs/coda/coda_linux.c +++ b/fs/coda/coda_linux.c @@ -18,7 +18,7 @@ #include <linux/string.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> +#include "coda_psdev.h" #include "coda_linux.h" /* initialize the debugging variables */ @@ -66,6 +66,25 @@ unsigned short coda_flags_to_cflags(unsigned short flags) return coda_flags; } +static struct timespec64 coda_to_timespec64(struct coda_timespec ts) +{ + struct timespec64 ts64 = { + .tv_sec = ts.tv_sec, + .tv_nsec = ts.tv_nsec, + }; + + return ts64; +} + +static struct coda_timespec timespec64_to_coda(struct timespec64 ts64) +{ + struct coda_timespec ts = { + .tv_sec = ts64.tv_sec, + .tv_nsec = ts64.tv_nsec, + }; + + return ts; +} /* utility functions below */ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr) @@ -105,11 +124,11 @@ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr) if (attr->va_size != -1) inode->i_blocks = (attr->va_size + 511) >> 9; if (attr->va_atime.tv_sec != -1) - inode->i_atime = timespec_to_timespec64(attr->va_atime); + inode->i_atime = coda_to_timespec64(attr->va_atime); if (attr->va_mtime.tv_sec != -1) - inode->i_mtime = timespec_to_timespec64(attr->va_mtime); + inode->i_mtime = coda_to_timespec64(attr->va_mtime); if (attr->va_ctime.tv_sec != -1) - inode->i_ctime = timespec_to_timespec64(attr->va_ctime); + inode->i_ctime = coda_to_timespec64(attr->va_ctime); } @@ -130,12 +149,12 @@ void coda_iattr_to_vattr(struct iattr *iattr, struct coda_vattr *vattr) vattr->va_uid = (vuid_t) -1; vattr->va_gid = (vgid_t) -1; vattr->va_size = (off_t) -1; - vattr->va_atime.tv_sec = (time_t) -1; - vattr->va_atime.tv_nsec = (time_t) -1; - vattr->va_mtime.tv_sec = (time_t) -1; - vattr->va_mtime.tv_nsec = (time_t) -1; - vattr->va_ctime.tv_sec = (time_t) -1; - vattr->va_ctime.tv_nsec = (time_t) -1; + vattr->va_atime.tv_sec = (int64_t) -1; + vattr->va_atime.tv_nsec = (long) -1; + vattr->va_mtime.tv_sec = (int64_t) -1; + vattr->va_mtime.tv_nsec = (long) -1; + vattr->va_ctime.tv_sec = (int64_t) -1; + vattr->va_ctime.tv_nsec = (long) -1; vattr->va_type = C_VNON; vattr->va_fileid = -1; vattr->va_gen = -1; @@ -175,13 +194,13 @@ void coda_iattr_to_vattr(struct iattr *iattr, struct coda_vattr *vattr) vattr->va_size = iattr->ia_size; } if ( valid & ATTR_ATIME ) { - vattr->va_atime = timespec64_to_timespec(iattr->ia_atime); + vattr->va_atime = timespec64_to_coda(iattr->ia_atime); } if ( valid & ATTR_MTIME ) { - vattr->va_mtime = timespec64_to_timespec(iattr->ia_mtime); + vattr->va_mtime = timespec64_to_coda(iattr->ia_mtime); } if ( valid & ATTR_CTIME ) { - vattr->va_ctime = timespec64_to_timespec(iattr->ia_ctime); + vattr->va_ctime = timespec64_to_coda(iattr->ia_ctime); } } diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h index 126155cadfa9..d5ebd36fb2cc 100644 --- a/fs/coda/coda_linux.h +++ b/fs/coda/coda_linux.h @@ -59,22 +59,6 @@ void coda_vattr_to_iattr(struct inode *, struct coda_vattr *); void coda_iattr_to_vattr(struct iattr *, struct coda_vattr *); unsigned short coda_flags_to_cflags(unsigned short); -/* sysctl.h */ -void coda_sysctl_init(void); -void coda_sysctl_clean(void); - -#define CODA_ALLOC(ptr, cast, size) do { \ - if (size < PAGE_SIZE) \ - ptr = kzalloc((unsigned long) size, GFP_KERNEL); \ - else \ - ptr = (cast)vzalloc((unsigned long) size); \ - if (!ptr) \ - pr_warn("kernel malloc returns 0 at %s:%d\n", __FILE__, __LINE__); \ -} while (0) - - -#define CODA_FREE(ptr, size) kvfree((ptr)) - /* inode to cnode access functions */ static inline struct coda_inode_info *ITOC(struct inode *inode) diff --git a/fs/coda/coda_psdev.h b/fs/coda/coda_psdev.h new file mode 100644 index 000000000000..801423cbbdfc --- /dev/null +++ b/fs/coda/coda_psdev.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __CODA_PSDEV_H +#define __CODA_PSDEV_H + +#include <linux/backing-dev.h> +#include <linux/magic.h> +#include <linux/mutex.h> + +#define CODA_PSDEV_MAJOR 67 +#define MAX_CODADEVS 5 /* how many do we allow */ + +struct kstatfs; + +/* messages between coda filesystem in kernel and Venus */ +struct upc_req { + struct list_head uc_chain; + caddr_t uc_data; + u_short uc_flags; + u_short uc_inSize; /* Size is at most 5000 bytes */ + u_short uc_outSize; + u_short uc_opcode; /* copied from data to save lookup */ + int uc_unique; + wait_queue_head_t uc_sleep; /* process' wait queue */ +}; + +#define CODA_REQ_ASYNC 0x1 +#define CODA_REQ_READ 0x2 +#define CODA_REQ_WRITE 0x4 +#define CODA_REQ_ABORT 0x8 + +/* communication pending/processing queues */ +struct venus_comm { + u_long vc_seq; + wait_queue_head_t vc_waitq; /* Venus wait queue */ + struct list_head vc_pending; + struct list_head vc_processing; + int vc_inuse; + struct super_block *vc_sb; + struct mutex vc_mutex; +}; + +static inline struct venus_comm *coda_vcp(struct super_block *sb) +{ + return (struct venus_comm *)((sb)->s_fs_info); +} + +/* upcalls */ +int venus_rootfid(struct super_block *sb, struct CodaFid *fidp); +int venus_getattr(struct super_block *sb, struct CodaFid *fid, + struct coda_vattr *attr); +int venus_setattr(struct super_block *, struct CodaFid *, struct coda_vattr *); +int venus_lookup(struct super_block *sb, struct CodaFid *fid, + const char *name, int length, int *type, + struct CodaFid *resfid); +int venus_close(struct super_block *sb, struct CodaFid *fid, int flags, + kuid_t uid); +int venus_open(struct super_block *sb, struct CodaFid *fid, int flags, + struct file **f); +int venus_mkdir(struct super_block *sb, struct CodaFid *dirfid, + const char *name, int length, + struct CodaFid *newfid, struct coda_vattr *attrs); +int venus_create(struct super_block *sb, struct CodaFid *dirfid, + const char *name, int length, int excl, int mode, + struct CodaFid *newfid, struct coda_vattr *attrs); +int venus_rmdir(struct super_block *sb, struct CodaFid *dirfid, + const char *name, int length); +int venus_remove(struct super_block *sb, struct CodaFid *dirfid, + const char *name, int length); +int venus_readlink(struct super_block *sb, struct CodaFid *fid, + char *buffer, int *length); +int venus_rename(struct super_block *sb, struct CodaFid *new_fid, + struct CodaFid *old_fid, size_t old_length, + size_t new_length, const char *old_name, + const char *new_name); +int venus_link(struct super_block *sb, struct CodaFid *fid, + struct CodaFid *dirfid, const char *name, int len ); +int venus_symlink(struct super_block *sb, struct CodaFid *fid, + const char *name, int len, const char *symname, int symlen); +int venus_access(struct super_block *sb, struct CodaFid *fid, int mask); +int venus_pioctl(struct super_block *sb, struct CodaFid *fid, + unsigned int cmd, struct PioctlData *data); +int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out, + size_t nbytes); +int venus_fsync(struct super_block *sb, struct CodaFid *fid); +int venus_statfs(struct dentry *dentry, struct kstatfs *sfs); + +/* + * Statistics + */ + +extern struct venus_comm coda_comms[]; +#endif diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 00876ddadb43..ca40c2556ba6 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -23,7 +23,7 @@ #include <linux/uaccess.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> +#include "coda_psdev.h" #include "coda_linux.h" #include "coda_cache.h" @@ -47,8 +47,8 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsig int type = 0; if (length > CODA_MAXNAMLEN) { - pr_err("name too long: lookup, %s (%*s)\n", - coda_i2s(dir), (int)length, name); + pr_err("name too long: lookup, %s %zu\n", + coda_i2s(dir), length); return ERR_PTR(-ENAMETOOLONG); } @@ -356,8 +356,7 @@ static int coda_venus_readdir(struct file *coda_file, struct dir_context *ctx) ino_t ino; int ret; - cfi = CODA_FTOC(coda_file); - BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); + cfi = coda_ftoc(coda_file); host_file = cfi->cfi_container; cii = ITOC(file_inode(coda_file)); @@ -426,8 +425,7 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx) struct file *host_file; int ret; - cfi = CODA_FTOC(coda_file); - BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); + cfi = coda_ftoc(coda_file); host_file = cfi->cfi_container; if (host_file->f_op->iterate || host_file->f_op->iterate_shared) { diff --git a/fs/coda/file.c b/fs/coda/file.c index 1cbc1f2298ee..0dbd13ab72e3 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -22,18 +22,22 @@ #include <linux/uaccess.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> - +#include "coda_psdev.h" #include "coda_linux.h" #include "coda_int.h" +struct coda_vm_ops { + atomic_t refcnt; + struct file *coda_file; + const struct vm_operations_struct *host_vm_ops; + struct vm_operations_struct vm_ops; +}; + static ssize_t coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *coda_file = iocb->ki_filp; - struct coda_file_info *cfi = CODA_FTOC(coda_file); - - BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); + struct coda_file_info *cfi = coda_ftoc(coda_file); return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos, 0); } @@ -43,12 +47,10 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *coda_file = iocb->ki_filp; struct inode *coda_inode = file_inode(coda_file); - struct coda_file_info *cfi = CODA_FTOC(coda_file); + struct coda_file_info *cfi = coda_ftoc(coda_file); struct file *host_file; ssize_t ret; - BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); - host_file = cfi->cfi_container; file_start_write(host_file); inode_lock(coda_inode); @@ -61,6 +63,34 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) return ret; } +static void +coda_vm_open(struct vm_area_struct *vma) +{ + struct coda_vm_ops *cvm_ops = + container_of(vma->vm_ops, struct coda_vm_ops, vm_ops); + + atomic_inc(&cvm_ops->refcnt); + + if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->open) + cvm_ops->host_vm_ops->open(vma); +} + +static void +coda_vm_close(struct vm_area_struct *vma) +{ + struct coda_vm_ops *cvm_ops = + container_of(vma->vm_ops, struct coda_vm_ops, vm_ops); + + if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->close) + cvm_ops->host_vm_ops->close(vma); + + if (atomic_dec_and_test(&cvm_ops->refcnt)) { + vma->vm_ops = cvm_ops->host_vm_ops; + fput(cvm_ops->coda_file); + kfree(cvm_ops); + } +} + static int coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) { @@ -68,14 +98,22 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) struct coda_inode_info *cii; struct file *host_file; struct inode *coda_inode, *host_inode; + struct coda_vm_ops *cvm_ops; + int ret; - cfi = CODA_FTOC(coda_file); - BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); + cfi = coda_ftoc(coda_file); host_file = cfi->cfi_container; if (!host_file->f_op->mmap) return -ENODEV; + if (WARN_ON(coda_file != vma->vm_file)) + return -EIO; + + cvm_ops = kmalloc(sizeof(struct coda_vm_ops), GFP_KERNEL); + if (!cvm_ops) + return -ENOMEM; + coda_inode = file_inode(coda_file); host_inode = file_inode(host_file); @@ -89,6 +127,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) * the container file on us! */ else if (coda_inode->i_mapping != host_inode->i_mapping) { spin_unlock(&cii->c_lock); + kfree(cvm_ops); return -EBUSY; } @@ -97,7 +136,29 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) cfi->cfi_mapcount++; spin_unlock(&cii->c_lock); - return call_mmap(host_file, vma); + vma->vm_file = get_file(host_file); + ret = call_mmap(vma->vm_file, vma); + + if (ret) { + /* if call_mmap fails, our caller will put coda_file so we + * should drop the reference to the host_file that we got. + */ + fput(host_file); + kfree(cvm_ops); + } else { + /* here we add redirects for the open/close vm_operations */ + cvm_ops->host_vm_ops = vma->vm_ops; + if (vma->vm_ops) + cvm_ops->vm_ops = *vma->vm_ops; + + cvm_ops->vm_ops.open = coda_vm_open; + cvm_ops->vm_ops.close = coda_vm_close; + cvm_ops->coda_file = coda_file; + atomic_set(&cvm_ops->refcnt, 1); + + vma->vm_ops = &cvm_ops->vm_ops; + } + return ret; } int coda_open(struct inode *coda_inode, struct file *coda_file) @@ -142,8 +203,7 @@ int coda_release(struct inode *coda_inode, struct file *coda_file) struct inode *host_inode; int err; - cfi = CODA_FTOC(coda_file); - BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); + cfi = coda_ftoc(coda_file); err = venus_close(coda_inode->i_sb, coda_i2f(coda_inode), coda_flags, coda_file->f_cred->fsuid); @@ -185,8 +245,7 @@ int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync) return err; inode_lock(coda_inode); - cfi = CODA_FTOC(coda_file); - BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); + cfi = coda_ftoc(coda_file); host_file = cfi->cfi_container; err = vfs_fsync(host_file, datasync); @@ -207,4 +266,3 @@ const struct file_operations coda_file_operations = { .fsync = coda_fsync, .splice_read = generic_file_splice_read, }; - diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 23f6ebd08e80..321f56e487cb 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -27,7 +27,7 @@ #include <linux/vmalloc.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> +#include "coda_psdev.h" #include "coda_linux.h" #include "coda_cache.h" @@ -236,6 +236,7 @@ static void coda_put_super(struct super_block *sb) vcp->vc_sb = NULL; sb->s_fs_info = NULL; mutex_unlock(&vcp->vc_mutex); + mutex_destroy(&vcp->vc_mutex); pr_info("Bye bye.\n"); } diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c index e0c17b7dccce..644d48c12ce8 100644 --- a/fs/coda/pioctl.c +++ b/fs/coda/pioctl.c @@ -20,8 +20,7 @@ #include <linux/uaccess.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> - +#include "coda_psdev.h" #include "coda_linux.h" /* pioctl ops */ diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index 0ceef32e6fae..ebfbbea9fa48 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -38,8 +38,7 @@ #include <linux/uaccess.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> - +#include "coda_psdev.h" #include "coda_linux.h" #include "coda_int.h" @@ -100,8 +99,12 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf, ssize_t retval = 0, count = 0; int error; + /* make sure there is enough to copy out the (opcode, unique) values */ + if (nbytes < (2 * sizeof(u_int32_t))) + return -EINVAL; + /* Peek at the opcode, uniquefier */ - if (copy_from_user(&hdr, buf, 2 * sizeof(u_long))) + if (copy_from_user(&hdr, buf, 2 * sizeof(u_int32_t))) return -EFAULT; if (DOWNCALL(hdr.opcode)) { @@ -119,17 +122,21 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf, hdr.opcode, hdr.unique); nbytes = size; } - CODA_ALLOC(dcbuf, union outputArgs *, nbytes); + dcbuf = kvmalloc(nbytes, GFP_KERNEL); + if (!dcbuf) { + retval = -ENOMEM; + goto out; + } if (copy_from_user(dcbuf, buf, nbytes)) { - CODA_FREE(dcbuf, nbytes); + kvfree(dcbuf); retval = -EFAULT; goto out; } /* what downcall errors does Venus handle ? */ - error = coda_downcall(vcp, hdr.opcode, dcbuf); + error = coda_downcall(vcp, hdr.opcode, dcbuf, nbytes); - CODA_FREE(dcbuf, nbytes); + kvfree(dcbuf); if (error) { pr_warn("%s: coda_downcall error: %d\n", __func__, error); @@ -182,8 +189,11 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf, if (req->uc_opcode == CODA_OPEN_BY_FD) { struct coda_open_by_fd_out *outp = (struct coda_open_by_fd_out *)req->uc_data; - if (!outp->oh.result) + if (!outp->oh.result) { outp->fh = fget(outp->fd); + if (!outp->fh) + return -EBADF; + } } wake_up(&req->uc_sleep); @@ -252,7 +262,7 @@ static ssize_t coda_psdev_read(struct file * file, char __user * buf, goto out; } - CODA_FREE(req->uc_data, sizeof(struct coda_in_hdr)); + kvfree(req->uc_data); kfree(req); out: mutex_unlock(&vcp->vc_mutex); @@ -314,7 +324,7 @@ static int coda_psdev_release(struct inode * inode, struct file * file) /* Async requests need to be freed here */ if (req->uc_flags & CODA_REQ_ASYNC) { - CODA_FREE(req->uc_data, sizeof(struct coda_in_hdr)); + kvfree(req->uc_data); kfree(req); continue; } @@ -347,13 +357,13 @@ static const struct file_operations coda_psdev_fops = { .llseek = noop_llseek, }; -static int init_coda_psdev(void) +static int __init init_coda_psdev(void) { int i, err = 0; if (register_chrdev(CODA_PSDEV_MAJOR, "coda", &coda_psdev_fops)) { pr_err("%s: unable to get major %d\n", __func__, CODA_PSDEV_MAJOR); - return -EIO; + return -EIO; } coda_psdev_class = class_create(THIS_MODULE, "coda"); if (IS_ERR(coda_psdev_class)) { @@ -378,7 +388,7 @@ MODULE_AUTHOR("Jan Harkes, Peter J. Braam"); MODULE_DESCRIPTION("Coda Distributed File System VFS interface"); MODULE_ALIAS_CHARDEV_MAJOR(CODA_PSDEV_MAJOR); MODULE_LICENSE("GPL"); -MODULE_VERSION("6.6"); +MODULE_VERSION("6.11"); static int __init init_coda(void) { diff --git a/fs/coda/symlink.c b/fs/coda/symlink.c index 202297d156df..8907d0508198 100644 --- a/fs/coda/symlink.c +++ b/fs/coda/symlink.c @@ -17,8 +17,7 @@ #include <linux/pagemap.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> - +#include "coda_psdev.h" #include "coda_linux.h" static int coda_symlink_filler(struct file *file, struct page *page) diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c index 0301d45000a8..fda3b702b1c5 100644 --- a/fs/coda/sysctl.c +++ b/fs/coda/sysctl.c @@ -12,7 +12,6 @@ #include "coda_int.h" -#ifdef CONFIG_SYSCTL static struct ctl_table_header *fs_table_header; static struct ctl_table coda_table[] = { @@ -62,13 +61,3 @@ void coda_sysctl_clean(void) fs_table_header = NULL; } } - -#else -void coda_sysctl_init(void) -{ -} - -void coda_sysctl_clean(void) -{ -} -#endif diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c index 1175a1722411..15c0e4fdb0e3 100644 --- a/fs/coda/upcall.c +++ b/fs/coda/upcall.c @@ -33,7 +33,7 @@ #include <linux/vfs.h> #include <linux/coda.h> -#include <linux/coda_psdev.h> +#include "coda_psdev.h" #include "coda_linux.h" #include "coda_cache.h" @@ -46,7 +46,7 @@ static void *alloc_upcall(int opcode, int size) { union inputArgs *inp; - CODA_ALLOC(inp, union inputArgs *, size); + inp = kvzalloc(size, GFP_KERNEL); if (!inp) return ERR_PTR(-ENOMEM); @@ -85,7 +85,7 @@ int venus_rootfid(struct super_block *sb, struct CodaFid *fidp) if (!error) *fidp = outp->coda_root.VFid; - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -104,7 +104,7 @@ int venus_getattr(struct super_block *sb, struct CodaFid *fid, if (!error) *attr = outp->coda_getattr.attr; - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -123,7 +123,7 @@ int venus_setattr(struct super_block *sb, struct CodaFid *fid, error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -153,7 +153,7 @@ int venus_lookup(struct super_block *sb, struct CodaFid *fid, *type = outp->coda_lookup.vtype; } - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -173,7 +173,7 @@ int venus_close(struct super_block *sb, struct CodaFid *fid, int flags, error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -194,7 +194,7 @@ int venus_open(struct super_block *sb, struct CodaFid *fid, if (!error) *fh = outp->coda_open_by_fd.fh; - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -224,7 +224,7 @@ int venus_mkdir(struct super_block *sb, struct CodaFid *dirfid, *newfid = outp->coda_mkdir.VFid; } - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -262,7 +262,7 @@ int venus_rename(struct super_block *sb, struct CodaFid *old_fid, error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -295,7 +295,7 @@ int venus_create(struct super_block *sb, struct CodaFid *dirfid, *newfid = outp->coda_create.VFid; } - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -318,7 +318,7 @@ int venus_rmdir(struct super_block *sb, struct CodaFid *dirfid, error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -340,7 +340,7 @@ int venus_remove(struct super_block *sb, struct CodaFid *dirfid, error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -370,7 +370,7 @@ int venus_readlink(struct super_block *sb, struct CodaFid *fid, *(buffer + retlen) = '\0'; } - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -398,7 +398,7 @@ int venus_link(struct super_block *sb, struct CodaFid *fid, error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -433,7 +433,7 @@ int venus_symlink(struct super_block *sb, struct CodaFid *fid, error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -449,7 +449,7 @@ int venus_fsync(struct super_block *sb, struct CodaFid *fid) inp->coda_fsync.VFid = *fid; error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -467,7 +467,7 @@ int venus_access(struct super_block *sb, struct CodaFid *fid, int mask) error = coda_upcall(coda_vcp(sb), insize, &outsize, inp); - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -543,7 +543,7 @@ int venus_pioctl(struct super_block *sb, struct CodaFid *fid, } exit: - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -553,7 +553,7 @@ int venus_statfs(struct dentry *dentry, struct kstatfs *sfs) union outputArgs *outp; int insize, outsize, error; - insize = max_t(unsigned int, INSIZE(statfs), OUTSIZE(statfs)); + insize = SIZE(statfs); UPARG(CODA_STATFS); error = coda_upcall(coda_vcp(dentry->d_sb), insize, &outsize, inp); @@ -565,7 +565,7 @@ int venus_statfs(struct dentry *dentry, struct kstatfs *sfs) sfs->f_ffree = outp->coda_statfs.stat.f_ffree; } - CODA_FREE(inp, insize); + kvfree(inp); return error; } @@ -743,7 +743,7 @@ static int coda_upcall(struct venus_comm *vcp, sig_req = kmalloc(sizeof(struct upc_req), GFP_KERNEL); if (!sig_req) goto exit; - CODA_ALLOC((sig_req->uc_data), char *, sizeof(struct coda_in_hdr)); + sig_req->uc_data = kvzalloc(sizeof(struct coda_in_hdr), GFP_KERNEL); if (!sig_req->uc_data) { kfree(sig_req); goto exit; @@ -804,12 +804,44 @@ exit: * * CODA_REPLACE -- replace one CodaFid with another throughout the name cache */ -int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out) +int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out, + size_t nbytes) { struct inode *inode = NULL; struct CodaFid *fid = NULL, *newfid; struct super_block *sb; + /* + * Make sure we have received enough data from the cache + * manager to populate the necessary fields in the buffer + */ + switch (opcode) { + case CODA_PURGEUSER: + if (nbytes < sizeof(struct coda_purgeuser_out)) + return -EINVAL; + break; + + case CODA_ZAPDIR: + if (nbytes < sizeof(struct coda_zapdir_out)) + return -EINVAL; + break; + + case CODA_ZAPFILE: + if (nbytes < sizeof(struct coda_zapfile_out)) + return -EINVAL; + break; + + case CODA_PURGEFID: + if (nbytes < sizeof(struct coda_purgefid_out)) + return -EINVAL; + break; + + case CODA_REPLACE: + if (nbytes < sizeof(struct coda_replace_out)) + return -EINVAL; + break; + } + /* Handle invalidation requests. */ mutex_lock(&vcp->vc_mutex); sb = vcp->vc_sb; diff --git a/fs/coredump.c b/fs/coredump.c index e42e17e55bfd..b1ea7dfbd149 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -7,6 +7,7 @@ #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> +#include <linux/ctype.h> #include <linux/string.h> #include <linux/init.h> #include <linux/pagemap.h> @@ -187,11 +188,13 @@ put_exe_file: * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ -static int format_corename(struct core_name *cn, struct coredump_params *cprm) +static int format_corename(struct core_name *cn, struct coredump_params *cprm, + size_t **argv, int *argc) { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); + bool was_space = false; int pid_in_pattern = 0; int err = 0; @@ -201,12 +204,35 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) return -ENOMEM; cn->corename[0] = '\0'; - if (ispipe) + if (ispipe) { + int argvs = sizeof(core_pattern) / 2; + (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL); + if (!(*argv)) + return -ENOMEM; + (*argv)[(*argc)++] = 0; ++pat_ptr; + } /* Repeat as long as we have more pattern to process and more output space */ while (*pat_ptr) { + /* + * Split on spaces before doing template expansion so that + * %e and %E don't get split if they have spaces in them + */ + if (ispipe) { + if (isspace(*pat_ptr)) { + was_space = true; + pat_ptr++; + continue; + } else if (was_space) { + was_space = false; + err = cn_printf(cn, "%c", '\0'); + if (err) + return err; + (*argv)[(*argc)++] = cn->used; + } + } if (*pat_ptr != '%') { err = cn_printf(cn, "%c", *pat_ptr++); } else { @@ -546,6 +572,8 @@ void do_coredump(const kernel_siginfo_t *siginfo) struct cred *cred; int retval = 0; int ispipe; + size_t *argv = NULL; + int argc = 0; struct files_struct *displaced; /* require nonrelative corefile path and be extra careful */ bool need_suid_safe = false; @@ -592,9 +620,10 @@ void do_coredump(const kernel_siginfo_t *siginfo) old_cred = override_creds(cred); - ispipe = format_corename(&cn, &cprm); + ispipe = format_corename(&cn, &cprm, &argv, &argc); if (ispipe) { + int argi; int dump_count; char **helper_argv; struct subprocess_info *sub_info; @@ -637,12 +666,16 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto fail_dropcount; } - helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL); + helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), + GFP_KERNEL); if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory\n", __func__); goto fail_dropcount; } + for (argi = 0; argi < argc; argi++) + helper_argv[argi] = cn.corename + argv[argi]; + helper_argv[argi] = NULL; retval = -ENOMEM; sub_info = call_usermodehelper_setup(helper_argv[0], @@ -652,7 +685,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) retval = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); - argv_free(helper_argv); + kfree(helper_argv); if (retval) { printk(KERN_INFO "Core dump to |%s pipe failed\n", cn.corename); @@ -766,6 +799,7 @@ fail_dropcount: if (ispipe) atomic_dec(&core_dump_count); fail_unlock: + kfree(argv); kfree(cn.corename); coredump_finish(mm, core_dumped); revert_creds(old_cred); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index c6f513100cc9..38d2e8a29f0d 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -291,7 +291,6 @@ static LIST_HEAD(tfile_check_list); #include <linux/sysctl.h> -static long zero; static long long_max = LONG_MAX; struct ctl_table epoll_table[] = { @@ -301,7 +300,7 @@ struct ctl_table epoll_table[] = { .maxlen = sizeof(max_user_watches), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, .extra2 = &long_max, }, { } @@ -2325,7 +2324,7 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, error = do_epoll_wait(epfd, events, maxevents, timeout); - restore_user_sigmask(sigmask, &sigsaved); + restore_user_sigmask(sigmask, &sigsaved, error == -EINTR); return error; } @@ -2350,7 +2349,7 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, err = do_epoll_wait(epfd, events, maxevents, timeout); - restore_user_sigmask(sigmask, &sigsaved); + restore_user_sigmask(sigmask, &sigsaved, err == -EINTR); return err; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 052dba97d814..e1c078a7ed04 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2915,7 +2915,7 @@ int f2fs_migrate_page(struct address_space *mapping, /* one extra reference was held for atomic_write page */ extra_count = atomic_written ? 1 : 0; rc = migrate_page_move_mapping(mapping, newpage, - page, mode, extra_count); + page, extra_count); if (rc != MIGRATEPAGE_SUCCESS) { if (atomic_written) mutex_unlock(&fi->inmem_lock); diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index d5403b4004c9..bb0b27d88e50 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -407,7 +407,7 @@ static int copy_name(char *buffer, const char *xattr_name, int name_len) int offset = 0; if (!is_known_namespace(xattr_name)) { - strncpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN); + memcpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN); offset += XATTR_MAC_OSX_PREFIX_LEN; len += XATTR_MAC_OSX_PREFIX_LEN; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 1fc7ec573019..6f76b31093e0 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2419,11 +2419,12 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, } ret = wait_event_interruptible(ctx->wait, io_cqring_events(ring) >= min_events); - if (ret == -ERESTARTSYS) - ret = -EINTR; if (sig) - restore_user_sigmask(sig, &sigsaved); + restore_user_sigmask(sig, &sigsaved, ret == -ERESTARTSYS); + + if (ret == -ERESTARTSYS) + ret = -EINTR; return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0; } diff --git a/fs/iomap.c b/fs/iomap.c index 23ef63fd1669..52b0a6ee4f83 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -562,7 +562,7 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage, { int ret; - ret = migrate_page_move_mapping(mapping, newpage, page, mode, 0); + ret = migrate_page_move_mapping(mapping, newpage, page, 0); if (ret != MIGRATEPAGE_SUCCESS) return ret; diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 7d8654a1472e..f8fb89b10227 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -109,9 +109,9 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg) return ret; } -int jffs2_do_readpage_unlock(struct inode *inode, struct page *pg) +int jffs2_do_readpage_unlock(void *data, struct page *pg) { - int ret = jffs2_do_readpage_nolock(inode, pg); + int ret = jffs2_do_readpage_nolock(data, pg); unlock_page(pg); return ret; } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 112d85849db1..8a20ddd25f2d 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct page *pg; pg = read_cache_page(inode->i_mapping, offset >> PAGE_SHIFT, - (void *)jffs2_do_readpage_unlock, inode); + jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index a2dbbb3f4c74..bd3d5f0ddc34 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -155,7 +155,7 @@ extern const struct file_operations jffs2_file_operations; extern const struct inode_operations jffs2_file_inode_operations; extern const struct address_space_operations jffs2_file_address_operations; int jffs2_fsync(struct file *, loff_t, loff_t, int); -int jffs2_do_readpage_unlock (struct inode *inode, struct page *pg); +int jffs2_do_readpage_unlock(void *data, struct page *pg); /* ioctl.c */ long jffs2_ioctl(struct file *, unsigned int, unsigned long); diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index e6fde1a5c072..4b26aa7e4d78 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -288,10 +288,13 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, /* * For queues with unlimited length lost events are not expected and * can possibly have security implications. Avoid losing events when - * memory is short. + * memory is short. For the limited size queues, avoid OOM killer in the + * target monitoring memcg as it may have security repercussion. */ if (group->max_events == UINT_MAX) gfp |= __GFP_NOFAIL; + else + gfp |= __GFP_RETRY_MAYFAIL; /* Whoever is interested in the event, pays for the allocation. */ memalloc_use_memcg(group->memcg); diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 2fda08b2b885..d510223d302c 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -90,9 +90,13 @@ int inotify_handle_event(struct fsnotify_group *group, i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); - /* Whoever is interested in the event, pays for the allocation. */ + /* + * Whoever is interested in the event, pays for the allocation. Do not + * trigger OOM killer in the target monitoring memcg as it may have + * security repercussion. + */ memalloc_use_memcg(group->memcg); - event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT); + event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); memalloc_unuse_memcg(); if (unlikely(!event)) { diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index cce8de32779f..0b815178126e 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -45,8 +45,6 @@ struct kmem_cache *inotify_inode_mark_cachep __read_mostly; #include <linux/sysctl.h> -static int zero; - struct ctl_table inotify_table[] = { { .procname = "max_user_instances", @@ -54,7 +52,7 @@ struct ctl_table inotify_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "max_user_watches", @@ -62,7 +60,7 @@ struct ctl_table inotify_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = SYSCTL_ZERO, }, { .procname = "max_queued_events", @@ -70,7 +68,7 @@ struct ctl_table inotify_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = SYSCTL_ZERO }, { } }; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index d1348fc4ca6d..2443224d0c42 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5993,6 +5993,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb) struct buffer_head *data_alloc_bh = NULL; struct ocfs2_dinode *di; struct ocfs2_truncate_log *tl; + struct ocfs2_journal *journal = osb->journal; BUG_ON(inode_trylock(tl_inode)); @@ -6013,6 +6014,20 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb) goto out; } + /* Appending truncate log(TA) and and flushing truncate log(TF) are + * two separated transactions. They can be both committed but not + * checkpointed. If crash occurs then, both two transaction will be + * replayed with several already released to global bitmap clusters. + * Then truncate log will be replayed resulting in cluster double free. + */ + jbd2_journal_lock_updates(journal->j_journal); + status = jbd2_journal_flush(journal->j_journal); + jbd2_journal_unlock_updates(journal->j_journal); + if (status < 0) { + mlog_errno(status); + goto out; + } + data_alloc_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index a4c905d6b575..3e0a93e799ea 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2139,13 +2139,30 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, struct ocfs2_dio_write_ctxt *dwc = NULL; struct buffer_head *di_bh = NULL; u64 p_blkno; - loff_t pos = iblock << inode->i_sb->s_blocksize_bits; + unsigned int i_blkbits = inode->i_sb->s_blocksize_bits; + loff_t pos = iblock << i_blkbits; + sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits; unsigned len, total_len = bh_result->b_size; int ret = 0, first_get_block = 0; len = osb->s_clustersize - (pos & (osb->s_clustersize - 1)); len = min(total_len, len); + /* + * bh_result->b_size is count in get_more_blocks according to write + * "pos" and "end", we need map twice to return different buffer state: + * 1. area in file size, not set NEW; + * 2. area out file size, set NEW. + * + * iblock endblk + * |--------|---------|---------|--------- + * |<-------area in file------->| + */ + + if ((iblock <= endblk) && + ((iblock + ((len - 1) >> i_blkbits)) > endblk)) + len = (endblk - iblock + 1) << i_blkbits; + mlog(0, "get block of %lu at %llu:%u req %u\n", inode->i_ino, pos, len, total_len); @@ -2229,6 +2246,9 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock, if (desc->c_needs_zero) set_buffer_new(bh_result); + if (iblock > endblk) + set_buffer_new(bh_result); + /* May sleep in end_io. It should not happen in a irq context. So defer * it to dio work queue. */ set_buffer_defer_completion(bh_result); diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 7a3a096856a8..7f74fcc6d7d9 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1184,7 +1184,7 @@ bail: if (atomic_read(®->hr_steady_iterations) != 0) { if (atomic_dec_and_test(®->hr_unsteady_iterations)) { printk(KERN_NOTICE "o2hb: Unable to stabilize " - "heartbeart on region %s (%s)\n", + "heartbeat on region %s (%s)\n", config_item_name(®->hr_item), reg->hr_dev_name); atomic_set(®->hr_steady_iterations, 0); diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index 3d5d4b2b1356..5c424a099280 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -76,7 +76,7 @@ static void o2quo_fence_self(void) }; } -/* Indicate that a timeout occurred on a hearbeat region write. The +/* Indicate that a timeout occurred on a heartbeat region write. The * other nodes in the cluster may consider us dead at that time so we * want to "fence" ourselves so that we don't scribble on the disk * after they think they've recovered us. This can't solve all diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index c599463d0694..c07c9aac537a 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1762,7 +1762,7 @@ static void o2net_hb_node_up_cb(struct o2nm_node *node, int node_num, (msecs_to_jiffies(o2net_reconnect_delay()) + 1); if (node_num != o2nm_this_node()) { - /* believe it or not, accept and node hearbeating testing + /* believe it or not, accept and node heartbeating testing * can succeed for this node before we got here.. so * only use set_nn_state to clear the persistent error * if that hasn't already happened */ diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 2d016937fdda..42a61eecdacd 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -296,6 +296,18 @@ int ocfs2_dentry_attach_lock(struct dentry *dentry, out_attach: spin_lock(&dentry_attach_lock); + if (unlikely(dentry->d_fsdata && !alias)) { + /* d_fsdata is set by a racing thread which is doing + * the same thing as this thread is doing. Leave the racing + * thread going ahead and we return here. + */ + spin_unlock(&dentry_attach_lock); + iput(dl->dl_inode); + ocfs2_lock_res_free(&dl->dl_lockres); + kfree(dl); + return 0; + } + dentry->d_fsdata = dl; dl->dl_count++; spin_unlock(&dentry_attach_lock); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 810f841494ef..74b768ca1cd8 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2161,7 +2161,7 @@ put: * think that $RECOVERY is currently mastered by a dead node. If so, * we wait a short time to allow that node to get notified by its own * heartbeat stack, then check again. All $RECOVERY lock resources - * mastered by dead nodes are purged when the hearbeat callback is + * mastered by dead nodes are purged when the heartbeat callback is * fired, so we can know for sure that it is safe to continue once * the node returns a live node or no node. */ static int dlm_pre_master_reco_lockres(struct dlm_ctxt *dlm, diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index e78657742bd8..3883633e82eb 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -90,7 +90,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, enum dlm_status status; int actions = 0; int in_use; - u8 owner; + u8 owner; + int recovery_wait = 0; mlog(0, "master_node = %d, valblk = %d\n", master_node, flags & LKM_VALBLK); @@ -193,9 +194,12 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, } if (flags & LKM_CANCEL) lock->cancel_pending = 0; - else - lock->unlock_pending = 0; - + else { + if (!lock->unlock_pending) + recovery_wait = 1; + else + lock->unlock_pending = 0; + } } /* get an extra ref on lock. if we are just switching @@ -229,6 +233,17 @@ leave: spin_unlock(&res->spinlock); wake_up(&res->wq); + if (recovery_wait) { + spin_lock(&res->spinlock); + /* Unlock request will directly succeed after owner dies, + * and the lock is already removed from grant list. We have to + * wait for RECOVERING done or we miss the chance to purge it + * since the removement is much faster than RECOVERING proc. + */ + __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_RECOVERING); + spin_unlock(&res->spinlock); + } + /* let the caller's final dlm_lock_put handle the actual kfree */ if (actions & DLM_UNLOCK_FREE_LOCK) { /* this should always be coupled with list removal */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index b5fc5d3c7525..9317d04fb03b 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -434,7 +434,7 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, struct ocfs2_mask_waiter *mw, int ret) { u32 usec; - ktime_t kt; + ktime_t last, kt; struct ocfs2_lock_stats *stats; if (level == LKM_PRMODE) @@ -444,7 +444,8 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, else return; - kt = ktime_sub(ktime_get(), mw->mw_lock_start); + last = ktime_get(); + kt = ktime_sub(last, mw->mw_lock_start); usec = ktime_to_us(kt); stats->ls_gets++; @@ -460,6 +461,8 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, if (ret) stats->ls_fail++; + + stats->ls_last = ktime_to_timespec(last).tv_sec; } static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres) @@ -2989,6 +2992,8 @@ struct ocfs2_dlm_debug *ocfs2_new_dlm_debug(void) kref_init(&dlm_debug->d_refcnt); INIT_LIST_HEAD(&dlm_debug->d_lockres_tracking); dlm_debug->d_locking_state = NULL; + dlm_debug->d_locking_filter = NULL; + dlm_debug->d_filter_secs = 0; out: return dlm_debug; } @@ -3079,17 +3084,41 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos) * - Lock stats printed * New in version 3 * - Max time in lock stats is in usecs (instead of nsecs) + * New in version 4 + * - Add last pr/ex unlock times in secs */ -#define OCFS2_DLM_DEBUG_STR_VERSION 3 +#define OCFS2_DLM_DEBUG_STR_VERSION 4 static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) { int i; char *lvb; + u32 now, last = 0; struct ocfs2_lock_res *lockres = v; + struct ocfs2_dlm_debug *dlm_debug = + ((struct ocfs2_dlm_seq_priv *)m->private)->p_dlm_debug; if (!lockres) return -EINVAL; + if (dlm_debug->d_filter_secs) { + now = ktime_to_timespec(ktime_get()).tv_sec; +#ifdef CONFIG_OCFS2_FS_STATS + if (lockres->l_lock_prmode.ls_last > + lockres->l_lock_exmode.ls_last) + last = lockres->l_lock_prmode.ls_last; + else + last = lockres->l_lock_exmode.ls_last; +#endif + /* + * Use d_filter_secs field to filter lock resources dump, + * the default d_filter_secs(0) value filters nothing, + * otherwise, only dump the last N seconds active lock + * resources. + */ + if ((now - last) > dlm_debug->d_filter_secs) + return 0; + } + seq_printf(m, "0x%x\t", OCFS2_DLM_DEBUG_STR_VERSION); if (lockres->l_type == OCFS2_LOCK_TYPE_DENTRY) @@ -3131,6 +3160,8 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) # define lock_max_prmode(_l) ((_l)->l_lock_prmode.ls_max) # define lock_max_exmode(_l) ((_l)->l_lock_exmode.ls_max) # define lock_refresh(_l) ((_l)->l_lock_refresh) +# define lock_last_prmode(_l) ((_l)->l_lock_prmode.ls_last) +# define lock_last_exmode(_l) ((_l)->l_lock_exmode.ls_last) #else # define lock_num_prmode(_l) (0) # define lock_num_exmode(_l) (0) @@ -3141,6 +3172,8 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) # define lock_max_prmode(_l) (0) # define lock_max_exmode(_l) (0) # define lock_refresh(_l) (0) +# define lock_last_prmode(_l) (0) +# define lock_last_exmode(_l) (0) #endif /* The following seq_print was added in version 2 of this output */ seq_printf(m, "%u\t" @@ -3151,6 +3184,8 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) "%llu\t" "%u\t" "%u\t" + "%u\t" + "%u\t" "%u\t", lock_num_prmode(lockres), lock_num_exmode(lockres), @@ -3160,7 +3195,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) lock_total_exmode(lockres), lock_max_prmode(lockres), lock_max_exmode(lockres), - lock_refresh(lockres)); + lock_refresh(lockres), + lock_last_prmode(lockres), + lock_last_exmode(lockres)); /* End the line */ seq_printf(m, "\n"); @@ -3231,6 +3268,17 @@ static int ocfs2_dlm_init_debug(struct ocfs2_super *osb) goto out; } + dlm_debug->d_locking_filter = debugfs_create_u32("locking_filter", + 0600, + osb->osb_debug_root, + &dlm_debug->d_filter_secs); + if (!dlm_debug->d_locking_filter) { + ret = -EINVAL; + mlog(ML_ERROR, + "Unable to create locking filter debugfs file.\n"); + goto out; + } + ocfs2_get_dlm_debug(dlm_debug); out: return ret; @@ -3242,6 +3290,7 @@ static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb) if (dlm_debug) { debugfs_remove(dlm_debug->d_locking_state); + debugfs_remove(dlm_debug->d_locking_filter); ocfs2_put_dlm_debug(dlm_debug); } } diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index a4647a646f07..9b2a72ff6f7c 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -150,6 +150,7 @@ struct ocfs2_lock_stats { /* Storing max wait in usecs saves 24 bytes per inode */ u32 ls_max; /* Max wait in USEC */ + u32 ls_last; /* Last unlock time in SEC */ }; #endif @@ -222,6 +223,8 @@ struct ocfs2_orphan_scan { struct ocfs2_dlm_debug { struct kref d_refcnt; struct dentry *d_locking_state; + struct dentry *d_locking_filter; + u32 d_filter_secs; struct list_head d_lockres_tracking; }; diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 62ee41b4bbd0..b74ea844abd5 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -58,7 +58,8 @@ config PROC_VMCORE_DEVICE_DUMP snapshot. If you say Y here, the collected device dumps will be added - as ELF notes to /proc/vmcore. + as ELF notes to /proc/vmcore. You can still disable device + dump using the kernel command line option 'novmcoredd'. config PROC_SYSCTL bool "Sysctl support (/proc/sys)" if EXPERT diff --git a/fs/proc/array.c b/fs/proc/array.c index 84908556ea58..46dcb6f0eccf 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -462,7 +462,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * a program is not able to use ptrace(2) in that case. It is * safe because the task has stopped executing permanently. */ - if (permitted && (task->flags & PF_DUMPCORE)) { + if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) { if (try_get_task_stack(task)) { eip = KSTK_EIP(task); esp = KSTK_ESP(task); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 5f8d215b3fd0..dbe43a50caf2 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -200,7 +200,8 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) struct proc_dir_entry *pde = PDE(file_inode(file)); loff_t rv = -EINVAL; if (use_pde(pde)) { - loff_t (*llseek)(struct file *, loff_t, int); + typeof_member(struct file_operations, llseek) llseek; + llseek = pde->proc_fops->llseek; if (!llseek) llseek = default_llseek; @@ -212,10 +213,11 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence) static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - ssize_t (*read)(struct file *, char __user *, size_t, loff_t *); struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (use_pde(pde)) { + typeof_member(struct file_operations, read) read; + read = pde->proc_fops->read; if (read) rv = read(file, buf, count, ppos); @@ -226,10 +228,11 @@ static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *); struct proc_dir_entry *pde = PDE(file_inode(file)); ssize_t rv = -EIO; if (use_pde(pde)) { + typeof_member(struct file_operations, write) write; + write = pde->proc_fops->write; if (write) rv = write(file, buf, count, ppos); @@ -242,8 +245,9 @@ static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts) { struct proc_dir_entry *pde = PDE(file_inode(file)); __poll_t rv = DEFAULT_POLLMASK; - __poll_t (*poll)(struct file *, struct poll_table_struct *); if (use_pde(pde)) { + typeof_member(struct file_operations, poll) poll; + poll = pde->proc_fops->poll; if (poll) rv = poll(file, pts); @@ -256,8 +260,9 @@ static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigne { struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; - long (*ioctl)(struct file *, unsigned int, unsigned long); if (use_pde(pde)) { + typeof_member(struct file_operations, unlocked_ioctl) ioctl; + ioctl = pde->proc_fops->unlocked_ioctl; if (ioctl) rv = ioctl(file, cmd, arg); @@ -271,8 +276,9 @@ static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned { struct proc_dir_entry *pde = PDE(file_inode(file)); long rv = -ENOTTY; - long (*compat_ioctl)(struct file *, unsigned int, unsigned long); if (use_pde(pde)) { + typeof_member(struct file_operations, compat_ioctl) compat_ioctl; + compat_ioctl = pde->proc_fops->compat_ioctl; if (compat_ioctl) rv = compat_ioctl(file, cmd, arg); @@ -286,8 +292,9 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) { struct proc_dir_entry *pde = PDE(file_inode(file)); int rv = -EIO; - int (*mmap)(struct file *, struct vm_area_struct *); if (use_pde(pde)) { + typeof_member(struct file_operations, mmap) mmap; + mmap = pde->proc_fops->mmap; if (mmap) rv = mmap(file, vma); @@ -305,7 +312,7 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long rv = -EIO; if (use_pde(pde)) { - typeof(proc_reg_get_unmapped_area) *get_area; + typeof_member(struct file_operations, get_unmapped_area) get_area; get_area = pde->proc_fops->get_unmapped_area; #ifdef CONFIG_MMU @@ -326,8 +333,8 @@ static int proc_reg_open(struct inode *inode, struct file *file) { struct proc_dir_entry *pde = PDE(inode); int rv = 0; - int (*open)(struct inode *, struct file *); - int (*release)(struct inode *, struct file *); + typeof_member(struct file_operations, open) open; + typeof_member(struct file_operations, release) release; struct pde_opener *pdeo; /* diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c74570736b24..2b1b60e2e9cb 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -22,6 +22,10 @@ static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; +/* shared constants to be used in various sysctls */ +const int sysctl_vals[] = { 0, 1, INT_MAX }; +EXPORT_SYMBOL(sysctl_vals); + /* Support for permanently empty directories */ struct ctl_table sysctl_mount_point[] = { diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 7bb96fdd38ad..a531d548d685 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/crash_dump.h> #include <linux/list.h> +#include <linux/moduleparam.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> @@ -54,6 +55,9 @@ static struct proc_dir_entry *proc_vmcore; /* Device Dump list and mutex to synchronize access to list */ static LIST_HEAD(vmcoredd_list); static DEFINE_MUTEX(vmcoredd_mutex); + +static bool vmcoredd_disabled; +core_param(novmcoredd, vmcoredd_disabled, bool, 0); #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ /* Device Dump Size */ @@ -1452,6 +1456,11 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) size_t data_size; int ret; + if (vmcoredd_disabled) { + pr_err_once("Device dump is disabled\n"); + return -EINVAL; + } + if (!data || !strlen(data->dump_name) || !data->vmcoredd_callback || !data->size) return -EINVAL; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 11201b2d06b9..a26ae0b83f8f 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -145,6 +145,17 @@ static int ramfs_symlink(struct inode * dir, struct dentry *dentry, const char * return error; } +static int ramfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + + inode = ramfs_get_inode(dir->i_sb, dir, mode, 0); + if (!inode) + return -ENOSPC; + d_tmpfile(dentry, inode); + return 0; +} + static const struct inode_operations ramfs_dir_inode_operations = { .create = ramfs_create, .lookup = simple_lookup, @@ -155,6 +166,7 @@ static const struct inode_operations ramfs_dir_inode_operations = { .rmdir = simple_rmdir, .mknod = ramfs_mknod, .rename = simple_rename, + .tmpfile = ramfs_tmpfile, }; /* diff --git a/fs/select.c b/fs/select.c index 6cbc9ff56ba0..a4d8f6e8b63c 100644 --- a/fs/select.c +++ b/fs/select.c @@ -758,10 +758,9 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, return ret; ret = core_sys_select(n, inp, outp, exp, to); + restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND); ret = poll_select_copy_remaining(&end_time, tsp, type, ret); - restore_user_sigmask(sigmask, &sigsaved); - return ret; } @@ -1106,8 +1105,7 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1142,8 +1140,7 @@ SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1350,10 +1347,9 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp, return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); + restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND); ret = poll_select_copy_remaining(&end_time, tsp, type, ret); - restore_user_sigmask(sigmask, &sigsaved); - return ret; } @@ -1425,8 +1421,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1461,8 +1456,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 512e7d9c60cd..cb4c07e65874 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1482,7 +1482,7 @@ static int ubifs_migrate_page(struct address_space *mapping, { int rc; - rc = migrate_page_move_mapping(mapping, newpage, page, mode, 0); + rc = migrate_page_move_mapping(mapping, newpage, page, 0); if (rc != MIGRATEPAGE_SUCCESS) return rc; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 3d247c0d92aa..4ed0dca52ec8 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1407,11 +1407,9 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf) struct super_block *sb = dentry->d_sb; struct ufs_sb_private_info *uspi= UFS_SB(sb)->s_uspi; unsigned flags = UFS_SB(sb)->s_flags; - struct ufs_super_block_third *usb3; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); mutex_lock(&UFS_SB(sb)->s_lock); - usb3 = ubh_get_usb_third(uspi); if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) buf->f_type = UFS2_MAGIC; |