diff options
Diffstat (limited to 'fs')
52 files changed, 576 insertions, 594 deletions
diff --git a/fs/afs/cell.c b/fs/afs/cell.c index cf445dbd5f2e..9de46116c749 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -173,6 +173,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, rcu_assign_pointer(cell->vl_servers, vllist); cell->dns_expiry = TIME64_MAX; + __clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags); } else { cell->dns_expiry = ktime_get_real_seconds(); } @@ -167,9 +167,13 @@ struct kioctx { unsigned id; }; +/* + * First field must be the file pointer in all the + * iocb unions! See also 'struct kiocb' in <linux/fs.h> + */ struct fsync_iocb { - struct work_struct work; struct file *file; + struct work_struct work; bool datasync; }; @@ -183,8 +187,15 @@ struct poll_iocb { struct work_struct work; }; +/* + * NOTE! Each of the iocb union members has the file pointer + * as the first entry in their struct definition. So you can + * access the file pointer through any of the sub-structs, + * or directly as just 'ki_filp' in this struct. + */ struct aio_kiocb { union { + struct file *ki_filp; struct kiocb rw; struct fsync_iocb fsync; struct poll_iocb poll; @@ -1060,6 +1071,8 @@ static inline void iocb_put(struct aio_kiocb *iocb) { if (refcount_read(&iocb->ki_refcnt) == 0 || refcount_dec_and_test(&iocb->ki_refcnt)) { + if (iocb->ki_filp) + fput(iocb->ki_filp); percpu_ref_put(&iocb->ki_ctx->reqs); kmem_cache_free(kiocb_cachep, iocb); } @@ -1424,7 +1437,6 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) file_end_write(kiocb->ki_filp); } - fput(kiocb->ki_filp); aio_complete(iocb, res, res2); } @@ -1432,9 +1444,6 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) { int ret; - req->ki_filp = fget(iocb->aio_fildes); - if (unlikely(!req->ki_filp)) - return -EBADF; req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; @@ -1451,7 +1460,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) ret = ioprio_check_cap(iocb->aio_reqprio); if (ret) { pr_debug("aio ioprio check cap error: %d\n", ret); - goto out_fput; + return ret; } req->ki_ioprio = iocb->aio_reqprio; @@ -1460,14 +1469,10 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); if (unlikely(ret)) - goto out_fput; + return ret; req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */ return 0; - -out_fput: - fput(req->ki_filp); - return ret; } static int aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec, @@ -1521,24 +1526,19 @@ static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, if (ret) return ret; file = req->ki_filp; - - ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_READ))) - goto out_fput; + return -EBADF; ret = -EINVAL; if (unlikely(!file->f_op->read_iter)) - goto out_fput; + return -EINVAL; ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter); if (ret) - goto out_fput; + return ret; ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) aio_rw_done(req, call_read_iter(file, req, &iter)); kfree(iovec); -out_fput: - if (unlikely(ret)) - fput(file); return ret; } @@ -1555,16 +1555,14 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, return ret; file = req->ki_filp; - ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_WRITE))) - goto out_fput; - ret = -EINVAL; + return -EBADF; if (unlikely(!file->f_op->write_iter)) - goto out_fput; + return -EINVAL; ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter); if (ret) - goto out_fput; + return ret; ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) { /* @@ -1582,9 +1580,6 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, aio_rw_done(req, call_write_iter(file, req, &iter)); } kfree(iovec); -out_fput: - if (unlikely(ret)) - fput(file); return ret; } @@ -1594,7 +1589,6 @@ static void aio_fsync_work(struct work_struct *work) int ret; ret = vfs_fsync(req->file, req->datasync); - fput(req->file); aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0); } @@ -1605,13 +1599,8 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, iocb->aio_rw_flags)) return -EINVAL; - req->file = fget(iocb->aio_fildes); - if (unlikely(!req->file)) - return -EBADF; - if (unlikely(!req->file->f_op->fsync)) { - fput(req->file); + if (unlikely(!req->file->f_op->fsync)) return -EINVAL; - } req->datasync = datasync; INIT_WORK(&req->work, aio_fsync_work); @@ -1621,10 +1610,7 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask) { - struct file *file = iocb->poll.file; - aio_complete(iocb, mangle_poll(mask), 0); - fput(file); } static void aio_poll_complete_work(struct work_struct *work) @@ -1680,6 +1666,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct poll_iocb *req = container_of(wait, struct poll_iocb, wait); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); __poll_t mask = key_to_poll(key); + unsigned long flags; req->woken = true; @@ -1688,10 +1675,15 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (!(mask & req->events)) return 0; - /* try to complete the iocb inline if we can: */ - if (spin_trylock(&iocb->ki_ctx->ctx_lock)) { + /* + * Try to complete the iocb inline if we can. Use + * irqsave/irqrestore because not all filesystems (e.g. fuse) + * call this function with IRQs disabled and because IRQs + * have to be disabled before ctx_lock is obtained. + */ + if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { list_del(&iocb->ki_list); - spin_unlock(&iocb->ki_ctx->ctx_lock); + spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); list_del_init(&req->wait.entry); aio_poll_complete(iocb, mask); @@ -1743,9 +1735,6 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) INIT_WORK(&req->work, aio_poll_complete_work); req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; - req->file = fget(iocb->aio_fildes); - if (unlikely(!req->file)) - return -EBADF; req->head = NULL; req->woken = false; @@ -1788,10 +1777,8 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) spin_unlock_irq(&ctx->ctx_lock); out: - if (unlikely(apt.error)) { - fput(req->file); + if (unlikely(apt.error)) return apt.error; - } if (mask) aio_poll_complete(aiocb, mask); @@ -1829,6 +1816,11 @@ static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, if (unlikely(!req)) goto out_put_reqs_available; + req->ki_filp = fget(iocb->aio_fildes); + ret = -EBADF; + if (unlikely(!req->ki_filp)) + goto out_put_req; + if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an @@ -2199,11 +2191,11 @@ SYSCALL_DEFINE6(io_pgetevents_time32, #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id, - compat_long_t, min_nr, - compat_long_t, nr, - struct io_event __user *, events, - struct old_timespec32 __user *, timeout) +SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, + __s32, min_nr, + __s32, nr, + struct io_event __user *, events, + struct old_timespec32 __user *, timeout) { struct timespec64 t; int ret; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index ca9725f18e00..1fefd87eb4b4 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -29,97 +29,14 @@ #include <linux/uaccess.h> #include <asm/cacheflush.h> -#include <asm/a.out-core.h> static int load_aout_binary(struct linux_binprm *); static int load_aout_library(struct file*); -#ifdef CONFIG_COREDUMP -/* - * Routine writes a core dump image in the current directory. - * Currently only a stub-function. - * - * Note that setuid/setgid files won't make a core-dump if the uid/gid - * changed due to the set[u|g]id. It's enforced by the "current->mm->dumpable" - * field, which also makes sure the core-dumps won't be recursive if the - * dumping of the process results in another error.. - */ -static int aout_core_dump(struct coredump_params *cprm) -{ - mm_segment_t fs; - int has_dumped = 0; - void __user *dump_start; - int dump_size; - struct user dump; -#ifdef __alpha__ -# define START_DATA(u) ((void __user *)u.start_data) -#else -# define START_DATA(u) ((void __user *)((u.u_tsize << PAGE_SHIFT) + \ - u.start_code)) -#endif -# define START_STACK(u) ((void __user *)u.start_stack) - - fs = get_fs(); - set_fs(KERNEL_DS); - has_dumped = 1; - strncpy(dump.u_comm, current->comm, sizeof(dump.u_comm)); - dump.u_ar0 = offsetof(struct user, regs); - dump.signal = cprm->siginfo->si_signo; - aout_dump_thread(cprm->regs, &dump); - -/* If the size of the dump file exceeds the rlimit, then see what would happen - if we wrote the stack, but not the data area. */ - if ((dump.u_dsize + dump.u_ssize+1) * PAGE_SIZE > cprm->limit) - dump.u_dsize = 0; - -/* Make sure we have enough room to write the stack and data areas. */ - if ((dump.u_ssize + 1) * PAGE_SIZE > cprm->limit) - dump.u_ssize = 0; - -/* make sure we actually have a data and stack area to dump */ - set_fs(USER_DS); - if (!access_ok(START_DATA(dump), dump.u_dsize << PAGE_SHIFT)) - dump.u_dsize = 0; - if (!access_ok(START_STACK(dump), dump.u_ssize << PAGE_SHIFT)) - dump.u_ssize = 0; - - set_fs(KERNEL_DS); -/* struct user */ - if (!dump_emit(cprm, &dump, sizeof(dump))) - goto end_coredump; -/* Now dump all of the user data. Include malloced stuff as well */ - if (!dump_skip(cprm, PAGE_SIZE - sizeof(dump))) - goto end_coredump; -/* now we start writing out the user space info */ - set_fs(USER_DS); -/* Dump the data area */ - if (dump.u_dsize != 0) { - dump_start = START_DATA(dump); - dump_size = dump.u_dsize << PAGE_SHIFT; - if (!dump_emit(cprm, dump_start, dump_size)) - goto end_coredump; - } -/* Now prepare to dump the stack area */ - if (dump.u_ssize != 0) { - dump_start = START_STACK(dump); - dump_size = dump.u_ssize << PAGE_SHIFT; - if (!dump_emit(cprm, dump_start, dump_size)) - goto end_coredump; - } -end_coredump: - set_fs(fs); - return has_dumped; -} -#else -#define aout_core_dump NULL -#endif - static struct linux_binfmt aout_format = { .module = THIS_MODULE, .load_binary = load_aout_binary, .load_shlib = load_aout_library, - .core_dump = aout_core_dump, - .min_coredump = PAGE_SIZE }; #define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE) diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index d0078cbb718b..e996174cbfc0 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -14,13 +14,30 @@ #include <linux/err.h> #include <linux/fs.h> +static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } +static inline char *next_non_spacetab(char *first, const char *last) +{ + for (; first <= last; first++) + if (!spacetab(*first)) + return first; + return NULL; +} +static inline char *next_terminator(char *first, const char *last) +{ + for (; first <= last; first++) + if (spacetab(*first) || !*first) + return first; + return NULL; +} + static int load_script(struct linux_binprm *bprm) { const char *i_arg, *i_name; - char *cp; + char *cp, *buf_end; struct file *file; int retval; + /* Not ours to exec if we don't start with "#!". */ if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) return -ENOEXEC; @@ -33,23 +50,41 @@ static int load_script(struct linux_binprm *bprm) if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) return -ENOENT; - /* - * This section does the #! interpretation. - * Sorta complicated, but hopefully it will work. -TYT - */ - + /* Release since we are not mapping a binary into memory. */ allow_write_access(bprm->file); fput(bprm->file); bprm->file = NULL; - for (cp = bprm->buf+2;; cp++) { - if (cp >= bprm->buf + BINPRM_BUF_SIZE) + /* + * This section handles parsing the #! line into separate + * interpreter path and argument strings. We must be careful + * because bprm->buf is not yet guaranteed to be NUL-terminated + * (though the buffer will have trailing NUL padding when the + * file size was smaller than the buffer size). + * + * We do not want to exec a truncated interpreter path, so either + * we find a newline (which indicates nothing is truncated), or + * we find a space/tab/NUL after the interpreter path (which + * itself may be preceded by spaces/tabs). Truncating the + * arguments is fine: the interpreter can re-read the script to + * parse them on its own. + */ + buf_end = bprm->buf + sizeof(bprm->buf) - 1; + cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); + if (!cp) { + cp = next_non_spacetab(bprm->buf + 2, buf_end); + if (!cp) + return -ENOEXEC; /* Entire buf is spaces/tabs */ + /* + * If there is no later space/tab/NUL we must assume the + * interpreter path is truncated. + */ + if (!next_terminator(cp, buf_end)) return -ENOEXEC; - if (!*cp || (*cp == '\n')) - break; + cp = buf_end; } + /* NUL-terminate the buffer and any trailing spaces/tabs. */ *cp = '\0'; - while (cp > bprm->buf) { cp--; if ((*cp == ' ') || (*cp == '\t')) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 041c27ea8de1..f74193da0e09 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -616,7 +616,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, capsnap->size); spin_lock(&mdsc->snap_flush_lock); - list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); + if (list_empty(&ci->i_snap_flush_item)) + list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); spin_unlock(&mdsc->snap_flush_lock); return 1; /* caller may want to ceph_flush_snaps */ } diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 1e11a683f63d..322ce9686bdb 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -47,7 +47,7 @@ static int derive_key_aes(const u8 *master_key, tfm = NULL; goto out; } - crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); req = skcipher_request_alloc(tfm, GFP_NOFS); if (!req) { res = -ENOMEM; @@ -257,7 +257,7 @@ allocate_skcipher_for_mode(struct fscrypt_mode *mode, const u8 *raw_key, mode->friendly_name, crypto_skcipher_alg(tfm)->base.cra_driver_name); } - crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); err = crypto_skcipher_setkey(tfm, raw_key, mode->keysize); if (err) goto err_free_tfm; diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 76976d6e50f9..c98ad9777ad9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1089,12 +1089,12 @@ static void sctp_connect_to_sock(struct connection *con) * since O_NONBLOCK argument in connect() function does not work here, * then, we should restore the default value of this attribute. */ - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len, 0); memset(&tv, 0, sizeof(tv)); - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); if (result == -EINPROGRESS) diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 4dd842f72846..f664da55234e 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -610,7 +610,8 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat) full_alg_name); goto out_free; } - crypto_skcipher_set_flags(crypt_stat->tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(crypt_stat->tfm, + CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); rc = 0; out_free: kfree(full_alg_name); @@ -1590,7 +1591,7 @@ ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm, "[%s]; rc = [%d]\n", full_alg_name, rc); goto out; } - crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY); + crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS); if (*key_size == 0) *key_size = crypto_skcipher_default_keysize(*key_tfm); get_random_bytes(dummy_key, *key_size); diff --git a/fs/exec.c b/fs/exec.c index fb72d36f7823..74f3672146a7 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -932,7 +932,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, bytes = kernel_read(file, *buf + pos, i_size - pos, &pos); if (bytes < 0) { ret = bytes; - goto out; + goto out_free; } if (bytes == 0) @@ -1189,7 +1189,7 @@ no_thread_group: flush_itimer_signals(); #endif - if (atomic_read(&oldsighand->count) != 1) { + if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND @@ -1199,7 +1199,7 @@ no_thread_group: if (!newsighand) return -ENOMEM; - atomic_set(&newsighand->count, 1); + refcount_set(&newsighand->count, 1); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 712f00995390..5508baa11bb6 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -116,16 +116,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = file_write_and_wait_range(file, start, end); - if (ret) - return ret; - if (!journal) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL - }; - - ret = ext4_write_inode(inode, &wbc); + ret = __generic_file_fsync(file, start, end, datasync); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) @@ -133,6 +125,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } + ret = file_write_and_wait_range(file, start, end); + if (ret) + return ret; /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. diff --git a/fs/file.c b/fs/file.c index 3209ee271c41..a10487aa0a84 100644 --- a/fs/file.c +++ b/fs/file.c @@ -457,6 +457,7 @@ struct files_struct init_files = { .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), + .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index f15b4c57c4bd..78510ab91835 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -28,7 +28,6 @@ #include "util.h" #include "trans.h" #include "dir.h" -#include "lops.h" struct workqueue_struct *gfs2_freeze_wq; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 5bfaf381921a..b8830fda51e8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -733,7 +733,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, lh->lh_crc = cpu_to_be32(crc); gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags); log_flush_wait(sdp); } @@ -810,7 +810,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) gfs2_ordered_write(sdp); lops_before_commit(sdp, tr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, 0); if (sdp->sd_log_head != sdp->sd_log_flush_head) { log_flush_wait(sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 94dcab655bc0..2295042bc625 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -17,9 +17,7 @@ #include <linux/bio.h> #include <linux/fs.h> #include <linux/list_sort.h> -#include <linux/blkdev.h> -#include "bmap.h" #include "dir.h" #include "gfs2.h" #include "incore.h" @@ -195,6 +193,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, /** * gfs2_end_log_write - end of i/o to the log * @bio: The bio + * @error: Status of i/o request * * Each bio_vec contains either data from the pagecache or data * relating to the log itself. Here we iterate over the bio_vec @@ -231,19 +230,20 @@ static void gfs2_end_log_write(struct bio *bio) /** * gfs2_log_submit_bio - Submit any pending log bio * @biop: Address of the bio pointer - * @opf: REQ_OP | op_flags + * @op: REQ_OP + * @op_flags: req_flag_bits * * Submit any pending part-built or full bio to the block device. If * there is no pending bio, then this is a no-op. */ -void gfs2_log_submit_bio(struct bio **biop, int opf) +void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags) { struct bio *bio = *biop; if (bio) { struct gfs2_sbd *sdp = bio->bi_private; atomic_inc(&sdp->sd_log_in_flight); - bio->bi_opf = opf; + bio_set_op_attrs(bio, op, op_flags); submit_bio(bio); *biop = NULL; } @@ -304,7 +304,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno, nblk >>= sdp->sd_fsb2bb_shift; if (blkno == nblk && !flush) return bio; - gfs2_log_submit_bio(biop, op); + gfs2_log_submit_bio(biop, op, 0); } *biop = gfs2_log_alloc_bio(sdp, blkno, end_io); @@ -375,184 +375,6 @@ void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) gfs2_log_bmap(sdp)); } -/** - * gfs2_end_log_read - end I/O callback for reads from the log - * @bio: The bio - * - * Simply unlock the pages in the bio. The main thread will wait on them and - * process them in order as necessary. - */ - -static void gfs2_end_log_read(struct bio *bio) -{ - struct page *page; - struct bio_vec *bvec; - int i; - - bio_for_each_segment_all(bvec, bio, i) { - page = bvec->bv_page; - if (bio->bi_status) { - int err = blk_status_to_errno(bio->bi_status); - - SetPageError(page); - mapping_set_error(page->mapping, err); - } - unlock_page(page); - } - - bio_put(bio); -} - -/** - * gfs2_jhead_pg_srch - Look for the journal head in a given page. - * @jd: The journal descriptor - * @page: The page to look in - * - * Returns: 1 if found, 0 otherwise. - */ - -static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head, - struct page *page) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct gfs2_log_header_host uninitialized_var(lh); - void *kaddr = kmap_atomic(page); - unsigned int offset; - bool ret = false; - - for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { - if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { - if (lh.lh_sequence > head->lh_sequence) - *head = lh; - else { - ret = true; - break; - } - } - } - kunmap_atomic(kaddr); - return ret; -} - -/** - * gfs2_jhead_process_page - Search/cleanup a page - * @jd: The journal descriptor - * @index: Index of the page to look into - * @done: If set, perform only cleanup, else search and set if found. - * - * Find the page with 'index' in the journal's mapping. Search the page for - * the journal head if requested (cleanup == false). Release refs on the - * page so the page cache can reclaim it (put_page() twice). We grabbed a - * reference on this page two times, first when we did a find_or_create_page() - * to obtain the page to add it to the bio and second when we do a - * find_get_page() here to get the page to wait on while I/O on it is being - * completed. - * This function is also used to free up a page we might've grabbed but not - * used. Maybe we added it to a bio, but not submitted it for I/O. Or we - * submitted the I/O, but we already found the jhead so we only need to drop - * our references to the page. - */ - -static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index, - struct gfs2_log_header_host *head, - bool *done) -{ - struct page *page; - - page = find_get_page(jd->jd_inode->i_mapping, index); - wait_on_page_locked(page); - - if (PageError(page)) - *done = true; - - if (!*done) - *done = gfs2_jhead_pg_srch(jd, head, page); - - put_page(page); /* Once for find_get_page */ - put_page(page); /* Once more for find_or_create_page */ -} - -/** - * gfs2_find_jhead - find the head of a log - * @jd: The journal descriptor - * @head: The log descriptor for the head of the log is returned here - * - * Do a search of a journal by reading it in large chunks using bios and find - * the valid log entry with the highest sequence number. (i.e. the log head) - * - * Returns: 0 on success, errno otherwise - */ - -int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct address_space *mapping = jd->jd_inode->i_mapping; - struct gfs2_journal_extent *je; - u32 block, read_idx = 0, submit_idx = 0, index = 0; - int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; - int blocks_per_page = 1 << shift, sz, ret = 0; - struct bio *bio = NULL; - struct page *page; - bool done = false; - errseq_t since; - - memset(head, 0, sizeof(*head)); - if (list_empty(&jd->extent_list)) - gfs2_map_journal_extents(sdp, jd); - - since = filemap_sample_wb_err(mapping); - list_for_each_entry(je, &jd->extent_list, list) { - for (block = 0; block < je->blocks; block += blocks_per_page) { - index = (je->lblock + block) >> shift; - - page = find_or_create_page(mapping, index, GFP_NOFS); - if (!page) { - ret = -ENOMEM; - done = true; - goto out; - } - - if (bio) { - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - if (sz == PAGE_SIZE) - goto page_added; - submit_idx = index; - submit_bio(bio); - bio = NULL; - } - - bio = gfs2_log_alloc_bio(sdp, - je->dblock + (index << shift), - gfs2_end_log_read); - bio->bi_opf = REQ_OP_READ; - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - gfs2_assert_warn(sdp, sz == PAGE_SIZE); - -page_added: - if (submit_idx <= read_idx + BIO_MAX_PAGES) { - /* Keep at least one bio in flight */ - continue; - } - - gfs2_jhead_process_page(jd, read_idx++, head, &done); - if (done) - goto out; /* found */ - } - } - -out: - if (bio) - submit_bio(bio); - while (read_idx <= index) - gfs2_jhead_process_page(jd, read_idx++, head, &done); - - if (!ret) - ret = filemap_check_wb_err(mapping, since); - - return ret; -} - static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, u32 ld_length, u32 ld_data1) { diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 331160fc568b..711c4d89c063 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -30,10 +30,8 @@ extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp); extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, unsigned size, unsigned offset, u64 blkno); extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); -extern void gfs2_log_submit_bio(struct bio **biop, int opf); +extern void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); -extern int gfs2_find_jhead(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1179763f6370..b041cb8ae383 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -41,7 +41,6 @@ #include "dir.h" #include "meta_io.h" #include "trace_gfs2.h" -#include "lops.h" #define DO 0 #define UNDO 1 diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 7389e445a7a7..2dac43065382 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -182,6 +182,129 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk, } /** + * find_good_lh - find a good log header + * @jd: the journal + * @blk: the segment to start searching from + * @lh: the log header to fill in + * @forward: if true search forward in the log, else search backward + * + * Call get_log_header() to get a log header for a segment, but if the + * segment is bad, either scan forward or backward until we find a good one. + * + * Returns: errno + */ + +static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk, + struct gfs2_log_header_host *head) +{ + unsigned int orig_blk = *blk; + int error; + + for (;;) { + error = get_log_header(jd, *blk, head); + if (error <= 0) + return error; + + if (++*blk == jd->jd_blocks) + *blk = 0; + + if (*blk == orig_blk) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + } +} + +/** + * jhead_scan - make sure we've found the head of the log + * @jd: the journal + * @head: this is filled in with the log descriptor of the head + * + * At this point, seg and lh should be either the head of the log or just + * before. Scan forward until we find the head. + * + * Returns: errno + */ + +static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + unsigned int blk = head->lh_blkno; + struct gfs2_log_header_host lh; + int error; + + for (;;) { + if (++blk == jd->jd_blocks) + blk = 0; + + error = get_log_header(jd, blk, &lh); + if (error < 0) + return error; + if (error == 1) + continue; + + if (lh.lh_sequence == head->lh_sequence) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + if (lh.lh_sequence < head->lh_sequence) + break; + + *head = lh; + } + + return 0; +} + +/** + * gfs2_find_jhead - find the head of a log + * @jd: the journal + * @head: the log descriptor for the head of the log is returned here + * + * Do a binary search of a journal and find the valid log entry with the + * highest sequence number. (i.e. the log head) + * + * Returns: errno + */ + +int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + struct gfs2_log_header_host lh_1, lh_m; + u32 blk_1, blk_2, blk_m; + int error; + + blk_1 = 0; + blk_2 = jd->jd_blocks - 1; + + for (;;) { + blk_m = (blk_1 + blk_2) / 2; + + error = find_good_lh(jd, &blk_1, &lh_1); + if (error) + return error; + + error = find_good_lh(jd, &blk_m, &lh_m); + if (error) + return error; + + if (blk_1 == blk_m || blk_m == blk_2) + break; + + if (lh_1.lh_sequence <= lh_m.lh_sequence) + blk_1 = blk_m; + else + blk_2 = blk_m; + } + + error = jhead_scan(jd, &lh_1); + if (error) + return error; + + *head = lh_1; + + return error; +} + +/** * foreach_descriptor - go through the active part of the log * @jd: the journal * @start: the first log header in the active region diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 99575ab81202..11d81248be85 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -27,6 +27,8 @@ extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where); extern void gfs2_revoke_clean(struct gfs2_jdesc *jd); +extern int gfs2_find_jhead(struct gfs2_jdesc *jd, + struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait); extern void gfs2_recover_func(struct work_struct *work); extern int __get_log_header(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index d4b11c903971..ca71163ff7cf 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -45,7 +45,6 @@ #include "util.h" #include "sys.h" #include "xattr.h" -#include "lops.h" #define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 32920a10100e..b0eef008de67 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -530,7 +530,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) inode_lock(inode); /* protected by i_mutex */ - if (info->seals & F_SEAL_WRITE) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { inode_unlock(inode); return -EPERM; } @@ -859,6 +859,18 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, rc = migrate_huge_page_move_mapping(mapping, newpage, page); if (rc != MIGRATEPAGE_SUCCESS) return rc; + + /* + * page_private is subpool pointer in hugetlb pages. Transfer to + * new page. PagePrivate is not associated with page_private for + * hugetlb pages and can not be set here as only page_huge_active + * pages can be migrated. + */ + if (page_private(page)) { + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + } + if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); else diff --git a/fs/inode.c b/fs/inode.c index 0cd47fe0dbe5..e9d97add2b36 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -730,11 +730,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_REMOVED; } - /* - * Recently referenced inodes and inodes with many attached pages - * get one more pass. - */ - if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) { + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; @@ -2096,14 +2093,8 @@ EXPORT_SYMBOL(inode_dio_wait); void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { - unsigned int old_flags, new_flags; - WARN_ON_ONCE(flags & ~mask); - do { - old_flags = READ_ONCE(inode->i_flags); - new_flags = (old_flags & ~mask) | flags; - } while (unlikely(cmpxchg(&inode->i_flags, old_flags, - new_flags) != old_flags)); + set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index f8d5021a652e..ae948aaa4c53 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn) * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ +__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) +{ + struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); + struct kernfs_open_node *on = kn->attr.open; + + poll_wait(of->file, &on->poll, wait); + + if (of->event != atomic_read(&on->event)) + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + + return DEFAULT_POLLMASK; +} + static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); - struct kernfs_open_node *on = kn->attr.open; + __poll_t ret; if (!kernfs_get_active(kn)) - goto trigger; + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; - poll_wait(filp, &on->poll, wait); + if (kn->attr.ops->poll) + ret = kn->attr.ops->poll(of, wait); + else + ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); - - if (of->event != atomic_read(&on->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + return ret; } static void kernfs_notify_workfn(struct work_struct *work) diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 450eb388bae6..f3ac352699cf 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -196,8 +196,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, return dentry; knparent = find_next_ancestor(kn, NULL); - if (WARN_ON(!knparent)) + if (WARN_ON(!knparent)) { + dput(dentry); return ERR_PTR(-EINVAL); + } do { struct dentry *dtmp; @@ -206,8 +208,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, if (kn == knparent) return dentry; kntmp = find_next_ancestor(kn, knparent); - if (WARN_ON(!kntmp)) + if (WARN_ON(!kntmp)) { + dput(dentry); return ERR_PTR(-EINVAL); + } dtmp = lookup_one_len_unlocked(kntmp->name, dentry, strlen(kntmp->name)); dput(dentry); diff --git a/fs/locks.c b/fs/locks.c index ff6af2c32601..eaa1cfaf73b0 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1058,7 +1058,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) return -ENOMEM; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; @@ -1100,7 +1100,7 @@ find_conflict: out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -1138,7 +1138,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, new_fl2 = locks_alloc_lock(); } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If @@ -1312,7 +1312,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); /* * Free any unused locks. */ @@ -1584,7 +1584,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1636,13 +1636,13 @@ restart: locks_insert_block(fl, new_fl, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_blocker, break_time); - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); @@ -1659,7 +1659,7 @@ restart: } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1729,7 +1729,7 @@ int fcntl_getlease(struct file *filp) ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { @@ -1739,7 +1739,7 @@ int fcntl_getlease(struct file *filp) break; } spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } @@ -1813,7 +1813,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg, lease->fl_flags); @@ -1884,7 +1884,7 @@ out_setup: lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); @@ -1907,7 +1907,7 @@ static int generic_delete_lease(struct file *filp, void *owner) return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && @@ -1920,7 +1920,7 @@ static int generic_delete_lease(struct file *filp, void *owner) if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } @@ -2643,13 +2643,13 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) if (list_empty(&ctx->flc_lease)) return; - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) if (filp == fl->fl_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } diff --git a/fs/namespace.c b/fs/namespace.c index a677b59efd74..c4e83d94840c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2698,7 +2698,6 @@ static long exact_copy_from_user(void *to, const void __user * from, if (!access_ok(from, n)) return n; - current->kernel_uaccess_faults_ok++; while (n) { if (__get_user(c, f)) { memset(t, 0, n); @@ -2708,7 +2707,6 @@ static long exact_copy_from_user(void *to, const void __user * from, f++; n--; } - current->kernel_uaccess_faults_ok--; return n; } @@ -2746,7 +2744,7 @@ void *copy_mount_options(const void __user * data) char *copy_mount_string(const void __user *data) { - return data ? strndup_user(data, PAGE_SIZE) : NULL; + return data ? strndup_user(data, PATH_MAX) : NULL; } /* diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 3f23b6840547..bf34ddaa2ad7 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -44,6 +44,7 @@ #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> +#include <keys/request_key_auth-type.h> #include <linux/module.h> #include "internal.h" @@ -59,7 +60,7 @@ static struct key_type key_type_id_resolver_legacy; struct idmap_legacy_upcalldata { struct rpc_pipe_msg pipe_msg; struct idmap_msg idmap_msg; - struct key_construction *key_cons; + struct key *authkey; struct idmap *idmap; }; @@ -384,7 +385,7 @@ static const match_table_t nfs_idmap_tokens = { { Opt_find_err, NULL } }; -static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); +static int nfs_idmap_legacy_upcall(struct key *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); static void idmap_release_pipe(struct inode *); @@ -549,11 +550,12 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, static void nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret) { - struct key_construction *cons = idmap->idmap_upcall_data->key_cons; + struct key *authkey = idmap->idmap_upcall_data->authkey; kfree(idmap->idmap_upcall_data); idmap->idmap_upcall_data = NULL; - complete_request_key(cons, ret); + complete_request_key(authkey, ret); + key_put(authkey); } static void @@ -563,15 +565,14 @@ nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret) nfs_idmap_complete_pipe_upcall_locked(idmap, ret); } -static int nfs_idmap_legacy_upcall(struct key_construction *cons, - const char *op, - void *aux) +static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) { struct idmap_legacy_upcalldata *data; + struct request_key_auth *rka = get_request_key_auth(authkey); struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; - struct key *key = cons->key; + struct key *key = rka->target_key; int ret = -ENOKEY; if (!aux) @@ -586,7 +587,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, msg = &data->pipe_msg; im = &data->idmap_msg; data->idmap = idmap; - data->key_cons = cons; + data->authkey = key_get(authkey); ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) @@ -604,7 +605,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, out2: kfree(data); out1: - complete_request_key(cons, ret); + complete_request_key(authkey, ret); return ret; } @@ -651,9 +652,10 @@ out: static ssize_t idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { + struct request_key_auth *rka; struct rpc_inode *rpci = RPC_I(file_inode(filp)); struct idmap *idmap = (struct idmap *)rpci->private; - struct key_construction *cons; + struct key *authkey; struct idmap_msg im; size_t namelen_in; int ret = -ENOKEY; @@ -665,7 +667,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (idmap->idmap_upcall_data == NULL) goto out_noupcall; - cons = idmap->idmap_upcall_data->key_cons; + authkey = idmap->idmap_upcall_data->authkey; + rka = get_request_key_auth(authkey); if (mlen != sizeof(im)) { ret = -ENOSPC; @@ -690,9 +693,9 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) ret = nfs_idmap_read_and_verify_message(&im, &idmap->idmap_upcall_data->idmap_msg, - cons->key, cons->authkey); + rka->target_key, authkey); if (ret >= 0) { - key_set_timeout(cons->key, nfs_idmap_cache_timeout); + key_set_timeout(rka->target_key, nfs_idmap_cache_timeout); ret = mlen; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f12cb31a41e5..d09c9f878141 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -238,9 +238,9 @@ out: } /* A writeback failed: mark the page as bad, and invalidate the page cache */ -static void nfs_set_pageerror(struct page *page) +static void nfs_set_pageerror(struct address_space *mapping) { - nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page)); + nfs_zap_mapping(mapping->host, mapping); } /* @@ -994,7 +994,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { - nfs_set_pageerror(req->wb_page); + nfs_set_pageerror(page_file_mapping(req->wb_page)); nfs_context_set_write_error(req->wb_context, hdr->error); goto remove_req; } @@ -1348,7 +1348,8 @@ int nfs_updatepage(struct file *file, struct page *page, unsigned int offset, unsigned int count) { struct nfs_open_context *ctx = nfs_file_open_context(file); - struct inode *inode = page_file_mapping(page)->host; + struct address_space *mapping = page_file_mapping(page); + struct inode *inode = mapping->host; int status = 0; nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); @@ -1366,7 +1367,7 @@ int nfs_updatepage(struct file *file, struct page *page, status = nfs_writepage_setup(ctx, page, offset, count); if (status < 0) - nfs_set_pageerror(page); + nfs_set_pageerror(mapping); else __set_page_dirty_nobuffers(page); out: diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index b33f9785b756..72a7681f4046 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1239,8 +1239,8 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; - nn->nfsd4_lease = 45; /* default lease time */ - nn->nfsd4_grace = 45; + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; nn->clverifier_counter = prandom_u32(); nn->clientid_counter = prandom_u32(); diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index d1cbb27808e2..6f0999015a44 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7532,10 +7532,11 @@ static int ocfs2_trim_group(struct super_block *sb, return count; } -int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) +static +int ocfs2_trim_mainbm(struct super_block *sb, struct fstrim_range *range) { struct ocfs2_super *osb = OCFS2_SB(sb); - u64 start, len, trimmed, first_group, last_group, group; + u64 start, len, trimmed = 0, first_group, last_group = 0, group = 0; int ret, cnt; u32 first_bit, last_bit, minlen; struct buffer_head *main_bm_bh = NULL; @@ -7543,7 +7544,6 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) struct buffer_head *gd_bh = NULL; struct ocfs2_dinode *main_bm; struct ocfs2_group_desc *gd = NULL; - struct ocfs2_trim_fs_info info, *pinfo = NULL; start = range->start >> osb->s_clustersize_bits; len = range->len >> osb->s_clustersize_bits; @@ -7552,6 +7552,9 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) if (minlen >= osb->bitmap_cpg || range->len < sb->s_blocksize) return -EINVAL; + trace_ocfs2_trim_mainbm(start, len, minlen); + +next_group: main_bm_inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); @@ -7570,64 +7573,34 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) } main_bm = (struct ocfs2_dinode *)main_bm_bh->b_data; - if (start >= le32_to_cpu(main_bm->i_clusters)) { - ret = -EINVAL; - goto out_unlock; - } - - len = range->len >> osb->s_clustersize_bits; - if (start + len > le32_to_cpu(main_bm->i_clusters)) - len = le32_to_cpu(main_bm->i_clusters) - start; - - trace_ocfs2_trim_fs(start, len, minlen); - - ocfs2_trim_fs_lock_res_init(osb); - ret = ocfs2_trim_fs_lock(osb, NULL, 1); - if (ret < 0) { - if (ret != -EAGAIN) { - mlog_errno(ret); - ocfs2_trim_fs_lock_res_uninit(osb); + /* + * Do some check before trim the first group. + */ + if (!group) { + if (start >= le32_to_cpu(main_bm->i_clusters)) { + ret = -EINVAL; goto out_unlock; } - mlog(ML_NOTICE, "Wait for trim on device (%s) to " - "finish, which is running from another node.\n", - osb->dev_str); - ret = ocfs2_trim_fs_lock(osb, &info, 0); - if (ret < 0) { - mlog_errno(ret); - ocfs2_trim_fs_lock_res_uninit(osb); - goto out_unlock; - } + if (start + len > le32_to_cpu(main_bm->i_clusters)) + len = le32_to_cpu(main_bm->i_clusters) - start; - if (info.tf_valid && info.tf_success && - info.tf_start == start && info.tf_len == len && - info.tf_minlen == minlen) { - /* Avoid sending duplicated trim to a shared device */ - mlog(ML_NOTICE, "The same trim on device (%s) was " - "just done from node (%u), return.\n", - osb->dev_str, info.tf_nodenum); - range->len = info.tf_trimlen; - goto out_trimunlock; - } + /* + * Determine first and last group to examine based on + * start and len + */ + first_group = ocfs2_which_cluster_group(main_bm_inode, start); + if (first_group == osb->first_cluster_group_blkno) + first_bit = start; + else + first_bit = start - ocfs2_blocks_to_clusters(sb, + first_group); + last_group = ocfs2_which_cluster_group(main_bm_inode, + start + len - 1); + group = first_group; } - info.tf_nodenum = osb->node_num; - info.tf_start = start; - info.tf_len = len; - info.tf_minlen = minlen; - - /* Determine first and last group to examine based on start and len */ - first_group = ocfs2_which_cluster_group(main_bm_inode, start); - if (first_group == osb->first_cluster_group_blkno) - first_bit = start; - else - first_bit = start - ocfs2_blocks_to_clusters(sb, first_group); - last_group = ocfs2_which_cluster_group(main_bm_inode, start + len - 1); - last_bit = osb->bitmap_cpg; - - trimmed = 0; - for (group = first_group; group <= last_group;) { + do { if (first_bit + len >= osb->bitmap_cpg) last_bit = osb->bitmap_cpg; else @@ -7659,21 +7632,81 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) group = ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg); else group += ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg); - } - range->len = trimmed * sb->s_blocksize; + } while (0); - info.tf_trimlen = range->len; - info.tf_success = (ret ? 0 : 1); - pinfo = &info; -out_trimunlock: - ocfs2_trim_fs_unlock(osb, pinfo); - ocfs2_trim_fs_lock_res_uninit(osb); out_unlock: ocfs2_inode_unlock(main_bm_inode, 0); brelse(main_bm_bh); + main_bm_bh = NULL; out_mutex: inode_unlock(main_bm_inode); iput(main_bm_inode); + + /* + * If all the groups trim are not done or failed, but we should release + * main_bm related locks for avoiding the current IO starve, then go to + * trim the next group + */ + if (ret >= 0 && group <= last_group) + goto next_group; out: + range->len = trimmed * sb->s_blocksize; + return ret; +} + +int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) +{ + int ret; + struct ocfs2_super *osb = OCFS2_SB(sb); + struct ocfs2_trim_fs_info info, *pinfo = NULL; + + ocfs2_trim_fs_lock_res_init(osb); + + trace_ocfs2_trim_fs(range->start, range->len, range->minlen); + + ret = ocfs2_trim_fs_lock(osb, NULL, 1); + if (ret < 0) { + if (ret != -EAGAIN) { + mlog_errno(ret); + ocfs2_trim_fs_lock_res_uninit(osb); + return ret; + } + + mlog(ML_NOTICE, "Wait for trim on device (%s) to " + "finish, which is running from another node.\n", + osb->dev_str); + ret = ocfs2_trim_fs_lock(osb, &info, 0); + if (ret < 0) { + mlog_errno(ret); + ocfs2_trim_fs_lock_res_uninit(osb); + return ret; + } + + if (info.tf_valid && info.tf_success && + info.tf_start == range->start && + info.tf_len == range->len && + info.tf_minlen == range->minlen) { + /* Avoid sending duplicated trim to a shared device */ + mlog(ML_NOTICE, "The same trim on device (%s) was " + "just done from node (%u), return.\n", + osb->dev_str, info.tf_nodenum); + range->len = info.tf_trimlen; + goto out; + } + } + + info.tf_nodenum = osb->node_num; + info.tf_start = range->start; + info.tf_len = range->len; + info.tf_minlen = range->minlen; + + ret = ocfs2_trim_mainbm(sb, range); + + info.tf_trimlen = range->len; + info.tf_success = (ret < 0 ? 0 : 1); + pinfo = &info; +out: + ocfs2_trim_fs_unlock(osb, pinfo); + ocfs2_trim_fs_lock_res_uninit(osb); return ret; } diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 0e4166cc23a0..4ac775e32240 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -621,13 +621,15 @@ static void o2nm_node_group_drop_item(struct config_group *group, struct o2nm_node *node = to_o2nm_node(item); struct o2nm_cluster *cluster = to_o2nm_cluster(group->cg_item.ci_parent); - o2net_disconnect_node(node); + if (cluster->cl_nodes[node->nd_num] == node) { + o2net_disconnect_node(node); - if (cluster->cl_has_local && - (cluster->cl_local_node == node->nd_num)) { - cluster->cl_has_local = 0; - cluster->cl_local_node = O2NM_INVALID_NODE_NUM; - o2net_stop_listening(node); + if (cluster->cl_has_local && + (cluster->cl_local_node == node->nd_num)) { + cluster->cl_has_local = 0; + cluster->cl_local_node = O2NM_INVALID_NODE_NUM; + o2net_stop_listening(node); + } } /* XXX call into net to stop this node from trading messages */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 7c835824247e..af405586c5b1 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -686,6 +686,9 @@ void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb) { struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres; + /* Only one trimfs thread are allowed to work at the same time. */ + mutex_lock(&osb->obs_trim_fs_mutex); + ocfs2_lock_res_init_once(lockres); ocfs2_build_lock_name(OCFS2_LOCK_TYPE_TRIM_FS, 0, 0, lockres->l_name); ocfs2_lock_res_init_common(osb, lockres, OCFS2_LOCK_TYPE_TRIM_FS, @@ -698,6 +701,8 @@ void ocfs2_trim_fs_lock_res_uninit(struct ocfs2_super *osb) ocfs2_simple_drop_lockres(osb, lockres); ocfs2_lock_res_free(lockres); + + mutex_unlock(&osb->obs_trim_fs_mutex); } static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res, diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 4f86ac0027b5..1f029fbe8b8d 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -407,6 +407,7 @@ struct ocfs2_super struct ocfs2_lock_res osb_rename_lockres; struct ocfs2_lock_res osb_nfs_sync_lockres; struct ocfs2_lock_res osb_trim_fs_lockres; + struct mutex obs_trim_fs_mutex; struct ocfs2_dlm_debug *osb_dlm_debug; struct dentry *osb_debug_root; diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 2ee76a90ba8f..dc4bce1649c1 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -712,6 +712,8 @@ TRACE_EVENT(ocfs2_trim_extent, DEFINE_OCFS2_ULL_UINT_UINT_UINT_EVENT(ocfs2_trim_group); +DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_mainbm); + DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_fs); /* End of trace events for fs/ocfs2/alloc.c. */ diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index d7407994f308..ea0756d83250 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -55,7 +55,7 @@ struct ocfs2_slot_info { unsigned int si_blocks; struct buffer_head **si_bh; unsigned int si_num_slots; - struct ocfs2_slot *si_slots; + struct ocfs2_slot si_slots[]; }; @@ -420,9 +420,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb) struct inode *inode = NULL; struct ocfs2_slot_info *si; - si = kzalloc(sizeof(struct ocfs2_slot_info) + - (sizeof(struct ocfs2_slot) * osb->max_slots), - GFP_KERNEL); + si = kzalloc(struct_size(si, si_slots, osb->max_slots), GFP_KERNEL); if (!si) { status = -ENOMEM; mlog_errno(status); @@ -431,8 +429,6 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb) si->si_extended = ocfs2_uses_extended_slot_map(osb); si->si_num_slots = osb->max_slots; - si->si_slots = (struct ocfs2_slot *)((char *)si + - sizeof(struct ocfs2_slot_info)); inode = ocfs2_get_system_file_inode(osb, SLOT_MAP_SYSTEM_INODE, OCFS2_INVALID_SLOT); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 3415e0b09398..96ae7cedd487 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1847,6 +1847,8 @@ static int ocfs2_mount_volume(struct super_block *sb) if (ocfs2_is_hard_readonly(osb)) goto leave; + mutex_init(&osb->obs_trim_fs_mutex); + status = ocfs2_dlm_init(osb); if (status < 0) { mlog_errno(status); diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index a5a2fe76568f..b094d3d79354 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -398,8 +398,6 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter loff_t pos = iocb->ki_pos; ssize_t rc = 0; - BUG_ON(iocb->private); - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n"); orangefs_stats.reads++; @@ -416,8 +414,6 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite loff_t pos; ssize_t rc; - BUG_ON(iocb->private); - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n"); inode_lock(file->f_mapping->host); diff --git a/fs/pipe.c b/fs/pipe.c index bdc5d3c0977d..51d5fd8840ab 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -140,8 +140,7 @@ static int anon_pipe_buf_steal(struct pipe_inode_info *pipe, struct page *page = buf->page; if (page_count(page) == 1) { - if (memcg_kmem_enabled()) - memcg_kmem_uncharge(page, 0); + memcg_kmem_uncharge(page, 0); __SetPageLocked(page); return 0; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 9d428d5a0ac8..2edbb657f859 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -343,28 +343,28 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #endif - seq_printf(m, "\nSpeculation_Store_Bypass:\t"); + seq_puts(m, "\nSpeculation_Store_Bypass:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { case -EINVAL: - seq_printf(m, "unknown"); + seq_puts(m, "unknown"); break; case PR_SPEC_NOT_AFFECTED: - seq_printf(m, "not vulnerable"); + seq_puts(m, "not vulnerable"); break; case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: - seq_printf(m, "thread force mitigated"); + seq_puts(m, "thread force mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_DISABLE: - seq_printf(m, "thread mitigated"); + seq_puts(m, "thread mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_ENABLE: - seq_printf(m, "thread vulnerable"); + seq_puts(m, "thread vulnerable"); break; case PR_SPEC_DISABLE: - seq_printf(m, "globally mitigated"); + seq_puts(m, "globally mitigated"); break; default: - seq_printf(m, "vulnerable"); + seq_puts(m, "vulnerable"); break; } seq_putc(m, '\n'); diff --git a/fs/proc/base.c b/fs/proc/base.c index 633a63462573..511b279ec69c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -456,7 +456,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { if (unlikely(!sched_info_on())) - seq_printf(m, "0 0 0\n"); + seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, @@ -1086,10 +1086,6 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) task_lock(p); if (!p->vfork_done && process_shares_mm(p, mm)) { - pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n", - task_pid_nr(p), p->comm, - p->signal->oom_score_adj, oom_adj, - task_pid_nr(task), task->comm); p->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) p->signal->oom_score_adj_min = (short)oom_adj; @@ -3165,7 +3161,7 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry, return d_splice_alias(inode, dentry); } -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) +struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 95b14196f284..4fc5a9b68f76 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -162,7 +162,7 @@ extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struc extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); extern int proc_pid_readdir(struct file *, struct dir_context *); -extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int); +struct dentry *proc_pid_lookup(struct dentry *, unsigned int); extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ diff --git a/fs/proc/page.c b/fs/proc/page.c index 40b05e0d4274..544d1ee15aee 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -152,8 +152,8 @@ u64 stable_page_flags(struct page *page) else if (page_count(page) == 0 && is_free_buddy_page(page)) u |= 1 << KPF_BUDDY; - if (PageBalloon(page)) - u |= 1 << KPF_BALLOON; + if (PageOffline(page)) + u |= 1 << KPF_OFFLINE; if (PageTable(page)) u |= 1 << KPF_PGTABLE; diff --git a/fs/proc/root.c b/fs/proc/root.c index f4b1a9d2eca6..621e6ec322ca 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -154,7 +154,7 @@ static int proc_root_getattr(const struct path *path, struct kstat *stat, static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { - if (!proc_pid_lookup(dir, dentry, flags)) + if (!proc_pid_lookup(dentry, flags)) return NULL; return proc_lookup(dir, dentry, flags); diff --git a/fs/proc/self.c b/fs/proc/self.c index 127265e5c55f..57c0a1047250 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -38,6 +38,7 @@ int proc_setup_self(struct super_block *s) struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *self; + int ret = -ENOMEM; inode_lock(root_inode); self = d_alloc_name(s->s_root, "self"); @@ -51,20 +52,19 @@ int proc_setup_self(struct super_block *s) inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_self_inode_operations; d_add(self, inode); + ret = 0; } else { dput(self); - self = ERR_PTR(-ENOMEM); } - } else { - self = ERR_PTR(-ENOMEM); } inode_unlock(root_inode); - if (IS_ERR(self)) { + + if (ret) pr_err("proc_fill_super: can't allocate /proc/self\n"); - return PTR_ERR(self); - } - ns->proc_self = self; - return 0; + else + ns->proc_self = self; + + return ret; } void __init proc_self_init(void) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 535eda7857cf..80c305f206bb 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -23,21 +23,21 @@ #ifdef arch_idle_time -static u64 get_idle_time(int cpu) +static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle; - idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle = kcs->cpustat[CPUTIME_IDLE]; if (cpu_online(cpu) && !nr_iowait_cpu(cpu)) idle += arch_idle_time(cpu); return idle; } -static u64 get_iowait_time(int cpu) +static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait; - iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + iowait = kcs->cpustat[CPUTIME_IOWAIT]; if (cpu_online(cpu) && nr_iowait_cpu(cpu)) iowait += arch_idle_time(cpu); return iowait; @@ -45,7 +45,7 @@ static u64 get_iowait_time(int cpu) #else -static u64 get_idle_time(int cpu) +static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; @@ -54,14 +54,14 @@ static u64 get_idle_time(int cpu) if (idle_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.idle */ - idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle = kcs->cpustat[CPUTIME_IDLE]; else idle = idle_usecs * NSEC_PER_USEC; return idle; } -static u64 get_iowait_time(int cpu) +static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait, iowait_usecs = -1ULL; @@ -70,7 +70,7 @@ static u64 get_iowait_time(int cpu) if (iowait_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */ - iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + iowait = kcs->cpustat[CPUTIME_IOWAIT]; else iowait = iowait_usecs * NSEC_PER_USEC; @@ -79,6 +79,31 @@ static u64 get_iowait_time(int cpu) #endif +static void show_irq_gap(struct seq_file *p, unsigned int gap) +{ + static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0"; + + while (gap > 0) { + unsigned int inc; + + inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2); + seq_write(p, zeros, 2 * inc); + gap -= inc; + } +} + +static void show_all_irqs(struct seq_file *p) +{ + unsigned int i, next = 0; + + for_each_active_irq(i) { + show_irq_gap(p, i - next); + seq_put_decimal_ull(p, " ", kstat_irqs_usr(i)); + next = i + 1; + } + show_irq_gap(p, nr_irqs - next); +} + static int show_stat(struct seq_file *p, void *v) { int i, j; @@ -95,16 +120,18 @@ static int show_stat(struct seq_file *p, void *v) getboottime64(&boottime); for_each_possible_cpu(i) { - user += kcpustat_cpu(i).cpustat[CPUTIME_USER]; - nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE]; - system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; - idle += get_idle_time(i); - iowait += get_iowait_time(i); - irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; - softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; - steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; - guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; - guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + struct kernel_cpustat *kcs = &kcpustat_cpu(i); + + user += kcs->cpustat[CPUTIME_USER]; + nice += kcs->cpustat[CPUTIME_NICE]; + system += kcs->cpustat[CPUTIME_SYSTEM]; + idle += get_idle_time(kcs, i); + iowait += get_iowait_time(kcs, i); + irq += kcs->cpustat[CPUTIME_IRQ]; + softirq += kcs->cpustat[CPUTIME_SOFTIRQ]; + steal += kcs->cpustat[CPUTIME_STEAL]; + guest += kcs->cpustat[CPUTIME_GUEST]; + guest_nice += kcs->cpustat[CPUTIME_GUEST_NICE]; sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); @@ -130,17 +157,19 @@ static int show_stat(struct seq_file *p, void *v) seq_putc(p, '\n'); for_each_online_cpu(i) { + struct kernel_cpustat *kcs = &kcpustat_cpu(i); + /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ - user = kcpustat_cpu(i).cpustat[CPUTIME_USER]; - nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE]; - system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; - idle = get_idle_time(i); - iowait = get_iowait_time(i); - irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; - softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; - steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; - guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; - guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + user = kcs->cpustat[CPUTIME_USER]; + nice = kcs->cpustat[CPUTIME_NICE]; + system = kcs->cpustat[CPUTIME_SYSTEM]; + idle = get_idle_time(kcs, i); + iowait = get_iowait_time(kcs, i); + irq = kcs->cpustat[CPUTIME_IRQ]; + softirq = kcs->cpustat[CPUTIME_SOFTIRQ]; + steal = kcs->cpustat[CPUTIME_STEAL]; + guest = kcs->cpustat[CPUTIME_GUEST]; + guest_nice = kcs->cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d", i); seq_put_decimal_ull(p, " ", nsec_to_clock_t(user)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); @@ -156,9 +185,7 @@ static int show_stat(struct seq_file *p, void *v) } seq_put_decimal_ull(p, "intr ", (unsigned long long)sum); - /* sum again ? it could be updated? */ - for_each_irq_nr(j) - seq_put_decimal_ull(p, " ", kstat_irqs_usr(j)); + show_all_irqs(p); seq_printf(p, "\nctxt %llu\n" diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f0ec9edab2f3..beccb0b1d57c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -423,7 +423,7 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty) + bool compound, bool young, bool dirty, bool locked) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -450,24 +450,31 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, else mss->private_clean += size; mss->pss += (u64)size << PSS_SHIFT; + if (locked) + mss->pss_locked += (u64)size << PSS_SHIFT; return; } for (i = 0; i < nr; i++, page++) { int mapcount = page_mapcount(page); + unsigned long pss = (PAGE_SIZE << PSS_SHIFT); if (mapcount >= 2) { if (dirty || PageDirty(page)) mss->shared_dirty += PAGE_SIZE; else mss->shared_clean += PAGE_SIZE; - mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; + mss->pss += pss / mapcount; + if (locked) + mss->pss_locked += pss / mapcount; } else { if (dirty || PageDirty(page)) mss->private_dirty += PAGE_SIZE; else mss->private_clean += PAGE_SIZE; - mss->pss += PAGE_SIZE << PSS_SHIFT; + mss->pss += pss; + if (locked) + mss->pss_locked += pss; } } } @@ -490,6 +497,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; if (pte_present(*pte)) { @@ -532,7 +540,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte)); + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -541,6 +549,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page; /* FOLL_DUMP will return -EFAULT on huge zero page */ @@ -555,7 +564,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else VM_BUG_ON_PAGE(1, page); - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd)); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -737,11 +746,8 @@ static void smap_gather_stats(struct vm_area_struct *vma, } } #endif - /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); - if (vma->vm_flags & VM_LOCKED) - mss->pss_locked += mss->pss; } #define SEQ_PUT_DEC(str, val) \ @@ -942,10 +948,12 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, pte_t ptent = *pte; if (pte_present(ptent)) { - ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte); - ptent = pte_wrprotect(ptent); + pte_t old_pte; + + old_pte = ptep_modify_prot_start(vma, addr, pte); + ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); - ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent); + ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); } else if (is_swap_pte(ptent)) { ptent = pte_swp_clear_soft_dirty(ptent); set_pte_at(vma->vm_mm, addr, pte, ptent); diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 0b63d68dedb2..36bf0f2e102e 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -64,7 +64,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) else bytes += kobjsize(current->files); - if (current->sighand && atomic_read(¤t->sighand->count) > 1) + if (current->sighand && refcount_read(¤t->sighand->count) > 1) sbytes += kobjsize(current->sighand); else bytes += kobjsize(current->sighand); @@ -178,7 +178,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) seq_file_path(m, file, ""); } else if (mm && is_stack(vma)) { seq_pad(m, ' '); - seq_printf(m, "[stack]"); + seq_puts(m, "[stack]"); } seq_putc(m, '\n'); diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index b905010ca9eb..f61ae53533f5 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -38,6 +38,7 @@ int proc_setup_thread_self(struct super_block *s) struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *thread_self; + int ret = -ENOMEM; inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); @@ -51,20 +52,19 @@ int proc_setup_thread_self(struct super_block *s) inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_thread_self_inode_operations; d_add(thread_self, inode); + ret = 0; } else { dput(thread_self); - thread_self = ERR_PTR(-ENOMEM); } - } else { - thread_self = ERR_PTR(-ENOMEM); } inode_unlock(root_inode); - if (IS_ERR(thread_self)) { + + if (ret) pr_err("proc_fill_super: can't allocate /proc/thread_self\n"); - return PTR_ERR(thread_self); - } - ns->proc_thread_self = thread_self; - return 0; + else + ns->proc_thread_self = thread_self; + + return ret; } void __init proc_thread_self_init(void) diff --git a/fs/read_write.c b/fs/read_write.c index ff3c5e6f87cf..30df848b7451 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -426,7 +426,7 @@ ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) ssize_t result; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ result = vfs_read(file, (void __user *)buf, count, pos); set_fs(old_fs); @@ -499,7 +499,7 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t return -EINVAL; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); p = (__force const char __user *)buf; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; @@ -521,7 +521,7 @@ ssize_t kernel_write(struct file *file, const void *buf, size_t count, ssize_t res; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ res = vfs_write(file, (__force const char __user *)buf, count, pos); set_fs(old_fs); diff --git a/fs/select.c b/fs/select.c index d0f35dbc0e8f..6cbc9ff56ba0 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1379,7 +1379,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp, #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, +COMPAT_SYSCALL_DEFINE6(pselect6_time32, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, struct old_timespec32 __user *, tsp, void __user *, sig) { @@ -1402,7 +1402,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, #endif #if defined(CONFIG_COMPAT_32BIT_TIME) -COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, +COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { diff --git a/fs/splice.c b/fs/splice.c index de2ede048473..6489fb9436e4 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -357,7 +357,7 @@ static ssize_t kernel_readv(struct file *file, const struct kvec *vec, ssize_t res; old_fs = get_fs(); - set_fs(get_ds()); + set_fs(KERNEL_DS); /* The cast to a user pointer is valid due to the set_fs() */ res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0); set_fs(old_fs); @@ -1123,6 +1123,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, if (ipipe == opipe) return -EINVAL; + if ((in->f_flags | out->f_flags) & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + return splice_pipe_to_pipe(ipipe, opipe, len, flags); } @@ -1148,6 +1151,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, if (unlikely(ret < 0)) return ret; + if (in->f_flags & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + file_start_write(out); ret = do_splice_from(ipipe, out, &offset, len, flags); file_end_write(out); @@ -1172,6 +1178,9 @@ static long do_splice(struct file *in, loff_t __user *off_in, offset = in->f_pos; } + if (out->f_flags & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + pipe_lock(opipe); ret = wait_for_space(opipe, flags); if (!ret) @@ -1717,6 +1726,9 @@ static long do_tee(struct file *in, struct file *out, size_t len, * copying the data. */ if (ipipe && opipe && ipipe != opipe) { + if ((in->f_flags | out->f_flags) & O_NONBLOCK) + flags |= SPLICE_F_NONBLOCK; + /* * Keep going, unless we encounter an error. The ipipe/opipe * ordering doesn't really matter. diff --git a/fs/timerfd.c b/fs/timerfd.c index 803ca070d42e..6a6fc8aa1de7 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -560,7 +560,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, +SYSCALL_DEFINE4(timerfd_settime32, int, ufd, int, flags, const struct old_itimerspec32 __user *, utmr, struct old_itimerspec32 __user *, otmr) { @@ -577,7 +577,7 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, return ret; } -COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd, +SYSCALL_DEFINE2(timerfd_gettime32, int, ufd, struct old_itimerspec32 __user *, otmr) { struct itimerspec64 kotmr; diff --git a/fs/utimes.c b/fs/utimes.c index bdcf2daf39c1..350c9c16ace1 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -224,8 +224,8 @@ SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) * of sys_utimes. */ #ifdef __ARCH_WANT_SYS_UTIME32 -COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, - struct old_utimbuf32 __user *, t) +SYSCALL_DEFINE2(utime32, const char __user *, filename, + struct old_utimbuf32 __user *, t) { struct timespec64 tv[2]; @@ -240,7 +240,7 @@ COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, } #endif -COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) +SYSCALL_DEFINE4(utimensat_time32, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) { struct timespec64 tv[2]; @@ -276,14 +276,14 @@ static long do_compat_futimesat(unsigned int dfd, const char __user *filename, return do_utimes(dfd, filename, t ? tv : NULL, 0); } -COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, +SYSCALL_DEFINE3(futimesat_time32, unsigned int, dfd, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(dfd, filename, t); } -COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct old_timeval32 __user *, t) +SYSCALL_DEFINE2(utimes_time32, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(AT_FDCWD, filename, t); } |
