diff options
66 files changed, 662 insertions, 310 deletions
diff --git a/Documentation/filesystems/idmappings.rst b/Documentation/filesystems/idmappings.rst index ac0af679e61e..77930c77fcfe 100644 --- a/Documentation/filesystems/idmappings.rst +++ b/Documentation/filesystems/idmappings.rst @@ -821,7 +821,7 @@ the same idmapping to the mount. We now perform three steps: /* Map the userspace id down into a kernel id in the filesystem's idmapping. */ make_kuid(u0:k20000:r10000, u1000) = k21000 -2. Verify that the caller's kernel ids can be mapped to userspace ids in the +3. Verify that the caller's kernel ids can be mapped to userspace ids in the filesystem's idmapping:: from_kuid(u0:k20000:r10000, k21000) = u1000 @@ -854,10 +854,10 @@ The same translation algorithm works with the third example. /* Map the userspace id down into a kernel id in the filesystem's idmapping. */ make_kuid(u0:k0:r4294967295, u1000) = k1000 -2. Verify that the caller's kernel ids can be mapped to userspace ids in the +3. Verify that the caller's kernel ids can be mapped to userspace ids in the filesystem's idmapping:: - from_kuid(u0:k0:r4294967295, k21000) = u1000 + from_kuid(u0:k0:r4294967295, k1000) = u1000 So the ownership that lands on disk will be ``u1000``. @@ -994,7 +994,7 @@ from above::: /* Map the userspace id down into a kernel id in the filesystem's idmapping. */ make_kuid(u0:k0:r4294967295, u1000) = k1000 -2. Verify that the caller's filesystem ids can be mapped to userspace ids in the +3. Verify that the caller's filesystem ids can be mapped to userspace ids in the filesystem's idmapping:: from_kuid(u0:k0:r4294967295, k1000) = u1000 diff --git a/Documentation/filesystems/iomap/design.rst b/Documentation/filesystems/iomap/design.rst index f8ee3427bc1a..37594e1c5914 100644 --- a/Documentation/filesystems/iomap/design.rst +++ b/Documentation/filesystems/iomap/design.rst @@ -142,9 +142,9 @@ Definitions * **pure overwrite**: A write operation that does not require any metadata or zeroing operations to perform during either submission or completion. - This implies that the fileystem must have already allocated space + This implies that the filesystem must have already allocated space on disk as ``IOMAP_MAPPED`` and the filesystem must not place any - constaints on IO alignment or size. + constraints on IO alignment or size. The only constraints on I/O alignment are device level (minimum I/O size and alignment, typically sector size). @@ -394,7 +394,7 @@ iomap is concerned: * The **upper** level primitive is provided by the filesystem to coordinate access to different iomap operations. - The exact primitive is specifc to the filesystem and operation, + The exact primitive is specific to the filesystem and operation, but is often a VFS inode, pagecache invalidation, or folio lock. For example, a filesystem might take ``i_rwsem`` before calling ``iomap_file_buffered_write`` and ``iomap_file_unshare`` to prevent diff --git a/MAINTAINERS b/MAINTAINERS index 988bc1e94c3c..f0310d42374d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8635,6 +8635,7 @@ M: Christian Brauner <brauner@kernel.org> R: Jan Kara <jack@suse.cz> L: linux-fsdevel@vger.kernel.org S: Maintained +T: git https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git F: fs/* F: include/linux/fs.h F: include/linux/fs_types.h diff --git a/drivers/char/adi.c b/drivers/char/adi.c index 751d7cc0da1b..1c76c8758f0f 100644 --- a/drivers/char/adi.c +++ b/drivers/char/adi.c @@ -14,12 +14,6 @@ #define MAX_BUF_SZ PAGE_SIZE -static int adi_open(struct inode *inode, struct file *file) -{ - file->f_mode |= FMODE_UNSIGNED_OFFSET; - return 0; -} - static int read_mcd_tag(unsigned long addr) { long err; @@ -206,9 +200,9 @@ static loff_t adi_llseek(struct file *file, loff_t offset, int whence) static const struct file_operations adi_fops = { .owner = THIS_MODULE, .llseek = adi_llseek, - .open = adi_open, .read = adi_read, .write = adi_write, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static struct miscdevice adi_miscdev = { diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 7c359cc406d5..169eed162a7f 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -643,6 +643,7 @@ static const struct file_operations __maybe_unused mem_fops = { .get_unmapped_area = get_unmapped_area_mem, .mmap_capabilities = memory_mmap_capabilities, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct file_operations null_fops = { @@ -693,7 +694,7 @@ static const struct memdev { umode_t mode; } devlist[] = { #ifdef CONFIG_DEVMEM - [DEVMEM_MINOR] = { "mem", &mem_fops, FMODE_UNSIGNED_OFFSET, 0 }, + [DEVMEM_MINOR] = { "mem", &mem_fops, 0, 0 }, #endif [3] = { "null", &null_fops, FMODE_NOWAIT, 0666 }, #ifdef CONFIG_DEVPORT diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 094498a0964b..d7ef8cbecf6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2908,6 +2908,7 @@ static const struct file_operations amdgpu_driver_kms_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv) diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 714e42b05108..f8de3cba1a08 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -318,6 +318,8 @@ int drm_open_helper(struct file *filp, struct drm_minor *minor) if (dev->switch_power_state != DRM_SWITCH_POWER_ON && dev->switch_power_state != DRM_SWITCH_POWER_DYNAMIC_OFF) return -EINVAL; + if (WARN_ON_ONCE(!(filp->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) + return -EINVAL; drm_dbg_core(dev, "comm=\"%s\", pid=%d, minor=%d\n", current->comm, task_pid_nr(current), minor->index); @@ -335,7 +337,6 @@ int drm_open_helper(struct file *filp, struct drm_minor *minor) } filp->private_data = priv; - filp->f_mode |= FMODE_UNSIGNED_OFFSET; priv->filp = filp; mutex_lock(&dev->filelist_mutex); diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 8b64f61ffaf9..d67c2b3ad901 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -498,6 +498,7 @@ static const struct file_operations psb_gem_fops = { .mmap = drm_gem_mmap, .poll = drm_poll, .read = drm_read, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_driver driver = { diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index fb8e9c2fcea5..cf276299bccb 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -1671,6 +1671,7 @@ static const struct file_operations i915_driver_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index a58c31089613..e243b42f8582 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1274,6 +1274,7 @@ nouveau_driver_fops = { .compat_ioctl = nouveau_compat_ioctl, #endif .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static struct drm_driver diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 7bf08164140e..ac49779ed03d 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -520,6 +520,7 @@ static const struct file_operations radeon_driver_kms_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = radeon_kms_compat_ioctl, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_ioctl_desc radeon_ioctls_kms[] = { diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index d79c76a287f2..bc08b813c197 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -801,6 +801,7 @@ static const struct file_operations tegra_drm_fops = { .read = drm_read, .compat_ioctl = drm_compat_ioctl, .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int tegra_drm_context_cleanup(int id, void *p, void *data) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 50ad3105c16e..2825dd3149ed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1609,6 +1609,7 @@ static const struct file_operations vmwgfx_driver_fops = { .compat_ioctl = vmw_compat_ioctl, #endif .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_driver driver = { diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index c89deffffb6d..59ee84ac1937 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -241,6 +241,7 @@ static const struct file_operations xe_driver_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static struct drm_driver driver = { diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 08232d8dc815..db5330d97348 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -360,7 +360,7 @@ static int read_file_page(struct file *file, unsigned long index, pr_debug("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE, (unsigned long long)index << PAGE_SHIFT); - bh = alloc_page_buffers(page, blocksize, false); + bh = alloc_page_buffers(page, blocksize); if (!bh) { ret = -ENOMEM; goto out; @@ -100,7 +100,7 @@ struct kioctx { unsigned long user_id; - struct __percpu kioctx_cpu *cpu; + struct kioctx_cpu __percpu *cpu; /* * For percpu reqs_available, number of slots we move to/from global diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index 8c1d587b3eef..77c7991d89aa 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -62,6 +62,7 @@ struct autofs_info { struct list_head expiring; struct autofs_sb_info *sbi; + unsigned long exp_timeout; unsigned long last_used; int count; @@ -81,6 +82,9 @@ struct autofs_info { */ #define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */ +#define AUTOFS_INF_EXPIRE_SET (1<<3) /* per-dentry expire timeout set for + this mount point. + */ struct autofs_wait_queue { wait_queue_head_t queue; struct autofs_wait_queue *next; diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index 5bf781ea6d67..f011e026358e 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -128,7 +128,13 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) goto out; } + /* Setting the per-dentry expire timeout requires a trailing + * path component, ie. no '/', so invert the logic of the + * check_name() return for AUTOFS_DEV_IOCTL_TIMEOUT_CMD. + */ err = check_name(param->path); + if (cmd == AUTOFS_DEV_IOCTL_TIMEOUT_CMD) + err = err ? 0 : -EINVAL; if (err) { pr_warn("invalid path supplied for cmd(0x%08x)\n", cmd); @@ -396,16 +402,97 @@ static int autofs_dev_ioctl_catatonic(struct file *fp, return 0; } -/* Set the autofs mount timeout */ +/* + * Set the autofs mount expire timeout. + * + * There are two places an expire timeout can be set, in the autofs + * super block info. (this is all that's needed for direct and offset + * mounts because there's a distinct mount corresponding to each of + * these) and per-dentry within within the dentry info. If a per-dentry + * timeout is set it will override the expire timeout set in the parent + * autofs super block info. + * + * If setting the autofs super block expire timeout the autofs_dev_ioctl + * size field will be equal to the autofs_dev_ioctl structure size. If + * setting the per-dentry expire timeout the mount point name is passed + * in the autofs_dev_ioctl path field and the size field updated to + * reflect this. + * + * Setting the autofs mount expire timeout sets the timeout in the super + * block info. struct. Setting the per-dentry timeout does a little more. + * If the timeout is equal to -1 the per-dentry timeout (and flag) is + * cleared which reverts to using the super block timeout, otherwise if + * timeout is 0 the timeout is set to this value and the flag is left + * set which disables expiration for the mount point, lastly the flag + * and the timeout are set enabling the dentry to use this timeout. + */ static int autofs_dev_ioctl_timeout(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { - unsigned long timeout; + unsigned long timeout = param->timeout.timeout; + + /* If setting the expire timeout for an individual indirect + * mount point dentry the mount trailing component path is + * placed in param->path and param->size adjusted to account + * for it otherwise param->size it is set to the structure + * size. + */ + if (param->size == AUTOFS_DEV_IOCTL_SIZE) { + param->timeout.timeout = sbi->exp_timeout / HZ; + sbi->exp_timeout = timeout * HZ; + } else { + struct dentry *base = fp->f_path.dentry; + struct inode *inode = base->d_inode; + int path_len = param->size - AUTOFS_DEV_IOCTL_SIZE - 1; + struct dentry *dentry; + struct autofs_info *ino; + + if (!autofs_type_indirect(sbi->type)) + return -EINVAL; + + /* An expire timeout greater than the superblock timeout + * could be a problem at shutdown but the super block + * timeout itself can change so all we can really do is + * warn the user. + */ + if (timeout >= sbi->exp_timeout) + pr_warn("per-mount expire timeout is greater than " + "the parent autofs mount timeout which could " + "prevent shutdown\n"); + + inode_lock_shared(inode); + dentry = try_lookup_one_len(param->path, base, path_len); + inode_unlock_shared(inode); + if (IS_ERR_OR_NULL(dentry)) + return dentry ? PTR_ERR(dentry) : -ENOENT; + ino = autofs_dentry_ino(dentry); + if (!ino) { + dput(dentry); + return -ENOENT; + } + + if (ino->exp_timeout && ino->flags & AUTOFS_INF_EXPIRE_SET) + param->timeout.timeout = ino->exp_timeout / HZ; + else + param->timeout.timeout = sbi->exp_timeout / HZ; + + if (timeout == -1) { + /* Revert to using the super block timeout */ + ino->flags &= ~AUTOFS_INF_EXPIRE_SET; + ino->exp_timeout = 0; + } else { + /* Set the dentry expire flag and timeout. + * + * If timeout is 0 it will prevent the expire + * of this particular automount. + */ + ino->flags |= AUTOFS_INF_EXPIRE_SET; + ino->exp_timeout = timeout * HZ; + } + dput(dentry); + } - timeout = param->timeout.timeout; - param->timeout.timeout = sbi->exp_timeout / HZ; - sbi->exp_timeout = timeout * HZ; return 0; } diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index 39d8c84c16f4..5c2d459e1e48 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -429,8 +429,6 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb, if (!root) return NULL; - timeout = sbi->exp_timeout; - dentry = NULL; while ((dentry = get_next_positive_subdir(dentry, root))) { spin_lock(&sbi->fs_lock); @@ -441,6 +439,11 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb, } spin_unlock(&sbi->fs_lock); + if (ino->flags & AUTOFS_INF_EXPIRE_SET) + timeout = ino->exp_timeout; + else + timeout = sbi->exp_timeout; + expired = should_expire(dentry, mnt, timeout, how); if (!expired) continue; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index cf792d4de4f1..ee2edccaef70 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -19,6 +19,7 @@ struct autofs_info *autofs_new_ino(struct autofs_sb_info *sbi) INIT_LIST_HEAD(&ino->expiring); ino->last_used = jiffies; ino->sbi = sbi; + ino->exp_timeout = -1; ino->count = 1; } return ino; @@ -28,6 +29,7 @@ void autofs_clean_ino(struct autofs_info *ino) { ino->uid = GLOBAL_ROOT_UID; ino->gid = GLOBAL_ROOT_GID; + ino->exp_timeout = -1; ino->last_used = jiffies; } @@ -172,8 +174,7 @@ static int autofs_parse_fd(struct fs_context *fc, struct autofs_sb_info *sbi, ret = autofs_check_pipe(pipe); if (ret < 0) { errorf(fc, "Invalid/unusable pipe"); - if (param->type != fs_value_is_file) - fput(pipe); + fput(pipe); return -EBADF; } diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 257f07656e5f..011817afc3ad 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1652,14 +1652,16 @@ again: break; } } else if (clean_pass && this_pass_clean) { - wait_queue_head_t *wq = bit_waitqueue(&inode->v.i_state, __I_NEW); - DEFINE_WAIT_BIT(wait, &inode->v.i_state, __I_NEW); + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + wq_head = inode_bit_waitqueue(&wqe, &inode->v, __I_NE |