From dfcb264a01a9199e8338a548731baf5bbe77ef19 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 4 Nov 2023 16:49:06 +0100 Subject: power: supply: bq27xxx: Stop and start delayed work in suspend and resume This driver uses delayed work to perform periodic battery state read out. This delayed work is not stopped across suspend and resume cycle. The read out can occur early in the resume cycle. In case of an I2C variant of this hardware, that read out triggers I2C transfer. That I2C transfer may happen while the I2C controller is still suspended, which produces a WARNING in the kernel log. Fix this by introducing trivial PM ops, which stop the delayed work before the system enters suspend, and schedule the delayed work right after the system resumes. Signed-off-by: Marek Vasut Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20231104154920.68585-1-marex@denx.de Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 7c8d65414a70..7d8025fb74b7 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -83,5 +83,6 @@ struct bq27xxx_device_info { void bq27xxx_battery_update(struct bq27xxx_device_info *di); int bq27xxx_battery_setup(struct bq27xxx_device_info *di); void bq27xxx_battery_teardown(struct bq27xxx_device_info *di); +extern const struct dev_pm_ops bq27xxx_battery_battery_pm_ops; #endif -- cgit v1.2.3 From 5b20755b7780464fea3e54af0af744258dcc2841 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 26 Nov 2023 16:19:14 +0900 Subject: init: move THIS_MODULE from to Commit f50169324df4 ("module.h: split out the EXPORT_SYMBOL into export.h") appropriately separated EXPORT_SYMBOL into because modules and EXPORT_SYMBOL are orthogonal; modules are symbol consumers, while EXPORT_SYMBOL are used by symbol providers, which may not be necessarily a module. However, that commit also relocated THIS_MODULE. As explained in the commit description, the intention was to define THIS_MODULE in a lightweight header, but I do not believe was the best location because EXPORT_SYMBOL and THIS_MODULE are unrelated. Move it to another lightweight header, . The reason for choosing is to make self-contained without relying on incorrectly including . With this adjustment, the role of becomes clearer as it only defines EXPORT_SYMBOL. Signed-off-by: Masahiro Yamada Reviewed-by: Luis Chamberlain --- include/linux/export.h | 18 ------------------ include/linux/init.h | 7 +++++++ 2 files changed, 7 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index 9911508a9604..0bbd02fd351d 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -6,15 +6,6 @@ #include #include -/* - * Export symbols from the kernel to modules. Forked from module.h - * to reduce the amount of pointless cruft we feed to gcc when only - * exporting a simple symbol or two. - * - * Try not to add #includes here. It slows compilation and makes kernel - * hackers place grumpy comments in header files. - */ - /* * This comment block is used by fixdep. Please do not remove. * @@ -23,15 +14,6 @@ * side effect of the *.o build rule. */ -#ifndef __ASSEMBLY__ -#ifdef MODULE -extern struct module __this_module; -#define THIS_MODULE (&__this_module) -#else -#define THIS_MODULE ((struct module *)0) -#endif -#endif /* __ASSEMBLY__ */ - #ifdef CONFIG_64BIT #define __EXPORT_SYMBOL_REF(sym) \ .balign 8 ASM_NL \ diff --git a/include/linux/init.h b/include/linux/init.h index 01b52c9c7526..3fa3f6241350 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -179,6 +179,13 @@ extern void (*late_time_init)(void); extern bool initcall_debug; +#ifdef MODULE +extern struct module __this_module; +#define THIS_MODULE (&__this_module) +#else +#define THIS_MODULE ((struct module *)0) +#endif + #endif #ifndef MODULE -- cgit v1.2.3 From 4498a8eccc97de3d65f876b6fdeddb439ef73abc Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 20 Nov 2023 17:09:47 +0000 Subject: netfs, fscache: Remove ->begin_cache_operation Remove ->begin_cache_operation() in favour of just calling fscache directly. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: Christian Brauner cc: linux-fsdevel@vger.kernel.org cc: linux-cachefs@redhat.com --- include/linux/fscache.h | 3 --- include/linux/netfs.h | 4 +--- 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 8e312c8323a8..9ed6696aee7a 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -437,9 +437,6 @@ const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_r * indicates the cache resources to which the operation state should be * attached; @cookie indicates the cache object that will be accessed. * - * This is intended to be called from the ->begin_cache_operation() netfs lib - * operation as implemented by the network filesystem. - * * @cres->inval_counter is set from @cookie->inval_counter for comparison at * the end of the operation. This allows invalidation during the operation to * be detected by the caller. diff --git a/include/linux/netfs.h b/include/linux/netfs.h index b11a84f6c32b..d294ff8f9ae4 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -208,7 +208,6 @@ struct netfs_io_request { struct netfs_request_ops { int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); - int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); @@ -229,8 +228,7 @@ enum netfs_read_from_hole { }; /* - * Table of operations for access to a cache. This is obtained by - * rreq->ops->begin_cache_operation(). + * Table of operations for access to a cache. */ struct netfs_cache_ops { /* End an operation */ -- cgit v1.2.3 From 7eb5b3e3a0a55f2d166ca949ef47ca6e0c704aab Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 21 Nov 2023 15:43:52 +0000 Subject: netfs, fscache: Move /proc/fs/fscache to /proc/fs/netfs and put in a symlink Rename /proc/fs/fscache to "netfs" and make a symlink from fscache to that. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: Christian Brauner cc: linux-fsdevel@vger.kernel.org cc: linux-cachefs@redhat.com --- include/linux/netfs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index d294ff8f9ae4..9bd91cd615d5 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -294,7 +294,6 @@ void netfs_get_subrequest(struct netfs_io_subrequest *subreq, enum netfs_sreq_ref_trace what); void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, enum netfs_sreq_ref_trace what); -void netfs_stats_show(struct seq_file *); ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, struct iov_iter *new, iov_iter_extraction_t extraction_flags); -- cgit v1.2.3 From c9c4ff12df110feb1b91951010f673f4b16e49e8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 27 Nov 2023 13:58:07 +0000 Subject: netfs: Move pinning-for-writeback from fscache to netfs Move the resource pinning-for-writeback from fscache code to netfslib code. This is used to keep a cache backing object pinned whilst we have dirty pages on the netfs inode in the pagecache such that VM writeback will be able to reach it. Whilst we're at it, switch the parameters of netfs_unpin_writeback() to match ->write_inode() so that it can be used for that directly. Note that this mechanism could be more generically useful than that for network filesystems. Quite often they have to keep around other resources (e.g. authentication tokens or network connections) until the writeback is complete. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/fs.h | 2 +- include/linux/fscache.h | 42 ------------------------------------------ include/linux/netfs.h | 3 +++ include/linux/writeback.h | 2 +- 4 files changed, 5 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98b7a7a8c42e..68a957261694 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2294,7 +2294,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) -#define I_PINNING_FSCACHE_WB (1 << 18) +#define I_PINNING_NETFS_WB (1 << 18) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 9ed6696aee7a..6e8562cbcc43 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -626,48 +626,6 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, } -#if __fscache_available -bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio, - struct fscache_cookie *cookie); -#else -#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \ - filemap_dirty_folio(MAPPING, FOLIO) -#endif - -/** - * fscache_unpin_writeback - Unpin writeback resources - * @wbc: The writeback control - * @cookie: The cookie referring to the cache object - * - * Unpin the writeback resources pinned by fscache_dirty_folio(). This is - * intended to be called by the netfs's ->write_inode() method. - */ -static inline void fscache_unpin_writeback(struct writeback_control *wbc, - struct fscache_cookie *cookie) -{ - if (wbc->unpinned_fscache_wb) - fscache_unuse_cookie(cookie, NULL, NULL); -} - -/** - * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode - * @cookie: The cookie referring to the cache object - * @inode: The inode to clean up - * @aux: Auxiliary data to apply to the inode - * - * Clear any writeback resources held by an inode when the inode is evicted. - * This must be called before clear_inode() is called. - */ -static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, - struct inode *inode, - const void *aux) -{ - if (inode->i_state & I_PINNING_FSCACHE_WB) { - loff_t i_size = i_size_read(inode); - fscache_unuse_cookie(cookie, aux, &i_size); - } -} - /** * fscache_note_page_release - Note that a netfs page got released * @cookie: The cookie corresponding to the file diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 9bd91cd615d5..32faf6c89702 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -288,6 +288,9 @@ int netfs_read_folio(struct file *, struct folio *); int netfs_write_begin(struct netfs_inode *, struct file *, struct address_space *, loff_t pos, unsigned int len, struct folio **, void **fsdata); +bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio); +int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); +void netfs_clear_inode_writeback(struct inode *inode, const void *aux); void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); void netfs_get_subrequest(struct netfs_io_subrequest *subreq, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 083387c00f0c..1e08392fb43e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -60,7 +60,7 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ - unsigned unpinned_fscache_wb:1; /* Cleared I_PINNING_FSCACHE_WB */ + unsigned unpinned_netfs_wb:1; /* Cleared I_PINNING_NETFS_WB */ /* * When writeback IOs are bounced through async layers, only the -- cgit v1.2.3 From 87b57a048964abfd5f3d8b79bc55687327f5a380 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 4 Mar 2022 10:34:27 +0000 Subject: netfs: Add a procfile to list in-progress requests Add a procfile, /proc/fs/netfs/requests, to list in-progress netfslib I/O requests. Signed-off-by: David Howells cc: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 32faf6c89702..7244ddebd974 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -175,10 +175,14 @@ enum netfs_io_origin { * operations to a variety of data stores and then stitch the result together. */ struct netfs_io_request { - struct work_struct work; + union { + struct work_struct work; + struct rcu_head rcu; + }; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ struct netfs_cache_resources cache_resources; + struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; -- cgit v1.2.3 From cc3cb0a18da46a51d9fc173155576ba1d068e536 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 9 Mar 2022 11:01:12 +0000 Subject: netfs: Allow the netfs to make the io (sub)request alloc larger Allow the network filesystem to specify extra space to be allocated on the end of the io (sub)request. This allows cifs, for example, to use this space rather than allocating its own cifs_readdata struct. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 7244ddebd974..d6f27000eeb0 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -210,6 +210,8 @@ struct netfs_io_request { * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { + unsigned int io_request_size; /* Alloc size for netfs_io_request struct */ + unsigned int io_subrequest_size; /* Alloc size for netfs_io_subrequest struct */ int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); -- cgit v1.2.3 From 5f5ce7ba15e7e6a6539ac8e1f845757aaebecf0d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Feb 2022 11:19:14 +0000 Subject: netfs: Add a ->free_subrequest() op Add a ->free_subrequest() op so that the netfs can clean up data attached to a subrequest. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index d6f27000eeb0..06f57d9d09f6 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -214,6 +214,7 @@ struct netfs_request_ops { unsigned int io_subrequest_size; /* Alloc size for netfs_io_subrequest struct */ int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); + void (*free_subrequest)(struct netfs_io_subrequest *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); -- cgit v1.2.3 From c1ec4d7c2e13471558cfea302b7583856284f94c Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 20 Aug 2021 17:08:30 +0100 Subject: netfs: Provide invalidate_folio and release_folio calls Provide default invalidate_folio and release_folio calls. These will need to interact with invalidation correctly at some point. They will be needed if netfslib is to make use of folio->private for its own purposes. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 06f57d9d09f6..8efbfd3b2820 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -293,11 +293,13 @@ struct readahead_control; void netfs_readahead(struct readahead_control *); int netfs_read_folio(struct file *, struct folio *); int netfs_write_begin(struct netfs_inode *, struct file *, - struct address_space *, loff_t pos, unsigned int len, - struct folio **, void **fsdata); + struct address_space *, loff_t pos, unsigned int len, + struct folio **, void **fsdata); bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio); int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); void netfs_clear_inode_writeback(struct inode *inode, const void *aux); +void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); +bool netfs_release_folio(struct folio *folio, gfp_t gfp); void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); void netfs_get_subrequest(struct netfs_io_subrequest *subreq, -- cgit v1.2.3 From 46ed60dcd4f2c94d27735743ce55cd8d6b93cc1d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Oct 2023 15:34:07 +0100 Subject: netfs: Implement unbuffered/DIO vs buffered I/O locking Borrow NFS's direct-vs-buffered I/O locking into netfslib. Similar code is also used in ceph. Modify it to have the correct checker annotations for i_rwsem lock acquisition/release and to return -ERESTARTSYS if waits are interrupted. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 8efbfd3b2820..fc6d9756a029 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -129,6 +129,8 @@ struct netfs_inode { struct fscache_cookie *cache; #endif loff_t remote_i_size; /* Size of the remote file */ + unsigned long flags; +#define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ }; /* @@ -310,6 +312,13 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, struct iov_iter *new, iov_iter_extraction_t extraction_flags); +int netfs_start_io_read(struct inode *inode); +void netfs_end_io_read(struct inode *inode); +int netfs_start_io_write(struct inode *inode); +void netfs_end_io_write(struct inode *inode); +int netfs_start_io_direct(struct inode *inode); +void netfs_end_io_direct(struct inode *inode); + /** * netfs_inode - Get the netfs inode context from the inode * @inode: The inode to query @@ -335,6 +344,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, { ctx->ops = ops; ctx->remote_i_size = i_size_read(&ctx->inode); + ctx->flags = 0; #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif -- cgit v1.2.3 From 92b6cc5d1e7cbe569f00e9c1249ac8214fd5e2d2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 26 Sep 2023 17:42:26 +0100 Subject: netfs: Add iov_iters to (sub)requests to describe various buffers Add three iov_iter structs: (1) Add an iov_iter (->iter) to the I/O request to describe the unencrypted-side buffer. (2) Add an iov_iter (->io_iter) to the I/O request to describe the encrypted-side I/O buffer. This may be a different size to the buffer in (1). (3) Add an iov_iter (->io_iter) to the I/O subrequest to describe the part of the I/O buffer for that subrequest. This will allow future patches to point to a bounce buffer instead for purposes of handling oversize writes, decryption (where we want to save the encrypted data to the cache) and decompression. These iov_iters persist for the lifetime of the (sub)request, and so can be accessed multiple times without worrying about them being deallocated upon return to the caller. The network filesystem must appropriately advance the iterator before terminating the request. Signed-off-by: David Howells cc: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index fc6d9756a029..3da962e977f5 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -150,6 +150,7 @@ struct netfs_cache_resources { struct netfs_io_subrequest { struct netfs_io_request *rreq; /* Supervising I/O request */ struct list_head rreq_link; /* Link in rreq->subrequests */ + struct iov_iter io_iter; /* Iterator for this subrequest */ loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ @@ -186,6 +187,8 @@ struct netfs_io_request { struct netfs_cache_resources cache_resources; struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ + struct iov_iter iter; /* Unencrypted-side iterator */ + struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; atomic_t nr_outstanding; /* Number of ops in progress */ -- cgit v1.2.3 From 21d706d5cf570917594b21edee81893bdce09ab8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 9 Jul 2021 08:41:17 +0100 Subject: netfs: Add support for DIO buffering Add a bvec array pointer and an iterator to netfs_io_request for either holding a copy of a DIO iterator or a list of all the bits of buffer pointed to by a DIO iterator. There are two problems: Firstly, if an iovec-class iov_iter is passed to ->read_iter() or ->write_iter(), this cannot be passed directly to kernel_sendmsg() or kernel_recvmsg() as that may cause locking recursion if a fault is generated, so we need to keep track of the pages involved separately. Secondly, if the I/O is asynchronous, we must copy the iov_iter describing the buffer before returning to the caller as it may be immediately deallocated. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 3da962e977f5..2bb1273b38f4 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -190,6 +190,8 @@ struct netfs_io_request { struct iov_iter iter; /* Unencrypted-side iterator */ struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ void *netfs_priv; /* Private data for the netfs */ + struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ + unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; atomic_t nr_outstanding; /* Number of ops in progress */ atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ @@ -197,6 +199,7 @@ struct netfs_io_request { size_t len; /* Length of the request */ short error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ + bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ -- cgit v1.2.3 From 7d828a06634799aba0fa392913c7fe2953eb64a6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 22 Sep 2023 13:25:22 +0100 Subject: netfs: Provide tools to create a buffer in an xarray Provide tools to create a buffer in an xarray, with a function to add new folios with a mark. This will be used to create bounce buffer and can be used more easily to create a list of folios the span of which would require more than a page's worth of bio_vec structs. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 2bb1273b38f4..c05365e3f428 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -109,6 +109,10 @@ static inline int wait_on_page_fscache_killable(struct page *page) return folio_wait_private_2_killable(page_folio(page)); } +/* Marks used on xarray-based buffers */ +#define NETFS_BUF_PUT_MARK XA_MARK_0 /* - Page needs putting */ +#define NETFS_BUF_PAGECACHE_MARK XA_MARK_1 /* - Page needs wb/dirty flag wrangling */ + enum netfs_io_source { NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, -- cgit v1.2.3 From cae932d3aee55035a54415dcea8e7ecf2ec469b5 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 22 Sep 2023 14:49:47 +0100 Subject: netfs: Add func to calculate pagecount/size-limited span of an iterator Add a function to work out how much of an ITER_BVEC or ITER_XARRAY iterator we can use in a pagecount-limited and size-limited span. This will be used, for example, to limit the number of segments in a subrequest to the maximum number of elements that an RDMA transfer can handle. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c05365e3f428..d673d0785b9d 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -321,6 +321,8 @@ void netfs_put_subrequest(struct netfs_io_subrequest *subreq, ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, struct iov_iter *new, iov_iter_extraction_t extraction_flags); +size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs); int netfs_start_io_read(struct inode *inode); void netfs_end_io_read(struct inode *inode); -- cgit v1.2.3 From 768ddb1eacf5dd997ecf393e7bab9796bad047e0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 27 May 2022 13:45:28 +0100 Subject: netfs: Limit subrequest by size or number of segments Limit a subrequest to a maximum size and/or a maximum number of contiguous physical regions. This permits, for instance, an subreq's iterator to be limited to the number of DMA'able segments that a large RDMA request can handle. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index d673d0785b9d..44cd13ad695a 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -161,6 +161,7 @@ struct netfs_io_subrequest { refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ + unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */ enum netfs_io_source source; /* Where to read from/write to */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ -- cgit v1.2.3 From 16af134ca4b7051b1587108f2066ec90ae029f74 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 9 Feb 2022 19:52:13 +0000 Subject: netfs: Extend the netfs_io_*request structs to handle writes Modify the netfs_io_request struct to act as a point around which writes can be coordinated. It represents and pins a range of pages that need writing and a list of regions of dirty data in that range of pages. If RMW is required, the original data can be downloaded into the bounce buffer, decrypted if necessary, the modifications made, then the modified data can be reencrypted/recompressed and sent back to the server. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 44cd13ad695a..f302123a3e38 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -118,6 +118,9 @@ enum netfs_io_source { NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, NETFS_INVALID_READ, + NETFS_UPLOAD_TO_SERVER, + NETFS_WRITE_TO_CACHE, + NETFS_INVALID_WRITE, } __mode(byte); typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, @@ -149,9 +152,14 @@ struct netfs_cache_resources { }; /* - * Descriptor for a single component subrequest. + * Descriptor for a single component subrequest. Each operation represents an + * individual read/write from/to a server, a cache, a journal, etc.. + * + * The buffer iterator is persistent for the life of the subrequest struct and + * the pages it points to can be relied on to exist for the duration. */ struct netfs_io_subrequest { + struct work_struct work; struct netfs_io_request *rreq; /* Supervising I/O request */ struct list_head rreq_link; /* Link in rreq->subrequests */ struct iov_iter io_iter; /* Iterator for this subrequest */ @@ -176,6 +184,8 @@ enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ + NETFS_WRITEBACK, /* This write was triggered by writepages */ + nr__netfs_io_origin } __mode(byte); /* @@ -198,6 +208,7 @@ struct netfs_io_request { struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; + unsigned int subreq_counter; /* Next subreq->debug_index */ atomic_t nr_outstanding; /* Number of ops in progress */ atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ @@ -216,6 +227,8 @@ struct netfs_io_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ +#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ +#define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ const struct netfs_request_ops *netfs_ops; }; -- cgit v1.2.3 From c6dc54dd91bbf597942b4975b8adec660a16827d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Feb 2022 12:27:53 +0000 Subject: netfs: Add a hook to allow tell the netfs to update its i_size Add a hook for netfslib's write helpers to call to tell the network filesystem that it should update its i_size. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index f302123a3e38..3fc41f616621 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -242,6 +242,7 @@ struct netfs_request_ops { void (*free_request)(struct netfs_io_request *rreq); void (*free_subrequest)(struct netfs_io_subrequest *rreq); + /* Read request handling */ void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); @@ -249,6 +250,9 @@ struct netfs_request_ops { int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio **foliop, void **_fsdata); void (*done)(struct netfs_io_request *rreq); + + /* Modification handling */ + void (*update_i_size)(struct inode *inode, loff_t i_size); }; /* -- cgit v1.2.3 From 9ebff83e648148b9ece97d4e4890dd84ca54d6ce Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 29 Sep 2023 17:28:25 +0100 Subject: netfs: Prep to use folio->private for write grouping and streaming write Prepare to use folio->private to hold information write grouping and streaming write. These are implemented in the same commit as they both make use of folio->private and will be both checked at the same time in several places. "Write grouping" involves ordering the writeback of groups of writes, such as is needed for ceph snaps. A group is represented by a filesystem-supplied object which must contain a netfs_group struct. This contains just a refcount and a pointer to a destructor. "Streaming write" is the storage of data in folios that are marked dirty, but not uptodate, to avoid unnecessary reads of data. This is represented by a netfs_folio struct. This contains the offset and length of the modified region plus the otherwise displaced write grouping pointer. The way folio->private is multiplexed is: (1) If private is NULL then neither is in operation on a dirty folio. (2) If private is set, with bit 0 clear, then this points to a group. (3) If private is set, with bit 0 set, then this points to a netfs_folio struct (with bit 0 AND'ed out). Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 3fc41f616621..cfba83e3e3d2 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -140,6 +140,47 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ }; +/* + * A netfs group - for instance a ceph snap. This is marked on dirty pages and + * pages marked with a group must be flushed before they can be written under + * the domain of another group. + */ +struct netfs_group { + refcount_t ref; + void (*free)(struct netfs_group *netfs_group); +}; + +/* + * Information about a dirty page (attached only if necessary). + * folio->private + */ +struct netfs_folio { + struct netfs_group *netfs_group; /* Filesystem's grouping marker (or NULL). */ + unsigned int dirty_offset; /* Write-streaming dirty data offset */ + unsigned int dirty_len; /* Write-streaming dirty data length */ +}; +#define NETFS_FOLIO_INFO 0x1UL /* OR'd with folio->private. */ + +static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +{ + void *priv = folio_get_private(folio); + + if ((unsigned long)priv & NETFS_FOLIO_INFO) + return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO); + return NULL; +} + +static inline struct netfs_group *netfs_folio_group(struct folio *folio) +{ + struct netfs_folio *finfo; + void *priv = folio_get_private(folio); + + finfo = netfs_folio_info(folio); + if (finfo) + return finfo->netfs_group; + return priv; +} + /* * Resources required to do operations on a cache. */ -- cgit v1.2.3 From 0e0f2dfe880fb19e4b15a7ca468623eb0b4ba586 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Jun 2021 22:31:48 +0100 Subject: netfs: Dispatch write requests to process a writeback slice Dispatch one or more write reqeusts to process a writeback slice, where a slice is tailored more to logical block divisions within the file (such as crypto blocks, an object layout or cache granules) than the protocol RPC maximum capacity. The dispatch doesn't happen until throttling allows, at which point the entire writeback slice is processed and queued. A slice may be written to multiple destinations (one or more servers and the local cache) and the writes to each destination might be split up along different lines. The writeback slice holds the required folios pinned. An iov_iter is provided in netfs_write_request that describes the buffer to be used. This may be part of the pagecache, may have auxiliary padding pages attached or may be a bounce buffer resulting from crypto or compression. Consequently, the filesystem must not twiddle the folio markings directly. The following API is available to the filesystem: (1) The ->create_write_requests() method is called to ask the filesystem to create the requests it needs. This is passed the writeback slice to be processed. (2) The filesystem should then call netfs_create_write_request() to create the requests it needs. (3) Once a request is initialised, netfs_queue_write_request() can be called to dispatch it asynchronously, if not completed immediately. (4) netfs_write_request_completed() should be called to note the completion of a request. (5) netfs_get_write_request() and netfs_put_write_request() are provided to refcount a request. These take constants from the netfs_wreq_trace enum for logging into ftrace. (6) The ->free_write_request is method is called to ask the filesystem to clean up a request. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index cfba83e3e3d2..890a5d8b2299 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -249,6 +249,7 @@ struct netfs_io_request { struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; + unsigned int wsize; /* Maximum write size (0 for none) */ unsigned int subreq_counter; /* Next subreq->debug_index */ atomic_t nr_outstanding; /* Number of ops in progress */ atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ @@ -271,6 +272,7 @@ struct netfs_io_request { #define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ const struct netfs_request_ops *netfs_ops; + void (*cleanup)(struct netfs_io_request *req); }; /* @@ -294,6 +296,11 @@ struct netfs_request_ops { /* Modification handling */ void (*update_i_size)(struct inode *inode, loff_t i_size); + + /* Write request handling */ + void (*create_write_requests)(struct netfs_io_request *wreq, + loff_t start, size_t len); + void (*invalidate_cache)(struct netfs_io_request *wreq); }; /* @@ -382,6 +389,12 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, iov_iter_extraction_t extraction_flags); size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs); +struct netfs_io_subrequest *netfs_create_write_request( + struct netfs_io_request *wreq, enum netfs_io_source dest, + loff_t start, size_t len, work_func_t worker); +void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, + bool was_async); +void netfs_queue_write_request(struct netfs_io_subrequest *subreq); int netfs_start_io_read(struct inode *inode); void netfs_end_io_read(struct inode *inode); -- cgit v1.2.3 From c38f4e96e605f17990e871214e6ea1496bc4e65f Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Jun 2021 13:09:21 +0100 Subject: netfs: Provide func to copy data to pagecache for buffered write Provide a netfs write helper, netfs_perform_write() to buffer data to be written in the pagecache and mark the modified folios dirty. It will perform "streaming writes" for folios that aren't currently resident, if possible, storing data in partially modified folios that are marked dirty, but not uptodate. It will also tag pages as belonging to fs-specific write groups if so directed by the filesystem. This is derived from generic_perform_write(), but doesn't use ->write_begin() and ->write_end(), having that logic rolled in instead. Signed-off-by: David Howells cc: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 890a5d8b2299..70f578cf3715 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -367,6 +367,11 @@ struct netfs_cache_ops { loff_t *_data_start, size_t *_data_len); }; +/* High-level write API */ +ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group); + +/* Address operations API */ struct readahead_control; void netfs_readahead(struct readahead_control *); int netfs_read_folio(struct file *, struct folio *); -- cgit v1.2.3 From 016dc8516aec8719641e7aaaacd78d344759178e Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Jan 2022 17:39:55 +0000 Subject: netfs: Implement unbuffered/DIO read support Implement support for unbuffered and DIO reads in the netfs library, utilising the existing read helper code to do block splitting and individual queuing. The code also handles extraction of the destination buffer from the supplied iterator, allowing async unbuffered reads to take place. The read will be split up according to the rsize setting and, if supplied, the ->clamp_length() method. Note that the next subrequest will be issued as soon as issue_op returns, without waiting for previous ones to finish. The network filesystem needs to pause or handle queuing them if it doesn't want to fire them all at the server simultaneously. Once all the subrequests have finished, the state will be assessed and the amount of data to be indicated as having being obtained will be determined. As the subrequests may finish in any order, if an intermediate subrequest is short, any further subrequests may be copied into the buffer and then abandoned. In the future, this will also take care of doing an unbuffered read from encrypted content, with the decryption being done by the library. Signed-off-by: David Howells cc: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 70f578cf3715..7c1309568459 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -226,6 +226,7 @@ enum netfs_io_origin { NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ NETFS_WRITEBACK, /* This write was triggered by writepages */ + NETFS_DIO_READ, /* This is a direct I/O read */ nr__netfs_io_origin } __mode(byte); @@ -240,6 +241,7 @@ struct netfs_io_request { }; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ + struct kiocb *iocb; /* AIO completion vector */ struct netfs_cache_resources cache_resources; struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ @@ -249,12 +251,14 @@ struct netfs_io_request { struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; + unsigned int rsize; /* Maximum read size (0 for none) */ unsigned int wsize; /* Maximum write size (0 for none) */ unsigned int subreq_counter; /* Next subreq->debug_index */ atomic_t nr_outstanding; /* Number of ops in progress */ atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ + size_t transferred; /* Amount to be indicated as transferred */ short error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ @@ -271,6 +275,8 @@ struct netfs_io_request { #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ #define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ +#define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ +#define NETFS_RREQ_BLOCKED 10 /* We blocked */ const struct netfs_request_ops *netfs_ops; void (*cleanup)(struct netfs_io_request *req); }; @@ -367,6 +373,9 @@ struct netfs_cache_ops { loff_t *_data_start, size_t *_data_len); }; +/* High-level read API. */ +ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); + /* High-level write API */ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, struct netfs_group *netfs_group); -- cgit v1.2.3 From 153a9961b551101cd38e94e26cd92fbfd198b19b Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 21 Feb 2022 11:38:17 +0000 Subject: netfs: Implement unbuffered/DIO write support Implement support for unbuffered writes and direct I/O writes. If the write is misaligned with respect to the fscrypt block size, then RMW cycles are performed if necessary. DIO writes are a special case of unbuffered writes with extra restriction imposed, such as block size alignment requirements. Also provide a field that can tell the code to add some extra space onto the bounce buffer for use by the filesystem in the case of a content-encrypted file. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 7c1309568459..e1dfd6775c2c 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -138,6 +138,7 @@ struct netfs_inode { loff_t remote_i_size; /* Size of the remote file */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ +#define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ }; /* @@ -226,7 +227,9 @@ enum netfs_io_origin { NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ NETFS_WRITEBACK, /* This write was triggered by writepages */ + NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_READ, /* This is a direct I/O read */ + NETFS_DIO_WRITE, /* This is a direct I/O write */ nr__netfs_io_origin } __mode(byte); @@ -379,6 +382,7 @@ ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); /* High-level write API */ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, struct netfs_group *netfs_group); +ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from); /* Address operations API */ struct readahead_control; -- cgit v1.2.3 From 938e13a73b244278a3777f38fa915bd239b2efd2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Jun 2021 13:09:21 +0100 Subject: netfs: Implement buffered write API Institute a netfs write helper, netfs_file_write_iter(), to be pointed at by the network filesystem ->write_iter() call. Make it handled buffered writes by calling the previously defined netfs_perform_write() to copy the source data into the pagecache. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index e1dfd6775c2c..0948ecf69aa5 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -382,7 +382,10 @@ ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); /* High-level write API */ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, struct netfs_group *netfs_group); +ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from, + struct netfs_group *netfs_group); ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from); +ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); /* Address operations API */ struct readahead_control; -- cgit v1.2.3 From 102a7e2c598c22bd2621fa97eb1c93c89d469a12 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 15 Feb 2022 23:15:57 +0000 Subject: netfs: Allow buffered shared-writeable mmap through netfs_page_mkwrite() Provide an entry point to delegate a filesystem's ->page_mkwrite() to. This checks for conflicting writes, then attached any netfs-specific group marking (e.g. ceph snap) to the page to be considered dirty. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 0948ecf69aa5..d7f324c7c22a 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -400,6 +400,10 @@ void netfs_clear_inode_writeback(struct inode *inode, const void *aux); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); bool netfs_release_folio(struct folio *folio, gfp_t gfp); +/* VMA operations API. */ +vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); + +/* (Sub)request management API. */ void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); void netfs_get_subrequest(struct netfs_io_subrequest *subreq, enum netfs_sreq_ref_trace what); -- cgit v1.2.3 From 80645bd4aa33a5c325f11b8dc6b38b38410ad5c0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Oct 2023 09:29:43 +0100 Subject: netfs: Provide netfs_file_read_iter() Provide a top-level-ish function that can be pointed to directly by ->read_iter file op. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index d7f324c7c22a..19a41c437af3 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -378,6 +378,8 @@ struct netfs_cache_ops { /* High-level read API. */ ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); +ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); +ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); /* High-level write API */ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, -- cgit v1.2.3 From e0ace6ca98bef0d8d354040f13ffc0a498813ee9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 22 Nov 2023 17:18:17 +0000 Subject: netfs, cachefiles: Pass upper bound length to allow expansion Make netfslib pass the maximum length to the ->prepare_write() op to tell the cache how much it can expand the length of a write to. This allows a write to the server at the end of a file to be limited to a few bytes whilst writing an entire block to the cache (something required by direct I/O). Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 19a41c437af3..2856389f4694 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -261,6 +261,7 @@ struct netfs_io_request { atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ + size_t upper_len; /* Length can be extended to here */ size_t transferred; /* Amount to be indicated as transferred */ short error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ @@ -357,8 +358,8 @@ struct netfs_cache_ops { * actually do. */ int (*prepare_write)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size, - bool no_space_allocated_yet); + loff_t *_start, size_t *_len, size_t upper_len, + loff_t i_size, bool no_space_allocated_yet); /* Prepare an on-demand read operation, shortening it to a cached/uncached * boundary as appropriate. -- cgit v1.2.3 From 62c3b7481b9a108cb99ef9438dba66bb4738768b Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 28 Sep 2023 11:46:49 +0100 Subject: netfs: Provide a writepages implementation Provide an implementation of writepages for network filesystems to delegate to. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 2856389f4694..86bb8cb7f8d0 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -397,6 +397,8 @@ int netfs_read_folio(struct file *, struct folio *); int netfs_write_begin(struct netfs_inode *, struct file *, struct address_space *, loff_t pos, unsigned int len, struct folio **, void **fsdata); +int netfs_writepages(struct address_space *mapping, + struct writeback_control *wbc); bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio); int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); void netfs_clear_inode_writeback(struct inode *inode, const void *aux); -- cgit v1.2.3 From 4a79616cfb27d76947ea37f0336745ef929d56be Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 5 Oct 2023 16:52:58 +0100 Subject: netfs: Provide a launder_folio implementation Provide a launder_folio implementation for netfslib. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 86bb8cb7f8d0..29c66acad925 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -227,6 +227,7 @@ enum netfs_io_origin { NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ NETFS_WRITEBACK, /* This write was triggered by writepages */ + NETFS_LAUNDER_WRITE, /* This is triggered by ->launder_folio() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_DIO_WRITE, /* This is a direct I/O write */ @@ -404,6 +405,7 @@ int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); void netfs_clear_inode_writeback(struct inode *inode, const void *aux); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); bool netfs_release_folio(struct folio *folio, gfp_t gfp); +int netfs_launder_folio(struct folio *folio); /* VMA operations API. */ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); -- cgit v1.2.3 From 41d8e7673a7726cba57cb8112d81c89cfb6c3e35 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Oct 2023 09:06:24 +0100 Subject: netfs: Implement a write-through caching option Provide a flag whereby a filesystem may request that cifs_perform_write() perform write-through caching. This involves putting pages directly into writeback rather than dirty and attaching them to a write operation as we go. Further, the writes being made are limited to the byte range being written rather than whole folios being written. This can be used by cifs, for example, to deal with strict byte-range locking. This can't be used with content encryption as that may require expansion of the write RPC beyond the write being made. This doesn't affect writes via mmap - those are written back in the normal way; similarly failed writethrough writes are marked dirty and left to writeback to retry. Another option would be to simply invalidate them, but the contents can be simultaneously accessed by read() and through mmap. Signed-off-by: David Howells cc: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 29c66acad925..8a2dd882a781 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -139,6 +139,7 @@ struct netfs_inode { unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ +#define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ }; /* @@ -227,6 +228,7 @@ enum netfs_io_origin { NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ NETFS_WRITEBACK, /* This write was triggered by writepages */ + NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ NETFS_LAUNDER_WRITE, /* This is triggered by ->launder_folio() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_READ, /* This is a direct I/O read */ -- cgit v1.2.3 From 100ccd18bb41ea7abb4fbb419202c06079559501 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 24 Nov 2023 13:39:02 +0000 Subject: netfs: Optimise away reads above the point at which there can be no data Track the file position above which the server is not expected to have any data (the "zero point") and preemptively assume that we can satisfy requests by filling them with zeroes locally rather than attempting to download them if they're over that line - even if we've written data back to the server. Assume that any data that was written back above that position is held in the local cache. Note that we have to split requests that straddle the line. Make use of this to optimise away some reads from the server. We need to set the zero point in the following circumstances: (1) When we see an extant remote inode and have no cache for it, we set the zero_point to i_size. (2) On local inode creation, we set zero_point to 0. (3) On local truncation down, we reduce zero_point to the new i_size if the new i_size is lower. (4) On local truncation up, we don't change zero_point. (5) On local modification, we don't change zero_point. (6) On remote invalidation, we set zero_point to the new i_size. (7) If stored data is discarded from the pagecache or culled from fscache, we must set zero_point above that if the data also got written to the server. (8) If dirty data is written back to the server, but not fscache, we must set zero_point above that. (9) If a direct I/O write is made, set zero_point above that. Assuming the above, any read from the server at or above the zero_point position will return all zeroes. The zero_point value can be stored in the cache, provided the above rules are applied to it by any code that culls part of the local cache. Signed-off-by: David Howells cc: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 8a2dd882a781..852956aa3c4b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -136,6 +136,8 @@ struct netfs_inode { struct fscache_cookie *cache; #endif loff_t remote_i_size; /* Size of the remote file */ + loff_t zero_point; /* Size after which we assume there's no data + * on the server */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ @@ -453,31 +455,44 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode) * netfs_inode_init - Initialise a netfslib inode context * @ctx: The netfs inode to initialise * @ops: The netfs's operations list + * @use_zero_point: True to use the zero_point read optimisation * * Initialise the netfs library context struct. This is expected to follow on * directly from the VFS inode struct. */ static inline void netfs_inode_init(struct netfs_inode *ctx, - const struct netfs_request_ops *ops) + const struct netfs_request_ops *ops, + bool use_zero_point) { ctx->ops = ops; ctx->remote_i_size = i_size_read(&ctx->inode); + ctx->zero_point = LLONG_MAX; ctx->flags = 0; #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif + /* ->releasepage() drives zero_point */ + if (use_zero_point) { + ctx->zero_point = ctx->remote_i_size; + mapping_set_release_always(ctx->inode.i_mapping); + } } /** * netfs_resize_file - Note that a file got resized * @ctx: The netfs inode being resized * @new_i_size: The new file size + * @changed_on_server: The change was applied to the server * * Inform the netfs lib that a file got resized so that it can adjust its state. */ -static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size) +static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size, + bool changed_on_server) { - ctx->remote_i_size = new_i_size; + if (changed_on_server) + ctx->remote_i_size = new_i_size; + if (new_i_size < ctx->zero_point) + ctx->zero_point = new_i_size; } /** -- cgit v1.2.3 From 2ad28ce9b98f8b22feaecc0966c706a8ef59cbf0 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Mon, 1 Jan 2024 12:35:27 +0200 Subject: nvme: remove unused definition There is no users for NVMF_AUTH_HASH_LEN macro. Reviewed-by: Israel Rukshin Reviewed-by: Sagi Grimberg Signed-off-by: Max Gurtovoy Signed-off-by: Keith Busch --- include/linux/nvme.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 44325c068b6a..462c21e0e417 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -20,7 +20,6 @@ #define NVMF_TRSVCID_SIZE 32 #define NVMF_TRADDR_SIZE 256 #define NVMF_TSAS_SIZE 256 -#define NVMF_AUTH_HASH_LEN 64 #define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery" -- cgit v1.2.3 From 040a82be54c09a72162a3db2f5cd2ba289c0f224 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 13 Oct 2023 12:26:31 +0100 Subject: netfs: Rearrange netfs_io_subrequest to put request pointer first Rearrange the netfs_io_subrequest struct to put the netfs_io_request pointer (rreq) first. This then allows netfs_io_subrequest to be put in a union with a pointer to a wrapper around netfs_io_request. This will be useful in the future for cifs and maybe ceph. Signed-off-by: David Howells cc: Steve French cc: Shyam Prasad N cc: Rohith Surabattula cc: Jeff Layton cc: linux-cifs@vger.kernel.org cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 852956aa3c4b..d3bac60fcd6f 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -204,8 +204,8 @@ struct netfs_cache_resources { * the pages it points to can be relied on to exist for the duration. */ struct netfs_io_subrequest { - struct work_struct work; struct netfs_io_request *rreq; /* Supervising I/O request */ + struct work_struct work; struct list_head rreq_link; /* Link in rreq->subrequests */ struct iov_iter io_iter; /* Iterator for this subrequest */ loff_t start; /* Where to start the I/O */ -- cgit v1.2.3 From 92a714d727ec9e7ccfcc7432d348aba730145914 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 4 Jan 2024 15:52:11 +0000 Subject: netfs: Fix interaction between write-streaming and cachefiles culling An issue can occur between write-streaming (storing dirty data in partial non-uptodate pages) and a cachefiles object being culled to make space. The problem occurs because the cache object is only marked in use while there are files open using it. Once it has been released, it can be culled and the cookie marked disabled. At this point, a streaming write is permitted to occur (if the cache is active, we require pages to be prefetched and cached), but the cache can become active again before this gets flushed out - and then two effects can occur: (1) The cache may be asked to write out a region that's less than its DIO block size (assumed by cachefiles to be PAGE_SIZE) - and this causes one of two debugging statements to be emitted. (2) netfs_how_to_modify() gets confused because it sees a page that isn't allowed to be non-uptodate being uptodate and tries to prefetch it - leading to a warning that PG_fscache is set twice. Fix this by the following means: (1) Add a netfs_inode flag to disallow write-streaming to an inode and set it if we ever do local caching of that inode. It remains set for the lifetime of that inode - even if the cookie becomes disabled. (2) If the no-write-streaming flag is set, then make netfs_how_to_modify() always want to prefetch instead. (3) If netfs_how_to_modify() decides it wants to prefetch a folio, but that folio has write-streamed data in it, then it requires the folio be flushed first. (4) Export a counter of the number of times we wanted to prefetch a non-uptodate page, but found it had write-streamed data in it. (5) Export a counter of the number of times we cancelled a write to the cache because it didn't DIO align and remove the debug statements. Reported-by: Marc Dionne Signed-off-by: David Howells cc: Jeff Layton cc: linux-cachefs@redhat.com cc: linux-erofs@lists.ozlabs.org cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org --- include/linux/fscache-cache.h | 3 +++ include/linux/netfs.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index a174cedf4d90..bdf7f3eddf0a 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -189,17 +189,20 @@ extern atomic_t fscache_n_write; extern atomic_t fscache_n_no_write_space; extern atomic_t fscache_n_no_create_space; extern atomic_t fscache_n_culled; +extern atomic_t fscache_n_dio_misfit; #define fscache_count_read() atomic_inc(&fscache_n_read) #define fscache_count_write() atomic_inc(&fscache_n_write) #define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space) #define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space) #define fscache_count_culled() atomic_inc(&fscache_n_culled) +#define fscache_count_dio_misfit() atomic_inc(&fscache_n_dio_misfit) #else #define fscache_count_read() do {} while(0) #define fscache_count_write() do {} while(0) #define fscache_count_no_write_space() do {} while(0) #define fscache_count_no_create_space() do {} while(0) #define fscache_count_culled() do {} while(0) +#define fscache_count_dio_misfit() do {} while(0) #endif #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/netfs.h b/include/linux/netfs.h index d3bac60fcd6f..100cbb261269 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -142,6 +142,7 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ +#define NETFS_ICTX_NO_WRITE_STREAMING 3 /* Don't engage in write-streaming */ }; /* -- cgit v1.2.3 From 3b7cb745473aec7255d66e3854abaa9c3f46f952 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 8 Jan 2024 11:50:16 -0700 Subject: block: move __get_task_ioprio() into header file We call this once per IO, which can be millions of times per second. Since nobody really uses io priorities, or at least it isn't very common, this is all wasted time and can amount to as much as 3% of the total kernel time. Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/ioprio.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index 7578d4f6a969..d6a9b5b7ed16 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -47,7 +47,30 @@ static inline int task_nice_ioclass(struct task_struct *task) } #ifdef CONFIG_BLOCK -int __get_task_ioprio(struct task_struct *p); +/* + * If the task has set an I/O priority, use that. Otherwise, return + * the default I/O priority. + * + * Expected to be called for current task or with task_lock() held to keep + * io_context stable. + */ +static inline int __get_task_ioprio(struct task_struct *p) +{ + struct io_context *ioc = p->io_context; + int prio; + + if (p != current) + lockdep_assert_held(&p->alloc_lock); + if (ioc) + prio = ioc->ioprio; + else + prio = IOPRIO_DEFAULT; + + if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE) + prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p), + task_nice_ioprio(p)); + return prio; +} #else static inline int __get_task_ioprio(struct task_struct *p) { -- cgit v1.2.3 From 53889bcaf536b3abedeaf104019877cee37dd08b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 8 Jan 2024 11:51:57 -0700 Subject: block: make __get_task_ioprio() easier to read We don't need to do any gymnastics if we don't have an io_context assigned at all, so just return early with our default priority. Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/ioprio.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index d6a9b5b7ed16..db1249cd9692 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -59,13 +59,13 @@ static inline int __get_task_ioprio(struct task_struct *p) struct io_context *ioc = p->io_context; int prio; + if (!ioc) + return IOPRIO_DEFAULT; + if (p != current) lockdep_assert_held(&p->alloc_lock); - if (ioc) - prio = ioc->ioprio; - else - prio = IOPRIO_DEFAULT; + prio = ioc->ioprio; if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE) prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p), task_nice_ioprio(p)); -- cgit v1.2.3 From aaefabc4a5f7ae48682c4d2d5d10faaf95c08eb9 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 7 Nov 2023 10:44:41 +0800 Subject: ceph: try to allocate a smaller extent map for sparse read In fscrypt case and for a smaller read length we can predict the max count of the extent map. And for small read length use cases this could save some memories. [ idryomov: squash into a single patch to avoid build break, drop redundant variable in ceph_alloc_sparse_ext_map() ] Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index b8610e9d2471..fa018d5864e7 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -572,9 +572,12 @@ int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt); */ #define CEPH_SPARSE_EXT_ARRAY_INITIAL 16 -static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op) +static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt) { - return __ceph_alloc_sparse_ext_map(op, CEPH_SPARSE_EXT_ARRAY_INITIAL); + if (!cnt) + cnt = CEPH_SPARSE_EXT_ARRAY_INITIAL; + + return __ceph_alloc_sparse_ext_map(op, cnt); } extern void ceph_osdc_get_request(struct ceph_osd_request *req); -- cgit v1.2.3 From 5f4c01f1e3c7b0c8d1e5dd6f080531de7aa5e47b Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Mon, 15 Jan 2024 17:19:34 -0300 Subject: spinlock: Fix failing build for PREEMPT_RT Since 1d71b30e1f85 ("sched.h: Move (spin|rwlock)_needbreak() to spinlock.h") build fails for PREEMPT_RT, since there is no definition available of either spin_needbreak() and rwlock_needbreak(). Since it was moved on the mentioned commit, it was placed inside a !PREEMPT_RT part of the code, making it out of reach for an RT kernel. Fix this by moving code it a few lines down so it can be reached by an RT build, where it can also make use of the *_is_contended() definition added by the spinlock_rt.h. Fixes: d1d71b30e1f85 ("sched.h: Move (spin|rwlock)_needbreak() to spinlock.h") Signed-off-by: Leonardo Bras Signed-off-by: Kent Overstreet Acked-by: Waiman Long --- include/linux/spinlock.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 0c71f06454d9..b5c59fdad160 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -449,6 +449,12 @@ static __always_inline int spin_is_contended(spinlock_t *lock) return raw_spin_is_contended(&lock->rlock); } +#define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) + +#else /* !CONFIG_PREEMPT_RT */ +# include +#endif /* CONFIG_PREEMPT_RT */ + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, @@ -480,12 +486,6 @@ static inline int rwlock_needbreak(rwlock_t *lock) #endif } -#define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) - -#else /* !CONFIG_PREEMPT_RT */ -# include -#endif /* CONFIG_PREEMPT_RT */ - /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) -- cgit v1.2.3 From 7bed6f3d08b7af27b7015da8dc3acf2b9c1f21d7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 16 Jan 2024 21:29:59 +0000 Subject: block: Fix iterating over an empty bio with bio_for_each_folio_all If the bio contains no data, bio_first_folio() calls page_folio() on a NULL pointer and oopses. Move the test that we've reached the end of the bio from bio_next_folio() to bio_first_folio(). Reported-by: syzbot+8b23309d5788a79d3eea@syzkaller.appspotmail.com Reported-by: syzbot+004c1e0fced2b4bc3dcc@syzkaller.appspotmail.com Fixes: 640d1930bef4 ("block: Add bio_for_each_folio_all()") Cc: stable@vger.kernel.org Signed-off-by: Matthew Wilcox (Oracle) Link: https://lore.kernel.org/r/20240116212959.3413014-1-willy@infradead.org [axboe: add unlikely() to error case] Signed-off-by: Jens Axboe --- include/linux/bio.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index ec4db73e5f4e..875d792bffff 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -286,6 +286,11 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, { struct bio_vec *bvec = bio_first_bvec_all(bio) + i; + if (unlikely(i >= bio->bi_vcnt)) { + fi->folio = NULL; + return; + } + fi->folio = page_folio(bvec->bv_page); fi->offset = bvec->bv_offset + PAGE_SIZE * (bvec->bv_page - &fi->folio->page); @@ -303,10 +308,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); fi->_next = folio_next(fi->folio); - } else if (fi->_i + 1 < bio->bi_vcnt) { - bio_first_folio(fi, bio, fi->_i + 1); } else { - fi->folio = NULL; + bio_first_folio(fi, bio, fi->_i + 1); } } -- cgit v1.2.3 From 49e60333d743ae32db3bdde2f93bc818482dd741 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 17 Jan 2024 12:36:09 -0800 Subject: blk-mq: Remove the hctx 'run' debugfs attribute Nobody uses the debugfs hctx 'run' attribute. Hence remove this attribute and also the code that updates the corresponding member variable. Suggested-by: Jens Axboe Cc: Gabriel Ryan Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240117203609.4122520-1-bvanassche@acm.org Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index a676e116085f..7a8150a5f051 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -391,9 +391,6 @@ struct blk_mq_hw_ctx { */ struct blk_mq_tags *sched_tags; - /** @run: Number of dispatched requests. */ - unsigned long run; - /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; /** @queue_num: Index of this hardware queue. */ -- cgit v1.2.3 From ef175b29a242fea98f467f008237484b03c94834 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 15 Jan 2021 15:24:59 -0600 Subject: of: Stop circularly including of_device.h and of_platform.h The DT of_device.h and of_platform.h headers date back to the separate of_platform_bus_type before it was merged into the regular platform bus. As part of that merge prepping Arm DT support 13 years ago, they "temporarily" include each other. The headers also include platform_device.h and of.h. The result was lots of drivers relied on these implicit includes. Now the entire tree has been fixed over the last couple of cycles to explicitly include the necessary headers instead of relying on of_device.h and/or of_platform.h implicit includes, so the implicit and circular includes can finally be removed. Signed-off-by: Rob Herring --- include/linux/of_device.h | 5 +---- include/linux/of_platform.h | 4 ++-- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index a72661e47faa..9042bca5bb84 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -2,10 +2,7 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H -#include -#include /* temporary until merge */ - -#include +#include struct device; struct of_device_id; diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index fadfea575485..a2ff1ad48f7f 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -7,11 +7,11 @@ */ #include -#include -#include struct device; +struct device_node; struct of_device_id; +struct platform_device; /** * struct of_dev_auxdata - lookup table entry for device names & platform_data -- cgit v1.2.3 From d26270061ae66b915138af7cd73ca6f8b85e6b44 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 18 Jan 2024 12:31:55 -0800 Subject: string: Remove strlcpy() With all the users of strlcpy() removed[1] from the kernel, remove the API, self-tests, and other references. Leave mentions in Documentation (about its deprecation), and in checkpatch.pl (to help migrate host-only tools/ usage). Long live strscpy(). Link: https://github.com/KSPP/linux/issues/89 [1] Cc: Azeem Shaikh Cc: Andrew Morton Cc: Andy Whitcroft Cc: Joe Perches Cc: Dwaipayan Ray Cc: Lukas Bulwahn Cc: linux-hardening@vger.kernel.org Reviewed-by: Andy Shevchenko Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 51 ------------------------------------------ include/linux/string.h | 3 --- 2 files changed, 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 79ef6ac4c021..89a6888f2f9e 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -214,51 +214,6 @@ __kernel_size_t __fortify_strlen(const char * const POS p) return ret; } -/* Defined after fortified strlen() to reuse it. */ -extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); -/** - * strlcpy - Copy a string into another string buffer - * - * @p: pointer to destination of copy - * @q: pointer to NUL-terminated source string to copy - * @size: maximum number of bytes to write at @p - * - * If strlen(@q) >= @size, the copy of @q will be truncated at - * @size - 1 bytes. @p will always be NUL-terminated. - * - * Do not use this function. While FORTIFY_SOURCE tries to avoid - * over-reads when calculating strlen(@q), it is still possible. - * Prefer strscpy(), though note its different return values for - * detecting truncation. - * - * Returns total number of bytes written to @p, including terminating NUL. - * - */ -__FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size) -{ - const size_t p_size = __member_size(p); - const size_t q_size = __member_size(q); - size_t q_len; /* Full count of source string length. */ - size_t len; /* Count of characters going into destination. */ - - if (p_size == SIZE_MAX && q_size == SIZE_MAX) - return __real_strlcpy(p, q, size); - q_len = strlen(q); - len = (q_len >= size) ? size - 1 : q_len; - if (__builtin_constant_p(size) && __builtin_constant_p(q_len) && size) { - /* Write size is always larger than destination. */ - if (len >= p_size) - __write_overflow(); - } - if (size) { - if (len >= p_size) - fortify_panic(__func__); - __underlying_memcpy(p, q, len); - p[len] = '\0'; - } - return q_len; -} - /* Defined after fortified strnlen() to reuse it. */ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); /** @@ -272,12 +227,6 @@ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); * @p buffer. The behavior is undefined if the string buffers overlap. The * destination @p buffer is always NUL terminated, unless it's zero-sized. * - * Preferred to strlcpy() since the API doesn't require reading memory - * from the source @q string beyond the specified @size bytes, and since - * the return value is easier to error-check than strlcpy()'s. - * In addition, the implementation is robust to the string changing out - * from underneath it, unlike the current strlcpy() implementation. - * * Preferred to strncpy() since it always returns a valid string, and * doesn't unnecessarily force the tail of the destination buffer to be * zero padded. If padding is desired please use strscpy_pad(). diff --git a/include/linux/string.h b/include/linux/string.h index ce137830a0b9..ab148d8dbfc1 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -66,9 +66,6 @@ extern char * strcpy(char *,const char *); #ifndef __HAVE_ARCH_STRNCPY extern char * strncpy(char *,const char *, __kernel_size_t); #endif -#ifndef __HAVE_ARCH_STRLCPY -size_t strlcpy(char *, const char *, size_t); -#endif #ifndef __HAVE_ARCH_STRSCPY ssize_t strscpy(char *, const char *, size_t); #endif -- cgit v1.2.3 From a54d51fb2dfb846aedf3751af501e9688db447f5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Jan 2024 20:17:49 +0000 Subject: udp: fix busy polling Generic sk_busy_loop_end() only looks at sk->sk_receive_queue for presence of packets. Problem is that for UDP sockets after blamed commit, some packets could be present in another queue: udp_sk(sk)->reader_queue In some cases, a busy poller could spin until timeout expiration, even if some packets are available in udp_sk(sk)->reader_queue. v3: - make sk_busy_loop_end() nicer (Willem) v2: - add a READ_ONCE(sk->sk_family) in sk_is_inet() to avoid KCSAN splats. - add a sk_is_inet() check in sk_is_udp() (Willem feedback) - add a sk_is_inet() check in sk_is_tcp(). Fixes: 2276f58ac589 ("udp: use a separate rx queue for packet reception") Signed-off-by: Eric Dumazet Reviewed-by: Paolo Abeni Reviewed-by: Willem de Bruijn Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/linux/skmsg.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 888a4b217829..e65ec3fd2799 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -505,12 +505,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } -static inline bool sk_is_udp(const struct sock *sk) -{ - return sk->sk_type == SOCK_DGRAM && - sk->sk_protocol == IPPROTO_UDP; -} - #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) -- cgit v1.2.3 From 25461ce8b3d28528f2c55f5e737e99d2906eda83 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 15 Dec 2023 19:31:14 -0800 Subject: net/mlx5e: Use the correct lag ports number when creating TISes The cited commit moved the code of mlx5e_create_tises() and changed the loop to create TISes over MLX5_MAX_PORTS constant value, instead of getting the correct lag ports supported by the device, which can cause FW errors on devices with less than MLX5_MAX_PORTS ports. Change that back to mlx5e_get_num_lag_ports(mdev). Also IPoIB interfaces create there own TISes, they don't use the eth TISes, pass a flag to indicate that. This fixes the following errors that might appear in kernel log: mlx5_cmd_out_err:808:(pid 650): CREATE_TIS(0x912) op_mod(0x0) failed, status bad parameter(0x3), syndrome (0x595b5d), err(-22) mlx5e_create_mdev_resources:174:(pid 650): alloc tises failed, -22 Fixes: b25bd37c859f ("net/mlx5: Move TISes from priv to mdev HW resources") Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8c55ff351e5f..41f03b352401 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -681,6 +681,7 @@ struct mlx5e_resources { struct mlx5_sq_bfreg bfreg; #define MLX5_MAX_NUM_TC 8 u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]; + bool tisn_valid; } hw_objs; struct net_device *uplink_netdev; struct mutex uplink_netdev_lock; -- cgit v1.2.3 From cfbc3608a8c69b48bf238bd68f768192f0238e0d Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 19 Dec 2023 14:46:20 +0200 Subject: net/mlx5: Fix query of sd_group field The sd_group field moved in the HW spec from the MPIR register to the vport context. Align the query accordingly. Fixes: f5e956329960 ("net/mlx5: Expose Management PCIe Index Register (MPIR)") Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 10 +++++++--- include/linux/mlx5/vport.h | 1 + 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bf5320b28b8b..37230253f9f1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4036,8 +4036,13 @@ struct mlx5_ifc_nic_vport_context_bits { u8 affiliation_criteria[0x4]; u8 affiliated_vhca_id[0x10]; - u8 reserved_at_60[0xd0]; + u8 reserved_at_60[0xa0]; + u8 reserved_at_100[0x1]; + u8 sd_group[0x3]; + u8 reserved_at_104[0x1c]; + + u8 reserved_at_120[0x10]; u8 mtu[0x10]; u8 system_image_guid[0x40]; @@ -10122,8 +10127,7 @@ struct mlx5_ifc_mpir_reg_bits { u8 reserved_at_20[0x20]; u8 local_port[0x8]; - u8 reserved_at_28[0x15]; - u8 sd_group[0x3]; + u8 reserved_at_28[0x18]; u8 reserved_at_60[0x20]; }; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index fbb9bf447889..c36cc6d82926 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -72,6 +72,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); +int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group); int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, u16 vport, u64 node_guid); -- cgit v1.2.3 From ec7cc38ef9f83553102e84c82536971a81630739 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Sat, 30 Dec 2023 22:40:37 +0200 Subject: net/mlx5: Bridge, fix multicast packets sent to uplink To enable multicast packets which are offloaded in bridge multicast offload mode to be sent also to uplink, FTE bit uplink_hairpin_en should be set. Add this bit to FTE for the bridge multicast offload rules. Fixes: 18c2916cee12 ("net/mlx5: Bridge, snoop igmp/mld packets") Signed-off-by: Moshe Shemesh Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + include/linux/mlx5/mlx5_ifc.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 6f7725238abc..3fb428ce7d1c 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -132,6 +132,7 @@ struct mlx5_flow_handle; enum { FLOW_CONTEXT_HAS_TAG = BIT(0), + FLOW_CONTEXT_UPLINK_HAIRPIN_EN = BIT(1), }; struct mlx5_flow_context { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 37230253f9f1..c726f90ab752 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3576,7 +3576,7 @@ struct mlx5_ifc_flow_context_bits { u8 action[0x10]; u8 extended_destination[0x1]; - u8 reserved_at_81[0x1]; + u8 uplink_hairpin_en[0x1]; u8 flow_source[0x2]; u8 encrypt_decrypt_type[0x4]; u8 destination_list_size[0x18]; -- cgit v1.2.3 From 90383cc07895183c75a0db2460301c2ffd912359 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 24 Jan 2024 11:15:33 -0800 Subject: exec: Distinguish in_execve from in_exec Just to help distinguish the fs->in_exec flag from the current->in_execve flag, add comments in check_unsafe_exec() and copy_fs() for more context. Also note that in_execve is only used by TOMOYO now. Cc: Kentaro Takeda Cc: Tetsuo Handa Cc: Alexander Viro Cc: Christian Brauner Cc: Jan Kara Cc: Eric Biederman Cc: Andrew Morton Cc: Sebastian Andrzej Siewior Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Signed-off-by: Kees Cook --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index cdb8ea53c365..ffe8f618ab86 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -920,7 +920,7 @@ struct task_struct { unsigned sched_rt_mutex:1; #endif - /* Bit to tell LSMs we're in execve(): */ + /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK -- cgit v1.2.3