diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-03-30 04:55:37 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-03-30 04:55:37 +0300 |
| commit | 965181d7ef7e1a863477536dc328c23a7ebc8a1d (patch) | |
| tree | 80ee88a3ca55592b815f93bb6bfd92c397c7222c | |
| parent | 1ec48f95519bd3e920536118e8ddd30e28cde4ab (diff) | |
| parent | 7c9d845f0612e5bcd23456a2ec43be8ac43458f1 (diff) | |
| download | linux-965181d7ef7e1a863477536dc328c23a7ebc8a1d.tar.xz | |
Merge tag 'nfs-for-5.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs
Pull NFS client updates from Trond Myklebust:
"Highlights include:
Features:
- Switch NFS to use readahead instead of the obsolete readpages.
- Readdir fixes to improve cacheability of large directories when
there are multiple readers and writers.
- Readdir performance improvements when doing a seekdir() immediately
after opening the directory (common when re-exporting NFS).
- NFS swap improvements from Neil Brown.
- Loosen up memory allocation to permit direct reclaim and write back
in cases where there is no danger of deadlocking the writeback code
or NFS swap.
- Avoid sillyrename when the NFSv4 server claims to support the
necessary features to recover the unlinked but open file after
reboot.
Bugfixes:
- Patch from Olga to add a mount option to control NFSv4.1 session
trunking discovery, and default it to being off.
- Fix a lockup in nfs_do_recoalesce().
- Two fixes for list iterator variables being used when pointing to
the list head.
- Fix a kernel memory scribble when reading from a non-socket
transport in /sys/kernel/sunrpc.
- Fix a race where reconnecting to a server could leave the TCP
socket stuck forever in the connecting state.
- Patch from Neil to fix a shutdown race which can leave the SUNRPC
transport timer primed after we free the struct xprt itself.
- Patch from Xin Xiong to fix reference count leaks in the NFSv4.2
copy offload.
- Sunrpc patch from Olga to avoid resending a task on an offlined
transport.
Cleanups:
- Patches from Dave Wysochanski to clean up the fscache code"
* tag 'nfs-for-5.18-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (91 commits)
NFSv4/pNFS: Fix another issue with a list iterator pointing to the head
NFS: Don't loop forever in nfs_do_recoalesce()
SUNRPC: Don't return error values in sysfs read of closed files
SUNRPC: Do not dereference non-socket transports in sysfs
NFSv4.1: don't retry BIND_CONN_TO_SESSION on session error
SUNRPC don't resend a task on an offlined transport
NFS: replace usage of found with dedicated list iterator variable
SUNRPC: avoid race between mod_timer() and del_timer_sync()
pNFS/files: Ensure pNFS allocation modes are consistent with nfsiod
pNFS/flexfiles: Ensure pNFS allocation modes are consistent with nfsiod
NFSv4/pnfs: Ensure pNFS allocation modes are consistent with nfsiod
NFS: Avoid writeback threads getting stuck in mempool_alloc()
NFS: nfsiod should not block forever in mempool_alloc()
SUNRPC: Make the rpciod and xprtiod slab allocation modes consistent
SUNRPC: Fix unx_lookup_cred() allocation
NFS: Fix memory allocation in rpc_alloc_task()
NFS: Fix memory allocation in rpc_malloc()
SUNRPC: Improve accuracy of socket ENOBUFS determination
SUNRPC: Replace internal use of SOCKWQ_ASYNC_NOSPACE
SUNRPC: Fix socket waits for write buffer space
...
60 files changed, 1317 insertions, 813 deletions
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 14a72224b657..47a53b3362b6 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -4,6 +4,10 @@ config NFS_FS depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC + select CRYPTO + select CRYPTO_HASH + select XXHASH + select CRYPTO_XXHASH select NFS_ACL_SUPPORT if NFS_V3_ACL help Choose Y here if you want to access files residing on other diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index c343666d9a42..c8520284dda7 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -358,12 +358,11 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp, struct cb_process_state *cps) { struct cb_devicenotifyargs *args = argp; + const struct pnfs_layoutdriver_type *ld = NULL; uint32_t i; __be32 res = 0; - struct nfs_client *clp = cps->clp; - struct nfs_server *server = NULL; - if (!clp) { + if (!cps->clp) { res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION); goto out; } @@ -371,23 +370,15 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp, for (i = 0; i < args->ndevs; i++) { struct cb_devicenotifyitem *dev = &args->devs[i]; - if (!server || - server->pnfs_curr_ld->id != dev->cbd_layout_type) { - rcu_read_lock(); - list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) - if (server->pnfs_curr_ld && - server->pnfs_curr_ld->id == dev->cbd_layout_type) { - rcu_read_unlock(); - goto found; - } - rcu_read_unlock(); - continue; + if (!ld || ld->id != dev->cbd_layout_type) { + pnfs_put_layoutdriver(ld); + ld = pnfs_find_layoutdriver(dev->cbd_layout_type); + if (!ld) + continue; } - - found: - nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id); + nfs4_delete_deviceid(ld, cps->clp, &dev->cbd_dev_id); } - + pnfs_put_layoutdriver(ld); out: kfree(args->devs); return res; @@ -710,7 +701,7 @@ __be32 nfs4_callback_offload(void *data, void *dummy, struct nfs4_copy_state *copy, *tmp_copy; bool found = false; - copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); + copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL); if (!copy) return htonl(NFS4ERR_SERVERFAULT); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index f90de8043b0f..8dcb08e1a885 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -271,10 +271,6 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, n = ntohl(*p++); if (n == 0) goto out; - if (n > ULONG_MAX / sizeof(*args->devs)) { - status = htonl(NFS4ERR_BADXDR); - goto out; - } args->devs = kmalloc_array(n, sizeof(*args->devs), GFP_KERNEL); if (!args->devs) { diff --git a/fs/nfs/client.c b/fs/nfs/client.c index d1f34229e11a..e828504cc396 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -857,7 +857,8 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str } if (clp->rpc_ops->discover_trunking != NULL && - (server->caps & NFS_CAP_FS_LOCATIONS)) { + (server->caps & NFS_CAP_FS_LOCATIONS && + (server->flags & NFS_MOUNT_TRUNK_DISCOVERY))) { error = clp->rpc_ops->discover_trunking(server, mntfh); if (error < 0) return error; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 7c9eb679dbdb..5c97cad741a7 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -439,7 +439,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, struct nfs_delegation *freeme = NULL; int status = 0; - delegation = kmalloc(sizeof(*delegation), GFP_NOFS); + delegation = kmalloc(sizeof(*delegation), GFP_KERNEL_ACCOUNT); if (delegation == NULL) return -ENOMEM; nfs4_stateid_copy(&delegation->stateid, stateid); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 75cb1cbe4cde..bac4cf1a308e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -39,6 +39,7 @@ #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> +#include <linux/xxhash.h> #include "delegation.h" #include "iostat.h" @@ -69,26 +70,26 @@ const struct address_space_operations nfs_dir_aops = { .freepage = nfs_readdir_clear_array, }; -static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir) +#define NFS_INIT_DTSIZE PAGE_SIZE + +static struct nfs_open_dir_context * +alloc_nfs_open_dir_context(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); struct nfs_open_dir_context *ctx; - ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (ctx != NULL) { - ctx->duped = 0; ctx->attr_gencount = nfsi->attr_gencount; - ctx->dir_cookie = 0; - ctx->dup_cookie = 0; - ctx->page_index = 0; - ctx->eof = false; + ctx->dtsize = NFS_INIT_DTSIZE; spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) nfs_set_cache_invalid(dir, NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); - list_add(&ctx->list, &nfsi->open_files); - clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags); + list_add_tail_rcu(&ctx->list, &nfsi->open_files); + memcpy(ctx->verf, nfsi->cookieverf, sizeof(ctx->verf)); spin_unlock(&dir->i_lock); return ctx; } @@ -98,9 +99,9 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx) { spin_lock(&dir->i_lock); - list_del(&ctx->list); + list_del_rcu(&ctx->list); spin_unlock(&dir->i_lock); - kfree(ctx); + kfree_rcu(ctx, rcu_head); } /* @@ -142,6 +143,7 @@ struct nfs_cache_array_entry { }; struct nfs_cache_array { + u64 change_attr; u64 last_cookie; unsigned int size; unsigned char page_full : 1, @@ -155,11 +157,10 @@ struct nfs_readdir_descriptor { struct page *page; struct dir_context *ctx; pgoff_t page_index; + pgoff_t page_index_max; u64 dir_cookie; u64 last_cookie; - u64 dup_cookie; loff_t current_index; - loff_t prev_index; __be32 verf[NFS_DIR_VERIFIER_SIZE]; unsigned long dir_verifier; @@ -167,24 +168,47 @@ struct nfs_readdir_descriptor { unsigned long gencount; unsigned long attr_gencount; unsigned int cache_entry_index; - signed char duped; + unsigned int buffer_fills; + unsigned int dtsize; + bool clear_cache; bool plus; bool eob; bool eof; }; -static void nfs_readdir_array_init(struct nfs_cache_array *array) +static void nfs_set_dtsize(struct nfs_readdir_descriptor *desc, unsigned int sz) +{ + struct nfs_server *server = NFS_SERVER(file_inode(desc->file)); + unsigned int maxsize = server->dtsize; + + if (sz > maxsize) + sz = maxsize; + if (sz < NFS_MIN_FILE_IO_SIZE) + sz = NFS_MIN_FILE_IO_SIZE; + desc->dtsize = sz; +} + +static void nfs_shrink_dtsize(struct nfs_readdir_descriptor *desc) { - memset(array, 0, sizeof(struct nfs_cache_array)); + nfs_set_dtsize(desc, desc->dtsize >> 1); } -static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie) +static void nfs_grow_dtsize(struct nfs_readdir_descriptor *desc) +{ + nfs_set_dtsize(desc, desc->dtsize << 1); +} + +static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie, + u64 change_attr) { struct nfs_cache_array *array; array = kmap_atomic(page); - nfs_readdir_array_init(array); + array->change_attr = change_attr; array->last_cookie = last_cookie; + array->size = 0; + array->page_full = 0; + array->page_is_eof = 0; array->cookies_are_ordered = 1; kunmap_atomic(array); } @@ -192,25 +216,31 @@ static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie) /* * we are freeing strings created by nfs_add_to_readdir_array() */ -static -void nfs_readdir_clear_array(struct page *page) +static void nfs_readdir_clear_array(struct page *page) { struct nfs_cache_array *array; - int i; + unsigned int i; array = kmap_atomic(page); for (i = 0; i < array->size; i++) kfree(array->array[i].name); - nfs_readdir_array_init(array); + array->size = 0; kunmap_atomic(array); } +static void nfs_readdir_page_reinit_array(struct page *page, u64 last_cookie, + u64 change_attr) +{ + nfs_readdir_clear_array(page); + nfs_readdir_page_init_array(page, last_cookie, change_attr); +} + static struct page * nfs_readdir_page_array_alloc(u64 last_cookie, gfp_t gfp_flags) { struct page *page = alloc_page(gfp_flags); if (page) - nfs_readdir_page_init_array(page, last_cookie); + nfs_readdir_page_init_array(page, last_cookie, 0); return page; } @@ -222,6 +252,11 @@ static void nfs_readdir_page_array_free(struct page *page) } } +static u64 nfs_readdir_array_index_cookie(struct nfs_cache_array *array) +{ + return array->size == 0 ? array->last_cookie : array->array[0].cookie; +} + static void nfs_readdir_array_set_eof(struct nfs_cache_array *array) { array->page_is_eof = 1; @@ -251,36 +286,40 @@ static const char *nfs_readdir_copy_name(const char *name, unsigned int len) return ret; } +static size_t nfs_readdir_array_maxentries(void) +{ + return (PAGE_SIZE - sizeof(struct nfs_cache_array)) / + sizeof(struct nfs_cache_array_entry); +} + /* * Check that the next array entry lies entirely within the page bounds */ static int nfs_readdir_array_can_expand(struct nfs_cache_array *array) { - struct nfs_cache_array_entry *cache_entry; - if (array->page_full) return -ENOSPC; - cache_entry = &array->array[array->size + 1]; - if ((char *)cache_entry - (char *)array > PAGE_SIZE) { + if (array->size == nfs_readdir_array_maxentries()) { array->page_full = 1; return -ENOSPC; } return 0; } -static -int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) +static int nfs_readdir_page_array_append(struct page *page, + const struct nfs_entry *entry, + u64 *cookie) { struct nfs_cache_array *array; struct nfs_cache_array_entry *cache_entry; const char *name; - int ret; + int ret = -ENOMEM; name = nfs_readdir_copy_name(entry->name, entry->len); - if (!name) - return -ENOMEM; array = kmap_atomic(page); + if (!name) + goto out; ret = nfs_readdir_array_can_expand(array); if (ret) { kfree(name); @@ -288,7 +327,7 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) } cache_entry = &array->array[array->size]; - cache_entry->cookie = entry->prev_cookie; + cache_entry->cookie = array->last_cookie; cache_entry->ino = entry->ino; cache_entry->d_type = entry->d_type; cache_entry->name_len = entry->len; @@ -300,23 +339,75 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) if (entry->eof != 0) nfs_readdir_array_set_eof(array); out: + *cookie = array->last_cookie; + kunmap_atomic(array); + return ret; +} + +#define NFS_READDIR_COOKIE_MASK (U32_MAX >> 14) +/* + * Hash algorithm allowing content addressible access to sequences + * of directory cookies. Content is addressed by the value of the + * cookie index of the first readdir entry in a page. + * + * The xxhash algorithm is chosen because it is fast, and is supposed + * to result in a decent flat distribution of hashes. + * + * We then select only the first 18 bits to avoid issues with excessive + * memory use for the page cache XArray. 18 bits should allow the caching + * of 262144 pages of sequences of readdir entries. Since each page holds + * 127 readdir entries for a typical 64-bit system, that works out to a + * cache of ~ 33 million entries per directory. + */ +static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie) +{ + if (cookie == 0) + return 0; + return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK; +} + +static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, + u64 change_attr) +{ + struct nfs_cache_array *array = kmap_atomic(page); + int ret = true; + + if (array->change_attr != change_attr) + ret = false; + if (nfs_readdir_array_index_cookie(array) != last_cookie) + ret = false; kunmap_atomic(array); return ret; } +static void nfs_readdir_page_unlock_and_put(struct page *page) +{ + unlock_page(page); + put_page(page); +} + +static void nfs_readdir_page_init_and_validate(struct page *page, u64 cookie, + u64 change_attr) +{ + if (PageUptodate(page)) { + if (nfs_readdir_page_validate(page, cookie, change_attr)) + return; + nfs_readdir_clear_array(page); + } + nfs_readdir_page_init_array(page, cookie, change_attr); + SetPageUptodate(page); +} + static struct page *nfs_readdir_page_get_locked(struct address_space *mapping, - pgoff_t index, u64 last_cookie) + u64 cookie, u64 change_attr) { + pgoff_t index = nfs_readdir_page_cookie_hash(cookie); struct page *page; page = grab_cache_page(mapping, index); - if (page && !PageUptodate(page)) { - nfs_readdir_page_init_array(page, last_cookie); - if (invalidate_inode_pages2_range(mapping, index + 1, -1) < 0) - nfs_zap_mapping(mapping->host, mapping); - SetPageUptodate(page); - } - + if (!page) + return NULL; + nfs_readdir_page_init_and_validate(page, cookie, change_attr); return page; } @@ -351,24 +442,19 @@ static void nfs_readdir_page_set_eof(struct page *page) kunmap_atomic(array); } -static void nfs_readdir_page_unlock_and_put(struct page *page) -{ - unlock_page(page); - put_page(page); -} - static struct page *nfs_readdir_page_get_next(struct address_space *mapping, - pgoff_t index, u64 cookie) + u64 cookie, u64 change_attr) { + pgoff_t index = nfs_readdir_page_cookie_hash(cookie); struct page *page; - page = nfs_readdir_page_get_locked(mapping, index, cookie); - if (page) { - if (nfs_readdir_page_last_cookie(page) == cookie) - return page; - nfs_readdir_page_unlock_and_put(page); - } - return NULL; + page = grab_cache_page_nowait(mapping, index); + if (!page) + return NULL; + nfs_readdir_page_init_and_validate(page, cookie, change_attr); + if (nfs_readdir_page_last_cookie(page) != cookie) + nfs_readdir_page_reinit_array(page, cookie, change_attr); + return page; } static inline @@ -390,6 +476,25 @@ bool nfs_readdir_use_cookie(const struct file *filp) return true; } +static void nfs_readdir_seek_next_array(struct nfs_cache_array *array, + struct nfs_readdir_descriptor *desc) +{ + if (array->page_full) { + desc->last_cookie = array->last_cookie; + desc->current_index += array->size; + desc->cache_entry_index = 0; + desc->page_index++; + } else + desc->last_cookie = nfs_readdir_array_index_cookie(array); +} + +static void nfs_readdir_rewind_search(struct nfs_readdir_descriptor *desc) +{ + desc->current_index = 0; + desc->last_cookie = 0; + desc->page_index = 0; +} + static int nfs_readdir_search_for_pos(struct nfs_cache_array *array, struct nfs_readdir_descriptor *desc) { @@ -401,6 +506,7 @@ static int nfs_readdir_search_for_pos(struct nfs_cache_array *array, if (diff >= array->size) { if (array->page_is_eof) goto out_eof; + nfs_readdir_seek_next_array(array, desc); return -EAGAIN; } @@ -413,16 +519,6 @@ out_eof: return -EBADCOOKIE; } -static bool -nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi) -{ - if (nfsi->cache_validity & (NFS_INO_INVALID_CHANGE | - NFS_INO_INVALID_DATA)) - return false; - smp_rmb(); - return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags); -} - static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array, u64 cookie) { @@ -439,8 +535,7 @@ static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array, static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, struct nfs_readdir_descriptor *desc) { - int i; - loff_t new_pos; + unsigned int i; int status = -EAGAIN; if (!nfs_readdir_array_cookie_in_range(array, desc->dir_cookie)) @@ -448,33 +543,10 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, for (i = 0; i < array->size; i++) { if (array->array[i].cookie == desc->dir_cookie) { - struct nfs_inode *nfsi = NFS_I(file_inode(desc->file)); - - new_pos = desc->current_index + i; - if (desc->attr_gencount != nfsi->attr_gencount || - !nfs_readdir_inode_mapping_valid(nfsi)) { - desc->duped = 0; - desc->attr_gencount = nfsi->attr_gencount; - } else if (new_pos < desc->prev_index) { - if (desc->duped > 0 - && desc->dup_cookie == desc->dir_cookie) { - if (printk_ratelimit()) { - pr_notice("NFS: directory %pD2 contains a readdir loop." - "Please contact your server vendor. " - "The file: %s has duplicate cookie %llu\n", - desc->file, array->array[i].name, desc->dir_cookie); - } - status = -ELOOP; - goto out; - } - desc->dup_cookie = desc->dir_cookie; - desc->duped = -1; - } if (nfs_readdir_use_cookie(desc->file)) desc->ctx->pos = desc->dir_cookie; else - desc->ctx->pos = new_pos; - desc->prev_index = new_pos; + desc->ctx->pos = desc->current_index + i; desc->cache_entry_index = i; return 0; } @@ -484,8 +556,8 @@ check_eof: status = -EBADCOOKIE; if (desc->dir_cookie == array->last_cookie) desc->eof = true; - } -out: + } else + nfs_readdir_seek_next_array(array, desc); return status; } @@ -501,11 +573,6 @@ static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc) else status = nfs_readdir_search_for_cookie(array, desc); - if (status == -EAGAIN) { - desc->last_cookie = array->last_cookie; - desc->current_index += array->size; - desc->page_index++; - } kunmap_atomic(array); return status; } @@ -541,7 +608,6 @@ static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc, /* We requested READDIRPLUS, but the server doesn't grok it */ if (error == -ENOTSUPP && desc->plus) { NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS; - clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); desc->plus = arg.plus = false; goto again; } @@ -591,51 +657,68 @@ int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry) return 1; } -static -bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx) +#define NFS_READDIR_CACHE_USAGE_THRESHOLD (8UL) + +static bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx, + unsigned int cache_hits, + unsigned int cache_misses) { if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS)) return false; - if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags)) - return true; - if (ctx->pos == 0) + if (ctx->pos == 0 || + cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD) return true; return false; } /* - * This function is called by the lookup and getattr code to request the + * This function is called by the getattr code to request the * use of readdirplus to accelerate any future lookups in the same * directory. */ -void nfs_advise_use_readdirplus(struct inode *dir) +void nfs_readdir_record_entry_cache_hit(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); + struct nfs_open_dir_context *ctx; if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && - !list_empty(&nfsi->open_files)) - set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); + S_ISDIR(dir->i_mode)) { + rcu_read_lock(); + list_for_each_entry_rcu (ctx, &nfsi->open_files, list) + atomic_inc(&ctx->cache_hits); + rcu_read_unlock(); + } } /* * This function is mainly for use by nfs_getattr(). * * If this is an 'ls -l', we want to force use of readdirplus. - * Do this by checking if there is an active file descriptor - * and calling nfs_advise_use_readdirplus, then forcing a - * cache flush. */ -void nfs_force_use_readdirplus(struct inode *dir) +void nfs_readdir_record_entry_cache_miss(struct inode *dir) { struct nfs_inode *nfsi = NFS_I(dir); + struct nfs_open_dir_context *ctx; if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && - !list_empty(&nfsi->open_files)) { - set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); - set_bit(NFS_INO_FORCE_READDIR, &nfsi->flags); + S_ISDIR(dir->i_mode)) { + rcu_read_lock(); + list_for_each_entry_rcu (ctx, &nfsi->open_files, list) + atomic_inc(&ctx->cache_misses); + rcu_read_unlock(); } } +static void nfs_lookup_advise_force_readdirplus(struct inode *dir, + unsigned int flags) +{ + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + return; + if (flags & (LOOKUP_EXCL | LOOKUP_PARENT | LOOKUP_REVAL)) + return; + nfs_readdir_record_entry_cache_miss(dir); +} + static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry, unsigned long dir_verifier) @@ -686,8 +769,12 @@ again: status = nfs_refresh_inode(d_inode(dentry), entry->fattr); if (!status) nfs_setsecurity(d_inode(dentry), entry->fattr); + trace_nfs_readdir_lookup_revalidate(d_inode(parent), + dentry, 0, status); goto out; } else { + trace_nfs_readdir_lookup_revalidate_failed( + d_inode(parent), dentry, 0); d_invalidate(dentry); dput(dentry); dentry = NULL; @@ -709,22 +796,38 @@ again: dentry = alias; } nfs_set_verifier(dentry, dir_verifier); + trace_nfs_readdir_lookup(d_inode(parent), dentry, 0); out: dput(dentry); } +static int nfs_readdir_entry_decode(struct nfs_readdir_descriptor *desc, + struct nfs_entry *entry, + struct xdr_stream *stream) +{ + int ret; + + if (entry->fattr->label) + entry->fattr->label->len = NFS4_MAXLABELLEN; + ret = xdr_decode(desc, entry, stream); + if (ret || !desc->plus) + return ret; + nfs_prime_dcache(file_dentry(desc->file), entry, desc->dir_verifier); + return 0; +} + /* Perform conversion from xdr to cache array */ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, struct nfs_entry *entry, - struct page **xdr_pages, - unsigned int buflen, - struct page **arrays, - size_t narrays) + struct page **xdr_pages, unsigned int buflen, + struct page **arrays, size_t narrays, + u64 change_attr) { struct address_space *mapping = desc->file->f_mapping; struct xdr_stream stream; struct xdr_buf buf; struct page *scratch, *new, *page = *arrays; + u64 cookie; int status; scratch = alloc_page(GFP_KERNEL); @@ -735,54 +838,50 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, xdr_set_scratch_page(&stream, scratch); do { - if (entry->fattr->label) - entry->fattr->label->len = NFS4_MAXLABELLEN; - - status = xdr_decode(desc, entry, &stream); + status = nfs_readdir_entry_decode(desc, entry, &stream); if (status != 0) break; - if (desc->plus) - nfs_prime_dcache(file_dentry(desc->file), entry, - desc->dir_verifier); - - status = nfs_readdir_add_to_array(entry, page); + status = nfs_readdir_page_array_append(page, entry, &cookie); if (status != -ENOSPC) continue; if (page->mapping != mapping) { if (!--narrays) break; - new = nfs_readdir_page_array_alloc(entry->prev_cookie, - GFP_KERNEL); + new = nfs_readdir_page_array_alloc(cookie, GFP_KERNEL); if (!new) break; arrays++; *arrays = page = new; } else { - new = nfs_readdir_page_get_next(mapping, - page->index + 1, - entry->prev_cookie); + new = nfs_readdir_page_get_next(mapping, cookie, + change_attr); if (!new) break; if (page != *arrays) nfs_readdir_page_unlock_and_put(page); page = new; } - status = nfs_readdir_add_to_array(entry, page); + desc->page_index_max++; + status = nfs_readdir_page_array_append(page, entry, &cookie); } while (!status && !entry->eof); switch (status) { case -EBADCOOKIE: - if (entry->eof) { - nfs_readdir_page_set_eof(page); - status = 0; - } - break; - case -ENOSPC: + if (!entry->eof) + break; + nfs_readdir_page_set_eof(page); + fallthrough; case -EAGAIN: status = 0; break; + case -ENOSPC: + status = 0; + if (!desc->plus) + break; + while (!nfs_readdir_entry_decode(desc, entry, &stream)) + ; } if (page != *arrays) @@ -828,12 +927,14 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, __be32 *verf_arg, __be32 *verf_res, struct page **arrays, size_t narrays) { + u64 change_attr; struct page **pages; struct page *page = *arrays; struct nfs_entry *entry; size_t array_size; struct inode *inode = file_inode(desc->file); - size_t dtsize = NFS_SERVER(inode)->dtsize; + unsigned int dtsize = desc->dtsize; + unsigned int pglen; int status = -ENOMEM; entry = kzalloc(sizeof(*entry), GFP_KERNEL); @@ -851,27 +952,21 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, if (!pages) goto out; - do { - unsigned int pglen; - status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, - pages, dtsize, - verf_res); - if (status < 0) - break; - - pglen = status; - if (pglen == 0) { - nfs_readdir_page_set_eof(page); - break; - } - - verf_arg = verf_res; + change_attr = inode_peek_iversion_raw(inode); + status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, pages, + dtsize, verf_res); + if (status < 0) + goto free_pages; + pglen = status; + if (pglen != 0) status = nfs_readdir_page_filler(desc, entry, pages, pglen, - arrays, narrays); - } while (!status && nfs_readdir_page_needs_filling(page) && - page_mapping(page)); + arrays, narrays, change_attr); + else + nfs_readdir_page_set_eof(page); + desc->buffer_fills++; +free_pages: nfs_readdir_free_pages(pages, array_size); out: nfs_free_fattr(entry->fattr); @@ -896,9 +991,17 @@ nfs_readdir_page_unlock_and_put_cached(struct nfs_readdir_descriptor *desc) static struct page * nfs_readdir_page_get_cached(struct nfs_readdir_descriptor *desc) { - return nfs_readdir_page_get_locked(desc->file->f_mapping, - desc->page_index, - desc->last_cookie); + struct address_space *mapping = desc->file->f_mapping; + u64 change_attr = inode_peek_iversion_raw(mapping->host); + u64 cookie = desc->last_cookie; + struct page *page; + + page = nfs_readdir_page_get_locked(mapping, cookie, change_attr); + if (!page) + return NULL; + if (desc->clear_cache && !nfs_readdir_page_needs_filling(page)) + nfs_readdir_page_reinit_array(page, cookie, change_attr); + return page; } /* @@ -916,13 +1019,23 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) if (!desc->page) return -ENOMEM; if (nfs_readdir_page_needs_filling(desc->page)) { + /* Grow the dtsize if we had to go back for more pages */ + if (desc->page_index == desc->page_index_max) + nfs_grow_dtsize(desc); + desc->page_index_max = desc->page_index; + trace_nfs_readdir_cache_fill(desc->file, nfsi->cookieverf, + desc->last_cookie, + desc->page->index, desc->dtsize); res = nfs_readdir_xdr_to_array(desc, nfsi->cookieverf, verf, &desc->page, 1); if (res < 0) { nfs_readdir_page_unlock_and_put_cached(desc); + trace_nfs_readdir_cache_fill_done(inode, res); if (res == -EBADCOOKIE || res == -ENOTSYNC) { invalidate_inode_pages2(desc->file->f_mapping); - desc->page_index = 0; + nfs_readdir_rewind_search(desc); + trace_nfs_readdir_invalidate_cache_range( + inode, 0, MAX_LFS_FILESIZE); return -EAGAIN; } return res; @@ -930,9 +1043,16 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) /* * Set the cookie verifier if the page cache was empty */ - if (desc->page_index == 0) + if (desc->last_cookie == 0 && + memcmp(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf))) { memcpy(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf)); + invalidate_inode_pages2_range(desc->file->f_mapping, 1, + -1); + trace_nfs_readdir_invalidate_cache_range( + inode, 1, MAX_LFS_FILESIZE); + } + desc->clear_cache = false; } res = nfs_readdir_search_array(desc); if (res == 0) @@ -941,34 +1061,12 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) return res; } -static bool nfs_readdir_dont_search_cache(struct nfs_readdir_descriptor *desc) -{ - struct address_space *mapping = desc->file->f_mapping; - struct inode *dir = file_inode(desc->file); - unsigned int dtsize = NFS_SERVER(dir)->dtsize; - loff_t size = i_size_read(dir); - - /* - * Default to uncached readdir if the page cache is empty, and - * we're looking for a non-zero cookie in a large directory. - */ - return desc->dir_cookie != 0 && mapping->nrpages == 0 && size > dtsize; -} - /* Search for desc->dir_cookie from the beginning of the page cache */ static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc) { int res; - if (nfs_readdir_dont_search_cache(desc)) - return -EBADCOOKIE; - do { - if (desc->page_index == 0) { - desc->current_index = 0; - desc->prev_index = 0; - desc->last_cookie = 0; - } res = find_and_lock_cache_page(desc); } while (res == -EAGAIN); return res; @@ -982,7 +1080,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, { struct file *file = desc->file; struct nfs_cache_array *array; - unsigned int i = 0; + unsigned int i; array = kmap(desc->page); for (i = desc->cache_entry_index; i < array->size; i++) { @@ -995,16 +1093,17 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, break; } memcpy(desc->verf, verf, sizeof(desc->verf)); - if (i < (array->size-1)) - desc->dir_cookie = array->array[i+1].cookie; - else + if (i == array->size - 1) { desc->dir_cookie = array->last_cookie; + nfs_readdir_seek_next_array(array, desc); + } else { + desc->dir_cookie = array->array[i + 1].cookie; + desc->last_cookie = array->array[0].cookie; + } if (nfs_readdir_use_cookie(file)) desc->ctx->pos = desc->dir_cookie; else desc->ctx->pos++; - if (desc->duped != 0) - desc->duped = 1; } if (array->page_is_eof) desc->eof = !desc->eob; @@ -1046,9 +1145,16 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) desc->page_index = 0; desc->cache_entry_index = 0; desc->last_cookie = desc->dir_cookie; - desc->duped = 0; + desc->page_index_max = 0; + + trace_nfs_readdir_uncached(desc->file, desc->verf, desc->last_cookie, + -1, desc->dtsize); status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz); + if (status < 0) { + trace_nfs_readdir_uncached_done(file_inode(desc->file), status); + goto out_free; + } for (i = 0; !desc->eob && i < sz && arrays[i]; i++) { desc->page = arrays[i]; @@ -1056,15 +1162,44 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) } desc->page = NULL; - + /* + * Grow the dtsize if we have to go back for more pages, + * or shrink it if we're reading too many. + */ + if (!desc->eof) { + if (!desc->eob) + nfs_grow_dtsize(desc); + else if (desc->buffer_fills == 1 && + i < (desc->page_index_max >> 1)) + nfs_shrink_dtsize(desc); + } +out_free: for (i = 0; i < sz && arrays[i]; i++) nfs_readdir_page_array_free(arrays[i]); out: + if (!nfs_readdir_use_cookie(desc->file)) + nfs_readdir_rewind_search(desc); + desc->page_index_max = -1; kfree(arrays); dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status); return status; } +#define NFS_READDIR_CACHE_MISS_THRESHOLD (16UL) + +static bool nfs_readdir_handle_cache_misses(struct inode *inode, + struct nfs_readdir_descriptor *desc, + unsigned int cache_misses, + bool force_clear) +{ + if (desc->ctx->pos == 0 || !desc->plus) + return false; + if (cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD && !force_clear) + return false; + trace_nfs_readdir_force_readdirplus(inode); + return true; +} + /* The file offset position represents the dirent entry number. A last cookie cache takes care of the common case of reading the whole directory. @@ -1076,7 +1211,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_dir_context *dir_ctx = file->private_data; struct nfs_readdir_descriptor *desc; - pgoff_t page_index; + unsigned int cache_hits, cache_misses; + bool force_clear; int res; dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n", @@ -1089,11 +1225,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) * to either find the entry with the appropriate number or * revalidate the cookie. */ - if (ctx->pos == 0 || nfs_attribute_cache_expired(inode)) { - res = nfs_revalidate_mapping(inode, file->f_mapping); - if (res < 0) - goto out; - } + nfs_revalidate_mapping(inode, file->f_mapping); res = -ENOMEM; desc = kzalloc(sizeof(*desc), GFP_KERNEL); @@ -1101,16 +1233,19 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) goto out; desc->file = file; desc->ctx = ctx; - desc->plus = nfs_use_readdirplus(inode, ctx); + desc->page_index_max = -1; spin_lock(&file->f_lock); desc->dir_cookie = dir_ctx->dir_cookie; - desc->dup_cookie = dir_ctx->dup_cookie; - desc->duped = dir_ctx->duped; - page_index = dir_ctx->page_index; + desc->page_index = dir_ctx->page_index; + desc->last_cookie = dir_ctx->last_cookie; desc->attr_gencount = dir_ctx->attr_gencount; desc->eof = dir_ctx->eof; + nfs_set_dtsize(desc, dir_ctx->dtsize); memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf)); + cache_hits = atomic_xchg(&dir_ctx->cache_hits, 0); + cache_misses = atomic_xchg(&dir_ctx->cache_misses, 0); + force_clear = dir_ctx->force_clear; spin_unlock(&file->f_lock); if (desc->eof) { @@ -1118,9 +1253,10 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) goto out_free; } - if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) && - list_is_singular(&nfsi->open_files)) - invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1); + desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses); + force_clear = nfs_readdir_handle_cache_misses(inode, desc, cache_misses, + force_clear); + desc->clear_cache = force_clear; do { res = readdir_search_pagecache(desc); @@ -1139,9 +1275,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) break; } if (res == -ETOOSMALL && desc->plus) { - clear_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); nfs_zap_caches(inode); - desc->page_index = 0; desc->plus = false; desc->eof = false; continue; @@ -1151,15 +1285,18 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) nfs_do_filldir(desc, nfsi->cookieverf); nfs_readdir_page_unlock_and_put_cached(desc); + if (desc->page_index == desc->page_index_max) + desc->clear_cache = force_clear; } while (!desc->eob && !desc->eof); spin_lock(&file->f_lock); dir_ctx->dir_cookie = desc->dir_cookie; - dir_ctx->dup_cookie = desc->dup_cookie; - dir_ctx->duped = desc->duped; + dir_ctx->last_cookie = desc->last_cookie; dir_ctx->attr_gencount = desc->attr_gencount; dir_ctx->page_index = desc->page_index; + dir_ctx->force_clear = force_clear; dir_ctx->eof = desc->eof; + dir_ctx->dtsize = desc->dtsize; memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf)); spin_unlock(&file->f_lock); out_free: @@ -1197,13 +1334,14 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) } if (offset != filp->f_pos) { filp->f_pos = offset; - if (nfs_readdir_use_cookie(filp)) - dir_ctx->dir_cookie = offset; - else + dir_ctx->page_index = 0; + if (!nfs_readdir_use_cookie(filp)) { dir_ctx->dir_cookie = 0; - if (offset == 0) - memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf)); - dir_ctx->duped = 0; + dir_ctx->last_cookie = 0; + } else { + dir_ctx->dir_cookie = offset; + dir_ctx->last_cookie = offset; + } dir_ctx->eof = false; } spin_unlock(&filp->f_lock); @@ -1419,7 +1557,12 @@ int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags) if (flags & LOOKUP_REVAL) goto out_force; out: - return (inode->i_nlink == 0) ? -ESTALE : 0; + if (inode->i_nlink > 0 || + (inode->i_nlink == 0 && + test_bit(NFS_INO_PRESERVE_UNLINKED, &NFS_I(inode)->flags))) + return 0; + else + return -ESTALE; out_force: if (flags & LOOKUP_RCU) return -ECHILD; @@ -1469,9 +1612,7 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry, { switch (error) { case 1: - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n", - __func__, dentry); - return 1; + break; case 0: /* * We can't d_drop the root of a disconnected tree: @@ -1480,13 +1621,10 @@ nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry, * inodes on unmount and further oopses. */ if (inode && IS_ROOT(dentry)) - return 1; - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n", - __func__, dentry); - return 0; + error = 1; + break; } - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n", - __func__, dentry, error); + trace_nfs_lookup_revalidate_exit(dir, dentry, 0, error); return error; } @@ -1511,15 +1649,17 @@ nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry, return nfs_lookup_revalidate_done(dir, dentry, inode, 1); } -static int -nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, - struct inode *inode) +static int nfs_lookup_revalidate_dentry(struct inode *dir, + struct dentry *dentry, + struct inode *inode, unsigned int flags) { struct nfs_fh *fhandle; struct nfs_fattr *fattr; unsigned long dir_verifier; int ret; + trace_nfs_lookup_revalidate_enter(dir, dentry, flags); + ret = -ENOMEM; fhandle = nfs_alloc_fhandle(); fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); @@ -1540,6 +1680,10 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, } goto out; } + + /* Request help from readdirplus */ + nfs_lookup_advise_force_readdirplus(dir, flags); + ret = 0; if (nfs_compare_fh(NFS_FH(inode), fhandle)) goto out; @@ -1549,8 +1693,6 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, nfs_setsecurity(inode, fattr); nfs_set_verifier(dentry, dir_verifier); - /* set a readdirplus hint that we had a cache miss */ - nfs_force_use_readdirplus(dir); ret = 1; out: nfs_free_fattr(fattr); @@ -1607,7 +1749,6 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, nfs_mark_dir_for_revalidate(dir); goto out_bad; } - nfs_advise_use_readdirplus(dir); goto out_valid; } @@ -1617,10 +1758,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, if (NFS_STALE(inode)) goto out_bad; - trace_nfs_lookup_revalidate_enter(dir, dentry, flags); - error = nfs_lookup_revalidate_dentry(dir, dentry, inode); - trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); - return error; + return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags); out_valid: return nfs_lookup_revalidate_done(dir, dentry, inode, 1); out_bad: @@ -1814,7 +1952,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in goto out; /* Notify readdir to use READDIRPLUS */ - nfs_force_use_readdirplus(dir); + nfs_lookup_advise_force_readdirplus(dir, flags); no_entry: res = d_splice_alias(inode, dentry); @@ -2077,7 +2215,7 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, reval_dentry: if (flags & LOOKUP_RCU) return -ECHILD; - return nfs_lookup_revalidate_dentry(dir, dentry, inode); + return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags); full_reval: return nfs_do_lookup_revalidate(dir, dentry, flags); @@ -2330,7 +2468,8 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) trace_nfs_unlink_enter(dir, dentry); spin_lock(&dentry->d_lock); - if (d_count(dentry) > 1) { + if (d_count(dentry) > 1 && !test_bit(NFS_INO_PRESERVE_UNLINKED, + &NFS_I(d_inode(dentry))->flags)) { spin_unlock(&dentry->d_lock); /* Start asynchronous writeout of the inode */ write_inode_now(d_inode(dentry), 0); @@ -2989,11 +3128,8 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) /* * Determine which access bits we want to ask for... */ - cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND; - if (nfs_server_capable(inode, NFS_CAP_XATTR)) { - cache.mask |= NFS_ACCESS_XAREAD | NFS_ACCESS_XAWRITE | - NFS_ACCESS_XALIST; - } + cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND | + nfs_access_xattr_mask(NFS_SERVER(inode)); if (S_ISDIR(inode->i_mode)) cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP; else diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index eabfdab543c8..11c566d8769f 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -173,8 +173,8 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); if (iov_iter_rw(iter) == READ) - return nfs_file_direct_read(iocb, iter); - return nfs_file_direct_write(iocb, iter); + return nfs_file_direct_read(iocb, iter, true); + return nfs_file_direct_write(iocb, iter, true); } static void nfs_direct_release_pages(struct page **pages, unsigned int npages) @@ -425,6 +425,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers into which to read data + * @swap: flag indicating this is swap IO, not O_DIRECT IO * * We use this function for direct reads instead of calling * generic_file_aio_read() in order to avoid gfar's check to see if @@ -440,7 +441,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) +ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, + bool swap) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -482,12 +484,14 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) if (iter_is_iovec(iter)) dreq->flags = NFS_ODIRECT_SHOULD_DIRTY; - nfs_start_io_direct(inode); + if (!swap) + nfs_start_io_direct(inode); NFS_I(inode)->read_io += count; requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); - nfs_end_io_direct(inode); + if (!swap) + nfs_end_io_direct(inode); if (requested > 0) { result = nfs_direct_wait(dreq); @@ -790,7 +794,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { */ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, struct iov_iter *iter, - loff_t pos) + loff_t pos, int ioflags) { struct nfs_pageio_descriptor desc; struct inode *inode = dreq->inode; @@ -798,7 +802,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, size_t requested_bytes = 0; size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE); - nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false, + nfs_pageio_init_write(&desc, inode, ioflags, false, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; get_dreq(dreq); @@ -876,6 +880,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block * @iter: vector of user buffers from which to write data + * @swap: flag indicating this is swap IO, not O_DIRECT IO * * We use this function for direct writes instead of calling * generic_file_aio_write() in order to avoid taking the inode @@ -892,7 +897,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * Note that O_APPEND is not supported for NFS direct writes, as there * is no atomic O_APPEND write facility in the NFS protocol. */ -ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) +ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, + bool swap) { ssize_t result, requested; size_t count; @@ -906,7 +912,11 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) dfprintk(FILE, "NFS: direct write(%pD2, %zd@%Ld)\n", file, iov_iter_count(iter), (long long) iocb->ki_pos); - result = generic_write_checks(iocb, iter); + if (swap) + /* bypass generic checks */ + result = iov_iter_count(iter); + else + result = generic_write_checks(iocb, iter); if (result <= 0) return result; count = result; @@ -937,16 +947,22 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) dreq->iocb = iocb; pnfs_init_ds_commit_info_ops(&dreq->ds_cinfo, inode); - nfs_start_io_direct(inode); + if (swap) { + requested = nfs_direct_write_schedule_iovec(dreq, iter, pos, + FLUSH_STABLE); + } else { + nfs_start_io_direct(inode); - requested = nfs_direct_write_schedule_iovec(dreq, iter, pos); + requested = nfs_direct_write_schedule_iovec(dreq, iter, pos, + FLUSH_COND_STABLE); - if (mapping->nrpages) { - invalidate_inode_pages2_range(mapping, - pos >> PAGE_SHIFT, end); - } + if (mapping->nrpages) { + invalidate_inode_pages2_range(mapping, + pos >> PAGE_SHIFT, end); + } - nfs_end_io_direct(inode); + nfs_end_io_direct(inode); + } if (requested > 0) { result = nfs_direct_wait(dreq); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 2df2a5392737..b0ca244c50d0 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -44,11 +44,6 @@ static const struct vm_operations_struct nfs_file_vm_ops; -/* Hack for future NFS swap support */ -#ifndef IS_SWAPFILE -# define IS_SWAPFILE(inode) (0) -#endif - int nfs_check_flags(int flags) { if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT)) @@ -162,7 +157,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to) ssize_t result; if (iocb->ki_flags & IOCB_DIRECT) - return nfs_file_direct_read(iocb, to); + return nfs_file_direct_read(iocb, to, false); dprintk("NFS: read(%pD2, %zu@%lu)\n", iocb->ki_filp, @@ -488,8 +483,9 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, { unsigned long blocks; long long isize; - struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); - struct inode *inode = file->f_mapping->host; + struct inode *inode = file_inode(file); + struct rpc_clnt *clnt = NFS_CLIENT(inode); + struct nfs_client *cl = NFS_SERVER(inode)->nfs_client; spin_lock(&inode->i_lock); blocks = inode->i_blocks; @@ -502,19 +498,27 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, *span = sis->pages; + + if (cl->rpc_ops->enable_swap) + cl->rpc_ops->enable_swap(inode); + return rpc_clnt_swap_activate(clnt); } static void nfs_swap_deactivate(struct file *file) { - struct rpc_clnt *clnt = NFS_CLIENT(file->f_mapping->host); + struct inode *inode = file_inode(file); + struct rpc_clnt *clnt = NFS_CLIENT(inode); + struct nfs_client *cl = NFS_SERVER(inode)->nfs_client; rpc_clnt_swap_deactivate(clnt); + if (cl->rpc_ops->disable_swap) + cl->rpc_ops->disable_swap(file_inode(file)); } const struct address_space_operations nfs_file_aops = { .readpage = nfs_readpage, - .readpages = nfs_readpages, + .readahead = nfs_readahead, .dirty_folio = filemap_dirty_folio, .writepage = nfs_writepage, .writepages = nfs_writepages, @@ -619,7 +623,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) return result; if (iocb->ki_flags & IOCB_DIRECT) - return nfs_file_direct_write(iocb, from); + return nfs_file_direct_write(iocb, from, false); dprintk("NFS: write(%pD2, %zu@%Ld)\n", file, iov_iter_count(from), (long long) iocb->ki_pos); diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 9c96e3e5ed35..76deddab0a8f 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -1075,7 +1075,7 @@ filelayout_setup_ds_info(struct pnfs_ds_commit_info *fl_cinfo, unsigned int size = (fl->stripe_type == STRIPE_SPARSE) ? fl->dsaddr->ds_num : fl->dsaddr->stripe_count; - new = pnfs_alloc_commit_array(size, GFP_NOIO); + new = pnfs_alloc_commit_array(size, nfs_io_gfp_mask()); if (new) { spin_lock(&inode->i_lock); array = pnfs_add_commit_array(fl_cinfo, new, lseg); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index a553d59afa8b..604be402ae13 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -663,7 +663,7 @@ nfs4_ff_layout_stat_io_start_read(struct inode *inode, spin_unlock(&mirror->lock); if (report) - pnfs_report_layoutstat(inode, GFP_KERNEL); + pnfs_report_layoutstat(inode, nfs_io_gfp_mask()); } static void @@ -694,7 +694,7 @@ nfs4_ff_layout_stat_io_start_write(struct inode *inode, spin_unlock(&mirror->lock); if (report) - pnfs_report_layoutstat(inode, GFP_NOIO); + pnfs_report_layoutstat(inode, nfs_io_gfp_mask()); } static void @@ -806,13 +806,10 @@ ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio, bool strict_iomode) { pnfs_put_lseg(pgio->pg_lseg); - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - req->wb_bytes, - IOMODE_READ, - strict_iomode, - GFP_KERNEL); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), req->wb_bytes, IOMODE_READ, + strict_iomode, nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -894,13 +891,10 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, retry: ff_layout_pg_check_layout(pgio, req); if (!pgio->pg_lseg) { - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - req->wb_bytes, - IOMODE_RW, - false, - GFP_NOFS); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), req->wb_bytes, + IOMODE_RW, false, nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -953,13 +947,10 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { if (!pgio->pg_lseg) { - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - req->wb_bytes, - IOMODE_RW, - false, - GFP_NOFS); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), req->wb_bytes, + IOMODE_RW, false, nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -1258,7 +1249,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, mirror = FF_LAYOUT_COMP(lseg, idx); err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout), mirror, offset, length, status, opnum, - GFP_NOIO); + nfs_io_gfp_mask()); switch (status) { case NFS4ERR_DELAY: @@ -1973,7 +1964,8 @@ ff_layout_setup_ds_info(struct pnfs_ds_commit_info *fl_cinfo, struct inode *inode = lseg->pls_layout->plh_inode; struct pnfs_commit_array *array, *new; - new = pnfs_alloc_commit_array(flseg->mirror_array_cnt, GFP_NOIO); + new = pnfs_alloc_commit_array(flseg->mirror_array_cnt, + nfs_io_gfp_mask()); if (new) { spin_lock(&inode->i_lock); array = pnfs_add_commit_array(fl_cinfo, new, lseg); @@ -2152,10 +2144,10 @@ ff_layout_prepare_layoutreturn(struct nfs4_layoutreturn_args *args) struct nfs4_flexfile_layoutreturn_args *ff_args; struct nfs4_flexfile_layout *ff_layout = FF_LAYOUT_FROM_HDR(args->layout); - ff_args = kmalloc(sizeof(*ff_args), GFP_KERNEL); + ff_args = kmalloc(sizeof(*ff_args), nfs_io_gfp_mask()); if (!ff_args) goto out_nomem; - ff_args->pages[0] = alloc_page(GFP_KERNEL); + ff_args->pages[0] = alloc_page(nfs_io_gfp_mask()); if (!ff_args->pages[0]) goto out_nomem_free; @@ -2192,8 +2184,8 @@ ff_layout_send_layouterror(struct pnfs_layout_segment *lseg) if (list_empty(&head)) return; - errors = kmalloc_array(NFS42_LAYOUTERROR_MAX, - sizeof(*errors), GFP_NOFS); + errors = kmalloc_array(NFS42_LAYOUTERROR_MAX, sizeof(*errors), + nfs_io_gfp_mask()); if (errors != NULL) { const struct nfs4_ff_layout_ds_err *pos; size_t n = 0; @@ -2444,7 +2436,8 @@ ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) const int dev_count = PNFS_LAYOUTSTATS_MAXDEV; /* For now, send at most PNFS_LAYOUTSTATS_MAXDEV statistics */ - args->devinfo = kmalloc_array(dev_count, sizeof(*args->devinfo), GFP_NOIO); + args->devinfo = kmalloc_array(dev_count, sizeof(*args->devinfo), + nfs_io_gfp_mask()); if (!args->devinfo) return -ENOMEM; diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index ea17fa1f31ec..e2d59bb5e6bb 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -80,6 +80,7 @@ enum nfs_param { Opt_source, Opt_tcp, Opt_timeo, + Opt_trunkdiscovery, Opt_udp, Opt_v, Opt_vers, @@ -180,6 +181,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_string("source", Opt_source), fsparam_flag ("tcp", Opt_tcp), fsparam_u32 ("timeo", Opt_timeo), + fsparam_flag_no("trunkdiscovery", Opt_trunkdiscovery), fsparam_flag ("udp", Opt_udp), fsparam_flag ("v2", Opt_v), fsparam_flag ("v3", Opt_v), @@ -529,6 +531,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, else ctx->flags &= ~NFS_MOUNT_NOCTO; break; + case Opt_trunkdiscovery: + if (result.negated) + ctx->flags &= ~NFS_MOUNT_TRUNK_DISCOVERY; + else + ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY; + break; case Opt_ac: if (result.negated) ctx->flags |= NFS_MOUNT_NOAC; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index cfe901650ab0..4dee53ceb941 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -19,8 +19,7 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" - -#define NFSDBG_FACILITY NFSDBG_FSCACHE +#include "nfstrace.h" #define NFS_MAX_KEY_LEN 1000 @@ -128,8 +127,6 @@ int nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int u vcookie = fscache_acquire_volume(key, NULL, /* preferred_cache */ NULL, 0 /* coherency_data */); - dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n", - nfss, vcookie); if (IS_ERR(vcookie)) { if (vcookie != ERR_PTR(-EBUSY)) { kfree(key); @@ -152,9 +149,6 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) { struct nfs_server *nfss = NFS_SB(sb); - dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n", - nfss, nfss->fscache); - fscache_relinquish_volume(nfss->fscache, NULL, false); nfss->fscache = NULL; kfree(nfss->fscache_uniq); @@ -173,7 +167,7 @@ void nfs_fscache_init_inode(struct inode *inode) if (!(nfss->fscache && S_ISREG(inode->i_mode))) return; - nfs_fscache_update_auxdata(&auxdata, nfsi); + nfs_fscache_update_auxdata(&auxdata, inode); nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, 0, @@ -181,7 +175,7 @@ void nfs_fscache_init_inode(struct inode *inode) nfsi->fh.size, &auxdata, /* aux_data */ sizeof(auxdata), - i_size_read(&nfsi->vfs_inode)); + i_size_read(inode)); } /* @@ -192,8 +186,6 @@ void nfs_fscache_clear_inode(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); - dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie); - fscache_relinquish_cookie(cookie, false); nfsi->fscache = NULL; } @@ -220,7 +212,6 @@ void nfs_fscache_clear_inode(struct inode *inode) void nfs_fscache_open_file(struct inode *inode, struct file *filp) { struct nfs_fscache_inode_auxdata auxdata; - struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); bool open_for_write = inode_is_open_for_write(inode); @@ -229,8 +220,7 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp) fscache_use_cookie(cookie, open_for_write); if (open_for_write) { - dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi); - nfs_fscache_update_auxdata(&auxdata, nfsi); + nfs_fscache_update_auxdata(&auxdata, inode); fscache_invalidate(cookie, &auxdata, i_size_read(inode), FSCACHE_INVAL_DIO_WRITE); } @@ -240,11 +230,10 @@ EXPORT_SYMBOL_GPL(nfs_fscache_open_file); void nfs_fscache_release_file(struct inode *inode, struct file *filp) { struct nfs_fscache_inode_auxdata auxdata; - struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); if (fscache_cookie_valid(cookie)) { - nfs_fscache_update_auxdata(&auxdata, nfsi); + nfs_fscache_update_auxdata(&auxdata, inode); fscache_unuse_cookie(cookie, &auxdata, NULL); } } @@ -319,58 +308,50 @@ static int fscache_fallback_write_page(struct inode *inode, struct page *page, /* * Retrieve a page from fscache */ -int __nfs_readpage_from_fscache(struct inode *inode, struct page *page) +int __nfs_fscache_read_page(struct inode *inode, struct page *page) { int ret; - dfprintk(FSCACHE, - "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n", - nfs_i_fscache(inode), page, page->index, page->flags, inode); - + trace_nfs_fscache_read_page(inode, page); if (PageChecked(page)) { - dfprintk(FSCACHE, "NFS: readpage_from_fscache: PageChecked\n"); ClearPageChecked(page); - return 1; + ret = 1; + goto out; } ret = fscache_fallback_read_page(inode, page); if (ret < 0) { nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - dfprintk(FSCACHE, - "NFS: readpage_from_fscache failed %d\n", ret); SetPageChecked(page); - return ret; + goto out; } /* Read completed synchronously */ - dfprintk(FSCACHE, "NFS: readpage_from_fscache: read successful\n"); nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); SetPageUptodate(page); - return 0; + ret = 0; +out: + trace_nfs_fscache_read_page_exit(inode, page, ret); + return ret; } /* * Store a newly fetched page in fscache. We can be certain there's no page * stored in the cache as yet otherwise we would've read it from there. */ -void __nfs_readpage_to_fscache(struct inode *inode, struct page *page) +void __nfs_fscache_write_page(struct inode *inode, struct page *page) { int ret; - dfprintk(FSCACHE, - "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx))\n", - nfs_i_fscache(inode), page, page->index, page->flags); + trace_nfs_fscache_write_page(inode, page); ret = fscache_fallback_write_page(inode, page, true); - dfprintk(FSCACHE, - "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n", - page, page->index, page->flags, ret); - if (ret != 0) { nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); } else { nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_OK); } + trace_nfs_fscache_write_page_exit(inode, page, ret); } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 25a5c0f82392..4e980cc04779 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -45,10 +45,8 @@ extern void nfs_fscache_clear_inode(struct inode *); extern void nfs_fscache_open_file(struct inode *, struct file *); extern void nfs_fscache_release_file(struct inode *, struct file *); -extern int __nfs_readpage_from_fscache(struct inode *, struct page *); -extern void __nfs_read_completion_to_fscache(struct nfs_pgio_header *hdr, - unsigned long bytes); -extern void __nfs_readpage_to_fscache(struct inode *, struct page *); +extern int __nfs_fscache_read_page(struct inode *, struct page *); +extern void __nfs_fscache_write_page(struct inode *, struct page *); static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { @@ -66,11 +64,10 @@ static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) /* * Retrieve a page from an inode data storage object. */ -static inline int nfs_readpage_from_fscache(struct inode *inode, - struct page *page) +static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) { - if (NFS_I(inode)->fscache) - return __nfs_readpage_from_fscache(inode, page); + if (nfs_i_fscache(inode)) + return __nfs_fscache_read_page(inode, page); return -ENOBUFS; } @@ -78,24 +75,24 @@ static inline int nfs_readpage_from_fscache(struct inode *inode, * Store a page newly fetched from the server in an inode data storage object * in the cache. */ -static inline void nfs_readpage_to_fscache(struct inode *inode, +static inline void nfs_fscache_write_page(struct inode *inode, struct page *page) { - if (NFS_I(inode)->fscache) - __nfs_readpage_to_fscache(inode, page); + if (nfs_i_fscache(inode)) + __nfs_fscache_write_page(inode, page); } static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, - struct nfs_inode *nfsi) + struct inode *inode) { memset(auxdata, 0, sizeof(*auxdata)); - auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; + auxdata->mtime_sec = inode->i_mtime.tv_sec; + auxdata->mtime_nsec = inode->i_mtime.tv_nsec; + auxdata->ctime_sec = inode->i_ctime.tv_sec; + auxdata->ctime_nsec = inode->i_ctime.tv_nsec; - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); + if (NFS_SERVER(inode)->nfs_client->rpc_ops->version == 4) + auxdata->change_attr = inode_peek_iversion_raw(inode); } /* @@ -107,9 +104,9 @@ static inline void nfs_fscache_invalidate(struct inode *inode, int flags) struct nfs_inode *nfsi = NFS_I(inode); if (nfsi->fscache) { - nfs_fscache_update_auxdata(&auxdata, nfsi); + nfs_fscache_update_auxdata(&auxdata, inode); fscache_invalidate(nfsi->fscache, &auxdata, - i_size_read(&nfsi->vfs_inode), flags); + i_size_read(inode), flags); } } @@ -136,15 +133,11 @@ static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { return 1; /* True: may release page */ } -static inline int nfs_readpage_from_fscache(struct inode *inode, - struct page *page) +static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) { return -ENOBUFS; } -static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page) {} - - +static inline void nfs_fscache_write_page(struct inode *inode, struct page *page) {} static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {} static inline const char *nfs_server_fscache_state(struct nfs_server *server) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 3351c2de3e08..7eb3b08d702f 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -203,14 +203,13 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) NFS_INO_INVALID_OTHER | NFS_INO_INVALID_XATTR); flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); - } else if (flags & NFS_INO_REVAL_PAGECACHE) - flags |= NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE; + } if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) nfs_fscache_invalidate(inode, 0); - flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); + flags &= ~NFS_INO_REVAL_FORCED; nfsi->cache_validity |= flags; @@ -236,19 +235,17 @@ static void nfs_zap_caches_locked(struct inode *inode) nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; - if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { - nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_DATA - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_XATTR - | NFS_INO_REVAL_PAGECACHE); - } else - nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_XATTR - | NFS_INO_REVAL_PAGECACHE); + if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | + NFS_INO_INVALID_DATA | + NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL | + NFS_INO_INVALID_XATTR); + else + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | + NFS_INO_INVALID_ACCESS | + NFS_INO_INVALID_ACL | + NFS_INO_INVALID_XATTR); nfs_zap_label_cache_locked(nfsi); } @@ -564,8 +561,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_gid = fattr->gid; else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); - if (nfs_server_capable(inode, NFS_CAP_XATTR)) - nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED && @@ -785,26 +780,32 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, } EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); -static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry) +/* + * Don't request help from readdirplus if the file is being written to, + * or if attribute caching is turned off + */ +static bool nfs_getattr_readdirplus_enable(const struct inode *inode) { - struct dentry *parent; + return nfs_server_capable(inode, NFS_CAP_READDIRPLUS) && + !nfs_have_writebacks(inode) && NFS_MAXATTRTIMEO(inode) > 5 * HZ; +} - if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS)) - return; - parent = dget_parent(dentry); - nfs_force_use_readdirplus(d_inode(parent)); - dput(parent); +static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry) +{ + if (!IS_ROOT(dentry)) { + struct dentry *parent = dget_parent(dentry); + nfs_readdir_record_entry_cache_miss(d_inode(parent)); + dput(parent); + } } static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry) { - struct dentry *parent; - - if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS)) - return; - parent = dget_parent(dentry); - nfs_advise_use_readdirplus(d_inode(parent)); - dput(parent); + if (!IS_ROOT(dentry)) { + struct dentry *parent = dget_parent(dentry); + nfs_readdir_record_entry_cache_hit(d_inode(parent)); + dput(parent); + } } static u32 nfs_get_valid_attrmask(struct inode *inode) @@ -840,6 +841,7 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, int err = 0; bool force_sync = query_flags & AT_STATX_FORCE_SYNC; bool do_update = false; + bool readdirplus_enabled = nfs_getattr_readdirplus_enable(inode); trace_nfs_getattr_enter(inode); @@ -848,7 +850,8 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, STATX_INO | STATX_SIZE | STATX_BLOCKS; if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) { - nfs_readdirplus_parent_cache_hit(path->dentry); + if (readdirplus_enabled) + nfs_readdirplus_parent_cache_hit(path->dentry); goto out_no_revalidate; } @@ -898,15 +901,12 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path, do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { - /* Update the attribute cache */ - if (!(server->flags & NFS_MOUNT_NOAC)) + if (readdirplus_enabled) nfs_readdirplus_parent_cache_miss(path->dentry); - else - nfs_readdirplus_parent_cache_hit(path->dentry); err = __nfs_revalidate_inode(server, inode); if (err) goto out; - } else + } else if (readdirplus_enabled) nfs_readdirplus_parent_cache_hit(path->dentry); out_no_revalidate: /* Only return attributes that were revalidated. */ @@ -952,7 +952,7 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) res = __nfs_find_lock_context(ctx); rcu_read_unlock(); if (res == NULL) { - new = kmalloc(sizeof(*new), GFP_KERNEL); + new = kmalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); if (new == NULL) return ERR_PTR(-ENOMEM); nfs_init_lock_context(new); @@ -1030,7 +1030,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, { struct nfs_open_context *ctx; - ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (!ctx) return ERR_PTR(-ENOMEM); nfs_sb_active(dentry->d_sb); @@ -1583,7 +1583,7 @@ struct nfs_fattr *nfs_alloc_fattr(void) { struct nfs_fattr *fattr; - fattr = kmalloc(sizeof(*fattr), GFP_NOFS); + fattr = kmalloc(sizeof(*fattr), GFP_KERNEL); if (fattr != NULL) { nfs_fattr_init(fattr); fattr->label = NULL; @@ -1599,7 +1599,7 @@ struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server) if (!fattr) return NULL; - fattr->label = nfs4_label_alloc(server, GFP_NOFS); + fattr->label = nfs4_label_alloc(server, GFP_KERNEL); if (IS_ERR(fattr->label)) { kfree(fattr); return NULL; @@ -1613,7 +1613,7 @@ struct nfs_fh *nfs_alloc_fhandle(void) { struct nfs_fh *fh; - fh = kmalloc(sizeof(struct nfs_fh), GFP_NOFS); + fh = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); if (fh != NULL) fh->size = 0; return fh; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2de7c56a1fbe..57b0497105c8 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -366,8 +366,8 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); /* dir.c */ -extern void nfs_advise_use_readdirplus(struct inode *dir); -extern void nfs_force_use_readdirplus(struct inode *dir); +extern void nfs_readdir_record_entry_cache_hit(struct inode *dir); +extern void nfs_readdir_record_entry_cache_miss(struct inode *dir); extern unsigned long nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc); extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, @@ -388,6 +388,20 @@ int nfs_mknod(struct user_namespace *, struct inode *, struct dentry *, umode_t, int nfs_rename(struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); +#ifdef CONFIG_NFS_V4_2 +static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) +{ + if (!(server->caps & NFS_CAP_XATTR)) + return 0; + return NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | NFS4_ACCESS_XALIST; +} +#else +static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server) +{ + return 0; +} +#endif + /* file.c */ int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync); loff_t nfs_file_llseek(struct file *, loff_t, int); @@ -573,6 +587,13 @@ nfs_write_match_verf(const struct nfs_writeverf *verf, !nfs_write_verifier_cmp(&req->wb_verf, &verf->verifier); } +static inline gfp_t nfs_io_gfp_mask(void) +{ + if (current->flags & PF_WQ_WORKER) + return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + return GFP_KERNEL; +} + /* unlink.c */ extern struct rpc_task * nfs_async_rename(struct inode *old_dir, struct inode *new_dir, diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 7fba7711e6b3..05c3b4b2b3dd 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -949,13 +949,12 @@ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, error = decode_filename_inline(xdr, &entry->name, &entry->len); if (unlikely(error)) - return error; + return -EAGAIN; /* * The type (size and byte order) of nfscookie isn't defined in * RFC 1094. This implementation assumes that it's an XDR uint32. */ - entry->prev_cookie = entry->cookie; p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) return -EAGAIN; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 9274c9c5efea..3b0b650c9c5a 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1261,6 +1261,8 @@ static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req, static void encode_readdirplus3args(struct xdr_stream *xdr, const struct nfs3_readdirargs *args) { + uint32_t dircount = args->count; + uint32_t maxcount = args->count; __be32 *p; encode_nfs_fh3(xdr, args->fh); @@ -1273,9 +1275,8 @@ static void encode_readdirplus3args(struct xdr_stream *xdr, * readdirplus: need dircount + buffer size. * We just make sure we make dircount big enough */ - *p++ = cpu_to_be32(args->count >> 3); - - *p = cpu_to_be32(args->count); + *p++ = cpu_to_be32(dircount); + *p = cpu_to_be32(maxcount); } static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req, @@ -1967,7 +1968,6 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, bool plus) { struct user_namespace *userns = rpc_userns(entry->server->client); - struct nfs_entry old = *entry; __be32 *p; int error; u64 new_cookie; @@ -1987,15 +1987,15 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, error = decode_fileid3(xdr, &entry->ino); if (unlikely(error)) - return error; + return -EAGAIN; error = decode_inline_filename3(xdr, &entry->name, &entry->len); if (unlikely(error)) - return error; + return -EAGAIN; error = decode_cookie3(xdr, &new_cookie); if (unlikely(error)) - return error; + return -EAGAIN; entry->d_type = DT_UNKNOWN; @@ -2003,7 +2003,7 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, entry->fattr->valid = 0; error = decode_post_op_attr(xdr, entry->fattr, userns); if (unlikely(error)) - return error; + return -EAGAIN; if (entry->fattr->valid & NFS_ATTR_FATTR_V3) entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); @@ -2018,24 +2018,15 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, return -EAGAIN; if (*p != xdr_zero) { error = decode_nfs_fh3(xdr, entry->fh); - if (unlikely(error)) { - if (error == -E2BIG) - goto out_truncated; - return error; - } + if (unlikely(error)) + return -EAGAIN; } else zero_nfs_fh3(entry->fh); } - entry->prev_cookie = entry->cookie; entry->cookie = new_cookie; return 0; - -out_truncated: - dprintk("NFS: directory entry contains invalid file handle\n"); - *entry = old; - return -EAGAIN; } /* @@ -2228,6 +2219,7 @@ static int decode_fsinfo3resok(struct xdr_stream *xdr, /* ignore properties */ result->lease_time = 0; result->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED; + result->xattr_support = 0; return 0; } diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 32129446beca..068c45b3bc1a 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -175,28 +175,27 @@ static int handle_async_copy(struct nfs42_copy_res *res, nfs4_stateid *src_stateid, bool *restart) { - struct nfs4_copy_state *copy, *tmp_copy; + struct nfs4_copy_state *copy, *tmp_copy = NULL, *iter; int status = NFS4_OK; - bool found_pending = false; struct nfs_open_context *dst_ctx = nfs_file_open_context(dst); struct nfs_open_context *src_ctx = nfs_file_open_context(src); - copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); + copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL); if (!copy) return -ENOMEM; spin_lock(&dst_server->nfs_client->cl_lock); - list_for_each_entry(tmp_copy, + list_for_each_entry(iter, &dst_server->nfs_client->pending_cb_stateids, copies) { - if (memcmp(&res->write_res.stateid, &tmp_copy->stateid, + if (memcmp(&res->write_res.stateid, &iter->stateid, NFS4_STATEID_SIZE)) continue; - found_pending = true; - list_del(&tmp_copy->copies); + tmp_copy = iter; + list_del(&iter->copies); break; } - if (found_pending) { + if (tmp_copy) { spin_unlock(&dst_server->nfs_client->cl_lock); kfree(copy); copy = tmp_copy; @@ -254,7 +253,7 @@ static int process_copy_commit(struct file *dst, loff_t pos_dst, struct nfs_commitres cres; int status = -ENOMEM; - cres.verf = kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS); + cres.verf = kzalloc(sizeof(struct nfs_writeverf), GFP_KERNEL); if (!cres.verf) goto out; @@ -357,7 +356,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, res->commit_res.verf = NULL; if (args->sync) { res->commit_res.verf = - kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS); + kzalloc(sizeof(struct nfs_writeverf), GFP_KERNEL); if (!res->commit_res.verf) return -ENOMEM; } @@ -552,7 +551,7 @@ static int nfs42_do_offload_cancel_async(struct file *dst, if (!(dst_server->caps & NFS_CAP_OFFLOAD_CANCEL)) return -EOPNOTSUPP; - data = kzalloc(sizeof(struct nfs42_offloadcancel_data), GFP_NOFS); + data = kzalloc(sizeof(struct nfs42_offloadcancel_data), GFP_KERNEL); if (data == NULL) return -ENOMEM; @@ -591,8 +590,10 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst, ctx = get_nfs_open_context(nfs_file_open_context(src)); l_ctx = nfs_get_lock_context(ctx); - if (IS_ERR(l_ctx)) - return PTR_ERR(l_ctx); + if (IS_ERR(l_ctx)) { + status = PTR_ERR(l_ctx); + goto out; + } status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx, FMODE_READ); @@ -600,7 +601,7 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst, if (status) { if (status == -EAGAIN) status = -NFS4ERR_BAD_STATEID; - return status; + goto out; } status = nfs4_call_sync(src_server->client, src_server, &msg, @@ -609,6 +610,7 @@ static int _nfs42_proc_copy_notify(struct file *src, struct file *dst, if (status == -ENOTSUPP) src_server->caps &= ~NFS_CAP_COPY_NOTIFY; +out: put_nfs_open_context(nfs_file_open_context(src)); return status; } @@ -626,7 +628,7 @@ int nfs42_proc_copy_notify(struct file *src, struct file *dst, if (!(src_server->caps & NFS_CAP_COPY_NOTIFY)) return -EOPNOTSUPP; - args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS); + args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_KERNEL); if (args == NULL) return -ENOMEM; @@ -1014,7 +1016,7 @@ int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg, return -EOPNOTSUPP; if (n > NFS42_LAYOUTERROR_MAX) return -EINVAL; - data = nfs42_alloc_layouterror_data(lseg, GFP_NOFS); + data = nfs42_alloc_layouterror_data(lseg, nfs_io_gfp_mask()); if (!data) return -ENOMEM; for (i = 0; i < n; i++) { diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index 1c4d2a05b401..ad3405c64b9e 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -199,7 +199,7 @@ nfs4_xattr_alloc_entry(const char *name, const void *value, flags = NFS4_XATTR_ENTRY_EXTVAL; } - buf = kmalloc(alloclen, GFP_KERNEL_ACCOUNT | GFP_NOFS); + buf = kmalloc(alloclen, GFP_KERNEL); if (buf == NULL) return NULL; entry = (struct nfs4_xattr_entry *)buf; @@ -213,7 +213,7 @@ nfs4_xattr_alloc_entry(const char *name, const void *value, if (flags & NFS4_XATTR_ENTRY_EXTVAL) { - valp = kvmalloc(len, GFP_KERNEL_ACCOUNT | GFP_NOFS); + valp = kvmalloc(len, GFP_KERNEL); if (valp == NULL) { kfree(buf); return NULL; @@ -289,8 +289,7 @@ nfs4_xattr_alloc_cache(void) { struct nfs4_xattr_cache *cache; - cache = kmem_cache_alloc(nfs4_xattr_cache_cachep, - GFP_KERNEL_ACCOUNT | GFP_NOFS); + cache = kmem_cache_alloc(nfs4_xattr_cache_cachep, GFP_KERNEL); if (cache == NULL) return NULL; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 84f39b6f1b1e..79df6e83881b 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -42,6 +42,7 @@ enum nfs4_client_state { NFS4CLNT_LEASE_MOVED, NFS4CLNT_DELEGATION_EXPIRED, NFS4CLNT_RUN_MANAGER, + NFS4CLNT_MANAGER_AVAILABLE, NFS4CLNT_RECALL_RUNNING, NFS4CLNT_RECALL_ANY_LAYOUT_READ, NFS4CLNT_RECALL_ANY_LAYOUT_RW, diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index e79ae4cbc395..d258933cf8c8 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -165,7 +165,7 @@ retry: if (sync) return -EOPNOTSUPP; cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res), - GFP_NOFS); + GFP_KERNEL); if (unlikely(cn_resp == NULL)) return -ENOMEM; @@ -180,8 +180,8 @@ retry: ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count, nss, cnrs, sync); out: - if (!nfs42_files_from_same_server(file_in, file_out)) - kfree(cn_resp); + kfree(cn_resp); + if (ret == -EAGAIN) goto retry; return ret; @@ -339,7 +339,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, res = ERR_PTR(-ENOMEM); len = strlen(SSC_READ_NAME_BODY) + 16; - read_name = kzalloc(len, GFP_NOFS); + read_name = kzalloc(len, GFP_KERNEL); if (read_name == NULL) goto out; snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0e0db6c27619..e3f5b380cefe 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1392,13 +1392,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, case NFS4_OPEN_CLAIM_FH: p->o_arg.access = NFS4_ACCESS_READ | NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE | - NFS4_ACCESS_EXECUTE; -#ifdef CONFIG_NFS_V4_2 - if (!(server->caps & NFS_CAP_XATTR)) - break; - p->o_arg.access |= NFS4_ACCESS_XAREAD | NFS4_ACCESS_XAWRITE | - NFS4_ACCESS_XALIST; -#endif + NFS4_ACCESS_EXECUTE | + nfs_access_xattr_mask(server); } p->o_arg.clientid = server->nfs_client->cl_clientid; p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time); @@ -3050,6 +3045,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, set_bit(NFS_STATE_POSIX_LOCKS, &state->flags); if (opendata->o_res.rflags & NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK) set_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags); + if (opendata->o_res.rflags & NFS4_OPEN_RESULT_PRESERVE_UNLINKED) + set_bit(NFS_INO_PRESERVE_UNLINKED, &NFS_I(state->inode)->flags); dentry = opendata->dentry; if (d_really_is_negative(dentry)) { @@ -5904,7 +5901,7 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu buflen = server->rsize; npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1; - pages = kmalloc_array(npages, sizeof(struct page *), GFP_NOFS); + pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (!pages) return -ENOMEM; @@ -6609,7 +6606,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, }; int status = 0; - data = kzalloc(sizeof(*data), GFP_NOFS); + data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) return -ENOMEM; @@ -6797,7 +6794,7 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, struct nfs4_state *state = lsp->ls_state; struct inode *inode = state->inode; - p = kzalloc(sizeof(*p), GFP_NOFS); + p = kzalloc(sizeof(*p), GFP_KERNEL); if (p == NULL) return NULL; p->arg.fh = NFS_FH(inode); @@ -7202,8 +7199,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f task_setup_data.flags |= RPC_TASK_MOVEABLE; data = nfs4_alloc_lockdata(fl, nfs_file_open_context(fl->fl_file), - fl->fl_u.nfs4_fl.owner, - recovery_type == NFS_LOCK_NEW ? GFP_KERNEL : GFP_NOFS); + fl->fl_u.nfs4_fl.owner, GFP_KERNEL); if (data == NULL) return -ENOMEM; if (IS_SETLKW(cmd)) @@ -7626,7 +7622,7 @@ nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp) if (server->nfs_client->cl_mvops->minor_version != 0) return; - data = kmalloc(sizeof(*data), GFP_NOFS); + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return; data->lsp = lsp; @@ -8012,6 +8008,18 @@ static int _nfs41_proc_get_locations(struct nfs_server *server, .rpc_resp = &res, .rpc_cred = cred, }; + struct nfs4_call_sync_data data = { + .seq_server = server, + .seq_args = &args.seq_args, + .seq_res = &res.seq_res, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .rpc_message = &msg, + .callback_ops = server->nfs_client->cl_mvops->call_sync_ops, + .callback_data = &data, + .flags = RPC_TASK_NO_ROUND_ROBIN, + }; int status; nfs_fattr_init(&locations->fattr); @@ -8019,8 +8027,7 @@ static int _nfs41_proc_get_locations(struct nfs_server *server, locations->nlocations = 0; nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 1); - status = nfs4_call_sync_sequence(clnt, server, &msg, - &args.seq_args, &res.seq_res); + status = nfs4_call_sync_custom(&task_setup_data); if (status == NFS4_OK && res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED) status = -NFS4ERR_LEASE_MOVED; @@ -8333,6 +8340,7 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata) case -NFS4ERR_DEADSESSION: nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); + return; } if (args->dir == NFS4_CDFC4_FORE_OR_BOTH && res->dir != NFS4_CDFS4_BOTH) { @@ -9291,7 +9299,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, goto out_err; ret = ERR_PTR(-ENOMEM); - calldata = kzalloc(sizeof(*calldata), GFP_NOFS); + calldata = kzalloc(sizeof(*calldata), GFP_KERNEL); if (calldata == NULL) goto out_put_clp; nfs4_init_sequence(&calldata->args, &calldata->res, 0, is_privileged); @@ -10222,7 +10230,7 @@ static int nfs41_free_stateid(struct nfs_server *server, &task_setup.rpc_client, &msg); dprintk("NFS call free_stateid %p\n", stateid); - data = kmalloc(sizeof(*data), GFP_NOFS); + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; data->server = server; @@ -10461,6 +10469,24 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) return error + error2 + error3; } +static void nfs4_enable_swap(struct inode *inode) +{ + /* The state manager thread must always be running. + * It will notice the client is a swapper, and stay put. + */ + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + + nfs4_schedule_state_manager(clp); +} + +static void nfs4_disable_swap(struct inode *inode) +{ + /* The state manager thread will now exit once it is + * woken. + */ + wake_up_var(&NFS_SERVER(inode)->nfs_client->cl_state); +} + static const struct inode_operations nfs4_dir_inode_operations = { .create = nfs_create, .lookup = nfs_lookup, @@ -10538,6 +10564,8 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .create_server = nfs4_create_server, .clone_server = nfs_clone_server, .discover_trunking = nfs4_discover_trunking, + .enable_swap = nfs4_enable_swap, + .disable_swap = nfs4_disable_swap, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 02a899e4390f..9e1c987c81e7 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -49,6 +49,7 @@ #include <linux/workqueue.h> #include <linux/bitops.h> #include <linux/jiffies.h> +#include <linux/sched/mm.h> #include <linux/sunrpc/clnt.h> @@ -666,7 +667,7 @@ nfs4_alloc_open_state(void) { struct nfs4_state *state; - state = kzalloc(sizeof(*state), GFP_NOFS); + state = kzalloc(sizeof(*state), GFP_KERNEL_ACCOUNT); if (!state) return NULL; refcount_set(&state->count, 1); @@ -820,7 +821,7 @@ static void __nfs4_close(struct nfs4_state *state, void nfs4_close_state(struct nfs4_state *state, fmode_t fmode) { - __nfs4_close(state, fmode, GFP_NOFS, 0); + __nfs4_close(state, fmode, GFP_KERNEL, 0); } void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode) @@ -869,14 +870,15 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f struct nfs4_lock_state *lsp; struct nfs_server *server = state->owner->so_server; - lsp = kzalloc(sizeof(*lsp), GFP_NOFS); + lsp = kzalloc(sizeof(*lsp), GFP_KERNEL_ACCOUNT); if (lsp == NULL) return NULL; nfs4_init_seqid_counter(&lsp->ls_seqid); refcount_set(&lsp->ls_count, 1); lsp->ls_state = state; lsp->ls_owner = fl_owner; - lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS); + lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, + 0, 0, GFP_KERNEL_ACCOUNT); if (lsp->ls_seqid.owner_id < 0) goto out_free; INIT_LIST_HEAD(&lsp->ls_locks); @@ -1205,10 +1207,17 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *cl = clp->cl_rpcclient; + + while (cl != cl->cl_parent) + cl = cl->cl_parent; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { + wake_up_var(&clp->cl_state); return; + } + set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1224,6 +1233,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) printk(KERN_ERR "%s: kthread_run: %ld\n", __func__, PTR_ERR(task)); nfs4_clear_state_manager_bit(clp); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -2560,9 +2570,17 @@ static void nfs4_layoutreturn_any_run(struct nfs_client *clp) static void nfs4_state_manager(struct nfs_client *clp) { + unsigned int memflags; int status = 0; const char *section = "", *section_sep = ""; + /* + * State recovery can deadlock if the direct reclaim code tries + * start NFS writeback. So ensure memory allocations are all + * GFP_NOFS. + */ + memflags = memalloc_nofs_save(); + /* Ensure exclusive access to NFSv4 state */ do { trace_nfs4_state_mgr(clp); @@ -2657,6 +2675,7 @@ static void nfs4_state_manager(struct nfs_client *clp) clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state); } + memalloc_nofs_restore(memflags); nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); @@ -2669,11 +2688,8 @@ static void nfs4_state_manager(struct nfs_client *clp) clear_bit(NFS4CLNT_RECALL_RUNNING, &clp->cl_state); } - /* Did we race with an attempt to give us more work? */ - if (!test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) - return; - if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) - return; + return; + } while (refcount_read(&clp->cl_count) > 1 && !signalled()); goto out_drain; @@ -2686,6 +2702,7 @@ out_error: clp->cl_hostname, -status); ssleep(1); out_drain: + memalloc_nofs_restore(memflags); nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); } @@ -2693,9 +2710,31 @@ out_drain: static int nfs4_run_state_manager(void *ptr) { struct nfs_client *clp = ptr; + struct rpc_clnt *cl = clp->cl_rpcclient; + + while (cl != cl->cl_parent) + cl = cl->cl_parent; allow_signal(SIGKILL); +again: + set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); + if (atomic_read(&cl->cl_swapper)) { + wait_var_event_interruptible(&clp->cl_state, + test_bit(NFS4CLNT_RUN_MANAGER, + &clp->cl_state)); + if (atomic_read(&cl->cl_swapper) && + test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + goto again; + /* Either no longer a swapper, or were signalled */ + } + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && + !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + goto again; + nfs_put_client(clp); return 0; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 8e70b92df4cc..86a5f6516928 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1605,7 +1605,8 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg FATTR4_WORD0_RDATTR_ERROR, FATTR4_WORD1_MOUNTED_ON_FILEID, }; - uint32_t dircount = readdir->count >> 1; + uint32_t dircount = readdir->count; + uint32_t maxcount = readdir->count; __be32 *p, verf[2]; uint32_t attrlen = 0; unsigned int i; @@ -1618,7 +1619,6 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS| FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY; attrs[2] |= FATTR4_WORD2_SECURITY_LABEL; - dircount >>= 1; } /* Use mounted_on_fileid only if the server supports it */ if (!(readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) @@ -1634,7 +1634,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg encode_nfs4_verifier(xdr, &readdir->verifier); p = reserve_space(xdr, 12 + (attrlen << 2)); *p++ = cpu_to_be32(dircount); - *p++ = cpu_to_be32(readdir->count); + *p++ = cpu_to_be32(maxcount); *p++ = cpu_to_be32(attrlen); for (i = 0; i < attrlen; i++) *p++ = cpu_to_be32(attrs[i]); @@ -7508,7 +7508,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE) entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); - entry->prev_cookie = entry->cookie; entry->cookie = new_cookie; return 0; diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 317ce27bdc4b..012bd7339862 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -21,7 +21,6 @@ { NFS_INO_INVALID_ATIME, "INVALID_ATIME" }, \ { NFS_INO_INVALID_ACCESS, "INVALID_ACCESS" }, \ { NFS_INO_INVALID_ACL, "INVALID_ACL" }, \ - { NFS_INO_REVAL_PAGECACHE, "REVAL_PAGECACHE" }, \ { NFS_INO_REVAL_FORCED, "REVAL_FORCED" }, \ { NFS_INO_INVALID_LABEL, "INVALID_LABEL" }, \ { NFS_INO_INVALID_CHANGE, "INVALID_CHANGE" }, \ @@ -37,7 +36,6 @@ #define nfs_show_nfsi_flags(v) \ __print_flags(v, "|", \ - { BIT(NFS_INO_ADVISE_RDPLUS), "ADVISE_RDPLUS" }, \ { BIT(NFS_INO_STALE), "STALE" }, \ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \ @@ -162,6 +160,9 @@ DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); DEFINE_NFS_INODE_EVENT(nfs_access_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid); +DEFINE_NFS_INODE_EVENT(nfs_readdir_force_readdirplus); +DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_cache_fill_done); +DEFINE_NFS_INODE_EVENT_DONE(nfs_readdir_uncached_done); TRACE_EVENT(nfs_access_exit, TP_PROTO( @@ -273,6 +274,122 @@ DEFINE_NFS_UPDATE_SIZE_EVENT(wcc); DEFINE_NFS_UPDATE_SIZE_EVENT(update); DEFINE_NFS_UPDATE_SIZE_EVENT(grow); +DECLARE_EVENT_CLASS(nfs_inode_range_event, + TP_PROTO( + const struct inode *inode, + loff_t range_start, + loff_t range_end + ), + + TP_ARGS(inode, range_start, range_end), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + __field(loff_t, range_start) + __field(loff_t, range_end) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->dev = inode->i_sb->s_dev; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->fileid = nfsi->fileid; + __entry->version = inode_peek_iversion_raw(inode); + __entry->range_start = range_start; + __entry->range_end = range_end; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " + "range=[%lld, %lld]", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, __entry->version, + __entry->range_start, __entry->range_end + ) +); + +#define DEFINE_NFS_INODE_RANGE_EVENT(name) \ + DEFINE_EVENT(nfs_inode_range_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + loff_t range_start, \ + loff_t range_end \ + ), \ + TP_ARGS(inode, range_start, range_end)) + +DEFINE_NFS_INODE_RANGE_EVENT(nfs_readdir_invalidate_cache_range); + +DECLARE_EVENT_CLASS(nfs_readdir_event, + TP_PROTO( + const struct file *file, + const __be32 *verifier, + u64 cookie, + pgoff_t page_index, + unsigned int dtsize + ), + + TP_ARGS(file, verifier, cookie, page_index, dtsize), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(u64, version) + __array(char, verifier, NFS4_VERIFIER_SIZE) + __field(u64, cookie) + __field(pgoff_t, index) + __field(unsigned int, dtsize) + ), + + TP_fast_assign( + const struct inode *dir = file_inode(file); + const struct nfs_inode *nfsi = NFS_I(dir); + + __entry->dev = dir->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + __entry->version = inode_peek_iversion_raw(dir); + if (cookie != 0) + memcpy(__entry->verifier, verifier, + NFS4_VERIFIER_SIZE); + else + memset(__entry->verifier, 0, + NFS4_VERIFIER_SIZE); + __entry->cookie = cookie; + __entry->index = page_index; + __entry->dtsize = dtsize; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu " + "cookie=%s:0x%llx cache_index=%lu dtsize=%u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, __entry->fhandle, + __entry->version, show_nfs4_verifier(__entry->verifier), + (unsigned long long)__entry->cookie, __entry->index, + __entry->dtsize + ) +); + +#define DEFINE_NFS_READDIR_EVENT(name) \ + DEFINE_EVENT(nfs_readdir_event, name, \ + TP_PROTO( \ + const struct file *file, \ + const __be32 *verifier, \ + u64 cookie, \ + pgoff_t page_index, \ + unsigned int dtsize \ + ), \ + TP_ARGS(file, verifier, cookie, page_index, dtsize)) + +DEFINE_NFS_READDIR_EVENT(nfs_readdir_cache_fill); +DEFINE_NFS_READDIR_EVENT(nfs_readdir_uncached); + DECLARE_EVENT_CLASS(nfs_lookup_event, TP_PROTO( const struct inode *dir, @@ -366,6 +483,9 @@ DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_exit); DEFINE_NFS_LOOKUP_EVENT(nfs_lookup_revalidate_enter); DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_lookup_revalidate_exit); +DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup); +DEFINE_NFS_LOOKUP_EVENT(nfs_readdir_lookup_revalidate_failed); +DEFINE_NFS_LOOKUP_EVENT_DONE(nfs_readdir_lookup_revalidate); TRACE_EVENT(nfs_atomic_open_enter, TP_PROTO( @@ -889,11 +1009,11 @@ TRACE_EVENT(nfs_aop_readpage_done, TRACE_EVENT(nfs_aop_readahead, TP_PROTO( const struct inode *inode, - struct page *page, + loff_t pos, unsigned int nr_pages ), - TP_ARGS(inode, page, nr_pages), + TP_ARGS(inode, pos, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) @@ -911,7 +1031,7 @@ TRACE_EVENT(nfs_aop_readahead, __entry->fileid = nfsi->fileid; __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); __entry->version = inode_peek_iversion_raw(inode); - __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->offset = pos; __entry->nr_pages = nr_pages; ), @@ -1095,6 +1215,97 @@ TRACE_EVENT(nfs_readpage_short, ) ); +DECLARE_EVENT_CLASS(nfs_fscache_page_event, + TP_PROTO( + const struct inode *inode, + struct page *page + ), + + TP_ARGS(inode, page), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = &nfsi->fh; + + __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset + ) +); +DECLARE_EVENT_CLASS(nfs_fscache_page_event_done, + TP_PROTO( + const struct inode *inode, + struct page *page, + int error + ), + + TP_ARGS(inode, page, error), + + TP_STRUCT__entry( + __field(int, error) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + __field(loff_t, offset) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + const struct nfs_fh *fh = &nfsi->fh; + + __entry->offset = page_index(page) << PAGE_SHIFT; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(fh); + __entry->error = error; + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld error=%d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + (long long)__entry->offset, __entry->error + ) +); +#define DEFINE_NFS_FSCACHE_PAGE_EVENT(name) \ + DEFINE_EVENT(nfs_fscache_page_event, name, \ + TP_PROTO( \ + const struct inode *inode, \ + struct page *page \ + ), \ + TP_ARGS(inode, page)) +#define DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(name) \ + DEFINE_EVENT(nfs_fscache_page_event_done, name, \ + TP_PROTO( \ + const struct inode *inode, \ + struct page *page, \ + int error \ + ), \ + TP_ARGS(inode, page, error)) +DEFINE_NFS_FSCACHE_PAGE_EVENT(nfs_fscache_read_page); +DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(nfs_fscache_read_page_exit); +DEFINE_NFS_FSCACHE_PAGE_EVENT(nfs_fscache_write_page); +DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(nfs_fscache_write_page_exit); + TRACE_EVENT(nfs_pgio_error, TP_PROTO( const struct nfs_pgio_header *hdr, diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ad7f83dc9a2d..9157dd19b8b4 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -90,10 +90,10 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) } } -static inline struct nfs_page * -nfs_page_alloc(void) +static inline struct nfs_page *nfs_page_alloc(void) { - struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL); + struct nfs_page *p = + kmem_cache_zalloc(nfs_page_cachep, nfs_io_gfp_mask()); if (p) INIT_LIST_HEAD(&p->wb_list); return p; @@ -892,7 +892,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, struct nfs_commit_info cinfo; struct nfs_page_array *pg_array = &hdr->page_array; unsigned int pagecount, pageused; - gfp_t gfp_flags = GFP_KERNEL; + gfp_t gfp_flags = nfs_io_gfp_mask(); pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); pg_array->npages = pagecount; @@ -979,7 +979,7 @@ nfs_pageio_alloc_mirrors(struct nfs_pageio_descriptor *desc, desc->pg_mirrors_dynamic = NULL; if (mirror_count == 1) return desc->pg_mirrors_static; - ret = kmalloc_array(mirror_count, sizeof(*ret), GFP_KERNEL); + ret = kmalloc_array(mirror_count, sizeof(*ret), nfs_io_gfp_mask()); if (ret != NULL) { for (i = 0; i < mirror_count; i++) nfs_pageio_mirror_init(&ret[i], desc->pg_bsize); @@ -1218,6 +1218,7 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) do { list_splice_init(&mirror->pg_list, &head); + mirror->pg_recoalesce = 0; while (!list_empty(&head)) { struct nfs_page *req; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 7c9090a28e5c..856c962273c7 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -92,6 +92,17 @@ find_pnfs_driver(u32 id) return local; } +const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id) +{ + return find_pnfs_driver(id); +} + +void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld) +{ + if (ld) + module_put(ld->owner); +} + void unset_pnfs_layoutdriver(struct nfs_server *nfss) { @@ -1233,7 +1244,7 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, int status = 0; *pcred = NULL; - lrp = kzalloc(sizeof(*lrp), GFP_NOFS); + lrp = kzalloc(sizeof(*lrp), nfs_io_gfp_mask()); if (unlikely(lrp == NULL)) { status = -ENOMEM; spin_lock(&ino->i_lock); @@ -2206,7 +2217,7 @@ _pnfs_grab_empty_layout(struct inode *ino, struct nfs_open_context *ctx) struct pnfs_layout_hdr *lo; spin_lock(&ino->i_lock); - lo = pnfs_find_alloc_layout(ino, ctx, GFP_KERNEL); + lo = pnfs_find_alloc_layout(ino, ctx, nfs_io_gfp_mask()); if (!lo) goto out_unlock; if (!test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) @@ -2249,8 +2260,8 @@ static void _lgopen_prepare_attached(struct nfs4_opendata *data, lo = _pnfs_grab_empty_layout(ino, ctx); if (!lo) return; - lgp = pnfs_alloc_init_layoutget_args(ino, ctx, ¤t_stateid, - &rng, GFP_KERNEL); + lgp = pnfs_alloc_init_layoutget_args(ino, ctx, ¤t_stateid, &rng, + nfs_io_gfp_mask()); if (!lgp) { pnfs_clear_first_layoutget(lo); nfs_layoutget_end(lo); @@ -2275,8 +2286,8 @@ static void _lgopen_prepare_floating(struct nfs4_opendata *data, }; struct nfs4_layoutget *lgp; - lgp = pnfs_alloc_init_layoutget_args(ino, ctx, ¤t_stateid, - &rng, GFP_KERNEL); + lgp = pnfs_alloc_init_layoutget_args(ino, ctx, ¤t_stateid, &rng, + nfs_io_gfp_mask()); if (!lgp) return; data->lgp = lgp; @@ -2691,13 +2702,11 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r else rd_size = nfs_dreq_bytes_left(pgio->pg_dreq); - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - rd_size, - IOMODE_READ, - false, - GFP_KERNEL); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), rd_size, + IOMODE_READ, false, + nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -2718,13 +2727,10 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, pnfs_generic_pg_check_layout(pgio); pnfs_generic_pg_check_range(pgio, req); if (pgio->pg_lseg == NULL) { - pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, - nfs_req_openctx(req), - req_offset(req), - wb_size, - IOMODE_RW, - false, - GFP_KERNEL); + pgio->pg_lseg = + pnfs_update_layout(pgio->pg_inode, nfs_req_openctx(req), + req_offset(req), wb_size, IOMODE_RW, + false, nfs_io_gfp_mask()); if (IS_ERR(pgio->pg_lseg)) { pgio->pg_error = PTR_ERR(pgio->pg_lseg); pgio->pg_lseg = NULL; @@ -3183,7 +3189,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) status = -ENOMEM; /* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */ - data = kzalloc(sizeof(*data), GFP_NOFS); + data = kzalloc(sizeof(*data), nfs_io_gfp_mask()); if (!data) goto clear_layoutcommitting; @@ -3250,7 +3256,7 @@ struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) { struct nfs4_threshold *thp; - thp = kzalloc(sizeof(*thp), GFP_NOFS); + thp = kzalloc(sizeof(*thp), nfs_io_gfp_mask()); if (!thp) { dprintk("%s mdsthreshold allocation failed\n", __func__); return NULL; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index f4d7548d67b2..07f11489e4e9 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -234,6 +234,8 @@ struct pnfs_devicelist { extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); +extern const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id); +extern void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld); /* nfs4proc.c */ extern size_t max_response_pages(struct nfs_server *server); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 316f68f96e57..657c242a18ff 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -419,7 +419,7 @@ static struct nfs_commit_data * pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket, struct nfs_commit_info *cinfo) { - struct nfs_commit_data *data = nfs_commitdata_alloc(false); + struct nfs_commit_data *data = nfs_commitdata_alloc(); if (!data) return NULL; @@ -515,7 +515,11 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, unsigned int nreq = 0; if (!list_empty(mds_pages)) { - data = nfs_commitdata_alloc(true); + data = nfs_commitdata_alloc(); + if (!data) { + nfs_retry_commit(mds_pages, NULL, cinfo, -1); + return -ENOMEM; + } data->ds_commit_index = -1; list_splice_init(mds_pages, &data->pages); list_add_tail(&data->list, &list); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 73dcaa99fa9b..e3570c656b0f 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -92,6 +92,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, info->maxfilesize = 0x7FFFFFFF; info->lease_time = 0; info->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED; + info->xattr_support = 0; return 0; } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index eb00229c1a50..5e7657374bc3 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -123,7 +123,7 @@ static void nfs_readpage_release(struct nfs_page *req, int error) struct address_space *mapping = page_file_mapping(page); if (PageUptodate(page)) - nfs_readpage_to_fscache(inode, page); + nfs_fscache_write_page(inode, page); else if (!PageError(page) && !PagePrivate(page)) generic_error_remove_page(mapping, page); unlock_page(page); @@ -194,10 +194,6 @@ static void nfs_initiate_read(struct nfs_pgio_header *hdr, const struct nfs_rpc_ops *rpc_ops, struct rpc_task_setup *task_setup_data, int how) { - struct inode *inode = hdr->inode; - int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0; - - task_setup_data->flags |= swap_flags; rpc_ops->read_setup(hdr, msg); trace_nfs_initiate_read(hdr); } @@ -290,9 +286,8 @@ static void nfs_readpage_result(struct rpc_task *task, } static int -readpage_async_filler(void *data, struct page *page) +readpage_async_filler(struct nfs_readdesc *desc, struct page *page) { - struct nfs_readdesc *desc = data; struct inode *inode = page_file_mapping(page)->host; unsigned int rsize = NFS_SERVER(inode)->rsize; struct nfs_page *new; @@ -306,7 +301,7 @@ readpage_async_filler(void *data, struct page *page) aligned_len = min_t(unsigned int, ALIGN(len, rsize), PAGE_SIZE); if (!IS_SYNC(page->mapping->host)) { - error = nfs_readpage_from_fscache(page->mapping->host, page); + error = nfs_fscache_read_page(page->mapping->host, page); if (error == 0) goto out_unlock; } @@ -397,14 +392,16 @@ out_unlock: return ret; } -int nfs_readpages(struct file *file, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages) +void nfs_readahead(struct readahead_control *ractl) { + unsigned int nr_pages = readahead_count(ractl); + struct file *file = ractl->file; struct nfs_readdesc desc; - struct inode *inode = mapping->host; + struct inode *inode = ractl->mapping->host; + struct page *page; int ret; - trace_nfs_aop_readahead(inode, lru_to_page(pages), nr_pages); + trace_nfs_aop_readahead(inode, readahead_pos(ractl), nr_pages); nfs_inc_stats(inode, NFSIOS_VFSREADPAGES); ret = -ESTALE; @@ -422,14 +419,18 @@ int nfs_readpages(struct file *file, struct address_space *mapping, nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); - ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); + while ((page = readahead_page(ractl)) != NULL) { + ret = readpage_async_filler(&desc, page); + put_page(page); + if (ret) + break; + } nfs_pageio_complete_read(&desc.pgio); put_nfs_open_context(desc.ctx); out: trace_nfs_aop_readahead_done(inode, nr_pages, ret); - return ret; } int __init nfs_init_readpagecache(void) diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 614e2809032e..f00d45cf80ef 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -70,27 +70,17 @@ static mempool_t *nfs_wdata_mempool; static struct kmem_cache *nfs_cdata_cachep; static mempool_t *nfs_commit_mempool; -struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail) +struct nfs_commit_data *nfs_commitdata_alloc(void) { struct nfs_commit_data *p; - if (never_fail) - p = mempool_alloc(nfs_commit_mempool, GFP_NOIO); - else { - /* It is OK to do some reclaim, not no safe to wait - * for anything to be returned to the pool. - * mempool_alloc() cannot handle that particular combination, - * so we need two separate attempts. - */ + p = kmem_cache_zalloc(nfs_cdata_cachep, nfs_io_gfp_mask()); + if (!p) { p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT); if (!p) - p = kmem_cache_alloc(nfs_cdata_cachep, GFP_NOIO | - __GFP_NOWARN | __GFP_NORETRY); - if (!p) return NULL; + memset(p, 0, sizeof(*p)); } - - memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); return p; } @@ -104,9 +94,15 @@ EXPORT_SYMBOL_GPL(nfs_commit_free); static struct nfs_pgio_header *nfs_writehdr_alloc(void) { - struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_KERNEL); + struct nfs_pgio_header *p; - memset(p, 0, sizeof(*p)); + p = kmem_cache_zalloc(nfs_wdata_cachep, nfs_io_gfp_mask()); + if (!p) { + p = mempool_alloc(nfs_wdata_mempool, GFP_NOWAIT); + if (!p) + return NULL; + memset(p, 0, sizeof(*p)); + } p->rw_mode = FMODE_WRITE; return p; } @@ -306,7 +302,7 @@ static void nfs_set_pageerror(struct address_space *mapping) /* Force file size revalidation */ spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_REVAL_FORCED | - NFS_INO_REVAL_PAGECACHE | + NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); spin_unlock(&inode->i_lock); } @@ -316,7 +312,10 @@ static void nfs_mapping_set_error(struct page *page, int error) struct address_space *mapping = page_file_mapping(page); SetPageError(page); - mapping_set_error(mapping, error); + filemap_set_wb_err(mapping, error); + if (mapping->host) + errseq_set(&mapping->host->i_sb->s_wb_err, + error == -ENOSPC ? -ENOSPC : -EIO); nfs_set_pageerror(mapping); } @@ -1417,6 +1416,8 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, { int priority = flush_task_priority(how); + if (IS_SWAPFILE(hdr->inode)) + task_setup_data->flags |= RPC_TASK_SWAPPER; task_setup_data->priority = priority; rpc_ops->write_setup(hdr, msg, &task_setup_data->rpc_client); trace_nfs_initiate_write(hdr); @@ -1829,7 +1830,11 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, if (list_empty(head)) return 0; - data = nfs_commitdata_alloc(true); + data = nfs_commitdata_alloc(); + if (!data) { + nfs_retry_commit(head, NULL, cinfo, -1); + return -ENOMEM; + } /* Set up the argument struct */ nfs_init_commit(data, head, NULL, cinfo); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 784120cc217e..b48b9259e02c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -46,11 +46,6 @@ #define NFS_MAX_TRANSPORTS 16 /* - * These are the default flags for swap requests - */ -#define NFS_RPC_SWAPFLAGS (RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS) - -/* * Size of the NFS directory verifier */ #define NFS_DIR_VERIFIER_SIZE 2 @@ -101,13 +96,17 @@ struct nfs_open_context { struct nfs_open_dir_context { struct list_head list; + atomic_t cache_hits; + atomic_t cache_misses; unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; - __u64 dup_cookie; + __u64 last_cookie; pgoff_t page_index; - signed char duped; + unsigned int dtsize; + bool force_clear; bool eof; + struct rcu_head rcu_head; }; /* @@ -247,7 +246,6 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ #define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ #define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ -#define NFS_INO_REVAL_PAGECACHE BIT(5) /* must revalidate pagecache */ #define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ #define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ #define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ @@ -273,12 +271,11 @@ struct nfs4_copy_state { /* * Bit offsets in flags field */ -#define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ +#define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ -#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ @@ -355,17 +352,15 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_CHANGE - | NFS_INO_INVALID_CTIME; + nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | + NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | + NFS_INO_INVALID_SIZE; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } -static inline int nfs_server_capable(struct inode *inode, int cap) +static inline int nfs_server_capable(const struct inode *inode, int cap) { return NFS_SERVER(inode)->caps & cap; } @@ -513,10 +508,10 @@ static inline const struct cred *nfs_file_cred(struct file *file) * linux/fs/nfs/direct.c */ extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, - struct iov_iter *iter); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, - struct iov_iter *iter); +ssize_t nfs_file_direct_read(struct kiocb *iocb, + struct iov_iter *iter, bool swap); +ssize_t nfs_file_direct_write(struct kiocb *iocb, + struct iov_iter *iter, bool swap); /* * linux/fs/nfs/dir.c @@ -585,24 +580,22 @@ extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page *page); int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); +extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); -static inline int -nfs_have_writebacks(struct inode *inode) +static inline bool nfs_have_writebacks(const struct inode *inode) { if (S_ISREG(inode->i_mode)) return atomic_long_read(&NFS_I(inode)->nrequests) != 0; - return 0; + return false; } /* * linux/fs/nfs/read.c */ extern int nfs_readpage(struct file *, struct page *); -extern int nfs_readpages(struct file *, struct address_space *, - struct list_head *, unsigned); +void nfs_readahead(struct readahead_control *); /* * inline functions diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 6aa2a200676a..157d2bd6b241 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -152,6 +152,7 @@ struct nfs_server { #define NFS_MOUNT_SOFTREVAL 0x800000 #define NFS_MOUNT_WRITE_EAGER 0x01000000 #define NFS_MOUNT_WRITE_WAIT 0x02000000 +#define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 728cb0c1f0b6..49ba486aea5f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -745,8 +745,7 @@ struct nfs_auth_info { */ struct nfs_entry { __u64 ino; - __u64 cookie, - prev_cookie; + __u64 cookie; const char * name; unsigned int len; int eof; @@ -1798,6 +1797,8 @@ struct nfs_rpc_ops { struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); int (*discover_trunking)(struct nfs_server *, struct nfs_fh *); + void (*enable_swap)(struct inode *inode); + void (*disable_swap)(struct inode *inode); }; /* diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 98da816b5fc2..3e6ce288a7fc 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -99,6 +99,7 @@ struct rpc_auth_create_args { /* Flags for rpcauth_lookupcred() */ #define RPCAUTH_LOOKUP_NEW 0x01 /* Accept an uninitialised cred */ +#define RPCAUTH_LOOKUP_ASYNC 0x02 /* Don't block waiting for memory */ /* * Client authentication ops diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index db964bb63912..1d7a3e51b795 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -124,7 +124,6 @@ struct rpc_task_setup { #define RPC_TASK_MOVEABLE 0x0004 /* nfs4.1+ rpc tasks */ #define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ -#define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ #define RPC_TASK_NO_ROUND_ROBIN 0x0100 /* send requests on "main" xprt */ #define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */ @@ -263,6 +262,7 @@ void rpc_destroy_mempool(void); extern struct workqueue_struct *rpciod_workqueue; extern struct workqueue_struct *xprtiod_workqueue; void rpc_prepare_task(struct rpc_task *task); +gfp_t rpc_task_gfp_mask(void); static inline int rpc_wait_for_completion_task(struct rpc_task *task) { diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 3cdc8d878d81..45a9530d3839 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -139,6 +139,9 @@ struct rpc_xprt_ops { void (*rpcbind)(struct rpc_task *task); void (*set_port)(struct rpc_xprt *xprt, unsigned short port); void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); + int (*get_srcaddr)(struct rpc_xprt *xprt, char *buf, + size_t buflen); + unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); void (*prepare_request)(struct rpc_rqst *req); diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 8c2a712cb242..38284f25eddf 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -10,7 +10,6 @@ int init_socket_xprt(void); void cleanup_socket_xprt(void); -unsigned short get_srcport(struct rpc_xprt *); #define RPC_MIN_RESVPORT (1U) #define RPC_MAX_RESVPORT (65535U) @@ -89,5 +88,7 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_WRITE (5) #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) +#define XPRT_SOCK_CONNECT_SENT (8) +#define XPRT_SOCK_NOSPACE (9) #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ab8ae1f6ba84..0f34f13ebd55 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -311,7 +311,6 @@ TRACE_EVENT(rpc_request, { RPC_TASK_MOVEABLE, "MOVEABLE" }, \ { RPC_TASK_NULLCREDS, "NULLCREDS" }, \ { RPC_CALL_MAJORSEEN, "MAJORSEEN" }, \ - { RPC_TASK_ROOTCREDS, "ROOTCREDS" }, \ { RPC_TASK_DYNAMIC, "DYNAMIC" }, \ { RPC_TASK_NO_ROUND_ROBIN, "NO_ROUND_ROBIN" }, \ { RPC_TASK_SOFT, "SOFT" }, \ diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index 800bb0ffa6e6..1d2043708bf1 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -45,6 +45,7 @@ #define NFS4_OPEN_RESULT_CONFIRM 0x0002 #define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004 +#define NFS4_OPEN_RESULT_PRESERVE_UNLINKED 0x0008 #define NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK 0x0020 #define NFS4_SHARE_ACCESS_MASK 0x000F diff --git a/include/uapi/linux/nfs_fs.h b/include/uapi/linux/nfs_fs.h index 3afe3767c55d..ae0de165c014 100644 --- a/include/uapi/linux/nfs_fs.h +++ b/include/uapi/linux/nfs_fs.h @@ -52,7 +52,7 @@ #define NFSDBG_CALLBACK 0x0100 #define NFSDBG_CLIENT 0x0200 #define NFSDBG_MOUNT 0x0400 -#define NFSDBG_FSCACHE 0x0800 +#define NFSDBG_FSCACHE 0x0800 /* unused */ #define NFSDBG_PNFS 0x1000 #define NFSDBG_PNFS_LD 0x2000 #define NFSDBG_STATE 0x4000 diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index a9f0d17fdb0d..682fcd24bf43 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -615,6 +615,8 @@ rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags) }; struct rpc_cred *ret; + if (RPC_IS_ASYNC(task)) + lookupflags |= RPCAUTH_LOOKUP_ASYNC; ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags); put_cred(acred.cred); return ret; @@ -631,6 +633,8 @@ rpcauth_bind_machine_cred(struct rpc_task *task, int lookupflags) if (!acred.principal) return NULL; + if (RPC_IS_ASYNC(task)) + lookupflags |= RPCAUTH_LOOKUP_ASYNC; return auth->au_ops->lookup_cred(auth, &acred, lookupflags); } @@ -654,7 +658,7 @@ rpcauth_bindcred(struct rpc_task *task, const struct cred *cred, int flags) }; if (flags & RPC_TASK_ASYNC) - lookupflags |= RPCAUTH_LOOKUP_NEW; + lookupflags |= RPCAUTH_LOOKUP_NEW | RPCAUTH_LOOKUP_ASYNC; if (task->tk_op_cred) /* Task must use exactly this rpc_cred */ new = get_rpccred(task->tk_op_cred); @@ -666,7 +670,7 @@ rpcauth_bindcred(struct rpc_task *task, const struct cred *cred, int flags) /* If machine cred couldn't be bound, try a root cred */ if (new) ; - else if (cred == &machine_cred || (flags & RPC_TASK_ROOTCREDS)) + else if (cred == &machine_cred) new = rpcauth_bind_root_cred(task, lookupflags); else if (flags & RPC_TASK_NULLCREDS) new = authnull_ops.lookup_cred(NULL, NULL, 0); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 8eb7e8544815..de7e5b41ab8f 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -146,7 +146,7 @@ gss_alloc_context(void) { struct gss_cl_ctx *ctx; - ctx = kzalloc(sizeof(*ctx), GFP_NOFS); + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (ctx != NULL) { ctx->gc_proc = RPC_GSS_PROC_DATA; ctx->gc_seq = 1; /* NetApp 6.4R1 doesn't accept seq. no. 0 */ @@ -209,7 +209,7 @@ gss_fill_context(const void *p, const void *end, struct gss_cl_ctx *ctx, struct p = ERR_PTR(-EFAULT); goto err; } - ret = gss_import_sec_context(p, seclen, gm, &ctx->gc_gss_ctx, NULL, GFP_NOFS); + ret = gss_import_sec_context(p, seclen, gm, &ctx->gc_gss_ctx, NULL, GFP_KERNEL); if (ret < 0) { trace_rpcgss_import_ctx(ret); p = ERR_PTR(ret); @@ -511,7 +511,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, int vers; int err = -ENOMEM; - gss_msg = kzalloc(sizeof(*gss_msg), GFP_NOFS); + gss_msg = kzalloc(sizeof(*gss_msg), GFP_KERNEL); if (gss_msg == NULL) goto err; vers = get_pipe_version(gss_auth->net); @@ -527,7 +527,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, gss_msg->auth = gss_auth; kref_get(&gss_auth->kref); if (service_name) { - gss_msg->service_name = kstrdup_const(service_name, GFP_NOFS); + gss_msg->service_name = kstrdup_const(service_name, GFP_KERNEL); if (!gss_msg->service_name) { err = -ENOMEM; goto err_put_pipe_version; @@ -703,7 +703,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (mlen > MSG_BUF_MAXSIZE) goto out; err = -ENOMEM; - buf = kmalloc(mlen, GFP_NOFS); + buf = kmalloc(mlen, GFP_KERNEL); if (!buf) goto out; @@ -1220,7 +1220,7 @@ gss_dup_cred(struct gss_auth *gss_auth, struct gss_cred *gss_cred) struct gss_cred *new; /* Make a copy of the cred so that we can reference count it */ - new = kzalloc(sizeof(*gss_cred), GFP_NOFS); + new = kzalloc(sizeof(*gss_cred), GFP_KERNEL); if (new) { struct auth_cred acred = { .cred = gss_cred->gc_base.cr_cred, @@ -1343,7 +1343,11 @@ gss_hash_cred(struct auth_cred *acred, unsigned int hashbits) static struct rpc_cred * gss_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) { - return rpcauth_lookup_credcache(auth, acred, flags, GFP_NOFS); + gfp_t gfp = GFP_KERNEL; + + if (flags & RPCAUTH_LOOKUP_ASYNC) + gfp = GFP_NOWAIT | __GFP_NOWARN; + return rpcauth_lookup_credcache(auth, acred, flags, gfp); } static struct rpc_cred * @@ -1669,7 +1673,7 @@ gss_validate(struct rpc_task *task, struct xdr_stream *xdr) if (!p) goto validate_failed; - seq = kmalloc(4, GFP_NOFS); + seq = kmalloc(4, GFP_KERNEL); if (!seq) goto validate_failed; *seq = cpu_to_be32(task->tk_rqstp->rq_seqno); @@ -1779,11 +1783,11 @@ alloc_enc_pages(struct rpc_rqst *rqstp) rqstp->rq_enc_pages = kmalloc_array(rqstp->rq_enc_pages_num, sizeof(struct page *), - GFP_NOFS); + GFP_KERNEL); if (!rqstp->rq_enc_pages) goto out; for (i=0; i < rqstp->rq_enc_pages_num; i++) { - rqstp->rq_enc_pages[i] = alloc_page(GFP_NOFS); + rqstp->rq_enc_pages[i] = alloc_page(GFP_KERNEL); if (rqstp->rq_enc_pages[i] == NULL) goto out_free; } @@ -1987,7 +1991,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred, if (offset + len > rcv_buf->len) goto unwrap_failed; mic.len = len; - mic.data = kmalloc(len, GFP_NOFS); + mic.data = kmalloc(len, GFP_KERNEL); if (!mic.data) goto unwrap_failed; if (read_bytes_from_xdr_buf(rcv_buf, offset, mic.data, mic.len)) diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h index f6d9631bd9d0..c53b329092d4 100644 --- a/net/sunrpc/auth_gss/auth_gss_internal.h +++ b/net/sunrpc/auth_gss/auth_gss_internal.h @@ -35,7 +35,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) if (unlikely(q > end || q < p)) return ERR_PTR(-EFAULT); if (len) { - dest->data = kmemdup(p, len, GFP_NOFS); + dest->data = kmemdup(p, len, GFP_KERNEL); if (unlikely(dest->data == NULL)) return ERR_PTR(-ENOMEM); } else diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 634b6c6e0dcb..3ea58175e159 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -161,7 +161,7 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, return GSS_S_FAILURE; } - checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS); + checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_KERNEL); if (checksumdata == NULL) return GSS_S_FAILURE; @@ -169,7 +169,7 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen, if (IS_ERR(tfm)) goto out_free_cksum; - req = ahash_request_alloc(tfm, GFP_NOFS); + req = ahash_request_alloc(tfm, GFP_KERNEL); if (!req) goto out_free_ahash; @@ -257,7 +257,7 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen, return GSS_S_FAILURE; } - checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS); + checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_KERNEL); if (!checksumdata) return GSS_S_FAILURE; @@ -265,7 +265,7 @@ make_checksum_v2(struct krb5_ctx *kctx, char *header, int hdrlen, if (IS_ERR(tfm)) goto out_free_cksum; - req = ahash_request_alloc(tfm, GFP_NOFS); + req = ahash_request_alloc(tfm, GFP_KERNEL); if (!req) goto out_free_ahash; @@ -554,7 +554,7 @@ gss_krb5_cts_crypt(struct crypto_sync_skcipher *cipher, struct xdr_buf *buf, WARN_ON(0); return -ENOMEM; } - data = kmalloc(GSS_KRB5_MAX_BLOCKSIZE * 2, GFP_NOFS); + data = kmalloc(GSS_KRB5_MAX_BLOCKSIZE * 2, GFP_KERNEL); if (!data) return -ENOMEM; diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index fb117817ff5d..3200b971a814 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -49,7 +49,7 @@ krb5_make_seq_num(struct krb5_ctx *kctx, unsigned char *plain; s32 code; - plain = kmalloc(8, GFP_NOFS); + plain = kmalloc(8, GFP_KERNEL); if (!plain) return -ENOMEM; @@ -80,7 +80,7 @@ krb5_get_seq_num(struct krb5_ctx *kctx, dprintk("RPC: krb5_get_seq_num:\n"); - plain = kmalloc(8, GFP_NOFS); + plain = kmalloc(8, GFP_KERNEL); if (!plain) return -ENOMEM; diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index e95c009bb869..5f96e75f9eec 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -409,7 +409,7 @@ static u32 gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages) { - u8 *ptr, *plainhdr; + u8 *ptr; time64_t now; u8 flags = 0x00; __be16 *be16ptr; @@ -426,7 +426,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, return GSS_S_FAILURE; /* construct gss token header */ - ptr = plainhdr = buf->head[0].iov_base + offset; + ptr = buf->head[0].iov_base + offset; *ptr++ = (unsigned char) ((KG2_TOK_WRAP>>8) & 0xff); *ptr++ = (unsigned char) (KG2_TOK_WRAP & 0xff); diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index e7df1f782b2e..1e091d3fa607 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -40,11 +40,19 @@ unx_destroy(struct rpc_auth *auth) /* * Lookup AUTH_UNIX creds for current process */ -static struct rpc_cred * -unx_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) +static struct rpc_cred *unx_lookup_cred(struct rpc_auth *auth, + struct auth_cred *acred, int flags) { - struct rpc_cred *ret = mempool_alloc(unix_pool, GFP_NOFS); - + struct rpc_cred *ret; + + ret = kmalloc(sizeof(*ret), rpc_task_gfp_mask()); + if (!ret) { + if (!(flags & RPCAUTH_LOOKUP_ASYNC)) + return ERR_PTR(-ENOMEM); + ret = mempool_alloc(unix_pool, GFP_NOWAIT); + if (!ret) + return ERR_PTR(-ENOMEM); + } rpcauth_init_cred(ret, acred, auth, &unix_credops); ret->cr_flags = 1UL << RPCAUTH_CRED_UPTODATE; return ret; diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 22a2c235abf1..5a6b61dcdf2d 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -75,9 +75,9 @@ static int xprt_alloc_xdr_buf(struct xdr_buf *buf, gfp_t gfp_flags) return 0; } -static -struct rpc_rqst *xprt_alloc_bc_req(struct rpc_xprt *xprt, gfp_t gfp_flags) +static struct rpc_rqst *xprt_alloc_bc_req(struct rpc_xprt *xprt) { + gfp_t gfp_flags = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; struct rpc_rqst *req; /* Pre-allocate one backchannel rpc_rqst */ @@ -154,7 +154,7 @@ int xprt_setup_bc(struct rpc_xprt *xprt, unsigned int min_reqs) INIT_LIST_HEAD(&tmp_list); for (i = 0; i < min_reqs; i++) { /* Pre-allocate one backchannel rpc_rqst */ - req = xprt_alloc_bc_req(xprt, GFP_KERNEL); + req = xprt_alloc_bc_req(xprt); if (req == NULL) { printk(KERN_ERR "Failed to create bc rpc_rqst\n"); goto out_free; @@ -343,7 +343,7 @@ found: break; } else if (req) break; - new = xprt_alloc_bc_req(xprt, GFP_KERNEL); + new = xprt_alloc_bc_req(xprt); } while (new); return req; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index c83fe618767c..8bf2af8546d2 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1065,7 +1065,9 @@ rpc_task_get_next_xprt(struct rpc_clnt *clnt) static void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) { - if (task->tk_xprt) + if (task->tk_xprt && + !(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) && + (task->tk_flags & RPC_TASK_MOVEABLE))) return; if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN) task->tk_xprt = rpc_task_get_first_xprt(clnt); @@ -1085,8 +1087,6 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) task->tk_flags |= RPC_TASK_TIMEOUT; if (clnt->cl_noretranstimeo) task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT; - if (atomic_read(&clnt->cl_swapper)) - task->tk_flags |= RPC_TASK_SWAPPER; /* Add to the client's list of all tasks */ spin_lock(&clnt->cl_lock); list_add_tail(&task->tk_task, &clnt->cl_tasks); @@ -1745,6 +1745,9 @@ call_refreshresult(struct rpc_task *task) task->tk_cred_retry--; trace_rpc_retry_refresh_status(task); return; + case -ENOMEM: + rpc_delay(task, HZ >> 4); + return; } trace_rpc_refresh_status(task); rpc_call_rpcerror(task, status); @@ -2793,7 +2796,7 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, return -EINVAL; } - data = kmalloc(sizeof(*data), GFP_NOFS); + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; data->xps = xprt_switch_get(xps); @@ -3068,6 +3071,8 @@ rpc_clnt_swap_activate_callback(struct rpc_clnt *clnt, int rpc_clnt_swap_activate(struct rpc_clnt *clnt) { + while (clnt != clnt->cl_parent) + clnt = clnt->cl_parent; if (atomic_inc_return(&clnt->cl_swapper) == 1) return rpc_clnt_iterate_for_each_xprt(clnt, rpc_clnt_swap_activate_callback, NULL); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 647b323cc1d5..5a8e6d46809a 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -714,7 +714,7 @@ void rpcb_getport_async(struct rpc_task *task) goto bailout_nofree; } - map = kzalloc(sizeof(struct rpcbind_args), GFP_NOFS); + map = kzalloc(sizeof(struct rpcbind_args), rpc_task_gfp_mask()); if (!map) { status = -ENOMEM; goto bailout_release_client; @@ -730,7 +730,7 @@ void rpcb_getport_async(struct rpc_task *task) case RPCBVERS_4: case RPCBVERS_3: map->r_netid = xprt->address_strings[RPC_DISPLAY_NETID]; - map->r_addr = rpc_sockaddr2uaddr(sap, GFP_NOFS); + map->r_addr = rpc_sockaddr2uaddr(sap, rpc_task_gfp_mask()); if (!map->r_addr) { status = -ENOMEM; goto bailout_free_args; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index e2c835482791..b258b87a3ec2 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -57,6 +57,13 @@ struct workqueue_struct *rpciod_workqueue __read_mostly; struct workqueue_struct *xprtiod_workqueue __read_mostly; EXPORT_SYMBOL_GPL(xprtiod_workqueue); +gfp_t rpc_task_gfp_mask(void) +{ + if (current->flags & PF_WQ_WORKER) + return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + return GFP_KERNEL; +} + unsigned long rpc_task_timeout(const struct rpc_task *task) { @@ -186,11 +193,6 @@ static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue, /* * Add new request to wait queue. - * - * Swapper tasks always get inserted at the head of the queue. - * This should avoid many nasty memory deadlocks and hopefully - * improve overall performance. - * Everyone else gets appended to the queue to ensure proper FIFO behavior. */ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, struct rpc_task *task, @@ -199,8 +201,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, INIT_LIST_HEAD(&task->u.tk_wait.timer_list); if (RPC_IS_PRIORITY(queue)) __rpc_add_wait_queue_priority(queue, task, queue_priority); - else if (RPC_IS_SWAPPER(task)) - list_add(&task->u.tk_wait.list, &queue->tasks[0]); else list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]); task->tk_waitqueue = queue; @@ -876,6 +876,15 @@ void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata) ops->rpc_release(calldata); } +static bool xprt_needs_memalloc(struct rpc_xprt *xprt, struct rpc_task *tk) +{ + if (!xprt) + return false; + if (!atomic_read(&xprt->swapper)) + return false; + return test_bit(XPRT_LOCKED, &xprt->state) && xprt->snd_task == tk; +} + /* * This is the RPC `scheduler' (or rather, the finite state machine). */ @@ -884,6 +893,7 @@ static void __rpc_execute(struct rpc_task *task) struct rpc_wait_queue *queue; int task_is_async = RPC_IS_ASYNC(task); int status = 0; + unsigned long pflags = current->flags; WARN_ON_ONCE(RPC_IS_QUEUED(task)); if (RPC_IS_QUEUED(task)) @@ -906,6 +916,10 @@ static void __rpc_execute(struct rpc_task *task) } if (!do_action) break; + if (RPC_IS_SWAPPER(task) || + xprt_needs_memalloc(task->tk_xprt, task)) + current->flags |= PF_MEMALLOC; + trace_rpc_task_run_action(task, do_action); do_action(task); @@ -943,7 +957,7 @@ static void __rpc_execute(struct rpc_task *task) rpc_clear_running(task); spin_unlock(&queue->lock); if (task_is_async) - return; + goto out; /* sync task: sleep here */ trace_rpc_task_sync_sleep(task, task->tk_action); @@ -967,6 +981,8 @@ static void __rpc_execute(struct rpc_task *task) /* Release all resources associated with the task */ rpc_release_task(task); +out: + current_restore_flags(pflags, PF_MEMALLOC); } /* @@ -1021,15 +1037,15 @@ int rpc_malloc(struct rpc_task *task) struct rpc_rqst *rqst = task->tk_rqstp; size_t size = rqst->rq_callsize + rqst->rq_rcvsize; struct rpc_buffer *buf; - gfp_t gfp = GFP_NOFS; - - if (RPC_IS_SWAPPER(task)) - gfp = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN; + gfp_t gfp = rpc_task_gfp_mask(); size += sizeof(struct rpc_buffer); - if (size <= RPC_BUFFER_MAXSIZE) - buf = mempool_alloc(rpc_buffer_mempool, gfp); - else + if (size <= RPC_BUFFER_MAXSIZE) { + buf = kmem_cache_alloc(rpc_buffer_slabp, gfp); + /* Reach for the mempool if dynamic allocation fails */ + if (!buf && RPC_IS_ASYNC(task)) + buf = mempool_alloc(rpc_buffer_mempool, GFP_NOWAIT); + } else buf = kmalloc(size, gfp); if (!buf) @@ -1092,10 +1108,14 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta rpc_init_task_statistics(task); } -static struct rpc_task * -rpc_alloc_task(void) +static struct rpc_task *rpc_alloc_task(void) { - return (struct rpc_task *)mempool_alloc(rpc_task_mempool, GFP_NOFS); + struct rpc_task *task; + + task = kmem_cache_alloc(rpc_task_slabp, rpc_task_gfp_mask()); + if (task) + return task; + return mempool_alloc(rpc_task_mempool, GFP_NOWAIT); } /* diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index d52313af82bc..05b38bf68316 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -15,6 +15,7 @@ #include <linux/pagemap.h> #include <linux/udp.h> #include <linux/sunrpc/msg_prot.h> +#include <linux/sunrpc/sched.h> #include <linux/sunrpc/xdr.h> #include <linux/export.h> @@ -222,7 +223,7 @@ static int xprt_send_pagedata(struct socket *sock, struct msghdr *msg, { int err; - err = xdr_alloc_bvec(xdr, GFP_KERNEL); + err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); if (err < 0) return err; diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index 05c758da6a92..a3a2f8aeb80e 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -93,11 +93,14 @@ static ssize_t rpc_sysfs_xprt_dstaddr_show(struct kobject *kobj, struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj); ssize_t ret; - if (!xprt) - return 0; + if (!xprt) { + ret = sprintf(buf, "<closed>\n"); + goto out; + } ret = sprintf(buf, "%s\n", xprt->address_strings[RPC_DISPLAY_ADDR]); xprt_put(xprt); - return ret + 1; +out: + return ret; } static ssize_t rpc_sysfs_xprt_srcaddr_show(struct kobject *kobj, @@ -105,41 +108,45 @@ static ssize_t rpc_sysfs_xprt_srcaddr_show(struct kobject *kobj, char *buf) { struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj); - struct sockaddr_storage saddr; - struct sock_xprt *sock; - ssize_t ret = -1; + size_t buflen = PAGE_SIZE; + ssize_t ret; if (!xprt || !xprt_connected(xprt)) { - xprt_put(xprt); - return -ENOTCONN; - } - - sock = container_of(xprt, struct sock_xprt, xprt); - mutex_lock(&sock->recv_mutex); - if (sock->sock == NULL || - kernel_getsockname(sock->sock, (struct sockaddr *)&saddr) < 0) - goto out; - - ret = sprintf(buf, "%pISc\n", &saddr); -out: - mutex_unlock(&sock->recv_mutex); + ret = sprintf(buf, "<closed>\n"); + } else if (xprt->ops->get_srcaddr) { + ret = xprt->ops->get_srcaddr(xprt, buf, buflen); + if (ret > 0) { + if (ret < buflen - 1) { + buf[ret] = '\n'; + ret++; + buf[ret] = '\0'; + } + } else + ret = sprintf(buf, "<closed>\n"); + } else + ret = sprintf(buf, "<not a socket>\n"); xprt_put(xprt); - return ret + 1; + return ret; } static ssize_t rpc_sysfs_xprt_info_show(struct kobject *kobj, - struct kobj_attribute *attr, - char *buf) + struct kobj_attribute *attr, char *buf) { struct rpc_xprt *xprt = rpc_sysfs_xprt_kobj_get_xprt(kobj); + unsigned short srcport = 0; + size_t buflen = PAGE_SIZE; ssize_t ret; if (!xprt || !xprt_connected(xprt)) { - xprt_put(xprt); - return -ENOTCONN; + ret = sprintf(buf, "<closed>\n"); + goto out; } - ret = sprintf(buf, "last_used=%lu\ncur_cong=%lu\ncong_win=%lu\n" + if (xprt->ops->get_srcport) + srcport = xprt->ops->get_srcport(xprt); + + ret = snprintf(buf, buflen, + "last_used=%lu\ncur_cong=%lu\ncong_win=%lu\n" "max_num_slots=%u\nmin_num_slots=%u\nnum_reqs=%u\n" "binding_q_len=%u\nsending_q_len=%u\npending_q_len=%u\n" "backlog_q_len=%u\nmain_xprt=%d\nsrc_port=%u\n" @@ -147,14 +154,12 @@ static ssize_t rpc_sysfs_xprt_info_show(struct kobject *kobj, xprt->last_used, xprt->cong, xprt->cwnd, xprt->max_reqs, xprt->min_reqs, xprt->num_reqs, xprt->binding.qlen, xprt->sending.qlen, xprt->pending.qlen, - xprt->backlog.qlen, xprt->main, - (xprt->xprt_class->ident == XPRT_TRANSPORT_TCP) ? - get_srcport(xprt) : 0, + xprt->backlog.qlen, xprt->main, srcport, atomic_long_read(&xprt->queuelen), - (xprt->xprt_class->ident == XPRT_TRANSPORT_TCP) ? - xprt->address_strings[RPC_DISPLAY_PORT] : "0"); + xprt->address_strings[RPC_DISPLAY_PORT]); +out: xprt_put(xprt); - return ret + 1; + return ret; } static ssize_t rpc_sysfs_xprt_state_show(struct kobject *kobj, @@ -166,10 +171,7 @@ static ssize_t rpc_sysfs_xprt_state_show(struct kobject *kobj, int locked, connected, connecting, close_wait, bound, binding, closing, congested, cwnd_wait, write_space, offline, remove; - if (!xprt) - return 0; - - if (!xprt->state) { + if (!(xprt && xprt->state)) { ret = sprintf(buf, "state=CLOSED\n"); } else { locked = test_bit(XPRT_LOCKED, &xprt->state); @@ -201,7 +203,7 @@ static ssize_t rpc_sysfs_xprt_state_show(struct kobject *kobj, } xprt_put(xprt); - return ret + 1; + return ret; } static ssize_t rpc_sysfs_xprt_switch_info_show(struct kobject *kobj, @@ -220,7 +222,7 @@ static ssize_t rpc_sysfs_xprt_switch_info_show(struct kobject *kobj, xprt_switch->xps_nunique_destaddr_xprts, atomic_long_read(&xprt_switch->xps_queuelen)); xprt_switch_put(xprt_switch); - return ret + 1; + return ret; } static ssize_t rpc_sysfs_xprt_dstaddr_store(struct kobject *kobj, diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 5af484d6ba5e..515501f79290 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1354,17 +1354,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task) INIT_LIST_HEAD(&req->rq_xmit2); goto out; } - } else if (RPC_IS_SWAPPER(task)) { - list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) { - if (pos->rq_cong || pos->rq_bytes_sent) - continue; - if (RPC_IS_SWAPPER(pos->rq_task)) - continue; - /* Note: req is added _before_ pos */ - list_add_tail(&req->rq_xmit, &pos->rq_xmit); - INIT_LIST_HEAD(&req->rq_xmit2); - goto out; - } } else if (!req->rq_seqno) { list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) { if (pos->rq_task->tk_owner != task->tk_owner) @@ -1503,6 +1492,9 @@ bool xprt_prepare_transmit(struct rpc_task *task) return false; } + if (atomic_read(&xprt->swapper)) + /* This will be clear in __rpc_execute */ + current->flags |= PF_MEMALLOC; return true; } @@ -1692,7 +1684,7 @@ static struct rpc_rqst *xprt_dynamic_alloc_slot(struct rpc_xprt *xprt) goto out; ++xprt->num_reqs; spin_unlock(&xprt->reserve_lock); - req = kzalloc(sizeof(struct rpc_rqst), GFP_NOFS); + req = kzalloc(sizeof(*req), rpc_task_gfp_mask()); spin_lock(&xprt->reserve_lock); if (req != NULL) goto out; @@ -2112,7 +2104,14 @@ static void xprt_destroy(struct rpc_xprt *xprt) */ wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE); + /* + * xprt_schedule_autodisconnect() can run after XPRT_LOCKED + * is cleared. We use ->transport_lock to ensure the mod_timer() + * can only run *before* del_time_sync(), never after. + */ + spin_lock(&xprt->transport_lock); del_timer_sync(&xprt->timer); + spin_unlock(&xprt->transport_lock); /* * Destroy sockets etc from the system workqueue so they can diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 515dd7a66a04..3fcd8e1b2550 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -130,7 +130,7 @@ int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) if (IS_ERR(frmr)) goto out_mr_err; - sg = kmalloc_array(depth, sizeof(*sg), GFP_NOFS); + sg = kmalloc_array(depth, sizeof(*sg), GFP_KERNEL); if (!sg) goto out_list_err; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 42e375dbdadb..6b7e10e5a141 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -235,8 +235,11 @@ xprt_rdma_connect_worker(struct work_struct *work) struct rpcrdma_xprt *r_xprt = container_of(work, struct rpcrdma_xprt, rx_connect_worker.work); struct rpc_xprt *xprt = &r_xprt->rx_xprt; + unsigned int pflags = current->flags; int rc; + if (atomic_read(&xprt->swapper)) + current->flags |= PF_MEMALLOC; rc = rpcrdma_xprt_connect(r_xprt); xprt_clear_connecting(xprt); if (!rc) { @@ -250,6 +253,7 @@ xprt_rdma_connect_worker(struct work_struct *work) rpcrdma_xprt_disconnect(r_xprt); xprt_unlock_connect(xprt, r_xprt); xprt_wake_pending_tasks(xprt, rc); + current_restore_flags(pflags, PF_MEMALLOC); } /** @@ -517,7 +521,7 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) return; out_sleep: - task->tk_status = -EAGAIN; + task->tk_status = -ENOMEM; xprt_add_backlog(xprt, task); } @@ -570,8 +574,8 @@ xprt_rdma_allocate(struct rpc_task *task) gfp_t flags; flags = RPCRDMA_DEF_GFP; - if (RPC_IS_SWAPPER(task)) - flags = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN; + if (RPC_IS_ASYNC(task)) + flags = GFP_NOWAIT | __GFP_NOWARN; if (!rpcrdma_check_regbuf(r_xprt, req->rl_sendbuf, rqst->rq_callsize, flags)) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 7b5fce2faa10..2fbe9aaeec34 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -373,7 +373,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) struct rpcrdma_ep *ep; int rc; - ep = kzalloc(sizeof(*ep), GFP_NOFS); + ep = kzalloc(sizeof(*ep), GFP_KERNEL); if (!ep) return -ENOTCONN; ep->re_xprt = &r_xprt->rx_xprt; @@ -746,7 +746,7 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt) struct rpcrdma_mr *mr; int rc; - mr = kzalloc(sizeof(*mr), GFP_NOFS); + mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) break; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0f39e08ee580..78af7518f263 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -58,6 +58,7 @@ #include "sunrpc.h" static void xs_close(struct rpc_xprt *xprt); +static void xs_set_srcport(struct sock_xprt *transport, struct socket *sock); static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, struct socket *sock); @@ -427,9 +428,9 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, offset += want; } - want = xs_alloc_sparse_pages(buf, - min_t(size_t, count - offset, buf->page_len), - GFP_KERNEL); + want = xs_alloc_sparse_pages( + buf, min_t(size_t, count - offset, buf->page_len), + GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (seek < want) { ret = xs_read_bvec(sock, msg, flags, buf->bvec, xdr_buf_pagecount(buf), @@ -763,12 +764,12 @@ xs_stream_start_connect(struct sock_xprt *transport) /** * xs_nospace - handle transmit was incomplete * @req: pointer to RPC request + * @transport: pointer to struct sock_xprt * */ -static int xs_nospace(struct rpc_rqst *req) +static int xs_nospace(struct rpc_rqst *req, struct sock_xprt *transport) { - struct rpc_xprt *xprt = req->rq_xprt; - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + struct rpc_xprt *xprt = &transport->xprt; struct sock *sk = transport->inet; int ret = -EAGAIN; @@ -780,24 +781,44 @@ static int xs_nospace(struct rpc_rqst *req) /* Don't race with disconnect */ if (xprt_connected(xprt)) { /* wait for more buffer space */ + set_bit(XPRT_SOCK_NOSPACE, &transport->sock_state); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; xprt_wait_for_buffer_space(xprt); } else ret = -ENOTCONN; spin_unlock(&xprt->transport_lock); + return ret; +} - /* Race breaker in case memory is freed before above code is called */ - if (ret == -EAGAIN) { - struct socket_wq *wq; +static int xs_sock_nospace(struct rpc_rqst *req) +{ + struct sock_xprt *transport = + container_of(req->rq_xprt, struct sock_xprt, xprt); + struct sock *sk = transport->inet; + int ret = -EAGAIN; - rcu_read_lock(); - wq = rcu_dereference(sk->sk_wq); - set_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags); - rcu_read_unlock(); + lock_sock(sk); + if (!sock_writeable(sk)) + ret = xs_nospace(req, transport); + release_sock(sk); + return ret; +} - sk->sk_write_space(sk); - } +static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait) +{ + struct sock_xprt *transport = + container_of(req->rq_xprt, struct sock_xprt, xprt); + struct sock *sk = transport->inet; + int ret = -EAGAIN; + + if (vm_wait) + return -ENOBUFS; + lock_sock(sk); + if (!sk_stream_memory_free(sk)) + ret = xs_nospace(req, transport); + release_sock(sk); return ret; } @@ -805,7 +826,8 @@ static void xs_stream_prepare_request(struct rpc_rqst *req) { xdr_free_bvec(&req->rq_rcv_buf); - req->rq_task->tk_status = xdr_alloc_bvec(&req->rq_rcv_buf, GFP_KERNEL); + req->rq_task->tk_status = xdr_alloc_bvec( + &req->rq_rcv_buf, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); } /* @@ -851,6 +873,7 @@ static int xs_local_send_request(struct rpc_rqst *req) struct msghdr msg = { .msg_flags = XS_SENDMSG_FLAGS, }; + bool vm_wait; unsigned int sent; int status; @@ -863,15 +886,14 @@ static int xs_local_send_request(struct rpc_rqst *req) xs_pktdump("packet data:", req->rq_svec->iov_base, req->rq_svec->iov_len); + vm_wait = sk_stream_is_writeable(transport->inet) ? true : false; + req->rq_xtime = ktime_get(); status = xprt_sock_sendmsg(transport->sock, &msg, xdr, transport->xmit.offset, rm, &sent); dprintk("RPC: %s(%u) = %d\n", __func__, xdr->len - transport->xmit.offset, status); - if (status == -EAGAIN && sock_writeable(transport->inet)) - status = -ENOBUFS; - if (likely(sent > 0) || status == 0) { transport->xmit.offset += sent; req->rq_bytes_sent = transport->xmit.offset; @@ -881,13 +903,12 @@ static int xs_local_send_request(struct rpc_rqst *req) return 0; } status = -EAGAIN; + vm_wait = false; } switch (status) { - case -ENOBUFS: - break; case -EAGAIN: - status = xs_nospace(req); + status = xs_stream_nospace(req, vm_wait); break; default: dprintk("RPC: sendmsg returned unrecognized error %d\n", @@ -963,7 +984,7 @@ process_status: /* Should we call xs_close() here? */ break; case -EAGAIN: - status = xs_nospace(req); + status = xs_sock_nospace(req); break; case -ENETUNREACH: case -ENOBUFS: @@ -1005,7 +1026,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req) struct msghdr msg = { .msg_flags = XS_SENDMSG_FLAGS, }; - bool vm_wait = false; + bool vm_wait; unsigned int sent; int status; @@ -1025,12 +1046,17 @@ static int xs_tcp_send_request(struct rpc_rqst *req) if (test_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state)) xs_tcp_set_socket_timeouts(xprt, transport->sock); + xs_set_srcport(transport, transport->sock); + /* Continue transmitting the packet/record. We must be careful * to cope with writespace callbacks arriving _after_ we have * called sendmsg(). */ req->rq_xtime = ktime_get(); tcp_sock_set_cork(transport->inet, true); - while (1) { + + vm_wait = sk_stream_is_writeable(transport->inet) ? true : false; + + do { status = xprt_sock_sendmsg(transport->sock, &msg, xdr, transport->xmit.offset, rm, &sent); @@ -1051,31 +1077,10 @@ static int xs_tcp_send_request(struct rpc_rqst *req) WARN_ON_ONCE(sent == 0 && status == 0); - if (status == -EAGAIN ) { - /* - * Return EAGAIN if we're sure we're hitting the - * socket send buffer limits. - */ - if (test_bit(SOCK_NOSPACE, &transport->sock->flags)) - break; - /* - * Did we hit a memory allocation failure? - */ - if (sent == 0) { - status = -ENOBUFS; - if (vm_wait) - break; - /* Retry, knowing now that we're below the - * socket send buffer limit - */ - vm_wait = true; - } - continue; - } - if (status < 0) - break; - vm_wait = false; - } + if (sent > 0) + vm_wait = false; + + } while (status == 0); switch (status) { case -ENOTSOCK: @@ -1083,7 +1088,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req) /* Should we call xs_close() here? */ break; case -EAGAIN: - status = xs_nospace(req); + status = xs_stream_nospace(req, vm_wait); break; case -ECONNRESET: case -ECONNREFUSED: @@ -1124,6 +1129,7 @@ static void xs_sock_reset_state_flags(struct rpc_xprt *xprt) clear_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state); clear_bit(XPRT_SOCK_WAKE_WRITE, &transport->sock_state); clear_bit(XPRT_SOCK_WAKE_DISCONNECT, &transport->sock_state); + clear_bit(XPRT_SOCK_NOSPACE, &transport->sock_state); } static void xs_run_error_worker(struct sock_xprt *transport, unsigned int nr) @@ -1470,7 +1476,6 @@ static void xs_tcp_state_change(struct sock *sk) static void xs_write_space(struct sock *sk) { - struct socket_wq *wq; struct sock_xprt *transport; struct rpc_xprt *xprt; @@ -1481,15 +1486,10 @@ static void xs_write_space(struct sock *sk) if (unlikely(!(xprt = xprt_from_sock(sk)))) return; transport = container_of(xprt, struct sock_xprt, xprt); - rcu_read_lock(); - wq = rcu_dereference(sk->sk_wq); - if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) - goto out; - + if (!test_and_clear_bit(XPRT_SOCK_NOSPACE, &transport->sock_state)) + return; xs_run_error_worker(transport, XPRT_SOCK_WAKE_WRITE); sk->sk_write_pending--; -out: - rcu_read_unlock(); } /** @@ -1638,7 +1638,7 @@ static int xs_get_srcport(struct sock_xprt *transport) return port; } -unsigned short get_srcport(struct rpc_xprt *xprt) +static unsigned short xs_sock_srcport(struct rpc_xprt *xprt) { struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt); unsigned short ret = 0; @@ -1648,7 +1648,25 @@ unsigned short get_srcport(struct rpc_xprt *xprt) mutex_unlock(&sock->recv_mutex); return ret; } -EXPORT_SYMBOL(get_srcport); + +static int xs_sock_srcaddr(struct rpc_xprt *xprt, char *buf, size_t buflen) +{ + struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt); + union { + struct sockaddr sa; + struct sockaddr_storage st; + } saddr; + int ret = -ENOTCONN; + + mutex_lock(&sock->recv_mutex); + if (sock->sock) { + ret = kernel_getsockname(sock->sock, &saddr.sa); + if (ret >= 0) + ret = snprintf(buf, buflen, "%pISc", &saddr.sa); + } + mutex_unlock(&sock->recv_mutex); + return ret; +} static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port) { @@ -1830,7 +1848,6 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_user_data = xprt; sk->sk_data_ready = xs_data_ready; sk->sk_write_space = xs_udp_write_space; - sock_set_flag(sk, SOCK_FASYNC); sk->sk_error_report = xs_error_report; xprt_clear_connected(xprt); @@ -1936,9 +1953,9 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) #if IS_ENABLED(CONFIG_SUNRPC_SWAP) /* - * Note that this should be called with XPRT_LOCKED held (or when we otherwise - * know that we have exclusive access to the socket), to guard against - * races with xs_reset_transport. + * Note that this should be called with XPRT_LOCKED held, or recv_mutex + * held, or when we otherwise know that we have exclusive access to the + * socket, to guard against races with xs_reset_transport. */ static void xs_set_memalloc(struct rpc_xprt *xprt) { @@ -1967,13 +1984,11 @@ xs_enable_swap(struct rpc_xprt *xprt) { struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt); - if (atomic_inc_return(&xprt->swapper) != 1) - return 0; - if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) - return -ERESTARTSYS; - if (xs->inet) + mutex_lock(&xs->recv_mutex); + if (atomic_inc_return(&xprt->swapper) == 1 && + xs->inet) sk_set_memalloc(xs->inet); - xprt_release_xprt(xprt, NULL); + mutex_unlock(&xs->recv_mutex); return 0; } @@ -1989,13 +2004,11 @@ xs_disable_swap(struct rpc_xprt *xprt) { struct sock_xprt *xs = container_of(xprt, struct sock_xprt, xprt); - if (!atomic_dec_and_test(&xprt->swapper)) - return; - if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) - return; - if (xs->inet) + mutex_lock(&xs->recv_mutex); + if (atomic_dec_and_test(&xprt->swapper) && + xs->inet) sk_clear_memalloc(xs->inet); - xprt_release_xprt(xprt, NULL); + mutex_unlock(&xs->recv_mutex); } #else static void xs_set_memalloc(struct rpc_xprt *xprt) @@ -2028,7 +2041,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_user_data = xprt; sk->sk_data_ready = xs_data_ready; sk->sk_write_space = xs_udp_write_space; - sock_set_flag(sk, SOCK_FASYNC); xprt_set_connected(xprt); @@ -2052,7 +2064,10 @@ static void xs_udp_setup_socket(struct work_struct *work) struct rpc_xprt *xprt = &transport->xprt; struct socket *sock; int status = -EIO; + unsigned int pflags = current->flags; + if (atomic_read(&xprt->swapper)) + current->flags |= PF_MEMALLOC; sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, SOCK_DGRAM, IPPROTO_UDP, false); @@ -2072,6 +2087,7 @@ out: xprt_clear_connecting(xprt); xprt_unlock_connect(xprt, transport); xprt_wake_pending_tasks(xprt, status); + current_restore_flags(pflags, PF_MEMALLOC); } /** @@ -2191,7 +2207,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_data_ready; sk->sk_state_change = xs_tcp_state_change; sk->sk_write_space = xs_tcp_write_space; - sock_set_flag(sk, SOCK_FASYNC); sk->sk_error_report = xs_error_report; /* socket options */ @@ -2231,11 +2246,19 @@ static void xs_tcp_setup_socket(struct work_struct *work) struct socket *sock = transport->sock; struct rpc_xprt *xprt = &transport->xprt; int status; + unsigned int pflags = current->flags; - if (!sock) { - sock = xs_create_sock(xprt, transport, - xs_addr(xprt)->sa_family, SOCK_STREAM, - IPPROTO_TCP, true); + if (atomic_read(&xprt->swapper)) + current->flags |= PF_MEMALLOC; + + if (xprt_connected(xprt)) + goto out; + if (test_and_clear_bit(XPRT_SOCK_CONNECT_SENT, + &transport->sock_state) || + !sock) { + xs_reset_transport(transport); + sock = xs_create_sock(xprt, transport, xs_addr(xprt)->sa_family, + SOCK_STREAM, IPPROTO_TCP, true); if (IS_ERR(sock)) { xprt_wake_pending_tasks(xprt, PTR_ERR(sock)); goto out; @@ -2255,10 +2278,9 @@ static void xs_tcp_setup_socket(struct work_struct *work) sock->sk->sk_state); switch (status) { case 0: - xs_set_srcport(transport, sock); - fallthrough; case -EINPROGRESS: /* SYN_SENT! */ + set_bit(XPRT_SOCK_CONNECT_SENT, &transport->sock_state); if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; fallthrough; @@ -2296,6 +2318,7 @@ out: xprt_clear_connecting(xprt); out_unlock: xprt_unlock_connect(xprt, transport); + current_restore_flags(pflags, PF_MEMALLOC); } /** @@ -2319,13 +2342,9 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); - if (transport->sock != NULL && !xprt_connecting(xprt)) { + if (transport->sock != NULL) { dprintk("RPC: xs_connect delayed xprt %p for %lu " - "seconds\n", - xprt, xprt->reestablish_timeout / HZ); - - /* Start by resetting any existing state */ - xs_reset_transport(transport); + "seconds\n", xprt, xprt->reestablish_timeout / HZ); delay = xprt_reconnect_delay(xprt); xprt_reconnect_backoff(xprt, XS_TCP_INIT_REEST_TO); @@ -2487,7 +2506,7 @@ static int bc_malloc(struct rpc_task *task) return -EINVAL; } - page = alloc_page(GFP_KERNEL); + page = alloc_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); if (!page) return -ENOMEM; @@ -2621,6 +2640,8 @@ static const struct rpc_xprt_ops xs_udp_ops = { .rpcbind = rpcb_getport_async, .set_port = xs_set_port, .connect = xs_connect, + .get_srcaddr = xs_sock_srcaddr, + .get_srcport = xs_sock_srcport, .buf_alloc = rpc_malloc, .buf_free = rpc_free, .send_request = xs_udp_send_request, @@ -2643,6 +2664,8 @@ static const struct rpc_xprt_ops xs_tcp_ops = { .rpcbind = rpcb_getport_async, .set_port = xs_set_port, .connect = xs_connect, + .get_srcaddr = xs_sock_srcaddr, + .get_srcport = xs_sock_srcport, .buf_alloc = rpc_malloc, .buf_free = rpc_free, .prepare_request = xs_stream_prepare_request, |