diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-03-12 14:50:42 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-03-12 14:50:42 -0700 |
commit | 1fbf3e48123d701584bc75ccac67ef2fe412ac4c (patch) | |
tree | caca042e8d753d4147219820db8497a766b873bd /fs/nfs/dir.c | |
parent | f88c5942cfaf7d55e46d395136cccaca65b2e3bf (diff) | |
parent | 4d6c671ace569d4b0d3f8d92ab3aef18a5d166bc (diff) | |
download | linux-1fbf3e48123d701584bc75ccac67ef2fe412ac4c.tar.bz2 |
Merge tag 'nfs-for-5.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs
Pull NFS client updates from Trond Myklebust:
"Highlights include:
Stable fixes:
- Fixes for NFS I/O request leakages
- Fix error handling paths in the NFS I/O recoalescing code
- Reinitialise NFSv4.1 sequence results before retransmitting a
request
- Fix a soft lockup in the delegation recovery code
- Bulk destroy of layouts needs to be safe w.r.t. umount
- Prevent thundering herd issues when the SUNRPC socket is not
connected
- Respect RPC call timeouts when retrying transmission
Features:
- Convert rpc auth layer to use xdr_streams
- Config option to disable insecure RPCSEC_GSS crypto types
- Reduce size of RPC receive buffers
- Readdirplus optimization by cache mechanism
- Convert SUNRPC socket send code to use iov_iter()
- SUNRPC micro-optimisations to avoid indirect calls
- Add support for the pNFS LAYOUTERROR operation and use it with the
pNFS/flexfiles driver
- Add trace events to report non-zero NFS status codes
- Various removals of unnecessary dprintks
Bugfixes and cleanups:
- Fix a number of sparse warnings and documentation format warnings
- Fix nfs_parse_devname to not modify it's argument
- Fix potential corruption of page being written through pNFS/blocks
- fix xfstest generic/099 failures on nfsv3
- Avoid NFSv4.1 "false retries" when RPC calls are interrupted
- Abort I/O early if the pNFS/flexfiles layout segment was
invalidated
- Avoid unnecessary pNFS/flexfiles layout invalidations"
* tag 'nfs-for-5.1-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (90 commits)
SUNRPC: Take the transport send lock before binding+connecting
SUNRPC: Micro-optimise when the task is known not to be sleeping
SUNRPC: Check whether the task was transmitted before rebind/reconnect
SUNRPC: Remove redundant calls to RPC_IS_QUEUED()
SUNRPC: Clean up
SUNRPC: Respect RPC call timeouts when retrying transmission
SUNRPC: Fix up RPC back channel transmission
SUNRPC: Prevent thundering herd when the socket is not connected
SUNRPC: Allow dynamic allocation of back channel slots
NFSv4.1: Bump the default callback session slot count to 16
SUNRPC: Convert remaining GFP_NOIO, and GFP_NOWAIT sites in sunrpc
NFS/flexfiles: Clean up mirror DS initialisation
NFS/flexfiles: Remove dead code in ff_layout_mirror_valid()
NFS/flexfile: Simplify nfs4_ff_layout_select_ds_stateid()
NFS/flexfile: Simplify nfs4_ff_layout_ds_version()
NFS/flexfiles: Simplify ff_layout_get_ds_cred()
NFS/flexfiles: Simplify nfs4_ff_find_or_create_ds_client()
NFS/flexfiles: Simplify nfs4_ff_layout_select_ds_fh()
NFS/flexfiles: Speed up read failover when DSes are down
NFS/flexfiles: Don't invalidate DS deviceids for being unresponsive
...
Diffstat (limited to 'fs/nfs/dir.c')
-rw-r--r-- | fs/nfs/dir.c | 98 |
1 files changed, 88 insertions, 10 deletions
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 6bf4471850c8..a71d0b42d160 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -139,12 +139,19 @@ struct nfs_cache_array { struct nfs_cache_array_entry array[0]; }; +struct readdirvec { + unsigned long nr; + unsigned long index; + struct page *pages[NFS_MAX_READDIR_RAPAGES]; +}; + typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, bool); typedef struct { struct file *file; struct page *page; struct dir_context *ctx; unsigned long page_index; + struct readdirvec pvec; u64 *dir_cookie; u64 last_cookie; loff_t current_index; @@ -524,6 +531,10 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en struct nfs_cache_array *array; unsigned int count = 0; int status; + int max_rapages = NFS_MAX_READDIR_RAPAGES; + + desc->pvec.index = desc->page_index; + desc->pvec.nr = 0; scratch = alloc_page(GFP_KERNEL); if (scratch == NULL) @@ -548,20 +559,40 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en if (desc->plus) nfs_prime_dcache(file_dentry(desc->file), entry); - status = nfs_readdir_add_to_array(entry, page); + status = nfs_readdir_add_to_array(entry, desc->pvec.pages[desc->pvec.nr]); + if (status == -ENOSPC) { + desc->pvec.nr++; + if (desc->pvec.nr == max_rapages) + break; + status = nfs_readdir_add_to_array(entry, desc->pvec.pages[desc->pvec.nr]); + } if (status != 0) break; } while (!entry->eof); + /* + * page and desc->pvec.pages[0] are valid, don't need to check + * whether or not to be NULL. + */ + copy_highpage(page, desc->pvec.pages[0]); + out_nopages: if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) { - array = kmap(page); + array = kmap_atomic(desc->pvec.pages[desc->pvec.nr]); array->eof_index = array->size; status = 0; - kunmap(page); + kunmap_atomic(array); } put_page(scratch); + + /* + * desc->pvec.nr > 0 means at least one page was completely filled, + * we should return -ENOSPC. Otherwise function + * nfs_readdir_xdr_to_array will enter infinite loop. + */ + if (desc->pvec.nr > 0) + return -ENOSPC; return status; } @@ -574,8 +605,8 @@ void nfs_readdir_free_pages(struct page **pages, unsigned int npages) } /* - * nfs_readdir_large_page will allocate pages that must be freed with a call - * to nfs_readdir_free_pagearray + * nfs_readdir_alloc_pages() will allocate pages that must be freed with a call + * to nfs_readdir_free_pages() */ static int nfs_readdir_alloc_pages(struct page **pages, unsigned int npages) @@ -595,6 +626,24 @@ out_freepages: return -ENOMEM; } +/* + * nfs_readdir_rapages_init initialize rapages by nfs_cache_array structure. + */ +static +void nfs_readdir_rapages_init(nfs_readdir_descriptor_t *desc) +{ + struct nfs_cache_array *array; + int max_rapages = NFS_MAX_READDIR_RAPAGES; + int index; + + for (index = 0; index < max_rapages; index++) { + array = kmap_atomic(desc->pvec.pages[index]); + memset(array, 0, sizeof(struct nfs_cache_array)); + array->eof_index = -1; + kunmap_atomic(array); + } +} + static int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode) { @@ -605,6 +654,12 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, int status = -ENOMEM; unsigned int array_size = ARRAY_SIZE(pages); + /* + * This means we hit readdir rdpages miss, the preallocated rdpages + * are useless, the preallocate rdpages should be reinitialized. + */ + nfs_readdir_rapages_init(desc); + entry.prev_cookie = 0; entry.cookie = desc->last_cookie; entry.eof = 0; @@ -664,9 +719,24 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) struct inode *inode = file_inode(desc->file); int ret; - ret = nfs_readdir_xdr_to_array(desc, page, inode); - if (ret < 0) - goto error; + /* + * If desc->page_index in range desc->pvec.index and + * desc->pvec.index + desc->pvec.nr, we get readdir cache hit. + */ + if (desc->page_index >= desc->pvec.index && + desc->page_index < (desc->pvec.index + desc->pvec.nr)) { + /* + * page and desc->pvec.pages[x] are valid, don't need to check + * whether or not to be NULL. + */ + copy_highpage(page, desc->pvec.pages[desc->page_index - desc->pvec.index]); + ret = 0; + } else { + ret = nfs_readdir_xdr_to_array(desc, page, inode); + if (ret < 0) + goto error; + } + SetPageUptodate(page); if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) { @@ -831,6 +901,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) *desc = &my_desc; struct nfs_open_dir_context *dir_ctx = file->private_data; int res = 0; + int max_rapages = NFS_MAX_READDIR_RAPAGES; dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n", file, (long long)ctx->pos); @@ -850,6 +921,12 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->decode = NFS_PROTO(inode)->decode_dirent; desc->plus = nfs_use_readdirplus(inode, ctx); + res = nfs_readdir_alloc_pages(desc->pvec.pages, max_rapages); + if (res < 0) + return -ENOMEM; + + nfs_readdir_rapages_init(desc); + if (ctx->pos == 0 || nfs_attribute_cache_expired(inode)) res = nfs_revalidate_mapping(inode, file->f_mapping); if (res < 0) @@ -885,6 +962,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) break; } while (!desc->eof); out: + nfs_readdir_free_pages(desc->pvec.pages, max_rapages); if (res > 0) res = 0; dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res); @@ -945,7 +1023,7 @@ static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, /** * nfs_force_lookup_revalidate - Mark the directory as having changed - * @dir - pointer to directory inode + * @dir: pointer to directory inode * * This forces the revalidation code in nfs_lookup_revalidate() to do a * full lookup on all child dentries of 'dir' whenever a change occurs @@ -1649,7 +1727,7 @@ 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); full_reval: return nfs_do_lookup_revalidate(dir, dentry, flags); |