From 8c71139d9f84c1963b0a416941244502a20a7e52 Mon Sep 17 00:00:00 2001 From: Calum Mackay Date: Sat, 24 Oct 2020 22:36:38 +0100 Subject: SUNRPC: correct error code comment in xs_tcp_setup_socket() This comment was introduced by commit 6ea44adce915 ("SUNRPC: ensure correct error is reported by xs_tcp_setup_socket()"). I believe EIO was a typo at the time: it should have been EAGAIN. Subsequently, commit 0445f92c5d53 ("SUNRPC: Fix disconnection races") changed that to ENOTCONN. Rather than trying to keep the comment here in sync with the code in xprt_force_disconnect(), make the point in a non-specific way. Fixes: 6ea44adce915 ("SUNRPC: ensure correct error is reported by xs_tcp_setup_socket()") Signed-off-by: Calum Mackay Signed-off-by: Anna Schumaker --- net/sunrpc/xprtsock.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c56a66cdf4ac..2e84da64200e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2276,10 +2276,8 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EHOSTUNREACH: case -EADDRINUSE: case -ENOBUFS: - /* - * xs_tcp_force_close() wakes tasks with -EIO. - * We need to wake them first to ensure the - * correct error code. + /* xs_tcp_force_close() wakes tasks with a fixed error code. + * We need to wake them first to ensure the correct error code. */ xprt_wake_pending_tasks(xprt, status); xs_tcp_force_close(xprt); -- cgit From 12b20ce34933c007cc850151cadf9c8c585c8b8d Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Mon, 9 Nov 2020 15:24:05 +0530 Subject: net: sunrpc: xprtsock.c: Corrected few spellings ,in comments Few trivial and rudimentary spell corrections. Signed-off-by: Bhaskar Chowdhury Signed-off-by: Anna Schumaker --- net/sunrpc/xprtsock.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2e84da64200e..e1ed21d45cdb 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -829,7 +829,7 @@ xs_stream_record_marker(struct xdr_buf *xdr) * EAGAIN: The socket was blocked, please call again later to * complete the request * ENOTCONN: Caller needs to invoke connect logic then call again - * other: Some other error occured, the request was not sent + * other: Some other error occurred, the request was not sent */ static int xs_local_send_request(struct rpc_rqst *req) { @@ -1665,7 +1665,7 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) * This ensures that we can continue to establish TCP * connections even when all local ephemeral ports are already * a part of some TCP connection. This makes no difference - * for UDP sockets, but also doens't harm them. + * for UDP sockets, but also doesn't harm them. * * If we're asking for any reserved port (i.e. port == 0 && * transport->xprt.resvport == 1) xs_get_srcport above will @@ -2378,7 +2378,7 @@ static void xs_error_handle(struct work_struct *work) } /** - * xs_local_print_stats - display AF_LOCAL socket-specifc stats + * xs_local_print_stats - display AF_LOCAL socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2407,7 +2407,7 @@ static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) } /** - * xs_udp_print_stats - display UDP socket-specifc stats + * xs_udp_print_stats - display UDP socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * @@ -2431,7 +2431,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) } /** - * xs_tcp_print_stats - display TCP socket-specifc stats + * xs_tcp_print_stats - display TCP socket-specific stats * @xprt: rpc_xprt struct containing statistics * @seq: output file * -- cgit From c0da04ae079fb4979b921f8b46a6eeb15a4f803c Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 9 Nov 2020 03:12:03 -0500 Subject: fs/nfs: remove duplicate include 'nfs42.h' is already included above and can be removed here. Signed-off-by: Menglong Dong Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2f4679a62712..224773eb61b1 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -71,10 +71,6 @@ #include "nfs4trace.h" -#ifdef CONFIG_NFS_V4_2 -#include "nfs42.h" -#endif /* CONFIG_NFS_V4_2 */ - #define NFSDBG_FACILITY NFSDBG_PROC #define NFS4_BITMASK_SZ 3 -- cgit From 93f479d3ad05497f29f2bed58e4a6c6a4f0a548c Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 20 Nov 2020 12:40:02 -0600 Subject: SUNRPC: Fix fall-through warnings for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix multiple warnings by explicitly adding multiple break statements instead of letting the code fall through to the next case. Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva Signed-off-by: Anna Schumaker --- net/sunrpc/rpc_pipe.c | 1 + net/sunrpc/xprtsock.c | 1 + 2 files changed, 2 insertions(+) diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 8241f5a4a01c..09c000d490a1 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -478,6 +478,7 @@ rpc_get_inode(struct super_block *sb, umode_t mode) inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; inc_nlink(inode); + break; default: break; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e1ed21d45cdb..e35760f238a4 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1875,6 +1875,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start; xprt_set_connected(xprt); + break; case -ENOBUFS: break; case -ENOENT: -- cgit From ffb81717a166b3c4a676ada61283b3121448e503 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 20 Nov 2020 12:26:46 -0600 Subject: nfs: Fix fall-through warnings for Clang In preparation to enable -Wimplicit-fallthrough for Clang, fix multiple warnings by explicitly add multiple break/goto/return/fallthrough statements instead of just letting the code fall through to the next case. Link: https://github.com/KSPP/linux/issues/115 Signed-off-by: Gustavo A. R. Silva Signed-off-by: Anna Schumaker --- fs/nfs/nfs3acl.c | 1 + fs/nfs/nfs4client.c | 1 + fs/nfs/nfs4proc.c | 2 ++ fs/nfs/nfs4state.c | 1 + fs/nfs/pnfs.c | 2 ++ 5 files changed, 7 insertions(+) diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index c6c863382f37..68e206cf4c4e 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -111,6 +111,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type) fallthrough; case -ENOTSUPP: status = -EOPNOTSUPP; + goto getout; default: goto getout; } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 86acffe7335c..889a9f4c0310 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -609,6 +609,7 @@ found: * changed. Schedule recovery! */ nfs4_schedule_path_down_recovery(pos); + goto out; default: goto out; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 224773eb61b1..34570a7785fa 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2227,6 +2227,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct default: printk(KERN_ERR "NFS: %s: unhandled error " "%d.\n", __func__, err); + fallthrough; case 0: case -ENOENT: case -EAGAIN: @@ -9701,6 +9702,7 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata) case -NFS4ERR_BADLAYOUT: /* no layout */ case -NFS4ERR_GRACE: /* loca_recalim always false */ task->tk_status = 0; + break; case 0: break; default: diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 4bf10792cb5b..3a51351bdc6a 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1125,6 +1125,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) " sequence-id error on an" " unconfirmed sequence %p!\n", seqid->sequence); + return; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_BAD_STATEID: diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index af64b4e6fd1f..102b66e0bdef 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2875,6 +2875,7 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc, switch (trypnfs) { case PNFS_NOT_ATTEMPTED: pnfs_write_through_mds(desc, hdr); + break; case PNFS_ATTEMPTED: break; case PNFS_TRY_AGAIN: @@ -3019,6 +3020,7 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) switch (trypnfs) { case PNFS_NOT_ATTEMPTED: pnfs_read_through_mds(desc, hdr); + break; case PNFS_ATTEMPTED: break; case PNFS_TRY_AGAIN: -- cgit From 49dee70052b89498cc0fc61e0e193cefeee40989 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:54:59 -0500 Subject: NFS: Clean up nfs_readpage() and nfs_readpages() In prep for the new fscache netfs API, refactor nfs_readpage() and nfs_readpages() for future patches. No functional change. Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- fs/nfs/read.c | 45 +++++++++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 22 deletions(-) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index eb854f1f86e2..dd92156e27c5 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -314,7 +314,7 @@ int nfs_readpage(struct file *file, struct page *page) { struct nfs_open_context *ctx; struct inode *inode = page_file_mapping(page)->host; - int error; + int ret; dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", page, PAGE_SIZE, page_index(page)); @@ -328,18 +328,18 @@ int nfs_readpage(struct file *file, struct page *page) * be any new pending writes generated at this point * for this page (other pages can be written to). */ - error = nfs_wb_page(inode, page); - if (error) + ret = nfs_wb_page(inode, page); + if (ret) goto out_unlock; if (PageUptodate(page)) goto out_unlock; - error = -ESTALE; + ret = -ESTALE; if (NFS_STALE(inode)) goto out_unlock; if (file == NULL) { - error = -EBADF; + ret = -EBADF; ctx = nfs_find_open_context(inode, NULL, FMODE_READ); if (ctx == NULL) goto out_unlock; @@ -347,24 +347,24 @@ int nfs_readpage(struct file *file, struct page *page) ctx = get_nfs_open_context(nfs_file_open_context(file)); if (!IS_SYNC(inode)) { - error = nfs_readpage_from_fscache(ctx, inode, page); - if (error == 0) + ret = nfs_readpage_from_fscache(ctx, inode, page); + if (ret == 0) goto out; } xchg(&ctx->error, 0); - error = nfs_readpage_async(ctx, inode, page); - if (!error) { - error = wait_on_page_locked_killable(page); - if (!PageUptodate(page) && !error) - error = xchg(&ctx->error, 0); + ret = nfs_readpage_async(ctx, inode, page); + if (!ret) { + ret = wait_on_page_locked_killable(page); + if (!PageUptodate(page) && !ret) + ret = xchg(&ctx->error, 0); } out: put_nfs_open_context(ctx); - return error; + return ret; out_unlock: unlock_page(page); - return error; + return ret; } struct nfs_readdesc { @@ -404,17 +404,15 @@ out: return error; } -int nfs_readpages(struct file *filp, struct address_space *mapping, +int nfs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { struct nfs_pageio_descriptor pgio; struct nfs_pgio_mirror *pgm; - struct nfs_readdesc desc = { - .pgio = &pgio, - }; + struct nfs_readdesc desc; struct inode *inode = mapping->host; unsigned long npages; - int ret = -ESTALE; + int ret; dprintk("NFS: nfs_readpages (%s/%Lu %d)\n", inode->i_sb->s_id, @@ -422,15 +420,17 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, nr_pages); nfs_inc_stats(inode, NFSIOS_VFSREADPAGES); + ret = -ESTALE; if (NFS_STALE(inode)) goto out; - if (filp == NULL) { + if (file == NULL) { + ret = -EBADF; desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ); if (desc.ctx == NULL) - return -EBADF; + goto out; } else - desc.ctx = get_nfs_open_context(nfs_file_open_context(filp)); + desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); /* attempt to read as many of the pages as possible from the cache * - this returns -ENOBUFS immediately if the cookie is negative @@ -440,6 +440,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ + desc.pgio = &pgio; nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); -- cgit From 6ddfd213f4ea22ac955bcd82100c57cd294494d2 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:55:00 -0500 Subject: NFS: In nfs_readpage() only increment NFSIOS_READPAGES when read succeeds There is a small inconsistency with nfs_readpage() vs nfs_readpages() with regards to NFSIOS_READPAGES. In readpage we unconditionally increment NFSIOS_READPAGES at the top, which means even if the read fails. In readpages, we increment NFSIOS_READPAGES at the bottom based on how many pages were successfully read. Change readpage to be consistent with readpages and so NFSIOS_READPAGES only reflects successful, non-fscache reads. Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- fs/nfs/read.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index dd92156e27c5..464077daf62f 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -319,7 +319,6 @@ int nfs_readpage(struct file *file, struct page *page) dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", page, PAGE_SIZE, page_index(page)); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); - nfs_add_stats(inode, NFSIOS_READPAGES, 1); /* * Try to flush any pending writes to the file.. @@ -359,6 +358,7 @@ int nfs_readpage(struct file *file, struct page *page) if (!PageUptodate(page) && !ret) ret = xchg(&ctx->error, 0); } + nfs_add_stats(inode, NFSIOS_READPAGES, 1); out: put_nfs_open_context(ctx); return ret; -- cgit From 1af7e7f8c12f521c111bd7cf0d138be7e15b51a5 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:55:01 -0500 Subject: NFS: Refactor nfs_readpage() and nfs_readpage_async() to use nfs_readdesc Both nfs_readpage() and nfs_readpages() use similar code. This patch should be no functional change, and refactors nfs_readpage_async() to use nfs_readdesc to enable future merging of nfs_readpage_async() and nfs_readpage_async_filler(). Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- fs/nfs/read.c | 62 ++++++++++++++++++++++++-------------------------- include/linux/nfs_fs.h | 3 +-- 2 files changed, 31 insertions(+), 34 deletions(-) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 464077daf62f..8c05e56dab65 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -114,18 +114,23 @@ static void nfs_readpage_release(struct nfs_page *req, int error) nfs_release_request(req); } -int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, +struct nfs_readdesc { + struct nfs_pageio_descriptor pgio; + struct nfs_open_context *ctx; +}; + +int nfs_readpage_async(void *data, struct inode *inode, struct page *page) { + struct nfs_readdesc *desc = data; struct nfs_page *new; unsigned int len; - struct nfs_pageio_descriptor pgio; struct nfs_pgio_mirror *pgm; len = nfs_page_length(page); if (len == 0) return nfs_return_empty_page(page); - new = nfs_create_request(ctx, page, 0, len); + new = nfs_create_request(desc->ctx, page, 0, len); if (IS_ERR(new)) { unlock_page(page); return PTR_ERR(new); @@ -133,21 +138,21 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, if (len < PAGE_SIZE) zero_user_segment(page, len, PAGE_SIZE); - nfs_pageio_init_read(&pgio, inode, false, + nfs_pageio_init_read(&desc->pgio, inode, false, &nfs_async_read_completion_ops); - if (!nfs_pageio_add_request(&pgio, new)) { + if (!nfs_pageio_add_request(&desc->pgio, new)) { nfs_list_remove_request(new); - nfs_readpage_release(new, pgio.pg_error); + nfs_readpage_release(new, desc->pgio.pg_error); } - nfs_pageio_complete(&pgio); + nfs_pageio_complete(&desc->pgio); /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(pgio.pg_mirror_count != 1); + WARN_ON_ONCE(desc->pgio.pg_mirror_count != 1); - pgm = &pgio.pg_mirrors[0]; + pgm = &desc->pgio.pg_mirrors[0]; NFS_I(inode)->read_io += pgm->pg_bytes_written; - return pgio.pg_error < 0 ? pgio.pg_error : 0; + return desc->pgio.pg_error < 0 ? desc->pgio.pg_error : 0; } static void nfs_page_group_set_uptodate(struct nfs_page *req) @@ -312,7 +317,7 @@ static void nfs_readpage_result(struct rpc_task *task, */ int nfs_readpage(struct file *file, struct page *page) { - struct nfs_open_context *ctx; + struct nfs_readdesc desc; struct inode *inode = page_file_mapping(page)->host; int ret; @@ -339,39 +344,34 @@ int nfs_readpage(struct file *file, struct page *page) if (file == NULL) { ret = -EBADF; - ctx = nfs_find_open_context(inode, NULL, FMODE_READ); - if (ctx == NULL) + desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ); + if (desc.ctx == NULL) goto out_unlock; } else - ctx = get_nfs_open_context(nfs_file_open_context(file)); + desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); if (!IS_SYNC(inode)) { - ret = nfs_readpage_from_fscache(ctx, inode, page); + ret = nfs_readpage_from_fscache(desc.ctx, inode, page); if (ret == 0) goto out; } - xchg(&ctx->error, 0); - ret = nfs_readpage_async(ctx, inode, page); + xchg(&desc.ctx->error, 0); + ret = nfs_readpage_async(&desc, inode, page); if (!ret) { ret = wait_on_page_locked_killable(page); if (!PageUptodate(page) && !ret) - ret = xchg(&ctx->error, 0); + ret = xchg(&desc.ctx->error, 0); } nfs_add_stats(inode, NFSIOS_READPAGES, 1); out: - put_nfs_open_context(ctx); + put_nfs_open_context(desc.ctx); return ret; out_unlock: unlock_page(page); return ret; } -struct nfs_readdesc { - struct nfs_pageio_descriptor *pgio; - struct nfs_open_context *ctx; -}; - static int readpage_async_filler(void *data, struct page *page) { @@ -390,9 +390,9 @@ readpage_async_filler(void *data, struct page *page) if (len < PAGE_SIZE) zero_user_segment(page, len, PAGE_SIZE); - if (!nfs_pageio_add_request(desc->pgio, new)) { + if (!nfs_pageio_add_request(&desc->pgio, new)) { nfs_list_remove_request(new); - error = desc->pgio->pg_error; + error = desc->pgio.pg_error; nfs_readpage_release(new, error); goto out; } @@ -407,7 +407,6 @@ out: int nfs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { - struct nfs_pageio_descriptor pgio; struct nfs_pgio_mirror *pgm; struct nfs_readdesc desc; struct inode *inode = mapping->host; @@ -440,17 +439,16 @@ int nfs_readpages(struct file *file, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ - desc.pgio = &pgio; - nfs_pageio_init_read(&pgio, inode, false, + nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); - nfs_pageio_complete(&pgio); + nfs_pageio_complete(&desc.pgio); /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(pgio.pg_mirror_count != 1); + WARN_ON_ONCE(desc.pgio.pg_mirror_count != 1); - pgm = &pgio.pg_mirrors[0]; + pgm = &desc.pgio.pg_mirrors[0]; NFS_I(inode)->read_io += pgm->pg_bytes_written; npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> PAGE_SHIFT; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 681ed98e4ba8..cb0248a34518 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -570,8 +570,7 @@ nfs_have_writebacks(struct inode *inode) extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); -extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, - struct page *); +extern int nfs_readpage_async(void *, struct inode *, struct page *); /* * inline functions -- cgit From 0c119e3a18f994251c74c751e1657e4ef8da0c00 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:55:02 -0500 Subject: NFS: Call readpage_async_filler() from nfs_readpage_async() Refactor slightly so nfs_readpage_async() calls into readpage_async_filler(). Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- fs/nfs/read.c | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 8c05e56dab65..0ed79e6bc486 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -119,31 +119,22 @@ struct nfs_readdesc { struct nfs_open_context *ctx; }; +static int readpage_async_filler(void *data, struct page *page); + int nfs_readpage_async(void *data, struct inode *inode, struct page *page) { struct nfs_readdesc *desc = data; - struct nfs_page *new; - unsigned int len; struct nfs_pgio_mirror *pgm; - - len = nfs_page_length(page); - if (len == 0) - return nfs_return_empty_page(page); - new = nfs_create_request(desc->ctx, page, 0, len); - if (IS_ERR(new)) { - unlock_page(page); - return PTR_ERR(new); - } - if (len < PAGE_SIZE) - zero_user_segment(page, len, PAGE_SIZE); + int error; nfs_pageio_init_read(&desc->pgio, inode, false, &nfs_async_read_completion_ops); - if (!nfs_pageio_add_request(&desc->pgio, new)) { - nfs_list_remove_request(new); - nfs_readpage_release(new, desc->pgio.pg_error); - } + + error = readpage_async_filler(desc, page); + if (error) + goto out; + nfs_pageio_complete(&desc->pgio); /* It doesn't make sense to do mirrored reads! */ @@ -153,6 +144,9 @@ int nfs_readpage_async(void *data, struct inode *inode, NFS_I(inode)->read_io += pgm->pg_bytes_written; return desc->pgio.pg_error < 0 ? desc->pgio.pg_error : 0; + +out: + return error; } static void nfs_page_group_set_uptodate(struct nfs_page *req) -- cgit From 1e83b173b2663b7d357309584678cf24787f0713 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:55:03 -0500 Subject: NFS: Add nfs_pageio_complete_read() and remove nfs_readpage_async() Add nfs_pageio_complete_read() and call this from both nfs_readpage() and nfs_readpages(), since the submission and accounting is the same for both functions. Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- fs/nfs/fscache.c | 4 -- fs/nfs/read.c | 137 ++++++++++++++++++++++--------------------------- include/linux/nfs_fs.h | 1 - 3 files changed, 61 insertions(+), 81 deletions(-) diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index a60df88efc40..c4c021c6ebbd 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -390,10 +390,6 @@ static void nfs_readpage_from_fscache_complete(struct page *page, if (!error) { SetPageUptodate(page); unlock_page(page); - } else { - error = nfs_readpage_async(context, page->mapping->host, page); - if (error) - unlock_page(page); } } diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 0ed79e6bc486..d2b6dce1f99f 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -74,6 +74,24 @@ void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, } EXPORT_SYMBOL_GPL(nfs_pageio_init_read); +static void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode) +{ + struct nfs_pgio_mirror *pgm; + unsigned long npages; + + nfs_pageio_complete(pgio); + + /* It doesn't make sense to do mirrored reads! */ + WARN_ON_ONCE(pgio->pg_mirror_count != 1); + + pgm = &pgio->pg_mirrors[0]; + NFS_I(inode)->read_io += pgm->pg_bytes_written; + npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> PAGE_SHIFT; + nfs_add_stats(inode, NFSIOS_READPAGES, npages); +} + + void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { struct nfs_pgio_mirror *mirror; @@ -119,36 +137,6 @@ struct nfs_readdesc { struct nfs_open_context *ctx; }; -static int readpage_async_filler(void *data, struct page *page); - -int nfs_readpage_async(void *data, struct inode *inode, - struct page *page) -{ - struct nfs_readdesc *desc = data; - struct nfs_pgio_mirror *pgm; - int error; - - nfs_pageio_init_read(&desc->pgio, inode, false, - &nfs_async_read_completion_ops); - - error = readpage_async_filler(desc, page); - if (error) - goto out; - - nfs_pageio_complete(&desc->pgio); - - /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(desc->pgio.pg_mirror_count != 1); - - pgm = &desc->pgio.pg_mirrors[0]; - NFS_I(inode)->read_io += pgm->pg_bytes_written; - - return desc->pgio.pg_error < 0 ? desc->pgio.pg_error : 0; - -out: - return error; -} - static void nfs_page_group_set_uptodate(struct nfs_page *req) { if (nfs_page_group_sync_on_bit(req, PG_UPTODATE)) @@ -170,8 +158,7 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr) if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { /* note: regions of the page not covered by a - * request are zeroed in nfs_readpage_async / - * readpage_async_filler */ + * request are zeroed in readpage_async_filler */ if (bytes > hdr->good_bytes) { /* nothing in this request was good, so zero * the full extent of the request */ @@ -303,6 +290,38 @@ static void nfs_readpage_result(struct rpc_task *task, nfs_readpage_retry(task, hdr); } +static int +readpage_async_filler(void *data, struct page *page) +{ + struct nfs_readdesc *desc = data; + struct nfs_page *new; + unsigned int len; + int error; + + len = nfs_page_length(page); + if (len == 0) + return nfs_return_empty_page(page); + + new = nfs_create_request(desc->ctx, page, 0, len); + if (IS_ERR(new)) + goto out_error; + + if (len < PAGE_SIZE) + zero_user_segment(page, len, PAGE_SIZE); + if (!nfs_pageio_add_request(&desc->pgio, new)) { + nfs_list_remove_request(new); + error = desc->pgio.pg_error; + nfs_readpage_release(new, error); + goto out; + } + return 0; +out_error: + error = PTR_ERR(new); + unlock_page(page); +out: + return error; +} + /* * Read a page over NFS. * We read the page synchronously in the following case: @@ -351,13 +370,20 @@ int nfs_readpage(struct file *file, struct page *page) } xchg(&desc.ctx->error, 0); - ret = nfs_readpage_async(&desc, inode, page); + nfs_pageio_init_read(&desc.pgio, inode, false, + &nfs_async_read_completion_ops); + + ret = readpage_async_filler(&desc, page); + + if (!ret) + nfs_pageio_complete_read(&desc.pgio, inode); + + ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; if (!ret) { ret = wait_on_page_locked_killable(page); if (!PageUptodate(page) && !ret) ret = xchg(&desc.ctx->error, 0); } - nfs_add_stats(inode, NFSIOS_READPAGES, 1); out: put_nfs_open_context(desc.ctx); return ret; @@ -366,45 +392,11 @@ out_unlock: return ret; } -static int -readpage_async_filler(void *data, struct page *page) -{ - struct nfs_readdesc *desc = (struct nfs_readdesc *)data; - struct nfs_page *new; - unsigned int len; - int error; - - len = nfs_page_length(page); - if (len == 0) - return nfs_return_empty_page(page); - - new = nfs_create_request(desc->ctx, page, 0, len); - if (IS_ERR(new)) - goto out_error; - - if (len < PAGE_SIZE) - zero_user_segment(page, len, PAGE_SIZE); - if (!nfs_pageio_add_request(&desc->pgio, new)) { - nfs_list_remove_request(new); - error = desc->pgio.pg_error; - nfs_readpage_release(new, error); - goto out; - } - return 0; -out_error: - error = PTR_ERR(new); - unlock_page(page); -out: - return error; -} - int nfs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { - struct nfs_pgio_mirror *pgm; struct nfs_readdesc desc; struct inode *inode = mapping->host; - unsigned long npages; int ret; dprintk("NFS: nfs_readpages (%s/%Lu %d)\n", @@ -437,16 +429,9 @@ int nfs_readpages(struct file *file, struct address_space *mapping, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); - nfs_pageio_complete(&desc.pgio); - /* It doesn't make sense to do mirrored reads! */ - WARN_ON_ONCE(desc.pgio.pg_mirror_count != 1); + nfs_pageio_complete_read(&desc.pgio, inode); - pgm = &desc.pgio.pg_mirrors[0]; - NFS_I(inode)->read_io += pgm->pg_bytes_written; - npages = (pgm->pg_bytes_written + PAGE_SIZE - 1) >> - PAGE_SHIFT; - nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: put_nfs_open_context(desc.ctx); out: diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index cb0248a34518..3cfcf219e96b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -570,7 +570,6 @@ nfs_have_writebacks(struct inode *inode) extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); -extern int nfs_readpage_async(void *, struct inode *, struct page *); /* * inline functions -- cgit From 9929f4adce3679b08262b9193fbe0e04d65abb11 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 Feb 2021 11:59:01 -0500 Subject: xprtrdma: Remove FMR support in rpcrdma_convert_iovs() Support for FMR was removed by commit ba69cd122ece ("xprtrdma: Remove support for FMR memory registration") [Dec 2018]. That means the buffer-splitting behavior of rpcrdma_convert_kvec(), added by commit 821c791a0bde ("xprtrdma: Segment head and tail XDR buffers on page boundaries") [Mar 2016], is no longer necessary. FRWR memory registration handles this case with aplomb. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 27 +++++++-------------------- 1 file changed, 7 insertions(+), 20 deletions(-) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 8f5d0cb68360..57f9217048d8 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -204,9 +204,7 @@ rpcrdma_alloc_sparse_pages(struct xdr_buf *buf) return 0; } -/* Split @vec on page boundaries into SGEs. FMR registers pages, not - * a byte range. Other modes coalesce these SGEs into a single MR - * when they can. +/* Convert @vec to a single SGL element. * * Returns pointer to next available SGE, and bumps the total number * of SGEs consumed. @@ -215,22 +213,11 @@ static struct rpcrdma_mr_seg * rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, unsigned int *n) { - u32 remaining, page_offset; - char *base; - - base = vec->iov_base; - page_offset = offset_in_page(base); - remaining = vec->iov_len; - while (remaining) { - seg->mr_page = NULL; - seg->mr_offset = base; - seg->mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining); - remaining -= seg->mr_len; - base += seg->mr_len; - ++seg; - ++(*n); - page_offset = 0; - } + seg->mr_page = NULL; + seg->mr_offset = vec->iov_base; + seg->mr_len = vec->iov_len; + ++seg; + ++(*n); return seg; } @@ -283,7 +270,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, goto out; if (xdrbuf->tail[0].iov_len) - seg = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n); + rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, &n); out: if (unlikely(n > RPCRDMA_MAX_SEGS)) -- cgit From 54e6aec57c251e36a4c3153ccfee9538f2ec1bcf Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 Feb 2021 11:59:07 -0500 Subject: xprtrdma: Simplify rpcrdma_convert_kvec() and frwr_map() Clean up. Remove a conditional branch from the SGL set-up loop in frwr_map(): Instead of using either sg_set_page() or sg_set_buf(), initialize the mr_page field properly when rpcrdma_convert_kvec() converts the kvec to an SGL entry. frwr_map() can then invoke sg_set_page() unconditionally. Signed-off-by: Chuck Lever Reviewed-by: Tom Talpey Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/frwr_ops.c | 12 ++++-------- net/sunrpc/xprtrdma/rpc_rdma.c | 2 +- net/sunrpc/xprtrdma/xprt_rdma.h | 9 +++++---- 3 files changed, 10 insertions(+), 13 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index baca49fe83af..13a50f77dddb 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -306,14 +306,10 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, if (nsegs > ep->re_max_fr_depth) nsegs = ep->re_max_fr_depth; for (i = 0; i < nsegs;) { - if (seg->mr_page) - sg_set_page(&mr->mr_sg[i], - seg->mr_page, - seg->mr_len, - offset_in_page(seg->mr_offset)); - else - sg_set_buf(&mr->mr_sg[i], seg->mr_offset, - seg->mr_len); + sg_set_page(&mr->mr_sg[i], + seg->mr_page, + seg->mr_len, + offset_in_page(seg->mr_offset)); ++seg; ++i; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 57f9217048d8..b36b9aae0588 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -213,7 +213,7 @@ static struct rpcrdma_mr_seg * rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, unsigned int *n) { - seg->mr_page = NULL; + seg->mr_page = virt_to_page(vec->iov_base); seg->mr_offset = vec->iov_base; seg->mr_len = vec->iov_len; ++seg; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 94b28657aeeb..02971e183989 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -283,10 +283,11 @@ enum { RPCRDMA_MAX_IOV_SEGS, }; -struct rpcrdma_mr_seg { /* chunk descriptors */ - u32 mr_len; /* length of chunk or segment */ - struct page *mr_page; /* owning page, if any */ - char *mr_offset; /* kva if no page, else offset */ +/* Arguments for DMA mapping and registration */ +struct rpcrdma_mr_seg { + u32 mr_len; /* length of segment */ + struct page *mr_page; /* underlying struct page */ + char *mr_offset; /* IN: page offset, OUT: iova */ }; /* The Send SGE array is provisioned to send a maximum size -- cgit From 67b16625d17b7c2e5babbbe817e12ad37c3fe3f4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 Feb 2021 11:59:13 -0500 Subject: xprtrdma: Refactor invocations of offset_in_page() Clean up so that offset_in_page() is invoked less often in the most common case, which is mapping xdr->pages. Signed-off-by: Chuck Lever Reviewed-by: Tom Talpey Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/frwr_ops.c | 8 +++----- net/sunrpc/xprtrdma/rpc_rdma.c | 4 ++-- net/sunrpc/xprtrdma/xprt_rdma.h | 2 +- 3 files changed, 6 insertions(+), 8 deletions(-) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 13a50f77dddb..766a1048a48a 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -306,16 +306,14 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, if (nsegs > ep->re_max_fr_depth) nsegs = ep->re_max_fr_depth; for (i = 0; i < nsegs;) { - sg_set_page(&mr->mr_sg[i], - seg->mr_page, - seg->mr_len, - offset_in_page(seg->mr_offset)); + sg_set_page(&mr->mr_sg[i], seg->mr_page, + seg->mr_len, seg->mr_offset); ++seg; ++i; if (ep->re_mrtype == IB_MR_TYPE_SG_GAPS) continue; - if ((i < nsegs && offset_in_page(seg->mr_offset)) || + if ((i < nsegs && seg->mr_offset) || offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index b36b9aae0588..b2482d9328d1 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -214,7 +214,7 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, unsigned int *n) { seg->mr_page = virt_to_page(vec->iov_base); - seg->mr_offset = vec->iov_base; + seg->mr_offset = offset_in_page(vec->iov_base); seg->mr_len = vec->iov_len; ++seg; ++(*n); @@ -246,7 +246,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, page_base = offset_in_page(xdrbuf->page_base); while (len) { seg->mr_page = *ppages; - seg->mr_offset = (char *)page_base; + seg->mr_offset = page_base; seg->mr_len = min_t(u32, PAGE_SIZE - page_base, len); len -= seg->mr_len; ++ppages; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 02971e183989..ed1c5444fb9d 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -287,7 +287,7 @@ enum { struct rpcrdma_mr_seg { u32 mr_len; /* length of segment */ struct page *mr_page; /* underlying struct page */ - char *mr_offset; /* IN: page offset, OUT: iova */ + u64 mr_offset; /* IN: page offset, OUT: iova */ }; /* The Send SGE array is provisioned to send a maximum size -- cgit From 84dff5eb86ceb2a356d5409fc1af21a366bf3c35 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 Feb 2021 11:59:19 -0500 Subject: rpcrdma: Fix comments about reverse-direction operation During the final stages of publication of RFC 8167, reviewers requested that we use the term "reverse direction" rather than "backwards direction". Update comments to reflect this preference. Signed-off-by: Chuck Lever Reviewed-by: Tom Talpey Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/backchannel.c | 4 ++-- net/sunrpc/xprtrdma/rpc_rdma.c | 6 +----- net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 4 ++-- net/sunrpc/xprtrdma/xprt_rdma.h | 6 +++--- 4 files changed, 8 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 946edf2db646..a249837d6a55 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2015-2020, Oracle and/or its affiliates. * - * Support for backward direction RPCs on RPC/RDMA. + * Support for reverse-direction RPCs on RPC/RDMA. */ #include @@ -208,7 +208,7 @@ create_req: } /** - * rpcrdma_bc_receive_call - Handle a backward direction call + * rpcrdma_bc_receive_call - Handle a reverse-direction Call * @r_xprt: transport receiving the call * @rep: receive buffer containing the call * diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index b2482d9328d1..283e9bfcab44 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1151,14 +1151,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep) */ p = xdr_inline_decode(xdr, 3 * sizeof(*p)); if (unlikely(!p)) - goto out_short; + return true; rpcrdma_bc_receive_call(r_xprt, rep); return true; - -out_short: - pr_warn("RPC/RDMA short backward direction call\n"); - return true; } #else /* CONFIG_SUNRPC_BACKCHANNEL */ { diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 63f8be974df2..4a1edbb4028e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -2,7 +2,7 @@ /* * Copyright (c) 2015-2018 Oracle. All rights reserved. * - * Support for backward direction RPCs on RPC/RDMA (server-side). + * Support for reverse-direction RPCs on RPC/RDMA (server-side). */ #include @@ -59,7 +59,7 @@ out_unlock: spin_unlock(&xprt->queue_lock); } -/* Send a backwards direction RPC call. +/* Send a reverse-direction RPC Call. * * Caller holds the connection's mutex and has already marshaled * the RPC/RDMA request. diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index ed1c5444fb9d..fe3be985e239 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -98,9 +98,9 @@ struct rpcrdma_ep { atomic_t re_completion_ids; }; -/* Pre-allocate extra Work Requests for handling backward receives - * and sends. This is a fixed value because the Work Queues are - * allocated when the forward channel is set up, long before the +/* Pre-allocate extra Work Requests for handling reverse-direction + * Receives and Sends. This is a fixed value because the Work Queues + * are allocated when the forward channel is set up, long before the * backchannel is provisioned. This value is two times * NFS4_DEF_CB_SLOT_TABLE_SIZE. */ -- cgit From 2324fbedc207568b11354b146c3fc4ff2b89d588 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 Feb 2021 11:59:25 -0500 Subject: xprtrdma: Pad optimization, revisited The NetApp Linux team discovered that with NFS/RDMA servers that do not support RFC 8797, the Linux client is forming NFSv4.x WRITE requests incorrectly. In this case, the Linux NFS client disables implicit chunk round-up for odd-length Read and Write chunks. The goal was to support old servers that needed that padding to be sent explicitly by clients. In that case the Linux NFS included the tail kvec in the Read chunk, since the tail contains any needed padding. That meant a separate memory registration is needed for the tail kvec, adding to the cost of forming such requests. To avoid that cost for a mere 3 bytes of zeroes that are always ignored by receivers, we try to use implicit roundup when possible. For NFSv4.x, the tail kvec also sometimes contains a trailing GETATTR operation. The Linux NFS client unintentionally includes that GETATTR operation in the Read chunk as well as inline. The fix is simply to /never/ include the tail kvec when forming a data payload Read chunk. The padding is thus now always present. Note that since commit 9ed5af268e88 ("SUNRPC: Clean up the handling of page padding in rpc_prepare_reply_pages()") [Dec 2020] the NFS client passes payload data to the transport with the padding in xdr->pages instead of in the send buffer's tail kvec. So now the Linux NFS client appends XDR padding to all odd-sized Read chunks. This shouldn't be a problem because: - RFC 8166-compliant servers are supposed to work with or without that XDR padding in Read chunks. - Since the padding is now in the same memory region as the data payload, a separate memory registration is not needed. In addition, the link layer extends data in RDMA Read responses to 4-byte boundaries anyway. Thus there is now no savings when the padding is not included. Because older kernels include the payload's XDR padding in the tail kvec, a fix there will be more complicated. Thus backporting this patch is not recommended. Reported by: Olga Kornievskaia Signed-off-by: Chuck Lever Reviewed-by: Tom Talpey Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 283e9bfcab44..1c3e377272e0 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -255,10 +255,7 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, page_base = 0; } - /* When encoding a Read chunk, the tail iovec contains an - * XDR pad and may be omitted. - */ - if (type == rpcrdma_readch && r_xprt->rx_ep->re_implicit_roundup) + if (type == rpcrdma_readch) goto out; /* When encoding a Write chunk, some servers need to see an -- cgit From c30f259a213802d5f4440fbb02e73b3b03403049 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 Feb 2021 11:59:32 -0500 Subject: rpcrdma: Capture bytes received in Receive completion tracepoints Make it easier to spot messages of an unusual size. Signed-off-by: Chuck Lever Acked-by: Tom Talpey Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 50 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-) diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 76e85e16854b..c838e7ac1c2d 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -60,6 +60,51 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class, ), \ TP_ARGS(wc, cid)) +DECLARE_EVENT_CLASS(rpcrdma_receive_completion_class, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid + ), + + TP_ARGS(wc, cid), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + __field(u32, received) + __field(unsigned long, status) + __field(unsigned int, vendor_err) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + __entry->status = wc->status; + if (wc->status) { + __entry->received = 0; + __entry->vendor_err = wc->vendor_err; + } else { + __entry->received = wc->byte_len; + __entry->vendor_err = 0; + } + ), + + TP_printk("cq.id=%u cid=%d status=%s (%lu/0x%x) received=%u", + __entry->cq_id, __entry->completion_id, + rdma_show_wc_status(__entry->status), + __entry->status, __entry->vendor_err, + __entry->received + ) +); + +#define DEFINE_RECEIVE_COMPLETION_EVENT(name) \ + DEFINE_EVENT(rpcrdma_receive_completion_class, name, \ + TP_PROTO( \ + const struct ib_wc *wc, \ + const struct rpc_rdma_cid *cid \ + ), \ + TP_ARGS(wc, cid)) + DECLARE_EVENT_CLASS(xprtrdma_reply_class, TP_PROTO( const struct rpcrdma_rep *rep @@ -838,7 +883,8 @@ TRACE_EVENT(xprtrdma_post_linv_err, ** Completion events **/ -DEFINE_COMPLETION_EVENT(xprtrdma_wc_receive); +DEFINE_RECEIVE_COMPLETION_EVENT(xprtrdma_wc_receive); + DEFINE_COMPLETION_EVENT(xprtrdma_wc_send); DEFINE_COMPLETION_EVENT(xprtrdma_wc_fastreg); DEFINE_COMPLETION_EVENT(xprtrdma_wc_li); @@ -1790,7 +1836,7 @@ TRACE_EVENT(svcrdma_post_recv, ) ); -DEFINE_COMPLETION_EVENT(svcrdma_wc_receive); +DEFINE_RECEIVE_COMPLETION_EVENT(svcrdma_wc_receive); TRACE_EVENT(svcrdma_rq_post_err, TP_PROTO( -- cgit From 586a0787ce35f2e32d399b7e344e634e07de2997 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 5 Feb 2021 11:31:34 -0500 Subject: xprtrdma: Clean up rpcrdma_prepare_readch() Since commit 9ed5af268e88 ("SUNRPC: Clean up the handling of page padding in rpc_prepare_reply_pages()") [Dec 2020] the NFS client passes payload data to the transport with the padding in xdr->pages instead of in the send buffer's tail kvec. There's no need for the extra logic to advance the base of the tail kvec because the upper layer no longer places XDR padding there. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 27 +++++++++------------------ 1 file changed, 9 insertions(+), 18 deletions(-) diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 1c3e377272e0..292f066d006e 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -628,9 +628,8 @@ out_mapping_err: return false; } -/* The tail iovec may include an XDR pad for the page list, - * as well as additional content, and may not reside in the - * same page as the head iovec. +/* The tail iovec might not reside in the same page as the + * head iovec. */ static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req, struct xdr_buf *xdr, @@ -748,27 +747,19 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct xdr_buf *xdr) { + struct kvec *tail = &xdr->tail[0]; + if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len)) return false; - /* If there is a Read chunk, the page list is being handled + /* If there is a Read chunk, the page list is handled * via explicit RDMA, and thus is skipped here. */ - /* Do not include the tail if it is only an XDR pad */ - if (xdr->tail[0].iov_len > 3) { - unsigned int page_base, len; - - /* If the content in the page list is an odd length, - * xdr_write_pages() adds a pad at the beginning of - * the tail iovec. Force the tail's non-pad content to - * land at the next XDR position in the Send message. - */ - page_base = offset_in_page(xdr->tail[0].iov_base); - len = xdr->tail[0].iov_len; - page_base += len & 3; - len -= len & 3; - if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len)) + if (tail->iov_len) { + if (!rpcrdma_prepare_tail_iov(req, xdr, + offset_in_page(tail->iov_base), + tail->iov_len)) return false; kref_get(&req->rl_kref); } -- cgit From 45901a231723a5a513ff08477983f3a274a6a910 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 8 Feb 2021 08:49:32 -0500 Subject: NFSv4: Fixes for nfs4_bitmask_adjust() We don't want to ask for the ACL in a WRITE reply, since we don't have a preallocated buffer. Instead of checking NFS_INO_INVALID_ACCESS, which is really about managing the access cache, we should look at the value of NFS_INO_INVALID_OTHER. Also ensure we assign the mode, owner and owner_group flags to the correct bit mask. Finally, fix up the check for NFS_INO_INVALID_CTIME to retrieve the ctime, and add a check for NFS_INO_INVALID_CHANGE. Fixes: 76bd5c016ef4 ("NFSv4: make cache consistency bitmask dynamic") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 34570a7785fa..8eb9c716010f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5435,15 +5435,16 @@ static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode, if (cache_validity & NFS_INO_INVALID_ATIME) bitmask[1] |= FATTR4_WORD1_TIME_ACCESS; - if (cache_validity & NFS_INO_INVALID_ACCESS) - bitmask[0] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | - FATTR4_WORD1_OWNER_GROUP; - if (cache_validity & NFS_INO_INVALID_ACL) - bitmask[0] |= FATTR4_WORD0_ACL; - if (cache_validity & NFS_INO_INVALID_LABEL) + if (cache_validity & NFS_INO_INVALID_OTHER) + bitmask[1] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | + FATTR4_WORD1_OWNER_GROUP | + FATTR4_WORD1_NUMLINKS; + if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL) bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL; - if (cache_validity & NFS_INO_INVALID_CTIME) + if (cache_validity & NFS_INO_INVALID_CHANGE) bitmask[0] |= FATTR4_WORD0_CHANGE; + if (cache_validity & NFS_INO_INVALID_CTIME) + bitmask[1] |= FATTR4_WORD1_TIME_METADATA; if (cache_validity & NFS_INO_INVALID_MTIME) bitmask[1] |= FATTR4_WORD1_TIME_MODIFY; if (cache_validity & NFS_INO_INVALID_SIZE) -- cgit From 37eaeed1a57e92d9db200ba7b4851a09c55eef5a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 8 Feb 2021 08:55:45 -0500 Subject: NFS: Fix documenting comment for nfs_revalidate_file_size() Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 63940a7a70be..d02a63af9c15 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -89,7 +89,7 @@ nfs_file_release(struct inode *inode, struct file *filp) EXPORT_SYMBOL_GPL(nfs_file_release); /** - * nfs_revalidate_size - Revalidate the file size + * nfs_revalidate_file_size - Revalidate the file size * @inode: pointer to inode struct * @filp: pointer to struct file * -- cgit From fc9dc401899ab280fe1849a0ca5800384726a793 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 8 Feb 2021 08:55:46 -0500 Subject: NFS: Optimise sparse writes past the end of file If we're doing a write, and the entire page lies beyond the end-of-file, then we can assume the write can be extended to cover the beginning of the page, since we know the data in that region will be all zeros. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/file.c | 4 +--- fs/nfs/write.c | 20 ++++++++++++-------- 2 files changed, 13 insertions(+), 11 deletions(-) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d02a63af9c15..02795a01c7ef 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -626,13 +626,11 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) /* * O_APPEND implies that we must revalidate the file length. */ - if (iocb->ki_flags & IOCB_APPEND) { + if (iocb->ki_flags & IOCB_APPEND || iocb->ki_pos > i_size_read(inode)) { result = nfs_revalidate_file_size(inode, file); if (result) goto out; } - if (iocb->ki_pos > i_size_read(inode)) - nfs_revalidate_mapping(inode, file->f_mapping); since = filemap_sample_wb_err(file->f_mapping); nfs_start_io_write(inode); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 639c34fec04a..6193350356a8 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1278,19 +1278,21 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode) * the PageUptodate() flag. In this case, we will need to turn off * write optimisations that depend on the page contents being correct. */ -static bool nfs_write_pageuptodate(struct page *page, struct inode *inode) +static bool nfs_write_pageuptodate(struct page *page, struct inode *inode, + unsigned int pagelen) { struct nfs_inode *nfsi = NFS_I(inode); if (nfs_have_delegated_attributes(inode)) goto out; - if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) + if (nfsi->cache_validity & + (NFS_INO_REVAL_PAGECACHE | NFS_INO_INVALID_SIZE)) return false; smp_rmb(); - if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags)) + if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags) && pagelen != 0) return false; out: - if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + if (nfsi->cache_validity & NFS_INO_INVALID_DATA && pagelen != 0) return false; return PageUptodate(page) != 0; } @@ -1310,7 +1312,8 @@ is_whole_file_wrlock(struct file_lock *fl) * If the file is opened for synchronous writes then we can just skip the rest * of the checks. */ -static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode) +static int nfs_can_extend_write(struct file *file, struct page *page, + struct inode *inode, unsigned int pagelen) { int ret; struct file_lock_context *flctx = inode->i_flctx; @@ -1318,7 +1321,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino if (file->f_flags & O_DSYNC) return 0; - if (!nfs_write_pageuptodate(page, inode)) + if (!nfs_write_pageuptodate(page, inode, pagelen)) return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; @@ -1356,6 +1359,7 @@ int nfs_updatepage(struct file *file, struct page *page, struct nfs_open_context *ctx = nfs_file_open_context(file); struct address_space *mapping = page_file_mapping(page); struct inode *inode = mapping->host; + unsigned int pagelen = nfs_page_length(page); int status = 0; nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); @@ -1366,8 +1370,8 @@ int nfs_updatepage(struct file *file, struct page *page, if (!count) goto out; - if (nfs_can_extend_write(file, page, inode)) { - count = max(count + offset, nfs_page_length(page)); + if (nfs_can_extend_write(file, page, inode, pagelen)) { + count = max(count + offset, pagelen); offset = 0; } -- cgit From 28aa2f9e73e762dbaa28fdca20cccb59c74cc139 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 8 Feb 2021 08:55:47 -0500 Subject: NFS: Always clear an invalid mapping when attempting a buffered write If the page cache is invalid, then we can't do read-modify-write, so ensure that we do clear it when we know it is invalid. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/file.c | 2 ++ fs/nfs/inode.c | 97 ++++++++++++++++++++++++++++---------------------- include/linux/nfs_fs.h | 1 + 3 files changed, 57 insertions(+), 43 deletions(-) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 02795a01c7ef..03fd1dcc96bd 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -632,6 +632,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) goto out; } + nfs_clear_invalid_mapping(file->f_mapping); + since = filemap_sample_wb_err(file->f_mapping); nfs_start_io_write(inode); result = generic_write_checks(iocb, from); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 522aa10a1a3e..2533053d764a 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1257,55 +1257,19 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map return 0; } -bool nfs_mapping_need_revalidate_inode(struct inode *inode) -{ - return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) || - NFS_STALE(inode); -} - -int nfs_revalidate_mapping_rcu(struct inode *inode) -{ - struct nfs_inode *nfsi = NFS_I(inode); - unsigned long *bitlock = &nfsi->flags; - int ret = 0; - - if (IS_SWAPFILE(inode)) - goto out; - if (nfs_mapping_need_revalidate_inode(inode)) { - ret = -ECHILD; - goto out; - } - spin_lock(&inode->i_lock); - if (test_bit(NFS_INO_INVALIDATING, bitlock) || - (nfsi->cache_validity & NFS_INO_INVALID_DATA)) - ret = -ECHILD; - spin_unlock(&inode->i_lock); -out: - return ret; -} - /** - * nfs_revalidate_mapping - Revalidate the pagecache - * @inode: pointer to host inode + * nfs_clear_invalid_mapping - Conditionally clear a mapping * @mapping: pointer to mapping + * + * If the NFS_INO_INVALID_DATA inode flag is set, clear the mapping. */ -int nfs_revalidate_mapping(struct inode *inode, - struct address_space *mapping) +int nfs_clear_invalid_mapping(struct address_space *mapping) { + struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; - /* swapfiles are not supposed to be shared. */ - if (IS_SWAPFILE(inode)) - goto out; - - if (nfs_mapping_need_revalidate_inode(inode)) { - ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); - if (ret < 0) - goto out; - } - /* * We must clear NFS_INO_INVALID_DATA first to ensure that * invalidations that come in while we're shooting down the mappings @@ -1336,8 +1300,8 @@ int nfs_revalidate_mapping(struct inode *inode, set_bit(NFS_INO_INVALIDATING, bitlock); smp_wmb(); - nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA| - NFS_INO_DATA_INVAL_DEFER); + nfsi->cache_validity &= + ~(NFS_INO_INVALID_DATA | NFS_INO_DATA_INVAL_DEFER); spin_unlock(&inode->i_lock); trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); @@ -1350,6 +1314,53 @@ out: return ret; } +bool nfs_mapping_need_revalidate_inode(struct inode *inode) +{ + return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) || + NFS_STALE(inode); +} + +int nfs_revalidate_mapping_rcu(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long *bitlock = &nfsi->flags; + int ret = 0; + + if (IS_SWAPFILE(inode)) + goto out; + if (nfs_mapping_need_revalidate_inode(inode)) { + ret = -ECHILD; + goto out; + } + spin_lock(&inode->i_lock); + if (test_bit(NFS_INO_INVALIDATING, bitlock) || + (nfsi->cache_validity & NFS_INO_INVALID_DATA)) + ret = -ECHILD; + spin_unlock(&inode->i_lock); +out: + return ret; +} + +/** + * nfs_revalidate_mapping - Revalidate the pagecache + * @inode: pointer to host inode + * @mapping: pointer to mapping + */ +int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) +{ + /* swapfiles are not supposed to be shared. */ + if (IS_SWAPFILE(inode)) + return 0; + + if (nfs_mapping_need_revalidate_inode(inode)) { + int ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); + if (ret < 0) + return ret; + } + + return nfs_clear_invalid_mapping(mapping); +} + static bool nfs_file_has_writers(struct nfs_inode *nfsi) { struct inode *inode = &nfsi->vfs_inode; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 3cfcf219e96b..2c662857247a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -387,6 +387,7 @@ extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); +extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -- cgit From 848fdd62399c638e65a1512616acaa5de7d5c5e8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 8 Feb 2021 16:45:49 -0500 Subject: NFS: Don't set NFS_INO_INVALID_XATTR if there is no xattr cache Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/inode.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 2533053d764a..1575e3e1dda9 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -195,6 +195,18 @@ bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags) } EXPORT_SYMBOL_GPL(nfs_check_cache_invalid); +#ifdef CONFIG_NFS_V4_2 +static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) +{ + return nfsi->xattr_cache != NULL; +} +#else +static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) +{ + return false; +} +#endif + static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) { struct nfs_inode *nfsi = NFS_I(inode); @@ -209,6 +221,8 @@ static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) | NFS_INO_INVALID_XATTR); } + if (!nfs_has_xattr_cache(nfsi)) + flags &= ~NFS_INO_INVALID_XATTR; if (inode->i_mapping->nrpages == 0) flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER); nfsi->cache_validity |= flags; -- cgit From 75cfb200cd081d23eb7eaa68deba9e0ab9320070 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Feb 2021 16:49:47 -0500 Subject: NFS: 'flags' field should be unsigned in struct nfs_server The mount flags are all unsigned integers, so we should not be storing them in a signed field. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 38e60ec742df..962e8313f007 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -142,7 +142,7 @@ struct nfs_server { struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ atomic_long_t writeback; /* number of writeback pages */ - int flags; /* various flags */ + unsigned int flags; /* various flags */ /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */ #define NFS_MOUNT_LOOKUP_CACHE_NONEG 0x10000 -- cgit From ed7bcdb374d20fab9e9dc36853a6735c047ad1b1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Feb 2021 16:49:48 -0500 Subject: NFS: Add support for eager writes Support eager writing to the server, meaning that we write the data to cache on the server, and wait for that to complete. This ensures that we see ENOSPC errors immediately. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/file.c | 19 +++++++++++++++++-- fs/nfs/write.c | 17 ++++++++++++----- include/linux/nfs_fs_sb.h | 2 ++ 3 files changed, 31 insertions(+), 7 deletions(-) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 03fd1dcc96bd..16ad5050e046 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -606,8 +606,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - unsigned long written = 0; - ssize_t result; + unsigned int mntflags = NFS_SERVER(inode)->flags; + ssize_t result, written; errseq_t since; int error; @@ -648,6 +648,21 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) written = result; iocb->ki_pos += written; + + if (mntflags & NFS_MOUNT_WRITE_EAGER) { + result = filemap_fdatawrite_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); + if (result < 0) + goto out; + } + if (mntflags & NFS_MOUNT_WRITE_WAIT) { + result = filemap_fdatawait_range(file->f_mapping, + iocb->ki_pos - written, + iocb->ki_pos - 1); + if (result < 0) + goto out; + } result = generic_write_sync(iocb, written); if (result < 0) goto out; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 6193350356a8..82bdcb982186 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -712,16 +712,23 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct nfs_pageio_descriptor pgio; - struct nfs_io_completion *ioc; + struct nfs_io_completion *ioc = NULL; + unsigned int mntflags = NFS_SERVER(inode)->flags; + int priority = 0; int err; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); - ioc = nfs_io_completion_alloc(GFP_KERNEL); - if (ioc) - nfs_io_completion_init(ioc, nfs_io_completion_commit, inode); + if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate || + wbc->for_background || wbc->for_sync || wbc->for_reclaim) { + ioc = nfs_io_completion_alloc(GFP_KERNEL); + if (ioc) + nfs_io_completion_init(ioc, nfs_io_completion_commit, + inode); + priority = wb_priority(wbc); + } - nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, + nfs_pageio_init_write(&pgio, inode, priority, false, &nfs_async_write_completion_ops); pgio.pg_io_completion = ioc; err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 962e8313f007..6f76b32a0238 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -153,6 +153,8 @@ struct nfs_server { #define NFS_MOUNT_LOCAL_FCNTL 0x200000 #define NFS_MOUNT_SOFTERR 0x400000 #define NFS_MOUNT_SOFTREVAL 0x800000 +#define NFS_MOUNT_WRITE_EAGER 0x01000000 +#define NFS_MOUNT_WRITE_WAIT 0x02000000 unsigned int caps; /* server capabilities */ unsigned int rsize; /* read size */ -- cgit From a0492339fc70f1f7aa98f0cab55b78b0be124711 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Feb 2021 16:49:49 -0500 Subject: NFS: Add mount options supporting eager writes Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/fs_context.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 06894bcdea2d..b6be02aa79f0 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -82,6 +82,7 @@ enum nfs_param { Opt_v, Opt_vers, Opt_wsize, + Opt_write, }; enum { @@ -113,6 +114,19 @@ static const struct constant_table nfs_param_enums_lookupcache[] = { {} }; +enum { + Opt_write_lazy, + Opt_write_eager, + Opt_write_wait, +}; + +static const struct constant_table nfs_param_enums_write[] = { + { "lazy", Opt_write_lazy }, + { "eager", Opt_write_eager }, + { "wait", Opt_write_wait }, + {} +}; + static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_flag_no("ac", Opt_ac), fsparam_u32 ("acdirmax", Opt_acdirmax), @@ -171,6 +185,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = { fsparam_flag ("v4.1", Opt_v), fsparam_flag ("v4.2", Opt_v), fsparam_string("vers", Opt_vers), + fsparam_enum ("write", Opt_write, nfs_param_enums_write), fsparam_u32 ("wsize", Opt_wsize), {} }; @@ -770,6 +785,24 @@ static int nfs_fs_context_parse_param(struct fs_context *fc, goto out_invalid_value; } break; + case Opt_write: + switch (result.uint_32) { + case Opt_write_lazy: + ctx->flags &= + ~(NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT); + break; + case Opt_write_eager: + ctx->flags |= NFS_MOUNT_WRITE_EAGER; + ctx->flags &= ~NFS_MOUNT_WRITE_WAIT; + break; + case Opt_write_wait: + ctx->flags |= + NFS_MOUNT_WRITE_EAGER | NFS_MOUNT_WRITE_WAIT; + break; + default: + goto out_invalid_value; + } + break; /* * Special options -- cgit From 6c17260ca4aeb17d11461647c6b7eefcc2602acc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Feb 2021 16:41:19 -0500 Subject: NFS: Set the stable writes flag when initialising the super block We need to wait for outstanding writes on the page to complete before we can update it. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/fs_context.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index b6be02aa79f0..971a9251c1d9 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -1512,6 +1512,8 @@ static int nfs_init_fs_context(struct fs_context *fc) ctx->selected_flavor = RPC_AUTH_MAXFLAVOR; ctx->minorversion = 0; ctx->need_mount = true; + + fc->s_iflags |= SB_I_STABLE_WRITES; } fc->fs_private = ctx; fc->ops = &nfs_fs_context_ops; -- cgit From 7ae017c7322e2b12472033e65a48aa25cde2fb22 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 17 Feb 2021 10:12:33 -0500 Subject: NFS: Support the '-owrite=' option in /proc/self/mounts and mountinfo Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/super.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 4034102010f0..bd22c9338600 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -511,6 +511,13 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, seq_puts(m, ",local_lock=flock"); else seq_puts(m, ",local_lock=posix"); + + if (nfss->flags & NFS_MOUNT_WRITE_EAGER) { + if (nfss->flags & NFS_MOUNT_WRITE_WAIT) + seq_puts(m, ",write=wait"); + else + seq_puts(m, ",write=eager"); + } } /* -- cgit