linux-stable/fs/nfs/read.c

485 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/nfs/read.c
*
* Block I/O for NFS
*
* Partial copy of Linus' read cache modifications to fs/nfs/file.c
* modified for async RPC by okir@monad.swb.de
*/
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
#include "nfs4_fs.h"
#include "internal.h"
#include "iostat.h"
#include "fscache.h"
#include "pnfs.h"
NFS: Add static NFS I/O tracepoints Tools like tcpdump and rpcdebug can be very useful. But there are plenty of environments where they are difficult or impossible to use. For example, we've had customers report I/O failures during workloads so heavy that collecting network traffic or enabling RPC debugging are themselves onerous. The kernel's static tracepoints are lightweight (less likely to introduce timing changes) and efficient (the trace data is compact). They also work in scenarios where capturing network traffic is not possible due to lack of hardware support (some InfiniBand HCAs) or where data or network privacy is a concern. Introduce tracepoints that show when an NFS READ, WRITE, or COMMIT is initiated, and when it completes. Record the arguments and results of each operation, which are not shown by existing sunrpc module's tracepoints. For instance, the recorded offset and count can be used to match an "initiate" event to a "done" event. If an NFS READ result returns fewer bytes than requested or zero, seeing the EOF flag can be probative. Seeing an NFS4ERR_BAD_STATEID result is also indication of a particular class of problems. The timing information attached to each event record can often be useful as well. Usage example: [root@manet tmp]# trace-cmd record -e nfs:*initiate* -e nfs:*done /sys/kernel/debug/tracing/events/nfs/*initiate*/filter /sys/kernel/debug/tracing/events/nfs/*done/filter Hit Ctrl^C to stop recording ^CKernel buffer statistics: Note: "entries" are the entries left in the kernel ring buffer and are not recorded in the trace data. They should all be zero. CPU: 0 entries: 0 overrun: 0 commit overrun: 0 bytes: 3680 oldest event ts: 78.367422 now ts: 100.124419 dropped events: 0 read events: 74 ... and so on. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2017-08-21 19:00:49 +00:00
#include "nfstrace.h"
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops;
static const struct nfs_rw_ops nfs_rw_read_ops;
static struct kmem_cache *nfs_rdata_cachep;
static struct nfs_pgio_header *nfs_readhdr_alloc(void)
{
struct nfs_pgio_header *p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
if (p)
p->rw_mode = FMODE_READ;
return p;
}
static void nfs_readhdr_free(struct nfs_pgio_header *rhdr)
{
kmem_cache_free(nfs_rdata_cachep, rhdr);
}
static
int nfs_return_empty_page(struct page *page)
{
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
zero_user(page, 0, PAGE_SIZE);
SetPageUptodate(page);
unlock_page(page);
return 0;
}
void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
struct inode *inode, bool force_mds,
const struct nfs_pgio_completion_ops *compl_ops)
{
struct nfs_server *server = NFS_SERVER(inode);
const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops;
#ifdef CONFIG_NFS_V4_1
if (server->pnfs_curr_ld && !force_mds)
pg_ops = server->pnfs_curr_ld->pg_read_ops;
#endif
nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops,
server->rsize, 0);
}
EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
{
struct nfs_pgio_mirror *mirror;
if (pgio->pg_ops && pgio->pg_ops->pg_cleanup)
pgio->pg_ops->pg_cleanup(pgio);
pgio->pg_ops = &nfs_pgio_rw_ops;
/* read path should never have more than one mirror */
WARN_ON_ONCE(pgio->pg_mirror_count != 1);
mirror = &pgio->pg_mirrors[0];
mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
}
EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
static void nfs_readpage_release(struct nfs_page *req, int error)
{
struct inode *inode = d_inode(nfs_req_openctx(req)->dentry);
struct page *page = req->wb_page;
dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id,
(unsigned long long)NFS_FILEID(inode), req->wb_bytes,
(long long)req_offset(req));
if (nfs_error_is_fatal_on_server(error) && error != -ETIMEDOUT)
SetPageError(page);
if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
struct address_space *mapping = page_file_mapping(page);
if (PageUptodate(page))
nfs_readpage_to_fscache(inode, page, 0);
else if (!PageError(page) && !PagePrivate(page))
generic_error_remove_page(mapping, page);
unlock_page(page);
}
nfs_release_request(req);
}
int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
struct page *page)
{
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);
if (IS_ERR(new)) {
unlock_page(page);
return PTR_ERR(new);
}
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
if (len < PAGE_SIZE)
zero_user_segment(page, len, PAGE_SIZE);
nfs_pageio_init_read(&pgio, inode, false,
&nfs_async_read_completion_ops);
if (!nfs_pageio_add_request(&pgio, new)) {
nfs_list_remove_request(new);
nfs_readpage_release(new, pgio.pg_error);
}
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;
return pgio.pg_error < 0 ? pgio.pg_error : 0;
}
static void nfs_page_group_set_uptodate(struct nfs_page *req)
{
if (nfs_page_group_sync_on_bit(req, PG_UPTODATE))
SetPageUptodate(req->wb_page);
}
static void nfs_read_completion(struct nfs_pgio_header *hdr)
{
unsigned long bytes = 0;
int error;
if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
goto out;
while (!list_empty(&hdr->pages)) {
struct nfs_page *req = nfs_list_entry(hdr->pages.next);
struct page *page = req->wb_page;
unsigned long start = req->wb_pgbase;
unsigned long end = req->wb_pgbase + req->wb_bytes;
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 */
if (bytes > hdr->good_bytes) {
/* nothing in this request was good, so zero
* the full extent of the request */
zero_user_segment(page, start, end);
} else if (hdr->good_bytes - bytes < req->wb_bytes) {
/* part of this request has good bytes, but
* not all. zero the bad bytes */
start += hdr->good_bytes - bytes;
WARN_ON(start < req->wb_pgbase);
zero_user_segment(page, start, end);
}
}
error = 0;
bytes += req->wb_bytes;
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
if (bytes <= hdr->good_bytes)
nfs_page_group_set_uptodate(req);
else {
error = hdr->error;
xchg(&nfs_req_openctx(req)->error, error);
}
} else
nfs_page_group_set_uptodate(req);
nfs_list_remove_request(req);
nfs_readpage_release(req, error);
}
out:
hdr->release(hdr);
}
static void nfs_initiate_read(struct nfs_pgio_header *hdr,
struct rpc_message *msg,
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);
}
static void
nfs_async_read_error(struct list_head *head, int error)
{
struct nfs_page *req;
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
nfs_readpage_release(req, error);
}
}
static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = {
.error_cleanup = nfs_async_read_error,
.completion = nfs_read_completion,
};
/*
* This is the callback from RPC telling us whether a reply was
* received or some error occurred (timeout or socket shutdown).
*/
static int nfs_readpage_done(struct rpc_task *task,
struct nfs_pgio_header *hdr,
struct inode *inode)
{
int status = NFS_PROTO(inode)->read_done(task, hdr);
if (status != 0)
return status;
nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, hdr->res.count);
trace_nfs_readpage_done(task, hdr);
if (task->tk_status == -ESTALE) {
nfs_set_inode_stale(inode);
nfs_mark_for_revalidate(inode);
}
return 0;
}
static void nfs_readpage_retry(struct rpc_task *task,
struct nfs_pgio_header *hdr)
{
struct nfs_pgio_args *argp = &hdr->args;
struct nfs_pgio_res *resp = &hdr->res;
/* This is a short read! */
nfs_inc_stats(hdr->inode, NFSIOS_SHORTREAD);
/* Has the server at least made some progress? */
if (resp->count == 0) {
nfs_set_pgio_error(hdr, -EIO, argp->offset);
return;
}
NFSv4.1/pnfs: Retry through MDS when getting bad length of data If non rpc-based layout driver return bad length of data, nfs retries by calling rpc_restart_call_prepare() that cause an NULL reference panic. This patch lets nfs retry through MDS for non rpc-based layout driver return bad length of data. [13034.883329] BUG: unable to handle kernel NULL pointer dereference at (null) [13034.884902] IP: [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.886558] PGD 0 [13034.888126] Oops: 0000 [#1] KASAN [13034.889710] Modules linked in: blocklayoutdriver(OE) nfsv4(OE) nfs(OE) fscache(E) nfsd(OE) xfs libcrc32c coretemp btrfs crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev vmw_balloon auth_rpcgss shpchp nfs_acl lockd vmw_vmci parport_pc xor raid6_pq grace parport sunrpc i2c_piix4 vmwgfx drm_kms_helper ttm drm mptspi e1000 serio_raw scsi_transport_spi mptscsih mptbase ata_generic pata_acpi [last unloaded: fscache] [13034.898260] CPU: 0 PID: 10112 Comm: kworker/0:1 Tainted: G OE 4.3.0-rc5+ #279 [13034.899932] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 [13034.903342] Workqueue: events bl_read_cleanup [blocklayoutdriver] [13034.905059] task: ffff88006a9148c0 ti: ffff880035e90000 task.ti: ffff880035e90000 [13034.906827] RIP: 0010:[<ffffffffa00db372>] [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.910522] RSP: 0018:ffff880035e97b58 EFLAGS: 00010282 [13034.912378] RAX: fffffbfff04a5a94 RBX: ffff880068fe4858 RCX: 0000000000000003 [13034.914339] RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 0000000000000282 [13034.916236] RBP: ffff880035e97b68 R08: 0000000000000001 R09: 0000000000000001 [13034.918229] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 [13034.920007] R13: ffff880068fe4858 R14: ffff880068fe4a60 R15: 0000000000001000 [13034.921845] FS: 0000000000000000(0000) GS:ffffffff82247000(0000) knlGS:0000000000000000 [13034.923645] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [13034.925525] CR2: 0000000000000000 CR3: 00000000063dd000 CR4: 00000000001406f0 [13034.932808] Stack: [13034.934813] ffff880068fe4780 0000000000001000 ffff880035e97ba8 ffffffffa08800d2 [13034.936675] ffffffffa088029d ffff880068fe4780 ffff880068fe4858 ffffffffa089c0a0 [13034.938593] ffff880068fe47e0 ffff88005d59faf0 ffff880035e97be0 ffffffffa087e08f [13034.940454] Call Trace: [13034.942388] [<ffffffffa08800d2>] nfs_readpage_result+0x112/0x200 [nfs] [13034.944317] [<ffffffffa088029d>] ? nfs_readpage_done+0xdd/0x160 [nfs] [13034.946267] [<ffffffffa087e08f>] nfs_pgio_result+0x9f/0x120 [nfs] [13034.948166] [<ffffffffa09266cc>] pnfs_ld_read_done+0x7c/0x1e0 [nfsv4] [13034.950247] [<ffffffffa03b07ee>] bl_read_cleanup+0x2e/0x60 [blocklayoutdriver] [13034.952156] [<ffffffff810ebf62>] process_one_work+0x412/0x870 [13034.954102] [<ffffffff810ebe84>] ? process_one_work+0x334/0x870 [13034.955949] [<ffffffff810ebb50>] ? queue_delayed_work_on+0x40/0x40 [13034.957985] [<ffffffff810ec441>] worker_thread+0x81/0x6a0 [13034.959817] [<ffffffff810ec3c0>] ? process_one_work+0x870/0x870 [13034.961785] [<ffffffff810f43bd>] kthread+0x17d/0x1a0 [13034.963544] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.965479] [<ffffffff81100428>] ? finish_task_switch+0x88/0x220 [13034.967223] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.968929] [<ffffffff81b6ae5f>] ret_from_fork+0x3f/0x70 [13034.970534] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.972176] Code: c7 43 50 40 84 0d a0 e8 3d fe 1c e1 48 8d 7b 58 c7 83 e4 00 00 00 00 00 00 00 e8 ca fe 1c e1 4c 8b 63 58 4c 89 e7 e8 be fe 1c e1 <49> 83 3c 24 00 74 12 48 c7 43 50 f0 a2 0e a0 b8 01 00 00 00 5b [13034.977148] RIP [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.978780] RSP <ffff880035e97b58> [13034.980399] CR2: 0000000000000000 Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-10-16 09:23:29 +00:00
/* For non rpc-based layout drivers, retry-through-MDS */
if (!task->tk_ops) {
hdr->pnfs_error = -EAGAIN;
return;
}
/* Yes, so retry the read at the end of the hdr */
hdr->mds_offset += resp->count;
argp->offset += resp->count;
argp->pgbase += resp->count;
argp->count -= resp->count;
resp->count = 0;
resp->eof = 0;
rpc_restart_call_prepare(task);
}
static void nfs_readpage_result(struct rpc_task *task,
struct nfs_pgio_header *hdr)
{
if (hdr->res.eof) {
loff_t pos = hdr->args.offset + hdr->res.count;
unsigned int new = pos - hdr->io_start;
if (hdr->good_bytes > new) {
hdr->good_bytes = new;
set_bit(NFS_IOHDR_EOF, &hdr->flags);
clear_bit(NFS_IOHDR_ERROR, &hdr->flags);
}
NFSv4.1/pnfs: Retry through MDS when getting bad length of data If non rpc-based layout driver return bad length of data, nfs retries by calling rpc_restart_call_prepare() that cause an NULL reference panic. This patch lets nfs retry through MDS for non rpc-based layout driver return bad length of data. [13034.883329] BUG: unable to handle kernel NULL pointer dereference at (null) [13034.884902] IP: [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.886558] PGD 0 [13034.888126] Oops: 0000 [#1] KASAN [13034.889710] Modules linked in: blocklayoutdriver(OE) nfsv4(OE) nfs(OE) fscache(E) nfsd(OE) xfs libcrc32c coretemp btrfs crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev vmw_balloon auth_rpcgss shpchp nfs_acl lockd vmw_vmci parport_pc xor raid6_pq grace parport sunrpc i2c_piix4 vmwgfx drm_kms_helper ttm drm mptspi e1000 serio_raw scsi_transport_spi mptscsih mptbase ata_generic pata_acpi [last unloaded: fscache] [13034.898260] CPU: 0 PID: 10112 Comm: kworker/0:1 Tainted: G OE 4.3.0-rc5+ #279 [13034.899932] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 [13034.903342] Workqueue: events bl_read_cleanup [blocklayoutdriver] [13034.905059] task: ffff88006a9148c0 ti: ffff880035e90000 task.ti: ffff880035e90000 [13034.906827] RIP: 0010:[<ffffffffa00db372>] [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.910522] RSP: 0018:ffff880035e97b58 EFLAGS: 00010282 [13034.912378] RAX: fffffbfff04a5a94 RBX: ffff880068fe4858 RCX: 0000000000000003 [13034.914339] RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 0000000000000282 [13034.916236] RBP: ffff880035e97b68 R08: 0000000000000001 R09: 0000000000000001 [13034.918229] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 [13034.920007] R13: ffff880068fe4858 R14: ffff880068fe4a60 R15: 0000000000001000 [13034.921845] FS: 0000000000000000(0000) GS:ffffffff82247000(0000) knlGS:0000000000000000 [13034.923645] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [13034.925525] CR2: 0000000000000000 CR3: 00000000063dd000 CR4: 00000000001406f0 [13034.932808] Stack: [13034.934813] ffff880068fe4780 0000000000001000 ffff880035e97ba8 ffffffffa08800d2 [13034.936675] ffffffffa088029d ffff880068fe4780 ffff880068fe4858 ffffffffa089c0a0 [13034.938593] ffff880068fe47e0 ffff88005d59faf0 ffff880035e97be0 ffffffffa087e08f [13034.940454] Call Trace: [13034.942388] [<ffffffffa08800d2>] nfs_readpage_result+0x112/0x200 [nfs] [13034.944317] [<ffffffffa088029d>] ? nfs_readpage_done+0xdd/0x160 [nfs] [13034.946267] [<ffffffffa087e08f>] nfs_pgio_result+0x9f/0x120 [nfs] [13034.948166] [<ffffffffa09266cc>] pnfs_ld_read_done+0x7c/0x1e0 [nfsv4] [13034.950247] [<ffffffffa03b07ee>] bl_read_cleanup+0x2e/0x60 [blocklayoutdriver] [13034.952156] [<ffffffff810ebf62>] process_one_work+0x412/0x870 [13034.954102] [<ffffffff810ebe84>] ? process_one_work+0x334/0x870 [13034.955949] [<ffffffff810ebb50>] ? queue_delayed_work_on+0x40/0x40 [13034.957985] [<ffffffff810ec441>] worker_thread+0x81/0x6a0 [13034.959817] [<ffffffff810ec3c0>] ? process_one_work+0x870/0x870 [13034.961785] [<ffffffff810f43bd>] kthread+0x17d/0x1a0 [13034.963544] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.965479] [<ffffffff81100428>] ? finish_task_switch+0x88/0x220 [13034.967223] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.968929] [<ffffffff81b6ae5f>] ret_from_fork+0x3f/0x70 [13034.970534] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.972176] Code: c7 43 50 40 84 0d a0 e8 3d fe 1c e1 48 8d 7b 58 c7 83 e4 00 00 00 00 00 00 00 e8 ca fe 1c e1 4c 8b 63 58 4c 89 e7 e8 be fe 1c e1 <49> 83 3c 24 00 74 12 48 c7 43 50 f0 a2 0e a0 b8 01 00 00 00 5b [13034.977148] RIP [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.978780] RSP <ffff880035e97b58> [13034.980399] CR2: 0000000000000000 Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-10-16 09:23:29 +00:00
} else if (hdr->res.count < hdr->args.count)
nfs_readpage_retry(task, hdr);
}
/*
* Read a page over NFS.
* We read the page synchronously in the following case:
* - The error flag is set for this page. This happens only when a
* previous async read operation failed.
*/
int nfs_readpage(struct file *file, struct page *page)
{
struct nfs_open_context *ctx;
struct inode *inode = page_file_mapping(page)->host;
int error;
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..
*
* NOTE! Because we own the page lock, there cannot
* 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)
goto out_unlock;
if (PageUptodate(page))
goto out_unlock;
error = -ESTALE;
if (NFS_STALE(inode))
goto out_unlock;
if (file == NULL) {
error = -EBADF;
ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
if (ctx == NULL)
goto out_unlock;
} else
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)
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);
}
out:
put_nfs_open_context(ctx);
return error;
out_unlock:
unlock_page(page);
return error;
}
struct nfs_readdesc {
struct nfs_pageio_descriptor *pgio;
struct nfs_open_context *ctx;
};
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;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
if (len < PAGE_SIZE)
zero_user_segment(page, len, PAGE_SIZE);
2008-03-19 15:24:39 +00:00
if (!nfs_pageio_add_request(desc->pgio, new)) {
nfs_list_remove_request(new);
2008-03-19 15:24:39 +00:00
error = desc->pgio->pg_error;
nfs_readpage_release(new, error);
goto out;
2008-03-19 15:24:39 +00:00
}
return 0;
out_error:
error = PTR_ERR(new);
unlock_page(page);
out:
return error;
}
int nfs_readpages(struct file *filp, 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 inode *inode = mapping->host;
unsigned long npages;
int ret = -ESTALE;
dprintk("NFS: nfs_readpages (%s/%Lu %d)\n",
inode->i_sb->s_id,
(unsigned long long)NFS_FILEID(inode),
nr_pages);
nfs_inc_stats(inode, NFSIOS_VFSREADPAGES);
if (NFS_STALE(inode))
goto out;
if (filp == NULL) {
desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ);
if (desc.ctx == NULL)
return -EBADF;
} else
desc.ctx = get_nfs_open_context(nfs_file_open_context(filp));
/* attempt to read as many of the pages as possible from the cache
* - this returns -ENOBUFS immediately if the cookie is negative
*/
ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping,
pages, &nr_pages);
if (ret == 0)
goto read_complete; /* all pages were read */
nfs_pageio_init_read(&pgio, inode, false,
&nfs_async_read_completion_ops);
ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
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;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
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:
return ret;
}
int __init nfs_init_readpagecache(void)
{
nfs_rdata_cachep = kmem_cache_create("nfs_read_data",
sizeof(struct nfs_pgio_header),
0, SLAB_HWCACHE_ALIGN,
NULL);
if (nfs_rdata_cachep == NULL)
return -ENOMEM;
return 0;
}
void nfs_destroy_readpagecache(void)
{
kmem_cache_destroy(nfs_rdata_cachep);
}
static const struct nfs_rw_ops nfs_rw_read_ops = {
.rw_alloc_header = nfs_readhdr_alloc,
.rw_free_header = nfs_readhdr_free,
.rw_done = nfs_readpage_done,
.rw_result = nfs_readpage_result,
.rw_initiate = nfs_initiate_read,
};