From dbe1b5ca26396b6c61d711c8ac4de13ebb02e9f6 Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Wed, 24 Dec 2014 08:51:38 +1100 Subject: xfs: Make xfs_vn_rename compliant with renameat2() syscall To be able to support RENAME_EXCHANGE flag from renameat2() system call, XFS must have its inode_operations updated, exporting .rename2 method, instead of .rename. This patch just replaces the (now old) .rename method by .rename2, using the same infra-structure, but checking rename flags. Calls to .rename2 using RENAME_EXCHANGE flag, although now handled inside XFS, still return -EINVAL. RENAME_NOREPLACE is handled via VFS and we don't need to care about it inside xfs_vn_rename. Signed-off-by: Carlos Maiolino Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_iops.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index c50311cae1b1..abb838a565ee 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -380,18 +380,23 @@ xfs_vn_rename( struct inode *odir, struct dentry *odentry, struct inode *ndir, - struct dentry *ndentry) + struct dentry *ndentry, + unsigned int flags) { struct inode *new_inode = ndentry->d_inode; struct xfs_name oname; struct xfs_name nname; + /* XFS does not support RENAME_EXCHANGE yet */ + if (flags & ~RENAME_NOREPLACE) + return -EINVAL; + xfs_dentry_to_name(&oname, odentry, 0); xfs_dentry_to_name(&nname, ndentry, odentry->d_inode->i_mode); return xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode), - XFS_I(ndir), &nname, new_inode ? - XFS_I(new_inode) : NULL); + XFS_I(ndir), &nname, + new_inode ? XFS_I(new_inode) : NULL); } /* @@ -1144,7 +1149,7 @@ static const struct inode_operations xfs_dir_inode_operations = { */ .rmdir = xfs_vn_unlink, .mknod = xfs_vn_mknod, - .rename = xfs_vn_rename, + .rename2 = xfs_vn_rename, .get_acl = xfs_get_acl, .set_acl = xfs_set_acl, .getattr = xfs_vn_getattr, @@ -1172,7 +1177,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = { */ .rmdir = xfs_vn_unlink, .mknod = xfs_vn_mknod, - .rename = xfs_vn_rename, + .rename2 = xfs_vn_rename, .get_acl = xfs_get_acl, .set_acl = xfs_set_acl, .getattr = xfs_vn_getattr, -- cgit v1.2.3 From d31a1825450062b85282b4afed1c840fd306d012 Mon Sep 17 00:00:00 2001 From: Carlos Maiolino Date: Wed, 24 Dec 2014 08:51:42 +1100 Subject: xfs: Add support to RENAME_EXCHANGE flag Adds a new function named xfs_cross_rename(), responsible for handling requests from sys_renameat2() using RENAME_EXCHANGE flag. Signed-off-by: Carlos Maiolino Reviewed-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_inode.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++++++++- fs/xfs/xfs_inode.h | 2 +- fs/xfs/xfs_iops.c | 12 +++-- 3 files changed, 142 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 41f804e740d7..9916aef60997 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2655,6 +2655,124 @@ xfs_sort_for_rename( } } +/* + * xfs_cross_rename() + * + * responsible for handling RENAME_EXCHANGE flag in renameat2() sytemcall + */ +STATIC int +xfs_cross_rename( + struct xfs_trans *tp, + struct xfs_inode *dp1, + struct xfs_name *name1, + struct xfs_inode *ip1, + struct xfs_inode *dp2, + struct xfs_name *name2, + struct xfs_inode *ip2, + struct xfs_bmap_free *free_list, + xfs_fsblock_t *first_block, + int spaceres) +{ + int error = 0; + int ip1_flags = 0; + int ip2_flags = 0; + int dp2_flags = 0; + + /* Swap inode number for dirent in first parent */ + error = xfs_dir_replace(tp, dp1, name1, + ip2->i_ino, + first_block, free_list, spaceres); + if (error) + goto out; + + /* Swap inode number for dirent in second parent */ + error = xfs_dir_replace(tp, dp2, name2, + ip1->i_ino, + first_block, free_list, spaceres); + if (error) + goto out; + + /* + * If we're renaming one or more directories across different parents, + * update the respective ".." entries (and link counts) to match the new + * parents. + */ + if (dp1 != dp2) { + dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + + if (S_ISDIR(ip2->i_d.di_mode)) { + error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot, + dp1->i_ino, first_block, + free_list, spaceres); + if (error) + goto out; + + /* transfer ip2 ".." reference to dp1 */ + if (!S_ISDIR(ip1->i_d.di_mode)) { + error = xfs_droplink(tp, dp2); + if (error) + goto out; + error = xfs_bumplink(tp, dp1); + if (error) + goto out; + } + + /* + * Although ip1 isn't changed here, userspace needs + * to be warned about the change, so that applications + * relying on it (like backup ones), will properly + * notify the change + */ + ip1_flags |= XFS_ICHGTIME_CHG; + ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + } + + if (S_ISDIR(ip1->i_d.di_mode)) { + error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot, + dp2->i_ino, first_block, + free_list, spaceres); + if (error) + goto out; + + /* transfer ip1 ".." reference to dp2 */ + if (!S_ISDIR(ip2->i_d.di_mode)) { + error = xfs_droplink(tp, dp1); + if (error) + goto out; + error = xfs_bumplink(tp, dp2); + if (error) + goto out; + } + + /* + * Although ip2 isn't changed here, userspace needs + * to be warned about the change, so that applications + * relying on it (like backup ones), will properly + * notify the change + */ + ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG; + ip2_flags |= XFS_ICHGTIME_CHG; + } + } + + if (ip1_flags) { + xfs_trans_ichgtime(tp, ip1, ip1_flags); + xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE); + } + if (ip2_flags) { + xfs_trans_ichgtime(tp, ip2, ip2_flags); + xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE); + } + if (dp2_flags) { + xfs_trans_ichgtime(tp, dp2, dp2_flags); + xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE); + } + xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE); +out: + return error; +} + /* * xfs_rename */ @@ -2665,7 +2783,8 @@ xfs_rename( xfs_inode_t *src_ip, xfs_inode_t *target_dp, struct xfs_name *target_name, - xfs_inode_t *target_ip) + xfs_inode_t *target_ip, + unsigned int flags) { xfs_trans_t *tp = NULL; xfs_mount_t *mp = src_dp->i_mount; @@ -2742,6 +2861,18 @@ xfs_rename( goto error_return; } + /* + * Handle RENAME_EXCHANGE flags + */ + if (flags & RENAME_EXCHANGE) { + error = xfs_cross_rename(tp, src_dp, src_name, src_ip, + target_dp, target_name, target_ip, + &free_list, &first_block, spaceres); + if (error) + goto abort_return; + goto finish_rename; + } + /* * Set up the target. */ @@ -2881,6 +3012,7 @@ xfs_rename( if (new_parent) xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE); +finish_rename: /* * If this is a synchronous mount, make sure that the * rename transaction goes to disk before returning to diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 4ed2ba9342dc..f7722960b69c 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -338,7 +338,7 @@ int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, struct xfs_inode *target_dp, struct xfs_name *target_name, - struct xfs_inode *target_ip); + struct xfs_inode *target_ip, unsigned int flags); void xfs_ilock(xfs_inode_t *, uint); int xfs_ilock_nowait(xfs_inode_t *, uint); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index abb838a565ee..ce80eeb8faa4 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -384,19 +384,23 @@ xfs_vn_rename( unsigned int flags) { struct inode *new_inode = ndentry->d_inode; + int omode = 0; struct xfs_name oname; struct xfs_name nname; - /* XFS does not support RENAME_EXCHANGE yet */ - if (flags & ~RENAME_NOREPLACE) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) return -EINVAL; - xfs_dentry_to_name(&oname, odentry, 0); + /* if we are exchanging files, we need to set i_mode of both files */ + if (flags & RENAME_EXCHANGE) + omode = ndentry->d_inode->i_mode; + + xfs_dentry_to_name(&oname, odentry, omode); xfs_dentry_to_name(&nname, ndentry, odentry->d_inode->i_mode); return xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode), XFS_I(ndir), &nname, - new_inode ? XFS_I(new_inode) : NULL); + new_inode ? XFS_I(new_inode) : NULL, flags); } /* -- cgit v1.2.3 From 96ab7954bca0eeedfb17094719db1351fba361d3 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Wed, 24 Dec 2014 09:46:23 +1100 Subject: xfs: initialize log buf I/O completion wq on log alloc Log buffer I/O completion passes through the high priority m_log_workqueue rather than the default metadata buffer workqueue. The log buffer wq is initialized at I/O submission time. The log buffers are reused once initialized, however, so this is not necessary. Initialize the log buffer I/O completion workqueue pointers once when the log is allocated and log buffers initialized rather than on every log buffer I/O submission. Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_log.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index e408bf5a3ff7..4f09e0f7c07a 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1395,6 +1395,8 @@ xlog_alloc_log( ASSERT(xfs_buf_islocked(bp)); xfs_buf_unlock(bp); + /* use high priority wq for log I/O completion */ + bp->b_ioend_wq = mp->m_log_workqueue; bp->b_iodone = xlog_iodone; log->l_xbuf = bp; @@ -1427,6 +1429,8 @@ xlog_alloc_log( ASSERT(xfs_buf_islocked(bp)); xfs_buf_unlock(bp); + /* use high priority wq for log I/O completion */ + bp->b_ioend_wq = mp->m_log_workqueue; bp->b_iodone = xlog_iodone; iclog->ic_bp = bp; iclog->ic_data = bp->b_addr; @@ -1806,8 +1810,6 @@ xlog_sync( XFS_BUF_ZEROFLAGS(bp); XFS_BUF_ASYNC(bp); bp->b_flags |= XBF_SYNCIO; - /* use high priority completion wq */ - bp->b_ioend_wq = log->l_mp->m_log_workqueue; if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) { bp->b_flags |= XBF_FUA; @@ -1856,8 +1858,6 @@ xlog_sync( bp->b_flags |= XBF_SYNCIO; if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) bp->b_flags |= XBF_FUA; - /* use high priority completion wq */ - bp->b_ioend_wq = log->l_mp->m_log_workqueue; ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1); ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize); -- cgit v1.2.3 From 77af574eef78c404ea630f7955a5ed0c926a63fe Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Wed, 24 Dec 2014 09:47:27 +1100 Subject: xfs: remove extra newlines from xfs messages xfs_warn() and friends add a newline by default, but some messages add another one. Particularly for the failing write message below, this can waste a lot of console real estate! Signed-off-by: Eric Sandeen Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_buf_item.c | 2 +- fs/xfs/xfs_log.c | 2 +- fs/xfs/xfs_super.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 3f9bd58edec7..925ead22803a 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -535,7 +535,7 @@ xfs_buf_item_push( if ((bp->b_flags & XBF_WRITE_FAIL) && ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) { xfs_warn(bp->b_target->bt_mount, -"Detected failing async write on buffer block 0x%llx. Retrying async write.\n", +"Detected failing async write on buffer block 0x%llx. Retrying async write.", (long long)bp->b_bn); } diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 4f09e0f7c07a..8fbbfb2d46e1 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -2027,7 +2027,7 @@ xlog_print_tic_res( " total reg = %u bytes (o/flow = %u bytes)\n" " ophdrs = %u (ophdr space = %u bytes)\n" " ophdr + reg = %u bytes\n" - " num regions = %u\n", + " num regions = %u", ((ticket->t_trans_type <= 0 || ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ? "bad-trans-type" : trans_type_str[ticket->t_trans_type-1]), diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 19cbda196369..22e6acaa0320 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -685,7 +685,7 @@ xfs_blkdev_get( mp); if (IS_ERR(*bdevp)) { error = PTR_ERR(*bdevp); - xfs_warn(mp, "Invalid device [%s], error=%d\n", name, error); + xfs_warn(mp, "Invalid device [%s], error=%d", name, error); } return error; -- cgit v1.2.3 From 1a43ec03ddd40793db00dbc7340685f5accf6fc3 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 24 Dec 2014 09:48:35 +1100 Subject: xfs: Keep sb_bad_features2 consistent with sb_features2 Currently when we modify sb_features2, we store the same value also in sb_bad_features2. However in most places we forget to mark field sb_bad_features2 for logging and thus it can happen that a change to it is lost. This results in an inconsistent sb_features2 and sb_bad_features2 fields e.g. after xfstests test xfs/187. Fix the problem by changing XFS_SB_FEATURES2 to actually mean both sb_features2 and sb_bad_features2 fields since this is always what we want to log. This isn't ideal because the fact that XFS_SB_FEATURES2 means two fields could cause some problem in future however the code is hopefully less error prone that it is now. Signed-off-by: Jan Kara Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_format.h | 10 +++++----- fs/xfs/xfs_mount.c | 5 ++--- 2 files changed, 7 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index fbd6da263571..476273287aaf 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -304,8 +304,8 @@ typedef enum { #define XFS_SB_ICOUNT XFS_SB_MVAL(ICOUNT) #define XFS_SB_IFREE XFS_SB_MVAL(IFREE) #define XFS_SB_FDBLOCKS XFS_SB_MVAL(FDBLOCKS) -#define XFS_SB_FEATURES2 XFS_SB_MVAL(FEATURES2) -#define XFS_SB_BAD_FEATURES2 XFS_SB_MVAL(BAD_FEATURES2) +#define XFS_SB_FEATURES2 (XFS_SB_MVAL(FEATURES2) | \ + XFS_SB_MVAL(BAD_FEATURES2)) #define XFS_SB_FEATURES_COMPAT XFS_SB_MVAL(FEATURES_COMPAT) #define XFS_SB_FEATURES_RO_COMPAT XFS_SB_MVAL(FEATURES_RO_COMPAT) #define XFS_SB_FEATURES_INCOMPAT XFS_SB_MVAL(FEATURES_INCOMPAT) @@ -319,9 +319,9 @@ typedef enum { XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | XFS_SB_GQUOTINO | \ XFS_SB_QFLAGS | XFS_SB_SHARED_VN | XFS_SB_UNIT | XFS_SB_WIDTH | \ XFS_SB_ICOUNT | XFS_SB_IFREE | XFS_SB_FDBLOCKS | XFS_SB_FEATURES2 | \ - XFS_SB_BAD_FEATURES2 | XFS_SB_FEATURES_COMPAT | \ - XFS_SB_FEATURES_RO_COMPAT | XFS_SB_FEATURES_INCOMPAT | \ - XFS_SB_FEATURES_LOG_INCOMPAT | XFS_SB_PQUOTINO) + XFS_SB_FEATURES_COMPAT | XFS_SB_FEATURES_RO_COMPAT | \ + XFS_SB_FEATURES_INCOMPAT | XFS_SB_FEATURES_LOG_INCOMPAT | \ + XFS_SB_PQUOTINO) /* diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index d3d38836f87f..71d2c97cf58a 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -678,7 +678,7 @@ xfs_mountfs( xfs_warn(mp, "correcting sb_features alignment problem"); sbp->sb_features2 |= sbp->sb_bad_features2; sbp->sb_bad_features2 = sbp->sb_features2; - mp->m_update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2; + mp->m_update_flags |= XFS_SB_FEATURES2; /* * Re-check for ATTR2 in case it was found in bad_features2 @@ -1436,8 +1436,7 @@ xfs_mount_log_sb( int error; ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID | - XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2 | - XFS_SB_VERSIONNUM)); + XFS_SB_FEATURES2 | XFS_SB_VERSIONNUM)); tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT); error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); -- cgit v1.2.3 From e1f1fe798d2f2eab904624125ba924d08205f960 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 19 Dec 2014 06:51:26 +0000 Subject: jfs: get rid of homegrown endianness helpers Get rid of le24 stuff, along with the bitfields use - all that stuff can be done with standard stuff, in sparse-verifiable manner. Moreover, that way (shift-and-mask) often generates better code - gcc optimizer sucks on bitfields... Signed-off-by: Al Viro Signed-off-by: Dave Kleikamp ---- --- fs/jfs/endian24.h | 49 ------------------------------------------------ fs/jfs/jfs_dtree.c | 4 ++-- fs/jfs/jfs_types.h | 55 ++++++++++++++++++++++++++++++++---------------------- fs/jfs/jfs_xtree.h | 25 +++++++++---------------- 4 files changed, 44 insertions(+), 89 deletions(-) delete mode 100644 fs/jfs/endian24.h (limited to 'fs') diff --git a/fs/jfs/endian24.h b/fs/jfs/endian24.h deleted file mode 100644 index fa92f7f1d0d0..000000000000 --- a/fs/jfs/endian24.h +++ /dev/null @@ -1,49 +0,0 @@ -/* - * Copyright (C) International Business Machines Corp., 2001 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#ifndef _H_ENDIAN24 -#define _H_ENDIAN24 - -/* - * endian24.h: - * - * Endian conversion for 24-byte data - * - */ -#define __swab24(x) \ -({ \ - __u32 __x = (x); \ - ((__u32)( \ - ((__x & (__u32)0x000000ffUL) << 16) | \ - (__x & (__u32)0x0000ff00UL) | \ - ((__x & (__u32)0x00ff0000UL) >> 16) )); \ -}) - -#if (defined(__KERNEL__) && defined(__LITTLE_ENDIAN)) || (defined(__BYTE_ORDER) && (__BYTE_ORDER == __LITTLE_ENDIAN)) - #define __cpu_to_le24(x) ((__u32)(x)) - #define __le24_to_cpu(x) ((__u32)(x)) -#else - #define __cpu_to_le24(x) __swab24(x) - #define __le24_to_cpu(x) __swab24(x) -#endif - -#ifdef __KERNEL__ - #define cpu_to_le24 __cpu_to_le24 - #define le24_to_cpu __le24_to_cpu -#endif - -#endif /* !_H_ENDIAN24 */ diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 984c2bbf4f61..d88576e23fe4 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -1040,8 +1040,8 @@ static int dtSplitUp(tid_t tid, pxdlist.maxnpxd = 1; pxdlist.npxd = 0; pxd = &pxdlist.pxd[0]; - PXDaddress(pxd, nxaddr) - PXDlength(pxd, xlen + n); + PXDaddress(pxd, nxaddr); + PXDlength(pxd, xlen + n); split->pxdlist = &pxdlist; if ((rc = dtExtendPage(tid, ip, split, btstack))) { nxaddr = addressPXD(pxd); diff --git a/fs/jfs/jfs_types.h b/fs/jfs/jfs_types.h index 43ea3713c083..8f602dcb51fa 100644 --- a/fs/jfs/jfs_types.h +++ b/fs/jfs/jfs_types.h @@ -30,8 +30,6 @@ #include #include -#include "endian24.h" - /* * transaction and lock id's * @@ -59,26 +57,42 @@ struct timestruc_t { /* * physical xd (pxd) + * + * The leftmost 24 bits of len_addr are the extent length. + * The rightmost 8 bits of len_addr are the most signficant bits of + * the extent address */ typedef struct { - unsigned len:24; - unsigned addr1:8; + __le32 len_addr; __le32 addr2; } pxd_t; /* xd_t field construction */ -#define PXDlength(pxd, length32) ((pxd)->len = __cpu_to_le24(length32)) -#define PXDaddress(pxd, address64)\ -{\ - (pxd)->addr1 = ((s64)address64) >> 32;\ - (pxd)->addr2 = __cpu_to_le32((address64) & 0xffffffff);\ +static inline void PXDlength(pxd_t *pxd, __u32 len) +{ + pxd->len_addr = (pxd->len_addr & cpu_to_le32(~0xffffff)) | + cpu_to_le32(len & 0xffffff); +} + +static inline void PXDaddress(pxd_t *pxd, __u64 addr) +{ + pxd->len_addr = (pxd->len_addr & cpu_to_le32(0xffffff)) | + cpu_to_le32((addr >> 32)<<24); + pxd->addr2 = cpu_to_le32(addr & 0xffffffff); } /* xd_t field extraction */ -#define lengthPXD(pxd) __le24_to_cpu((pxd)->len) -#define addressPXD(pxd)\ - ( ((s64)((pxd)->addr1)) << 32 | __le32_to_cpu((pxd)->addr2)) +static inline __u32 lengthPXD(pxd_t *pxd) +{ + return le32_to_cpu((pxd)->len_addr) & 0xffffff; +} + +static inline __u64 addressPXD(pxd_t *pxd) +{ + __u64 n = le32_to_cpu(pxd->len_addr) & ~0xffffff; + return (n << 8) + le32_to_cpu(pxd->addr2); +} #define MAXTREEHEIGHT 8 /* pxd list */ @@ -93,12 +107,10 @@ struct pxdlist { * data extent descriptor (dxd) */ typedef struct { - unsigned flag:8; /* 1: flags */ - unsigned rsrvd:24; + __u8 flag; /* 1: flags */ + __u8 rsrvd[3]; __le32 size; /* 4: size in byte */ - unsigned len:24; /* 3: length in unit of fsblksize */ - unsigned addr1:8; /* 1: address in unit of fsblksize */ - __le32 addr2; /* 4: address in unit of fsblksize */ + pxd_t loc; /* 8: address and length in unit of fsblksize */ } dxd_t; /* - 16 - */ /* dxd_t flags */ @@ -109,12 +121,11 @@ typedef struct { #define DXD_CORRUPT 0x08 /* Inconsistency detected */ /* dxd_t field construction - * Conveniently, the PXD macros work for DXD */ -#define DXDlength PXDlength -#define DXDaddress PXDaddress -#define lengthDXD lengthPXD -#define addressDXD addressPXD +#define DXDlength(dxd, len) PXDlength(&(dxd)->loc, len) +#define DXDaddress(dxd, addr) PXDaddress(&(dxd)->loc, addr) +#define lengthDXD(dxd) lengthPXD(&(dxd)->loc) +#define addressDXD(dxd) addressPXD(&(dxd)->loc) #define DXDsize(dxd, size32) ((dxd)->size = cpu_to_le32(size32)) #define sizeDXD(dxd) le32_to_cpu((dxd)->size) diff --git a/fs/jfs/jfs_xtree.h b/fs/jfs/jfs_xtree.h index 08c0c749b986..1e0987986d5f 100644 --- a/fs/jfs/jfs_xtree.h +++ b/fs/jfs/jfs_xtree.h @@ -29,13 +29,11 @@ * extent allocation descriptor (xad) */ typedef struct xad { - unsigned flag:8; /* 1: flag */ - unsigned rsvrd:16; /* 2: reserved */ - unsigned off1:8; /* 1: offset in unit of fsblksize */ - __le32 off2; /* 4: offset in unit of fsblksize */ - unsigned len:24; /* 3: length in unit of fsblksize */ - unsigned addr1:8; /* 1: address in unit of fsblksize */ - __le32 addr2; /* 4: address in unit of fsblksize */ + __u8 flag; /* 1: flag */ + __u8 rsvrd[2]; /* 2: reserved */ + __u8 off1; /* 1: offset in unit of fsblksize */ + __le32 off2; /* 4: offset in unit of fsblksize */ + pxd_t loc; /* 8: length and address in unit of fsblksize */ } xad_t; /* (16) */ #define MAXXLEN ((1 << 24) - 1) @@ -49,19 +47,14 @@ typedef struct xad { (xad)->off1 = ((u64)offset64) >> 32;\ (xad)->off2 = __cpu_to_le32((offset64) & 0xffffffff);\ } -#define XADaddress(xad, address64)\ -{\ - (xad)->addr1 = ((u64)address64) >> 32;\ - (xad)->addr2 = __cpu_to_le32((address64) & 0xffffffff);\ -} -#define XADlength(xad, length32) (xad)->len = __cpu_to_le24(length32) +#define XADaddress(xad, address64) PXDaddress(&(xad)->loc, address64) +#define XADlength(xad, length32) PXDlength(&(xad)->loc, length32) /* xad_t field extraction */ #define offsetXAD(xad)\ ( ((s64)((xad)->off1)) << 32 | __le32_to_cpu((xad)->off2)) -#define addressXAD(xad)\ - ( ((s64)((xad)->addr1)) << 32 | __le32_to_cpu((xad)->addr2)) -#define lengthXAD(xad) __le24_to_cpu((xad)->len) +#define addressXAD(xad) addressPXD(&(xad)->loc) +#define lengthXAD(xad) lengthPXD(&(xad)->loc) /* xad list */ struct xadlist { -- cgit v1.2.3 From 2c561bc362da5131a26ef9bd34a58918e23a019c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 5 Jan 2015 11:04:37 +0100 Subject: udf: Update Kconfig description Update description of UDF in Kconfig to mention that UDF is also suitable for removable USB disks. Signed-off-by: Jan Kara --- fs/udf/Kconfig | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/udf/Kconfig b/fs/udf/Kconfig index 0e0e99bd6bce..c6e17a744c3b 100644 --- a/fs/udf/Kconfig +++ b/fs/udf/Kconfig @@ -2,10 +2,12 @@ config UDF_FS tristate "UDF file system support" select CRC_ITU_T help - This is the new file system used on some CD-ROMs and DVDs. Say Y if - you intend to mount DVD discs or CDRW's written in packet mode, or - if written to by other UDF utilities, such as DirectCD. - Please read . + This is a file system used on some CD-ROMs and DVDs. Since the + file system is supported by multiple operating systems and is more + compatible with standard unix file systems, it is also suitable for + removable USB disks. Say Y if you intend to mount DVD discs or CDRW's + written in packet mode, or if you want to use UDF for removable USB + disks. Please read . To compile this file system support as a module, choose M here: the module will be called udf. -- cgit v1.2.3 From 6744e90b0fa1fc6a908fa26935a5ed9e63413063 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Sat, 27 Dec 2014 16:01:22 +0100 Subject: ext3: destroy sbi mutexes in put_super Call mutex_destroy() on superblock mutexes in ext3_put_super(). Otherwise mutex debugging code isn't able to detect that mutex is used after being freed. Signed-off-by: Fabian Frederick Signed-off-by: Jan Kara --- fs/ext3/super.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 9b4e7d750d4f..d4dbf3c259b3 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -466,6 +466,8 @@ static void ext3_put_super (struct super_block * sb) } sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); + mutex_destroy(&sbi->s_orphan_lock); + mutex_destroy(&sbi->s_resize_lock); kfree(sbi); } -- cgit v1.2.3 From 62c204ddfe9649f0b1d273549f4bd68c23ed7c0d Mon Sep 17 00:00:00 2001 From: Leif Lindholm Date: Thu, 18 Dec 2014 17:50:49 +0000 Subject: fs: Make efivarfs a pseudo filesystem, built by default with EFI efivars is currently enabled under MISC_FILESYSTEMS, which is decribed as "such as filesystems that came from other operating systems". In reality, it is a pseudo filesystem, providing access to the kernel UEFI variable interface. Since this is the preferred interface for accessing UEFI variables, over the legacy efivars interface, also build it by default as a module if CONFIG_EFI. Signed-off-by: Leif Lindholm Signed-off-by: Matt Fleming --- fs/Kconfig | 2 +- fs/efivarfs/Kconfig | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/Kconfig b/fs/Kconfig index 664991afe0c0..a6bb530b1ec5 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -165,6 +165,7 @@ config HUGETLB_PAGE def_bool HUGETLBFS source "fs/configfs/Kconfig" +source "fs/efivarfs/Kconfig" endmenu @@ -209,7 +210,6 @@ source "fs/sysv/Kconfig" source "fs/ufs/Kconfig" source "fs/exofs/Kconfig" source "fs/f2fs/Kconfig" -source "fs/efivarfs/Kconfig" endif # MISC_FILESYSTEMS diff --git a/fs/efivarfs/Kconfig b/fs/efivarfs/Kconfig index 367bbb10c543..c2499ef174a2 100644 --- a/fs/efivarfs/Kconfig +++ b/fs/efivarfs/Kconfig @@ -1,6 +1,7 @@ config EFIVAR_FS tristate "EFI Variable filesystem" depends on EFI + default m help efivarfs is a replacement filesystem for the old EFI variable support via sysfs, as it doesn't suffer from the -- cgit v1.2.3 From 83fe27ea531161a655f02dc7732d14cfaa27fd5d Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Fri, 5 Dec 2014 11:24:45 -0500 Subject: rcu: Make SRCU optional by using CONFIG_SRCU SRCU is not necessary to be compiled by default in all cases. For tinification efforts not compiling SRCU unless necessary is desirable. The current patch tries to make compiling SRCU optional by introducing a new Kconfig option CONFIG_SRCU which is selected when any of the components making use of SRCU are selected. If we do not select CONFIG_SRCU, srcu.o will not be compiled at all. text data bss dec hex filename 2007 0 0 2007 7d7 kernel/rcu/srcu.o Size of arch/powerpc/boot/zImage changes from text data bss dec hex filename 831552 64180 23944 919676 e087c arch/powerpc/boot/zImage : before 829504 64180 23952 917636 e0084 arch/powerpc/boot/zImage : after so the savings are about ~2000 bytes. Signed-off-by: Pranith Kumar CC: Paul E. McKenney CC: Josh Triplett CC: Lai Jiangshan Signed-off-by: Paul E. McKenney [ paulmck: resolve conflict due to removal of arch/ia64/kvm/Kconfig. ] --- arch/arm/kvm/Kconfig | 1 + arch/arm64/kvm/Kconfig | 1 + arch/mips/kvm/Kconfig | 1 + arch/powerpc/kvm/Kconfig | 1 + arch/s390/kvm/Kconfig | 1 + arch/tile/kvm/Kconfig | 1 + arch/x86/Kconfig | 1 + arch/x86/kvm/Kconfig | 1 + drivers/clk/Kconfig | 1 + drivers/cpufreq/Kconfig | 1 + drivers/devfreq/Kconfig | 1 + drivers/md/Kconfig | 1 + drivers/net/Kconfig | 1 + fs/btrfs/Kconfig | 1 + fs/notify/Kconfig | 1 + fs/quota/Kconfig | 1 + init/Kconfig | 9 +++++++++ kernel/notifier.c | 3 +++ kernel/power/Kconfig | 1 + kernel/rcu/Makefile | 3 ++- lib/Kconfig.debug | 1 + mm/Kconfig | 1 + security/tomoyo/Kconfig | 1 + 23 files changed, 34 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 466bd299b1a8..3afee5f40f4f 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -23,6 +23,7 @@ config KVM select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_ARM_HOST + select SRCU depends on ARM_VIRT_EXT && ARM_LPAE ---help--- Support hosting virtualized guest machines. You will also diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 8ba85e9ea388..b334084d3675 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -26,6 +26,7 @@ config KVM select KVM_ARM_HOST select KVM_ARM_VGIC select KVM_ARM_TIMER + select SRCU ---help--- Support hosting virtualized guest machines. diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index 30e334e823bd..2ae12825529f 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -20,6 +20,7 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select KVM_MMIO + select SRCU ---help--- Support for hosting Guest kernels. Currently supported on MIPS32 processors. diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index f5769f19ae25..11850f310fb4 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select HAVE_KVM_EVENTFD + select SRCU config KVM_BOOK3S_HANDLER bool diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 646db9c467d1..5fce52cf0e57 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING + select SRCU ---help--- Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/tile/kvm/Kconfig b/arch/tile/kvm/Kconfig index 2298cb1daff7..1e968f7550dc 100644 --- a/arch/tile/kvm/Kconfig +++ b/arch/tile/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM depends on HAVE_KVM && MODULES select PREEMPT_NOTIFIERS select ANON_INODES + select SRCU ---help--- Support hosting paravirtualized guest machines. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba397bde7948..661269953c1a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -138,6 +138,7 @@ config X86 select HAVE_ACPI_APEI_NMI if ACPI select ACPI_LEGACY_TABLES_LOOKUP if ACPI select X86_FEATURE_NAMES if PROC_FS + select SRCU config INSTRUCTION_DECODER def_bool y diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index f9d16ff56c6b..7dc7ba577ecd 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -40,6 +40,7 @@ config KVM select HAVE_KVM_MSI select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_VFIO + select SRCU ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 3f44f292d066..91f86131bb7a 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -13,6 +13,7 @@ config COMMON_CLK bool select HAVE_CLK_PREPARE select CLKDEV_LOOKUP + select SRCU ---help--- The common clock framework is a single definition of struct clk, useful across many platforms, as well as an diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 29b2ef5a68b9..a171fef2c2b6 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -2,6 +2,7 @@ menu "CPU Frequency scaling" config CPU_FREQ bool "CPU Frequency scaling" + select SRCU help CPU Frequency scaling allows you to change the clock speed of CPUs on the fly. This is a nice method to save power, because diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index faf4e70c42e0..3891f6781298 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -1,5 +1,6 @@ menuconfig PM_DEVFREQ bool "Generic Dynamic Voltage and Frequency Scaling (DVFS) support" + select SRCU help A device may have a list of frequencies and voltages available. devfreq, a generic DVFS framework can be registered for a device diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 5bdedf6df153..c355a226a024 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -5,6 +5,7 @@ menuconfig MD bool "Multiple devices driver support (RAID and LVM)" depends on BLOCK + select SRCU help Support multiple physical spindles through a single logical device. Required for RAID and logical volume management. diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index d6607ee9c855..84673ebcf428 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -197,6 +197,7 @@ config NETCONSOLE_DYNAMIC config NETPOLL def_bool NETCONSOLE + select SRCU config NET_POLL_CONTROLLER def_bool NETPOLL diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index a66768ebc8d1..80e9c18ea64f 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -8,6 +8,7 @@ config BTRFS_FS select LZO_DECOMPRESS select RAID6_PQ select XOR_BLOCKS + select SRCU help Btrfs is a general purpose copy-on-write filesystem with extents, diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig index 22c629eedd82..2a24249b30af 100644 --- a/fs/notify/Kconfig +++ b/fs/notify/Kconfig @@ -1,5 +1,6 @@ config FSNOTIFY def_bool n + select SRCU source "fs/notify/dnotify/Kconfig" source "fs/notify/inotify/Kconfig" diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig index c51df1dd237e..4a09975aac90 100644 --- a/fs/quota/Kconfig +++ b/fs/quota/Kconfig @@ -5,6 +5,7 @@ config QUOTA bool "Quota support" select QUOTACTL + select SRCU help If you say Y here, you will be able to set per user limits for disk usage (also called disk quotas). Currently, it works for the diff --git a/init/Kconfig b/init/Kconfig index 9afb971497f4..f085969ba340 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -501,9 +501,17 @@ config TINY_RCU endchoice +config SRCU + bool + help + This option selects the sleepable version of RCU. This version + permits arbitrary sleeping or blocking within RCU read-side critical + sections. + config TASKS_RCU bool "Task_based RCU implementation using voluntary context switch" default n + select SRCU help This option enables a task-based RCU implementation that uses only voluntary context switch (not preemption!), idle, and @@ -1595,6 +1603,7 @@ config PERF_EVENTS depends on HAVE_PERF_EVENTS select ANON_INODES select IRQ_WORK + select SRCU help Enable kernel support for various performance events provided by software and hardware. diff --git a/kernel/notifier.c b/kernel/notifier.c index 4803da6eab62..ae9fc7cc360e 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -402,6 +402,7 @@ int raw_notifier_call_chain(struct raw_notifier_head *nh, } EXPORT_SYMBOL_GPL(raw_notifier_call_chain); +#ifdef CONFIG_SRCU /* * SRCU notifier chain routines. Registration and unregistration * use a mutex, and call_chain is synchronized by SRCU (no locks). @@ -528,6 +529,8 @@ void srcu_init_notifier_head(struct srcu_notifier_head *nh) } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); +#endif /* CONFIG_SRCU */ + static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace notify_die(enum die_val val, const char *str, diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 48b28d387c7f..7e01f78f0417 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -251,6 +251,7 @@ config APM_EMULATION config PM_OPP bool + select SRCU ---help--- SOCs have a standard set of tuples consisting of frequency and voltage pairs that the device will support per voltage domain. This diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index e6fae503d1bc..50a808424b06 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -1,4 +1,5 @@ -obj-y += update.o srcu.o +obj-y += update.o +obj-$(CONFIG_SRCU) += srcu.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_TREE_RCU) += tree.o obj-$(CONFIG_PREEMPT_RCU) += tree.o diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 5f2ce616c046..7a9c93e327f2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1215,6 +1215,7 @@ config RCU_TORTURE_TEST tristate "torture tests for RCU" depends on DEBUG_KERNEL select TORTURE_TEST + select SRCU default n help This option provides a kernel module that runs torture tests diff --git a/mm/Kconfig b/mm/Kconfig index 1d1ae6b078fd..4395b12869c8 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -325,6 +325,7 @@ config VIRT_TO_BUS config MMU_NOTIFIER bool + select SRCU config KSM bool "Enable KSM for page merging" diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig index 8eb779b9d77f..604e718d68d3 100644 --- a/security/tomoyo/Kconfig +++ b/security/tomoyo/Kconfig @@ -5,6 +5,7 @@ config SECURITY_TOMOYO select SECURITYFS select SECURITY_PATH select SECURITY_NETWORK + select SRCU default n help This selects TOMOYO Linux, pathname-based access control. -- cgit v1.2.3 From e4a93be6cb281fb3dbbd41b22aee02cb0e551ba8 Mon Sep 17 00:00:00 2001 From: Oscar Forner Martinez Date: Tue, 6 Jan 2015 16:54:19 -0800 Subject: isofs: Fix bug in the way to check if the year is a leap year Changed the whole algorithm for a call to mktime64 that takes care of all that details. Signed-off-by: Oscar Forner Martinez Signed-off-by: Jan Kara --- fs/isofs/util.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'fs') diff --git a/fs/isofs/util.c b/fs/isofs/util.c index 01e1ee7a998b..005a15cfd30a 100644 --- a/fs/isofs/util.c +++ b/fs/isofs/util.c @@ -2,6 +2,7 @@ * linux/fs/isofs/util.c */ +#include #include "isofs.h" /* @@ -17,9 +18,9 @@ int iso_date(char * p, int flag) { int year, month, day, hour, minute, second, tz; - int crtime, days, i; + int crtime; - year = p[0] - 70; + year = p[0]; month = p[1]; day = p[2]; hour = p[3]; @@ -31,18 +32,7 @@ int iso_date(char * p, int flag) if (year < 0) { crtime = 0; } else { - int monlen[12] = {31,28,31,30,31,30,31,31,30,31,30,31}; - - days = year * 365; - if (year > 2) - days += (year+1) / 4; - for (i = 1; i < month; i++) - days += monlen[i-1]; - if (((year+2) % 4) == 0 && month > 2) - days++; - days += day - 1; - crtime = ((((days * 24) + hour) * 60 + minute) * 60) - + second; + crtime = mktime64(year+1900, month, day, hour, minute, second); /* sign extend */ if (tz & 0x80) -- cgit v1.2.3 From 79144954278d4bb5989f8b903adcac7a20ff2a5a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 7 Jan 2015 13:46:16 +0100 Subject: udf: Remove repeated loads blocksize Store blocksize in a local variable in udf_fill_inode() since it is used a lot of times. Signed-off-by: Jan Kara --- fs/udf/inode.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 5bc71d9a674a..95cb6970c3ea 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1288,6 +1288,7 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode) struct kernel_lb_addr *iloc = &iinfo->i_location; unsigned int link_count; unsigned int indirections = 0; + int bs = inode->i_sb->s_blocksize; int ret = -EIO; reread: @@ -1374,38 +1375,35 @@ reread: if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_EFE)) { iinfo->i_efe = 1; iinfo->i_use = 0; - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - + ret = udf_alloc_i_data(inode, bs - sizeof(struct extendedFileEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct extendedFileEntry), - inode->i_sb->s_blocksize - - sizeof(struct extendedFileEntry)); + bs - sizeof(struct extendedFileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_FE)) { iinfo->i_efe = 0; iinfo->i_use = 0; - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - - sizeof(struct fileEntry)); + ret = udf_alloc_i_data(inode, bs - sizeof(struct fileEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct fileEntry), - inode->i_sb->s_blocksize - sizeof(struct fileEntry)); + bs - sizeof(struct fileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) { iinfo->i_efe = 0; iinfo->i_use = 1; iinfo->i_lenAlloc = le32_to_cpu( ((struct unallocSpaceEntry *)bh->b_data)-> lengthAllocDescs); - ret = udf_alloc_i_data(inode, inode->i_sb->s_blocksize - + ret = udf_alloc_i_data(inode, bs - sizeof(struct unallocSpaceEntry)); if (ret) goto out; memcpy(iinfo->i_ext.i_data, bh->b_data + sizeof(struct unallocSpaceEntry), - inode->i_sb->s_blocksize - - sizeof(struct unallocSpaceEntry)); + bs - sizeof(struct unallocSpaceEntry)); return 0; } @@ -1498,8 +1496,7 @@ reread: if (iinfo->i_lenAlloc != inode->i_size) goto out; /* File in ICB has to fit in there... */ - if (inode->i_size > inode->i_sb->s_blocksize - - udf_file_entry_alloc_offset(inode)) + if (inode->i_size > bs - udf_file_entry_alloc_offset(inode)) goto out; } -- cgit v1.2.3 From 23b133bdc452aa441fcb9b82cbf6dd05cfd342d0 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 7 Jan 2015 13:49:08 +0100 Subject: udf: Check length of extended attributes and allocation descriptors Check length of extended attributes and allocation descriptors when loading inodes from disk. Otherwise corrupted filesystems could confuse the code and make the kernel oops. Reported-by: Carl Henrik Lunde CC: stable@vger.kernel.org Signed-off-by: Jan Kara --- fs/udf/inode.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs') diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 95cb6970c3ea..7b72b7dd8906 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1487,6 +1487,15 @@ reread: } inode->i_generation = iinfo->i_unique; + /* + * Sanity check length of allocation descriptors and extended attrs to + * avoid integer overflows + */ + if (iinfo->i_lenEAttr > bs || iinfo->i_lenAlloc > bs) + goto out; + /* Now do exact checks */ + if (udf_file_entry_alloc_offset(inode) + iinfo->i_lenAlloc > bs) + goto out; /* Sanity checks for files in ICB so that we don't get confused later */ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { /* -- cgit v1.2.3 From 67db10344816c74709271c30905bb83781e7050c Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Sat, 13 Dec 2014 09:11:40 -0500 Subject: nfsd: fi_delegees doesn't need to be an atomic_t fi_delegees is always handled under the fi_lock, so there's no need to use an atomic_t for this field. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 8 ++++---- fs/nfsd/state.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c06a1ba80d73..277f8b8529d6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -688,7 +688,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp) struct file *filp = NULL; spin_lock(&fp->fi_lock); - if (fp->fi_deleg_file && atomic_dec_and_test(&fp->fi_delegees)) + if (fp->fi_deleg_file && --fp->fi_delegees == 0) swap(filp, fp->fi_deleg_file); spin_unlock(&fp->fi_lock); @@ -3855,12 +3855,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp) /* Race breaker */ if (fp->fi_deleg_file) { status = 0; - atomic_inc(&fp->fi_delegees); + ++fp->fi_delegees; hash_delegation_locked(dp, fp); goto out_unlock; } fp->fi_deleg_file = filp; - atomic_set(&fp->fi_delegees, 1); + fp->fi_delegees = 1; hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -3901,7 +3901,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, status = -EAGAIN; goto out_unlock; } - atomic_inc(&fp->fi_delegees); + ++fp->fi_delegees; hash_delegation_locked(dp, fp); status = 0; out_unlock: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 9d3be371240a..dab6553ceea1 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -493,7 +493,7 @@ struct nfs4_file { atomic_t fi_access[2]; u32 fi_share_deny; struct file *fi_deleg_file; - atomic_t fi_delegees; + int fi_delegees; struct knfsd_fh fi_fhandle; bool fi_had_conflict; }; -- cgit v1.2.3 From 0ec016e3e02fe07e7250b87daffab611f219e7f1 Mon Sep 17 00:00:00 2001 From: J. Bruce Fields Date: Fri, 19 Dec 2014 18:01:35 -0500 Subject: nfsd4: tweak rd_dircount accounting RFC 3530 14.2.24 says This value represents the length of the names of the directory entries and the cookie value for these entries. This length represents the XDR encoding of the data (names and cookies)... The "xdr encoding" of the name should probably include the 4 bytes for the length. But this is all just a hint so not worth e.g. backporting to stable. Also reshuffle some lines to more clearly group together the dircount-related code. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 15f7b73e0c0f..91f7a3644ffb 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2768,16 +2768,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, if (entry_bytes > cd->rd_maxcount) goto fail; cd->rd_maxcount -= entry_bytes; - if (!cd->rd_dircount) - goto fail; /* * RFC 3530 14.2.24 describes rd_dircount as only a "hint", so * let's always let through the first entry, at least: */ - name_and_cookie = 4 * XDR_QUADLEN(namlen) + 8; + if (!cd->rd_dircount) + goto fail; + name_and_cookie = 4 + 4 * XDR_QUADLEN(namlen) + 8; if (name_and_cookie > cd->rd_dircount && cd->cookie_offset) goto fail; cd->rd_dircount -= min(cd->rd_dircount, name_and_cookie); + cd->cookie_offset = cookie_offset; skip_entry: cd->common.err = nfs_ok; -- cgit v1.2.3 From 26e022727f5e88c6e5054e14d954425deacbe56a Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 18 Dec 2014 16:02:17 +0100 Subject: efi: Rename efi_guid_unparse to efi_guid_to_str Call it what it does - "unparse" is plain-misleading. Signed-off-by: Borislav Petkov Signed-off-by: Ricardo Neri --- block/partitions/efi.c | 2 +- drivers/firmware/efi/efi.c | 4 ++-- drivers/firmware/efi/efivars.c | 6 +++--- fs/efivarfs/super.c | 2 +- include/linux/efi.h | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/block/partitions/efi.c b/block/partitions/efi.c index 56d08fd75b1a..26cb624ace05 100644 --- a/block/partitions/efi.c +++ b/block/partitions/efi.c @@ -715,7 +715,7 @@ int efi_partition(struct parsed_partitions *state) state->parts[i + 1].flags = ADDPART_FLAG_RAID; info = &state->parts[i + 1].info; - efi_guid_unparse(&ptes[i].unique_partition_guid, info->uuid); + efi_guid_to_str(&ptes[i].unique_partition_guid, info->uuid); /* Naively convert UTF16-LE to 7 bits. */ label_max = min(ARRAY_SIZE(info->volname) - 1, diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 8590099ac148..ff0bbe383b31 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -272,10 +272,10 @@ static __init int match_config_table(efi_guid_t *guid, int i; if (table_types) { - efi_guid_unparse(guid, str); + efi_guid_to_str(guid, str); for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) { - efi_guid_unparse(&table_types[i].guid, str); + efi_guid_to_str(&table_types[i].guid, str); if (!efi_guidcmp(*guid, table_types[i].guid)) { *(table_types[i].ptr) = table; diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index f256ecd8a176..7b2e0496e0c0 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -39,7 +39,7 @@ * fix locking per Peter Chubb's findings * * 25 Mar 2002 - Matt Domsch - * move uuid_unparse() to include/asm-ia64/efi.h:efi_guid_unparse() + * move uuid_unparse() to include/asm-ia64/efi.h:efi_guid_to_str() * * 12 Feb 2002 - Matt Domsch * use list_for_each_safe when deleting vars. @@ -128,7 +128,7 @@ efivar_guid_read(struct efivar_entry *entry, char *buf) if (!entry || !buf) return 0; - efi_guid_unparse(&var->VendorGuid, str); + efi_guid_to_str(&var->VendorGuid, str); str += strlen(str); str += sprintf(str, "\n"); @@ -569,7 +569,7 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var) private variables from another's. */ *(short_name + strlen(short_name)) = '-'; - efi_guid_unparse(&new_var->var.VendorGuid, + efi_guid_to_str(&new_var->var.VendorGuid, short_name + strlen(short_name)); new_var->kobj.kset = efivars_kset; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 6dad1176ec52..ddbce42548c9 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -140,7 +140,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len] = '-'; - efi_guid_unparse(&entry->var.VendorGuid, name + len + 1); + efi_guid_to_str(&entry->var.VendorGuid, name + len + 1); name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; diff --git a/include/linux/efi.h b/include/linux/efi.h index 0949f9c7e872..d762c81e62a8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -844,7 +844,7 @@ efi_guidcmp (efi_guid_t left, efi_guid_t right) } static inline char * -efi_guid_unparse(efi_guid_t *guid, char *out) +efi_guid_to_str(efi_guid_t *guid, char *out) { sprintf(out, "%pUl", guid->b); return out; -- cgit v1.2.3 From 2155355fda502e75cd942db101fbb08e1a826ba8 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 9 Jan 2015 10:45:13 +1100 Subject: xfs: move xfs_fs.h to libxfs Ioctl API definitions are shared with userspace, so move the header file that defines them all to libxfs along with all the other code shared with userspace. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_fs.h | 576 +++++++++++++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_fs.h | 576 ------------------------------------------------- 2 files changed, 576 insertions(+), 576 deletions(-) create mode 100644 fs/xfs/libxfs/xfs_fs.h delete mode 100644 fs/xfs/xfs_fs.h (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h new file mode 100644 index 000000000000..18dc721ca19f --- /dev/null +++ b/fs/xfs/libxfs/xfs_fs.h @@ -0,0 +1,576 @@ +/* + * Copyright (c) 1995-2005 Silicon Graphics, Inc. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with this program; if not, write the Free Software Foundation, + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ +#ifndef __XFS_FS_H__ +#define __XFS_FS_H__ + +/* + * SGI's XFS filesystem's major stuff (constants, structures) + */ + +/* + * Direct I/O attribute record used with XFS_IOC_DIOINFO + * d_miniosz is the min xfer size, xfer size multiple and file seek offset + * alignment. + */ +#ifndef HAVE_DIOATTR +struct dioattr { + __u32 d_mem; /* data buffer memory alignment */ + __u32 d_miniosz; /* min xfer size */ + __u32 d_maxiosz; /* max xfer size */ +}; +#endif + +/* + * Structure for XFS_IOC_FSGETXATTR[A] and XFS_IOC_FSSETXATTR. + */ +#ifndef HAVE_FSXATTR +struct fsxattr { + __u32 fsx_xflags; /* xflags field value (get/set) */ + __u32 fsx_extsize; /* extsize field value (get/set)*/ + __u32 fsx_nextents; /* nextents field value (get) */ + __u32 fsx_projid; /* project identifier (get/set) */ + unsigned char fsx_pad[12]; +}; +#endif + +/* + * Flags for the bs_xflags/fsx_xflags field + * There should be a one-to-one correspondence between these flags and the + * XFS_DIFLAG_s. + */ +#define XFS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ +#define XFS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */ +#define XFS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */ +#define XFS_XFLAG_APPEND 0x00000010 /* all writes append */ +#define XFS_XFLAG_SYNC 0x00000020 /* all writes synchronous */ +#define XFS_XFLAG_NOATIME 0x00000040 /* do not update access time */ +#define XFS_XFLAG_NODUMP 0x00000080 /* do not include in backups */ +#define XFS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */ +#define XFS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */ +#define XFS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */ +#define XFS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */ +#define XFS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */ +#define XFS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */ +#define XFS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ +#define XFS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ + +/* + * Structure for XFS_IOC_GETBMAP. + * On input, fill in bmv_offset and bmv_length of the first structure + * to indicate the area of interest in the file, and bmv_entries with + * the number of array elements given back. The first structure is + * updated on return to give the offset and length for the next call. + */ +#ifndef HAVE_GETBMAP +struct getbmap { + __s64 bmv_offset; /* file offset of segment in blocks */ + __s64 bmv_block; /* starting block (64-bit daddr_t) */ + __s64 bmv_length; /* length of segment, blocks */ + __s32 bmv_count; /* # of entries in array incl. 1st */ + __s32 bmv_entries; /* # of entries filled in (output) */ +}; +#endif + +/* + * Structure for XFS_IOC_GETBMAPX. Fields bmv_offset through bmv_entries + * are used exactly as in the getbmap structure. The getbmapx structure + * has additional bmv_iflags and bmv_oflags fields. The bmv_iflags field + * is only used for the first structure. It contains input flags + * specifying XFS_IOC_GETBMAPX actions. The bmv_oflags field is filled + * in by the XFS_IOC_GETBMAPX command for each returned structure after + * the first. + */ +#ifndef HAVE_GETBMAPX +struct getbmapx { + __s64 bmv_offset; /* file offset of segment in blocks */ + __s64 bmv_block; /* starting block (64-bit daddr_t) */ + __s64 bmv_length; /* length of segment, blocks */ + __s32 bmv_count; /* # of entries in array incl. 1st */ + __s32 bmv_entries; /* # of entries filled in (output). */ + __s32 bmv_iflags; /* input flags (1st structure) */ + __s32 bmv_oflags; /* output flags (after 1st structure)*/ + __s32 bmv_unused1; /* future use */ + __s32 bmv_unused2; /* future use */ +}; +#endif + +/* bmv_iflags values - set by XFS_IOC_GETBMAPX caller. */ +#define BMV_IF_ATTRFORK 0x1 /* return attr fork rather than data */ +#define BMV_IF_NO_DMAPI_READ 0x2 /* Do not generate DMAPI read event */ +#define BMV_IF_PREALLOC 0x4 /* rtn status BMV_OF_PREALLOC if req */ +#define BMV_IF_DELALLOC 0x8 /* rtn status BMV_OF_DELALLOC if req */ +#define BMV_IF_NO_HOLES 0x10 /* Do not return holes */ +#define BMV_IF_VALID \ + (BMV_IF_ATTRFORK|BMV_IF_NO_DMAPI_READ|BMV_IF_PREALLOC| \ + BMV_IF_DELALLOC|BMV_IF_NO_HOLES) + +/* bmv_oflags values - returned for each non-header segment */ +#define BMV_OF_PREALLOC 0x1 /* segment = unwritten pre-allocation */ +#define BMV_OF_DELALLOC 0x2 /* segment = delayed allocation */ +#define BMV_OF_LAST 0x4 /* segment is the last in the file */ + +/* + * Structure for XFS_IOC_FSSETDM. + * For use by backup and restore programs to set the XFS on-disk inode + * fields di_dmevmask and di_dmstate. These must be set to exactly and + * only values previously obtained via xfs_bulkstat! (Specifically the + * xfs_bstat_t fields bs_dmevmask and bs_dmstate.) + */ +#ifndef HAVE_FSDMIDATA +struct fsdmidata { + __u32 fsd_dmevmask; /* corresponds to di_dmevmask */ + __u16 fsd_padding; + __u16 fsd_dmstate; /* corresponds to di_dmstate */ +}; +#endif + +/* + * File segment locking set data type for 64 bit access. + * Also used for all the RESV/FREE interfaces. + */ +typedef struct xfs_flock64 { + __s16 l_type; + __s16 l_whence; + __s64 l_start; + __s64 l_len; /* len == 0 means until end of file */ + __s32 l_sysid; + __u32 l_pid; + __s32 l_pad[4]; /* reserve area */ +} xfs_flock64_t; + +/* + * Output for XFS_IOC_FSGEOMETRY_V1 + */ +typedef struct xfs_fsop_geom_v1 { + __u32 blocksize; /* filesystem (data) block size */ + __u32 rtextsize; /* realtime extent size */ + __u32 agblocks; /* fsblocks in an AG */ + __u32 agcount; /* number of allocation groups */ + __u32 logblocks; /* fsblocks in the log */ + __u32 sectsize; /* (data) sector size, bytes */ + __u32 inodesize; /* inode size in bytes */ + __u32 imaxpct; /* max allowed inode space(%) */ + __u64 datablocks; /* fsblocks in data subvolume */ + __u64 rtblocks; /* fsblocks in realtime subvol */ + __u64 rtextents; /* rt extents in realtime subvol*/ + __u64 logstart; /* starting fsblock of the log */ + unsigned char uuid[16]; /* unique id of the filesystem */ + __u32 sunit; /* stripe unit, fsblocks */ + __u32 swidth; /* stripe width, fsblocks */ + __s32 version; /* structure version */ + __u32 flags; /* superblock version flags */ + __u32 logsectsize; /* log sector size, bytes */ + __u32 rtsectsize; /* realtime sector size, bytes */ + __u32 dirblocksize; /* directory block size, bytes */ +} xfs_fsop_geom_v1_t; + +/* + * Output for XFS_IOC_FSGEOMETRY + */ +typedef struct xfs_fsop_geom { + __u32 blocksize; /* filesystem (data) block size */ + __u32 rtextsize; /* realtime extent size */ + __u32 agblocks; /* fsblocks in an AG */ + __u32 agcount; /* number of allocation groups */ + __u32 logblocks; /* fsblocks in the log */ + __u32 sectsize; /* (data) sector size, bytes */ + __u32 inodesize; /* inode size in bytes */ + __u32 imaxpct; /* max allowed inode space(%) */ + __u64 datablocks; /* fsblocks in data subvolume */ + __u64 rtblocks; /* fsblocks in realtime subvol */ + __u64 rtextents; /* rt extents in realtime subvol*/ + __u64 logstart; /* starting fsblock of the log */ + unsigned char uuid[16]; /* unique id of the filesystem */ + __u32 sunit; /* stripe unit, fsblocks */ + __u32 swidth; /* stripe width, fsblocks */ + __s32 version; /* structure version */ + __u32 flags; /* superblock version flags */ + __u32 logsectsize; /* log sector size, bytes */ + __u32 rtsectsize; /* realtime sector size, bytes */ + __u32 dirblocksize; /* directory block size, bytes */ + __u32 logsunit; /* log stripe unit, bytes */ +} xfs_fsop_geom_t; + +/* Output for XFS_FS_COUNTS */ +typedef struct xfs_fsop_counts { + __u64 freedata; /* free data section blocks */ + __u64 freertx; /* free rt extents */ + __u64 freeino; /* free inodes */ + __u64 allocino; /* total allocated inodes */ +} xfs_fsop_counts_t; + +/* Input/Output for XFS_GET_RESBLKS and XFS_SET_RESBLKS */ +typedef struct xfs_fsop_resblks { + __u64 resblks; + __u64 resblks_avail; +} xfs_fsop_resblks_t; + +#define XFS_FSOP_GEOM_VERSION 0 + +#define XFS_FSOP_GEOM_FLAGS_ATTR 0x0001 /* attributes in use */ +#define XFS_FSOP_GEOM_FLAGS_NLINK 0x0002 /* 32-bit nlink values */ +#define XFS_FSOP_GEOM_FLAGS_QUOTA 0x0004 /* quotas enabled */ +#define XFS_FSOP_GEOM_FLAGS_IALIGN 0x0008 /* inode alignment */ +#define XFS_FSOP_GEOM_FLAGS_DALIGN 0x0010 /* large data alignment */ +#define XFS_FSOP_GEOM_FLAGS_SHARED 0x0020 /* read-only shared */ +#define XFS_FSOP_GEOM_FLAGS_EXTFLG 0x0040 /* special extent flag */ +#define XFS_FSOP_GEOM_FLAGS_DIRV2 0x0080 /* directory version 2 */ +#define XFS_FSOP_GEOM_FLAGS_LOGV2 0x0100 /* log format version 2 */ +#define XFS_FSOP_GEOM_FLAGS_SECTOR 0x0200 /* sector sizes >1BB */ +#define XFS_FSOP_GEOM_FLAGS_ATTR2 0x0400 /* inline attributes rework */ +#define XFS_FSOP_GEOM_FLAGS_PROJID32 0x0800 /* 32-bit project IDs */ +#define XFS_FSOP_GEOM_FLAGS_DIRV2CI 0x1000 /* ASCII only CI names */ +#define XFS_FSOP_GEOM_FLAGS_LAZYSB 0x4000 /* lazy superblock counters */ +#define XFS_FSOP_GEOM_FLAGS_V5SB 0x8000 /* version 5 superblock */ +#define XFS_FSOP_GEOM_FLAGS_FTYPE 0x10000 /* inode directory types */ +#define XFS_FSOP_GEOM_FLAGS_FINOBT 0x20000 /* free inode btree */ + +/* + * Minimum and maximum sizes need for growth checks. + * + * Block counts are in units of filesystem blocks, not basic blocks. + */ +#define XFS_MIN_AG_BLOCKS 64 +#define XFS_MIN_LOG_BLOCKS 512ULL +#define XFS_MAX_LOG_BLOCKS (1024 * 1024ULL) +#define XFS_MIN_LOG_BYTES (10 * 1024 * 1024ULL) + +/* keep the maximum size under 2^31 by a small amount */ +#define XFS_MAX_LOG_BYTES \ + ((2 * 1024 * 1024 * 1024ULL) - XFS_MIN_LOG_BYTES) + +/* Used for sanity checks on superblock */ +#define XFS_MAX_DBLOCKS(s) ((xfs_rfsblock_t)(s)->sb_agcount * (s)->sb_agblocks) +#define XFS_MIN_DBLOCKS(s) ((xfs_rfsblock_t)((s)->sb_agcount - 1) * \ + (s)->sb_agblocks + XFS_MIN_AG_BLOCKS) + +/* + * Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT + */ +typedef struct xfs_growfs_data { + __u64 newblocks; /* new data subvol size, fsblocks */ + __u32 imaxpct; /* new inode space percentage limit */ +} xfs_growfs_data_t; + +typedef struct xfs_growfs_log { + __u32 newblocks; /* new log size, fsblocks */ + __u32 isint; /* 1 if new log is internal */ +} xfs_growfs_log_t; + +typedef struct xfs_growfs_rt { + __u64 newblocks; /* new realtime size, fsblocks */ + __u32 extsize; /* new realtime extent size, fsblocks */ +} xfs_growfs_rt_t; + + +/* + * Structures returned from ioctl XFS_IOC_FSBULKSTAT & XFS_IOC_FSBULKSTAT_SINGLE + */ +typedef struct xfs_bstime { + time_t tv_sec; /* seconds */ + __s32 tv_nsec; /* and nanoseconds */ +} xfs_bstime_t; + +typedef struct xfs_bstat { + __u64 bs_ino; /* inode number */ + __u16 bs_mode; /* type and mode */ + __u16 bs_nlink; /* number of links */ + __u32 bs_uid; /* user id */ + __u32 bs_gid; /* group id */ + __u32 bs_rdev; /* device value */ + __s32 bs_blksize; /* block size */ + __s64 bs_size; /* file size */ + xfs_bstime_t bs_atime; /* access time */ + xfs_bstime_t bs_mtime; /* modify time */ + xfs_bstime_t bs_ctime; /* inode change time */ + int64_t bs_blocks; /* number of blocks */ + __u32 bs_xflags; /* extended flags */ + __s32 bs_extsize; /* extent size */ + __s32 bs_extents; /* number of extents */ + __u32 bs_gen; /* generation count */ + __u16 bs_projid_lo; /* lower part of project id */ +#define bs_projid bs_projid_lo /* (previously just bs_projid) */ + __u16 bs_forkoff; /* inode fork offset in bytes */ + __u16 bs_projid_hi; /* higher part of project id */ + unsigned char bs_pad[10]; /* pad space, unused */ + __u32 bs_dmevmask; /* DMIG event mask */ + __u16 bs_dmstate; /* DMIG state info */ + __u16 bs_aextents; /* attribute number of extents */ +} xfs_bstat_t; + +/* + * Project quota id helpers (previously projid was 16bit only + * and using two 16bit values to hold new 32bit projid was choosen + * to retain compatibility with "old" filesystems). + */ +static inline __uint32_t +bstat_get_projid(struct xfs_bstat *bs) +{ + return (__uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo; +} + +/* + * The user-level BulkStat Request interface structure. + */ +typedef struct xfs_fsop_bulkreq { + __u64 __user *lastip; /* last inode # pointer */ + __s32 icount; /* count of entries in buffer */ + void __user *ubuffer;/* user buffer for inode desc. */ + __s32 __user *ocount; /* output count pointer */ +} xfs_fsop_bulkreq_t; + + +/* + * Structures returned from xfs_inumbers routine (XFS_IOC_FSINUMBERS). + */ +typedef struct xfs_inogrp { + __u64 xi_startino; /* starting inode number */ + __s32 xi_alloccount; /* # bits set in allocmask */ + __u64 xi_allocmask; /* mask of allocated inodes */ +} xfs_inogrp_t; + + +/* + * Error injection. + */ +typedef struct xfs_error_injection { + __s32 fd; + __s32 errtag; +} xfs_error_injection_t; + + +/* + * Speculative preallocation trimming. + */ +#define XFS_EOFBLOCKS_VERSION 1 +struct xfs_fs_eofblocks { + __u32 eof_version; + __u32 eof_flags; + uid_t eof_uid; + gid_t eof_gid; + prid_t eof_prid; + __u32 pad32; + __u64 eof_min_file_size; + __u64 pad64[12]; +}; + +/* eof_flags values */ +#define XFS_EOF_FLAGS_SYNC (1 << 0) /* sync/wait mode scan */ +#define XFS_EOF_FLAGS_UID (1 << 1) /* filter by uid */ +#define XFS_EOF_FLAGS_GID (1 << 2) /* filter by gid */ +#define XFS_EOF_FLAGS_PRID (1 << 3) /* filter by project id */ +#define XFS_EOF_FLAGS_MINFILESIZE (1 << 4) /* filter by min file size */ +#define XFS_EOF_FLAGS_UNION (1 << 5) /* union filter algorithm; + * kernel only, not included in + * valid mask */ +#define XFS_EOF_FLAGS_VALID \ + (XFS_EOF_FLAGS_SYNC | \ + XFS_EOF_FLAGS_UID | \ + XFS_EOF_FLAGS_GID | \ + XFS_EOF_FLAGS_PRID | \ + XFS_EOF_FLAGS_MINFILESIZE) + + +/* + * The user-level Handle Request interface structure. + */ +typedef struct xfs_fsop_handlereq { + __u32 fd; /* fd for FD_TO_HANDLE */ + void __user *path; /* user pathname */ + __u32 oflags; /* open flags */ + void __user *ihandle;/* user supplied handle */ + __u32 ihandlen; /* user supplied length */ + void __user *ohandle;/* user buffer for handle */ + __u32 __user *ohandlen;/* user buffer length */ +} xfs_fsop_handlereq_t; + +/* + * Compound structures for passing args through Handle Request interfaces + * xfs_fssetdm_by_handle, xfs_attrlist_by_handle, xfs_attrmulti_by_handle + * - ioctls: XFS_IOC_FSSETDM_BY_HANDLE, XFS_IOC_ATTRLIST_BY_HANDLE, and + * XFS_IOC_ATTRMULTI_BY_HANDLE + */ + +typedef struct xfs_fsop_setdm_handlereq { + struct xfs_fsop_handlereq hreq; /* handle information */ + struct fsdmidata __user *data; /* DMAPI data */ +} xfs_fsop_setdm_handlereq_t; + +typedef struct xfs_attrlist_cursor { + __u32 opaque[4]; +} xfs_attrlist_cursor_t; + +typedef struct xfs_fsop_attrlist_handlereq { + struct xfs_fsop_handlereq hreq; /* handle interface structure */ + struct xfs_attrlist_cursor pos; /* opaque cookie, list offset */ + __u32 flags; /* which namespace to use */ + __u32 buflen; /* length of buffer supplied */ + void __user *buffer; /* returned names */ +} xfs_fsop_attrlist_handlereq_t; + +typedef struct xfs_attr_multiop { + __u32 am_opcode; +#define ATTR_OP_GET 1 /* return the indicated attr's value */ +#define ATTR_OP_SET 2 /* set/create the indicated attr/value pair */ +#define ATTR_OP_REMOVE 3 /* remove the indicated attr */ + __s32 am_error; + void __user *am_attrname; + void __user *am_attrvalue; + __u32 am_length; + __u32 am_flags; +} xfs_attr_multiop_t; + +typedef struct xfs_fsop_attrmulti_handlereq { + struct xfs_fsop_handlereq hreq; /* handle interface structure */ + __u32 opcount;/* count of following multiop */ + struct xfs_attr_multiop __user *ops; /* attr_multi data */ +} xfs_fsop_attrmulti_handlereq_t; + +/* + * per machine unique filesystem identifier types. + */ +typedef struct { __u32 val[2]; } xfs_fsid_t; /* file system id type */ + +typedef struct xfs_fid { + __u16 fid_len; /* length of remainder */ + __u16 fid_pad; + __u32 fid_gen; /* generation number */ + __u64 fid_ino; /* 64 bits inode number */ +} xfs_fid_t; + +typedef struct xfs_handle { + union { + __s64 align; /* force alignment of ha_fid */ + xfs_fsid_t _ha_fsid; /* unique file system identifier */ + } ha_u; + xfs_fid_t ha_fid; /* file system specific file ID */ +} xfs_handle_t; +#define ha_fsid ha_u._ha_fsid + +#define XFS_HSIZE(handle) (((char *) &(handle).ha_fid.fid_pad \ + - (char *) &(handle)) \ + + (handle).ha_fid.fid_len) + +/* + * Structure passed to XFS_IOC_SWAPEXT + */ +typedef struct xfs_swapext +{ + __int64_t sx_version; /* version */ +#define XFS_SX_VERSION 0 + __int64_t sx_fdtarget; /* fd of target file */ + __int64_t sx_fdtmp; /* fd of tmp file */ + xfs_off_t sx_offset; /* offset into file */ + xfs_off_t sx_length; /* leng from offset */ + char sx_pad[16]; /* pad space, unused */ + xfs_bstat_t sx_stat; /* stat of target b4 copy */ +} xfs_swapext_t; + +/* + * Flags for going down operation + */ +#define XFS_FSOP_GOING_FLAGS_DEFAULT 0x0 /* going down */ +#define XFS_FSOP_GOING_FLAGS_LOGFLUSH 0x1 /* flush log but not data */ +#define XFS_FSOP_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */ + +/* + * ioctl commands that are used by Linux filesystems + */ +#define XFS_IOC_GETXFLAGS FS_IOC_GETFLAGS +#define XFS_IOC_SETXFLAGS FS_IOC_SETFLAGS +#define XFS_IOC_GETVERSION FS_IOC_GETVERSION + +/* + * ioctl commands that replace IRIX fcntl()'s + * For 'documentation' purposed more than anything else, + * the "cmd #" field reflects the IRIX fcntl number. + */ +#define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64) +#define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64) +#define XFS_IOC_DIOINFO _IOR ('X', 30, struct dioattr) +#define XFS_IOC_FSGETXATTR _IOR ('X', 31, struct fsxattr) +#define XFS_IOC_FSSETXATTR _IOW ('X', 32, struct fsxattr) +#define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64) +#define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64) +#define XFS_IOC_GETBMAP _IOWR('X', 38, struct getbmap) +#define XFS_IOC_FSSETDM _IOW ('X', 39, struct fsdmidata) +#define XFS_IOC_RESVSP _IOW ('X', 40, struct xfs_flock64) +#define XFS_IOC_UNRESVSP _IOW ('X', 41, struct xfs_flock64) +#define XFS_IOC_RESVSP64 _IOW ('X', 42, struct xfs_flock64) +#define XFS_IOC_UNRESVSP64 _IOW ('X', 43, struct xfs_flock64) +#define XFS_IOC_GETBMAPA _IOWR('X', 44, struct getbmap) +#define XFS_IOC_FSGETXATTRA _IOR ('X', 45, struct fsxattr) +/* XFS_IOC_SETBIOSIZE ---- deprecated 46 */ +/* XFS_IOC_GETBIOSIZE ---- deprecated 47 */ +#define XFS_IOC_GETBMAPX _IOWR('X', 56, struct getbmap) +#define XFS_IOC_ZERO_RANGE _IOW ('X', 57, struct xfs_flock64) +#define XFS_IOC_FREE_EOFBLOCKS _IOR ('X', 58, struct xfs_fs_eofblocks) + +/* + * ioctl commands that replace IRIX syssgi()'s + */ +#define XFS_IOC_FSGEOMETRY_V1 _IOR ('X', 100, struct xfs_fsop_geom_v1) +#define XFS_IOC_FSBULKSTAT _IOWR('X', 101, struct xfs_fsop_bulkreq) +#define XFS_IOC_FSBULKSTAT_SINGLE _IOWR('X', 102, struct xfs_fsop_bulkreq) +#define XFS_IOC_FSINUMBERS _IOWR('X', 103, struct xfs_fsop_bulkreq) +#define XFS_IOC_PATH_TO_FSHANDLE _IOWR('X', 104, struct xfs_fsop_handlereq) +#define XFS_IOC_PATH_TO_HANDLE _IOWR('X', 105, struct xfs_fsop_handlereq) +#define XFS_IOC_FD_TO_HANDLE _IOWR('X', 106, struct xfs_fsop_handlereq) +#define XFS_IOC_OPEN_BY_HANDLE _IOWR('X', 107, struct xfs_fsop_handlereq) +#define XFS_IOC_READLINK_BY_HANDLE _IOWR('X', 108, struct xfs_fsop_handlereq) +#define XFS_IOC_SWAPEXT _IOWR('X', 109, struct xfs_swapext) +#define XFS_IOC_FSGROWFSDATA _IOW ('X', 110, struct xfs_growfs_data) +#define XFS_IOC_FSGROWFSLOG _IOW ('X', 111, struct xfs_growfs_log) +#define XFS_IOC_FSGROWFSRT _IOW ('X', 112, struct xfs_growfs_rt) +#define XFS_IOC_FSCOUNTS _IOR ('X', 113, struct xfs_fsop_counts) +#define XFS_IOC_SET_RESBLKS _IOWR('X', 114, struct xfs_fsop_resblks) +#define XFS_IOC_GET_RESBLKS _IOR ('X', 115, struct xfs_fsop_resblks) +#define XFS_IOC_ERROR_INJECTION _IOW ('X', 116, struct xfs_error_injection) +#define XFS_IOC_ERROR_CLEARALL _IOW ('X', 117, struct xfs_error_injection) +/* XFS_IOC_ATTRCTL_BY_HANDLE -- deprecated 118 */ + +/* XFS_IOC_FREEZE -- FIFREEZE 119 */ +/* XFS_IOC_THAW -- FITHAW 120 */ +#ifndef FIFREEZE +#define XFS_IOC_FREEZE _IOWR('X', 119, int) +#define XFS_IOC_THAW _IOWR('X', 120, int) +#endif + +#define XFS_IOC_FSSETDM_BY_HANDLE _IOW ('X', 121, struct xfs_fsop_setdm_handlereq) +#define XFS_IOC_ATTRLIST_BY_HANDLE _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq) +#define XFS_IOC_ATTRMULTI_BY_HANDLE _IOW ('X', 123, struct xfs_fsop_attrmulti_handlereq) +#define XFS_IOC_FSGEOMETRY _IOR ('X', 124, struct xfs_fsop_geom) +#define XFS_IOC_GOINGDOWN _IOR ('X', 125, __uint32_t) +/* XFS_IOC_GETFSUUID ---------- deprecated 140 */ + + +#ifndef HAVE_BBMACROS +/* + * Block I/O parameterization. A basic block (BB) is the lowest size of + * filesystem allocation, and must equal 512. Length units given to bio + * routines are in BB's. + */ +#define BBSHIFT 9 +#define BBSIZE (1<> BBSHIFT) +#define BTOBBT(bytes) ((__u64)(bytes) >> BBSHIFT) +#define BBTOB(bbs) ((bbs) << BBSHIFT) +#endif + +#endif /* __XFS_FS_H__ */ diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h deleted file mode 100644 index 18dc721ca19f..000000000000 --- a/fs/xfs/xfs_fs.h +++ /dev/null @@ -1,576 +0,0 @@ -/* - * Copyright (c) 1995-2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public License - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_FS_H__ -#define __XFS_FS_H__ - -/* - * SGI's XFS filesystem's major stuff (constants, structures) - */ - -/* - * Direct I/O attribute record used with XFS_IOC_DIOINFO - * d_miniosz is the min xfer size, xfer size multiple and file seek offset - * alignment. - */ -#ifndef HAVE_DIOATTR -struct dioattr { - __u32 d_mem; /* data buffer memory alignment */ - __u32 d_miniosz; /* min xfer size */ - __u32 d_maxiosz; /* max xfer size */ -}; -#endif - -/* - * Structure for XFS_IOC_FSGETXATTR[A] and XFS_IOC_FSSETXATTR. - */ -#ifndef HAVE_FSXATTR -struct fsxattr { - __u32 fsx_xflags; /* xflags field value (get/set) */ - __u32 fsx_extsize; /* extsize field value (get/set)*/ - __u32 fsx_nextents; /* nextents field value (get) */ - __u32 fsx_projid; /* project identifier (get/set) */ - unsigned char fsx_pad[12]; -}; -#endif - -/* - * Flags for the bs_xflags/fsx_xflags field - * There should be a one-to-one correspondence between these flags and the - * XFS_DIFLAG_s. - */ -#define XFS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ -#define XFS_XFLAG_PREALLOC 0x00000002 /* preallocated file extents */ -#define XFS_XFLAG_IMMUTABLE 0x00000008 /* file cannot be modified */ -#define XFS_XFLAG_APPEND 0x00000010 /* all writes append */ -#define XFS_XFLAG_SYNC 0x00000020 /* all writes synchronous */ -#define XFS_XFLAG_NOATIME 0x00000040 /* do not update access time */ -#define XFS_XFLAG_NODUMP 0x00000080 /* do not include in backups */ -#define XFS_XFLAG_RTINHERIT 0x00000100 /* create with rt bit set */ -#define XFS_XFLAG_PROJINHERIT 0x00000200 /* create with parents projid */ -#define XFS_XFLAG_NOSYMLINKS 0x00000400 /* disallow symlink creation */ -#define XFS_XFLAG_EXTSIZE 0x00000800 /* extent size allocator hint */ -#define XFS_XFLAG_EXTSZINHERIT 0x00001000 /* inherit inode extent size */ -#define XFS_XFLAG_NODEFRAG 0x00002000 /* do not defragment */ -#define XFS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ -#define XFS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */ - -/* - * Structure for XFS_IOC_GETBMAP. - * On input, fill in bmv_offset and bmv_length of the first structure - * to indicate the area of interest in the file, and bmv_entries with - * the number of array elements given back. The first structure is - * updated on return to give the offset and length for the next call. - */ -#ifndef HAVE_GETBMAP -struct getbmap { - __s64 bmv_offset; /* file offset of segment in blocks */ - __s64 bmv_block; /* starting block (64-bit daddr_t) */ - __s64 bmv_length; /* length of segment, blocks */ - __s32 bmv_count; /* # of entries in array incl. 1st */ - __s32 bmv_entries; /* # of entries filled in (output) */ -}; -#endif - -/* - * Structure for XFS_IOC_GETBMAPX. Fields bmv_offset through bmv_entries - * are used exactly as in the getbmap structure. The getbmapx structure - * has additional bmv_iflags and bmv_oflags fields. The bmv_iflags field - * is only used for the first structure. It contains input flags - * specifying XFS_IOC_GETBMAPX actions. The bmv_oflags field is filled - * in by the XFS_IOC_GETBMAPX command for each returned structure after - * the first. - */ -#ifndef HAVE_GETBMAPX -struct getbmapx { - __s64 bmv_offset; /* file offset of segment in blocks */ - __s64 bmv_block; /* starting block (64-bit daddr_t) */ - __s64 bmv_length; /* length of segment, blocks */ - __s32 bmv_count; /* # of entries in array incl. 1st */ - __s32 bmv_entries; /* # of entries filled in (output). */ - __s32 bmv_iflags; /* input flags (1st structure) */ - __s32 bmv_oflags; /* output flags (after 1st structure)*/ - __s32 bmv_unused1; /* future use */ - __s32 bmv_unused2; /* future use */ -}; -#endif - -/* bmv_iflags values - set by XFS_IOC_GETBMAPX caller. */ -#define BMV_IF_ATTRFORK 0x1 /* return attr fork rather than data */ -#define BMV_IF_NO_DMAPI_READ 0x2 /* Do not generate DMAPI read event */ -#define BMV_IF_PREALLOC 0x4 /* rtn status BMV_OF_PREALLOC if req */ -#define BMV_IF_DELALLOC 0x8 /* rtn status BMV_OF_DELALLOC if req */ -#define BMV_IF_NO_HOLES 0x10 /* Do not return holes */ -#define BMV_IF_VALID \ - (BMV_IF_ATTRFORK|BMV_IF_NO_DMAPI_READ|BMV_IF_PREALLOC| \ - BMV_IF_DELALLOC|BMV_IF_NO_HOLES) - -/* bmv_oflags values - returned for each non-header segment */ -#define BMV_OF_PREALLOC 0x1 /* segment = unwritten pre-allocation */ -#define BMV_OF_DELALLOC 0x2 /* segment = delayed allocation */ -#define BMV_OF_LAST 0x4 /* segment is the last in the file */ - -/* - * Structure for XFS_IOC_FSSETDM. - * For use by backup and restore programs to set the XFS on-disk inode - * fields di_dmevmask and di_dmstate. These must be set to exactly and - * only values previously obtained via xfs_bulkstat! (Specifically the - * xfs_bstat_t fields bs_dmevmask and bs_dmstate.) - */ -#ifndef HAVE_FSDMIDATA -struct fsdmidata { - __u32 fsd_dmevmask; /* corresponds to di_dmevmask */ - __u16 fsd_padding; - __u16 fsd_dmstate; /* corresponds to di_dmstate */ -}; -#endif - -/* - * File segment locking set data type for 64 bit access. - * Also used for all the RESV/FREE interfaces. - */ -typedef struct xfs_flock64 { - __s16 l_type; - __s16 l_whence; - __s64 l_start; - __s64 l_len; /* len == 0 means until end of file */ - __s32 l_sysid; - __u32 l_pid; - __s32 l_pad[4]; /* reserve area */ -} xfs_flock64_t; - -/* - * Output for XFS_IOC_FSGEOMETRY_V1 - */ -typedef struct xfs_fsop_geom_v1 { - __u32 blocksize; /* filesystem (data) block size */ - __u32 rtextsize; /* realtime extent size */ - __u32 agblocks; /* fsblocks in an AG */ - __u32 agcount; /* number of allocation groups */ - __u32 logblocks; /* fsblocks in the log */ - __u32 sectsize; /* (data) sector size, bytes */ - __u32 inodesize; /* inode size in bytes */ - __u32 imaxpct; /* max allowed inode space(%) */ - __u64 datablocks; /* fsblocks in data subvolume */ - __u64 rtblocks; /* fsblocks in realtime subvol */ - __u64 rtextents; /* rt extents in realtime subvol*/ - __u64 logstart; /* starting fsblock of the log */ - unsigned char uuid[16]; /* unique id of the filesystem */ - __u32 sunit; /* stripe unit, fsblocks */ - __u32 swidth; /* stripe width, fsblocks */ - __s32 version; /* structure version */ - __u32 flags; /* superblock version flags */ - __u32 logsectsize; /* log sector size, bytes */ - __u32 rtsectsize; /* realtime sector size, bytes */ - __u32 dirblocksize; /* directory block size, bytes */ -} xfs_fsop_geom_v1_t; - -/* - * Output for XFS_IOC_FSGEOMETRY - */ -typedef struct xfs_fsop_geom { - __u32 blocksize; /* filesystem (data) block size */ - __u32 rtextsize; /* realtime extent size */ - __u32 agblocks; /* fsblocks in an AG */ - __u32 agcount; /* number of allocation groups */ - __u32 logblocks; /* fsblocks in the log */ - __u32 sectsize; /* (data) sector size, bytes */ - __u32 inodesize; /* inode size in bytes */ - __u32 imaxpct; /* max allowed inode space(%) */ - __u64 datablocks; /* fsblocks in data subvolume */ - __u64 rtblocks; /* fsblocks in realtime subvol */ - __u64 rtextents; /* rt extents in realtime subvol*/ - __u64 logstart; /* starting fsblock of the log */ - unsigned char uuid[16]; /* unique id of the filesystem */ - __u32 sunit; /* stripe unit, fsblocks */ - __u32 swidth; /* stripe width, fsblocks */ - __s32 version; /* structure version */ - __u32 flags; /* superblock version flags */ - __u32 logsectsize; /* log sector size, bytes */ - __u32 rtsectsize; /* realtime sector size, bytes */ - __u32 dirblocksize; /* directory block size, bytes */ - __u32 logsunit; /* log stripe unit, bytes */ -} xfs_fsop_geom_t; - -/* Output for XFS_FS_COUNTS */ -typedef struct xfs_fsop_counts { - __u64 freedata; /* free data section blocks */ - __u64 freertx; /* free rt extents */ - __u64 freeino; /* free inodes */ - __u64 allocino; /* total allocated inodes */ -} xfs_fsop_counts_t; - -/* Input/Output for XFS_GET_RESBLKS and XFS_SET_RESBLKS */ -typedef struct xfs_fsop_resblks { - __u64 resblks; - __u64 resblks_avail; -} xfs_fsop_resblks_t; - -#define XFS_FSOP_GEOM_VERSION 0 - -#define XFS_FSOP_GEOM_FLAGS_ATTR 0x0001 /* attributes in use */ -#define XFS_FSOP_GEOM_FLAGS_NLINK 0x0002 /* 32-bit nlink values */ -#define XFS_FSOP_GEOM_FLAGS_QUOTA 0x0004 /* quotas enabled */ -#define XFS_FSOP_GEOM_FLAGS_IALIGN 0x0008 /* inode alignment */ -#define XFS_FSOP_GEOM_FLAGS_DALIGN 0x0010 /* large data alignment */ -#define XFS_FSOP_GEOM_FLAGS_SHARED 0x0020 /* read-only shared */ -#define XFS_FSOP_GEOM_FLAGS_EXTFLG 0x0040 /* special extent flag */ -#define XFS_FSOP_GEOM_FLAGS_DIRV2 0x0080 /* directory version 2 */ -#define XFS_FSOP_GEOM_FLAGS_LOGV2 0x0100 /* log format version 2 */ -#define XFS_FSOP_GEOM_FLAGS_SECTOR 0x0200 /* sector sizes >1BB */ -#define XFS_FSOP_GEOM_FLAGS_ATTR2 0x0400 /* inline attributes rework */ -#define XFS_FSOP_GEOM_FLAGS_PROJID32 0x0800 /* 32-bit project IDs */ -#define XFS_FSOP_GEOM_FLAGS_DIRV2CI 0x1000 /* ASCII only CI names */ -#define XFS_FSOP_GEOM_FLAGS_LAZYSB 0x4000 /* lazy superblock counters */ -#define XFS_FSOP_GEOM_FLAGS_V5SB 0x8000 /* version 5 superblock */ -#define XFS_FSOP_GEOM_FLAGS_FTYPE 0x10000 /* inode directory types */ -#define XFS_FSOP_GEOM_FLAGS_FINOBT 0x20000 /* free inode btree */ - -/* - * Minimum and maximum sizes need for growth checks. - * - * Block counts are in units of filesystem blocks, not basic blocks. - */ -#define XFS_MIN_AG_BLOCKS 64 -#define XFS_MIN_LOG_BLOCKS 512ULL -#define XFS_MAX_LOG_BLOCKS (1024 * 1024ULL) -#define XFS_MIN_LOG_BYTES (10 * 1024 * 1024ULL) - -/* keep the maximum size under 2^31 by a small amount */ -#define XFS_MAX_LOG_BYTES \ - ((2 * 1024 * 1024 * 1024ULL) - XFS_MIN_LOG_BYTES) - -/* Used for sanity checks on superblock */ -#define XFS_MAX_DBLOCKS(s) ((xfs_rfsblock_t)(s)->sb_agcount * (s)->sb_agblocks) -#define XFS_MIN_DBLOCKS(s) ((xfs_rfsblock_t)((s)->sb_agcount - 1) * \ - (s)->sb_agblocks + XFS_MIN_AG_BLOCKS) - -/* - * Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT - */ -typedef struct xfs_growfs_data { - __u64 newblocks; /* new data subvol size, fsblocks */ - __u32 imaxpct; /* new inode space percentage limit */ -} xfs_growfs_data_t; - -typedef struct xfs_growfs_log { - __u32 newblocks; /* new log size, fsblocks */ - __u32 isint; /* 1 if new log is internal */ -} xfs_growfs_log_t; - -typedef struct xfs_growfs_rt { - __u64 newblocks; /* new realtime size, fsblocks */ - __u32 extsize; /* new realtime extent size, fsblocks */ -} xfs_growfs_rt_t; - - -/* - * Structures returned from ioctl XFS_IOC_FSBULKSTAT & XFS_IOC_FSBULKSTAT_SINGLE - */ -typedef struct xfs_bstime { - time_t tv_sec; /* seconds */ - __s32 tv_nsec; /* and nanoseconds */ -} xfs_bstime_t; - -typedef struct xfs_bstat { - __u64 bs_ino; /* inode number */ - __u16 bs_mode; /* type and mode */ - __u16 bs_nlink; /* number of links */ - __u32 bs_uid; /* user id */ - __u32 bs_gid; /* group id */ - __u32 bs_rdev; /* device value */ - __s32 bs_blksize; /* block size */ - __s64 bs_size; /* file size */ - xfs_bstime_t bs_atime; /* access time */ - xfs_bstime_t bs_mtime; /* modify time */ - xfs_bstime_t bs_ctime; /* inode change time */ - int64_t bs_blocks; /* number of blocks */ - __u32 bs_xflags; /* extended flags */ - __s32 bs_extsize; /* extent size */ - __s32 bs_extents; /* number of extents */ - __u32 bs_gen; /* generation count */ - __u16 bs_projid_lo; /* lower part of project id */ -#define bs_projid bs_projid_lo /* (previously just bs_projid) */ - __u16 bs_forkoff; /* inode fork offset in bytes */ - __u16 bs_projid_hi; /* higher part of project id */ - unsigned char bs_pad[10]; /* pad space, unused */ - __u32 bs_dmevmask; /* DMIG event mask */ - __u16 bs_dmstate; /* DMIG state info */ - __u16 bs_aextents; /* attribute number of extents */ -} xfs_bstat_t; - -/* - * Project quota id helpers (previously projid was 16bit only - * and using two 16bit values to hold new 32bit projid was choosen - * to retain compatibility with "old" filesystems). - */ -static inline __uint32_t -bstat_get_projid(struct xfs_bstat *bs) -{ - return (__uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo; -} - -/* - * The user-level BulkStat Request interface structure. - */ -typedef struct xfs_fsop_bulkreq { - __u64 __user *lastip; /* last inode # pointer */ - __s32 icount; /* count of entries in buffer */ - void __user *ubuffer;/* user buffer for inode desc. */ - __s32 __user *ocount; /* output count pointer */ -} xfs_fsop_bulkreq_t; - - -/* - * Structures returned from xfs_inumbers routine (XFS_IOC_FSINUMBERS). - */ -typedef struct xfs_inogrp { - __u64 xi_startino; /* starting inode number */ - __s32 xi_alloccount; /* # bits set in allocmask */ - __u64 xi_allocmask; /* mask of allocated inodes */ -} xfs_inogrp_t; - - -/* - * Error injection. - */ -typedef struct xfs_error_injection { - __s32 fd; - __s32 errtag; -} xfs_error_injection_t; - - -/* - * Speculative preallocation trimming. - */ -#define XFS_EOFBLOCKS_VERSION 1 -struct xfs_fs_eofblocks { - __u32 eof_version; - __u32 eof_flags; - uid_t eof_uid; - gid_t eof_gid; - prid_t eof_prid; - __u32 pad32; - __u64 eof_min_file_size; - __u64 pad64[12]; -}; - -/* eof_flags values */ -#define XFS_EOF_FLAGS_SYNC (1 << 0) /* sync/wait mode scan */ -#define XFS_EOF_FLAGS_UID (1 << 1) /* filter by uid */ -#define XFS_EOF_FLAGS_GID (1 << 2) /* filter by gid */ -#define XFS_EOF_FLAGS_PRID (1 << 3) /* filter by project id */ -#define XFS_EOF_FLAGS_MINFILESIZE (1 << 4) /* filter by min file size */ -#define XFS_EOF_FLAGS_UNION (1 << 5) /* union filter algorithm; - * kernel only, not included in - * valid mask */ -#define XFS_EOF_FLAGS_VALID \ - (XFS_EOF_FLAGS_SYNC | \ - XFS_EOF_FLAGS_UID | \ - XFS_EOF_FLAGS_GID | \ - XFS_EOF_FLAGS_PRID | \ - XFS_EOF_FLAGS_MINFILESIZE) - - -/* - * The user-level Handle Request interface structure. - */ -typedef struct xfs_fsop_handlereq { - __u32 fd; /* fd for FD_TO_HANDLE */ - void __user *path; /* user pathname */ - __u32 oflags; /* open flags */ - void __user *ihandle;/* user supplied handle */ - __u32 ihandlen; /* user supplied length */ - void __user *ohandle;/* user buffer for handle */ - __u32 __user *ohandlen;/* user buffer length */ -} xfs_fsop_handlereq_t; - -/* - * Compound structures for passing args through Handle Request interfaces - * xfs_fssetdm_by_handle, xfs_attrlist_by_handle, xfs_attrmulti_by_handle - * - ioctls: XFS_IOC_FSSETDM_BY_HANDLE, XFS_IOC_ATTRLIST_BY_HANDLE, and - * XFS_IOC_ATTRMULTI_BY_HANDLE - */ - -typedef struct xfs_fsop_setdm_handlereq { - struct xfs_fsop_handlereq hreq; /* handle information */ - struct fsdmidata __user *data; /* DMAPI data */ -} xfs_fsop_setdm_handlereq_t; - -typedef struct xfs_attrlist_cursor { - __u32 opaque[4]; -} xfs_attrlist_cursor_t; - -typedef struct xfs_fsop_attrlist_handlereq { - struct xfs_fsop_handlereq hreq; /* handle interface structure */ - struct xfs_attrlist_cursor pos; /* opaque cookie, list offset */ - __u32 flags; /* which namespace to use */ - __u32 buflen; /* length of buffer supplied */ - void __user *buffer; /* returned names */ -} xfs_fsop_attrlist_handlereq_t; - -typedef struct xfs_attr_multiop { - __u32 am_opcode; -#define ATTR_OP_GET 1 /* return the indicated attr's value */ -#define ATTR_OP_SET 2 /* set/create the indicated attr/value pair */ -#define ATTR_OP_REMOVE 3 /* remove the indicated attr */ - __s32 am_error; - void __user *am_attrname; - void __user *am_attrvalue; - __u32 am_length; - __u32 am_flags; -} xfs_attr_multiop_t; - -typedef struct xfs_fsop_attrmulti_handlereq { - struct xfs_fsop_handlereq hreq; /* handle interface structure */ - __u32 opcount;/* count of following multiop */ - struct xfs_attr_multiop __user *ops; /* attr_multi data */ -} xfs_fsop_attrmulti_handlereq_t; - -/* - * per machine unique filesystem identifier types. - */ -typedef struct { __u32 val[2]; } xfs_fsid_t; /* file system id type */ - -typedef struct xfs_fid { - __u16 fid_len; /* length of remainder */ - __u16 fid_pad; - __u32 fid_gen; /* generation number */ - __u64 fid_ino; /* 64 bits inode number */ -} xfs_fid_t; - -typedef struct xfs_handle { - union { - __s64 align; /* force alignment of ha_fid */ - xfs_fsid_t _ha_fsid; /* unique file system identifier */ - } ha_u; - xfs_fid_t ha_fid; /* file system specific file ID */ -} xfs_handle_t; -#define ha_fsid ha_u._ha_fsid - -#define XFS_HSIZE(handle) (((char *) &(handle).ha_fid.fid_pad \ - - (char *) &(handle)) \ - + (handle).ha_fid.fid_len) - -/* - * Structure passed to XFS_IOC_SWAPEXT - */ -typedef struct xfs_swapext -{ - __int64_t sx_version; /* version */ -#define XFS_SX_VERSION 0 - __int64_t sx_fdtarget; /* fd of target file */ - __int64_t sx_fdtmp; /* fd of tmp file */ - xfs_off_t sx_offset; /* offset into file */ - xfs_off_t sx_length; /* leng from offset */ - char sx_pad[16]; /* pad space, unused */ - xfs_bstat_t sx_stat; /* stat of target b4 copy */ -} xfs_swapext_t; - -/* - * Flags for going down operation - */ -#define XFS_FSOP_GOING_FLAGS_DEFAULT 0x0 /* going down */ -#define XFS_FSOP_GOING_FLAGS_LOGFLUSH 0x1 /* flush log but not data */ -#define XFS_FSOP_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */ - -/* - * ioctl commands that are used by Linux filesystems - */ -#define XFS_IOC_GETXFLAGS FS_IOC_GETFLAGS -#define XFS_IOC_SETXFLAGS FS_IOC_SETFLAGS -#define XFS_IOC_GETVERSION FS_IOC_GETVERSION - -/* - * ioctl commands that replace IRIX fcntl()'s - * For 'documentation' purposed more than anything else, - * the "cmd #" field reflects the IRIX fcntl number. - */ -#define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64) -#define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64) -#define XFS_IOC_DIOINFO _IOR ('X', 30, struct dioattr) -#define XFS_IOC_FSGETXATTR _IOR ('X', 31, struct fsxattr) -#define XFS_IOC_FSSETXATTR _IOW ('X', 32, struct fsxattr) -#define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64) -#define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64) -#define XFS_IOC_GETBMAP _IOWR('X', 38, struct getbmap) -#define XFS_IOC_FSSETDM _IOW ('X', 39, struct fsdmidata) -#define XFS_IOC_RESVSP _IOW ('X', 40, struct xfs_flock64) -#define XFS_IOC_UNRESVSP _IOW ('X', 41, struct xfs_flock64) -#define XFS_IOC_RESVSP64 _IOW ('X', 42, struct xfs_flock64) -#define XFS_IOC_UNRESVSP64 _IOW ('X', 43, struct xfs_flock64) -#define XFS_IOC_GETBMAPA _IOWR('X', 44, struct getbmap) -#define XFS_IOC_FSGETXATTRA _IOR ('X', 45, struct fsxattr) -/* XFS_IOC_SETBIOSIZE ---- deprecated 46 */ -/* XFS_IOC_GETBIOSIZE ---- deprecated 47 */ -#define XFS_IOC_GETBMAPX _IOWR('X', 56, struct getbmap) -#define XFS_IOC_ZERO_RANGE _IOW ('X', 57, struct xfs_flock64) -#define XFS_IOC_FREE_EOFBLOCKS _IOR ('X', 58, struct xfs_fs_eofblocks) - -/* - * ioctl commands that replace IRIX syssgi()'s - */ -#define XFS_IOC_FSGEOMETRY_V1 _IOR ('X', 100, struct xfs_fsop_geom_v1) -#define XFS_IOC_FSBULKSTAT _IOWR('X', 101, struct xfs_fsop_bulkreq) -#define XFS_IOC_FSBULKSTAT_SINGLE _IOWR('X', 102, struct xfs_fsop_bulkreq) -#define XFS_IOC_FSINUMBERS _IOWR('X', 103, struct xfs_fsop_bulkreq) -#define XFS_IOC_PATH_TO_FSHANDLE _IOWR('X', 104, struct xfs_fsop_handlereq) -#define XFS_IOC_PATH_TO_HANDLE _IOWR('X', 105, struct xfs_fsop_handlereq) -#define XFS_IOC_FD_TO_HANDLE _IOWR('X', 106, struct xfs_fsop_handlereq) -#define XFS_IOC_OPEN_BY_HANDLE _IOWR('X', 107, struct xfs_fsop_handlereq) -#define XFS_IOC_READLINK_BY_HANDLE _IOWR('X', 108, struct xfs_fsop_handlereq) -#define XFS_IOC_SWAPEXT _IOWR('X', 109, struct xfs_swapext) -#define XFS_IOC_FSGROWFSDATA _IOW ('X', 110, struct xfs_growfs_data) -#define XFS_IOC_FSGROWFSLOG _IOW ('X', 111, struct xfs_growfs_log) -#define XFS_IOC_FSGROWFSRT _IOW ('X', 112, struct xfs_growfs_rt) -#define XFS_IOC_FSCOUNTS _IOR ('X', 113, struct xfs_fsop_counts) -#define XFS_IOC_SET_RESBLKS _IOWR('X', 114, struct xfs_fsop_resblks) -#define XFS_IOC_GET_RESBLKS _IOR ('X', 115, struct xfs_fsop_resblks) -#define XFS_IOC_ERROR_INJECTION _IOW ('X', 116, struct xfs_error_injection) -#define XFS_IOC_ERROR_CLEARALL _IOW ('X', 117, struct xfs_error_injection) -/* XFS_IOC_ATTRCTL_BY_HANDLE -- deprecated 118 */ - -/* XFS_IOC_FREEZE -- FIFREEZE 119 */ -/* XFS_IOC_THAW -- FITHAW 120 */ -#ifndef FIFREEZE -#define XFS_IOC_FREEZE _IOWR('X', 119, int) -#define XFS_IOC_THAW _IOWR('X', 120, int) -#endif - -#define XFS_IOC_FSSETDM_BY_HANDLE _IOW ('X', 121, struct xfs_fsop_setdm_handlereq) -#define XFS_IOC_ATTRLIST_BY_HANDLE _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq) -#define XFS_IOC_ATTRMULTI_BY_HANDLE _IOW ('X', 123, struct xfs_fsop_attrmulti_handlereq) -#define XFS_IOC_FSGEOMETRY _IOR ('X', 124, struct xfs_fsop_geom) -#define XFS_IOC_GOINGDOWN _IOR ('X', 125, __uint32_t) -/* XFS_IOC_GETFSUUID ---------- deprecated 140 */ - - -#ifndef HAVE_BBMACROS -/* - * Block I/O parameterization. A basic block (BB) is the lowest size of - * filesystem allocation, and must equal 512. Length units given to bio - * routines are in BB's. - */ -#define BBSHIFT 9 -#define BBSIZE (1<> BBSHIFT) -#define BTOBBT(bytes) ((__u64)(bytes) >> BBSHIFT) -#define BBTOB(bbs) ((bbs) << BBSHIFT) -#endif - -#endif /* __XFS_FS_H__ */ -- cgit v1.2.3 From 5ebdc213ac02877e23fe7594d4b92b120488aac9 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 9 Jan 2015 10:46:31 +1100 Subject: xfs: move xfs_types.h to libxfs The types used by the core XFS code are common between kernel and userspace. xfs_types.h is duplicated in both kernel and userspace, so move it to libxfs along with all the other shared code. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_types.h | 137 ++++++++++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_types.h | 137 ---------------------------------------------- 2 files changed, 137 insertions(+), 137 deletions(-) create mode 100644 fs/xfs/libxfs/xfs_types.h delete mode 100644 fs/xfs/xfs_types.h (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h new file mode 100644 index 000000000000..b79dc66b2ecd --- /dev/null +++ b/fs/xfs/libxfs/xfs_types.h @@ -0,0 +1,137 @@ +/* + * Copyright (c) 2000-2005 Silicon Graphics, Inc. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write the Free Software Foundation, + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ +#ifndef __XFS_TYPES_H__ +#define __XFS_TYPES_H__ + +typedef __uint32_t prid_t; /* project ID */ + +typedef __uint32_t xfs_agblock_t; /* blockno in alloc. group */ +typedef __uint32_t xfs_agino_t; /* inode # within allocation grp */ +typedef __uint32_t xfs_extlen_t; /* extent length in blocks */ +typedef __uint32_t xfs_agnumber_t; /* allocation group number */ +typedef __int32_t xfs_extnum_t; /* # of extents in a file */ +typedef __int16_t xfs_aextnum_t; /* # extents in an attribute fork */ +typedef __int64_t xfs_fsize_t; /* bytes in a file */ +typedef __uint64_t xfs_ufsize_t; /* unsigned bytes in a file */ + +typedef __int32_t xfs_suminfo_t; /* type of bitmap summary info */ +typedef __int32_t xfs_rtword_t; /* word type for bitmap manipulations */ + +typedef __int64_t xfs_lsn_t; /* log sequence number */ +typedef __int32_t xfs_tid_t; /* transaction identifier */ + +typedef __uint32_t xfs_dablk_t; /* dir/attr block number (in file) */ +typedef __uint32_t xfs_dahash_t; /* dir/attr hash value */ + +typedef __uint64_t xfs_fsblock_t; /* blockno in filesystem (agno|agbno) */ +typedef __uint64_t xfs_rfsblock_t; /* blockno in filesystem (raw) */ +typedef __uint64_t xfs_rtblock_t; /* extent (block) in realtime area */ +typedef __uint64_t xfs_fileoff_t; /* block number in a file */ +typedef __uint64_t xfs_filblks_t; /* number of blocks in a file */ + +typedef __int64_t xfs_srtblock_t; /* signed version of xfs_rtblock_t */ +typedef __int64_t xfs_sfiloff_t; /* signed block number in a file */ + +/* + * Null values for the types. + */ +#define NULLFSBLOCK ((xfs_fsblock_t)-1) +#define NULLRFSBLOCK ((xfs_rfsblock_t)-1) +#define NULLRTBLOCK ((xfs_rtblock_t)-1) +#define NULLFILEOFF ((xfs_fileoff_t)-1) + +#define NULLAGBLOCK ((xfs_agblock_t)-1) +#define NULLAGNUMBER ((xfs_agnumber_t)-1) +#define NULLEXTNUM ((xfs_extnum_t)-1) + +#define NULLCOMMITLSN ((xfs_lsn_t)-1) + +#define NULLFSINO ((xfs_ino_t)-1) +#define NULLAGINO ((xfs_agino_t)-1) + +/* + * Max values for extlen, extnum, aextnum. + */ +#define MAXEXTLEN ((xfs_extlen_t)0x001fffff) /* 21 bits */ +#define MAXEXTNUM ((xfs_extnum_t)0x7fffffff) /* signed int */ +#define MAXAEXTNUM ((xfs_aextnum_t)0x7fff) /* signed short */ + +/* + * Minimum and maximum blocksize and sectorsize. + * The blocksize upper limit is pretty much arbitrary. + * The sectorsize upper limit is due to sizeof(sb_sectsize). + */ +#define XFS_MIN_BLOCKSIZE_LOG 9 /* i.e. 512 bytes */ +#define XFS_MAX_BLOCKSIZE_LOG 16 /* i.e. 65536 bytes */ +#define XFS_MIN_BLOCKSIZE (1 << XFS_MIN_BLOCKSIZE_LOG) +#define XFS_MAX_BLOCKSIZE (1 << XFS_MAX_BLOCKSIZE_LOG) +#define XFS_MIN_SECTORSIZE_LOG 9 /* i.e. 512 bytes */ +#define XFS_MAX_SECTORSIZE_LOG 15 /* i.e. 32768 bytes */ +#define XFS_MIN_SECTORSIZE (1 << XFS_MIN_SECTORSIZE_LOG) +#define XFS_MAX_SECTORSIZE (1 << XFS_MAX_SECTORSIZE_LOG) + +/* + * Inode fork identifiers. + */ +#define XFS_DATA_FORK 0 +#define XFS_ATTR_FORK 1 + +/* + * Min numbers of data/attr fork btree root pointers. + */ +#define MINDBTPTRS 3 +#define MINABTPTRS 2 + +/* + * MAXNAMELEN is the length (including the terminating null) of + * the longest permissible file (component) name. + */ +#define MAXNAMELEN 256 + +typedef enum { + XFS_LOOKUP_EQi, XFS_LOOKUP_LEi, XFS_LOOKUP_GEi +} xfs_lookup_t; + +typedef enum { + XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_BMAPi, XFS_BTNUM_INOi, + XFS_BTNUM_FINOi, XFS_BTNUM_MAX +} xfs_btnum_t; + +struct xfs_name { + const unsigned char *name; + int len; + int type; +}; + +/* + * uid_t and gid_t are hard-coded to 32 bits in the inode. + * Hence, an 'id' in a dquot is 32 bits.. + */ +typedef __uint32_t xfs_dqid_t; + +/* + * Constants for bit manipulations. + */ +#define XFS_NBBYLOG 3 /* log2(NBBY) */ +#define XFS_WORDLOG 2 /* log2(sizeof(xfs_rtword_t)) */ +#define XFS_NBWORDLOG (XFS_NBBYLOG + XFS_WORDLOG) +#define XFS_NBWORD (1 << XFS_NBWORDLOG) +#define XFS_WORDMASK ((1 << XFS_WORDLOG) - 1) + + +#endif /* __XFS_TYPES_H__ */ diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h deleted file mode 100644 index b79dc66b2ecd..000000000000 --- a/fs/xfs/xfs_types.h +++ /dev/null @@ -1,137 +0,0 @@ -/* - * Copyright (c) 2000-2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_TYPES_H__ -#define __XFS_TYPES_H__ - -typedef __uint32_t prid_t; /* project ID */ - -typedef __uint32_t xfs_agblock_t; /* blockno in alloc. group */ -typedef __uint32_t xfs_agino_t; /* inode # within allocation grp */ -typedef __uint32_t xfs_extlen_t; /* extent length in blocks */ -typedef __uint32_t xfs_agnumber_t; /* allocation group number */ -typedef __int32_t xfs_extnum_t; /* # of extents in a file */ -typedef __int16_t xfs_aextnum_t; /* # extents in an attribute fork */ -typedef __int64_t xfs_fsize_t; /* bytes in a file */ -typedef __uint64_t xfs_ufsize_t; /* unsigned bytes in a file */ - -typedef __int32_t xfs_suminfo_t; /* type of bitmap summary info */ -typedef __int32_t xfs_rtword_t; /* word type for bitmap manipulations */ - -typedef __int64_t xfs_lsn_t; /* log sequence number */ -typedef __int32_t xfs_tid_t; /* transaction identifier */ - -typedef __uint32_t xfs_dablk_t; /* dir/attr block number (in file) */ -typedef __uint32_t xfs_dahash_t; /* dir/attr hash value */ - -typedef __uint64_t xfs_fsblock_t; /* blockno in filesystem (agno|agbno) */ -typedef __uint64_t xfs_rfsblock_t; /* blockno in filesystem (raw) */ -typedef __uint64_t xfs_rtblock_t; /* extent (block) in realtime area */ -typedef __uint64_t xfs_fileoff_t; /* block number in a file */ -typedef __uint64_t xfs_filblks_t; /* number of blocks in a file */ - -typedef __int64_t xfs_srtblock_t; /* signed version of xfs_rtblock_t */ -typedef __int64_t xfs_sfiloff_t; /* signed block number in a file */ - -/* - * Null values for the types. - */ -#define NULLFSBLOCK ((xfs_fsblock_t)-1) -#define NULLRFSBLOCK ((xfs_rfsblock_t)-1) -#define NULLRTBLOCK ((xfs_rtblock_t)-1) -#define NULLFILEOFF ((xfs_fileoff_t)-1) - -#define NULLAGBLOCK ((xfs_agblock_t)-1) -#define NULLAGNUMBER ((xfs_agnumber_t)-1) -#define NULLEXTNUM ((xfs_extnum_t)-1) - -#define NULLCOMMITLSN ((xfs_lsn_t)-1) - -#define NULLFSINO ((xfs_ino_t)-1) -#define NULLAGINO ((xfs_agino_t)-1) - -/* - * Max values for extlen, extnum, aextnum. - */ -#define MAXEXTLEN ((xfs_extlen_t)0x001fffff) /* 21 bits */ -#define MAXEXTNUM ((xfs_extnum_t)0x7fffffff) /* signed int */ -#define MAXAEXTNUM ((xfs_aextnum_t)0x7fff) /* signed short */ - -/* - * Minimum and maximum blocksize and sectorsize. - * The blocksize upper limit is pretty much arbitrary. - * The sectorsize upper limit is due to sizeof(sb_sectsize). - */ -#define XFS_MIN_BLOCKSIZE_LOG 9 /* i.e. 512 bytes */ -#define XFS_MAX_BLOCKSIZE_LOG 16 /* i.e. 65536 bytes */ -#define XFS_MIN_BLOCKSIZE (1 << XFS_MIN_BLOCKSIZE_LOG) -#define XFS_MAX_BLOCKSIZE (1 << XFS_MAX_BLOCKSIZE_LOG) -#define XFS_MIN_SECTORSIZE_LOG 9 /* i.e. 512 bytes */ -#define XFS_MAX_SECTORSIZE_LOG 15 /* i.e. 32768 bytes */ -#define XFS_MIN_SECTORSIZE (1 << XFS_MIN_SECTORSIZE_LOG) -#define XFS_MAX_SECTORSIZE (1 << XFS_MAX_SECTORSIZE_LOG) - -/* - * Inode fork identifiers. - */ -#define XFS_DATA_FORK 0 -#define XFS_ATTR_FORK 1 - -/* - * Min numbers of data/attr fork btree root pointers. - */ -#define MINDBTPTRS 3 -#define MINABTPTRS 2 - -/* - * MAXNAMELEN is the length (including the terminating null) of - * the longest permissible file (component) name. - */ -#define MAXNAMELEN 256 - -typedef enum { - XFS_LOOKUP_EQi, XFS_LOOKUP_LEi, XFS_LOOKUP_GEi -} xfs_lookup_t; - -typedef enum { - XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_BMAPi, XFS_BTNUM_INOi, - XFS_BTNUM_FINOi, XFS_BTNUM_MAX -} xfs_btnum_t; - -struct xfs_name { - const unsigned char *name; - int len; - int type; -}; - -/* - * uid_t and gid_t are hard-coded to 32 bits in the inode. - * Hence, an 'id' in a dquot is 32 bits.. - */ -typedef __uint32_t xfs_dqid_t; - -/* - * Constants for bit manipulations. - */ -#define XFS_NBBYLOG 3 /* log2(NBBY) */ -#define XFS_WORDLOG 2 /* log2(sizeof(xfs_rtword_t)) */ -#define XFS_NBWORDLOG (XFS_NBBYLOG + XFS_WORDLOG) -#define XFS_NBWORD (1 << XFS_NBWORDLOG) -#define XFS_WORDMASK ((1 << XFS_WORDLOG) - 1) - - -#endif /* __XFS_TYPES_H__ */ -- cgit v1.2.3 From 9799b438ce21662fa173ffc0b30d93567a71dfa0 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 9 Jan 2015 10:46:49 +1100 Subject: xfs: move struct xfs_bmalloca to libxfs It no long is used for stack splits, so strip the kernel workqueue bits from it and push it back into libxfs/xfs_bmap.h so that it can be shared with the userspace code. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.h | 31 +++++++++++++++++++++++++++++++ fs/xfs/xfs_bmap_util.h | 35 +---------------------------------- 2 files changed, 32 insertions(+), 34 deletions(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 44db6db86402..856f53c33f4e 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -27,6 +27,37 @@ struct xfs_trans; extern kmem_zone_t *xfs_bmap_free_item_zone; +/* + * Argument structure for xfs_bmap_alloc. + */ +struct xfs_bmalloca { + xfs_fsblock_t *firstblock; /* i/o first block allocated */ + struct xfs_bmap_free *flist; /* bmap freelist */ + struct xfs_trans *tp; /* transaction pointer */ + struct xfs_inode *ip; /* incore inode pointer */ + struct xfs_bmbt_irec prev; /* extent before the new one */ + struct xfs_bmbt_irec got; /* extent after, or delayed */ + + xfs_fileoff_t offset; /* offset in file filling in */ + xfs_extlen_t length; /* i/o length asked/allocated */ + xfs_fsblock_t blkno; /* starting block of new extent */ + + struct xfs_btree_cur *cur; /* btree cursor */ + xfs_extnum_t idx; /* current extent index */ + int nallocs;/* number of extents alloc'd */ + int logflags;/* flags for transaction logging */ + + xfs_extlen_t total; /* total blocks needed for xaction */ + xfs_extlen_t minlen; /* minimum allocation size (blocks) */ + xfs_extlen_t minleft; /* amount must be left after alloc */ + bool eof; /* set if allocating past last extent */ + bool wasdel; /* replacing a delayed allocation */ + bool userdata;/* set if is user data */ + bool aeof; /* allocated space at eof */ + bool conv; /* overwriting unwritten extents */ + int flags; +}; + /* * List of extents to be free "later". * The list is kept sorted on xbf_startblock. diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 2fdb72d2c908..1fce0f364829 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -26,40 +26,7 @@ struct xfs_ifork; struct xfs_inode; struct xfs_mount; struct xfs_trans; - -/* - * Argument structure for xfs_bmap_alloc. - */ -struct xfs_bmalloca { - xfs_fsblock_t *firstblock; /* i/o first block allocated */ - struct xfs_bmap_free *flist; /* bmap freelist */ - struct xfs_trans *tp; /* transaction pointer */ - struct xfs_inode *ip; /* incore inode pointer */ - struct xfs_bmbt_irec prev; /* extent before the new one */ - struct xfs_bmbt_irec got; /* extent after, or delayed */ - - xfs_fileoff_t offset; /* offset in file filling in */ - xfs_extlen_t length; /* i/o length asked/allocated */ - xfs_fsblock_t blkno; /* starting block of new extent */ - - struct xfs_btree_cur *cur; /* btree cursor */ - xfs_extnum_t idx; /* current extent index */ - int nallocs;/* number of extents alloc'd */ - int logflags;/* flags for transaction logging */ - - xfs_extlen_t total; /* total blocks needed for xaction */ - xfs_extlen_t minlen; /* minimum allocation size (blocks) */ - xfs_extlen_t minleft; /* amount must be left after alloc */ - bool eof; /* set if allocating past last extent */ - bool wasdel; /* replacing a delayed allocation */ - bool userdata;/* set if is user data */ - bool aeof; /* allocated space at eof */ - bool conv; /* overwriting unwritten extents */ - int flags; - struct completion *done; - struct work_struct work; - int result; -}; +struct xfs_bmalloca; int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist, int *committed); -- cgit v1.2.3 From aa5d95c1b57792119804c587b9a468019219d7e0 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 9 Jan 2015 10:47:14 +1100 Subject: xfs: move xfs_bmap_finish prototype This function is used libxfs code, but is implemented separately in userspace. Move the function prototype to xfs_bmap.h so that the prototype is shared even if the implementations aren't. Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.h | 2 ++ fs/xfs/xfs_bmap_util.h | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 856f53c33f4e..b9d8a499d2c4 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -180,6 +180,8 @@ void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len, struct xfs_bmap_free *flist, struct xfs_mount *mp); void xfs_bmap_cancel(struct xfs_bmap_free *flist); +int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist, + int *committed); void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork); int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip, xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork); diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 1fce0f364829..736429a72a12 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -28,8 +28,6 @@ struct xfs_mount; struct xfs_trans; struct xfs_bmalloca; -int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist, - int *committed); int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); -- cgit v1.2.3 From 64af7a6ea5a4c7e12ae79415250d054424b7e0c2 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 9 Jan 2015 10:47:43 +1100 Subject: xfs: remove deprecated sysctls xfsbufd_centisecs and age_buffer_centisecs were due for removal in 3.14. We forgot to do that - it's now well past time to remove these deprecated, unused sysctls. Signed-off-by: Dave Chinner Reviewed-by: Eric Sandeen Signed-off-by: Dave Chinner --- Documentation/filesystems/xfs.txt | 17 +++++++---------- fs/xfs/xfs_sysctl.c | 18 ------------------ 2 files changed, 7 insertions(+), 28 deletions(-) (limited to 'fs') diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt index 5be51fd888bd..7077103ac541 100644 --- a/Documentation/filesystems/xfs.txt +++ b/Documentation/filesystems/xfs.txt @@ -348,16 +348,13 @@ The following sysctls are available for the XFS filesystem: Deprecated Sysctls ================== - fs.xfs.xfsbufd_centisecs (Min: 50 Default: 100 Max: 3000) - Dirty metadata is now tracked by the log subsystem and - flushing is driven by log space and idling demands. The - xfsbufd no longer exists, so this syctl does nothing. +None at present. - Due for removal in 3.14. - fs.xfs.age_buffer_centisecs (Min: 100 Default: 1500 Max: 720000) - Dirty metadata is now tracked by the log subsystem and - flushing is driven by log space and idling demands. The - xfsbufd no longer exists, so this syctl does nothing. +Removed Sysctls +=============== - Due for removal in 3.14. + Name Removed + ---- ------- + fs.xfs.xfsbufd_centisec v3.20 + fs.xfs.age_buffer_centisecs v3.20 diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index 1743b9f8e23d..a0c8067cea6f 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -148,24 +148,6 @@ static struct ctl_table xfs_table[] = { .extra1 = &xfs_params.inherit_noatim.min, .extra2 = &xfs_params.inherit_noatim.max }, - { - .procname = "xfsbufd_centisecs", - .data = &xfs_params.xfs_buf_timer.val, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &xfs_params.xfs_buf_timer.min, - .extra2 = &xfs_params.xfs_buf_timer.max - }, - { - .procname = "age_buffer_centisecs", - .data = &xfs_params.xfs_buf_age.val, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &xfs_params.xfs_buf_age.min, - .extra2 = &xfs_params.xfs_buf_age.max - }, { .procname = "inherit_nosymlinks", .data = &xfs_params.inherit_nosym.val, -- cgit v1.2.3 From d32057fc84c141af22ddf07b58e52570e52369cd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Jan 2015 10:48:12 +1100 Subject: xfs: pass a 64-bit count argument to xfs_iomap_write_unwritten The code is already ready for it, and the pnfs layout commit code expects to be able to pass a larger than 32-bit argument. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_iomap.c | 2 +- fs/xfs/xfs_iomap.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index c980e2a5086b..ccb1dd0d509e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -802,7 +802,7 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - size_t count) + xfs_off_t count) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 411fbb8919ef..8688e663d744 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,6 +27,6 @@ int xfs_iomap_write_delay(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *); int xfs_iomap_write_allocate(struct xfs_inode *, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, size_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); #endif /* __XFS_IOMAP_H__*/ -- cgit v1.2.3 From 43fd1fce9643586e0995ee5d11fb40641575348a Mon Sep 17 00:00:00 2001 From: Nicholas Mc Guire Date: Fri, 9 Jan 2015 10:48:58 +1100 Subject: xfs: fix implicit bool to int conversion try_wait_for_completion returns bool so the wrapper function xfs_dqflock_nowait should probably also return bool and not int. Signed-off-by: Nicholas Mc Guire Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_dquot.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index c24c67e22a2a..2f536f33cd26 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -86,7 +86,7 @@ static inline void xfs_dqflock(xfs_dquot_t *dqp) wait_for_completion(&dqp->q_flush); } -static inline int xfs_dqflock_nowait(xfs_dquot_t *dqp) +static inline bool xfs_dqflock_nowait(xfs_dquot_t *dqp) { return try_wait_for_completion(&dqp->q_flush); } -- cgit v1.2.3 From 8f6cb409f016e52b753a93e393622770556d1ab9 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Mon, 5 Jan 2015 13:25:10 -0500 Subject: GFS2: Eliminate __gfs2_glock_remove_from_lru Since the only caller of function __gfs2_glock_remove_from_lru locks the same spin_lock as gfs2_glock_remove_from_lru, the functions can be combined. Signed-off-by: Bob Peterson Signed-off-by: Steven Whitehouse --- fs/gfs2/glock.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index a23524aa3eac..aeb7bc958a18 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -173,19 +173,14 @@ void gfs2_glock_add_to_lru(struct gfs2_glock *gl) spin_unlock(&lru_lock); } -static void __gfs2_glock_remove_from_lru(struct gfs2_glock *gl) +static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) { + spin_lock(&lru_lock); if (!list_empty(&gl->gl_lru)) { list_del_init(&gl->gl_lru); atomic_dec(&lru_count); clear_bit(GLF_LRU, &gl->gl_flags); } -} - -static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) -{ - spin_lock(&lru_lock); - __gfs2_glock_remove_from_lru(gl); spin_unlock(&lru_lock); } @@ -205,9 +200,7 @@ void gfs2_glock_put(struct gfs2_glock *gl) lockref_mark_dead(&gl->gl_lockref); - spin_lock(&lru_lock); - __gfs2_glock_remove_from_lru(gl); - spin_unlock(&lru_lock); + gfs2_glock_remove_from_lru(gl); spin_unlock(&gl->gl_lockref.lock); spin_lock_bucket(gl->gl_hash); hlist_bl_del_rcu(&gl->gl_list); -- cgit v1.2.3 From bbe48dd811474adc2df96803f910d4dc2b5e5bde Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Sat, 10 Jan 2015 19:13:32 +0100 Subject: udf: destroy sbi mutex in put_super Call mutex_destroy() on superblock mutex in udf_put_super() otherwise mutex debugging code isn't able to detect that mutex is used after being freed. (thanks to Jan Kara for complete definition). Signed-off-by: Fabian Frederick Signed-off-by: Jan Kara --- fs/udf/super.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/udf/super.c b/fs/udf/super.c index 3ccb2f11fc76..3d35a754293a 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -2300,6 +2300,7 @@ static void udf_put_super(struct super_block *sb) udf_close_lvid(sb); brelse(sbi->s_lvid_bh); udf_sb_free_partitions(sb); + mutex_destroy(&sbi->s_alloc_mutex); kfree(sb->s_fs_info); sb->s_fs_info = NULL; } -- cgit v1.2.3 From 3566c964767811f3965979fa9598027b6550026d Mon Sep 17 00:00:00 2001 From: alex chen Date: Mon, 12 Jan 2015 19:01:03 +0800 Subject: GFS2: fix sprintf format specifier Sprintf format specifier "%d" and "%u" are mixed up in gfs2_recovery_done() and freeze_show(). So correct them. Signed-off-by: Alex Chen Reviewed-by: Joseph Qi Signed-off-by: Steven Whitehouse --- fs/gfs2/recovery.c | 2 +- fs/gfs2/sys.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 573bd3b758fa..1b645773c98e 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -439,7 +439,7 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid, ls->ls_recover_jid_done = jid; ls->ls_recover_jid_status = message; - sprintf(env_jid, "JID=%d", jid); + sprintf(env_jid, "JID=%u", jid); sprintf(env_status, "RECOVERY=%s", message == LM_RD_SUCCESS ? "Done" : "Failed"); kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 3ab566ba5696..ae8e8811f0e8 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -96,7 +96,7 @@ static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf) struct super_block *sb = sdp->sd_vfs; int frozen = (sb->s_writers.frozen == SB_UNFROZEN) ? 0 : 1; - return snprintf(buf, PAGE_SIZE, "%u\n", frozen); + return snprintf(buf, PAGE_SIZE, "%d\n", frozen); } static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len) -- cgit v1.2.3 From 4cb7208a4105a74581ccd4541af75cfd772e99fb Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Sat, 10 Jan 2015 18:02:42 +0100 Subject: lockd: xdr: Remove unused function Remove the function nlm_encode_fh() that is not used anywhere. This was partially found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Signed-off-by: J. Bruce Fields --- fs/lockd/xdr.c | 8 -------- 1 file changed, 8 deletions(-) (limited to 'fs') diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 9340e7e10ef6..5b651daad518 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -95,14 +95,6 @@ nlm_decode_fh(__be32 *p, struct nfs_fh *f) return p + XDR_QUADLEN(NFS2_FHSIZE); } -static inline __be32 * -nlm_encode_fh(__be32 *p, struct nfs_fh *f) -{ - *p++ = htonl(NFS2_FHSIZE); - memcpy(p, f->data, NFS2_FHSIZE); - return p + XDR_QUADLEN(NFS2_FHSIZE); -} - /* * Encode and decode owner handle */ -- cgit v1.2.3 From 917937025a955e239e5cdcc62b6ca9a5ef9e5e48 Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Tue, 13 Jan 2015 21:57:24 +0100 Subject: nfsd: nfs4state: Remove unused function Remove the function renew_client() that is not used anywhere. This was partially found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 277f8b8529d6..f924f0618cb5 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -150,16 +150,6 @@ renew_client_locked(struct nfs4_client *clp) clp->cl_time = get_seconds(); } -static inline void -renew_client(struct nfs4_client *clp) -{ - struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - - spin_lock(&nn->client_lock); - renew_client_locked(clp); - spin_unlock(&nn->client_lock); -} - static void put_client_renew_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); -- cgit v1.2.3 From 6dee60f69d48fcef021b4b53b3431797ec440764 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:54 -0500 Subject: locks: add new struct list_head to struct file_lock ...that we can use to queue file_locks to per-ctx list_heads. Go ahead and convert locks_delete_lock and locks_dispose_list to use it instead of the fl_block list. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/locks.c | 8 +++++--- include/linux/fs.h | 1 + 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/locks.c b/fs/locks.c index 59e2f905e4ff..bfe5f17401de 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -207,6 +207,7 @@ static struct kmem_cache *filelock_cache __read_mostly; static void locks_init_lock_heads(struct file_lock *fl) { INIT_HLIST_NODE(&fl->fl_link); + INIT_LIST_HEAD(&fl->fl_list); INIT_LIST_HEAD(&fl->fl_block); init_waitqueue_head(&fl->fl_wait); } @@ -243,6 +244,7 @@ EXPORT_SYMBOL_GPL(locks_release_private); void locks_free_lock(struct file_lock *fl) { BUG_ON(waitqueue_active(&fl->fl_wait)); + BUG_ON(!list_empty(&fl->fl_list)); BUG_ON(!list_empty(&fl->fl_block)); BUG_ON(!hlist_unhashed(&fl->fl_link)); @@ -257,8 +259,8 @@ locks_dispose_list(struct list_head *dispose) struct file_lock *fl; while (!list_empty(dispose)) { - fl = list_first_entry(dispose, struct file_lock, fl_block); - list_del_init(&fl->fl_block); + fl = list_first_entry(dispose, struct file_lock, fl_list); + list_del_init(&fl->fl_list); locks_free_lock(fl); } } @@ -691,7 +693,7 @@ static void locks_delete_lock(struct file_lock **thisfl_p, locks_unlink_lock(thisfl_p); if (dispose) - list_add(&fl->fl_block, dispose); + list_add(&fl->fl_list, dispose); else locks_free_lock(fl); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..cd6818115162 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -934,6 +934,7 @@ int locks_in_grace(struct net *); */ struct file_lock { struct file_lock *fl_next; /* singly linked list for this inode */ + struct list_head fl_list; /* link into file_lock_context */ struct hlist_node fl_link; /* node in global lists */ struct list_head fl_block; /* circular list of blocked processes */ fl_owner_t fl_owner; -- cgit v1.2.3 From dd459bb1974c5e9cff3dfbf4f6fdb3e9363ef32e Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:54 -0500 Subject: locks: have locks_release_file use flock_lock_file to release generic flock locks ...instead of open-coding it and removing flock locks directly. This helps consolidate the flock lock removal logic into a single spot. Signed-off-by: Jeff Layton --- fs/locks.c | 49 +++++++++++++++++++++++++++++++------------------ 1 file changed, 31 insertions(+), 18 deletions(-) (limited to 'fs') diff --git a/fs/locks.c b/fs/locks.c index bfe5f17401de..ae1e7cf721d6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2360,6 +2360,30 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) EXPORT_SYMBOL(locks_remove_posix); +static void +locks_remove_flock(struct file *filp) +{ + struct file_lock fl = { + .fl_owner = filp, + .fl_pid = current->tgid, + .fl_file = filp, + .fl_flags = FL_FLOCK, + .fl_type = F_UNLCK, + .fl_end = OFFSET_MAX, + }; + + if (!file_inode(filp)->i_flock) + return; + + if (filp->f_op->flock) + filp->f_op->flock(filp, F_SETLKW, &fl); + else + flock_lock_file(filp, &fl); + + if (fl.fl_ops && fl.fl_ops->fl_release_private) + fl.fl_ops->fl_release_private(&fl); +} + /* * This function is called on the last close of an open file. */ @@ -2370,24 +2394,14 @@ void locks_remove_file(struct file *filp) struct file_lock **before; LIST_HEAD(dispose); - if (!inode->i_flock) - return; - + /* remove any OFD locks */ locks_remove_posix(filp, filp); - if (filp->f_op->flock) { - struct file_lock fl = { - .fl_owner = filp, - .fl_pid = current->tgid, - .fl_file = filp, - .fl_flags = FL_FLOCK, - .fl_type = F_UNLCK, - .fl_end = OFFSET_MAX, - }; - filp->f_op->flock(filp, F_SETLKW, &fl); - if (fl.fl_ops && fl.fl_ops->fl_release_private) - fl.fl_ops->fl_release_private(&fl); - } + /* remove flock locks */ + locks_remove_flock(filp); + + if (!inode->i_flock) + return; spin_lock(&inode->i_lock); before = &inode->i_flock; @@ -2407,8 +2421,7 @@ void locks_remove_file(struct file *filp) * some info about it and then just remove it from * the list. */ - WARN(!IS_FLOCK(fl), - "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", + WARN(1, "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino, fl->fl_type, fl->fl_flags, -- cgit v1.2.3 From 4a075e39c86490cc0f0c10ac6abe3592d1689463 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:54 -0500 Subject: locks: add a new struct file_locking_context pointer to struct inode The current scheme of using the i_flock list is really difficult to manage. There is also a legitimate desire for a per-inode spinlock to manage these lists that isn't the i_lock. Start conversion to a new scheme to eventually replace the old i_flock list with a new "file_lock_context" object. We start by adding a new i_flctx to struct inode. For now, it lives in parallel with i_flock list, but will eventually replace it. The idea is to allocate a structure to sit in that pointer and act as a locus for all things file locking. We allocate a file_lock_context for an inode when the first lock is added to it, and it's only freed when the inode is freed. We use the i_lock to protect the assignment, but afterward it should mostly be accessed locklessly. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/inode.c | 3 ++- fs/locks.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 11 +++++++++++ 3 files changed, 57 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/inode.c b/fs/inode.c index aa149e7262ac..f30872ade6d7 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -194,7 +194,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif - + inode->i_flctx = NULL; this_cpu_inc(nr_inodes); return 0; @@ -237,6 +237,7 @@ void __destroy_inode(struct inode *inode) BUG_ON(inode_has_buffers(inode)); security_inode_free(inode); fsnotify_inode_delete(inode); + locks_free_lock_context(inode->i_flctx); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); diff --git a/fs/locks.c b/fs/locks.c index ae1e7cf721d6..526d5fca67c8 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -202,8 +202,49 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); */ static DEFINE_SPINLOCK(blocked_lock_lock); +static struct kmem_cache *flctx_cache __read_mostly; static struct kmem_cache *filelock_cache __read_mostly; +static struct file_lock_context * +locks_get_lock_context(struct inode *inode) +{ + struct file_lock_context *new; + + if (likely(inode->i_flctx)) + goto out; + + new = kmem_cache_alloc(flctx_cache, GFP_KERNEL); + if (!new) + goto out; + + INIT_LIST_HEAD(&new->flc_flock); + + /* + * Assign the pointer if it's not already assigned. If it is, then + * free the context we just allocated. + */ + spin_lock(&inode->i_lock); + if (likely(!inode->i_flctx)) { + inode->i_flctx = new; + new = NULL; + } + spin_unlock(&inode->i_lock); + + if (new) + kmem_cache_free(flctx_cache, new); +out: + return inode->i_flctx; +} + +void +locks_free_lock_context(struct file_lock_context *ctx) +{ + if (ctx) { + WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); + kmem_cache_free(flctx_cache, ctx); + } +} + static void locks_init_lock_heads(struct file_lock *fl) { INIT_HLIST_NODE(&fl->fl_link); @@ -2636,6 +2677,9 @@ static int __init filelock_init(void) { int i; + flctx_cache = kmem_cache_create("file_lock_ctx", + sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); + filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); diff --git a/include/linux/fs.h b/include/linux/fs.h index cd6818115162..dec0d38b05de 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -626,6 +626,7 @@ struct inode { #endif const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct file_lock *i_flock; + struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { @@ -965,6 +966,10 @@ struct file_lock { } fl_u; }; +struct file_lock_context { + struct list_head flc_flock; +}; + /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1))) @@ -991,6 +996,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ +void locks_free_lock_context(struct file_lock_context *ctx); void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); extern struct file_lock * locks_alloc_lock(void); @@ -1048,6 +1054,11 @@ static inline int fcntl_getlease(struct file *filp) return F_UNLCK; } +static inline void +locks_free_lock_context(struct file_lock_context *ctx) +{ +} + static inline void locks_init_lock(struct file_lock *fl) { return; -- cgit v1.2.3 From c362781cadd37858c3d8f5d18b1e9957d4671298 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:55 -0500 Subject: ceph: move spinlocking into ceph_encode_locks_to_buffer and ceph_count_locks There is only a single call site for each of these functions, and the caller takes the i_lock prior to calling them and drops it just afterward. Move the spinlocking into the functions instead. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/ceph/locks.c | 4 ++++ fs/ceph/mds_client.c | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index c35c5c614e38..366dc2412605 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -251,12 +251,14 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) *fcntl_count = 0; *flock_count = 0; + spin_lock(&inode->i_lock); for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { if (lock->fl_flags & FL_POSIX) ++(*fcntl_count); else if (lock->fl_flags & FL_FLOCK) ++(*flock_count); } + spin_unlock(&inode->i_lock); dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); } @@ -279,6 +281,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, dout("encoding %d flock and %d fcntl locks", num_flock_locks, num_fcntl_locks); + spin_lock(&inode->i_lock); for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { if (lock->fl_flags & FL_POSIX) { ++seen_fcntl; @@ -306,6 +309,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, } } fail: + spin_unlock(&inode->i_lock); return err; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index d2171f4a6980..5f62fb7a5d0a 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2700,20 +2700,16 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, struct ceph_filelock *flocks; encode_again: - spin_lock(&inode->i_lock); ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks); - spin_unlock(&inode->i_lock); flocks = kmalloc((num_fcntl_locks+num_flock_locks) * sizeof(struct ceph_filelock), GFP_NOFS); if (!flocks) { err = -ENOMEM; goto out_free; } - spin_lock(&inode->i_lock); err = ceph_encode_locks_to_buffer(inode, flocks, num_fcntl_locks, num_flock_locks); - spin_unlock(&inode->i_lock); if (err) { kfree(flocks); if (err == -ENOSPC) -- cgit v1.2.3 From 5263e31e452fb84138b9bee061d5c06c0f359fea Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:55 -0500 Subject: locks: move flock locks to file_lock_context Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/ceph/locks.c | 23 ++++++++++++++++------- fs/locks.c | 54 ++++++++++++++++++++++++++++++++++------------------- fs/nfs/delegation.c | 19 +++++++++++++++++-- fs/nfs/nfs4state.c | 42 +++++++++++++++++++++++++++++++++++++++-- fs/nfs/pagelist.c | 6 ++++++ fs/nfs/write.c | 43 +++++++++++++++++++++++++++++++++++++----- 6 files changed, 152 insertions(+), 35 deletions(-) (limited to 'fs') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 366dc2412605..917656ea8dcf 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -239,14 +239,16 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) return err; } -/** - * Must be called with lock_flocks() already held. Fills in the passed - * counter variables, so you can prepare pagelist metadata before calling - * ceph_encode_locks. +/* + * Fills in the passed counter variables, so you can prepare pagelist metadata + * before calling ceph_encode_locks. + * + * FIXME: add counters to struct file_lock_context so we don't need to do this? */ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) { struct file_lock *lock; + struct file_lock_context *ctx; *fcntl_count = 0; *flock_count = 0; @@ -255,7 +257,11 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { if (lock->fl_flags & FL_POSIX) ++(*fcntl_count); - else if (lock->fl_flags & FL_FLOCK) + } + + ctx = inode->i_flctx; + if (ctx) { + list_for_each_entry(lock, &ctx->flc_flock, fl_list) ++(*flock_count); } spin_unlock(&inode->i_lock); @@ -273,6 +279,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, int num_fcntl_locks, int num_flock_locks) { struct file_lock *lock; + struct file_lock_context *ctx; int err = 0; int seen_fcntl = 0; int seen_flock = 0; @@ -295,8 +302,10 @@ int ceph_encode_locks_to_buffer(struct inode *inode, ++l; } } - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_FLOCK) { + + ctx = inode->i_flctx; + if (ctx) { + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { ++seen_flock; if (seen_flock > num_flock_locks) { err = -ENOSPC; diff --git a/fs/locks.c b/fs/locks.c index 526d5fca67c8..055df53f19de 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -694,6 +694,14 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) locks_insert_global_locks(fl); } +static void +locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) +{ + fl->fl_nspid = get_pid(task_tgid(current)); + list_add_tail(&fl->fl_list, before); + locks_insert_global_locks(fl); +} + /** * locks_delete_lock - Delete a lock and then free it. * @thisfl_p: pointer that points to the fl_next field of the previous @@ -739,6 +747,18 @@ static void locks_delete_lock(struct file_lock **thisfl_p, locks_free_lock(fl); } +static void +locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) +{ + locks_delete_global_locks(fl); + if (fl->fl_nspid) { + put_pid(fl->fl_nspid); + fl->fl_nspid = NULL; + } + locks_wake_up_blocks(fl); + list_move(&fl->fl_list, dispose); +} + /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ @@ -888,12 +908,17 @@ static int posix_locks_deadlock(struct file_lock *caller_fl, static int flock_lock_file(struct file *filp, struct file_lock *request) { struct file_lock *new_fl = NULL; - struct file_lock **before; - struct inode * inode = file_inode(filp); + struct file_lock *fl; + struct file_lock_context *ctx; + struct inode *inode = file_inode(filp); int error = 0; - int found = 0; + bool found = false; LIST_HEAD(dispose); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) @@ -904,18 +929,13 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) if (request->fl_flags & FL_ACCESS) goto find_conflict; - for_each_lock(inode, before) { - struct file_lock *fl = *before; - if (IS_POSIX(fl)) - break; - if (IS_LEASE(fl)) - continue; + list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (filp != fl->fl_file) continue; if (request->fl_type == fl->fl_type) goto out; - found = 1; - locks_delete_lock(before, &dispose); + found = true; + locks_delete_lock_ctx(fl, &dispose); break; } @@ -936,12 +956,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) } find_conflict: - for_each_lock(inode, before) { - struct file_lock *fl = *before; - if (IS_POSIX(fl)) - break; - if (IS_LEASE(fl)) - continue; + list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (!flock_locks_conflict(request, fl)) continue; error = -EAGAIN; @@ -954,7 +969,7 @@ find_conflict: if (request->fl_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); - locks_insert_lock(before, new_fl); + locks_insert_lock_ctx(new_fl, &ctx->flc_flock); new_fl = NULL; error = 0; @@ -2412,8 +2427,9 @@ locks_remove_flock(struct file *filp) .fl_type = F_UNLCK, .fl_end = OFFSET_MAX, }; + struct file_lock_context *flctx = file_inode(filp)->i_flctx; - if (!file_inode(filp)->i_flock) + if (!flctx || list_empty(&flctx->flc_flock)) return; if (filp->f_op->flock) diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 7f3f60641344..9f9f67b17e2b 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -85,15 +85,16 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ { struct inode *inode = state->inode; struct file_lock *fl; + struct file_lock_context *flctx; int status = 0; - if (inode->i_flock == NULL) + if (inode->i_flock == NULL && inode->i_flctx == NULL) goto out; /* Protect inode->i_flock using the i_lock */ spin_lock(&inode->i_lock); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) + if (!(fl->fl_flags & (FL_POSIX))) continue; if (nfs_file_open_context(fl->fl_file) != ctx) continue; @@ -103,6 +104,20 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ goto out; spin_lock(&inode->i_lock); } + + flctx = inode->i_flctx; + if (flctx) { + list_for_each_entry(fl, &flctx->flc_flock, fl_list) { + if (nfs_file_open_context(fl->fl_file) != ctx) + continue; + spin_unlock(&inode->i_lock); + status = nfs4_lock_delegation_recall(fl, state, + stateid); + if (status < 0) + goto out; + spin_lock(&inode->i_lock); + } + } spin_unlock(&inode->i_lock); out: return status; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5194933ed419..65c404bf61ae 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1366,8 +1366,9 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ struct nfs_inode *nfsi = NFS_I(inode); struct file_lock *fl; int status = 0; + struct file_lock_context *flctx = inode->i_flctx; - if (inode->i_flock == NULL) + if (inode->i_flock == NULL && flctx == NULL) return 0; /* Guard against delegation returns and new lock/unlock calls */ @@ -1375,7 +1376,7 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ /* Protect inode->i_flock using the BKL */ spin_lock(&inode->i_lock); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) + if (!(fl->fl_flags & FL_POSIX)) continue; if (nfs_file_open_context(fl->fl_file)->state != state) continue; @@ -1408,6 +1409,43 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ } spin_lock(&inode->i_lock); } + + if (!flctx) + goto out_unlock; + + list_for_each_entry(fl, &flctx->flc_flock, fl_list) { + if (nfs_file_open_context(fl->fl_file)->state != state) + continue; + spin_unlock(&inode->i_lock); + status = ops->recover_lock(state, fl); + switch (status) { + case 0: + break; + case -ESTALE: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_EXPIRED: + case -NFS4ERR_NO_GRACE: + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_BADSESSION: + case -NFS4ERR_BADSLOT: + case -NFS4ERR_BAD_HIGH_SLOT: + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + goto out; + default: + pr_err("NFS: %s: unhandled error %d\n", + __func__, status); + case -ENOMEM: + case -NFS4ERR_DENIED: + case -NFS4ERR_RECLAIM_BAD: + case -NFS4ERR_RECLAIM_CONFLICT: + /* kill_proc(fl->fl_pid, SIGLOST, 1); */ + status = 0; + } + spin_lock(&inode->i_lock); + } +out_unlock: spin_unlock(&inode->i_lock); out: up_write(&nfsi->rwsem); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 2b5e769beb16..a3b62e15b444 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -826,6 +826,7 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, struct nfs_pageio_descriptor *pgio) { size_t size; + struct file_lock_context *flctx; if (prev) { if (!nfs_match_open_context(req->wb_context, prev->wb_context)) @@ -834,6 +835,11 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context)) return false; + flctx = req->wb_context->dentry->d_inode->i_flctx; + if (flctx != NULL && !list_empty_careful(&flctx->flc_flock) && + !nfs_match_lock_context(req->wb_lock_context, + prev->wb_lock_context)) + return false; if (req_offset(req) != req_offset(prev) + prev->wb_bytes) return false; if (req->wb_page == prev->wb_page) { diff --git a/fs/nfs/write.c b/fs/nfs/write.c index af3af685a9e3..e072aeb34195 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1113,6 +1113,11 @@ int nfs_flush_incompatible(struct file *file, struct page *page) do_flush |= l_ctx->lockowner.l_owner != current->files || l_ctx->lockowner.l_pid != current->tgid; } + if (l_ctx && ctx->dentry->d_inode->i_flctx && + !list_empty_careful(&ctx->dentry->d_inode->i_flctx->flc_flock)) { + do_flush |= l_ctx->lockowner.l_owner != current->files + || l_ctx->lockowner.l_pid != current->tgid; + } nfs_release_request(req); if (!do_flush) return 0; @@ -1170,6 +1175,13 @@ out: return PageUptodate(page) != 0; } +static bool +is_whole_file_wrlock(struct file_lock *fl) +{ + return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX && + fl->fl_type == F_WRLCK; +} + /* If we know the page is up to date, and we're not using byte range locks (or * if we have the whole file locked for writing), it may be more efficient to * extend the write to cover the entire page in order to avoid fragmentation @@ -1180,17 +1192,38 @@ out: */ static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode) { + int ret; + struct file_lock_context *flctx = inode->i_flctx; + struct file_lock *fl; + if (file->f_flags & O_DSYNC) return 0; if (!nfs_write_pageuptodate(page, inode)) return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; - if (inode->i_flock == NULL || (inode->i_flock->fl_start == 0 && - inode->i_flock->fl_end == OFFSET_MAX && - inode->i_flock->fl_type != F_RDLCK)) - return 1; - return 0; + if (!inode->i_flock && !flctx) + return 0; + + /* Check to see if there are whole file write locks */ + spin_lock(&inode->i_lock); + ret = 0; + + fl = inode->i_flock; + if (fl && is_whole_file_wrlock(fl)) { + ret = 1; + goto out; + } + + if (!list_empty(&flctx->flc_flock)) { + fl = list_first_entry(&flctx->flc_flock, struct file_lock, + fl_list); + if (fl->fl_type == F_WRLCK) + ret = 1; + } +out: + spin_unlock(&inode->i_lock); + return ret; } /* -- cgit v1.2.3 From bd61e0a9c852de2d705b6f1bb2cc54c5774db570 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:55 -0500 Subject: locks: convert posix locks to file_lock_context Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/ceph/locks.c | 58 +++++++++++++--------------- fs/cifs/file.c | 26 +++++-------- fs/lockd/svcsubs.c | 20 ++++++---- fs/locks.c | 108 +++++++++++++++++++++++++++------------------------- fs/nfs/delegation.c | 28 +++++--------- fs/nfs/nfs4state.c | 52 +++++-------------------- fs/nfs/pagelist.c | 8 ++-- fs/nfs/write.c | 30 +++++++-------- fs/nfsd/nfs4state.c | 18 +++++---- fs/read_write.c | 2 +- include/linux/fs.h | 3 +- 11 files changed, 155 insertions(+), 198 deletions(-) (limited to 'fs') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 917656ea8dcf..19beeed83233 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -253,18 +253,15 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) *fcntl_count = 0; *flock_count = 0; - spin_lock(&inode->i_lock); - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_POSIX) - ++(*fcntl_count); - } - ctx = inode->i_flctx; if (ctx) { + spin_lock(&inode->i_lock); + list_for_each_entry(lock, &ctx->flc_posix, fl_list) + ++(*fcntl_count); list_for_each_entry(lock, &ctx->flc_flock, fl_list) ++(*flock_count); + spin_unlock(&inode->i_lock); } - spin_unlock(&inode->i_lock); dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); } @@ -279,7 +276,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, int num_fcntl_locks, int num_flock_locks) { struct file_lock *lock; - struct file_lock_context *ctx; + struct file_lock_context *ctx = inode->i_flctx; int err = 0; int seen_fcntl = 0; int seen_flock = 0; @@ -288,34 +285,31 @@ int ceph_encode_locks_to_buffer(struct inode *inode, dout("encoding %d flock and %d fcntl locks", num_flock_locks, num_fcntl_locks); + if (!ctx) + return 0; + spin_lock(&inode->i_lock); - for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) { - if (lock->fl_flags & FL_POSIX) { - ++seen_fcntl; - if (seen_fcntl > num_fcntl_locks) { - err = -ENOSPC; - goto fail; - } - err = lock_to_ceph_filelock(lock, &flocks[l]); - if (err) - goto fail; - ++l; + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_fcntl; + if (seen_fcntl > num_fcntl_locks) { + err = -ENOSPC; + goto fail; } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; } - - ctx = inode->i_flctx; - if (ctx) { - list_for_each_entry(lock, &ctx->flc_flock, fl_list) { - ++seen_flock; - if (seen_flock > num_flock_locks) { - err = -ENOSPC; - goto fail; - } - err = lock_to_ceph_filelock(lock, &flocks[l]); - if (err) - goto fail; - ++l; + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_flock; + if (seen_flock > num_flock_locks) { + err = -ENOSPC; + goto fail; } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; } fail: spin_unlock(&inode->i_lock); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 96b7e9b7706d..ea78f6f81ce2 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1109,11 +1109,6 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) return rc; } -/* copied from fs/locks.c with a name change */ -#define cifs_for_each_lock(inode, lockp) \ - for (lockp = &inode->i_flock; *lockp != NULL; \ - lockp = &(*lockp)->fl_next) - struct lock_to_push { struct list_head llist; __u64 offset; @@ -1128,8 +1123,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) { struct inode *inode = cfile->dentry->d_inode; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct file_lock *flock, **before; - unsigned int count = 0, i = 0; + struct file_lock *flock; + struct file_lock_context *flctx = inode->i_flctx; + unsigned int count = 0, i; int rc = 0, xid, type; struct list_head locks_to_send, *el; struct lock_to_push *lck, *tmp; @@ -1137,10 +1133,12 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) xid = get_xid(); + if (!flctx) + goto out; + spin_lock(&inode->i_lock); - cifs_for_each_lock(inode, before) { - if ((*before)->fl_flags & FL_POSIX) - count++; + list_for_each(el, &flctx->flc_posix) { + count++; } spin_unlock(&inode->i_lock); @@ -1151,7 +1149,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) * added to the list while we are holding cinode->lock_sem that * protects locking operations of this inode. */ - for (; i < count; i++) { + for (i = 0; i < count; i++) { lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL); if (!lck) { rc = -ENOMEM; @@ -1162,10 +1160,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) el = locks_to_send.next; spin_lock(&inode->i_lock); - cifs_for_each_lock(inode, before) { - flock = *before; - if ((flock->fl_flags & FL_POSIX) == 0) - continue; + list_for_each_entry(flock, &flctx->flc_posix, fl_list) { if (el == &locks_to_send) { /* * The list ended. We don't have enough allocated @@ -1185,7 +1180,6 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) lck->length = length; lck->type = type; lck->offset = flock->fl_start; - el = el->next; } spin_unlock(&inode->i_lock); diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index d12ff4e2dbe7..5300bb53835f 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -164,12 +164,15 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; struct nlm_host *lockhost; + if (!flctx || list_empty_careful(&flctx->flc_posix)) + return 0; again: file->f_locks = 0; spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl; fl = fl->fl_next) { + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_lmops != &nlmsvc_lock_operations) continue; @@ -223,18 +226,21 @@ nlm_file_inuse(struct nlm_file *file) { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; + struct file_lock_context *flctx = inode->i_flctx; if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; - spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl; fl = fl->fl_next) { - if (fl->fl_lmops == &nlmsvc_lock_operations) { - spin_unlock(&inode->i_lock); - return 1; + if (flctx && !list_empty_careful(&flctx->flc_posix)) { + spin_lock(&inode->i_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_lmops == &nlmsvc_lock_operations) { + spin_unlock(&inode->i_lock); + return 1; + } } + spin_unlock(&inode->i_lock); } - spin_unlock(&inode->i_lock); file->f_locks = 0; return 0; } diff --git a/fs/locks.c b/fs/locks.c index 055df53f19de..e50bb4d9e757 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -157,9 +157,6 @@ static int target_leasetype(struct file_lock *fl) int leases_enable = 1; int lease_break_time = 45; -#define for_each_lock(inode, lockp) \ - for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next) - /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock via @@ -218,6 +215,7 @@ locks_get_lock_context(struct inode *inode) goto out; INIT_LIST_HEAD(&new->flc_flock); + INIT_LIST_HEAD(&new->flc_posix); /* * Assign the pointer if it's not already assigned. If it is, then @@ -241,6 +239,7 @@ locks_free_lock_context(struct file_lock_context *ctx) { if (ctx) { WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); + WARN_ON_ONCE(!list_empty(&ctx->flc_posix)); kmem_cache_free(flctx_cache, ctx); } } @@ -809,21 +808,26 @@ void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; + struct file_lock_context *ctx; struct inode *inode = file_inode(filp); + ctx = inode->i_flctx; + if (!ctx || list_empty_careful(&ctx->flc_posix)) { + fl->fl_type = F_UNLCK; + return; + } + spin_lock(&inode->i_lock); - for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) { - if (!IS_POSIX(cfl)) - continue; - if (posix_locks_conflict(fl, cfl)) - break; + list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { + if (posix_locks_conflict(fl, cfl)) { + locks_copy_conflock(fl, cfl); + if (cfl->fl_nspid) + fl->fl_pid = pid_vnr(cfl->fl_nspid); + goto out; + } } - if (cfl) { - locks_copy_conflock(fl, cfl); - if (cfl->fl_nspid) - fl->fl_pid = pid_vnr(cfl->fl_nspid); - } else - fl->fl_type = F_UNLCK; + fl->fl_type = F_UNLCK; +out: spin_unlock(&inode->i_lock); return; } @@ -983,16 +987,20 @@ out: static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { - struct file_lock *fl; + struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; - struct file_lock **before; + struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. @@ -1013,8 +1021,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * blocker's list of waiters and the global blocked_hash. */ if (request->fl_type != F_UNLCK) { - for_each_lock(inode, before) { - fl = *before; + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (!IS_POSIX(fl)) continue; if (!posix_locks_conflict(request, fl)) @@ -1044,29 +1051,25 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str if (request->fl_flags & FL_ACCESS) goto out; - /* - * Find the first old lock with the same owner as the new lock. - */ - - before = &inode->i_flock; - - /* First skip locks owned by other processes. */ - while ((fl = *before) && (!IS_POSIX(fl) || - !posix_same_owner(request, fl))) { - before = &fl->fl_next; + /* Find the first old lock with the same owner as the new lock */ + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { + if (posix_same_owner(request, fl)) + break; } /* Process locks with this owner. */ - while ((fl = *before) && posix_same_owner(request, fl)) { - /* Detect adjacent or overlapping regions (if same lock type) - */ + list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) { + if (!posix_same_owner(request, fl)) + break; + + /* Detect adjacent or overlapping regions (if same lock type) */ if (request->fl_type == fl->fl_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) - goto next_lock; + continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ @@ -1087,18 +1090,17 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str else request->fl_end = fl->fl_end; if (added) { - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &dispose); continue; } request = fl; added = true; - } - else { + } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) - goto next_lock; + continue; if (fl->fl_start > request->fl_end) break; if (request->fl_type == F_UNLCK) @@ -1117,7 +1119,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * one (This may happen several times). */ if (added) { - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &dispose); continue; } /* @@ -1133,15 +1135,11 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_copy_lock(new_fl, request); request = new_fl; new_fl = NULL; - locks_delete_lock(before, &dispose); - locks_insert_lock(before, request); + locks_insert_lock_ctx(request, &fl->fl_list); + locks_delete_lock_ctx(fl, &dispose); added = true; } } - /* Go on to next lock. - */ - next_lock: - before = &fl->fl_next; } /* @@ -1166,7 +1164,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str goto out; } locks_copy_lock(new_fl, request); - locks_insert_lock(before, new_fl); + locks_insert_lock_ctx(new_fl, &fl->fl_list); new_fl = NULL; } if (right) { @@ -1177,7 +1175,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); - locks_insert_lock(before, left); + locks_insert_lock_ctx(left, &fl->fl_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(right); @@ -1257,22 +1255,29 @@ EXPORT_SYMBOL(posix_lock_file_wait); */ int locks_mandatory_locked(struct file *file) { + int ret; struct inode *inode = file_inode(file); + struct file_lock_context *ctx; struct file_lock *fl; + ctx = inode->i_flctx; + if (!ctx || list_empty_careful(&ctx->flc_posix)) + return 0; + /* * Search the lock list for this inode for any POSIX locks. */ spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!IS_POSIX(fl)) - continue; + ret = 0; + list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (fl->fl_owner != current->files && - fl->fl_owner != file) + fl->fl_owner != file) { + ret = -EAGAIN; break; + } } spin_unlock(&inode->i_lock); - return fl ? -EAGAIN : 0; + return ret; } /** @@ -2389,13 +2394,14 @@ out: void locks_remove_posix(struct file *filp, fl_owner_t owner) { struct file_lock lock; + struct file_lock_context *ctx = file_inode(filp)->i_flctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - if (!file_inode(filp)->i_flock) + if (!ctx || list_empty(&ctx->flc_posix)) return; lock.fl_type = F_UNLCK; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 9f9f67b17e2b..3fb1caa3874d 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -85,17 +85,17 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ { struct inode *inode = state->inode; struct file_lock *fl; - struct file_lock_context *flctx; + struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; int status = 0; - if (inode->i_flock == NULL && inode->i_flctx == NULL) + if (flctx == NULL) goto out; - /* Protect inode->i_flock using the i_lock */ + list = &flctx->flc_posix; spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & (FL_POSIX))) - continue; +restart: + list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file) != ctx) continue; spin_unlock(&inode->i_lock); @@ -104,19 +104,9 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ goto out; spin_lock(&inode->i_lock); } - - flctx = inode->i_flctx; - if (flctx) { - list_for_each_entry(fl, &flctx->flc_flock, fl_list) { - if (nfs_file_open_context(fl->fl_file) != ctx) - continue; - spin_unlock(&inode->i_lock); - status = nfs4_lock_delegation_recall(fl, state, - stateid); - if (status < 0) - goto out; - spin_lock(&inode->i_lock); - } + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; } spin_unlock(&inode->i_lock); out: diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 65c404bf61ae..6084c267f3a0 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1367,53 +1367,18 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ struct file_lock *fl; int status = 0; struct file_lock_context *flctx = inode->i_flctx; + struct list_head *list; - if (inode->i_flock == NULL && flctx == NULL) + if (flctx == NULL) return 0; + list = &flctx->flc_posix; + /* Guard against delegation returns and new lock/unlock calls */ down_write(&nfsi->rwsem); - /* Protect inode->i_flock using the BKL */ spin_lock(&inode->i_lock); - for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { - if (!(fl->fl_flags & FL_POSIX)) - continue; - if (nfs_file_open_context(fl->fl_file)->state != state) - continue; - spin_unlock(&inode->i_lock); - status = ops->recover_lock(state, fl); - switch (status) { - case 0: - break; - case -ESTALE: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_STALE_STATEID: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_EXPIRED: - case -NFS4ERR_NO_GRACE: - case -NFS4ERR_STALE_CLIENTID: - case -NFS4ERR_BADSESSION: - case -NFS4ERR_BADSLOT: - case -NFS4ERR_BAD_HIGH_SLOT: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: - goto out; - default: - printk(KERN_ERR "NFS: %s: unhandled error %d\n", - __func__, status); - case -ENOMEM: - case -NFS4ERR_DENIED: - case -NFS4ERR_RECLAIM_BAD: - case -NFS4ERR_RECLAIM_CONFLICT: - /* kill_proc(fl->fl_pid, SIGLOST, 1); */ - status = 0; - } - spin_lock(&inode->i_lock); - } - - if (!flctx) - goto out_unlock; - - list_for_each_entry(fl, &flctx->flc_flock, fl_list) { +restart: + list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file)->state != state) continue; spin_unlock(&inode->i_lock); @@ -1445,7 +1410,10 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ } spin_lock(&inode->i_lock); } -out_unlock: + if (list == &flctx->flc_posix) { + list = &flctx->flc_flock; + goto restart; + } spin_unlock(&inode->i_lock); out: up_write(&nfsi->rwsem); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index a3b62e15b444..29c7f33c9cf1 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -831,12 +831,10 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, if (prev) { if (!nfs_match_open_context(req->wb_context, prev->wb_context)) return false; - if (req->wb_context->dentry->d_inode->i_flock != NULL && - !nfs_match_lock_context(req->wb_lock_context, - prev->wb_lock_context)) - return false; flctx = req->wb_context->dentry->d_inode->i_flctx; - if (flctx != NULL && !list_empty_careful(&flctx->flc_flock) && + if (flctx != NULL && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock)) && !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context)) return false; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e072aeb34195..784c13485b3f 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1091,6 +1091,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) { struct nfs_open_context *ctx = nfs_file_open_context(file); struct nfs_lock_context *l_ctx; + struct file_lock_context *flctx = file_inode(file)->i_flctx; struct nfs_page *req; int do_flush, status; /* @@ -1109,12 +1110,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page) do_flush = req->wb_page != page || req->wb_context != ctx; /* for now, flush if more than 1 request in page_group */ do_flush |= req->wb_this_page != req; - if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) { - do_flush |= l_ctx->lockowner.l_owner != current->files - || l_ctx->lockowner.l_pid != current->tgid; - } - if (l_ctx && ctx->dentry->d_inode->i_flctx && - !list_empty_careful(&ctx->dentry->d_inode->i_flctx->flc_flock)) { + if (l_ctx && flctx && + !(list_empty_careful(&flctx->flc_posix) && + list_empty_careful(&flctx->flc_flock))) { do_flush |= l_ctx->lockowner.l_owner != current->files || l_ctx->lockowner.l_pid != current->tgid; } @@ -1202,26 +1200,24 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino return 0; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return 1; - if (!inode->i_flock && !flctx) + if (!flctx || (list_empty_careful(&flctx->flc_flock) && + list_empty_careful(&flctx->flc_posix))) return 0; /* Check to see if there are whole file write locks */ - spin_lock(&inode->i_lock); ret = 0; - - fl = inode->i_flock; - if (fl && is_whole_file_wrlock(fl)) { - ret = 1; - goto out; - } - - if (!list_empty(&flctx->flc_flock)) { + spin_lock(&inode->i_lock); + if (!list_empty(&flctx->flc_posix)) { + fl = list_first_entry(&flctx->flc_posix, struct file_lock, + fl_list); + if (is_whole_file_wrlock(fl)) + ret = 1; + } else if (!list_empty(&flctx->flc_flock)) { fl = list_first_entry(&flctx->flc_flock, struct file_lock, fl_list); if (fl->fl_type == F_WRLCK) ret = 1; } -out: spin_unlock(&inode->i_lock); return ret; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c06a1ba80d73..fad821991369 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5556,10 +5556,11 @@ out_nfserr: static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { - struct file_lock **flpp; + struct file_lock *fl; int status = false; struct file *filp = find_any_file(fp); struct inode *inode; + struct file_lock_context *flctx; if (!filp) { /* Any valid lock stateid should have some sort of access */ @@ -5568,15 +5569,18 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } inode = file_inode(filp); + flctx = inode->i_flctx; - spin_lock(&inode->i_lock); - for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) { - if ((*flpp)->fl_owner == (fl_owner_t)lowner) { - status = true; - break; + if (flctx && !list_empty_careful(&flctx->flc_posix)) { + spin_lock(&inode->i_lock); + list_for_each_entry(fl, &flctx->flc_posix, fl_list) { + if (fl->fl_owner == (fl_owner_t)lowner) { + status = true; + break; + } } + spin_unlock(&inode->i_lock); } - spin_unlock(&inode->i_lock); fput(filp); return status; } diff --git a/fs/read_write.c b/fs/read_write.c index c0805c93b6fa..4060691e78f7 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -358,7 +358,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t return retval; } - if (unlikely(inode->i_flock && mandatory_lock(inode))) { + if (unlikely(inode->i_flctx && mandatory_lock(inode))) { retval = locks_mandatory_area( read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, inode, file, pos, count); diff --git a/include/linux/fs.h b/include/linux/fs.h index dec0d38b05de..571f113588e9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -968,6 +968,7 @@ struct file_lock { struct file_lock_context { struct list_head flc_flock; + struct list_head flc_posix; }; /* The following constant reflects the upper bound of the file/locking space */ @@ -1971,7 +1972,7 @@ static inline int locks_verify_truncate(struct inode *inode, struct file *filp, loff_t size) { - if (inode->i_flock && mandatory_lock(inode)) + if (inode->i_flctx && mandatory_lock(inode)) return locks_mandatory_area( FLOCK_VERIFY_WRITE, inode, filp, size < inode->i_size ? size : inode->i_size, -- cgit v1.2.3 From 8634b51f6ca298fb8b07aa4847340764903533ab Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:55 -0500 Subject: locks: convert lease handling to file_lock_context Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/locks.c | 252 +++++++++++++++++++++-------------------------------- include/linux/fs.h | 5 +- 2 files changed, 102 insertions(+), 155 deletions(-) (limited to 'fs') diff --git a/fs/locks.c b/fs/locks.c index e50bb4d9e757..d46e70567b99 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -216,6 +216,7 @@ locks_get_lock_context(struct inode *inode) INIT_LIST_HEAD(&new->flc_flock); INIT_LIST_HEAD(&new->flc_posix); + INIT_LIST_HEAD(&new->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then @@ -240,6 +241,7 @@ locks_free_lock_context(struct file_lock_context *ctx) if (ctx) { WARN_ON_ONCE(!list_empty(&ctx->flc_flock)); WARN_ON_ONCE(!list_empty(&ctx->flc_posix)); + WARN_ON_ONCE(!list_empty(&ctx->flc_lease)); kmem_cache_free(flctx_cache, ctx); } } @@ -677,22 +679,6 @@ static void locks_wake_up_blocks(struct file_lock *blocker) spin_unlock(&blocked_lock_lock); } -/* Insert file lock fl into an inode's lock list at the position indicated - * by pos. At the same time add the lock to the global file lock list. - * - * Must be called with the i_lock held! - */ -static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) -{ - fl->fl_nspid = get_pid(task_tgid(current)); - - /* insert into file's list */ - fl->fl_next = *pos; - *pos = fl; - - locks_insert_global_locks(fl); -} - static void locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) { @@ -701,63 +687,28 @@ locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) locks_insert_global_locks(fl); } -/** - * locks_delete_lock - Delete a lock and then free it. - * @thisfl_p: pointer that points to the fl_next field of the previous - * inode->i_flock list entry - * - * Unlink a lock from all lists and free the namespace reference, but don't - * free it yet. Wake up processes that are blocked waiting for this lock and - * notify the FS that the lock has been cleared. - * - * Must be called with the i_lock held! - */ -static void locks_unlink_lock(struct file_lock **thisfl_p) +static void +locks_unlink_lock_ctx(struct file_lock *fl) { - struct file_lock *fl = *thisfl_p; - locks_delete_global_locks(fl); - - *thisfl_p = fl->fl_next; - fl->fl_next = NULL; - + list_del_init(&fl->fl_list); if (fl->fl_nspid) { put_pid(fl->fl_nspid); fl->fl_nspid = NULL; } - locks_wake_up_blocks(fl); } -/* - * Unlink a lock from all lists and free it. - * - * Must be called with i_lock held! - */ -static void locks_delete_lock(struct file_lock **thisfl_p, - struct list_head *dispose) +static void +locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) { - struct file_lock *fl = *thisfl_p; - - locks_unlink_lock(thisfl_p); + locks_unlink_lock_ctx(fl); if (dispose) list_add(&fl->fl_list, dispose); else locks_free_lock(fl); } -static void -locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) -{ - locks_delete_global_locks(fl); - if (fl->fl_nspid) { - put_pid(fl->fl_nspid); - fl->fl_nspid = NULL; - } - locks_wake_up_blocks(fl); - list_move(&fl->fl_list, dispose); -} - /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ @@ -1376,7 +1327,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } - locks_delete_lock(before, dispose); + locks_delete_lock_ctx(fl, dispose); } return 0; } @@ -1392,20 +1343,17 @@ static bool past_time(unsigned long then) static void time_out_leases(struct inode *inode, struct list_head *dispose) { - struct file_lock **before; - struct file_lock *fl; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl, *tmp; lockdep_assert_held(&inode->i_lock); - before = &inode->i_flock; - while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) { + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) - lease_modify(before, F_RDLCK, dispose); + lease_modify(&fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) - lease_modify(before, F_UNLCK, dispose); - if (fl == *before) /* lease_modify may have freed fl */ - before = &fl->fl_next; + lease_modify(&fl, F_UNLCK, dispose); } } @@ -1419,11 +1367,12 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) static bool any_leases_conflict(struct inode *inode, struct file_lock *breaker) { + struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl; lockdep_assert_held(&inode->i_lock); - for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (leases_conflict(fl, breaker)) return true; } @@ -1447,7 +1396,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; struct file_lock *new_fl; - struct file_lock *fl, **before; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); @@ -1457,6 +1407,12 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return PTR_ERR(new_fl); new_fl->fl_flags = type; + /* typically we will check that ctx is non-NULL before calling */ + if (!ctx) { + WARN_ON_ONCE(1); + return error; + } + spin_lock(&inode->i_lock); time_out_leases(inode, &dispose); @@ -1471,9 +1427,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) break_time++; /* so that 0 means no break time */ } - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (!leases_conflict(fl, new_fl)) continue; if (want_write) { @@ -1482,17 +1436,16 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) fl->fl_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { - if (lease_breaking(inode->i_flock)) + if (lease_breaking(fl)) continue; fl->fl_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) - locks_delete_lock(before, &dispose); + locks_delete_lock_ctx(fl, &dispose); } - fl = inode->i_flock; - if (!fl || !IS_LEASE(fl)) + if (list_empty(&ctx->flc_lease)) goto out; if (mode & O_NONBLOCK) { @@ -1502,12 +1455,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) } restart: - break_time = inode->i_flock->fl_break_time; + fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); + break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; - locks_insert_block(inode->i_flock, new_fl); + locks_insert_block(fl, new_fl); trace_break_lease_block(inode, new_fl); spin_unlock(&inode->i_lock); locks_dispose_list(&dispose); @@ -1525,10 +1479,8 @@ restart: time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; - error = 0; } - out: spin_unlock(&inode->i_lock); locks_dispose_list(&dispose); @@ -1550,13 +1502,17 @@ EXPORT_SYMBOL(__break_lease); void lease_get_mtime(struct inode *inode, struct timespec *time) { bool has_lease = false; - struct file_lock *flock; + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl; - if (inode->i_flock) { + if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&inode->i_lock); - flock = inode->i_flock; - if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK)) - has_lease = true; + if (!list_empty(&ctx->flc_lease)) { + fl = list_first_entry(&ctx->flc_lease, + struct file_lock, fl_list); + if (fl->fl_type == F_WRLCK) + has_lease = true; + } spin_unlock(&inode->i_lock); } @@ -1595,20 +1551,22 @@ int fcntl_getlease(struct file *filp) { struct file_lock *fl; struct inode *inode = file_inode(filp); + struct file_lock_context *ctx = inode->i_flctx; int type = F_UNLCK; LIST_HEAD(dispose); - spin_lock(&inode->i_lock); - time_out_leases(file_inode(filp), &dispose); - for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl); - fl = fl->fl_next) { - if (fl->fl_file == filp) { + if (ctx && !list_empty_careful(&ctx->flc_lease)) { + spin_lock(&inode->i_lock); + time_out_leases(file_inode(filp), &dispose); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file != filp) + continue; type = target_leasetype(fl); break; } + spin_unlock(&inode->i_lock); + locks_dispose_list(&dispose); } - spin_unlock(&inode->i_lock); - locks_dispose_list(&dispose); return type; } @@ -1641,9 +1599,10 @@ check_conflicting_open(const struct dentry *dentry, const long arg) static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { - struct file_lock *fl, **before, **my_before = NULL, *lease; + struct file_lock *fl, *my_fl = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; + struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; LIST_HEAD(dispose); @@ -1651,6 +1610,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr lease = *flp; trace_generic_add_lease(inode, lease); + ctx = locks_get_lock_context(inode); + if (!ctx) + return -ENOMEM; + /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_mutex. We trylock @@ -1684,13 +1647,12 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * except for this filp. */ error = -EAGAIN; - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp) { - my_before = before; + my_fl = fl; continue; } + /* * No exclusive leases if someone else has a lease on * this file: @@ -1705,9 +1667,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr goto out; } - if (my_before != NULL) { - lease = *my_before; - error = lease->fl_lmops->lm_change(my_before, arg, &dispose); + if (my_fl != NULL) { + error = lease->fl_lmops->lm_change(&my_fl, arg, &dispose); if (error) goto out; goto out_setup; @@ -1717,7 +1678,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr if (!leases_enable) goto out; - locks_insert_lock(before, lease); + locks_insert_lock_ctx(lease, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting @@ -1729,8 +1690,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr */ smp_mb(); error = check_conflicting_open(dentry, arg); - if (error) - goto out_unlink; + if (error) { + locks_unlink_lock_ctx(lease); + goto out; + } out_setup: if (lease->fl_lmops->lm_setup) @@ -1740,33 +1703,35 @@ out: locks_dispose_list(&dispose); if (is_deleg) mutex_unlock(&inode->i_mutex); - if (!error && !my_before) + if (!error && !my_fl) *flp = NULL; return error; -out_unlink: - locks_unlink_lock(before); - goto out; } static int generic_delete_lease(struct file *filp) { int error = -EAGAIN; - struct file_lock *fl, **before; + struct file_lock *fl, *victim = NULL; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; + struct file_lock_context *ctx = inode->i_flctx; LIST_HEAD(dispose); + if (!ctx) { + trace_generic_delete_lease(inode, NULL); + return error; + } + spin_lock(&inode->i_lock); - time_out_leases(inode, &dispose); - for (before = &inode->i_flock; - ((fl = *before) != NULL) && IS_LEASE(fl); - before = &fl->fl_next) { - if (fl->fl_file == filp) + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file == filp) { + victim = fl; break; + } } trace_generic_delete_lease(inode, fl); - if (fl && IS_LEASE(fl)) - error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose); + if (victim) + error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose); spin_unlock(&inode->i_lock); locks_dispose_list(&dispose); return error; @@ -2447,56 +2412,37 @@ locks_remove_flock(struct file *filp) fl.fl_ops->fl_release_private(&fl); } +static void +locks_remove_lease(struct file *filp) +{ + struct inode *inode = file_inode(filp); + struct file_lock_context *ctx = inode->i_flctx; + struct file_lock *fl, *tmp; + LIST_HEAD(dispose); + + if (!ctx || list_empty(&ctx->flc_lease)) + return; + + spin_lock(&inode->i_lock); + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) + lease_modify(&fl, F_UNLCK, &dispose); + spin_unlock(&inode->i_lock); + locks_dispose_list(&dispose); +} + /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { - struct inode * inode = file_inode(filp); - struct file_lock *fl; - struct file_lock **before; - LIST_HEAD(dispose); - /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ locks_remove_flock(filp); - if (!inode->i_flock) - return; - - spin_lock(&inode->i_lock); - before = &inode->i_flock; - - while ((fl = *before) != NULL) { - if (fl->fl_file == filp) { - if (IS_LEASE(fl)) { - lease_modify(before, F_UNLCK, &dispose); - continue; - } - - /* - * There's a leftover lock on the list of a type that - * we didn't expect to see. Most likely a classic - * POSIX lock that ended up not getting released - * properly, or that raced onto the list somehow. Log - * some info about it and then just remove it from - * the list. - */ - WARN(1, "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", - MAJOR(inode->i_sb->s_dev), - MINOR(inode->i_sb->s_dev), inode->i_ino, - fl->fl_type, fl->fl_flags, - fl->fl_start, fl->fl_end); - - locks_delete_lock(before, &dispose); - continue; - } - before = &fl->fl_next; - } - spin_unlock(&inode->i_lock); - locks_dispose_list(&dispose); + /* remove any leases */ + locks_remove_lease(filp); } /** diff --git a/include/linux/fs.h b/include/linux/fs.h index 571f113588e9..2ddec3cf81b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -969,6 +969,7 @@ struct file_lock { struct file_lock_context { struct list_head flc_flock; struct list_head flc_posix; + struct list_head flc_lease; }; /* The following constant reflects the upper bound of the file/locking space */ @@ -1990,7 +1991,7 @@ static inline int break_lease(struct inode *inode, unsigned int mode) * end up racing with tasks trying to set a new lease on this file. */ smp_mb(); - if (inode->i_flock) + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } @@ -2003,7 +2004,7 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) * end up racing with tasks trying to set a new lease on this file. */ smp_mb(); - if (inode->i_flock) + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } -- cgit v1.2.3 From 6109c85037e53443f29fd39c0de69f578a1cf285 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: add a dedicated spinlock to protect i_flctx lists We can now add a dedicated spinlock without expanding struct inode. Change to using that to protect the various i_flctx lists. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/ceph/locks.c | 8 ++--- fs/cifs/file.c | 8 ++--- fs/lockd/svcsubs.c | 12 ++++---- fs/locks.c | 87 +++++++++++++++++++++++++++-------------------------- fs/nfs/delegation.c | 8 ++--- fs/nfs/nfs4state.c | 8 ++--- fs/nfs/write.c | 4 +-- fs/nfsd/nfs4state.c | 4 +-- include/linux/fs.h | 1 + 9 files changed, 71 insertions(+), 69 deletions(-) (limited to 'fs') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 19beeed83233..0303da8e3233 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -255,12 +255,12 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) ctx = inode->i_flctx; if (ctx) { - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry(lock, &ctx->flc_posix, fl_list) ++(*fcntl_count); list_for_each_entry(lock, &ctx->flc_flock, fl_list) ++(*flock_count); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); } dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); @@ -288,7 +288,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, if (!ctx) return 0; - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry(lock, &ctx->flc_flock, fl_list) { ++seen_fcntl; if (seen_fcntl > num_fcntl_locks) { @@ -312,7 +312,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, ++l; } fail: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); return err; } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index ea78f6f81ce2..b65166eb111e 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1136,11 +1136,11 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) if (!flctx) goto out; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each(el, &flctx->flc_posix) { count++; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); INIT_LIST_HEAD(&locks_to_send); @@ -1159,7 +1159,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) } el = locks_to_send.next; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each_entry(flock, &flctx->flc_posix, fl_list) { if (el == &locks_to_send) { /* @@ -1181,7 +1181,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) lck->type = type; lck->offset = flock->fl_start; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) { int stored_rc; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 5300bb53835f..665ef5a05183 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -171,7 +171,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, return 0; again: file->f_locks = 0; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_lmops != &nlmsvc_lock_operations) continue; @@ -183,7 +183,7 @@ again: if (match(lockhost, host)) { struct file_lock lock = *fl; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); lock.fl_type = F_UNLCK; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; @@ -195,7 +195,7 @@ again: goto again; } } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); return 0; } @@ -232,14 +232,14 @@ nlm_file_inuse(struct nlm_file *file) return 1; if (flctx && !list_empty_careful(&flctx->flc_posix)) { - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_lmops == &nlmsvc_lock_operations) { - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); return 1; } } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); } file->f_locks = 0; return 0; diff --git a/fs/locks.c b/fs/locks.c index d46e70567b99..a268d959ccd6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -161,7 +161,7 @@ int lease_break_time = 45; * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock via * the file_lock_lglock. Note that alterations to the list also require that - * the relevant i_lock is held. + * the relevant flc_lock is held. */ DEFINE_STATIC_LGLOCK(file_lock_lglock); static DEFINE_PER_CPU(struct hlist_head, file_lock_list); @@ -189,13 +189,13 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); * contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, - * we often hold the i_lock as well. In certain cases, when reading the fields + * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the - * i_lock. + * flc_lock. * * In particular, adding an entry to the fl_block list requires that you hold - * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting - * an entry from the list however only requires the file_lock_lock. + * both the flc_lock and the blocked_lock_lock (acquired in that order). + * Deleting an entry from the list however only requires the file_lock_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); @@ -214,6 +214,7 @@ locks_get_lock_context(struct inode *inode) if (!new) goto out; + spin_lock_init(&new->flc_lock); INIT_LIST_HEAD(&new->flc_flock); INIT_LIST_HEAD(&new->flc_posix); INIT_LIST_HEAD(&new->flc_lease); @@ -557,7 +558,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) return fl1->fl_owner == fl2->fl_owner; } -/* Must be called with the i_lock held! */ +/* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock *fl) { lg_local_lock(&file_lock_lglock); @@ -566,12 +567,12 @@ static void locks_insert_global_locks(struct file_lock *fl) lg_local_unlock(&file_lock_lglock); } -/* Must be called with the i_lock held! */ +/* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock *fl) { /* * Avoid taking lock if already unhashed. This is safe since this check - * is done while holding the i_lock, and new insertions into the list + * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&fl->fl_link)) @@ -623,10 +624,10 @@ static void locks_delete_block(struct file_lock *waiter) * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * - * Must be called with both the i_lock and blocked_lock_lock held. The fl_block - * list itself is protected by the blocked_lock_lock, but by ensuring that the - * i_lock is also held on insertions we can avoid taking the blocked_lock_lock - * in some cases when we see that the fl_block list is empty. + * Must be called with both the flc_lock and blocked_lock_lock held. The + * fl_block list itself is protected by the blocked_lock_lock, but by ensuring + * that the flc_lock is also held on insertions we can avoid taking the + * blocked_lock_lock in some cases when we see that the fl_block list is empty. */ static void __locks_insert_block(struct file_lock *blocker, struct file_lock *waiter) @@ -638,7 +639,7 @@ static void __locks_insert_block(struct file_lock *blocker, locks_insert_global_blocked(waiter); } -/* Must be called with i_lock held. */ +/* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock *blocker, struct file_lock *waiter) { @@ -650,15 +651,15 @@ static void locks_insert_block(struct file_lock *blocker, /* * Wake up processes blocked waiting for blocker. * - * Must be called with the inode->i_lock held! + * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new - * blocked requests are only added to the list under the i_lock, and - * the i_lock is always held here. Note that removal from the fl_block - * list does not require the i_lock, so we must recheck list_empty() + * blocked requests are only added to the list under the flc_lock, and + * the flc_lock is always held here. Note that removal from the fl_block + * list does not require the flc_lock, so we must recheck list_empty() * after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->fl_block)) @@ -768,7 +769,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) return; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { if (posix_locks_conflict(fl, cfl)) { locks_copy_conflock(fl, cfl); @@ -779,7 +780,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) } fl->fl_type = F_UNLCK; out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); @@ -880,7 +881,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) return -ENOMEM; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; @@ -905,9 +906,9 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) * give it the opportunity to lock the file. */ if (found) { - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); cond_resched(); - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); } find_conflict: @@ -929,7 +930,7 @@ find_conflict: error = 0; out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -965,7 +966,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str new_fl2 = locks_alloc_lock(); } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the @@ -1136,7 +1137,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_wake_up_blocks(left); } out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); /* * Free any unused locks. */ @@ -1218,7 +1219,7 @@ int locks_mandatory_locked(struct file *file) /* * Search the lock list for this inode for any POSIX locks. */ - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); ret = 0; list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (fl->fl_owner != current->files && @@ -1227,7 +1228,7 @@ int locks_mandatory_locked(struct file *file) break; } } - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); return ret; } @@ -1346,7 +1347,7 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl, *tmp; - lockdep_assert_held(&inode->i_lock); + lockdep_assert_held(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); @@ -1370,7 +1371,7 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker) struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl; - lockdep_assert_held(&inode->i_lock); + lockdep_assert_held(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (leases_conflict(fl, breaker)) @@ -1413,7 +1414,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) return error; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1463,11 +1464,11 @@ restart: break_time++; locks_insert_block(fl, new_fl); trace_break_lease_block(inode, new_fl); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_next, break_time); - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); if (error >= 0) { @@ -1482,7 +1483,7 @@ restart: error = 0; } out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); locks_free_lock(new_fl); return error; @@ -1506,14 +1507,14 @@ void lease_get_mtime(struct inode *inode, struct timespec *time) struct file_lock *fl; if (ctx && !list_empty_careful(&ctx->flc_lease)) { - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); if (!list_empty(&ctx->flc_lease)) { fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); if (fl->fl_type == F_WRLCK) has_lease = true; } - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); } if (has_lease) @@ -1556,7 +1557,7 @@ int fcntl_getlease(struct file *filp) LIST_HEAD(dispose); if (ctx && !list_empty_careful(&ctx->flc_lease)) { - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); time_out_leases(file_inode(filp), &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file != filp) @@ -1564,7 +1565,7 @@ int fcntl_getlease(struct file *filp) type = target_leasetype(fl); break; } - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); } return type; @@ -1632,7 +1633,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr return -EINVAL; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(dentry, arg); if (error) @@ -1699,7 +1700,7 @@ out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); if (is_deleg) mutex_unlock(&inode->i_mutex); @@ -1722,7 +1723,7 @@ static int generic_delete_lease(struct file *filp) return error; } - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp) { victim = fl; @@ -1732,7 +1733,7 @@ static int generic_delete_lease(struct file *filp) trace_generic_delete_lease(inode, fl); if (victim) error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); return error; } @@ -2423,10 +2424,10 @@ locks_remove_lease(struct file *filp) if (!ctx || list_empty(&ctx->flc_lease)) return; - spin_lock(&inode->i_lock); + spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) lease_modify(&fl, F_UNLCK, &dispose); - spin_unlock(&inode->i_lock); + spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 3fb1caa3874d..8cdb2b28a104 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -93,22 +93,22 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ goto out; list = &flctx->flc_posix; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); restart: list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file) != ctx) continue; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); status = nfs4_lock_delegation_recall(fl, state, stateid); if (status < 0) goto out; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); } if (list == &flctx->flc_posix) { list = &flctx->flc_flock; goto restart; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); out: return status; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 6084c267f3a0..a3bb22ab68c5 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1376,12 +1376,12 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ /* Guard against delegation returns and new lock/unlock calls */ down_write(&nfsi->rwsem); - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); restart: list_for_each_entry(fl, list, fl_list) { if (nfs_file_open_context(fl->fl_file)->state != state) continue; - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); status = ops->recover_lock(state, fl); switch (status) { case 0: @@ -1408,13 +1408,13 @@ restart: /* kill_proc(fl->fl_pid, SIGLOST, 1); */ status = 0; } - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); } if (list == &flctx->flc_posix) { list = &flctx->flc_flock; goto restart; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); out: up_write(&nfsi->rwsem); return status; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 784c13485b3f..4ae66f416eb9 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1206,7 +1206,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino /* Check to see if there are whole file write locks */ ret = 0; - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); if (!list_empty(&flctx->flc_posix)) { fl = list_first_entry(&flctx->flc_posix, struct file_lock, fl_list); @@ -1218,7 +1218,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino if (fl->fl_type == F_WRLCK) ret = 1; } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); return ret; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index fad821991369..80242f5bd621 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5572,14 +5572,14 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) flctx = inode->i_flctx; if (flctx && !list_empty_careful(&flctx->flc_posix)) { - spin_lock(&inode->i_lock); + spin_lock(&flctx->flc_lock); list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_owner == (fl_owner_t)lowner) { status = true; break; } } - spin_unlock(&inode->i_lock); + spin_unlock(&flctx->flc_lock); } fput(filp); return status; diff --git a/include/linux/fs.h b/include/linux/fs.h index ce0873af0b97..32eafa9b5c9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -968,6 +968,7 @@ struct file_lock { }; struct file_lock_context { + spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; -- cgit v1.2.3 From 7448cc37b1a6b620d948aaee3bb30960c06d5d5d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: clean up the lm_change prototype Now that we use standard list_heads for tracking leases, we can have lm_change take a pointer to the lease to be modified instead of a double pointer. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/locks.c | 13 ++++++------- fs/nfsd/nfs4state.c | 3 ++- include/linux/fs.h | 6 +++--- 3 files changed, 11 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/locks.c b/fs/locks.c index a268d959ccd6..864f2460a0ad 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1309,9 +1309,8 @@ static void lease_clear_pending(struct file_lock *fl, int arg) } /* We already had a lease on this file; just change its type */ -int lease_modify(struct file_lock **before, int arg, struct list_head *dispose) +int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { - struct file_lock *fl = *before; int error = assign_type(fl, arg); if (error) @@ -1352,9 +1351,9 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) - lease_modify(&fl, F_RDLCK, dispose); + lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) - lease_modify(&fl, F_UNLCK, dispose); + lease_modify(fl, F_UNLCK, dispose); } } @@ -1669,7 +1668,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr } if (my_fl != NULL) { - error = lease->fl_lmops->lm_change(&my_fl, arg, &dispose); + error = lease->fl_lmops->lm_change(my_fl, arg, &dispose); if (error) goto out; goto out_setup; @@ -1732,7 +1731,7 @@ static int generic_delete_lease(struct file *filp) } trace_generic_delete_lease(inode, fl); if (victim) - error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose); + error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); return error; @@ -2426,7 +2425,7 @@ locks_remove_lease(struct file *filp) spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) - lease_modify(&fl, F_UNLCK, &dispose); + lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); locks_dispose_list(&dispose); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 80242f5bd621..532a60cca2fb 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3477,7 +3477,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) } static int -nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose) +nfsd_change_deleg_cb(struct file_lock *onlist, int arg, + struct list_head *dispose) { if (arg & F_UNLCK) return lease_modify(onlist, arg, dispose); diff --git a/include/linux/fs.h b/include/linux/fs.h index 32eafa9b5c9f..94e706a0a408 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -900,7 +900,7 @@ struct lock_manager_operations { void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock **, int, struct list_head *); + int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); }; @@ -1021,7 +1021,7 @@ extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int t extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); -extern int lease_modify(struct file_lock **, int, struct list_head *); +extern int lease_modify(struct file_lock *, int, struct list_head *); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1153,7 +1153,7 @@ static inline int vfs_setlease(struct file *filp, long arg, return -EINVAL; } -static inline int lease_modify(struct file_lock **before, int arg, +static inline int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { return -EINVAL; -- cgit v1.2.3 From 9bd0f45b7037fcfa8b575c7e27d0431d6e6dc3bb Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: keep a count of locks on the flctx lists This makes things a bit more efficient in the cifs and ceph lock pushing code. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- fs/ceph/locks.c | 11 ++--------- fs/cifs/file.c | 14 ++++---------- fs/locks.c | 45 +++++++++++++++++++++++++++++---------------- include/linux/fs.h | 3 +++ 4 files changed, 38 insertions(+), 35 deletions(-) (limited to 'fs') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 0303da8e3233..06ea5cd05cd9 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -242,12 +242,9 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) /* * Fills in the passed counter variables, so you can prepare pagelist metadata * before calling ceph_encode_locks. - * - * FIXME: add counters to struct file_lock_context so we don't need to do this? */ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) { - struct file_lock *lock; struct file_lock_context *ctx; *fcntl_count = 0; @@ -255,12 +252,8 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) ctx = inode->i_flctx; if (ctx) { - spin_lock(&ctx->flc_lock); - list_for_each_entry(lock, &ctx->flc_posix, fl_list) - ++(*fcntl_count); - list_for_each_entry(lock, &ctx->flc_flock, fl_list) - ++(*flock_count); - spin_unlock(&ctx->flc_lock); + *fcntl_count = ctx->flc_posix_cnt; + *flock_count = ctx->flc_flock_cnt; } dout("counted %d flock locks and %d fcntl locks", *flock_count, *fcntl_count); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index b65166eb111e..8c2ca6f62bad 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1125,7 +1125,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct file_lock *flock; struct file_lock_context *flctx = inode->i_flctx; - unsigned int count = 0, i; + unsigned int i; int rc = 0, xid, type; struct list_head locks_to_send, *el; struct lock_to_push *lck, *tmp; @@ -1136,20 +1136,14 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile) if (!flctx) goto out; - spin_lock(&flctx->flc_lock); - list_for_each(el, &flctx->flc_posix) { - count++; - } - spin_unlock(&flctx->flc_lock); - INIT_LIST_HEAD(&locks_to_send); /* - * Allocating count locks is enough because no FL_POSIX locks can be - * added to the list while we are holding cinode->lock_sem that + * Allocating flc_posix_cnt locks is enough because no FL_POSIX locks + * can be added to the list while we are holding cinode->lock_sem that * protects locking operations of this inode. */ - for (i = 0; i < count; i++) { + for (i = 0; i < flctx->flc_posix_cnt; i++) { lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL); if (!lck) { rc = -ENOMEM; diff --git a/fs/locks.c b/fs/locks.c index 864f2460a0ad..bd578700342d 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -681,18 +681,21 @@ static void locks_wake_up_blocks(struct file_lock *blocker) } static void -locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) +locks_insert_lock_ctx(struct file_lock *fl, int *counter, + struct list_head *before) { fl->fl_nspid = get_pid(task_tgid(current)); list_add_tail(&fl->fl_list, before); + ++*counter; locks_insert_global_locks(fl); } static void -locks_unlink_lock_ctx(struct file_lock *fl) +locks_unlink_lock_ctx(struct file_lock *fl, int *counter) { locks_delete_global_locks(fl); list_del_init(&fl->fl_list); + --*counter; if (fl->fl_nspid) { put_pid(fl->fl_nspid); fl->fl_nspid = NULL; @@ -701,9 +704,10 @@ locks_unlink_lock_ctx(struct file_lock *fl) } static void -locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) +locks_delete_lock_ctx(struct file_lock *fl, int *counter, + struct list_head *dispose) { - locks_unlink_lock_ctx(fl); + locks_unlink_lock_ctx(fl, counter); if (dispose) list_add(&fl->fl_list, dispose); else @@ -891,7 +895,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) if (request->fl_type == fl->fl_type) goto out; found = true; - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_flock_cnt, &dispose); break; } @@ -925,7 +929,7 @@ find_conflict: if (request->fl_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); - locks_insert_lock_ctx(new_fl, &ctx->flc_flock); + locks_insert_lock_ctx(new_fl, &ctx->flc_flock_cnt, &ctx->flc_flock); new_fl = NULL; error = 0; @@ -1042,7 +1046,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str else request->fl_end = fl->fl_end; if (added) { - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_posix_cnt, + &dispose); continue; } request = fl; @@ -1071,7 +1076,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str * one (This may happen several times). */ if (added) { - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(fl, + &ctx->flc_posix_cnt, &dispose); continue; } /* @@ -1087,8 +1093,10 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_copy_lock(new_fl, request); request = new_fl; new_fl = NULL; - locks_insert_lock_ctx(request, &fl->fl_list); - locks_delete_lock_ctx(fl, &dispose); + locks_insert_lock_ctx(request, + &ctx->flc_posix_cnt, &fl->fl_list); + locks_delete_lock_ctx(fl, + &ctx->flc_posix_cnt, &dispose); added = true; } } @@ -1116,7 +1124,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str goto out; } locks_copy_lock(new_fl, request); - locks_insert_lock_ctx(new_fl, &fl->fl_list); + locks_insert_lock_ctx(new_fl, &ctx->flc_posix_cnt, + &fl->fl_list); new_fl = NULL; } if (right) { @@ -1127,7 +1136,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); - locks_insert_lock_ctx(left, &fl->fl_list); + locks_insert_lock_ctx(left, &ctx->flc_posix_cnt, + &fl->fl_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(right); @@ -1311,6 +1321,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg) /* We already had a lease on this file; just change its type */ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { + struct file_lock_context *flctx; int error = assign_type(fl, arg); if (error) @@ -1320,6 +1331,7 @@ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) if (arg == F_UNLCK) { struct file *filp = fl->fl_file; + flctx = file_inode(filp)->i_flctx; f_delown(filp); filp->f_owner.signum = 0; fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); @@ -1327,7 +1339,7 @@ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } - locks_delete_lock_ctx(fl, dispose); + locks_delete_lock_ctx(fl, &flctx->flc_lease_cnt, dispose); } return 0; } @@ -1442,7 +1454,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(fl, &ctx->flc_lease_cnt, + &dispose); } if (list_empty(&ctx->flc_lease)) @@ -1678,7 +1691,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr if (!leases_enable) goto out; - locks_insert_lock_ctx(lease, &ctx->flc_lease); + locks_insert_lock_ctx(lease, &ctx->flc_lease_cnt, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting @@ -1691,7 +1704,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr smp_mb(); error = check_conflicting_open(dentry, arg); if (error) { - locks_unlink_lock_ctx(lease); + locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt); goto out; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 94e706a0a408..f87cb2f03103 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -972,6 +972,9 @@ struct file_lock_context { struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; + int flc_flock_cnt; + int flc_posix_cnt; + int flc_lease_cnt; }; /* The following constant reflects the upper bound of the file/locking space */ -- cgit v1.2.3 From 3d8e560de4a076b302cb0cc17e998aaace2b176a Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:58 -0500 Subject: locks: consolidate NULL i_flctx checks in locks_remove_file We have each of the locks_remove_* variants doing this individually. Have the caller do it instead, and have locks_remove_flock and locks_remove_lease just assume that it's a valid pointer. Signed-off-by: Jeff Layton --- fs/locks.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/locks.c b/fs/locks.c index bd578700342d..2fc36b3772a0 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2400,6 +2400,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) EXPORT_SYMBOL(locks_remove_posix); +/* The i_flctx must be valid when calling into here */ static void locks_remove_flock(struct file *filp) { @@ -2413,7 +2414,7 @@ locks_remove_flock(struct file *filp) }; struct file_lock_context *flctx = file_inode(filp)->i_flctx; - if (!flctx || list_empty(&flctx->flc_flock)) + if (list_empty(&flctx->flc_flock)) return; if (filp->f_op->flock) @@ -2425,6 +2426,7 @@ locks_remove_flock(struct file *filp) fl.fl_ops->fl_release_private(&fl); } +/* The i_flctx must be valid when calling into here */ static void locks_remove_lease(struct file *filp) { @@ -2433,7 +2435,7 @@ locks_remove_lease(struct file *filp) struct file_lock *fl, *tmp; LIST_HEAD(dispose); - if (!ctx || list_empty(&ctx->flc_lease)) + if (list_empty(&ctx->flc_lease)) return; spin_lock(&ctx->flc_lock); @@ -2448,6 +2450,9 @@ locks_remove_lease(struct file *filp) */ void locks_remove_file(struct file *filp) { + if (!file_inode(filp)->i_flctx) + return; + /* remove any OFD locks */ locks_remove_posix(filp, filp); -- cgit v1.2.3 From dbaffde76405012778b8815b7721554b1302038e Mon Sep 17 00:00:00 2001 From: Mark Salyzyn Date: Tue, 6 Jan 2015 11:18:24 -0800 Subject: pstore: Use scnprintf() in pstore_mkfile() No guarantees that the names will not exceed the name buffer with future adjustments. Signed-off-by: Mark Salyzyn Acked-by: Kees Cook Signed-off-by: Tony Luck --- fs/pstore/inode.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 50416602774d..d69586f09ffd 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -338,32 +338,35 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, switch (type) { case PSTORE_TYPE_DMESG: - sprintf(name, "dmesg-%s-%lld%s", psname, id, - compressed ? ".enc.z" : ""); + scnprintf(name, sizeof(name), "dmesg-%s-%lld%s", + psname, id, compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: - sprintf(name, "console-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "console-%s-%lld", psname, id); break; case PSTORE_TYPE_FTRACE: - sprintf(name, "ftrace-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "ftrace-%s-%lld", psname, id); break; case PSTORE_TYPE_MCE: - sprintf(name, "mce-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "mce-%s-%lld", psname, id); break; case PSTORE_TYPE_PPC_RTAS: - sprintf(name, "rtas-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "rtas-%s-%lld", psname, id); break; case PSTORE_TYPE_PPC_OF: - sprintf(name, "powerpc-ofw-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "powerpc-ofw-%s-%lld", + psname, id); break; case PSTORE_TYPE_PPC_COMMON: - sprintf(name, "powerpc-common-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "powerpc-common-%s-%lld", + psname, id); break; case PSTORE_TYPE_UNKNOWN: - sprintf(name, "unknown-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id); break; default: - sprintf(name, "type%d-%s-%lld", type, psname, id); + scnprintf(name, sizeof(name), "type%d-%s-%lld", + type, psname, id); break; } -- cgit v1.2.3 From ff6bf6e8024f073ecea7dbf5c6afe6bd3872a569 Mon Sep 17 00:00:00 2001 From: Mark Salyzyn Date: Tue, 13 Jan 2015 14:32:35 -0800 Subject: pstore: Remove superfluous memory size check All previous checks will fail with error if memory size is not sufficient to register a zone, so this legacy check has become redundant. Signed-off-by: Mark Salyzyn Acked-by: Kees Cook Signed-off-by: Tony Luck --- fs/pstore/ram.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'fs') diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 8613e5b35c22..34ed8f860e23 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -474,14 +474,6 @@ static int ramoops_probe(struct platform_device *pdev) if (err) goto fail_init_fprz; - if (!cxt->przs && !cxt->cprz && !cxt->fprz) { - pr_err("memory size too small, minimum is %zu\n", - cxt->console_size + cxt->record_size + - cxt->ftrace_size); - err = -EINVAL; - goto fail_cnt; - } - cxt->pstore.data = cxt; /* * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we @@ -525,7 +517,6 @@ fail_buf: kfree(cxt->pstore.buf); fail_clear: cxt->pstore.bufsize = 0; -fail_cnt: kfree(cxt->fprz); fail_init_fprz: kfree(cxt->cprz); -- cgit v1.2.3 From f44f96528a8cd4134a4f2c1a9d8c785600aa4888 Mon Sep 17 00:00:00 2001 From: Mark Salyzyn Date: Tue, 13 Jan 2015 14:32:50 -0800 Subject: pstore: Handle zero-sized prz in series ramoops_pstore_read fails to return the next in a prz series after first zero-sized entry, not venturing to the next non-zero entry. Signed-off-by: Mark Salyzyn Acked-by: Kees Cook Signed-off-by: Tony Luck --- fs/pstore/ram.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 34ed8f860e23..6150e54eed30 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -164,6 +164,12 @@ static int ramoops_read_kmsg_hdr(char *buffer, struct timespec *time, return header_length; } +static bool prz_ok(struct persistent_ram_zone *prz) +{ + return !!prz && !!(persistent_ram_old_size(prz) + + persistent_ram_ecc_string(prz, NULL, 0)); +} + static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, bool *compressed, @@ -178,13 +184,13 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, prz = ramoops_get_next_prz(cxt->przs, &cxt->dump_read_cnt, cxt->max_dump_cnt, id, type, PSTORE_TYPE_DMESG, 1); - if (!prz) + if (!prz_ok(prz)) prz = ramoops_get_next_prz(&cxt->cprz, &cxt->console_read_cnt, 1, id, type, PSTORE_TYPE_CONSOLE, 0); - if (!prz) + if (!prz_ok(prz)) prz = ramoops_get_next_prz(&cxt->fprz, &cxt->ftrace_read_cnt, 1, id, type, PSTORE_TYPE_FTRACE, 0); - if (!prz) + if (!prz_ok(prz)) return 0; if (!persistent_ram_old(prz)) -- cgit v1.2.3 From 9d5438f462abd6398cdb7b3211bdcec271873a3b Mon Sep 17 00:00:00 2001 From: Mark Salyzyn Date: Fri, 16 Jan 2015 16:01:10 -0800 Subject: pstore: Add pmsg - user-space accessible pstore object A secured user-space accessible pstore object. Writes to /dev/pmsg0 are appended to the buffer, on reboot the persistent contents are available in /sys/fs/pstore/pmsg-ramoops-[ID]. One possible use is syslogd, or other daemon, can write messages, then on reboot provides a means to triage user-space activities leading up to a panic as a companion to the pstore dmesg or console logs. Signed-off-by: Mark Salyzyn Acked-by: Kees Cook Signed-off-by: Tony Luck --- fs/pstore/Kconfig | 10 ++++ fs/pstore/Makefile | 2 + fs/pstore/inode.c | 3 ++ fs/pstore/internal.h | 6 +++ fs/pstore/platform.c | 1 + fs/pstore/pmsg.c | 114 +++++++++++++++++++++++++++++++++++++++++++++ fs/pstore/ram.c | 34 +++++++++++++- include/linux/pstore.h | 1 + include/linux/pstore_ram.h | 1 + 9 files changed, 170 insertions(+), 2 deletions(-) create mode 100644 fs/pstore/pmsg.c (limited to 'fs') diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 983d9510becc..916b8e23d968 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -21,6 +21,16 @@ config PSTORE_CONSOLE When the option is enabled, pstore will log all kernel messages, even if no oops or panic happened. +config PSTORE_PMSG + bool "Log user space messages" + depends on PSTORE + help + When the option is enabled, pstore will export a character + interface /dev/pmsg0 to log user space messages. On reboot + data can be retrieved from /sys/fs/pstore/pmsg-ramoops-[ID]. + + If unsure, say N. + config PSTORE_FTRACE bool "Persistent function tracer" depends on PSTORE diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile index 4c9095c2781e..e647d8e81712 100644 --- a/fs/pstore/Makefile +++ b/fs/pstore/Makefile @@ -7,5 +7,7 @@ obj-y += pstore.o pstore-objs += inode.o platform.o obj-$(CONFIG_PSTORE_FTRACE) += ftrace.o +obj-$(CONFIG_PSTORE_PMSG) += pmsg.o + ramoops-objs += ram.o ram_core.o obj-$(CONFIG_PSTORE_RAM) += ramoops.o diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index d69586f09ffd..b32ce53d24ee 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -361,6 +361,9 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, scnprintf(name, sizeof(name), "powerpc-common-%s-%lld", psname, id); break; + case PSTORE_TYPE_PMSG: + scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id); + break; case PSTORE_TYPE_UNKNOWN: scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id); break; diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 3b3d305277c4..c36ba2cd0b5d 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -45,6 +45,12 @@ extern void pstore_register_ftrace(void); static inline void pstore_register_ftrace(void) {} #endif +#ifdef CONFIG_PSTORE_PMSG +extern void pstore_register_pmsg(void); +#else +static inline void pstore_register_pmsg(void) {} +#endif + extern struct pstore_info *psinfo; extern void pstore_set_kmsg_bytes(int); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 0a9b72cdfeca..15ee78c5020b 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -447,6 +447,7 @@ int pstore_register(struct pstore_info *psi) if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) { pstore_register_console(); pstore_register_ftrace(); + pstore_register_pmsg(); } if (pstore_update_ms >= 0) { diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c new file mode 100644 index 000000000000..feb5dd2948b4 --- /dev/null +++ b/fs/pstore/pmsg.c @@ -0,0 +1,114 @@ +/* + * Copyright 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include "internal.h" + +static DEFINE_MUTEX(pmsg_lock); +#define PMSG_MAX_BOUNCE_BUFFER_SIZE (2*PAGE_SIZE) + +static ssize_t write_pmsg(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + size_t i, buffer_size; + char *buffer; + + if (!count) + return 0; + + if (!access_ok(VERIFY_READ, buf, count)) + return -EFAULT; + + buffer_size = count; + if (buffer_size > PMSG_MAX_BOUNCE_BUFFER_SIZE) + buffer_size = PMSG_MAX_BOUNCE_BUFFER_SIZE; + buffer = vmalloc(buffer_size); + + mutex_lock(&pmsg_lock); + for (i = 0; i < count; ) { + size_t c = min(count - i, buffer_size); + u64 id; + long ret; + + ret = __copy_from_user(buffer, buf + i, c); + if (unlikely(ret != 0)) { + mutex_unlock(&pmsg_lock); + vfree(buffer); + return -EFAULT; + } + psinfo->write_buf(PSTORE_TYPE_PMSG, 0, &id, 0, buffer, 0, c, + psinfo); + + i += c; + } + + mutex_unlock(&pmsg_lock); + vfree(buffer); + return count; +} + +static const struct file_operations pmsg_fops = { + .owner = THIS_MODULE, + .llseek = noop_llseek, + .write = write_pmsg, +}; + +static struct class *pmsg_class; +static int pmsg_major; +#define PMSG_NAME "pmsg" +#undef pr_fmt +#define pr_fmt(fmt) PMSG_NAME ": " fmt + +static char *pmsg_devnode(struct device *dev, umode_t *mode) +{ + if (mode) + *mode = 0220; + return NULL; +} + +void pstore_register_pmsg(void) +{ + struct device *pmsg_device; + + pmsg_major = register_chrdev(0, PMSG_NAME, &pmsg_fops); + if (pmsg_major < 0) { + pr_err("register_chrdev failed\n"); + goto err; + } + + pmsg_class = class_create(THIS_MODULE, PMSG_NAME); + if (IS_ERR(pmsg_class)) { + pr_err("device class file already in use\n"); + goto err_class; + } + pmsg_class->devnode = pmsg_devnode; + + pmsg_device = device_create(pmsg_class, NULL, MKDEV(pmsg_major, 0), + NULL, "%s%d", PMSG_NAME, 0); + if (IS_ERR(pmsg_device)) { + pr_err("failed to create device\n"); + goto err_device; + } + return; + +err_device: + class_destroy(pmsg_class); +err_class: + unregister_chrdev(pmsg_major, PMSG_NAME); +err: + return; +} diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 6150e54eed30..39d1373128e9 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -51,6 +51,10 @@ static ulong ramoops_ftrace_size = MIN_MEM_SIZE; module_param_named(ftrace_size, ramoops_ftrace_size, ulong, 0400); MODULE_PARM_DESC(ftrace_size, "size of ftrace log"); +static ulong ramoops_pmsg_size = MIN_MEM_SIZE; +module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400); +MODULE_PARM_DESC(pmsg_size, "size of user space message log"); + static ulong mem_address; module_param(mem_address, ulong, 0400); MODULE_PARM_DESC(mem_address, @@ -82,12 +86,14 @@ struct ramoops_context { struct persistent_ram_zone **przs; struct persistent_ram_zone *cprz; struct persistent_ram_zone *fprz; + struct persistent_ram_zone *mprz; phys_addr_t phys_addr; unsigned long size; unsigned int memtype; size_t record_size; size_t console_size; size_t ftrace_size; + size_t pmsg_size; int dump_oops; struct persistent_ram_ecc_info ecc_info; unsigned int max_dump_cnt; @@ -96,6 +102,7 @@ struct ramoops_context { unsigned int dump_read_cnt; unsigned int console_read_cnt; unsigned int ftrace_read_cnt; + unsigned int pmsg_read_cnt; struct pstore_info pstore; }; @@ -109,6 +116,7 @@ static int ramoops_pstore_open(struct pstore_info *psi) cxt->dump_read_cnt = 0; cxt->console_read_cnt = 0; cxt->ftrace_read_cnt = 0; + cxt->pmsg_read_cnt = 0; return 0; } @@ -190,6 +198,9 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, if (!prz_ok(prz)) prz = ramoops_get_next_prz(&cxt->fprz, &cxt->ftrace_read_cnt, 1, id, type, PSTORE_TYPE_FTRACE, 0); + if (!prz_ok(prz)) + prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt, + 1, id, type, PSTORE_TYPE_PMSG, 0); if (!prz_ok(prz)) return 0; @@ -258,6 +269,11 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, return -ENOMEM; persistent_ram_write(cxt->fprz, buf, size); return 0; + } else if (type == PSTORE_TYPE_PMSG) { + if (!cxt->mprz) + return -ENOMEM; + persistent_ram_write(cxt->mprz, buf, size); + return 0; } if (type != PSTORE_TYPE_DMESG) @@ -315,6 +331,9 @@ static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count, case PSTORE_TYPE_FTRACE: prz = cxt->fprz; break; + case PSTORE_TYPE_PMSG: + prz = cxt->mprz; + break; default: return -EINVAL; } @@ -441,7 +460,7 @@ static int ramoops_probe(struct platform_device *pdev) goto fail_out; if (!pdata->mem_size || (!pdata->record_size && !pdata->console_size && - !pdata->ftrace_size)) { + !pdata->ftrace_size && !pdata->pmsg_size)) { pr_err("The memory size and the record/console size must be " "non-zero\n"); goto fail_out; @@ -453,6 +472,8 @@ static int ramoops_probe(struct platform_device *pdev) pdata->console_size = rounddown_pow_of_two(pdata->console_size); if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size)) pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size); + if (pdata->pmsg_size && !is_power_of_2(pdata->pmsg_size)) + pdata->pmsg_size = rounddown_pow_of_two(pdata->pmsg_size); cxt->size = pdata->mem_size; cxt->phys_addr = pdata->mem_address; @@ -460,12 +481,14 @@ static int ramoops_probe(struct platform_device *pdev) cxt->record_size = pdata->record_size; cxt->console_size = pdata->console_size; cxt->ftrace_size = pdata->ftrace_size; + cxt->pmsg_size = pdata->pmsg_size; cxt->dump_oops = pdata->dump_oops; cxt->ecc_info = pdata->ecc_info; paddr = cxt->phys_addr; - dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size; + dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size + - cxt->pmsg_size; err = ramoops_init_przs(dev, cxt, &paddr, dump_mem_sz); if (err) goto fail_out; @@ -480,6 +503,10 @@ static int ramoops_probe(struct platform_device *pdev) if (err) goto fail_init_fprz; + err = ramoops_init_prz(dev, cxt, &cxt->mprz, &paddr, cxt->pmsg_size, 0); + if (err) + goto fail_init_mprz; + cxt->pstore.data = cxt; /* * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we @@ -523,6 +550,8 @@ fail_buf: kfree(cxt->pstore.buf); fail_clear: cxt->pstore.bufsize = 0; + kfree(cxt->mprz); +fail_init_mprz: kfree(cxt->fprz); fail_init_fprz: kfree(cxt->cprz); @@ -580,6 +609,7 @@ static void ramoops_register_dummy(void) dummy_data->record_size = record_size; dummy_data->console_size = ramoops_console_size; dummy_data->ftrace_size = ramoops_ftrace_size; + dummy_data->pmsg_size = ramoops_pmsg_size; dummy_data->dump_oops = dump_oops; /* * For backwards compatibility ramoops.ecc=1 means 16 bytes ECC diff --git a/include/linux/pstore.h b/include/linux/pstore.h index ece0c6bbfcc5..8884f6e507f7 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -39,6 +39,7 @@ enum pstore_type_id { PSTORE_TYPE_PPC_RTAS = 4, PSTORE_TYPE_PPC_OF = 5, PSTORE_TYPE_PPC_COMMON = 6, + PSTORE_TYPE_PMSG = 7, PSTORE_TYPE_UNKNOWN = 255 }; diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 4af3fdc85b01..9c9d6c154c8e 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -81,6 +81,7 @@ struct ramoops_platform_data { unsigned long record_size; unsigned long console_size; unsigned long ftrace_size; + unsigned long pmsg_size; int dump_oops; struct persistent_ram_ecc_info ecc_info; }; -- cgit v1.2.3 From a6b8978c54b771308f6f1692b9735ac0bb087cc2 Mon Sep 17 00:00:00 2001 From: alex chen Date: Fri, 16 Jan 2015 15:52:03 -0800 Subject: pstore: Fix sprintf format specifier in pstore_dump() We should use sprintf format specifier "%u" instead of "%d" for argument of type 'unsigned int' in pstore_dump(). Signed-off-by: Alex Chen Reviewed-by: Joseph Qi Acked-by: Kees Cook Signed-off-by: Tony Luck --- fs/pstore/platform.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 15ee78c5020b..c4c9a10c5760 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -301,7 +301,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, if (big_oops_buf) { dst = big_oops_buf; - hsize = sprintf(dst, "%s#%d Part%d\n", why, + hsize = sprintf(dst, "%s#%d Part%u\n", why, oopscount, part); size = big_oops_buf_sz - hsize; @@ -321,7 +321,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, } } else { dst = psinfo->buf; - hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, + hsize = sprintf(dst, "%s#%d Part%u\n", why, oopscount, part); size = psinfo->bufsize - hsize; dst += hsize; -- cgit v1.2.3 From 053c095a82cf773075e83d7233b5cc19a1f73ece Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jan 2015 22:09:00 +0100 Subject: netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- drivers/acpi/event.c | 7 +------ drivers/net/ethernet/rocker/rocker.c | 3 ++- drivers/net/vxlan.c | 3 ++- drivers/net/wireless/mac80211_hwsim.c | 3 ++- drivers/scsi/pmcraid.c | 8 +------- drivers/target/target_core_user.c | 4 +--- drivers/thermal/thermal_core.c | 6 +----- fs/dlm/netlink.c | 7 +------ include/net/genetlink.h | 4 ++-- include/net/netlink.h | 6 +----- kernel/taskstats.c | 13 ++----------- net/bridge/br_fdb.c | 3 ++- net/bridge/br_mdb.c | 3 ++- net/bridge/br_netlink.c | 3 ++- net/can/gw.c | 3 ++- net/core/fib_rules.c | 3 ++- net/core/neighbour.c | 12 ++++++++---- net/core/rtnetlink.c | 9 ++++++--- net/decnet/dn_dev.c | 3 ++- net/decnet/dn_route.c | 3 ++- net/decnet/dn_table.c | 3 ++- net/ieee802154/netlink.c | 12 ++---------- net/ieee802154/nl-mac.c | 3 ++- net/ieee802154/nl-phy.c | 3 ++- net/ieee802154/nl802154.c | 6 ++++-- net/ipv4/devinet.c | 8 +++++--- net/ipv4/fib_semantics.c | 3 ++- net/ipv4/inet_diag.c | 9 ++++++--- net/ipv4/ipmr.c | 3 ++- net/ipv4/route.c | 3 ++- net/ipv4/tcp_metrics.c | 3 ++- net/ipv6/addrconf.c | 32 +++++++++++++++++++------------- net/ipv6/addrlabel.c | 5 +++-- net/ipv6/ip6_fib.c | 1 - net/ipv6/ip6mr.c | 3 ++- net/ipv6/route.c | 3 ++- net/l2tp/l2tp_netlink.c | 10 ++++++---- net/netfilter/ipvs/ip_vs_ctl.c | 9 ++++++--- net/netfilter/nf_tables_api.c | 18 ++++++++++++------ net/netlabel/netlabel_cipso_v4.c | 3 ++- net/netlabel/netlabel_mgmt.c | 6 ++++-- net/netlabel/netlabel_unlabeled.c | 3 ++- net/netlink/diag.c | 3 ++- net/netlink/genetlink.c | 6 ++++-- net/nfc/netlink.c | 12 +++++++----- net/openvswitch/datapath.c | 9 ++++++--- net/packet/diag.c | 3 ++- net/phonet/pn_netlink.c | 16 +++++++++++----- net/unix/diag.c | 3 ++- net/wireless/nl80211.c | 27 ++++++++++++++++++--------- net/xfrm/xfrm_user.c | 27 ++++++++++++++++++--------- 51 files changed, 203 insertions(+), 158 deletions(-) (limited to 'fs') diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index ef2d730734dc..e24ea4e796e4 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -100,7 +100,6 @@ int acpi_bus_generate_netlink_event(const char *device_class, struct acpi_genl_event *event; void *msg_header; int size; - int result; /* allocate memory */ size = nla_total_size(sizeof(struct acpi_genl_event)) + @@ -137,11 +136,7 @@ int acpi_bus_generate_netlink_event(const char *device_class, event->data = data; /* send multicast genetlink message */ - result = genlmsg_end(skb, msg_header); - if (result < 0) { - nlmsg_free(skb); - return result; - } + genlmsg_end(skb, msg_header); genlmsg_multicast(&acpi_event_genl_family, skb, 0, 0, GFP_ATOMIC); return 0; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 964d719b150f..d54781e71cd4 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3674,7 +3674,8 @@ static int rocker_fdb_fill_info(struct sk_buff *skb, if (vid && nla_put_u16(skb, NDA_VLAN, vid)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 6b6b45622a0a..c5f79e7513a6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -363,7 +363,8 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 494e7335aa64..4a4c6586a8d2 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2557,7 +2557,8 @@ static int mac80211_hwsim_get_radio(struct sk_buff *skb, if (res < 0) goto out_err; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; out_err: genlmsg_cancel(skb, hdr); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 8c27b6a77ec4..cf222f46eac5 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -1473,13 +1473,7 @@ static int pmcraid_notify_aen( } /* send genetlink multicast message to notify appplications */ - result = genlmsg_end(skb, msg_header); - - if (result < 0) { - pmcraid_err("genlmsg_end failed\n"); - nlmsg_free(skb); - return result; - } + genlmsg_end(skb, msg_header); result = genlmsg_multicast(&pmcraid_event_family, skb, 0, 0, GFP_ATOMIC); diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 1157b559683b..1a1bcf71ec9d 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -784,9 +784,7 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, int mino if (ret < 0) goto free_skb; - ret = genlmsg_end(skb, msg_header); - if (ret < 0) - goto free_skb; + genlmsg_end(skb, msg_header); ret = genlmsg_multicast(&tcmu_genl_family, skb, 0, TCMU_MCGRP_CONFIG, GFP_KERNEL); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 87e0b0782023..48491d1a81d6 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1759,11 +1759,7 @@ int thermal_generate_netlink_event(struct thermal_zone_device *tz, thermal_event->event = event; /* send multicast genetlink message */ - result = genlmsg_end(skb, msg_header); - if (result < 0) { - nlmsg_free(skb); - return result; - } + genlmsg_end(skb, msg_header); result = genlmsg_multicast(&thermal_event_genl_family, skb, 0, 0, GFP_ATOMIC); diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index e7cfbaf8d0e2..1e6e227134d7 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -56,13 +56,8 @@ static int send_data(struct sk_buff *skb) { struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data); void *data = genlmsg_data(genlhdr); - int rv; - rv = genlmsg_end(skb, data); - if (rv < 0) { - nlmsg_free(skb); - return rv; - } + genlmsg_end(skb, data); return genlmsg_unicast(&init_net, skb, listener_nlportid); } diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 84125088c309..f24aa83b80b6 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -245,9 +245,9 @@ static inline void *genlmsg_put_reply(struct sk_buff *skb, * @skb: socket buffer the message is stored in * @hdr: user specific header */ -static inline int genlmsg_end(struct sk_buff *skb, void *hdr) +static inline void genlmsg_end(struct sk_buff *skb, void *hdr) { - return nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); + nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** diff --git a/include/net/netlink.h b/include/net/netlink.h index d5869b90bfbb..e010ee8da41d 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -490,14 +490,10 @@ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags) * Corrects the netlink message header to include the appeneded * attributes. Only necessary if attributes have been added to * the message. - * - * Returns the total data length of the skb. */ -static inline int nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) +static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) { nlh->nlmsg_len = skb_tail_pointer(skb) - (unsigned char *)nlh; - - return skb->len; } /** diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 670fff88a961..21f82c29c914 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -111,13 +111,8 @@ static int send_reply(struct sk_buff *skb, struct genl_info *info) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); - int rc; - rc = genlmsg_end(skb, reply); - if (rc < 0) { - nlmsg_free(skb); - return rc; - } + genlmsg_end(skb, reply); return genlmsg_reply(skb, info); } @@ -134,11 +129,7 @@ static void send_cpu_listeners(struct sk_buff *skb, void *reply = genlmsg_data(genlhdr); int rc, delcount = 0; - rc = genlmsg_end(skb, reply); - if (rc < 0) { - nlmsg_free(skb); - return; - } + genlmsg_end(skb, reply); rc = 0; down_read(&listeners->sem); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 03667e65cc29..08bf04bdac58 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -633,7 +633,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, if (fdb->vlan_id && nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index fed61c971b17..409608960899 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -190,7 +190,8 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb, nla_nest_end(skb, nest2); nla_nest_end(skb, nest); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; end: nla_nest_end(skb, nest); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 163950b10d8c..528cf2790a5f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -263,7 +263,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, } done: - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/can/gw.c b/net/can/gw.c index 295f62e62eb3..a6f448e18ea8 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -575,7 +575,8 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, goto cancel; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; cancel: nlmsg_cancel(skb, nlh); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 185c341fafbd..44706e81b2e0 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -609,7 +609,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8d614c93f86a..d36d564f149f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1884,7 +1884,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, goto nla_put_failure; read_unlock_bh(&tbl->lock); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: read_unlock_bh(&tbl->lock); @@ -1917,7 +1918,8 @@ static int neightbl_fill_param_info(struct sk_buff *skb, goto errout; read_unlock_bh(&tbl->lock); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); @@ -2202,7 +2204,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -2232,7 +2235,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eadc5c0e2dfa..e13b9dbdf154 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1199,7 +1199,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_end(skb, af_spec); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -2326,7 +2327,8 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -2809,7 +2811,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, nla_nest_end(skb, protinfo); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 4400da7739da..b2c26b081134 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -702,7 +702,8 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || nla_put_u32(skb, IFA_FLAGS, ifa_flags)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index daccc4a36d80..812e5e6e88fb 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1616,7 +1616,8 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 portid, u32 seq, nla_put_u32(skb, RTA_IIF, rt->fld.flowidn_iif) < 0) goto errout; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: nlmsg_cancel(skb, nlh); diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 3f19fcbf126d..1540b506e3e0 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -367,7 +367,8 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_nest_end(skb, mp_head); } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: nlmsg_cancel(skb, nlh); diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index fa1464762d0d..c8133c07ceee 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -63,13 +63,9 @@ int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group) struct nlmsghdr *nlh = nlmsg_hdr(msg); void *hdr = genlmsg_data(nlmsg_data(nlh)); - if (genlmsg_end(msg, hdr) < 0) - goto out; + genlmsg_end(msg, hdr); return genlmsg_multicast(&nl802154_family, msg, 0, group, GFP_ATOMIC); -out: - nlmsg_free(msg); - return -ENOBUFS; } struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info, @@ -96,13 +92,9 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info) struct nlmsghdr *nlh = nlmsg_hdr(msg); void *hdr = genlmsg_data(nlmsg_data(nlh)); - if (genlmsg_end(msg, hdr) < 0) - goto out; + genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); -out: - nlmsg_free(msg); - return -ENOBUFS; } static const struct genl_ops ieee8021154_ops[] = { diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 3c902e9516fb..9105265920fe 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -136,7 +136,8 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, } wpan_phy_put(phy); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: wpan_phy_put(phy); diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 7baf98b14611..1b9d25f6e898 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -65,7 +65,8 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, goto nla_put_failure; mutex_unlock(&phy->pib_lock); kfree(buf); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: mutex_unlock(&phy->pib_lock); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index a25b9bbd077b..a4daf91b8d0a 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -306,7 +306,8 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, goto nla_put_failure; finish: - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -489,7 +490,8 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, if (nla_put_u8(msg, NL802154_ATTR_LBT_MODE, wpan_dev->lbt)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 214882e7d6de..5f344eb3fc25 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1522,7 +1522,8 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, preferred, valid)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -1566,7 +1567,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWADDR, NLM_F_MULTI) <= 0) { + RTM_NEWADDR, NLM_F_MULTI) < 0) { rcu_read_unlock(); goto done; } @@ -1749,7 +1750,8 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d2b7b5521b1b..265cb72b7c1b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1091,7 +1091,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_nest_end(skb, mp); } #endif - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e34dccbc4d70..81751f12645f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -203,7 +203,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, icsk->icsk_ca_ops->get_info(sk, ext, skb); out: - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: nlmsg_cancel(skb, nlh); @@ -271,7 +272,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, } #endif - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, @@ -758,7 +760,8 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, } #endif - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c8034587859d..9d78427652d2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2290,7 +2290,8 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, if (err < 0 && err != -ENOENT) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ce112d0f2698..f6e43ca5e641 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2390,7 +2390,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index ed9c9a91851c..e5f41bd5ec1b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -886,7 +886,8 @@ static int tcp_metrics_dump_info(struct sk_buff *skb, if (tcp_metrics_fill_info(skb, tm) < 0) goto nla_put_failure; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f7c8bbeb27b7..8975d9501d50 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -489,7 +489,8 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -619,7 +620,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, - -1) <= 0) { + -1) < 0) { rcu_read_unlock(); goto done; } @@ -635,7 +636,7 @@ cont: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, - -1) <= 0) + -1) < 0) goto done; else h++; @@ -646,7 +647,7 @@ cont: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, - -1) <= 0) + -1) < 0) goto done; else h++; @@ -4047,7 +4048,8 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) goto error; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; error: nlmsg_cancel(skb, nlh); @@ -4076,7 +4078,8 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return -EMSGSIZE; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, @@ -4101,7 +4104,8 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, return -EMSGSIZE; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } enum addr_type_t { @@ -4134,7 +4138,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_NEWADDR, NLM_F_MULTI); - if (err <= 0) + if (err < 0) break; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); } @@ -4151,7 +4155,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_GETMULTICAST, NLM_F_MULTI); - if (err <= 0) + if (err < 0) break; } break; @@ -4166,7 +4170,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_GETANYCAST, NLM_F_MULTI); - if (err <= 0) + if (err < 0) break; } break; @@ -4638,7 +4642,8 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, goto nla_put_failure; nla_nest_end(skb, protoinfo); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -4670,7 +4675,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (inet6_fill_ifinfo(skb, idev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWLINK, NLM_F_MULTI) <= 0) + RTM_NEWLINK, NLM_F_MULTI) < 0) goto out; cont: idx++; @@ -4747,7 +4752,8 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, ci.valid_time = ntohl(pinfo->valid); if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index fd0dc47f471d..e43e79d0a612 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -490,7 +490,8 @@ static int ip6addrlbl_fill(struct sk_buff *skb, return -EMSGSIZE; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) @@ -510,7 +511,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, RTM_NEWADDRLABEL, NLM_F_MULTI); - if (err <= 0) + if (err < 0) break; } idx++; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 03c520a4ebeb..53775ee7d376 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -277,7 +277,6 @@ static int fib6_dump_node(struct fib6_walker *w) w->leaf = rt; return 1; } - WARN_ON(res == 0); } w->leaf = NULL; return 0; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 722669754bbf..34b682617f50 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2388,7 +2388,8 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, if (err < 0 && err != -ENOENT) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 34dcbb59df75..c60f15775c53 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2725,7 +2725,8 @@ static int rt6_fill_node(struct net *net, if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 6b16598f31d5..b4e923f77954 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -390,7 +390,8 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla } out: - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -451,7 +452,7 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - tunnel, L2TP_CMD_TUNNEL_GET) <= 0) + tunnel, L2TP_CMD_TUNNEL_GET) < 0) goto out; ti++; @@ -752,7 +753,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl goto nla_put_failure; nla_nest_end(skb, nest); - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -816,7 +818,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - session, L2TP_CMD_SESSION_GET) <= 0) + session, L2TP_CMD_SESSION_GET) < 0) break; si++; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b8295a430a56..e55759056361 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2887,7 +2887,8 @@ static int ip_vs_genl_dump_service(struct sk_buff *skb, if (ip_vs_genl_fill_service(skb, svc) < 0) goto nla_put_failure; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -3079,7 +3080,8 @@ static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest, if (ip_vs_genl_fill_dest(skb, dest) < 0) goto nla_put_failure; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -3215,7 +3217,8 @@ static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state, if (ip_vs_genl_fill_daemon(skb, state, mcast_ifn, syncid)) goto nla_put_failure; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3b3ddb4fb9ee..70f697827b9b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -427,7 +427,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use))) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -971,7 +972,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -1707,7 +1709,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule))) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -2361,7 +2364,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; nla_nest_end(skb, desc); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -3035,7 +3039,8 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, nla_nest_end(skb, nest); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -3324,7 +3329,8 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq))) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index c2f2a53a4879..179625353cac 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -641,7 +641,8 @@ static int netlbl_cipsov4_listall_cb(struct cipso_v4_doi *doi_def, void *arg) if (ret_val != 0) goto listall_cb_failure; - return genlmsg_end(cb_arg->skb, data); + genlmsg_end(cb_arg->skb, data); + return 0; listall_cb_failure: genlmsg_cancel(cb_arg->skb, data); diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index e66e977ef2fa..8b3b789c43c2 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -456,7 +456,8 @@ static int netlbl_mgmt_listall_cb(struct netlbl_dom_map *entry, void *arg) goto listall_cb_failure; cb_arg->seq++; - return genlmsg_end(cb_arg->skb, data); + genlmsg_end(cb_arg->skb, data); + return 0; listall_cb_failure: genlmsg_cancel(cb_arg->skb, data); @@ -620,7 +621,8 @@ static int netlbl_mgmt_protocols_cb(struct sk_buff *skb, if (ret_val != 0) goto protocols_cb_failure; - return genlmsg_end(skb, data); + genlmsg_end(skb, data); + return 0; protocols_cb_failure: genlmsg_cancel(skb, data); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 78a63c18779e..aec7994f78cf 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1163,7 +1163,8 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd, goto list_cb_failure; cb_arg->seq++; - return genlmsg_end(cb_arg->skb, data); + genlmsg_end(cb_arg->skb, data); + return 0; list_cb_failure: genlmsg_cancel(cb_arg->skb, data); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index bb59a7ed0859..3ee63a3cff30 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -91,7 +91,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, sk_diag_put_rings_cfg(sk, skb)) goto out_nlmsg_trim; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_nlmsg_trim: nlmsg_cancel(skb, nlh); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2e11061ef885..f52a7d5734cd 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -756,7 +756,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq, nla_nest_end(skb, nla_grps); } - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -796,7 +797,8 @@ static int ctrl_fill_mcgrp_info(struct genl_family *family, nla_nest_end(skb, nest); nla_nest_end(skb, nla_grps); - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 44989fc8cddf..be387e6219a0 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -102,7 +102,8 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, goto nla_put_failure; } - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -518,7 +519,8 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -908,7 +910,8 @@ static int nfc_genl_send_params(struct sk_buff *msg, nla_put_u16(msg, NFC_ATTR_LLC_PARAM_MIUX, be16_to_cpu(local->miux))) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: @@ -1247,8 +1250,7 @@ static int nfc_genl_send_se(struct sk_buff *msg, struct nfc_dev *dev, nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type)) goto nla_put_failure; - if (genlmsg_end(msg, hdr) < 0) - goto nla_put_failure; + genlmsg_end(msg, hdr); } return 0; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 8bda3cc12344..f45f1bf4422c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -799,7 +799,8 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex, if (err) goto error; - return genlmsg_end(skb, ovs_header); + genlmsg_end(skb, ovs_header); + return 0; error: genlmsg_cancel(skb, ovs_header); @@ -1349,7 +1350,8 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features)) goto nla_put_failure; - return genlmsg_end(skb, ovs_header); + genlmsg_end(skb, ovs_header); + return 0; nla_put_failure: genlmsg_cancel(skb, ovs_header); @@ -1723,7 +1725,8 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (err == -EMSGSIZE) goto error; - return genlmsg_end(skb, ovs_header); + genlmsg_end(skb, ovs_header); + return 0; nla_put_failure: err = -EMSGSIZE; diff --git a/net/packet/diag.c b/net/packet/diag.c index 92f2c7107eec..0ed68f0238bf 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -177,7 +177,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, PACKET_DIAG_FILTER)) goto out_nlmsg_trim; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_nlmsg_trim: nlmsg_cancel(skb, nlh); diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index b64151ade6b3..54d766842c2b 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -121,7 +121,8 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, ifm->ifa_index = dev->ifindex; if (nla_put_u8(skb, IFA_LOCAL, addr)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -190,7 +191,8 @@ static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst, if (nla_put_u8(skb, RTA_DST, dst) || nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -282,9 +284,13 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) if (addr_idx++ < addr_start_idx) continue; - if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWROUTE)) - goto out; + fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWROUTE); + /* fill_route() used to return > 0 (or negative errors) but + * never 0 - ignore the return value and just go out to + * call dumpit again from outside to preserve the behavior + */ + goto out; } out: diff --git a/net/unix/diag.c b/net/unix/diag.c index 86fa0f3b2caf..ef542fbca9fe 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -155,7 +155,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown)) goto out_nlmsg_trim; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_nlmsg_trim: nlmsg_cancel(skb, nlh); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 380784378df8..4ed9039bd5f9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1721,7 +1721,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, break; } finish: - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -2404,7 +2405,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag goto nla_put_failure; } - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -3825,7 +3827,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, sinfo->assoc_req_ies)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -4555,7 +4558,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, nla_nest_end(msg, pinfoattr); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -5507,7 +5511,8 @@ static int nl80211_send_regdom(struct sk_buff *msg, struct netlink_callback *cb, nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -6577,7 +6582,8 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, nla_nest_end(msg, bss); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; fail_unlock_rcu: rcu_read_unlock(); @@ -6686,7 +6692,8 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, nla_nest_end(msg, infoattr); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -11025,7 +11032,8 @@ static int nl80211_send_scan_msg(struct sk_buff *msg, /* ignore errors and send incomplete event anyway */ nl80211_add_scan_req(msg, rdev); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -11048,7 +11056,8 @@ nl80211_send_sched_scan_msg(struct sk_buff *msg, nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8128594ab379..7de2ed9ec46d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1019,7 +1019,8 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net, return err; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_set_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1121,7 +1122,8 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net, return err; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1842,7 +1844,8 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) goto out_cancel; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_cancel: nlmsg_cancel(skb, nlh); @@ -2282,7 +2285,8 @@ static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, goto out_cancel; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_cancel: nlmsg_cancel(skb, nlh); @@ -2490,7 +2494,8 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) return err; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c) @@ -2712,7 +2717,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, return err; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, @@ -2827,7 +2833,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, } upe->hard = !!hard; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) @@ -2986,7 +2993,8 @@ static int build_report(struct sk_buff *skb, u8 proto, return err; } } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_send_report(struct net *net, u8 proto, @@ -3031,7 +3039,8 @@ static int build_mapping(struct sk_buff *skb, struct xfrm_state *x, um->old_sport = x->encap->encap_sport; um->reqid = x->props.reqid; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, -- cgit v1.2.3 From 378ff1a53b5724f3ac97b0aba3c9ecac072f6fcd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 18 Jan 2015 23:37:32 -0500 Subject: fix deadlock in cifs_ioctl_clone() It really needs to check that src is non-directory *and* use {un,}lock_two_nodirectories(). As it is, it's trivial to cause double-lock (ioctl(fd, CIFS_IOC_COPYCHUNK_FILE, fd)) and if the last argument is an fd of directory, we are asking for trouble by violating the locking order - all directories go before all non-directories. If the last argument is an fd of parent directory, it has 50% odds of locking child before parent, which will cause AB-BA deadlock if we race with unlink(). Cc: stable@vger.kernel.org @ 3.13+ Signed-off-by: Al Viro --- fs/cifs/ioctl.c | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) (limited to 'fs') diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 45cb59bcc791..8b7898b7670f 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -86,21 +86,16 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, } src_inode = file_inode(src_file.file); + rc = -EINVAL; + if (S_ISDIR(src_inode->i_mode)) + goto out_fput; /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants * server could even support copy of range where source = target */ - - /* so we do not deadlock racing two ioctls on same files */ - if (target_inode < src_inode) { - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); - } else { - mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_CHILD); - } + lock_two_nondirectories(target_inode, src_inode); /* determine range to clone */ rc = -EINVAL; @@ -124,13 +119,7 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file, out_unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ - if (target_inode < src_inode) { - mutex_unlock(&src_inode->i_mutex); - mutex_unlock(&target_inode->i_mutex); - } else { - mutex_unlock(&target_inode->i_mutex); - mutex_unlock(&src_inode->i_mutex); - } + unlock_two_nondirectories(src_inode, target_inode); out_fput: fdput(src_file); out_drop_write: -- cgit v1.2.3 From 98bd5c547ef2300f915fc1adce5b6f25c195d4d4 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 19 Jan 2015 14:21:02 +0100 Subject: btrfs: sync ioctl, handle errors after transaction start The version merged to 3.19 did not handle errors from start_trancaction and could pass an invalid pointer to commit_transaction. Fixes: 6b5fe46dfa52441f ("btrfs: do commit in sync_fs if there are pending changes") Reported-by: Filipe Manana Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 60f7cbe815e9..c86fb5438454 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1001,9 +1001,9 @@ int btrfs_sync_fs(struct super_block *sb, int wait) if (fs_info->pending_changes == 0) return 0; trans = btrfs_start_transaction(root, 0); - } else { - return PTR_ERR(trans); } + if (IS_ERR(trans)) + return PTR_ERR(trans); } return btrfs_commit_transaction(trans, root); } -- cgit v1.2.3 From 379d6854a2092e38b6e56a8067d922e31461b7e2 Mon Sep 17 00:00:00 2001 From: Tsutomu Itoh Date: Fri, 9 Jan 2015 17:37:52 +0900 Subject: Btrfs: fix incorrect freeing in scrub_stripe The address that should be freed is not 'ppath' but 'path'. Signed-off-by: Tsutomu Itoh Reviewed-by: Miao Xie Signed-off-by: Chris Mason --- fs/btrfs/scrub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 9e1569ffbf6e..2f0fbc374e87 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3053,7 +3053,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, ppath = btrfs_alloc_path(); if (!ppath) { - btrfs_free_path(ppath); + btrfs_free_path(path); return -ENOMEM; } -- cgit v1.2.3 From 75c68e9fbbdfc04467c9edcac76be998beaa630b Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Fri, 16 Jan 2015 13:24:40 +0000 Subject: Btrfs: fix race deleting block group from space_info->ro_bgs list When removing a block group we were deleting it from its space_info's ro_bgs list without the correct protection - the space info's spinlock. Fix this by doing the list delete while holding the spinlock of the corresponding space info, which is the correct lock for any operation on that list. This issue was introduced in the 3.19 kernel by the following change: Btrfs: move read only block groups onto their own list V2 commit 633c0aad4c0243a506a3e8590551085ad78af82d I ran into a kernel crash while a task was running statfs, which iterates the space_info->ro_bgs list while holding the space info's spinlock, and another task was deleting it from the same list, without holding that spinlock, as part of the block group remove operation (while running the function btrfs_remove_block_group). This happened often when running the stress test xfstests/generic/038 I recently made. Signed-off-by: Filipe Manana Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 1 + fs/btrfs/extent-tree.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7e607416755a..0b180708bf79 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1171,6 +1171,7 @@ struct btrfs_space_info { struct percpu_counter total_bytes_pinned; struct list_head list; + /* Protected by the spinlock 'lock'. */ struct list_head ro_bgs; struct rw_semaphore groups_sem; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 15116585e714..a684086c3c81 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -9422,7 +9422,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, * are still on the list after taking the semaphore */ list_del_init(&block_group->list); - list_del_init(&block_group->ro_list); if (list_empty(&block_group->space_info->block_groups[index])) { kobj = block_group->space_info->block_group_kobjs[index]; block_group->space_info->block_group_kobjs[index] = NULL; @@ -9464,6 +9463,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, btrfs_remove_free_space_cache(block_group); spin_lock(&block_group->space_info->lock); + list_del_init(&block_group->ro_list); block_group->space_info->total_bytes -= block_group->key.offset; block_group->space_info->bytes_readonly -= block_group->key.offset; block_group->space_info->disk_total -= block_group->key.offset * factor; -- cgit v1.2.3 From 6e1103a6e9b19dbdc348077d04a546b626911fc5 Mon Sep 17 00:00:00 2001 From: Satoru Takeuchi Date: Thu, 25 Dec 2014 18:21:41 +0900 Subject: btrfs: fix state->private cast on 32 bit machines Suppress the following warning displayed on building 32bit (i686) kernel. =============================================================================== ... CC [M] fs/btrfs/extent_io.o fs/btrfs/extent_io.c: In function ‘btrfs_free_io_failure_record’: fs/btrfs/extent_io.c:2193:13: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] failrec = (struct io_failure_record *)state->private; ... =============================================================================== Signed-off-by: Satoru Takeuchi Reported-by: Chris Murphy Signed-off-by: Chris Mason --- fs/btrfs/extent_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4ebabd237153..790dbae3343c 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2190,7 +2190,7 @@ void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end) next = next_state(state); - failrec = (struct io_failure_record *)state->private; + failrec = (struct io_failure_record *)(unsigned long)state->private; free_extent_state(state); kfree(failrec); -- cgit v1.2.3 From f99dbfa4b39f90c3ba95169000cc2cdd59413f4e Mon Sep 17 00:00:00 2001 From: Giel van Schijndel Date: Tue, 6 Jan 2015 22:37:00 +0100 Subject: cifs: use memzero_explicit to clear stack buffer When leaving a function use memzero_explicit instead of memset(0) to clear stack allocated buffers. memset(0) may be optimized away. This particular buffer is highly likely to contain sensitive data which we shouldn't leak (it's named 'passwd' after all). Signed-off-by: Giel van Schijndel Acked-by: Herbert Xu Reported-at: http://www.viva64.com/en/b/0299/ Reported-by: Andrey Karpov Reported-by: Svyatoslav Razmyslov Signed-off-by: Steve French --- fs/cifs/smbencrypt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c index 6c1566366a66..a4232ec4f2ba 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/cifs/smbencrypt.c @@ -221,7 +221,7 @@ E_md4hash(const unsigned char *passwd, unsigned char *p16, } rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__le16)); - memset(wpwd, 0, 129 * sizeof(__le16)); + memzero_explicit(wpwd, sizeof(wpwd)); return rc; } -- cgit v1.2.3 From ca7df8e0bb2a5ec79691de8a1a4c0e611fe04e60 Mon Sep 17 00:00:00 2001 From: Sachin Prabhu Date: Thu, 15 Jan 2015 12:22:04 +0000 Subject: Complete oplock break jobs before closing file handle Commit c11f1df5003d534fd067f0168bfad7befffb3b5c requires writers to wait for any pending oplock break handler to complete before proceeding to write. This is done by waiting on bit CIFS_INODE_PENDING_OPLOCK_BREAK in cifsFileInfo->flags. This bit is cleared by the oplock break handler job queued on the workqueue once it has completed handling the oplock break allowing writers to proceed with writing to the file. While testing, it was noticed that the filehandle could be closed while there is a pending oplock break which results in the oplock break handler on the cifsiod workqueue being cancelled before it has had a chance to execute and clear the CIFS_INODE_PENDING_OPLOCK_BREAK bit. Any subsequent attempt to write to this file hangs waiting for the CIFS_INODE_PENDING_OPLOCK_BREAK bit to be cleared. We fix this by ensuring that we also clear the bit CIFS_INODE_PENDING_OPLOCK_BREAK when we remove the oplock break handler from the workqueue. The bug was found by Red Hat QA while testing using ltp's fsstress command. Signed-off-by: Sachin Prabhu Acked-by: Shirish Pargaonkar Signed-off-by: Jeff Layton Cc: stable@vger.kernel.org Signed-off-by: Steve French --- fs/cifs/file.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 96b7e9b7706d..74f12877493a 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -366,6 +366,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) struct cifsLockInfo *li, *tmp; struct cifs_fid fid; struct cifs_pending_open open; + bool oplock_break_cancelled; spin_lock(&cifs_file_list_lock); if (--cifs_file->count > 0) { @@ -397,7 +398,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) } spin_unlock(&cifs_file_list_lock); - cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -409,6 +410,9 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) _free_xid(xid); } + if (oplock_break_cancelled) + cifs_done_oplock_break(cifsi); + cifs_del_pending_open(&open); /* -- cgit v1.2.3 From a7a2c680a2ad81b3181a335ee76e23d5195007ee Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:30 +0100 Subject: fs: deduplicate noop_backing_dev_info hugetlbfs, kernfs and dlmfs can simply use noop_backing_dev_info instead of creating a local duplicate. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/hugetlbfs/inode.c | 14 +------------- fs/kernfs/inode.c | 14 +------------- fs/kernfs/kernfs-internal.h | 1 - fs/kernfs/mount.c | 1 - fs/ocfs2/dlmfs/dlmfs.c | 16 ++-------------- 5 files changed, 4 insertions(+), 42 deletions(-) (limited to 'fs') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 5eba47f593f8..de7c95c7d840 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -62,12 +62,6 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } -static struct backing_dev_info hugetlbfs_backing_dev_info = { - .name = "hugetlbfs", - .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; - int sysctl_hugetlb_shm_group; enum { @@ -498,7 +492,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; - inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info; + inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->private_data = resv_map; info = HUGETLBFS_I(inode); @@ -1032,10 +1026,6 @@ static int __init init_hugetlbfs_fs(void) return -ENOTSUPP; } - error = bdi_init(&hugetlbfs_backing_dev_info); - if (error) - return error; - error = -ENOMEM; hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache", sizeof(struct hugetlbfs_inode_info), @@ -1071,7 +1061,6 @@ static int __init init_hugetlbfs_fs(void) out: kmem_cache_destroy(hugetlbfs_inode_cachep); out2: - bdi_destroy(&hugetlbfs_backing_dev_info); return error; } @@ -1091,7 +1080,6 @@ static void __exit exit_hugetlbfs_fs(void) for_each_hstate(h) kern_unmount(hugetlbfs_vfsmount[i++]); unregister_filesystem(&hugetlbfs_fs_type); - bdi_destroy(&hugetlbfs_backing_dev_info); } module_init(init_hugetlbfs_fs) diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 985217626e66..06f06887b2d2 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -24,12 +24,6 @@ static const struct address_space_operations kernfs_aops = { .write_end = simple_write_end, }; -static struct backing_dev_info kernfs_bdi = { - .name = "kernfs", - .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; - static const struct inode_operations kernfs_iops = { .permission = kernfs_iop_permission, .setattr = kernfs_iop_setattr, @@ -40,12 +34,6 @@ static const struct inode_operations kernfs_iops = { .listxattr = kernfs_iop_listxattr, }; -void __init kernfs_inode_init(void) -{ - if (bdi_init(&kernfs_bdi)) - panic("failed to init kernfs_bdi"); -} - static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) { static DEFINE_MUTEX(iattr_mutex); @@ -298,7 +286,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) kernfs_get(kn); inode->i_private = kn; inode->i_mapping->a_ops = &kernfs_aops; - inode->i_mapping->backing_dev_info = &kernfs_bdi; + inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_op = &kernfs_iops; set_default_inode_attr(inode, kn->mode); diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index dc84a3ef9ca2..af9fa7499919 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -88,7 +88,6 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name); ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf, size_t size); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); -void kernfs_inode_init(void); /* * dir.c diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index f973ae9b05f1..8eaf417187f1 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -246,5 +246,4 @@ void __init kernfs_init(void) kernfs_node_cache = kmem_cache_create("kernfs_node_cache", sizeof(struct kernfs_node), 0, SLAB_PANIC, NULL); - kernfs_inode_init(); } diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 57c40e34f56f..6000d3029b26 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -390,12 +390,6 @@ clear_fields: ip->ip_conn = NULL; } -static struct backing_dev_info dlmfs_backing_dev_info = { - .name = "ocfs2-dlmfs", - .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; - static struct inode *dlmfs_get_root_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); @@ -404,7 +398,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) if (inode) { inode->i_ino = get_next_ino(); inode_init_owner(inode, NULL, mode); - inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; + inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inc_nlink(inode); @@ -428,7 +422,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, inode->i_ino = get_next_ino(); inode_init_owner(inode, parent, mode); - inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; + inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; ip = DLMFS_I(inode); @@ -643,10 +637,6 @@ static int __init init_dlmfs_fs(void) int status; int cleanup_inode = 0, cleanup_worker = 0; - status = bdi_init(&dlmfs_backing_dev_info); - if (status) - return status; - dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache", sizeof(struct dlmfs_inode_private), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| @@ -673,7 +663,6 @@ bail: kmem_cache_destroy(dlmfs_inode_cache); if (cleanup_worker) destroy_workqueue(user_dlm_worker); - bdi_destroy(&dlmfs_backing_dev_info); } else printk("OCFS2 User DLM kernel interface loaded\n"); return status; @@ -693,7 +682,6 @@ static void __exit exit_dlmfs_fs(void) rcu_barrier(); kmem_cache_destroy(dlmfs_inode_cache); - bdi_destroy(&dlmfs_backing_dev_info); } MODULE_AUTHOR("Oracle"); -- cgit v1.2.3 From b4caecd48005fbed3949dde6c1cb233142fd69e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:32 +0100 Subject: fs: introduce f_op->mmap_capabilities for nommu mmap support Since "BDI: Provide backing device capability information [try #3]" the backing_dev_info structure also provides flags for the kind of mmap operation available in a nommu environment, which is entirely unrelated to it's original purpose. Introduce a new nommu-only file operation to provide this information to the nommu mmap code instead. Splitting this from the backing_dev_info structure allows to remove lots of backing_dev_info instance that aren't otherwise needed, and entirely gets rid of the concept of providing a backing_dev_info for a character device. It also removes the need for the mtd_inodefs filesystem. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Acked-by: Brian Norris Signed-off-by: Jens Axboe --- Documentation/nommu-mmap.txt | 8 +-- block/blk-core.c | 2 +- drivers/char/mem.c | 64 ++++++++++---------- drivers/mtd/mtdchar.c | 72 ++++------------------ drivers/mtd/mtdconcat.c | 10 ---- drivers/mtd/mtdcore.c | 80 +++++++------------------ drivers/mtd/mtdpart.c | 1 - drivers/staging/lustre/lustre/llite/llite_lib.c | 2 +- fs/9p/v9fs.c | 2 +- fs/afs/volume.c | 2 +- fs/aio.c | 14 +---- fs/btrfs/disk-io.c | 3 +- fs/char_dev.c | 24 -------- fs/cifs/connect.c | 2 +- fs/coda/inode.c | 2 +- fs/configfs/configfs_internal.h | 2 - fs/configfs/inode.c | 18 +----- fs/configfs/mount.c | 11 +--- fs/ecryptfs/main.c | 2 +- fs/exofs/super.c | 2 +- fs/ncpfs/inode.c | 2 +- fs/ramfs/file-nommu.c | 7 +++ fs/ramfs/inode.c | 22 +------ fs/romfs/mmap-nommu.c | 10 ++++ fs/ubifs/super.c | 2 +- include/linux/backing-dev.h | 33 ++-------- include/linux/cdev.h | 2 - include/linux/fs.h | 23 +++++++ include/linux/mtd/mtd.h | 2 + mm/backing-dev.c | 7 +-- mm/nommu.c | 69 ++++++++++----------- security/security.c | 13 ++-- 32 files changed, 169 insertions(+), 346 deletions(-) (limited to 'fs') diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt index 8e1ddec2c78a..ae57b9ea0d41 100644 --- a/Documentation/nommu-mmap.txt +++ b/Documentation/nommu-mmap.txt @@ -43,12 +43,12 @@ and it's also much more restricted in the latter case: even if this was created by another process. - If possible, the file mapping will be directly on the backing device - if the backing device has the BDI_CAP_MAP_DIRECT capability and + if the backing device has the NOMMU_MAP_DIRECT capability and appropriate mapping protection capabilities. Ramfs, romfs, cramfs and mtd might all permit this. - If the backing device device can't or won't permit direct sharing, - but does have the BDI_CAP_MAP_COPY capability, then a copy of the + but does have the NOMMU_MAP_COPY capability, then a copy of the appropriate bit of the file will be read into a contiguous bit of memory and any extraneous space beyond the EOF will be cleared @@ -220,7 +220,7 @@ directly (can't be copied). The file->f_op->mmap() operation will be called to actually inaugurate the mapping. It can be rejected at that point. Returning the ENOSYS error will -cause the mapping to be copied instead if BDI_CAP_MAP_COPY is specified. +cause the mapping to be copied instead if NOMMU_MAP_COPY is specified. The vm_ops->close() routine will be invoked when the last mapping on a chardev is removed. An existing mapping will be shared, partially or not, if possible @@ -232,7 +232,7 @@ want to handle it, despite the fact it's got an operation. For instance, it might try directing the call to a secondary driver which turns out not to implement it. Such is the case for the framebuffer driver which attempts to direct the call to the device-specific driver. Under such circumstances, the -mapping request will be rejected if BDI_CAP_MAP_COPY is not specified, and a +mapping request will be rejected if NOMMU_MAP_COPY is not specified, and a copy mapped otherwise. IMPORTANT NOTE: diff --git a/block/blk-core.c b/block/blk-core.c index 3ad405571dcc..928aac29bccd 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -607,7 +607,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; q->backing_dev_info.state = 0; - q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY; + q->backing_dev_info.capabilities = 0; q->backing_dev_info.name = "block"; q->node = node_id; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 4c58333b4257..9a6b63783a94 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -287,13 +287,24 @@ static unsigned long get_unmapped_area_mem(struct file *file, return pgoff << PAGE_SHIFT; } +/* permit direct mmap, for read, write or exec */ +static unsigned memory_mmap_capabilities(struct file *file) +{ + return NOMMU_MAP_DIRECT | + NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC; +} + +static unsigned zero_mmap_capabilities(struct file *file) +{ + return NOMMU_MAP_COPY; +} + /* can't do an in-place private mapping if there's no MMU */ static inline int private_mapping_ok(struct vm_area_struct *vma) { return vma->vm_flags & VM_MAYSHARE; } #else -#define get_unmapped_area_mem NULL static inline int private_mapping_ok(struct vm_area_struct *vma) { @@ -721,7 +732,10 @@ static const struct file_operations mem_fops = { .write = write_mem, .mmap = mmap_mem, .open = open_mem, +#ifndef CONFIG_MMU .get_unmapped_area = get_unmapped_area_mem, + .mmap_capabilities = memory_mmap_capabilities, +#endif }; #ifdef CONFIG_DEVKMEM @@ -731,7 +745,10 @@ static const struct file_operations kmem_fops = { .write = write_kmem, .mmap = mmap_kmem, .open = open_kmem, +#ifndef CONFIG_MMU .get_unmapped_area = get_unmapped_area_mem, + .mmap_capabilities = memory_mmap_capabilities, +#endif }; #endif @@ -760,16 +777,9 @@ static const struct file_operations zero_fops = { .read_iter = read_iter_zero, .aio_write = aio_write_zero, .mmap = mmap_zero, -}; - -/* - * capabilities for /dev/zero - * - permits private mappings, "copies" are taken of the source of zeros - * - no writeback happens - */ -static struct backing_dev_info zero_bdi = { - .name = "char/mem", - .capabilities = BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK, +#ifndef CONFIG_MMU + .mmap_capabilities = zero_mmap_capabilities, +#endif }; static const struct file_operations full_fops = { @@ -783,22 +793,22 @@ static const struct memdev { const char *name; umode_t mode; const struct file_operations *fops; - struct backing_dev_info *dev_info; + fmode_t fmode; } devlist[] = { - [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi }, + [1] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET }, #ifdef CONFIG_DEVKMEM - [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi }, + [2] = { "kmem", 0, &kmem_fops, FMODE_UNSIGNED_OFFSET }, #endif - [3] = { "null", 0666, &null_fops, NULL }, + [3] = { "null", 0666, &null_fops, 0 }, #ifdef CONFIG_DEVPORT - [4] = { "port", 0, &port_fops, NULL }, + [4] = { "port", 0, &port_fops, 0 }, #endif - [5] = { "zero", 0666, &zero_fops, &zero_bdi }, - [7] = { "full", 0666, &full_fops, NULL }, - [8] = { "random", 0666, &random_fops, NULL }, - [9] = { "urandom", 0666, &urandom_fops, NULL }, + [5] = { "zero", 0666, &zero_fops, 0 }, + [7] = { "full", 0666, &full_fops, 0 }, + [8] = { "random", 0666, &random_fops, 0 }, + [9] = { "urandom", 0666, &urandom_fops, 0 }, #ifdef CONFIG_PRINTK - [11] = { "kmsg", 0644, &kmsg_fops, NULL }, + [11] = { "kmsg", 0644, &kmsg_fops, 0 }, #endif }; @@ -816,12 +826,7 @@ static int memory_open(struct inode *inode, struct file *filp) return -ENXIO; filp->f_op = dev->fops; - if (dev->dev_info) - filp->f_mapping->backing_dev_info = dev->dev_info; - - /* Is /dev/mem or /dev/kmem ? */ - if (dev->dev_info == &directly_mappable_cdev_bdi) - filp->f_mode |= FMODE_UNSIGNED_OFFSET; + filp->f_mode |= dev->fmode; if (dev->fops->open) return dev->fops->open(inode, filp); @@ -846,11 +851,6 @@ static struct class *mem_class; static int __init chr_dev_init(void) { int minor; - int err; - - err = bdi_init(&zero_bdi); - if (err) - return err; if (register_chrdev(MEM_MAJOR, "mem", &memory_fops)) printk("unable to get major %d for memory devs\n", MEM_MAJOR); diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index 53563955931b..55fa27ecf4e1 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -49,7 +49,6 @@ static DEFINE_MUTEX(mtd_mutex); */ struct mtd_file_info { struct mtd_info *mtd; - struct inode *ino; enum mtd_file_modes mode; }; @@ -59,10 +58,6 @@ static loff_t mtdchar_lseek(struct file *file, loff_t offset, int orig) return fixed_size_llseek(file, offset, orig, mfi->mtd->size); } -static int count; -static struct vfsmount *mnt; -static struct file_system_type mtd_inodefs_type; - static int mtdchar_open(struct inode *inode, struct file *file) { int minor = iminor(inode); @@ -70,7 +65,6 @@ static int mtdchar_open(struct inode *inode, struct file *file) int ret = 0; struct mtd_info *mtd; struct mtd_file_info *mfi; - struct inode *mtd_ino; pr_debug("MTD_open\n"); @@ -78,10 +72,6 @@ static int mtdchar_open(struct inode *inode, struct file *file) if ((file->f_mode & FMODE_WRITE) && (minor & 1)) return -EACCES; - ret = simple_pin_fs(&mtd_inodefs_type, &mnt, &count); - if (ret) - return ret; - mutex_lock(&mtd_mutex); mtd = get_mtd_device(NULL, devnum); @@ -95,43 +85,26 @@ static int mtdchar_open(struct inode *inode, struct file *file) goto out1; } - mtd_ino = iget_locked(mnt->mnt_sb, devnum); - if (!mtd_ino) { - ret = -ENOMEM; - goto out1; - } - if (mtd_ino->i_state & I_NEW) { - mtd_ino->i_private = mtd; - mtd_ino->i_mode = S_IFCHR; - mtd_ino->i_data.backing_dev_info = mtd->backing_dev_info; - unlock_new_inode(mtd_ino); - } - file->f_mapping = mtd_ino->i_mapping; - /* You can't open it RW if it's not a writeable device */ if ((file->f_mode & FMODE_WRITE) && !(mtd->flags & MTD_WRITEABLE)) { ret = -EACCES; - goto out2; + goto out1; } mfi = kzalloc(sizeof(*mfi), GFP_KERNEL); if (!mfi) { ret = -ENOMEM; - goto out2; + goto out1; } - mfi->ino = mtd_ino; mfi->mtd = mtd; file->private_data = mfi; mutex_unlock(&mtd_mutex); return 0; -out2: - iput(mtd_ino); out1: put_mtd_device(mtd); out: mutex_unlock(&mtd_mutex); - simple_release_fs(&mnt, &count); return ret; } /* mtdchar_open */ @@ -148,12 +121,9 @@ static int mtdchar_close(struct inode *inode, struct file *file) if ((file->f_mode & FMODE_WRITE)) mtd_sync(mtd); - iput(mfi->ino); - put_mtd_device(mtd); file->private_data = NULL; kfree(mfi); - simple_release_fs(&mnt, &count); return 0; } /* mtdchar_close */ @@ -1117,6 +1087,13 @@ static unsigned long mtdchar_get_unmapped_area(struct file *file, ret = mtd_get_unmapped_area(mtd, len, offset, flags); return ret == -EOPNOTSUPP ? -ENODEV : ret; } + +static unsigned mtdchar_mmap_capabilities(struct file *file) +{ + struct mtd_file_info *mfi = file->private_data; + + return mtd_mmap_capabilities(mfi->mtd); +} #endif /* @@ -1160,27 +1137,10 @@ static const struct file_operations mtd_fops = { .mmap = mtdchar_mmap, #ifndef CONFIG_MMU .get_unmapped_area = mtdchar_get_unmapped_area, + .mmap_capabilities = mtdchar_mmap_capabilities, #endif }; -static const struct super_operations mtd_ops = { - .drop_inode = generic_delete_inode, - .statfs = simple_statfs, -}; - -static struct dentry *mtd_inodefs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) -{ - return mount_pseudo(fs_type, "mtd_inode:", &mtd_ops, NULL, MTD_INODE_FS_MAGIC); -} - -static struct file_system_type mtd_inodefs_type = { - .name = "mtd_inodefs", - .mount = mtd_inodefs_mount, - .kill_sb = kill_anon_super, -}; -MODULE_ALIAS_FS("mtd_inodefs"); - int __init init_mtdchar(void) { int ret; @@ -1193,23 +1153,11 @@ int __init init_mtdchar(void) return ret; } - ret = register_filesystem(&mtd_inodefs_type); - if (ret) { - pr_err("Can't register mtd_inodefs filesystem, error %d\n", - ret); - goto err_unregister_chdev; - } - - return ret; - -err_unregister_chdev: - __unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd"); return ret; } void __exit cleanup_mtdchar(void) { - unregister_filesystem(&mtd_inodefs_type); __unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd"); } diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c index b9000563b9f4..eacc3aac7327 100644 --- a/drivers/mtd/mtdconcat.c +++ b/drivers/mtd/mtdconcat.c @@ -732,8 +732,6 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[], /* subdevices to c concat->mtd.ecc_stats.badblocks = subdev[0]->ecc_stats.badblocks; - concat->mtd.backing_dev_info = subdev[0]->backing_dev_info; - concat->subdev[0] = subdev[0]; for (i = 1; i < num_devs; i++) { @@ -761,14 +759,6 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[], /* subdevices to c subdev[i]->flags & MTD_WRITEABLE; } - /* only permit direct mapping if the BDIs are all the same - * - copy-mapping is still permitted - */ - if (concat->mtd.backing_dev_info != - subdev[i]->backing_dev_info) - concat->mtd.backing_dev_info = - &default_backing_dev_info; - concat->mtd.size += subdev[i]->size; concat->mtd.ecc_stats.badblocks += subdev[i]->ecc_stats.badblocks; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 4c611871d7e6..ff38a1df22f7 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -43,33 +43,7 @@ #include "mtdcore.h" -/* - * backing device capabilities for non-mappable devices (such as NAND flash) - * - permits private mappings, copies are taken of the data - */ -static struct backing_dev_info mtd_bdi_unmappable = { - .capabilities = BDI_CAP_MAP_COPY, -}; - -/* - * backing device capabilities for R/O mappable devices (such as ROM) - * - permits private mappings, copies are taken of the data - * - permits non-writable shared mappings - */ -static struct backing_dev_info mtd_bdi_ro_mappable = { - .capabilities = (BDI_CAP_MAP_COPY | BDI_CAP_MAP_DIRECT | - BDI_CAP_EXEC_MAP | BDI_CAP_READ_MAP), -}; - -/* - * backing device capabilities for writable mappable devices (such as RAM) - * - permits private mappings, copies are taken of the data - * - permits non-writable shared mappings - */ -static struct backing_dev_info mtd_bdi_rw_mappable = { - .capabilities = (BDI_CAP_MAP_COPY | BDI_CAP_MAP_DIRECT | - BDI_CAP_EXEC_MAP | BDI_CAP_READ_MAP | - BDI_CAP_WRITE_MAP), +static struct backing_dev_info mtd_bdi = { }; static int mtd_cls_suspend(struct device *dev, pm_message_t state); @@ -365,6 +339,22 @@ static struct device_type mtd_devtype = { .release = mtd_release, }; +#ifndef CONFIG_MMU +unsigned mtd_mmap_capabilities(struct mtd_info *mtd) +{ + switch (mtd->type) { + case MTD_RAM: + return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC | + NOMMU_MAP_READ | NOMMU_MAP_WRITE; + case MTD_ROM: + return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC | + NOMMU_MAP_READ; + default: + return NOMMU_MAP_COPY; + } +} +#endif + /** * add_mtd_device - register an MTD device * @mtd: pointer to new MTD device info structure @@ -380,19 +370,7 @@ int add_mtd_device(struct mtd_info *mtd) struct mtd_notifier *not; int i, error; - if (!mtd->backing_dev_info) { - switch (mtd->type) { - case MTD_RAM: - mtd->backing_dev_info = &mtd_bdi_rw_mappable; - break; - case MTD_ROM: - mtd->backing_dev_info = &mtd_bdi_ro_mappable; - break; - default: - mtd->backing_dev_info = &mtd_bdi_unmappable; - break; - } - } + mtd->backing_dev_info = &mtd_bdi; BUG_ON(mtd->writesize == 0); mutex_lock(&mtd_table_mutex); @@ -1237,17 +1215,9 @@ static int __init init_mtd(void) if (ret) goto err_reg; - ret = mtd_bdi_init(&mtd_bdi_unmappable, "mtd-unmap"); - if (ret) - goto err_bdi1; - - ret = mtd_bdi_init(&mtd_bdi_ro_mappable, "mtd-romap"); - if (ret) - goto err_bdi2; - - ret = mtd_bdi_init(&mtd_bdi_rw_mappable, "mtd-rwmap"); + ret = mtd_bdi_init(&mtd_bdi, "mtd"); if (ret) - goto err_bdi3; + goto err_bdi; proc_mtd = proc_create("mtd", 0, NULL, &mtd_proc_ops); @@ -1260,11 +1230,7 @@ static int __init init_mtd(void) out_procfs: if (proc_mtd) remove_proc_entry("mtd", NULL); -err_bdi3: - bdi_destroy(&mtd_bdi_ro_mappable); -err_bdi2: - bdi_destroy(&mtd_bdi_unmappable); -err_bdi1: +err_bdi: class_unregister(&mtd_class); err_reg: pr_err("Error registering mtd class or bdi: %d\n", ret); @@ -1277,9 +1243,7 @@ static void __exit cleanup_mtd(void) if (proc_mtd) remove_proc_entry("mtd", NULL); class_unregister(&mtd_class); - bdi_destroy(&mtd_bdi_unmappable); - bdi_destroy(&mtd_bdi_ro_mappable); - bdi_destroy(&mtd_bdi_rw_mappable); + bdi_destroy(&mtd_bdi); } module_init(init_mtd); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index a3e3a7d074d5..e779de315ade 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -378,7 +378,6 @@ static struct mtd_part *allocate_partition(struct mtd_info *master, slave->mtd.name = name; slave->mtd.owner = master->owner; - slave->mtd.backing_dev_info = master->backing_dev_info; /* NOTE: we don't arrange MTDs as a tree; it'd be error-prone * to have the same data be in two different partitions. diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c index a3367bfb1456..d5b149c5542d 100644 --- a/drivers/staging/lustre/lustre/llite/llite_lib.c +++ b/drivers/staging/lustre/lustre/llite/llite_lib.c @@ -987,7 +987,7 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt) if (err) goto out_free; lsi->lsi_flags |= LSI_BDI_INITIALIZED; - lsi->lsi_bdi.capabilities = BDI_CAP_MAP_COPY; + lsi->lsi_bdi.capabilities = 0; err = ll_bdi_register(&lsi->lsi_bdi); if (err) goto out_free; diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 6894b085f0ee..620d93489539 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -335,7 +335,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, } init_rwsem(&v9ses->rename_sem); - rc = bdi_setup_and_register(&v9ses->bdi, "9p", BDI_CAP_MAP_COPY); + rc = bdi_setup_and_register(&v9ses->bdi, "9p"); if (rc) { kfree(v9ses->aname); kfree(v9ses->uname); diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 2b607257820c..d142a2449e65 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -106,7 +106,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params) volume->cell = params->cell; volume->vid = vlocation->vldb.vid[params->type]; - ret = bdi_setup_and_register(&volume->bdi, "afs", BDI_CAP_MAP_COPY); + ret = bdi_setup_and_register(&volume->bdi, "afs"); if (ret) goto error_bdi; diff --git a/fs/aio.c b/fs/aio.c index 1b7893ecc296..6f13d3fab07f 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -165,15 +165,6 @@ static struct vfsmount *aio_mnt; static const struct file_operations aio_ring_fops; static const struct address_space_operations aio_ctx_aops; -/* Backing dev info for aio fs. - * -no dirty page accounting or writeback happens - */ -static struct backing_dev_info aio_fs_backing_dev_info = { - .name = "aiofs", - .state = 0, - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY, -}; - static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) { struct qstr this = QSTR_INIT("[aio]", 5); @@ -185,7 +176,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) inode->i_mapping->a_ops = &aio_ctx_aops; inode->i_mapping->private_data = ctx; - inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info; + inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_size = PAGE_SIZE * nr_pages; path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this); @@ -230,9 +221,6 @@ static int __init aio_setup(void) if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); - if (bdi_init(&aio_fs_backing_dev_info)) - panic("Failed to init aio fs backing dev info."); - kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8c63419a7f70..afc4092989cd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1715,8 +1715,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) { int err; - bdi->capabilities = BDI_CAP_MAP_COPY; - err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY); + err = bdi_setup_and_register(bdi, "btrfs"); if (err) return err; diff --git a/fs/char_dev.c b/fs/char_dev.c index 67b2007f10fe..ea06a3d0364c 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -24,27 +24,6 @@ #include "internal.h" -/* - * capabilities for /dev/mem, /dev/kmem and similar directly mappable character - * devices - * - permits shared-mmap for read, write and/or exec - * - does not permit private mmap in NOMMU mode (can't do COW) - * - no readahead or I/O queue unplugging required - */ -struct backing_dev_info directly_mappable_cdev_bdi = { - .name = "char", - .capabilities = ( -#ifdef CONFIG_MMU - /* permit private copies of the data to be taken */ - BDI_CAP_MAP_COPY | -#endif - /* permit direct mmap, for read, write or exec */ - BDI_CAP_MAP_DIRECT | - BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP | - /* no writeback happens */ - BDI_CAP_NO_ACCT_AND_WRITEBACK), -}; - static struct kobj_map *cdev_map; static DEFINE_MUTEX(chrdevs_lock); @@ -575,8 +554,6 @@ static struct kobject *base_probe(dev_t dev, int *part, void *data) void __init chrdev_init(void) { cdev_map = kobj_map_init(base_probe, &chrdevs_lock); - if (bdi_init(&directly_mappable_cdev_bdi)) - panic("Failed to init directly mappable cdev bdi"); } @@ -590,4 +567,3 @@ EXPORT_SYMBOL(cdev_del); EXPORT_SYMBOL(cdev_add); EXPORT_SYMBOL(__register_chrdev); EXPORT_SYMBOL(__unregister_chrdev); -EXPORT_SYMBOL(directly_mappable_cdev_bdi); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 2a772da16b83..d3aa999ab785 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3446,7 +3446,7 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info) int referral_walks_count = 0; #endif - rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY); + rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs"); if (rc) return rc; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index b945410bfcd5..82ec68b59208 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -183,7 +183,7 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent) goto unlock_out; } - error = bdi_setup_and_register(&vc->bdi, "coda", BDI_CAP_MAP_COPY); + error = bdi_setup_and_register(&vc->bdi, "coda"); if (error) goto unlock_out; diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index bd4a3c167091..a315677e44d3 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -70,8 +70,6 @@ extern int configfs_is_root(struct config_item *item); extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *); extern int configfs_create(struct dentry *, umode_t mode, int (*init)(struct inode *)); -extern int configfs_inode_init(void); -extern void configfs_inode_exit(void); extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); extern int configfs_make_dirent(struct configfs_dirent *, diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 5946ad98053f..0ad6b4d6de00 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -50,12 +50,6 @@ static const struct address_space_operations configfs_aops = { .write_end = simple_write_end, }; -static struct backing_dev_info configfs_backing_dev_info = { - .name = "configfs", - .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, -}; - static const struct inode_operations configfs_inode_operations ={ .setattr = configfs_setattr, }; @@ -137,7 +131,7 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd, if (inode) { inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &configfs_aops; - inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; + inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_op = &configfs_inode_operations; if (sd->s_iattr) { @@ -283,13 +277,3 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name) } mutex_unlock(&dir->d_inode->i_mutex); } - -int __init configfs_inode_init(void) -{ - return bdi_init(&configfs_backing_dev_info); -} - -void configfs_inode_exit(void) -{ - bdi_destroy(&configfs_backing_dev_info); -} diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index f6c285833390..da94e41bdbf6 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -145,19 +145,13 @@ static int __init configfs_init(void) if (!config_kobj) goto out2; - err = configfs_inode_init(); - if (err) - goto out3; - err = register_filesystem(&configfs_fs_type); if (err) - goto out4; + goto out3; return 0; -out4: - pr_err("Unable to register filesystem!\n"); - configfs_inode_exit(); out3: + pr_err("Unable to register filesystem!\n"); kobject_put(config_kobj); out2: kmem_cache_destroy(configfs_dir_cachep); @@ -172,7 +166,6 @@ static void __exit configfs_exit(void) kobject_put(config_kobj); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; - configfs_inode_exit(); } MODULE_AUTHOR("Oracle"); diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index d9eb84bda559..1895d60f4122 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -520,7 +520,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags goto out; } - rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY); + rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs"); if (rc) goto out1; diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 95965503afcb..fcc2e565f540 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -836,7 +836,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) goto free_sbi; } - ret = bdi_setup_and_register(&sbi->bdi, "exofs", BDI_CAP_MAP_COPY); + ret = bdi_setup_and_register(&sbi->bdi, "exofs"); if (ret) { EXOFS_DBGMSG("Failed to bdi_setup_and_register\n"); dput(sb->s_root); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index e31e589369a4..a699a3fc62c0 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -560,7 +560,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent) server = NCP_SBP(sb); memset(server, 0, sizeof(*server)); - error = bdi_setup_and_register(&server->bdi, "ncpfs", BDI_CAP_MAP_COPY); + error = bdi_setup_and_register(&server->bdi, "ncpfs"); if (error) goto out_fput; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index bbafbde3471a..f6ab41b39612 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -34,7 +34,14 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, unsigned long flags); static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma); +static unsigned ramfs_mmap_capabilities(struct file *file) +{ + return NOMMU_MAP_DIRECT | NOMMU_MAP_COPY | NOMMU_MAP_READ | + NOMMU_MAP_WRITE | NOMMU_MAP_EXEC; +} + const struct file_operations ramfs_file_operations = { + .mmap_capabilities = ramfs_mmap_capabilities, .mmap = ramfs_nommu_mmap, .get_unmapped_area = ramfs_nommu_get_unmapped_area, .read = new_sync_read, diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index d365b1c4eb3c..ad4d712002f4 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -50,14 +50,6 @@ static const struct address_space_operations ramfs_aops = { .set_page_dirty = __set_page_dirty_no_writeback, }; -static struct backing_dev_info ramfs_backing_dev_info = { - .name = "ramfs", - .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | - BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY | - BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP, -}; - struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev) { @@ -67,7 +59,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_mapping->a_ops = &ramfs_aops; - inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; + inode->i_mapping->backing_dev_info = &noop_backing_dev_info; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -267,19 +259,9 @@ static struct file_system_type ramfs_fs_type = { int __init init_ramfs_fs(void) { static unsigned long once; - int err; if (test_and_set_bit(0, &once)) return 0; - - err = bdi_init(&ramfs_backing_dev_info); - if (err) - return err; - - err = register_filesystem(&ramfs_fs_type); - if (err) - bdi_destroy(&ramfs_backing_dev_info); - - return err; + return register_filesystem(&ramfs_fs_type); } fs_initcall(init_ramfs_fs); diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c index ea06c7554860..7da9e2153953 100644 --- a/fs/romfs/mmap-nommu.c +++ b/fs/romfs/mmap-nommu.c @@ -70,6 +70,15 @@ static int romfs_mmap(struct file *file, struct vm_area_struct *vma) return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS; } +static unsigned romfs_mmap_capabilities(struct file *file) +{ + struct mtd_info *mtd = file_inode(file)->i_sb->s_mtd; + + if (!mtd) + return NOMMU_MAP_COPY; + return mtd_mmap_capabilities(mtd); +} + const struct file_operations romfs_ro_fops = { .llseek = generic_file_llseek, .read = new_sync_read, @@ -77,4 +86,5 @@ const struct file_operations romfs_ro_fops = { .splice_read = generic_file_splice_read, .mmap = romfs_mmap, .get_unmapped_area = romfs_get_unmapped_area, + .mmap_capabilities = romfs_mmap_capabilities, }; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 106bf20629ce..ed93dc6ae245 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2017,7 +2017,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) * Read-ahead will be disabled because @c->bdi.ra_pages is 0. */ c->bdi.name = "ubifs", - c->bdi.capabilities = BDI_CAP_MAP_COPY; + c->bdi.capabilities = 0; err = bdi_init(&c->bdi); if (err) goto out_close; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e936cea856dc..478f95d92d73 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -114,7 +114,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); -int __must_check bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); +int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, enum wb_reason reason); void bdi_start_background_writeback(struct backing_dev_info *bdi); @@ -228,42 +228,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages - * - * These flags let !MMU mmap() govern direct device mapping vs immediate - * copying more easily for MAP_PRIVATE, especially for ROM filesystems. - * - * BDI_CAP_MAP_COPY: Copy can be mapped (MAP_PRIVATE) - * BDI_CAP_MAP_DIRECT: Can be mapped directly (MAP_SHARED) - * BDI_CAP_READ_MAP: Can be mapped for reading - * BDI_CAP_WRITE_MAP: Can be mapped for writing - * BDI_CAP_EXEC_MAP: Can be mapped for execution - * * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 -#define BDI_CAP_MAP_COPY 0x00000004 -#define BDI_CAP_MAP_DIRECT 0x00000008 -#define BDI_CAP_READ_MAP 0x00000010 -#define BDI_CAP_WRITE_MAP 0x00000020 -#define BDI_CAP_EXEC_MAP 0x00000040 -#define BDI_CAP_NO_ACCT_WB 0x00000080 -#define BDI_CAP_STABLE_WRITES 0x00000200 -#define BDI_CAP_STRICTLIMIT 0x00000400 - -#define BDI_CAP_VMFLAGS \ - (BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP) +#define BDI_CAP_NO_ACCT_WB 0x00000004 +#define BDI_CAP_STABLE_WRITES 0x00000008 +#define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) -#if defined(VM_MAYREAD) && \ - (BDI_CAP_READ_MAP != VM_MAYREAD || \ - BDI_CAP_WRITE_MAP != VM_MAYWRITE || \ - BDI_CAP_EXEC_MAP != VM_MAYEXEC) -#error please change backing_dev_info::capabilities flags -#endif - extern struct backing_dev_info default_backing_dev_info; extern struct backing_dev_info noop_backing_dev_info; diff --git a/include/linux/cdev.h b/include/linux/cdev.h index fb4591977b03..f8763615a5f2 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -30,6 +30,4 @@ void cdev_del(struct cdev *); void cd_forget(struct inode *); -extern struct backing_dev_info directly_mappable_cdev_bdi; - #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..1dada399aa23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1502,6 +1502,26 @@ struct block_device_operations; #define HAVE_COMPAT_IOCTL 1 #define HAVE_UNLOCKED_IOCTL 1 +/* + * These flags let !MMU mmap() govern direct device mapping vs immediate + * copying more easily for MAP_PRIVATE, especially for ROM filesystems. + * + * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) + * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) + * NOMMU_MAP_READ: Can be mapped for reading + * NOMMU_MAP_WRITE: Can be mapped for writing + * NOMMU_MAP_EXEC: Can be mapped for execution + */ +#define NOMMU_MAP_COPY 0x00000001 +#define NOMMU_MAP_DIRECT 0x00000008 +#define NOMMU_MAP_READ VM_MAYREAD +#define NOMMU_MAP_WRITE VM_MAYWRITE +#define NOMMU_MAP_EXEC VM_MAYEXEC + +#define NOMMU_VMFLAGS \ + (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) + + struct iov_iter; struct file_operations { @@ -1536,6 +1556,9 @@ struct file_operations { long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); +#ifndef CONFIG_MMU + unsigned (*mmap_capabilities)(struct file *); +#endif }; struct inode_operations { diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 031ff3a9a0bd..3301c4c289d6 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -408,4 +408,6 @@ static inline int mtd_is_bitflip_or_eccerr(int err) { return mtd_is_bitflip(err) || mtd_is_eccerr(err); } +unsigned mtd_mmap_capabilities(struct mtd_info *mtd); + #endif /* __MTD_MTD_H__ */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 0ae0df55000b..16c68958aeda 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -17,8 +17,6 @@ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); struct backing_dev_info default_backing_dev_info = { .name = "default", .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, - .state = 0, - .capabilities = BDI_CAP_MAP_COPY, }; EXPORT_SYMBOL_GPL(default_backing_dev_info); @@ -513,13 +511,12 @@ EXPORT_SYMBOL(bdi_destroy); * For use from filesystems to quickly init and register a bdi associated * with dirty writeback */ -int bdi_setup_and_register(struct backing_dev_info *bdi, char *name, - unsigned int cap) +int bdi_setup_and_register(struct backing_dev_info *bdi, char *name) { int err; bdi->name = name; - bdi->capabilities = cap; + bdi->capabilities = 0; err = bdi_init(bdi); if (err) return err; diff --git a/mm/nommu.c b/mm/nommu.c index b51eadf6d952..13af96f35a4b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -946,9 +946,6 @@ static int validate_mmap_request(struct file *file, return -EOVERFLOW; if (file) { - /* validate file mapping requests */ - struct address_space *mapping; - /* files must support mmap */ if (!file->f_op->mmap) return -ENODEV; @@ -957,28 +954,22 @@ static int validate_mmap_request(struct file *file, * - we support chardevs that provide their own "memory" * - we support files/blockdevs that are memory backed */ - mapping = file->f_mapping; - if (!mapping) - mapping = file_inode(file)->i_mapping; - - capabilities = 0; - if (mapping && mapping->backing_dev_info) - capabilities = mapping->backing_dev_info->capabilities; - - if (!capabilities) { + if (file->f_op->mmap_capabilities) { + capabilities = file->f_op->mmap_capabilities(file); + } else { /* no explicit capabilities set, so assume some * defaults */ switch (file_inode(file)->i_mode & S_IFMT) { case S_IFREG: case S_IFBLK: - capabilities = BDI_CAP_MAP_COPY; + capabilities = NOMMU_MAP_COPY; break; case S_IFCHR: capabilities = - BDI_CAP_MAP_DIRECT | - BDI_CAP_READ_MAP | - BDI_CAP_WRITE_MAP; + NOMMU_MAP_DIRECT | + NOMMU_MAP_READ | + NOMMU_MAP_WRITE; break; default: @@ -989,9 +980,9 @@ static int validate_mmap_request(struct file *file, /* eliminate any capabilities that we can't support on this * device */ if (!file->f_op->get_unmapped_area) - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; if (!file->f_op->read) - capabilities &= ~BDI_CAP_MAP_COPY; + capabilities &= ~NOMMU_MAP_COPY; /* The file shall have been opened with read permission. */ if (!(file->f_mode & FMODE_READ)) @@ -1010,29 +1001,29 @@ static int validate_mmap_request(struct file *file, if (locks_verify_locked(file)) return -EAGAIN; - if (!(capabilities & BDI_CAP_MAP_DIRECT)) + if (!(capabilities & NOMMU_MAP_DIRECT)) return -ENODEV; /* we mustn't privatise shared mappings */ - capabilities &= ~BDI_CAP_MAP_COPY; + capabilities &= ~NOMMU_MAP_COPY; } else { /* we're going to read the file into private memory we * allocate */ - if (!(capabilities & BDI_CAP_MAP_COPY)) + if (!(capabilities & NOMMU_MAP_COPY)) return -ENODEV; /* we don't permit a private writable mapping to be * shared with the backing device */ if (prot & PROT_WRITE) - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; } - if (capabilities & BDI_CAP_MAP_DIRECT) { - if (((prot & PROT_READ) && !(capabilities & BDI_CAP_READ_MAP)) || - ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) || - ((prot & PROT_EXEC) && !(capabilities & BDI_CAP_EXEC_MAP)) + if (capabilities & NOMMU_MAP_DIRECT) { + if (((prot & PROT_READ) && !(capabilities & NOMMU_MAP_READ)) || + ((prot & PROT_WRITE) && !(capabilities & NOMMU_MAP_WRITE)) || + ((prot & PROT_EXEC) && !(capabilities & NOMMU_MAP_EXEC)) ) { - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; if (flags & MAP_SHARED) { printk(KERN_WARNING "MAP_SHARED not completely supported on !MMU\n"); @@ -1049,21 +1040,21 @@ static int validate_mmap_request(struct file *file, } else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) { /* handle implication of PROT_EXEC by PROT_READ */ if (current->personality & READ_IMPLIES_EXEC) { - if (capabilities & BDI_CAP_EXEC_MAP) + if (capabilities & NOMMU_MAP_EXEC) prot |= PROT_EXEC; } } else if ((prot & PROT_READ) && (prot & PROT_EXEC) && - !(capabilities & BDI_CAP_EXEC_MAP) + !(capabilities & NOMMU_MAP_EXEC) ) { /* backing file is not executable, try to copy */ - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; } } else { /* anonymous mappings are always memory backed and can be * privately mapped */ - capabilities = BDI_CAP_MAP_COPY; + capabilities = NOMMU_MAP_COPY; /* handle PROT_EXEC implication by PROT_READ */ if ((prot & PROT_READ) && @@ -1095,7 +1086,7 @@ static unsigned long determine_vm_flags(struct file *file, vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags); /* vm_flags |= mm->def_flags; */ - if (!(capabilities & BDI_CAP_MAP_DIRECT)) { + if (!(capabilities & NOMMU_MAP_DIRECT)) { /* attempt to share read-only copies of mapped file chunks */ vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; if (file && !(prot & PROT_WRITE)) @@ -1104,7 +1095,7 @@ static unsigned long determine_vm_flags(struct file *file, /* overlay a shareable mapping on the backing device or inode * if possible - used for chardevs, ramfs/tmpfs/shmfs and * romfs/cramfs */ - vm_flags |= VM_MAYSHARE | (capabilities & BDI_CAP_VMFLAGS); + vm_flags |= VM_MAYSHARE | (capabilities & NOMMU_VMFLAGS); if (flags & MAP_SHARED) vm_flags |= VM_SHARED; } @@ -1157,7 +1148,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * shared mappings on devices or memory * - VM_MAYSHARE will be set if it may attempt to share */ - if (capabilities & BDI_CAP_MAP_DIRECT) { + if (capabilities & NOMMU_MAP_DIRECT) { ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); if (ret == 0) { /* shouldn't return success if we're not sharing */ @@ -1346,7 +1337,7 @@ unsigned long do_mmap_pgoff(struct file *file, if ((pregion->vm_pgoff != pgoff || rpglen != pglen) && !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) { /* new mapping is not a subset of the region */ - if (!(capabilities & BDI_CAP_MAP_DIRECT)) + if (!(capabilities & NOMMU_MAP_DIRECT)) goto sharing_violation; continue; } @@ -1385,7 +1376,7 @@ unsigned long do_mmap_pgoff(struct file *file, * - this is the hook for quasi-memory character devices to * tell us the location of a shared mapping */ - if (capabilities & BDI_CAP_MAP_DIRECT) { + if (capabilities & NOMMU_MAP_DIRECT) { addr = file->f_op->get_unmapped_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) { @@ -1397,10 +1388,10 @@ unsigned long do_mmap_pgoff(struct file *file, * the mapping so we'll have to attempt to copy * it */ ret = -ENODEV; - if (!(capabilities & BDI_CAP_MAP_COPY)) + if (!(capabilities & NOMMU_MAP_COPY)) goto error_just_free; - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; } else { vma->vm_start = region->vm_start = addr; vma->vm_end = region->vm_end = addr + len; @@ -1411,7 +1402,7 @@ unsigned long do_mmap_pgoff(struct file *file, vma->vm_region = region; /* set up the mapping - * - the region is filled in if BDI_CAP_MAP_DIRECT is still set + * - the region is filled in if NOMMU_MAP_DIRECT is still set */ if (file && vma->vm_flags & VM_SHARED) ret = do_mmap_shared_file(vma); diff --git a/security/security.c b/security/security.c index 18b35c63fc0c..a0442b20f001 100644 --- a/security/security.c +++ b/security/security.c @@ -726,16 +726,15 @@ static inline unsigned long mmap_prot(struct file *file, unsigned long prot) return prot | PROT_EXEC; /* * ditto if it's not on noexec mount, except that on !MMU we need - * BDI_CAP_EXEC_MMAP (== VM_MAYEXEC) in this case + * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case */ if (!(file->f_path.mnt->mnt_flags & MNT_NOEXEC)) { #ifndef CONFIG_MMU - unsigned long caps = 0; - struct address_space *mapping = file->f_mapping; - if (mapping && mapping->backing_dev_info) - caps = mapping->backing_dev_info->capabilities; - if (!(caps & BDI_CAP_EXEC_MAP)) - return prot; + if (file->f_op->mmap_capabilities) { + unsigned caps = file->f_op->mmap_capabilities(file); + if (!(caps & NOMMU_MAP_EXEC)) + return prot; + } #endif return prot | PROT_EXEC; } -- cgit v1.2.3 From 564f00f6c03a9339c259eb71a5b3aa8ef7ff1c2e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:33 +0100 Subject: block_dev: only write bdev inode on close Since 018a17bdc865 ("bdi: reimplement bdev_inode_switch_bdi()") the block device code writes out all dirty data whenever switching the backing_dev_info for a block device inode. But a block device inode can only be dirtied when it is in use, which means we only have to write it out on the final blkdev_put, but not when doing a blkdev_get. Factoring out the write out from the bdi list switch prepares from removing the list switch later in the series. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- fs/block_dev.c | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index b48c41bf0f86..026ca7b8431c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -49,6 +49,17 @@ inline struct block_device *I_BDEV(struct inode *inode) } EXPORT_SYMBOL(I_BDEV); +static void bdev_write_inode(struct inode *inode) +{ + spin_lock(&inode->i_lock); + while (inode->i_state & I_DIRTY) { + spin_unlock(&inode->i_lock); + WARN_ON_ONCE(write_inode_now(inode, true)); + spin_lock(&inode->i_lock); + } + spin_unlock(&inode->i_lock); +} + /* * Move the inode from its current bdi to a new bdi. Make sure the inode * is clean before moving so that it doesn't linger on the old bdi. @@ -56,16 +67,10 @@ EXPORT_SYMBOL(I_BDEV); static void bdev_inode_switch_bdi(struct inode *inode, struct backing_dev_info *dst) { - while (true) { - spin_lock(&inode->i_lock); - if (!(inode->i_state & I_DIRTY)) { - inode->i_data.backing_dev_info = dst; - spin_unlock(&inode->i_lock); - return; - } - spin_unlock(&inode->i_lock); - WARN_ON_ONCE(write_inode_now(inode, true)); - } + spin_lock(&inode->i_lock); + WARN_ON_ONCE(inode->i_state & I_DIRTY); + inode->i_data.backing_dev_info = dst; + spin_unlock(&inode->i_lock); } /* Kill _all_ buffers and pagecache , dirty or not.. */ @@ -1464,9 +1469,11 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) WARN_ON_ONCE(bdev->bd_holders); sync_blockdev(bdev); kill_bdev(bdev); - /* ->release can cause the old bdi to disappear, - * so must switch it out first + /* + * ->release can cause the queue to disappear, so flush all + * dirty data before. */ + bdev_write_inode(bdev->bd_inode); bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info); } -- cgit v1.2.3 From 495a276e1ca96af622edb67ad0f85431935b20d2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:34 +0100 Subject: block_dev: get bdev inode bdi directly from the block device Directly grab the backing_dev_info from the request_queue instead of detouring through the address_space. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 2d609a5fbfea..e8116a44cc29 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -69,10 +69,10 @@ EXPORT_SYMBOL(writeback_in_progress); static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb = inode->i_sb; - +#ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) - return inode->i_mapping->backing_dev_info; - + return blk_get_backing_dev_info(I_BDEV(inode)); +#endif return sb->s_bdi; } -- cgit v1.2.3 From 26ff13047e3dc6c0230a629867e8dbd4a15a7626 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:35 +0100 Subject: nilfs2: set up s_bdi like the generic mount_bdev code mapping->backing_dev_info will go away, so don't rely on it. Signed-off-by: Christoph Hellwig Acked-by: Ryusuke Konishi Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- fs/nilfs2/super.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 2e5b3ec85b8f..3d4bbac36bea 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1057,7 +1057,6 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) { struct the_nilfs *nilfs; struct nilfs_root *fsroot; - struct backing_dev_info *bdi; __u64 cno; int err; @@ -1077,8 +1076,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_time_gran = 1; sb->s_max_links = NILFS_LINK_MAX; - bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info; - sb->s_bdi = bdi ? : &default_backing_dev_info; + sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info; err = load_nilfs(nilfs, sb); if (err) -- cgit v1.2.3 From de1414a654e66b81b5348dbc5259ecf2fb61655e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:36 +0100 Subject: fs: export inode_to_bdi and use it in favor of mapping->backing_dev_info Now that we got rid of the bdi abuse on character devices we can always use sb->s_bdi to get at the backing_dev_info for a file, except for the block device special case. Export inode_to_bdi and replace uses of mapping->backing_dev_info with it to prepare for the removal of mapping->backing_dev_info. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- fs/btrfs/file.c | 2 +- fs/ceph/file.c | 2 +- fs/ext2/ialloc.c | 2 +- fs/ext4/super.c | 2 +- fs/fs-writeback.c | 3 ++- fs/fuse/file.c | 10 +++++----- fs/gfs2/aops.c | 2 +- fs/gfs2/super.c | 2 +- fs/nfs/filelayout/filelayout.c | 2 +- fs/nfs/write.c | 6 +++--- fs/ntfs/file.c | 3 ++- fs/ocfs2/file.c | 2 +- fs/xfs/xfs_file.c | 2 +- include/linux/backing-dev.h | 6 ++++-- include/trace/events/writeback.h | 6 +++--- mm/fadvise.c | 4 ++-- mm/filemap.c | 4 ++-- mm/filemap_xip.c | 3 ++- mm/page-writeback.c | 29 +++++++++++++---------------- mm/readahead.c | 4 ++-- mm/truncate.c | 2 +- mm/vmscan.c | 4 ++-- 22 files changed, 52 insertions(+), 50 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e4090259569b..835c04a874fd 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1746,7 +1746,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, mutex_lock(&inode->i_mutex); - current->backing_dev_info = inode->i_mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) { mutex_unlock(&inode->i_mutex); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ce74b394b49d..905986dd4c3c 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -945,7 +945,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) mutex_lock(&inode->i_mutex); /* We can write back this queue in page reclaim */ - current->backing_dev_info = file->f_mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 7d66fb0e4cca..6c14bb8322fa 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -170,7 +170,7 @@ static void ext2_preread_inode(struct inode *inode) struct ext2_group_desc * gdp; struct backing_dev_info *bdi; - bdi = inode->i_mapping->backing_dev_info; + bdi = inode_to_bdi(inode); if (bdi_read_congested(bdi)) return; if (bdi_write_congested(bdi)) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 74c5f53595fb..ad88e601a6cd 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -334,7 +334,7 @@ static void save_error_info(struct super_block *sb, const char *func, static int block_device_ejected(struct super_block *sb) { struct inode *bd_inode = sb->s_bdev->bd_inode; - struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(bd_inode); return bdi->dev == NULL; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e8116a44cc29..a20b1145f4d5 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -66,7 +66,7 @@ int writeback_in_progress(struct backing_dev_info *bdi) } EXPORT_SYMBOL(writeback_in_progress); -static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) +struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb = inode->i_sb; #ifdef CONFIG_BLOCK @@ -75,6 +75,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) #endif return sb->s_bdi; } +EXPORT_SYMBOL_GPL(inode_to_bdi); static inline struct inode *wb_inode(struct list_head *head) { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 760b2c552197..19d80b82d344 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1159,7 +1159,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) mutex_lock(&inode->i_mutex); /* We can write back this queue in page reclaim */ - current->backing_dev_info = mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) @@ -1464,7 +1464,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req) { struct inode *inode = req->inode; struct fuse_inode *fi = get_fuse_inode(inode); - struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(inode); int i; list_del(&req->writepages_entry); @@ -1658,7 +1658,7 @@ static int fuse_writepage_locked(struct page *page) req->end = fuse_writepage_end; req->inode = inode; - inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK); + inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK); inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP); spin_lock(&fc->lock); @@ -1768,7 +1768,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, if (old_req->num_pages == 1 && (old_req->state == FUSE_REQ_INIT || old_req->state == FUSE_REQ_PENDING)) { - struct backing_dev_info *bdi = page->mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(page->mapping->host); copy_highpage(old_req->pages[0], page); spin_unlock(&fc->lock); @@ -1872,7 +1872,7 @@ static int fuse_writepages_fill(struct page *page, req->page_descs[req->num_pages].offset = 0; req->page_descs[req->num_pages].length = PAGE_SIZE; - inc_bdi_stat(page->mapping->backing_dev_info, BDI_WRITEBACK); + inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK); inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP); err = 0; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 805b37fed638..4ad4f94edebe 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -289,7 +289,7 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - trace_wbc_writepage(wbc, mapping->backing_dev_info); + trace_wbc_writepage(wbc, inode_to_bdi(inode)); ret = __gfs2_jdata_writepage(page, wbc); if (unlikely(ret)) { diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 5b327f837de7..1666382b198d 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -743,7 +743,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc) struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl); - struct backing_dev_info *bdi = metamapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(metamapping->host); int ret = 0; if (wbc->sync_mode == WB_SYNC_ALL) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 7afb52f6a25a..51aa889611cf 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -1081,7 +1081,7 @@ mds_commit: spin_unlock(cinfo->lock); if (!cinfo->dreq) { inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info, + inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host), BDI_RECLAIMABLE); __mark_inode_dirty(req->wb_context->dentry->d_inode, I_DIRTY_DATASYNC); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index af3af685a9e3..298abcc5281b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -786,7 +786,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, spin_unlock(cinfo->lock); if (!cinfo->dreq) { inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info, + inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host), BDI_RECLAIMABLE); __mark_inode_dirty(req->wb_context->dentry->d_inode, I_DIRTY_DATASYNC); @@ -853,7 +853,7 @@ static void nfs_clear_page_commit(struct page *page) { dec_zone_page_state(page, NR_UNSTABLE_NFS); - dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE); + dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE); } /* Called holding inode (/cinfo) lock */ @@ -1564,7 +1564,7 @@ void nfs_retry_commit(struct list_head *page_list, nfs_mark_request_commit(req, lseg, cinfo); if (!cinfo->dreq) { dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info, + dec_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host), BDI_RECLAIMABLE); } nfs_unlock_and_release_request(req); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 643faa44f22b..1da9b2d184dc 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -19,6 +19,7 @@ * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include #include #include #include @@ -2091,7 +2092,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, count = iov_length(iov, nr_segs); pos = *ppos; /* We can write back this queue in page reclaim. */ - current->backing_dev_info = mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); written = 0; err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 3950693dd0f6..abe7d98d6178 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2363,7 +2363,7 @@ relock: goto out_dio; } } else { - current->backing_dev_info = file->f_mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); written = generic_perform_write(file, from, *ppos); if (likely(written >= 0)) iocb->ki_pos = *ppos + written; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 13e974e6a889..5684ac3e7d18 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -699,7 +699,7 @@ xfs_file_buffered_aio_write( iov_iter_truncate(from, count); /* We can write back this queue in page reclaim */ - current->backing_dev_info = mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); write_retry: trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 478f95d92d73..ed59dee03a71 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -106,6 +106,8 @@ struct backing_dev_info { #endif }; +struct backing_dev_info *inode_to_bdi(struct inode *inode); + int __must_check bdi_init(struct backing_dev_info *bdi); void bdi_destroy(struct backing_dev_info *bdi); @@ -303,12 +305,12 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { - return bdi_cap_writeback_dirty(mapping->backing_dev_info); + return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host)); } static inline bool mapping_cap_account_dirty(struct address_space *mapping) { - return bdi_cap_account_dirty(mapping->backing_dev_info); + return bdi_cap_account_dirty(inode_to_bdi(mapping->host)); } static inline int bdi_sched_wait(void *word) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index cee02d65ab3f..74f5207bd090 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -47,7 +47,7 @@ TRACE_EVENT(writeback_dirty_page, TP_fast_assign( strncpy(__entry->name, - mapping ? dev_name(mapping->backing_dev_info->dev) : "(unknown)", 32); + mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", 32); __entry->ino = mapping ? mapping->host->i_ino : 0; __entry->index = page->index; ), @@ -72,7 +72,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template, ), TP_fast_assign( - struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strncpy(__entry->name, @@ -116,7 +116,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_fast_assign( strncpy(__entry->name, - dev_name(inode->i_mapping->backing_dev_info->dev), 32); + dev_name(inode_to_bdi(inode)->dev), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; ), diff --git a/mm/fadvise.c b/mm/fadvise.c index 2ad7adf4f0a4..fac23ecf8d72 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -73,7 +73,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) else endbyte--; /* inclusive */ - bdi = mapping->backing_dev_info; + bdi = inode_to_bdi(mapping->host); switch (advice) { case POSIX_FADV_NORMAL: @@ -113,7 +113,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) case POSIX_FADV_NOREUSE: break; case POSIX_FADV_DONTNEED: - if (!bdi_write_congested(mapping->backing_dev_info)) + if (!bdi_write_congested(bdi)) __filemap_fdatawrite_range(mapping, offset, endbyte, WB_SYNC_NONE); diff --git a/mm/filemap.c b/mm/filemap.c index 673e4581a2e5..5d7c23c26f81 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -211,7 +211,7 @@ void __delete_from_page_cache(struct page *page, void *shadow) */ if (PageDirty(page) && mapping_cap_account_dirty(mapping)) { dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); } } @@ -2565,7 +2565,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) size_t count = iov_iter_count(from); /* We can write back this queue in page reclaim */ - current->backing_dev_info = mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) goto out; diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 0d105aeff82f..26897fbfbe19 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -410,7 +411,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len, count = len; /* We can write back this queue in page reclaim */ - current->backing_dev_info = mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode)); if (ret) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6f4335238e33..d4cbb4bd7d1c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1351,7 +1351,7 @@ static void balance_dirty_pages(struct address_space *mapping, unsigned long task_ratelimit; unsigned long dirty_ratelimit; unsigned long pos_ratio; - struct backing_dev_info *bdi = mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; @@ -1574,7 +1574,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { - struct backing_dev_info *bdi = mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); int ratelimit; int *p; @@ -1929,7 +1929,7 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - trace_wbc_writepage(wbc, mapping->backing_dev_info); + trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); ret = (*writepage)(page, wbc, data); if (unlikely(ret)) { if (ret == AOP_WRITEPAGE_ACTIVATE) { @@ -2094,10 +2094,12 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) trace_writeback_dirty_page(page, mapping); if (mapping_cap_account_dirty(mapping)) { + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_DIRTIED); - __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); - __inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED); + __inc_bdi_stat(bdi, BDI_RECLAIMABLE); + __inc_bdi_stat(bdi, BDI_DIRTIED); task_io_account_write(PAGE_CACHE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); @@ -2156,7 +2158,7 @@ void account_page_redirty(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { current->nr_dirtied--; dec_zone_page_state(page, NR_DIRTIED); - dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED); + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED); } } EXPORT_SYMBOL(account_page_redirty); @@ -2295,7 +2297,7 @@ int clear_page_dirty_for_io(struct page *page) */ if (TestClearPageDirty(page)) { dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(mapping->backing_dev_info, + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); return 1; } @@ -2315,7 +2317,7 @@ int test_clear_page_writeback(struct page *page) memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags); if (mapping) { - struct backing_dev_info *bdi = mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); @@ -2352,7 +2354,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags); if (mapping) { - struct backing_dev_info *bdi = mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); @@ -2406,12 +2408,7 @@ EXPORT_SYMBOL(mapping_tagged); */ void wait_for_stable_page(struct page *page) { - struct address_space *mapping = page_mapping(page); - struct backing_dev_info *bdi = mapping->backing_dev_info; - - if (!bdi_cap_stable_pages_required(bdi)) - return; - - wait_on_page_writeback(page); + if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host))) + wait_on_page_writeback(page); } EXPORT_SYMBOL_GPL(wait_for_stable_page); diff --git a/mm/readahead.c b/mm/readahead.c index 17b9172ec37f..935675844b2e 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -27,7 +27,7 @@ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { - ra->ra_pages = mapping->backing_dev_info->ra_pages; + ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); @@ -541,7 +541,7 @@ page_cache_async_readahead(struct address_space *mapping, /* * Defer asynchronous read-ahead on IO congestion. */ - if (bdi_read_congested(mapping->backing_dev_info)) + if (bdi_read_congested(inode_to_bdi(mapping->host))) return; /* do read-ahead */ diff --git a/mm/truncate.c b/mm/truncate.c index f1e4d6052369..ddec5a5966d7 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -112,7 +112,7 @@ void cancel_dirty_page(struct page *page, unsigned int account_size) struct address_space *mapping = page->mapping; if (mapping && mapping_cap_account_dirty(mapping)) { dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(mapping->backing_dev_info, + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); if (account_size) task_io_account_cancelled_write(account_size); diff --git a/mm/vmscan.c b/mm/vmscan.c index ab2505c3ef54..e00a16393f21 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -497,7 +497,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; - if (!may_write_to_queue(mapping->backing_dev_info, sc)) + if (!may_write_to_queue(inode_to_bdi(mapping->host), sc)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { @@ -876,7 +876,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ mapping = page_mapping(page); if (((dirty || writeback) && mapping && - bdi_write_congested(mapping->backing_dev_info)) || + bdi_write_congested(inode_to_bdi(mapping->host))) || (writeback && PageReclaim(page))) nr_congested++; -- cgit v1.2.3 From b83ae6d421435c6204150300f1c25bfbd39cd62b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:37 +0100 Subject: fs: remove mapping->backing_dev_info Now that we never use the backing_dev_info pointer in struct address_space we can simply remove it and save 4 to 8 bytes in every inode. Signed-off-by: Christoph Hellwig Acked-by: Ryusuke Konishi Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- drivers/char/raw.c | 4 +--- fs/aio.c | 1 - fs/block_dev.c | 26 +------------------------- fs/btrfs/disk-io.c | 1 - fs/btrfs/inode.c | 6 ------ fs/ceph/inode.c | 2 -- fs/cifs/inode.c | 2 -- fs/configfs/inode.c | 1 - fs/ecryptfs/inode.c | 1 - fs/exofs/inode.c | 2 -- fs/fuse/inode.c | 1 - fs/gfs2/glock.c | 1 - fs/gfs2/ops_fstype.c | 1 - fs/hugetlbfs/inode.c | 1 - fs/inode.c | 13 ------------- fs/kernfs/inode.c | 1 - fs/ncpfs/inode.c | 1 - fs/nfs/inode.c | 1 - fs/nilfs2/gcinode.c | 1 - fs/nilfs2/mdt.c | 6 ++---- fs/nilfs2/page.c | 4 +--- fs/nilfs2/page.h | 3 +-- fs/nilfs2/super.c | 2 +- fs/ocfs2/dlmfs/dlmfs.c | 2 -- fs/ramfs/inode.c | 1 - fs/romfs/super.c | 3 --- fs/ubifs/dir.c | 2 -- fs/ubifs/super.c | 3 --- include/linux/fs.h | 3 +-- mm/backing-dev.c | 1 - mm/shmem.c | 1 - mm/swap_state.c | 1 - 32 files changed, 8 insertions(+), 91 deletions(-) (limited to 'fs') diff --git a/drivers/char/raw.c b/drivers/char/raw.c index a24891b97547..6e29bf2db536 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -104,11 +104,9 @@ static int raw_release(struct inode *inode, struct file *filp) mutex_lock(&raw_mutex); bdev = raw_devices[minor].binding; - if (--raw_devices[minor].inuse == 0) { + if (--raw_devices[minor].inuse == 0) /* Here inode->i_mapping == bdev->bd_inode->i_mapping */ inode->i_mapping = &inode->i_data; - inode->i_mapping->backing_dev_info = &default_backing_dev_info; - } mutex_unlock(&raw_mutex); blkdev_put(bdev, filp->f_mode | FMODE_EXCL); diff --git a/fs/aio.c b/fs/aio.c index 6f13d3fab07f..3bf8b1d250c3 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -176,7 +176,6 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) inode->i_mapping->a_ops = &aio_ctx_aops; inode->i_mapping->private_data = ctx; - inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_size = PAGE_SIZE * nr_pages; path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this); diff --git a/fs/block_dev.c b/fs/block_dev.c index 026ca7b8431c..a9f92794d7a0 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -60,19 +60,6 @@ static void bdev_write_inode(struct inode *inode) spin_unlock(&inode->i_lock); } -/* - * Move the inode from its current bdi to a new bdi. Make sure the inode - * is clean before moving so that it doesn't linger on the old bdi. - */ -static void bdev_inode_switch_bdi(struct inode *inode, - struct backing_dev_info *dst) -{ - spin_lock(&inode->i_lock); - WARN_ON_ONCE(inode->i_state & I_DIRTY); - inode->i_data.backing_dev_info = dst; - spin_unlock(&inode->i_lock); -} - /* Kill _all_ buffers and pagecache , dirty or not.. */ void kill_bdev(struct block_device *bdev) { @@ -589,7 +576,6 @@ struct block_device *bdget(dev_t dev) inode->i_bdev = bdev; inode->i_data.a_ops = &def_blk_aops; mapping_set_gfp_mask(&inode->i_data, GFP_USER); - inode->i_data.backing_dev_info = &default_backing_dev_info; spin_lock(&bdev_lock); list_add(&bdev->bd_list, &all_bdevs); spin_unlock(&bdev_lock); @@ -1150,8 +1136,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; if (!partno) { - struct backing_dev_info *bdi; - ret = -ENXIO; bdev->bd_part = disk_get_part(disk, partno); if (!bdev->bd_part) @@ -1177,11 +1161,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret) { + if (!ret) bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); - bdi = blk_get_backing_dev_info(bdev); - bdev_inode_switch_bdi(bdev->bd_inode, bdi); - } /* * If the device is invalidated, rescan partition @@ -1208,8 +1189,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (ret) goto out_clear; bdev->bd_contains = whole; - bdev_inode_switch_bdi(bdev->bd_inode, - whole->bd_inode->i_data.backing_dev_info); bdev->bd_part = disk_get_part(disk, partno); if (!(disk->flags & GENHD_FL_UP) || !bdev->bd_part || !bdev->bd_part->nr_sects) { @@ -1249,7 +1228,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = NULL; bdev->bd_part = NULL; bdev->bd_queue = NULL; - bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info); if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; @@ -1474,8 +1452,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) * dirty data before. */ bdev_write_inode(bdev->bd_inode); - bdev_inode_switch_bdi(bdev->bd_inode, - &default_backing_dev_info); } if (bdev->bd_contains == bdev) { if (disk->fops->release) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index afc4092989cd..1ec872e3a926 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2318,7 +2318,6 @@ int open_ctree(struct super_block *sb, */ fs_info->btree_inode->i_size = OFFSET_MAX; fs_info->btree_inode->i_mapping->a_ops = &btree_aops; - fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi; RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node); extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8bf326affb94..54bcf639d1cf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3608,7 +3608,6 @@ cache_acl: switch (inode->i_mode & S_IFMT) { case S_IFREG: inode->i_mapping->a_ops = &btrfs_aops; - inode->i_mapping->backing_dev_info = &root->fs_info->bdi; BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops; inode->i_fop = &btrfs_file_operations; inode->i_op = &btrfs_file_inode_operations; @@ -3623,7 +3622,6 @@ cache_acl: case S_IFLNK: inode->i_op = &btrfs_symlink_inode_operations; inode->i_mapping->a_ops = &btrfs_symlink_aops; - inode->i_mapping->backing_dev_info = &root->fs_info->bdi; break; default: inode->i_op = &btrfs_special_inode_operations; @@ -6088,7 +6086,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, inode->i_fop = &btrfs_file_operations; inode->i_op = &btrfs_file_inode_operations; inode->i_mapping->a_ops = &btrfs_aops; - inode->i_mapping->backing_dev_info = &root->fs_info->bdi; err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name); if (err) @@ -9203,7 +9200,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, inode->i_fop = &btrfs_file_operations; inode->i_op = &btrfs_file_inode_operations; inode->i_mapping->a_ops = &btrfs_aops; - inode->i_mapping->backing_dev_info = &root->fs_info->bdi; BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops; err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name); @@ -9247,7 +9243,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, inode->i_op = &btrfs_symlink_inode_operations; inode->i_mapping->a_ops = &btrfs_symlink_aops; - inode->i_mapping->backing_dev_info = &root->fs_info->bdi; inode_set_bytes(inode, name_len); btrfs_i_size_write(inode, name_len); err = btrfs_update_inode(trans, root, inode); @@ -9459,7 +9454,6 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) inode->i_op = &btrfs_file_inode_operations; inode->i_mapping->a_ops = &btrfs_aops; - inode->i_mapping->backing_dev_info = &root->fs_info->bdi; BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops; ret = btrfs_init_inode_security(trans, inode, dir, NULL); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index f61a74115beb..6b5173605154 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -783,8 +783,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page, } inode->i_mapping->a_ops = &ceph_aops; - inode->i_mapping->backing_dev_info = - &ceph_sb_to_client(inode->i_sb)->backing_dev_info; switch (inode->i_mode & S_IFMT) { case S_IFIFO: diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 0c3ce464cae4..2d4f37235ed0 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -937,8 +937,6 @@ retry_iget5_locked: inode->i_flags |= S_NOATIME | S_NOCMTIME; if (inode->i_state & I_NEW) { inode->i_ino = hash; - if (S_ISREG(inode->i_mode)) - inode->i_data.backing_dev_info = sb->s_bdi; #ifdef CONFIG_CIFS_FSCACHE /* initialize per-inode cache cookie pointer */ CIFS_I(inode)->fscache = NULL; diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 0ad6b4d6de00..65af86147154 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -131,7 +131,6 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd, if (inode) { inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &configfs_aops; - inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_op = &configfs_inode_operations; if (sd->s_iattr) { diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 1686dc2da9fd..34b36a504059 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -67,7 +67,6 @@ static int ecryptfs_inode_set(struct inode *inode, void *opaque) inode->i_ino = lower_inode->i_ino; inode->i_version++; inode->i_mapping->a_ops = &ecryptfs_aops; - inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi; if (S_ISLNK(inode->i_mode)) inode->i_op = &ecryptfs_symlink_iops; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index f1d3d4eb8c4f..6fc91df99ff8 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1214,7 +1214,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino) memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data)); } - inode->i_mapping->backing_dev_info = sb->s_bdi; if (S_ISREG(inode->i_mode)) { inode->i_op = &exofs_file_inode_operations; inode->i_fop = &exofs_file_operations; @@ -1314,7 +1313,6 @@ struct inode *exofs_new_inode(struct inode *dir, umode_t mode) set_obj_2bcreated(oi); - inode->i_mapping->backing_dev_info = sb->s_bdi; inode_init_owner(inode, dir, mode); inode->i_ino = sbi->s_nextid++; inode->i_blkbits = EXOFS_BLKSHIFT; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index f38256e4476e..e8799c11424b 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -308,7 +308,6 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, if (!fc->writeback_cache || !S_ISREG(attr->mode)) inode->i_flags |= S_NOCMTIME; inode->i_generation = generation; - inode->i_data.backing_dev_info = &fc->bdi; fuse_init_inode(inode, attr); unlock_new_inode(inode); } else if ((inode->i_mode ^ attr->mode) & S_IFMT) { diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index a23524aa3eac..08ea717981f7 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -775,7 +775,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); mapping->private_data = NULL; - mapping->backing_dev_info = s->s_bdi; mapping->writeback_index = 0; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 8633ad328ee2..efc8e254787c 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -112,7 +112,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); mapping->private_data = NULL; - mapping->backing_dev_info = sb->s_bdi; mapping->writeback_index = 0; spin_lock_init(&sdp->sd_log_lock); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index de7c95c7d840..c274aca8e8dc 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -492,7 +492,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; - inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->private_data = resv_map; info = HUGETLBFS_I(inode); diff --git a/fs/inode.c b/fs/inode.c index aa149e7262ac..e4e8caa7464c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -170,20 +170,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) atomic_set(&mapping->i_mmap_writable, 0); mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->private_data = NULL; - mapping->backing_dev_info = &default_backing_dev_info; mapping->writeback_index = 0; - - /* - * If the block_device provides a backing_dev_info for client - * inodes then use that. Otherwise the inode share the bdev's - * backing_dev_info. - */ - if (sb->s_bdev) { - struct backing_dev_info *bdi; - - bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info; - mapping->backing_dev_info = bdi; - } inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 06f06887b2d2..9000874a945b 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -286,7 +286,6 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) kernfs_get(kn); inode->i_private = kn; inode->i_mapping->a_ops = &kernfs_aops; - inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_op = &kernfs_iops; set_default_inode_attr(inode, kn->mode); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index a699a3fc62c0..01a9e16e9782 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -267,7 +267,6 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info) if (inode) { atomic_set(&NCP_FINFO(inode)->opened, info->opened); - inode->i_mapping->backing_dev_info = sb->s_bdi; inode->i_ino = info->ino; ncp_set_attr(inode, info); if (S_ISREG(inode->i_mode)) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 4bffe637ea32..24aac72420f4 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -387,7 +387,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st if (S_ISREG(inode->i_mode)) { inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; inode->i_data.a_ops = &nfs_file_aops; - inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info; } else if (S_ISDIR(inode->i_mode)) { inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 57ceaf33d177..748ca238915a 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -172,7 +172,6 @@ int nilfs_init_gcinode(struct inode *inode) inode->i_mode = S_IFREG; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); inode->i_mapping->a_ops = &empty_aops; - inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi; ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index c4dcd1db57ee..892cf5ffdb8e 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -429,7 +429,6 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz) inode->i_mode = S_IFREG; mapping_set_gfp_mask(inode->i_mapping, gfp_mask); - inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi; inode->i_op = &def_mdt_iops; inode->i_fop = &def_mdt_fops; @@ -457,13 +456,12 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode, struct nilfs_shadow_map *shadow) { struct nilfs_mdt_info *mi = NILFS_MDT(inode); - struct backing_dev_info *bdi = inode->i_sb->s_bdi; INIT_LIST_HEAD(&shadow->frozen_buffers); address_space_init_once(&shadow->frozen_data); - nilfs_mapping_init(&shadow->frozen_data, inode, bdi); + nilfs_mapping_init(&shadow->frozen_data, inode); address_space_init_once(&shadow->frozen_btnodes); - nilfs_mapping_init(&shadow->frozen_btnodes, inode, bdi); + nilfs_mapping_init(&shadow->frozen_btnodes, inode); mi->mi_shadow = shadow; return 0; } diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index da276640f776..700ecbcca55d 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -461,14 +461,12 @@ unsigned nilfs_page_count_clean_buffers(struct page *page, return nc; } -void nilfs_mapping_init(struct address_space *mapping, struct inode *inode, - struct backing_dev_info *bdi) +void nilfs_mapping_init(struct address_space *mapping, struct inode *inode) { mapping->host = inode; mapping->flags = 0; mapping_set_gfp_mask(mapping, GFP_NOFS); mapping->private_data = NULL; - mapping->backing_dev_info = bdi; mapping->a_ops = &empty_aops; } diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index ef30c5c2426f..a43b8287d012 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -57,8 +57,7 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *); void nilfs_copy_back_pages(struct address_space *, struct address_space *); void nilfs_clear_dirty_page(struct page *, bool); void nilfs_clear_dirty_pages(struct address_space *, bool); -void nilfs_mapping_init(struct address_space *mapping, struct inode *inode, - struct backing_dev_info *bdi); +void nilfs_mapping_init(struct address_space *mapping, struct inode *inode); unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned); unsigned long nilfs_find_uncommitted_extent(struct inode *inode, sector_t start_blk, diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 3d4bbac36bea..5bc2a1cf73c3 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -166,7 +166,7 @@ struct inode *nilfs_alloc_inode(struct super_block *sb) ii->i_state = 0; ii->i_cno = 0; ii->vfs_inode.i_version = 1; - nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode, sb->s_bdi); + nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode); return &ii->vfs_inode; } diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 6000d3029b26..061ba6a91bf2 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -398,7 +398,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) if (inode) { inode->i_ino = get_next_ino(); inode_init_owner(inode, NULL, mode); - inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inc_nlink(inode); @@ -422,7 +421,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent, inode->i_ino = get_next_ino(); inode_init_owner(inode, parent, mode); - inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; ip = DLMFS_I(inode); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index ad4d712002f4..889d558b4e05 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -59,7 +59,6 @@ struct inode *ramfs_get_inode(struct super_block *sb, inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_mapping->a_ops = &ramfs_aops; - inode->i_mapping->backing_dev_info = &noop_backing_dev_info; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/romfs/super.c b/fs/romfs/super.c index e98dd88197d5..268733cda397 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -355,9 +355,6 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) case ROMFH_REG: i->i_fop = &romfs_ro_fops; i->i_data.a_ops = &romfs_aops; - if (i->i_sb->s_mtd) - i->i_data.backing_dev_info = - i->i_sb->s_mtd->backing_dev_info; if (nextfh & ROMFH_EXEC) mode |= S_IXUGO; break; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index ea41649e4ca5..c49b1981ac95 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -108,8 +108,6 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir, inode->i_mtime = inode->i_atime = inode->i_ctime = ubifs_current_time(inode); inode->i_mapping->nrpages = 0; - /* Disable readahead */ - inode->i_mapping->backing_dev_info = &c->bdi; switch (mode & S_IFMT) { case S_IFREG: diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index ed93dc6ae245..6197154f36ca 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -156,9 +156,6 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) if (err) goto out_invalid; - /* Disable read-ahead */ - inode->i_mapping->backing_dev_info = &c->bdi; - switch (inode->i_mode & S_IFMT) { case S_IFREG: inode->i_mapping->a_ops = &ubifs_file_address_operations; diff --git a/include/linux/fs.h b/include/linux/fs.h index 1dada399aa23..65d02de342e1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -34,6 +34,7 @@ #include #include +struct backing_dev_info; struct export_operations; struct hd_geometry; struct iovec; @@ -394,7 +395,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); -struct backing_dev_info; struct address_space { struct inode *host; /* owner: inode, block_device */ struct radix_tree_root page_tree; /* radix tree of all pages */ @@ -409,7 +409,6 @@ struct address_space { pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ unsigned long flags; /* error bits/gfp mask */ - struct backing_dev_info *backing_dev_info; /* device readahead, etc */ spinlock_t private_lock; /* for use by the address_space */ struct list_head private_list; /* ditto */ void *private_data; /* ditto */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 16c68958aeda..52e0c7652448 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -24,7 +24,6 @@ struct backing_dev_info noop_backing_dev_info = { .name = "noop", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; -EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; diff --git a/mm/shmem.c b/mm/shmem.c index 1b77eaf589fd..4c61d3d5bfb4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1410,7 +1410,6 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_blocks = 0; - inode->i_mapping->backing_dev_info = &noop_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_generation = get_seconds(); info = SHMEM_I(inode); diff --git a/mm/swap_state.c b/mm/swap_state.c index 1c137b69ecde..405923f77334 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -37,7 +37,6 @@ struct address_space swapper_spaces[MAX_SWAPFILES] = { .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), .i_mmap_writable = ATOMIC_INIT(0), .a_ops = &swap_aops, - .backing_dev_info = &noop_backing_dev_info, } }; -- cgit v1.2.3 From e4d2750909aa26129bd0bf1b0dc832e0845aae90 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:38 +0100 Subject: ceph: remove call to bdi_unregister bdi_destroy already does all the work, and if we delay freeing the anon bdev we can get away with just that single call. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- fs/ceph/super.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'fs') diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 50f06cddc94b..e350cc1611e4 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -40,17 +40,6 @@ static void ceph_put_super(struct super_block *s) dout("put_super\n"); ceph_mdsc_close_sessions(fsc->mdsc); - - /* - * ensure we release the bdi before put_anon_super releases - * the device name. - */ - if (s->s_bdi == &fsc->backing_dev_info) { - bdi_unregister(&fsc->backing_dev_info); - s->s_bdi = NULL; - } - - return; } static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) @@ -1002,11 +991,16 @@ out_final: static void ceph_kill_sb(struct super_block *s) { struct ceph_fs_client *fsc = ceph_sb_to_client(s); + dev_t dev = s->s_dev; + dout("kill_sb %p\n", s); + ceph_mdsc_pre_umount(fsc->mdsc); - kill_anon_super(s); /* will call put_super after sb is r/o */ + generic_shutdown_super(s); ceph_mdsc_destroy(fsc); + destroy_fs_client(fsc); + free_anon_bdev(dev); } static struct file_system_type ceph_fs_type = { -- cgit v1.2.3 From 7b14a213890a81473ec97ad7e322d5c2f19854ae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:39 +0100 Subject: nfs: don't call bdi_unregister bdi_destroy already does all the work, and if we delay freeing the anon bdev we can get away with just that single call. Addintionally remove the call during mount failure, as deactivate_super_locked will already call ->kill_sb and clean up the bdi for us. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- fs/nfs/internal.h | 1 - fs/nfs/nfs4super.c | 1 - fs/nfs/super.c | 24 ++++++------------------ 3 files changed, 6 insertions(+), 20 deletions(-) (limited to 'fs') diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index efaa31c70fbe..f519d4187332 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -416,7 +416,6 @@ int nfs_show_options(struct seq_file *, struct dentry *); int nfs_show_devname(struct seq_file *, struct dentry *); int nfs_show_path(struct seq_file *, struct dentry *); int nfs_show_stats(struct seq_file *, struct dentry *); -void nfs_put_super(struct super_block *); int nfs_remount(struct super_block *sb, int *flags, char *raw_data); /* write.c */ diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 6f340f02f2ba..ab30a3a637de 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -53,7 +53,6 @@ static const struct super_operations nfs4_sops = { .destroy_inode = nfs_destroy_inode, .write_inode = nfs4_write_inode, .drop_inode = nfs_drop_inode, - .put_super = nfs_put_super, .statfs = nfs_statfs, .evict_inode = nfs4_evict_inode, .umount_begin = nfs_umount_begin, diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 31a11b0e885d..6ec4fe23b756 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -311,7 +311,6 @@ const struct super_operations nfs_sops = { .destroy_inode = nfs_destroy_inode, .write_inode = nfs_write_inode, .drop_inode = nfs_drop_inode, - .put_super = nfs_put_super, .statfs = nfs_statfs, .evict_inode = nfs_evict_inode, .umount_begin = nfs_umount_begin, @@ -2569,7 +2568,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, error = nfs_bdi_register(server); if (error) { mntroot = ERR_PTR(error); - goto error_splat_bdi; + goto error_splat_super; } server->super = s; } @@ -2601,9 +2600,6 @@ error_splat_root: dput(mntroot); mntroot = ERR_PTR(error); error_splat_super: - if (server && !s->s_root) - bdi_unregister(&server->backing_dev_info); -error_splat_bdi: deactivate_locked_super(s); goto out; } @@ -2650,28 +2646,20 @@ out: } EXPORT_SYMBOL_GPL(nfs_fs_mount); -/* - * Ensure that we unregister the bdi before kill_anon_super - * releases the device name - */ -void nfs_put_super(struct super_block *s) -{ - struct nfs_server *server = NFS_SB(s); - - bdi_unregister(&server->backing_dev_info); -} -EXPORT_SYMBOL_GPL(nfs_put_super); - /* * Destroy an NFS2/3 superblock */ void nfs_kill_super(struct super_block *s) { struct nfs_server *server = NFS_SB(s); + dev_t dev = s->s_dev; + + generic_shutdown_super(s); - kill_anon_super(s); nfs_fscache_release_super_cookie(s); + nfs_free_server(server); + free_anon_bdev(dev); } EXPORT_SYMBOL_GPL(nfs_kill_super); -- cgit v1.2.3 From df0ce26cb4ee8bc233d50213b97213532aff0a3c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:41 +0100 Subject: fs: remove default_backing_dev_info Now that default_backing_dev_info is not used for writeback purposes we can git rid of it easily: - instead of using it's name for tracing unregistered bdi we just use "unknown" - btrfs and ceph can just assign the default read ahead window themselves like several other filesystems already do. - we can assign noop_backing_dev_info as the default one in alloc_super. All filesystems already either assigned their own or noop_backing_dev_info. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- fs/btrfs/disk-io.c | 2 +- fs/ceph/super.c | 2 +- fs/super.c | 8 ++------ include/linux/backing-dev.h | 1 - include/trace/events/writeback.h | 6 ++---- mm/backing-dev.c | 9 --------- 6 files changed, 6 insertions(+), 22 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1ec872e3a926..1afb18226da8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1719,7 +1719,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) if (err) return err; - bdi->ra_pages = default_backing_dev_info.ra_pages; + bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE; bdi->congested_fn = btrfs_congested_fn; bdi->congested_data = info; return 0; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index e350cc1611e4..5ae62587a71d 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -899,7 +899,7 @@ static int ceph_register_bdi(struct super_block *sb, >> PAGE_SHIFT; else fsc->backing_dev_info.ra_pages = - default_backing_dev_info.ra_pages; + VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE; err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld", atomic_long_inc_return(&bdi_seq)); diff --git a/fs/super.c b/fs/super.c index eae088f6aaae..3b4dadafdd60 100644 --- a/fs/super.c +++ b/fs/super.c @@ -185,8 +185,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) } init_waitqueue_head(&s->s_writers.wait); init_waitqueue_head(&s->s_writers.wait_unfrozen); + s->s_bdi = &noop_backing_dev_info; s->s_flags = flags; - s->s_bdi = &default_backing_dev_info; INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_anon); INIT_LIST_HEAD(&s->s_inodes); @@ -863,10 +863,7 @@ EXPORT_SYMBOL(free_anon_bdev); int set_anon_super(struct super_block *s, void *data) { - int error = get_anon_bdev(&s->s_dev); - if (!error) - s->s_bdi = &noop_backing_dev_info; - return error; + return get_anon_bdev(&s->s_dev); } EXPORT_SYMBOL(set_anon_super); @@ -1111,7 +1108,6 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) sb = root->d_sb; BUG_ON(!sb); WARN_ON(!sb->s_bdi); - WARN_ON(sb->s_bdi == &default_backing_dev_info); sb->s_flags |= MS_BORN; error = security_sb_kern_mount(sb, flags, secdata); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ed59dee03a71..d94077fea1f8 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -241,7 +241,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) -extern struct backing_dev_info default_backing_dev_info; extern struct backing_dev_info noop_backing_dev_info; int writeback_in_progress(struct backing_dev_info *bdi); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 74f5207bd090..0e9310905413 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -156,10 +156,8 @@ DECLARE_EVENT_CLASS(writeback_work_class, __field(int, reason) ), TP_fast_assign( - struct device *dev = bdi->dev; - if (!dev) - dev = default_backing_dev_info.dev; - strncpy(__entry->name, dev_name(dev), 32); + strncpy(__entry->name, + bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 1725adb242e0..7690ec77c722 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -14,12 +14,6 @@ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); -struct backing_dev_info default_backing_dev_info = { - .name = "default", - .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, -}; -EXPORT_SYMBOL_GPL(default_backing_dev_info); - struct backing_dev_info noop_backing_dev_info = { .name = "noop", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, @@ -250,9 +244,6 @@ static int __init default_bdi_init(void) if (!bdi_wq) return -ENOMEM; - err = bdi_init(&default_backing_dev_info); - if (!err) - bdi_register(&default_backing_dev_info, NULL, "default"); err = bdi_init(&noop_backing_dev_info); return err; -- cgit v1.2.3 From 6c9fe14f9d64cc12401a825a60ec5c5723496ca4 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 20 Jan 2015 17:05:33 +0800 Subject: btrfs: Fix the bug that fs_info->pending_changes is never cleared. Fs_info->pending_changes is never cleared since the original code uses cmpxchg(&fs_info->pending_changes, 0, 0), which will only clear it if pending_changes is already 0. This will cause a lot of problem when mount it with inode_cache mount option. If the btrfs is mounted as inode_cache, pending_changes will always be 1, even when the fs is frozen. Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index a605d4e2f2bc..e88b59d13439 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2118,7 +2118,7 @@ void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info) unsigned long prev; unsigned long bit; - prev = cmpxchg(&fs_info->pending_changes, 0, 0); + prev = xchg(&fs_info->pending_changes, 0); if (!prev) return; -- cgit v1.2.3 From a53f4f8e9c8ebe6c9ee3b34c368913aae9876e22 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 19 Jan 2015 15:42:41 +0800 Subject: btrfs: Don't call btrfs_start_transaction() on frozen fs to avoid deadlock. Commit 6b5fe46dfa52 (btrfs: do commit in sync_fs if there are pending changes) will call btrfs_start_transaction() in sync_fs(), to handle some operations needed to be done in next transaction. However this can cause deadlock if the filesystem is frozen, with the following sys_r+w output: [ 143.255932] Call Trace: [ 143.255936] [] schedule+0x29/0x70 [ 143.255939] [] __sb_start_write+0xb3/0x100 [ 143.255971] [] start_transaction+0x2e6/0x5a0 [btrfs] [ 143.255992] [] btrfs_start_transaction+0x1b/0x20 [btrfs] [ 143.256003] [] btrfs_sync_fs+0xca/0xd0 [btrfs] [ 143.256007] [] sync_fs_one_sb+0x20/0x30 [ 143.256011] [] iterate_supers+0xe1/0xf0 [ 143.256014] [] sys_sync+0x55/0x90 [ 143.256017] [] system_call_fastpath+0x12/0x17 [ 143.256111] Call Trace: [ 143.256114] [] schedule+0x29/0x70 [ 143.256119] [] rwsem_down_write_failed+0x1c5/0x2d0 [ 143.256123] [] call_rwsem_down_write_failed+0x13/0x20 [ 143.256131] [] thaw_super+0x28/0xc0 [ 143.256135] [] do_vfs_ioctl+0x3f5/0x540 [ 143.256187] [] SyS_ioctl+0x91/0xb0 [ 143.256213] [] system_call_fastpath+0x12/0x17 The reason is like the following: (Holding s_umount) VFS sync_fs staff: |- btrfs_sync_fs() |- btrfs_start_transaction() |- sb_start_intwrite() (Waiting thaw_fs to unfreeze) VFS thaw_fs staff: thaw_fs() (Waiting sync_fs to release s_umount) So deadlock happens. This can be easily triggered by fstest/generic/068 with inode_cache mount option. The fix is to check if the fs is frozen, if the fs is frozen, just return and waiting for the next transaction. Cc: David Sterba Reported-by: Gui Hecheng Signed-off-by: Qu Wenruo [enhanced comment, changed to SB_FREEZE_WRITE] Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/super.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c86fb5438454..6f49b2872a64 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1000,6 +1000,16 @@ int btrfs_sync_fs(struct super_block *sb, int wait) */ if (fs_info->pending_changes == 0) return 0; + /* + * A non-blocking test if the fs is frozen. We must not + * start a new transaction here otherwise a deadlock + * happens. The pending operations are delayed to the + * next commit after thawing. + */ + if (__sb_start_write(sb, SB_FREEZE_WRITE, false)) + __sb_end_write(sb, SB_FREEZE_WRITE); + else + return 0; trans = btrfs_start_transaction(root, 0); } if (IS_ERR(trans)) -- cgit v1.2.3 From c119c5b9749e4df5e6344b5d2ccd959dd403c959 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 19 Nov 2014 09:03:28 +0100 Subject: quota: Don't store flags for v2 quota format Currently, v2 quota format blindly stored flags from in-memory dqinfo on disk, although there are no flags supported. Since it is stupid to store flags which have no effect, just store 0 unconditionally and don't bother loading it from disk. Note that userspace could have stored some flags there via Q_SETINFO quotactl and then later read them (although flags have no effect) but I'm pretty sure noone does that (most definitely quota-tools don't and quota interface doesn't have too much other users). Signed-off-by: Jan Kara --- fs/quota/quota_v2.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 02751ec695c5..54cac436ac72 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -126,7 +126,8 @@ static int v2_read_file_info(struct super_block *sb, int type) } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); - info->dqi_flags = le32_to_cpu(dinfo.dqi_flags); + /* No flags currently supported */ + info->dqi_flags = 0; qinfo->dqi_sb = sb; qinfo->dqi_type = type; qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks); @@ -157,7 +158,8 @@ static int v2_write_file_info(struct super_block *sb, int type) info->dqi_flags &= ~DQF_INFO_DIRTY; dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace); dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace); - dinfo.dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK); + /* No flags currently supported */ + dinfo.dqi_flags = cpu_to_le32(0); spin_unlock(&dq_data_lock); dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks); dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk); -- cgit v1.2.3 From 96827adcc2d0eed3fdf7f88e73a50a83b23def96 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 19 Nov 2014 10:41:41 +0100 Subject: ocfs2: Move OLQF_CLEAN flag out of generic quota flags OLQF_CLEAN flag is used by OCFS2 on disk to recognize whether quota recovery is needed or not. We also somewhat abuse mem_dqinfo->dqi_flags to pass this flag around. Use private flags for this to avoid clashes with other quota flags / not pollute generic quota flag namespace. Signed-off-by: Jan Kara --- fs/ocfs2/quota.h | 1 + fs/ocfs2/quota_local.c | 10 +++++----- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h index 1eae330193a6..b6d51333ad02 100644 --- a/fs/ocfs2/quota.h +++ b/fs/ocfs2/quota.h @@ -48,6 +48,7 @@ struct ocfs2_quota_recovery { /* In-memory structure with quota header information */ struct ocfs2_mem_dqinfo { unsigned int dqi_type; /* Quota type this structure describes */ + unsigned int dqi_flags; /* Flags OLQF_* */ unsigned int dqi_chunks; /* Number of chunks in local quota file */ unsigned int dqi_blocks; /* Number of blocks allocated for local quota file */ unsigned int dqi_syncms; /* How often should we sync with other nodes */ diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 10b653930ee2..55f832f553cb 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -292,7 +292,7 @@ static void olq_update_info(struct buffer_head *bh, void *private) ldinfo = (struct ocfs2_local_disk_dqinfo *)(bh->b_data + OCFS2_LOCAL_INFO_OFF); spin_lock(&dq_data_lock); - ldinfo->dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK); + ldinfo->dqi_flags = cpu_to_le32(oinfo->dqi_flags); ldinfo->dqi_chunks = cpu_to_le32(oinfo->dqi_chunks); ldinfo->dqi_blocks = cpu_to_le32(oinfo->dqi_blocks); spin_unlock(&dq_data_lock); @@ -737,13 +737,13 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) } ldinfo = (struct ocfs2_local_disk_dqinfo *)(bh->b_data + OCFS2_LOCAL_INFO_OFF); - info->dqi_flags = le32_to_cpu(ldinfo->dqi_flags); + oinfo->dqi_flags = le32_to_cpu(ldinfo->dqi_flags); oinfo->dqi_chunks = le32_to_cpu(ldinfo->dqi_chunks); oinfo->dqi_blocks = le32_to_cpu(ldinfo->dqi_blocks); oinfo->dqi_libh = bh; /* We crashed when using local quota file? */ - if (!(info->dqi_flags & OLQF_CLEAN)) { + if (!(oinfo->dqi_flags & OLQF_CLEAN)) { rec = OCFS2_SB(sb)->quota_rec; if (!rec) { rec = ocfs2_alloc_quota_recovery(); @@ -772,7 +772,7 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) } /* Now mark quota file as used */ - info->dqi_flags &= ~OLQF_CLEAN; + oinfo->dqi_flags &= ~OLQF_CLEAN; status = ocfs2_modify_bh(lqinode, bh, olq_update_info, info); if (status < 0) { mlog_errno(status); @@ -857,7 +857,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type) goto out; /* Mark local file as clean */ - info->dqi_flags |= OLQF_CLEAN; + oinfo->dqi_flags |= OLQF_CLEAN; status = ocfs2_modify_bh(sb_dqopt(sb)->files[type], oinfo->dqi_libh, olq_update_info, -- cgit v1.2.3 From 9c45101e88b2bf2ce36b8833fcfa784a9149aa74 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 19 Nov 2014 09:21:58 +0100 Subject: quota: Cleanup flags definitions Currently all quota flags were defined just in kernel-private headers. Export flags readable / writeable from userspace to userspace via include/uapi/linux/quota.h. Signed-off-by: Jan Kara --- fs/quota/dquot.c | 2 +- include/linux/dqblk_v1.h | 3 --- include/linux/quota.h | 14 ++++++++------ include/uapi/linux/quota.h | 14 +++++++++++++- 4 files changed, 22 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8f0acef3d184..f8be368b9086 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1248,7 +1248,7 @@ static int ignore_hardlimit(struct dquot *dquot) return capable(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || - !(info->dqi_flags & V1_DQF_RSQUASH)); + !(info->dqi_flags & DQF_ROOT_SQUASH)); } /* needs dq_data_lock */ diff --git a/include/linux/dqblk_v1.h b/include/linux/dqblk_v1.h index 3713a7232dd8..c0d4d1e2a45c 100644 --- a/include/linux/dqblk_v1.h +++ b/include/linux/dqblk_v1.h @@ -5,9 +5,6 @@ #ifndef _LINUX_DQBLK_V1_H #define _LINUX_DQBLK_V1_H -/* Root squash turned on */ -#define V1_DQF_RSQUASH 1 - /* Numbers of blocks needed for updates */ #define V1_INIT_ALLOC 1 #define V1_INIT_REWRITE 1 diff --git a/include/linux/quota.h b/include/linux/quota.h index 50978b781a19..0c42113607ce 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -223,12 +223,14 @@ struct mem_dqinfo { struct super_block; -#define DQF_MASK 0xffff /* Mask for format specific flags */ -#define DQF_GETINFO_MASK 0x1ffff /* Mask for flags passed to userspace */ -#define DQF_SETINFO_MASK 0xffff /* Mask for flags modifiable from userspace */ -#define DQF_SYS_FILE_B 16 -#define DQF_SYS_FILE (1 << DQF_SYS_FILE_B) /* Quota file stored as system file */ -#define DQF_INFO_DIRTY_B 31 +/* Mask for flags passed to userspace */ +#define DQF_GETINFO_MASK (DQF_ROOT_SQUASH | DQF_SYS_FILE) +/* Mask for flags modifiable from userspace */ +#define DQF_SETINFO_MASK DQF_ROOT_SQUASH + +enum { + DQF_INFO_DIRTY_B = DQF_PRIVATE, +}; #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B) /* Is info dirty? */ extern void mark_info_dirty(struct super_block *sb, int type); diff --git a/include/uapi/linux/quota.h b/include/uapi/linux/quota.h index 3b6cfbeb086d..1f49b8341c99 100644 --- a/include/uapi/linux/quota.h +++ b/include/uapi/linux/quota.h @@ -126,10 +126,22 @@ struct if_dqblk { #define IIF_FLAGS 4 #define IIF_ALL (IIF_BGRACE | IIF_IGRACE | IIF_FLAGS) +enum { + DQF_ROOT_SQUASH_B = 0, + DQF_SYS_FILE_B = 16, + /* Kernel internal flags invisible to userspace */ + DQF_PRIVATE +}; + +/* Root squash enabled (for v1 quota format) */ +#define DQF_ROOT_SQUASH (1 << DQF_ROOT_SQUASH_B) +/* Quota stored in a system file */ +#define DQF_SYS_FILE (1 << DQF_SYS_FILE_B) + struct if_dqinfo { __u64 dqi_bgrace; __u64 dqi_igrace; - __u32 dqi_flags; + __u32 dqi_flags; /* DFQ_* */ __u32 dqi_valid; }; -- cgit v1.2.3 From ca6cb0918e8765de304916a15554b42203e6e1fc Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 19 Nov 2014 09:32:39 +0100 Subject: quota: Verify flags passed to Q_SETINFO Currently flags passed via Q_SETINFO were just stored. This makes it hard to add new flags since in theory userspace could be just setting / clearing random flags. Since currently there is only one userspace settable flag and that is somewhat obscure flags only for ancient v1 quota format, I'm reasonably sure noone operates these flags and hopefully we are fine just adding the check that passed flags are sane. If we indeed find some userspace program that gets broken by the strict check, we can always remove it again. Signed-off-by: Jan Kara --- fs/quota/dquot.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'fs') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index f8be368b9086..d25c3243c196 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2582,6 +2582,14 @@ int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii) goto out; } mi = sb_dqopt(sb)->info + type; + if (ii->dqi_valid & IIF_FLAGS) { + if (ii->dqi_flags & ~DQF_SETINFO_MASK || + (ii->dqi_flags & DQF_ROOT_SQUASH && + mi->dqi_format->qf_fmt_id != QFMT_VFS_OLD)) { + err = -EINVAL; + goto out; + } + } spin_lock(&dq_data_lock); if (ii->dqi_valid & IIF_BGRACE) mi->dqi_bgrace = ii->dqi_bgrace; -- cgit v1.2.3 From 8a2fdd4a49d40017b3fca42beb2e1c8c0174a743 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 11:44:47 +0200 Subject: xfs: Remove useless test Q_XQUOTARM is never passed to xfs_fs_set_xstate() so remove the test. Reviewed-by: Brian Foster Signed-off-by: Jan Kara --- fs/xfs/xfs_quotaops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index 7542bbeca6a1..8fcd20dbf89a 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -75,7 +75,7 @@ xfs_fs_set_xstate( if (sb->s_flags & MS_RDONLY) return -EROFS; - if (op != Q_XQUOTARM && !XFS_IS_QUOTA_RUNNING(mp)) + if (!XFS_IS_QUOTA_RUNNING(mp)) return -ENOSYS; if (uflags & FS_QUOTA_UDQ_ACCT) -- cgit v1.2.3 From fbf64b3df34e6640fbbc89d6daa5f79833036890 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 11:52:52 +0200 Subject: xfs: Remove some useless flags tests 'flags' have XFS_ALL_QUOTA_ACCT cleared immediately on function entry. There's no point in checking these bits later in the function. Also because we check something is going to change, we know some enforcement bits are being added and thus there's no point in testing that later. Reviewed-by: Brian Foster Signed-off-by: Jan Kara --- fs/xfs/xfs_qm_syscalls.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 74fca68e43b6..b7a8f5665d7b 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -330,22 +330,16 @@ xfs_qm_scall_quotaon( return -EINVAL; } - /* No fs can turn on quotas with a delayed effect */ - ASSERT((flags & XFS_ALL_QUOTA_ACCT) == 0); - /* * Can't enforce without accounting. We check the superblock * qflags here instead of m_qflags because rootfs can have * quota acct on ondisk without m_qflags' knowing. */ - if (((flags & XFS_UQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 && + if (((mp->m_sb.sb_qflags & XFS_UQUOTA_ACCT) == 0 && (flags & XFS_UQUOTA_ENFD)) || - ((flags & XFS_GQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 && + ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 && (flags & XFS_GQUOTA_ENFD)) || - ((flags & XFS_PQUOTA_ACCT) == 0 && - (mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 && + ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) == 0 && (flags & XFS_PQUOTA_ENFD))) { xfs_debug(mp, "%s: Can't enforce without acct, flags=%x sbflags=%x", @@ -384,8 +378,7 @@ xfs_qm_scall_quotaon( ((mp->m_sb.sb_qflags & XFS_PQUOTA_ACCT) != (mp->m_qflags & XFS_PQUOTA_ACCT)) || ((mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) != - (mp->m_qflags & XFS_GQUOTA_ACCT)) || - (flags & XFS_ALL_QUOTA_ENFD) == 0) + (mp->m_qflags & XFS_GQUOTA_ACCT))) return 0; if (! XFS_IS_QUOTA_RUNNING(mp)) -- cgit v1.2.3 From a39427007e7ccd83dbb7cd81b18156cebeab4d1e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 12 Dec 2014 20:53:36 +0100 Subject: xfs: Remove some pointless quota checks xfs_fs_get_xstate() and xfs_fs_get_xstatev() check whether there's quota running before calling xfs_qm_scall_getqstat() or xfs_qm_scall_getqstatv(). Thus we are certain that superblock supports quota and xfs_sb_version_hasquota() check is pointless. Similarly we know that when quota is running, mp->m_quotainfo will be allocated. Reviewed-by: Brian Foster Signed-off-by: Jan Kara --- fs/xfs/xfs_qm_syscalls.c | 59 ++++++++++++++++-------------------------------- 1 file changed, 20 insertions(+), 39 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index b7a8f5665d7b..42a15ddedb07 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -415,20 +415,12 @@ xfs_qm_scall_getqstat( memset(out, 0, sizeof(fs_quota_stat_t)); out->qs_version = FS_QSTAT_VERSION; - if (!xfs_sb_version_hasquota(&mp->m_sb)) { - out->qs_uquota.qfs_ino = NULLFSINO; - out->qs_gquota.qfs_ino = NULLFSINO; - return 0; - } - out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags & (XFS_ALL_QUOTA_ACCT| XFS_ALL_QUOTA_ENFD)); - if (q) { - uip = q->qi_uquotaip; - gip = q->qi_gquotaip; - pip = q->qi_pquotaip; - } + uip = q->qi_uquotaip; + gip = q->qi_gquotaip; + pip = q->qi_pquotaip; if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &uip) == 0) @@ -474,14 +466,13 @@ xfs_qm_scall_getqstat( if (temppqip) IRELE(pip); } - if (q) { - out->qs_incoredqs = q->qi_dquots; - out->qs_btimelimit = q->qi_btimelimit; - out->qs_itimelimit = q->qi_itimelimit; - out->qs_rtbtimelimit = q->qi_rtbtimelimit; - out->qs_bwarnlimit = q->qi_bwarnlimit; - out->qs_iwarnlimit = q->qi_iwarnlimit; - } + out->qs_incoredqs = q->qi_dquots; + out->qs_btimelimit = q->qi_btimelimit; + out->qs_itimelimit = q->qi_itimelimit; + out->qs_rtbtimelimit = q->qi_rtbtimelimit; + out->qs_bwarnlimit = q->qi_bwarnlimit; + out->qs_iwarnlimit = q->qi_iwarnlimit; + return 0; } @@ -502,13 +493,6 @@ xfs_qm_scall_getqstatv( bool tempgqip = false; bool temppqip = false; - if (!xfs_sb_version_hasquota(&mp->m_sb)) { - out->qs_uquota.qfs_ino = NULLFSINO; - out->qs_gquota.qfs_ino = NULLFSINO; - out->qs_pquota.qfs_ino = NULLFSINO; - return 0; - } - out->qs_flags = (__uint16_t) xfs_qm_export_flags(mp->m_qflags & (XFS_ALL_QUOTA_ACCT| XFS_ALL_QUOTA_ENFD)); @@ -516,11 +500,9 @@ xfs_qm_scall_getqstatv( out->qs_gquota.qfs_ino = mp->m_sb.sb_gquotino; out->qs_pquota.qfs_ino = mp->m_sb.sb_pquotino; - if (q) { - uip = q->qi_uquotaip; - gip = q->qi_gquotaip; - pip = q->qi_pquotaip; - } + uip = q->qi_uquotaip; + gip = q->qi_gquotaip; + pip = q->qi_pquotaip; if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) { if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &uip) == 0) @@ -555,14 +537,13 @@ xfs_qm_scall_getqstatv( if (temppqip) IRELE(pip); } - if (q) { - out->qs_incoredqs = q->qi_dquots; - out->qs_btimelimit = q->qi_btimelimit; - out->qs_itimelimit = q->qi_itimelimit; - out->qs_rtbtimelimit = q->qi_rtbtimelimit; - out->qs_bwarnlimit = q->qi_bwarnlimit; - out->qs_iwarnlimit = q->qi_iwarnlimit; - } + out->qs_incoredqs = q->qi_dquots; + out->qs_btimelimit = q->qi_btimelimit; + out->qs_itimelimit = q->qi_itimelimit; + out->qs_rtbtimelimit = q->qi_rtbtimelimit; + out->qs_bwarnlimit = q->qi_bwarnlimit; + out->qs_iwarnlimit = q->qi_iwarnlimit; + return 0; } -- cgit v1.2.3 From 4d11a40239405e531fc0e9dcd07921f00b965931 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 22 Jan 2015 09:10:26 +1100 Subject: xfs: remove bitfield based superblock updates When we log changes to the superblock, we first have to write them to the on-disk buffer, and then log that. Right now we have a complex bitfield based arrangement to only write the modified field to the buffer before we log it. This used to be necessary as a performance optimisation because we logged the superblock buffer in every extent or inode allocation or freeing, and so performance was extremely important. We haven't done this for years, however, ever since the lazy superblock counters pulled the superblock logging out of the transaction commit fast path. Hence we have a bunch of complexity that is not necessary that makes writing the in-core superblock to disk much more complex than it needs to be. We only need to log the superblock now during management operations (e.g. during mount, unmount or quota control operations) so it is not a performance critical path anymore. As such, remove the complex field based logging mechanism and replace it with a simple conversion function similar to what we use for all other on-disk structures. This means we always log the entirity of the superblock, but again because we rarely modify the superblock this is not an issue for log bandwidth or CPU time. Indeed, if we do log the superblock frequently, delayed logging will minimise the impact of this overhead. [Fixed gquota/pquota inode sharing regression noticed by bfoster.] Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_attr_leaf.c | 2 +- fs/xfs/libxfs/xfs_bmap.c | 14 +-- fs/xfs/libxfs/xfs_sb.c | 277 +++++++++++++++--------------------------- fs/xfs/libxfs/xfs_sb.h | 10 +- fs/xfs/xfs_fsops.c | 6 +- fs/xfs/xfs_mount.c | 22 ++-- fs/xfs/xfs_mount.h | 2 +- fs/xfs/xfs_qm.c | 26 +--- fs/xfs/xfs_qm.h | 2 +- fs/xfs/xfs_qm_syscalls.c | 13 +- fs/xfs/xfs_super.c | 2 +- 11 files changed, 130 insertions(+), 246 deletions(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 5d38e8b8a913..c9144221798f 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -403,7 +403,7 @@ xfs_sbversion_add_attr2(xfs_mount_t *mp, xfs_trans_t *tp) if (!xfs_sb_version_hasattr2(&mp->m_sb)) { xfs_sb_version_addattr2(&mp->m_sb); spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp, XFS_SB_VERSIONNUM | XFS_SB_FEATURES2); + xfs_mod_sb(tp); } else spin_unlock(&mp->m_sb_lock); } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index b5eb4743f75a..8c39cc852e4b 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1221,22 +1221,20 @@ xfs_bmap_add_attrfork( goto bmap_cancel; if (!xfs_sb_version_hasattr(&mp->m_sb) || (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) { - __int64_t sbfields = 0; + bool mod_sb = false; spin_lock(&mp->m_sb_lock); if (!xfs_sb_version_hasattr(&mp->m_sb)) { xfs_sb_version_addattr(&mp->m_sb); - sbfields |= XFS_SB_VERSIONNUM; + mod_sb = true; } if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) { xfs_sb_version_addattr2(&mp->m_sb); - sbfields |= (XFS_SB_VERSIONNUM | XFS_SB_FEATURES2); + mod_sb = true; } - if (sbfields) { - spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp, sbfields); - } else - spin_unlock(&mp->m_sb_lock); + spin_unlock(&mp->m_sb_lock); + if (mod_sb) + xfs_mod_sb(tp); } error = xfs_bmap_finish(&tp, &flist, &committed); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 752915fa775a..115a7cd3a6fb 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -40,69 +40,6 @@ * Physical superblock buffer manipulations. Shared with libxfs in userspace. */ -static const struct { - short offset; - short type; /* 0 = integer - * 1 = binary / string (no translation) - */ -} xfs_sb_info[] = { - { offsetof(xfs_sb_t, sb_magicnum), 0 }, - { offsetof(xfs_sb_t, sb_blocksize), 0 }, - { offsetof(xfs_sb_t, sb_dblocks), 0 }, - { offsetof(xfs_sb_t, sb_rblocks), 0 }, - { offsetof(xfs_sb_t, sb_rextents), 0 }, - { offsetof(xfs_sb_t, sb_uuid), 1 }, - { offsetof(xfs_sb_t, sb_logstart), 0 }, - { offsetof(xfs_sb_t, sb_rootino), 0 }, - { offsetof(xfs_sb_t, sb_rbmino), 0 }, - { offsetof(xfs_sb_t, sb_rsumino), 0 }, - { offsetof(xfs_sb_t, sb_rextsize), 0 }, - { offsetof(xfs_sb_t, sb_agblocks), 0 }, - { offsetof(xfs_sb_t, sb_agcount), 0 }, - { offsetof(xfs_sb_t, sb_rbmblocks), 0 }, - { offsetof(xfs_sb_t, sb_logblocks), 0 }, - { offsetof(xfs_sb_t, sb_versionnum), 0 }, - { offsetof(xfs_sb_t, sb_sectsize), 0 }, - { offsetof(xfs_sb_t, sb_inodesize), 0 }, - { offsetof(xfs_sb_t, sb_inopblock), 0 }, - { offsetof(xfs_sb_t, sb_fname[0]), 1 }, - { offsetof(xfs_sb_t, sb_blocklog), 0 }, - { offsetof(xfs_sb_t, sb_sectlog), 0 }, - { offsetof(xfs_sb_t, sb_inodelog), 0 }, - { offsetof(xfs_sb_t, sb_inopblog), 0 }, - { offsetof(xfs_sb_t, sb_agblklog), 0 }, - { offsetof(xfs_sb_t, sb_rextslog), 0 }, - { offsetof(xfs_sb_t, sb_inprogress), 0 }, - { offsetof(xfs_sb_t, sb_imax_pct), 0 }, - { offsetof(xfs_sb_t, sb_icount), 0 }, - { offsetof(xfs_sb_t, sb_ifree), 0 }, - { offsetof(xfs_sb_t, sb_fdblocks), 0 }, - { offsetof(xfs_sb_t, sb_frextents), 0 }, - { offsetof(xfs_sb_t, sb_uquotino), 0 }, - { offsetof(xfs_sb_t, sb_gquotino), 0 }, - { offsetof(xfs_sb_t, sb_qflags), 0 }, - { offsetof(xfs_sb_t, sb_flags), 0 }, - { offsetof(xfs_sb_t, sb_shared_vn), 0 }, - { offsetof(xfs_sb_t, sb_inoalignmt), 0 }, - { offsetof(xfs_sb_t, sb_unit), 0 }, - { offsetof(xfs_sb_t, sb_width), 0 }, - { offsetof(xfs_sb_t, sb_dirblklog), 0 }, - { offsetof(xfs_sb_t, sb_logsectlog), 0 }, - { offsetof(xfs_sb_t, sb_logsectsize), 0 }, - { offsetof(xfs_sb_t, sb_logsunit), 0 }, - { offsetof(xfs_sb_t, sb_features2), 0 }, - { offsetof(xfs_sb_t, sb_bad_features2), 0 }, - { offsetof(xfs_sb_t, sb_features_compat), 0 }, - { offsetof(xfs_sb_t, sb_features_ro_compat), 0 }, - { offsetof(xfs_sb_t, sb_features_incompat), 0 }, - { offsetof(xfs_sb_t, sb_features_log_incompat), 0 }, - { offsetof(xfs_sb_t, sb_crc), 0 }, - { offsetof(xfs_sb_t, sb_pad), 0 }, - { offsetof(xfs_sb_t, sb_pquotino), 0 }, - { offsetof(xfs_sb_t, sb_lsn), 0 }, - { sizeof(xfs_sb_t), 0 } -}; - /* * Reference counting access wrappers to the perag structures. * Because we never free per-ag structures, the only thing we @@ -461,58 +398,49 @@ xfs_sb_from_disk( __xfs_sb_from_disk(to, from, true); } -static inline void +static void xfs_sb_quota_to_disk( - xfs_dsb_t *to, - xfs_sb_t *from, - __int64_t *fields) + struct xfs_dsb *to, + struct xfs_sb *from) { __uint16_t qflags = from->sb_qflags; + to->sb_uquotino = cpu_to_be64(from->sb_uquotino); + if (xfs_sb_version_has_pquotino(from)) { + to->sb_qflags = cpu_to_be16(from->sb_qflags); + to->sb_gquotino = cpu_to_be64(from->sb_gquotino); + to->sb_pquotino = cpu_to_be64(from->sb_pquotino); + return; + } + /* - * We need to do these manipilations only if we are working - * with an older version of on-disk superblock. + * The in-core version of sb_qflags do not have XFS_OQUOTA_* + * flags, whereas the on-disk version does. So, convert incore + * XFS_{PG}QUOTA_* flags to on-disk XFS_OQUOTA_* flags. */ - if (xfs_sb_version_has_pquotino(from)) - return; + qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD | + XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD); - if (*fields & XFS_SB_QFLAGS) { - /* - * The in-core version of sb_qflags do not have - * XFS_OQUOTA_* flags, whereas the on-disk version - * does. So, convert incore XFS_{PG}QUOTA_* flags - * to on-disk XFS_OQUOTA_* flags. - */ - qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD | - XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD); - - if (from->sb_qflags & - (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD)) - qflags |= XFS_OQUOTA_ENFD; - if (from->sb_qflags & - (XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) - qflags |= XFS_OQUOTA_CHKD; - to->sb_qflags = cpu_to_be16(qflags); - *fields &= ~XFS_SB_QFLAGS; - } + if (from->sb_qflags & + (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD)) + qflags |= XFS_OQUOTA_ENFD; + if (from->sb_qflags & + (XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) + qflags |= XFS_OQUOTA_CHKD; + to->sb_qflags = cpu_to_be16(qflags); /* - * GQUOTINO and PQUOTINO cannot be used together in versions of - * superblock that do not have pquotino. from->sb_flags tells us which - * quota is active and should be copied to disk. If neither are active, - * make sure we write NULLFSINO to the sb_gquotino field as a quota - * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature - * bit is set. + * GQUOTINO and PQUOTINO cannot be used together in versions + * of superblock that do not have pquotino. from->sb_flags + * tells us which quota is active and should be copied to + * disk. If neither are active, we should NULL the inode. * - * Note that we don't need to handle the sb_uquotino or sb_pquotino here - * as they do not require any translation. Hence the main sb field loop - * will write them appropriately from the in-core superblock. + * In all cases, the separate pquotino must remain 0 because it + * it beyond the "end" of the valid non-pquotino superblock. */ - if ((*fields & XFS_SB_GQUOTINO) && - (from->sb_qflags & XFS_GQUOTA_ACCT)) + if (from->sb_qflags & XFS_GQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_gquotino); - else if ((*fields & XFS_SB_PQUOTINO) && - (from->sb_qflags & XFS_PQUOTA_ACCT)) + else if (from->sb_qflags & XFS_PQUOTA_ACCT) to->sb_gquotino = cpu_to_be64(from->sb_pquotino); else { /* @@ -526,63 +454,72 @@ xfs_sb_quota_to_disk( to->sb_gquotino = cpu_to_be64(NULLFSINO); } - *fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO); + to->sb_pquotino = 0; } -/* - * Copy in core superblock to ondisk one. - * - * The fields argument is mask of superblock fields to copy. - */ void xfs_sb_to_disk( - xfs_dsb_t *to, - xfs_sb_t *from, - __int64_t fields) + struct xfs_dsb *to, + struct xfs_sb *from) { - xfs_caddr_t to_ptr = (xfs_caddr_t)to; - xfs_caddr_t from_ptr = (xfs_caddr_t)from; - xfs_sb_field_t f; - int first; - int size; - - ASSERT(fields); - if (!fields) - return; + xfs_sb_quota_to_disk(to, from); + + to->sb_magicnum = cpu_to_be32(from->sb_magicnum); + to->sb_blocksize = cpu_to_be32(from->sb_blocksize); + to->sb_dblocks = cpu_to_be64(from->sb_dblocks); + to->sb_rblocks = cpu_to_be64(from->sb_rblocks); + to->sb_rextents = cpu_to_be64(from->sb_rextents); + memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid)); + to->sb_logstart = cpu_to_be64(from->sb_logstart); + to->sb_rootino = cpu_to_be64(from->sb_rootino); + to->sb_rbmino = cpu_to_be64(from->sb_rbmino); + to->sb_rsumino = cpu_to_be64(from->sb_rsumino); + to->sb_rextsize = cpu_to_be32(from->sb_rextsize); + to->sb_agblocks = cpu_to_be32(from->sb_agblocks); + to->sb_agcount = cpu_to_be32(from->sb_agcount); + to->sb_rbmblocks = cpu_to_be32(from->sb_rbmblocks); + to->sb_logblocks = cpu_to_be32(from->sb_logblocks); + to->sb_versionnum = cpu_to_be16(from->sb_versionnum); + to->sb_sectsize = cpu_to_be16(from->sb_sectsize); + to->sb_inodesize = cpu_to_be16(from->sb_inodesize); + to->sb_inopblock = cpu_to_be16(from->sb_inopblock); + memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname)); + to->sb_blocklog = from->sb_blocklog; + to->sb_sectlog = from->sb_sectlog; + to->sb_inodelog = from->sb_inodelog; + to->sb_inopblog = from->sb_inopblog; + to->sb_agblklog = from->sb_agblklog; + to->sb_rextslog = from->sb_rextslog; + to->sb_inprogress = from->sb_inprogress; + to->sb_imax_pct = from->sb_imax_pct; + to->sb_icount = cpu_to_be64(from->sb_icount); + to->sb_ifree = cpu_to_be64(from->sb_ifree); + to->sb_fdblocks = cpu_to_be64(from->sb_fdblocks); + to->sb_frextents = cpu_to_be64(from->sb_frextents); - /* We should never write the crc here, it's updated in the IO path */ - fields &= ~XFS_SB_CRC; - - xfs_sb_quota_to_disk(to, from, &fields); - while (fields) { - f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields); - first = xfs_sb_info[f].offset; - size = xfs_sb_info[f + 1].offset - first; - - ASSERT(xfs_sb_info[f].type == 0 || xfs_sb_info[f].type == 1); - - if (size == 1 || xfs_sb_info[f].type == 1) { - memcpy(to_ptr + first, from_ptr + first, size); - } else { - switch (size) { - case 2: - *(__be16 *)(to_ptr + first) = - cpu_to_be16(*(__u16 *)(from_ptr + first)); - break; - case 4: - *(__be32 *)(to_ptr + first) = - cpu_to_be32(*(__u32 *)(from_ptr + first)); - break; - case 8: - *(__be64 *)(to_ptr + first) = - cpu_to_be64(*(__u64 *)(from_ptr + first)); - break; - default: - ASSERT(0); - } - } - fields &= ~(1LL << f); + to->sb_flags = from->sb_flags; + to->sb_shared_vn = from->sb_shared_vn; + to->sb_inoalignmt = cpu_to_be32(from->sb_inoalignmt); + to->sb_unit = cpu_to_be32(from->sb_unit); + to->sb_width = cpu_to_be32(from->sb_width); + to->sb_dirblklog = from->sb_dirblklog; + to->sb_logsectlog = from->sb_logsectlog; + to->sb_logsectsize = cpu_to_be16(from->sb_logsectsize); + to->sb_logsunit = cpu_to_be32(from->sb_logsunit); + to->sb_features2 = cpu_to_be32(from->sb_features2); + to->sb_bad_features2 = cpu_to_be32(from->sb_bad_features2); + + if (xfs_sb_version_hascrc(from)) { + to->sb_features_compat = cpu_to_be32(from->sb_features_compat); + to->sb_features_ro_compat = + cpu_to_be32(from->sb_features_ro_compat); + to->sb_features_incompat = + cpu_to_be32(from->sb_features_incompat); + to->sb_features_log_incompat = + cpu_to_be32(from->sb_features_log_incompat); + to->sb_pad = 0; + to->sb_lsn = cpu_to_be64(from->sb_lsn); } } @@ -823,35 +760,13 @@ xfs_initialize_perag_data( * access. */ void -xfs_mod_sb(xfs_trans_t *tp, __int64_t fields) +xfs_mod_sb( + struct xfs_trans *tp) { - xfs_buf_t *bp; - int first; - int last; - xfs_mount_t *mp; - xfs_sb_field_t f; - - ASSERT(fields); - if (!fields) - return; - mp = tp->t_mountp; - bp = xfs_trans_getsb(tp, mp, 0); - first = sizeof(xfs_sb_t); - last = 0; - - /* translate/copy */ - - xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, fields); - - /* find modified range */ - f = (xfs_sb_field_t)xfs_highbit64((__uint64_t)fields); - ASSERT((1LL << f) & XFS_SB_MOD_BITS); - last = xfs_sb_info[f + 1].offset - 1; - - f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields); - ASSERT((1LL << f) & XFS_SB_MOD_BITS); - first = xfs_sb_info[f].offset; + struct xfs_mount *mp = tp->t_mountp; + struct xfs_buf *bp = xfs_trans_getsb(tp, mp, 0); + xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb); xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); - xfs_trans_log_buf(tp, bp, first, last); + xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb)); } diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index 8eb1c54bafbf..e193caa42988 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -27,11 +27,11 @@ extern struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t, extern void xfs_perag_put(struct xfs_perag *pag); extern int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t); -extern void xfs_sb_calc_crc(struct xfs_buf *); -extern void xfs_mod_sb(struct xfs_trans *, __int64_t); -extern void xfs_sb_mount_common(struct xfs_mount *, struct xfs_sb *); -extern void xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *); -extern void xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t); +extern void xfs_sb_calc_crc(struct xfs_buf *bp); +extern void xfs_mod_sb(struct xfs_trans *tp); +extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp); +extern void xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from); +extern void xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from); extern void xfs_sb_quota_from_disk(struct xfs_sb *sbp); #endif /* __XFS_SB_H__ */ diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index fdc64220fcb0..82af857405af 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -541,7 +541,7 @@ xfs_growfs_data_private( saved_error = error; continue; } - xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, XFS_SB_ALL_BITS); + xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb); error = xfs_bwrite(bp); xfs_buf_relse(bp); @@ -780,9 +780,7 @@ xfs_fs_log_dummy( xfs_trans_cancel(tp, 0); return error; } - - /* log the UUID because it is an unchanging field */ - xfs_mod_sb(tp, XFS_SB_UUID); + xfs_mod_sb(tp); xfs_trans_set_sync(tp); return xfs_trans_commit(tp, 0); } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index d3d38836f87f..2953d46be249 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -613,7 +613,7 @@ xfs_mount_reset_sbqflags( return error; } - xfs_mod_sb(tp, XFS_SB_QFLAGS); + xfs_mod_sb(tp); return xfs_trans_commit(tp, 0); } @@ -896,7 +896,7 @@ xfs_mountfs( * perform the update e.g. for the root filesystem. */ if (mp->m_update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) { - error = xfs_mount_log_sb(mp, mp->m_update_flags); + error = xfs_mount_log_sb(mp); if (error) { xfs_warn(mp, "failed to write sb changes"); goto out_rtunmount; @@ -1126,7 +1126,7 @@ xfs_log_sbcount(xfs_mount_t *mp) return error; } - xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS); + xfs_mod_sb(tp); xfs_trans_set_sync(tp); error = xfs_trans_commit(tp, 0); return error; @@ -1429,15 +1429,10 @@ xfs_freesb( */ int xfs_mount_log_sb( - xfs_mount_t *mp, - __int64_t fields) + struct xfs_mount *mp) { - xfs_trans_t *tp; - int error; - - ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID | - XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2 | - XFS_SB_VERSIONNUM)); + struct xfs_trans *tp; + int error; tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT); error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); @@ -1445,9 +1440,8 @@ xfs_mount_log_sb( xfs_trans_cancel(tp, 0); return error; } - xfs_mod_sb(tp, fields); - error = xfs_trans_commit(tp, 0); - return error; + xfs_mod_sb(tp); + return xfs_trans_commit(tp, 0); } /* diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 22ccf69d4d3c..28b341bf1555 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -378,7 +378,7 @@ extern void xfs_unmountfs(xfs_mount_t *); extern int xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int); extern int xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *, uint, int); -extern int xfs_mount_log_sb(xfs_mount_t *, __int64_t); +extern int xfs_mount_log_sb(xfs_mount_t *); extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int); extern int xfs_readsb(xfs_mount_t *, int); extern void xfs_freesb(xfs_mount_t *); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 79fb19dd9c83..c815a8060b59 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -714,7 +714,6 @@ STATIC int xfs_qm_qino_alloc( xfs_mount_t *mp, xfs_inode_t **ip, - __int64_t sbfields, uint flags) { xfs_trans_t *tp; @@ -777,11 +776,6 @@ xfs_qm_qino_alloc( spin_lock(&mp->m_sb_lock); if (flags & XFS_QMOPT_SBVERSION) { ASSERT(!xfs_sb_version_hasquota(&mp->m_sb)); - ASSERT((sbfields & (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | - XFS_SB_GQUOTINO | XFS_SB_PQUOTINO | XFS_SB_QFLAGS)) == - (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | - XFS_SB_GQUOTINO | XFS_SB_PQUOTINO | - XFS_SB_QFLAGS)); xfs_sb_version_addquota(&mp->m_sb); mp->m_sb.sb_uquotino = NULLFSINO; @@ -798,7 +792,7 @@ xfs_qm_qino_alloc( else mp->m_sb.sb_pquotino = (*ip)->i_ino; spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp, sbfields); + xfs_mod_sb(tp); if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES))) { xfs_alert(mp, "%s failed (error %d)!", __func__, error); @@ -1451,7 +1445,7 @@ xfs_qm_mount_quotas( spin_unlock(&mp->m_sb_lock); if (sbf != (mp->m_qflags & XFS_MOUNT_QUOTA_ALL)) { - if (xfs_qm_write_sb_changes(mp, XFS_SB_QFLAGS)) { + if (xfs_qm_write_sb_changes(mp)) { /* * We could only have been turning quotas off. * We aren't in very good shape actually because @@ -1482,7 +1476,6 @@ xfs_qm_init_quotainos( struct xfs_inode *gip = NULL; struct xfs_inode *pip = NULL; int error; - __int64_t sbflags = 0; uint flags = 0; ASSERT(mp->m_quotainfo); @@ -1517,9 +1510,6 @@ xfs_qm_init_quotainos( } } else { flags |= XFS_QMOPT_SBVERSION; - sbflags |= (XFS_SB_VERSIONNUM | XFS_SB_UQUOTINO | - XFS_SB_GQUOTINO | XFS_SB_PQUOTINO | - XFS_SB_QFLAGS); } /* @@ -1530,7 +1520,6 @@ xfs_qm_init_quotainos( */ if (XFS_IS_UQUOTA_ON(mp) && uip == NULL) { error = xfs_qm_qino_alloc(mp, &uip, - sbflags | XFS_SB_UQUOTINO, flags | XFS_QMOPT_UQUOTA); if (error) goto error_rele; @@ -1539,7 +1528,6 @@ xfs_qm_init_quotainos( } if (XFS_IS_GQUOTA_ON(mp) && gip == NULL) { error = xfs_qm_qino_alloc(mp, &gip, - sbflags | XFS_SB_GQUOTINO, flags | XFS_QMOPT_GQUOTA); if (error) goto error_rele; @@ -1548,7 +1536,6 @@ xfs_qm_init_quotainos( } if (XFS_IS_PQUOTA_ON(mp) && pip == NULL) { error = xfs_qm_qino_alloc(mp, &pip, - sbflags | XFS_SB_PQUOTINO, flags | XFS_QMOPT_PQUOTA); if (error) goto error_rele; @@ -1593,8 +1580,7 @@ xfs_qm_dqfree_one( */ int xfs_qm_write_sb_changes( - xfs_mount_t *mp, - __int64_t flags) + struct xfs_mount *mp) { xfs_trans_t *tp; int error; @@ -1606,10 +1592,8 @@ xfs_qm_write_sb_changes( return error; } - xfs_mod_sb(tp, flags); - error = xfs_trans_commit(tp, 0); - - return error; + xfs_mod_sb(tp); + return xfs_trans_commit(tp, 0); } diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 3a07a937e232..bddd23fda9ce 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -157,7 +157,7 @@ struct xfs_dquot_acct { #define XFS_QM_RTBWARNLIMIT 5 extern void xfs_qm_destroy_quotainfo(struct xfs_mount *); -extern int xfs_qm_write_sb_changes(struct xfs_mount *, __int64_t); +extern int xfs_qm_write_sb_changes(struct xfs_mount *); /* dquot stuff */ extern void xfs_qm_dqpurge_all(struct xfs_mount *, uint); diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 74fca68e43b6..8d7e5f068803 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -92,8 +92,7 @@ xfs_qm_scall_quotaoff( mutex_unlock(&q->qi_quotaofflock); /* XXX what to do if error ? Revert back to old vals incore ? */ - error = xfs_qm_write_sb_changes(mp, XFS_SB_QFLAGS); - return error; + return xfs_qm_write_sb_changes(mp); } dqtype = 0; @@ -314,7 +313,6 @@ xfs_qm_scall_quotaon( { int error; uint qf; - __int64_t sbflags; flags &= (XFS_ALL_QUOTA_ACCT | XFS_ALL_QUOTA_ENFD); /* @@ -322,8 +320,6 @@ xfs_qm_scall_quotaon( */ flags &= ~(XFS_ALL_QUOTA_ACCT); - sbflags = 0; - if (flags == 0) { xfs_debug(mp, "%s: zero flags, m_qflags=%x", __func__, mp->m_qflags); @@ -370,11 +366,10 @@ xfs_qm_scall_quotaon( /* * There's nothing to change if it's the same. */ - if ((qf & flags) == flags && sbflags == 0) + if ((qf & flags) == flags) return -EEXIST; - sbflags |= XFS_SB_QFLAGS; - if ((error = xfs_qm_write_sb_changes(mp, sbflags))) + if ((error = xfs_qm_write_sb_changes(mp))) return error; /* * If we aren't trying to switch on quota enforcement, we are done. @@ -801,7 +796,7 @@ xfs_qm_log_quotaoff( mp->m_sb.sb_qflags = (mp->m_qflags & ~(flags)) & XFS_MOUNT_QUOTA_ALL; spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp, XFS_SB_QFLAGS); + xfs_mod_sb(tp); /* * We have to make sure that the transaction is secure on disk before we diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 19cbda196369..6fb298963d1b 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1258,7 +1258,7 @@ xfs_fs_remount( * might have some superblock changes to update. */ if (mp->m_update_flags) { - error = xfs_mount_log_sb(mp, mp->m_update_flags); + error = xfs_mount_log_sb(mp); if (error) { xfs_warn(mp, "failed to write sb changes"); return error; -- cgit v1.2.3 From 61e63ecb577f9b56bfb3182f1215b64e37a12c38 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 22 Jan 2015 09:10:31 +1100 Subject: xfs: consolidate superblock logging functions We now have several superblock loggin functions that are identical except for the transaction reservation and whether it shoul dbe a synchronous transaction or not. Consolidate these all into a single function, a single reserveration and a sync flag and call it xfs_sync_sb(). Also, xfs_mod_sb() is not really a modification function - it's the operation of logging the superblock buffer. hence change the name of it to reflect this. Note that we have to change the mp->m_update_flags that are passed around at mount time to a boolean simply to indicate a superblock update is needed. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_attr_leaf.c | 2 +- fs/xfs/libxfs/xfs_bmap.c | 10 +++--- fs/xfs/libxfs/xfs_sb.c | 43 +++++++++++++++++++---- fs/xfs/libxfs/xfs_sb.h | 3 +- fs/xfs/libxfs/xfs_shared.h | 33 ++++++++---------- fs/xfs/libxfs/xfs_trans_resv.c | 14 -------- fs/xfs/libxfs/xfs_trans_resv.h | 1 - fs/xfs/xfs_fsops.c | 29 ---------------- fs/xfs/xfs_log.c | 18 ++++++++-- fs/xfs/xfs_mount.c | 78 +++++++----------------------------------- fs/xfs/xfs_mount.h | 3 +- fs/xfs/xfs_qm.c | 27 ++------------- fs/xfs/xfs_qm.h | 1 - fs/xfs/xfs_qm_syscalls.c | 7 ++-- fs/xfs/xfs_super.c | 13 +++---- 15 files changed, 101 insertions(+), 181 deletions(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index c9144221798f..15105dbc9e28 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -403,7 +403,7 @@ xfs_sbversion_add_attr2(xfs_mount_t *mp, xfs_trans_t *tp) if (!xfs_sb_version_hasattr2(&mp->m_sb)) { xfs_sb_version_addattr2(&mp->m_sb); spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp); + xfs_log_sb(tp); } else spin_unlock(&mp->m_sb_lock); } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 8c39cc852e4b..63a5bb9113ee 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1221,20 +1221,20 @@ xfs_bmap_add_attrfork( goto bmap_cancel; if (!xfs_sb_version_hasattr(&mp->m_sb) || (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) { - bool mod_sb = false; + bool log_sb = false; spin_lock(&mp->m_sb_lock); if (!xfs_sb_version_hasattr(&mp->m_sb)) { xfs_sb_version_addattr(&mp->m_sb); - mod_sb = true; + log_sb = true; } if (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2) { xfs_sb_version_addattr2(&mp->m_sb); - mod_sb = true; + log_sb = true; } spin_unlock(&mp->m_sb_lock); - if (mod_sb) - xfs_mod_sb(tp); + if (log_sb) + xfs_log_sb(tp); } error = xfs_bmap_finish(&tp, &flist, &committed); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 115a7cd3a6fb..63f814872dfb 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -753,14 +753,13 @@ xfs_initialize_perag_data( } /* - * xfs_mod_sb() can be used to copy arbitrary changes to the - * in-core superblock into the superblock buffer to be logged. - * It does not provide the higher level of locking that is - * needed to protect the in-core superblock from concurrent - * access. + * xfs_log_sb() can be used to copy arbitrary changes to the in-core superblock + * into the superblock buffer to be logged. It does not provide the higher + * level of locking that is needed to protect the in-core superblock from + * concurrent access. */ void -xfs_mod_sb( +xfs_log_sb( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; @@ -770,3 +769,35 @@ xfs_mod_sb( xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb)); } + +/* + * xfs_sync_sb + * + * Sync the superblock to disk. + * + * Note that the caller is responsible for checking the frozen state of the + * filesystem. This procedure uses the non-blocking transaction allocator and + * thus will allow modifications to a frozen fs. This is required because this + * code can be called during the process of freezing where use of the high-level + * allocator would deadlock. + */ +int +xfs_sync_sb( + struct xfs_mount *mp, + bool wait) +{ + struct xfs_trans *tp; + int error; + + tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_CHANGE, KM_SLEEP); + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } + + xfs_log_sb(tp); + if (wait) + xfs_trans_set_sync(tp); + return xfs_trans_commit(tp, 0); +} diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index e193caa42988..b25bb9a343f3 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -28,7 +28,8 @@ extern void xfs_perag_put(struct xfs_perag *pag); extern int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t); extern void xfs_sb_calc_crc(struct xfs_buf *bp); -extern void xfs_mod_sb(struct xfs_trans *tp); +extern void xfs_log_sb(struct xfs_trans *tp); +extern int xfs_sync_sb(struct xfs_mount *mp, bool wait); extern void xfs_sb_mount_common(struct xfs_mount *mp, struct xfs_sb *sbp); extern void xfs_sb_from_disk(struct xfs_sb *to, struct xfs_dsb *from); extern void xfs_sb_to_disk(struct xfs_dsb *to, struct xfs_sb *from); diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 82404da2ca67..8dda4b321343 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -82,7 +82,7 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; #define XFS_TRANS_ATTR_RM 23 #define XFS_TRANS_ATTR_FLAG 24 #define XFS_TRANS_CLEAR_AGI_BUCKET 25 -#define XFS_TRANS_QM_SBCHANGE 26 +#define XFS_TRANS_SB_CHANGE 26 /* * Dummy entries since we use the transaction type to index into the * trans_type[] in xlog_recover_print_trans_head() @@ -95,17 +95,15 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; #define XFS_TRANS_QM_DQCLUSTER 32 #define XFS_TRANS_QM_QINOCREATE 33 #define XFS_TRANS_QM_QUOTAOFF_END 34 -#define XFS_TRANS_SB_UNIT 35 -#define XFS_TRANS_FSYNC_TS 36 -#define XFS_TRANS_GROWFSRT_ALLOC 37 -#define XFS_TRANS_GROWFSRT_ZERO 38 -#define XFS_TRANS_GROWFSRT_FREE 39 -#define XFS_TRANS_SWAPEXT 40 -#define XFS_TRANS_SB_COUNT 41 -#define XFS_TRANS_CHECKPOINT 42 -#define XFS_TRANS_ICREATE 43 -#define XFS_TRANS_CREATE_TMPFILE 44 -#define XFS_TRANS_TYPE_MAX 44 +#define XFS_TRANS_FSYNC_TS 35 +#define XFS_TRANS_GROWFSRT_ALLOC 36 +#define XFS_TRANS_GROWFSRT_ZERO 37 +#define XFS_TRANS_GROWFSRT_FREE 38 +#define XFS_TRANS_SWAPEXT 39 +#define XFS_TRANS_CHECKPOINT 40 +#define XFS_TRANS_ICREATE 41 +#define XFS_TRANS_CREATE_TMPFILE 42 +#define XFS_TRANS_TYPE_MAX 43 /* new transaction types need to be reflected in xfs_logprint(8) */ #define XFS_TRANS_TYPES \ @@ -113,7 +111,6 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; { XFS_TRANS_SETATTR_SIZE, "SETATTR_SIZE" }, \ { XFS_TRANS_INACTIVE, "INACTIVE" }, \ { XFS_TRANS_CREATE, "CREATE" }, \ - { XFS_TRANS_CREATE_TMPFILE, "CREATE_TMPFILE" }, \ { XFS_TRANS_CREATE_TRUNC, "CREATE_TRUNC" }, \ { XFS_TRANS_TRUNCATE_FILE, "TRUNCATE_FILE" }, \ { XFS_TRANS_REMOVE, "REMOVE" }, \ @@ -134,23 +131,23 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; { XFS_TRANS_ATTR_RM, "ATTR_RM" }, \ { XFS_TRANS_ATTR_FLAG, "ATTR_FLAG" }, \ { XFS_TRANS_CLEAR_AGI_BUCKET, "CLEAR_AGI_BUCKET" }, \ - { XFS_TRANS_QM_SBCHANGE, "QM_SBCHANGE" }, \ + { XFS_TRANS_SB_CHANGE, "SBCHANGE" }, \ + { XFS_TRANS_DUMMY1, "DUMMY1" }, \ + { XFS_TRANS_DUMMY2, "DUMMY2" }, \ { XFS_TRANS_QM_QUOTAOFF, "QM_QUOTAOFF" }, \ { XFS_TRANS_QM_DQALLOC, "QM_DQALLOC" }, \ { XFS_TRANS_QM_SETQLIM, "QM_SETQLIM" }, \ { XFS_TRANS_QM_DQCLUSTER, "QM_DQCLUSTER" }, \ { XFS_TRANS_QM_QINOCREATE, "QM_QINOCREATE" }, \ { XFS_TRANS_QM_QUOTAOFF_END, "QM_QOFF_END" }, \ - { XFS_TRANS_SB_UNIT, "SB_UNIT" }, \ { XFS_TRANS_FSYNC_TS, "FSYNC_TS" }, \ { XFS_TRANS_GROWFSRT_ALLOC, "GROWFSRT_ALLOC" }, \ { XFS_TRANS_GROWFSRT_ZERO, "GROWFSRT_ZERO" }, \ { XFS_TRANS_GROWFSRT_FREE, "GROWFSRT_FREE" }, \ { XFS_TRANS_SWAPEXT, "SWAPEXT" }, \ - { XFS_TRANS_SB_COUNT, "SB_COUNT" }, \ { XFS_TRANS_CHECKPOINT, "CHECKPOINT" }, \ - { XFS_TRANS_DUMMY1, "DUMMY1" }, \ - { XFS_TRANS_DUMMY2, "DUMMY2" }, \ + { XFS_TRANS_ICREATE, "ICREATE" }, \ + { XFS_TRANS_CREATE_TMPFILE, "CREATE_TMPFILE" }, \ { XLOG_UNMOUNT_REC_TYPE, "UNMOUNT" } /* diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 6c1330f29050..68cb1e7bf2bb 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -715,17 +715,6 @@ xfs_calc_clear_agi_bucket_reservation( return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize); } -/* - * Clearing the quotaflags in the superblock. - * the super block for changing quota flags: sector size - */ -STATIC uint -xfs_calc_qm_sbchange_reservation( - struct xfs_mount *mp) -{ - return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize); -} - /* * Adjusting quota limits. * the xfs_disk_dquot_t: sizeof(struct xfs_disk_dquot) @@ -864,9 +853,6 @@ xfs_trans_resv_calc( * The following transactions are logged in logical format with * a default log count. */ - resp->tr_qm_sbchange.tr_logres = xfs_calc_qm_sbchange_reservation(mp); - resp->tr_qm_sbchange.tr_logcount = XFS_DEFAULT_LOG_COUNT; - resp->tr_qm_setqlim.tr_logres = xfs_calc_qm_setqlim_reservation(mp); resp->tr_qm_setqlim.tr_logcount = XFS_DEFAULT_LOG_COUNT; diff --git a/fs/xfs/libxfs/xfs_trans_resv.h b/fs/xfs/libxfs/xfs_trans_resv.h index 1097d14cd583..2d5bdfce6d8f 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.h +++ b/fs/xfs/libxfs/xfs_trans_resv.h @@ -56,7 +56,6 @@ struct xfs_trans_resv { struct xfs_trans_res tr_growrtalloc; /* grow realtime allocations */ struct xfs_trans_res tr_growrtzero; /* grow realtime zeroing */ struct xfs_trans_res tr_growrtfree; /* grow realtime freeing */ - struct xfs_trans_res tr_qm_sbchange; /* change quota flags */ struct xfs_trans_res tr_qm_setqlim; /* adjust quota limits */ struct xfs_trans_res tr_qm_dqalloc; /* allocate quota on disk */ struct xfs_trans_res tr_qm_quotaoff; /* turn quota off */ diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 82af857405af..f7114527cd2f 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -756,35 +756,6 @@ out: return 0; } -/* - * Dump a transaction into the log that contains no real change. This is needed - * to be able to make the log dirty or stamp the current tail LSN into the log - * during the covering operation. - * - * We cannot use an inode here for this - that will push dirty state back up - * into the VFS and then periodic inode flushing will prevent log covering from - * making progress. Hence we log a field in the superblock instead and use a - * synchronous transaction to ensure the superblock is immediately unpinned - * and can be written back. - */ -int -xfs_fs_log_dummy( - xfs_mount_t *mp) -{ - xfs_trans_t *tp; - int error; - - tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1, KM_SLEEP); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - xfs_mod_sb(tp); - xfs_trans_set_sync(tp); - return xfs_trans_commit(tp, 0); -} - int xfs_fs_goingdown( xfs_mount_t *mp, diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index e408bf5a3ff7..2b8dcf2b3dd1 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -33,6 +33,7 @@ #include "xfs_fsops.h" #include "xfs_cksum.h" #include "xfs_sysfs.h" +#include "xfs_sb.h" kmem_zone_t *xfs_log_ticket_zone; @@ -1290,9 +1291,20 @@ xfs_log_worker( struct xfs_mount *mp = log->l_mp; /* dgc: errors ignored - not fatal and nowhere to report them */ - if (xfs_log_need_covered(mp)) - xfs_fs_log_dummy(mp); - else + if (xfs_log_need_covered(mp)) { + /* + * Dump a transaction into the log that contains no real change. + * This is needed to stamp the current tail LSN into the log + * during the covering operation. + * + * We cannot use an inode here for this - that will push dirty + * state back up into the VFS and then periodic inode flushing + * will prevent log covering from making progress. Hence we + * synchronously log the superblock instead to ensure the + * superblock is immediately unpinned and can be written back. + */ + xfs_sync_sb(mp, true); + } else xfs_log_force(mp, 0); /* start pushing all the metadata that is currently dirty */ diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 2953d46be249..5ef9aa2bfa19 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -408,11 +408,11 @@ xfs_update_alignment(xfs_mount_t *mp) if (xfs_sb_version_hasdalign(sbp)) { if (sbp->sb_unit != mp->m_dalign) { sbp->sb_unit = mp->m_dalign; - mp->m_update_flags |= XFS_SB_UNIT; + mp->m_update_sb = true; } if (sbp->sb_width != mp->m_swidth) { sbp->sb_width = mp->m_swidth; - mp->m_update_flags |= XFS_SB_WIDTH; + mp->m_update_sb = true; } } else { xfs_warn(mp, @@ -583,38 +583,19 @@ int xfs_mount_reset_sbqflags( struct xfs_mount *mp) { - int error; - struct xfs_trans *tp; - mp->m_qflags = 0; - /* - * It is OK to look at sb_qflags here in mount path, - * without m_sb_lock. - */ + /* It is OK to look at sb_qflags in the mount path without m_sb_lock. */ if (mp->m_sb.sb_qflags == 0) return 0; spin_lock(&mp->m_sb_lock); mp->m_sb.sb_qflags = 0; spin_unlock(&mp->m_sb_lock); - /* - * If the fs is readonly, let the incore superblock run - * with quotas off but don't flush the update out to disk - */ - if (mp->m_flags & XFS_MOUNT_RDONLY) + if (!xfs_fs_writable(mp, SB_FREEZE_WRITE)) return 0; - tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_sbchange, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - xfs_alert(mp, "%s: Superblock update failed!", __func__); - return error; - } - - xfs_mod_sb(tp); - return xfs_trans_commit(tp, 0); + return xfs_sync_sb(mp, false); } __uint64_t @@ -678,7 +659,7 @@ xfs_mountfs( xfs_warn(mp, "correcting sb_features alignment problem"); sbp->sb_features2 |= sbp->sb_bad_features2; sbp->sb_bad_features2 = sbp->sb_features2; - mp->m_update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2; + mp->m_update_sb = true; /* * Re-check for ATTR2 in case it was found in bad_features2 @@ -692,17 +673,17 @@ xfs_mountfs( if (xfs_sb_version_hasattr2(&mp->m_sb) && (mp->m_flags & XFS_MOUNT_NOATTR2)) { xfs_sb_version_removeattr2(&mp->m_sb); - mp->m_update_flags |= XFS_SB_FEATURES2; + mp->m_update_sb = true; /* update sb_versionnum for the clearing of the morebits */ if (!sbp->sb_features2) - mp->m_update_flags |= XFS_SB_VERSIONNUM; + mp->m_update_sb = true; } /* always use v2 inodes by default now */ if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) { mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT; - mp->m_update_flags |= XFS_SB_VERSIONNUM; + mp->m_update_sb = true; } /* @@ -895,8 +876,8 @@ xfs_mountfs( * the next remount into writeable mode. Otherwise we would never * perform the update e.g. for the root filesystem. */ - if (mp->m_update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) { - error = xfs_mount_log_sb(mp); + if (mp->m_update_sb && !(mp->m_flags & XFS_MOUNT_RDONLY)) { + error = xfs_sync_sb(mp, false); if (error) { xfs_warn(mp, "failed to write sb changes"); goto out_rtunmount; @@ -1103,9 +1084,6 @@ xfs_fs_writable( int xfs_log_sbcount(xfs_mount_t *mp) { - xfs_trans_t *tp; - int error; - /* allow this to proceed during the freeze sequence... */ if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE)) return 0; @@ -1119,17 +1097,7 @@ xfs_log_sbcount(xfs_mount_t *mp) if (!xfs_sb_version_haslazysbcount(&mp->m_sb)) return 0; - tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - - xfs_mod_sb(tp); - xfs_trans_set_sync(tp); - error = xfs_trans_commit(tp, 0); - return error; + return xfs_sync_sb(mp, true); } /* @@ -1422,28 +1390,6 @@ xfs_freesb( xfs_buf_relse(bp); } -/* - * Used to log changes to the superblock unit and width fields which could - * be altered by the mount options, as well as any potential sb_features2 - * fixup. Only the first superblock is updated. - */ -int -xfs_mount_log_sb( - struct xfs_mount *mp) -{ - struct xfs_trans *tp; - int error; - - tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - xfs_mod_sb(tp); - return xfs_trans_commit(tp, 0); -} - /* * If the underlying (data/log/rt) device is readonly, there are some * operations that cannot proceed. diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 28b341bf1555..a5b2ff822653 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -162,8 +162,7 @@ typedef struct xfs_mount { struct delayed_work m_reclaim_work; /* background inode reclaim */ struct delayed_work m_eofblocks_work; /* background eof blocks trimming */ - __int64_t m_update_flags; /* sb flags we need to update - on the next remount,rw */ + bool m_update_sb; /* sb needs update in mount */ int64_t m_low_space[XFS_LOWSP_MAX]; /* low free space thresholds */ struct xfs_kobj m_kobj; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index c815a8060b59..3e8186279541 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -792,7 +792,7 @@ xfs_qm_qino_alloc( else mp->m_sb.sb_pquotino = (*ip)->i_ino; spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp); + xfs_log_sb(tp); if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES))) { xfs_alert(mp, "%s failed (error %d)!", __func__, error); @@ -1445,7 +1445,7 @@ xfs_qm_mount_quotas( spin_unlock(&mp->m_sb_lock); if (sbf != (mp->m_qflags & XFS_MOUNT_QUOTA_ALL)) { - if (xfs_qm_write_sb_changes(mp)) { + if (xfs_sync_sb(mp, false)) { /* * We could only have been turning quotas off. * We aren't in very good shape actually because @@ -1574,29 +1574,6 @@ xfs_qm_dqfree_one( xfs_qm_dqdestroy(dqp); } -/* - * Start a transaction and write the incore superblock changes to - * disk. flags parameter indicates which fields have changed. - */ -int -xfs_qm_write_sb_changes( - struct xfs_mount *mp) -{ - xfs_trans_t *tp; - int error; - - tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_sbchange, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - - xfs_mod_sb(tp); - return xfs_trans_commit(tp, 0); -} - - /* --------------- utility functions for vnodeops ---------------- */ diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index bddd23fda9ce..d6e4d88094ab 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -157,7 +157,6 @@ struct xfs_dquot_acct { #define XFS_QM_RTBWARNLIMIT 5 extern void xfs_qm_destroy_quotainfo(struct xfs_mount *); -extern int xfs_qm_write_sb_changes(struct xfs_mount *); /* dquot stuff */ extern void xfs_qm_dqpurge_all(struct xfs_mount *, uint); diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 8d7e5f068803..b8a565edb4ae 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -92,7 +92,7 @@ xfs_qm_scall_quotaoff( mutex_unlock(&q->qi_quotaofflock); /* XXX what to do if error ? Revert back to old vals incore ? */ - return xfs_qm_write_sb_changes(mp); + return xfs_sync_sb(mp, false); } dqtype = 0; @@ -369,7 +369,8 @@ xfs_qm_scall_quotaon( if ((qf & flags) == flags) return -EEXIST; - if ((error = xfs_qm_write_sb_changes(mp))) + error = xfs_sync_sb(mp, false); + if (error) return error; /* * If we aren't trying to switch on quota enforcement, we are done. @@ -796,7 +797,7 @@ xfs_qm_log_quotaoff( mp->m_sb.sb_qflags = (mp->m_qflags & ~(flags)) & XFS_MOUNT_QUOTA_ALL; spin_unlock(&mp->m_sb_lock); - xfs_mod_sb(tp); + xfs_log_sb(tp); /* * We have to make sure that the transaction is secure on disk before we diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 6fb298963d1b..a3b791b85336 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1257,13 +1257,13 @@ xfs_fs_remount( * If this is the first remount to writeable state we * might have some superblock changes to update. */ - if (mp->m_update_flags) { - error = xfs_mount_log_sb(mp); + if (mp->m_update_sb) { + error = xfs_sync_sb(mp, false); if (error) { xfs_warn(mp, "failed to write sb changes"); return error; } - mp->m_update_flags = 0; + mp->m_update_sb = false; } /* @@ -1293,8 +1293,9 @@ xfs_fs_remount( /* * Second stage of a freeze. The data is already frozen so we only - * need to take care of the metadata. Once that's done write a dummy - * record to dirty the log in case of a crash while frozen. + * need to take care of the metadata. Once that's done sync the superblock + * to the log to dirty it in case of a crash while frozen. This ensures that we + * will recover the unlinked inode lists on the next mount. */ STATIC int xfs_fs_freeze( @@ -1304,7 +1305,7 @@ xfs_fs_freeze( xfs_save_resvblks(mp); xfs_quiesce_attr(mp); - return xfs_fs_log_dummy(mp); + return xfs_sync_sb(mp, true); } STATIC int -- cgit v1.2.3 From 074e427ba7f7398427e4f8e2aec071edcc509673 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 22 Jan 2015 09:10:33 +1100 Subject: xfs: sanitise sb_bad_features2 handling We currently have to ensure that every time we update sb_features2 that we update sb_bad_features2. Now that we log and format the superblock in it's entirety we actually don't have to care because we can simply update the sb_bad_features2 when we format it into the buffer. This removes the need for anything but the mount and superblock formatting code to care about sb_bad_features2, and hence removes the possibility that we forget to update bad_features2 when necessary in the future. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_format.h | 14 +++++++------- fs/xfs/libxfs/xfs_sb.c | 8 +++++++- fs/xfs/xfs_mount.c | 23 +++++++++++------------ 3 files changed, 25 insertions(+), 20 deletions(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index fbd6da263571..749c86102794 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -151,10 +151,13 @@ typedef struct xfs_sb { __uint32_t sb_features2; /* additional feature bits */ /* - * bad features2 field as a result of failing to pad the sb - * structure to 64 bits. Some machines will be using this field - * for features2 bits. Easiest just to mark it bad and not use - * it for anything else. + * bad features2 field as a result of failing to pad the sb structure to + * 64 bits. Some machines will be using this field for features2 bits. + * Easiest just to mark it bad and not use it for anything else. + * + * This is not kept up to date in memory; it is always overwritten by + * the value in sb_features2 when formatting the incore superblock to + * the disk buffer. */ __uint32_t sb_bad_features2; @@ -453,13 +456,11 @@ static inline void xfs_sb_version_addattr2(struct xfs_sb *sbp) { sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT; sbp->sb_features2 |= XFS_SB_VERSION2_ATTR2BIT; - sbp->sb_bad_features2 |= XFS_SB_VERSION2_ATTR2BIT; } static inline void xfs_sb_version_removeattr2(struct xfs_sb *sbp) { sbp->sb_features2 &= ~XFS_SB_VERSION2_ATTR2BIT; - sbp->sb_bad_features2 &= ~XFS_SB_VERSION2_ATTR2BIT; if (!sbp->sb_features2) sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT; } @@ -475,7 +476,6 @@ static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp) { sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT; sbp->sb_features2 |= XFS_SB_VERSION2_PROJID32BIT; - sbp->sb_bad_features2 |= XFS_SB_VERSION2_PROJID32BIT; } /* diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 63f814872dfb..b0a5fe95a3e2 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -497,7 +497,6 @@ xfs_sb_to_disk( to->sb_fdblocks = cpu_to_be64(from->sb_fdblocks); to->sb_frextents = cpu_to_be64(from->sb_frextents); - to->sb_flags = from->sb_flags; to->sb_shared_vn = from->sb_shared_vn; to->sb_inoalignmt = cpu_to_be32(from->sb_inoalignmt); @@ -507,6 +506,13 @@ xfs_sb_to_disk( to->sb_logsectlog = from->sb_logsectlog; to->sb_logsectsize = cpu_to_be16(from->sb_logsectsize); to->sb_logsunit = cpu_to_be32(from->sb_logsunit); + + /* + * We need to ensure that bad_features2 always matches features2. + * Hence we enforce that here rather than having to remember to do it + * everywhere else that updates features2. + */ + from->sb_bad_features2 = from->sb_features2; to->sb_features2 = cpu_to_be32(from->sb_features2); to->sb_bad_features2 = cpu_to_be32(from->sb_bad_features2); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 5ef9aa2bfa19..4fa80e63eea2 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -640,25 +640,24 @@ xfs_mountfs( xfs_sb_mount_common(mp, sbp); /* - * Check for a mismatched features2 values. Older kernels - * read & wrote into the wrong sb offset for sb_features2 - * on some platforms due to xfs_sb_t not being 64bit size aligned - * when sb_features2 was added, which made older superblock - * reading/writing routines swap it as a 64-bit value. + * Check for a mismatched features2 values. Older kernels read & wrote + * into the wrong sb offset for sb_features2 on some platforms due to + * xfs_sb_t not being 64bit size aligned when sb_features2 was added, + * which made older superblock reading/writing routines swap it as a + * 64-bit value. * * For backwards compatibility, we make both slots equal. * - * If we detect a mismatched field, we OR the set bits into the - * existing features2 field in case it has already been modified; we - * don't want to lose any features. We then update the bad location - * with the ORed value so that older kernels will see any features2 - * flags, and mark the two fields as needing updates once the - * transaction subsystem is online. + * If we detect a mismatched field, we OR the set bits into the existing + * features2 field in case it has already been modified; we don't want + * to lose any features. We then update the bad location with the ORed + * value so that older kernels will see any features2 flags. The + * superblock writeback code ensures the new sb_features2 is copied to + * sb_bad_features2 before it is logged or written to disk. */ if (xfs_sb_has_mismatched_features2(sbp)) { xfs_warn(mp, "correcting sb_features alignment problem"); sbp->sb_features2 |= sbp->sb_bad_features2; - sbp->sb_bad_features2 = sbp->sb_features2; mp->m_update_sb = true; /* -- cgit v1.2.3 From 0d612fb570b71ea2e49554a770cff4c489018b2c Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 22 Jan 2015 09:29:05 +1100 Subject: xfs: ensure buffer types are set correctly Jan Kara reported that log recovery was finding buffers with invalid types in them. This should not happen, and indicates a bug in the logging of buffers. To catch this, add asserts to the buffer formatting code to ensure that the buffer type is in range when the transaction is committed. We don't set a type on buffers being marked stale - they are not going to get replayed, the format item exists only for recovery to be able to prevent replay of the buffer, so the type does not matter. Hence that needs special casing here. cc: # 3.10 to current Reported-by: Jan Kara Tested-by: Jan Kara Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_buf_item.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs') diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 3f9bd58edec7..744352bf3240 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -319,6 +319,10 @@ xfs_buf_item_format( ASSERT(atomic_read(&bip->bli_refcount) > 0); ASSERT((bip->bli_flags & XFS_BLI_LOGGED) || (bip->bli_flags & XFS_BLI_STALE)); + ASSERT((bip->bli_flags & XFS_BLI_STALE) || + (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF + && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF)); + /* * If it is an inode buffer, transfer the in-memory state to the -- cgit v1.2.3 From f19b872b086711bb4b22c3a0f52f16aa920bcc61 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 22 Jan 2015 09:29:40 +1100 Subject: xfs: inode unlink does not set AGI buffer type This leads to log recovery throwing errors like: XFS (md0): Mounting V5 Filesystem XFS (md0): Starting recovery (logdev: internal) XFS (md0): Unknown buffer type 0! XFS (md0): _xfs_buf_ioapply: no ops on block 0xaea8802/0x1 ffff8800ffc53800: 58 41 47 49 ..... Which is the AGI buffer magic number. Ensure that we set the type appropriately in both unlink list addition and removal. cc: # 3.10 to current Tested-by: Jan Kara Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_inode.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 41f804e740d7..d745e1a9bf2e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1995,6 +1995,7 @@ xfs_iunlink( agi->agi_unlinked[bucket_index] = cpu_to_be32(agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); return 0; @@ -2086,6 +2087,7 @@ xfs_iunlink_remove( agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket_index); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); } else { -- cgit v1.2.3 From fe22d552b82d7cc7de1851233ae8bef579198637 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 22 Jan 2015 09:30:06 +1100 Subject: xfs: set buf types when converting extent formats Conversion from local to extent format does not set the buffer type correctly on the new extent buffer when a symlink data is moved out of line. Fix the symlink code and leave a comment in the generic bmap code reminding us that the format-specific data copy needs to set the destination buffer type appropriately. cc: # 3.10 to current Tested-by: Jan Kara Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 6 +++++- fs/xfs/libxfs/xfs_symlink_remote.c | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index b5eb4743f75a..4e20fe7497b3 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -973,7 +973,11 @@ xfs_bmap_local_to_extents( *firstblock = args.fsbno; bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0); - /* initialise the block and copy the data */ + /* + * Initialise the block and copy the data + * + * Note: init_fn must set the buffer log item type correctly! + */ init_fn(tp, bp, ip, ifp); /* account for the change in fork size and log everything */ diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index c80c5236c3da..e7e26bd6468f 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -178,6 +178,8 @@ xfs_symlink_local_to_remote( struct xfs_mount *mp = ip->i_mount; char *buf; + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF); + if (!xfs_sb_version_hascrc(&mp->m_sb)) { bp->b_ops = NULL; memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes); -- cgit v1.2.3 From 3443a3bca54588f43286b725d8648d33a38c86f1 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 22 Jan 2015 09:30:23 +1100 Subject: xfs: set superblock buffer type correctly When the superblock is modified in a transaction, the commonly modified fields are not actually copied to the superblock buffer to avoid the buffer lock becoming a serialisation point. However, there are some other operations that modify the superblock fields within the transaction that don't directly log to the superblock but rely on the changes to be applied during the transaction commit (to minimise the buffer lock hold time). When we do this, we fail to mark the buffer log item as being a superblock buffer and that can lead to the buffer not being marked with the corect type in the log and hence causing recovery issues. Fix it by setting the type correctly, similar to xfs_mod_sb()... cc: # 3.10 to current Tested-by: Jan Kara Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_trans.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index fa3135b9bf04..eb90cd59a0ec 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -472,6 +472,7 @@ xfs_trans_apply_sb_deltas( whole = 1; } + xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF); if (whole) /* * Log the whole thing, the fields are noncontiguous. -- cgit v1.2.3 From 4d949021aac8b63c9c3b8a83cc8a29759c7e1d5e Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Thu, 22 Jan 2015 10:04:24 +1100 Subject: xfs: remove incorrect error negation in attr_multi ioctl xfs_compat_attrmulti_by_handle() calls memdup_user() which returns a negative error code. The error code is negated by the caller and thus incorrectly converted to a positive error code. Remove the error negation such that the negative error is passed correctly back up to userspace. Signed-off-by: Brian Foster Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index ec6772866f3d..bfc7c7c8a0c8 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -423,7 +423,7 @@ xfs_compat_attrmulti_by_handle( ops = memdup_user(compat_ptr(am_hreq.ops), size); if (IS_ERR(ops)) { - error = -PTR_ERR(ops); + error = PTR_ERR(ops); goto out_dput; } -- cgit v1.2.3 From 8116bf4cb62d337c953cfa5369ef4cf83e73140c Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 21 Jan 2015 20:44:01 -0500 Subject: locks: update comments that refer to inode->i_flock Signed-off-by: Jeff Layton --- fs/locks.c | 2 +- include/linux/fs.h | 19 ++++++++++--------- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/locks.c b/fs/locks.c index 2fc36b3772a0..4d0d41163a50 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2212,7 +2212,7 @@ again: */ /* * we need that spin_lock here - it prevents reordering between - * update of inode->i_flock and check for it done in close(). + * update of i_flctx->flc_posix and check for it done in close(). * rcu_read_lock() wouldn't do. */ spin_lock(¤t->files->file_lock); diff --git a/include/linux/fs.h b/include/linux/fs.h index f87cb2f03103..ddd2fa7cefd3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -925,12 +925,11 @@ int locks_in_grace(struct net *); * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * - * The i_flock list is ordered by: + * The varous i_flctx lists are ordered by: * - * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX - * 2) lock owner - * 3) lock range start - * 4) lock range end + * 1) lock owner + * 2) lock range start + * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ @@ -1992,8 +1991,9 @@ static inline int break_lease(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking inode->i_flock. Otherwise, we could - * end up racing with tasks trying to set a new lease on this file. + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) @@ -2005,8 +2005,9 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking inode->i_flock. Otherwise, we could - * end up racing with tasks trying to set a new lease on this file. + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) -- cgit v1.2.3 From b520252aa287b14e1f39a51e20051775b273b82a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 Jan 2015 08:13:17 -0700 Subject: fs: make inode_to_bdi() handle NULL inode Running a heavy fs workload, I ran into a situation where we pass down a page for writeback/swap that doesn't have an inode mapping: BUG: unable to handle kernel NULL pointer dereference at 0000000000000028 IP: [] inode_to_bdi+0xf/0x50 PGD 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: wl(O) tun cfg80211 btusb joydev hid_apple hid_generic usbhid hid bcm5974 usb_storage nouveau snd_hda_codec_hdmi snd_hda_codec_cirrus snd_hda_codec_generic x86_pkg_temp_thermal snd_hda_intel kvm_intel snd_hda_controller snd_hda_codec kvm snd_hwdep snd_pcm applesmc input_polldev snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq snd_timer snd_seq_device snd xhci_pci xhci_hcd ttm thunderbolt soundcore apple_gmux apple_bl bluetooth binfmt_misc fuse nls_iso8859_1 nls_cp437 vfat fat [last unloaded: wl] CPU: 4 PID: 50 Comm: kswapd0 Tainted: G U O 3.19.0-rc5+ #60 Hardware name: Apple Inc. MacBookPro11,3/Mac-2BD1B31983FE1663, BIOS MBP112.88Z.0138.B02.1310181745 10/18/2013 task: ffff880462e917f0 ti: ffff880462edc000 task.ti: ffff880462edc000 RIP: 0010:[] [] inode_to_bdi+0xf/0x50 RSP: 0000:ffff880462edf8e8 EFLAGS: 00010282 RAX: ffffffff81c4cd80 RBX: ffffea0001b3abc0 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff880462edf8f8 R08: 00000000001e8500 R09: ffff880460f7cb68 R10: ffff880462edfa00 R11: 0000000000000101 R12: 0000000000000000 R13: ffffffff81c4cd98 R14: 0000000000000000 R15: ffff880460f7c9c0 FS: 0000000000000000(0000) GS:ffff88047f300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000028 CR3: 00000002b6341000 CR4: 00000000001407e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: ffffea0001b3abc0 ffffffff81c4cd80 ffff880462edf948 ffffffff811244aa ffffffff811565b0 ffff880460f7c9c0 ffff880462edf948 ffffea0001b3abc0 0000000000000001 ffff880462edfb40 ffff880008b999c0 ffff880460f7c9c0 Call Trace: [] __test_set_page_writeback+0x3a/0x170 [] ? SyS_madvise+0x790/0x790 [] __swap_writepage+0x216/0x280 [] ? radix_tree_insert+0x32/0xe0 [] ? swap_info_get+0x61/0xf0 [] ? page_swapcount+0x4c/0x60 [] swap_writepage+0x2d/0x50 [] shmem_writepage+0x198/0x2c0 [] shrink_page_list+0x464/0xa00 [] shrink_inactive_list+0x266/0x500 [] shrink_lruvec+0x5d5/0x720 [] shrink_zone+0x5b/0x190 [] kswapd+0x48f/0x8d0 [] ? try_to_free_pages+0x4c0/0x4c0 [] kthread+0xd2/0xf0 [] ? workqueue_congested+0x30/0x80 [] ? kthread_create_on_node+0x180/0x180 [] ret_from_fork+0x7c/0xb0 [] ? kthread_create_on_node+0x180/0x180 Code: 00 48 c7 c7 8d 8d a4 81 e8 3f 62 eb ff e9 fc fe ff ff 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 54 49 89 fc 53 <48> 8b 5f 28 48 89 df e8 15 f8 00 00 85 c0 75 11 48 8b 83 d8 00 RIP [] inode_to_bdi+0xf/0x50 RSP CR2: 0000000000000028 ---[ end trace eb0e21aa7dad3ddf ]--- Handle this in inode_to_bdi() by punting it to noop_backing_dev_info, if mapping->host is NULL. Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index a20b1145f4d5..c399152de397 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -68,7 +68,12 @@ EXPORT_SYMBOL(writeback_in_progress); struct backing_dev_info *inode_to_bdi(struct inode *inode) { - struct super_block *sb = inode->i_sb; + struct super_block *sb; + + if (!inode) + return &noop_backing_dev_info; + + sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) return blk_get_backing_dev_info(I_BDEV(inode)); -- cgit v1.2.3 From bbc7f33ac6ff6f48709ce892aa906ddb68b34517 Mon Sep 17 00:00:00 2001 From: J. Bruce Fields Date: Tue, 20 Jan 2015 11:51:26 -0500 Subject: nfsd: fix year-2038 nfs4 state problem Someone with a weird time_t happened to notice this, it shouldn't really manifest till 2038. It may not be our ownly year-2038 problem. Reported-by: Aaron Pace Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f924f0618cb5..1f4b85b15125 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1508,7 +1508,12 @@ unhash_session(struct nfsd4_session *ses) static int STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) { - if (clid->cl_boot == nn->boot_time) + /* + * We're assuming the clid was not given out from a boot + * precisely 2^32 (about 136 years) before this one. That seems + * a safe assumption: + */ + if (clid->cl_boot == (u32)nn->boot_time) return 0; dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n", clid->cl_boot, clid->cl_id, nn->boot_time); -- cgit v1.2.3 From 3c5199143bc4b35f472c5c2534026d74821e2044 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 22 Jan 2015 08:19:32 -0500 Subject: sunrpc/lockd: fix references to the BKL The BKL is completely out of the picture in the lockd and sunrpc code these days. Update the antiquated comments that refer to it. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- fs/lockd/svclock.c | 4 ++-- include/linux/sunrpc/svc.h | 2 +- net/sunrpc/svc.c | 4 ++-- net/sunrpc/svc_xprt.c | 3 +-- 4 files changed, 6 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 56598742dde4..5581e020644b 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -57,8 +57,8 @@ static DEFINE_SPINLOCK(nlm_blocked_lock); static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie) { /* - * We can get away with a static buffer because we're only - * called with BKL held. + * We can get away with a static buffer because this is only called + * from lockd, which is single-threaded. */ static char buf[2*NLM_MAXCOOKIELEN+1]; unsigned int i, len = sizeof(buf); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6f22cfeef5e3..fae6fb947fc8 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -110,7 +110,7 @@ struct svc_serv { * We use sv_nrthreads as a reference count. svc_destroy() drops * this refcount, so we need to bump it up around operations that * change the number of threads. Horrible, but there it is. - * Should be called with the BKL held. + * Should be called with the "service mutex" held. */ static inline void svc_get(struct svc_serv *serv) { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 91eaef1844c8..78974e4d9ad2 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -768,8 +768,8 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) EXPORT_SYMBOL_GPL(svc_set_num_threads); /* - * Called from a server thread as it's exiting. Caller must hold the BKL or - * the "service mutex", whichever is appropriate for the service. + * Called from a server thread as it's exiting. Caller must hold the "service + * mutex" for the service. */ void svc_exit_thread(struct svc_rqst *rqstp) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index c69358b3cf7f..163ac45c3639 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -42,7 +42,7 @@ static LIST_HEAD(svc_xprt_class_list); * svc_pool->sp_lock protects most of the fields of that pool. * svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt. * when both need to be taken (rare), svc_serv->sv_lock is first. - * BKL protects svc_serv->sv_nrthread. + * The "service mutex" protects svc_serv->sv_nrthread. * svc_sock->sk_lock protects the svc_sock->sk_deferred list * and the ->sk_info_authunix cache. * @@ -67,7 +67,6 @@ static LIST_HEAD(svc_xprt_class_list); * that no other thread will be using the transport or will * try to set XPT_DEAD. */ - int svc_reg_xprt_class(struct svc_xprt_class *xcl) { struct svc_xprt_class *cl; -- cgit v1.2.3 From 4c94e13e9caed09103419c087f436d79f9d2faba Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 22 Jan 2015 12:09:50 +0100 Subject: nfsd: factor out a helper to decode nfstime4 values Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4xdr.c | 43 ++++++++++++++++++++++++++----------------- 1 file changed, 26 insertions(+), 17 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 91f7a3644ffb..974533e5a427 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -234,6 +234,26 @@ static char *savemem(struct nfsd4_compoundargs *argp, __be32 *p, int nbytes) return ret; } +/* + * We require the high 32 bits of 'seconds' to be 0, and + * we ignore all 32 bits of 'nseconds'. + */ +static __be32 +nfsd4_decode_time(struct nfsd4_compoundargs *argp, struct timespec *tv) +{ + DECODE_HEAD; + u64 sec; + + READ_BUF(12); + p = xdr_decode_hyper(p, &sec); + tv->tv_sec = sec; + tv->tv_nsec = be32_to_cpup(p++); + if (tv->tv_nsec >= (u32)1000000000) + return nfserr_inval; + + DECODE_TAIL; +} + static __be32 nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval) { @@ -267,7 +287,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, { int expected_len, len = 0; u32 dummy32; - u64 sec; char *buf; DECODE_HEAD; @@ -358,15 +377,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, dummy32 = be32_to_cpup(p++); switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: - /* We require the high 32 bits of 'seconds' to be 0, and we ignore - all 32 bits of 'nseconds'. */ - READ_BUF(12); len += 12; - p = xdr_decode_hyper(p, &sec); - iattr->ia_atime.tv_sec = (time_t)sec; - iattr->ia_atime.tv_nsec = be32_to_cpup(p++); - if (iattr->ia_atime.tv_nsec >= (u32)1000000000) - return nfserr_inval; + status = nfsd4_decode_time(argp, &iattr->ia_atime); + if (status) + return status; iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); break; case NFS4_SET_TO_SERVER_TIME: @@ -382,15 +396,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, dummy32 = be32_to_cpup(p++); switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: - /* We require the high 32 bits of 'seconds' to be 0, and we ignore - all 32 bits of 'nseconds'. */ - READ_BUF(12); len += 12; - p = xdr_decode_hyper(p, &sec); - iattr->ia_mtime.tv_sec = sec; - iattr->ia_mtime.tv_nsec = be32_to_cpup(p++); - if (iattr->ia_mtime.tv_nsec >= (u32)1000000000) - return nfserr_inval; + status = nfsd4_decode_time(argp, &iattr->ia_mtime); + if (status) + return status; iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); break; case NFS4_SET_TO_SERVER_TIME: -- cgit v1.2.3 From 45094a58b1f56fd5942545659f7c1829ae4520eb Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Thu, 22 Jan 2015 11:11:55 -0500 Subject: GFS2: Eliminate a nonsense goto This patch just removes a goto that did nothing. Signed-off-by: Bob Peterson Signed-off-by: Steven Whitehouse --- fs/gfs2/inode.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'fs') diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 9054002ebe70..73c72253faac 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -543,10 +543,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, } error = gfs2_dir_add(&dip->i_inode, name, ip, da); - if (error) - goto fail_end_trans; -fail_end_trans: gfs2_trans_end(sdp); fail_ipreserv: gfs2_inplace_release(dip); -- cgit v1.2.3 From 7a1ceba071709d11271ebd921310b5a18404dd33 Mon Sep 17 00:00:00 2001 From: Niklas Cassel Date: Thu, 22 Jan 2015 14:16:34 +0100 Subject: cifs: fix MUST SecurityFlags filtering If CONFIG_CIFS_WEAK_PW_HASH is not set, CIFSSEC_MUST_LANMAN and CIFSSEC_MUST_PLNTXT is defined as 0. When setting new SecurityFlags without any MUST flags, your flags would be overwritten with CIFSSEC_MUST_LANMAN (0). Signed-off-by: Niklas Cassel Signed-off-by: Steve French --- fs/cifs/cifs_debug.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 9c56ef776407..7febcf2475c5 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -606,9 +606,11 @@ cifs_security_flags_handle_must_flags(unsigned int *flags) *flags = CIFSSEC_MUST_NTLMV2; else if ((*flags & CIFSSEC_MUST_NTLM) == CIFSSEC_MUST_NTLM) *flags = CIFSSEC_MUST_NTLM; - else if ((*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN) + else if (CIFSSEC_MUST_LANMAN && + (*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN) *flags = CIFSSEC_MUST_LANMAN; - else if ((*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT) + else if (CIFSSEC_MUST_PLNTXT && + (*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT) *flags = CIFSSEC_MUST_PLNTXT; *flags |= signflags; -- cgit v1.2.3 From 063c54dccdecb0479662778ddf54ee45aa55423d Mon Sep 17 00:00:00 2001 From: Gui Hecheng Date: Fri, 9 Jan 2015 09:39:40 +0800 Subject: btrfs: fix raid56 scrub failed in xfstests btrfs/072 The xfstests btrfs/072 reports uncorrectable read errors in dmesg, because scrub forgets to use commit_root for parity scrub routine and scrub attempts to scrub those extents items whose contents are not fully on disk. To fix it, we just add the @search_commit_root flag back. Signed-off-by: Gui Hecheng Signed-off-by: Qu Wenruo Reviewed-by: Miao Xie Signed-off-by: Chris Mason --- fs/btrfs/scrub.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 2f0fbc374e87..e427cb7ee12c 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3065,6 +3065,8 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, path->search_commit_root = 1; path->skip_locking = 1; + ppath->search_commit_root = 1; + ppath->skip_locking = 1; /* * trigger the readahead for extent tree csum tree and wait for * completion. During readahead, the scrub is officially paused -- cgit v1.2.3 From b07ef35244424cbeda9844198607c7077099c82c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 28 Jan 2015 08:38:20 +0100 Subject: udf: Release preallocation on last writeable close Commit 6fb1ca92a640 "udf: Fix race between write(2) and close(2)" changed the condition when preallocation is released. The idea was that we don't want to release the preallocation for an inode on close when there are other writeable file descriptors for the inode. However the condition was written in the opposite way so we released preallocation only if there were other writeable file descriptors. Fix the problem by changing the condition properly. CC: stable@vger.kernel.org Fixes: 6fb1ca92a6409a9d5b0696447cd4997bc9aaf5a2 Reported-by: Fabian Frederick Signed-off-by: Jan Kara --- fs/udf/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/udf/file.c b/fs/udf/file.c index bb15771b92ae..08f3555fbeac 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -224,7 +224,7 @@ out: static int udf_release_file(struct inode *inode, struct file *filp) { if (filp->f_mode & FMODE_WRITE && - atomic_read(&inode->i_writecount) > 1) { + atomic_read(&inode->i_writecount) == 1) { /* * Grab i_mutex to avoid races with writes changing i_size * while we are running. -- cgit v1.2.3 From 14bf61ffe6ac54afcd1e888a4407fe16054483db Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 9 Oct 2014 16:03:13 +0200 Subject: quota: Switch ->get_dqblk() and ->set_dqblk() to use bytes as space units Currently ->get_dqblk() and ->set_dqblk() use struct fs_disk_quota which tracks space limits and usage in 512-byte blocks. However VFS quotas track usage in bytes (as some filesystems require that) and we need to somehow pass this information. Upto now it wasn't a problem because we didn't do any unit conversion (thus VFS quota routines happily stuck number of bytes into d_bcount field of struct fd_disk_quota). Only if you tried to use Q_XGETQUOTA or Q_XSETQLIM for VFS quotas (or Q_GETQUOTA / Q_SETQUOTA for XFS quotas), you got bogus results. Hardly anyone tried this but reportedly some Samba users hit the problem in practice. So when we want interfaces compatible we need to fix this. We bite the bullet and define another quota structure used for passing information from/to ->get_dqblk()/->set_dqblk. It's somewhat sad we have to have more conversion routines in fs/quota/quota.c and another copying of quota structure slows down getting of quota information by about 2% but it seems cleaner than overloading e.g. units of d_bcount to bytes. CC: stable@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/gfs2/quota.c | 49 +++++++------- fs/quota/dquot.c | 83 ++++++++++++------------ fs/quota/quota.c | 162 +++++++++++++++++++++++++++++++++++++++-------- fs/xfs/xfs_qm.h | 4 +- fs/xfs/xfs_qm_syscalls.c | 156 +++++++++++++++++++-------------------------- fs/xfs/xfs_quotaops.c | 8 +-- include/linux/quota.h | 47 +++++++++++++- include/linux/quotaops.h | 4 +- 8 files changed, 318 insertions(+), 195 deletions(-) (limited to 'fs') diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index c8b148bbdc8b..3e193cb36996 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -667,7 +667,7 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change) static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, s64 change, struct gfs2_quota_data *qd, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct inode *inode = &ip->i_inode; struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -697,16 +697,16 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, be64_add_cpu(&q.qu_value, change); qd->qd_qb.qb_value = q.qu_value; if (fdq) { - if (fdq->d_fieldmask & FS_DQ_BSOFT) { - q.qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPC_SOFT) { + q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_warn = q.qu_warn; } - if (fdq->d_fieldmask & FS_DQ_BHARD) { - q.qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPC_HARD) { + q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_limit = q.qu_limit; } - if (fdq->d_fieldmask & FS_DQ_BCOUNT) { - q.qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift); + if (fdq->d_fieldmask & QC_SPACE) { + q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift); qd->qd_qb.qb_value = q.qu_value; } } @@ -1497,7 +1497,7 @@ static int gfs2_quota_get_xstate(struct super_block *sb, } static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_quota_lvb *qlvb; @@ -1505,7 +1505,7 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, struct gfs2_holder q_gh; int error; - memset(fdq, 0, sizeof(struct fs_disk_quota)); + memset(fdq, 0, sizeof(*fdq)); if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return -ESRCH; /* Crazy XFS error code */ @@ -1522,12 +1522,9 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid, goto out; qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr; - fdq->d_version = FS_DQUOT_VERSION; - fdq->d_flags = (qid.type == USRQUOTA) ? FS_USER_QUOTA : FS_GROUP_QUOTA; - fdq->d_id = from_kqid_munged(current_user_ns(), qid); - fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift; - fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift; - fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift; + fdq->d_spc_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_sb.sb_bsize_shift; + fdq->d_spc_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_sb.sb_bsize_shift; + fdq->d_space = be64_to_cpu(qlvb->qb_value) << sdp->sd_sb.sb_bsize_shift; gfs2_glock_dq_uninit(&q_gh); out: @@ -1536,10 +1533,10 @@ out: } /* GFS2 only supports a subset of the XFS fields */ -#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT) +#define GFS2_FIELDMASK (QC_SPC_SOFT|QC_SPC_HARD|QC_SPACE) static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *fdq) { struct gfs2_sbd *sdp = sb->s_fs_info; struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode); @@ -1583,17 +1580,17 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid, goto out_i; /* If nothing has changed, this is a no-op */ - if ((fdq->d_fieldmask & FS_DQ_BSOFT) && - ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) - fdq->d_fieldmask ^= FS_DQ_BSOFT; + if ((fdq->d_fieldmask & QC_SPC_SOFT) && + ((fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) + fdq->d_fieldmask ^= QC_SPC_SOFT; - if ((fdq->d_fieldmask & FS_DQ_BHARD) && - ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) - fdq->d_fieldmask ^= FS_DQ_BHARD; + if ((fdq->d_fieldmask & QC_SPC_HARD) && + ((fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) + fdq->d_fieldmask ^= QC_SPC_HARD; - if ((fdq->d_fieldmask & FS_DQ_BCOUNT) && - ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value))) - fdq->d_fieldmask ^= FS_DQ_BCOUNT; + if ((fdq->d_fieldmask & QC_SPACE) && + ((fdq->d_space >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_value))) + fdq->d_fieldmask ^= QC_SPACE; if (fdq->d_fieldmask == 0) goto out_i; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 8f0acef3d184..69df5b239844 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2396,30 +2396,25 @@ static inline qsize_t stoqb(qsize_t space) } /* Generic routine for getting common part of quota structure */ -static void do_get_dqblk(struct dquot *dquot, struct fs_disk_quota *di) +static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; memset(di, 0, sizeof(*di)); - di->d_version = FS_DQUOT_VERSION; - di->d_flags = dquot->dq_id.type == USRQUOTA ? - FS_USER_QUOTA : FS_GROUP_QUOTA; - di->d_id = from_kqid_munged(current_user_ns(), dquot->dq_id); - spin_lock(&dq_data_lock); - di->d_blk_hardlimit = stoqb(dm->dqb_bhardlimit); - di->d_blk_softlimit = stoqb(dm->dqb_bsoftlimit); + di->d_spc_hardlimit = dm->dqb_bhardlimit; + di->d_spc_softlimit = dm->dqb_bsoftlimit; di->d_ino_hardlimit = dm->dqb_ihardlimit; di->d_ino_softlimit = dm->dqb_isoftlimit; - di->d_bcount = dm->dqb_curspace + dm->dqb_rsvspace; - di->d_icount = dm->dqb_curinodes; - di->d_btimer = dm->dqb_btime; - di->d_itimer = dm->dqb_itime; + di->d_space = dm->dqb_curspace + dm->dqb_rsvspace; + di->d_ino_count = dm->dqb_curinodes; + di->d_spc_timer = dm->dqb_btime; + di->d_ino_timer = dm->dqb_itime; spin_unlock(&dq_data_lock); } int dquot_get_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *di) + struct qc_dqblk *di) { struct dquot *dquot; @@ -2433,70 +2428,70 @@ int dquot_get_dqblk(struct super_block *sb, struct kqid qid, } EXPORT_SYMBOL(dquot_get_dqblk); -#define VFS_FS_DQ_MASK \ - (FS_DQ_BCOUNT | FS_DQ_BSOFT | FS_DQ_BHARD | \ - FS_DQ_ICOUNT | FS_DQ_ISOFT | FS_DQ_IHARD | \ - FS_DQ_BTIMER | FS_DQ_ITIMER) +#define VFS_QC_MASK \ + (QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \ + QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \ + QC_SPC_TIMER | QC_INO_TIMER) /* Generic routine for setting common part of quota structure */ -static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) +static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; int check_blim = 0, check_ilim = 0; struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; - if (di->d_fieldmask & ~VFS_FS_DQ_MASK) + if (di->d_fieldmask & ~VFS_QC_MASK) return -EINVAL; - if (((di->d_fieldmask & FS_DQ_BSOFT) && - (di->d_blk_softlimit > dqi->dqi_maxblimit)) || - ((di->d_fieldmask & FS_DQ_BHARD) && - (di->d_blk_hardlimit > dqi->dqi_maxblimit)) || - ((di->d_fieldmask & FS_DQ_ISOFT) && + if (((di->d_fieldmask & QC_SPC_SOFT) && + stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) || + ((di->d_fieldmask & QC_SPC_HARD) && + stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) || + ((di->d_fieldmask & QC_INO_SOFT) && (di->d_ino_softlimit > dqi->dqi_maxilimit)) || - ((di->d_fieldmask & FS_DQ_IHARD) && + ((di->d_fieldmask & QC_INO_HARD) && (di->d_ino_hardlimit > dqi->dqi_maxilimit))) return -ERANGE; spin_lock(&dq_data_lock); - if (di->d_fieldmask & FS_DQ_BCOUNT) { - dm->dqb_curspace = di->d_bcount - dm->dqb_rsvspace; + if (di->d_fieldmask & QC_SPACE) { + dm->dqb_curspace = di->d_space - dm->dqb_rsvspace; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_BSOFT) - dm->dqb_bsoftlimit = qbtos(di->d_blk_softlimit); - if (di->d_fieldmask & FS_DQ_BHARD) - dm->dqb_bhardlimit = qbtos(di->d_blk_hardlimit); - if (di->d_fieldmask & (FS_DQ_BSOFT | FS_DQ_BHARD)) { + if (di->d_fieldmask & QC_SPC_SOFT) + dm->dqb_bsoftlimit = di->d_spc_softlimit; + if (di->d_fieldmask & QC_SPC_HARD) + dm->dqb_bhardlimit = di->d_spc_hardlimit; + if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) { check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ICOUNT) { - dm->dqb_curinodes = di->d_icount; + if (di->d_fieldmask & QC_INO_COUNT) { + dm->dqb_curinodes = di->d_ino_count; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ISOFT) + if (di->d_fieldmask & QC_INO_SOFT) dm->dqb_isoftlimit = di->d_ino_softlimit; - if (di->d_fieldmask & FS_DQ_IHARD) + if (di->d_fieldmask & QC_INO_HARD) dm->dqb_ihardlimit = di->d_ino_hardlimit; - if (di->d_fieldmask & (FS_DQ_ISOFT | FS_DQ_IHARD)) { + if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) { check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_BTIMER) { - dm->dqb_btime = di->d_btimer; + if (di->d_fieldmask & QC_SPC_TIMER) { + dm->dqb_btime = di->d_spc_timer; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags); } - if (di->d_fieldmask & FS_DQ_ITIMER) { - dm->dqb_itime = di->d_itimer; + if (di->d_fieldmask & QC_INO_TIMER) { + dm->dqb_itime = di->d_ino_timer; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags); } @@ -2506,7 +2501,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) dm->dqb_curspace < dm->dqb_bsoftlimit) { dm->dqb_btime = 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); - } else if (!(di->d_fieldmask & FS_DQ_BTIMER)) + } else if (!(di->d_fieldmask & QC_SPC_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_btime = get_seconds() + dqi->dqi_bgrace; } @@ -2515,7 +2510,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) dm->dqb_curinodes < dm->dqb_isoftlimit) { dm->dqb_itime = 0; clear_bit(DQ_INODES_B, &dquot->dq_flags); - } else if (!(di->d_fieldmask & FS_DQ_ITIMER)) + } else if (!(di->d_fieldmask & QC_INO_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_itime = get_seconds() + dqi->dqi_igrace; } @@ -2531,7 +2526,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di) } int dquot_set_dqblk(struct super_block *sb, struct kqid qid, - struct fs_disk_quota *di) + struct qc_dqblk *di) { struct dquot *dquot; int rc; diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 2aa4151f99d2..6f3856328eea 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -118,17 +118,27 @@ static int quota_setinfo(struct super_block *sb, int type, void __user *addr) return sb->s_qcop->set_info(sb, type, &info); } -static void copy_to_if_dqblk(struct if_dqblk *dst, struct fs_disk_quota *src) +static inline qsize_t qbtos(qsize_t blocks) +{ + return blocks << QIF_DQBLKSIZE_BITS; +} + +static inline qsize_t stoqb(qsize_t space) +{ + return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; +} + +static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src) { memset(dst, 0, sizeof(*dst)); - dst->dqb_bhardlimit = src->d_blk_hardlimit; - dst->dqb_bsoftlimit = src->d_blk_softlimit; - dst->dqb_curspace = src->d_bcount; + dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit); + dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit); + dst->dqb_curspace = src->d_space; dst->dqb_ihardlimit = src->d_ino_hardlimit; dst->dqb_isoftlimit = src->d_ino_softlimit; - dst->dqb_curinodes = src->d_icount; - dst->dqb_btime = src->d_btimer; - dst->dqb_itime = src->d_itimer; + dst->dqb_curinodes = src->d_ino_count; + dst->dqb_btime = src->d_spc_timer; + dst->dqb_itime = src->d_ino_timer; dst->dqb_valid = QIF_ALL; } @@ -136,7 +146,7 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct kqid qid; - struct fs_disk_quota fdq; + struct qc_dqblk fdq; struct if_dqblk idq; int ret; @@ -154,36 +164,36 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id, return 0; } -static void copy_from_if_dqblk(struct fs_disk_quota *dst, struct if_dqblk *src) +static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src) { - dst->d_blk_hardlimit = src->dqb_bhardlimit; - dst->d_blk_softlimit = src->dqb_bsoftlimit; - dst->d_bcount = src->dqb_curspace; + dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit); + dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit); + dst->d_space = src->dqb_curspace; dst->d_ino_hardlimit = src->dqb_ihardlimit; dst->d_ino_softlimit = src->dqb_isoftlimit; - dst->d_icount = src->dqb_curinodes; - dst->d_btimer = src->dqb_btime; - dst->d_itimer = src->dqb_itime; + dst->d_ino_count = src->dqb_curinodes; + dst->d_spc_timer = src->dqb_btime; + dst->d_ino_timer = src->dqb_itime; dst->d_fieldmask = 0; if (src->dqb_valid & QIF_BLIMITS) - dst->d_fieldmask |= FS_DQ_BSOFT | FS_DQ_BHARD; + dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD; if (src->dqb_valid & QIF_SPACE) - dst->d_fieldmask |= FS_DQ_BCOUNT; + dst->d_fieldmask |= QC_SPACE; if (src->dqb_valid & QIF_ILIMITS) - dst->d_fieldmask |= FS_DQ_ISOFT | FS_DQ_IHARD; + dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD; if (src->dqb_valid & QIF_INODES) - dst->d_fieldmask |= FS_DQ_ICOUNT; + dst->d_fieldmask |= QC_INO_COUNT; if (src->dqb_valid & QIF_BTIME) - dst->d_fieldmask |= FS_DQ_BTIMER; + dst->d_fieldmask |= QC_SPC_TIMER; if (src->dqb_valid & QIF_ITIME) - dst->d_fieldmask |= FS_DQ_ITIMER; + dst->d_fieldmask |= QC_INO_TIMER; } static int quota_setquota(struct super_block *sb, int type, qid_t id, void __user *addr) { - struct fs_disk_quota fdq; + struct qc_dqblk fdq; struct if_dqblk idq; struct kqid qid; @@ -247,10 +257,78 @@ static int quota_getxstatev(struct super_block *sb, void __user *addr) return ret; } +/* + * XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them + * out of there as xfsprogs rely on definitions being in that header file. So + * just define same functions here for quota purposes. + */ +#define XFS_BB_SHIFT 9 + +static inline u64 quota_bbtob(u64 blocks) +{ + return blocks << XFS_BB_SHIFT; +} + +static inline u64 quota_btobb(u64 bytes) +{ + return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT; +} + +static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src) +{ + dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit); + dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit); + dst->d_ino_hardlimit = src->d_ino_hardlimit; + dst->d_ino_softlimit = src->d_ino_softlimit; + dst->d_space = quota_bbtob(src->d_bcount); + dst->d_ino_count = src->d_icount; + dst->d_ino_timer = src->d_itimer; + dst->d_spc_timer = src->d_btimer; + dst->d_ino_warns = src->d_iwarns; + dst->d_spc_warns = src->d_bwarns; + dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit); + dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit); + dst->d_rt_space = quota_bbtob(src->d_rtbcount); + dst->d_rt_spc_timer = src->d_rtbtimer; + dst->d_rt_spc_warns = src->d_rtbwarns; + dst->d_fieldmask = 0; + if (src->d_fieldmask & FS_DQ_ISOFT) + dst->d_fieldmask |= QC_INO_SOFT; + if (src->d_fieldmask & FS_DQ_IHARD) + dst->d_fieldmask |= QC_INO_HARD; + if (src->d_fieldmask & FS_DQ_BSOFT) + dst->d_fieldmask |= QC_SPC_SOFT; + if (src->d_fieldmask & FS_DQ_BHARD) + dst->d_fieldmask |= QC_SPC_HARD; + if (src->d_fieldmask & FS_DQ_RTBSOFT) + dst->d_fieldmask |= QC_RT_SPC_SOFT; + if (src->d_fieldmask & FS_DQ_RTBHARD) + dst->d_fieldmask |= QC_RT_SPC_HARD; + if (src->d_fieldmask & FS_DQ_BTIMER) + dst->d_fieldmask |= QC_SPC_TIMER; + if (src->d_fieldmask & FS_DQ_ITIMER) + dst->d_fieldmask |= QC_INO_TIMER; + if (src->d_fieldmask & FS_DQ_RTBTIMER) + dst->d_fieldmask |= QC_RT_SPC_TIMER; + if (src->d_fieldmask & FS_DQ_BWARNS) + dst->d_fieldmask |= QC_SPC_WARNS; + if (src->d_fieldmask & FS_DQ_IWARNS) + dst->d_fieldmask |= QC_INO_WARNS; + if (src->d_fieldmask & FS_DQ_RTBWARNS) + dst->d_fieldmask |= QC_RT_SPC_WARNS; + if (src->d_fieldmask & FS_DQ_BCOUNT) + dst->d_fieldmask |= QC_SPACE; + if (src->d_fieldmask & FS_DQ_ICOUNT) + dst->d_fieldmask |= QC_INO_COUNT; + if (src->d_fieldmask & FS_DQ_RTBCOUNT) + dst->d_fieldmask |= QC_RT_SPACE; +} + static int quota_setxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; + struct qc_dqblk qdq; struct kqid qid; if (copy_from_user(&fdq, addr, sizeof(fdq))) @@ -260,13 +338,44 @@ static int quota_setxquota(struct super_block *sb, int type, qid_t id, qid = make_kqid(current_user_ns(), type, id); if (!qid_valid(qid)) return -EINVAL; - return sb->s_qcop->set_dqblk(sb, qid, &fdq); + copy_from_xfs_dqblk(&qdq, &fdq); + return sb->s_qcop->set_dqblk(sb, qid, &qdq); +} + +static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src, + int type, qid_t id) +{ + memset(dst, 0, sizeof(*dst)); + dst->d_version = FS_DQUOT_VERSION; + dst->d_id = id; + if (type == USRQUOTA) + dst->d_flags = FS_USER_QUOTA; + else if (type == PRJQUOTA) + dst->d_flags = FS_PROJ_QUOTA; + else + dst->d_flags = FS_GROUP_QUOTA; + dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit); + dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit); + dst->d_ino_hardlimit = src->d_ino_hardlimit; + dst->d_ino_softlimit = src->d_ino_softlimit; + dst->d_bcount = quota_btobb(src->d_space); + dst->d_icount = src->d_ino_count; + dst->d_itimer = src->d_ino_timer; + dst->d_btimer = src->d_spc_timer; + dst->d_iwarns = src->d_ino_warns; + dst->d_bwarns = src->d_spc_warns; + dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit); + dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit); + dst->d_rtbcount = quota_btobb(src->d_rt_space); + dst->d_rtbtimer = src->d_rt_spc_timer; + dst->d_rtbwarns = src->d_rt_spc_warns; } static int quota_getxquota(struct super_block *sb, int type, qid_t id, void __user *addr) { struct fs_disk_quota fdq; + struct qc_dqblk qdq; struct kqid qid; int ret; @@ -275,8 +384,11 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id, qid = make_kqid(current_user_ns(), type, id); if (!qid_valid(qid)) return -EINVAL; - ret = sb->s_qcop->get_dqblk(sb, qid, &fdq); - if (!ret && copy_to_user(addr, &fdq, sizeof(fdq))) + ret = sb->s_qcop->get_dqblk(sb, qid, &qdq); + if (ret) + return ret; + copy_to_xfs_dqblk(&fdq, &qdq, type, id); + if (copy_to_user(addr, &fdq, sizeof(fdq))) return -EFAULT; return ret; } diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index 3a07a937e232..41f6c0b9d51c 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -166,9 +166,9 @@ extern void xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint); /* quota ops */ extern int xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint); extern int xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t, - uint, struct fs_disk_quota *); + uint, struct qc_dqblk *); extern int xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint, - struct fs_disk_quota *); + struct qc_dqblk *); extern int xfs_qm_scall_getqstat(struct xfs_mount *, struct fs_quota_stat *); extern int xfs_qm_scall_getqstatv(struct xfs_mount *, diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index 74fca68e43b6..cb6168ec92c9 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -39,7 +39,6 @@ STATIC int xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint); STATIC int xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *, uint); STATIC uint xfs_qm_export_flags(uint); -STATIC uint xfs_qm_export_qtype_flags(uint); /* * Turn off quota accounting and/or enforcement for all udquots and/or @@ -573,8 +572,8 @@ xfs_qm_scall_getqstatv( return 0; } -#define XFS_DQ_MASK \ - (FS_DQ_LIMIT_MASK | FS_DQ_TIMER_MASK | FS_DQ_WARNS_MASK) +#define XFS_QC_MASK \ + (QC_LIMIT_MASK | QC_TIMER_MASK | QC_WARNS_MASK) /* * Adjust quota limits, and start/stop timers accordingly. @@ -584,7 +583,7 @@ xfs_qm_scall_setqlim( struct xfs_mount *mp, xfs_dqid_t id, uint type, - fs_disk_quota_t *newlim) + struct qc_dqblk *newlim) { struct xfs_quotainfo *q = mp->m_quotainfo; struct xfs_disk_dquot *ddq; @@ -593,9 +592,9 @@ xfs_qm_scall_setqlim( int error; xfs_qcnt_t hard, soft; - if (newlim->d_fieldmask & ~XFS_DQ_MASK) + if (newlim->d_fieldmask & ~XFS_QC_MASK) return -EINVAL; - if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0) + if ((newlim->d_fieldmask & XFS_QC_MASK) == 0) return 0; /* @@ -633,11 +632,11 @@ xfs_qm_scall_setqlim( /* * Make sure that hardlimits are >= soft limits before changing. */ - hard = (newlim->d_fieldmask & FS_DQ_BHARD) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) : + hard = (newlim->d_fieldmask & QC_SPC_HARD) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) : be64_to_cpu(ddq->d_blk_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) : + soft = (newlim->d_fieldmask & QC_SPC_SOFT) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) : be64_to_cpu(ddq->d_blk_softlimit); if (hard == 0 || hard >= soft) { ddq->d_blk_hardlimit = cpu_to_be64(hard); @@ -650,11 +649,11 @@ xfs_qm_scall_setqlim( } else { xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft); } - hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) : + hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) : be64_to_cpu(ddq->d_rtb_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ? - (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) : + soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ? + (xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) : be64_to_cpu(ddq->d_rtb_softlimit); if (hard == 0 || hard >= soft) { ddq->d_rtb_hardlimit = cpu_to_be64(hard); @@ -667,10 +666,10 @@ xfs_qm_scall_setqlim( xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft); } - hard = (newlim->d_fieldmask & FS_DQ_IHARD) ? + hard = (newlim->d_fieldmask & QC_INO_HARD) ? (xfs_qcnt_t) newlim->d_ino_hardlimit : be64_to_cpu(ddq->d_ino_hardlimit); - soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ? + soft = (newlim->d_fieldmask & QC_INO_SOFT) ? (xfs_qcnt_t) newlim->d_ino_softlimit : be64_to_cpu(ddq->d_ino_softlimit); if (hard == 0 || hard >= soft) { @@ -687,12 +686,12 @@ xfs_qm_scall_setqlim( /* * Update warnings counter(s) if requested */ - if (newlim->d_fieldmask & FS_DQ_BWARNS) - ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns); - if (newlim->d_fieldmask & FS_DQ_IWARNS) - ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns); - if (newlim->d_fieldmask & FS_DQ_RTBWARNS) - ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns); + if (newlim->d_fieldmask & QC_SPC_WARNS) + ddq->d_bwarns = cpu_to_be16(newlim->d_spc_warns); + if (newlim->d_fieldmask & QC_INO_WARNS) + ddq->d_iwarns = cpu_to_be16(newlim->d_ino_warns); + if (newlim->d_fieldmask & QC_RT_SPC_WARNS) + ddq->d_rtbwarns = cpu_to_be16(newlim->d_rt_spc_warns); if (id == 0) { /* @@ -702,24 +701,24 @@ xfs_qm_scall_setqlim( * soft and hard limit values (already done, above), and * for warnings. */ - if (newlim->d_fieldmask & FS_DQ_BTIMER) { - q->qi_btimelimit = newlim->d_btimer; - ddq->d_btimer = cpu_to_be32(newlim->d_btimer); + if (newlim->d_fieldmask & QC_SPC_TIMER) { + q->qi_btimelimit = newlim->d_spc_timer; + ddq->d_btimer = cpu_to_be32(newlim->d_spc_timer); } - if (newlim->d_fieldmask & FS_DQ_ITIMER) { - q->qi_itimelimit = newlim->d_itimer; - ddq->d_itimer = cpu_to_be32(newlim->d_itimer); + if (newlim->d_fieldmask & QC_INO_TIMER) { + q->qi_itimelimit = newlim->d_ino_timer; + ddq->d_itimer = cpu_to_be32(newlim->d_ino_timer); } - if (newlim->d_fieldmask & FS_DQ_RTBTIMER) { - q->qi_rtbtimelimit = newlim->d_rtbtimer; - ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer); + if (newlim->d_fieldmask & QC_RT_SPC_TIMER) { + q->qi_rtbtimelimit = newlim->d_rt_spc_timer; + ddq->d_rtbtimer = cpu_to_be32(newlim->d_rt_spc_timer); } - if (newlim->d_fieldmask & FS_DQ_BWARNS) - q->qi_bwarnlimit = newlim->d_bwarns; - if (newlim->d_fieldmask & FS_DQ_IWARNS) - q->qi_iwarnlimit = newlim->d_iwarns; - if (newlim->d_fieldmask & FS_DQ_RTBWARNS) - q->qi_rtbwarnlimit = newlim->d_rtbwarns; + if (newlim->d_fieldmask & QC_SPC_WARNS) + q->qi_bwarnlimit = newlim->d_spc_warns; + if (newlim->d_fieldmask & QC_INO_WARNS) + q->qi_iwarnlimit = newlim->d_ino_warns; + if (newlim->d_fieldmask & QC_RT_SPC_WARNS) + q->qi_rtbwarnlimit = newlim->d_rt_spc_warns; } else { /* * If the user is now over quota, start the timelimit. @@ -824,7 +823,7 @@ xfs_qm_scall_getquota( struct xfs_mount *mp, xfs_dqid_t id, uint type, - struct fs_disk_quota *dst) + struct qc_dqblk *dst) { struct xfs_dquot *dqp; int error; @@ -848,28 +847,25 @@ xfs_qm_scall_getquota( } memset(dst, 0, sizeof(*dst)); - dst->d_version = FS_DQUOT_VERSION; - dst->d_flags = xfs_qm_export_qtype_flags(dqp->q_core.d_flags); - dst->d_id = be32_to_cpu(dqp->q_core.d_id); - dst->d_blk_hardlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit)); - dst->d_blk_softlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit)); + dst->d_spc_hardlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit)); + dst->d_spc_softlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit)); dst->d_ino_hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit); dst->d_ino_softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit); - dst->d_bcount = XFS_FSB_TO_BB(mp, dqp->q_res_bcount); - dst->d_icount = dqp->q_res_icount; - dst->d_btimer = be32_to_cpu(dqp->q_core.d_btimer); - dst->d_itimer = be32_to_cpu(dqp->q_core.d_itimer); - dst->d_iwarns = be16_to_cpu(dqp->q_core.d_iwarns); - dst->d_bwarns = be16_to_cpu(dqp->q_core.d_bwarns); - dst->d_rtb_hardlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit)); - dst->d_rtb_softlimit = - XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit)); - dst->d_rtbcount = XFS_FSB_TO_BB(mp, dqp->q_res_rtbcount); - dst->d_rtbtimer = be32_to_cpu(dqp->q_core.d_rtbtimer); - dst->d_rtbwarns = be16_to_cpu(dqp->q_core.d_rtbwarns); + dst->d_space = XFS_FSB_TO_B(mp, dqp->q_res_bcount); + dst->d_ino_count = dqp->q_res_icount; + dst->d_spc_timer = be32_to_cpu(dqp->q_core.d_btimer); + dst->d_ino_timer = be32_to_cpu(dqp->q_core.d_itimer); + dst->d_ino_warns = be16_to_cpu(dqp->q_core.d_iwarns); + dst->d_spc_warns = be16_to_cpu(dqp->q_core.d_bwarns); + dst->d_rt_spc_hardlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit)); + dst->d_rt_spc_softlimit = + XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit)); + dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_res_rtbcount); + dst->d_rt_spc_timer = be32_to_cpu(dqp->q_core.d_rtbtimer); + dst->d_rt_spc_warns = be16_to_cpu(dqp->q_core.d_rtbwarns); /* * Internally, we don't reset all the timers when quota enforcement @@ -882,23 +878,23 @@ xfs_qm_scall_getquota( dqp->q_core.d_flags == XFS_DQ_GROUP) || (!XFS_IS_PQUOTA_ENFORCED(mp) && dqp->q_core.d_flags == XFS_DQ_PROJ)) { - dst->d_btimer = 0; - dst->d_itimer = 0; - dst->d_rtbtimer = 0; + dst->d_spc_timer = 0; + dst->d_ino_timer = 0; + dst->d_rt_spc_timer = 0; } #ifdef DEBUG - if (((XFS_IS_UQUOTA_ENFORCED(mp) && dst->d_flags == FS_USER_QUOTA) || - (XFS_IS_GQUOTA_ENFORCED(mp) && dst->d_flags == FS_GROUP_QUOTA) || - (XFS_IS_PQUOTA_ENFORCED(mp) && dst->d_flags == FS_PROJ_QUOTA)) && - dst->d_id != 0) { - if ((dst->d_bcount > dst->d_blk_softlimit) && - (dst->d_blk_softlimit > 0)) { - ASSERT(dst->d_btimer != 0); + if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) || + (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) || + (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) && + id != 0) { + if ((dst->d_space > dst->d_spc_softlimit) && + (dst->d_spc_softlimit > 0)) { + ASSERT(dst->d_spc_timer != 0); } - if ((dst->d_icount > dst->d_ino_softlimit) && + if ((dst->d_ino_count > dst->d_ino_softlimit) && (dst->d_ino_softlimit > 0)) { - ASSERT(dst->d_itimer != 0); + ASSERT(dst->d_ino_timer != 0); } } #endif @@ -907,26 +903,6 @@ out_put: return error; } -STATIC uint -xfs_qm_export_qtype_flags( - uint flags) -{ - /* - * Can't be more than one, or none. - */ - ASSERT((flags & (FS_PROJ_QUOTA | FS_USER_QUOTA)) != - (FS_PROJ_QUOTA | FS_USER_QUOTA)); - ASSERT((flags & (FS_PROJ_QUOTA | FS_GROUP_QUOTA)) != - (FS_PROJ_QUOTA | FS_GROUP_QUOTA)); - ASSERT((flags & (FS_USER_QUOTA | FS_GROUP_QUOTA)) != - (FS_USER_QUOTA | FS_GROUP_QUOTA)); - ASSERT((flags & (FS_PROJ_QUOTA|FS_USER_QUOTA|FS_GROUP_QUOTA)) != 0); - - return (flags & XFS_DQ_USER) ? - FS_USER_QUOTA : (flags & XFS_DQ_PROJ) ? - FS_PROJ_QUOTA : FS_GROUP_QUOTA; -} - STATIC uint xfs_qm_export_flags( uint flags) diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index 7542bbeca6a1..801a84c1cdc3 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -131,7 +131,7 @@ STATIC int xfs_fs_get_dqblk( struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); @@ -141,14 +141,14 @@ xfs_fs_get_dqblk( return -ESRCH; return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid), - xfs_quota_type(qid.type), fdq); + xfs_quota_type(qid.type), qdq); } STATIC int xfs_fs_set_dqblk( struct super_block *sb, struct kqid qid, - struct fs_disk_quota *fdq) + struct qc_dqblk *qdq) { struct xfs_mount *mp = XFS_M(sb); @@ -160,7 +160,7 @@ xfs_fs_set_dqblk( return -ESRCH; return xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid), - xfs_quota_type(qid.type), fdq); + xfs_quota_type(qid.type), qdq); } const struct quotactl_ops xfs_quotactl_operations = { diff --git a/include/linux/quota.h b/include/linux/quota.h index 50978b781a19..097d7eb2441e 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -321,6 +321,49 @@ struct dquot_operations { struct path; +/* Structure for communicating via ->get_dqblk() & ->set_dqblk() */ +struct qc_dqblk { + int d_fieldmask; /* mask of fields to change in ->set_dqblk() */ + u64 d_spc_hardlimit; /* absolute limit on used space */ + u64 d_spc_softlimit; /* preferred limit on used space */ + u64 d_ino_hardlimit; /* maximum # allocated inodes */ + u64 d_ino_softlimit; /* preferred inode limit */ + u64 d_space; /* Space owned by the user */ + u64 d_ino_count; /* # inodes owned by the user */ + s64 d_ino_timer; /* zero if within inode limits */ + /* if not, we refuse service */ + s64 d_spc_timer; /* similar to above; for space */ + int d_ino_warns; /* # warnings issued wrt num inodes */ + int d_spc_warns; /* # warnings issued wrt used space */ + u64 d_rt_spc_hardlimit; /* absolute limit on realtime space */ + u64 d_rt_spc_softlimit; /* preferred limit on RT space */ + u64 d_rt_space; /* realtime space owned */ + s64 d_rt_spc_timer; /* similar to above; for RT space */ + int d_rt_spc_warns; /* # warnings issued wrt RT space */ +}; + +/* Field specifiers for ->set_dqblk() in struct qc_dqblk */ +#define QC_INO_SOFT (1<<0) +#define QC_INO_HARD (1<<1) +#define QC_SPC_SOFT (1<<2) +#define QC_SPC_HARD (1<<3) +#define QC_RT_SPC_SOFT (1<<4) +#define QC_RT_SPC_HARD (1<<5) +#define QC_LIMIT_MASK (QC_INO_SOFT | QC_INO_HARD | QC_SPC_SOFT | QC_SPC_HARD | \ + QC_RT_SPC_SOFT | QC_RT_SPC_HARD) +#define QC_SPC_TIMER (1<<6) +#define QC_INO_TIMER (1<<7) +#define QC_RT_SPC_TIMER (1<<8) +#define QC_TIMER_MASK (QC_SPC_TIMER | QC_INO_TIMER | QC_RT_SPC_TIMER) +#define QC_SPC_WARNS (1<<9) +#define QC_INO_WARNS (1<<10) +#define QC_RT_SPC_WARNS (1<<11) +#define QC_WARNS_MASK (QC_SPC_WARNS | QC_INO_WARNS | QC_RT_SPC_WARNS) +#define QC_SPACE (1<<12) +#define QC_INO_COUNT (1<<13) +#define QC_RT_SPACE (1<<14) +#define QC_ACCT_MASK (QC_SPACE | QC_INO_COUNT | QC_RT_SPACE) + /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); @@ -329,8 +372,8 @@ struct quotactl_ops { int (*quota_sync)(struct super_block *, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); - int (*get_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *); - int (*set_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *); + int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); + int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); int (*set_xstate)(struct super_block *, unsigned int, int); int (*get_xstatev)(struct super_block *, struct fs_quota_statv *); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index f23538a6e411..29e3455f7d41 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -98,9 +98,9 @@ int dquot_quota_sync(struct super_block *sb, int type); int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii); int dquot_get_dqblk(struct super_block *sb, struct kqid id, - struct fs_disk_quota *di); + struct qc_dqblk *di); int dquot_set_dqblk(struct super_block *sb, struct kqid id, - struct fs_disk_quota *di); + struct qc_dqblk *di); int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); int dquot_transfer(struct inode *inode, struct iattr *iattr); -- cgit v1.2.3 From 38e478c4489a845a5e8baf7849c286af5fed5b66 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 15:56:21 +0200 Subject: quota: Split ->set_xstate callback into two Split ->set_xstate callback into two callbacks - one for turning quotas on (->quota_enable) and one for turning quotas off (->quota_disable). That way we don't have to pass quotactl command into the callback which seems cleaner. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/quota/quota.c | 20 +++++++++++++---- fs/xfs/xfs_quotaops.c | 59 ++++++++++++++++++++++++++++++++------------------- include/linux/quota.h | 3 ++- 3 files changed, 55 insertions(+), 27 deletions(-) (limited to 'fs') diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 6f3856328eea..e2ae2b99e555 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -208,15 +208,26 @@ static int quota_setquota(struct super_block *sb, int type, qid_t id, return sb->s_qcop->set_dqblk(sb, qid, &fdq); } -static int quota_setxstate(struct super_block *sb, int cmd, void __user *addr) +static int quota_enable(struct super_block *sb, void __user *addr) { __u32 flags; if (copy_from_user(&flags, addr, sizeof(flags))) return -EFAULT; - if (!sb->s_qcop->set_xstate) + if (!sb->s_qcop->quota_enable) return -ENOSYS; - return sb->s_qcop->set_xstate(sb, flags, cmd); + return sb->s_qcop->quota_enable(sb, flags); +} + +static int quota_disable(struct super_block *sb, void __user *addr) +{ + __u32 flags; + + if (copy_from_user(&flags, addr, sizeof(flags))) + return -EFAULT; + if (!sb->s_qcop->quota_disable) + return -ENOSYS; + return sb->s_qcop->quota_disable(sb, flags); } static int quota_getxstate(struct super_block *sb, void __user *addr) @@ -447,8 +458,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, return -ENOSYS; return sb->s_qcop->quota_sync(sb, type); case Q_XQUOTAON: + return quota_enable(sb, addr); case Q_XQUOTAOFF: - return quota_setxstate(sb, cmd, addr); + return quota_disable(sb, addr); case Q_XQUOTARM: return quota_rmxquota(sb, addr); case Q_XGETQSTAT: diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index a226203fa46a..6923905ab33d 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -64,19 +64,10 @@ xfs_fs_get_xstatev( return xfs_qm_scall_getqstatv(mp, fqs); } -STATIC int -xfs_fs_set_xstate( - struct super_block *sb, - unsigned int uflags, - int op) +static unsigned int +xfs_quota_flags(unsigned int uflags) { - struct xfs_mount *mp = XFS_M(sb); - unsigned int flags = 0; - - if (sb->s_flags & MS_RDONLY) - return -EROFS; - if (!XFS_IS_QUOTA_RUNNING(mp)) - return -ENOSYS; + unsigned int flags = 0; if (uflags & FS_QUOTA_UDQ_ACCT) flags |= XFS_UQUOTA_ACCT; @@ -91,16 +82,39 @@ xfs_fs_set_xstate( if (uflags & FS_QUOTA_PDQ_ENFD) flags |= XFS_PQUOTA_ENFD; - switch (op) { - case Q_XQUOTAON: - return xfs_qm_scall_quotaon(mp, flags); - case Q_XQUOTAOFF: - if (!XFS_IS_QUOTA_ON(mp)) - return -EINVAL; - return xfs_qm_scall_quotaoff(mp, flags); - } + return flags; +} + +STATIC int +xfs_quota_enable( + struct super_block *sb, + unsigned int uflags) +{ + struct xfs_mount *mp = XFS_M(sb); + + if (sb->s_flags & MS_RDONLY) + return -EROFS; + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + + return xfs_qm_scall_quotaon(mp, xfs_quota_flags(uflags)); +} + +STATIC int +xfs_quota_disable( + struct super_block *sb, + unsigned int uflags) +{ + struct xfs_mount *mp = XFS_M(sb); + + if (sb->s_flags & MS_RDONLY) + return -EROFS; + if (!XFS_IS_QUOTA_RUNNING(mp)) + return -ENOSYS; + if (!XFS_IS_QUOTA_ON(mp)) + return -EINVAL; - return -EINVAL; + return xfs_qm_scall_quotaoff(mp, xfs_quota_flags(uflags)); } STATIC int @@ -166,7 +180,8 @@ xfs_fs_set_dqblk( const struct quotactl_ops xfs_quotactl_operations = { .get_xstatev = xfs_fs_get_xstatev, .get_xstate = xfs_fs_get_xstate, - .set_xstate = xfs_fs_set_xstate, + .quota_enable = xfs_quota_enable, + .quota_disable = xfs_quota_disable, .rm_xquota = xfs_fs_rm_xquota, .get_dqblk = xfs_fs_get_dqblk, .set_dqblk = xfs_fs_set_dqblk, diff --git a/include/linux/quota.h b/include/linux/quota.h index 227f37f463c9..4da497b807c4 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -371,13 +371,14 @@ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); int (*quota_on_meta)(struct super_block *, int, int); int (*quota_off)(struct super_block *, int); + int (*quota_enable)(struct super_block *, unsigned int); + int (*quota_disable)(struct super_block *, unsigned int); int (*quota_sync)(struct super_block *, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); - int (*set_xstate)(struct super_block *, unsigned int, int); int (*get_xstatev)(struct super_block *, struct fs_quota_statv *); int (*rm_xquota)(struct super_block *, unsigned int); }; -- cgit v1.2.3 From d3b863248577504f6eecca2a464d6ddf86b71584 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 16:07:12 +0200 Subject: quota: Wire up ->quota_{enable,disable} callbacks into Q_QUOTA{ON,OFF} Make Q_QUOTAON / Q_QUOTAOFF quotactl call ->quota_enable / ->quota_disable callback when provided. To match current behavior of ocfs2 & ext4 we make these quotactls turn on / off quota enforcement for appropriate quota type. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/quota/quota.c | 31 +++++++++++++++++++++++++++---- include/linux/quotaops.h | 2 ++ 2 files changed, 29 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/quota/quota.c b/fs/quota/quota.c index e2ae2b99e555..ce78a70a596f 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -66,18 +66,43 @@ static int quota_sync_all(int type) return ret; } +unsigned int qtype_enforce_flag(int type) +{ + switch (type) { + case USRQUOTA: + return FS_QUOTA_UDQ_ENFD; + case GRPQUOTA: + return FS_QUOTA_GDQ_ENFD; + case PRJQUOTA: + return FS_QUOTA_PDQ_ENFD; + } + return 0; +} + static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id, struct path *path) { - if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta) + if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta && + !sb->s_qcop->quota_enable) return -ENOSYS; if (sb->s_qcop->quota_on_meta) return sb->s_qcop->quota_on_meta(sb, type, id); + if (sb->s_qcop->quota_enable) + return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type)); if (IS_ERR(path)) return PTR_ERR(path); return sb->s_qcop->quota_on(sb, type, id, path); } +static int quota_quotaoff(struct super_block *sb, int type) +{ + if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable) + return -ENOSYS; + if (sb->s_qcop->quota_disable) + return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type)); + return sb->s_qcop->quota_off(sb, type); +} + static int quota_getfmt(struct super_block *sb, int type, void __user *addr) { __u32 fmt; @@ -440,9 +465,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, case Q_QUOTAON: return quota_quotaon(sb, type, cmd, id, path); case Q_QUOTAOFF: - if (!sb->s_qcop->quota_off) - return -ENOSYS; - return sb->s_qcop->quota_off(sb, type); + return quota_quotaoff(sb, type); case Q_GETFMT: return quota_getfmt(sb, type, addr); case Q_GETINFO: diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 29e3455f7d41..ff0b665591d0 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -386,4 +386,6 @@ static inline void dquot_release_reservation_block(struct inode *inode, __dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE); } +unsigned int qtype_enforce_flag(int type); + #endif /* _LINUX_QUOTAOPS_ */ -- cgit v1.2.3 From 3e2af67e66ff025796af1a8a1fcbb4236304f90c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 6 Oct 2014 18:40:51 +0200 Subject: quota: Add ->quota_{enable,disable} callbacks for VFS quotas Add functions which translate ->quota_enable / ->quota_disable calls into appropriate changes in VFS quota. This will enable filesystems supporting VFS quota files in system inodes to be controlled via Q_XQUOTA[ON|OFF] quotactls for better userspace compatibility. Also provide a vector for quotactl using these functions which can be used by filesystems with quota files stored in hidden system files. Signed-off-by: Jan Kara --- fs/quota/dquot.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/quotaops.h | 1 + 2 files changed, 92 insertions(+) (limited to 'fs') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 29eb9dc5728a..b47d0c17ea6f 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2385,6 +2385,86 @@ out: } EXPORT_SYMBOL(dquot_quota_on_mount); +static int dquot_quota_enable(struct super_block *sb, unsigned int flags) +{ + int ret; + int type; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return -ENOSYS; + /* Accounting cannot be turned on while fs is mounted */ + flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT); + if (!flags) + return -EINVAL; + for (type = 0; type < MAXQUOTAS; type++) { + if (!(flags & qtype_enforce_flag(type))) + continue; + /* Can't enforce without accounting */ + if (!sb_has_quota_usage_enabled(sb, type)) + return -EINVAL; + ret = dquot_enable(dqopt->files[type], type, + dqopt->info[type].dqi_fmt_id, + DQUOT_LIMITS_ENABLED); + if (ret < 0) + goto out_err; + } + return 0; +out_err: + /* Backout enforcement enablement we already did */ + for (type--; type >= 0; type--) { + if (flags & qtype_enforce_flag(type)) + dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); + } + /* Error code translation for better compatibility with XFS */ + if (ret == -EBUSY) + ret = -EEXIST; + return ret; +} + +static int dquot_quota_disable(struct super_block *sb, unsigned int flags) +{ + int ret; + int type; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) + return -ENOSYS; + /* + * We don't support turning off accounting via quotactl. In principle + * quota infrastructure can do this but filesystems don't expect + * userspace to be able to do it. + */ + if (flags & + (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT)) + return -EOPNOTSUPP; + + /* Filter out limits not enabled */ + for (type = 0; type < MAXQUOTAS; type++) + if (!sb_has_quota_limits_enabled(sb, type)) + flags &= ~qtype_enforce_flag(type); + /* Nothing left? */ + if (!flags) + return -EEXIST; + for (type = 0; type < MAXQUOTAS; type++) { + if (flags & qtype_enforce_flag(type)) { + ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); + if (ret < 0) + goto out_err; + } + } + return 0; +out_err: + /* Backout enforcement disabling we already did */ + for (type--; type >= 0; type--) { + if (flags & qtype_enforce_flag(type)) + dquot_enable(dqopt->files[type], type, + dqopt->info[type].dqi_fmt_id, + DQUOT_LIMITS_ENABLED); + } + return ret; +} + static inline qsize_t qbtos(qsize_t blocks) { return blocks << QIF_DQBLKSIZE_BITS; @@ -2614,6 +2694,17 @@ const struct quotactl_ops dquot_quotactl_ops = { }; EXPORT_SYMBOL(dquot_quotactl_ops); +const struct quotactl_ops dquot_quotactl_sysfile_ops = { + .quota_enable = dquot_quota_enable, + .quota_disable = dquot_quota_disable, + .quota_sync = dquot_quota_sync, + .get_info = dquot_get_dqinfo, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk +}; +EXPORT_SYMBOL(dquot_quotactl_sysfile_ops); + static int do_proc_dqstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index ff0b665591d0..df73258cca47 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -166,6 +166,7 @@ static inline bool sb_has_quota_active(struct super_block *sb, int type) */ extern const struct dquot_operations dquot_operations; extern const struct quotactl_ops dquot_quotactl_ops; +extern const struct quotactl_ops dquot_quotactl_sysfile_ops; #else -- cgit v1.2.3 From 1fa5efe3622db58cb8c7b9a50665e9eb9a6c7e97 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 18:26:54 +0200 Subject: ext4: Use generic helpers for quotaon and quotaoff Ext4 can just use the generic helpers provided by quota code for turning quotas on and off when quota files are stored as system inodes. The only difference is the feature test in ext4_quota_on_sysfile() but the same is achieved in dquot_quota_enable() by checking whether usage tracking for the corresponding quota type is enabled (which can happen only if quota feature is set). Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/ext4/super.c | 42 +----------------------------------------- 1 file changed, 1 insertion(+), 41 deletions(-) (limited to 'fs') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 74c5f53595fb..ac64edbe501d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1046,10 +1046,7 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot); static int ext4_write_info(struct super_block *sb, int type); static int ext4_quota_on(struct super_block *sb, int type, int format_id, struct path *path); -static int ext4_quota_on_sysfile(struct super_block *sb, int type, - int format_id); static int ext4_quota_off(struct super_block *sb, int type); -static int ext4_quota_off_sysfile(struct super_block *sb, int type); static int ext4_quota_on_mount(struct super_block *sb, int type); static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); @@ -1084,16 +1081,6 @@ static const struct quotactl_ops ext4_qctl_operations = { .get_dqblk = dquot_get_dqblk, .set_dqblk = dquot_set_dqblk }; - -static const struct quotactl_ops ext4_qctl_sysfile_operations = { - .quota_on_meta = ext4_quota_on_sysfile, - .quota_off = ext4_quota_off_sysfile, - .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, - .set_info = dquot_set_dqinfo, - .get_dqblk = dquot_get_dqblk, - .set_dqblk = dquot_set_dqblk -}; #endif static const struct super_operations ext4_sops = { @@ -3935,7 +3922,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - sb->s_qcop = &ext4_qctl_sysfile_operations; + sb->s_qcop = &dquot_quotactl_sysfile_ops; else sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; @@ -5288,21 +5275,6 @@ static int ext4_enable_quotas(struct super_block *sb) return 0; } -/* - * quota_on function that is used when QUOTA feature is set. - */ -static int ext4_quota_on_sysfile(struct super_block *sb, int type, - int format_id) -{ - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - return -EINVAL; - - /* - * USAGE was enabled at mount time. Only need to enable LIMITS now. - */ - return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED); -} - static int ext4_quota_off(struct super_block *sb, int type) { struct inode *inode = sb_dqopt(sb)->files[type]; @@ -5329,18 +5301,6 @@ out: return dquot_quota_off(sb, type); } -/* - * quota_off function that is used when QUOTA feature is set. - */ -static int ext4_quota_off_sysfile(struct super_block *sb, int type) -{ - if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) - return -EINVAL; - - /* Disable only the limits. */ - return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); -} - /* Read data from quotafile - avoid pagecache and such because we cannot afford * acquiring the locks... As quota files are never truncated and quota code * itself serializes the operations (and no one else should touch the files) -- cgit v1.2.3 From 664dbd5fe5485ccb20dbec0081c1033308999220 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 18:30:19 +0200 Subject: ocfs2: Use generic helpers for quotaon and quotaoff Ocfs2 can just use the generic helpers provided by quota code for turning quotas on and off when quota files are stored as system inodes. The only difference is the feature test in ocfs2_quota_on() and that is covered by dquot_quota_enable() checking whether usage tracking is enabled (which can happen only if the filesystem has the quota feature set). Signed-off-by: Jan Kara --- fs/ocfs2/super.c | 32 +------------------------------- 1 file changed, 1 insertion(+), 31 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 83723179e1ec..706c71c2955d 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1000,36 +1000,6 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) } } -/* Handle quota on quotactl */ -static int ocfs2_quota_on(struct super_block *sb, int type, int format_id) -{ - unsigned int feature[OCFS2_MAXQUOTAS] = { - OCFS2_FEATURE_RO_COMPAT_USRQUOTA, - OCFS2_FEATURE_RO_COMPAT_GRPQUOTA}; - - if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type])) - return -EINVAL; - - return dquot_enable(sb_dqopt(sb)->files[type], type, - format_id, DQUOT_LIMITS_ENABLED); -} - -/* Handle quota off quotactl */ -static int ocfs2_quota_off(struct super_block *sb, int type) -{ - return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); -} - -static const struct quotactl_ops ocfs2_quotactl_ops = { - .quota_on_meta = ocfs2_quota_on, - .quota_off = ocfs2_quota_off, - .quota_sync = dquot_quota_sync, - .get_info = dquot_get_dqinfo, - .set_info = dquot_set_dqinfo, - .get_dqblk = dquot_get_dqblk, - .set_dqblk = dquot_set_dqblk, -}; - static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) { struct dentry *root; @@ -2079,7 +2049,7 @@ static int ocfs2_initialize_super(struct super_block *sb, sb->s_op = &ocfs2_sops; sb->s_d_op = &ocfs2_dentry_ops; sb->s_export_op = &ocfs2_export_ops; - sb->s_qcop = &ocfs2_quotactl_ops; + sb->s_qcop = &dquot_quotactl_sysfile_ops; sb->dq_op = &ocfs2_quota_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; sb->s_xattr = ocfs2_xattr_handlers; -- cgit v1.2.3 From aaa3daed156ff3c6acb28c8b18028f8b57d6c91b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 18:35:31 +0200 Subject: quota: Remove quota_on_meta callback There are no more users for quota_on_meta callback. Just remove it. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/quota/quota.c | 5 +---- include/linux/quota.h | 1 - 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/quota/quota.c b/fs/quota/quota.c index ce78a70a596f..d14a799c7785 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -82,11 +82,8 @@ unsigned int qtype_enforce_flag(int type) static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id, struct path *path) { - if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta && - !sb->s_qcop->quota_enable) + if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable) return -ENOSYS; - if (sb->s_qcop->quota_on_meta) - return sb->s_qcop->quota_on_meta(sb, type, id); if (sb->s_qcop->quota_enable) return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type)); if (IS_ERR(path)) diff --git a/include/linux/quota.h b/include/linux/quota.h index 4da497b807c4..0938159d65c8 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -369,7 +369,6 @@ struct qc_dqblk { /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); - int (*quota_on_meta)(struct super_block *, int, int); int (*quota_off)(struct super_block *, int); int (*quota_enable)(struct super_block *, unsigned int); int (*quota_disable)(struct super_block *, unsigned int); -- cgit v1.2.3 From b10a08194c2b615955dfab2300331a90ae9344c7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 9 Oct 2014 16:54:13 +0200 Subject: quota: Store maximum space limit in bytes Currently maximum space limit quota format supports is in blocks however since we store space limits in bytes, this is somewhat confusing. So store the maximum limit in bytes as well. Also rename the field to match the new unit and related inode field to match the new naming scheme. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/ocfs2/quota_local.c | 4 ++-- fs/quota/dquot.c | 18 ++++-------------- fs/quota/quota_v1.c | 4 ++-- fs/quota/quota_v2.c | 10 +++++----- include/linux/quota.h | 4 ++-- 5 files changed, 15 insertions(+), 25 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 55f832f553cb..89c0b2620814 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -701,8 +701,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) /* We don't need the lock and we have to acquire quota file locks * which will later depend on this lock */ mutex_unlock(&sb_dqopt(sb)->dqio_mutex); - info->dqi_maxblimit = 0x7fffffffffffffffLL; - info->dqi_maxilimit = 0x7fffffffffffffffLL; + info->dqi_max_spc_limit = 0x7fffffffffffffffLL; + info->dqi_max_ino_limit = 0x7fffffffffffffffLL; oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS); if (!oinfo) { mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota" diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index b47d0c17ea6f..0ccd4ba3a246 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2465,16 +2465,6 @@ out_err: return ret; } -static inline qsize_t qbtos(qsize_t blocks) -{ - return blocks << QIF_DQBLKSIZE_BITS; -} - -static inline qsize_t stoqb(qsize_t space) -{ - return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS; -} - /* Generic routine for getting common part of quota structure */ static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) { @@ -2524,13 +2514,13 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) return -EINVAL; if (((di->d_fieldmask & QC_SPC_SOFT) && - stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) || + di->d_spc_softlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_SPC_HARD) && - stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) || + di->d_spc_hardlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_INO_SOFT) && - (di->d_ino_softlimit > dqi->dqi_maxilimit)) || + (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) || ((di->d_fieldmask & QC_INO_HARD) && - (di->d_ino_hardlimit > dqi->dqi_maxilimit))) + (di->d_ino_hardlimit > dqi->dqi_max_ino_limit))) return -ERANGE; spin_lock(&dq_data_lock); diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c index 469c6848b322..8fe79beced5c 100644 --- a/fs/quota/quota_v1.c +++ b/fs/quota/quota_v1.c @@ -169,8 +169,8 @@ static int v1_read_file_info(struct super_block *sb, int type) } ret = 0; /* limits are stored as unsigned 32-bit data */ - dqopt->info[type].dqi_maxblimit = 0xffffffff; - dqopt->info[type].dqi_maxilimit = 0xffffffff; + dqopt->info[type].dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + dqopt->info[type].dqi_max_ino_limit = 0xffffffff; dqopt->info[type].dqi_igrace = dqblk.dqb_itime ? dqblk.dqb_itime : MAX_IQ_TIME; dqopt->info[type].dqi_bgrace = diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 54cac436ac72..9cb10d7197f7 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -117,12 +117,12 @@ static int v2_read_file_info(struct super_block *sb, int type) qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ - info->dqi_maxblimit = 0xffffffff; - info->dqi_maxilimit = 0xffffffff; + info->dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS; + info->dqi_max_ino_limit = 0xffffffff; } else { - /* used space is stored as unsigned 64-bit value */ - info->dqi_maxblimit = 0xffffffffffffffffULL; /* 2^64-1 */ - info->dqi_maxilimit = 0xffffffffffffffffULL; + /* used space is stored as unsigned 64-bit value in bytes */ + info->dqi_max_spc_limit = 0xffffffffffffffffULL; /* 2^64-1 */ + info->dqi_max_ino_limit = 0xffffffffffffffffULL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); diff --git a/include/linux/quota.h b/include/linux/quota.h index 0938159d65c8..d534e8ed308a 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -216,8 +216,8 @@ struct mem_dqinfo { unsigned long dqi_flags; unsigned int dqi_bgrace; unsigned int dqi_igrace; - qsize_t dqi_maxblimit; - qsize_t dqi_maxilimit; + qsize_t dqi_max_spc_limit; + qsize_t dqi_max_ino_limit; void *dqi_priv; }; -- cgit v1.2.3 From 8add71ca3fd67c5f222622711f95cfd6cec2a996 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 2 Feb 2015 09:53:56 +1100 Subject: xfs: factor out a xfs_update_prealloc_flags() helper This logic is duplicated in xfs_file_fallocate and xfs_ioc_space, and we'll need another copy of it for pNFS block support. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 64 +++++++++++++++++++++++++++++++++++------------------- fs/xfs/xfs_inode.h | 9 ++++++++ fs/xfs/xfs_ioctl.c | 50 ++++++++++-------------------------------- 3 files changed, 63 insertions(+), 60 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 13e974e6a889..712d312d8e3e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -127,6 +127,42 @@ xfs_iozero( return (-status); } +int +xfs_update_prealloc_flags( + struct xfs_inode *ip, + enum xfs_prealloc_flags flags) +{ + struct xfs_trans *tp; + int error; + + tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID); + error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + if (!(flags & XFS_PREALLOC_INVISIBLE)) { + ip->i_d.di_mode &= ~S_ISUID; + if (ip->i_d.di_mode & S_IXGRP) + ip->i_d.di_mode &= ~S_ISGID; + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + } + + if (flags & XFS_PREALLOC_SET) + ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; + if (flags & XFS_PREALLOC_CLEAR) + ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC; + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + if (flags & XFS_PREALLOC_SYNC) + xfs_trans_set_sync(tp); + return xfs_trans_commit(tp, 0); +} + /* * Fsync operations on directories are much simpler than on regular files, * as there is no file data to flush, and thus also no need for explicit @@ -784,8 +820,8 @@ xfs_file_fallocate( { struct inode *inode = file_inode(file); struct xfs_inode *ip = XFS_I(inode); - struct xfs_trans *tp; long error; + enum xfs_prealloc_flags flags = 0; loff_t new_size = 0; if (!S_ISREG(inode->i_mode)) @@ -822,6 +858,8 @@ xfs_file_fallocate( if (error) goto out_unlock; } else { + flags |= XFS_PREALLOC_SET; + if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) { new_size = offset + len; @@ -839,28 +877,10 @@ xfs_file_fallocate( goto out_unlock; } - tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID); - error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - goto out_unlock; - } - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - ip->i_d.di_mode &= ~S_ISUID; - if (ip->i_d.di_mode & S_IXGRP) - ip->i_d.di_mode &= ~S_ISGID; - - if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE))) - ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; - - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (file->f_flags & O_DSYNC) - xfs_trans_set_sync(tp); - error = xfs_trans_commit(tp, 0); + flags |= XFS_PREALLOC_SYNC; + + error = xfs_update_prealloc_flags(ip, flags); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 4ed2ba9342dc..bc220bcedded 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -377,6 +377,15 @@ int xfs_droplink(struct xfs_trans *, struct xfs_inode *); int xfs_bumplink(struct xfs_trans *, struct xfs_inode *); /* from xfs_file.c */ +enum xfs_prealloc_flags { + XFS_PREALLOC_SET = (1 << 1), + XFS_PREALLOC_CLEAR = (1 << 2), + XFS_PREALLOC_SYNC = (1 << 3), + XFS_PREALLOC_INVISIBLE = (1 << 4), +}; + +int xfs_update_prealloc_flags(struct xfs_inode *, + enum xfs_prealloc_flags); int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t); int xfs_iozero(struct xfs_inode *, loff_t, size_t); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a1831980a68e..d58bcd28f5f8 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -606,11 +606,8 @@ xfs_ioc_space( unsigned int cmd, xfs_flock64_t *bf) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_trans *tp; struct iattr iattr; - bool setprealloc = false; - bool clrprealloc = false; + enum xfs_prealloc_flags flags = 0; int error; /* @@ -630,6 +627,11 @@ xfs_ioc_space( if (!S_ISREG(inode->i_mode)) return -EINVAL; + if (filp->f_flags & O_DSYNC) + flags |= XFS_PREALLOC_SYNC; + if (ioflags & XFS_IO_INVIS) + flags |= XFS_PREALLOC_INVISIBLE; + error = mnt_want_write_file(filp); if (error) return error; @@ -673,25 +675,23 @@ xfs_ioc_space( } if (bf->l_start < 0 || - bf->l_start > mp->m_super->s_maxbytes || + bf->l_start > inode->i_sb->s_maxbytes || bf->l_start + bf->l_len < 0 || - bf->l_start + bf->l_len >= mp->m_super->s_maxbytes) { + bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) { error = -EINVAL; goto out_unlock; } switch (cmd) { case XFS_IOC_ZERO_RANGE: + flags |= XFS_PREALLOC_SET; error = xfs_zero_file_space(ip, bf->l_start, bf->l_len); - if (!error) - setprealloc = true; break; case XFS_IOC_RESVSP: case XFS_IOC_RESVSP64: + flags |= XFS_PREALLOC_SET; error = xfs_alloc_file_space(ip, bf->l_start, bf->l_len, XFS_BMAPI_PREALLOC); - if (!error) - setprealloc = true; break; case XFS_IOC_UNRESVSP: case XFS_IOC_UNRESVSP64: @@ -701,6 +701,7 @@ xfs_ioc_space( case XFS_IOC_ALLOCSP64: case XFS_IOC_FREESP: case XFS_IOC_FREESP64: + flags |= XFS_PREALLOC_CLEAR; if (bf->l_start > XFS_ISIZE(ip)) { error = xfs_alloc_file_space(ip, XFS_ISIZE(ip), bf->l_start - XFS_ISIZE(ip), 0); @@ -712,8 +713,6 @@ xfs_ioc_space( iattr.ia_size = bf->l_start; error = xfs_setattr_size(ip, &iattr); - if (!error) - clrprealloc = true; break; default: ASSERT(0); @@ -723,32 +722,7 @@ xfs_ioc_space( if (error) goto out_unlock; - tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID); - error = xfs_trans_reserve(tp, &M_RES(mp)->tr_writeid, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - goto out_unlock; - } - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - - if (!(ioflags & XFS_IO_INVIS)) { - ip->i_d.di_mode &= ~S_ISUID; - if (ip->i_d.di_mode & S_IXGRP) - ip->i_d.di_mode &= ~S_ISGID; - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - } - - if (setprealloc) - ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC; - else if (clrprealloc) - ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC; - - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (filp->f_flags & O_DSYNC) - xfs_trans_set_sync(tp); - error = xfs_trans_commit(tp, 0); + error = xfs_update_prealloc_flags(ip, flags); out_unlock: xfs_iunlock(ip, XFS_IOLOCK_EXCL); -- cgit v1.2.3 From f3d215526e6955028dfbbfd446db8716275fb0c7 Mon Sep 17 00:00:00 2001 From: Wang, Yalin Date: Mon, 2 Feb 2015 09:54:18 +1100 Subject: xfs: change kmem_free to use generic kvfree() Change kmem_free to use kvfree() generic function, remove the duplicated code. Signed-off-by: Yalin Wang Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/kmem.c | 10 ---------- fs/xfs/kmem.h | 5 ++++- 2 files changed, 4 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 53e95b2a1369..a7a3a63bb360 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -91,16 +91,6 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags) return ptr; } -void -kmem_free(const void *ptr) -{ - if (!is_vmalloc_addr(ptr)) { - kfree(ptr); - } else { - vfree(ptr); - } -} - void * kmem_realloc(const void *ptr, size_t newsize, size_t oldsize, xfs_km_flags_t flags) diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index 64db0e53edea..cc6b768fc068 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -63,7 +63,10 @@ kmem_flags_convert(xfs_km_flags_t flags) extern void *kmem_alloc(size_t, xfs_km_flags_t); extern void *kmem_zalloc_large(size_t size, xfs_km_flags_t); extern void *kmem_realloc(const void *, size_t, size_t, xfs_km_flags_t); -extern void kmem_free(const void *); +static inline void kmem_free(const void *ptr) +{ + kvfree(ptr); +} extern void *kmem_zalloc_greedy(size_t *, size_t, size_t); -- cgit v1.2.3 From 2ba66237029d1ad6c1a5e2241b0ffbbfff55f750 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 2 Feb 2015 10:02:09 +1100 Subject: xfs: don't allocate an ioend for direct I/O completions Back in the days when the direct I/O ->end_io callback could be called from interrupt context for AIO we needed a structure to hand off to the workqueue, and reused the ioend structure for this purpose. These days ->end_io is always called from user or workqueue context, which allows us to avoid this memory allocation and simplify the code significantly. [dchinner: removed now unused xfs_finish_ioend_sync() function after Brian Foster did an initial review. ] Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_aops.c | 149 ++++++++++++++++++++++-------------------------------- fs/xfs/xfs_aops.h | 3 -- 2 files changed, 61 insertions(+), 91 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 18e2f3bbae5e..3a9b7a1b8704 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -135,30 +135,22 @@ xfs_setfilesize_trans_alloc( */ STATIC int xfs_setfilesize( - struct xfs_ioend *ioend) + struct xfs_inode *ip, + struct xfs_trans *tp, + xfs_off_t offset, + size_t size) { - struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_trans *tp = ioend->io_append_trans; xfs_fsize_t isize; - /* - * The transaction may have been allocated in the I/O submission thread, - * thus we need to mark ourselves as beeing in a transaction manually. - * Similarly for freeze protection. - */ - current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); - rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], - 0, 1, _THIS_IP_); - xfs_ilock(ip, XFS_ILOCK_EXCL); - isize = xfs_new_eof(ip, ioend->io_offset + ioend->io_size); + isize = xfs_new_eof(ip, offset + size); if (!isize) { xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_trans_cancel(tp, 0); return 0; } - trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size); + trace_xfs_setfilesize(ip, offset, size); ip->i_d.di_size = isize; xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); @@ -167,6 +159,25 @@ xfs_setfilesize( return xfs_trans_commit(tp, 0); } +STATIC int +xfs_setfilesize_ioend( + struct xfs_ioend *ioend) +{ + struct xfs_inode *ip = XFS_I(ioend->io_inode); + struct xfs_trans *tp = ioend->io_append_trans; + + /* + * The transaction may have been allocated in the I/O submission thread, + * thus we need to mark ourselves as being in a transaction manually. + * Similarly for freeze protection. + */ + current_set_flags_nested(&tp->t_pflags, PF_FSTRANS); + rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1], + 0, 1, _THIS_IP_); + + return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size); +} + /* * Schedule IO completion handling on the final put of an ioend. * @@ -182,8 +193,7 @@ xfs_finish_ioend( if (ioend->io_type == XFS_IO_UNWRITTEN) queue_work(mp->m_unwritten_workqueue, &ioend->io_work); - else if (ioend->io_append_trans || - (ioend->io_isdirect && xfs_ioend_is_append(ioend))) + else if (ioend->io_append_trans) queue_work(mp->m_data_workqueue, &ioend->io_work); else xfs_destroy_ioend(ioend); @@ -215,22 +225,8 @@ xfs_end_io( if (ioend->io_type == XFS_IO_UNWRITTEN) { error = xfs_iomap_write_unwritten(ip, ioend->io_offset, ioend->io_size); - } else if (ioend->io_isdirect && xfs_ioend_is_append(ioend)) { - /* - * For direct I/O we do not know if we need to allocate blocks - * or not so we can't preallocate an append transaction as that - * results in nested reservations and log space deadlocks. Hence - * allocate the transaction here. While this is sub-optimal and - * can block IO completion for some time, we're stuck with doing - * it this way until we can pass the ioend to the direct IO - * allocation callbacks and avoid nesting that way. - */ - error = xfs_setfilesize_trans_alloc(ioend); - if (error) - goto done; - error = xfs_setfilesize(ioend); } else if (ioend->io_append_trans) { - error = xfs_setfilesize(ioend); + error = xfs_setfilesize_ioend(ioend); } else { ASSERT(!xfs_ioend_is_append(ioend)); } @@ -241,17 +237,6 @@ done: xfs_destroy_ioend(ioend); } -/* - * Call IO completion handling in caller context on the final put of an ioend. - */ -STATIC void -xfs_finish_ioend_sync( - struct xfs_ioend *ioend) -{ - if (atomic_dec_and_test(&ioend->io_remaining)) - xfs_end_io(&ioend->io_work); -} - /* * Allocate and initialise an IO completion structure. * We need to track unwritten extent write completion here initially. @@ -273,7 +258,6 @@ xfs_alloc_ioend( * all the I/O from calling the completion routine too early. */ atomic_set(&ioend->io_remaining, 1); - ioend->io_isdirect = 0; ioend->io_error = 0; ioend->io_list = NULL; ioend->io_type = type; @@ -1459,11 +1443,7 @@ xfs_get_blocks_direct( * * If the private argument is non-NULL __xfs_get_blocks signals us that we * need to issue a transaction to convert the range from unwritten to written - * extents. In case this is regular synchronous I/O we just call xfs_end_io - * to do this and we are done. But in case this was a successful AIO - * request this handler is called from interrupt context, from which we - * can't start transactions. In that case offload the I/O completion to - * the workqueues we also use for buffered I/O completion. + * extents. */ STATIC void xfs_end_io_direct_write( @@ -1472,7 +1452,12 @@ xfs_end_io_direct_write( ssize_t size, void *private) { - struct xfs_ioend *ioend = iocb->private; + struct inode *inode = file_inode(iocb->ki_filp); + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + + if (XFS_FORCED_SHUTDOWN(mp)) + return; /* * While the generic direct I/O code updates the inode size, it does @@ -1480,22 +1465,33 @@ xfs_end_io_direct_write( * end_io handler thinks the on-disk size is outside the in-core * size. To prevent this just update it a little bit earlier here. */ - if (offset + size > i_size_read(ioend->io_inode)) - i_size_write(ioend->io_inode, offset + size); + if (offset + size > i_size_read(inode)) + i_size_write(inode, offset + size); /* - * blockdev_direct_IO can return an error even after the I/O - * completion handler was called. Thus we need to protect - * against double-freeing. + * For direct I/O we do not know if we need to allocate blocks or not, + * so we can't preallocate an append transaction, as that results in + * nested reservations and log space deadlocks. Hence allocate the + * transaction here. While this is sub-optimal and can block IO + * completion for some time, we're stuck with doing it this way until + * we can pass the ioend to the direct IO allocation callbacks and + * avoid nesting that way. */ - iocb->private = NULL; - - ioend->io_offset = offset; - ioend->io_size = size; - if (private && size > 0) - ioend->io_type = XFS_IO_UNWRITTEN; + if (private && size > 0) { + xfs_iomap_write_unwritten(ip, offset, size); + } else if (offset + size > ip->i_d.di_size) { + struct xfs_trans *tp; + int error; + + tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return; + } - xfs_finish_ioend_sync(ioend); + xfs_setfilesize(ip, tp, offset, size); + } } STATIC ssize_t @@ -1507,39 +1503,16 @@ xfs_vm_direct_IO( { struct inode *inode = iocb->ki_filp->f_mapping->host; struct block_device *bdev = xfs_find_bdev_for_inode(inode); - struct xfs_ioend *ioend = NULL; - ssize_t ret; if (rw & WRITE) { - size_t size = iov_iter_count(iter); - - /* - * We cannot preallocate a size update transaction here as we - * don't know whether allocation is necessary or not. Hence we - * can only tell IO completion that one is necessary if we are - * not doing unwritten extent conversion. - */ - iocb->private = ioend = xfs_alloc_ioend(inode, XFS_IO_DIRECT); - if (offset + size > XFS_I(inode)->i_d.di_size) - ioend->io_isdirect = 1; - - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, + return __blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset, xfs_get_blocks_direct, xfs_end_io_direct_write, NULL, DIO_ASYNC_EXTEND); - if (ret != -EIOCBQUEUED && iocb->private) - goto out_destroy_ioend; - } else { - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, - offset, xfs_get_blocks_direct, - NULL, NULL, 0); } - - return ret; - -out_destroy_ioend: - xfs_destroy_ioend(ioend); - return ret; + return __blockdev_direct_IO(rw, iocb, inode, bdev, iter, + offset, xfs_get_blocks_direct, + NULL, NULL, 0); } /* diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index f94dd459dff9..ac644e0137a4 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -24,14 +24,12 @@ extern mempool_t *xfs_ioend_pool; * Types of I/O for bmap clustering and I/O completion tracking. */ enum { - XFS_IO_DIRECT = 0, /* special case for direct I/O ioends */ XFS_IO_DELALLOC, /* covers delalloc region */ XFS_IO_UNWRITTEN, /* covers allocated but uninitialized data */ XFS_IO_OVERWRITE, /* covers already allocated extent */ }; #define XFS_IO_TYPES \ - { 0, "" }, \ { XFS_IO_DELALLOC, "delalloc" }, \ { XFS_IO_UNWRITTEN, "unwritten" }, \ { XFS_IO_OVERWRITE, "overwrite" } @@ -45,7 +43,6 @@ typedef struct xfs_ioend { unsigned int io_type; /* delalloc / unwritten */ int io_error; /* I/O error code */ atomic_t io_remaining; /* hold count */ - unsigned int io_isdirect : 1;/* direct I/O */ struct inode *io_inode; /* file being written to */ struct buffer_head *io_buffer_head;/* buffer linked list head */ struct buffer_head *io_buffer_tail;/* buffer linked list tail */ -- cgit v1.2.3 From 817b6c480e330a5325ed9acb0cef8143923a52de Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 2 Feb 2015 10:14:04 +1100 Subject: xfs: FSX_NONBLOCK is not used It is set if the filp is set ot non-blocking, but the flag is not used anywhere. Hence we can kill it. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a1831980a68e..0c0e74f314a6 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1016,7 +1016,6 @@ xfs_diflags_to_linux( #define FSX_PROJID 1 #define FSX_EXTSIZE 2 #define FSX_XFLAGS 4 -#define FSX_NONBLOCK 8 STATIC int xfs_ioctl_setattr( @@ -1299,8 +1298,6 @@ xfs_ioc_fssetxattr( return -EFAULT; mask = FSX_XFLAGS | FSX_EXTSIZE | FSX_PROJID; - if (filp->f_flags & (O_NDELAY|O_NONBLOCK)) - mask |= FSX_NONBLOCK; error = mnt_want_write_file(filp); if (error) @@ -1343,8 +1340,6 @@ xfs_ioc_setxflags( return -EOPNOTSUPP; mask = FSX_XFLAGS; - if (filp->f_flags & (O_NDELAY|O_NONBLOCK)) - mask |= FSX_NONBLOCK; fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip)); error = mnt_want_write_file(filp); -- cgit v1.2.3 From 29a17c00d4b1b8eab61b85b71cb5a83455a7dc5e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 2 Feb 2015 10:14:25 +1100 Subject: xfs: separate xflags from xfs_ioctl_setattr The setting of the extended flags is down through two separate interfaces, but they are munged together into xfs_ioctl_setattr and make that function far more complex than it needs to be. Separate it out into a helper function along with all the other common inode changes and transaction manipulations in xfs_ioctl_setattr(). Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 89 +++++++++++++++++++++++++----------------------------- 1 file changed, 41 insertions(+), 48 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0c0e74f314a6..b0064bdb7a6e 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1013,6 +1013,44 @@ xfs_diflags_to_linux( inode->i_flags &= ~S_NOATIME; } +static int +xfs_ioctl_setattr_xflags( + struct xfs_trans *tp, + struct xfs_inode *ip, + struct fsxattr *fa) +{ + struct xfs_mount *mp = ip->i_mount; + + /* Can't change realtime flag if any extents are allocated. */ + if ((ip->i_d.di_nextents || ip->i_delayed_blks) && + XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & XFS_XFLAG_REALTIME)) + return -EINVAL; + + /* If realtime flag is set then must have realtime device */ + if (fa->fsx_xflags & XFS_XFLAG_REALTIME) { + if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 || + (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) + return -EINVAL; + } + + /* + * Can't modify an immutable/append-only file unless + * we have appropriate permission. + */ + if (((ip->i_d.di_flags & (XFS_DIFLAG_IMMUTABLE | XFS_DIFLAG_APPEND)) || + (fa->fsx_xflags & (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) && + !capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + xfs_trans_ijoin(tp, ip, 0); + xfs_set_diflags(ip, fa->fsx_xflags); + xfs_diflags_to_linux(ip); + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + XFS_STATS_INC(xs_ig_attrchg); + return 0; +} + #define FSX_PROJID 1 #define FSX_EXTSIZE 2 #define FSX_XFLAGS 4 @@ -1159,44 +1197,9 @@ xfs_ioctl_setattr( } - if (mask & FSX_XFLAGS) { - /* - * Can't change realtime flag if any extents are allocated. - */ - if ((ip->i_d.di_nextents || ip->i_delayed_blks) && - (XFS_IS_REALTIME_INODE(ip)) != - (fa->fsx_xflags & XFS_XFLAG_REALTIME)) { - code = -EINVAL; /* EFBIG? */ - goto error_return; - } - - /* - * If realtime flag is set then must have realtime data. - */ - if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) { - if ((mp->m_sb.sb_rblocks == 0) || - (mp->m_sb.sb_rextsize == 0) || - (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) { - code = -EINVAL; - goto error_return; - } - } - - /* - * Can't modify an immutable/append-only file unless - * we have appropriate permission. - */ - if ((ip->i_d.di_flags & - (XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) || - (fa->fsx_xflags & - (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) && - !capable(CAP_LINUX_IMMUTABLE)) { - code = -EPERM; - goto error_return; - } - } - - xfs_trans_ijoin(tp, ip, 0); + code = xfs_ioctl_setattr_xflags(tp, ip, fa); + if (code) + goto error_return; /* * Change file ownership. Must be the owner or privileged. @@ -1227,11 +1230,6 @@ xfs_ioctl_setattr( } - if (mask & FSX_XFLAGS) { - xfs_set_diflags(ip, fa->fsx_xflags); - xfs_diflags_to_linux(ip); - } - /* * Only set the extent size hint if we've already determined that the * extent size hint should be set on the inode. If no extent size flags @@ -1246,11 +1244,6 @@ xfs_ioctl_setattr( ip->i_d.di_extsize = extsize; } - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - XFS_STATS_INC(xs_ig_attrchg); - /* * If this is a synchronous mount, make sure that the * transaction goes to disk before returning to the user. -- cgit v1.2.3 From 8f3d17ab060ec21cead88b81c65050a6ff77e9be Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 2 Feb 2015 10:15:35 +1100 Subject: xfs: factor out xfs_ioctl_setattr transaciton preamble The setup of the transaction is done after a random smattering of checks and before another bunch of ioperations specific validity checks. Pull all the preamble out into a helper function that returns a transaction or error. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 101 +++++++++++++++++++++++++++++------------------------ 1 file changed, 55 insertions(+), 46 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index b0064bdb7a6e..0f62f5b3e221 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1042,7 +1042,6 @@ xfs_ioctl_setattr_xflags( !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; - xfs_trans_ijoin(tp, ip, 0); xfs_set_diflags(ip, fa->fsx_xflags); xfs_diflags_to_linux(ip); xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); @@ -1051,6 +1050,54 @@ xfs_ioctl_setattr_xflags( return 0; } +/* + * Set up the transaction structure for the setattr operation, checking that we + * have permission to do so. On success, return a clean transaction and the + * inode locked exclusively ready for further operation specific checks. On + * failure, return an error without modifying or locking the inode. + */ +static struct xfs_trans * +xfs_ioctl_setattr_get_trans( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int error; + + if (mp->m_flags & XFS_MOUNT_RDONLY) + return ERR_PTR(-EROFS); + if (XFS_FORCED_SHUTDOWN(mp)) + return ERR_PTR(-EIO); + + tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); + error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0); + if (error) + goto out_cancel; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + /* + * CAP_FOWNER overrides the following restrictions: + * + * The user ID of the calling process must be equal to the file owner + * ID, except in cases where the CAP_FSETID capability is applicable. + */ + if (!inode_owner_or_capable(VFS_I(ip))) { + error = -EPERM; + goto out_cancel; + } + + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_trans_set_sync(tp); + + return tp; + +out_cancel: + xfs_trans_cancel(tp, 0); + return ERR_PTR(error); +} + #define FSX_PROJID 1 #define FSX_EXTSIZE 2 #define FSX_XFLAGS 4 @@ -1063,7 +1110,6 @@ xfs_ioctl_setattr( { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; - unsigned int lock_flags = 0; struct xfs_dquot *udqp = NULL; struct xfs_dquot *pdqp = NULL; struct xfs_dquot *olddquot = NULL; @@ -1071,11 +1117,6 @@ xfs_ioctl_setattr( trace_xfs_ioctl_setattr(ip); - if (mp->m_flags & XFS_MOUNT_RDONLY) - return -EROFS; - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - /* * Disallow 32bit project ids when projid32bit feature is not enabled. */ @@ -1099,28 +1140,10 @@ xfs_ioctl_setattr( return code; } - /* - * For the other attributes, we acquire the inode lock and - * first do an error checking pass. - */ - tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); - code = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0); - if (code) - goto error_return; - - lock_flags = XFS_ILOCK_EXCL; - xfs_ilock(ip, lock_flags); - - /* - * CAP_FOWNER overrides the following restrictions: - * - * The user ID of the calling process must be equal - * to the file owner ID, except in cases where the - * CAP_FSETID capability is applicable. - */ - if (!inode_owner_or_capable(VFS_I(ip))) { - code = -EPERM; - goto error_return; + tp = xfs_ioctl_setattr_get_trans(ip); + if (IS_ERR(tp)) { + code = PTR_ERR(tp); + goto error_free_dquots; } /* @@ -1244,20 +1267,7 @@ xfs_ioctl_setattr( ip->i_d.di_extsize = extsize; } - /* - * If this is a synchronous mount, make sure that the - * transaction goes to disk before returning to the user. - * This is slightly sub-optimal in that truncates require - * two sync transactions instead of one for wsync filesystems. - * One for the truncate and one for the timestamps since we - * don't want to change the timestamps unless we're sure the - * truncate worked. Truncates are less than 1% of the laddis - * mix so this probably isn't worth the trouble to optimize. - */ - if (mp->m_flags & XFS_MOUNT_WSYNC) - xfs_trans_set_sync(tp); code = xfs_trans_commit(tp, 0); - xfs_iunlock(ip, lock_flags); /* * Release any dquot(s) the inode had kept before chown. @@ -1268,12 +1278,11 @@ xfs_ioctl_setattr( return code; - error_return: +error_return: + xfs_trans_cancel(tp, 0); +error_free_dquots: xfs_qm_dqrele(udqp); xfs_qm_dqrele(pdqp); - xfs_trans_cancel(tp, 0); - if (lock_flags) - xfs_iunlock(ip, lock_flags); return code; } -- cgit v1.2.3 From f96291f6a39c2b60bede851efa059ba89e5f8277 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 2 Feb 2015 10:15:56 +1100 Subject: xfs: disaggregate xfs_ioctl_setattr xfs_ioctl_setxflags doesn't need all of the functionailty in xfs_ioctl_setattr() and now we have separate helper functions that share the checks and modifications that xfs_ioctl_setxflags requires. Hence disaggregate it from xfs_ioctl_setattr() to allow further work to be done on xfs_ioctl_setattr. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0f62f5b3e221..383e61f514f7 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1324,14 +1324,14 @@ xfs_ioc_getxflags( STATIC int xfs_ioc_setxflags( - xfs_inode_t *ip, + struct xfs_inode *ip, struct file *filp, void __user *arg) { + struct xfs_trans *tp; struct fsxattr fa; unsigned int flags; - unsigned int mask; - int error; + int error; if (copy_from_user(&flags, arg, sizeof(flags))) return -EFAULT; @@ -1341,13 +1341,26 @@ xfs_ioc_setxflags( FS_SYNC_FL)) return -EOPNOTSUPP; - mask = FSX_XFLAGS; fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip)); error = mnt_want_write_file(filp); if (error) return error; - error = xfs_ioctl_setattr(ip, &fa, mask); + + tp = xfs_ioctl_setattr_get_trans(ip); + if (IS_ERR(tp)) { + error = PTR_ERR(tp); + goto out_drop_write; + } + + error = xfs_ioctl_setattr_xflags(tp, ip, &fa); + if (error) { + xfs_trans_cancel(tp, 0); + goto out_drop_write; + } + + error = xfs_trans_commit(tp, 0); +out_drop_write: mnt_drop_write_file(filp); return error; } -- cgit v1.2.3 From fd179b9c3bdab682ae5bb3e10380a31853be179a Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 2 Feb 2015 10:16:25 +1100 Subject: xfs: kill xfs_ioctl_setattr behaviour mask Now there is only one caller to xfs_ioctl_setattr that uses all the functionality of the function we can kill the behviour mask and start cleaning up the code. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 168 +++++++++++++++++++++-------------------------------- 1 file changed, 65 insertions(+), 103 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 383e61f514f7..a1f285411b74 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1098,15 +1098,10 @@ out_cancel: return ERR_PTR(error); } -#define FSX_PROJID 1 -#define FSX_EXTSIZE 2 -#define FSX_XFLAGS 4 - STATIC int xfs_ioctl_setattr( xfs_inode_t *ip, - struct fsxattr *fa, - int mask) + struct fsxattr *fa) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; @@ -1120,8 +1115,8 @@ xfs_ioctl_setattr( /* * Disallow 32bit project ids when projid32bit feature is not enabled. */ - if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) && - !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) + if (fa->fsx_projid > (__uint16_t)-1 && + !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) return -EINVAL; /* @@ -1132,7 +1127,7 @@ xfs_ioctl_setattr( * If the IDs do change before we take the ilock, we're covered * because the i_*dquot fields will get updated anyway. */ - if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) { + if (XFS_IS_QUOTA_ON(mp)) { code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid, ip->i_d.di_gid, fa->fsx_projid, XFS_QMOPT_PQUOTA, &udqp, NULL, &pdqp); @@ -1151,72 +1146,53 @@ xfs_ioctl_setattr( * Only allow changing of projid from init_user_ns since it is a * non user namespace aware identifier. */ - if (mask & FSX_PROJID) { - if (current_user_ns() != &init_user_ns) { - code = -EINVAL; - goto error_return; - } - - if (XFS_IS_QUOTA_RUNNING(mp) && - XFS_IS_PQUOTA_ON(mp) && - xfs_get_projid(ip) != fa->fsx_projid) { - ASSERT(tp); - code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, - pdqp, capable(CAP_FOWNER) ? - XFS_QMOPT_FORCE_RES : 0); - if (code) /* out of quota */ - goto error_return; - } + if (current_user_ns() != &init_user_ns) { + code = -EINVAL; + goto error_return; } - if (mask & FSX_EXTSIZE) { - /* - * Can't change extent size if any extents are allocated. - */ - if (ip->i_d.di_nextents && - ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != - fa->fsx_extsize)) { - code = -EINVAL; /* EFBIG? */ + if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && + xfs_get_projid(ip) != fa->fsx_projid) { + code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp, + capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); + if (code) /* out of quota */ goto error_return; - } + } - /* - * Extent size must be a multiple of the appropriate block - * size, if set at all. It must also be smaller than the - * maximum extent size supported by the filesystem. - * - * Also, for non-realtime files, limit the extent size hint to - * half the size of the AGs in the filesystem so alignment - * doesn't result in extents larger than an AG. - */ - if (fa->fsx_extsize != 0) { - xfs_extlen_t size; - xfs_fsblock_t extsize_fsb; + /* Can't change extent size if any extents are allocated. */ + code = -EINVAL; + if (ip->i_d.di_nextents && + ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) + goto error_return; - extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); - if (extsize_fsb > MAXEXTLEN) { - code = -EINVAL; - goto error_return; - } - - if (XFS_IS_REALTIME_INODE(ip) || - ((mask & FSX_XFLAGS) && - (fa->fsx_xflags & XFS_XFLAG_REALTIME))) { - size = mp->m_sb.sb_rextsize << - mp->m_sb.sb_blocklog; - } else { - size = mp->m_sb.sb_blocksize; - if (extsize_fsb > mp->m_sb.sb_agblocks / 2) { - code = -EINVAL; - goto error_return; - } - } - - if (fa->fsx_extsize % size) { - code = -EINVAL; + /* + * Extent size must be a multiple of the appropriate block size, if set + * at all. It must also be smaller than the maximum extent size + * supported by the filesystem. + * + * Also, for non-realtime files, limit the extent size hint to half the + * size of the AGs in the filesystem so alignment doesn't result in + * extents larger than an AG. + */ + if (fa->fsx_extsize != 0) { + xfs_extlen_t size; + xfs_fsblock_t extsize_fsb; + + extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); + if (extsize_fsb > MAXEXTLEN) + goto error_return; + + if (XFS_IS_REALTIME_INODE(ip) || + (fa->fsx_xflags & XFS_XFLAG_REALTIME)) { + size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; + } else { + size = mp->m_sb.sb_blocksize; + if (extsize_fsb > mp->m_sb.sb_agblocks / 2) goto error_return; - } } + + if (fa->fsx_extsize % size) + goto error_return; } @@ -1225,32 +1201,25 @@ xfs_ioctl_setattr( goto error_return; /* - * Change file ownership. Must be the owner or privileged. + * Change file ownership. Must be the owner or privileged. CAP_FSETID + * overrides the following restrictions: + * + * The set-user-ID and set-group-ID bits of a file will be cleared upon + * successful return from chown() */ - if (mask & FSX_PROJID) { - /* - * CAP_FSETID overrides the following restrictions: - * - * The set-user-ID and set-group-ID bits of a file will be - * cleared upon successful return from chown() - */ - if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && - !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) - ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); - /* - * Change the ownerships and register quota modifications - * in the transaction. - */ - if (xfs_get_projid(ip) != fa->fsx_projid) { - if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) { - olddquot = xfs_qm_vop_chown(tp, ip, - &ip->i_pdquot, pdqp); - } - ASSERT(ip->i_d.di_version > 1); - xfs_set_projid(ip, fa->fsx_projid); - } + if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && + !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID)) + ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); + /* Change the ownerships and register project quota modifications */ + if (xfs_get_projid(ip) != fa->fsx_projid) { + if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) { + olddquot = xfs_qm_vop_chown(tp, ip, + &ip->i_pdquot, pdqp); + } + ASSERT(ip->i_d.di_version > 1); + xfs_set_projid(ip, fa->fsx_projid); } /* @@ -1258,14 +1227,10 @@ xfs_ioctl_setattr( * extent size hint should be set on the inode. If no extent size flags * are set on the inode then unconditionally clear the extent size hint. */ - if (mask & FSX_EXTSIZE) { - int extsize = 0; - - if (ip->i_d.di_flags & - (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT)) - extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog; - ip->i_d.di_extsize = extsize; - } + if (ip->i_d.di_flags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT)) + ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog; + else + ip->i_d.di_extsize = 0; code = xfs_trans_commit(tp, 0); @@ -1293,18 +1258,15 @@ xfs_ioc_fssetxattr( void __user *arg) { struct fsxattr fa; - unsigned int mask; int error; if (copy_from_user(&fa, arg, sizeof(fa))) return -EFAULT; - mask = FSX_XFLAGS | FSX_EXTSIZE | FSX_PROJID; - error = mnt_want_write_file(filp); if (error) return error; - error = xfs_ioctl_setattr(ip, &fa, mask); + error = xfs_ioctl_setattr(ip, &fa); mnt_drop_write_file(filp); return error; } -- cgit v1.2.3 From 41c145271d79eae508321340b727d3e3c9a66664 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 2 Feb 2015 10:17:51 +1100 Subject: xfs: XFS_IOCTL_SETXATTR can run in user namespaces Currently XFS_IOCTL_SETXATTR will fail if run in a user namespace as it it not allowed to change project IDs. The current code, however, also prevents any other change being made as well, so things like extent size hints cannot be set in user namespaces. This is wrong, so only disallow access to project IDs and related flags from inside the init namespace. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a1f285411b74..b65817cbc318 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1119,6 +1119,19 @@ xfs_ioctl_setattr( !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) return -EINVAL; + /* + * Project Quota ID state is only allowed to change from within the init + * namespace. Enforce that restriction only if we are trying to change + * the quota ID state. Everything else is allowed in user namespaces. + */ + if (current_user_ns() != &init_user_ns) { + if (xfs_get_projid(ip) != fa->fsx_projid) + return -EINVAL; + if ((fa->fsx_xflags & XFS_XFLAG_PROJINHERIT) != + (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)) + return -EINVAL; + } + /* * If disk quotas is on, we make sure that the dquots do exist on disk, * before we start any other transactions. Trying to do this later @@ -1141,15 +1154,6 @@ xfs_ioctl_setattr( goto error_free_dquots; } - /* - * Do a quota reservation only if projid is actually going to change. - * Only allow changing of projid from init_user_ns since it is a - * non user namespace aware identifier. - */ - if (current_user_ns() != &init_user_ns) { - code = -EINVAL; - goto error_return; - } if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && xfs_get_projid(ip) != fa->fsx_projid) { -- cgit v1.2.3 From d4388d3c0988ec00787ad1f8e63b5e2a6abef1dc Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 2 Feb 2015 10:22:20 +1100 Subject: xfs: factor extsize hint checking out of xfs_ioctl_setattr The extent size hint change checking is fairly complex, so isolate that into it's own function. This simplifies the logic flow of the setattr code, making it easier to read. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 90 +++++++++++++++++++++++++++++++----------------------- 1 file changed, 51 insertions(+), 39 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index b65817cbc318..9f808539fc61 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1098,6 +1098,51 @@ out_cancel: return ERR_PTR(error); } +int +xfs_ioctl_setattr_check_extsize( + struct xfs_inode *ip, + struct fsxattr *fa) +{ + struct xfs_mount *mp = ip->i_mount; + + /* Can't change extent size if any extents are allocated. */ + if (ip->i_d.di_nextents && + ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) + return -EINVAL; + + /* + * Extent size must be a multiple of the appropriate block size, if set + * at all. It must also be smaller than the maximum extent size + * supported by the filesystem. + * + * Also, for non-realtime files, limit the extent size hint to half the + * size of the AGs in the filesystem so alignment doesn't result in + * extents larger than an AG. + */ + if (fa->fsx_extsize != 0) { + xfs_extlen_t size; + xfs_fsblock_t extsize_fsb; + + extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); + if (extsize_fsb > MAXEXTLEN) + return -EINVAL; + + if (XFS_IS_REALTIME_INODE(ip) || + (fa->fsx_xflags & XFS_XFLAG_REALTIME)) { + size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; + } else { + size = mp->m_sb.sb_blocksize; + if (extsize_fsb > mp->m_sb.sb_agblocks / 2) + return -EINVAL; + } + + if (fa->fsx_extsize % size) + return -EINVAL; + } + return 0; +} + + STATIC int xfs_ioctl_setattr( xfs_inode_t *ip, @@ -1160,49 +1205,16 @@ xfs_ioctl_setattr( code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp, capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); if (code) /* out of quota */ - goto error_return; - } - - /* Can't change extent size if any extents are allocated. */ - code = -EINVAL; - if (ip->i_d.di_nextents && - ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) - goto error_return; - - /* - * Extent size must be a multiple of the appropriate block size, if set - * at all. It must also be smaller than the maximum extent size - * supported by the filesystem. - * - * Also, for non-realtime files, limit the extent size hint to half the - * size of the AGs in the filesystem so alignment doesn't result in - * extents larger than an AG. - */ - if (fa->fsx_extsize != 0) { - xfs_extlen_t size; - xfs_fsblock_t extsize_fsb; - - extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); - if (extsize_fsb > MAXEXTLEN) - goto error_return; - - if (XFS_IS_REALTIME_INODE(ip) || - (fa->fsx_xflags & XFS_XFLAG_REALTIME)) { - size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; - } else { - size = mp->m_sb.sb_blocksize; - if (extsize_fsb > mp->m_sb.sb_agblocks / 2) - goto error_return; - } - - if (fa->fsx_extsize % size) - goto error_return; + goto error_trans_cancel; } + code = xfs_ioctl_setattr_check_extsize(ip, fa); + if (code) + goto error_trans_cancel; code = xfs_ioctl_setattr_xflags(tp, ip, fa); if (code) - goto error_return; + goto error_trans_cancel; /* * Change file ownership. Must be the owner or privileged. CAP_FSETID @@ -1247,7 +1259,7 @@ xfs_ioctl_setattr( return code; -error_return: +error_trans_cancel: xfs_trans_cancel(tp, 0); error_free_dquots: xfs_qm_dqrele(udqp); -- cgit v1.2.3 From 23bd0735cfdf5322170a9ef48c7d47c2e6567ba8 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 2 Feb 2015 10:22:53 +1100 Subject: xfs: factor projid hint checking out of xfs_ioctl_setattr The project ID change checking is one of the few remaining open coded checks in xfs_ioctl_setattr(). Factor it into a helper function so that the setattr code mostly becomes a flow of check and action helpers, making it easier to read and follow. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 50 +++++++++++++++++++++++++++++++------------------- 1 file changed, 31 insertions(+), 19 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 9f808539fc61..1f186d2eec06 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1142,6 +1142,34 @@ xfs_ioctl_setattr_check_extsize( return 0; } +int +xfs_ioctl_setattr_check_projid( + struct xfs_inode *ip, + struct fsxattr *fa) +{ + /* Disallow 32bit project ids if projid32bit feature is not enabled. */ + if (fa->fsx_projid > (__uint16_t)-1 && + !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) + return -EINVAL; + + /* + * Project Quota ID state is only allowed to change from within the init + * namespace. Enforce that restriction only if we are trying to change + * the quota ID state. Everything else is allowed in user namespaces. + */ + if (current_user_ns() == &init_user_ns) + return 0; + + if (xfs_get_projid(ip) != fa->fsx_projid) + return -EINVAL; + if ((fa->fsx_xflags & XFS_XFLAG_PROJINHERIT) != + (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)) + return -EINVAL; + + return 0; +} + + STATIC int xfs_ioctl_setattr( @@ -1157,25 +1185,9 @@ xfs_ioctl_setattr( trace_xfs_ioctl_setattr(ip); - /* - * Disallow 32bit project ids when projid32bit feature is not enabled. - */ - if (fa->fsx_projid > (__uint16_t)-1 && - !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) - return -EINVAL; - - /* - * Project Quota ID state is only allowed to change from within the init - * namespace. Enforce that restriction only if we are trying to change - * the quota ID state. Everything else is allowed in user namespaces. - */ - if (current_user_ns() != &init_user_ns) { - if (xfs_get_projid(ip) != fa->fsx_projid) - return -EINVAL; - if ((fa->fsx_xflags & XFS_XFLAG_PROJINHERIT) != - (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)) - return -EINVAL; - } + code = xfs_ioctl_setattr_check_projid(ip, fa); + if (code) + return code; /* * If disk quotas is on, we make sure that the dquots do exist on disk, -- cgit v1.2.3 From 9b94fcc39822b450af823b3d8cbef6b53ce87ed9 Mon Sep 17 00:00:00 2001 From: Iustin Pop Date: Mon, 2 Feb 2015 10:26:26 +1100 Subject: xfs: fix behaviour of XFS_IOC_FSSETXATTR on directories Currently, the ioctl handling code for XFS_IOC_FSSETXATTR treats all targets as regular files: it refuses to change the extent size if extents are allocated. This is wrong for directories, as there the extent size is only used as a default for children. The patch fixes this issue and improves validation of flag combinations: - only disallow extent size changes after extents have been allocated for regular files - only allow XFS_XFLAG_EXTSIZE for regular files - only allow XFS_XFLAG_EXTSZINHERIT for directories - automatically clear the flags if the extent size is zero Thanks to Dave Chinner for guidance on the proper fix for this issue. [dchinner: ported changes onto cleanup series. Makes changes clear and obvious.] [dchinner: added comments documenting validity checking rules.] Signed-off-by: Iustin Pop Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1f186d2eec06..0f6b6abb7c7a 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1098,6 +1098,20 @@ out_cancel: return ERR_PTR(error); } +/* + * extent size hint validation is somewhat cumbersome. Rules are: + * + * 1. extent size hint is only valid for directories and regular files + * 2. XFS_XFLAG_EXTSIZE is only valid for regular files + * 3. XFS_XFLAG_EXTSZINHERIT is only valid for directories. + * 4. can only be changed on regular files if no extents are allocated + * 5. can be changed on directories at any time + * 6. extsize hint of 0 turns off hints, clears inode flags. + * 7. Extent size must be a multiple of the appropriate block size. + * 8. for non-realtime files, the extent size hint must be limited + * to half the AG size to avoid alignment extending the extent beyond the + * limits of the AG. + */ int xfs_ioctl_setattr_check_extsize( struct xfs_inode *ip, @@ -1105,20 +1119,17 @@ xfs_ioctl_setattr_check_extsize( { struct xfs_mount *mp = ip->i_mount; - /* Can't change extent size if any extents are allocated. */ - if (ip->i_d.di_nextents && + if ((fa->fsx_xflags & XFS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode)) + return -EINVAL; + + if ((fa->fsx_xflags & XFS_XFLAG_EXTSZINHERIT) && + !S_ISDIR(ip->i_d.di_mode)) + return -EINVAL; + + if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents && ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) return -EINVAL; - /* - * Extent size must be a multiple of the appropriate block size, if set - * at all. It must also be smaller than the maximum extent size - * supported by the filesystem. - * - * Also, for non-realtime files, limit the extent size hint to half the - * size of the AGs in the filesystem so alignment doesn't result in - * extents larger than an AG. - */ if (fa->fsx_extsize != 0) { xfs_extlen_t size; xfs_fsblock_t extsize_fsb; @@ -1138,7 +1149,9 @@ xfs_ioctl_setattr_check_extsize( if (fa->fsx_extsize % size) return -EINVAL; - } + } else + fa->fsx_xflags &= ~(XFS_XFLAG_EXTSIZE | XFS_XFLAG_EXTSZINHERIT); + return 0; } @@ -1169,8 +1182,6 @@ xfs_ioctl_setattr_check_projid( return 0; } - - STATIC int xfs_ioctl_setattr( xfs_inode_t *ip, -- cgit v1.2.3 From 15d0f5ea348b9c4e6d41df294dde38a56a39c7bf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 2 Feb 2015 10:07:59 -0700 Subject: Make super_blocks and sb_lock static The only user outside of fs/super.c is gone now Signed-off-by: Al Viro Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/super.c | 4 ++-- include/linux/fs.h | 2 -- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/super.c b/fs/super.c index 3b4dadafdd60..05a021638b11 100644 --- a/fs/super.c +++ b/fs/super.c @@ -36,8 +36,8 @@ #include "internal.h" -LIST_HEAD(super_blocks); -DEFINE_SPINLOCK(sb_lock); +static LIST_HEAD(super_blocks); +static DEFINE_SPINLOCK(sb_lock); static char *sb_writers_name[SB_FREEZE_LEVELS] = { "sb_writers", diff --git a/include/linux/fs.h b/include/linux/fs.h index 65d02de342e1..2f717baefdf8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1183,8 +1183,6 @@ struct mm_struct; #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ -extern struct list_head super_blocks; -extern spinlock_t sb_lock; /* Possible states of 'frozen' field */ enum { -- cgit v1.2.3 From 2ab99ee12440e66ec1efd2a98599010471de785e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Jan 2015 19:14:02 +0100 Subject: fs: track fl_owner for leases Just like for other lock types we should allow different owners to have a read lease on a file. Currently this can't happen, but with the addition of pNFS layout leases we'll need this feature. Signed-off-by: Christoph Hellwig --- fs/locks.c | 12 +++++++----- fs/nfsd/nfs4state.c | 2 +- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/locks.c b/fs/locks.c index 4d0d41163a50..22ac7694cc84 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1661,7 +1661,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr */ error = -EAGAIN; list_for_each_entry(fl, &ctx->flc_lease, fl_list) { - if (fl->fl_file == filp) { + if (fl->fl_file == filp && + fl->fl_owner == lease->fl_owner) { my_fl = fl; continue; } @@ -1721,7 +1722,7 @@ out: return error; } -static int generic_delete_lease(struct file *filp) +static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lock *fl, *victim = NULL; @@ -1737,7 +1738,8 @@ static int generic_delete_lease(struct file *filp) spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { - if (fl->fl_file == filp) { + if (fl->fl_file == filp && + fl->fl_owner == owner) { victim = fl; break; } @@ -1778,7 +1780,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp, switch (arg) { case F_UNLCK: - return generic_delete_lease(filp); + return generic_delete_lease(filp, *priv); case F_RDLCK: case F_WRLCK: if (!(*flp)->fl_lmops->lm_break) { @@ -1857,7 +1859,7 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) int fcntl_setlease(unsigned int fd, struct file *filp, long arg) { if (arg == F_UNLCK) - return vfs_setlease(filp, F_UNLCK, NULL, NULL); + return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); return do_fcntl_add_lease(fd, filp, arg); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 370a53a5da13..e6b354a0d89e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -683,7 +683,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp) spin_unlock(&fp->fi_lock); if (filp) { - vfs_setlease(filp, F_UNLCK, NULL, NULL); + vfs_setlease(filp, F_UNLCK, NULL, (void **)&fp); fput(filp); } } -- cgit v1.2.3 From 11afe9f76e121e960445deee5b7f26f0787a1990 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Jan 2015 19:17:03 +0100 Subject: fs: add FL_LAYOUT lease type This (ab-)uses the file locking code to allow filesystems to recall outstanding pNFS layouts on a file. This new lease type is similar but not quite the same as FL_DELEG. A FL_LAYOUT lease can always be granted, an a per-filesystem lock (XFS iolock for the initial implementation) ensures not FL_LAYOUT leases granted when we would need to recall them. Also included are changes that allow multiple outstanding read leases of different types on the same file as long as they have a differnt owner. This wasn't a problem until now as nfsd never set FL_LEASE leases, and no one else used FL_DELEG leases, but given that nfsd will also issues FL_LAYOUT leases we will have to handle it now. Signed-off-by: Christoph Hellwig --- fs/locks.c | 14 ++++++++++---- include/linux/fs.h | 16 ++++++++++++++++ 2 files changed, 26 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/locks.c b/fs/locks.c index 22ac7694cc84..4753218f308e 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -137,7 +137,7 @@ #define IS_POSIX(fl) (fl->fl_flags & FL_POSIX) #define IS_FLOCK(fl) (fl->fl_flags & FL_FLOCK) -#define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG)) +#define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) #define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK) static bool lease_breaking(struct file_lock *fl) @@ -1371,6 +1371,8 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) { + if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) + return false; if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) return false; return locks_conflict(breaker, lease); @@ -1594,11 +1596,14 @@ int fcntl_getlease(struct file *filp) * conflict with the lease we're trying to set. */ static int -check_conflicting_open(const struct dentry *dentry, const long arg) +check_conflicting_open(const struct dentry *dentry, const long arg, int flags) { int ret = 0; struct inode *inode = dentry->d_inode; + if (flags & FL_LAYOUT) + return 0; + if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0)) return -EAGAIN; @@ -1647,7 +1652,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); - error = check_conflicting_open(dentry, arg); + error = check_conflicting_open(dentry, arg, lease->fl_flags); if (error) goto out; @@ -1703,7 +1708,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * precedes these checks. */ smp_mb(); - error = check_conflicting_open(dentry, arg); + error = check_conflicting_open(dentry, arg, lease->fl_flags); if (error) { locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt); goto out; @@ -1787,6 +1792,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp, WARN_ON_ONCE(1); return -ENOLCK; } + return generic_add_lease(filp, arg, flp, priv); default: return -EINVAL; diff --git a/include/linux/fs.h b/include/linux/fs.h index ddd2fa7cefd3..84740145f835 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -875,6 +875,7 @@ static inline struct file *get_file(struct file *f) #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ +#define FL_LAYOUT 2048 /* outstanding pNFS layout */ /* * Special return value from posix_lock_file() and vfs_lock_file() for @@ -2037,6 +2038,16 @@ static inline int break_deleg_wait(struct inode **delegated_inode) return ret; } +static inline int break_layout(struct inode *inode, bool wait) +{ + smp_mb(); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + return __break_lease(inode, + wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, + FL_LAYOUT); + return 0; +} + #else /* !CONFIG_FILE_LOCKING */ static inline int locks_mandatory_locked(struct file *file) { @@ -2092,6 +2103,11 @@ static inline int break_deleg_wait(struct inode **delegated_inode) return 0; } +static inline int break_layout(struct inode *inode, bool wait) +{ + return 0; +} + #endif /* CONFIG_FILE_LOCKING */ /* fs/open.c */ -- cgit v1.2.3 From 4d94c2ef2008a07fb1467e33da156de6fba9aad1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Aug 2014 08:41:48 +0200 Subject: nfsd: move nfsd_fh_match to nfsfh.h The pnfs code will need it too. Also remove the nfsd_ prefix to match the other filehandle helpers in that file. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4state.c | 12 ++---------- fs/nfsd/nfsfh.h | 9 +++++++++ 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index e6b354a0d89e..eb0336e526d2 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -398,14 +398,6 @@ static unsigned int file_hashval(struct knfsd_fh *fh) return nfsd_fh_hashval(fh) & (FILE_HASH_SIZE - 1); } -static bool nfsd_fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) -{ - return fh1->fh_size == fh2->fh_size && - !memcmp(fh1->fh_base.fh_pad, - fh2->fh_base.fh_pad, - fh1->fh_size); -} - static struct hlist_head file_hashtbl[FILE_HASH_SIZE]; static void @@ -3295,7 +3287,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval) struct nfs4_file *fp; hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) { - if (nfsd_fh_match(&fp->fi_fhandle, fh)) { + if (fh_match(&fp->fi_fhandle, fh)) { if (atomic_inc_not_zero(&fp->fi_ref)) return fp; } @@ -4290,7 +4282,7 @@ laundromat_main(struct work_struct *laundry) static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp) { - if (!nfsd_fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle)) + if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle)) return nfserr_bad_stateid; return nfs_ok; } diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 08236d70c667..e24d95436db3 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -187,6 +187,15 @@ fh_init(struct svc_fh *fhp, int maxsize) return fhp; } +static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +{ + if (fh1->fh_size != fh2->fh_size) + return false; + if (memcmp(fh1->fh_base.fh_pad, fh2->fh_base.fh_pad, fh1->fh_size) != 0) + return false; + return true; +} + #ifdef CONFIG_NFSD_V3 /* * The wcc data stored in current_fh should be cleared -- cgit v1.2.3 From 9558f2500a2028ffc05cfd8fceaa0fe0a0a3804e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 13 Aug 2014 20:56:13 +0200 Subject: nfsd: add fh_fsid_match helper Add a helper to check that the fsid parts of two file handles match. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfsfh.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs') diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index e24d95436db3..84cae2079d21 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -196,6 +196,15 @@ static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) return true; } +static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +{ + if (fh1->fh_fsid_type != fh2->fh_fsid_type) + return false; + if (memcmp(fh1->fh_fsid, fh2->fh_fsid, key_len(fh1->fh_fsid_type) != 0)) + return false; + return true; +} + #ifdef CONFIG_NFSD_V3 /* * The wcc data stored in current_fh should be cleared -- cgit v1.2.3 From cd61c522318f2c30ce731bfdb14e7c34203e3d7c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Aug 2014 08:44:57 +0200 Subject: nfsd: make lookup/alloc/unhash_stid available outside nfs4state.c Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4state.c | 8 ++++---- fs/nfsd/state.h | 6 ++++++ 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index eb0336e526d2..75faacb03e8e 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -476,7 +476,7 @@ static void nfs4_file_put_access(struct nfs4_file *fp, u32 access) __nfs4_file_put_access(fp, O_RDONLY); } -static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, +struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab) { struct nfs4_stid *stid; @@ -680,7 +680,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp) } } -static void unhash_stid(struct nfs4_stid *s) +void nfs4_unhash_stid(struct nfs4_stid *s) { s->sc_type = 0; } @@ -988,7 +988,7 @@ static void unhash_lock_stateid(struct nfs4_ol_stateid *stp) list_del_init(&stp->st_locks); unhash_ol_stateid(stp); - unhash_stid(&stp->st_stid); + nfs4_unhash_stid(&stp->st_stid); } static void release_lock_stateid(struct nfs4_ol_stateid *stp) @@ -4433,7 +4433,7 @@ out_unlock: return status; } -static __be32 +__be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index dab6553ceea1..55a3ece5fe06 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -545,6 +545,12 @@ struct nfsd_net; extern __be32 nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate, stateid_t *stateid, int flags, struct file **filp); +__be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, + stateid_t *stateid, unsigned char typemask, + struct nfs4_stid **s, struct nfsd_net *nn); +struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, + struct kmem_cache *slab); +void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); extern void nfs4_release_reclaim(struct nfsd_net *); -- cgit v1.2.3 From e6ba76e1944613f16dddcba4b5836954ed3981f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Aug 2014 08:50:16 +0200 Subject: nfsd: make find/get/put file available outside nfs4state.c Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4state.c | 10 ++-------- fs/nfsd/state.h | 7 +++++++ 2 files changed, 9 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 75faacb03e8e..f5fc5d72c362 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -272,7 +272,7 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu) kmem_cache_free(file_slab, fp); } -static inline void +void put_nfs4_file(struct nfs4_file *fi) { might_lock(&state_lock); @@ -285,12 +285,6 @@ put_nfs4_file(struct nfs4_file *fi) } } -static inline void -get_nfs4_file(struct nfs4_file *fi) -{ - atomic_inc(&fi->fi_ref); -} - static struct file * __nfs4_get_fd(struct nfs4_file *f, int oflag) { @@ -3295,7 +3289,7 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval) return NULL; } -static struct nfs4_file * +struct nfs4_file * find_file(struct knfsd_fh *fh) { struct nfs4_file *fp; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 55a3ece5fe06..8bc961e192f2 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -573,6 +573,13 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name, struct nfsd_net *nn); extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn); +struct nfs4_file *find_file(struct knfsd_fh *fh); +void put_nfs4_file(struct nfs4_file *fi); +static inline void get_nfs4_file(struct nfs4_file *fi) +{ + atomic_inc(&fi->fi_ref); +} + /* grace period management */ void nfsd4_end_grace(struct nfsd_net *nn); -- cgit v1.2.3 From 4d227fca1b32f95f1246894ebef879efccb2ec15 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 17 Aug 2014 07:40:00 -0500 Subject: nfsd: make find_any_file available outside nfs4state.c Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4state.c | 2 +- fs/nfsd/state.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index f5fc5d72c362..eefd29ec43f2 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -342,7 +342,7 @@ find_readable_file(struct nfs4_file *f) return ret; } -static struct file * +struct file * find_any_file(struct nfs4_file *f) { struct file *ret; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 8bc961e192f2..38ebb1268b59 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -579,6 +579,7 @@ static inline void get_nfs4_file(struct nfs4_file *fi) { atomic_inc(&fi->fi_ref); } +struct file *find_any_file(struct nfs4_file *f); /* grace period management */ void nfsd4_end_grace(struct nfsd_net *nn); -- cgit v1.2.3 From 9cf514ccfacb301f3b1b4509a8ce25dffad55880 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 5 May 2014 13:11:59 +0200 Subject: nfsd: implement pNFS operations Add support for the GETDEVICEINFO, LAYOUTGET, LAYOUTCOMMIT and LAYOUTRETURN NFSv4.1 operations, as well as backing code to manage outstanding layouts and devices. Layout management is very straight forward, with a nfs4_layout_stateid structure that extends nfs4_stid to manage layout stateids as the top-level structure. It is linked into the nfs4_file and nfs4_client structures like the other stateids, and contains a linked list of layouts that hang of the stateid. The actual layout operations are implemented in layout drivers that are not part of this commit, but will be added later. The worst part of this commit is the management of the pNFS device IDs, which suffers from a specification that is not sanely implementable due to the fact that the device-IDs are global and not bound to an export, and have a small enough size so that we can't store the fsid portion of a file handle, and must never be reused. As we still do need perform all export authentication and validation checks on a device ID passed to GETDEVICEINFO we are caught between a rock and a hard place. To work around this issue we add a new hash that maps from a 64-bit integer to a fsid so that we can look up the export to authenticate against it, a 32-bit integer as a generation that we can bump when changing the device, and a currently unused 32-bit integer that could be used in the future to handle more than a single device per export. Entries in this hash table are never deleted as we can't reuse the ids anyway, and would have a severe lifetime problem anyway as Linux export structures are temporary structures that can go away under load. Parts of the XDR data, structures and marshaling/unmarshaling code, as well as many concepts are derived from the old pNFS server implementation from Andy Adamson, Benny Halevy, Dean Hildebrand, Marc Eshel, Fred Isaman, Mike Sager, Ricardo Labiaga and many others. Signed-off-by: Christoph Hellwig --- fs/nfsd/Kconfig | 10 + fs/nfsd/Makefile | 1 + fs/nfsd/export.c | 8 + fs/nfsd/export.h | 2 + fs/nfsd/nfs4layouts.c | 487 +++++++++++++++++++++++++++++++++++++++ fs/nfsd/nfs4proc.c | 302 ++++++++++++++++++++++++ fs/nfsd/nfs4state.c | 16 +- fs/nfsd/nfs4xdr.c | 312 +++++++++++++++++++++++++ fs/nfsd/nfsctl.c | 9 +- fs/nfsd/nfsd.h | 16 +- fs/nfsd/pnfs.h | 80 +++++++ fs/nfsd/state.h | 21 ++ fs/nfsd/xdr4.h | 59 +++++ include/linux/nfs4.h | 1 + include/uapi/linux/nfsd/debug.h | 1 + include/uapi/linux/nfsd/export.h | 4 +- 16 files changed, 1324 insertions(+), 5 deletions(-) create mode 100644 fs/nfsd/nfs4layouts.c create mode 100644 fs/nfsd/pnfs.h (limited to 'fs') diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 73395156bdb4..683bf718aead 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -82,6 +82,16 @@ config NFSD_V4 If unsure, say N. +config NFSD_PNFS + bool "NFSv4.1 server support for Parallel NFS (pNFS)" + depends on NFSD_V4 + help + This option enables support for the parallel NFS features of the + minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS + server. + + If unsure, say N. + config NFSD_V4_SECURITY_LABEL bool "Provide Security Label support for NFSv4 server" depends on NFSD_V4 && SECURITY diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index af32ef06b4fe..5806270a8567 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -12,3 +12,4 @@ nfsd-$(CONFIG_NFSD_V3) += nfs3proc.o nfs3xdr.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ nfs4acl.o nfs4callback.o nfs4recover.o +nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 30a739d896ff..c3e3b6e55ae2 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -20,6 +20,7 @@ #include "nfsd.h" #include "nfsfh.h" #include "netns.h" +#include "pnfs.h" #define NFSDDBG_FACILITY NFSDDBG_EXPORT @@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) exp.ex_client = dom; exp.cd = cd; + exp.ex_devid_map = NULL; /* expiry */ err = -EINVAL; @@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) if (!gid_valid(exp.ex_anon_gid)) goto out4; err = 0; + + nfsd4_setup_layout_type(&exp); } expp = svc_export_lookup(&exp); @@ -703,6 +707,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) new->ex_fslocs.locations = NULL; new->ex_fslocs.locations_count = 0; new->ex_fslocs.migrated = 0; + new->ex_layout_type = 0; new->ex_uuid = NULL; new->cd = item->cd; } @@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) new->ex_anon_uid = item->ex_anon_uid; new->ex_anon_gid = item->ex_anon_gid; new->ex_fsid = item->ex_fsid; + new->ex_devid_map = item->ex_devid_map; + item->ex_devid_map = NULL; new->ex_uuid = item->ex_uuid; item->ex_uuid = NULL; new->ex_fslocs.locations = item->ex_fslocs.locations; @@ -725,6 +732,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) item->ex_fslocs.locations_count = 0; new->ex_fslocs.migrated = item->ex_fslocs.migrated; item->ex_fslocs.migrated = 0; + new->ex_layout_type = item->ex_layout_type; new->ex_nflavors = item->ex_nflavors; for (i = 0; i < MAX_SECINFO_LIST; i++) { new->ex_flavors[i] = item->ex_flavors[i]; diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index 04dc8c167b0c..1f52bfcc436f 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -56,6 +56,8 @@ struct svc_export { struct nfsd4_fs_locations ex_fslocs; uint32_t ex_nflavors; struct exp_flavor_info ex_flavors[MAX_SECINFO_LIST]; + enum pnfs_layouttype ex_layout_type; + struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; }; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c new file mode 100644 index 000000000000..8273270418b1 --- /dev/null +++ b/fs/nfsd/nfs4layouts.c @@ -0,0 +1,487 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ +#include +#include + +#include "pnfs.h" +#include "netns.h" + +#define NFSDDBG_FACILITY NFSDDBG_PNFS + +struct nfs4_layout { + struct list_head lo_perstate; + struct nfs4_layout_stateid *lo_state; + struct nfsd4_layout_seg lo_seg; +}; + +static struct kmem_cache *nfs4_layout_cache; +static struct kmem_cache *nfs4_layout_stateid_cache; + +const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { +}; + +/* pNFS device ID to export fsid mapping */ +#define DEVID_HASH_BITS 8 +#define DEVID_HASH_SIZE (1 << DEVID_HASH_BITS) +#define DEVID_HASH_MASK (DEVID_HASH_SIZE - 1) +static u64 nfsd_devid_seq = 1; +static struct list_head nfsd_devid_hash[DEVID_HASH_SIZE]; +static DEFINE_SPINLOCK(nfsd_devid_lock); + +static inline u32 devid_hashfn(u64 idx) +{ + return jhash_2words(idx, idx >> 32, 0) & DEVID_HASH_MASK; +} + +static void +nfsd4_alloc_devid_map(const struct svc_fh *fhp) +{ + const struct knfsd_fh *fh = &fhp->fh_handle; + size_t fsid_len = key_len(fh->fh_fsid_type); + struct nfsd4_deviceid_map *map, *old; + int i; + + map = kzalloc(sizeof(*map) + fsid_len, GFP_KERNEL); + if (!map) + return; + + map->fsid_type = fh->fh_fsid_type; + memcpy(&map->fsid, fh->fh_fsid, fsid_len); + + spin_lock(&nfsd_devid_lock); + if (fhp->fh_export->ex_devid_map) + goto out_unlock; + + for (i = 0; i < DEVID_HASH_SIZE; i++) { + list_for_each_entry(old, &nfsd_devid_hash[i], hash) { + if (old->fsid_type != fh->fh_fsid_type) + continue; + if (memcmp(old->fsid, fh->fh_fsid, + key_len(old->fsid_type))) + continue; + + fhp->fh_export->ex_devid_map = old; + goto out_unlock; + } + } + + map->idx = nfsd_devid_seq++; + list_add_tail_rcu(&map->hash, &nfsd_devid_hash[devid_hashfn(map->idx)]); + fhp->fh_export->ex_devid_map = map; + map = NULL; + +out_unlock: + spin_unlock(&nfsd_devid_lock); + kfree(map); +} + +struct nfsd4_deviceid_map * +nfsd4_find_devid_map(int idx) +{ + struct nfsd4_deviceid_map *map, *ret = NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(map, &nfsd_devid_hash[devid_hashfn(idx)], hash) + if (map->idx == idx) + ret = map; + rcu_read_unlock(); + + return ret; +} + +int +nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, + u32 device_generation) +{ + if (!fhp->fh_export->ex_devid_map) { + nfsd4_alloc_devid_map(fhp); + if (!fhp->fh_export->ex_devid_map) + return -ENOMEM; + } + + id->fsid_idx = fhp->fh_export->ex_devid_map->idx; + id->generation = device_generation; + id->pad = 0; + return 0; +} + +void nfsd4_setup_layout_type(struct svc_export *exp) +{ + if (exp->ex_flags & NFSEXP_NOPNFS) + return; +} + +static void +nfsd4_free_layout_stateid(struct nfs4_stid *stid) +{ + struct nfs4_layout_stateid *ls = layoutstateid(stid); + struct nfs4_client *clp = ls->ls_stid.sc_client; + struct nfs4_file *fp = ls->ls_stid.sc_file; + + spin_lock(&clp->cl_lock); + list_del_init(&ls->ls_perclnt); + spin_unlock(&clp->cl_lock); + + spin_lock(&fp->fi_lock); + list_del_init(&ls->ls_perfile); + spin_unlock(&fp->fi_lock); + + kmem_cache_free(nfs4_layout_stateid_cache, ls); +} + +static struct nfs4_layout_stateid * +nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, + struct nfs4_stid *parent, u32 layout_type) +{ + struct nfs4_client *clp = cstate->clp; + struct nfs4_file *fp = parent->sc_file; + struct nfs4_layout_stateid *ls; + struct nfs4_stid *stp; + + stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache); + if (!stp) + return NULL; + stp->sc_free = nfsd4_free_layout_stateid; + get_nfs4_file(fp); + stp->sc_file = fp; + + ls = layoutstateid(stp); + INIT_LIST_HEAD(&ls->ls_perclnt); + INIT_LIST_HEAD(&ls->ls_perfile); + spin_lock_init(&ls->ls_lock); + INIT_LIST_HEAD(&ls->ls_layouts); + ls->ls_layout_type = layout_type; + + spin_lock(&clp->cl_lock); + stp->sc_type = NFS4_LAYOUT_STID; + list_add(&ls->ls_perclnt, &clp->cl_lo_states); + spin_unlock(&clp->cl_lock); + + spin_lock(&fp->fi_lock); + list_add(&ls->ls_perfile, &fp->fi_lo_states); + spin_unlock(&fp->fi_lock); + + return ls; +} + +__be32 +nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, stateid_t *stateid, + bool create, u32 layout_type, struct nfs4_layout_stateid **lsp) +{ + struct nfs4_layout_stateid *ls; + struct nfs4_stid *stid; + unsigned char typemask = NFS4_LAYOUT_STID; + __be32 status; + + if (create) + typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID); + + status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid, + net_generic(SVC_NET(rqstp), nfsd_net_id)); + if (status) + goto out; + + if (!fh_match(&cstate->current_fh.fh_handle, + &stid->sc_file->fi_fhandle)) { + status = nfserr_bad_stateid; + goto out_put_stid; + } + + if (stid->sc_type != NFS4_LAYOUT_STID) { + ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type); + nfs4_put_stid(stid); + + status = nfserr_jukebox; + if (!ls) + goto out; + } else { + ls = container_of(stid, struct nfs4_layout_stateid, ls_stid); + + status = nfserr_bad_stateid; + if (stateid->si_generation > stid->sc_stateid.si_generation) + goto out_put_stid; + if (layout_type != ls->ls_layout_type) + goto out_put_stid; + } + + *lsp = ls; + return 0; + +out_put_stid: + nfs4_put_stid(stid); +out: + return status; +} + +static inline u64 +layout_end(struct nfsd4_layout_seg *seg) +{ + u64 end = seg->offset + seg->length; + return end >= seg->offset ? end : NFS4_MAX_UINT64; +} + +static void +layout_update_len(struct nfsd4_layout_seg *lo, u64 end) +{ + if (end == NFS4_MAX_UINT64) + lo->length = NFS4_MAX_UINT64; + else + lo->length = end - lo->offset; +} + +static bool +layouts_overlapping(struct nfs4_layout *lo, struct nfsd4_layout_seg *s) +{ + if (s->iomode != IOMODE_ANY && s->iomode != lo->lo_seg.iomode) + return false; + if (layout_end(&lo->lo_seg) <= s->offset) + return false; + if (layout_end(s) <= lo->lo_seg.offset) + return false; + return true; +} + +static bool +layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new) +{ + if (lo->iomode != new->iomode) + return false; + if (layout_end(new) < lo->offset) + return false; + if (layout_end(lo) < new->offset) + return false; + + lo->offset = min(lo->offset, new->offset); + layout_update_len(lo, max(layout_end(lo), layout_end(new))); + return true; +} + +__be32 +nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) +{ + struct nfsd4_layout_seg *seg = &lgp->lg_seg; + struct nfs4_layout *lp, *new = NULL; + + spin_lock(&ls->ls_lock); + list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) { + if (layouts_try_merge(&lp->lo_seg, seg)) + goto done; + } + spin_unlock(&ls->ls_lock); + + new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL); + if (!new) + return nfserr_jukebox; + memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg)); + new->lo_state = ls; + + spin_lock(&ls->ls_lock); + list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) { + if (layouts_try_merge(&lp->lo_seg, seg)) + goto done; + } + + atomic_inc(&ls->ls_stid.sc_count); + list_add_tail(&new->lo_perstate, &ls->ls_layouts); + new = NULL; +done: + update_stateid(&ls->ls_stid.sc_stateid); + memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); + spin_unlock(&ls->ls_lock); + if (new) + kmem_cache_free(nfs4_layout_cache, new); + return nfs_ok; +} + +static void +nfsd4_free_layouts(struct list_head *reaplist) +{ + while (!list_empty(reaplist)) { + struct nfs4_layout *lp = list_first_entry(reaplist, + struct nfs4_layout, lo_perstate); + + list_del(&lp->lo_perstate); + nfs4_put_stid(&lp->lo_state->ls_stid); + kmem_cache_free(nfs4_layout_cache, lp); + } +} + +static void +nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg, + struct list_head *reaplist) +{ + struct nfsd4_layout_seg *lo = &lp->lo_seg; + u64 end = layout_end(lo); + + if (seg->offset <= lo->offset) { + if (layout_end(seg) >= end) { + list_move_tail(&lp->lo_perstate, reaplist); + return; + } + end = seg->offset; + } else { + /* retain the whole layout segment on a split. */ + if (layout_end(seg) < end) { + dprintk("%s: split not supported\n", __func__); + return; + } + + lo->offset = layout_end(seg); + } + + layout_update_len(lo, end); +} + +__be32 +nfsd4_return_file_layouts(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp) +{ + struct nfs4_layout_stateid *ls; + struct nfs4_layout *lp, *n; + LIST_HEAD(reaplist); + __be32 nfserr; + int found = 0; + + nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid, + false, lrp->lr_layout_type, + &ls); + if (nfserr) + return nfserr; + + spin_lock(&ls->ls_lock); + list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) { + if (layouts_overlapping(lp, &lrp->lr_seg)) { + nfsd4_return_file_layout(lp, &lrp->lr_seg, &reaplist); + found++; + } + } + if (!list_empty(&ls->ls_layouts)) { + if (found) { + update_stateid(&ls->ls_stid.sc_stateid); + memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid, + sizeof(stateid_t)); + } + lrp->lrs_present = 1; + } else { + nfs4_unhash_stid(&ls->ls_stid); + lrp->lrs_present = 0; + } + spin_unlock(&ls->ls_lock); + + nfs4_put_stid(&ls->ls_stid); + nfsd4_free_layouts(&reaplist); + return nfs_ok; +} + +__be32 +nfsd4_return_client_layouts(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp) +{ + struct nfs4_layout_stateid *ls, *n; + struct nfs4_client *clp = cstate->clp; + struct nfs4_layout *lp, *t; + LIST_HEAD(reaplist); + + lrp->lrs_present = 0; + + spin_lock(&clp->cl_lock); + list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) { + if (lrp->lr_return_type == RETURN_FSID && + !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle, + &cstate->current_fh.fh_handle)) + continue; + + spin_lock(&ls->ls_lock); + list_for_each_entry_safe(lp, t, &ls->ls_layouts, lo_perstate) { + if (lrp->lr_seg.iomode == IOMODE_ANY || + lrp->lr_seg.iomode == lp->lo_seg.iomode) + list_move_tail(&lp->lo_perstate, &reaplist); + } + spin_unlock(&ls->ls_lock); + } + spin_unlock(&clp->cl_lock); + + nfsd4_free_layouts(&reaplist); + return 0; +} + +static void +nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls, + struct list_head *reaplist) +{ + spin_lock(&ls->ls_lock); + list_splice_init(&ls->ls_layouts, reaplist); + spin_unlock(&ls->ls_lock); +} + +void +nfsd4_return_all_client_layouts(struct nfs4_client *clp) +{ + struct nfs4_layout_stateid *ls, *n; + LIST_HEAD(reaplist); + + spin_lock(&clp->cl_lock); + list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) + nfsd4_return_all_layouts(ls, &reaplist); + spin_unlock(&clp->cl_lock); + + nfsd4_free_layouts(&reaplist); +} + +void +nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp) +{ + struct nfs4_layout_stateid *ls, *n; + LIST_HEAD(reaplist); + + spin_lock(&fp->fi_lock); + list_for_each_entry_safe(ls, n, &fp->fi_lo_states, ls_perfile) { + if (ls->ls_stid.sc_client == clp) + nfsd4_return_all_layouts(ls, &reaplist); + } + spin_unlock(&fp->fi_lock); + + nfsd4_free_layouts(&reaplist); +} + +int +nfsd4_init_pnfs(void) +{ + int i; + + for (i = 0; i < DEVID_HASH_SIZE; i++) + INIT_LIST_HEAD(&nfsd_devid_hash[i]); + + nfs4_layout_cache = kmem_cache_create("nfs4_layout", + sizeof(struct nfs4_layout), 0, 0, NULL); + if (!nfs4_layout_cache) + return -ENOMEM; + + nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid", + sizeof(struct nfs4_layout_stateid), 0, 0, NULL); + if (!nfs4_layout_stateid_cache) { + kmem_cache_destroy(nfs4_layout_cache); + return -ENOMEM; + } + return 0; +} + +void +nfsd4_exit_pnfs(void) +{ + int i; + + kmem_cache_destroy(nfs4_layout_cache); + kmem_cache_destroy(nfs4_layout_stateid_cache); + + for (i = 0; i < DEVID_HASH_SIZE; i++) { + struct nfsd4_deviceid_map *map, *n; + + list_for_each_entry_safe(map, n, &nfsd_devid_hash[i], hash) + kfree(map); + } +} diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ac71d13c69ef..2b91443497cc 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -43,6 +43,7 @@ #include "current_stateid.h" #include "netns.h" #include "acl.h" +#include "pnfs.h" #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #include @@ -1178,6 +1179,252 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status == nfserr_same ? nfs_ok : status; } +#ifdef CONFIG_NFSD_PNFS +static const struct nfsd4_layout_ops * +nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type) +{ + if (!exp->ex_layout_type) { + dprintk("%s: export does not support pNFS\n", __func__); + return NULL; + } + + if (exp->ex_layout_type != layout_type) { + dprintk("%s: layout type %d not supported\n", + __func__, layout_type); + return NULL; + } + + return nfsd4_layout_ops[layout_type]; +} + +static __be32 +nfsd4_getdeviceinfo(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_getdeviceinfo *gdp) +{ + const struct nfsd4_layout_ops *ops; + struct nfsd4_deviceid_map *map; + struct svc_export *exp; + __be32 nfserr; + + dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n", + __func__, + gdp->gd_layout_type, + gdp->gd_devid.fsid_idx, gdp->gd_devid.generation, + gdp->gd_maxcount); + + map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx); + if (!map) { + dprintk("%s: couldn't find device ID to export mapping!\n", + __func__); + return nfserr_noent; + } + + exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid); + if (IS_ERR(exp)) { + dprintk("%s: could not find device id\n", __func__); + return nfserr_noent; + } + + nfserr = nfserr_layoutunavailable; + ops = nfsd4_layout_verify(exp, gdp->gd_layout_type); + if (!ops) + goto out; + + nfserr = nfs_ok; + if (gdp->gd_maxcount != 0) + nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp); + + gdp->gd_notify_types &= ops->notify_types; + exp_put(exp); +out: + return nfserr; +} + +static __be32 +nfsd4_layoutget(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutget *lgp) +{ + struct svc_fh *current_fh = &cstate->current_fh; + const struct nfsd4_layout_ops *ops; + struct nfs4_layout_stateid *ls; + __be32 nfserr; + int accmode; + + switch (lgp->lg_seg.iomode) { + case IOMODE_READ: + accmode = NFSD_MAY_READ; + break; + case IOMODE_RW: + accmode = NFSD_MAY_READ | NFSD_MAY_WRITE; + break; + default: + dprintk("%s: invalid iomode %d\n", + __func__, lgp->lg_seg.iomode); + nfserr = nfserr_badiomode; + goto out; + } + + nfserr = fh_verify(rqstp, current_fh, 0, accmode); + if (nfserr) + goto out; + + nfserr = nfserr_layoutunavailable; + ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type); + if (!ops) + goto out; + + /* + * Verify minlength and range as per RFC5661: + * o If loga_length is less than loga_minlength, + * the metadata server MUST return NFS4ERR_INVAL. + * o If the sum of loga_offset and loga_minlength exceeds + * NFS4_UINT64_MAX, and loga_minlength is not + * NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result. + * o If the sum of loga_offset and loga_length exceeds + * NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX, + * the error NFS4ERR_INVAL MUST result. + */ + nfserr = nfserr_inval; + if (lgp->lg_seg.length < lgp->lg_minlength || + (lgp->lg_minlength != NFS4_MAX_UINT64 && + lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) || + (lgp->lg_seg.length != NFS4_MAX_UINT64 && + lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset)) + goto out; + if (lgp->lg_seg.length == 0) + goto out; + + nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid, + true, lgp->lg_layout_type, &ls); + if (nfserr) + goto out; + + nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode, + current_fh, lgp); + if (nfserr) + goto out_put_stid; + + nfserr = nfsd4_insert_layout(lgp, ls); + +out_put_stid: + nfs4_put_stid(&ls->ls_stid); +out: + return nfserr; +} + +static __be32 +nfsd4_layoutcommit(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutcommit *lcp) +{ + const struct nfsd4_layout_seg *seg = &lcp->lc_seg; + struct svc_fh *current_fh = &cstate->current_fh; + const struct nfsd4_layout_ops *ops; + loff_t new_size = lcp->lc_last_wr + 1; + struct inode *inode; + struct nfs4_layout_stateid *ls; + __be32 nfserr; + + nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE); + if (nfserr) + goto out; + + nfserr = nfserr_layoutunavailable; + ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type); + if (!ops) + goto out; + inode = current_fh->fh_dentry->d_inode; + + nfserr = nfserr_inval; + if (new_size <= seg->offset) { + dprintk("pnfsd: last write before layout segment\n"); + goto out; + } + if (new_size > seg->offset + seg->length) { + dprintk("pnfsd: last write beyond layout segment\n"); + goto out; + } + if (!lcp->lc_newoffset && new_size > i_size_read(inode)) { + dprintk("pnfsd: layoutcommit beyond EOF\n"); + goto out; + } + + nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid, + false, lcp->lc_layout_type, + &ls); + if (nfserr) { + /* fixup error code as per RFC5661 */ + if (nfserr == nfserr_bad_stateid) + nfserr = nfserr_badlayout; + goto out; + } + + nfserr = ops->proc_layoutcommit(inode, lcp); + if (nfserr) + goto out_put_stid; + + if (new_size > i_size_read(inode)) { + lcp->lc_size_chg = 1; + lcp->lc_newsize = new_size; + } else { + lcp->lc_size_chg = 0; + } + +out_put_stid: + nfs4_put_stid(&ls->ls_stid); +out: + return nfserr; +} + +static __be32 +nfsd4_layoutreturn(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp) +{ + struct svc_fh *current_fh = &cstate->current_fh; + __be32 nfserr; + + nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP); + if (nfserr) + goto out; + + nfserr = nfserr_layoutunavailable; + if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type)) + goto out; + + switch (lrp->lr_seg.iomode) { + case IOMODE_READ: + case IOMODE_RW: + case IOMODE_ANY: + break; + default: + dprintk("%s: invalid iomode %d\n", __func__, + lrp->lr_seg.iomode); + nfserr = nfserr_inval; + goto out; + } + + switch (lrp->lr_return_type) { + case RETURN_FILE: + nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp); + break; + case RETURN_FSID: + case RETURN_ALL: + nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp); + break; + default: + dprintk("%s: invalid return_type %d\n", __func__, + lrp->lr_return_type); + nfserr = nfserr_inval; + break; + } +out: + return nfserr; +} +#endif /* CONFIG_NFSD_PNFS */ + /* * NULL call. */ @@ -1679,6 +1926,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd op_encode_channel_attrs_maxsz) * sizeof(__be32); } +#ifdef CONFIG_NFSD_PNFS +/* + * At this stage we don't really know what layout driver will handle the request, + * so we need to define an arbitrary upper bound here. + */ +#define MAX_LAYOUT_SIZE 128 +static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +{ + return (op_encode_hdr_size + + 1 /* logr_return_on_close */ + + op_encode_stateid_maxsz + + 1 /* nr of layouts */ + + MAX_LAYOUT_SIZE) * sizeof(__be32); +} + +static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +{ + return (op_encode_hdr_size + + 1 /* locr_newsize */ + + 2 /* ns_size */) * sizeof(__be32); +} + +static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) +{ + return (op_encode_hdr_size + + 1 /* lrs_stateid */ + + op_encode_stateid_maxsz) * sizeof(__be32); +} +#endif /* CONFIG_NFSD_PNFS */ + static struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { .op_func = (nfsd4op_func)nfsd4_access, @@ -1966,6 +2243,31 @@ static struct nfsd4_operation nfsd4_ops[] = { .op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid, .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, }, +#ifdef CONFIG_NFSD_PNFS + [OP_GETDEVICEINFO] = { + .op_func = (nfsd4op_func)nfsd4_getdeviceinfo, + .op_flags = ALLOWED_WITHOUT_FH, + .op_name = "OP_GETDEVICEINFO", + }, + [OP_LAYOUTGET] = { + .op_func = (nfsd4op_func)nfsd4_layoutget, + .op_flags = OP_MODIFIES_SOMETHING, + .op_name = "OP_LAYOUTGET", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize, + }, + [OP_LAYOUTCOMMIT] = { + .op_func = (nfsd4op_func)nfsd4_layoutcommit, + .op_flags = OP_MODIFIES_SOMETHING, + .op_name = "OP_LAYOUTCOMMIT", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize, + }, + [OP_LAYOUTRETURN] = { + .op_func = (nfsd4op_func)nfsd4_layoutreturn, + .op_flags = OP_MODIFIES_SOMETHING, + .op_name = "OP_LAYOUTRETURN", + .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize, + }, +#endif /* CONFIG_NFSD_PNFS */ /* NFSv4.2 operations */ [OP_ALLOCATE] = { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index eefd29ec43f2..c89f79dc69e2 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -48,6 +48,7 @@ #include "current_stateid.h" #include "netns.h" +#include "pnfs.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -1539,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) INIT_LIST_HEAD(&clp->cl_lru); INIT_LIST_HEAD(&clp->cl_callbacks); INIT_LIST_HEAD(&clp->cl_revoked); +#ifdef CONFIG_NFSD_PNFS + INIT_LIST_HEAD(&clp->cl_lo_states); +#endif spin_lock_init(&clp->cl_lock); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); return clp; @@ -1643,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp) nfs4_get_stateowner(&oo->oo_owner); release_openowner(oo); } + nfsd4_return_all_client_layouts(clp); nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); @@ -2126,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, static void nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) { - /* pNFS is not supported */ +#ifdef CONFIG_NFSD_PNFS + new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS; +#else new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS; +#endif /* Referrals are supported, Migration is not. */ new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER; @@ -3055,6 +3063,9 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval, fp->fi_share_deny = 0; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); +#ifdef CONFIG_NFSD_PNFS + INIT_LIST_HEAD(&fp->fi_lo_states); +#endif hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); } @@ -4841,6 +4852,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, update_stateid(&stp->st_stid.sc_stateid); memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); + nfsd4_return_all_file_layouts(stp->st_stateowner->so_client, + stp->st_stid.sc_file); + nfsd4_close_open_stateid(stp); /* put reference from nfs4_preprocess_seqid_op */ diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 974533e5a427..df5e66caf100 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -47,6 +47,7 @@ #include "state.h" #include "cache.h" #include "netns.h" +#include "pnfs.h" #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #include @@ -1522,6 +1523,127 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str DECODE_TAIL; } +#ifdef CONFIG_NFSD_PNFS +static __be32 +nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, + struct nfsd4_getdeviceinfo *gdev) +{ + DECODE_HEAD; + u32 num, i; + + READ_BUF(sizeof(struct nfsd4_deviceid) + 3 * 4); + COPYMEM(&gdev->gd_devid, sizeof(struct nfsd4_deviceid)); + gdev->gd_layout_type = be32_to_cpup(p++); + gdev->gd_maxcount = be32_to_cpup(p++); + num = be32_to_cpup(p++); + if (num) { + READ_BUF(4 * num); + gdev->gd_notify_types = be32_to_cpup(p++); + for (i = 1; i < num; i++) { + if (be32_to_cpup(p++)) { + status = nfserr_inval; + goto out; + } + } + } + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, + struct nfsd4_layoutget *lgp) +{ + DECODE_HEAD; + + READ_BUF(36); + lgp->lg_signal = be32_to_cpup(p++); + lgp->lg_layout_type = be32_to_cpup(p++); + lgp->lg_seg.iomode = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &lgp->lg_seg.offset); + p = xdr_decode_hyper(p, &lgp->lg_seg.length); + p = xdr_decode_hyper(p, &lgp->lg_minlength); + nfsd4_decode_stateid(argp, &lgp->lg_sid); + READ_BUF(4); + lgp->lg_maxcount = be32_to_cpup(p++); + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, + struct nfsd4_layoutcommit *lcp) +{ + DECODE_HEAD; + u32 timechange; + + READ_BUF(20); + p = xdr_decode_hyper(p, &lcp->lc_seg.offset); + p = xdr_decode_hyper(p, &lcp->lc_seg.length); + lcp->lc_reclaim = be32_to_cpup(p++); + nfsd4_decode_stateid(argp, &lcp->lc_sid); + READ_BUF(4); + lcp->lc_newoffset = be32_to_cpup(p++); + if (lcp->lc_newoffset) { + READ_BUF(8); + p = xdr_decode_hyper(p, &lcp->lc_last_wr); + } else + lcp->lc_last_wr = 0; + READ_BUF(4); + timechange = be32_to_cpup(p++); + if (timechange) { + status = nfsd4_decode_time(argp, &lcp->lc_mtime); + if (status) + return status; + } else { + lcp->lc_mtime.tv_nsec = UTIME_NOW; + } + READ_BUF(8); + lcp->lc_layout_type = be32_to_cpup(p++); + + /* + * Save the layout update in XDR format and let the layout driver deal + * with it later. + */ + lcp->lc_up_len = be32_to_cpup(p++); + if (lcp->lc_up_len > 0) { + READ_BUF(lcp->lc_up_len); + READMEM(lcp->lc_up_layout, lcp->lc_up_len); + } + + DECODE_TAIL; +} + +static __be32 +nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, + struct nfsd4_layoutreturn *lrp) +{ + DECODE_HEAD; + + READ_BUF(16); + lrp->lr_reclaim = be32_to_cpup(p++); + lrp->lr_layout_type = be32_to_cpup(p++); + lrp->lr_seg.iomode = be32_to_cpup(p++); + lrp->lr_return_type = be32_to_cpup(p++); + if (lrp->lr_return_type == RETURN_FILE) { + READ_BUF(16); + p = xdr_decode_hyper(p, &lrp->lr_seg.offset); + p = xdr_decode_hyper(p, &lrp->lr_seg.length); + nfsd4_decode_stateid(argp, &lrp->lr_sid); + READ_BUF(4); + lrp->lrf_body_len = be32_to_cpup(p++); + if (lrp->lrf_body_len > 0) { + READ_BUF(lrp->lrf_body_len); + READMEM(lrp->lrf_body, lrp->lrf_body_len); + } + } else { + lrp->lr_seg.offset = 0; + lrp->lr_seg.length = NFS4_MAX_UINT64; + } + + DECODE_TAIL; +} +#endif /* CONFIG_NFSD_PNFS */ + static __be32 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, struct nfsd4_fallocate *fallocate) @@ -1616,11 +1738,19 @@ static nfsd4_dec nfsd4_dec_ops[] = { [OP_DESTROY_SESSION] = (nfsd4_dec)nfsd4_decode_destroy_session, [OP_FREE_STATEID] = (nfsd4_dec)nfsd4_decode_free_stateid, [OP_GET_DIR_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, +#ifdef CONFIG_NFSD_PNFS + [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_getdeviceinfo, + [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_layoutcommit, + [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_layoutget, + [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_layoutreturn, +#else [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_notsupp, [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_notsupp, +#endif [OP_SECINFO_NO_NAME] = (nfsd4_dec)nfsd4_decode_secinfo_no_name, [OP_SEQUENCE] = (nfsd4_dec)nfsd4_decode_sequence, [OP_SET_SSV] = (nfsd4_dec)nfsd4_decode_notsupp, @@ -2548,6 +2678,30 @@ out_acl: get_parent_attributes(exp, &stat); p = xdr_encode_hyper(p, stat.ino); } +#ifdef CONFIG_NFSD_PNFS + if ((bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) || + (bmval2 & FATTR4_WORD2_LAYOUT_TYPES)) { + if (exp->ex_layout_type) { + p = xdr_reserve_space(xdr, 8); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(1); + *p++ = cpu_to_be32(exp->ex_layout_type); + } else { + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(0); + } + } + + if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) { + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out_resource; + *p++ = cpu_to_be32(stat.blksize); + } +#endif /* CONFIG_NFSD_PNFS */ if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { status = nfsd4_encode_security_label(xdr, rqstp, context, contextlen); @@ -3824,6 +3978,156 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr; } +#ifdef CONFIG_NFSD_PNFS +static __be32 +nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_getdeviceinfo *gdev) +{ + struct xdr_stream *xdr = &resp->xdr; + const struct nfsd4_layout_ops *ops = + nfsd4_layout_ops[gdev->gd_layout_type]; + u32 starting_len = xdr->buf->len, needed_len; + __be32 *p; + + dprintk("%s: err %d\n", __func__, nfserr); + if (nfserr) + goto out; + + nfserr = nfserr_resource; + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; + + *p++ = cpu_to_be32(gdev->gd_layout_type); + + /* If maxcount is 0 then just update notifications */ + if (gdev->gd_maxcount != 0) { + nfserr = ops->encode_getdeviceinfo(xdr, gdev); + if (nfserr) { + /* + * We don't bother to burden the layout drivers with + * enforcing gd_maxcount, just tell the client to + * come back with a bigger buffer if it's not enough. + */ + if (xdr->buf->len + 4 > gdev->gd_maxcount) + goto toosmall; + goto out; + } + } + + nfserr = nfserr_resource; + if (gdev->gd_notify_types) { + p = xdr_reserve_space(xdr, 4 + 4); + if (!p) + goto out; + *p++ = cpu_to_be32(1); /* bitmap length */ + *p++ = cpu_to_be32(gdev->gd_notify_types); + } else { + p = xdr_reserve_space(xdr, 4); + if (!p) + goto out; + *p++ = 0; + } + + nfserr = 0; +out: + kfree(gdev->gd_device); + dprintk("%s: done: %d\n", __func__, be32_to_cpu(nfserr)); + return nfserr; + +toosmall: + dprintk("%s: maxcount too small\n", __func__); + needed_len = xdr->buf->len + 4 /* notifications */; + xdr_truncate_encode(xdr, starting_len); + p = xdr_reserve_space(xdr, 4); + if (!p) { + nfserr = nfserr_resource; + } else { + *p++ = cpu_to_be32(needed_len); + nfserr = nfserr_toosmall; + } + goto out; +} + +static __be32 +nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_layoutget *lgp) +{ + struct xdr_stream *xdr = &resp->xdr; + const struct nfsd4_layout_ops *ops = + nfsd4_layout_ops[lgp->lg_layout_type]; + __be32 *p; + + dprintk("%s: err %d\n", __func__, nfserr); + if (nfserr) + goto out; + + nfserr = nfserr_resource; + p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t)); + if (!p) + goto out; + + *p++ = cpu_to_be32(1); /* we always set return-on-close */ + *p++ = cpu_to_be32(lgp->lg_sid.si_generation); + p = xdr_encode_opaque_fixed(p, &lgp->lg_sid.si_opaque, + sizeof(stateid_opaque_t)); + + *p++ = cpu_to_be32(1); /* we always return a single layout */ + p = xdr_encode_hyper(p, lgp->lg_seg.offset); + p = xdr_encode_hyper(p, lgp->lg_seg.length); + *p++ = cpu_to_be32(lgp->lg_seg.iomode); + *p++ = cpu_to_be32(lgp->lg_layout_type); + + nfserr = ops->encode_layoutget(xdr, lgp); +out: + kfree(lgp->lg_content); + return nfserr; +} + +static __be32 +nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_layoutcommit *lcp) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + if (nfserr) + return nfserr; + + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(lcp->lc_size_chg); + if (lcp->lc_size_chg) { + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + p = xdr_encode_hyper(p, lcp->lc_newsize); + } + + return nfs_ok; +} + +static __be32 +nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, + struct nfsd4_layoutreturn *lrp) +{ + struct xdr_stream *xdr = &resp->xdr; + __be32 *p; + + if (nfserr) + return nfserr; + + p = xdr_reserve_space(xdr, 4); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(lrp->lrs_present); + if (lrp->lrs_present) + nfsd4_encode_stateid(xdr, &lrp->lr_sid); + return nfs_ok; +} +#endif /* CONFIG_NFSD_PNFS */ + static __be32 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_seek *seek) @@ -3900,11 +4204,19 @@ static nfsd4_enc nfsd4_enc_ops[] = { [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_noop, [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop, [OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, +#ifdef CONFIG_NFSD_PNFS + [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_getdeviceinfo, + [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_layoutcommit, + [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_layoutget, + [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_layoutreturn, +#else [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop, [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_noop, [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_noop, [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_noop, +#endif [OP_SECINFO_NO_NAME] = (nfsd4_enc)nfsd4_encode_secinfo_no_name, [OP_SEQUENCE] = (nfsd4_enc)nfsd4_encode_sequence, [OP_SET_SSV] = (nfsd4_enc)nfsd4_encode_noop, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 19ace74d35f6..aa47d75ddb26 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -21,6 +21,7 @@ #include "cache.h" #include "state.h" #include "netns.h" +#include "pnfs.h" /* * We have a single directory with several nodes in it. @@ -1258,9 +1259,12 @@ static int __init init_nfsd(void) retval = nfsd4_init_slabs(); if (retval) goto out_unregister_pernet; - retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */ + retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; + retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */ + if (retval) + goto out_exit_pnfs; nfsd_stat_init(); /* Statistics */ retval = nfsd_reply_cache_init(); if (retval) @@ -1282,6 +1286,8 @@ out_free_lockd: out_free_stat: nfsd_stat_shutdown(); nfsd_fault_inject_cleanup(); +out_exit_pnfs: + nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); out_unregister_pernet: @@ -1299,6 +1305,7 @@ static void __exit exit_nfsd(void) nfsd_stat_shutdown(); nfsd_lockd_shutdown(); nfsd4_free_slabs(); + nfsd4_exit_pnfs(); nfsd_fault_inject_cleanup(); unregister_filesystem(&nfsd_fs_type); unregister_pernet_subsys(&nfsd_net_ops); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 33a46a8dfaf7..565c4da1a9eb 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -325,15 +325,27 @@ void nfsd_lockd_shutdown(void); #define NFSD4_SUPPORTED_ATTRS_WORD2 0 +/* 4.1 */ +#ifdef CONFIG_NFSD_PNFS +#define PNFSD_SUPPORTED_ATTRS_WORD1 FATTR4_WORD1_FS_LAYOUT_TYPES +#define PNFSD_SUPPORTED_ATTRS_WORD2 \ +(FATTR4_WORD2_LAYOUT_BLKSIZE | FATTR4_WORD2_LAYOUT_TYPES) +#else +#define PNFSD_SUPPORTED_ATTRS_WORD1 0 +#define PNFSD_SUPPORTED_ATTRS_WORD2 0 +#endif /* CONFIG_NFSD_PNFS */ + #define NFSD4_1_SUPPORTED_ATTRS_WORD0 \ NFSD4_SUPPORTED_ATTRS_WORD0 #define NFSD4_1_SUPPORTED_ATTRS_WORD1 \ - NFSD4_SUPPORTED_ATTRS_WORD1 + (NFSD4_SUPPORTED_ATTRS_WORD1 | PNFSD_SUPPORTED_ATTRS_WORD1) #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \ - (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT) + (NFSD4_SUPPORTED_ATTRS_WORD2 | PNFSD_SUPPORTED_ATTRS_WORD2 | \ + FATTR4_WORD2_SUPPATTR_EXCLCREAT) +/* 4.2 */ #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #define NFSD4_2_SECURITY_ATTRS FATTR4_WORD2_SECURITY_LABEL #else diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h new file mode 100644 index 000000000000..a9616a4e13cd --- /dev/null +++ b/fs/nfsd/pnfs.h @@ -0,0 +1,80 @@ +#ifndef _FS_NFSD_PNFS_H +#define _FS_NFSD_PNFS_H 1 + +#include +#include + +#include "state.h" +#include "xdr4.h" + +struct xdr_stream; + +struct nfsd4_deviceid_map { + struct list_head hash; + u64 idx; + int fsid_type; + u32 fsid[]; +}; + +struct nfsd4_layout_ops { + u32 notify_types; + + __be32 (*proc_getdeviceinfo)(struct super_block *sb, + struct nfsd4_getdeviceinfo *gdevp); + __be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr, + struct nfsd4_getdeviceinfo *gdevp); + + __be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp, + struct nfsd4_layoutget *lgp); + __be32 (*encode_layoutget)(struct xdr_stream *, + struct nfsd4_layoutget *lgp); + + __be32 (*proc_layoutcommit)(struct inode *inode, + struct nfsd4_layoutcommit *lcp); +}; + +extern const struct nfsd4_layout_ops *nfsd4_layout_ops[]; + +__be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, stateid_t *stateid, + bool create, u32 layout_type, struct nfs4_layout_stateid **lsp); +__be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp, + struct nfs4_layout_stateid *ls); +__be32 nfsd4_return_file_layouts(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp); +__be32 nfsd4_return_client_layouts(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + struct nfsd4_layoutreturn *lrp); +int nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, + u32 device_generation); +struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx); + +#ifdef CONFIG_NFSD_PNFS +void nfsd4_setup_layout_type(struct svc_export *exp); +void nfsd4_return_all_client_layouts(struct nfs4_client *); +void nfsd4_return_all_file_layouts(struct nfs4_client *clp, + struct nfs4_file *fp); +int nfsd4_init_pnfs(void); +void nfsd4_exit_pnfs(void); +#else +static inline void nfsd4_setup_layout_type(struct svc_export *exp) +{ +} + +static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp) +{ +} +static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp, + struct nfs4_file *fp) +{ +} +static inline void nfsd4_exit_pnfs(void) +{ +} +static inline int nfsd4_init_pnfs(void) +{ + return 0; +} +#endif /* CONFIG_NFSD_PNFS */ +#endif /* _FS_NFSD_PNFS_H */ diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 38ebb1268b59..5f66b7fd0297 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -92,6 +92,7 @@ struct nfs4_stid { /* For a deleg stateid kept around only to process free_stateid's: */ #define NFS4_REVOKED_DELEG_STID 16 #define NFS4_CLOSED_DELEG_STID 32 +#define NFS4_LAYOUT_STID 64 unsigned char sc_type; stateid_t sc_stateid; struct nfs4_client *sc_client; @@ -297,6 +298,9 @@ struct nfs4_client { struct list_head cl_delegations; struct list_head cl_revoked; /* unacknowledged, revoked 4.1 state */ struct list_head cl_lru; /* tail queue */ +#ifdef CONFIG_NFSD_PNFS + struct list_head cl_lo_states; /* outstanding layout states */ +#endif struct xdr_netobj cl_name; /* id generated by client */ nfs4_verifier cl_verifier; /* generated by client */ time_t cl_time; /* time of last lease renewal */ @@ -496,6 +500,9 @@ struct nfs4_file { int fi_delegees; struct knfsd_fh fi_fhandle; bool fi_had_conflict; +#ifdef CONFIG_NFSD_PNFS + struct list_head fi_lo_states; +#endif }; /* @@ -528,6 +535,20 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s) return container_of(s, struct nfs4_ol_stateid, st_stid); } +struct nfs4_layout_stateid { + struct nfs4_stid ls_stid; + struct list_head ls_perclnt; + struct list_head ls_perfile; + spinlock_t ls_lock; + struct list_head ls_layouts; + u32 ls_layout_type; +}; + +static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s) +{ + return container_of(s, struct nfs4_layout_stateid, ls_stid); +} + /* flags for preprocess_seqid_op() */ #define RD_STATE 0x00000010 #define WR_STATE 0x00000020 diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 90a5925bd6ab..0bda93e58e1b 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -428,6 +428,61 @@ struct nfsd4_reclaim_complete { u32 rca_one_fs; }; +struct nfsd4_deviceid { + u64 fsid_idx; + u32 generation; + u32 pad; +}; + +struct nfsd4_layout_seg { + u32 iomode; + u64 offset; + u64 length; +}; + +struct nfsd4_getdeviceinfo { + struct nfsd4_deviceid gd_devid; /* request */ + u32 gd_layout_type; /* request */ + u32 gd_maxcount; /* request */ + u32 gd_notify_types;/* request - response */ + void *gd_device; /* response */ +}; + +struct nfsd4_layoutget { + u64 lg_minlength; /* request */ + u32 lg_signal; /* request */ + u32 lg_layout_type; /* request */ + u32 lg_maxcount; /* request */ + stateid_t lg_sid; /* request/response */ + struct nfsd4_layout_seg lg_seg; /* request/response */ + void *lg_content; /* response */ +}; + +struct nfsd4_layoutcommit { + stateid_t lc_sid; /* request */ + struct nfsd4_layout_seg lc_seg; /* request */ + u32 lc_reclaim; /* request */ + u32 lc_newoffset; /* request */ + u64 lc_last_wr; /* request */ + struct timespec lc_mtime; /* request */ + u32 lc_layout_type; /* request */ + u32 lc_up_len; /* layout length */ + void *lc_up_layout; /* decoded by callback */ + u32 lc_size_chg; /* boolean for response */ + u64 lc_newsize; /* response */ +}; + +struct nfsd4_layoutreturn { + u32 lr_return_type; /* request */ + u32 lr_layout_type; /* request */ + struct nfsd4_layout_seg lr_seg; /* request */ + u32 lr_reclaim; /* request */ + u32 lrf_body_len; /* request */ + void *lrf_body; /* request */ + stateid_t lr_sid; /* request/response */ + u32 lrs_present; /* response */ +}; + struct nfsd4_fallocate { /* request */ stateid_t falloc_stateid; @@ -491,6 +546,10 @@ struct nfsd4_op { struct nfsd4_reclaim_complete reclaim_complete; struct nfsd4_test_stateid test_stateid; struct nfsd4_free_stateid free_stateid; + struct nfsd4_getdeviceinfo getdeviceinfo; + struct nfsd4_layoutget layoutget; + struct nfsd4_layoutcommit layoutcommit; + struct nfsd4_layoutreturn layoutreturn; /* NFSv4.2 */ struct nfsd4_fallocate allocate; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 8a3589c2542c..bc10d687f2ce 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -411,6 +411,7 @@ enum lock_type4 { #define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22) #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) +#define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h index 1fdc95bb2375..0bf130a1c58d 100644 --- a/include/uapi/linux/nfsd/debug.h +++ b/include/uapi/linux/nfsd/debug.h @@ -32,6 +32,7 @@ #define NFSDDBG_REPCACHE 0x0080 #define NFSDDBG_XDR 0x0100 #define NFSDDBG_LOCKD 0x0200 +#define NFSDDBG_PNFS 0x0400 #define NFSDDBG_ALL 0x7FFF #define NFSDDBG_NOCHANGE 0xFFFF diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h index 584b6ef3a5e8..4742f2cb42f2 100644 --- a/include/uapi/linux/nfsd/export.h +++ b/include/uapi/linux/nfsd/export.h @@ -47,8 +47,10 @@ * exported filesystem. */ #define NFSEXP_V4ROOT 0x10000 +#define NFSEXP_NOPNFS 0x20000 + /* All flags that we claim to support. (Note we don't support NOACL.) */ -#define NFSEXP_ALLFLAGS 0x1FE7F +#define NFSEXP_ALLFLAGS 0x3FE7F /* The flags that may vary depending on security flavor: */ #define NFSEXP_SECINFO_FLAGS (NFSEXP_READONLY | NFSEXP_ROOTSQUASH \ -- cgit v1.2.3 From c5c707f96fc9a6e5a57ca5baac892673270abe3d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 23 Sep 2014 12:38:48 +0200 Subject: nfsd: implement pNFS layout recalls Add support to issue layout recalls to clients. For now we only support full-file recalls to get a simple and stable implementation. This allows to embedd a nfsd4_callback structure in the layout_state and thus avoid any memory allocations under spinlocks during a recall. For normal use cases that do not intent to share a single file between multiple clients this implementation is fully sufficient. To ensure layouts are recalled on local filesystem access each layout state registers a new FL_LAYOUT lease with the kernel file locking code, which filesystems that support pNFS exports that require recalls need to break on conflicting access patterns. The XDR code is based on the old pNFS server implementation by Andy Adamson, Benny Halevy, Boaz Harrosh, Dean Hildebrand, Fred Isaman, Marc Eshel, Mike Sager and Ricardo Labiaga. Signed-off-by: Christoph Hellwig --- fs/nfsd/nfs4callback.c | 99 +++++++++++++++++++++++ fs/nfsd/nfs4layouts.c | 214 ++++++++++++++++++++++++++++++++++++++++++++++++- fs/nfsd/nfs4proc.c | 4 + fs/nfsd/nfs4state.c | 1 + fs/nfsd/state.h | 6 ++ fs/nfsd/xdr4cb.h | 7 ++ 6 files changed, 330 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7cbdf1b2e4ab..58277859a467 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -546,6 +546,102 @@ out: return status; } +#ifdef CONFIG_NFSD_PNFS +/* + * CB_LAYOUTRECALL4args + * + * struct layoutrecall_file4 { + * nfs_fh4 lor_fh; + * offset4 lor_offset; + * length4 lor_length; + * stateid4 lor_stateid; + * }; + * + * union layoutrecall4 switch(layoutrecall_type4 lor_recalltype) { + * case LAYOUTRECALL4_FILE: + * layoutrecall_file4 lor_layout; + * case LAYOUTRECALL4_FSID: + * fsid4 lor_fsid; + * case LAYOUTRECALL4_ALL: + * void; + * }; + * + * struct CB_LAYOUTRECALL4args { + * layouttype4 clora_type; + * layoutiomode4 clora_iomode; + * bool clora_changed; + * layoutrecall4 clora_recall; + * }; + */ +static void encode_cb_layout4args(struct xdr_stream *xdr, + const struct nfs4_layout_stateid *ls, + struct nfs4_cb_compound_hdr *hdr) +{ + __be32 *p; + + BUG_ON(hdr->minorversion == 0); + + p = xdr_reserve_space(xdr, 5 * 4); + *p++ = cpu_to_be32(OP_CB_LAYOUTRECALL); + *p++ = cpu_to_be32(ls->ls_layout_type); + *p++ = cpu_to_be32(IOMODE_ANY); + *p++ = cpu_to_be32(1); + *p = cpu_to_be32(RETURN_FILE); + + encode_nfs_fh4(xdr, &ls->ls_stid.sc_file->fi_fhandle); + + p = xdr_reserve_space(xdr, 2 * 8); + p = xdr_encode_hyper(p, 0); + xdr_encode_hyper(p, NFS4_MAX_UINT64); + + encode_stateid4(xdr, &ls->ls_recall_sid); + + hdr->nops++; +} + +static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req, + struct xdr_stream *xdr, + const struct nfsd4_callback *cb) +{ + const struct nfs4_layout_stateid *ls = + container_of(cb, struct nfs4_layout_stateid, ls_recall); + struct nfs4_cb_compound_hdr hdr = { + .ident = 0, + .minorversion = cb->cb_minorversion, + }; + + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_layout4args(xdr, ls, &hdr); + encode_cb_nops(&hdr); +} + +static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfsd4_callback *cb) +{ + struct nfs4_cb_compound_hdr hdr; + enum nfsstat4 nfserr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + goto out; + if (cb) { + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status)) + goto out; + } + status = decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &nfserr); + if (unlikely(status)) + goto out; + if (unlikely(nfserr != NFS4_OK)) + status = nfs_cb_stat_to_errno(nfserr); +out: + return status; +} +#endif /* CONFIG_NFSD_PNFS */ + /* * RPC procedure tables */ @@ -563,6 +659,9 @@ out: static struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NULL, NULL, cb_null, cb_null), PROC(CB_RECALL, COMPOUND, cb_recall, cb_recall), +#ifdef CONFIG_NFSD_PNFS + PROC(CB_LAYOUT, COMPOUND, cb_layout, cb_layout), +#endif }; static struct rpc_version nfs_cb_version4 = { diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 8273270418b1..d926865df94f 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -1,8 +1,11 @@ /* * Copyright (c) 2014 Christoph Hellwig. */ +#include +#include #include #include +#include #include "pnfs.h" #include "netns.h" @@ -18,6 +21,9 @@ struct nfs4_layout { static struct kmem_cache *nfs4_layout_cache; static struct kmem_cache *nfs4_layout_stateid_cache; +static struct nfsd4_callback_ops nfsd4_cb_layout_ops; +static const struct lock_manager_operations nfsd4_layouts_lm_ops; + const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { }; @@ -127,9 +133,42 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid) list_del_init(&ls->ls_perfile); spin_unlock(&fp->fi_lock); + vfs_setlease(ls->ls_file, F_UNLCK, NULL, (void **)&ls); + fput(ls->ls_file); + + if (ls->ls_recalled) + atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls); + kmem_cache_free(nfs4_layout_stateid_cache, ls); } +static int +nfsd4_layout_setlease(struct nfs4_layout_stateid *ls) +{ + struct file_lock *fl; + int status; + + fl = locks_alloc_lock(); + if (!fl) + return -ENOMEM; + locks_init_lock(fl); + fl->fl_lmops = &nfsd4_layouts_lm_ops; + fl->fl_flags = FL_LAYOUT; + fl->fl_type = F_RDLCK; + fl->fl_end = OFFSET_MAX; + fl->fl_owner = ls; + fl->fl_pid = current->tgid; + fl->fl_file = ls->ls_file; + + status = vfs_setlease(fl->fl_file, fl->fl_type, &fl, NULL); + if (status) { + locks_free_lock(fl); + return status; + } + BUG_ON(fl != NULL); + return 0; +} + static struct nfs4_layout_stateid * nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, struct nfs4_stid *parent, u32 layout_type) @@ -152,6 +191,20 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, spin_lock_init(&ls->ls_lock); INIT_LIST_HEAD(&ls->ls_layouts); ls->ls_layout_type = layout_type; + nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops, + NFSPROC4_CLNT_CB_LAYOUT); + + if (parent->sc_type == NFS4_DELEG_STID) + ls->ls_file = get_file(fp->fi_deleg_file); + else + ls->ls_file = find_any_file(fp); + BUG_ON(!ls->ls_file); + + if (nfsd4_layout_setlease(ls)) { + put_nfs4_file(fp); + kmem_cache_free(nfs4_layout_stateid_cache, ls); + return NULL; + } spin_lock(&clp->cl_lock); stp->sc_type = NFS4_LAYOUT_STID; @@ -215,6 +268,27 @@ out: return status; } +static void +nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) +{ + spin_lock(&ls->ls_lock); + if (ls->ls_recalled) + goto out_unlock; + + ls->ls_recalled = true; + atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); + if (list_empty(&ls->ls_layouts)) + goto out_unlock; + + atomic_inc(&ls->ls_stid.sc_count); + update_stateid(&ls->ls_stid.sc_stateid); + memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); + nfsd4_run_cb(&ls->ls_recall); + +out_unlock: + spin_unlock(&ls->ls_lock); +} + static inline u64 layout_end(struct nfsd4_layout_seg *seg) { @@ -258,18 +332,44 @@ layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new) return true; } +static __be32 +nfsd4_recall_conflict(struct nfs4_layout_stateid *ls) +{ + struct nfs4_file *fp = ls->ls_stid.sc_file; + struct nfs4_layout_stateid *l, *n; + __be32 nfserr = nfs_ok; + + assert_spin_locked(&fp->fi_lock); + + list_for_each_entry_safe(l, n, &fp->fi_lo_states, ls_perfile) { + if (l != ls) { + nfsd4_recall_file_layout(l); + nfserr = nfserr_recallconflict; + } + } + + return nfserr; +} + __be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) { struct nfsd4_layout_seg *seg = &lgp->lg_seg; + struct nfs4_file *fp = ls->ls_stid.sc_file; struct nfs4_layout *lp, *new = NULL; + __be32 nfserr; + spin_lock(&fp->fi_lock); + nfserr = nfsd4_recall_conflict(ls); + if (nfserr) + goto out; spin_lock(&ls->ls_lock); list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) { if (layouts_try_merge(&lp->lo_seg, seg)) goto done; } spin_unlock(&ls->ls_lock); + spin_unlock(&fp->fi_lock); new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL); if (!new) @@ -277,6 +377,10 @@ nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls) memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg)); new->lo_state = ls; + spin_lock(&fp->fi_lock); + nfserr = nfsd4_recall_conflict(ls); + if (nfserr) + goto out; spin_lock(&ls->ls_lock); list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) { if (layouts_try_merge(&lp->lo_seg, seg)) @@ -290,9 +394,11 @@ done: update_stateid(&ls->ls_stid.sc_stateid); memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); spin_unlock(&ls->ls_lock); +out: + spin_unlock(&fp->fi_lock); if (new) kmem_cache_free(nfs4_layout_cache, new); - return nfs_ok; + return nfserr; } static void @@ -448,6 +554,112 @@ nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp) nfsd4_free_layouts(&reaplist); } +static void +nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) +{ + struct nfs4_client *clp = ls->ls_stid.sc_client; + char addr_str[INET6_ADDRSTRLEN]; + static char *envp[] = { + "HOME=/", + "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", + NULL + }; + char *argv[8]; + int error; + + rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str)); + + printk(KERN_WARNING + "nfsd: client %s failed to respond to layout recall. " + " Fencing..\n", addr_str); + + argv[0] = "/sbin/nfsd-recall-failed"; + argv[1] = addr_str; + argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id; + argv[3] = NULL; + + error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); + if (error) { + printk(KERN_ERR "nfsd: fence failed for client %s: %d!\n", + addr_str, error); + } +} + +static int +nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) +{ + struct nfs4_layout_stateid *ls = + container_of(cb, struct nfs4_layout_stateid, ls_recall); + LIST_HEAD(reaplist); + + switch (task->tk_status) { + case 0: + return 1; + case -NFS4ERR_NOMATCHING_LAYOUT: + task->tk_status = 0; + return 1; + case -NFS4ERR_DELAY: + /* Poll the client until it's done with the layout */ + /* FIXME: cap number of retries. + * The pnfs standard states that we need to only expire + * the client after at-least "lease time" .eg lease-time * 2 + * when failing to communicate a recall + */ + rpc_delay(task, HZ/100); /* 10 mili-seconds */ + return 0; + default: + /* + * Unknown error or non-responding client, we'll need to fence. + */ + nfsd4_cb_layout_fail(ls); + return -1; + } +} + +static void +nfsd4_cb_layout_release(struct nfsd4_callback *cb) +{ + struct nfs4_layout_stateid *ls = + container_of(cb, struct nfs4_layout_stateid, ls_recall); + LIST_HEAD(reaplist); + + nfsd4_return_all_layouts(ls, &reaplist); + nfsd4_free_layouts(&reaplist); + nfs4_put_stid(&ls->ls_stid); +} + +static struct nfsd4_callback_ops nfsd4_cb_layout_ops = { + .done = nfsd4_cb_layout_done, + .release = nfsd4_cb_layout_release, +}; + +static bool +nfsd4_layout_lm_break(struct file_lock *fl) +{ + /* + * We don't want the locks code to timeout the lease for us; + * we'll remove it ourself if a layout isn't returned + * in time: + */ + fl->fl_break_time = 0; + nfsd4_recall_file_layout(fl->fl_owner); + return false; +} + +static int +nfsd4_layout_lm_change(struct file_lock *onlist, int arg, + struct list_head *dispose) +{ + BUG_ON(!(arg & F_UNLCK)); + return lease_modify(onlist, arg, dispose); +} + +static const struct lock_manager_operations nfsd4_layouts_lm_ops = { + .lm_break = nfsd4_layout_lm_break, + .lm_change = nfsd4_layout_lm_change, +}; + int nfsd4_init_pnfs(void) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 2b91443497cc..fa14359eb956 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1301,6 +1301,10 @@ nfsd4_layoutget(struct svc_rqst *rqstp, if (nfserr) goto out; + nfserr = nfserr_recallconflict; + if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls)) + goto out_put_stid; + nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode, current_fh, lgp); if (nfserr) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c89f79dc69e2..f6b2a09f793f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3065,6 +3065,7 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval, memset(fp->fi_access, 0, sizeof(fp->fi_access)); #ifdef CONFIG_NFSD_PNFS INIT_LIST_HEAD(&fp->fi_lo_states); + atomic_set(&fp->fi_lo_recalls, 0); #endif hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 5f66b7fd0297..4f3bfeb11766 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -502,6 +502,7 @@ struct nfs4_file { bool fi_had_conflict; #ifdef CONFIG_NFSD_PNFS struct list_head fi_lo_states; + atomic_t fi_lo_recalls; #endif }; @@ -542,6 +543,10 @@ struct nfs4_layout_stateid { spinlock_t ls_lock; struct list_head ls_layouts; u32 ls_layout_type; + struct file *ls_file; + struct nfsd4_callback ls_recall; + stateid_t ls_recall_sid; + bool ls_recalled; }; static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s) @@ -556,6 +561,7 @@ static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s) enum nfsd4_cb_op { NFSPROC4_CLNT_CB_NULL = 0, NFSPROC4_CLNT_CB_RECALL, + NFSPROC4_CLNT_CB_LAYOUT, NFSPROC4_CLNT_CB_SEQUENCE, }; diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index c5c55dfb91a9..c47f6fdb111a 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -21,3 +21,10 @@ #define NFS4_dec_cb_recall_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) +#define NFS4_enc_cb_layout_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ + 1 + 3 + \ + enc_nfs4_fh_sz + 4) +#define NFS4_dec_cb_layout_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + \ + op_dec_sz) -- cgit v1.2.3 From 31ef83dc053835fc14741426e20c60dbbba8c13d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 16 Aug 2014 19:02:22 -0500 Subject: nfsd: add trace events For now just a few simple events to trace the layout stateid lifetime, but these already were enough to find several bugs in the Linux client layout stateid handling. Signed-off-by: Christoph Hellwig --- fs/nfsd/Makefile | 7 ++++++- fs/nfsd/nfs4layouts.c | 16 ++++++++++++++- fs/nfsd/nfs4proc.c | 6 +++++- fs/nfsd/trace.c | 5 +++++ fs/nfsd/trace.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 85 insertions(+), 3 deletions(-) create mode 100644 fs/nfsd/trace.c create mode 100644 fs/nfsd/trace.h (limited to 'fs') diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 5806270a8567..6cba933880c5 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -2,9 +2,14 @@ # Makefile for the Linux nfs server # +ccflags-y += -I$(src) # needed for trace events + obj-$(CONFIG_NFSD) += nfsd.o -nfsd-y := nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \ +# this one should be compiled first, as the tracing macros can easily blow up +nfsd-y += trace.o + +nfsd-y += nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \ export.o auth.o lockd.o nfscache.o nfsxdr.o stats.o nfsd-$(CONFIG_NFSD_FAULT_INJECTION) += fault_inject.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index d926865df94f..60137c54b2f7 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -9,6 +9,7 @@ #include "pnfs.h" #include "netns.h" +#include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS @@ -125,6 +126,8 @@ nfsd4_free_layout_stateid(struct nfs4_stid *stid) struct nfs4_client *clp = ls->ls_stid.sc_client; struct nfs4_file *fp = ls->ls_stid.sc_file; + trace_layoutstate_free(&ls->ls_stid.sc_stateid); + spin_lock(&clp->cl_lock); list_del_init(&ls->ls_perclnt); spin_unlock(&clp->cl_lock); @@ -215,6 +218,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, list_add(&ls->ls_perfile, &fp->fi_lo_states); spin_unlock(&fp->fi_lock); + trace_layoutstate_alloc(&ls->ls_stid.sc_stateid); return ls; } @@ -280,6 +284,8 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) if (list_empty(&ls->ls_layouts)) goto out_unlock; + trace_layout_recall(&ls->ls_stid.sc_stateid); + atomic_inc(&ls->ls_stid.sc_count); update_stateid(&ls->ls_stid.sc_stateid); memcpy(&ls->ls_recall_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t)); @@ -454,8 +460,10 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid, false, lrp->lr_layout_type, &ls); - if (nfserr) + if (nfserr) { + trace_layout_return_lookup_fail(&lrp->lr_sid); return nfserr; + } spin_lock(&ls->ls_lock); list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) { @@ -472,6 +480,7 @@ nfsd4_return_file_layouts(struct svc_rqst *rqstp, } lrp->lrs_present = 1; } else { + trace_layoutstate_unhash(&ls->ls_stid.sc_stateid); nfs4_unhash_stid(&ls->ls_stid); lrp->lrs_present = 0; } @@ -570,6 +579,8 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls) rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str)); + nfsd4_cb_layout_fail(ls); + printk(KERN_WARNING "nfsd: client %s failed to respond to layout recall. " " Fencing..\n", addr_str); @@ -597,6 +608,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) case 0: return 1; case -NFS4ERR_NOMATCHING_LAYOUT: + trace_layout_recall_done(&ls->ls_stid.sc_stateid); task->tk_status = 0; return 1; case -NFS4ERR_DELAY: @@ -624,6 +636,8 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb) container_of(cb, struct nfs4_layout_stateid, ls_recall); LIST_HEAD(reaplist); + trace_layout_recall_release(&ls->ls_stid.sc_stateid); + nfsd4_return_all_layouts(ls, &reaplist); nfsd4_free_layouts(&reaplist); nfs4_put_stid(&ls->ls_stid); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index fa14359eb956..d30bea8d0277 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -44,6 +44,7 @@ #include "netns.h" #include "acl.h" #include "pnfs.h" +#include "trace.h" #ifdef CONFIG_NFSD_V4_SECURITY_LABEL #include @@ -1298,8 +1299,10 @@ nfsd4_layoutget(struct svc_rqst *rqstp, nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid, true, lgp->lg_layout_type, &ls); - if (nfserr) + if (nfserr) { + trace_layout_get_lookup_fail(&lgp->lg_sid); goto out; + } nfserr = nfserr_recallconflict; if (atomic_read(&ls->ls_stid.sc_file->fi_lo_recalls)) @@ -1359,6 +1362,7 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp, false, lcp->lc_layout_type, &ls); if (nfserr) { + trace_layout_commit_lookup_fail(&lcp->lc_sid); /* fixup error code as per RFC5661 */ if (nfserr == nfserr_bad_stateid) nfserr = nfserr_badlayout; diff --git a/fs/nfsd/trace.c b/fs/nfsd/trace.c new file mode 100644 index 000000000000..82f89070594c --- /dev/null +++ b/fs/nfsd/trace.c @@ -0,0 +1,5 @@ + +#include "state.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h new file mode 100644 index 000000000000..c668520c344b --- /dev/null +++ b/fs/nfsd/trace.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM nfsd + +#if !defined(_NFSD_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _NFSD_TRACE_H + +#include + +DECLARE_EVENT_CLASS(nfsd_stateid_class, + TP_PROTO(stateid_t *stp), + TP_ARGS(stp), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + ), + TP_fast_assign( + __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; + __entry->cl_id = stp->si_opaque.so_clid.cl_id; + __entry->si_id = stp->si_opaque.so_id; + __entry->si_generation = stp->si_generation; + ), + TP_printk("client %08x:%08x stateid %08x:%08x", + __entry->cl_boot, + __entry->cl_id, + __entry->si_id, + __entry->si_generation) +) + +#define DEFINE_STATEID_EVENT(name) \ +DEFINE_EVENT(nfsd_stateid_class, name, \ + TP_PROTO(stateid_t *stp), \ + TP_ARGS(stp)) +DEFINE_STATEID_EVENT(layoutstate_alloc); +DEFINE_STATEID_EVENT(layoutstate_unhash); +DEFINE_STATEID_EVENT(layoutstate_free); +DEFINE_STATEID_EVENT(layout_get_lookup_fail); +DEFINE_STATEID_EVENT(layout_commit_lookup_fail); +DEFINE_STATEID_EVENT(layout_return_lookup_fail); +DEFINE_STATEID_EVENT(layout_recall); +DEFINE_STATEID_EVENT(layout_recall_done); +DEFINE_STATEID_EVENT(layout_recall_fail); +DEFINE_STATEID_EVENT(layout_recall_release); + +#endif /* _NFSD_TRACE_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace +#include -- cgit v1.2.3 From 648695c74811f09a8ad80d7c3be72b8169589a64 Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Sun, 1 Feb 2015 17:00:24 +0100 Subject: jfs: Deletion of an unnecessary check before the function call "unload_nls" The unload_nls() function tests whether its argument is NULL and then returns immediately. Thus the test around the call is not needed. This issue was detected by using the Coccinelle software. Signed-off-by: Markus Elfring Signed-off-by: Dave Kleikamp --- fs/jfs/super.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 16c3a9556634..5d30c56ae075 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -619,8 +619,7 @@ out_mount_failed: iput(sbi->direct_inode); sbi->direct_inode = NULL; out_unload: - if (sbi->nls_tab) - unload_nls(sbi->nls_tab); + unload_nls(sbi->nls_tab); out_kfree: kfree(sbi); return ret; -- cgit v1.2.3 From 9c9ce763b114e608b5cf3aa6cb69ad9f6e8b6adf Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 3 Feb 2015 19:29:05 -0500 Subject: aio: annotate aio_read_event_ring for sleep patterns Under CONFIG_DEBUG_ATOMIC_SLEEP=y, aio_read_event_ring() will throw warnings like the following due to being called from wait_event context: WARNING: CPU: 0 PID: 16006 at kernel/sched/core.c:7300 __might_sleep+0x7f/0x90() do not call blocking ops when !TASK_RUNNING; state=1 set at [] prepare_to_wait_event+0x63/0x110 Modules linked in: CPU: 0 PID: 16006 Comm: aio-dio-fcntl-r Not tainted 3.19.0-rc6-dgc+ #705 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 ffffffff821c0372 ffff88003c117cd8 ffffffff81daf2bd 000000000000d8d8 ffff88003c117d28 ffff88003c117d18 ffffffff8109beda ffff88003c117cf8 ffffffff821c115e 0000000000000061 0000000000000000 00007ffffe4aa300 Call Trace: [] dump_stack+0x4c/0x65 [] warn_slowpath_common+0x8a/0xc0 [] warn_slowpath_fmt+0x46/0x50 [] ? prepare_to_wait_event+0x63/0x110 [] ? prepare_to_wait_event+0x63/0x110 [] __might_sleep+0x7f/0x90 [] mutex_lock+0x24/0x45 [] aio_read_events+0x4c/0x290 [] read_events+0x1ec/0x220 [] ? prepare_to_wait_event+0x110/0x110 [] ? hrtimer_get_res+0x50/0x50 [] SyS_io_getevents+0x4d/0xb0 [] system_call_fastpath+0x12/0x17 ---[ end trace bde69eaf655a4fea ]--- There is not actually a bug here, so annotate the code to tell the debug logic that everything is just fine and not to fire a false positive. Signed-off-by: Dave Chinner Signed-off-by: Benjamin LaHaise --- fs/aio.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs') diff --git a/fs/aio.c b/fs/aio.c index 1b7893ecc296..c428871f1093 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1140,6 +1140,13 @@ static long aio_read_events_ring(struct kioctx *ctx, long ret = 0; int copy_ret; + /* + * The mutex can block and wake us up and that will cause + * wait_event_interruptible_hrtimeout() to schedule without sleeping + * and repeat. This should be rare enough that it doesn't cause + * peformance issues. See the comment in read_events() for more detail. + */ + sched_annotate_sleep(); mutex_lock(&ctx->ring_lock); /* Access to ->ring_pages here is protected by ctx->ring_lock. */ -- cgit v1.2.3 From 2e90b1c45e34240eeeacab0b37d5f8f739462bdc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 27 Nov 2014 21:50:31 -0500 Subject: rxrpc: make the users of rxrpc_kernel_send_data() set kvec-backed msg_iter properly Use iov_iter_kvec() there, get rid of set_fs() games - now that rxrpc_send_data() uses iov_iter primitives, it'll handle ITER_KVEC just fine. Signed-off-by: Al Viro --- fs/afs/rxrpc.c | 14 +++++++------- net/rxrpc/ar-output.c | 3 --- 2 files changed, 7 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 06e14bfb3496..dbc732e9a5c0 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -306,8 +306,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg, _debug("- range %u-%u%s", offset, to, msg->msg_flags ? " [more]" : ""); - iov_iter_init(&msg->msg_iter, WRITE, - (struct iovec *) iov, 1, to - offset); + iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, + iov, 1, to - offset); /* have to change the state *before* sending the last * packet as RxRPC might give us the reply before it @@ -384,7 +384,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iov, 1, + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, call->request_size); msg.msg_control = NULL; msg.msg_controllen = 0; @@ -770,7 +770,7 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, void afs_send_empty_reply(struct afs_call *call) { struct msghdr msg; - struct iovec iov[1]; + struct kvec iov[1]; _enter(""); @@ -778,7 +778,7 @@ void afs_send_empty_reply(struct afs_call *call) iov[0].iov_len = 0; msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_init(&msg.msg_iter, WRITE, iov, 0, 0); /* WTF? */ + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 0, 0); /* WTF? */ msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -805,7 +805,7 @@ void afs_send_empty_reply(struct afs_call *call) void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) { struct msghdr msg; - struct iovec iov[1]; + struct kvec iov[1]; int n; _enter(""); @@ -814,7 +814,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) iov[0].iov_len = len; msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_init(&msg.msg_iter, WRITE, iov, 1, len); + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, len); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index 963a5b91f3e8..8331c95e1522 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -232,10 +232,7 @@ int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, call->state != RXRPC_CALL_SERVER_SEND_REPLY) { ret = -EPROTO; /* request phase complete for this client call */ } else { - mm_segment_t oldfs = get_fs(); - set_fs(KERNEL_DS); ret = rxrpc_send_data(NULL, call->socket, call, msg, len); - set_fs(oldfs); } release_sock(&call->socket->sk); -- cgit v1.2.3 From 7456a37d55ced3928fd96615fde0dd739985f0dc Mon Sep 17 00:00:00 2001 From: Oleg Drokin Date: Sun, 1 Feb 2015 22:59:54 -0500 Subject: GFS2: use __vmalloc GFP_NOFS for fs-related allocations. leaf_dealloc uses vzalloc as a fallback to kzalloc(GFP_NOFS), so it clearly does not want any shrinker activity within the fs itself. convert vzalloc into __vmalloc(GFP_NOFS|__GFP_ZERO) to better achieve this goal. Signed-off-by: Oleg Drokin Signed-off-by: Steven Whitehouse --- fs/gfs2/dir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index c5a34f09e228..6371192961e2 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -1896,7 +1896,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, ht = kzalloc(size, GFP_NOFS | __GFP_NOWARN); if (ht == NULL) - ht = vzalloc(size); + ht = __vmalloc(size, GFP_NOFS | __GFP_NOWARN | __GFP_ZERO, + PAGE_KERNEL); if (!ht) return -ENOMEM; -- cgit v1.2.3 From f8079b850c9e130423829c919f3c0802e677099d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 5 Feb 2015 11:13:21 +1100 Subject: xfs: growfs should use synchronous transactions Growfs updates the secondary superblocks using synchronous unlogged buffer writes after committing the updates to the primary superblock. Mark the transaction to the primary superblock as synchronous so that we guarantee it is committed to disk before we update the secondary superblocks. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_fsops.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index f7114527cd2f..fba6532efba4 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -488,6 +488,7 @@ xfs_growfs_data_private( xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, nfree); if (dpct) xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct); + xfs_trans_set_sync(tp); error = xfs_trans_commit(tp, 0); if (error) return error; -- cgit v1.2.3 From f92090e95cd26ea0a80dc8305b685cc30f6a501f Mon Sep 17 00:00:00 2001 From: kbuild test robot Date: Thu, 5 Feb 2015 11:13:21 +1100 Subject: xfs: xfs_ioctl_setattr_check_projid can be static fs/xfs/xfs_ioctl.c:1146:1: sparse: symbol 'xfs_ioctl_setattr_check_projid' was not declared. Should it be static? Also fix xfs_ioctl_setattr_check_extsize at the same time. Signed-off-by: Fengguang Wu Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_ioctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 0f6b6abb7c7a..f1dc90be508c 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1112,7 +1112,7 @@ out_cancel: * to half the AG size to avoid alignment extending the extent beyond the * limits of the AG. */ -int +static int xfs_ioctl_setattr_check_extsize( struct xfs_inode *ip, struct fsxattr *fa) @@ -1155,7 +1155,7 @@ xfs_ioctl_setattr_check_extsize( return 0; } -int +static int xfs_ioctl_setattr_check_projid( struct xfs_inode *ip, struct fsxattr *fa) -- cgit v1.2.3 From 3da5ab56482f322a9736c484db8773899c5c731b Mon Sep 17 00:00:00 2001 From: Forrest Liu Date: Fri, 30 Jan 2015 19:42:12 +0800 Subject: Btrfs: add missing blk_finish_plug in btrfs_sync_log() Add missing blk_finish_plug in btrfs_sync_log() Signed-off-by: Forrest Liu Reviewed-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9a02da16f2be..1a9585d4380a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2591,6 +2591,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, } if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { + blk_finish_plug(&plug); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; -- cgit v1.2.3 From 8650b8a058502d6957ba13dfb5544724fa038118 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Jan 2015 11:40:00 +0100 Subject: nfsd: pNFS block layout driver Add a small shim between core nfsd and filesystems to translate the somewhat cumbersome pNFS data structures and semantics to something more palatable for Linux filesystems. Thanks to Rick McNeal for the old prototype pNFS blocklayout server code, which gave a lot of inspiration to this version even if no code is left from it. Signed-off-by: Christoph Hellwig --- .../filesystems/nfs/pnfs-block-server.txt | 37 ++++ fs/nfsd/Makefile | 2 +- fs/nfsd/blocklayout.c | 189 +++++++++++++++++++++ fs/nfsd/blocklayoutxdr.c | 157 +++++++++++++++++ fs/nfsd/blocklayoutxdr.h | 62 +++++++ fs/nfsd/nfs4layouts.c | 8 + fs/nfsd/pnfs.h | 1 + 7 files changed, 455 insertions(+), 1 deletion(-) create mode 100644 Documentation/filesystems/nfs/pnfs-block-server.txt create mode 100644 fs/nfsd/blocklayout.c create mode 100644 fs/nfsd/blocklayoutxdr.c create mode 100644 fs/nfsd/blocklayoutxdr.h (limited to 'fs') diff --git a/Documentation/filesystems/nfs/pnfs-block-server.txt b/Documentation/filesystems/nfs/pnfs-block-server.txt new file mode 100644 index 000000000000..2143673cf154 --- /dev/null +++ b/Documentation/filesystems/nfs/pnfs-block-server.txt @@ -0,0 +1,37 @@ +pNFS block layout server user guide + +The Linux NFS server now supports the pNFS block layout extension. In this +case the NFS server acts as Metadata Server (MDS) for pNFS, which in addition +to handling all the metadata access to the NFS export also hands out layouts +to the clients to directly access the underlying block devices that are +shared with the client. + +To use pNFS block layouts with with the Linux NFS server the exported file +system needs to support the pNFS block layouts (currently just XFS), and the +file system must sit on shared storage (typically iSCSI) that is accessible +to the clients in addition to the MDS. As of now the file system needs to +sit directly on the exported volume, striping or concatenation of +volumes on the MDS and clients is not supported yet. + +On the server, pNFS block volume support is automatically if the file system +support it. On the client make sure the kernel has the CONFIG_PNFS_BLOCK +option enabled, the blkmapd daemon from nfs-utils is running, and the +file system is mounted using the NFSv4.1 protocol version (mount -o vers=4.1). + +If the nfsd server needs to fence a non-responding client it calls +/sbin/nfsd-recall-failed with the first argument set to the IP address of +the client, and the second argument set to the device node without the /dev +prefix for the file system to be fenced. Below is an example file that shows +how to translate the device into a serial number from SCSI EVPD 0x80: + +cat > /sbin/nfsd-recall-failed << EOF +#!/bin/sh + +CLIENT="$1" +DEV="/dev/$2" +EVPD=`sg_inq --page=0x80 ${DEV} | \ + grep "Unit serial number:" | \ + awk -F ': ' '{print $2}'` + +echo "fencing client ${CLIENT} serial ${EVPD}" >> /var/log/pnfsd-fence.log +EOF diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 6cba933880c5..9a6028e120c6 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -17,4 +17,4 @@ nfsd-$(CONFIG_NFSD_V3) += nfs3proc.o nfs3xdr.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ nfs4acl.o nfs4callback.o nfs4recover.o -nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o +nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o blocklayout.o blocklayoutxdr.o diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c new file mode 100644 index 000000000000..cdbc78c72542 --- /dev/null +++ b/fs/nfsd/blocklayout.c @@ -0,0 +1,189 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ +#include +#include +#include + +#include + +#include "blocklayoutxdr.h" +#include "pnfs.h" + +#define NFSDDBG_FACILITY NFSDDBG_PNFS + + +static int +nfsd4_block_get_device_info_simple(struct super_block *sb, + struct nfsd4_getdeviceinfo *gdp) +{ + struct pnfs_block_deviceaddr *dev; + struct pnfs_block_volume *b; + + dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) + + sizeof(struct pnfs_block_volume), GFP_KERNEL); + if (!dev) + return -ENOMEM; + gdp->gd_device = dev; + + dev->nr_volumes = 1; + b = &dev->volumes[0]; + + b->type = PNFS_BLOCK_VOLUME_SIMPLE; + b->simple.sig_len = PNFS_BLOCK_UUID_LEN; + return sb->s_export_op->get_uuid(sb, b->simple.sig, &b->simple.sig_len, + &b->simple.offset); +} + +static __be32 +nfsd4_block_proc_getdeviceinfo(struct super_block *sb, + struct nfsd4_getdeviceinfo *gdp) +{ + if (sb->s_bdev != sb->s_bdev->bd_contains) + return nfserr_inval; + return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp)); +} + +static __be32 +nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp, + struct nfsd4_layoutget *args) +{ + struct nfsd4_layout_seg *seg = &args->lg_seg; + struct super_block *sb = inode->i_sb; + u32 block_size = (1 << inode->i_blkbits); + struct pnfs_block_extent *bex; + struct iomap iomap; + u32 device_generation = 0; + int error; + + /* + * We do not attempt to support I/O smaller than the fs block size, + * or not aligned to it. + */ + if (args->lg_minlength < block_size) { + dprintk("pnfsd: I/O too small\n"); + goto out_layoutunavailable; + } + if (seg->offset & (block_size - 1)) { + dprintk("pnfsd: I/O misaligned\n"); + goto out_layoutunavailable; + } + + /* + * Some clients barf on non-zero block numbers for NONE or INVALID + * layouts, so make sure to zero the whole structure. + */ + error = -ENOMEM; + bex = kzalloc(sizeof(*bex), GFP_KERNEL); + if (!bex) + goto out_error; + args->lg_content = bex; + + error = sb->s_export_op->map_blocks(inode, seg->offset, seg->length, + &iomap, seg->iomode != IOMODE_READ, + &device_generation); + if (error) { + if (error == -ENXIO) + goto out_layoutunavailable; + goto out_error; + } + + if (iomap.length < args->lg_minlength) { + dprintk("pnfsd: extent smaller than minlength\n"); + goto out_layoutunavailable; + } + + switch (iomap.type) { + case IOMAP_MAPPED: + if (seg->iomode == IOMODE_READ) + bex->es = PNFS_BLOCK_READ_DATA; + else + bex->es = PNFS_BLOCK_READWRITE_DATA; + bex->soff = (iomap.blkno << 9); + break; + case IOMAP_UNWRITTEN: + if (seg->iomode & IOMODE_RW) { + /* + * Crack monkey special case from section 2.3.1. + */ + if (args->lg_minlength == 0) { + dprintk("pnfsd: no soup for you!\n"); + goto out_layoutunavailable; + } + + bex->es = PNFS_BLOCK_INVALID_DATA; + bex->soff = (iomap.blkno << 9); + break; + } + /*FALLTHRU*/ + case IOMAP_HOLE: + if (seg->iomode == IOMODE_READ) { + bex->es = PNFS_BLOCK_NONE_DATA; + break; + } + /*FALLTHRU*/ + case IOMAP_DELALLOC: + default: + WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type); + goto out_layoutunavailable; + } + + error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation); + if (error) + goto out_error; + bex->foff = iomap.offset; + bex->len = iomap.length; + + seg->offset = iomap.offset; + seg->length = iomap.length; + + dprintk("GET: %lld:%lld %d\n", bex->foff, bex->len, bex->es); + return 0; + +out_error: + seg->length = 0; + return nfserrno(error); +out_layoutunavailable: + seg->length = 0; + return nfserr_layoutunavailable; +} + +static __be32 +nfsd4_block_proc_layoutcommit(struct inode *inode, + struct nfsd4_layoutcommit *lcp) +{ + loff_t new_size = lcp->lc_last_wr + 1; + struct iattr iattr = { .ia_valid = 0 }; + struct iomap *iomaps; + int nr_iomaps; + int error; + + nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout, + lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits); + if (nr_iomaps < 0) + return nfserrno(nr_iomaps); + + if (lcp->lc_mtime.tv_nsec == UTIME_NOW || + timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0) + lcp->lc_mtime = current_fs_time(inode->i_sb); + iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME; + iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime; + + if (new_size > i_size_read(inode)) { + iattr.ia_valid |= ATTR_SIZE; + iattr.ia_size = new_size; + } + + error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps, + nr_iomaps, &iattr); + kfree(iomaps); + return nfserrno(error); +} + +const struct nfsd4_layout_ops bl_layout_ops = { + .proc_getdeviceinfo = nfsd4_block_proc_getdeviceinfo, + .encode_getdeviceinfo = nfsd4_block_encode_getdeviceinfo, + .proc_layoutget = nfsd4_block_proc_layoutget, + .encode_layoutget = nfsd4_block_encode_layoutget, + .proc_layoutcommit = nfsd4_block_proc_layoutcommit, +}; diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c new file mode 100644 index 000000000000..9da89fddab33 --- /dev/null +++ b/fs/nfsd/blocklayoutxdr.c @@ -0,0 +1,157 @@ +/* + * Copyright (c) 2014 Christoph Hellwig. + */ +#include +#include +#include + +#include "nfsd.h" +#include "blocklayoutxdr.h" + +#define NFSDDBG_FACILITY NFSDDBG_PNFS + + +__be32 +nfsd4_block_encode_layoutget(struct xdr_stream *xdr, + struct nfsd4_layoutget *lgp) +{ + struct pnfs_block_extent *b = lgp->lg_content; + int len = sizeof(__be32) + 5 * sizeof(__be64) + sizeof(__be32); + __be32 *p; + + p = xdr_reserve_space(xdr, sizeof(__be32) + len); + if (!p) + return nfserr_toosmall; + + *p++ = cpu_to_be32(len); + *p++ = cpu_to_be32(1); /* we always return a single extent */ + + p = xdr_encode_opaque_fixed(p, &b->vol_id, + sizeof(struct nfsd4_deviceid)); + p = xdr_encode_hyper(p, b->foff); + p = xdr_encode_hyper(p, b->len); + p = xdr_encode_hyper(p, b->soff); + *p++ = cpu_to_be32(b->es); + return 0; +} + +static int +nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b) +{ + __be32 *p; + int len; + + switch (b->type) { + case PNFS_BLOCK_VOLUME_SIMPLE: + len = 4 + 4 + 8 + 4 + b->simple.sig_len; + p = xdr_reserve_space(xdr, len); + if (!p) + return -ETOOSMALL; + + *p++ = cpu_to_be32(b->type); + *p++ = cpu_to_be32(1); /* single signature */ + p = xdr_encode_hyper(p, b->simple.offset); + p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len); + break; + default: + return -ENOTSUPP; + } + + return len; +} + +__be32 +nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, + struct nfsd4_getdeviceinfo *gdp) +{ + struct pnfs_block_deviceaddr *dev = gdp->gd_device; + int len = sizeof(__be32), ret, i; + __be32 *p; + + p = xdr_reserve_space(xdr, len + sizeof(__be32)); + if (!p) + return nfserr_resource; + + for (i = 0; i < dev->nr_volumes; i++) { + ret = nfsd4_block_encode_volume(xdr, &dev->volumes[i]); + if (ret < 0) + return nfserrno(ret); + len += ret; + } + + /* + * Fill in the overall length and number of volumes at the beginning + * of the layout. + */ + *p++ = cpu_to_be32(len); + *p++ = cpu_to_be32(dev->nr_volumes); + return 0; +} + +int +nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, + u32 block_size) +{ + struct iomap *iomaps; + u32 nr_iomaps, expected, i; + + if (len < sizeof(u32)) { + dprintk("%s: extent array too small: %u\n", __func__, len); + return -EINVAL; + } + + nr_iomaps = be32_to_cpup(p++); + expected = sizeof(__be32) + nr_iomaps * NFS4_BLOCK_EXTENT_SIZE; + if (len != expected) { + dprintk("%s: extent array size mismatch: %u/%u\n", + __func__, len, expected); + return -EINVAL; + } + + iomaps = kcalloc(nr_iomaps, sizeof(*iomaps), GFP_KERNEL); + if (!iomaps) { + dprintk("%s: failed to allocate extent array\n", __func__); + return -ENOMEM; + } + + for (i = 0; i < nr_iomaps; i++) { + struct pnfs_block_extent bex; + + memcpy(&bex.vol_id, p, sizeof(struct nfsd4_deviceid)); + p += XDR_QUADLEN(sizeof(struct nfsd4_deviceid)); + + p = xdr_decode_hyper(p, &bex.foff); + if (bex.foff & (block_size - 1)) { + dprintk("%s: unaligned offset %lld\n", + __func__, bex.foff); + goto fail; + } + p = xdr_decode_hyper(p, &bex.len); + if (bex.len & (block_size - 1)) { + dprintk("%s: unaligned length %lld\n", + __func__, bex.foff); + goto fail; + } + p = xdr_decode_hyper(p, &bex.soff); + if (bex.soff & (block_size - 1)) { + dprintk("%s: unaligned disk offset %lld\n", + __func__, bex.soff); + goto fail; + } + bex.es = be32_to_cpup(p++); + if (bex.es != PNFS_BLOCK_READWRITE_DATA) { + dprintk("%s: incorrect extent state %d\n", + __func__, bex.es); + goto fail; + } + + iomaps[i].offset = bex.foff; + iomaps[i].length = bex.len; + } + + *iomapp = iomaps; + return nr_iomaps; +fail: + kfree(iomaps); + return -EINVAL; +} diff --git a/fs/nfsd/blocklayoutxdr.h b/fs/nfsd/blocklayoutxdr.h new file mode 100644 index 000000000000..fdc79037c0e7 --- /dev/null +++ b/fs/nfsd/blocklayoutxdr.h @@ -0,0 +1,62 @@ +#ifndef _NFSD_BLOCKLAYOUTXDR_H +#define _NFSD_BLOCKLAYOUTXDR_H 1 + +#include +#include "xdr4.h" + +struct iomap; +struct xdr_stream; + +enum pnfs_block_extent_state { + PNFS_BLOCK_READWRITE_DATA = 0, + PNFS_BLOCK_READ_DATA = 1, + PNFS_BLOCK_INVALID_DATA = 2, + PNFS_BLOCK_NONE_DATA = 3, +}; + +struct pnfs_block_extent { + struct nfsd4_deviceid vol_id; + u64 foff; + u64 len; + u64 soff; + enum pnfs_block_extent_state es; +}; +#define NFS4_BLOCK_EXTENT_SIZE 44 + +enum pnfs_block_volume_type { + PNFS_BLOCK_VOLUME_SIMPLE = 0, + PNFS_BLOCK_VOLUME_SLICE = 1, + PNFS_BLOCK_VOLUME_CONCAT = 2, + PNFS_BLOCK_VOLUME_STRIPE = 3, +}; + +/* + * Random upper cap for the uuid length to avoid unbounded allocation. + * Not actually limited by the protocol. + */ +#define PNFS_BLOCK_UUID_LEN 128 + +struct pnfs_block_volume { + enum pnfs_block_volume_type type; + union { + struct { + u64 offset; + u32 sig_len; + u8 sig[PNFS_BLOCK_UUID_LEN]; + } simple; + }; +}; + +struct pnfs_block_deviceaddr { + u32 nr_volumes; + struct pnfs_block_volume volumes[]; +}; + +__be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, + struct nfsd4_getdeviceinfo *gdp); +__be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr, + struct nfsd4_layoutget *lgp); +int nfsd4_block_decode_layoutupdate(__be32 *p, u32 len, struct iomap **iomapp, + u32 block_size); + +#endif /* _NFSD_BLOCKLAYOUTXDR_H */ diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 60137c54b2f7..3c1bfa155571 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -26,6 +26,7 @@ static struct nfsd4_callback_ops nfsd4_cb_layout_ops; static const struct lock_manager_operations nfsd4_layouts_lm_ops; const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] = { + [LAYOUT_BLOCK_VOLUME] = &bl_layout_ops, }; /* pNFS device ID to export fsid mapping */ @@ -115,8 +116,15 @@ nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp, void nfsd4_setup_layout_type(struct svc_export *exp) { + struct super_block *sb = exp->ex_path.mnt->mnt_sb; + if (exp->ex_flags & NFSEXP_NOPNFS) return; + + if (sb->s_export_op->get_uuid && + sb->s_export_op->map_blocks && + sb->s_export_op->commit_blocks) + exp->ex_layout_type = LAYOUT_BLOCK_VOLUME; } static void diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h index a9616a4e13cd..fedb4d620a81 100644 --- a/fs/nfsd/pnfs.h +++ b/fs/nfsd/pnfs.h @@ -34,6 +34,7 @@ struct nfsd4_layout_ops { }; extern const struct nfsd4_layout_ops *nfsd4_layout_ops[]; +extern const struct nfsd4_layout_ops bl_layout_ops; __be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid, -- cgit v1.2.3 From 2b8f942111b1be0ae4916de6a7c60658431269da Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Feb 2015 18:15:04 +0100 Subject: udf: use bool for done variable 'done' is only used for true/false in loop. Signed-off-by: Fabian Frederick Signed-off-by: Jan Kara --- fs/udf/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/udf/super.c b/fs/udf/super.c index 3d35a754293a..f169411c4ea0 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1599,7 +1599,7 @@ static noinline int udf_process_sequence( struct udf_vds_record *curr; struct generic_desc *gd; struct volDescPtr *vdp; - int done = 0; + bool done = false; uint32_t vdsn; uint16_t ident; long next_s = 0, next_e = 0; @@ -1680,7 +1680,7 @@ static noinline int udf_process_sequence( lastblock = next_e; next_s = next_e = 0; } else - done = 1; + done = true; break; } brelse(bh); -- cgit v1.2.3 From 6981498d7956e3177b6f74926aa4a5c2a45b4edb Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Wed, 4 Feb 2015 18:26:27 +0100 Subject: udf: remove bool assignment to 0/1 Fix the following coccinelle warnings: fs/udf/inode.c:753:2-13: WARNING: Assignment of bool to 0/1 fs/udf/inode.c:795:2-13: WARNING: Assignment of bool to 0/1 Signed-off-by: Fabian Frederick Signed-off-by: Jan Kara --- fs/udf/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 7b72b7dd8906..a445d599098d 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -750,7 +750,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* Are we beyond EOF? */ if (etype == -1) { int ret; - isBeyondEOF = 1; + isBeyondEOF = true; if (count) { if (c) laarr[0] = laarr[1]; @@ -792,7 +792,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, endnum = c + 1; lastblock = 1; } else { - isBeyondEOF = 0; + isBeyondEOF = false; endnum = startnum = ((count > 2) ? 2 : count); /* if the current extent is in position 0, -- cgit v1.2.3 From 7ef3ff2fea8bf5e4a21cef47ad87710a3d0fdb52 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 5 Feb 2015 12:25:20 -0800 Subject: nilfs2: fix deadlock of segment constructor over I_SYNC flag Nilfs2 eventually hangs in a stress test with fsstress program. This issue was caused by the following deadlock over I_SYNC flag between nilfs_segctor_thread() and writeback_sb_inodes(): nilfs_segctor_thread() nilfs_segctor_thread_construct() nilfs_segctor_unlock() nilfs_dispose_list() iput() iput_final() evict() inode_wait_for_writeback() * wait for I_SYNC flag writeback_sb_inodes() * set I_SYNC flag on inode->i_state __writeback_single_inode() do_writepages() nilfs_writepages() nilfs_construct_dsync_segment() nilfs_segctor_sync() * wait for completion of segment constructor inode_sync_complete() * clear I_SYNC flag after __writeback_single_inode() completed writeback_sb_inodes() calls do_writepages() for dirty inodes after setting I_SYNC flag on inode->i_state. do_writepages() in turn calls nilfs_writepages(), which can run segment constructor and wait for its completion. On the other hand, segment constructor calls iput(), which can call evict() and wait for the I_SYNC flag on inode_wait_for_writeback(). Since segment constructor doesn't know when I_SYNC will be set, it cannot know whether iput() will block or not unless inode->i_nlink has a non-zero count. We can prevent evict() from being called in iput() by implementing sop->drop_inode(), but it's not preferable to leave inodes with i_nlink == 0 for long periods because it even defers file truncation and inode deallocation. So, this instead resolves the deadlock by calling iput() asynchronously with a workqueue for inodes with i_nlink == 0. Signed-off-by: Ryusuke Konishi Cc: Al Viro Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nilfs2/nilfs.h | 2 -- fs/nilfs2/segment.c | 44 +++++++++++++++++++++++++++++++++++++++----- fs/nilfs2/segment.h | 5 +++++ 3 files changed, 44 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 91093cd74f0d..385704027575 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -141,7 +141,6 @@ enum { * @ti_save: Backup of journal_info field of task_struct * @ti_flags: Flags * @ti_count: Nest level - * @ti_garbage: List of inode to be put when releasing semaphore */ struct nilfs_transaction_info { u32 ti_magic; @@ -150,7 +149,6 @@ struct nilfs_transaction_info { one of other filesystems has a bug. */ unsigned short ti_flags; unsigned short ti_count; - struct list_head ti_garbage; }; /* ti_magic */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 7ef18fc656c2..469086b9f99b 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -305,7 +305,6 @@ static void nilfs_transaction_lock(struct super_block *sb, ti->ti_count = 0; ti->ti_save = cur_ti; ti->ti_magic = NILFS_TI_MAGIC; - INIT_LIST_HEAD(&ti->ti_garbage); current->journal_info = ti; for (;;) { @@ -332,8 +331,6 @@ static void nilfs_transaction_unlock(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); current->journal_info = ti->ti_save; - if (!list_empty(&ti->ti_garbage)) - nilfs_dispose_list(nilfs, &ti->ti_garbage, 0); } static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci, @@ -746,6 +743,15 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs, } } +static void nilfs_iput_work_func(struct work_struct *work) +{ + struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info, + sc_iput_work); + struct the_nilfs *nilfs = sci->sc_super->s_fs_info; + + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0); +} + static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs, struct nilfs_root *root) { @@ -1900,8 +1906,8 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci, static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, struct the_nilfs *nilfs) { - struct nilfs_transaction_info *ti = current->journal_info; struct nilfs_inode_info *ii, *n; + int defer_iput = false; spin_lock(&nilfs->ns_inode_lock); list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) { @@ -1912,9 +1918,24 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci, clear_bit(NILFS_I_BUSY, &ii->i_state); brelse(ii->i_bh); ii->i_bh = NULL; - list_move_tail(&ii->i_dirty, &ti->ti_garbage); + list_del_init(&ii->i_dirty); + if (!ii->vfs_inode.i_nlink) { + /* + * Defer calling iput() to avoid a deadlock + * over I_SYNC flag for inodes with i_nlink == 0 + */ + list_add_tail(&ii->i_dirty, &sci->sc_iput_queue); + defer_iput = true; + } else { + spin_unlock(&nilfs->ns_inode_lock); + iput(&ii->vfs_inode); + spin_lock(&nilfs->ns_inode_lock); + } } spin_unlock(&nilfs->ns_inode_lock); + + if (defer_iput) + schedule_work(&sci->sc_iput_work); } /* @@ -2583,6 +2604,8 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_segbufs); INIT_LIST_HEAD(&sci->sc_write_logs); INIT_LIST_HEAD(&sci->sc_gc_inodes); + INIT_LIST_HEAD(&sci->sc_iput_queue); + INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); init_timer(&sci->sc_timer); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; @@ -2609,6 +2632,8 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) ret = nilfs_segctor_construct(sci, SC_LSEG_SR); nilfs_transaction_unlock(sci->sc_super); + flush_work(&sci->sc_iput_work); + } while (ret && retrycount-- > 0); } @@ -2633,6 +2658,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + if (flush_work(&sci->sc_iput_work)) + flag = true; + if (flag || !nilfs_segctor_confirm(sci)) nilfs_segctor_write_out(sci); @@ -2642,6 +2670,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1); } + if (!list_empty(&sci->sc_iput_queue)) { + nilfs_warning(sci->sc_super, __func__, + "iput queue is not empty\n"); + nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1); + } + WARN_ON(!list_empty(&sci->sc_segbufs)); WARN_ON(!list_empty(&sci->sc_write_logs)); diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 38a1d0013314..a48d6de1e02c 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -26,6 +26,7 @@ #include #include #include +#include #include #include "nilfs.h" @@ -92,6 +93,8 @@ struct nilfs_segsum_pointer { * @sc_nblk_inc: Block count of current generation * @sc_dirty_files: List of files to be written * @sc_gc_inodes: List of GC inodes having blocks to be written + * @sc_iput_queue: list of inodes for which iput should be done + * @sc_iput_work: work struct to defer iput call * @sc_freesegs: array of segment numbers to be freed * @sc_nfreesegs: number of segments on @sc_freesegs * @sc_dsync_inode: inode whose data pages are written for a sync operation @@ -135,6 +138,8 @@ struct nilfs_sc_info { struct list_head sc_dirty_files; struct list_head sc_gc_inodes; + struct list_head sc_iput_queue; + struct work_struct sc_iput_work; __u64 *sc_freesegs; size_t sc_nfreesegs; -- cgit v1.2.3 From 01f9882eac84b85421a469cb65ee9bb555a5985f Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 6 Feb 2015 09:53:02 +1100 Subject: xfs: report proper f_files in statfs if we overshoot imaxpct Normally, a statfs syscall reports m_maxicount as f_files (total file nodes in file system) because it is supposed to be the upper limit for dynamically-allocated inodes. It's possible, however, to overshoot imaxpct / m_maxicount. If this happens, we should report the actual number of allocated inodes, which is contained in sb_icount. Add one more adjustment to the statfs code to make this happen. Reported-by: Alexander Tsvetkov Signed-off-by: Eric Sandeen Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_super.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'fs') diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index a3b791b85336..26afa436fafe 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1111,6 +1111,11 @@ xfs_fs_statfs( statp->f_files, mp->m_maxicount); + /* If sb_icount overshot maxicount, report actual allocation */ + statp->f_files = max_t(typeof(statp->f_files), + statp->f_files, + sbp->sb_icount); + /* make sure statp->f_ffree does not underflow */ ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree); statp->f_ffree = max_t(__int64_t, ffree, 0); -- cgit v1.2.3 From c23ae6017835b5bc9b9ec9d5d9c2b1523053f503 Mon Sep 17 00:00:00 2001 From: J. Bruce Fields Date: Mon, 12 Jan 2015 14:52:15 -0500 Subject: nfsd: default NFSv4.2 to on The code seems to work. The protocol looks stable. The kernel's version defaults can be overridden by rpc.nfsd arguments. Signed-off-by: J. Bruce Fields --- fs/nfsd/nfssvc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 314f5c8f8f1a..9277cc91c21b 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -119,6 +119,7 @@ struct svc_program nfsd_program = { static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = { [0] = 1, [1] = 1, + [2] = 1, }; int nfsd_vers(int vers, enum vers_op change) -- cgit v1.2.3 From e9892d3cc853afdda2cc69e2576d9ddb5fafad71 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 10 Feb 2015 09:23:40 +1100 Subject: xfs: only trace buffer items if they exist The commit 2d3d0c5 ("xfs: lobotomise xfs_trans_read_buf_map()") left a landmine in the tracing code: trace_xfs_trans_buf_read() is now call on all buffers that are read through this interface rather than just buffers in transactions. For buffers outside transaction context, bp->b_fspriv is null, and so the buf log item tracing functions cannot be called. This causes a NULL pointer dereference in the trace_xfs_trans_buf_read() function when tracing is turned on. cc: Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_trans_buf.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 0a4d4ab6d9a9..75798412859a 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -327,9 +327,10 @@ xfs_trans_read_buf_map( return -EIO; } - if (tp) + if (tp) { _xfs_trans_bjoin(tp, bp, 1); - trace_xfs_trans_read_buf(bp->b_fspriv); + trace_xfs_trans_read_buf(bp->b_fspriv); + } *bpp = bp; return 0; -- cgit v1.2.3 From 278702074ff77b1a3fa2061267997095959f5e2c Mon Sep 17 00:00:00 2001 From: Andrew Elble Date: Mon, 9 Feb 2015 12:53:04 -0500 Subject: GFS2: Fix crash during ACL deletion in acl max entry check in gfs2_set_acl() Fixes: e01580bf9e ("gfs2: use generic posix ACL infrastructure") Reported-by: Eric Meddaugh Tested-by: Eric Meddaugh Signed-off-by: Andrew Elble Signed-off-by: Steven Whitehouse --- fs/gfs2/acl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 3088e2a38e30..7b3143064af1 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -73,7 +73,7 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) BUG_ON(name == NULL); - if (acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode))) + if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode))) return -E2BIG; if (type == ACL_TYPE_ACCESS) { -- cgit v1.2.3 From a118449a7792ea800db6f23cf6c1d2f937c2629a Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Tue, 10 Feb 2015 14:08:21 -0800 Subject: fanotify: only destroy mark when both mask and ignored_mask are cleared In fanotify_mark_remove_from_mask() a mark is destroyed if only one of both bitmasks (mask or ignored_mask) of a mark is cleared. However the other mask may still be set and contain information that should not be lost. So only destroy a mark if both masks are cleared. Signed-off-by: Lino Sanfilippo Reviewed-by: Jan Kara Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify_user.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index bff8567aa42d..25adb6d1b3db 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -497,10 +497,9 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, oldmask = fsn_mark->ignored_mask; fsnotify_set_mark_ignored_mask_locked(fsn_mark, (oldmask & ~mask)); } + *destroy = !(fsn_mark->mask | fsn_mark->ignored_mask); spin_unlock(&fsn_mark->lock); - *destroy = !(oldmask & ~mask); - return mask & oldmask; } -- cgit v1.2.3 From d2c1874ce687c175b544bc28b6187bf03735a931 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Tue, 10 Feb 2015 14:08:24 -0800 Subject: fanotify: don't recalculate a marks mask if only the ignored mask changed If removing bits from a mark's ignored mask, the concerning inodes/vfsmounts mask is not affected. So don't recalculate it. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Lino Sanfilippo Reviewed-by: Jan Kara Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify_user.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 25adb6d1b3db..f4d279807a96 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -487,15 +487,16 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, unsigned int flags, int *destroy) { - __u32 oldmask; + __u32 oldmask = 0; spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { oldmask = fsn_mark->mask; fsnotify_set_mark_mask_locked(fsn_mark, (oldmask & ~mask)); } else { - oldmask = fsn_mark->ignored_mask; - fsnotify_set_mark_ignored_mask_locked(fsn_mark, (oldmask & ~mask)); + __u32 tmask = fsn_mark->ignored_mask & ~mask; + + fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); } *destroy = !(fsn_mark->mask | fsn_mark->ignored_mask); spin_unlock(&fsn_mark->lock); -- cgit v1.2.3 From 66ba93c0d7fe63def447ad0afe380307ff9ebcad Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Tue, 10 Feb 2015 14:08:27 -0800 Subject: fanotify: don't set FAN_ONDIR implicitly on a marks ignored mask Currently FAN_ONDIR is always set on a mark's ignored mask when the event mask is extended without FAN_MARK_ONDIR being set. This may result in events for directories being ignored unexpectedly for call sequences like fanotify_mark(fd, FAN_MARK_ADD, FAN_OPEN | FAN_ONDIR , AT_FDCWD, "dir"); fanotify_mark(fd, FAN_MARK_ADD, FAN_CLOSE, AT_FDCWD, "dir"); Also FAN_MARK_ONDIR is only honored when adding events to a mark's mask, but not for event removal. Fix both issues by not setting FAN_ONDIR implicitly on the ignore mask any more. Instead treat FAN_ONDIR as any other event flag and require FAN_MARK_ONDIR to be set by the user for both event mask and ignore mask. Furthermore take FAN_MARK_ONDIR into account when set for event removal. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Lino Sanfilippo Reviewed-by: Jan Kara Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify.c | 2 +- fs/notify/fanotify/fanotify_user.c | 25 +++++++++++++++++-------- 2 files changed, 18 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 30d3addfad75..51ceb8107284 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -140,7 +140,7 @@ static bool fanotify_should_send_event(struct fsnotify_mark *inode_mark, } if (S_ISDIR(path->dentry->d_inode->i_mode) && - (marks_ignored_mask & FS_ISDIR)) + !(marks_mask & FS_ISDIR & ~marks_ignored_mask)) return false; if (event_mask & marks_mask & ~marks_ignored_mask) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index f4d279807a96..cf275500a665 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -491,10 +491,17 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { + __u32 tmask = fsn_mark->mask & ~mask; + + if (flags & FAN_MARK_ONDIR) + tmask &= ~FAN_ONDIR; + oldmask = fsn_mark->mask; - fsnotify_set_mark_mask_locked(fsn_mark, (oldmask & ~mask)); + fsnotify_set_mark_mask_locked(fsn_mark, tmask); } else { __u32 tmask = fsn_mark->ignored_mask & ~mask; + if (flags & FAN_MARK_ONDIR) + tmask &= ~FAN_ONDIR; fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); } @@ -569,20 +576,22 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { + __u32 tmask = fsn_mark->mask | mask; + + if (flags & FAN_MARK_ONDIR) + tmask |= FAN_ONDIR; + oldmask = fsn_mark->mask; - fsnotify_set_mark_mask_locked(fsn_mark, (oldmask | mask)); + fsnotify_set_mark_mask_locked(fsn_mark, tmask); } else { __u32 tmask = fsn_mark->ignored_mask | mask; + if (flags & FAN_MARK_ONDIR) + tmask |= FAN_ONDIR; + fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); if (flags & FAN_MARK_IGNORED_SURV_MODIFY) fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY; } - - if (!(flags & FAN_MARK_ONDIR)) { - __u32 tmask = fsn_mark->ignored_mask | FAN_ONDIR; - fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); - } - spin_unlock(&fsn_mark->lock); return mask & ~oldmask; -- cgit v1.2.3 From b934beaf4b920a95db012b3d4476e8375dd4415b Mon Sep 17 00:00:00 2001 From: Xue jiufei Date: Tue, 10 Feb 2015 14:08:40 -0800 Subject: ocfs2/dlm: add missing dlm_lock_put() when recovery master down When the recovery master is down, the owner of $RECOVERY calls dlm_do_local_recovery_cleanup() to prune any $RECOVERY entries for dead nodes. The lock is in the granted list and the refcount must be 2. We should put twice to remove this lock. Otherwise, it will lead to a memory leak. Signed-off-by: joyce.xue Reported-by: yangwenfang Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmrecovery.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index cecd875653e4..ce12e0b1a31f 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1070,6 +1070,9 @@ static void dlm_move_reco_locks_to_list(struct dlm_ctxt *dlm, dead_node, dlm->name); list_del_init(&lock->list); dlm_lock_put(lock); + /* Can't schedule DLM_UNLOCK_FREE_LOCK + * - do manually */ + dlm_lock_put(lock); break; } } @@ -2346,6 +2349,10 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) dead_node, dlm->name); list_del_init(&lock->list); dlm_lock_put(lock); + /* Can't schedule + * DLM_UNLOCK_FREE_LOCK + * - do manually */ + dlm_lock_put(lock); break; } } -- cgit v1.2.3 From e6e746187dd3fc5f8d9c5dc48a12f65941841467 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Tue, 10 Feb 2015 14:08:43 -0800 Subject: ocfs2: remove unnecessary else in ocfs2_set_acl() else is unnecessary after return. Signed-off-by: Fabian Frederick Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/acl.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 7e8282dcea2a..c58a1bcfda0f 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -245,16 +245,14 @@ int ocfs2_set_acl(handle_t *handle, ret = posix_acl_equiv_mode(acl, &mode); if (ret < 0) return ret; - else { - if (ret == 0) - acl = NULL; - ret = ocfs2_acl_set_mode(inode, di_bh, - handle, mode); - if (ret) - return ret; + if (ret == 0) + acl = NULL; - } + ret = ocfs2_acl_set_mode(inode, di_bh, + handle, mode); + if (ret) + return ret; } break; case ACL_TYPE_DEFAULT: -- cgit v1.2.3 From 696cdf730f40c97ebccacddd40c5382608dc8320 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Tue, 10 Feb 2015 14:08:46 -0800 Subject: ocfs2: fix uninitialized variable access Variable "why" is not yet initialized at line 615, fix it. Signed-off-by: Junxiao Bi Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 3950693dd0f6..245db4f504da 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -569,7 +569,7 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start, handle_t *handle = NULL; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; - enum ocfs2_alloc_restarted why; + enum ocfs2_alloc_restarted why = RESTART_NONE; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_extent_tree et; int did_quota = 0; -- cgit v1.2.3 From 41d6247fdd1a30d4145c9c2590db3928ddc3d323 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Tue, 10 Feb 2015 14:08:48 -0800 Subject: ocfs2: fix wrong comment O2NET_CONN_IDLE_DELAY is not defined, connection attempts will not be canceled due to timeout. Signed-off-by: Junxiao Bi Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/tcp_internal.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h index dc024367110a..b95e7df5b76a 100644 --- a/fs/ocfs2/cluster/tcp_internal.h +++ b/fs/ocfs2/cluster/tcp_internal.h @@ -107,12 +107,12 @@ struct o2net_node { struct list_head nn_status_list; /* connects are attempted from when heartbeat comes up until either hb - * goes down, the node is unconfigured, no connect attempts succeed - * before O2NET_CONN_IDLE_DELAY, or a connect succeeds. connect_work - * is queued from set_nn_state both from hb up and from itself if a - * connect attempt fails and so can be self-arming. shutdown is - * careful to first mark the nn such that no connects will be attempted - * before canceling delayed connect work and flushing the queue. */ + * goes down, the node is unconfigured, or a connect succeeds. + * connect_work is queued from set_nn_state both from hb up and from + * itself if a connect attempt fails and so can be self-arming. + * shutdown is careful to first mark the nn such that no connects will + * be attempted before canceling delayed connect work and flushing the + * queue. */ struct delayed_work nn_connect_work; unsigned long nn_last_connect_attempt; -- cgit v1.2.3 From 79c83ea1aae1536b3e21e59946b97be150033ec7 Mon Sep 17 00:00:00 2001 From: alex chen Date: Tue, 10 Feb 2015 14:08:51 -0800 Subject: ocfs2: fix snprintf format specifier in dlmdebug.c Use snprintf format specifier "%lu" instead of "%ld" for argument of type 'unsigned long'. Signed-off-by: Alex Chen Reviewed-by: Joseph Qi Reviewed-by: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmdebug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index 149eb556b8c6..825136070d2c 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -406,7 +406,7 @@ static int debug_purgelist_print(struct dlm_ctxt *dlm, char *buf, int len) } spin_unlock(&dlm->spinlock); - out += snprintf(buf + out, len - out, "Total on list: %ld\n", total); + out += snprintf(buf + out, len - out, "Total on list: %lu\n", total); return out; } @@ -464,7 +464,7 @@ static int debug_mle_print(struct dlm_ctxt *dlm, char *buf, int len) spin_unlock(&dlm->master_lock); out += snprintf(buf + out, len - out, - "Total: %ld, Longest: %ld\n", total, longest); + "Total: %lu, Longest: %lu\n", total, longest); return out; } -- cgit v1.2.3 From d6edc87af85988ba126db05b4f26ac9ffa6c04fb Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Tue, 10 Feb 2015 14:08:54 -0800 Subject: ocfs2: xattr: remove unused function Remove ocfs2_xattr_bucket_get_val() that is not used anywhere. This was partially found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/xattr.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 662f8dee149f..85b190dc132f 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -5334,16 +5334,6 @@ out: return ret; } -static inline char *ocfs2_xattr_bucket_get_val(struct inode *inode, - struct ocfs2_xattr_bucket *bucket, - int offs) -{ - int block_off = offs >> inode->i_sb->s_blocksize_bits; - - offs = offs % inode->i_sb->s_blocksize; - return bucket_block(bucket, block_off) + offs; -} - /* * Truncate the specified xe_off entry in xattr bucket. * bucket is indicated by header_bh and len is the new length. -- cgit v1.2.3 From 7ea62d70311d92d4c40fa0514940110af055f7a9 Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Tue, 10 Feb 2015 14:08:56 -0800 Subject: ocfs2: quota_local: remove unused function Remove ol_dqblk_file_block() that is not used anywhere. This was partially found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/quota_local.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 10b653930ee2..bb72af344475 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -73,12 +73,6 @@ static loff_t ol_dqblk_off(struct super_block *sb, int c, int off) ol_dqblk_block_off(sb, c, off); } -/* Compute block number from given offset */ -static inline unsigned int ol_dqblk_file_block(struct super_block *sb, loff_t off) -{ - return off >> sb->s_blocksize_bits; -} - static inline unsigned int ol_dqblk_block_offset(struct super_block *sb, loff_t off) { return off & ((1 << sb->s_blocksize_bits) - 1); -- cgit v1.2.3 From 95671c63d5ef3b8794fc9a05d44f0162cc5db425 Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Tue, 10 Feb 2015 14:08:59 -0800 Subject: ocfs2: dlm: dlmdomain: remove unused function Remove dlm_joined() that is not used anywhere. This was partially found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmdomain.c | 14 -------------- fs/ocfs2/dlm/dlmdomain.h | 1 - 2 files changed, 15 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 50a59d2337b2..7df88a6dd626 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -674,20 +674,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm) spin_unlock(&dlm->spinlock); } -int dlm_joined(struct dlm_ctxt *dlm) -{ - int ret = 0; - - spin_lock(&dlm_domain_lock); - - if (dlm->dlm_state == DLM_CTXT_JOINED) - ret = 1; - - spin_unlock(&dlm_domain_lock); - - return ret; -} - int dlm_shutting_down(struct dlm_ctxt *dlm) { int ret = 0; diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h index 2f7f60bfeb3b..fd6122a38dbd 100644 --- a/fs/ocfs2/dlm/dlmdomain.h +++ b/fs/ocfs2/dlm/dlmdomain.h @@ -28,7 +28,6 @@ extern spinlock_t dlm_domain_lock; extern struct list_head dlm_domains; -int dlm_joined(struct dlm_ctxt *dlm); int dlm_shutting_down(struct dlm_ctxt *dlm); void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm, int node_num); -- cgit v1.2.3 From 15eba0fe3eeaeb1b80489c1ebb9d47d6d7003f57 Mon Sep 17 00:00:00 2001 From: alex chen Date: Tue, 10 Feb 2015 14:09:02 -0800 Subject: ocfs2: fix journal commit deadlock in ocfs2_convert_inline_data_to_extents Similar to ocfs2_write_end_nolock() which is metioned at commit 136f49b91710 ("ocfs2: fix journal commit deadlock"), we should unlock pages before ocfs2_commit_trans() in ocfs2_convert_inline_data_to_extents. Otherwise, it will cause a deadlock with journal commit threads. Signed-off-by: Alex Chen Reviewed-by: Joseph Qi Cc: Joel Becker Cc: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/alloc.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index fcae9ef1a328..044158bd22be 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6873,7 +6873,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); - goto out_unlock; + goto out; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, @@ -6931,7 +6931,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, if (ret) { mlog_errno(ret); need_free = 1; - goto out_commit; + goto out_unlock; } page_end = PAGE_CACHE_SIZE; @@ -6964,12 +6964,16 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, if (ret) { mlog_errno(ret); need_free = 1; - goto out_commit; + goto out_unlock; } inode->i_blocks = ocfs2_inode_sector_count(inode); } +out_unlock: + if (pages) + ocfs2_unlock_and_free_pages(pages, num_pages); + out_commit: if (ret < 0 && did_quota) dquot_free_space_nodirty(inode, @@ -6989,15 +6993,11 @@ out_commit: ocfs2_commit_trans(osb, handle); -out_unlock: +out: if (data_ac) ocfs2_free_alloc_context(data_ac); - -out: - if (pages) { - ocfs2_unlock_and_free_pages(pages, num_pages); + if (pages) kfree(pages); - } return ret; } -- cgit v1.2.3 From 1dfeb768475dfded66bba03a1744c2e8141d3429 Mon Sep 17 00:00:00 2001 From: alex chen Date: Tue, 10 Feb 2015 14:09:04 -0800 Subject: ocfs2: add a mount option journal_async_commit on ocfs2 filesystem Add a mount option to support JBD2 feature: JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT. When this feature is opened, journal commit block can be written to disk without waiting for descriptor blocks, which can improve journal commit performance. This option will enable 'journal_checksum' internally. Using the fs_mark benchmark, using journal_async_commit shows a 50% improvement, the files per second go up from 215.2 to 317.5. test script: fs_mark -d /mnt/ocfs2/ -s 10240 -n 1000 default: FSUse% Count Size Files/sec App Overhead 0 1000 10240 215.2 17878 with journal_async_commit option: FSUse% Count Size Files/sec App Overhead 0 1000 10240 317.5 17881 Signed-off-by: Alex Chen Signed-off-by: Weiwei Wang Reviewed-by: Joseph Qi Reviewed-by: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/ocfs2.txt | 4 ++++ fs/ocfs2/ocfs2.h | 2 ++ fs/ocfs2/super.c | 17 +++++++++++++++++ 3 files changed, 23 insertions(+) (limited to 'fs') diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt index 7618a287aa41..28f8c08201e2 100644 --- a/Documentation/filesystems/ocfs2.txt +++ b/Documentation/filesystems/ocfs2.txt @@ -100,3 +100,7 @@ coherency=full (*) Disallow concurrent O_DIRECT writes, cluster inode coherency=buffered Allow concurrent O_DIRECT writes without EX lock among nodes, which gains high performance at risk of getting stale data on other nodes. +journal_async_commit Commit block can be written to disk without waiting + for descriptor blocks. If enabled older kernels cannot + mount the device. This will enable 'journal_checksum' + internally. diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 7d6b7d090452..fdbcbfed529e 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -279,6 +279,8 @@ enum ocfs2_mount_options writes */ OCFS2_MOUNT_HB_NONE = 1 << 13, /* No heartbeat */ OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */ + + OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */ }; #define OCFS2_OSB_SOFT_RO 0x0001 diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 83723179e1ec..c09d6da23c3d 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -191,6 +191,7 @@ enum { Opt_coherency_full, Opt_resv_level, Opt_dir_resv_level, + Opt_journal_async_commit, Opt_err, }; @@ -222,6 +223,7 @@ static const match_table_t tokens = { {Opt_coherency_full, "coherency=full"}, {Opt_resv_level, "resv_level=%u"}, {Opt_dir_resv_level, "dir_resv_level=%u"}, + {Opt_journal_async_commit, "journal_async_commit"}, {Opt_err, NULL} }; @@ -1500,6 +1502,9 @@ static int ocfs2_parse_options(struct super_block *sb, option < OCFS2_MAX_RESV_LEVEL) mopt->dir_resv_level = option; break; + case Opt_journal_async_commit: + mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT; + break; default: mlog(ML_ERROR, "Unrecognized mount option \"%s\" " @@ -1606,6 +1611,9 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root) if (osb->osb_dir_resv_level != osb->osb_resv_level) seq_printf(s, ",dir_resv_level=%d", osb->osb_resv_level); + if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT) + seq_printf(s, ",journal_async_commit"); + return 0; } @@ -2475,6 +2483,15 @@ static int ocfs2_check_volume(struct ocfs2_super *osb) goto finally; } + if (osb->s_mount_opt & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT) + jbd2_journal_set_features(osb->journal->j_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + else + jbd2_journal_clear_features(osb->journal->j_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + if (dirty) { /* recover my local alloc if we didn't unmount cleanly. */ status = ocfs2_begin_local_alloc_recovery(osb, -- cgit v1.2.3 From d9510a20f81467b48cd005e86e17b5288990bc71 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 10 Feb 2015 14:09:07 -0800 Subject: ocfs2: remove pointless assignment from ocfs2_calc_refcount_meta_credits() The assigned value is never used. Coverity-id 1226847. Signed-off-by: Jan Kara Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/refcounttree.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index d81f6e2a97f5..ee541f92dab4 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2428,8 +2428,6 @@ static int ocfs2_calc_refcount_meta_credits(struct super_block *sb, get_bh(prev_bh); } - rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; - trace_ocfs2_calc_refcount_meta_credits_iterate( recs_add, (unsigned long long)cpos, clusters, (unsigned long long)le64_to_cpu(rec.r_cpos), -- cgit v1.2.3 From e6d9f86d6b80dec23fd0e90bab114e642dac483e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 10 Feb 2015 14:09:10 -0800 Subject: ocfs2: o2net: silence uninitialized variable warning Smatch complains that, if o2net_tx_can_proceed() returns false, then "sc" and "ret" are uninialized or maybe we are re-using the data from previous iteration. I do not know if we can hit this bug in real life but checking the return value is harmless and we may as well silence the static checker warning. Signed-off-by: Dan Carpenter Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/tcp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 2e355e0f8335..56c403a563bc 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1016,7 +1016,8 @@ void o2net_fill_node_map(unsigned long *map, unsigned bytes) memset(map, 0, bytes); for (node = 0; node < O2NM_MAX_NODES; ++node) { - o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret); + if (!o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret)) + continue; if (!ret) { set_bit(node, map); sc_put(sc); -- cgit v1.2.3 From 592a202a3d463d683632c268a3948978237a868d Mon Sep 17 00:00:00 2001 From: Daeseok Youn Date: Tue, 10 Feb 2015 14:09:12 -0800 Subject: ocfs2: remove unreachable code Signed-off-by: Daeseok Youn Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dir.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 319e786175af..940be6d994a9 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3513,7 +3513,6 @@ next: de = (struct ocfs2_dir_entry *)((char *) de + le16_to_cpu(de->rec_len)); } - status = 0; bail: brelse(bh); if (status) -- cgit v1.2.3 From 9b57269170820d707b048f305bb59a7b23cc5448 Mon Sep 17 00:00:00 2001 From: Daeseok Youn Date: Tue, 10 Feb 2015 14:09:15 -0800 Subject: ocfs2: removes mlog_errno() call twice in ocfs2_find_dir_space_el() mlog_errno() is called twice when some functions are failed. Signed-off-by: Daeseok Youn Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dir.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 940be6d994a9..b08050bd3f2e 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3456,10 +3456,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, int blocksize = dir->i_sb->s_blocksize; status = ocfs2_read_dir_block(dir, 0, &bh, 0); - if (status) { - mlog_errno(status); + if (status) goto bail; - } rec_len = OCFS2_DIR_REC_LEN(namelen); offset = 0; @@ -3480,10 +3478,9 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, status = ocfs2_read_dir_block(dir, offset >> sb->s_blocksize_bits, &bh, 0); - if (status) { - mlog_errno(status); + if (status) goto bail; - } + /* move to next block */ de = (struct ocfs2_dir_entry *) bh->b_data; } -- cgit v1.2.3 From 9d6008c759b6fbca16a5adefdb3477d87fe4a15b Mon Sep 17 00:00:00 2001 From: Daeseok Youn Date: Tue, 10 Feb 2015 14:09:18 -0800 Subject: ocfs2: remove unreachable code in __ocfs2_recovery_thread() Signed-off-by: Daeseok Youn Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/journal.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 4f502382180f..d10860fde165 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1447,7 +1447,6 @@ bail: * requires that we call do_exit(). And it isn't exported, but * complete_and_exit() seems to be a minimal wrapper around it. */ complete_and_exit(NULL, status); - return status; } void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) -- cgit v1.2.3 From 8989b6733027e6d28d77662113704adb434d0eae Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Tue, 10 Feb 2015 14:09:20 -0800 Subject: ocfs2: make resv_lock spinlock static resv_lock is only used in reservations.c Signed-off-by: Fabian Frederick Cc: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/reservations.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c index 41ffd36c689c..6a348b0294ab 100644 --- a/fs/ocfs2/reservations.c +++ b/fs/ocfs2/reservations.c @@ -39,7 +39,7 @@ #define OCFS2_CHECK_RESERVATIONS #endif -DEFINE_SPINLOCK(resv_lock); +static DEFINE_SPINLOCK(resv_lock); #define OCFS2_MIN_RESV_WINDOW_BITS 8 #define OCFS2_MAX_RESV_WINDOW_BITS 1024 -- cgit v1.2.3 From 10ab88117d069a552a5efdb4b5fb1c087a948c63 Mon Sep 17 00:00:00 2001 From: alex chen Date: Tue, 10 Feb 2015 14:09:23 -0800 Subject: ocfs2: prune the dcache before deleting the dentry of directory In ocfs2_dentry_convert_worker, we should prune the dcache before deleting the dentry of directory, otherwise, in the following cases the inode of directory will still remain in orphan directory until the device being umounted. Mount point: /mnt/ocfs2 Node A Node B mkdir /mnt/ocfs2/testdir ocfs2_mkdir ->ocfs2_mknod ->ocfs2_dentry_attach_lock ->ocfs2_dentry_lock(dentry, 0) ... ... touch /mnt/ocfs2/testdir/testfile unlink /mnt/test/testdir/testfile rmdir /mnt/ocfs2/testdir ocfs2_unlink ->ocfs2_remote_dentry_delete ->ocfs2_dentry_lock(dentry, 1) ... ... ... ... ocfs2_downconvert_thread ->ocfs2_unblock_lock ->ocfs2_dentry_convert_worker ->ocfs2_find_local_alias ->dget_dlock ->d_delete Here the dentry can not be released because the children's dentry is negative but still exist. Finally, this inode will still remain in orphan directory until its children are destroyed. So before deleting dentry of directory, we should prune the dcache to remove unused children of the parent dentry by shrink_dcache_parent(). Signed-off-by: Alex Chen Reviewed-by: Joseph Qi Reviewed-by: joyce.xue Reviewed-by: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlmglue.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs') diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 1c423af04c69..11849a44dc5a 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3750,6 +3750,9 @@ static int ocfs2_dentry_convert_worker(struct ocfs2_lock_res *lockres, break; spin_unlock(&dentry_attach_lock); + if (S_ISDIR(dl->dl_inode->i_mode)) + shrink_dcache_parent(dentry); + mlog(0, "d_delete(%pd);\n", dentry); /* -- cgit v1.2.3 From 99b8874e79619498ade354357f64299768642af6 Mon Sep 17 00:00:00 2001 From: Srinivas Eeda Date: Tue, 10 Feb 2015 14:09:26 -0800 Subject: o2dlm: fix NULL pointer dereference in o2dlm_blocking_ast_wrapper A tiny race between BAST and unlock message causes the NULL dereference. A node sends an unlock request to master and receives a response. Before processing the response it receives a BAST from the master. Since both requests are processed by different threads it creates a race. While the BAST is being processed, lock can get freed by unlock code. This patch makes bast to return immediately if lock is found but unlock is pending. The code should handle this race. We also have to fix master node to skip sending BAST after receiving unlock message. Below is the crash stack BUG: unable to handle kernel NULL pointer dereference at 0000000000000048 IP: o2dlm_blocking_ast_wrapper+0xd/0x16 dlm_do_local_bast+0x8e/0x97 [ocfs2_dlm] dlm_proxy_ast_handler+0x838/0x87e [ocfs2_dlm] o2net_process_message+0x395/0x5b8 [ocfs2_nodemanager] o2net_rx_until_empty+0x762/0x90d [ocfs2_nodemanager] worker_thread+0x14d/0x1ed [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Srinivas Eeda Reviewed-by: Mark Fasheh Cc: Joel Becker Cc: Joseph Qi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmast.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index b46278f9ae44..fd6bbbbd7d78 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -385,8 +385,12 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data, head = &res->granted; list_for_each_entry(lock, head, list) { - if (lock->ml.cookie == cookie) + /* if lock is found but unlock is pending ignore the bast */ + if (lock->ml.cookie == cookie) { + if (lock->unlock_pending) + break; goto do_ast; + } } mlog(0, "Got %sast for unknown lock! cookie=%u:%llu, name=%.*s, " -- cgit v1.2.3 From 913e027ca17ee06fa9436a21e54464795b0fa0e8 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Tue, 10 Feb 2015 14:09:29 -0800 Subject: fsioctl.c: make generic_block_fiemap() signal-tolerant __generic_block_fiemap may spin very long time for large sparse files. Without this patch an unprivileged user may abuse system resources simply by spawning a vast number of unkilable busyloops (works on ext2/ext3): truncate --size 1T test for ((i=0;i<1024;i++)) do filefrag test > /dev/null & done Signed-off-by: Dmitry Monakhov Cc: Theodore Ts'o Cc: Al Viro Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/fiemap.txt | 3 ++- fs/ioctl.c | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt index 1b805a0efbb0..f6d9c99103a4 100644 --- a/Documentation/filesystems/fiemap.txt +++ b/Documentation/filesystems/fiemap.txt @@ -196,7 +196,8 @@ struct fiemap_extent_info { }; It is intended that the file system should not need to access any of this -structure directly. +structure directly. Filesystem handlers should be tolerant to signals and return +EINTR once fatal signal received. Flag checking should be done at the beginning of the ->fiemap callback via the diff --git a/fs/ioctl.c b/fs/ioctl.c index 214c3c11fbc2..5d01d2638ca5 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -379,6 +379,11 @@ int __generic_block_fiemap(struct inode *inode, past_eof = true; } cond_resched(); + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + } while (1); /* If ret is 1 then we just hit the end of the extent array */ -- cgit v1.2.3 From d83a08db5ba6072caa658745881f4baa9bad6a08 Mon Sep 17 00:00:00 2001 From: Kirill A. Shutemov Date: Tue, 10 Feb 2015 14:09:54 -0800 Subject: mm: drop vm_ops->remap_pages and generic_file_remap_pages() stub Nobody uses it anymore. [akpm@linux-foundation.org: fix filemap_xip.c] Signed-off-by: Kirill A. Shutemov Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/vfs_file.c | 2 -- fs/btrfs/file.c | 1 - fs/ceph/addr.c | 1 - fs/cifs/file.c | 1 - fs/ext4/file.c | 1 - fs/f2fs/file.c | 1 - fs/fuse/file.c | 1 - fs/gfs2/file.c | 1 - fs/nfs/file.c | 1 - fs/nilfs2/file.c | 1 - fs/ocfs2/mmap.c | 1 - fs/ubifs/file.c | 1 - fs/xfs/xfs_file.c | 1 - include/linux/fs.h | 6 ------ include/linux/mm.h | 3 --- mm/filemap.c | 1 - mm/filemap_xip.c | 1 - mm/shmem.c | 1 - 18 files changed, 26 deletions(-) (limited to 'fs') diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 5594505e6e73..b40133796b87 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -831,7 +831,6 @@ static const struct vm_operations_struct v9fs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = v9fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { @@ -839,7 +838,6 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = v9fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e4090259569b..a606ab551296 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2081,7 +2081,6 @@ static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = btrfs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c81c0e004588..24be059fd1f8 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1569,7 +1569,6 @@ out: static struct vm_operations_struct ceph_vmops = { .fault = ceph_filemap_fault, .page_mkwrite = ceph_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int ceph_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 74f12877493a..294ff302a237 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3248,7 +3248,6 @@ static struct vm_operations_struct cifs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = cifs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 8131be8c0af3..7cb592386121 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -195,7 +195,6 @@ static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 3c27e0ecb3bc..5674ba13102b 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -92,7 +92,6 @@ static const struct vm_operations_struct f2fs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = f2fs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int get_parent_ino(struct inode *inode, nid_t *pino) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 760b2c552197..d769e594855b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2062,7 +2062,6 @@ static const struct vm_operations_struct fuse_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = fuse_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 6e600abf694a..ec9c2d33477a 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -498,7 +498,6 @@ static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = gfs2_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; /** diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 2ab6f00dba5b..94712fc781fa 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -646,7 +646,6 @@ static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = nfs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int nfs_need_sync_write(struct file *filp, struct inode *inode) diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 3a03e0aea1fb..a8c728acb7a8 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -128,7 +128,6 @@ static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = nilfs_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 10d66c75cecb..9581d190f6e1 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -173,7 +173,6 @@ out: static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 538519ee37d9..035e51011444 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1536,7 +1536,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = ubifs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 13e974e6a889..ac7f1e8f92b3 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1384,5 +1384,4 @@ static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = xfs_vm_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 60c4996df7f3..47f557c7ef7e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2481,12 +2481,6 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -static inline int generic_file_remap_pages(struct vm_area_struct *vma, - unsigned long addr, unsigned long size, pgoff_t pgoff) -{ - BUG(); - return 0; -} int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/include/linux/mm.h b/include/linux/mm.h index 376e5c325dee..2ddd9d1d6268 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -285,9 +285,6 @@ struct vm_operations_struct { struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); #endif - /* called by sys_remap_file_pages() to populate non-linear mapping */ - int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff); }; struct mmu_gather; diff --git a/mm/filemap.c b/mm/filemap.c index 673e4581a2e5..bf7a27142704 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2087,7 +2087,6 @@ const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; /* This is used for a general mmap of a disk file */ diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 0d105aeff82f..70c09da1a419 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -301,7 +301,6 @@ out: static const struct vm_operations_struct xip_file_vm_ops = { .fault = xip_file_fault, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int xip_file_mmap(struct file * file, struct vm_area_struct * vma) diff --git a/mm/shmem.c b/mm/shmem.c index 993e6ba689cc..b3e403181981 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3201,7 +3201,6 @@ static const struct vm_operations_struct shmem_vm_ops = { .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif - .remap_pages = generic_file_remap_pages, }; static struct dentry *shmem_mount(struct file_system_type *fs_type, -- cgit v1.2.3 From 1da4b35b001481df99a6dcab12d5d39a876f7056 Mon Sep 17 00:00:00 2001 From: Kirill A. Shutemov Date: Tue, 10 Feb 2015 14:09:57 -0800 Subject: proc: drop handling non-linear mappings We have to handle non-linear mappings for /proc/PID/{smaps,clear_refs} which is unused now. Let's drop it. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 246eae84b13b..6396f88c6687 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -443,7 +443,6 @@ struct mem_size_stats { unsigned long anonymous; unsigned long anonymous_thp; unsigned long swap; - unsigned long nonlinear; u64 pss; }; @@ -484,7 +483,6 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = mss->vma; - pgoff_t pgoff = linear_page_index(vma, addr); struct page *page = NULL; if (pte_present(*pte)) { @@ -496,17 +494,10 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, mss->swap += PAGE_SIZE; else if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); - } else if (pte_file(*pte)) { - if (pte_to_pgoff(*pte) != pgoff) - mss->nonlinear += PAGE_SIZE; } if (!page) return; - - if (page->index != pgoff) - mss->nonlinear += PAGE_SIZE; - smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte)); } @@ -596,7 +587,6 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_ACCOUNT)] = "ac", [ilog2(VM_NORESERVE)] = "nr", [ilog2(VM_HUGETLB)] = "ht", - [ilog2(VM_NONLINEAR)] = "nl", [ilog2(VM_ARCH_1)] = "ar", [ilog2(VM_DONTDUMP)] = "dd", #ifdef CONFIG_MEM_SOFT_DIRTY @@ -668,10 +658,6 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) (vma->vm_flags & VM_LOCKED) ? (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0); - if (vma->vm_flags & VM_NONLINEAR) - seq_printf(m, "Nonlinear: %8lu kB\n", - mss.nonlinear >> 10); - show_smap_vma_flags(m, vma); m_cache_vma(m, vma); return 0; @@ -772,8 +758,6 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY); } else if (is_swap_pte(ptent)) { ptent = pte_swp_clear_soft_dirty(ptent); - } else if (pte_file(ptent)) { - ptent = pte_file_clear_soft_dirty(ptent); } set_pte_at(vma->vm_mm, addr, pte, ptent); -- cgit v1.2.3 From 27ba0644ea9dfe6e7693abc85837b60e40583b96 Mon Sep 17 00:00:00 2001 From: Kirill A. Shutemov Date: Tue, 10 Feb 2015 14:09:59 -0800 Subject: rmap: drop support of non-linear mappings We don't create non-linear mappings anymore. Let's drop code which handles them in rmap. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cachetlb.txt | 8 +- fs/inode.c | 1 - include/linux/fs.h | 4 +- include/linux/mm.h | 6 -- include/linux/mm_types.h | 4 +- include/linux/rmap.h | 2 - kernel/fork.c | 8 +- mm/migrate.c | 32 ------- mm/mmap.c | 24 ++--- mm/rmap.c | 225 +-------------------------------------------- mm/swap.c | 4 +- 11 files changed, 18 insertions(+), 300 deletions(-) (limited to 'fs') diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt index d79b008e4a32..3f9f808b5119 100644 --- a/Documentation/cachetlb.txt +++ b/Documentation/cachetlb.txt @@ -317,10 +317,10 @@ maps this page at its virtual address. about doing this. The idea is, first at flush_dcache_page() time, if - page->mapping->i_mmap is an empty tree and ->i_mmap_nonlinear - an empty list, just mark the architecture private page flag bit. - Later, in update_mmu_cache(), a check is made of this flag bit, - and if set the flush is done and the flag bit is cleared. + page->mapping->i_mmap is an empty tree, just mark the architecture + private page flag bit. Later, in update_mmu_cache(), a check is + made of this flag bit, and if set the flush is done and the flag + bit is cleared. IMPORTANT NOTE: It is often important, if you defer the flush, that the actual flush occurs on the same CPU diff --git a/fs/inode.c b/fs/inode.c index aa149e7262ac..c760fac33c92 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -355,7 +355,6 @@ void address_space_init_once(struct address_space *mapping) INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); mapping->i_mmap = RB_ROOT; - INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); } EXPORT_SYMBOL(address_space_init_once); diff --git a/include/linux/fs.h b/include/linux/fs.h index 47f557c7ef7e..60acab209701 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -401,7 +401,6 @@ struct address_space { spinlock_t tree_lock; /* and lock protecting it */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ struct rb_root i_mmap; /* tree of private and shared mappings */ - struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ @@ -493,8 +492,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) */ static inline int mapping_mapped(struct address_space *mapping) { - return !RB_EMPTY_ROOT(&mapping->i_mmap) || - !list_empty(&mapping->i_mmap_nonlinear); + return !RB_EMPTY_ROOT(&mapping->i_mmap); } /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ddd9d1d6268..18391eec4864 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1796,12 +1796,6 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) -static inline void vma_nonlinear_insert(struct vm_area_struct *vma, - struct list_head *list) -{ - list_add_tail(&vma->shared.nonlinear, list); -} - void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6d34aa266a8c..3b1d20fb0848 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -273,15 +273,13 @@ struct vm_area_struct { /* * For areas with an address space and backing store, - * linkage into the address_space->i_mmap interval tree, or - * linkage of vma in the address_space->i_mmap_nonlinear list. + * linkage into the address_space->i_mmap interval tree. */ union { struct { struct rb_node rb; unsigned long rb_subtree_last; } linear; - struct list_head nonlinear; } shared; /* diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d9d7e7e56352..b38f559130d5 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -246,7 +246,6 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); * arg: passed to rmap_one() and invalid_vma() * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition - * file_nonlinear: for handling file nonlinear mapping * anon_lock: for getting anon_lock by optimized way rather than default * invalid_vma: for skipping uninterested vma */ @@ -255,7 +254,6 @@ struct rmap_walk_control { int (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct page *page); - int (*file_nonlinear)(struct page *, struct address_space *, void *arg); struct anon_vma *(*anon_lock)(struct page *page); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; diff --git a/kernel/fork.c b/kernel/fork.c index 4dc2ddade9f1..b379d9abddc7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -438,12 +438,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ - if (unlikely(tmp->vm_flags & VM_NONLINEAR)) - vma_nonlinear_insert(tmp, - &mapping->i_mmap_nonlinear); - else - vma_interval_tree_insert_after(tmp, mpnt, - &mapping->i_mmap); + vma_interval_tree_insert_after(tmp, mpnt, + &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } diff --git a/mm/migrate.c b/mm/migrate.c index 344cdf692fc8..6e284bcca8bb 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -178,37 +178,6 @@ out: return SWAP_AGAIN; } -/* - * Congratulations to trinity for discovering this bug. - * mm/fremap.c's remap_file_pages() accepts any range within a single vma to - * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then - * replace the specified range by file ptes throughout (maybe populated after). - * If page migration finds a page within that range, while it's still located - * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem: - * zap_pte() clears the temporary migration entry before mmap_sem is dropped. - * But if the migrating page is in a part of the vma outside the range to be - * remapped, then it will not be cleared, and remove_migration_ptes() needs to - * deal with it. Fortunately, this part of the vma is of course still linear, - * so we just need to use linear location on the nonlinear list. - */ -static int remove_linear_migration_ptes_from_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - /* hugetlbfs does not support remap_pages, so no huge pgoff worries */ - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - unsigned long addr; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - if (addr >= vma->vm_start && addr < vma->vm_end) - remove_migration_pte(page, vma, addr, arg); - } - return SWAP_AGAIN; -} - /* * Get rid of all migration entries and replace them by * references to the indicated page. @@ -218,7 +187,6 @@ static void remove_migration_ptes(struct page *old, struct page *new) struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = old, - .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, }; rmap_walk(new, &rwc); diff --git a/mm/mmap.c b/mm/mmap.c index e023dc5e59a8..14d84666e8ba 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -243,10 +243,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - list_del_init(&vma->shared.nonlinear); - else - vma_interval_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } @@ -649,10 +646,7 @@ static void __vma_link_file(struct vm_area_struct *vma) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - else - vma_interval_tree_insert(vma, &mapping->i_mmap); + vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } @@ -789,14 +783,11 @@ again: remove_next = 1 + (end > next->vm_end); if (file) { mapping = file->f_mapping; - if (!(vma->vm_flags & VM_NONLINEAR)) { - root = &mapping->i_mmap; - uprobe_munmap(vma, vma->vm_start, vma->vm_end); + root = &mapping->i_mmap; + uprobe_munmap(vma, vma->vm_start, vma->vm_end); - if (adjust_next) - uprobe_munmap(next, next->vm_start, - next->vm_end); - } + if (adjust_next) + uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert) { @@ -3177,8 +3168,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * * mmap_sem in write mode is required in order to block all operations * that could modify pagetables and free pages without need of - * altering the vma layout (for example populate_range() with - * nonlinear vmas). It's also needed in write mode to avoid new + * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row diff --git a/mm/rmap.c b/mm/rmap.c index 71cd5bd0c17d..70b32498d4f2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -590,9 +590,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { - if (!vma->vm_file || - vma->vm_file->f_mapping != page->mapping) + } else if (page->mapping) { + if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; @@ -1274,7 +1273,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); set_pte_at(mm, address, pte, swp_pte); - BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ @@ -1316,211 +1314,6 @@ out_mlock: return ret; } -/* - * objrmap doesn't work for nonlinear VMAs because the assumption that - * offset-into-file correlates with offset-into-virtual-addresses does not hold. - * Consequently, given a particular page and its ->index, we cannot locate the - * ptes which are mapping that page without an exhaustive linear search. - * - * So what this code does is a mini "virtual scan" of each nonlinear VMA which - * maps the file to which the target page belongs. The ->vm_private_data field - * holds the current cursor into that scan. Successive searches will circulate - * around the vma's virtual address space. - * - * So as more replacement pressure is applied to the pages in a nonlinear VMA, - * more scanning pressure is placed against them as well. Eventually pages - * will become fully unmapped and are eligible for eviction. - * - * For very sparsely populated VMAs this is a little inefficient - chances are - * there there won't be many ptes located within the scan cluster. In this case - * maybe we could scan further - to the end of the pte page, perhaps. - * - * Mlocked pages: check VM_LOCKED under mmap_sem held for read, if we can - * acquire it without blocking. If vma locked, mlock the pages in the cluster, - * rather than unmapping them. If we encounter the "check_page" that vmscan is - * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN. - */ -#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE) -#define CLUSTER_MASK (~(CLUSTER_SIZE - 1)) - -static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, - struct vm_area_struct *vma, struct page *check_page) -{ - struct mm_struct *mm = vma->vm_mm; - pmd_t *pmd; - pte_t *pte; - pte_t pteval; - spinlock_t *ptl; - struct page *page; - unsigned long address; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - unsigned long end; - int ret = SWAP_AGAIN; - int locked_vma = 0; - - address = (vma->vm_start + cursor) & CLUSTER_MASK; - end = address + CLUSTER_SIZE; - if (address < vma->vm_start) - address = vma->vm_start; - if (end > vma->vm_end) - end = vma->vm_end; - - pmd = mm_find_pmd(mm, address); - if (!pmd) - return ret; - - mmun_start = address; - mmun_end = end; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - - /* - * If we can acquire the mmap_sem for read, and vma is VM_LOCKED, - * keep the sem while scanning the cluster for mlocking pages. - */ - if (down_read_trylock(&vma->vm_mm->mmap_sem)) { - locked_vma = (vma->vm_flags & VM_LOCKED); - if (!locked_vma) - up_read(&vma->vm_mm->mmap_sem); /* don't need it */ - } - - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); - - for (; address < end; pte++, address += PAGE_SIZE) { - if (!pte_present(*pte)) - continue; - page = vm_normal_page(vma, address, *pte); - BUG_ON(!page || PageAnon(page)); - - if (locked_vma) { - if (page == check_page) { - /* we know we have check_page locked */ - mlock_vma_page(page); - ret = SWAP_MLOCK; - } else if (trylock_page(page)) { - /* - * If we can lock the page, perform mlock. - * Otherwise leave the page alone, it will be - * eventually encountered again later. - */ - mlock_vma_page(page); - unlock_page(page); - } - continue; /* don't unmap */ - } - - /* - * No need for _notify because we're within an - * mmu_notifier_invalidate_range_ {start|end} scope. - */ - if (ptep_clear_flush_young(vma, address, pte)) - continue; - - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush_notify(vma, address, pte); - - /* If nonlinear, store the file page offset in the pte. */ - if (page->index != linear_page_index(vma, address)) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(pteval)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, address, pte, ptfile); - } - - /* Move the dirty bit to the physical page now the pte is gone. */ - if (pte_dirty(pteval)) - set_page_dirty(page); - - page_remove_rmap(page); - page_cache_release(page); - dec_mm_counter(mm, MM_FILEPAGES); - (*mapcount)--; - } - pte_unmap_unlock(pte - 1, ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - if (locked_vma) - up_read(&vma->vm_mm->mmap_sem); - return ret; -} - -static int try_to_unmap_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - int ret = SWAP_AGAIN; - unsigned long cursor; - unsigned long max_nl_cursor = 0; - unsigned long max_nl_size = 0; - unsigned int mapcount; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - if (cursor > max_nl_cursor) - max_nl_cursor = cursor; - cursor = vma->vm_end - vma->vm_start; - if (cursor > max_nl_size) - max_nl_size = cursor; - } - - if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - return SWAP_FAIL; - } - - /* - * We don't try to search for this page in the nonlinear vmas, - * and page_referenced wouldn't have found it anyway. Instead - * just walk the nonlinear vmas trying to age and unmap some. - * The mapcount of the page we came in with is irrelevant, - * but even so use it as a guide to how hard we should try? - */ - mapcount = page_mapcount(page); - if (!mapcount) - return ret; - - cond_resched(); - - max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; - if (max_nl_cursor == 0) - max_nl_cursor = CLUSTER_SIZE; - - do { - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - while (cursor < max_nl_cursor && - cursor < vma->vm_end - vma->vm_start) { - if (try_to_unmap_cluster(cursor, &mapcount, - vma, page) == SWAP_MLOCK) - ret = SWAP_MLOCK; - cursor += CLUSTER_SIZE; - vma->vm_private_data = (void *) cursor; - if ((int)mapcount <= 0) - return ret; - } - vma->vm_private_data = (void *) max_nl_cursor; - } - cond_resched(); - max_nl_cursor += CLUSTER_SIZE; - } while (max_nl_cursor <= max_nl_size); - - /* - * Don't loop forever (perhaps all the remaining pages are - * in locked vmas). Reset cursor on all unreserved nonlinear - * vmas, now forgetting on which ones it had fallen behind. - */ - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) - vma->vm_private_data = NULL; - - return ret; -} - bool is_vma_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -1566,7 +1359,6 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, - .file_nonlinear = try_to_unmap_nonlinear, .anon_lock = page_lock_anon_vma_read, }; @@ -1612,12 +1404,6 @@ int try_to_munlock(struct page *page) .rmap_one = try_to_unmap_one, .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, - /* - * We don't bother to try to find the munlocked page in - * nonlinears. It's costly. Instead, later, page reclaim logic - * may call try_to_unmap() and recover PG_mlocked lazily. - */ - .file_nonlinear = NULL, .anon_lock = page_lock_anon_vma_read, }; @@ -1748,13 +1534,6 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) goto done; } - if (!rwc->file_nonlinear) - goto done; - - if (list_empty(&mapping->i_mmap_nonlinear)) - goto done; - - ret = rwc->file_nonlinear(page, mapping, rwc->arg); done: i_mmap_unlock_read(mapping); return ret; diff --git a/mm/swap.c b/mm/swap.c index 8a12b33936b4..5b3087228b99 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1140,10 +1140,8 @@ void __init swap_setup(void) if (bdi_init(swapper_spaces[0].backing_dev_info)) panic("Failed to init swap bdi"); - for (i = 0; i < MAX_SWAPFILES; i++) { + for (i = 0; i < MAX_SWAPFILES; i++) spin_lock_init(&swapper_spaces[i].tree_lock); - INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); - } #endif /* Use a smaller cluster for small-memory machines */ -- cgit v1.2.3 From 56873f43abdcd574b25105867a990f067747b2f4 Mon Sep 17 00:00:00 2001 From: Wang, Yalin Date: Wed, 11 Feb 2015 15:24:51 -0800 Subject: mm:add KPF_ZERO_PAGE flag for /proc/kpageflags Add KPF_ZERO_PAGE flag for zero_page, so that userspace processes can detect zero_page in /proc/kpageflags, and then do memory analysis more accurately. Signed-off-by: Yalin Wang Acked-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/pagemap.txt | 8 ++++++++ fs/proc/page.c | 16 +++++++++++++--- include/linux/huge_mm.h | 12 ++++++++++++ include/uapi/linux/kernel-page-flags.h | 1 + mm/huge_memory.c | 7 +------ tools/vm/page-types.c | 1 + 6 files changed, 36 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt index 5948e455c4d2..6fbd55ef6b45 100644 --- a/Documentation/vm/pagemap.txt +++ b/Documentation/vm/pagemap.txt @@ -62,6 +62,8 @@ There are three components to pagemap: 20. NOPAGE 21. KSM 22. THP + 23. BALLOON + 24. ZERO_PAGE Short descriptions to the page flags: @@ -102,6 +104,12 @@ Short descriptions to the page flags: 22. THP contiguous pages which construct transparent hugepages +23. BALLOON + balloon compaction page + +24. ZERO_PAGE + zero page for pfn_zero or huge_zero page + [IO related page flags] 1. ERROR IO error occurred 3. UPTODATE page has up-to-date data diff --git a/fs/proc/page.c b/fs/proc/page.c index 1e3187da1fed..7eee2d8b97d9 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -121,9 +122,18 @@ u64 stable_page_flags(struct page *page) * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || - PageAnon(compound_head(page)))) - u |= 1 << KPF_THP; + else if (PageTransCompound(page)) { + struct page *head = compound_head(page); + + if (PageLRU(head) || PageAnon(head)) + u |= 1 << KPF_THP; + else if (is_huge_zero_page(head)) { + u |= 1 << KPF_ZERO_PAGE; + u |= 1 << KPF_THP; + } + } else if (is_zero_pfn(page_to_pfn(page))) + u |= 1 << KPF_ZERO_PAGE; + /* * Caveats on high order pages: page->_count will only be set diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ad9051bab267..f10b20f05159 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -157,6 +157,13 @@ static inline int hpage_nr_pages(struct page *page) extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp); +extern struct page *huge_zero_page; + +static inline bool is_huge_zero_page(struct page *page) +{ + return ACCESS_ONCE(huge_zero_page) == page; +} + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) @@ -206,6 +213,11 @@ static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_str return 0; } +static inline bool is_huge_zero_page(struct page *page) +{ + return false; +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h index 2f96d233c980..a6c4962e5d46 100644 --- a/include/uapi/linux/kernel-page-flags.h +++ b/include/uapi/linux/kernel-page-flags.h @@ -32,6 +32,7 @@ #define KPF_KSM 21 #define KPF_THP 22 #define KPF_BALLOON 23 +#define KPF_ZERO_PAGE 24 #endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 817a875f2b8c..889713180980 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -171,12 +171,7 @@ static int start_khugepaged(void) } static atomic_t huge_zero_refcount; -static struct page *huge_zero_page __read_mostly; - -static inline bool is_huge_zero_page(struct page *page) -{ - return ACCESS_ONCE(huge_zero_page) == page; -} +struct page *huge_zero_page __read_mostly; static inline bool is_huge_zero_pmd(pmd_t pmd) { diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 264fbc297e0b..8bdf16b8ba60 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -133,6 +133,7 @@ static const char * const page_flag_names[] = { [KPF_KSM] = "x:ksm", [KPF_THP] = "t:thp", [KPF_BALLOON] = "o:balloon", + [KPF_ZERO_PAGE] = "z:zero_page", [KPF_RESERVED] = "r:reserved", [KPF_MLOCKED] = "m:mlocked", -- cgit v1.2.3 From dc6c9a35b66b520cf67e05d8ca60ebecad3b0479 Mon Sep 17 00:00:00 2001 From: Kirill A. Shutemov Date: Wed, 11 Feb 2015 15:26:50 -0800 Subject: mm: account pmd page tables to the process Dave noticed that unprivileged process can allocate significant amount of memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and memory cgroup. The trick is to allocate a lot of PMD page tables. Linux kernel doesn't account PMD tables to the process, only PTE. The use-cases below use few tricks to allocate a lot of PMD page tables while keeping VmRSS and VmPTE low. oom_score for the process will be 0. #include #include #include #include #include #include #define PUD_SIZE (1UL << 30) #define PMD_SIZE (1UL << 21) #define NR_PUD 130000 int main(void) { char *addr = NULL; unsigned long i; prctl(PR_SET_THP_DISABLE); for (i = 0; i < NR_PUD ; i++) { addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); break; } *addr = 'x'; munmap(addr, PMD_SIZE); mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0); if (addr == MAP_FAILED) perror("re-mmap"), exit(1); } printf("PID %d consumed %lu KiB in PMD page tables\n", getpid(), i * 4096 >> 10); return pause(); } The patch addresses the issue by account PMD tables to the process the same way we account PTE. The main place where PMD tables is accounted is __pmd_alloc() and free_pmd_range(). But there're few corner cases: - HugeTLB can share PMD page tables. The patch handles by accounting the table to all processes who share it. - x86 PAE pre-allocates few PMD tables on fork. - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity check on exit(2). Accounting only happens on configuration where PMD page table's level is present (PMD is not folded). As with nr_ptes we use per-mm counter. The counter value is used to calculate baseline for badness score by oom-killer. Signed-off-by: Kirill A. Shutemov Reported-by: Dave Hansen Cc: Hugh Dickins Reviewed-by: Cyrill Gorcunov Cc: Pavel Emelyanov Cc: David Rientjes Tested-by: Sedat Dilek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 12 ++++++------ arch/x86/mm/pgtable.c | 14 +++++++++----- fs/proc/task_mmu.c | 9 ++++++--- include/linux/mm.h | 24 ++++++++++++++++++++++++ include/linux/mm_types.h | 3 ++- kernel/fork.c | 3 +++ mm/debug.c | 3 ++- mm/hugetlb.c | 8 ++++++-- mm/memory.c | 15 +++++++++------ mm/mmap.c | 4 +++- mm/oom_kill.c | 9 +++++---- 11 files changed, 75 insertions(+), 29 deletions(-) (limited to 'fs') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 4415aa915681..e9c706e4627a 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -555,12 +555,12 @@ this is causing problems for your system/application. oom_dump_tasks -Enables a system-wide task dump (excluding kernel threads) to be -produced when the kernel performs an OOM-killing and includes such -information as pid, uid, tgid, vm size, rss, nr_ptes, swapents, -oom_score_adj score, and name. This is helpful to determine why the -OOM killer was invoked, to identify the rogue task that caused it, -and to determine why the OOM killer chose the task it did to kill. +Enables a system-wide task dump (excluding kernel threads) to be produced +when the kernel performs an OOM-killing and includes such information as +pid, uid, tgid, vm size, rss, nr_ptes, nr_pmds, swapents, oom_score_adj +score, and name. This is helpful to determine why the OOM killer was +invoked, to identify the rogue task that caused it, and to determine why +the OOM killer chose the task it did to kill. If this is set to zero, this information is suppressed. On very large systems with thousands of tasks it may not be feasible to dump diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 6fb6927f9e76..7b22adaad4f1 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -190,7 +190,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) #endif /* CONFIG_X86_PAE */ -static void free_pmds(pmd_t *pmds[]) +static void free_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; @@ -198,10 +198,11 @@ static void free_pmds(pmd_t *pmds[]) if (pmds[i]) { pgtable_pmd_page_dtor(virt_to_page(pmds[i])); free_page((unsigned long)pmds[i]); + mm_dec_nr_pmds(mm); } } -static int preallocate_pmds(pmd_t *pmds[]) +static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; bool failed = false; @@ -215,11 +216,13 @@ static int preallocate_pmds(pmd_t *pmds[]) pmd = NULL; failed = true; } + if (pmd) + mm_inc_nr_pmds(mm); pmds[i] = pmd; } if (failed) { - free_pmds(pmds); + free_pmds(mm, pmds); return -ENOMEM; } @@ -246,6 +249,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); + mm_dec_nr_pmds(mm); } } } @@ -283,7 +287,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) mm->pgd = pgd; - if (preallocate_pmds(pmds) != 0) + if (preallocate_pmds(mm, pmds) != 0) goto out_free_pgd; if (paravirt_pgd_alloc(mm) != 0) @@ -304,7 +308,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) return pgd; out_free_pmds: - free_pmds(pmds); + free_pmds(mm, pmds); out_free_pgd: free_page((unsigned long)pgd); out: diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6396f88c6687..e6e0abeb5d12 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -21,7 +21,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) { - unsigned long data, text, lib, swap; + unsigned long data, text, lib, swap, ptes, pmds; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; /* @@ -42,6 +42,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10; lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text; swap = get_mm_counter(mm, MM_SWAPENTS); + ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes); + pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm); seq_printf(m, "VmPeak:\t%8lu kB\n" "VmSize:\t%8lu kB\n" @@ -54,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "VmExe:\t%8lu kB\n" "VmLib:\t%8lu kB\n" "VmPTE:\t%8lu kB\n" + "VmPMD:\t%8lu kB\n" "VmSwap:\t%8lu kB\n", hiwater_vm << (PAGE_SHIFT-10), total_vm << (PAGE_SHIFT-10), @@ -63,8 +66,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) total_rss << (PAGE_SHIFT-10), data << (PAGE_SHIFT-10), mm->stack_vm << (PAGE_SHIFT-10), text, lib, - (PTRS_PER_PTE * sizeof(pte_t) * - atomic_long_read(&mm->nr_ptes)) >> 10, + ptes >> 10, + pmds >> 10, swap << (PAGE_SHIFT-10)); } diff --git a/include/linux/mm.h b/include/linux/mm.h index c6bf813a6b3d..644990b83cda 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1438,8 +1438,32 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, { return 0; } + +static inline unsigned long mm_nr_pmds(struct mm_struct *mm) +{ + return 0; +} + +static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} +static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} + #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); + +static inline unsigned long mm_nr_pmds(struct mm_struct *mm) +{ + return atomic_long_read(&mm->nr_pmds); +} + +static inline void mm_inc_nr_pmds(struct mm_struct *mm) +{ + atomic_long_inc(&mm->nr_pmds); +} + +static inline void mm_dec_nr_pmds(struct mm_struct *mm) +{ + atomic_long_dec(&mm->nr_pmds); +} #endif int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 20ff2105b564..199a03aab8dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -363,7 +363,8 @@ struct mm_struct { pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ - atomic_long_t nr_ptes; /* Page table pages */ + atomic_long_t nr_ptes; /* PTE page table pages */ + atomic_long_t nr_pmds; /* PMD page table pages */ int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some counters */ diff --git a/kernel/fork.c b/kernel/fork.c index b379d9abddc7..c99098c52641 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -555,6 +555,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) INIT_LIST_HEAD(&mm->mmlist); mm->core_state = NULL; atomic_long_set(&mm->nr_ptes, 0); +#ifndef __PAGETABLE_PMD_FOLDED + atomic_long_set(&mm->nr_pmds, 0); +#endif mm->map_count = 0; mm->locked_vm = 0; mm->pinned_vm = 0; diff --git a/mm/debug.c b/mm/debug.c index d69cb5a7ba9a..3eb3ac2fcee7 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -173,7 +173,7 @@ void dump_mm(const struct mm_struct *mm) "get_unmapped_area %p\n" #endif "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" - "pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n" + "pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" "pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n" "start_code %lx end_code %lx start_data %lx end_data %lx\n" @@ -206,6 +206,7 @@ void dump_mm(const struct mm_struct *mm) mm->pgd, atomic_read(&mm->mm_users), atomic_read(&mm->mm_count), atomic_long_read((atomic_long_t *)&mm->nr_ptes), + mm_nr_pmds((struct mm_struct *)mm), mm->map_count, mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fd28d6ba5e5d..0a9ac6c26832 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3598,6 +3598,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (saddr) { spte = huge_pte_offset(svma->vm_mm, saddr); if (spte) { + mm_inc_nr_pmds(mm); get_page(virt_to_page(spte)); break; } @@ -3609,11 +3610,13 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte); spin_lock(ptl); - if (pud_none(*pud)) + if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); - else + } else { put_page(virt_to_page(spte)); + mm_inc_nr_pmds(mm); + } spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); @@ -3644,6 +3647,7 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) pud_clear(pud); put_page(virt_to_page(ptep)); + mm_dec_nr_pmds(mm); *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; return 1; } diff --git a/mm/memory.c b/mm/memory.c index d63849b5188f..bbe6a73a899d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -428,6 +428,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); + mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, @@ -3322,15 +3323,17 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) spin_lock(&mm->page_table_lock); #ifndef __ARCH_HAS_4LEVEL_HACK - if (pud_present(*pud)) /* Another has populated it */ - pmd_free(mm, new); - else + if (!pud_present(*pud)) { + mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); -#else - if (pgd_present(*pud)) /* Another has populated it */ + } else /* Another has populated it */ pmd_free(mm, new); - else +#else + if (!pgd_present(*pud)) { + mm_inc_nr_pmds(mm); pgd_populate(mm, pud, new); + } else /* Another has populated it */ + pmd_free(mm, new); #endif /* __ARCH_HAS_4LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; diff --git a/mm/mmap.c b/mm/mmap.c index 14d84666e8ba..6a7d36d133fb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2853,7 +2853,9 @@ void exit_mmap(struct mm_struct *mm) vm_unacct_memory(nr_accounted); WARN_ON(atomic_long_read(&mm->nr_ptes) > - (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); + round_up(FIRST_USER_ADDRESS, PMD_SIZE) >> PMD_SHIFT); + WARN_ON(mm_nr_pmds(mm) > + round_up(FIRST_USER_ADDRESS, PUD_SIZE) >> PUD_SHIFT); } /* Insert vm structure into process list sorted by address diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b8df76ee2be3..642f38cb175a 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -169,8 +169,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) + - get_mm_counter(p->mm, MM_SWAPENTS); + points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + + atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm); task_unlock(p); /* @@ -351,7 +351,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) struct task_struct *p; struct task_struct *task; - pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); + pr_info("[ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name\n"); rcu_read_lock(); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) @@ -367,10 +367,11 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu %5hd %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), atomic_long_read(&task->mm->nr_ptes), + mm_nr_pmds(task->mm), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); -- cgit v1.2.3 From 8d38633c3b4093aca7524945f1e9249d7d3a44da Mon Sep 17 00:00:00 2001 From: Konstantin Khebnikov Date: Wed, 11 Feb 2015 15:26:55 -0800 Subject: page_writeback: put account_page_redirty() after set_page_dirty() Helper account_page_redirty() fixes dirty pages counter for redirtied pages. This patch puts it after dirtying and prevents temporary underflows of dirtied pages counters on zone/bdi and current->nr_dirtied. Signed-off-by: Konstantin Khebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/extent_io.c | 2 +- mm/page-writeback.c | 5 ++++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 790dbae3343c..c73df6a7c9b6 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1407,8 +1407,8 @@ int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end) while (index <= end_index) { page = find_get_page(inode->i_mapping, index); BUG_ON(!page); /* Pages should be in the extent_io_tree */ - account_page_redirty(page); __set_page_dirty_nobuffers(page); + account_page_redirty(page); page_cache_release(page); index++; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index fb71e9deca85..6a73e47e81c6 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2168,9 +2168,12 @@ EXPORT_SYMBOL(account_page_redirty); */ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) { + int ret; + wbc->pages_skipped++; + ret = __set_page_dirty_nobuffers(page); account_page_redirty(page); - return __set_page_dirty_nobuffers(page); + return ret; } EXPORT_SYMBOL(redirty_page_for_writepage); -- cgit v1.2.3 From 05fbf357d94152171bc50f8a369390f1f16efd89 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 11 Feb 2015 15:27:31 -0800 Subject: proc/pagemap: walk page tables under pte lock Lockless access to pte in pagemap_pte_range() might race with page migration and trigger BUG_ON(!PageLocked()) in migration_entry_to_page(): CPU A (pagemap) CPU B (migration) lock_page() try_to_unmap(page, TTU_MIGRATION...) make_migration_entry() set_pte_at() pte_to_pagemap_entry() remove_migration_ptes() unlock_page() if(is_migration_entry()) migration_entry_to_page() BUG_ON(!PageLocked(page)) Also lockless read might be non-atomic if pte is larger than wordsize. Other pte walkers (smaps, numa_maps, clear_refs) already lock ptes. Fixes: 052fb0d635df ("proc: report file/anon bit in /proc/pid/pagemap") Signed-off-by: Konstantin Khlebnikov Reported-by: Andrey Ryabinin Reviewed-by: Cyrill Gorcunov Acked-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: [3.5+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e6e0abeb5d12..eeab30fcffcc 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1056,7 +1056,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct vm_area_struct *vma; struct pagemapread *pm = walk->private; spinlock_t *ptl; - pte_t *pte; + pte_t *pte, *orig_pte; int err = 0; /* find the first VMA at or above 'addr' */ @@ -1117,15 +1117,19 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, BUG_ON(is_vm_hugetlb_page(vma)); /* Addresses in the VMA. */ - for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) { + orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + for (; addr < min(end, vma->vm_end); pte++, addr += PAGE_SIZE) { pagemap_entry_t pme; - pte = pte_offset_map(pmd, addr); + pte_to_pagemap_entry(&pme, pm, vma, addr, *pte); - pte_unmap(pte); err = add_to_pagemap(addr, &pme, pm); if (err) - return err; + break; } + pte_unmap_unlock(orig_pte, ptl); + + if (err) + return err; if (addr == end) break; -- cgit v1.2.3 From 14eb6fdd4204d215a14ecd9f84a1ca66faabcc4d Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:43 -0800 Subject: smaps: remove mem_size_stats->vma and use walk_page_vma() pagewalk.c can handle vma in itself, so we don't have to pass vma via walk->private. And show_smap() walks pages on vma basis, so using walk_page_vma() is preferable. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index eeab30fcffcc..73425398b38c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -436,7 +436,6 @@ const struct file_operations proc_tid_maps_operations = { #ifdef CONFIG_PROC_PAGE_MONITOR struct mem_size_stats { - struct vm_area_struct *vma; unsigned long resident; unsigned long shared_clean; unsigned long shared_dirty; @@ -485,7 +484,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct mm_walk *walk) { struct mem_size_stats *mss = walk->private; - struct vm_area_struct *vma = mss->vma; + struct vm_area_struct *vma = walk->vma; struct page *page = NULL; if (pte_present(*pte)) { @@ -509,7 +508,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, struct mm_walk *walk) { struct mem_size_stats *mss = walk->private; - struct vm_area_struct *vma = mss->vma; + struct vm_area_struct *vma = walk->vma; struct page *page; /* FOLL_DUMP will return -EFAULT on huge zero page */ @@ -530,8 +529,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct mem_size_stats *mss = walk->private; - struct vm_area_struct *vma = mss->vma; + struct vm_area_struct *vma = walk->vma; pte_t *pte; spinlock_t *ptl; @@ -623,10 +621,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) }; memset(&mss, 0, sizeof mss); - mss.vma = vma; /* mmap_sem is held in m_start */ - if (vma->vm_mm && !is_vm_hugetlb_page(vma)) - walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk); + walk_page_vma(vma, &smaps_walk); show_map_vma(m, vma, is_pid); -- cgit v1.2.3 From 5c64f52acdbc615e3ef58692f42ee00b83d0225d Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:46 -0800 Subject: clear_refs: remove clear_refs_private->vma and introduce clear_refs_test_walk() clear_refs_write() has some prechecks to determine if we really walk over a given vma. Now we have a test_walk() callback to filter vmas, so let's utilize it. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 46 ++++++++++++++++++++++------------------------ 1 file changed, 22 insertions(+), 24 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 73425398b38c..bed0834715a5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -736,7 +736,6 @@ enum clear_refs_types { }; struct clear_refs_private { - struct vm_area_struct *vma; enum clear_refs_types type; }; @@ -767,7 +766,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct clear_refs_private *cp = walk->private; - struct vm_area_struct *vma = cp->vma; + struct vm_area_struct *vma = walk->vma; pte_t *pte, ptent; spinlock_t *ptl; struct page *page; @@ -801,6 +800,25 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, return 0; } +static int clear_refs_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct clear_refs_private *cp = walk->private; + struct vm_area_struct *vma = walk->vma; + + /* + * Writing 1 to /proc/pid/clear_refs affects all pages. + * Writing 2 to /proc/pid/clear_refs only affects anonymous pages. + * Writing 3 to /proc/pid/clear_refs only affects file mapped pages. + * Writing 4 to /proc/pid/clear_refs affects all pages. + */ + if (cp->type == CLEAR_REFS_ANON && vma->vm_file) + return 1; + if (cp->type == CLEAR_REFS_MAPPED && !vma->vm_file) + return 1; + return 0; +} + static ssize_t clear_refs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -841,6 +859,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, }; struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range, + .test_walk = clear_refs_test_walk, .mm = mm, .private = &cp, }; @@ -860,28 +879,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, } mmu_notifier_invalidate_range_start(mm, 0, -1); } - for (vma = mm->mmap; vma; vma = vma->vm_next) { - cp.vma = vma; - if (is_vm_hugetlb_page(vma)) - continue; - /* - * Writing 1 to /proc/pid/clear_refs affects all pages. - * - * Writing 2 to /proc/pid/clear_refs only affects - * Anonymous pages. - * - * Writing 3 to /proc/pid/clear_refs only affects file - * mapped pages. - * - * Writing 4 to /proc/pid/clear_refs affects all pages. - */ - if (type == CLEAR_REFS_ANON && vma->vm_file) - continue; - if (type == CLEAR_REFS_MAPPED && !vma->vm_file) - continue; - walk_page_range(vma->vm_start, vma->vm_end, - &clear_refs_walk); - } + walk_page_range(0, ~0UL, &clear_refs_walk); if (type == CLEAR_REFS_SOFT_DIRTY) mmu_notifier_invalidate_range_end(mm, 0, -1); flush_tlb_mm(mm); -- cgit v1.2.3 From f995ece24dfecb3614468befbe4e6e777b854cc0 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:48 -0800 Subject: pagemap: use walk->vma instead of calling find_vma() Page table walker has the information of the current vma in mm_walk, so we don't have to call find_vma() in each pagemap_(pte|hugetlb)_range() call any longer. Currently pagemap_pte_range() does vma loop itself, so this patch reduces many lines of code. NULL-vma check is omitted because we assume that we never run these callbacks on any address outside vma. And even if it were broken, NULL pointer dereference would be detected, so we can get enough information for debugging. Signed-off-by: Naoya Horiguchi Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Kirill A. Shutemov Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 68 +++++++++++------------------------------------------- 1 file changed, 14 insertions(+), 54 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index bed0834715a5..4206706dd92a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1047,15 +1047,13 @@ static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemap static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct vm_area_struct *vma; + struct vm_area_struct *vma = walk->vma; struct pagemapread *pm = walk->private; spinlock_t *ptl; pte_t *pte, *orig_pte; int err = 0; - /* find the first VMA at or above 'addr' */ - vma = find_vma(walk->mm, addr); - if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { int pmd_flags2; if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd)) @@ -1081,55 +1079,20 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (pmd_trans_unstable(pmd)) return 0; - while (1) { - /* End of address space hole, which we mark as non-present. */ - unsigned long hole_end; - - if (vma) - hole_end = min(end, vma->vm_start); - else - hole_end = end; - - for (; addr < hole_end; addr += PAGE_SIZE) { - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2)); - - err = add_to_pagemap(addr, &pme, pm); - if (err) - return err; - } - - if (!vma || vma->vm_start >= end) - break; - /* - * We can't possibly be in a hugetlb VMA. In general, - * for a mm_walk with a pmd_entry and a hugetlb_entry, - * the pmd_entry can only be called on addresses in a - * hugetlb if the walk starts in a non-hugetlb VMA and - * spans a hugepage VMA. Since pagemap_read walks are - * PMD-sized and PMD-aligned, this will never be true. - */ - BUG_ON(is_vm_hugetlb_page(vma)); - - /* Addresses in the VMA. */ - orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); - for (; addr < min(end, vma->vm_end); pte++, addr += PAGE_SIZE) { - pagemap_entry_t pme; - - pte_to_pagemap_entry(&pme, pm, vma, addr, *pte); - err = add_to_pagemap(addr, &pme, pm); - if (err) - break; - } - pte_unmap_unlock(orig_pte, ptl); + /* + * We can assume that @vma always points to a valid one and @end never + * goes beyond vma->vm_end. + */ + orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + for (; addr < end; pte++, addr += PAGE_SIZE) { + pagemap_entry_t pme; + pte_to_pagemap_entry(&pme, pm, vma, addr, *pte); + err = add_to_pagemap(addr, &pme, pm); if (err) - return err; - - if (addr == end) break; - - vma = find_vma(walk->mm, addr); } + pte_unmap_unlock(orig_pte, ptl); cond_resched(); @@ -1155,15 +1118,12 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, struct mm_walk *walk) { struct pagemapread *pm = walk->private; - struct vm_area_struct *vma; + struct vm_area_struct *vma = walk->vma; int err = 0; int flags2; pagemap_entry_t pme; - vma = find_vma(walk->mm, addr); - WARN_ON_ONCE(!vma); - - if (vma && (vma->vm_flags & VM_SOFTDIRTY)) + if (vma->vm_flags & VM_SOFTDIRTY) flags2 = __PM_SOFT_DIRTY; else flags2 = 0; -- cgit v1.2.3 From 632fd60fe46f9159f059ed7612eb529e475302a9 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:51 -0800 Subject: numa_maps: fix typo in gather_hugetbl_stats Just doing s/gather_hugetbl_stats/gather_hugetlb_stats/g, this makes code grep-friendly. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 4206706dd92a..ae4bc2960077 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1385,7 +1385,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, return 0; } #ifdef CONFIG_HUGETLB_PAGE -static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, +static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct numa_maps *md; @@ -1404,7 +1404,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, } #else -static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, +static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { return 0; @@ -1435,7 +1435,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) md->vma = vma; - walk.hugetlb_entry = gather_hugetbl_stats; + walk.hugetlb_entry = gather_hugetlb_stats; walk.pmd_entry = gather_pte_stats; walk.private = md; walk.mm = mm; -- cgit v1.2.3 From d85f4d6d3bfe3b82e2903ac51a2f837eab7115d7 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:54 -0800 Subject: numa_maps: remove numa_maps->vma pagewalk.c can handle vma in itself, so we don't have to pass vma via walk->private. And show_numa_map() walks pages on vma basis, so using walk_page_vma() is preferable. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ae4bc2960077..a36db4ad140b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1283,7 +1283,6 @@ const struct file_operations proc_pagemap_operations = { #ifdef CONFIG_NUMA struct numa_maps { - struct vm_area_struct *vma; unsigned long pages; unsigned long anon; unsigned long active; @@ -1352,18 +1351,17 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, static int gather_pte_stats(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct numa_maps *md; + struct numa_maps *md = walk->private; + struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *orig_pte; pte_t *pte; - md = walk->private; - - if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pte_t huge_pte = *(pte_t *)pmd; struct page *page; - page = can_gather_numa_stats(huge_pte, md->vma, addr); + page = can_gather_numa_stats(huge_pte, vma, addr); if (page) gather_stats(page, md, pte_dirty(huge_pte), HPAGE_PMD_SIZE/PAGE_SIZE); @@ -1375,7 +1373,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, return 0; orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); do { - struct page *page = can_gather_numa_stats(*pte, md->vma, addr); + struct page *page = can_gather_numa_stats(*pte, vma, addr); if (!page) continue; gather_stats(page, md, pte_dirty(*pte), 1); @@ -1422,7 +1420,12 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) struct numa_maps *md = &numa_priv->md; struct file *file = vma->vm_file; struct mm_struct *mm = vma->vm_mm; - struct mm_walk walk = {}; + struct mm_walk walk = { + .hugetlb_entry = gather_hugetlb_stats, + .pmd_entry = gather_pte_stats, + .private = md, + .mm = mm, + }; struct mempolicy *pol; char buffer[64]; int nid; @@ -1433,13 +1436,6 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) /* Ensure we start with an empty set of numa_maps statistics. */ memset(md, 0, sizeof(*md)); - md->vma = vma; - - walk.hugetlb_entry = gather_hugetlb_stats; - walk.pmd_entry = gather_pte_stats; - walk.private = md; - walk.mm = mm; - pol = __get_vma_policy(vma, vma->vm_start); if (pol) { mpol_to_str(buffer, sizeof(buffer), pol); @@ -1473,7 +1469,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) if (is_vm_hugetlb_page(vma)) seq_puts(m, " huge"); - walk_page_range(vma->vm_start, vma->vm_end, &walk); + /* mmap_sem is held by m_start */ + walk_page_vma(vma, &walk); if (!md->pages) goto out; -- cgit v1.2.3 From 48684a65b4e3ff544d62532c1b78962c9677b632 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:28:06 -0800 Subject: mm: pagewalk: fix misbehavior of walk_page_range for vma(VM_PFNMAP) walk_page_range() silently skips vma having VM_PFNMAP set, which leads to undesirable behaviour at client end (who called walk_page_range). For example for pagemap_read(), when no callbacks are called against VM_PFNMAP vma, pagemap_read() may prepare pagemap data for next virtual address range at wrong index. That could confuse and/or break userspace applications. This patch avoid this misbehavior caused by vma(VM_PFNMAP) like follows: - for pagemap_read() which has its own ->pte_hole(), call the ->pte_hole() over vma(VM_PFNMAP), - for clear_refs and queue_pages which have their own ->tests_walk, just return 1 and skip vma(VM_PFNMAP). This is no problem because these are not interested in hole regions, - for other callers, just skip the vma(VM_PFNMAP) as a default behavior. Signed-off-by: Naoya Horiguchi Signed-off-by: Shiraz Hashim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 3 +++ mm/mempolicy.c | 3 +++ mm/pagewalk.c | 21 +++++++++++++-------- 3 files changed, 19 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index a36db4ad140b..f5ca96524f5f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -806,6 +806,9 @@ static int clear_refs_test_walk(unsigned long start, unsigned long end, struct clear_refs_private *cp = walk->private; struct vm_area_struct *vma = walk->vma; + if (vma->vm_flags & VM_PFNMAP) + return 1; + /* * Writing 1 to /proc/pid/clear_refs affects all pages. * Writing 2 to /proc/pid/clear_refs only affects anonymous pages. diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b1dcd11d867a..f1bd23803576 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -591,6 +591,9 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; + if (vma->vm_flags & VM_PFNMAP) + return 1; + if (endvma > end) endvma = end; if (vma->vm_start > start) diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 4c9a653ba563..75c1f2878519 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -35,7 +35,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, do { again: next = pmd_addr_end(addr, end); - if (pmd_none(*pmd)) { + if (pmd_none(*pmd) || !walk->vma) { if (walk->pte_hole) err = walk->pte_hole(addr, next, walk); if (err) @@ -165,9 +165,6 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, * or skip it via the returned value. Return 0 if we do walk over the * current vma, and return 1 if we skip the vma. Negative values means * error, where we abort the current walk. - * - * Default check (only VM_PFNMAP check for now) is used when the caller - * doesn't define test_walk() callback. */ static int walk_page_test(unsigned long start, unsigned long end, struct mm_walk *walk) @@ -178,11 +175,19 @@ static int walk_page_test(unsigned long start, unsigned long end, return walk->test_walk(start, end, walk); /* - * Do not walk over vma(VM_PFNMAP), because we have no valid struct - * page backing a VM_PFNMAP range. See also commit a9ff785e4437. + * vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP + * range, so we don't walk over it as we do for normal vmas. However, + * Some callers are interested in handling hole range and they don't + * want to just ignore any single address range. Such users certainly + * define their ->pte_hole() callbacks, so let's delegate them to handle + * vma(VM_PFNMAP). */ - if (vma->vm_flags & VM_PFNMAP) - return 1; + if (vma->vm_flags & VM_PFNMAP) { + int err = 1; + if (walk->pte_hole) + err = walk->pte_hole(start, end, walk); + return err ? err : 1; + } return 0; } -- cgit v1.2.3 From 7d5b3bfaa2da150ce2dc45546f2125b854f962ef Mon Sep 17 00:00:00 2001 From: Kirill A. Shutemov Date: Wed, 11 Feb 2015 15:28:08 -0800 Subject: mm: /proc/pid/clear_refs: avoid split_huge_page() Currently pagewalker splits all THP pages on any clear_refs request. It's not necessary. We can handle this on PMD level. One side effect is that soft dirty will potentially see more dirty memory, since we will mark whole THP page dirty at once. Sanity checked with CRIU test suite. More testing is required. Signed-off-by: Kirill A. Shutemov Signed-off-by: Naoya Horiguchi Reviewed-by: Cyrill Gorcunov Cc: Pavel Emelyanov Cc: Andrea Arcangeli Cc: Dave Hansen Cc: "Kirill A. Shutemov" Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 47 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 44 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f5ca96524f5f..0e36c1e49fe3 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -739,10 +739,10 @@ struct clear_refs_private { enum clear_refs_types type; }; +#ifdef CONFIG_MEM_SOFT_DIRTY static inline void clear_soft_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { -#ifdef CONFIG_MEM_SOFT_DIRTY /* * The soft-dirty tracker uses #PF-s to catch writes * to pages, so write-protect the pte as well. See the @@ -759,9 +759,35 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, } set_pte_at(vma->vm_mm, addr, pte, ptent); -#endif } +static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + + pmd = pmd_wrprotect(pmd); + pmd = pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); + + if (vma->vm_flags & VM_SOFTDIRTY) + vma->vm_flags &= ~VM_SOFTDIRTY; + + set_pmd_at(vma->vm_mm, addr, pmdp, pmd); +} + +#else + +static inline void clear_soft_dirty(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte) +{ +} + +static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ +} +#endif + static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -771,7 +797,22 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, spinlock_t *ptl; struct page *page; - split_huge_page_pmd(vma, addr, pmd); + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (cp->type == CLEAR_REFS_SOFT_DIRTY) { + clear_soft_dirty_pmd(vma, addr, pmd); + goto out; + } + + page = pmd_page(*pmd); + + /* Clear accessed and referenced bits. */ + pmdp_test_and_clear_young(vma, addr, pmd); + ClearPageReferenced(page); +out: + spin_unlock(ptl); + return 0; + } + if (pmd_trans_unstable(pmd)) return 0; -- cgit v1.2.3 From d15bc38df607c893c36f4962dca0f57174c6a5c9 Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Fri, 13 Feb 2015 13:19:53 -0800 Subject: nfs: Provide and use helper functions for marking a page as unstable Signed-off-by: Tom Haynes Signed-off-by: Trond Myklebust --- fs/nfs/filelayout/filelayout.c | 9 ++------- fs/nfs/flexfilelayout/flexfilelayout.c | 9 ++------- fs/nfs/internal.h | 13 +++++++++++++ fs/nfs/write.c | 9 ++------- 4 files changed, 19 insertions(+), 21 deletions(-) (limited to 'fs') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 7ae1c263c5cf..e1e5ea262a13 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -1000,13 +1000,8 @@ mds_commit: nfs_list_add_request(req, list); cinfo->mds->ncommit++; spin_unlock(cinfo->lock); - if (!cinfo->dreq) { - inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host), - BDI_RECLAIMABLE); - __mark_inode_dirty(req->wb_context->dentry->d_inode, - I_DIRTY_DATASYNC); - } + if (!cinfo->dreq) + nfs_mark_page_unstable(req->wb_page); } static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index c22ecaa86c1c..423c2bc371fa 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1364,13 +1364,8 @@ ff_layout_mark_request_commit(struct nfs_page *req, nfs_list_add_request(req, list); cinfo->mds->ncommit++; spin_unlock(cinfo->lock); - if (!cinfo->dreq) { - inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host), - BDI_RECLAIMABLE); - __mark_inode_dirty(req->wb_context->dentry->d_inode, - I_DIRTY_DATASYNC); - } + if (!cinfo->dreq) + nfs_mark_page_unstable(req->wb_page); } static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 212b8c883d22..b802fb3a2d99 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -597,6 +597,19 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) sb->s_maxbytes = MAX_LFS_FILESIZE; } +/* + * Record the page as unstable and mark its inode as dirty. + */ +static inline +void nfs_mark_page_unstable(struct page *page) +{ + struct inode *inode = page_file_mapping(page)->host; + + inc_zone_page_state(page, NR_UNSTABLE_NFS); + inc_bdi_stat(inode_to_bdi(inode), BDI_RECLAIMABLE); + __mark_inode_dirty(inode, I_DIRTY_DATASYNC); +} + /* * Determine the number of bytes of data the page contains */ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 88a6d2196ece..76c278acaefc 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -789,13 +789,8 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, nfs_list_add_request(req, dst); cinfo->mds->ncommit++; spin_unlock(cinfo->lock); - if (!cinfo->dreq) { - inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host), - BDI_RECLAIMABLE); - __mark_inode_dirty(req->wb_context->dentry->d_inode, - I_DIRTY_DATASYNC); - } + if (!cinfo->dreq) + nfs_mark_page_unstable(req->wb_page); } EXPORT_SYMBOL_GPL(nfs_request_add_commit_list); -- cgit v1.2.3 From 487b9b8afde60986b606b3ee05169fb893adc153 Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Fri, 13 Feb 2015 13:19:54 -0800 Subject: nfs: Can call nfs_clear_page_commit() instead Signed-off-by: Tom Haynes Signed-off-by: Trond Myklebust --- fs/nfs/write.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 76c278acaefc..595d81e354d1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1600,11 +1600,8 @@ void nfs_retry_commit(struct list_head *page_list, req = nfs_list_entry(page_list->next); nfs_list_remove_request(req); nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx); - if (!cinfo->dreq) { - dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - dec_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host), - BDI_RECLAIMABLE); - } + if (!cinfo->dreq) + nfs_clear_page_commit(req->wb_page); nfs_unlock_and_release_request(req); } } -- cgit v1.2.3 From 338d00cfef07d74a072f96821c64b20f98517d72 Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Tue, 17 Feb 2015 14:58:15 -0800 Subject: pnfs: Refactor the *_layout_mark_request_commit to use pnfs_layout_mark_request_commit The File Layout's filelayout_mark_request_commit() is almost the Flex File Layout's ff_layout_mark_request_commit(). And that can be reduced by calling into nfs_request_add_commit_list(). Signed-off-by: Tom Haynes Signed-off-by: Trond Myklebust --- fs/nfs/filelayout/filelayout.c | 48 +++++++--------------------------- fs/nfs/flexfilelayout/flexfilelayout.c | 38 +-------------------------- fs/nfs/pnfs.h | 4 +++ fs/nfs/pnfs_nfs.c | 30 +++++++++++++++++++++ 4 files changed, 45 insertions(+), 75 deletions(-) (limited to 'fs') diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index e1e5ea262a13..91e88a7ecef0 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -960,48 +960,20 @@ filelayout_mark_request_commit(struct nfs_page *req, { struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); u32 i, j; - struct list_head *list; - struct pnfs_commit_bucket *buckets; if (fl->commit_through_mds) { - list = &cinfo->mds->list; - spin_lock(cinfo->lock); - goto mds_commit; - } - - /* Note that we are calling nfs4_fl_calc_j_index on each page - * that ends up being committed to a data server. An attractive - * alternative is to add a field to nfs_write_data and nfs_page - * to store the value calculated in filelayout_write_pagelist - * and just use that here. - */ - j = nfs4_fl_calc_j_index(lseg, req_offset(req)); - i = select_bucket_index(fl, j); - spin_lock(cinfo->lock); - buckets = cinfo->ds->buckets; - list = &buckets[i].written; - if (list_empty(list)) { - /* Non-empty buckets hold a reference on the lseg. That ref - * is normally transferred to the COMMIT call and released - * there. It could also be released if the last req is pulled - * off due to a rewrite, in which case it will be done in - * pnfs_generic_clear_request_commit + nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo); + } else { + /* Note that we are calling nfs4_fl_calc_j_index on each page + * that ends up being committed to a data server. An attractive + * alternative is to add a field to nfs_write_data and nfs_page + * to store the value calculated in filelayout_write_pagelist + * and just use that here. */ - buckets[i].wlseg = pnfs_get_lseg(lseg); + j = nfs4_fl_calc_j_index(lseg, req_offset(req)); + i = select_bucket_index(fl, j); + pnfs_layout_mark_request_commit(req, lseg, cinfo, i); } - set_bit(PG_COMMIT_TO_DS, &req->wb_flags); - cinfo->ds->nwritten++; - -mds_commit: - /* nfs_request_add_commit_list(). We need to add req to list without - * dropping cinfo lock. - */ - set_bit(PG_CLEAN, &(req)->wb_flags); - nfs_list_add_request(req, list); - cinfo->mds->ncommit++; - spin_unlock(cinfo->lock); - if (!cinfo->dreq) - nfs_mark_page_unstable(req->wb_page); } static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 423c2bc371fa..315cc68945b9 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1332,42 +1332,6 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) return PNFS_ATTEMPTED; } -static void -ff_layout_mark_request_commit(struct nfs_page *req, - struct pnfs_layout_segment *lseg, - struct nfs_commit_info *cinfo, - u32 ds_commit_idx) -{ - struct list_head *list; - struct pnfs_commit_bucket *buckets; - - spin_lock(cinfo->lock); - buckets = cinfo->ds->buckets; - list = &buckets[ds_commit_idx].written; - if (list_empty(list)) { - /* Non-empty buckets hold a reference on the lseg. That ref - * is normally transferred to the COMMIT call and released - * there. It could also be released if the last req is pulled - * off due to a rewrite, in which case it will be done in - * pnfs_common_clear_request_commit - */ - WARN_ON_ONCE(buckets[ds_commit_idx].wlseg != NULL); - buckets[ds_commit_idx].wlseg = pnfs_get_lseg(lseg); - } - set_bit(PG_COMMIT_TO_DS, &req->wb_flags); - cinfo->ds->nwritten++; - - /* nfs_request_add_commit_list(). We need to add req to list without - * dropping cinfo lock. - */ - set_bit(PG_CLEAN, &(req)->wb_flags); - nfs_list_add_request(req, list); - cinfo->mds->ncommit++; - spin_unlock(cinfo->lock); - if (!cinfo->dreq) - nfs_mark_page_unstable(req->wb_page); -} - static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) { return i; @@ -1535,7 +1499,7 @@ static struct pnfs_layoutdriver_type flexfilelayout_type = { .pg_write_ops = &ff_layout_pg_write_ops, .get_ds_info = ff_layout_get_ds_info, .free_deviceid_node = ff_layout_free_deveiceid_node, - .mark_request_commit = ff_layout_mark_request_commit, + .mark_request_commit = pnfs_layout_mark_request_commit, .clear_request_commit = pnfs_generic_clear_request_commit, .scan_commit_lists = pnfs_generic_scan_commit_lists, .recover_commit_reqs = pnfs_generic_recover_commit_reqs, diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 797cd6253adf..635f0865671c 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -344,6 +344,10 @@ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags); +void pnfs_layout_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx); static inline bool nfs_have_layout(struct inode *inode) { diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index fdc4f6562bb7..54e36b38fb5f 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -838,3 +838,33 @@ out_err: return NULL; } EXPORT_SYMBOL_GPL(nfs4_decode_mp_ds_addr); + +void +pnfs_layout_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + u32 ds_commit_idx) +{ + struct list_head *list; + struct pnfs_commit_bucket *buckets; + + spin_lock(cinfo->lock); + buckets = cinfo->ds->buckets; + list = &buckets[ds_commit_idx].written; + if (list_empty(list)) { + /* Non-empty buckets hold a reference on the lseg. That ref + * is normally transferred to the COMMIT call and released + * there. It could also be released if the last req is pulled + * off due to a rewrite, in which case it will be done in + * pnfs_common_clear_request_commit + */ + WARN_ON_ONCE(buckets[ds_commit_idx].wlseg != NULL); + buckets[ds_commit_idx].wlseg = pnfs_get_lseg(lseg); + } + set_bit(PG_COMMIT_TO_DS, &req->wb_flags); + cinfo->ds->nwritten++; + spin_unlock(cinfo->lock); + + nfs_request_add_commit_list(req, list, cinfo); +} +EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit); -- cgit v1.2.3