linux/fs/xfs/xfs_acl.c

278 lines
5.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2008, Christoph Hellwig
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_attr.h"
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-14 23:14:59 +00:00
#include "xfs_trace.h"
#include "xfs_error.h"
#include "xfs_acl.h"
#include <linux/posix_acl_xattr.h>
/*
* Locking scheme:
* - all ACL updates are protected by inode->i_mutex, which is taken before
* calling into this file.
*/
STATIC struct posix_acl *
xfs_acl_from_disk(
struct xfs_mount *mp,
const struct xfs_acl *aclp,
int len,
int max_entries)
{
struct posix_acl_entry *acl_e;
struct posix_acl *acl;
const struct xfs_acl_entry *ace;
unsigned int count, i;
if (len < sizeof(*aclp)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, aclp,
len);
return ERR_PTR(-EFSCORRUPTED);
}
count = be32_to_cpu(aclp->acl_cnt);
if (count > max_entries || XFS_ACL_SIZE(count) != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, aclp,
len);
return ERR_PTR(-EFSCORRUPTED);
}
acl = posix_acl_alloc(count, GFP_KERNEL);
if (!acl)
return ERR_PTR(-ENOMEM);
for (i = 0; i < count; i++) {
acl_e = &acl->a_entries[i];
ace = &aclp->acl_entry[i];
/*
* The tag is 32 bits on disk and 16 bits in core.
*
* Because every access to it goes through the core
* format first this is not a problem.
*/
acl_e->e_tag = be32_to_cpu(ace->ae_tag);
acl_e->e_perm = be16_to_cpu(ace->ae_perm);
switch (acl_e->e_tag) {
case ACL_USER:
acl_e->e_uid = xfs_uid_to_kuid(be32_to_cpu(ace->ae_id));
break;
case ACL_GROUP:
acl_e->e_gid = xfs_gid_to_kgid(be32_to_cpu(ace->ae_id));
break;
case ACL_USER_OBJ:
case ACL_GROUP_OBJ:
case ACL_MASK:
case ACL_OTHER:
break;
default:
goto fail;
}
}
return acl;
fail:
posix_acl_release(acl);
return ERR_PTR(-EINVAL);
}
STATIC void
xfs_acl_to_disk(struct xfs_acl *aclp, const struct posix_acl *acl)
{
const struct posix_acl_entry *acl_e;
struct xfs_acl_entry *ace;
int i;
aclp->acl_cnt = cpu_to_be32(acl->a_count);
for (i = 0; i < acl->a_count; i++) {
ace = &aclp->acl_entry[i];
acl_e = &acl->a_entries[i];
ace->ae_tag = cpu_to_be32(acl_e->e_tag);
switch (acl_e->e_tag) {
case ACL_USER:
ace->ae_id = cpu_to_be32(xfs_kuid_to_uid(acl_e->e_uid));
break;
case ACL_GROUP:
ace->ae_id = cpu_to_be32(xfs_kgid_to_gid(acl_e->e_gid));
break;
default:
ace->ae_id = cpu_to_be32(ACL_UNDEFINED_ID);
break;
}
ace->ae_perm = cpu_to_be16(acl_e->e_perm);
}
}
struct posix_acl *
xfs_get_acl(struct inode *inode, int type)
{
struct xfs_inode *ip = XFS_I(inode);
struct posix_acl *acl = NULL;
xfs: allocate xattr buffer on demand When doing file lookups and checking for permissions, we end up in xfs_get_acl() to see if there are any ACLs on the inode. This requires and xattr lookup, and to do that we have to supply a buffer large enough to hold an maximum sized xattr. On workloads were we are accessing a wide range of cache cold files under memory pressure (e.g. NFS fileservers) we end up spending a lot of time allocating the buffer. The buffer is 64k in length, so is a contiguous multi-page allocation, and if that then fails we fall back to vmalloc(). Hence the allocation here is /expensive/ when we are looking up hundreds of thousands of files a second. Initial numbers from a bpf trace show average time in xfs_get_acl() is ~32us, with ~19us of that in the memory allocation. Note these are average times, so there are going to be affected by the worst case allocations more than the common fast case... To avoid this, we could just do a "null" lookup to see if the ACL xattr exists and then only do the allocation if it exists. This, however, optimises the path for the "no ACL present" case at the expense of the "acl present" case. i.e. we can halve the time in xfs_get_acl() for the no acl case (i.e down to ~10-15us), but that then increases the ACL case by 30% (i.e. up to 40-45us). To solve this and speed up both cases, drive the xattr buffer allocation into the attribute code once we know what the actual xattr length is. For the no-xattr case, we avoid the allocation completely, speeding up that case. For the common ACL case, we'll end up with a fast heap allocation (because it'll be smaller than a page), and only for the rarer "we have a remote xattr" will we have a multi-page allocation occur. Hence the common ACL case will be much faster, too. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-08-29 16:04:10 +00:00
struct xfs_acl *xfs_acl = NULL;
unsigned char *ea_name;
int error;
int len;
trace_xfs_get_acl(ip);
switch (type) {
case ACL_TYPE_ACCESS:
ea_name = SGI_ACL_FILE;
break;
case ACL_TYPE_DEFAULT:
ea_name = SGI_ACL_DEFAULT;
break;
default:
BUG();
}
/*
* If we have a cached ACLs value just return it, not need to
* go out to the disk.
*/
len = XFS_ACL_MAX_SIZE(ip->i_mount);
error = xfs_attr_get(ip, ea_name, strlen(ea_name),
(unsigned char **)&xfs_acl, &len,
xfs: allocate xattr buffer on demand When doing file lookups and checking for permissions, we end up in xfs_get_acl() to see if there are any ACLs on the inode. This requires and xattr lookup, and to do that we have to supply a buffer large enough to hold an maximum sized xattr. On workloads were we are accessing a wide range of cache cold files under memory pressure (e.g. NFS fileservers) we end up spending a lot of time allocating the buffer. The buffer is 64k in length, so is a contiguous multi-page allocation, and if that then fails we fall back to vmalloc(). Hence the allocation here is /expensive/ when we are looking up hundreds of thousands of files a second. Initial numbers from a bpf trace show average time in xfs_get_acl() is ~32us, with ~19us of that in the memory allocation. Note these are average times, so there are going to be affected by the worst case allocations more than the common fast case... To avoid this, we could just do a "null" lookup to see if the ACL xattr exists and then only do the allocation if it exists. This, however, optimises the path for the "no ACL present" case at the expense of the "acl present" case. i.e. we can halve the time in xfs_get_acl() for the no acl case (i.e down to ~10-15us), but that then increases the ACL case by 30% (i.e. up to 40-45us). To solve this and speed up both cases, drive the xattr buffer allocation into the attribute code once we know what the actual xattr length is. For the no-xattr case, we avoid the allocation completely, speeding up that case. For the common ACL case, we'll end up with a fast heap allocation (because it'll be smaller than a page), and only for the rarer "we have a remote xattr" will we have a multi-page allocation occur. Hence the common ACL case will be much faster, too. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-08-29 16:04:10 +00:00
ATTR_ALLOC | ATTR_ROOT);
if (error) {
/*
* If the attribute doesn't exist make sure we have a negative
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 13:38:37 +00:00
* cache entry, for any other error assume it is transient.
*/
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 13:38:37 +00:00
if (error != -ENOATTR)
acl = ERR_PTR(error);
} else {
acl = xfs_acl_from_disk(ip->i_mount, xfs_acl, len,
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 13:38:37 +00:00
XFS_ACL_MAX_ENTRIES(ip->i_mount));
xfs: allocate xattr buffer on demand When doing file lookups and checking for permissions, we end up in xfs_get_acl() to see if there are any ACLs on the inode. This requires and xattr lookup, and to do that we have to supply a buffer large enough to hold an maximum sized xattr. On workloads were we are accessing a wide range of cache cold files under memory pressure (e.g. NFS fileservers) we end up spending a lot of time allocating the buffer. The buffer is 64k in length, so is a contiguous multi-page allocation, and if that then fails we fall back to vmalloc(). Hence the allocation here is /expensive/ when we are looking up hundreds of thousands of files a second. Initial numbers from a bpf trace show average time in xfs_get_acl() is ~32us, with ~19us of that in the memory allocation. Note these are average times, so there are going to be affected by the worst case allocations more than the common fast case... To avoid this, we could just do a "null" lookup to see if the ACL xattr exists and then only do the allocation if it exists. This, however, optimises the path for the "no ACL present" case at the expense of the "acl present" case. i.e. we can halve the time in xfs_get_acl() for the no acl case (i.e down to ~10-15us), but that then increases the ACL case by 30% (i.e. up to 40-45us). To solve this and speed up both cases, drive the xattr buffer allocation into the attribute code once we know what the actual xattr length is. For the no-xattr case, we avoid the allocation completely, speeding up that case. For the common ACL case, we'll end up with a fast heap allocation (because it'll be smaller than a page), and only for the rarer "we have a remote xattr" will we have a multi-page allocation occur. Hence the common ACL case will be much faster, too. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-08-29 16:04:10 +00:00
kmem_free(xfs_acl);
}
return acl;
}
int
__xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
struct xfs_inode *ip = XFS_I(inode);
unsigned char *ea_name;
int error;
switch (type) {
case ACL_TYPE_ACCESS:
ea_name = SGI_ACL_FILE;
break;
case ACL_TYPE_DEFAULT:
if (!S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
ea_name = SGI_ACL_DEFAULT;
break;
default:
return -EINVAL;
}
if (acl) {
struct xfs_acl *xfs_acl;
int len = XFS_ACL_MAX_SIZE(ip->i_mount);
xfs_acl = kmem_zalloc_large(len, 0);
if (!xfs_acl)
return -ENOMEM;
xfs_acl_to_disk(xfs_acl, acl);
/* subtract away the unused acl entries */
len -= sizeof(struct xfs_acl_entry) *
(XFS_ACL_MAX_ENTRIES(ip->i_mount) - acl->a_count);
error = xfs_attr_set(ip, ea_name, strlen(ea_name),
(unsigned char *)xfs_acl, len, ATTR_ROOT);
kmem_free(xfs_acl);
} else {
/*
* A NULL ACL argument means we want to remove the ACL.
*/
error = xfs_attr_remove(ip, ea_name,
strlen(ea_name),
ATTR_ROOT);
/*
* If the attribute didn't exist to start with that's fine.
*/
if (error == -ENOATTR)
error = 0;
}
if (!error)
set_cached_acl(inode, type, acl);
return error;
}
static int
xfs_set_mode(struct inode *inode, umode_t mode)
{
int error = 0;
if (mode != inode->i_mode) {
struct iattr iattr;
iattr.ia_valid = ATTR_MODE | ATTR_CTIME;
iattr.ia_mode = mode;
iattr.ia_ctime = current_time(inode);
error = xfs_setattr_nonsize(XFS_I(inode), &iattr, XFS_ATTR_NOACL);
}
return error;
}
int
xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
umode_t mode;
bool set_mode = false;
int error = 0;
if (!acl)
goto set_acl;
error = -E2BIG;
if (acl->a_count > XFS_ACL_MAX_ENTRIES(XFS_M(inode->i_sb)))
return error;
if (type == ACL_TYPE_ACCESS) {
error = posix_acl_update_mode(inode, &mode, &acl);
if (error)
return error;
set_mode = true;
}
set_acl:
error = __xfs_set_acl(inode, acl, type);
if (error)
return error;
/*
* We set the mode after successfully updating the ACL xattr because the
* xattr update can fail at ENOSPC and we don't want to change the mode
* if the ACL update hasn't been applied.
*/
if (set_mode)
error = xfs_set_mode(inode, mode);
return error;
}