From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/xfs/xfs_ioctl.c | 1372 +++++++++++++++++++++++++++++++++--------------------------
1 files changed, 769 insertions(+), 603 deletions(-)
diff --git a/kernel/fs/xfs/xfs_ioctl.c b/kernel/fs/xfs/xfs_ioctl.c
index f123089..103fa83 100644
--- a/kernel/fs/xfs/xfs_ioctl.c
+++ b/kernel/fs/xfs/xfs_ioctl.c
@@ -11,9 +11,8 @@
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
-#include "xfs_ioctl.h"
-#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
+#include "xfs_iwalk.h"
#include "xfs_itable.h"
#include "xfs_error.h"
#include "xfs_attr.h"
@@ -25,7 +24,6 @@
#include "xfs_export.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
-#include "xfs_symlink.h"
#include "xfs_trans.h"
#include "xfs_acl.h"
#include "xfs_btree.h"
@@ -33,15 +31,15 @@
#include "xfs_fsmap.h"
#include "scrub/xfs_scrub.h"
#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_health.h"
+#include "xfs_reflink.h"
+#include "xfs_ioctl.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
-#include <linux/capability.h>
-#include <linux/cred.h>
-#include <linux/dcache.h>
#include <linux/mount.h>
#include <linux/namei.h>
-#include <linux/pagemap.h>
-#include <linux/slab.h>
-#include <linux/exportfs.h>
/*
* xfs_find_handle maps from userspace xfs_fsop_handlereq structure to
@@ -73,7 +71,7 @@
return -EBADF;
inode = file_inode(f.file);
} else {
- error = user_lpath((const char __user *)hreq->path, &path);
+ error = user_path_at(AT_FDCWD, hreq->path, 0, &path);
if (error)
return error;
inode = d_inode(path.dentry);
@@ -296,138 +294,173 @@
return error;
}
-int
-xfs_set_dmattrs(
- xfs_inode_t *ip,
- uint evmask,
- uint16_t state)
+/*
+ * Format an attribute and copy it out to the user's buffer.
+ * Take care to check values and protect against them changing later,
+ * we may be reading them directly out of a user buffer.
+ */
+static void
+xfs_ioc_attr_put_listent(
+ struct xfs_attr_list_context *context,
+ int flags,
+ unsigned char *name,
+ int namelen,
+ int valuelen)
{
- xfs_mount_t *mp = ip->i_mount;
- xfs_trans_t *tp;
- int error;
+ struct xfs_attrlist *alist = context->buffer;
+ struct xfs_attrlist_ent *aep;
+ int arraytop;
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
+ ASSERT(!context->seen_enough);
+ ASSERT(context->count >= 0);
+ ASSERT(context->count < (ATTR_MAX_VALUELEN/8));
+ ASSERT(context->firstu >= sizeof(*alist));
+ ASSERT(context->firstu <= context->bufsize);
- if (XFS_FORCED_SHUTDOWN(mp))
- return -EIO;
+ /*
+ * Only list entries in the right namespace.
+ */
+ if (context->attr_filter != (flags & XFS_ATTR_NSP_ONDISK_MASK))
+ return;
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
- if (error)
- return error;
+ arraytop = sizeof(*alist) +
+ context->count * sizeof(alist->al_offset[0]);
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+ /* decrement by the actual bytes used by the attr */
+ context->firstu -= round_up(offsetof(struct xfs_attrlist_ent, a_name) +
+ namelen + 1, sizeof(uint32_t));
+ if (context->firstu < arraytop) {
+ trace_xfs_attr_list_full(context);
+ alist->al_more = 1;
+ context->seen_enough = 1;
+ return;
+ }
- ip->i_d.di_dmevmask = evmask;
- ip->i_d.di_dmstate = state;
-
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- error = xfs_trans_commit(tp);
-
- return error;
+ aep = context->buffer + context->firstu;
+ aep->a_valuelen = valuelen;
+ memcpy(aep->a_name, name, namelen);
+ aep->a_name[namelen] = 0;
+ alist->al_offset[context->count++] = context->firstu;
+ alist->al_count = context->count;
+ trace_xfs_attr_list_add(context);
}
-STATIC int
-xfs_fssetdm_by_handle(
- struct file *parfilp,
- void __user *arg)
+static unsigned int
+xfs_attr_filter(
+ u32 ioc_flags)
{
- int error;
- struct fsdmidata fsd;
- xfs_fsop_setdm_handlereq_t dmhreq;
- struct dentry *dentry;
+ if (ioc_flags & XFS_IOC_ATTR_ROOT)
+ return XFS_ATTR_ROOT;
+ if (ioc_flags & XFS_IOC_ATTR_SECURE)
+ return XFS_ATTR_SECURE;
+ return 0;
+}
- if (!capable(CAP_MKNOD))
- return -EPERM;
- if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t)))
+static unsigned int
+xfs_attr_flags(
+ u32 ioc_flags)
+{
+ if (ioc_flags & XFS_IOC_ATTR_CREATE)
+ return XATTR_CREATE;
+ if (ioc_flags & XFS_IOC_ATTR_REPLACE)
+ return XATTR_REPLACE;
+ return 0;
+}
+
+int
+xfs_ioc_attr_list(
+ struct xfs_inode *dp,
+ void __user *ubuf,
+ size_t bufsize,
+ int flags,
+ struct xfs_attrlist_cursor __user *ucursor)
+{
+ struct xfs_attr_list_context context = { };
+ struct xfs_attrlist *alist;
+ void *buffer;
+ int error;
+
+ if (bufsize < sizeof(struct xfs_attrlist) ||
+ bufsize > XFS_XATTR_LIST_MAX)
+ return -EINVAL;
+
+ /*
+ * Reject flags, only allow namespaces.
+ */
+ if (flags & ~(XFS_IOC_ATTR_ROOT | XFS_IOC_ATTR_SECURE))
+ return -EINVAL;
+ if (flags == (XFS_IOC_ATTR_ROOT | XFS_IOC_ATTR_SECURE))
+ return -EINVAL;
+
+ /*
+ * Validate the cursor.
+ */
+ if (copy_from_user(&context.cursor, ucursor, sizeof(context.cursor)))
return -EFAULT;
+ if (context.cursor.pad1 || context.cursor.pad2)
+ return -EINVAL;
+ if (!context.cursor.initted &&
+ (context.cursor.hashval || context.cursor.blkno ||
+ context.cursor.offset))
+ return -EINVAL;
- error = mnt_want_write_file(parfilp);
+ buffer = kvzalloc(bufsize, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
+ /*
+ * Initialize the output buffer.
+ */
+ context.dp = dp;
+ context.resynch = 1;
+ context.attr_filter = xfs_attr_filter(flags);
+ context.buffer = buffer;
+ context.bufsize = round_down(bufsize, sizeof(uint32_t));
+ context.firstu = context.bufsize;
+ context.put_listent = xfs_ioc_attr_put_listent;
+
+ alist = context.buffer;
+ alist->al_count = 0;
+ alist->al_more = 0;
+ alist->al_offset[0] = context.bufsize;
+
+ error = xfs_attr_list(&context);
if (error)
- return error;
+ goto out_free;
- dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq);
- if (IS_ERR(dentry)) {
- mnt_drop_write_file(parfilp);
- return PTR_ERR(dentry);
- }
-
- if (IS_IMMUTABLE(d_inode(dentry)) || IS_APPEND(d_inode(dentry))) {
- error = -EPERM;
- goto out;
- }
-
- if (copy_from_user(&fsd, dmhreq.data, sizeof(fsd))) {
+ if (copy_to_user(ubuf, buffer, bufsize) ||
+ copy_to_user(ucursor, &context.cursor, sizeof(context.cursor)))
error = -EFAULT;
- goto out;
- }
-
- error = xfs_set_dmattrs(XFS_I(d_inode(dentry)), fsd.fsd_dmevmask,
- fsd.fsd_dmstate);
-
- out:
- mnt_drop_write_file(parfilp);
- dput(dentry);
+out_free:
+ kmem_free(buffer);
return error;
}
STATIC int
xfs_attrlist_by_handle(
struct file *parfilp,
- void __user *arg)
+ struct xfs_fsop_attrlist_handlereq __user *p)
{
- int error = -ENOMEM;
- attrlist_cursor_kern_t *cursor;
- struct xfs_fsop_attrlist_handlereq __user *p = arg;
- xfs_fsop_attrlist_handlereq_t al_hreq;
+ struct xfs_fsop_attrlist_handlereq al_hreq;
struct dentry *dentry;
- char *kbuf;
+ int error = -ENOMEM;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
+ if (copy_from_user(&al_hreq, p, sizeof(al_hreq)))
return -EFAULT;
- if (al_hreq.buflen < sizeof(struct attrlist) ||
- al_hreq.buflen > XFS_XATTR_LIST_MAX)
- return -EINVAL;
-
- /*
- * Reject flags, only allow namespaces.
- */
- if (al_hreq.flags & ~(ATTR_ROOT | ATTR_SECURE))
- return -EINVAL;
dentry = xfs_handlereq_to_dentry(parfilp, &al_hreq.hreq);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- kbuf = kmem_zalloc_large(al_hreq.buflen, KM_SLEEP);
- if (!kbuf)
- goto out_dput;
-
- cursor = (attrlist_cursor_kern_t *)&al_hreq.pos;
- error = xfs_attr_list(XFS_I(d_inode(dentry)), kbuf, al_hreq.buflen,
- al_hreq.flags, cursor);
- if (error)
- goto out_kfree;
-
- if (copy_to_user(&p->pos, cursor, sizeof(attrlist_cursor_kern_t))) {
- error = -EFAULT;
- goto out_kfree;
- }
-
- if (copy_to_user(al_hreq.buffer, kbuf, al_hreq.buflen))
- error = -EFAULT;
-
-out_kfree:
- kmem_free(kbuf);
-out_dput:
+ error = xfs_ioc_attr_list(XFS_I(d_inode(dentry)), al_hreq.buffer,
+ al_hreq.buflen, al_hreq.flags, &p->pos);
dput(dentry);
return error;
}
-int
+static int
xfs_attrmulti_attr_get(
struct inode *inode,
unsigned char *name,
@@ -435,28 +468,33 @@
uint32_t *len,
uint32_t flags)
{
- unsigned char *kbuf;
- int error = -EFAULT;
+ struct xfs_da_args args = {
+ .dp = XFS_I(inode),
+ .attr_filter = xfs_attr_filter(flags),
+ .attr_flags = xfs_attr_flags(flags),
+ .name = name,
+ .namelen = strlen(name),
+ .valuelen = *len,
+ };
+ int error;
if (*len > XFS_XATTR_SIZE_MAX)
return -EINVAL;
- kbuf = kmem_zalloc_large(*len, KM_SLEEP);
- if (!kbuf)
- return -ENOMEM;
- error = xfs_attr_get(XFS_I(inode), name, kbuf, (int *)len, flags);
+ error = xfs_attr_get(&args);
if (error)
goto out_kfree;
- if (copy_to_user(ubuf, kbuf, *len))
+ *len = args.valuelen;
+ if (copy_to_user(ubuf, args.value, args.valuelen))
error = -EFAULT;
out_kfree:
- kmem_free(kbuf);
+ kmem_free(args.value);
return error;
}
-int
+static int
xfs_attrmulti_attr_set(
struct inode *inode,
unsigned char *name,
@@ -464,38 +502,75 @@
uint32_t len,
uint32_t flags)
{
- unsigned char *kbuf;
+ struct xfs_da_args args = {
+ .dp = XFS_I(inode),
+ .attr_filter = xfs_attr_filter(flags),
+ .attr_flags = xfs_attr_flags(flags),
+ .name = name,
+ .namelen = strlen(name),
+ };
int error;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
- if (len > XFS_XATTR_SIZE_MAX)
- return -EINVAL;
- kbuf = memdup_user(ubuf, len);
- if (IS_ERR(kbuf))
- return PTR_ERR(kbuf);
+ if (ubuf) {
+ if (len > XFS_XATTR_SIZE_MAX)
+ return -EINVAL;
+ args.value = memdup_user(ubuf, len);
+ if (IS_ERR(args.value))
+ return PTR_ERR(args.value);
+ args.valuelen = len;
+ }
- error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
- if (!error)
- xfs_forget_acl(inode, name, flags);
- kfree(kbuf);
+ error = xfs_attr_set(&args);
+ if (!error && (flags & XFS_IOC_ATTR_ROOT))
+ xfs_forget_acl(inode, name);
+ kfree(args.value);
return error;
}
int
-xfs_attrmulti_attr_remove(
+xfs_ioc_attrmulti_one(
+ struct file *parfilp,
struct inode *inode,
- unsigned char *name,
+ uint32_t opcode,
+ void __user *uname,
+ void __user *value,
+ uint32_t *len,
uint32_t flags)
{
+ unsigned char *name;
int error;
- if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
- return -EPERM;
- error = xfs_attr_remove(XFS_I(inode), name, flags);
- if (!error)
- xfs_forget_acl(inode, name, flags);
+ if ((flags & XFS_IOC_ATTR_ROOT) && (flags & XFS_IOC_ATTR_SECURE))
+ return -EINVAL;
+
+ name = strndup_user(uname, MAXNAMELEN);
+ if (IS_ERR(name))
+ return PTR_ERR(name);
+
+ switch (opcode) {
+ case ATTR_OP_GET:
+ error = xfs_attrmulti_attr_get(inode, name, value, len, flags);
+ break;
+ case ATTR_OP_REMOVE:
+ value = NULL;
+ *len = 0;
+ /* fall through */
+ case ATTR_OP_SET:
+ error = mnt_want_write_file(parfilp);
+ if (error)
+ break;
+ error = xfs_attrmulti_attr_set(inode, name, value, *len, flags);
+ mnt_drop_write_file(parfilp);
+ break;
+ default:
+ error = -EINVAL;
+ break;
+ }
+
+ kfree(name);
return error;
}
@@ -509,7 +584,6 @@
xfs_fsop_attrmulti_handlereq_t am_hreq;
struct dentry *dentry;
unsigned int i, size;
- unsigned char *attr_name;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -535,56 +609,17 @@
goto out_dput;
}
- error = -ENOMEM;
- attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
- if (!attr_name)
- goto out_kfree_ops;
-
error = 0;
for (i = 0; i < am_hreq.opcount; i++) {
- ops[i].am_error = strncpy_from_user((char *)attr_name,
- ops[i].am_attrname, MAXNAMELEN);
- if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
- error = -ERANGE;
- if (ops[i].am_error < 0)
- break;
-
- switch (ops[i].am_opcode) {
- case ATTR_OP_GET:
- ops[i].am_error = xfs_attrmulti_attr_get(
- d_inode(dentry), attr_name,
- ops[i].am_attrvalue, &ops[i].am_length,
- ops[i].am_flags);
- break;
- case ATTR_OP_SET:
- ops[i].am_error = mnt_want_write_file(parfilp);
- if (ops[i].am_error)
- break;
- ops[i].am_error = xfs_attrmulti_attr_set(
- d_inode(dentry), attr_name,
- ops[i].am_attrvalue, ops[i].am_length,
- ops[i].am_flags);
- mnt_drop_write_file(parfilp);
- break;
- case ATTR_OP_REMOVE:
- ops[i].am_error = mnt_want_write_file(parfilp);
- if (ops[i].am_error)
- break;
- ops[i].am_error = xfs_attrmulti_attr_remove(
- d_inode(dentry), attr_name,
- ops[i].am_flags);
- mnt_drop_write_file(parfilp);
- break;
- default:
- ops[i].am_error = -EINVAL;
- }
+ ops[i].am_error = xfs_ioc_attrmulti_one(parfilp,
+ d_inode(dentry), ops[i].am_opcode,
+ ops[i].am_attrname, ops[i].am_attrvalue,
+ &ops[i].am_length, ops[i].am_flags);
}
if (copy_to_user(am_hreq.ops, ops, size))
error = -EFAULT;
- kfree(attr_name);
- out_kfree_ops:
kfree(ops);
out_dput:
dput(dentry);
@@ -594,23 +629,14 @@
int
xfs_ioc_space(
struct file *filp,
- unsigned int cmd,
xfs_flock64_t *bf)
{
struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
struct iattr iattr;
- enum xfs_prealloc_flags flags = 0;
+ enum xfs_prealloc_flags flags = XFS_PREALLOC_CLEAR;
uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
int error;
-
- /*
- * Only allow the sys admin to reserve space unless
- * unwritten extents are enabled.
- */
- if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) &&
- !capable(CAP_SYS_ADMIN))
- return -EPERM;
if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
return -EPERM;
@@ -620,6 +646,9 @@
if (!S_ISREG(inode->i_mode))
return -EINVAL;
+
+ if (xfs_is_always_cow_inode(ip))
+ return -EOPNOTSUPP;
if (filp->f_flags & O_DSYNC)
flags |= XFS_PREALLOC_SYNC;
@@ -634,6 +663,7 @@
error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
if (error)
goto out_unlock;
+ inode_dio_wait(inode);
switch (bf->l_whence) {
case 0: /*SEEK_SET*/
@@ -649,74 +679,22 @@
goto out_unlock;
}
- /*
- * length of <= 0 for resv/unresv/zero is invalid. length for
- * alloc/free is ignored completely and we have no idea what userspace
- * might have set it to, so set it to zero to allow range
- * checks to pass.
- */
- switch (cmd) {
- case XFS_IOC_ZERO_RANGE:
- case XFS_IOC_RESVSP:
- case XFS_IOC_RESVSP64:
- case XFS_IOC_UNRESVSP:
- case XFS_IOC_UNRESVSP64:
- if (bf->l_len <= 0) {
- error = -EINVAL;
- goto out_unlock;
- }
- break;
- default:
- bf->l_len = 0;
- break;
- }
-
- if (bf->l_start < 0 ||
- bf->l_start > inode->i_sb->s_maxbytes ||
- bf->l_start + bf->l_len < 0 ||
- bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) {
+ if (bf->l_start < 0 || bf->l_start > 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);
- 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);
- break;
- case XFS_IOC_UNRESVSP:
- case XFS_IOC_UNRESVSP64:
- error = xfs_free_file_space(ip, bf->l_start, bf->l_len);
- break;
- case XFS_IOC_ALLOCSP:
- 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),
- XFS_BMAPI_PREALLOC);
- if (error)
- goto out_unlock;
- }
-
- iattr.ia_valid = ATTR_SIZE;
- iattr.ia_size = bf->l_start;
-
- error = xfs_vn_setattr_size(file_dentry(filp), &iattr);
- break;
- default:
- ASSERT(0);
- error = -EINVAL;
+ if (bf->l_start > XFS_ISIZE(ip)) {
+ error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
+ bf->l_start - XFS_ISIZE(ip),
+ XFS_BMAPI_PREALLOC);
+ if (error)
+ goto out_unlock;
}
+ iattr.ia_valid = ATTR_SIZE;
+ iattr.ia_size = bf->l_start;
+ error = xfs_vn_setattr_size(file_dentry(filp), &iattr);
if (error)
goto out_unlock;
@@ -728,16 +706,45 @@
return error;
}
+/* Return 0 on success or positive error */
+int
+xfs_fsbulkstat_one_fmt(
+ struct xfs_ibulk *breq,
+ const struct xfs_bulkstat *bstat)
+{
+ struct xfs_bstat bs1;
+
+ xfs_bulkstat_to_bstat(breq->mp, &bs1, bstat);
+ if (copy_to_user(breq->ubuffer, &bs1, sizeof(bs1)))
+ return -EFAULT;
+ return xfs_ibulk_advance(breq, sizeof(struct xfs_bstat));
+}
+
+int
+xfs_fsinumbers_fmt(
+ struct xfs_ibulk *breq,
+ const struct xfs_inumbers *igrp)
+{
+ struct xfs_inogrp ig1;
+
+ xfs_inumbers_to_inogrp(&ig1, igrp);
+ if (copy_to_user(breq->ubuffer, &ig1, sizeof(struct xfs_inogrp)))
+ return -EFAULT;
+ return xfs_ibulk_advance(breq, sizeof(struct xfs_inogrp));
+}
+
STATIC int
-xfs_ioc_bulkstat(
+xfs_ioc_fsbulkstat(
xfs_mount_t *mp,
unsigned int cmd,
void __user *arg)
{
- xfs_fsop_bulkreq_t bulkreq;
- int count; /* # of records returned */
- xfs_ino_t inlast; /* last inode number */
- int done;
+ struct xfs_fsop_bulkreq bulkreq;
+ struct xfs_ibulk breq = {
+ .mp = mp,
+ .ocount = 0,
+ };
+ xfs_ino_t lastino;
int error;
/* done = 1 if there are more stats to get and if bulkstat */
@@ -749,79 +756,291 @@
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
- if (copy_from_user(&bulkreq, arg, sizeof(xfs_fsop_bulkreq_t)))
+ if (copy_from_user(&bulkreq, arg, sizeof(struct xfs_fsop_bulkreq)))
return -EFAULT;
- if (copy_from_user(&inlast, bulkreq.lastip, sizeof(__s64)))
+ if (copy_from_user(&lastino, bulkreq.lastip, sizeof(__s64)))
return -EFAULT;
- if ((count = bulkreq.icount) <= 0)
+ if (bulkreq.icount <= 0)
return -EINVAL;
if (bulkreq.ubuffer == NULL)
return -EINVAL;
- if (cmd == XFS_IOC_FSINUMBERS)
- error = xfs_inumbers(mp, &inlast, &count,
- bulkreq.ubuffer, xfs_inumbers_fmt);
- else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE)
- error = xfs_bulkstat_one(mp, inlast, bulkreq.ubuffer,
- sizeof(xfs_bstat_t), NULL, &done);
- else /* XFS_IOC_FSBULKSTAT */
- error = xfs_bulkstat(mp, &inlast, &count, xfs_bulkstat_one,
- sizeof(xfs_bstat_t), bulkreq.ubuffer,
- &done);
+ breq.ubuffer = bulkreq.ubuffer;
+ breq.icount = bulkreq.icount;
+
+ /*
+ * FSBULKSTAT_SINGLE expects that *lastip contains the inode number
+ * that we want to stat. However, FSINUMBERS and FSBULKSTAT expect
+ * that *lastip contains either zero or the number of the last inode to
+ * be examined by the previous call and return results starting with
+ * the next inode after that. The new bulk request back end functions
+ * take the inode to start with, so we have to compute the startino
+ * parameter from lastino to maintain correct function. lastino == 0
+ * is a special case because it has traditionally meant "first inode
+ * in filesystem".
+ */
+ if (cmd == XFS_IOC_FSINUMBERS) {
+ breq.startino = lastino ? lastino + 1 : 0;
+ error = xfs_inumbers(&breq, xfs_fsinumbers_fmt);
+ lastino = breq.startino - 1;
+ } else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE) {
+ breq.startino = lastino;
+ breq.icount = 1;
+ error = xfs_bulkstat_one(&breq, xfs_fsbulkstat_one_fmt);
+ } else { /* XFS_IOC_FSBULKSTAT */
+ breq.startino = lastino ? lastino + 1 : 0;
+ error = xfs_bulkstat(&breq, xfs_fsbulkstat_one_fmt);
+ lastino = breq.startino - 1;
+ }
if (error)
return error;
- if (bulkreq.ocount != NULL) {
- if (copy_to_user(bulkreq.lastip, &inlast,
- sizeof(xfs_ino_t)))
- return -EFAULT;
+ if (bulkreq.lastip != NULL &&
+ copy_to_user(bulkreq.lastip, &lastino, sizeof(xfs_ino_t)))
+ return -EFAULT;
- if (copy_to_user(bulkreq.ocount, &count, sizeof(count)))
- return -EFAULT;
+ if (bulkreq.ocount != NULL &&
+ copy_to_user(bulkreq.ocount, &breq.ocount, sizeof(__s32)))
+ return -EFAULT;
+
+ return 0;
+}
+
+/* Return 0 on success or positive error */
+static int
+xfs_bulkstat_fmt(
+ struct xfs_ibulk *breq,
+ const struct xfs_bulkstat *bstat)
+{
+ if (copy_to_user(breq->ubuffer, bstat, sizeof(struct xfs_bulkstat)))
+ return -EFAULT;
+ return xfs_ibulk_advance(breq, sizeof(struct xfs_bulkstat));
+}
+
+/*
+ * Check the incoming bulk request @hdr from userspace and initialize the
+ * internal @breq bulk request appropriately. Returns 0 if the bulk request
+ * should proceed; -ECANCELED if there's nothing to do; or the usual
+ * negative error code.
+ */
+static int
+xfs_bulk_ireq_setup(
+ struct xfs_mount *mp,
+ struct xfs_bulk_ireq *hdr,
+ struct xfs_ibulk *breq,
+ void __user *ubuffer)
+{
+ if (hdr->icount == 0 ||
+ (hdr->flags & ~XFS_BULK_IREQ_FLAGS_ALL) ||
+ memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved)))
+ return -EINVAL;
+
+ breq->startino = hdr->ino;
+ breq->ubuffer = ubuffer;
+ breq->icount = hdr->icount;
+ breq->ocount = 0;
+ breq->flags = 0;
+
+ /*
+ * The @ino parameter is a special value, so we must look it up here.
+ * We're not allowed to have IREQ_AGNO, and we only return one inode
+ * worth of data.
+ */
+ if (hdr->flags & XFS_BULK_IREQ_SPECIAL) {
+ if (hdr->flags & XFS_BULK_IREQ_AGNO)
+ return -EINVAL;
+
+ switch (hdr->ino) {
+ case XFS_BULK_IREQ_SPECIAL_ROOT:
+ hdr->ino = mp->m_sb.sb_rootino;
+ break;
+ default:
+ return -EINVAL;
+ }
+ breq->icount = 1;
}
+
+ /*
+ * The IREQ_AGNO flag means that we only want results from a given AG.
+ * If @hdr->ino is zero, we start iterating in that AG. If @hdr->ino is
+ * beyond the specified AG then we return no results.
+ */
+ if (hdr->flags & XFS_BULK_IREQ_AGNO) {
+ if (hdr->agno >= mp->m_sb.sb_agcount)
+ return -EINVAL;
+
+ if (breq->startino == 0)
+ breq->startino = XFS_AGINO_TO_INO(mp, hdr->agno, 0);
+ else if (XFS_INO_TO_AGNO(mp, breq->startino) < hdr->agno)
+ return -EINVAL;
+
+ breq->flags |= XFS_IBULK_SAME_AG;
+
+ /* Asking for an inode past the end of the AG? We're done! */
+ if (XFS_INO_TO_AGNO(mp, breq->startino) > hdr->agno)
+ return -ECANCELED;
+ } else if (hdr->agno)
+ return -EINVAL;
+
+ /* Asking for an inode past the end of the FS? We're done! */
+ if (XFS_INO_TO_AGNO(mp, breq->startino) >= mp->m_sb.sb_agcount)
+ return -ECANCELED;
+
+ return 0;
+}
+
+/*
+ * Update the userspace bulk request @hdr to reflect the end state of the
+ * internal bulk request @breq.
+ */
+static void
+xfs_bulk_ireq_teardown(
+ struct xfs_bulk_ireq *hdr,
+ struct xfs_ibulk *breq)
+{
+ hdr->ino = breq->startino;
+ hdr->ocount = breq->ocount;
+}
+
+/* Handle the v5 bulkstat ioctl. */
+STATIC int
+xfs_ioc_bulkstat(
+ struct xfs_mount *mp,
+ unsigned int cmd,
+ struct xfs_bulkstat_req __user *arg)
+{
+ struct xfs_bulk_ireq hdr;
+ struct xfs_ibulk breq = {
+ .mp = mp,
+ };
+ int error;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return -EIO;
+
+ if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr)))
+ return -EFAULT;
+
+ error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->bulkstat);
+ if (error == -ECANCELED)
+ goto out_teardown;
+ if (error < 0)
+ return error;
+
+ error = xfs_bulkstat(&breq, xfs_bulkstat_fmt);
+ if (error)
+ return error;
+
+out_teardown:
+ xfs_bulk_ireq_teardown(&hdr, &breq);
+ if (copy_to_user(&arg->hdr, &hdr, sizeof(hdr)))
+ return -EFAULT;
return 0;
}
STATIC int
-xfs_ioc_fsgeometry_v1(
- xfs_mount_t *mp,
- void __user *arg)
+xfs_inumbers_fmt(
+ struct xfs_ibulk *breq,
+ const struct xfs_inumbers *igrp)
{
- xfs_fsop_geom_t fsgeo;
- int error;
+ if (copy_to_user(breq->ubuffer, igrp, sizeof(struct xfs_inumbers)))
+ return -EFAULT;
+ return xfs_ibulk_advance(breq, sizeof(struct xfs_inumbers));
+}
- error = xfs_fs_geometry(&mp->m_sb, &fsgeo, 3);
+/* Handle the v5 inumbers ioctl. */
+STATIC int
+xfs_ioc_inumbers(
+ struct xfs_mount *mp,
+ unsigned int cmd,
+ struct xfs_inumbers_req __user *arg)
+{
+ struct xfs_bulk_ireq hdr;
+ struct xfs_ibulk breq = {
+ .mp = mp,
+ };
+ int error;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return -EIO;
+
+ if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr)))
+ return -EFAULT;
+
+ error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->inumbers);
+ if (error == -ECANCELED)
+ goto out_teardown;
+ if (error < 0)
+ return error;
+
+ error = xfs_inumbers(&breq, xfs_inumbers_fmt);
if (error)
return error;
- /*
- * Caller should have passed an argument of type
- * xfs_fsop_geom_v1_t. This is a proper subset of the
- * xfs_fsop_geom_t that xfs_fs_geometry() fills in.
- */
- if (copy_to_user(arg, &fsgeo, sizeof(xfs_fsop_geom_v1_t)))
+out_teardown:
+ xfs_bulk_ireq_teardown(&hdr, &breq);
+ if (copy_to_user(&arg->hdr, &hdr, sizeof(hdr)))
return -EFAULT;
+
return 0;
}
STATIC int
xfs_ioc_fsgeometry(
- xfs_mount_t *mp,
+ struct xfs_mount *mp,
+ void __user *arg,
+ int struct_version)
+{
+ struct xfs_fsop_geom fsgeo;
+ size_t len;
+
+ xfs_fs_geometry(&mp->m_sb, &fsgeo, struct_version);
+
+ if (struct_version <= 3)
+ len = sizeof(struct xfs_fsop_geom_v1);
+ else if (struct_version == 4)
+ len = sizeof(struct xfs_fsop_geom_v4);
+ else {
+ xfs_fsop_geom_health(mp, &fsgeo);
+ len = sizeof(fsgeo);
+ }
+
+ if (copy_to_user(arg, &fsgeo, len))
+ return -EFAULT;
+ return 0;
+}
+
+STATIC int
+xfs_ioc_ag_geometry(
+ struct xfs_mount *mp,
void __user *arg)
{
- xfs_fsop_geom_t fsgeo;
+ struct xfs_ag_geometry ageo;
int error;
- error = xfs_fs_geometry(&mp->m_sb, &fsgeo, 4);
+ if (copy_from_user(&ageo, arg, sizeof(ageo)))
+ return -EFAULT;
+ if (ageo.ag_flags)
+ return -EINVAL;
+ if (memchr_inv(&ageo.ag_reserved, 0, sizeof(ageo.ag_reserved)))
+ return -EINVAL;
+
+ error = xfs_ag_get_geometry(mp, ageo.ag_number, &ageo);
if (error)
return error;
- if (copy_to_user(arg, &fsgeo, sizeof(fsgeo)))
+ if (copy_to_user(arg, &ageo, sizeof(ageo)))
return -EFAULT;
return 0;
}
@@ -857,13 +1076,18 @@
xflags |= FS_XFLAG_NODUMP;
else
xflags &= ~FS_XFLAG_NODUMP;
+ if (flags & FS_DAX_FL)
+ xflags |= FS_XFLAG_DAX;
+ else
+ xflags &= ~FS_XFLAG_DAX;
return xflags;
}
STATIC unsigned int
xfs_di2lxflags(
- uint16_t di_flags)
+ uint16_t di_flags,
+ uint64_t di_flags2)
{
unsigned int flags = 0;
@@ -877,7 +1101,29 @@
flags |= FS_NOATIME_FL;
if (di_flags & XFS_DIFLAG_NODUMP)
flags |= FS_NODUMP_FL;
+ if (di_flags2 & XFS_DIFLAG2_DAX) {
+ flags |= FS_DAX_FL;
+ }
return flags;
+}
+
+static void
+xfs_fill_fsxattr(
+ struct xfs_inode *ip,
+ bool attr,
+ struct fsxattr *fa)
+{
+ struct xfs_ifork *ifp = attr ? ip->i_afp : &ip->i_df;
+
+ simple_fill_fsxattr(fa, xfs_ip2xflags(ip));
+ fa->fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
+ fa->fsx_cowextsize = ip->i_d.di_cowextsize <<
+ ip->i_mount->m_sb.sb_blocklog;
+ fa->fsx_projid = ip->i_d.di_projid;
+ if (ifp && (ifp->if_flags & XFS_IFEXTENTS))
+ fa->fsx_nextents = xfs_iext_count(ifp);
+ else
+ fa->fsx_nextents = xfs_ifork_nextents(ifp);
}
STATIC int
@@ -888,29 +1134,8 @@
{
struct fsxattr fa;
- memset(&fa, 0, sizeof(struct fsxattr));
-
xfs_ilock(ip, XFS_ILOCK_SHARED);
- fa.fsx_xflags = xfs_ip2xflags(ip);
- fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
- fa.fsx_cowextsize = ip->i_d.di_cowextsize <<
- ip->i_mount->m_sb.sb_blocklog;
- fa.fsx_projid = xfs_get_projid(ip);
-
- if (attr) {
- if (ip->i_afp) {
- if (ip->i_afp->if_flags & XFS_IFEXTENTS)
- fa.fsx_nextents = xfs_iext_count(ip->i_afp);
- else
- fa.fsx_nextents = ip->i_d.di_anextents;
- } else
- fa.fsx_nextents = 0;
- } else {
- if (ip->i_df.if_flags & XFS_IFEXTENTS)
- fa.fsx_nextents = xfs_iext_count(&ip->i_df);
- else
- fa.fsx_nextents = ip->i_d.di_nextents;
- }
+ xfs_fill_fsxattr(ip, attr, &fa);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (copy_to_user(arg, &fa, sizeof(fa)))
@@ -966,7 +1191,8 @@
unsigned int xflags)
{
uint64_t di_flags2 =
- (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK);
+ (ip->i_d.di_flags2 & (XFS_DIFLAG2_REFLINK |
+ XFS_DIFLAG2_BIGTIME));
if (xflags & FS_XFLAG_DAX)
di_flags2 |= XFS_DIFLAG2_DAX;
@@ -974,37 +1200,6 @@
di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
return di_flags2;
-}
-
-STATIC void
-xfs_diflags_to_linux(
- struct xfs_inode *ip)
-{
- struct inode *inode = VFS_I(ip);
- unsigned int xflags = xfs_ip2xflags(ip);
-
- if (xflags & FS_XFLAG_IMMUTABLE)
- inode->i_flags |= S_IMMUTABLE;
- else
- inode->i_flags &= ~S_IMMUTABLE;
- if (xflags & FS_XFLAG_APPEND)
- inode->i_flags |= S_APPEND;
- else
- inode->i_flags &= ~S_APPEND;
- if (xflags & FS_XFLAG_SYNC)
- inode->i_flags |= S_SYNC;
- else
- inode->i_flags &= ~S_SYNC;
- if (xflags & FS_XFLAG_NOATIME)
- inode->i_flags |= S_NOATIME;
- else
- inode->i_flags &= ~S_NOATIME;
-#if 0 /* disabled until the flag switching races are sorted out */
- if (xflags & FS_XFLAG_DAX)
- inode->i_flags |= S_DAX;
- else
- inode->i_flags &= ~S_DAX;
-#endif
}
static int
@@ -1017,7 +1212,7 @@
uint64_t di_flags2;
/* Can't change realtime flag if any extents are allocated. */
- if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
+ if ((ip->i_df.if_nextents || ip->i_delayed_blks) &&
XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME))
return -EINVAL;
@@ -1036,90 +1231,41 @@
if ((fa->fsx_xflags & FS_XFLAG_DAX) && xfs_is_reflink_inode(ip))
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 & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND))) &&
- !capable(CAP_LINUX_IMMUTABLE))
- return -EPERM;
-
/* diflags2 only valid for v3 inodes. */
di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
- if (di_flags2 && ip->i_d.di_version < 3)
+ if (di_flags2 && !xfs_sb_version_has_v3inode(&mp->m_sb))
return -EINVAL;
ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags);
ip->i_d.di_flags2 = di_flags2;
- xfs_diflags_to_linux(ip);
+ xfs_diflags_to_iflags(ip, false);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
return 0;
}
-/*
- * If we are changing DAX flags, we have to ensure the file is clean and any
- * cached objects in the address space are invalidated and removed. This
- * requires us to lock out other IO and page faults similar to a truncate
- * operation. The locks need to be held until the transaction has been committed
- * so that the cache invalidation is atomic with respect to the DAX flag
- * manipulation.
- */
-static int
-xfs_ioctl_setattr_dax_invalidate(
+static void
+xfs_ioctl_setattr_prepare_dax(
struct xfs_inode *ip,
- struct fsxattr *fa,
- int *join_flags)
+ struct fsxattr *fa)
{
- struct inode *inode = VFS_I(ip);
- struct super_block *sb = inode->i_sb;
- int error;
-
- *join_flags = 0;
-
- /*
- * It is only valid to set the DAX flag on regular files and
- * directories on filesystems where the block size is equal to the page
- * size. On directories it serves as an inherited hint so we don't
- * have to check the device for dax support or flush pagecache.
- */
- if (fa->fsx_xflags & FS_XFLAG_DAX) {
- if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
- return -EINVAL;
- if (S_ISREG(inode->i_mode) &&
- !bdev_dax_supported(xfs_find_bdev_for_inode(VFS_I(ip)),
- sb->s_blocksize))
- return -EINVAL;
- }
-
- /* If the DAX state is not changing, we have nothing to do here. */
- if ((fa->fsx_xflags & FS_XFLAG_DAX) && IS_DAX(inode))
- return 0;
- if (!(fa->fsx_xflags & FS_XFLAG_DAX) && !IS_DAX(inode))
- return 0;
+ struct xfs_mount *mp = ip->i_mount;
+ struct inode *inode = VFS_I(ip);
if (S_ISDIR(inode->i_mode))
- return 0;
+ return;
- /* lock, flush and invalidate mapping in preparation for flag change */
- xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
- error = filemap_write_and_wait(inode->i_mapping);
- if (error)
- goto out_unlock;
- error = invalidate_inode_pages2(inode->i_mapping);
- if (error)
- goto out_unlock;
+ if ((mp->m_flags & XFS_MOUNT_DAX_ALWAYS) ||
+ (mp->m_flags & XFS_MOUNT_DAX_NEVER))
+ return;
- *join_flags = XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL;
- return 0;
-
-out_unlock:
- xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
- return error;
-
+ if (((fa->fsx_xflags & FS_XFLAG_DAX) &&
+ !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)) ||
+ (!(fa->fsx_xflags & FS_XFLAG_DAX) &&
+ (ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)))
+ d_mark_dontcache(inode);
}
/*
@@ -1127,17 +1273,10 @@
* 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.
- *
- * The inode might already be IO locked on call. If this is the case, it is
- * indicated in @join_flags and we take full responsibility for ensuring they
- * are unlocked from now on. Hence if we have an error here, we still have to
- * unlock them. Otherwise, once they are joined to the transaction, they will
- * be unlocked on commit/cancel.
*/
static struct xfs_trans *
xfs_ioctl_setattr_get_trans(
- struct xfs_inode *ip,
- int join_flags)
+ struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
@@ -1151,11 +1290,10 @@
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
if (error)
- return ERR_PTR(error);
+ goto out_unlock;
xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
- join_flags = 0;
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
/*
* CAP_FOWNER overrides the following restrictions:
@@ -1176,8 +1314,6 @@
out_cancel:
xfs_trans_cancel(tp);
out_unlock:
- if (join_flags)
- xfs_iunlock(ip, join_flags);
return ERR_PTR(error);
}
@@ -1203,39 +1339,31 @@
struct fsxattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
+ xfs_extlen_t size;
+ xfs_fsblock_t extsize_fsb;
- if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(VFS_I(ip)->i_mode))
- return -EINVAL;
-
- if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
- !S_ISDIR(VFS_I(ip)->i_mode))
- return -EINVAL;
-
- if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_d.di_nextents &&
+ if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents &&
((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
return -EINVAL;
- if (fa->fsx_extsize != 0) {
- xfs_extlen_t size;
- xfs_fsblock_t extsize_fsb;
+ if (fa->fsx_extsize == 0)
+ return 0;
- extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
- if (extsize_fsb > MAXEXTLEN)
+ 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 & FS_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 (XFS_IS_REALTIME_INODE(ip) ||
- (fa->fsx_xflags & FS_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;
- } else
- fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT);
+ if (fa->fsx_extsize % size)
+ return -EINVAL;
return 0;
}
@@ -1261,33 +1389,28 @@
struct fsxattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
+ xfs_extlen_t size;
+ xfs_fsblock_t cowextsize_fsb;
if (!(fa->fsx_xflags & FS_XFLAG_COWEXTSIZE))
return 0;
- if (!xfs_sb_version_hasreflink(&ip->i_mount->m_sb) ||
- ip->i_d.di_version != 3)
+ if (!xfs_sb_version_hasreflink(&ip->i_mount->m_sb))
return -EINVAL;
- if (!S_ISREG(VFS_I(ip)->i_mode) && !S_ISDIR(VFS_I(ip)->i_mode))
+ if (fa->fsx_cowextsize == 0)
+ return 0;
+
+ cowextsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_cowextsize);
+ if (cowextsize_fsb > MAXEXTLEN)
return -EINVAL;
- if (fa->fsx_cowextsize != 0) {
- xfs_extlen_t size;
- xfs_fsblock_t cowextsize_fsb;
+ size = mp->m_sb.sb_blocksize;
+ if (cowextsize_fsb > mp->m_sb.sb_agblocks / 2)
+ return -EINVAL;
- cowextsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_cowextsize);
- if (cowextsize_fsb > MAXEXTLEN)
- return -EINVAL;
-
- size = mp->m_sb.sb_blocksize;
- if (cowextsize_fsb > mp->m_sb.sb_agblocks / 2)
- return -EINVAL;
-
- if (fa->fsx_cowextsize % size)
- return -EINVAL;
- } else
- fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE;
+ if (fa->fsx_cowextsize % size)
+ return -EINVAL;
return 0;
}
@@ -1301,21 +1424,6 @@
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 & FS_XFLAG_PROJINHERIT) !=
- (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT))
- return -EINVAL;
-
return 0;
}
@@ -1324,13 +1432,12 @@
xfs_inode_t *ip,
struct fsxattr *fa)
{
+ struct fsxattr old_fa;
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
- struct xfs_dquot *udqp = NULL;
struct xfs_dquot *pdqp = NULL;
struct xfs_dquot *olddquot = NULL;
int code;
- int join_flags = 0;
trace_xfs_ioctl_setattr(ip);
@@ -1347,38 +1454,33 @@
* because the i_*dquot fields will get updated anyway.
*/
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);
+ code = xfs_qm_vop_dqalloc(ip, VFS_I(ip)->i_uid,
+ VFS_I(ip)->i_gid, fa->fsx_projid,
+ XFS_QMOPT_PQUOTA, NULL, NULL, &pdqp);
if (code)
return code;
}
- /*
- * Changing DAX config may require inode locking for mapping
- * invalidation. These need to be held all the way to transaction commit
- * or cancel time, so need to be passed through to
- * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
- * appropriately.
- */
- code = xfs_ioctl_setattr_dax_invalidate(ip, fa, &join_flags);
- if (code)
- goto error_free_dquots;
+ xfs_ioctl_setattr_prepare_dax(ip, fa);
- tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
+ tp = xfs_ioctl_setattr_get_trans(ip);
if (IS_ERR(tp)) {
code = PTR_ERR(tp);
goto error_free_dquots;
}
-
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,
+ ip->i_d.di_projid != fa->fsx_projid) {
+ code = xfs_qm_vop_chown_reserve(tp, ip, NULL, NULL, pdqp,
capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0);
if (code) /* out of quota */
goto error_trans_cancel;
}
+
+ xfs_fill_fsxattr(ip, false, &old_fa);
+ code = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, fa);
+ if (code)
+ goto error_trans_cancel;
code = xfs_ioctl_setattr_check_extsize(ip, fa);
if (code)
@@ -1405,13 +1507,12 @@
VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
/* Change the ownerships and register project quota modifications */
- if (xfs_get_projid(ip) != fa->fsx_projid) {
+ if (ip->i_d.di_projid != 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);
+ ip->i_d.di_projid = fa->fsx_projid;
}
/*
@@ -1423,7 +1524,7 @@
ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
else
ip->i_d.di_extsize = 0;
- if (ip->i_d.di_version == 3 &&
+ if (xfs_sb_version_has_v3inode(&mp->m_sb) &&
(ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
ip->i_d.di_cowextsize = fa->fsx_cowextsize >>
mp->m_sb.sb_blocklog;
@@ -1436,7 +1537,6 @@
* Release any dquot(s) the inode had kept before chown.
*/
xfs_qm_dqrele(olddquot);
- xfs_qm_dqrele(udqp);
xfs_qm_dqrele(pdqp);
return code;
@@ -1444,7 +1544,6 @@
error_trans_cancel:
xfs_trans_cancel(tp);
error_free_dquots:
- xfs_qm_dqrele(udqp);
xfs_qm_dqrele(pdqp);
return code;
}
@@ -1476,7 +1575,7 @@
{
unsigned int flags;
- flags = xfs_di2lxflags(ip->i_d.di_flags);
+ flags = xfs_di2lxflags(ip->i_d.di_flags, ip->i_d.di_flags2);
if (copy_to_user(arg, &flags, sizeof(flags)))
return -EFAULT;
return 0;
@@ -1490,8 +1589,8 @@
{
struct xfs_trans *tp;
struct fsxattr fa;
+ struct fsxattr old_fa;
unsigned int flags;
- int join_flags = 0;
int error;
if (copy_from_user(&flags, arg, sizeof(flags)))
@@ -1499,7 +1598,7 @@
if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
FS_NOATIME_FL | FS_NODUMP_FL | \
- FS_SYNC_FL))
+ FS_SYNC_FL | FS_DAX_FL))
return -EOPNOTSUPP;
fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
@@ -1508,20 +1607,18 @@
if (error)
return error;
- /*
- * Changing DAX config may require inode locking for mapping
- * invalidation. These need to be held all the way to transaction commit
- * or cancel time, so need to be passed through to
- * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
- * appropriately.
- */
- error = xfs_ioctl_setattr_dax_invalidate(ip, &fa, &join_flags);
- if (error)
- goto out_drop_write;
+ xfs_ioctl_setattr_prepare_dax(ip, &fa);
- tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
+ tp = xfs_ioctl_setattr_get_trans(ip);
if (IS_ERR(tp)) {
error = PTR_ERR(tp);
+ goto out_drop_write;
+ }
+
+ xfs_fill_fsxattr(ip, false, &old_fa);
+ error = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, &fa);
+ if (error) {
+ xfs_trans_cancel(tp);
goto out_drop_write;
}
@@ -1592,10 +1689,10 @@
if (bmx.bmv_count < 2)
return -EINVAL;
- if (bmx.bmv_count > ULONG_MAX / recsize)
+ if (bmx.bmv_count >= INT_MAX / recsize)
return -ENOMEM;
- buf = kmem_zalloc_large(bmx.bmv_count * sizeof(*buf), 0);
+ buf = kvzalloc(bmx.bmv_count * sizeof(*buf), GFP_KERNEL);
if (!buf)
return -ENOMEM;
@@ -1620,39 +1717,17 @@
return error;
}
-struct getfsmap_info {
- struct xfs_mount *mp;
- struct fsmap_head __user *data;
- unsigned int idx;
- __u32 last_flags;
-};
-
-STATIC int
-xfs_getfsmap_format(struct xfs_fsmap *xfm, void *priv)
-{
- struct getfsmap_info *info = priv;
- struct fsmap fm;
-
- trace_xfs_getfsmap_mapping(info->mp, xfm);
-
- info->last_flags = xfm->fmr_flags;
- xfs_fsmap_from_internal(&fm, xfm);
- if (copy_to_user(&info->data->fmh_recs[info->idx++], &fm,
- sizeof(struct fsmap)))
- return -EFAULT;
-
- return 0;
-}
-
STATIC int
xfs_ioc_getfsmap(
struct xfs_inode *ip,
struct fsmap_head __user *arg)
{
- struct getfsmap_info info = { NULL };
struct xfs_fsmap_head xhead = {0};
struct fsmap_head head;
- bool aborted = false;
+ struct fsmap *recs;
+ unsigned int count;
+ __u32 last_flags = 0;
+ bool done = false;
int error;
if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
@@ -1664,38 +1739,112 @@
sizeof(head.fmh_keys[1].fmr_reserved)))
return -EINVAL;
+ /*
+ * Use an internal memory buffer so that we don't have to copy fsmap
+ * data to userspace while holding locks. Start by trying to allocate
+ * up to 128k for the buffer, but fall back to a single page if needed.
+ */
+ count = min_t(unsigned int, head.fmh_count,
+ 131072 / sizeof(struct fsmap));
+ recs = kvzalloc(count * sizeof(struct fsmap), GFP_KERNEL);
+ if (!recs) {
+ count = min_t(unsigned int, head.fmh_count,
+ PAGE_SIZE / sizeof(struct fsmap));
+ recs = kvzalloc(count * sizeof(struct fsmap), GFP_KERNEL);
+ if (!recs)
+ return -ENOMEM;
+ }
+
xhead.fmh_iflags = head.fmh_iflags;
- xhead.fmh_count = head.fmh_count;
xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]);
xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]);
trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]);
- info.mp = ip->i_mount;
- info.data = arg;
- error = xfs_getfsmap(ip->i_mount, &xhead, xfs_getfsmap_format, &info);
- if (error == XFS_BTREE_QUERY_RANGE_ABORT) {
- error = 0;
- aborted = true;
- } else if (error)
- return error;
+ head.fmh_entries = 0;
+ do {
+ struct fsmap __user *user_recs;
+ struct fsmap *last_rec;
- /* If we didn't abort, set the "last" flag in the last fmx */
- if (!aborted && info.idx) {
- info.last_flags |= FMR_OF_LAST;
- if (copy_to_user(&info.data->fmh_recs[info.idx - 1].fmr_flags,
- &info.last_flags, sizeof(info.last_flags)))
- return -EFAULT;
+ user_recs = &arg->fmh_recs[head.fmh_entries];
+ xhead.fmh_entries = 0;
+ xhead.fmh_count = min_t(unsigned int, count,
+ head.fmh_count - head.fmh_entries);
+
+ /* Run query, record how many entries we got. */
+ error = xfs_getfsmap(ip->i_mount, &xhead, recs);
+ switch (error) {
+ case 0:
+ /*
+ * There are no more records in the result set. Copy
+ * whatever we got to userspace and break out.
+ */
+ done = true;
+ break;
+ case -ECANCELED:
+ /*
+ * The internal memory buffer is full. Copy whatever
+ * records we got to userspace and go again if we have
+ * not yet filled the userspace buffer.
+ */
+ error = 0;
+ break;
+ default:
+ goto out_free;
+ }
+ head.fmh_entries += xhead.fmh_entries;
+ head.fmh_oflags = xhead.fmh_oflags;
+
+ /*
+ * If the caller wanted a record count or there aren't any
+ * new records to return, we're done.
+ */
+ if (head.fmh_count == 0 || xhead.fmh_entries == 0)
+ break;
+
+ /* Copy all the records we got out to userspace. */
+ if (copy_to_user(user_recs, recs,
+ xhead.fmh_entries * sizeof(struct fsmap))) {
+ error = -EFAULT;
+ goto out_free;
+ }
+
+ /* Remember the last record flags we copied to userspace. */
+ last_rec = &recs[xhead.fmh_entries - 1];
+ last_flags = last_rec->fmr_flags;
+
+ /* Set up the low key for the next iteration. */
+ xfs_fsmap_to_internal(&xhead.fmh_keys[0], last_rec);
+ trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
+ } while (!done && head.fmh_entries < head.fmh_count);
+
+ /*
+ * If there are no more records in the query result set and we're not
+ * in counting mode, mark the last record returned with the LAST flag.
+ */
+ if (done && head.fmh_count > 0 && head.fmh_entries > 0) {
+ struct fsmap __user *user_rec;
+
+ last_flags |= FMR_OF_LAST;
+ user_rec = &arg->fmh_recs[head.fmh_entries - 1];
+
+ if (copy_to_user(&user_rec->fmr_flags, &last_flags,
+ sizeof(last_flags))) {
+ error = -EFAULT;
+ goto out_free;
+ }
}
/* copy back header */
- head.fmh_entries = xhead.fmh_entries;
- head.fmh_oflags = xhead.fmh_oflags;
- if (copy_to_user(arg, &head, sizeof(struct fsmap_head)))
- return -EFAULT;
+ if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) {
+ error = -EFAULT;
+ goto out_free;
+ }
- return 0;
+out_free:
+ kmem_free(recs);
+ return error;
}
STATIC int
@@ -1884,6 +2033,41 @@
return error;
}
+static inline int
+xfs_fs_eofblocks_from_user(
+ struct xfs_fs_eofblocks *src,
+ struct xfs_eofblocks *dst)
+{
+ if (src->eof_version != XFS_EOFBLOCKS_VERSION)
+ return -EINVAL;
+
+ if (src->eof_flags & ~XFS_EOF_FLAGS_VALID)
+ return -EINVAL;
+
+ if (memchr_inv(&src->pad32, 0, sizeof(src->pad32)) ||
+ memchr_inv(src->pad64, 0, sizeof(src->pad64)))
+ return -EINVAL;
+
+ dst->eof_flags = src->eof_flags;
+ dst->eof_prid = src->eof_prid;
+ dst->eof_min_file_size = src->eof_min_file_size;
+
+ dst->eof_uid = INVALID_UID;
+ if (src->eof_flags & XFS_EOF_FLAGS_UID) {
+ dst->eof_uid = make_kuid(current_user_ns(), src->eof_uid);
+ if (!uid_valid(dst->eof_uid))
+ return -EINVAL;
+ }
+
+ dst->eof_gid = INVALID_GID;
+ if (src->eof_flags & XFS_EOF_FLAGS_GID) {
+ dst->eof_gid = make_kgid(current_user_ns(), src->eof_gid);
+ if (!gid_valid(dst->eof_gid))
+ return -EINVAL;
+ }
+ return 0;
+}
+
/*
* Note: some of the ioctl's return positive numbers as a
* byte count indicating success, such as readlink_by_handle.
@@ -1913,24 +2097,17 @@
return xfs_ioc_setlabel(filp, mp, arg);
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
- case XFS_IOC_RESVSP:
- case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
- case XFS_IOC_FREESP64:
- case XFS_IOC_RESVSP64:
- case XFS_IOC_UNRESVSP64:
- case XFS_IOC_ZERO_RANGE: {
+ case XFS_IOC_FREESP64: {
xfs_flock64_t bf;
if (copy_from_user(&bf, arg, sizeof(bf)))
return -EFAULT;
- return xfs_ioc_space(filp, cmd, &bf);
+ return xfs_ioc_space(filp, &bf);
}
case XFS_IOC_DIOINFO: {
- struct dioattr da;
- xfs_buftarg_t *target =
- XFS_IS_REALTIME_INODE(ip) ?
- mp->m_rtdev_targp : mp->m_ddev_targp;
+ struct xfs_buftarg *target = xfs_inode_buftarg(ip);
+ struct dioattr da;
da.d_mem = da.d_miniosz = target->bt_logical_sectorsize;
da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
@@ -1943,13 +2120,22 @@
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
+ return xfs_ioc_fsbulkstat(mp, cmd, arg);
+
+ case XFS_IOC_BULKSTAT:
return xfs_ioc_bulkstat(mp, cmd, arg);
+ case XFS_IOC_INUMBERS:
+ return xfs_ioc_inumbers(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
- return xfs_ioc_fsgeometry_v1(mp, arg);
-
+ return xfs_ioc_fsgeometry(mp, arg, 3);
+ case XFS_IOC_FSGEOMETRY_V4:
+ return xfs_ioc_fsgeometry(mp, arg, 4);
case XFS_IOC_FSGEOMETRY:
- return xfs_ioc_fsgeometry(mp, arg);
+ return xfs_ioc_fsgeometry(mp, arg, 5);
+
+ case XFS_IOC_AG_GEOMETRY:
+ return xfs_ioc_ag_geometry(mp, arg);
case XFS_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *)arg);
@@ -1964,22 +2150,6 @@
return xfs_ioc_getxflags(ip, arg);
case XFS_IOC_SETXFLAGS:
return xfs_ioc_setxflags(ip, filp, arg);
-
- case XFS_IOC_FSSETDM: {
- struct fsdmidata dmi;
-
- if (copy_from_user(&dmi, arg, sizeof(dmi)))
- return -EFAULT;
-
- error = mnt_want_write_file(filp);
- if (error)
- return error;
-
- error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
- dmi.fsd_dmstate);
- mnt_drop_write_file(filp);
- return error;
- }
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
@@ -2008,8 +2178,6 @@
return -EFAULT;
return xfs_open_by_handle(filp, &hreq);
}
- case XFS_IOC_FSSETDM_BY_HANDLE:
- return xfs_fssetdm_by_handle(filp, arg);
case XFS_IOC_READLINK_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
@@ -2040,9 +2208,7 @@
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
- error = xfs_fs_counts(mp, &out);
- if (error)
- return error;
+ xfs_fs_counts(mp, &out);
if (copy_to_user(arg, &out, sizeof(out)))
return -EFAULT;
--
Gitblit v1.6.2