#include "util.h"
#include "log.h"
#include "inode.h"
-#include "ops_address.h"
+#include "trace_gfs2.h"
#define BFITNOENT ((u32)~0)
#define NO_BLOCK ((u64)~0)
{
u64 tmp;
static const u64 search[] = {
- [0] = 0xffffffffffffffff,
- [1] = 0xaaaaaaaaaaaaaaaa,
- [2] = 0x5555555555555555,
- [3] = 0x0000000000000000,
+ [0] = 0xffffffffffffffffULL,
+ [1] = 0xaaaaaaaaaaaaaaaaULL,
+ [2] = 0x5555555555555555ULL,
+ [3] = 0x0000000000000000ULL,
};
tmp = le64_to_cpu(*ptr) ^ search[state];
tmp &= (tmp >> 1);
* always aligned to a 64 bit boundary.
*
* The size of the buffer is in bytes, but is it assumed that it is
- * always ok to to read a complete multiple of 64 bits at the end
+ * always ok to read a complete multiple of 64 bits at the end
* of the block in case the end is no aligned to a natural boundary.
*
* Return: the block number (bitmap buffer scope) that was found
*/
-u32 gfs2_bitfit(const u8 *buf, const unsigned int len, u32 goal, u8 state)
+static u32 gfs2_bitfit(const u8 *buf, const unsigned int len,
+ u32 goal, u8 state)
{
u32 spoint = (goal << 1) & ((8*sizeof(u64)) - 1);
const __le64 *ptr = ((__le64 *)buf) + (goal >> 5);
const __le64 *end = (__le64 *)(buf + ALIGN(len, sizeof(u64)));
u64 tmp;
- u64 mask = 0x5555555555555555;
+ u64 mask = 0x5555555555555555ULL;
u32 bit;
BUG_ON(state > 3);
tmp = gfs2_bit_search(ptr, mask, state);
ptr++;
while(tmp == 0 && ptr < end) {
- tmp = gfs2_bit_search(ptr, 0x5555555555555555, state);
+ tmp = gfs2_bit_search(ptr, 0x5555555555555555ULL, state);
ptr++;
}
/* Mask off any bits which are more than len bytes from the start */
if (tmp == 0)
return BFITNOENT;
ptr--;
- bit = fls64(tmp);
- bit--; /* fls64 always adds one to the bit count */
+ bit = __ffs64(tmp);
bit /= 2; /* two bits per entry in the bitmap */
return (((const unsigned char *)ptr - buf) * GFS2_NBBY) + bit;
}
}
tmp = rgd->rd_data - rgd->rd_free - rgd->rd_dinodes;
- if (count[1] + count[2] != tmp) {
+ if (count[1] != tmp) {
if (gfs2_consist_rgrpd(rgd))
fs_err(sdp, "used data mismatch: %u != %u\n",
count[1], tmp);
return;
}
- if (count[3] != rgd->rd_dinodes) {
+ if (count[2] + count[3] != rgd->rd_dinodes) {
if (gfs2_consist_rgrpd(rgd))
fs_err(sdp, "used metadata mismatch: %u != %u\n",
- count[3], rgd->rd_dinodes);
+ count[2] + count[3], rgd->rd_dinodes);
return;
}
-
- if (count[2] > count[3]) {
- if (gfs2_consist_rgrpd(rgd))
- fs_err(sdp, "unlinked inodes > inodes: %u\n",
- count[2]);
- return;
- }
-
}
static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
for (x = 0; x < length; x++) {
bi = rgd->rd_bits + x;
+ bi->bi_flags = 0;
/* small rgrp; bitmap stored completely in header block */
if (length == 1) {
bytes = bytes_left;
rgd->rd_gl->gl_object = rgd;
rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
- rgd->rd_flags |= GFS2_RDF_CHECK;
return error;
}
u64 rgrp_count = ip->i_disksize;
int error;
- if (do_div(rgrp_count, sizeof(struct gfs2_rindex))) {
- gfs2_consist_inode(ip);
- return -EIO;
- }
-
+ do_div(rgrp_count, sizeof(struct gfs2_rindex));
clear_rgrpdi(sdp);
file_ra_state_init(&ra_state, inode->i_mapping);
u32 rg_flags;
rg_flags = be32_to_cpu(str->rg_flags);
- if (rg_flags & GFS2_RGF_NOALLOC)
- rgd->rd_flags |= GFS2_RDF_NOALLOC;
- else
- rgd->rd_flags &= ~GFS2_RDF_NOALLOC;
+ rg_flags &= ~GFS2_RDF_MASK;
+ rgd->rd_flags &= GFS2_RDF_MASK;
+ rgd->rd_flags |= rg_flags;
rgd->rd_free = be32_to_cpu(str->rg_free);
rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes);
rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration);
static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
{
struct gfs2_rgrp *str = buf;
- u32 rg_flags = 0;
- if (rgd->rd_flags & GFS2_RDF_NOALLOC)
- rg_flags |= GFS2_RGF_NOALLOC;
- str->rg_flags = cpu_to_be32(rg_flags);
+ str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK);
str->rg_free = cpu_to_be32(rgd->rd_free);
str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes);
str->__pad = cpu_to_be32(0);
}
if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) {
+ for (x = 0; x < length; x++)
+ clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags);
gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
- rgd->rd_flags |= GFS2_RDF_UPTODATE;
+ rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
}
spin_lock(&sdp->sd_rindex_spin);
struct super_block *sb = sdp->sd_vfs;
struct block_device *bdev = sb->s_bdev;
const unsigned int sects_per_blk = sdp->sd_sb.sb_bsize /
- bdev_hardsect_size(sb->s_bdev);
+ bdev_logical_block_size(sb->s_bdev);
u64 blk;
sector_t start = 0;
sector_t nr_sects = 0;
goto start_new_extent;
if ((start + nr_sects) != blk) {
rv = blkdev_issue_discard(bdev, start,
- nr_sects, GFP_NOFS);
+ nr_sects, GFP_NOFS,
+ DISCARD_FL_BARRIER);
if (rv)
goto fail;
nr_sects = 0;
}
}
if (nr_sects) {
- rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS);
+ rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS,
+ DISCARD_FL_BARRIER);
if (rv)
goto fail;
}
continue;
if (sdp->sd_args.ar_discard)
gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bi);
+ clear_bit(GBF_FULL, &bi->bi_flags);
memcpy(bi->bi_clone + bi->bi_offset,
bi->bi_bh->b_data + bi->bi_offset, bi->bi_len);
}
struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
{
BUG_ON(ip->i_alloc != NULL);
- ip->i_alloc = kzalloc(sizeof(struct gfs2_alloc), GFP_KERNEL);
+ ip->i_alloc = kzalloc(sizeof(struct gfs2_alloc), GFP_NOFS);
return ip->i_alloc;
}
struct gfs2_sbd *sdp = rgd->rd_sbd;
int ret = 0;
- if (rgd->rd_flags & GFS2_RDF_NOALLOC)
+ if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR))
return 0;
spin_lock(&sdp->sd_rindex_spin);
* Returns: The inode, if one has been found
*/
-static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
+static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked,
+ u64 skip)
{
struct inode *inode;
u32 goal = 0, block;
goal++;
if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
continue;
+ if (no_addr == skip)
+ continue;
*last_unlinked = no_addr;
inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
no_addr, -1, 1);
if (try_rgrp_fit(rgd, al))
goto out;
if (rgd->rd_flags & GFS2_RDF_CHECK)
- inode = try_rgrp_unlink(rgd, last_unlinked);
+ inode = try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
if (!rg_locked)
gfs2_glock_dq_uninit(&al->al_rgd_gh);
if (inode)
if (try_rgrp_fit(rgd, al))
goto out;
if (rgd->rd_flags & GFS2_RDF_CHECK)
- inode = try_rgrp_unlink(rgd, last_unlinked);
+ inode = try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
if (!rg_locked)
gfs2_glock_dq_uninit(&al->al_rgd_gh);
if (inode)
* Returns: The block type (GFS2_BLKST_*)
*/
-unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block)
+static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block)
{
struct gfs2_bitmap *bi = NULL;
u32 length, rgrp_block, buf_block;
{
struct gfs2_bitmap *bi = NULL;
const u32 length = rgd->rd_length;
- u32 blk = 0;
+ u32 blk = BFITNOENT;
unsigned int buf, x;
const unsigned int elen = *n;
- const u8 *buffer;
+ const u8 *buffer = NULL;
*n = 0;
/* Find bitmap block that contains bits for goal block */
for (buf = 0; buf < length; buf++) {
bi = rgd->rd_bits + buf;
- if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY)
- break;
+ /* Convert scope of "goal" from rgrp-wide to within found bit block */
+ if (goal < (bi->bi_start + bi->bi_len) * GFS2_NBBY) {
+ goal -= bi->bi_start * GFS2_NBBY;
+ goto do_search;
+ }
}
+ buf = 0;
+ goal = 0;
- gfs2_assert(rgd->rd_sbd, buf < length);
-
- /* Convert scope of "goal" from rgrp-wide to within found bit block */
- goal -= bi->bi_start * GFS2_NBBY;
-
+do_search:
/* Search (up to entire) bitmap in this rgrp for allocatable block.
"x <= length", instead of "x < length", because we typically start
the search in the middle of a bit block, but if we can't find an
allocatable block anywhere else, we want to be able wrap around and
search in the first part of our first-searched bit block. */
for (x = 0; x <= length; x++) {
+ bi = rgd->rd_bits + buf;
+
+ if (test_bit(GBF_FULL, &bi->bi_flags) &&
+ (old_state == GFS2_BLKST_FREE))
+ goto skip;
+
/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
bitmaps, so we must search the originals for that. */
buffer = bi->bi_bh->b_data + bi->bi_offset;
if (blk != BFITNOENT)
break;
+ if ((goal == 0) && (old_state == GFS2_BLKST_FREE))
+ set_bit(GBF_FULL, &bi->bi_flags);
+
/* Try next bitmap block (wrap back to rgrp header if at end) */
- buf = (buf + 1) % length;
- bi = rgd->rd_bits + buf;
+skip:
+ buf++;
+ buf %= length;
goal = 0;
}
- if (blk != BFITNOENT && old_state != new_state) {
- *n = 1;
- gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
+ if (blk == BFITNOENT)
+ return blk;
+ *n = 1;
+ if (old_state == new_state)
+ goto out;
+
+ gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
+ gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
+ bi->bi_len, blk, new_state);
+ goal = blk;
+ while (*n < elen) {
+ goal++;
+ if (goal >= (bi->bi_len * GFS2_NBBY))
+ break;
+ if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) !=
+ GFS2_BLKST_FREE)
+ break;
gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
- bi->bi_len, blk, new_state);
- goal = blk;
- while (*n < elen) {
- goal++;
- if (goal >= (bi->bi_len * GFS2_NBBY))
- break;
- if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) !=
- GFS2_BLKST_FREE)
- break;
- gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone,
- bi->bi_offset, bi->bi_len, goal,
- new_state);
- (*n)++;
- }
+ bi->bi_len, goal, new_state);
+ (*n)++;
}
-
- return (blk == BFITNOENT) ? blk : (bi->bi_start * GFS2_NBBY) + blk;
+out:
+ return (bi->bi_start * GFS2_NBBY) + blk;
}
/**
}
/**
- * gfs2_alloc_block - Allocate a block
+ * gfs2_rgrp_dump - print out an rgrp
+ * @seq: The iterator
+ * @gl: The glock in question
+ *
+ */
+
+int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl)
+{
+ const struct gfs2_rgrpd *rgd = gl->gl_object;
+ if (rgd == NULL)
+ return 0;
+ gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u\n",
+ (unsigned long long)rgd->rd_addr, rgd->rd_flags,
+ rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes);
+ return 0;
+}
+
+static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd)
+{
+ struct gfs2_sbd *sdp = rgd->rd_sbd;
+ fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n",
+ (unsigned long long)rgd->rd_addr);
+ fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n");
+ gfs2_rgrp_dump(NULL, rgd->rd_gl);
+ rgd->rd_flags |= GFS2_RDF_ERROR;
+}
+
+/**
+ * gfs2_alloc_block - Allocate one or more blocks
* @ip: the inode to allocate the block for
+ * @bn: Used to return the starting block number
+ * @n: requested number of blocks/extent length (value/result)
*
- * Returns: the allocated block
+ * Returns: 0 or error
*/
-u64 gfs2_alloc_block(struct gfs2_inode *ip, unsigned int *n)
+int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+ struct buffer_head *dibh;
struct gfs2_alloc *al = ip->i_alloc;
struct gfs2_rgrpd *rgd = al->al_rgd;
u32 goal, blk;
u64 block;
+ int error;
if (rgrp_contains_block(rgd, ip->i_goal))
goal = ip->i_goal - rgd->rd_data0;
goal = rgd->rd_last_alloc;
blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED, n);
- BUG_ON(blk == BFITNOENT);
+
+ /* Since all blocks are reserved in advance, this shouldn't happen */
+ if (blk == BFITNOENT)
+ goto rgrp_error;
rgd->rd_last_alloc = blk;
block = rgd->rd_data0 + blk;
ip->i_goal = block;
+ error = gfs2_meta_inode_buffer(ip, &dibh);
+ if (error == 0) {
+ struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
+ gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_goal);
+ brelse(dibh);
+ }
+ if (rgd->rd_free < *n)
+ goto rgrp_error;
- gfs2_assert_withdraw(sdp, rgd->rd_free >= *n);
rgd->rd_free -= *n;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
spin_lock(&sdp->sd_rindex_spin);
rgd->rd_free_clone -= *n;
spin_unlock(&sdp->sd_rindex_spin);
+ trace_gfs2_block_alloc(ip, block, *n, GFS2_BLKST_USED);
+ *bn = block;
+ return 0;
- return block;
+rgrp_error:
+ gfs2_rgrp_error(rgd);
+ return -EIO;
}
/**
* gfs2_alloc_di - Allocate a dinode
* @dip: the directory that the inode is going in
+ * @bn: the block number which is allocated
+ * @generation: the generation number of the inode
*
- * Returns: the block allocated
+ * Returns: 0 on success or error
*/
-u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation)
+int gfs2_alloc_di(struct gfs2_inode *dip, u64 *bn, u64 *generation)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_alloc *al = dip->i_alloc;
blk = rgblk_search(rgd, rgd->rd_last_alloc,
GFS2_BLKST_FREE, GFS2_BLKST_DINODE, &n);
- BUG_ON(blk == BFITNOENT);
- rgd->rd_last_alloc = blk;
+ /* Since all blocks are reserved in advance, this shouldn't happen */
+ if (blk == BFITNOENT)
+ goto rgrp_error;
+ rgd->rd_last_alloc = blk;
block = rgd->rd_data0 + blk;
+ if (rgd->rd_free == 0)
+ goto rgrp_error;
- gfs2_assert_withdraw(sdp, rgd->rd_free);
rgd->rd_free--;
rgd->rd_dinodes++;
*generation = rgd->rd_igeneration++;
+ if (*generation == 0)
+ *generation = rgd->rd_igeneration++;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
spin_lock(&sdp->sd_rindex_spin);
rgd->rd_free_clone--;
spin_unlock(&sdp->sd_rindex_spin);
+ trace_gfs2_block_alloc(dip, block, 1, GFS2_BLKST_DINODE);
+ *bn = block;
+ return 0;
- return block;
+rgrp_error:
+ gfs2_rgrp_error(rgd);
+ return -EIO;
}
/**
rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE);
if (!rgd)
return;
-
+ trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
rgd->rd_free += blen;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE);
if (!rgd)
return;
-
+ trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE);
rgd->rd_free += blen;
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED);
if (!rgd)
return;
+ trace_gfs2_block_alloc(ip, blkno, 1, GFS2_BLKST_UNLINKED);
gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
gfs2_trans_add_rg(rgd);
void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
{
gfs2_free_uninit_di(rgd, ip->i_no_addr);
+ trace_gfs2_block_alloc(ip, ip->i_no_addr, 1, GFS2_BLKST_FREE);
gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid);
gfs2_meta_wipe(ip, ip->i_no_addr, 1);
}
/**
+ * gfs2_check_blk_type - Check the type of a block
+ * @sdp: The superblock
+ * @no_addr: The block number to check
+ * @type: The block type we are looking for
+ *
+ * Returns: 0 if the block type matches the expected type
+ * -ESTALE if it doesn't match
+ * or -ve errno if something went wrong while checking
+ */
+
+int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
+{
+ struct gfs2_rgrpd *rgd;
+ struct gfs2_holder ri_gh, rgd_gh;
+ struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex);
+ int ri_locked = 0;
+ int error;
+
+ if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+ error = gfs2_rindex_hold(sdp, &ri_gh);
+ if (error)
+ goto fail;
+ ri_locked = 1;
+ }
+
+ error = -EINVAL;
+ rgd = gfs2_blk2rgrpd(sdp, no_addr);
+ if (!rgd)
+ goto fail_rindex;
+
+ error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
+ if (error)
+ goto fail_rindex;
+
+ if (gfs2_get_block_type(rgd, no_addr) != type)
+ error = -ESTALE;
+
+ gfs2_glock_dq_uninit(&rgd_gh);
+fail_rindex:
+ if (ri_locked)
+ gfs2_glock_dq_uninit(&ri_gh);
+fail:
+ return error;
+}
+
+/**
* gfs2_rlist_add - add a RG to a list of RGs
* @sdp: the filesystem
* @rlist: the list of resource groups
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff