xfs: add a realtime flag to the rmap update log redo items

Extend the rmap update (RUI) log items to handle realtime volumes by
adding a new log intent item type.

Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
This commit is contained in:
Darrick J. Wong 2024-11-20 16:20:24 -08:00
parent adafb31c80
commit 9e823fc274
9 changed files with 220 additions and 30 deletions

View File

@ -69,6 +69,7 @@ struct xfs_defer_op_type {
extern const struct xfs_defer_op_type xfs_bmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_refcount_update_defer_type;
extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_rtrmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
extern const struct xfs_defer_op_type xfs_rtextent_free_defer_type;

View File

@ -250,6 +250,8 @@ typedef struct xfs_trans_header {
#define XFS_LI_XMD 0x1249 /* mapping exchange done */
#define XFS_LI_EFI_RT 0x124a /* realtime extent free intent */
#define XFS_LI_EFD_RT 0x124b /* realtime extent free done */
#define XFS_LI_RUI_RT 0x124c /* realtime rmap update intent */
#define XFS_LI_RUD_RT 0x124d /* realtime rmap update done */
#define XFS_LI_TYPE_DESC \
{ XFS_LI_EFI, "XFS_LI_EFI" }, \
@ -271,7 +273,9 @@ typedef struct xfs_trans_header {
{ XFS_LI_XMI, "XFS_LI_XMI" }, \
{ XFS_LI_XMD, "XFS_LI_XMD" }, \
{ XFS_LI_EFI_RT, "XFS_LI_EFI_RT" }, \
{ XFS_LI_EFD_RT, "XFS_LI_EFD_RT" }
{ XFS_LI_EFD_RT, "XFS_LI_EFD_RT" }, \
{ XFS_LI_RUI_RT, "XFS_LI_RUI_RT" }, \
{ XFS_LI_RUD_RT, "XFS_LI_RUD_RT" }
/*
* Inode Log Item Format definitions.

View File

@ -79,6 +79,8 @@ extern const struct xlog_recover_item_ops xlog_xmi_item_ops;
extern const struct xlog_recover_item_ops xlog_xmd_item_ops;
extern const struct xlog_recover_item_ops xlog_rtefi_item_ops;
extern const struct xlog_recover_item_ops xlog_rtefd_item_ops;
extern const struct xlog_recover_item_ops xlog_rtrui_item_ops;
extern const struct xlog_recover_item_ops xlog_rtrud_item_ops;
/*
* Macros, structures, prototypes for internal log manager use.

View File

@ -1831,7 +1831,7 @@ xfs_refcount_alloc_cow_extent(
__xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len);
/* Add rmap entry */
xfs_rmap_alloc_extent(tp, fsb, len, XFS_RMAP_OWN_COW);
xfs_rmap_alloc_extent(tp, false, fsb, len, XFS_RMAP_OWN_COW);
}
/* Forget a CoW staging event in the refcount btree. */
@ -1847,7 +1847,7 @@ xfs_refcount_free_cow_extent(
return;
/* Remove rmap entry */
xfs_rmap_free_extent(tp, fsb, len, XFS_RMAP_OWN_COW);
xfs_rmap_free_extent(tp, false, fsb, len, XFS_RMAP_OWN_COW);
__xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len);
}

View File

@ -2710,6 +2710,7 @@ __xfs_rmap_add(
struct xfs_trans *tp,
enum xfs_rmap_intent_type type,
uint64_t owner,
bool isrt,
int whichfork,
struct xfs_bmbt_irec *bmap)
{
@ -2721,6 +2722,7 @@ __xfs_rmap_add(
ri->ri_owner = owner;
ri->ri_whichfork = whichfork;
ri->ri_bmap = *bmap;
ri->ri_realtime = isrt;
xfs_rmap_defer_add(tp, ri);
}
@ -2734,6 +2736,7 @@ xfs_rmap_map_extent(
struct xfs_bmbt_irec *PREV)
{
enum xfs_rmap_intent_type type = XFS_RMAP_MAP;
bool isrt = xfs_ifork_is_realtime(ip, whichfork);
if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
return;
@ -2741,7 +2744,7 @@ xfs_rmap_map_extent(
if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
type = XFS_RMAP_MAP_SHARED;
__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
__xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV);
}
/* Unmap an extent out of a file. */
@ -2753,6 +2756,7 @@ xfs_rmap_unmap_extent(
struct xfs_bmbt_irec *PREV)
{
enum xfs_rmap_intent_type type = XFS_RMAP_UNMAP;
bool isrt = xfs_ifork_is_realtime(ip, whichfork);
if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
return;
@ -2760,7 +2764,7 @@ xfs_rmap_unmap_extent(
if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
type = XFS_RMAP_UNMAP_SHARED;
__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
__xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV);
}
/*
@ -2778,6 +2782,7 @@ xfs_rmap_convert_extent(
struct xfs_bmbt_irec *PREV)
{
enum xfs_rmap_intent_type type = XFS_RMAP_CONVERT;
bool isrt = xfs_ifork_is_realtime(ip, whichfork);
if (!xfs_rmap_update_is_needed(mp, whichfork))
return;
@ -2785,13 +2790,14 @@ xfs_rmap_convert_extent(
if (whichfork != XFS_ATTR_FORK && xfs_is_reflink_inode(ip))
type = XFS_RMAP_CONVERT_SHARED;
__xfs_rmap_add(tp, type, ip->i_ino, whichfork, PREV);
__xfs_rmap_add(tp, type, ip->i_ino, isrt, whichfork, PREV);
}
/* Schedule the creation of an rmap for non-file data. */
void
xfs_rmap_alloc_extent(
struct xfs_trans *tp,
bool isrt,
xfs_fsblock_t fsbno,
xfs_extlen_t len,
uint64_t owner)
@ -2806,13 +2812,14 @@ xfs_rmap_alloc_extent(
bmap.br_startoff = 0;
bmap.br_state = XFS_EXT_NORM;
__xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap);
__xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, isrt, XFS_DATA_FORK, &bmap);
}
/* Schedule the deletion of an rmap for non-file data. */
void
xfs_rmap_free_extent(
struct xfs_trans *tp,
bool isrt,
xfs_fsblock_t fsbno,
xfs_extlen_t len,
uint64_t owner)
@ -2827,7 +2834,7 @@ xfs_rmap_free_extent(
bmap.br_startoff = 0;
bmap.br_state = XFS_EXT_NORM;
__xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap);
__xfs_rmap_add(tp, XFS_RMAP_FREE, owner, isrt, XFS_DATA_FORK, &bmap);
}
/* Compare rmap records. Returns -1 if a < b, 1 if a > b, and 0 if equal. */

View File

@ -175,6 +175,7 @@ struct xfs_rmap_intent {
uint64_t ri_owner;
struct xfs_bmbt_irec ri_bmap;
struct xfs_group *ri_group;
bool ri_realtime;
};
/* functions for updating the rmapbt based on bmbt map/unmap operations */
@ -185,9 +186,9 @@ void xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
void xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp,
struct xfs_inode *ip, int whichfork,
struct xfs_bmbt_irec *imap);
void xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_fsblock_t fsbno,
void xfs_rmap_alloc_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno,
xfs_extlen_t len, uint64_t owner);
void xfs_rmap_free_extent(struct xfs_trans *tp, xfs_fsblock_t fsbno,
void xfs_rmap_free_extent(struct xfs_trans *tp, bool isrt, xfs_fsblock_t fsbno,
xfs_extlen_t len, uint64_t owner);
int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri,

View File

@ -542,7 +542,7 @@ xrep_abt_dispose_one(
/* Add a deferred rmap for each extent we used. */
if (resv->used > 0)
xfs_rmap_alloc_extent(sc->tp,
xfs_rmap_alloc_extent(sc->tp, false,
xfs_agbno_to_fsb(pag, resv->agbno), resv->used,
XFS_RMAP_OWN_AG);

View File

@ -1820,6 +1820,8 @@ static const struct xlog_recover_item_ops *xlog_recover_item_ops[] = {
&xlog_xmd_item_ops,
&xlog_rtefi_item_ops,
&xlog_rtefd_item_ops,
&xlog_rtrui_item_ops,
&xlog_rtrud_item_ops,
};
static const struct xlog_recover_item_ops *

View File

@ -23,6 +23,7 @@
#include "xfs_ag.h"
#include "xfs_btree.h"
#include "xfs_trace.h"
#include "xfs_rtgroup.h"
struct kmem_cache *xfs_rui_cache;
struct kmem_cache *xfs_rud_cache;
@ -94,7 +95,9 @@ xfs_rui_item_format(
ASSERT(atomic_read(&ruip->rui_next_extent) ==
ruip->rui_format.rui_nextents);
ruip->rui_format.rui_type = XFS_LI_RUI;
ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT);
ruip->rui_format.rui_type = lip->li_type;
ruip->rui_format.rui_size = 1;
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUI_FORMAT, &ruip->rui_format,
@ -137,12 +140,15 @@ xfs_rui_item_release(
STATIC struct xfs_rui_log_item *
xfs_rui_init(
struct xfs_mount *mp,
unsigned short item_type,
uint nextents)
{
struct xfs_rui_log_item *ruip;
ASSERT(nextents > 0);
ASSERT(item_type == XFS_LI_RUI || item_type == XFS_LI_RUI_RT);
if (nextents > XFS_RUI_MAX_FAST_EXTENTS)
ruip = kzalloc(xfs_rui_log_item_sizeof(nextents),
GFP_KERNEL | __GFP_NOFAIL);
@ -150,7 +156,7 @@ xfs_rui_init(
ruip = kmem_cache_zalloc(xfs_rui_cache,
GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops);
xfs_log_item_init(mp, &ruip->rui_item, item_type, &xfs_rui_item_ops);
ruip->rui_format.rui_nextents = nextents;
ruip->rui_format.rui_id = (uintptr_t)(void *)ruip;
atomic_set(&ruip->rui_next_extent, 0);
@ -189,7 +195,9 @@ xfs_rud_item_format(
struct xfs_rud_log_item *rudp = RUD_ITEM(lip);
struct xfs_log_iovec *vecp = NULL;
rudp->rud_format.rud_type = XFS_LI_RUD;
ASSERT(lip->li_type == XFS_LI_RUD || lip->li_type == XFS_LI_RUD_RT);
rudp->rud_format.rud_type = lip->li_type;
rudp->rud_format.rud_size = 1;
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUD_FORMAT, &rudp->rud_format,
@ -233,6 +241,14 @@ static inline struct xfs_rmap_intent *ri_entry(const struct list_head *e)
return list_entry(e, struct xfs_rmap_intent, ri_list);
}
static inline bool
xfs_rui_item_isrt(const struct xfs_log_item *lip)
{
ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT);
return lip->li_type == XFS_LI_RUI_RT;
}
/* Sort rmap intents by AG. */
static int
xfs_rmap_update_diff_items(
@ -304,6 +320,28 @@ xfs_rmap_update_log_item(
}
}
static struct xfs_log_item *
__xfs_rmap_update_create_intent(
struct xfs_trans *tp,
struct list_head *items,
unsigned int count,
bool sort,
unsigned short item_type)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_rui_log_item *ruip;
struct xfs_rmap_intent *ri;
ASSERT(count > 0);
ruip = xfs_rui_init(mp, item_type, count);
if (sort)
list_sort(mp, items, xfs_rmap_update_diff_items);
list_for_each_entry(ri, items, ri_list)
xfs_rmap_update_log_item(tp, ruip, ri);
return &ruip->rui_item;
}
static struct xfs_log_item *
xfs_rmap_update_create_intent(
struct xfs_trans *tp,
@ -311,17 +349,14 @@ xfs_rmap_update_create_intent(
unsigned int count,
bool sort)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_rui_log_item *ruip = xfs_rui_init(mp, count);
struct xfs_rmap_intent *ri;
return __xfs_rmap_update_create_intent(tp, items, count, sort,
XFS_LI_RUI);
}
ASSERT(count > 0);
if (sort)
list_sort(mp, items, xfs_rmap_update_diff_items);
list_for_each_entry(ri, items, ri_list)
xfs_rmap_update_log_item(tp, ruip, ri);
return &ruip->rui_item;
static inline unsigned short
xfs_rud_type_from_rui(const struct xfs_rui_log_item *ruip)
{
return xfs_rui_item_isrt(&ruip->rui_item) ? XFS_LI_RUD_RT : XFS_LI_RUD;
}
/* Get an RUD so we can process all the deferred rmap updates. */
@ -335,8 +370,8 @@ xfs_rmap_update_create_done(
struct xfs_rud_log_item *rudp;
rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
&xfs_rud_item_ops);
xfs_log_item_init(tp->t_mountp, &rudp->rud_item,
xfs_rud_type_from_rui(ruip), &xfs_rud_item_ops);
rudp->rud_ruip = ruip;
rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
@ -351,11 +386,20 @@ xfs_rmap_defer_add(
{
struct xfs_mount *mp = tp->t_mountp;
/*
* Deferred rmap updates for the realtime and data sections must use
* separate transactions to finish deferred work because updates to
* realtime metadata files can lock AGFs to allocate btree blocks and
* we don't want that mixing with the AGF locks taken to finish data
* section updates.
*/
ri->ri_group = xfs_group_intent_get(mp, ri->ri_bmap.br_startblock,
XG_TYPE_AG);
ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG);
trace_xfs_rmap_defer(mp, ri);
xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type);
xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ?
&xfs_rtrmap_update_defer_type :
&xfs_rmap_update_defer_type);
}
/* Cancel a deferred rmap update. */
@ -566,10 +610,13 @@ xfs_rmap_relog_intent(
struct xfs_map_extent *map;
unsigned int count;
ASSERT(intent->li_type == XFS_LI_RUI ||
intent->li_type == XFS_LI_RUI_RT);
count = RUI_ITEM(intent)->rui_format.rui_nextents;
map = RUI_ITEM(intent)->rui_format.rui_extents;
ruip = xfs_rui_init(tp->t_mountp, count);
ruip = xfs_rui_init(tp->t_mountp, intent->li_type, count);
memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map));
atomic_set(&ruip->rui_next_extent, count);
@ -589,6 +636,47 @@ const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
.relog_intent = xfs_rmap_relog_intent,
};
#ifdef CONFIG_XFS_RT
static struct xfs_log_item *
xfs_rtrmap_update_create_intent(
struct xfs_trans *tp,
struct list_head *items,
unsigned int count,
bool sort)
{
return __xfs_rmap_update_create_intent(tp, items, count, sort,
XFS_LI_RUI_RT);
}
/* Clean up after calling xfs_rmap_finish_one. */
STATIC void
xfs_rtrmap_finish_one_cleanup(
struct xfs_trans *tp,
struct xfs_btree_cur *rcur,
int error)
{
if (rcur)
xfs_btree_del_cursor(rcur, error);
}
const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = {
.name = "rtrmap",
.max_items = XFS_RUI_MAX_FAST_EXTENTS,
.create_intent = xfs_rtrmap_update_create_intent,
.abort_intent = xfs_rmap_update_abort_intent,
.create_done = xfs_rmap_update_create_done,
.finish_item = xfs_rmap_update_finish_item,
.finish_cleanup = xfs_rtrmap_finish_one_cleanup,
.cancel_item = xfs_rmap_update_cancel_item,
.recover_work = xfs_rmap_recover_work,
.relog_intent = xfs_rmap_relog_intent,
};
#else
const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = {
.name = "rtrmap",
};
#endif
STATIC bool
xfs_rui_item_match(
struct xfs_log_item *lip,
@ -654,7 +742,7 @@ xlog_recover_rui_commit_pass2(
return -EFSCORRUPTED;
}
ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents);
xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
@ -668,6 +756,61 @@ const struct xlog_recover_item_ops xlog_rui_item_ops = {
.commit_pass2 = xlog_recover_rui_commit_pass2,
};
#ifdef CONFIG_XFS_RT
STATIC int
xlog_recover_rtrui_commit_pass2(
struct xlog *log,
struct list_head *buffer_list,
struct xlog_recover_item *item,
xfs_lsn_t lsn)
{
struct xfs_mount *mp = log->l_mp;
struct xfs_rui_log_item *ruip;
struct xfs_rui_log_format *rui_formatp;
size_t len;
rui_formatp = item->ri_buf[0].i_addr;
if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
if (item->ri_buf[0].i_len != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents);
xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
xlog_recover_intent_item(log, &ruip->rui_item, lsn,
&xfs_rtrmap_update_defer_type);
return 0;
}
#else
STATIC int
xlog_recover_rtrui_commit_pass2(
struct xlog *log,
struct list_head *buffer_list,
struct xlog_recover_item *item,
xfs_lsn_t lsn)
{
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
#endif
const struct xlog_recover_item_ops xlog_rtrui_item_ops = {
.item_type = XFS_LI_RUI_RT,
.commit_pass2 = xlog_recover_rtrui_commit_pass2,
};
/*
* This routine is called when an RUD format structure is found in a committed
* transaction in the log. Its purpose is to cancel the corresponding RUI if it
@ -699,3 +842,33 @@ const struct xlog_recover_item_ops xlog_rud_item_ops = {
.item_type = XFS_LI_RUD,
.commit_pass2 = xlog_recover_rud_commit_pass2,
};
#ifdef CONFIG_XFS_RT
STATIC int
xlog_recover_rtrud_commit_pass2(
struct xlog *log,
struct list_head *buffer_list,
struct xlog_recover_item *item,
xfs_lsn_t lsn)
{
struct xfs_rud_log_format *rud_formatp;
rud_formatp = item->ri_buf[0].i_addr;
if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
rud_formatp, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
xlog_recover_release_intent(log, XFS_LI_RUI_RT,
rud_formatp->rud_rui_id);
return 0;
}
#else
# define xlog_recover_rtrud_commit_pass2 xlog_recover_rtrui_commit_pass2
#endif
const struct xlog_recover_item_ops xlog_rtrud_item_ops = {
.item_type = XFS_LI_RUD_RT,
.commit_pass2 = xlog_recover_rtrud_commit_pass2,
};