Merge branch 'linux-next' of git://git.infradead.org/~dedekind/ubi-2.6
* 'linux-next' of git://git.infradead.org/~dedekind/ubi-2.6: UBI: fix checkpatch.pl warnings UBI: simplify PEB protection code UBI: prepare for protection tree improvements UBI: return -ENOMEM upon failing vmalloc UBI: document UBI ioctls UBI: handle write errors in WL worker UBI: fix error path UBI: some code re-structuring UBI: fix deadlock UBI: fix warnings when debugging is enabled
This commit is contained in:
commit
574c3fdae3
|
@ -97,6 +97,7 @@ Code Seq# Include File Comments
|
|||
<http://linux01.gwdg.de/~alatham/ppdd.html>
|
||||
'M' all linux/soundcard.h
|
||||
'N' 00-1F drivers/usb/scanner.h
|
||||
'O' 00-02 include/mtd/ubi-user.h UBI
|
||||
'P' all linux/soundcard.h
|
||||
'Q' all linux/soundcard.h
|
||||
'R' 00-1F linux/random.h
|
||||
|
@ -142,6 +143,9 @@ Code Seq# Include File Comments
|
|||
'n' 00-7F linux/ncp_fs.h
|
||||
'n' E0-FF video/matrox.h matroxfb
|
||||
'o' 00-1F fs/ocfs2/ocfs2_fs.h OCFS2
|
||||
'o' 00-03 include/mtd/ubi-user.h conflict! (OCFS2 and UBI overlaps)
|
||||
'o' 40-41 include/mtd/ubi-user.h UBI
|
||||
'o' 01-A1 include/linux/dvb/*.h DVB
|
||||
'p' 00-0F linux/phantom.h conflict! (OpenHaptics needs this)
|
||||
'p' 00-3F linux/mc146818rtc.h conflict!
|
||||
'p' 40-7F linux/nvram.h
|
||||
|
|
|
@ -815,19 +815,20 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, int vid_hdr_offset)
|
|||
if (err)
|
||||
goto out_free;
|
||||
|
||||
err = -ENOMEM;
|
||||
ubi->peb_buf1 = vmalloc(ubi->peb_size);
|
||||
if (!ubi->peb_buf1)
|
||||
goto out_free;
|
||||
|
||||
ubi->peb_buf2 = vmalloc(ubi->peb_size);
|
||||
if (!ubi->peb_buf2)
|
||||
goto out_free;
|
||||
goto out_free;
|
||||
|
||||
#ifdef CONFIG_MTD_UBI_DEBUG
|
||||
mutex_init(&ubi->dbg_buf_mutex);
|
||||
ubi->dbg_peb_buf = vmalloc(ubi->peb_size);
|
||||
if (!ubi->dbg_peb_buf)
|
||||
goto out_free;
|
||||
goto out_free;
|
||||
#endif
|
||||
|
||||
err = attach_by_scanning(ubi);
|
||||
|
|
|
@ -721,7 +721,8 @@ static int rename_volumes(struct ubi_device *ubi,
|
|||
* It seems we need to remove volume with name @re->new_name,
|
||||
* if it exists.
|
||||
*/
|
||||
desc = ubi_open_volume_nm(ubi->ubi_num, re->new_name, UBI_EXCLUSIVE);
|
||||
desc = ubi_open_volume_nm(ubi->ubi_num, re->new_name,
|
||||
UBI_EXCLUSIVE);
|
||||
if (IS_ERR(desc)) {
|
||||
err = PTR_ERR(desc);
|
||||
if (err == -ENODEV)
|
||||
|
|
|
@ -27,11 +27,11 @@
|
|||
#define dbg_err(fmt, ...) ubi_err(fmt, ##__VA_ARGS__)
|
||||
|
||||
#define ubi_assert(expr) do { \
|
||||
if (unlikely(!(expr))) { \
|
||||
printk(KERN_CRIT "UBI assert failed in %s at %u (pid %d)\n", \
|
||||
__func__, __LINE__, current->pid); \
|
||||
ubi_dbg_dump_stack(); \
|
||||
} \
|
||||
if (unlikely(!(expr))) { \
|
||||
printk(KERN_CRIT "UBI assert failed in %s at %u (pid %d)\n", \
|
||||
__func__, __LINE__, current->pid); \
|
||||
ubi_dbg_dump_stack(); \
|
||||
} \
|
||||
} while (0)
|
||||
|
||||
#define dbg_msg(fmt, ...) \
|
||||
|
|
|
@ -504,12 +504,9 @@ static int recover_peb(struct ubi_device *ubi, int pnum, int vol_id, int lnum,
|
|||
if (!vid_hdr)
|
||||
return -ENOMEM;
|
||||
|
||||
mutex_lock(&ubi->buf_mutex);
|
||||
|
||||
retry:
|
||||
new_pnum = ubi_wl_get_peb(ubi, UBI_UNKNOWN);
|
||||
if (new_pnum < 0) {
|
||||
mutex_unlock(&ubi->buf_mutex);
|
||||
ubi_free_vid_hdr(ubi, vid_hdr);
|
||||
return new_pnum;
|
||||
}
|
||||
|
@ -529,20 +526,23 @@ retry:
|
|||
goto write_error;
|
||||
|
||||
data_size = offset + len;
|
||||
mutex_lock(&ubi->buf_mutex);
|
||||
memset(ubi->peb_buf1 + offset, 0xFF, len);
|
||||
|
||||
/* Read everything before the area where the write failure happened */
|
||||
if (offset > 0) {
|
||||
err = ubi_io_read_data(ubi, ubi->peb_buf1, pnum, 0, offset);
|
||||
if (err && err != UBI_IO_BITFLIPS)
|
||||
goto out_put;
|
||||
goto out_unlock;
|
||||
}
|
||||
|
||||
memcpy(ubi->peb_buf1 + offset, buf, len);
|
||||
|
||||
err = ubi_io_write_data(ubi, ubi->peb_buf1, new_pnum, 0, data_size);
|
||||
if (err)
|
||||
if (err) {
|
||||
mutex_unlock(&ubi->buf_mutex);
|
||||
goto write_error;
|
||||
}
|
||||
|
||||
mutex_unlock(&ubi->buf_mutex);
|
||||
ubi_free_vid_hdr(ubi, vid_hdr);
|
||||
|
@ -553,8 +553,9 @@ retry:
|
|||
ubi_msg("data was successfully recovered");
|
||||
return 0;
|
||||
|
||||
out_put:
|
||||
out_unlock:
|
||||
mutex_unlock(&ubi->buf_mutex);
|
||||
out_put:
|
||||
ubi_wl_put_peb(ubi, new_pnum, 1);
|
||||
ubi_free_vid_hdr(ubi, vid_hdr);
|
||||
return err;
|
||||
|
@ -567,7 +568,6 @@ write_error:
|
|||
ubi_warn("failed to write to PEB %d", new_pnum);
|
||||
ubi_wl_put_peb(ubi, new_pnum, 1);
|
||||
if (++tries > UBI_IO_RETRIES) {
|
||||
mutex_unlock(&ubi->buf_mutex);
|
||||
ubi_free_vid_hdr(ubi, vid_hdr);
|
||||
return err;
|
||||
}
|
||||
|
@ -949,10 +949,14 @@ write_error:
|
|||
* This function copies logical eraseblock from physical eraseblock @from to
|
||||
* physical eraseblock @to. The @vid_hdr buffer may be changed by this
|
||||
* function. Returns:
|
||||
* o %0 in case of success;
|
||||
* o %1 if the operation was canceled and should be tried later (e.g.,
|
||||
* because a bit-flip was detected at the target PEB);
|
||||
* o %2 if the volume is being deleted and this LEB should not be moved.
|
||||
* o %0 in case of success;
|
||||
* o %1 if the operation was canceled because the volume is being deleted
|
||||
* or because the PEB was put meanwhile;
|
||||
* o %2 if the operation was canceled because there was a write error to the
|
||||
* target PEB;
|
||||
* o %-EAGAIN if the operation was canceled because a bit-flip was detected
|
||||
* in the target PEB;
|
||||
* o a negative error code in case of failure.
|
||||
*/
|
||||
int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
|
||||
struct ubi_vid_hdr *vid_hdr)
|
||||
|
@ -978,7 +982,7 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
|
|||
/*
|
||||
* Note, we may race with volume deletion, which means that the volume
|
||||
* this logical eraseblock belongs to might be being deleted. Since the
|
||||
* volume deletion unmaps all the volume's logical eraseblocks, it will
|
||||
* volume deletion un-maps all the volume's logical eraseblocks, it will
|
||||
* be locked in 'ubi_wl_put_peb()' and wait for the WL worker to finish.
|
||||
*/
|
||||
vol = ubi->volumes[idx];
|
||||
|
@ -986,7 +990,7 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
|
|||
/* No need to do further work, cancel */
|
||||
dbg_eba("volume %d is being removed, cancel", vol_id);
|
||||
spin_unlock(&ubi->volumes_lock);
|
||||
return 2;
|
||||
return 1;
|
||||
}
|
||||
spin_unlock(&ubi->volumes_lock);
|
||||
|
||||
|
@ -1023,7 +1027,7 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
|
|||
|
||||
/*
|
||||
* OK, now the LEB is locked and we can safely start moving it. Since
|
||||
* this function utilizes thie @ubi->peb1_buf buffer which is shared
|
||||
* this function utilizes the @ubi->peb1_buf buffer which is shared
|
||||
* with some other functions, so lock the buffer by taking the
|
||||
* @ubi->buf_mutex.
|
||||
*/
|
||||
|
@ -1068,8 +1072,11 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
|
|||
vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi));
|
||||
|
||||
err = ubi_io_write_vid_hdr(ubi, to, vid_hdr);
|
||||
if (err)
|
||||
if (err) {
|
||||
if (err == -EIO)
|
||||
err = 2;
|
||||
goto out_unlock_buf;
|
||||
}
|
||||
|
||||
cond_resched();
|
||||
|
||||
|
@ -1079,14 +1086,17 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
|
|||
if (err != UBI_IO_BITFLIPS)
|
||||
ubi_warn("cannot read VID header back from PEB %d", to);
|
||||
else
|
||||
err = 1;
|
||||
err = -EAGAIN;
|
||||
goto out_unlock_buf;
|
||||
}
|
||||
|
||||
if (data_size > 0) {
|
||||
err = ubi_io_write_data(ubi, ubi->peb_buf1, to, 0, aldata_size);
|
||||
if (err)
|
||||
if (err) {
|
||||
if (err == -EIO)
|
||||
err = 2;
|
||||
goto out_unlock_buf;
|
||||
}
|
||||
|
||||
cond_resched();
|
||||
|
||||
|
@ -1101,15 +1111,16 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to,
|
|||
ubi_warn("cannot read data back from PEB %d",
|
||||
to);
|
||||
else
|
||||
err = 1;
|
||||
err = -EAGAIN;
|
||||
goto out_unlock_buf;
|
||||
}
|
||||
|
||||
cond_resched();
|
||||
|
||||
if (memcmp(ubi->peb_buf1, ubi->peb_buf2, aldata_size)) {
|
||||
ubi_warn("read data back from PEB %d - it is different",
|
||||
to);
|
||||
ubi_warn("read data back from PEB %d and it is "
|
||||
"different", to);
|
||||
err = -EINVAL;
|
||||
goto out_unlock_buf;
|
||||
}
|
||||
}
|
||||
|
|
|
@ -637,8 +637,6 @@ int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum,
|
|||
|
||||
dbg_io("read EC header from PEB %d", pnum);
|
||||
ubi_assert(pnum >= 0 && pnum < ubi->peb_count);
|
||||
if (UBI_IO_DEBUG)
|
||||
verbose = 1;
|
||||
|
||||
err = ubi_io_read(ubi, ec_hdr, pnum, 0, UBI_EC_HDR_SIZE);
|
||||
if (err) {
|
||||
|
@ -685,6 +683,9 @@ int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum,
|
|||
if (verbose)
|
||||
ubi_warn("no EC header found at PEB %d, "
|
||||
"only 0xFF bytes", pnum);
|
||||
else if (UBI_IO_DEBUG)
|
||||
dbg_msg("no EC header found at PEB %d, "
|
||||
"only 0xFF bytes", pnum);
|
||||
return UBI_IO_PEB_EMPTY;
|
||||
}
|
||||
|
||||
|
@ -696,7 +697,9 @@ int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum,
|
|||
ubi_warn("bad magic number at PEB %d: %08x instead of "
|
||||
"%08x", pnum, magic, UBI_EC_HDR_MAGIC);
|
||||
ubi_dbg_dump_ec_hdr(ec_hdr);
|
||||
}
|
||||
} else if (UBI_IO_DEBUG)
|
||||
dbg_msg("bad magic number at PEB %d: %08x instead of "
|
||||
"%08x", pnum, magic, UBI_EC_HDR_MAGIC);
|
||||
return UBI_IO_BAD_EC_HDR;
|
||||
}
|
||||
|
||||
|
@ -708,7 +711,9 @@ int ubi_io_read_ec_hdr(struct ubi_device *ubi, int pnum,
|
|||
ubi_warn("bad EC header CRC at PEB %d, calculated "
|
||||
"%#08x, read %#08x", pnum, crc, hdr_crc);
|
||||
ubi_dbg_dump_ec_hdr(ec_hdr);
|
||||
}
|
||||
} else if (UBI_IO_DEBUG)
|
||||
dbg_msg("bad EC header CRC at PEB %d, calculated "
|
||||
"%#08x, read %#08x", pnum, crc, hdr_crc);
|
||||
return UBI_IO_BAD_EC_HDR;
|
||||
}
|
||||
|
||||
|
@ -912,8 +917,6 @@ int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
|
|||
|
||||
dbg_io("read VID header from PEB %d", pnum);
|
||||
ubi_assert(pnum >= 0 && pnum < ubi->peb_count);
|
||||
if (UBI_IO_DEBUG)
|
||||
verbose = 1;
|
||||
|
||||
p = (char *)vid_hdr - ubi->vid_hdr_shift;
|
||||
err = ubi_io_read(ubi, p, pnum, ubi->vid_hdr_aloffset,
|
||||
|
@ -960,6 +963,9 @@ int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
|
|||
if (verbose)
|
||||
ubi_warn("no VID header found at PEB %d, "
|
||||
"only 0xFF bytes", pnum);
|
||||
else if (UBI_IO_DEBUG)
|
||||
dbg_msg("no VID header found at PEB %d, "
|
||||
"only 0xFF bytes", pnum);
|
||||
return UBI_IO_PEB_FREE;
|
||||
}
|
||||
|
||||
|
@ -971,7 +977,9 @@ int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
|
|||
ubi_warn("bad magic number at PEB %d: %08x instead of "
|
||||
"%08x", pnum, magic, UBI_VID_HDR_MAGIC);
|
||||
ubi_dbg_dump_vid_hdr(vid_hdr);
|
||||
}
|
||||
} else if (UBI_IO_DEBUG)
|
||||
dbg_msg("bad magic number at PEB %d: %08x instead of "
|
||||
"%08x", pnum, magic, UBI_VID_HDR_MAGIC);
|
||||
return UBI_IO_BAD_VID_HDR;
|
||||
}
|
||||
|
||||
|
@ -983,7 +991,9 @@ int ubi_io_read_vid_hdr(struct ubi_device *ubi, int pnum,
|
|||
ubi_warn("bad CRC at PEB %d, calculated %#08x, "
|
||||
"read %#08x", pnum, crc, hdr_crc);
|
||||
ubi_dbg_dump_vid_hdr(vid_hdr);
|
||||
}
|
||||
} else if (UBI_IO_DEBUG)
|
||||
dbg_msg("bad CRC at PEB %d, calculated %#08x, "
|
||||
"read %#08x", pnum, crc, hdr_crc);
|
||||
return UBI_IO_BAD_VID_HDR;
|
||||
}
|
||||
|
||||
|
@ -1024,7 +1034,7 @@ int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum,
|
|||
|
||||
err = paranoid_check_peb_ec_hdr(ubi, pnum);
|
||||
if (err)
|
||||
return err > 0 ? -EINVAL: err;
|
||||
return err > 0 ? -EINVAL : err;
|
||||
|
||||
vid_hdr->magic = cpu_to_be32(UBI_VID_HDR_MAGIC);
|
||||
vid_hdr->version = UBI_VERSION;
|
||||
|
|
|
@ -73,6 +73,13 @@
|
|||
*/
|
||||
#define UBI_IO_RETRIES 3
|
||||
|
||||
/*
|
||||
* Length of the protection queue. The length is effectively equivalent to the
|
||||
* number of (global) erase cycles PEBs are protected from the wear-leveling
|
||||
* worker.
|
||||
*/
|
||||
#define UBI_PROT_QUEUE_LEN 10
|
||||
|
||||
/*
|
||||
* Error codes returned by the I/O sub-system.
|
||||
*
|
||||
|
@ -95,7 +102,8 @@ enum {
|
|||
|
||||
/**
|
||||
* struct ubi_wl_entry - wear-leveling entry.
|
||||
* @rb: link in the corresponding RB-tree
|
||||
* @u.rb: link in the corresponding (free/used) RB-tree
|
||||
* @u.list: link in the protection queue
|
||||
* @ec: erase counter
|
||||
* @pnum: physical eraseblock number
|
||||
*
|
||||
|
@ -104,7 +112,10 @@ enum {
|
|||
* RB-trees. See WL sub-system for details.
|
||||
*/
|
||||
struct ubi_wl_entry {
|
||||
struct rb_node rb;
|
||||
union {
|
||||
struct rb_node rb;
|
||||
struct list_head list;
|
||||
} u;
|
||||
int ec;
|
||||
int pnum;
|
||||
};
|
||||
|
@ -288,7 +299,7 @@ struct ubi_wl_entry;
|
|||
* @beb_rsvd_level: normal level of PEBs reserved for bad PEB handling
|
||||
*
|
||||
* @autoresize_vol_id: ID of the volume which has to be auto-resized at the end
|
||||
* of UBI ititializetion
|
||||
* of UBI initialization
|
||||
* @vtbl_slots: how many slots are available in the volume table
|
||||
* @vtbl_size: size of the volume table in bytes
|
||||
* @vtbl: in-RAM volume table copy
|
||||
|
@ -306,18 +317,17 @@ struct ubi_wl_entry;
|
|||
* @used: RB-tree of used physical eraseblocks
|
||||
* @free: RB-tree of free physical eraseblocks
|
||||
* @scrub: RB-tree of physical eraseblocks which need scrubbing
|
||||
* @prot: protection trees
|
||||
* @prot.pnum: protection tree indexed by physical eraseblock numbers
|
||||
* @prot.aec: protection tree indexed by absolute erase counter value
|
||||
* @wl_lock: protects the @used, @free, @prot, @lookuptbl, @abs_ec, @move_from,
|
||||
* @move_to, @move_to_put @erase_pending, @wl_scheduled, and @works
|
||||
* fields
|
||||
* @pq: protection queue (contain physical eraseblocks which are temporarily
|
||||
* protected from the wear-leveling worker)
|
||||
* @pq_head: protection queue head
|
||||
* @wl_lock: protects the @used, @free, @pq, @pq_head, @lookuptbl, @move_from,
|
||||
* @move_to, @move_to_put @erase_pending, @wl_scheduled and @works
|
||||
* fields
|
||||
* @move_mutex: serializes eraseblock moves
|
||||
* @work_sem: sycnhronizes the WL worker with use tasks
|
||||
* @work_sem: synchronizes the WL worker with use tasks
|
||||
* @wl_scheduled: non-zero if the wear-leveling was scheduled
|
||||
* @lookuptbl: a table to quickly find a &struct ubi_wl_entry object for any
|
||||
* physical eraseblock
|
||||
* @abs_ec: absolute erase counter
|
||||
* @move_from: physical eraseblock from where the data is being moved
|
||||
* @move_to: physical eraseblock where the data is being moved to
|
||||
* @move_to_put: if the "to" PEB was put
|
||||
|
@ -351,11 +361,11 @@ struct ubi_wl_entry;
|
|||
*
|
||||
* @peb_buf1: a buffer of PEB size used for different purposes
|
||||
* @peb_buf2: another buffer of PEB size used for different purposes
|
||||
* @buf_mutex: proptects @peb_buf1 and @peb_buf2
|
||||
* @buf_mutex: protects @peb_buf1 and @peb_buf2
|
||||
* @ckvol_mutex: serializes static volume checking when opening
|
||||
* @mult_mutex: serializes operations on multiple volumes, like re-nameing
|
||||
* @mult_mutex: serializes operations on multiple volumes, like re-naming
|
||||
* @dbg_peb_buf: buffer of PEB size used for debugging
|
||||
* @dbg_buf_mutex: proptects @dbg_peb_buf
|
||||
* @dbg_buf_mutex: protects @dbg_peb_buf
|
||||
*/
|
||||
struct ubi_device {
|
||||
struct cdev cdev;
|
||||
|
@ -392,16 +402,13 @@ struct ubi_device {
|
|||
struct rb_root used;
|
||||
struct rb_root free;
|
||||
struct rb_root scrub;
|
||||
struct {
|
||||
struct rb_root pnum;
|
||||
struct rb_root aec;
|
||||
} prot;
|
||||
struct list_head pq[UBI_PROT_QUEUE_LEN];
|
||||
int pq_head;
|
||||
spinlock_t wl_lock;
|
||||
struct mutex move_mutex;
|
||||
struct rw_semaphore work_sem;
|
||||
int wl_scheduled;
|
||||
struct ubi_wl_entry **lookuptbl;
|
||||
unsigned long long abs_ec;
|
||||
struct ubi_wl_entry *move_from;
|
||||
struct ubi_wl_entry *move_to;
|
||||
int move_to_put;
|
||||
|
|
|
@ -22,7 +22,7 @@
|
|||
* UBI wear-leveling sub-system.
|
||||
*
|
||||
* This sub-system is responsible for wear-leveling. It works in terms of
|
||||
* physical* eraseblocks and erase counters and knows nothing about logical
|
||||
* physical eraseblocks and erase counters and knows nothing about logical
|
||||
* eraseblocks, volumes, etc. From this sub-system's perspective all physical
|
||||
* eraseblocks are of two types - used and free. Used physical eraseblocks are
|
||||
* those that were "get" by the 'ubi_wl_get_peb()' function, and free physical
|
||||
|
@ -55,8 +55,39 @@
|
|||
*
|
||||
* As it was said, for the UBI sub-system all physical eraseblocks are either
|
||||
* "free" or "used". Free eraseblock are kept in the @wl->free RB-tree, while
|
||||
* used eraseblocks are kept in a set of different RB-trees: @wl->used,
|
||||
* @wl->prot.pnum, @wl->prot.aec, and @wl->scrub.
|
||||
* used eraseblocks are kept in @wl->used or @wl->scrub RB-trees, or
|
||||
* (temporarily) in the @wl->pq queue.
|
||||
*
|
||||
* When the WL sub-system returns a physical eraseblock, the physical
|
||||
* eraseblock is protected from being moved for some "time". For this reason,
|
||||
* the physical eraseblock is not directly moved from the @wl->free tree to the
|
||||
* @wl->used tree. There is a protection queue in between where this
|
||||
* physical eraseblock is temporarily stored (@wl->pq).
|
||||
*
|
||||
* All this protection stuff is needed because:
|
||||
* o we don't want to move physical eraseblocks just after we have given them
|
||||
* to the user; instead, we first want to let users fill them up with data;
|
||||
*
|
||||
* o there is a chance that the user will put the physical eraseblock very
|
||||
* soon, so it makes sense not to move it for some time, but wait; this is
|
||||
* especially important in case of "short term" physical eraseblocks.
|
||||
*
|
||||
* Physical eraseblocks stay protected only for limited time. But the "time" is
|
||||
* measured in erase cycles in this case. This is implemented with help of the
|
||||
* protection queue. Eraseblocks are put to the tail of this queue when they
|
||||
* are returned by the 'ubi_wl_get_peb()', and eraseblocks are removed from the
|
||||
* head of the queue on each erase operation (for any eraseblock). So the
|
||||
* length of the queue defines how may (global) erase cycles PEBs are protected.
|
||||
*
|
||||
* To put it differently, each physical eraseblock has 2 main states: free and
|
||||
* used. The former state corresponds to the @wl->free tree. The latter state
|
||||
* is split up on several sub-states:
|
||||
* o the WL movement is allowed (@wl->used tree);
|
||||
* o the WL movement is temporarily prohibited (@wl->pq queue);
|
||||
* o scrubbing is needed (@wl->scrub tree).
|
||||
*
|
||||
* Depending on the sub-state, wear-leveling entries of the used physical
|
||||
* eraseblocks may be kept in one of those structures.
|
||||
*
|
||||
* Note, in this implementation, we keep a small in-RAM object for each physical
|
||||
* eraseblock. This is surely not a scalable solution. But it appears to be good
|
||||
|
@ -70,9 +101,6 @@
|
|||
* target PEB, we pick a PEB with the highest EC if our PEB is "old" and we
|
||||
* pick target PEB with an average EC if our PEB is not very "old". This is a
|
||||
* room for future re-works of the WL sub-system.
|
||||
*
|
||||
* Note: the stuff with protection trees looks too complex and is difficult to
|
||||
* understand. Should be fixed.
|
||||
*/
|
||||
|
||||
#include <linux/slab.h>
|
||||
|
@ -84,14 +112,6 @@
|
|||
/* Number of physical eraseblocks reserved for wear-leveling purposes */
|
||||
#define WL_RESERVED_PEBS 1
|
||||
|
||||
/*
|
||||
* How many erase cycles are short term, unknown, and long term physical
|
||||
* eraseblocks protected.
|
||||
*/
|
||||
#define ST_PROTECTION 16
|
||||
#define U_PROTECTION 10
|
||||
#define LT_PROTECTION 4
|
||||
|
||||
/*
|
||||
* Maximum difference between two erase counters. If this threshold is
|
||||
* exceeded, the WL sub-system starts moving data from used physical
|
||||
|
@ -119,65 +139,10 @@
|
|||
*/
|
||||
#define WL_MAX_FAILURES 32
|
||||
|
||||
/**
|
||||
* struct ubi_wl_prot_entry - PEB protection entry.
|
||||
* @rb_pnum: link in the @wl->prot.pnum RB-tree
|
||||
* @rb_aec: link in the @wl->prot.aec RB-tree
|
||||
* @abs_ec: the absolute erase counter value when the protection ends
|
||||
* @e: the wear-leveling entry of the physical eraseblock under protection
|
||||
*
|
||||
* When the WL sub-system returns a physical eraseblock, the physical
|
||||
* eraseblock is protected from being moved for some "time". For this reason,
|
||||
* the physical eraseblock is not directly moved from the @wl->free tree to the
|
||||
* @wl->used tree. There is one more tree in between where this physical
|
||||
* eraseblock is temporarily stored (@wl->prot).
|
||||
*
|
||||
* All this protection stuff is needed because:
|
||||
* o we don't want to move physical eraseblocks just after we have given them
|
||||
* to the user; instead, we first want to let users fill them up with data;
|
||||
*
|
||||
* o there is a chance that the user will put the physical eraseblock very
|
||||
* soon, so it makes sense not to move it for some time, but wait; this is
|
||||
* especially important in case of "short term" physical eraseblocks.
|
||||
*
|
||||
* Physical eraseblocks stay protected only for limited time. But the "time" is
|
||||
* measured in erase cycles in this case. This is implemented with help of the
|
||||
* absolute erase counter (@wl->abs_ec). When it reaches certain value, the
|
||||
* physical eraseblocks are moved from the protection trees (@wl->prot.*) to
|
||||
* the @wl->used tree.
|
||||
*
|
||||
* Protected physical eraseblocks are searched by physical eraseblock number
|
||||
* (when they are put) and by the absolute erase counter (to check if it is
|
||||
* time to move them to the @wl->used tree). So there are actually 2 RB-trees
|
||||
* storing the protected physical eraseblocks: @wl->prot.pnum and
|
||||
* @wl->prot.aec. They are referred to as the "protection" trees. The
|
||||
* first one is indexed by the physical eraseblock number. The second one is
|
||||
* indexed by the absolute erase counter. Both trees store
|
||||
* &struct ubi_wl_prot_entry objects.
|
||||
*
|
||||
* Each physical eraseblock has 2 main states: free and used. The former state
|
||||
* corresponds to the @wl->free tree. The latter state is split up on several
|
||||
* sub-states:
|
||||
* o the WL movement is allowed (@wl->used tree);
|
||||
* o the WL movement is temporarily prohibited (@wl->prot.pnum and
|
||||
* @wl->prot.aec trees);
|
||||
* o scrubbing is needed (@wl->scrub tree).
|
||||
*
|
||||
* Depending on the sub-state, wear-leveling entries of the used physical
|
||||
* eraseblocks may be kept in one of those trees.
|
||||
*/
|
||||
struct ubi_wl_prot_entry {
|
||||
struct rb_node rb_pnum;
|
||||
struct rb_node rb_aec;
|
||||
unsigned long long abs_ec;
|
||||
struct ubi_wl_entry *e;
|
||||
};
|
||||
|
||||
/**
|
||||
* struct ubi_work - UBI work description data structure.
|
||||
* @list: a link in the list of pending works
|
||||
* @func: worker function
|
||||
* @priv: private data of the worker function
|
||||
* @e: physical eraseblock to erase
|
||||
* @torture: if the physical eraseblock has to be tortured
|
||||
*
|
||||
|
@ -198,9 +163,11 @@ struct ubi_work {
|
|||
static int paranoid_check_ec(struct ubi_device *ubi, int pnum, int ec);
|
||||
static int paranoid_check_in_wl_tree(struct ubi_wl_entry *e,
|
||||
struct rb_root *root);
|
||||
static int paranoid_check_in_pq(struct ubi_device *ubi, struct ubi_wl_entry *e);
|
||||
#else
|
||||
#define paranoid_check_ec(ubi, pnum, ec) 0
|
||||
#define paranoid_check_in_wl_tree(e, root)
|
||||
#define paranoid_check_in_pq(ubi, e) 0
|
||||
#endif
|
||||
|
||||
/**
|
||||
|
@ -220,7 +187,7 @@ static void wl_tree_add(struct ubi_wl_entry *e, struct rb_root *root)
|
|||
struct ubi_wl_entry *e1;
|
||||
|
||||
parent = *p;
|
||||
e1 = rb_entry(parent, struct ubi_wl_entry, rb);
|
||||
e1 = rb_entry(parent, struct ubi_wl_entry, u.rb);
|
||||
|
||||
if (e->ec < e1->ec)
|
||||
p = &(*p)->rb_left;
|
||||
|
@ -235,8 +202,8 @@ static void wl_tree_add(struct ubi_wl_entry *e, struct rb_root *root)
|
|||
}
|
||||
}
|
||||
|
||||
rb_link_node(&e->rb, parent, p);
|
||||
rb_insert_color(&e->rb, root);
|
||||
rb_link_node(&e->u.rb, parent, p);
|
||||
rb_insert_color(&e->u.rb, root);
|
||||
}
|
||||
|
||||
/**
|
||||
|
@ -331,7 +298,7 @@ static int in_wl_tree(struct ubi_wl_entry *e, struct rb_root *root)
|
|||
while (p) {
|
||||
struct ubi_wl_entry *e1;
|
||||
|
||||
e1 = rb_entry(p, struct ubi_wl_entry, rb);
|
||||
e1 = rb_entry(p, struct ubi_wl_entry, u.rb);
|
||||
|
||||
if (e->pnum == e1->pnum) {
|
||||
ubi_assert(e == e1);
|
||||
|
@ -355,50 +322,24 @@ static int in_wl_tree(struct ubi_wl_entry *e, struct rb_root *root)
|
|||
}
|
||||
|
||||
/**
|
||||
* prot_tree_add - add physical eraseblock to protection trees.
|
||||
* prot_queue_add - add physical eraseblock to the protection queue.
|
||||
* @ubi: UBI device description object
|
||||
* @e: the physical eraseblock to add
|
||||
* @pe: protection entry object to use
|
||||
* @abs_ec: absolute erase counter value when this physical eraseblock has
|
||||
* to be removed from the protection trees.
|
||||
*
|
||||
* @wl->lock has to be locked.
|
||||
* This function adds @e to the tail of the protection queue @ubi->pq, where
|
||||
* @e will stay for %UBI_PROT_QUEUE_LEN erase operations and will be
|
||||
* temporarily protected from the wear-leveling worker. Note, @wl->lock has to
|
||||
* be locked.
|
||||
*/
|
||||
static void prot_tree_add(struct ubi_device *ubi, struct ubi_wl_entry *e,
|
||||
struct ubi_wl_prot_entry *pe, int abs_ec)
|
||||
static void prot_queue_add(struct ubi_device *ubi, struct ubi_wl_entry *e)
|
||||
{
|
||||
struct rb_node **p, *parent = NULL;
|
||||
struct ubi_wl_prot_entry *pe1;
|
||||
int pq_tail = ubi->pq_head - 1;
|
||||
|
||||
pe->e = e;
|
||||
pe->abs_ec = ubi->abs_ec + abs_ec;
|
||||
|
||||
p = &ubi->prot.pnum.rb_node;
|
||||
while (*p) {
|
||||
parent = *p;
|
||||
pe1 = rb_entry(parent, struct ubi_wl_prot_entry, rb_pnum);
|
||||
|
||||
if (e->pnum < pe1->e->pnum)
|
||||
p = &(*p)->rb_left;
|
||||
else
|
||||
p = &(*p)->rb_right;
|
||||
}
|
||||
rb_link_node(&pe->rb_pnum, parent, p);
|
||||
rb_insert_color(&pe->rb_pnum, &ubi->prot.pnum);
|
||||
|
||||
p = &ubi->prot.aec.rb_node;
|
||||
parent = NULL;
|
||||
while (*p) {
|
||||
parent = *p;
|
||||
pe1 = rb_entry(parent, struct ubi_wl_prot_entry, rb_aec);
|
||||
|
||||
if (pe->abs_ec < pe1->abs_ec)
|
||||
p = &(*p)->rb_left;
|
||||
else
|
||||
p = &(*p)->rb_right;
|
||||
}
|
||||
rb_link_node(&pe->rb_aec, parent, p);
|
||||
rb_insert_color(&pe->rb_aec, &ubi->prot.aec);
|
||||
if (pq_tail < 0)
|
||||
pq_tail = UBI_PROT_QUEUE_LEN - 1;
|
||||
ubi_assert(pq_tail >= 0 && pq_tail < UBI_PROT_QUEUE_LEN);
|
||||
list_add_tail(&e->u.list, &ubi->pq[pq_tail]);
|
||||
dbg_wl("added PEB %d EC %d to the protection queue", e->pnum, e->ec);
|
||||
}
|
||||
|
||||
/**
|
||||
|
@ -414,14 +355,14 @@ static struct ubi_wl_entry *find_wl_entry(struct rb_root *root, int max)
|
|||
struct rb_node *p;
|
||||
struct ubi_wl_entry *e;
|
||||
|
||||
e = rb_entry(rb_first(root), struct ubi_wl_entry, rb);
|
||||
e = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb);
|
||||
max += e->ec;
|
||||
|
||||
p = root->rb_node;
|
||||
while (p) {
|
||||
struct ubi_wl_entry *e1;
|
||||
|
||||
e1 = rb_entry(p, struct ubi_wl_entry, rb);
|
||||
e1 = rb_entry(p, struct ubi_wl_entry, u.rb);
|
||||
if (e1->ec >= max)
|
||||
p = p->rb_left;
|
||||
else {
|
||||
|
@ -443,17 +384,12 @@ static struct ubi_wl_entry *find_wl_entry(struct rb_root *root, int max)
|
|||
*/
|
||||
int ubi_wl_get_peb(struct ubi_device *ubi, int dtype)
|
||||
{
|
||||
int err, protect, medium_ec;
|
||||
int err, medium_ec;
|
||||
struct ubi_wl_entry *e, *first, *last;
|
||||
struct ubi_wl_prot_entry *pe;
|
||||
|
||||
ubi_assert(dtype == UBI_LONGTERM || dtype == UBI_SHORTTERM ||
|
||||
dtype == UBI_UNKNOWN);
|
||||
|
||||
pe = kmalloc(sizeof(struct ubi_wl_prot_entry), GFP_NOFS);
|
||||
if (!pe)
|
||||
return -ENOMEM;
|
||||
|
||||
retry:
|
||||
spin_lock(&ubi->wl_lock);
|
||||
if (!ubi->free.rb_node) {
|
||||
|
@ -461,16 +397,13 @@ retry:
|
|||
ubi_assert(list_empty(&ubi->works));
|
||||
ubi_err("no free eraseblocks");
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
kfree(pe);
|
||||
return -ENOSPC;
|
||||
}
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
||||
err = produce_free_peb(ubi);
|
||||
if (err < 0) {
|
||||
kfree(pe);
|
||||
if (err < 0)
|
||||
return err;
|
||||
}
|
||||
goto retry;
|
||||
}
|
||||
|
||||
|
@ -483,7 +416,6 @@ retry:
|
|||
* %WL_FREE_MAX_DIFF.
|
||||
*/
|
||||
e = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF);
|
||||
protect = LT_PROTECTION;
|
||||
break;
|
||||
case UBI_UNKNOWN:
|
||||
/*
|
||||
|
@ -492,81 +424,63 @@ retry:
|
|||
* eraseblock with erase counter greater or equivalent than the
|
||||
* lowest erase counter plus %WL_FREE_MAX_DIFF.
|
||||
*/
|
||||
first = rb_entry(rb_first(&ubi->free), struct ubi_wl_entry, rb);
|
||||
last = rb_entry(rb_last(&ubi->free), struct ubi_wl_entry, rb);
|
||||
first = rb_entry(rb_first(&ubi->free), struct ubi_wl_entry,
|
||||
u.rb);
|
||||
last = rb_entry(rb_last(&ubi->free), struct ubi_wl_entry, u.rb);
|
||||
|
||||
if (last->ec - first->ec < WL_FREE_MAX_DIFF)
|
||||
e = rb_entry(ubi->free.rb_node,
|
||||
struct ubi_wl_entry, rb);
|
||||
struct ubi_wl_entry, u.rb);
|
||||
else {
|
||||
medium_ec = (first->ec + WL_FREE_MAX_DIFF)/2;
|
||||
e = find_wl_entry(&ubi->free, medium_ec);
|
||||
}
|
||||
protect = U_PROTECTION;
|
||||
break;
|
||||
case UBI_SHORTTERM:
|
||||
/*
|
||||
* For short term data we pick a physical eraseblock with the
|
||||
* lowest erase counter as we expect it will be erased soon.
|
||||
*/
|
||||
e = rb_entry(rb_first(&ubi->free), struct ubi_wl_entry, rb);
|
||||
protect = ST_PROTECTION;
|
||||
e = rb_entry(rb_first(&ubi->free), struct ubi_wl_entry, u.rb);
|
||||
break;
|
||||
default:
|
||||
protect = 0;
|
||||
e = NULL;
|
||||
BUG();
|
||||
}
|
||||
|
||||
paranoid_check_in_wl_tree(e, &ubi->free);
|
||||
|
||||
/*
|
||||
* Move the physical eraseblock to the protection trees where it will
|
||||
* Move the physical eraseblock to the protection queue where it will
|
||||
* be protected from being moved for some time.
|
||||
*/
|
||||
paranoid_check_in_wl_tree(e, &ubi->free);
|
||||
rb_erase(&e->rb, &ubi->free);
|
||||
prot_tree_add(ubi, e, pe, protect);
|
||||
|
||||
dbg_wl("PEB %d EC %d, protection %d", e->pnum, e->ec, protect);
|
||||
rb_erase(&e->u.rb, &ubi->free);
|
||||
dbg_wl("PEB %d EC %d", e->pnum, e->ec);
|
||||
prot_queue_add(ubi, e);
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
||||
return e->pnum;
|
||||
}
|
||||
|
||||
/**
|
||||
* prot_tree_del - remove a physical eraseblock from the protection trees
|
||||
* prot_queue_del - remove a physical eraseblock from the protection queue.
|
||||
* @ubi: UBI device description object
|
||||
* @pnum: the physical eraseblock to remove
|
||||
*
|
||||
* This function returns PEB @pnum from the protection trees and returns zero
|
||||
* in case of success and %-ENODEV if the PEB was not found in the protection
|
||||
* trees.
|
||||
* This function deletes PEB @pnum from the protection queue and returns zero
|
||||
* in case of success and %-ENODEV if the PEB was not found.
|
||||
*/
|
||||
static int prot_tree_del(struct ubi_device *ubi, int pnum)
|
||||
static int prot_queue_del(struct ubi_device *ubi, int pnum)
|
||||
{
|
||||
struct rb_node *p;
|
||||
struct ubi_wl_prot_entry *pe = NULL;
|
||||
struct ubi_wl_entry *e;
|
||||
|
||||
p = ubi->prot.pnum.rb_node;
|
||||
while (p) {
|
||||
e = ubi->lookuptbl[pnum];
|
||||
if (!e)
|
||||
return -ENODEV;
|
||||
|
||||
pe = rb_entry(p, struct ubi_wl_prot_entry, rb_pnum);
|
||||
if (paranoid_check_in_pq(ubi, e))
|
||||
return -ENODEV;
|
||||
|
||||
if (pnum == pe->e->pnum)
|
||||
goto found;
|
||||
|
||||
if (pnum < pe->e->pnum)
|
||||
p = p->rb_left;
|
||||
else
|
||||
p = p->rb_right;
|
||||
}
|
||||
|
||||
return -ENODEV;
|
||||
|
||||
found:
|
||||
ubi_assert(pe->e->pnum == pnum);
|
||||
rb_erase(&pe->rb_aec, &ubi->prot.aec);
|
||||
rb_erase(&pe->rb_pnum, &ubi->prot.pnum);
|
||||
kfree(pe);
|
||||
list_del(&e->u.list);
|
||||
dbg_wl("deleted PEB %d from the protection queue", e->pnum);
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
@ -632,47 +546,47 @@ out_free:
|
|||
}
|
||||
|
||||
/**
|
||||
* check_protection_over - check if it is time to stop protecting some PEBs.
|
||||
* serve_prot_queue - check if it is time to stop protecting PEBs.
|
||||
* @ubi: UBI device description object
|
||||
*
|
||||
* This function is called after each erase operation, when the absolute erase
|
||||
* counter is incremented, to check if some physical eraseblock have not to be
|
||||
* protected any longer. These physical eraseblocks are moved from the
|
||||
* protection trees to the used tree.
|
||||
* This function is called after each erase operation and removes PEBs from the
|
||||
* tail of the protection queue. These PEBs have been protected for long enough
|
||||
* and should be moved to the used tree.
|
||||
*/
|
||||
static void check_protection_over(struct ubi_device *ubi)
|
||||
static void serve_prot_queue(struct ubi_device *ubi)
|
||||
{
|
||||
struct ubi_wl_prot_entry *pe;
|
||||
struct ubi_wl_entry *e, *tmp;
|
||||
int count;
|
||||
|
||||
/*
|
||||
* There may be several protected physical eraseblock to remove,
|
||||
* process them all.
|
||||
*/
|
||||
while (1) {
|
||||
spin_lock(&ubi->wl_lock);
|
||||
if (!ubi->prot.aec.rb_node) {
|
||||
repeat:
|
||||
count = 0;
|
||||
spin_lock(&ubi->wl_lock);
|
||||
list_for_each_entry_safe(e, tmp, &ubi->pq[ubi->pq_head], u.list) {
|
||||
dbg_wl("PEB %d EC %d protection over, move to used tree",
|
||||
e->pnum, e->ec);
|
||||
|
||||
list_del(&e->u.list);
|
||||
wl_tree_add(e, &ubi->used);
|
||||
if (count++ > 32) {
|
||||
/*
|
||||
* Let's be nice and avoid holding the spinlock for
|
||||
* too long.
|
||||
*/
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
break;
|
||||
cond_resched();
|
||||
goto repeat;
|
||||
}
|
||||
|
||||
pe = rb_entry(rb_first(&ubi->prot.aec),
|
||||
struct ubi_wl_prot_entry, rb_aec);
|
||||
|
||||
if (pe->abs_ec > ubi->abs_ec) {
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
break;
|
||||
}
|
||||
|
||||
dbg_wl("PEB %d protection over, abs_ec %llu, PEB abs_ec %llu",
|
||||
pe->e->pnum, ubi->abs_ec, pe->abs_ec);
|
||||
rb_erase(&pe->rb_aec, &ubi->prot.aec);
|
||||
rb_erase(&pe->rb_pnum, &ubi->prot.pnum);
|
||||
wl_tree_add(pe->e, &ubi->used);
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
||||
kfree(pe);
|
||||
cond_resched();
|
||||
}
|
||||
|
||||
ubi->pq_head += 1;
|
||||
if (ubi->pq_head == UBI_PROT_QUEUE_LEN)
|
||||
ubi->pq_head = 0;
|
||||
ubi_assert(ubi->pq_head >= 0 && ubi->pq_head < UBI_PROT_QUEUE_LEN);
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
}
|
||||
|
||||
/**
|
||||
|
@ -680,8 +594,8 @@ static void check_protection_over(struct ubi_device *ubi)
|
|||
* @ubi: UBI device description object
|
||||
* @wrk: the work to schedule
|
||||
*
|
||||
* This function enqueues a work defined by @wrk to the tail of the pending
|
||||
* works list.
|
||||
* This function adds a work defined by @wrk to the tail of the pending works
|
||||
* list.
|
||||
*/
|
||||
static void schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk)
|
||||
{
|
||||
|
@ -739,13 +653,11 @@ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e,
|
|||
static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
|
||||
int cancel)
|
||||
{
|
||||
int err, put = 0, scrubbing = 0, protect = 0;
|
||||
struct ubi_wl_prot_entry *uninitialized_var(pe);
|
||||
int err, scrubbing = 0, torture = 0;
|
||||
struct ubi_wl_entry *e1, *e2;
|
||||
struct ubi_vid_hdr *vid_hdr;
|
||||
|
||||
kfree(wrk);
|
||||
|
||||
if (cancel)
|
||||
return 0;
|
||||
|
||||
|
@ -781,7 +693,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
|
|||
* highly worn-out free physical eraseblock. If the erase
|
||||
* counters differ much enough, start wear-leveling.
|
||||
*/
|
||||
e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, rb);
|
||||
e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb);
|
||||
e2 = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF);
|
||||
|
||||
if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) {
|
||||
|
@ -790,21 +702,21 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
|
|||
goto out_cancel;
|
||||
}
|
||||
paranoid_check_in_wl_tree(e1, &ubi->used);
|
||||
rb_erase(&e1->rb, &ubi->used);
|
||||
rb_erase(&e1->u.rb, &ubi->used);
|
||||
dbg_wl("move PEB %d EC %d to PEB %d EC %d",
|
||||
e1->pnum, e1->ec, e2->pnum, e2->ec);
|
||||
} else {
|
||||
/* Perform scrubbing */
|
||||
scrubbing = 1;
|
||||
e1 = rb_entry(rb_first(&ubi->scrub), struct ubi_wl_entry, rb);
|
||||
e1 = rb_entry(rb_first(&ubi->scrub), struct ubi_wl_entry, u.rb);
|
||||
e2 = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF);
|
||||
paranoid_check_in_wl_tree(e1, &ubi->scrub);
|
||||
rb_erase(&e1->rb, &ubi->scrub);
|
||||
rb_erase(&e1->u.rb, &ubi->scrub);
|
||||
dbg_wl("scrub PEB %d to PEB %d", e1->pnum, e2->pnum);
|
||||
}
|
||||
|
||||
paranoid_check_in_wl_tree(e2, &ubi->free);
|
||||
rb_erase(&e2->rb, &ubi->free);
|
||||
rb_erase(&e2->u.rb, &ubi->free);
|
||||
ubi->move_from = e1;
|
||||
ubi->move_to = e2;
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
@ -844,46 +756,67 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
|
|||
|
||||
err = ubi_eba_copy_leb(ubi, e1->pnum, e2->pnum, vid_hdr);
|
||||
if (err) {
|
||||
|
||||
if (err == -EAGAIN)
|
||||
goto out_not_moved;
|
||||
if (err < 0)
|
||||
goto out_error;
|
||||
if (err == 1)
|
||||
if (err == 2) {
|
||||
/* Target PEB write error, torture it */
|
||||
torture = 1;
|
||||
goto out_not_moved;
|
||||
|
||||
/*
|
||||
* For some reason the LEB was not moved - it might be because
|
||||
* the volume is being deleted. We should prevent this PEB from
|
||||
* being selected for wear-levelling movement for some "time",
|
||||
* so put it to the protection tree.
|
||||
*/
|
||||
|
||||
dbg_wl("cancelled moving PEB %d", e1->pnum);
|
||||
pe = kmalloc(sizeof(struct ubi_wl_prot_entry), GFP_NOFS);
|
||||
if (!pe) {
|
||||
err = -ENOMEM;
|
||||
goto out_error;
|
||||
}
|
||||
|
||||
protect = 1;
|
||||
/*
|
||||
* The LEB has not been moved because the volume is being
|
||||
* deleted or the PEB has been put meanwhile. We should prevent
|
||||
* this PEB from being selected for wear-leveling movement
|
||||
* again, so put it to the protection queue.
|
||||
*/
|
||||
|
||||
dbg_wl("canceled moving PEB %d", e1->pnum);
|
||||
ubi_assert(err == 1);
|
||||
|
||||
ubi_free_vid_hdr(ubi, vid_hdr);
|
||||
vid_hdr = NULL;
|
||||
|
||||
spin_lock(&ubi->wl_lock);
|
||||
prot_queue_add(ubi, e1);
|
||||
ubi_assert(!ubi->move_to_put);
|
||||
ubi->move_from = ubi->move_to = NULL;
|
||||
ubi->wl_scheduled = 0;
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
||||
e1 = NULL;
|
||||
err = schedule_erase(ubi, e2, 0);
|
||||
if (err)
|
||||
goto out_error;
|
||||
mutex_unlock(&ubi->move_mutex);
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* The PEB has been successfully moved */
|
||||
ubi_free_vid_hdr(ubi, vid_hdr);
|
||||
if (scrubbing && !protect)
|
||||
vid_hdr = NULL;
|
||||
if (scrubbing)
|
||||
ubi_msg("scrubbed PEB %d, data moved to PEB %d",
|
||||
e1->pnum, e2->pnum);
|
||||
|
||||
spin_lock(&ubi->wl_lock);
|
||||
if (protect)
|
||||
prot_tree_add(ubi, e1, pe, protect);
|
||||
if (!ubi->move_to_put)
|
||||
if (!ubi->move_to_put) {
|
||||
wl_tree_add(e2, &ubi->used);
|
||||
else
|
||||
put = 1;
|
||||
e2 = NULL;
|
||||
}
|
||||
ubi->move_from = ubi->move_to = NULL;
|
||||
ubi->move_to_put = ubi->wl_scheduled = 0;
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
||||
if (put) {
|
||||
err = schedule_erase(ubi, e1, 0);
|
||||
if (err) {
|
||||
e1 = NULL;
|
||||
goto out_error;
|
||||
}
|
||||
|
||||
if (e2) {
|
||||
/*
|
||||
* Well, the target PEB was put meanwhile, schedule it for
|
||||
* erasure.
|
||||
|
@ -894,13 +827,6 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
|
|||
goto out_error;
|
||||
}
|
||||
|
||||
if (!protect) {
|
||||
err = schedule_erase(ubi, e1, 0);
|
||||
if (err)
|
||||
goto out_error;
|
||||
}
|
||||
|
||||
|
||||
dbg_wl("done");
|
||||
mutex_unlock(&ubi->move_mutex);
|
||||
return 0;
|
||||
|
@ -908,20 +834,24 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
|
|||
/*
|
||||
* For some reasons the LEB was not moved, might be an error, might be
|
||||
* something else. @e1 was not changed, so return it back. @e2 might
|
||||
* be changed, schedule it for erasure.
|
||||
* have been changed, schedule it for erasure.
|
||||
*/
|
||||
out_not_moved:
|
||||
dbg_wl("canceled moving PEB %d", e1->pnum);
|
||||
ubi_free_vid_hdr(ubi, vid_hdr);
|
||||
vid_hdr = NULL;
|
||||
spin_lock(&ubi->wl_lock);
|
||||
if (scrubbing)
|
||||
wl_tree_add(e1, &ubi->scrub);
|
||||
else
|
||||
wl_tree_add(e1, &ubi->used);
|
||||
ubi_assert(!ubi->move_to_put);
|
||||
ubi->move_from = ubi->move_to = NULL;
|
||||
ubi->move_to_put = ubi->wl_scheduled = 0;
|
||||
ubi->wl_scheduled = 0;
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
||||
err = schedule_erase(ubi, e2, 0);
|
||||
e1 = NULL;
|
||||
err = schedule_erase(ubi, e2, torture);
|
||||
if (err)
|
||||
goto out_error;
|
||||
|
||||
|
@ -938,8 +868,10 @@ out_error:
|
|||
ubi->move_to_put = ubi->wl_scheduled = 0;
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
||||
kmem_cache_free(ubi_wl_entry_slab, e1);
|
||||
kmem_cache_free(ubi_wl_entry_slab, e2);
|
||||
if (e1)
|
||||
kmem_cache_free(ubi_wl_entry_slab, e1);
|
||||
if (e2)
|
||||
kmem_cache_free(ubi_wl_entry_slab, e2);
|
||||
ubi_ro_mode(ubi);
|
||||
|
||||
mutex_unlock(&ubi->move_mutex);
|
||||
|
@ -988,7 +920,7 @@ static int ensure_wear_leveling(struct ubi_device *ubi)
|
|||
* erase counter of free physical eraseblocks is greater then
|
||||
* %UBI_WL_THRESHOLD.
|
||||
*/
|
||||
e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, rb);
|
||||
e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb);
|
||||
e2 = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF);
|
||||
|
||||
if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD))
|
||||
|
@ -1050,7 +982,6 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
|
|||
kfree(wl_wrk);
|
||||
|
||||
spin_lock(&ubi->wl_lock);
|
||||
ubi->abs_ec += 1;
|
||||
wl_tree_add(e, &ubi->free);
|
||||
spin_unlock(&ubi->wl_lock);
|
||||
|
||||
|
@ -1058,7 +989,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
|
|||
* One more erase operation has happened, take care about
|
||||
* protected physical eraseblocks.
|
||||
*/
|
||||
check_protection_over(ubi);
|
||||
serve_prot_queue(ubi);
|
||||
|
||||
/* And take care about wear-leveling */
|
||||
err = ensure_wear_leveling(ubi);
|
||||
|
@ -1190,12 +1121,12 @@ retry:
|
|||
} else {
|
||||
if (in_wl_tree(e, &ubi->used)) {
|
||||
paranoid_check_in_wl_tree(e, &ubi->used);
|
||||
rb_erase(&e->rb, &ubi->used);
|
||||
rb_erase(&e->u.rb, &ubi->used);
|
||||
} else if (in_wl_tree(e, &ubi->scrub)) {
|
||||
paranoid_check_in_wl_tree(e, &ubi->scrub);
|
||||
rb_erase(&e->rb, &ubi->scrub);
|
||||
rb_erase(&e->u.rb, &ubi->scrub);
|
||||
} else {
|
||||
err = prot_tree_del(ubi, e->pnum);
|
||||
err = prot_queue_del(ubi, e->pnum);
|
||||
if (err) {
|
||||
ubi_err("PEB %d not found", pnum);
|
||||
ubi_ro_mode(ubi);
|
||||
|
@ -1255,11 +1186,11 @@ retry:
|
|||
|
||||
if (in_wl_tree(e, &ubi->used)) {
|
||||
paranoid_check_in_wl_tree(e, &ubi->used);
|
||||
rb_erase(&e->rb, &ubi->used);
|
||||
rb_erase(&e->u.rb, &ubi->used);
|
||||
} else {
|
||||
int err;
|
||||
|
||||
err = prot_tree_del(ubi, e->pnum);
|
||||
err = prot_queue_del(ubi, e->pnum);
|
||||
if (err) {
|
||||
ubi_err("PEB %d not found", pnum);
|
||||
ubi_ro_mode(ubi);
|
||||
|
@ -1290,7 +1221,7 @@ int ubi_wl_flush(struct ubi_device *ubi)
|
|||
int err;
|
||||
|
||||
/*
|
||||
* Erase while the pending works queue is not empty, but not more then
|
||||
* Erase while the pending works queue is not empty, but not more than
|
||||
* the number of currently pending works.
|
||||
*/
|
||||
dbg_wl("flush (%d pending works)", ubi->works_count);
|
||||
|
@ -1308,7 +1239,7 @@ int ubi_wl_flush(struct ubi_device *ubi)
|
|||
up_write(&ubi->work_sem);
|
||||
|
||||
/*
|
||||
* And in case last was the WL worker and it cancelled the LEB
|
||||
* And in case last was the WL worker and it canceled the LEB
|
||||
* movement, flush again.
|
||||
*/
|
||||
while (ubi->works_count) {
|
||||
|
@ -1337,11 +1268,11 @@ static void tree_destroy(struct rb_root *root)
|
|||
else if (rb->rb_right)
|
||||
rb = rb->rb_right;
|
||||
else {
|
||||
e = rb_entry(rb, struct ubi_wl_entry, rb);
|
||||
e = rb_entry(rb, struct ubi_wl_entry, u.rb);
|
||||
|
||||
rb = rb_parent(rb);
|
||||
if (rb) {
|
||||
if (rb->rb_left == &e->rb)
|
||||
if (rb->rb_left == &e->u.rb)
|
||||
rb->rb_left = NULL;
|
||||
else
|
||||
rb->rb_right = NULL;
|
||||
|
@ -1436,15 +1367,13 @@ static void cancel_pending(struct ubi_device *ubi)
|
|||
*/
|
||||
int ubi_wl_init_scan(struct ubi_device *ubi, struct ubi_scan_info *si)
|
||||
{
|
||||
int err;
|
||||
int err, i;
|
||||
struct rb_node *rb1, *rb2;
|
||||
struct ubi_scan_volume *sv;
|
||||
struct ubi_scan_leb *seb, *tmp;
|
||||
struct ubi_wl_entry *e;
|
||||
|
||||
|
||||
ubi->used = ubi->free = ubi->scrub = RB_ROOT;
|
||||
ubi->prot.pnum = ubi->prot.aec = RB_ROOT;
|
||||
spin_lock_init(&ubi->wl_lock);
|
||||
mutex_init(&ubi->move_mutex);
|
||||
init_rwsem(&ubi->work_sem);
|
||||
|
@ -1458,6 +1387,10 @@ int ubi_wl_init_scan(struct ubi_device *ubi, struct ubi_scan_info *si)
|
|||
if (!ubi->lookuptbl)
|
||||
return err;
|
||||
|
||||
for (i = 0; i < UBI_PROT_QUEUE_LEN; i++)
|
||||
INIT_LIST_HEAD(&ubi->pq[i]);
|
||||
ubi->pq_head = 0;
|
||||
|
||||
list_for_each_entry_safe(seb, tmp, &si->erase, u.list) {
|
||||
cond_resched();
|
||||
|
||||
|
@ -1552,33 +1485,18 @@ out_free:
|
|||
}
|
||||
|
||||
/**
|
||||
* protection_trees_destroy - destroy the protection RB-trees.
|
||||
* protection_queue_destroy - destroy the protection queue.
|
||||
* @ubi: UBI device description object
|
||||
*/
|
||||
static void protection_trees_destroy(struct ubi_device *ubi)
|
||||
static void protection_queue_destroy(struct ubi_device *ubi)
|
||||
{
|
||||
struct rb_node *rb;
|
||||
struct ubi_wl_prot_entry *pe;
|
||||
int i;
|
||||
struct ubi_wl_entry *e, *tmp;
|
||||
|
||||
rb = ubi->prot.aec.rb_node;
|
||||
while (rb) {
|
||||
if (rb->rb_left)
|
||||
rb = rb->rb_left;
|
||||
else if (rb->rb_right)
|
||||
rb = rb->rb_right;
|
||||
else {
|
||||
pe = rb_entry(rb, struct ubi_wl_prot_entry, rb_aec);
|
||||
|
||||
rb = rb_parent(rb);
|
||||
if (rb) {
|
||||
if (rb->rb_left == &pe->rb_aec)
|
||||
rb->rb_left = NULL;
|
||||
else
|
||||
rb->rb_right = NULL;
|
||||
}
|
||||
|
||||
kmem_cache_free(ubi_wl_entry_slab, pe->e);
|
||||
kfree(pe);
|
||||
for (i = 0; i < UBI_PROT_QUEUE_LEN; ++i) {
|
||||
list_for_each_entry_safe(e, tmp, &ubi->pq[i], u.list) {
|
||||
list_del(&e->u.list);
|
||||
kmem_cache_free(ubi_wl_entry_slab, e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
@ -1591,7 +1509,7 @@ void ubi_wl_close(struct ubi_device *ubi)
|
|||
{
|
||||
dbg_wl("close the WL sub-system");
|
||||
cancel_pending(ubi);
|
||||
protection_trees_destroy(ubi);
|
||||
protection_queue_destroy(ubi);
|
||||
tree_destroy(&ubi->used);
|
||||
tree_destroy(&ubi->free);
|
||||
tree_destroy(&ubi->scrub);
|
||||
|
@ -1661,4 +1579,27 @@ static int paranoid_check_in_wl_tree(struct ubi_wl_entry *e,
|
|||
return 1;
|
||||
}
|
||||
|
||||
/**
|
||||
* paranoid_check_in_pq - check if wear-leveling entry is in the protection
|
||||
* queue.
|
||||
* @ubi: UBI device description object
|
||||
* @e: the wear-leveling entry to check
|
||||
*
|
||||
* This function returns zero if @e is in @ubi->pq and %1 if it is not.
|
||||
*/
|
||||
static int paranoid_check_in_pq(struct ubi_device *ubi, struct ubi_wl_entry *e)
|
||||
{
|
||||
struct ubi_wl_entry *p;
|
||||
int i;
|
||||
|
||||
for (i = 0; i < UBI_PROT_QUEUE_LEN; ++i)
|
||||
list_for_each_entry(p, &ubi->pq[i], u.list)
|
||||
if (p == e)
|
||||
return 0;
|
||||
|
||||
ubi_err("paranoid check failed for PEB %d, EC %d, Protect queue",
|
||||
e->pnum, e->ec);
|
||||
ubi_dbg_dump_stack();
|
||||
return 1;
|
||||
}
|
||||
#endif /* CONFIG_MTD_UBI_DEBUG_PARANOID */
|
||||
|
|
Loading…
Reference in New Issue