diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-08 20:40:45 +0900 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-10-08 20:40:45 +0900 |
commit | e9eca4de957ac33744fb994ccacd4a5102e445a8 (patch) | |
tree | fc1cf7c808d3daa365a56856321834d030fcf10d /drivers/mtd | |
parent | 1929041bd8afeb3995b7c68d6f16e03422848a4c (diff) | |
parent | 76ac66e469f084d41742ba08923de76fbdc7dce3 (diff) | |
download | linux-stable-e9eca4de957ac33744fb994ccacd4a5102e445a8.tar.gz linux-stable-e9eca4de957ac33744fb994ccacd4a5102e445a8.tar.bz2 linux-stable-e9eca4de957ac33744fb994ccacd4a5102e445a8.zip |
Merge tag 'upstream-3.7-rc1-fastmap' of git://git.infradead.org/linux-ubi
Pull UBI fastmap changes from Artem Bityutskiy:
"This pull request contains the UBI fastmap support implemented by
Richard Weinberger from Linutronix. Fastmap is designed to address
UBI's slow scanning issues. Namely, it introduces a new on-flash
data-structure called "fastmap", which stores the information about
logical<->physical eraseblocks mappings. So now to get this
information just read the fastmap, instead of doing full scan. More
information here can be found in Richard's announcement in LKML
(Subject: UBI: Fastmap request for inclusion (v19)):
http://thread.gmane.org/gmane.linux.kernel/1364922/focus=1369109
One thing I want to explicitly say is that fastmap did not have large
enough linux-next exposure. It is partially my fault - I did not
respond quickly enough. I _really_ apologize for this. But it had
good testing and disabled by default, so I do not expect that we'll
break anything.
Fastmap is declared as experimental so far, and it is off by default.
We did declare that the on-flash format may be changed. The reason
for this is that no one used it in real production so far, so there is
a high risk that something is missing. Besides, we do not have
user-space tools supporting fastmap so far.
Nevertheless, I suggest we merge this feature. Many people want UBI's
scanning bottleneck to be fixed and merging fastmap now should
accelerate its production use. The plan is to make it bullet-prove,
somewhat clean-up, and make it the default for UBI. I do not know how
many kernel releases will it take.
Basically, I what I want to do for fastmap is something like Linus did
for btrfs few years ago."
* tag 'upstream-3.7-rc1-fastmap' of git://git.infradead.org/linux-ubi:
UBI: Wire-up fastmap
UBI: Add fastmap core
UBI: Add fastmap support to the WL sub-system
UBI: Add fastmap stuff to attach.c
UBI: Wire-up ->fm_sem
UBI: Add fastmap bits to build.c
UBI: Add self_check_eba()
UBI: Export next_sqnum()
UBI: Add fastmap stuff to ubi.h
UBI: Add fastmap on-flash data structures
Diffstat (limited to 'drivers/mtd')
-rw-r--r-- | drivers/mtd/ubi/Kconfig | 21 | ||||
-rw-r--r-- | drivers/mtd/ubi/Makefile | 1 | ||||
-rw-r--r-- | drivers/mtd/ubi/attach.c | 386 | ||||
-rw-r--r-- | drivers/mtd/ubi/build.c | 70 | ||||
-rw-r--r-- | drivers/mtd/ubi/eba.c | 126 | ||||
-rw-r--r-- | drivers/mtd/ubi/fastmap.c | 1537 | ||||
-rw-r--r-- | drivers/mtd/ubi/ubi-media.h | 137 | ||||
-rw-r--r-- | drivers/mtd/ubi/ubi.h | 118 | ||||
-rw-r--r-- | drivers/mtd/ubi/wl.c | 599 |
9 files changed, 2784 insertions, 211 deletions
diff --git a/drivers/mtd/ubi/Kconfig b/drivers/mtd/ubi/Kconfig index 271a842f8c39..36663af56d89 100644 --- a/drivers/mtd/ubi/Kconfig +++ b/drivers/mtd/ubi/Kconfig @@ -56,6 +56,27 @@ config MTD_UBI_BEB_LIMIT Leave the default value if unsure. +config MTD_UBI_FASTMAP + bool "UBI Fastmap (Experimental feature)" + default n + help + Important: this feature is experimental so far and the on-flash + format for fastmap may change in the next kernel versions + + Fastmap is a mechanism which allows attaching an UBI device + in nearly constant time. Instead of scanning the whole MTD device it + only has to locate a checkpoint (called fastmap) on the device. + The on-flash fastmap contains all information needed to attach + the device. Using fastmap makes only sense on large devices where + attaching by scanning takes long. UBI will not automatically install + a fastmap on old images, but you can set the UBI module parameter + fm_autoconvert to 1 if you want so. Please note that fastmap-enabled + images are still usable with UBI implementations without + fastmap support. On typical flash devices the whole fastmap fits + into one PEB. UBI will reserve PEBs to hold two fastmaps. + + If in doubt, say "N". + config MTD_UBI_GLUEBI tristate "MTD devices emulation driver (gluebi)" help diff --git a/drivers/mtd/ubi/Makefile b/drivers/mtd/ubi/Makefile index a0803ac74712..b46b0c978581 100644 --- a/drivers/mtd/ubi/Makefile +++ b/drivers/mtd/ubi/Makefile @@ -2,5 +2,6 @@ obj-$(CONFIG_MTD_UBI) += ubi.o ubi-y += vtbl.o vmt.o upd.o build.o cdev.o kapi.o eba.o io.o wl.o attach.o ubi-y += misc.o debug.o +ubi-$(CONFIG_MTD_UBI_FASTMAP) += fastmap.o obj-$(CONFIG_MTD_UBI_GLUEBI) += gluebi.o diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c index f7adf53e4f45..fec406b4553d 100644 --- a/drivers/mtd/ubi/attach.c +++ b/drivers/mtd/ubi/attach.c @@ -300,7 +300,7 @@ static struct ubi_ainf_volume *add_volume(struct ubi_attach_info *ai, } /** - * compare_lebs - find out which logical eraseblock is newer. + * ubi_compare_lebs - find out which logical eraseblock is newer. * @ubi: UBI device description object * @aeb: first logical eraseblock to compare * @pnum: physical eraseblock number of the second logical eraseblock to @@ -319,7 +319,7 @@ static struct ubi_ainf_volume *add_volume(struct ubi_attach_info *ai, * o bit 2 is cleared: the older LEB is not corrupted; * o bit 2 is set: the older LEB is corrupted. */ -static int compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb, +int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb, int pnum, const struct ubi_vid_hdr *vid_hdr) { void *buf; @@ -337,7 +337,7 @@ static int compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb, * support these images anymore. Well, those images still work, * but only if no unclean reboots happened. */ - ubi_err("unsupported on-flash UBI format\n"); + ubi_err("unsupported on-flash UBI format"); return -EINVAL; } @@ -507,7 +507,7 @@ int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum, * sequence numbers. We still can attach these images, unless * there is a need to distinguish between old and new * eraseblocks, in which case we'll refuse the image in - * 'compare_lebs()'. In other words, we attach old clean + * 'ubi_compare_lebs()'. In other words, we attach old clean * images, but refuse attaching old images with duplicated * logical eraseblocks because there was an unclean reboot. */ @@ -523,7 +523,7 @@ int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum, * Now we have to drop the older one and preserve the newer * one. */ - cmp_res = compare_lebs(ubi, aeb, pnum, vid_hdr); + cmp_res = ubi_compare_lebs(ubi, aeb, pnum, vid_hdr); if (cmp_res < 0) return cmp_res; @@ -748,7 +748,7 @@ struct ubi_ainf_peb *ubi_early_get_peb(struct ubi_device *ubi, /** * check_corruption - check the data area of PEB. * @ubi: UBI device description object - * @vid_hrd: the (corrupted) VID header of this PEB + * @vid_hdr: the (corrupted) VID header of this PEB * @pnum: the physical eraseblock number to check * * This is a helper function which is used to distinguish between VID header @@ -810,6 +810,8 @@ out_unlock: * @ubi: UBI device description object * @ai: attaching information * @pnum: the physical eraseblock number + * @vid: The volume ID of the found volume will be stored in this pointer + * @sqnum: The sqnum of the found volume will be stored in this pointer * * This function reads UBI headers of PEB @pnum, checks them, and adds * information about this PEB to the corresponding list or RB-tree in the @@ -817,10 +819,10 @@ out_unlock: * successfully handled and a negative error code in case of failure. */ static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai, - int pnum) + int pnum, int *vid, unsigned long long *sqnum) { long long uninitialized_var(ec); - int err, bitflips = 0, vol_id, ec_err = 0; + int err, bitflips = 0, vol_id = -1, ec_err = 0; dbg_bld("scan PEB %d", pnum); @@ -991,14 +993,21 @@ static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai, } vol_id = be32_to_cpu(vidh->vol_id); + if (vid) + *vid = vol_id; + if (sqnum) + *sqnum = be64_to_cpu(vidh->sqnum); if (vol_id > UBI_MAX_VOLUMES && vol_id != UBI_LAYOUT_VOLUME_ID) { int lnum = be32_to_cpu(vidh->lnum); /* Unsupported internal volume */ switch (vidh->compat) { case UBI_COMPAT_DELETE: - ubi_msg("\"delete\" compatible internal volume %d:%d found, will remove it", - vol_id, lnum); + if (vol_id != UBI_FM_SB_VOLUME_ID + && vol_id != UBI_FM_DATA_VOLUME_ID) { + ubi_msg("\"delete\" compatible internal volume %d:%d found, will remove it", + vol_id, lnum); + } err = add_to_list(ai, pnum, vol_id, lnum, ec, 1, &ai->erase); if (err) @@ -1121,51 +1130,126 @@ static int late_analysis(struct ubi_device *ubi, struct ubi_attach_info *ai) } /** + * destroy_av - free volume attaching information. + * @av: volume attaching information + * @ai: attaching information + * + * This function destroys the volume attaching information. + */ +static void destroy_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av) +{ + struct ubi_ainf_peb *aeb; + struct rb_node *this = av->root.rb_node; + + while (this) { + if (this->rb_left) + this = this->rb_left; + else if (this->rb_right) + this = this->rb_right; + else { + aeb = rb_entry(this, struct ubi_ainf_peb, u.rb); + this = rb_parent(this); + if (this) { + if (this->rb_left == &aeb->u.rb) + this->rb_left = NULL; + else + this->rb_right = NULL; + } + + kmem_cache_free(ai->aeb_slab_cache, aeb); + } + } + kfree(av); +} + +/** + * destroy_ai - destroy attaching information. + * @ai: attaching information + */ +static void destroy_ai(struct ubi_attach_info *ai) +{ + struct ubi_ainf_peb *aeb, *aeb_tmp; + struct ubi_ainf_volume *av; + struct rb_node *rb; + + list_for_each_entry_safe(aeb, aeb_tmp, &ai->alien, u.list) { + list_del(&aeb->u.list); + kmem_cache_free(ai->aeb_slab_cache, aeb); + } + list_for_each_entry_safe(aeb, aeb_tmp, &ai->erase, u.list) { + list_del(&aeb->u.list); + kmem_cache_free(ai->aeb_slab_cache, aeb); + } + list_for_each_entry_safe(aeb, aeb_tmp, &ai->corr, u.list) { + list_del(&aeb->u.list); + kmem_cache_free(ai->aeb_slab_cache, aeb); + } + list_for_each_entry_safe(aeb, aeb_tmp, &ai->free, u.list) { + list_del(&aeb->u.list); + kmem_cache_free(ai->aeb_slab_cache, aeb); + } + + /* Destroy the volume RB-tree */ + rb = ai->volumes.rb_node; + while (rb) { + if (rb->rb_left) + rb = rb->rb_left; + else if (rb->rb_right) + rb = rb->rb_right; + else { + av = rb_entry(rb, struct ubi_ainf_volume, rb); + + rb = rb_parent(rb); + if (rb) { + if (rb->rb_left == &av->rb) + rb->rb_left = NULL; + else + rb->rb_right = NULL; + } + + destroy_av(ai, av); + } + } + + if (ai->aeb_slab_cache) + kmem_cache_destroy(ai->aeb_slab_cache); + + kfree(ai); +} + +/** * scan_all - scan entire MTD device. * @ubi: UBI device description object + * @ai: attach info object + * @start: start scanning at this PEB * * This function does full scanning of an MTD device and returns complete * information about it in form of a "struct ubi_attach_info" object. In case * of failure, an error code is returned. */ -static struct ubi_attach_info *scan_all(struct ubi_device *ubi) +static int scan_all(struct ubi_device *ubi, struct ubi_attach_info *ai, + int start) { int err, pnum; struct rb_node *rb1, *rb2; struct ubi_ainf_volume *av; struct ubi_ainf_peb *aeb; - struct ubi_attach_info *ai; - - ai = kzalloc(sizeof(struct ubi_attach_info), GFP_KERNEL); - if (!ai) - return ERR_PTR(-ENOMEM); - - INIT_LIST_HEAD(&ai->corr); - INIT_LIST_HEAD(&ai->free); - INIT_LIST_HEAD(&ai->erase); - INIT_LIST_HEAD(&ai->alien); - ai->volumes = RB_ROOT; err = -ENOMEM; - ai->aeb_slab_cache = kmem_cache_create("ubi_aeb_slab_cache", - sizeof(struct ubi_ainf_peb), - 0, 0, NULL); - if (!ai->aeb_slab_cache) - goto out_ai; ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); if (!ech) - goto out_ai; + return err; vidh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL); if (!vidh) goto out_ech; - for (pnum = 0; pnum < ubi->peb_count; pnum++) { + for (pnum = start; pnum < ubi->peb_count; pnum++) { cond_resched(); dbg_gen("process PEB %d", pnum); - err = scan_peb(ubi, ai, pnum); + err = scan_peb(ubi, ai, pnum, NULL, NULL); if (err < 0) goto out_vidh; } @@ -1210,32 +1294,144 @@ static struct ubi_attach_info *scan_all(struct ubi_device *ubi) ubi_free_vid_hdr(ubi, vidh); kfree(ech); - return ai; + return 0; out_vidh: ubi_free_vid_hdr(ubi, vidh); out_ech: kfree(ech); -out_ai: - ubi_destroy_ai(ai); - return ERR_PTR(err); + return err; +} + +#ifdef CONFIG_MTD_UBI_FASTMAP + +/** + * scan_fastmap - try to find a fastmap and attach from it. + * @ubi: UBI device description object + * @ai: attach info object + * + * Returns 0 on success, negative return values indicate an internal + * error. + * UBI_NO_FASTMAP denotes that no fastmap was found. + * UBI_BAD_FASTMAP denotes that the found fastmap was invalid. + */ +static int scan_fast(struct ubi_device *ubi, struct ubi_attach_info *ai) +{ + int err, pnum, fm_anchor = -1; + unsigned long long max_sqnum = 0; + + err = -ENOMEM; + + ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); + if (!ech) + goto out; + + vidh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL); + if (!vidh) + goto out_ech; + + for (pnum = 0; pnum < UBI_FM_MAX_START; pnum++) { + int vol_id = -1; + unsigned long long sqnum = -1; + cond_resched(); + + dbg_gen("process PEB %d", pnum); + err = scan_peb(ubi, ai, pnum, &vol_id, &sqnum); + if (err < 0) + goto out_vidh; + + if (vol_id == UBI_FM_SB_VOLUME_ID && sqnum > max_sqnum) { + max_sqnum = sqnum; + fm_anchor = pnum; + } + } + + ubi_free_vid_hdr(ubi, vidh); + kfree(ech); + + if (fm_anchor < 0) + return UBI_NO_FASTMAP; + + return ubi_scan_fastmap(ubi, ai, fm_anchor); + +out_vidh: + ubi_free_vid_hdr(ubi, vidh); +out_ech: + kfree(ech); +out: + return err; +} + +#endif + +static struct ubi_attach_info *alloc_ai(const char *slab_name) +{ + struct ubi_attach_info *ai; + + ai = kzalloc(sizeof(struct ubi_attach_info), GFP_KERNEL); + if (!ai) + return ai; + + INIT_LIST_HEAD(&ai->corr); + INIT_LIST_HEAD(&ai->free); + INIT_LIST_HEAD(&ai->erase); + INIT_LIST_HEAD(&ai->alien); + ai->volumes = RB_ROOT; + ai->aeb_slab_cache = kmem_cache_create(slab_name, + sizeof(struct ubi_ainf_peb), + 0, 0, NULL); + if (!ai->aeb_slab_cache) { + kfree(ai); + ai = NULL; + } + + return ai; } /** * ubi_attach - attach an MTD device. * @ubi: UBI device descriptor + * @force_scan: if set to non-zero attach by scanning * * This function returns zero in case of success and a negative error code in * case of failure. */ -int ubi_attach(struct ubi_device *ubi) +int ubi_attach(struct ubi_device *ubi, int force_scan) { int err; struct ubi_attach_info *ai; - ai = scan_all(ubi); - if (IS_ERR(ai)) - return PTR_ERR(ai); + ai = alloc_ai("ubi_aeb_slab_cache"); + if (!ai) + return -ENOMEM; + +#ifdef CONFIG_MTD_UBI_FASTMAP + /* On small flash devices we disable fastmap in any case. */ + if ((int)mtd_div_by_eb(ubi->mtd->size, ubi->mtd) <= UBI_FM_MAX_START) { + ubi->fm_disabled = 1; + force_scan = 1; + } + + if (force_scan) + err = scan_all(ubi, ai, 0); + else { + err = scan_fast(ubi, ai); + if (err > 0) { + if (err != UBI_NO_FASTMAP) { + destroy_ai(ai); + ai = alloc_ai("ubi_aeb_slab_cache2"); + if (!ai) + return -ENOMEM; + } + + err = scan_all(ubi, ai, UBI_FM_MAX_START); + } + } +#else + err = scan_all(ubi, ai, 0); +#endif + if (err) + goto out_ai; ubi->bad_peb_count = ai->bad_peb_count; ubi->good_peb_count = ubi->peb_count - ubi->bad_peb_count; @@ -1256,7 +1452,29 @@ int ubi_attach(struct ubi_device *ubi) if (err) goto out_wl; - ubi_destroy_ai(ai); +#ifdef CONFIG_MTD_UBI_FASTMAP + if (ubi->fm && ubi->dbg->chk_gen) { + struct ubi_attach_info *scan_ai; + + scan_ai = alloc_ai("ubi_ckh_aeb_slab_cache"); + if (!scan_ai) + goto out_wl; + + err = scan_all(ubi, scan_ai, 0); + if (err) { + destroy_ai(scan_ai); + goto out_wl; + } + + err = self_check_eba(ubi, ai, scan_ai); + destroy_ai(scan_ai); + + if (err) + goto out_wl; + } +#endif + + destroy_ai(ai); return 0; out_wl: @@ -1265,99 +1483,11 @@ out_vtbl: ubi_free_internal_volumes(ubi); vfree(ubi->vtbl); out_ai: - ubi_destroy_ai(ai); + destroy_ai(ai); return err; } /** - * destroy_av - free volume attaching information. - * @av: volume attaching information - * @ai: attaching information - * - * This function destroys the volume attaching information. - */ -static void destroy_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av) -{ - struct ubi_ainf_peb *aeb; - struct rb_node *this = av->root.rb_node; - - while (this) { - if (this->rb_left) - this = this->rb_left; - else if (this->rb_right) - this = this->rb_right; - else { - aeb = rb_entry(this, struct ubi_ainf_peb, u.rb); - this = rb_parent(this); - if (this) { - if (this->rb_left == &aeb->u.rb) - this->rb_left = NULL; - else - this->rb_right = NULL; - } - - kmem_cache_free(ai->aeb_slab_cache, aeb); - } - } - kfree(av); -} - -/** - * ubi_destroy_ai - destroy attaching information. - * @ai: attaching information - */ -void ubi_destroy_ai(struct ubi_attach_info *ai) -{ - struct ubi_ainf_peb *aeb, *aeb_tmp; - struct ubi_ainf_volume *av; - struct rb_node *rb; - - list_for_each_entry_safe(aeb, aeb_tmp, &ai->alien, u.list) { - list_del(&aeb->u.list); - kmem_cache_free(ai->aeb_slab_cache, aeb); - } - list_for_each_entry_safe(aeb, aeb_tmp, &ai->erase, u.list) { - list_del(&aeb->u.list); - kmem_cache_free(ai->aeb_slab_cache, aeb); - } - list_for_each_entry_safe(aeb, aeb_tmp, &ai->corr, u.list) { - list_del(&aeb->u.list); - kmem_cache_free(ai->aeb_slab_cache, aeb); - } - list_for_each_entry_safe(aeb, aeb_tmp, &ai->free, u.list) { - list_del(&aeb->u.list); - kmem_cache_free(ai->aeb_slab_cache, aeb); - } - - /* Destroy the volume RB-tree */ - rb = ai->volumes.rb_node; - while (rb) { - if (rb->rb_left) - rb = rb->rb_left; - else if (rb->rb_right) - rb = rb->rb_right; - else { - av = rb_entry(rb, struct ubi_ainf_volume, rb); - - rb = rb_parent(rb); - if (rb) { - if (rb->rb_left == &av->rb) - rb->rb_left = NULL; - else - rb->rb_right = NULL; - } - - destroy_av(ai, av); - } - } - - if (ai->aeb_slab_cache) - kmem_cache_destroy(ai->aeb_slab_cache); - - kfree(ai); -} - -/** * self_check_ai - check the attaching information. * @ubi: UBI device description object * @ai: attaching information diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 34977039850c..344b4cb49d4e 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -76,7 +76,10 @@ static int __initdata mtd_devs; /* MTD devices specification parameters */ static struct mtd_dev_param __initdata mtd_dev_param[UBI_MAX_DEVICES]; - +#ifdef CONFIG_MTD_UBI_FASTMAP +/* UBI module parameter to enable fastmap automatically on non-fastmap images */ +static bool fm_autoconvert; +#endif /* Root UBI "class" object (corresponds to '/<sysfs>/class/ubi/') */ struct class *ubi_class; @@ -153,6 +156,19 @@ int ubi_volume_notify(struct ubi_device *ubi, struct ubi_volume *vol, int ntype) ubi_do_get_device_info(ubi, &nt.di); ubi_do_get_volume_info(ubi, vol, &nt.vi); + +#ifdef CONFIG_MTD_UBI_FASTMAP + switch (ntype) { + case UBI_VOLUME_ADDED: + case UBI_VOLUME_REMOVED: + case UBI_VOLUME_RESIZED: + case UBI_VOLUME_RENAMED: + if (ubi_update_fastmap(ubi)) { + ubi_err("Unable to update fastmap!"); + ubi_ro_mode(ubi); + } + } +#endif return blocking_notifier_call_chain(&ubi_notifiers, ntype, &nt); } @@ -918,10 +934,40 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, ubi->vid_hdr_offset = vid_hdr_offset; ubi->autoresize_vol_id = -1; +#ifdef CONFIG_MTD_UBI_FASTMAP + ubi->fm_pool.used = ubi->fm_pool.size = 0; + ubi->fm_wl_pool.used = ubi->fm_wl_pool.size = 0; + + /* + * fm_pool.max_size is 5% of the total number of PEBs but it's also + * between UBI_FM_MAX_POOL_SIZE and UBI_FM_MIN_POOL_SIZE. + */ + ubi->fm_pool.max_size = min(((int)mtd_div_by_eb(ubi->mtd->size, + ubi->mtd) / 100) * 5, UBI_FM_MAX_POOL_SIZE); + if (ubi->fm_pool.max_size < UBI_FM_MIN_POOL_SIZE) + ubi->fm_pool.max_size = UBI_FM_MIN_POOL_SIZE; + + ubi->fm_wl_pool.max_size = UBI_FM_WL_POOL_SIZE; + ubi->fm_disabled = !fm_autoconvert; + + if (!ubi->fm_disabled && (int)mtd_div_by_eb(ubi->mtd->size, ubi->mtd) + <= UBI_FM_MAX_START) { + ubi_err("More than %i PEBs are needed for fastmap, sorry.", + UBI_FM_MAX_START); + ubi->fm_disabled = 1; + } + + ubi_msg("default fastmap pool size: %d", ubi->fm_pool.max_size); + ubi_msg("default fastmap WL pool size: %d", ubi->fm_wl_pool.max_size); +#else + ubi->fm_disabled = 1; +#endif mutex_init(&ubi->buf_mutex); mutex_init(&ubi->ckvol_mutex); mutex_init(&ubi->device_mutex); spin_lock_init(&ubi->volumes_lock); + mutex_init(&ubi->fm_mutex); + init_rwsem(&ubi->fm_sem); ubi_msg("attaching mtd%d to ubi%d", mtd->index, ubi_num); @@ -934,11 +980,17 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, if (!ubi->peb_buf) goto out_free; +#ifdef CONFIG_MTD_UBI_FASTMAP + ubi->fm_size = ubi_calc_fm_size(ubi); + ubi->fm_buf = vzalloc(ubi->fm_size); + if (!ubi->fm_buf) + goto out_free; +#endif err = ubi_debugging_init_dev(ubi); if (err) goto out_free; - err = ubi_attach(ubi); + err = ubi_attach(ubi, 0); if (err) { ubi_err("failed to attach mtd%d, error %d", mtd->index, err); goto out_debugging; @@ -1012,6 +1064,7 @@ out_debugging: ubi_debugging_exit_dev(ubi); out_free: vfree(ubi->peb_buf); + vfree(ubi->fm_buf); if (ref) put_device(&ubi->dev); else @@ -1061,7 +1114,11 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway) ubi_assert(ubi_num == ubi->ubi_num); ubi_notify_all(ubi, UBI_VOLUME_REMOVED, NULL); ubi_msg("detaching mtd%d from ubi%d", ubi->mtd->index, ubi_num); - +#ifdef CONFIG_MTD_UBI_FASTMAP + /* If we don't write a new fastmap at detach time we lose all + * EC updates that have been made since the last written fastmap. */ + ubi_update_fastmap(ubi); +#endif /* * Before freeing anything, we have to stop the background thread to * prevent it from doing anything on this device while we are freeing. @@ -1077,12 +1134,14 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway) ubi_debugfs_exit_dev(ubi); uif_close(ubi); + ubi_wl_close(ubi); ubi_free_internal_volumes(ubi); vfree(ubi->vtbl); put_mtd_device(ubi->mtd); ubi_debugging_exit_dev(ubi); vfree(ubi->peb_buf); + vfree(ubi->fm_buf); ubi_msg("mtd%d is detached from ubi%d", ubi->mtd->index, ubi->ubi_num); put_device(&ubi->dev); return 0; @@ -1404,7 +1463,10 @@ MODULE_PARM_DESC(mtd, "MTD devices to attach. Parameter format: mtd=<name|num|pa "Example 2: mtd=content,1984 mtd=4 - attach MTD device with name \"content\" using VID header offset 1984, and MTD device number 4 with default VID header offset.\n" "Example 3: mtd=/dev/mtd1,0,25 - attach MTD device /dev/mtd1 using default VID header offset and reserve 25*nand_size_in_blocks/1024 erase blocks for bad block handling.\n" "\t(e.g. if the NAND *chipset* has 4096 PEB, 100 will be reserved for this UBI device)."); - +#ifdef CONFIG_MTD_UBI_FASTMAP +module_param(fm_autoconvert, bool, 0644); +MODULE_PARM_DESC(fm_autoconvert, "Set this parameter to enable fastmap automatically on images without a fastmap."); +#endif MODULE_VERSION(__stringify(UBI_VERSION)); MODULE_DESCRIPTION("UBI - Unsorted Block Images"); MODULE_AUTHOR("Artem Bityutskiy"); diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index a26d7d253174..0e11671dadc4 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -57,7 +57,7 @@ * global sequence counter value. It also increases the global sequence * counter. */ -static unsigned long long next_sqnum(struct ubi_device *ubi) +unsigned long long ubi_next_sqnum(struct ubi_device *ubi) { unsigned long long sqnum; @@ -340,7 +340,9 @@ int ubi_eba_unmap_leb(struct ubi_device *ubi, struct ubi_volume *vol, dbg_eba("erase LEB %d:%d, PEB %d", vol_id, lnum, pnum); + down_read(&ubi->fm_sem); vol->eba_tbl[lnum] = UBI_LEB_UNMAPPED; + up_read(&ubi->fm_sem); err = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 0); out_unlock: @@ -521,7 +523,7 @@ retry: goto out_put; } - vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi)); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); err = ubi_io_write_vid_hdr(ubi, new_pnum, vid_hdr); if (err) goto write_error; @@ -548,7 +550,9 @@ retry: mutex_unlock(&ubi->buf_mutex); ubi_free_vid_hdr(ubi, vid_hdr); + down_read(&ubi->fm_sem); vol->eba_tbl[lnum] = new_pnum; + up_read(&ubi->fm_sem); ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1); ubi_msg("data was successfully recovered"); @@ -632,7 +636,7 @@ int ubi_eba_write_leb(struct ubi_device *ubi, struct ubi_volume *vol, int lnum, } vid_hdr->vol_type = UBI_VID_DYNAMIC; - vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi)); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); vid_hdr->vol_id = cpu_to_be32(vol_id); vid_hdr->lnum = cpu_to_be32(lnum); vid_hdr->compat = ubi_get_compat(ubi, vol_id); @@ -665,7 +669,9 @@ retry: } } + down_read(&ubi->fm_sem); vol->eba_tbl[lnum] = pnum; + up_read(&ubi->fm_sem); leb_write_unlock(ubi, vol_id, lnum); ubi_free_vid_hdr(ubi, vid_hdr); @@ -692,7 +698,7 @@ write_error: return err; } - vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi)); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); ubi_msg("try another PEB"); goto retry; } @@ -745,7 +751,7 @@ int ubi_eba_write_leb_st(struct ubi_device *ubi, struct ubi_volume *vol, return err; } - vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi)); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); vid_hdr->vol_id = cpu_to_be32(vol_id); vid_hdr->lnum = cpu_to_be32(lnum); vid_hdr->compat = ubi_get_compat(ubi, vol_id); @@ -783,7 +789,9 @@ retry: } ubi_assert(vol->eba_tbl[lnum] < 0); + down_read(&ubi->fm_sem); vol->eba_tbl[lnum] = pnum; + up_read(&ubi->fm_sem); leb_write_unlock(ubi, vol_id, lnum); ubi_free_vid_hdr(ubi, vid_hdr); @@ -810,7 +818,7 @@ write_error: return err; } - vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi)); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); ubi_msg("try another PEB"); goto retry; } @@ -862,7 +870,7 @@ int ubi_eba_atomic_leb_change(struct ubi_device *ubi, struct ubi_volume *vol, if (err) goto out_mutex; - vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi)); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); vid_hdr->vol_id = cpu_to_be32(vol_id); vid_hdr->lnum = cpu_to_be32(lnum); vid_hdr->compat = ubi_get_compat(ubi, vol_id); @@ -904,7 +912,9 @@ retry: goto out_leb_unlock; } + down_read(&ubi->fm_sem); vol->eba_tbl[lnum] = pnum; + up_read(&ubi->fm_sem); out_leb_unlock: leb_write_unlock(ubi, vol_id, lnum); @@ -930,7 +940,7 @@ write_error: goto out_leb_unlock; } - vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi)); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); ubi_msg("try another PEB"); goto retry; } @@ -1089,7 +1099,7 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to, vid_hdr->data_size = cpu_to_be32(data_size); vid_hdr->data_crc = cpu_to_be32(crc); } - vid_hdr->sqnum = cpu_to_be64(next_sqnum(ubi)); + vid_hdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); err = ubi_io_write_vid_hdr(ubi, to, vid_hdr); if (err) { @@ -1151,7 +1161,9 @@ int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to, } ubi_assert(vol->eba_tbl[lnum] == from); + down_read(&ubi->fm_sem); vol->eba_tbl[lnum] = to; + up_read(&ubi->fm_sem); out_unlock_buf: mutex_unlock(&ubi->buf_mutex); @@ -1202,6 +1214,102 @@ static void print_rsvd_warning(struct ubi_device *ubi, } /** + * self_check_eba - run a self check on the EBA table constructed by fastmap. + * @ubi: UBI device description object + * @ai_fastmap: UBI attach info object created by fastmap + * @ai_scan: UBI attach info object created by scanning + * + * Returns < 0 in case of an internal error, 0 otherwise. + * If a bad EBA table entry was found it will be printed out and + * ubi_assert() triggers. + */ +int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap, + struct ubi_attach_info *ai_scan) +{ + int i, j, num_volumes, ret = 0; + int **scan_eba, **fm_eba; + struct ubi_ainf_volume *av; + struct ubi_volume *vol; + struct ubi_ainf_peb *aeb; + struct rb_node *rb; + + num_volumes = ubi->vtbl_slots + UBI_INT_VOL_COUNT; + + scan_eba = kmalloc(sizeof(*scan_eba) * num_volumes, GFP_KERNEL); + if (!scan_eba) + return -ENOMEM; + + fm_eba = kmalloc(sizeof(*fm_eba) * num_volumes, GFP_KERNEL); + if (!fm_eba) { + kfree(scan_eba); + return -ENOMEM; + } + + for (i = 0; i < num_volumes; i++) { + vol = ubi->volumes[i]; + if (!vol) + continue; + + scan_eba[i] = kmalloc(vol->reserved_pebs * sizeof(**scan_eba), + GFP_KERNEL); + if (!scan_eba[i]) { + ret = -ENOMEM; + goto out_free; + } + + fm_eba[i] = kmalloc(vol->reserved_pebs * sizeof(**fm_eba), + GFP_KERNEL); + if (!fm_eba[i]) { + ret = -ENOMEM; + goto out_free; + } + + for (j = 0; j < vol->reserved_pebs; j++) + scan_eba[i][j] = fm_eba[i][j] = UBI_LEB_UNMAPPED; + + av = ubi_find_av(ai_scan, idx2vol_id(ubi, i)); + if (!av) + continue; + + ubi_rb_for_each_entry(rb, aeb, &av->root, u.rb) + scan_eba[i][aeb->lnum] = aeb->pnum; + + av = ubi_find_av(ai_fastmap, idx2vol_id(ubi, i)); + if (!av) + continue; + + ubi_rb_for_each_entry(rb, aeb, &av->root, u.rb) + fm_eba[i][aeb->lnum] = aeb->pnum; + + for (j = 0; j < vol->reserved_pebs; j++) { + if (scan_eba[i][j] != fm_eba[i][j]) { + if (scan_eba[i][j] == UBI_LEB_UNMAPPED || + fm_eba[i][j] == UBI_LEB_UNMAPPED) + continue; + + ubi_err("LEB:%i:%i is PEB:%i instead of %i!", + vol->vol_id, i, fm_eba[i][j], + scan_eba[i][j]); + ubi_assert(0); + } + } + } + +out_free: + for (i = 0; i < num_volumes; i++) { + if (!ubi->volumes[i]) + continue; + + kfree(scan_eba[i]); + kfree(fm_eba[i]); + } + + kfree(scan_eba); + kfree(fm_eba); + return ret; +} + +/** * ubi_eba_init - initialize the EBA sub-system using attaching information. * @ubi: UBI device description object * @ai: attaching information diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c new file mode 100644 index 000000000000..1a5f53c090d4 --- /dev/null +++ b/drivers/mtd/ubi/fastmap.c @@ -0,0 +1,1537 @@ +/* + * Copyright (c) 2012 Linutronix GmbH + * Author: Richard Weinberger <richard@nod.at> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU General Public License for more details. + * + */ + +#include <linux/crc32.h> +#include "ubi.h" + +/** + * ubi_calc_fm_size - calculates the fastmap size in bytes for an UBI device. + * @ubi: UBI device description object + */ +size_t ubi_calc_fm_size(struct ubi_device *ubi) +{ + size_t size; + + size = sizeof(struct ubi_fm_hdr) + \ + sizeof(struct ubi_fm_scan_pool) + \ + sizeof(struct ubi_fm_scan_pool) + \ + (ubi->peb_count * sizeof(struct ubi_fm_ec)) + \ + (sizeof(struct ubi_fm_eba) + \ + (ubi->peb_count * sizeof(__be32))) + \ + sizeof(struct ubi_fm_volhdr) * UBI_MAX_VOLUMES; + return roundup(size, ubi->leb_size); +} + + +/** + * new_fm_vhdr - allocate a new volume header for fastmap usage. + * @ubi: UBI device description object + * @vol_id: the VID of the new header + * + * Returns a new struct ubi_vid_hdr on success. + * NULL indicates out of memory. + */ +static struct ubi_vid_hdr *new_fm_vhdr(struct ubi_device *ubi, int vol_id) +{ + struct ubi_vid_hdr *new; + + new = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL); + if (!new) + goto out; + + new->vol_type = UBI_VID_DYNAMIC; + new->vol_id = cpu_to_be32(vol_id); + + /* UBI implementations without fastmap support have to delete the + * fastmap. + */ + new->compat = UBI_COMPAT_DELETE; + +out: + return new; +} + +/** + * add_aeb - create and add a attach erase block to a given list. + * @ai: UBI attach info object + * @list: the target list + * @pnum: PEB number of the new attach erase block + * @ec: erease counter of the new LEB + * @scrub: scrub this PEB after attaching + * + * Returns 0 on success, < 0 indicates an internal error. + */ +static int add_aeb(struct ubi_attach_info *ai, struct list_head *list, + int pnum, int ec, int scrub) +{ + struct ubi_ainf_peb *aeb; + + aeb = kmem_cache_alloc(ai->aeb_slab_cache, GFP_KERNEL); + if (!aeb) + return -ENOMEM; + + aeb->pnum = pnum; + aeb->ec = ec; + aeb->lnum = -1; + aeb->scrub = scrub; + aeb->copy_flag = aeb->sqnum = 0; + + ai->ec_sum += aeb->ec; + ai->ec_count++; + + if (ai->max_ec < aeb->ec) + ai->max_ec = aeb->ec; + + if (ai->min_ec > aeb->ec) + ai->min_ec = aeb->ec; + + list_add_tail(&aeb->u.list, list); + + return 0; +} + +/** + * add_vol - create and add a new volume to ubi_attach_info. + * @ai: ubi_attach_info object + * @vol_id: VID of the new volume + * @used_ebs: number of used EBS + * @data_pad: data padding value of the new volume + * @vol_type: volume type + * @last_eb_bytes: number of bytes in the last LEB + * + * Returns the new struct ubi_ainf_volume on success. + * NULL indicates an error. + */ +static struct ubi_ainf_volume *add_vol(struct ubi_attach_info *ai, int vol_id, + int used_ebs, int data_pad, u8 vol_type, + int last_eb_bytes) +{ + struct ubi_ainf_volume *av; + struct rb_node **p = &ai->volumes.rb_node, *parent = NULL; + + while (*p) { + parent = *p; + av = rb_entry(parent, struct ubi_ainf_volume, rb); + + if (vol_id > av->vol_id) + p = &(*p)->rb_left; + else if (vol_id > av->vol_id) + p = &(*p)->rb_right; + } + + av = kmalloc(sizeof(struct ubi_ainf_volume), GFP_KERNEL); + if (!av) + goto out; + + av->highest_lnum = av->leb_count = 0; + av->vol_id = vol_id; + av->used_ebs = used_ebs; + av->data_pad = data_pad; + av->last_data_size = last_eb_bytes; + av->compat = 0; + av->vol_type = vol_type; + av->root = RB_ROOT; + + dbg_bld("found volume (ID %i)", vol_id); + + rb_link_node(&av->rb, parent, p); + rb_insert_color(&av->rb, &ai->volumes); + +out: + return av; +} + +/** + * assign_aeb_to_av - assigns a SEB to a given ainf_volume and removes it + * from it's original list. + * @ai: ubi_attach_info object + * @aeb: the to be assigned SEB + * @av: target scan volume + */ +static void assign_aeb_to_av(struct ubi_attach_info *ai, + struct ubi_ainf_peb *aeb, + struct ubi_ainf_volume *av) +{ + struct ubi_ainf_peb *tmp_aeb; + struct rb_node **p = &ai->volumes.rb_node, *parent = NULL; + + p = &av->root.rb_node; + while (*p) { + parent = *p; + + tmp_aeb = rb_entry(parent, struct ubi_ainf_peb, u.rb); + if (aeb->lnum != tmp_aeb->lnum) { + if (aeb->lnum < tmp_aeb->lnum) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + + continue; + } else + break; + } + + list_del(&aeb->u.list); + av->leb_count++; + + rb_link_node(&aeb->u.rb, parent, p); + rb_insert_color(&aeb->u.rb, &av->root); +} + +/** + * update_vol - inserts or updates a LEB which was found a pool. + * @ubi: the UBI device object + * @ai: attach info object + * @av: the volume this LEB belongs to + * @new_vh: the volume header derived from new_aeb + * @new_aeb: the AEB to be examined + * + * Returns 0 on success, < 0 indicates an internal error. + */ +static int update_vol(struct ubi_device *ubi, struct ubi_attach_info *ai, + struct ubi_ainf_volume *av, struct ubi_vid_hdr *new_vh, + struct ubi_ainf_peb *new_aeb) +{ + struct rb_node **p = &av->root.rb_node, *parent = NULL; + struct ubi_ainf_peb *aeb, *victim; + int cmp_res; + + while (*p) { + parent = *p; + aeb = rb_entry(parent, struct ubi_ainf_peb, u.rb); + + if (be32_to_cpu(new_vh->lnum) != aeb->lnum) { + if (be32_to_cpu(new_vh->lnum) < aeb->lnum) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + + continue; + } + + /* This case can happen if the fastmap gets written + * because of a volume change (creation, deletion, ..). + * Then a PEB can be within the persistent EBA and the pool. + */ + if (aeb->pnum == new_aeb->pnum) { + ubi_assert(aeb->lnum == new_aeb->lnum); + kmem_cache_free(ai->aeb_slab_cache, new_aeb); + + return 0; + } + + cmp_res = ubi_compare_lebs(ubi, aeb, new_aeb->pnum, new_vh); + if (cmp_res < 0) + return cmp_res; + + /* new_aeb is newer */ + if (cmp_res & 1) { + victim = kmem_cache_alloc(ai->aeb_slab_cache, + GFP_KERNEL); + if (!victim) + return -ENOMEM; + + victim->ec = aeb->ec; + victim->pnum = aeb->pnum; + list_add_tail(&victim->u.list, &ai->erase); + + if (av->highest_lnum == be32_to_cpu(new_vh->lnum)) + av->last_data_size = \ + be32_to_cpu(new_vh->data_size); + + dbg_bld("vol %i: AEB %i's PEB %i is the newer", + av->vol_id, aeb->lnum, new_aeb->pnum); + + aeb->ec = new_aeb->ec; + aeb->pnum = new_aeb->pnum; + aeb->copy_flag = new_vh->copy_flag; + aeb->scrub = new_aeb->scrub; + kmem_cache_free(ai->aeb_slab_cache, new_aeb); + + /* new_aeb is older */ + } else { + dbg_bld("vol %i: AEB %i's PEB %i is old, dropping it", + av->vol_id, aeb->lnum, new_aeb->pnum); + list_add_tail(&new_aeb->u.list, &ai->erase); + } + + return 0; + } + /* This LEB is new, let's add it to the volume */ + + if (av->highest_lnum <= be32_to_cpu(new_vh->lnum)) { + av->highest_lnum = be32_to_cpu(new_vh->lnum); + av->last_data_size = be32_to_cpu(new_vh->data_size); + } + + if (av->vol_type == UBI_STATIC_VOLUME) + av->used_ebs = be32_to_cpu(new_vh->used_ebs); + + av->leb_count++; + + rb_link_node(&new_aeb->u.rb, parent, p); + rb_insert_color(&new_aeb->u.rb, &av->root); + + return 0; +} + +/** + * process_pool_aeb - we found a non-empty PEB in a pool. + * @ubi: UBI device object + * @ai: attach info object + * @new_vh: the volume header derived from new_aeb + * @new_aeb: the AEB to be examined + * + * Returns 0 on success, < 0 indicates an internal error. + */ +static int process_pool_aeb(struct ubi_device *ubi, struct ubi_attach_info *ai, + struct ubi_vid_hdr *new_vh, + struct ubi_ainf_peb *new_aeb) +{ + struct ubi_ainf_volume *av, *tmp_av = NULL; + struct rb_node **p = &ai->volumes.rb_node, *parent = NULL; + int found = 0; + + if (be32_to_cpu(new_vh->vol_id) == UBI_FM_SB_VOLUME_ID || + be32_to_cpu(new_vh->vol_id) == UBI_FM_DATA_VOLUME_ID) { + kmem_cache_free(ai->aeb_slab_cache, new_aeb); + + return 0; + } + + /* Find the volume this SEB belongs to */ + while (*p) { + parent = *p; + tmp_av = rb_entry(parent, struct ubi_ainf_volume, rb); + + if (be32_to_cpu(new_vh->vol_id) > tmp_av->vol_id) + p = &(*p)->rb_left; + else if (be32_to_cpu(new_vh->vol_id) < tmp_av->vol_id) + p = &(*p)->rb_right; + else { + found = 1; + break; + } + } + + if (found) + av = tmp_av; + else { + ubi_err("orphaned volume in fastmap pool!"); + return UBI_BAD_FASTMAP; + } + + ubi_assert(be32_to_cpu(new_vh->vol_id) == av->vol_id); + + return update_vol(ubi, ai, av, new_vh, new_aeb); +} + +/** + * unmap_peb - unmap a PEB. + * If fastmap detects a free PEB in the pool it has to check whether + * this PEB has been unmapped after writing the fastmap. + * + * @ai: UBI attach info object + * @pnum: The PEB to be unmapped + */ +static void unmap_peb(struct ubi_attach_info *ai, int pnum) +{ + struct ubi_ainf_volume *av; + struct rb_node *node, *node2; + struct ubi_ainf_peb *aeb; + + for (node = rb_first(&ai->volumes); node; node = rb_next(node)) { + av = rb_entry(node, struct ubi_ainf_volume, rb); + + for (node2 = rb_first(&av->root); node2; + node2 = rb_next(node2)) { + aeb = rb_entry(node2, struct ubi_ainf_peb, u.rb); + if (aeb->pnum == pnum) { + rb_erase(&aeb->u.rb, &av->root); + kmem_cache_free(ai->aeb_slab_cache, aeb); + return; + } + } + } +} + +/** + * scan_pool - scans a pool for changed (no longer empty PEBs). + * @ubi: UBI device object + * @ai: attach info object + * @pebs: an array of all PEB numbers in the to be scanned pool + * @pool_size: size of the pool (number of entries in @pebs) + * @max_sqnum: pointer to the maximal sequence number + * @eba_orphans: list of PEBs which need to be scanned + * @free: list of PEBs which are most likely free (and go into @ai->free) + * + * Returns 0 on success, if the pool is unusable UBI_BAD_FASTMAP is returned. + * < 0 indicates an internal error. + */ +static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai, + int *pebs, int pool_size, unsigned long long *max_sqnum, + struct list_head *eba_orphans, struct list_head *free) +{ + struct ubi_vid_hdr *vh; + struct ubi_ec_hdr *ech; + struct ubi_ainf_peb *new_aeb, *tmp_aeb; + int i, pnum, err, found_orphan, ret = 0; + + ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); + if (!ech) + return -ENOMEM; + + vh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL); + if (!vh) { + kfree(ech); + return -ENOMEM; + } + + dbg_bld("scanning fastmap pool: size = %i", pool_size); + + /* + * Now scan all PEBs in the pool to find changes which have been made + * after the creation of the fastmap + */ + for (i = 0; i < pool_size; i++) { + int scrub = 0; + + pnum = be32_to_cpu(pebs[i]); + + if (ubi_io_is_bad(ubi, pnum)) { + ubi_err("bad PEB in fastmap pool!"); + ret = UBI_BAD_FASTMAP; + goto out; + } + + err = ubi_io_read_ec_hdr(ubi, pnum, ech, 0); + if (err && err != UBI_IO_BITFLIPS) { + ubi_err("unable to read EC header! PEB:%i err:%i", + pnum, err); + ret = err > 0 ? UBI_BAD_FASTMAP : err; + goto out; + } else if (ret == UBI_IO_BITFLIPS) + scrub = 1; + + if (be32_to_cpu(ech->image_seq) != ubi->image_seq) { + ubi_err("bad image seq: 0x%x, expected: 0x%x", + be32_to_cpu(ech->image_seq), ubi->image_seq); + err = UBI_BAD_FASTMAP; + goto out; + } + + err = ubi_io_read_vid_hdr(ubi, pnum, vh, 0); + if (err == UBI_IO_FF || err == UBI_IO_FF_BITFLIPS) { + unsigned long long ec = be64_to_cpu(ech->ec); + unmap_peb(ai, pnum); + dbg_bld("Adding PEB to free: %i", pnum); + if (err == UBI_IO_FF_BITFLIPS) + add_aeb(ai, free, pnum, ec, 1); + else + add_aeb(ai, free, pnum, ec, 0); + continue; + } else if (err == 0 || err == UBI_IO_BITFLIPS) { + dbg_bld("Found non empty PEB:%i in pool", pnum); + + if (err == UBI_IO_BITFLIPS) + scrub = 1; + + found_orphan = 0; + list_for_each_entry(tmp_aeb, eba_orphans, u.list) { + if (tmp_aeb->pnum == pnum) { + found_orphan = 1; + break; + } + } + if (found_orphan) { + kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); + list_del(&tmp_aeb->u.list); + } + + new_aeb = kmem_cache_alloc(ai->aeb_slab_cache, + GFP_KERNEL); + if (!new_aeb) { + ret = -ENOMEM; + goto out; + } + + new_aeb->ec = be64_to_cpu(ech->ec); + new_aeb->pnum = pnum; + new_aeb->lnum = be32_to_cpu(vh->lnum); + new_aeb->sqnum = be64_to_cpu(vh->sqnum); + new_aeb->copy_flag = vh->copy_flag; + new_aeb->scrub = scrub; + + if (*max_sqnum < new_aeb->sqnum) + *max_sqnum = new_aeb->sqnum; + + err = process_pool_aeb(ubi, ai, vh, new_aeb); + if (err) { + ret = err > 0 ? UBI_BAD_FASTMAP : err; + goto out; + } + } else { + /* We are paranoid and fall back to scanning mode */ + ubi_err("fastmap pool PEBs contains damaged PEBs!"); + ret = err > 0 ? UBI_BAD_FASTMAP : err; + goto out; + } + + } + +out: + ubi_free_vid_hdr(ubi, vh); + kfree(ech); + return ret; +} + +/** + * count_fastmap_pebs - Counts the PEBs found by fastmap. + * @ai: The UBI attach info object + */ +static int count_fastmap_pebs(struct ubi_attach_info *ai) +{ + struct ubi_ainf_peb *aeb; + struct ubi_ainf_volume *av; + struct rb_node *rb1, *rb2; + int n = 0; + + list_for_each_entry(aeb, &ai->erase, u.list) + n++; + + list_for_each_entry(aeb, &ai->free, u.list) + n++; + + ubi_rb_for_each_entry(rb1, av, &ai->volumes, rb) + ubi_rb_for_each_entry(rb2, aeb, &av->root, u.rb) + n++; + + return n; +} + +/** + * ubi_attach_fastmap - creates ubi_attach_info from a fastmap. + * @ubi: UBI device object + * @ai: UBI attach info object + * @fm: the fastmap to be attached + * + * Returns 0 on success, UBI_BAD_FASTMAP if the found fastmap was unusable. + * < 0 indicates an internal error. + */ +static int ubi_attach_fastmap(struct ubi_device *ubi, + struct ubi_attach_info *ai, + struct ubi_fastmap_layout *fm) +{ + struct list_head used, eba_orphans, free; + struct ubi_ainf_volume *av; + struct ubi_ainf_peb *aeb, *tmp_aeb, *_tmp_aeb; + struct ubi_ec_hdr *ech; + struct ubi_fm_sb *fmsb; + struct ubi_fm_hdr *fmhdr; + struct ubi_fm_scan_pool *fmpl1, *fmpl2; + struct ubi_fm_ec *fmec; + struct ubi_fm_volhdr *fmvhdr; + struct ubi_fm_eba *fm_eba; + int ret, i, j, pool_size, wl_pool_size; + size_t fm_pos = 0, fm_size = ubi->fm_size; + unsigned long long max_sqnum = 0; + void *fm_raw = ubi->fm_buf; + + INIT_LIST_HEAD(&used); + INIT_LIST_HEAD(&free); + INIT_LIST_HEAD(&eba_orphans); + INIT_LIST_HEAD(&ai->corr); + INIT_LIST_HEAD(&ai->free); + INIT_LIST_HEAD(&ai->erase); + INIT_LIST_HEAD(&ai->alien); + ai->volumes = RB_ROOT; + ai->min_ec = UBI_MAX_ERASECOUNTER; + + ai->aeb_slab_cache = kmem_cache_create("ubi_ainf_peb_slab", + sizeof(struct ubi_ainf_peb), + 0, 0, NULL); + if (!ai->aeb_slab_cache) { + ret = -ENOMEM; + goto fail; + } + + fmsb = (struct ubi_fm_sb *)(fm_raw); + ai->max_sqnum = fmsb->sqnum; + fm_pos += sizeof(struct ubi_fm_sb); + if (fm_pos >= fm_size) + goto fail_bad; + + fmhdr = (struct ubi_fm_hdr *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmhdr); + if (fm_pos >= fm_size) + goto fail_bad; + + if (be32_to_cpu(fmhdr->magic) != UBI_FM_HDR_MAGIC) { + ubi_err("bad fastmap header magic: 0x%x, expected: 0x%x", + be32_to_cpu(fmhdr->magic), UBI_FM_HDR_MAGIC); + goto fail_bad; + } + + fmpl1 = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmpl1); + if (fm_pos >= fm_size) + goto fail_bad; + if (be32_to_cpu(fmpl1->magic) != UBI_FM_POOL_MAGIC) { + ubi_err("bad fastmap pool magic: 0x%x, expected: 0x%x", + be32_to_cpu(fmpl1->magic), UBI_FM_POOL_MAGIC); + goto fail_bad; + } + + fmpl2 = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmpl2); + if (fm_pos >= fm_size) + goto fail_bad; + if (be32_to_cpu(fmpl2->magic) != UBI_FM_POOL_MAGIC) { + ubi_err("bad fastmap pool magic: 0x%x, expected: 0x%x", + be32_to_cpu(fmpl2->magic), UBI_FM_POOL_MAGIC); + goto fail_bad; + } + + pool_size = be16_to_cpu(fmpl1->size); + wl_pool_size = be16_to_cpu(fmpl2->size); + fm->max_pool_size = be16_to_cpu(fmpl1->max_size); + fm->max_wl_pool_size = be16_to_cpu(fmpl2->max_size); + + if (pool_size > UBI_FM_MAX_POOL_SIZE || pool_size < 0) { + ubi_err("bad pool size: %i", pool_size); + goto fail_bad; + } + + if (wl_pool_size > UBI_FM_MAX_POOL_SIZE || wl_pool_size < 0) { + ubi_err("bad WL pool size: %i", wl_pool_size); + goto fail_bad; + } + + + if (fm->max_pool_size > UBI_FM_MAX_POOL_SIZE || + fm->max_pool_size < 0) { + ubi_err("bad maximal pool size: %i", fm->max_pool_size); + goto fail_bad; + } + + if (fm->max_wl_pool_size > UBI_FM_MAX_POOL_SIZE || + fm->max_wl_pool_size < 0) { + ubi_err("bad maximal WL pool size: %i", fm->max_wl_pool_size); + goto fail_bad; + } + + /* read EC values from free list */ + for (i = 0; i < be32_to_cpu(fmhdr->free_peb_count); i++) { + fmec = (struct ubi_fm_ec *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmec); + if (fm_pos >= fm_size) + goto fail_bad; + + add_aeb(ai, &ai->free, be32_to_cpu(fmec->pnum), + be32_to_cpu(fmec->ec), 0); + } + + /* read EC values from used list */ + for (i = 0; i < be32_to_cpu(fmhdr->used_peb_count); i++) { + fmec = (struct ubi_fm_ec *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmec); + if (fm_pos >= fm_size) + goto fail_bad; + + add_aeb(ai, &used, be32_to_cpu(fmec->pnum), + be32_to_cpu(fmec->ec), 0); + } + + /* read EC values from scrub list */ + for (i = 0; i < be32_to_cpu(fmhdr->scrub_peb_count); i++) { + fmec = (struct ubi_fm_ec *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmec); + if (fm_pos >= fm_size) + goto fail_bad; + + add_aeb(ai, &used, be32_to_cpu(fmec->pnum), + be32_to_cpu(fmec->ec), 1); + } + + /* read EC values from erase list */ + for (i = 0; i < be32_to_cpu(fmhdr->erase_peb_count); i++) { + fmec = (struct ubi_fm_ec *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmec); + if (fm_pos >= fm_size) + goto fail_bad; + + add_aeb(ai, &ai->erase, be32_to_cpu(fmec->pnum), + be32_to_cpu(fmec->ec), 1); + } + + ai->mean_ec = div_u64(ai->ec_sum, ai->ec_count); + ai->bad_peb_count = be32_to_cpu(fmhdr->bad_peb_count); + + /* Iterate over all volumes and read their EBA table */ + for (i = 0; i < be32_to_cpu(fmhdr->vol_count); i++) { + fmvhdr = (struct ubi_fm_volhdr *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmvhdr); + if (fm_pos >= fm_size) + goto fail_bad; + + if (be32_to_cpu(fmvhdr->magic) != UBI_FM_VHDR_MAGIC) { + ubi_err("bad fastmap vol header magic: 0x%x, " \ + "expected: 0x%x", + be32_to_cpu(fmvhdr->magic), UBI_FM_VHDR_MAGIC); + goto fail_bad; + } + + av = add_vol(ai, be32_to_cpu(fmvhdr->vol_id), + be32_to_cpu(fmvhdr->used_ebs), + be32_to_cpu(fmvhdr->data_pad), + fmvhdr->vol_type, + be32_to_cpu(fmvhdr->last_eb_bytes)); + + if (!av) + goto fail_bad; + + ai->vols_found++; + if (ai->highest_vol_id < be32_to_cpu(fmvhdr->vol_id)) + ai->highest_vol_id = be32_to_cpu(fmvhdr->vol_id); + + fm_eba = (struct ubi_fm_eba *)(fm_raw + fm_pos); + fm_pos += sizeof(*fm_eba); + fm_pos += (sizeof(__be32) * be32_to_cpu(fm_eba->reserved_pebs)); + if (fm_pos >= fm_size) + goto fail_bad; + + if (be32_to_cpu(fm_eba->magic) != UBI_FM_EBA_MAGIC) { + ubi_err("bad fastmap EBA header magic: 0x%x, " \ + "expected: 0x%x", + be32_to_cpu(fm_eba->magic), UBI_FM_EBA_MAGIC); + goto fail_bad; + } + + for (j = 0; j < be32_to_cpu(fm_eba->reserved_pebs); j++) { + int pnum = be32_to_cpu(fm_eba->pnum[j]); + + if ((int)be32_to_cpu(fm_eba->pnum[j]) < 0) + continue; + + aeb = NULL; + list_for_each_entry(tmp_aeb, &used, u.list) { + if (tmp_aeb->pnum == pnum) + aeb = tmp_aeb; + } + + /* This can happen if a PEB is already in an EBA known + * by this fastmap but the PEB itself is not in the used + * list. + * In this case the PEB can be within the fastmap pool + * or while writing the fastmap it was in the protection + * queue. + */ + if (!aeb) { + aeb = kmem_cache_alloc(ai->aeb_slab_cache, + GFP_KERNEL); + if (!aeb) { + ret = -ENOMEM; + + goto fail; + } + + aeb->lnum = j; + aeb->pnum = be32_to_cpu(fm_eba->pnum[j]); + aeb->ec = -1; + aeb->scrub = aeb->copy_flag = aeb->sqnum = 0; + list_add_tail(&aeb->u.list, &eba_orphans); + continue; + } + + aeb->lnum = j; + + if (av->highest_lnum <= aeb->lnum) + av->highest_lnum = aeb->lnum; + + assign_aeb_to_av(ai, aeb, av); + + dbg_bld("inserting PEB:%i (LEB %i) to vol %i", + aeb->pnum, aeb->lnum, av->vol_id); + } + + ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); + if (!ech) { + ret = -ENOMEM; + goto fail; + } + + list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &eba_orphans, + u.list) { + int err; + + if (ubi_io_is_bad(ubi, tmp_aeb->pnum)) { + ubi_err("bad PEB in fastmap EBA orphan list"); + ret = UBI_BAD_FASTMAP; + kfree(ech); + goto fail; + } + + err = ubi_io_read_ec_hdr(ubi, tmp_aeb->pnum, ech, 0); + if (err && err != UBI_IO_BITFLIPS) { + ubi_err("unable to read EC header! PEB:%i " \ + "err:%i", tmp_aeb->pnum, err); + ret = err > 0 ? UBI_BAD_FASTMAP : err; + kfree(ech); + + goto fail; + } else if (err == UBI_IO_BITFLIPS) + tmp_aeb->scrub = 1; + + tmp_aeb->ec = be64_to_cpu(ech->ec); + assign_aeb_to_av(ai, tmp_aeb, av); + } + + kfree(ech); + } + + ret = scan_pool(ubi, ai, fmpl1->pebs, pool_size, &max_sqnum, + &eba_orphans, &free); + if (ret) + goto fail; + + ret = scan_pool(ubi, ai, fmpl2->pebs, wl_pool_size, &max_sqnum, + &eba_orphans, &free); + if (ret) + goto fail; + + if (max_sqnum > ai->max_sqnum) + ai->max_sqnum = max_sqnum; + + list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &free, u.list) { + list_del(&tmp_aeb->u.list); + list_add_tail(&tmp_aeb->u.list, &ai->free); + } + + /* + * If fastmap is leaking PEBs (must not happen), raise a + * fat warning and fall back to scanning mode. + * We do this here because in ubi_wl_init() it's too late + * and we cannot fall back to scanning. + */ + if (WARN_ON(count_fastmap_pebs(ai) != ubi->peb_count - + ai->bad_peb_count - fm->used_blocks)) + goto fail_bad; + + return 0; + +fail_bad: + ret = UBI_BAD_FASTMAP; +fail: + return ret; +} + +/** + * ubi_scan_fastmap - scan the fastmap. + * @ubi: UBI device object + * @ai: UBI attach info to be filled + * @fm_anchor: The fastmap starts at this PEB + * + * Returns 0 on success, UBI_NO_FASTMAP if no fastmap was found, + * UBI_BAD_FASTMAP if one was found but is not usable. + * < 0 indicates an internal error. + */ +int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai, + int fm_anchor) +{ + struct ubi_fm_sb *fmsb, *fmsb2; + struct ubi_vid_hdr *vh; + struct ubi_ec_hdr *ech; + struct ubi_fastmap_layout *fm; + int i, used_blocks, pnum, ret = 0; + size_t fm_size; + __be32 crc, tmp_crc; + unsigned long long sqnum = 0; + + mutex_lock(&ubi->fm_mutex); + memset(ubi->fm_buf, 0, ubi->fm_size); + + fmsb = kmalloc(sizeof(*fmsb), GFP_KERNEL); + if (!fmsb) { + ret = -ENOMEM; + goto out; + } + + fm = kzalloc(sizeof(*fm), GFP_KERNEL); + if (!fm) { + ret = -ENOMEM; + kfree(fmsb); + goto out; + } + + ret = ubi_io_read(ubi, fmsb, fm_anchor, ubi->leb_start, sizeof(*fmsb)); + if (ret && ret != UBI_IO_BITFLIPS) + goto free_fm_sb; + else if (ret == UBI_IO_BITFLIPS) + fm->to_be_tortured[0] = 1; + + if (be32_to_cpu(fmsb->magic) != UBI_FM_SB_MAGIC) { + ubi_err("bad super block magic: 0x%x, expected: 0x%x", + be32_to_cpu(fmsb->magic), UBI_FM_SB_MAGIC); + ret = UBI_BAD_FASTMAP; + goto free_fm_sb; + } + + if (fmsb->version != UBI_FM_FMT_VERSION) { + ubi_err("bad fastmap version: %i, expected: %i", + fmsb->version, UBI_FM_FMT_VERSION); + ret = UBI_BAD_FASTMAP; + goto free_fm_sb; + } + + used_blocks = be32_to_cpu(fmsb->used_blocks); + if (used_blocks > UBI_FM_MAX_BLOCKS || used_blocks < 1) { + ubi_err("number of fastmap blocks is invalid: %i", used_blocks); + ret = UBI_BAD_FASTMAP; + goto free_fm_sb; + } + + fm_size = ubi->leb_size * used_blocks; + if (fm_size != ubi->fm_size) { + ubi_err("bad fastmap size: %zi, expected: %zi", fm_size, + ubi->fm_size); + ret = UBI_BAD_FASTMAP; + goto free_fm_sb; + } + + ech = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); + if (!ech) { + ret = -ENOMEM; + goto free_fm_sb; + } + + vh = ubi_zalloc_vid_hdr(ubi, GFP_KERNEL); + if (!vh) { + ret = -ENOMEM; + goto free_hdr; + } + + for (i = 0; i < used_blocks; i++) { + pnum = be32_to_cpu(fmsb->block_loc[i]); + + if (ubi_io_is_bad(ubi, pnum)) { + ret = UBI_BAD_FASTMAP; + goto free_hdr; + } + + ret = ubi_io_read_ec_hdr(ubi, pnum, ech, 0); + if (ret && ret != UBI_IO_BITFLIPS) { + ubi_err("unable to read fastmap block# %i EC (PEB: %i)", + i, pnum); + if (ret > 0) + ret = UBI_BAD_FASTMAP; + goto free_hdr; + } else if (ret == UBI_IO_BITFLIPS) + fm->to_be_tortured[i] = 1; + + if (!ubi->image_seq) + ubi->image_seq = be32_to_cpu(ech->image_seq); + + if (be32_to_cpu(ech->image_seq) != ubi->image_seq) { + ret = UBI_BAD_FASTMAP; + goto free_hdr; + } + + ret = ubi_io_read_vid_hdr(ubi, pnum, vh, 0); + if (ret && ret != UBI_IO_BITFLIPS) { + ubi_err("unable to read fastmap block# %i (PEB: %i)", + i, pnum); + goto free_hdr; + } + + if (i == 0) { + if (be32_to_cpu(vh->vol_id) != UBI_FM_SB_VOLUME_ID) { + ubi_err("bad fastmap anchor vol_id: 0x%x," \ + " expected: 0x%x", + be32_to_cpu(vh->vol_id), + UBI_FM_SB_VOLUME_ID); + ret = UBI_BAD_FASTMAP; + goto free_hdr; + } + } else { + if (be32_to_cpu(vh->vol_id) != UBI_FM_DATA_VOLUME_ID) { + ubi_err("bad fastmap data vol_id: 0x%x," \ + " expected: 0x%x", + be32_to_cpu(vh->vol_id), + UBI_FM_DATA_VOLUME_ID); + ret = UBI_BAD_FASTMAP; + goto free_hdr; + } + } + + if (sqnum < be64_to_cpu(vh->sqnum)) + sqnum = be64_to_cpu(vh->sqnum); + + ret = ubi_io_read(ubi, ubi->fm_buf + (ubi->leb_size * i), pnum, + ubi->leb_start, ubi->leb_size); + if (ret && ret != UBI_IO_BITFLIPS) { + ubi_err("unable to read fastmap block# %i (PEB: %i, " \ + "err: %i)", i, pnum, ret); + goto free_hdr; + } + } + + kfree(fmsb); + fmsb = NULL; + + fmsb2 = (struct ubi_fm_sb *)(ubi->fm_buf); + tmp_crc = be32_to_cpu(fmsb2->data_crc); + fmsb2->data_crc = 0; + crc = crc32(UBI_CRC32_INIT, ubi->fm_buf, fm_size); + if (crc != tmp_crc) { + ubi_err("fastmap data CRC is invalid"); + ubi_err("CRC should be: 0x%x, calc: 0x%x", tmp_crc, crc); + ret = UBI_BAD_FASTMAP; + goto free_hdr; + } + + fmsb2->sqnum = sqnum; + + fm->used_blocks = used_blocks; + + ret = ubi_attach_fastmap(ubi, ai, fm); + if (ret) { + if (ret > 0) + ret = UBI_BAD_FASTMAP; + goto free_hdr; + } + + for (i = 0; i < used_blocks; i++) { + struct ubi_wl_entry *e; + + e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL); + if (!e) { + while (i--) + kfree(fm->e[i]); + + ret = -ENOMEM; + goto free_hdr; + } + + e->pnum = be32_to_cpu(fmsb2->block_loc[i]); + e->ec = be32_to_cpu(fmsb2->block_ec[i]); + fm->e[i] = e; + } + + ubi->fm = fm; + ubi->fm_pool.max_size = ubi->fm->max_pool_size; + ubi->fm_wl_pool.max_size = ubi->fm->max_wl_pool_size; + ubi_msg("attached by fastmap"); + ubi_msg("fastmap pool size: %d", ubi->fm_pool.max_size); + ubi_msg("fastmap WL pool size: %d", ubi->fm_wl_pool.max_size); + ubi->fm_disabled = 0; + + ubi_free_vid_hdr(ubi, vh); + kfree(ech); +out: + mutex_unlock(&ubi->fm_mutex); + if (ret == UBI_BAD_FASTMAP) + ubi_err("Attach by fastmap failed, doing a full scan!"); + return ret; + +free_hdr: + ubi_free_vid_hdr(ubi, vh); + kfree(ech); +free_fm_sb: + kfree(fmsb); + kfree(fm); + goto out; +} + +/** + * ubi_write_fastmap - writes a fastmap. + * @ubi: UBI device object + * @new_fm: the to be written fastmap + * + * Returns 0 on success, < 0 indicates an internal error. + */ +static int ubi_write_fastmap(struct ubi_device *ubi, + struct ubi_fastmap_layout *new_fm) +{ + size_t fm_pos = 0; + void *fm_raw; + struct ubi_fm_sb *fmsb; + struct ubi_fm_hdr *fmh; + struct ubi_fm_scan_pool *fmpl1, *fmpl2; + struct ubi_fm_ec *fec; + struct ubi_fm_volhdr *fvh; + struct ubi_fm_eba *feba; + struct rb_node *node; + struct ubi_wl_entry *wl_e; + struct ubi_volume *vol; + struct ubi_vid_hdr *avhdr, *dvhdr; + struct ubi_work *ubi_wrk; + int ret, i, j, free_peb_count, used_peb_count, vol_count; + int scrub_peb_count, erase_peb_count; + + fm_raw = ubi->fm_buf; + memset(ubi->fm_buf, 0, ubi->fm_size); + + avhdr = new_fm_vhdr(ubi, UBI_FM_SB_VOLUME_ID); + if (!avhdr) { + ret = -ENOMEM; + goto out; + } + + dvhdr = new_fm_vhdr(ubi, UBI_FM_DATA_VOLUME_ID); + if (!dvhdr) { + ret = -ENOMEM; + goto out_kfree; + } + + spin_lock(&ubi->volumes_lock); + spin_lock(&ubi->wl_lock); + + fmsb = (struct ubi_fm_sb *)fm_raw; + fm_pos += sizeof(*fmsb); + ubi_assert(fm_pos <= ubi->fm_size); + + fmh = (struct ubi_fm_hdr *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmh); + ubi_assert(fm_pos <= ubi->fm_size); + + fmsb->magic = cpu_to_be32(UBI_FM_SB_MAGIC); + fmsb->version = UBI_FM_FMT_VERSION; + fmsb->used_blocks = cpu_to_be32(new_fm->used_blocks); + /* the max sqnum will be filled in while *reading* the fastmap */ + fmsb->sqnum = 0; + + fmh->magic = cpu_to_be32(UBI_FM_HDR_MAGIC); + free_peb_count = 0; + used_peb_count = 0; + scrub_peb_count = 0; + erase_peb_count = 0; + vol_count = 0; + + fmpl1 = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmpl1); + fmpl1->magic = cpu_to_be32(UBI_FM_POOL_MAGIC); + fmpl1->size = cpu_to_be16(ubi->fm_pool.size); + fmpl1->max_size = cpu_to_be16(ubi->fm_pool.max_size); + + for (i = 0; i < ubi->fm_pool.size; i++) + fmpl1->pebs[i] = cpu_to_be32(ubi->fm_pool.pebs[i]); + + fmpl2 = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos); + fm_pos += sizeof(*fmpl2); + fmpl2->magic = cpu_to_be32(UBI_FM_POOL_MAGIC); + fmpl2->size = cpu_to_be16(ubi->fm_wl_pool.size); + fmpl2->max_size = cpu_to_be16(ubi->fm_wl_pool.max_size); + + for (i = 0; i < ubi->fm_wl_pool.size; i++) + fmpl2->pebs[i] = cpu_to_be32(ubi->fm_wl_pool.pebs[i]); + + for (node = rb_first(&ubi->free); node; node = rb_next(node)) { + wl_e = rb_entry(node, struct ubi_wl_entry, u.rb); + fec = (struct ubi_fm_ec *)(fm_raw + fm_pos); + + fec->pnum = cpu_to_be32(wl_e->pnum); + fec->ec = cpu_to_be32(wl_e->ec); + + free_peb_count++; + fm_pos += sizeof(*fec); + ubi_assert(fm_pos <= ubi->fm_size); + } + fmh->free_peb_count = cpu_to_be32(free_peb_count); + + for (node = rb_first(&ubi->used); node; node = rb_next(node)) { + wl_e = rb_entry(node, struct ubi_wl_entry, u.rb); + fec = (struct ubi_fm_ec *)(fm_raw + fm_pos); + + fec->pnum = cpu_to_be32(wl_e->pnum); + fec->ec = cpu_to_be32(wl_e->ec); + + used_peb_count++; + fm_pos += sizeof(*fec); + ubi_assert(fm_pos <= ubi->fm_size); + } + fmh->used_peb_count = cpu_to_be32(used_peb_count); + + for (node = rb_first(&ubi->scrub); node; node = rb_next(node)) { + wl_e = rb_entry(node, struct ubi_wl_entry, u.rb); + fec = (struct ubi_fm_ec *)(fm_raw + fm_pos); + + fec->pnum = cpu_to_be32(wl_e->pnum); + fec->ec = cpu_to_be32(wl_e->ec); + + scrub_peb_count++; + fm_pos += sizeof(*fec); + ubi_assert(fm_pos <= ubi->fm_size); + } + fmh->scrub_peb_count = cpu_to_be32(scrub_peb_count); + + + list_for_each_entry(ubi_wrk, &ubi->works, list) { + if (ubi_is_erase_work(ubi_wrk)) { + wl_e = ubi_wrk->e; + ubi_assert(wl_e); + + fec = (struct ubi_fm_ec *)(fm_raw + fm_pos); + + fec->pnum = cpu_to_be32(wl_e->pnum); + fec->ec = cpu_to_be32(wl_e->ec); + + erase_peb_count++; + fm_pos += sizeof(*fec); + ubi_assert(fm_pos <= ubi->fm_size); + } + } + fmh->erase_peb_count = cpu_to_be32(erase_peb_count); + + for (i = 0; i < UBI_MAX_VOLUMES + UBI_INT_VOL_COUNT; i++) { + vol = ubi->volumes[i]; + + if (!vol) + continue; + + vol_count++; + + fvh = (struct ubi_fm_volhdr *)(fm_raw + fm_pos); + fm_pos += sizeof(*fvh); + ubi_assert(fm_pos <= ubi->fm_size); + + fvh->magic = cpu_to_be32(UBI_FM_VHDR_MAGIC); + fvh->vol_id = cpu_to_be32(vol->vol_id); + fvh->vol_type = vol->vol_type; + fvh->used_ebs = cpu_to_be32(vol->used_ebs); + fvh->data_pad = cpu_to_be32(vol->data_pad); + fvh->last_eb_bytes = cpu_to_be32(vol->last_eb_bytes); + + ubi_assert(vol->vol_type == UBI_DYNAMIC_VOLUME || + vol->vol_type == UBI_STATIC_VOLUME); + + feba = (struct ubi_fm_eba *)(fm_raw + fm_pos); + fm_pos += sizeof(*feba) + (sizeof(__be32) * vol->reserved_pebs); + ubi_assert(fm_pos <= ubi->fm_size); + + for (j = 0; j < vol->reserved_pebs; j++) + feba->pnum[j] = cpu_to_be32(vol->eba_tbl[j]); + + feba->reserved_pebs = cpu_to_be32(j); + feba->magic = cpu_to_be32(UBI_FM_EBA_MAGIC); + } + fmh->vol_count = cpu_to_be32(vol_count); + fmh->bad_peb_count = cpu_to_be32(ubi->bad_peb_count); + + avhdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); + avhdr->lnum = 0; + + spin_unlock(&ubi->wl_lock); + spin_unlock(&ubi->volumes_lock); + + dbg_bld("writing fastmap SB to PEB %i", new_fm->e[0]->pnum); + ret = ubi_io_write_vid_hdr(ubi, new_fm->e[0]->pnum, avhdr); + if (ret) { + ubi_err("unable to write vid_hdr to fastmap SB!"); + goto out_kfree; + } + + for (i = 0; i < new_fm->used_blocks; i++) { + fmsb->block_loc[i] = cpu_to_be32(new_fm->e[i]->pnum); + fmsb->block_ec[i] = cpu_to_be32(new_fm->e[i]->ec); + } + + fmsb->data_crc = 0; + fmsb->data_crc = cpu_to_be32(crc32(UBI_CRC32_INIT, fm_raw, + ubi->fm_size)); + + for (i = 1; i < new_fm->used_blocks; i++) { + dvhdr->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); + dvhdr->lnum = cpu_to_be32(i); + dbg_bld("writing fastmap data to PEB %i sqnum %llu", + new_fm->e[i]->pnum, be64_to_cpu(dvhdr->sqnum)); + ret = ubi_io_write_vid_hdr(ubi, new_fm->e[i]->pnum, dvhdr); + if (ret) { + ubi_err("unable to write vid_hdr to PEB %i!", + new_fm->e[i]->pnum); + goto out_kfree; + } + } + + for (i = 0; i < new_fm->used_blocks; i++) { + ret = ubi_io_write(ubi, fm_raw + (i * ubi->leb_size), + new_fm->e[i]->pnum, ubi->leb_start, ubi->leb_size); + if (ret) { + ubi_err("unable to write fastmap to PEB %i!", + new_fm->e[i]->pnum); + goto out_kfree; + } + } + + ubi_assert(new_fm); + ubi->fm = new_fm; + + dbg_bld("fastmap written!"); + +out_kfree: + ubi_free_vid_hdr(ubi, avhdr); + ubi_free_vid_hdr(ubi, dvhdr); +out: + return ret; +} + +/** + * erase_block - Manually erase a PEB. + * @ubi: UBI device object + * @pnum: PEB to be erased + * + * Returns the new EC value on success, < 0 indicates an internal error. + */ +static int erase_block(struct ubi_device *ubi, int pnum) +{ + int ret; + struct ubi_ec_hdr *ec_hdr; + long long ec; + + ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_KERNEL); + if (!ec_hdr) + return -ENOMEM; + + ret = ubi_io_read_ec_hdr(ubi, pnum, ec_hdr, 0); + if (ret < 0) + goto out; + else if (ret && ret != UBI_IO_BITFLIPS) { + ret = -EINVAL; + goto out; + } + + ret = ubi_io_sync_erase(ubi, pnum, 0); + if (ret < 0) + goto out; + + ec = be64_to_cpu(ec_hdr->ec); + ec += ret; + if (ec > UBI_MAX_ERASECOUNTER) { + ret = -EINVAL; + goto out; + } + + ec_hdr->ec = cpu_to_be64(ec); + ret = ubi_io_write_ec_hdr(ubi, pnum, ec_hdr); + if (ret < 0) + goto out; + + ret = ec; +out: + kfree(ec_hdr); + return ret; +} + +/** + * invalidate_fastmap - destroys a fastmap. + * @ubi: UBI device object + * @fm: the fastmap to be destroyed + * + * Returns 0 on success, < 0 indicates an internal error. + */ +static int invalidate_fastmap(struct ubi_device *ubi, + struct ubi_fastmap_layout *fm) +{ + int ret, i; + struct ubi_vid_hdr *vh; + + ret = erase_block(ubi, fm->e[0]->pnum); + if (ret < 0) + return ret; + + vh = new_fm_vhdr(ubi, UBI_FM_SB_VOLUME_ID); + if (!vh) + return -ENOMEM; + + /* deleting the current fastmap SB is not enough, an old SB may exist, + * so create a (corrupted) SB such that fastmap will find it and fall + * back to scanning mode in any case */ + vh->sqnum = cpu_to_be64(ubi_next_sqnum(ubi)); + ret = ubi_io_write_vid_hdr(ubi, fm->e[0]->pnum, vh); + + for (i = 0; i < fm->used_blocks; i++) + ubi_wl_put_fm_peb(ubi, fm->e[i], i, fm->to_be_tortured[i]); + + return ret; +} + +/** + * ubi_update_fastmap - will be called by UBI if a volume changes or + * a fastmap pool becomes full. + * @ubi: UBI device object + * + * Returns 0 on success, < 0 indicates an internal error. + */ +int ubi_update_fastmap(struct ubi_device *ubi) +{ + int ret, i; + struct ubi_fastmap_layout *new_fm, *old_fm; + struct ubi_wl_entry *tmp_e; + + mutex_lock(&ubi->fm_mutex); + + ubi_refill_pools(ubi); + + if (ubi->ro_mode || ubi->fm_disabled) { + mutex_unlock(&ubi->fm_mutex); + return 0; + } + + ret = ubi_ensure_anchor_pebs(ubi); + if (ret) { + mutex_unlock(&ubi->fm_mutex); + return ret; + } + + new_fm = kzalloc(sizeof(*new_fm), GFP_KERNEL); + if (!new_fm) { + mutex_unlock(&ubi->fm_mutex); + return -ENOMEM; + } + + new_fm->used_blocks = ubi->fm_size / ubi->leb_size; + + for (i = 0; i < new_fm->used_blocks; i++) { + new_fm->e[i] = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL); + if (!new_fm->e[i]) { + while (i--) + kfree(new_fm->e[i]); + + kfree(new_fm); + mutex_unlock(&ubi->fm_mutex); + return -ENOMEM; + } + } + + old_fm = ubi->fm; + ubi->fm = NULL; + + if (new_fm->used_blocks > UBI_FM_MAX_BLOCKS) { + ubi_err("fastmap too large"); + ret = -ENOSPC; + goto err; + } + + for (i = 1; i < new_fm->used_blocks; i++) { + spin_lock(&ubi->wl_lock); + tmp_e = ubi_wl_get_fm_peb(ubi, 0); + spin_unlock(&ubi->wl_lock); + + if (!tmp_e && !old_fm) { + int j; + ubi_err("could not get any free erase block"); + + for (j = 1; j < i; j++) + ubi_wl_put_fm_peb(ubi, new_fm->e[j], j, 0); + + ret = -ENOSPC; + goto err; + } else if (!tmp_e && old_fm) { + ret = erase_block(ubi, old_fm->e[i]->pnum); + if (ret < 0) { + int j; + + for (j = 1; j < i; j++) + ubi_wl_put_fm_peb(ubi, new_fm->e[j], + j, 0); + + ubi_err("could not erase old fastmap PEB"); + goto err; + } + + new_fm->e[i]->pnum = old_fm->e[i]->pnum; + new_fm->e[i]->ec = old_fm->e[i]->ec; + } else { + new_fm->e[i]->pnum = tmp_e->pnum; + new_fm->e[i]->ec = tmp_e->ec; + + if (old_fm) + ubi_wl_put_fm_peb(ubi, old_fm->e[i], i, + old_fm->to_be_tortured[i]); + } + } + + spin_lock(&ubi->wl_lock); + tmp_e = ubi_wl_get_fm_peb(ubi, 1); + spin_unlock(&ubi->wl_lock); + + if (old_fm) { + /* no fresh anchor PEB was found, reuse the old one */ + if (!tmp_e) { + ret = erase_block(ubi, old_fm->e[0]->pnum); + if (ret < 0) { + int i; + ubi_err("could not erase old anchor PEB"); + + for (i = 1; i < new_fm->used_blocks; i++) + ubi_wl_put_fm_peb(ubi, new_fm->e[i], + i, 0); + goto err; + } + + new_fm->e[0]->pnum = old_fm->e[0]->pnum; + new_fm->e[0]->ec = ret; + } else { + /* we've got a new anchor PEB, return the old one */ + ubi_wl_put_fm_peb(ubi, old_fm->e[0], 0, + old_fm->to_be_tortured[0]); + + new_fm->e[0]->pnum = tmp_e->pnum; + new_fm->e[0]->ec = tmp_e->ec; + } + } else { + if (!tmp_e) { + int i; + ubi_err("could not find any anchor PEB"); + + for (i = 1; i < new_fm->used_blocks; i++) + ubi_wl_put_fm_peb(ubi, new_fm->e[i], i, 0); + + ret = -ENOSPC; + goto err; + } + + new_fm->e[0]->pnum = tmp_e->pnum; + new_fm->e[0]->ec = tmp_e->ec; + } + + down_write(&ubi->work_sem); + down_write(&ubi->fm_sem); + ret = ubi_write_fastmap(ubi, new_fm); + up_write(&ubi->fm_sem); + up_write(&ubi->work_sem); + + if (ret) + goto err; + +out_unlock: + mutex_unlock(&ubi->fm_mutex); + kfree(old_fm); + return ret; + +err: + kfree(new_fm); + + ubi_warn("Unable to write new fastmap, err=%i", ret); + + ret = 0; + if (old_fm) { + ret = invalidate_fastmap(ubi, old_fm); + if (ret < 0) + ubi_err("Unable to invalidiate current fastmap!"); + else if (ret) + ret = 0; + } + goto out_unlock; +} diff --git a/drivers/mtd/ubi/ubi-media.h b/drivers/mtd/ubi/ubi-media.h index 468ffbc0eabd..ac2b24d1783d 100644 --- a/drivers/mtd/ubi/ubi-media.h +++ b/drivers/mtd/ubi/ubi-media.h @@ -375,4 +375,141 @@ struct ubi_vtbl_record { __be32 crc; } __packed; +/* UBI fastmap on-flash data structures */ + +#define UBI_FM_SB_VOLUME_ID (UBI_LAYOUT_VOLUME_ID + 1) +#define UBI_FM_DATA_VOLUME_ID (UBI_LAYOUT_VOLUME_ID + 2) + +/* fastmap on-flash data structure format version */ +#define UBI_FM_FMT_VERSION 1 + +#define UBI_FM_SB_MAGIC 0x7B11D69F +#define UBI_FM_HDR_MAGIC 0xD4B82EF7 +#define UBI_FM_VHDR_MAGIC 0xFA370ED1 +#define UBI_FM_POOL_MAGIC 0x67AF4D08 +#define UBI_FM_EBA_MAGIC 0xf0c040a8 + +/* A fastmap supber block can be located between PEB 0 and + * UBI_FM_MAX_START */ +#define UBI_FM_MAX_START 64 + +/* A fastmap can use up to UBI_FM_MAX_BLOCKS PEBs */ +#define UBI_FM_MAX_BLOCKS 32 + +/* 5% of the total number of PEBs have to be scanned while attaching + * from a fastmap. + * But the size of this pool is limited to be between UBI_FM_MIN_POOL_SIZE and + * UBI_FM_MAX_POOL_SIZE */ +#define UBI_FM_MIN_POOL_SIZE 8 +#define UBI_FM_MAX_POOL_SIZE 256 + +#define UBI_FM_WL_POOL_SIZE 25 + +/** + * struct ubi_fm_sb - UBI fastmap super block + * @magic: fastmap super block magic number (%UBI_FM_SB_MAGIC) + * @version: format version of this fastmap + * @data_crc: CRC over the fastmap data + * @used_blocks: number of PEBs used by this fastmap + * @block_loc: an array containing the location of all PEBs of the fastmap + * @block_ec: the erase counter of each used PEB + * @sqnum: highest sequence number value at the time while taking the fastmap + * + */ +struct ubi_fm_sb { + __be32 magic; + __u8 version; + __u8 padding1[3]; + __be32 data_crc; + __be32 used_blocks; + __be32 block_loc[UBI_FM_MAX_BLOCKS]; + __be32 block_ec[UBI_FM_MAX_BLOCKS]; + __be64 sqnum; + __u8 padding2[32]; +} __packed; + +/** + * struct ubi_fm_hdr - header of the fastmap data set + * @magic: fastmap header magic number (%UBI_FM_HDR_MAGIC) + * @free_peb_count: number of free PEBs known by this fastmap + * @used_peb_count: number of used PEBs known by this fastmap + * @scrub_peb_count: number of to be scrubbed PEBs known by this fastmap + * @bad_peb_count: number of bad PEBs known by this fastmap + * @erase_peb_count: number of bad PEBs which have to be erased + * @vol_count: number of UBI volumes known by this fastmap + */ +struct ubi_fm_hdr { + __be32 magic; + __be32 free_peb_count; + __be32 used_peb_count; + __be32 scrub_peb_count; + __be32 bad_peb_count; + __be32 erase_peb_count; + __be32 vol_count; + __u8 padding[4]; +} __packed; + +/* struct ubi_fm_hdr is followed by two struct ubi_fm_scan_pool */ + +/** + * struct ubi_fm_scan_pool - Fastmap pool PEBs to be scanned while attaching + * @magic: pool magic numer (%UBI_FM_POOL_MAGIC) + * @size: current pool size + * @max_size: maximal pool size + * @pebs: an array containing the location of all PEBs in this pool + */ +struct ubi_fm_scan_pool { + __be32 magic; + __be16 size; + __be16 max_size; + __be32 pebs[UBI_FM_MAX_POOL_SIZE]; + __be32 padding[4]; +} __packed; + +/* ubi_fm_scan_pool is followed by nfree+nused struct ubi_fm_ec records */ + +/** + * struct ubi_fm_ec - stores the erase counter of a PEB + * @pnum: PEB number + * @ec: ec of this PEB + */ +struct ubi_fm_ec { + __be32 pnum; + __be32 ec; +} __packed; + +/** + * struct ubi_fm_volhdr - Fastmap volume header + * it identifies the start of an eba table + * @magic: Fastmap volume header magic number (%UBI_FM_VHDR_MAGIC) + * @vol_id: volume id of the fastmapped volume + * @vol_type: type of the fastmapped volume + * @data_pad: data_pad value of the fastmapped volume + * @used_ebs: number of used LEBs within this volume + * @last_eb_bytes: number of bytes used in the last LEB + */ +struct ubi_fm_volhdr { + __be32 magic; + __be32 vol_id; + __u8 vol_type; + __u8 padding1[3]; + __be32 data_pad; + __be32 used_ebs; + __be32 last_eb_bytes; + __u8 padding2[8]; +} __packed; + +/* struct ubi_fm_volhdr is followed by one struct ubi_fm_eba records */ + +/** + * struct ubi_fm_eba - denotes an association beween a PEB and LEB + * @magic: EBA table magic number + * @reserved_pebs: number of table entries + * @pnum: PEB number of LEB (LEB is the index) + */ +struct ubi_fm_eba { + __be32 magic; + __be32 reserved_pebs; + __be32 pnum[0]; +} __packed; #endif /* !__UBI_MEDIA_H__ */ diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index 383ee43d2425..7d57469723cf 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -133,6 +133,17 @@ enum { MOVE_RETRY, }; +/* + * Return codes of the fastmap sub-system + * + * UBI_NO_FASTMAP: No fastmap super block was found + * UBI_BAD_FASTMAP: A fastmap was found but it's unusable + */ +enum { + UBI_NO_FASTMAP = 1, + UBI_BAD_FASTMAP, +}; + /** * struct ubi_wl_entry - wear-leveling entry. * @u.rb: link in the corresponding (free/used) RB-tree @@ -199,6 +210,41 @@ struct ubi_rename_entry { struct ubi_volume_desc; /** + * struct ubi_fastmap_layout - in-memory fastmap data structure. + * @e: PEBs used by the current fastmap + * @to_be_tortured: if non-zero tortured this PEB + * @used_blocks: number of used PEBs + * @max_pool_size: maximal size of the user pool + * @max_wl_pool_size: maximal size of the pool used by the WL sub-system + */ +struct ubi_fastmap_layout { + struct ubi_wl_entry *e[UBI_FM_MAX_BLOCKS]; + int to_be_tortured[UBI_FM_MAX_BLOCKS]; + int used_blocks; + int max_pool_size; + int max_wl_pool_size; +}; + +/** + * struct ubi_fm_pool - in-memory fastmap pool + * @pebs: PEBs in this pool + * @used: number of used PEBs + * @size: total number of PEBs in this pool + * @max_size: maximal size of the pool + * + * A pool gets filled with up to max_size. + * If all PEBs within the pool are used a new fastmap will be written + * to the flash and the pool gets refilled with empty PEBs. + * + */ +struct ubi_fm_pool { + int pebs[UBI_FM_MAX_POOL_SIZE]; + int used; + int size; + int max_size; +}; + +/** * struct ubi_volume - UBI volume description data structure. * @dev: device object to make use of the the Linux device model * @cdev: character device object to create character device @@ -333,9 +379,21 @@ struct ubi_wl_entry; * @ltree: the lock tree * @alc_mutex: serializes "atomic LEB change" operations * + * @fm_disabled: non-zero if fastmap is disabled (default) + * @fm: in-memory data structure of the currently used fastmap + * @fm_pool: in-memory data structure of the fastmap pool + * @fm_wl_pool: in-memory data structure of the fastmap pool used by the WL + * sub-system + * @fm_mutex: serializes ubi_update_fastmap() and protects @fm_buf + * @fm_buf: vmalloc()'d buffer which holds the raw fastmap + * @fm_size: fastmap size in bytes + * @fm_sem: allows ubi_update_fastmap() to block EBA table changes + * @fm_work: fastmap work queue + * * @used: RB-tree of used physical eraseblocks * @erroneous: RB-tree of erroneous used physical eraseblocks * @free: RB-tree of free physical eraseblocks + * @free_count: Contains the number of elements in @free * @scrub: RB-tree of physical eraseblocks which need scrubbing * @pq: protection queue (contain physical eraseblocks which are temporarily * protected from the wear-leveling worker) @@ -426,10 +484,22 @@ struct ubi_device { struct rb_root ltree; struct mutex alc_mutex; + /* Fastmap stuff */ + int fm_disabled; + struct ubi_fastmap_layout *fm; + struct ubi_fm_pool fm_pool; + struct ubi_fm_pool fm_wl_pool; + struct rw_semaphore fm_sem; + struct mutex fm_mutex; + void *fm_buf; + size_t fm_size; + struct work_struct fm_work; + /* Wear-leveling sub-system's stuff */ struct rb_root used; struct rb_root erroneous; struct rb_root free; + int free_count; struct rb_root scrub; struct list_head pq[UBI_PROT_QUEUE_LEN]; int pq_head; @@ -596,6 +666,32 @@ struct ubi_attach_info { struct kmem_cache *aeb_slab_cache; }; +/** + * struct ubi_work - UBI work description data structure. + * @list: a link in the list of pending works + * @func: worker function + * @e: physical eraseblock to erase + * @vol_id: the volume ID on which this erasure is being performed + * @lnum: the logical eraseblock number + * @torture: if the physical eraseblock has to be tortured + * @anchor: produce a anchor PEB to by used by fastmap + * + * The @func pointer points to the worker function. If the @cancel argument is + * not zero, the worker has to free the resources and exit immediately. The + * worker has to return zero in case of success and a negative error code in + * case of failure. + */ +struct ubi_work { + struct list_head list; + int (*func)(struct ubi_device *ubi, struct ubi_work *wrk, int cancel); + /* The below fields are only relevant to erasure works */ + struct ubi_wl_entry *e; + int vol_id; + int lnum; + int torture; + int anchor; +}; + #include "debug.h" extern struct kmem_cache *ubi_wl_entry_slab; @@ -606,7 +702,7 @@ extern struct class *ubi_class; extern struct mutex ubi_devices_mutex; extern struct blocking_notifier_head ubi_notifiers; -/* scan.c */ +/* attach.c */ int ubi_add_to_av(struct ubi_device *ubi, struct ubi_attach_info *ai, int pnum, int ec, const struct ubi_vid_hdr *vid_hdr, int bitflips); struct ubi_ainf_volume *ubi_find_av(const struct ubi_attach_info *ai, @@ -614,7 +710,7 @@ struct ubi_ainf_volume *ubi_find_av(const struct ubi_attach_info *ai, void ubi_remove_av(struct ubi_attach_info *ai, struct ubi_ainf_volume *av); struct ubi_ainf_peb *ubi_early_get_peb(struct ubi_device *ubi, struct ubi_attach_info *ai); -int ubi_attach(struct ubi_device *ubi); +int ubi_attach(struct ubi_device *ubi, int force_scan); void ubi_destroy_ai(struct ubi_attach_info *ai); /* vtbl.c */ @@ -664,6 +760,9 @@ int ubi_eba_atomic_leb_change(struct ubi_device *ubi, struct ubi_volume *vol, int ubi_eba_copy_leb(struct ubi_device *ubi, int from, int to, struct ubi_vid_hdr *vid_hdr); int ubi_eba_init(struct ubi_device *ubi, struct ubi_attach_info *ai); +unsigned long long ubi_next_sqnum(struct ubi_device *ubi); +int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap, + struct ubi_attach_info *ai_scan); /* wl.c */ int ubi_wl_get_peb(struct ubi_device *ubi); @@ -674,6 +773,12 @@ int ubi_wl_scrub_peb(struct ubi_device *ubi, int pnum); int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai); void ubi_wl_close(struct ubi_device *ubi); int ubi_thread(void *u); +struct ubi_wl_entry *ubi_wl_get_fm_peb(struct ubi_device *ubi, int anchor); +int ubi_wl_put_fm_peb(struct ubi_device *ubi, struct ubi_wl_entry *used_e, + int lnum, int torture); +int ubi_is_erase_work(struct ubi_work *wrk); +void ubi_refill_pools(struct ubi_device *ubi); +int ubi_ensure_anchor_pebs(struct ubi_device *ubi); /* io.c */ int ubi_io_read(const struct ubi_device *ubi, void *buf, int pnum, int offset, @@ -711,6 +816,15 @@ void ubi_free_internal_volumes(struct ubi_device *ubi); void ubi_do_get_device_info(struct ubi_device *ubi, struct ubi_device_info *di); void ubi_do_get_volume_info(struct ubi_device *ubi, struct ubi_volume *vol, struct ubi_volume_info *vi); +/* scan.c */ +int ubi_compare_lebs(struct ubi_device *ubi, const struct ubi_ainf_peb *aeb, + int pnum, const struct ubi_vid_hdr *vid_hdr); + +/* fastmap.c */ +size_t ubi_calc_fm_size(struct ubi_device *ubi); +int ubi_update_fastmap(struct ubi_device *ubi); +int ubi_scan_fastmap(struct ubi_device *ubi, struct ubi_attach_info *ai, + int fm_anchor); /* * ubi_rb_for_each_entry - walk an RB-tree. diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 032fc57f1090..da7b44998b40 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -135,36 +135,48 @@ */ #define WL_MAX_FAILURES 32 -/** - * struct ubi_work - UBI work description data structure. - * @list: a link in the list of pending works - * @func: worker function - * @e: physical eraseblock to erase - * @vol_id: the volume ID on which this erasure is being performed - * @lnum: the logical eraseblock number - * @torture: if the physical eraseblock has to be tortured - * - * The @func pointer points to the worker function. If the @cancel argument is - * not zero, the worker has to free the resources and exit immediately. The - * worker has to return zero in case of success and a negative error code in - * case of failure. - */ -struct ubi_work { - struct list_head list; - int (*func)(struct ubi_device *ubi, struct ubi_work *wrk, int cancel); - /* The below fields are only relevant to erasure works */ - struct ubi_wl_entry *e; - int vol_id; - int lnum; - int torture; -}; - static int self_check_ec(struct ubi_device *ubi, int pnum, int ec); static int self_check_in_wl_tree(const struct ubi_device *ubi, struct ubi_wl_entry *e, struct rb_root *root); static int self_check_in_pq(const struct ubi_device *ubi, struct ubi_wl_entry *e); +#ifdef CONFIG_MTD_UBI_FASTMAP +/** + * update_fastmap_work_fn - calls ubi_update_fastmap from a work queue + * @wrk: the work description object + */ +static void update_fastmap_work_fn(struct work_struct *wrk) +{ + struct ubi_device *ubi = container_of(wrk, struct ubi_device, fm_work); + ubi_update_fastmap(ubi); +} + +/** + * ubi_ubi_is_fm_block - returns 1 if a PEB is currently used in a fastmap. + * @ubi: UBI device description object + * @pnum: the to be checked PEB + */ +static int ubi_is_fm_block(struct ubi_device *ubi, int pnum) +{ + int i; + + if (!ubi->fm) + return 0; + + for (i = 0; i < ubi->fm->used_blocks; i++) + if (ubi->fm->e[i]->pnum == pnum) + return 1; + + return 0; +} +#else +static int ubi_is_fm_block(struct ubi_device *ubi, int pnum) +{ + return 0; +} +#endif + /** * wl_tree_add - add a wear-leveling entry to a WL RB-tree. * @e: the wear-leveling entry to add @@ -261,18 +273,16 @@ static int produce_free_peb(struct ubi_device *ubi) { int err; - spin_lock(&ubi->wl_lock); while (!ubi->free.rb_node) { spin_unlock(&ubi->wl_lock); dbg_wl("do one work synchronously"); err = do_work(ubi); - if (err) - return err; spin_lock(&ubi->wl_lock); + if (err) + return err; } - spin_unlock(&ubi->wl_lock); return 0; } @@ -339,16 +349,18 @@ static void prot_queue_add(struct ubi_device *ubi, struct ubi_wl_entry *e) /** * find_wl_entry - find wear-leveling entry closest to certain erase counter. + * @ubi: UBI device description object * @root: the RB-tree where to look for * @diff: maximum possible difference from the smallest erase counter * * This function looks for a wear leveling entry with erase counter closest to * min + @diff, where min is the smallest erase counter. */ -static struct ubi_wl_entry *find_wl_entry(struct rb_root *root, int diff) +static struct ubi_wl_entry *find_wl_entry(struct ubi_device *ubi, + struct rb_root *root, int diff) { struct rb_node *p; - struct ubi_wl_entry *e; + struct ubi_wl_entry *e, *prev_e = NULL; int max; e = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb); @@ -363,35 +375,143 @@ static struct ubi_wl_entry *find_wl_entry(struct rb_root *root, int diff) p = p->rb_left; else { p = p->rb_right; + prev_e = e; e = e1; } } + /* If no fastmap has been written and this WL entry can be used + * as anchor PEB, hold it back and return the second best WL entry + * such that fastmap can use the anchor PEB later. */ + if (prev_e && !ubi->fm_disabled && + !ubi->fm && e->pnum < UBI_FM_MAX_START) + return prev_e; + return e; } /** - * ubi_wl_get_peb - get a physical eraseblock. + * find_mean_wl_entry - find wear-leveling entry with medium erase counter. + * @ubi: UBI device description object + * @root: the RB-tree where to look for + * + * This function looks for a wear leveling entry with medium erase counter, + * but not greater or equivalent than the lowest erase counter plus + * %WL_FREE_MAX_DIFF/2. + */ +static struct ubi_wl_entry *find_mean_wl_entry(struct ubi_device *ubi, + struct rb_root *root) +{ + struct ubi_wl_entry *e, *first, *last; + + first = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb); + last = rb_entry(rb_last(root), struct ubi_wl_entry, u.rb); + + if (last->ec - first->ec < WL_FREE_MAX_DIFF) { + e = rb_entry(root->rb_node, struct ubi_wl_entry, u.rb); + +#ifdef CONFIG_MTD_UBI_FASTMAP + /* If no fastmap has been written and this WL entry can be used + * as anchor PEB, hold it back and return the second best + * WL entry such that fastmap can use the anchor PEB later. */ + if (e && !ubi->fm_disabled && !ubi->fm && + e->pnum < UBI_FM_MAX_START) + e = rb_entry(rb_next(root->rb_node), + struct ubi_wl_entry, u.rb); +#endif + } else + e = find_wl_entry(ubi, root, WL_FREE_MAX_DIFF/2); + + return e; +} + +#ifdef CONFIG_MTD_UBI_FASTMAP +/** + * find_anchor_wl_entry - find wear-leveling entry to used as anchor PEB. + * @root: the RB-tree where to look for + */ +static struct ubi_wl_entry *find_anchor_wl_entry(struct rb_root *root) +{ + struct rb_node *p; + struct ubi_wl_entry *e, *victim = NULL; + int max_ec = UBI_MAX_ERASECOUNTER; + + ubi_rb_for_each_entry(p, e, root, u.rb) { + if (e->pnum < UBI_FM_MAX_START && e->ec < max_ec) { + victim = e; + max_ec = e->ec; + } + } + + return victim; +} + +static int anchor_pebs_avalible(struct rb_root *root) +{ + struct rb_node *p; + struct ubi_wl_entry *e; + + ubi_rb_for_each_entry(p, e, root, u.rb) + if (e->pnum < UBI_FM_MAX_START) + return 1; + + return 0; +} + +/** + * ubi_wl_get_fm_peb - find a physical erase block with a given maximal number. + * @ubi: UBI device description object + * @anchor: This PEB will be used as anchor PEB by fastmap + * + * The function returns a physical erase block with a given maximal number + * and removes it from the wl subsystem. + * Must be called with wl_lock held! + */ +struct ubi_wl_entry *ubi_wl_get_fm_peb(struct ubi_device *ubi, int anchor) +{ + struct ubi_wl_entry *e = NULL; + + if (!ubi->free.rb_node || (ubi->free_count - ubi->beb_rsvd_pebs < 1)) + goto out; + + if (anchor) + e = find_anchor_wl_entry(&ubi->free); + else + e = find_mean_wl_entry(ubi, &ubi->free); + + if (!e) + goto out; + + self_check_in_wl_tree(ubi, e, &ubi->free); + + /* remove it from the free list, + * the wl subsystem does no longer know this erase block */ + rb_erase(&e->u.rb, &ubi->free); + ubi->free_count--; +out: + return e; +} +#endif + +/** + * __wl_get_peb - get a physical eraseblock. * @ubi: UBI device description object * * This function returns a physical eraseblock in case of success and a * negative error code in case of failure. Might sleep. */ -int ubi_wl_get_peb(struct ubi_device *ubi) +static int __wl_get_peb(struct ubi_device *ubi) { int err; - struct ubi_wl_entry *e, *first, *last; + struct ubi_wl_entry *e; retry: - spin_lock(&ubi->wl_lock); if (!ubi->free.rb_node) { if (ubi->works_count == 0) { - ubi_assert(list_empty(&ubi->works)); ubi_err("no free eraseblocks"); - spin_unlock(&ubi->wl_lock); + ubi_assert(list_empty(&ubi->works)); return -ENOSPC; } - spin_unlock(&ubi->wl_lock); err = produce_free_peb(ubi); if (err < 0) @@ -399,13 +519,11 @@ retry: goto retry; } - 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, u.rb); - else - e = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF/2); + e = find_mean_wl_entry(ubi, &ubi->free); + if (!e) { + ubi_err("no free eraseblocks"); + return -ENOSPC; + } self_check_in_wl_tree(ubi, e, &ubi->free); @@ -414,10 +532,14 @@ retry: * be protected from being moved for some time. */ rb_erase(&e->u.rb, &ubi->free); + ubi->free_count--; dbg_wl("PEB %d EC %d", e->pnum, e->ec); +#ifndef CONFIG_MTD_UBI_FASTMAP + /* We have to enqueue e only if fastmap is disabled, + * is fastmap enabled prot_queue_add() will be called by + * ubi_wl_get_peb() after removing e from the pool. */ prot_queue_add(ubi, e); - spin_unlock(&ubi->wl_lock); - +#endif err = ubi_self_check_all_ff(ubi, e->pnum, ubi->vid_hdr_aloffset, ubi->peb_size - ubi->vid_hdr_aloffset); if (err) { @@ -428,6 +550,150 @@ retry: return e->pnum; } +#ifdef CONFIG_MTD_UBI_FASTMAP +/** + * return_unused_pool_pebs - returns unused PEB to the free tree. + * @ubi: UBI device description object + * @pool: fastmap pool description object + */ +static void return_unused_pool_pebs(struct ubi_device *ubi, + struct ubi_fm_pool *pool) +{ + int i; + struct ubi_wl_entry *e; + + for (i = pool->used; i < pool->size; i++) { + e = ubi->lookuptbl[pool->pebs[i]]; + wl_tree_add(e, &ubi->free); + ubi->free_count++; + } +} + +/** + * refill_wl_pool - refills all the fastmap pool used by the + * WL sub-system. + * @ubi: UBI device description object + */ +static void refill_wl_pool(struct ubi_device *ubi) +{ + struct ubi_wl_entry *e; + struct ubi_fm_pool *pool = &ubi->fm_wl_pool; + + return_unused_pool_pebs(ubi, pool); + + for (pool->size = 0; pool->size < pool->max_size; pool->size++) { + if (!ubi->free.rb_node || + (ubi->free_count - ubi->beb_rsvd_pebs < 5)) + break; + + e = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF); + self_check_in_wl_tree(ubi, e, &ubi->free); + rb_erase(&e->u.rb, &ubi->free); + ubi->free_count--; + + pool->pebs[pool->size] = e->pnum; + } + pool->used = 0; +} + +/** + * refill_wl_user_pool - refills all the fastmap pool used by ubi_wl_get_peb. + * @ubi: UBI device description object + */ +static void refill_wl_user_pool(struct ubi_device *ubi) +{ + struct ubi_fm_pool *pool = &ubi->fm_pool; + + return_unused_pool_pebs(ubi, pool); + + for (pool->size = 0; pool->size < pool->max_size; pool->size++) { + if (!ubi->free.rb_node || + (ubi->free_count - ubi->beb_rsvd_pebs < 1)) + break; + + pool->pebs[pool->size] = __wl_get_peb(ubi); + if (pool->pebs[pool->size] < 0) + break; + } + pool->used = 0; +} + +/** + * ubi_refill_pools - refills all fastmap PEB pools. + * @ubi: UBI device description object + */ +void ubi_refill_pools(struct ubi_device *ubi) +{ + spin_lock(&ubi->wl_lock); + refill_wl_pool(ubi); + refill_wl_user_pool(ubi); + spin_unlock(&ubi->wl_lock); +} + +/* ubi_wl_get_peb - works exaclty like __wl_get_peb but keeps track of + * the fastmap pool. + */ +int ubi_wl_get_peb(struct ubi_device *ubi) +{ + int ret; + struct ubi_fm_pool *pool = &ubi->fm_pool; + struct ubi_fm_pool *wl_pool = &ubi->fm_wl_pool; + + if (!pool->size || !wl_pool->size || pool->used == pool->size || + wl_pool->used == wl_pool->size) + ubi_update_fastmap(ubi); + + /* we got not a single free PEB */ + if (!pool->size) + ret = -ENOSPC; + else { + spin_lock(&ubi->wl_lock); + ret = pool->pebs[pool->used++]; + prot_queue_add(ubi, ubi->lookuptbl[ret]); + spin_unlock(&ubi->wl_lock); + } + + return ret; +} + +/* get_peb_for_wl - returns a PEB to be used internally by the WL sub-system. + * + * @ubi: UBI device description object + */ +static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi) +{ + struct ubi_fm_pool *pool = &ubi->fm_wl_pool; + int pnum; + + if (pool->used == pool->size || !pool->size) { + /* We cannot update the fastmap here because this + * function is called in atomic context. + * Let's fail here and refill/update it as soon as possible. */ + schedule_work(&ubi->fm_work); + return NULL; + } else { + pnum = pool->pebs[pool->used++]; + return ubi->lookuptbl[pnum]; + } +} +#else +static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi) +{ + return find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF); +} + +int ubi_wl_get_peb(struct ubi_device *ubi) +{ + int peb; + + spin_lock(&ubi->wl_lock); + peb = __wl_get_peb(ubi); + spin_unlock(&ubi->wl_lock); + + return peb; +} +#endif + /** * prot_queue_del - remove a physical eraseblock from the protection queue. * @ubi: UBI device description object @@ -558,14 +824,14 @@ repeat: } /** - * schedule_ubi_work - schedule a work. + * __schedule_ubi_work - schedule a work. * @ubi: UBI device description object * @wrk: the work to schedule * * This function adds a work defined by @wrk to the tail of the pending works - * list. + * list. Can only be used of ubi->work_sem is already held in read mode! */ -static void schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk) +static void __schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk) { spin_lock(&ubi->wl_lock); list_add_tail(&wrk->list, &ubi->works); @@ -576,9 +842,35 @@ static void schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk) spin_unlock(&ubi->wl_lock); } +/** + * schedule_ubi_work - schedule a work. + * @ubi: UBI device description object + * @wrk: the work to schedule + * + * 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) +{ + down_read(&ubi->work_sem); + __schedule_ubi_work(ubi, wrk); + up_read(&ubi->work_sem); +} + static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, int cancel); +#ifdef CONFIG_MTD_UBI_FASTMAP +/** + * ubi_is_erase_work - checks whether a work is erase work. + * @wrk: The work object to be checked + */ +int ubi_is_erase_work(struct ubi_work *wrk) +{ + return wrk->func == erase_worker; +} +#endif + /** * schedule_erase - schedule an erase work. * @ubi: UBI device description object @@ -595,6 +887,9 @@ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, { struct ubi_work *wl_wrk; + ubi_assert(e); + ubi_assert(!ubi_is_fm_block(ubi, e->pnum)); + dbg_wl("schedule erasure of PEB %d, EC %d, torture %d", e->pnum, e->ec, torture); @@ -613,6 +908,79 @@ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, } /** + * do_sync_erase - run the erase worker synchronously. + * @ubi: UBI device description object + * @e: the WL entry of the physical eraseblock to erase + * @vol_id: the volume ID that last used this PEB + * @lnum: the last used logical eraseblock number for the PEB + * @torture: if the physical eraseblock has to be tortured + * + */ +static int do_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, + int vol_id, int lnum, int torture) +{ + struct ubi_work *wl_wrk; + + dbg_wl("sync erase of PEB %i", e->pnum); + + wl_wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS); + if (!wl_wrk) + return -ENOMEM; + + wl_wrk->e = e; + wl_wrk->vol_id = vol_id; + wl_wrk->lnum = lnum; + wl_wrk->torture = torture; + + return erase_worker(ubi, wl_wrk, 0); +} + +#ifdef CONFIG_MTD_UBI_FASTMAP +/** + * ubi_wl_put_fm_peb - returns a PEB used in a fastmap to the wear-leveling + * sub-system. + * see: ubi_wl_put_peb() + * + * @ubi: UBI device description object + * @fm_e: physical eraseblock to return + * @lnum: the last used logical eraseblock number for the PEB + * @torture: if this physical eraseblock has to be tortured + */ +int ubi_wl_put_fm_peb(struct ubi_device *ubi, struct ubi_wl_entry *fm_e, + int lnum, int torture) +{ + struct ubi_wl_entry *e; + int vol_id, pnum = fm_e->pnum; + + dbg_wl("PEB %d", pnum); + + ubi_assert(pnum >= 0); + ubi_assert(pnum < ubi->peb_count); + + spin_lock(&ubi->wl_lock); + e = ubi->lookuptbl[pnum]; + + /* This can happen if we recovered from a fastmap the very + * first time and writing now a new one. In this case the wl system + * has never seen any PEB used by the original fastmap. + */ + if (!e) { + e = fm_e; + ubi_assert(e->ec >= 0); + ubi->lookuptbl[pnum] = e; + } else { + e->ec = fm_e->ec; + kfree(fm_e); + } + + spin_unlock(&ubi->wl_lock); + + vol_id = lnum ? UBI_FM_DATA_VOLUME_ID : UBI_FM_SB_VOLUME_ID; + return schedule_erase(ubi, e, vol_id, lnum, torture); +} +#endif + +/** * wear_leveling_worker - wear-leveling worker function. * @ubi: UBI device description object * @wrk: the work object @@ -627,6 +995,9 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, { int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0; int vol_id = -1, uninitialized_var(lnum); +#ifdef CONFIG_MTD_UBI_FASTMAP + int anchor = wrk->anchor; +#endif struct ubi_wl_entry *e1, *e2; struct ubi_vid_hdr *vid_hdr; @@ -660,14 +1031,35 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, goto out_cancel; } +#ifdef CONFIG_MTD_UBI_FASTMAP + /* Check whether we need to produce an anchor PEB */ + if (!anchor) + anchor = !anchor_pebs_avalible(&ubi->free); + + if (anchor) { + e1 = find_anchor_wl_entry(&ubi->used); + if (!e1) + goto out_cancel; + e2 = get_peb_for_wl(ubi); + if (!e2) + goto out_cancel; + + self_check_in_wl_tree(ubi, e1, &ubi->used); + rb_erase(&e1->u.rb, &ubi->used); + dbg_wl("anchor-move PEB %d to PEB %d", e1->pnum, e2->pnum); + } else if (!ubi->scrub.rb_node) { +#else if (!ubi->scrub.rb_node) { +#endif /* * Now pick the least worn-out used physical eraseblock and a * 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, u.rb); - e2 = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF); + e2 = get_peb_for_wl(ubi); + if (!e2) + goto out_cancel; if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) { dbg_wl("no WL needed: min used EC %d, max free EC %d", @@ -682,14 +1074,15 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, /* Perform scrubbing */ scrubbing = 1; e1 = rb_entry(rb_first(&ubi->scrub), struct ubi_wl_entry, u.rb); - e2 = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF); + e2 = get_peb_for_wl(ubi); + if (!e2) + goto out_cancel; + self_check_in_wl_tree(ubi, e1, &ubi->scrub); rb_erase(&e1->u.rb, &ubi->scrub); dbg_wl("scrub PEB %d to PEB %d", e1->pnum, e2->pnum); } - self_check_in_wl_tree(ubi, e2, &ubi->free); - rb_erase(&e2->u.rb, &ubi->free); ubi->move_from = e1; ubi->move_to = e2; spin_unlock(&ubi->wl_lock); @@ -806,7 +1199,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, ubi->move_to_put = ubi->wl_scheduled = 0; spin_unlock(&ubi->wl_lock); - err = schedule_erase(ubi, e1, vol_id, lnum, 0); + err = do_sync_erase(ubi, e1, vol_id, lnum, 0); if (err) { kmem_cache_free(ubi_wl_entry_slab, e1); if (e2) @@ -821,7 +1214,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, */ dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase", e2->pnum, vol_id, lnum); - err = schedule_erase(ubi, e2, vol_id, lnum, 0); + err = do_sync_erase(ubi, e2, vol_id, lnum, 0); if (err) { kmem_cache_free(ubi_wl_entry_slab, e2); goto out_ro; @@ -860,7 +1253,7 @@ out_not_moved: spin_unlock(&ubi->wl_lock); ubi_free_vid_hdr(ubi, vid_hdr); - err = schedule_erase(ubi, e2, vol_id, lnum, torture); + err = do_sync_erase(ubi, e2, vol_id, lnum, torture); if (err) { kmem_cache_free(ubi_wl_entry_slab, e2); goto out_ro; @@ -901,12 +1294,13 @@ out_cancel: /** * ensure_wear_leveling - schedule wear-leveling if it is needed. * @ubi: UBI device description object + * @nested: set to non-zero if this function is called from UBI worker * * This function checks if it is time to start wear-leveling and schedules it * if yes. This function returns zero in case of success and a negative error * code in case of failure. */ -static int ensure_wear_leveling(struct ubi_device *ubi) +static int ensure_wear_leveling(struct ubi_device *ubi, int nested) { int err = 0; struct ubi_wl_entry *e1; @@ -934,7 +1328,7 @@ static int ensure_wear_leveling(struct ubi_device *ubi) * %UBI_WL_THRESHOLD. */ e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb); - e2 = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF); + e2 = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF); if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) goto out_unlock; @@ -951,8 +1345,12 @@ static int ensure_wear_leveling(struct ubi_device *ubi) goto out_cancel; } + wrk->anchor = 0; wrk->func = &wear_leveling_worker; - schedule_ubi_work(ubi, wrk); + if (nested) + __schedule_ubi_work(ubi, wrk); + else + schedule_ubi_work(ubi, wrk); return err; out_cancel: @@ -963,6 +1361,38 @@ out_unlock: return err; } +#ifdef CONFIG_MTD_UBI_FASTMAP +/** + * ubi_ensure_anchor_pebs - schedule wear-leveling to produce an anchor PEB. + * @ubi: UBI device description object + */ +int ubi_ensure_anchor_pebs(struct ubi_device *ubi) +{ + struct ubi_work *wrk; + + spin_lock(&ubi->wl_lock); + if (ubi->wl_scheduled) { + spin_unlock(&ubi->wl_lock); + return 0; + } + ubi->wl_scheduled = 1; + spin_unlock(&ubi->wl_lock); + + wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS); + if (!wrk) { + spin_lock(&ubi->wl_lock); + ubi->wl_scheduled = 0; + spin_unlock(&ubi->wl_lock); + return -ENOMEM; + } + + wrk->anchor = 1; + wrk->func = &wear_leveling_worker; + schedule_ubi_work(ubi, wrk); + return 0; +} +#endif + /** * erase_worker - physical eraseblock erase worker function. * @ubi: UBI device description object @@ -993,6 +1423,8 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, dbg_wl("erase PEB %d EC %d LEB %d:%d", pnum, e->ec, wl_wrk->vol_id, wl_wrk->lnum); + ubi_assert(!ubi_is_fm_block(ubi, e->pnum)); + err = sync_erase(ubi, e, wl_wrk->torture); if (!err) { /* Fine, we've erased it successfully */ @@ -1000,6 +1432,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, spin_lock(&ubi->wl_lock); wl_tree_add(e, &ubi->free); + ubi->free_count++; spin_unlock(&ubi->wl_lock); /* @@ -1009,7 +1442,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, serve_prot_queue(ubi); /* And take care about wear-leveling */ - err = ensure_wear_leveling(ubi); + err = ensure_wear_leveling(ubi, 1); return err; } @@ -1247,7 +1680,7 @@ retry: * Technically scrubbing is the same as wear-leveling, so it is done * by the WL worker. */ - return ensure_wear_leveling(ubi); + return ensure_wear_leveling(ubi, 0); } /** @@ -1428,7 +1861,7 @@ static void cancel_pending(struct ubi_device *ubi) */ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) { - int err, i; + int err, i, reserved_pebs, found_pebs = 0; struct rb_node *rb1, *rb2; struct ubi_ainf_volume *av; struct ubi_ainf_peb *aeb, *tmp; @@ -1440,6 +1873,9 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) init_rwsem(&ubi->work_sem); ubi->max_ec = ai->max_ec; INIT_LIST_HEAD(&ubi->works); +#ifdef CONFIG_MTD_UBI_FASTMAP + INIT_WORK(&ubi->fm_work, update_fastmap_work_fn); +#endif sprintf(ubi->bgt_name, UBI_BGT_NAME_PATTERN, ubi->ubi_num); @@ -1461,13 +1897,17 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) e->pnum = aeb->pnum; e->ec = aeb->ec; + ubi_assert(!ubi_is_fm_block(ubi, e->pnum)); ubi->lookuptbl[e->pnum] = e; if (schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0)) { kmem_cache_free(ubi_wl_entry_slab, e); goto out_free; } + + found_pebs++; } + ubi->free_count = 0; list_for_each_entry(aeb, &ai->free, u.list) { cond_resched(); @@ -1478,8 +1918,14 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) e->pnum = aeb->pnum; e->ec = aeb->ec; ubi_assert(e->ec >= 0); + ubi_assert(!ubi_is_fm_block(ubi, e->pnum)); + wl_tree_add(e, &ubi->free); + ubi->free_count++; + ubi->lookuptbl[e->pnum] = e; + + found_pebs++; } ubi_rb_for_each_entry(rb1, av, &ai->volumes, rb) { @@ -1493,6 +1939,7 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) e->pnum = aeb->pnum; e->ec = aeb->ec; ubi->lookuptbl[e->pnum] = e; + if (!aeb->scrub) { dbg_wl("add PEB %d EC %d to the used tree", e->pnum, e->ec); @@ -1502,22 +1949,38 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) e->pnum, e->ec); wl_tree_add(e, &ubi->scrub); } + + found_pebs++; } } - if (ubi->avail_pebs < WL_RESERVED_PEBS) { + dbg_wl("found %i PEBs", found_pebs); + + if (ubi->fm) + ubi_assert(ubi->good_peb_count == \ + found_pebs + ubi->fm->used_blocks); + else + ubi_assert(ubi->good_peb_count == found_pebs); + + reserved_pebs = WL_RESERVED_PEBS; +#ifdef CONFIG_MTD_UBI_FASTMAP + /* Reserve enough LEBs to store two fastmaps. */ + reserved_pebs += (ubi->fm_size / ubi->leb_size) * 2; +#endif + + if (ubi->avail_pebs < reserved_pebs) { ubi_err("no enough physical eraseblocks (%d, need %d)", - ubi->avail_pebs, WL_RESERVED_PEBS); + ubi->avail_pebs, reserved_pebs); if (ubi->corr_peb_count) ubi_err("%d PEBs are corrupted and not used", ubi->corr_peb_count); goto out_free; } - ubi->avail_pebs -= WL_RESERVED_PEBS; - ubi->rsvd_pebs += WL_RESERVED_PEBS; + ubi->avail_pebs -= reserved_pebs; + ubi->rsvd_pebs += reserved_pebs; /* Schedule wear-leveling if needed */ - err = ensure_wear_leveling(ubi); + err = ensure_wear_leveling(ubi, 0); if (err) goto out_free; @@ -1596,7 +2059,7 @@ static int self_check_ec(struct ubi_device *ubi, int pnum, int ec) } read_ec = be64_to_cpu(ec_hdr->ec); - if (ec != read_ec) { + if (ec != read_ec && read_ec - ec > 1) { ubi_err("self-check failed for PEB %d", pnum); ubi_err("read EC is %lld, should be %d", read_ec, ec); dump_stack(); |