[RFC v9 4/5] pstore/blk: support pmsg for pstore block

From: liaoweixiong
Date: Tue Feb 19 2019 - 06:53:51 EST

To enable pmsg, just set pmsg_size when block device register blkzone.

Signed-off-by: liaoweixiong <liaoweixiong@xxxxxxxxxxxxxxxxx>
---
fs/pstore/Kconfig | 21 ++++
fs/pstore/blkoops.c | 11 ++
fs/pstore/blkzone.c | 254 +++++++++++++++++++++++++++++++++++++++++----
include/linux/pstore_blk.h | 1 +
4 files changed, 265 insertions(+), 22 deletions(-)

diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index a3c3f34..50d196e 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -210,6 +210,27 @@ config PSTORE_BLKOOPS_DMESG_SIZE
It is the first priority. Take care of that blkoops will take lower
priority settings if higher priority one do not set.

+config PSTORE_BLKOOPS_PMSG_SIZE
+ int "pmsg size in kbytes for blkoops"
+ depends on PSTORE_BLKOOPS
+ default 64
+ help
+ This just sets size of pmsg (pmsg_size) for pstore/blk. The value must
+ be a multiple of 4096. Pmsg work only if "blkdev" is set.
+
+ NOTE that, there are three ways to set parameters of blkoops and
+ prioritize according to configuration flexibility. That is
+ Kconfig < device tree < module parameters. It means that the value can
+ be overwritten by higher priority settings.
+ 1. Kconfig
+ It just sets a default value.
+ 2. device tree
+ It is set on device tree, which will overwrites value from Kconfig,
+ but can also be overwritten by module parameters.
+ 3. module parameters
+ It is the first priority. Take care of that blkoops will take lower
+ priority settings if higher priority one do not set.
+
config PSTORE_BLKOOPS_TOTAL_SIZE
int "total size in kbytes for blkoops"
depends on PSTORE_BLKOOPS
diff --git a/fs/pstore/blkoops.c b/fs/pstore/blkoops.c
index 3885584..5363b7f 100644
--- a/fs/pstore/blkoops.c
+++ b/fs/pstore/blkoops.c
@@ -30,6 +30,10 @@
module_param(dmesg_size, long, 0400);
MODULE_PARM_DESC(dmesg_size, "demsg size in kbytes");

+static long pmsg_size = -1;
+module_param(pmsg_size, long, 0400);
+MODULE_PARM_DESC(pmsg_size, "pmsg size in kbytes");
+
static long total_size = -1;
module_param(total_size, long, 0400);
MODULE_PARM_DESC(total_size, "total size in kbytes");
@@ -47,11 +51,13 @@ struct blkz_info blkz_info = {

struct blkoops_info {
unsigned long dmesg_size;
+ unsigned long pmsg_size;
unsigned long total_size;
const char *blkdev;
};
struct blkoops_info blkoops_info = {
.dmesg_size = CONFIG_PSTORE_BLKOOPS_DMESG_SIZE * 1024,
+ .pmsg_size = CONFIG_PSTORE_BLKOOPS_PMSG_SIZE * 1024,
.total_size = CONFIG_PSTORE_BLKOOPS_TOTAL_SIZE * 1024,
.blkdev = CONFIG_PSTORE_BLKOOPS_BLKDEV,
};
@@ -123,6 +129,7 @@ static int __init blkoops_parse_dt(struct blkoops_info *info,

parse_size("total-size", info->total_size);
parse_size("dmesg-size", info->dmesg_size);
+ parse_size("pmsg-size", info->pmsg_size);

#undef parse_size
return 0;
@@ -162,6 +169,7 @@ static int blkoops_probe(struct platform_device *pdev)

check_size(total_size, 4096);
check_size(dmesg_size, 4096);
+ check_size(pmsg_size, 4096);

#undef check_size

@@ -170,6 +178,7 @@ static int blkoops_probe(struct platform_device *pdev)
* through /sys/module/blkoops/parameters/
*/
dmesg_size = blkz_info.dmesg_size;
+ pmsg_size = blkz_info.pmsg_size;
total_size = blkz_info.total_size;
if (blkz_info.blkdev)
strncpy(blkdev, blkz_info.blkdev, 80 - 1);
@@ -217,6 +226,8 @@ void blkoops_register_dummy(void)
info->blkdev = (const char *)blkdev;
if (dmesg_size >= 0)
info->dmesg_size = (unsigned long)dmesg_size * 1024;
+ if (pmsg_size >= 0)
+ info->pmsg_size = (unsigned long)pmsg_size * 1024;

dummy = platform_device_register_data(NULL, MODNAME, -1, info,
sizeof(*info));
diff --git a/fs/pstore/blkzone.c b/fs/pstore/blkzone.c
index 83dd181..7a0129c 100644
--- a/fs/pstore/blkzone.c
+++ b/fs/pstore/blkzone.c
@@ -41,12 +41,14 @@
*
* @sig: signature to indicate header (BLK_SIG xor BLKZONE-type value)
* @datalen: length of data in @data
+ * @start: offset into @data where the beginning of the stored bytes begin
* @data: zone data.
*/
struct blkz_buffer {
#define BLK_SIG (0x43474244) /* DBGC */
uint32_t sig;
atomic_t datalen;
+ atomic_t start;
uint8_t data[];
};

@@ -79,6 +81,9 @@ struct blkz_dmesg_header {
* frontent name for this zone
* @buffer:
* pointer to data buffer managed by this zone
+ * @oldbuf:
+ * pointer to old data buffer. It is used for single zone such as pmsg,
+ * saving the old buffer.
* @buffer_size:
* bytes in @buffer->data
* @should_recover:
@@ -92,6 +97,7 @@ struct blkz_zone {
enum pstore_type_id type;

struct blkz_buffer *buffer;
+ struct blkz_buffer *oldbuf;
size_t buffer_size;
bool should_recover;
atomic_t dirty;
@@ -99,8 +105,10 @@ struct blkz_zone {

struct blkz_context {
struct blkz_zone **dbzs; /* dmesg block zones */
+ struct blkz_zone *pbz; /* Pmsg block zone */
unsigned int dmesg_max_cnt;
unsigned int dmesg_read_cnt;
+ unsigned int pmsg_read_cnt;
unsigned int dmesg_write_cnt;
/*
* the counter should be recovered when do recovery
@@ -133,6 +141,11 @@ static inline int buffer_datalen(struct blkz_zone *zone)
return atomic_read(&zone->buffer->datalen);
}

+static inline int buffer_start(struct blkz_zone *zone)
+{
+ return atomic_read(&zone->buffer->start);
+}
+
static inline bool is_on_panic(void)
{
struct blkz_context *cxt = &blkz_cxt;
@@ -389,6 +402,72 @@ static int blkz_recover_dmesg(struct blkz_context *cxt)
return ret;
}

+static int blkz_recover_pmsg(struct blkz_context *cxt)
+{
+ struct blkz_info *info = cxt->bzinfo;
+ struct blkz_buffer *oldbuf;
+ struct blkz_zone *zone = NULL;
+ ssize_t (*readop)(char *buf, size_t bytes, loff_t pos);
+ int ret = 0;
+ ssize_t rcnt, len;
+
+ zone = cxt->pbz;
+ if (!zone || zone->oldbuf)
+ return 0;
+
+ if (is_on_panic())
+ goto out;
+
+ readop = info->read;
+ if (unlikely(!readop))
+ return -EINVAL;
+
+ len = zone->buffer_size + sizeof(*oldbuf);
+ oldbuf = kzalloc(len, GFP_KERNEL);
+ if (!oldbuf)
+ return -ENOMEM;
+
+ rcnt = readop((char *)oldbuf, len, zone->off);
+ if (rcnt != len) {
+ pr_debug("recover pmsg failed\n");
+ ret = (int)rcnt < 0 ? (int)rcnt : -EIO;
+ goto free_oldbuf;
+ }
+
+ if (oldbuf->sig != zone->buffer->sig) {
+ pr_debug("no valid data in zone %s\n", zone->name);
+ goto free_oldbuf;
+ }
+
+ if (zone->buffer_size < atomic_read(&oldbuf->datalen) ||
+ zone->buffer_size < atomic_read(&oldbuf->start)) {
+ pr_info("found overtop zone: %s: off %lu, size %zu\n",
+ zone->name, zone->off, zone->buffer_size);
+ goto free_oldbuf;
+ }
+
+ if (!atomic_read(&oldbuf->datalen)) {
+ pr_debug("found erased zone: %s: id 0, off %lu, size %zu, datalen %d\n",
+ zone->name, zone->off, zone->buffer_size,
+ atomic_read(&oldbuf->datalen));
+ kfree(oldbuf);
+ goto out;
+ }
+
+ pr_debug("found nice zone: %s: id 0, off %lu, size %zu, datalen %d\n",
+ zone->name, zone->off, zone->buffer_size,
+ atomic_read(&oldbuf->datalen));
+ zone->oldbuf = oldbuf;
+out:
+ if (atomic_read(&zone->dirty))
+ blkz_zone_write(zone, FLUSH_ALL, NULL, buffer_datalen(zone), 0);
+ return 0;
+
+free_oldbuf:
+ kfree(oldbuf);
+ return ret;
+}
+
static inline int blkz_recovery(struct blkz_context *cxt)
{
int ret = -EBUSY;
@@ -400,6 +479,10 @@ static inline int blkz_recovery(struct blkz_context *cxt)
if (ret)
goto recover_fail;

+ ret = blkz_recover_pmsg(cxt);
+ if (ret)
+ goto recover_fail;
+
atomic_set(&cxt->recovery, 1);
pr_debug("recover end!\n");
return 0;
@@ -417,11 +500,18 @@ static int blkz_pstore_open(struct pstore_info *psi)
return 0;
}

+static inline bool blkz_old_ok(struct blkz_zone *zone)
+{
+ if (zone && zone->oldbuf && atomic_read(&zone->oldbuf->datalen))
+ return true;
+ return false;
+}
+
static inline bool blkz_ok(struct blkz_zone *zone)
{
- if (!zone || !zone->buffer || !buffer_datalen(zone))
- return false;
- return true;
+ if (zone && zone->buffer && buffer_datalen(zone))
+ return true;
+ return false;
}

static int blkz_pstore_erase(struct pstore_record *record)
@@ -429,13 +519,29 @@ static int blkz_pstore_erase(struct pstore_record *record)
struct blkz_context *cxt = record->psi->data;
struct blkz_zone *zone = NULL;

- if (record->type == PSTORE_TYPE_DMESG)
+ if (record->type == PSTORE_TYPE_DMESG) {
zone = cxt->dbzs[record->id];
- if (!blkz_ok(zone))
- return 0;
+ if (unlikely(!blkz_ok(zone)))
+ return 0;

- atomic_set(&zone->buffer->datalen, 0);
- return blkz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+ atomic_set(&zone->buffer->datalen, 0);
+ return blkz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+ } else if (record->type == PSTORE_TYPE_PMSG) {
+ zone = cxt->pbz;
+ if (unlikely(!blkz_old_ok(zone)))
+ return 0;
+
+ kfree(zone->oldbuf);
+ zone->oldbuf = NULL;
+ /**
+ * if there is new data in zone buffer, there is no need to
+ * flush 0 (erase) to block device
+ */
+ if (buffer_datalen(zone))
+ return 0;
+ return blkz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+ }
+ return -EINVAL;
}

static void blkz_write_kmsg_hdr(struct blkz_zone *zone,
@@ -453,8 +559,10 @@ static void blkz_write_kmsg_hdr(struct blkz_zone *zone,
hdr->reason = record->reason;
if (hdr->reason == KMSG_DUMP_OOPS)
hdr->counter = ++cxt->oops_counter;
- else
+ else if (hdr->reason == KMSG_DUMP_PANIC)
hdr->counter = ++cxt->panic_counter;
+ else
+ hdr->counter = 0;
}

static int notrace blkz_dmesg_write(struct blkz_context *cxt,
@@ -504,6 +612,55 @@ static int notrace blkz_dmesg_write(struct blkz_context *cxt,
return 0;
}

+static int notrace blkz_pmsg_write(struct blkz_context *cxt,
+ struct pstore_record *record)
+{
+ struct blkz_zone *zone;
+ size_t start, rem;
+ int cnt = record->size;
+ bool is_full_data = false;
+ char *buf = record->buf;
+
+ zone = cxt->pbz;
+ if (!zone)
+ return -ENOSPC;
+
+ if (atomic_read(&zone->buffer->datalen) >= zone->buffer_size)
+ is_full_data = true;
+
+ if (unlikely(cnt > zone->buffer_size)) {
+ buf += cnt - zone->buffer_size;
+ cnt = zone->buffer_size;
+ }
+
+ start = buffer_start(zone);
+ rem = zone->buffer_size - start;
+ if (unlikely(rem < cnt)) {
+ blkz_zone_write(zone, FLUSH_PART, buf, rem, start);
+ buf += rem;
+ cnt -= rem;
+ start = 0;
+ is_full_data = true;
+ }
+
+ atomic_set(&zone->buffer->start, cnt + start);
+ blkz_zone_write(zone, FLUSH_PART, buf, cnt, start);
+
+ /**
+ * blkz_zone_write will set datalen as start + cnt.
+ * It work if actual data length lesser than buffer size.
+ * If data length greater than buffer size, pmsg will rewrite to
+ * beginning of zone, which make buffer->datalen wrongly.
+ * So we should reset datalen as buffer size once actual data length
+ * greater than buffer size.
+ */
+ if (is_full_data) {
+ atomic_set(&zone->buffer->datalen, zone->buffer_size);
+ blkz_zone_write(zone, FLUSH_META, NULL, 0, 0);
+ }
+ return 0;
+}
+
static int notrace blkz_pstore_write(struct pstore_record *record)
{
struct blkz_context *cxt = record->psi->data;
@@ -521,6 +678,8 @@ static int notrace blkz_pstore_write(struct pstore_record *record)
switch (record->type) {
case PSTORE_TYPE_DMESG:
return blkz_dmesg_write(cxt, record);
+ case PSTORE_TYPE_PMSG:
+ return blkz_pmsg_write(cxt, record);
default:
return -EINVAL;
}
@@ -537,6 +696,13 @@ static struct blkz_zone *blkz_read_next_zone(struct blkz_context *cxt)
return zone;
}

+ if (cxt->pmsg_read_cnt == 0) {
+ cxt->pmsg_read_cnt++;
+ zone = cxt->pbz;
+ if (blkz_old_ok(zone))
+ return zone;
+ }
+
return NULL;
}

@@ -575,7 +741,8 @@ static ssize_t blkz_dmesg_read(struct blkz_zone *zone,
char *buf = kasprintf(GFP_KERNEL,
"%s: Total %d times\n",
record->reason == KMSG_DUMP_OOPS ? "Oops" :
- "Panic", record->count);
+ record->reason == KMSG_DUMP_PANIC ? "Panic" :
+ "Unknown", record->count);
hlen = strlen(buf);
record->buf = krealloc(buf, hlen + size, GFP_KERNEL);
if (!record->buf) {
@@ -597,6 +764,29 @@ static ssize_t blkz_dmesg_read(struct blkz_zone *zone,
return size + hlen;
}

+static ssize_t blkz_pmsg_read(struct blkz_zone *zone,
+ struct pstore_record *record)
+{
+ size_t size, start;
+ struct blkz_buffer *buf;
+
+ buf = (struct blkz_buffer *)zone->oldbuf;
+ if (!buf)
+ return READ_NEXT_ZONE;
+
+ size = atomic_read(&buf->datalen);
+ start = atomic_read(&buf->start);
+
+ record->buf = kmalloc(size, GFP_KERNEL);
+ if (!record->buf)
+ return -ENOMEM;
+
+ memcpy(record->buf, buf->data + start, size - start);
+ memcpy(record->buf + size - start, buf->data, start);
+
+ return size;
+}
+
static ssize_t blkz_pstore_read(struct pstore_record *record)
{
struct blkz_context *cxt = record->psi->data;
@@ -622,6 +812,9 @@ static ssize_t blkz_pstore_read(struct pstore_record *record)
blkz_read = blkz_dmesg_read;
record->id = cxt->dmesg_read_cnt - 1;
break;
+ case PSTORE_TYPE_PMSG:
+ blkz_read = blkz_pmsg_read;
+ break;
default:
goto next_zone;
}
@@ -798,8 +991,10 @@ static struct blkz_zone *blkz_init_zone(enum pstore_type_id type,
zone->type = type;
zone->buffer_size = size - sizeof(struct blkz_buffer);
zone->buffer->sig = type ^ BLK_SIG;
+ zone->oldbuf = NULL;
atomic_set(&zone->dirty, 0);
atomic_set(&zone->buffer->datalen, 0);
+ atomic_set(&zone->buffer->start, 0);

*off += size;

@@ -881,7 +1076,7 @@ static int blkz_cut_zones(struct blkz_context *cxt)
int err;
size_t size;

- size = info->total_size;
+ size = info->total_size - info->pmsg_size;
cxt->dbzs = blkz_init_zones(PSTORE_TYPE_DMESG, &off, size,
info->dmesg_size, &cxt->dmesg_max_cnt);
if (IS_ERR(cxt->dbzs)) {
@@ -889,7 +1084,16 @@ static int blkz_cut_zones(struct blkz_context *cxt)
goto fail_out;
}

+ size = info->pmsg_size;
+ cxt->pbz = blkz_init_zone(PSTORE_TYPE_PMSG, &off, size);
+ if (IS_ERR(cxt->pbz)) {
+ err = PTR_ERR(cxt->pbz);
+ goto free_dmesg_zones;
+ }
+
return 0;
+free_dmesg_zones:
+ blkz_free_zones(&cxt->dbzs, &cxt->dmesg_max_cnt);
fail_out:
return err;
}
@@ -911,7 +1115,7 @@ int blkz_register(struct blkz_info *info)
}
}

- if (!info->total_size || !info->dmesg_size) {
+ if (!info->total_size || (!info->dmesg_size && !info->pmsg_size)) {
pr_warn("The total size and the dmesg size must be non-zero\n");
return -EINVAL;
}
@@ -931,6 +1135,7 @@ int blkz_register(struct blkz_info *info)

check_size(total_size, 4096);
check_size(dmesg_size, SECTOR_SIZE);
+ check_size(pmsg_size, SECTOR_SIZE);

#undef check_size

@@ -957,20 +1162,25 @@ int blkz_register(struct blkz_info *info)
goto fail_out;
}

- cxt->pstore.bufsize = cxt->dbzs[0]->buffer_size -
+ if (info->dmesg_size) {
+ cxt->pstore.bufsize = cxt->dbzs[0]->buffer_size -
sizeof(struct blkz_dmesg_header);
- cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL);
- if (!cxt->pstore.buf) {
- pr_err("cannot allocate pstore crash dump buffer\n");
- err = -ENOMEM;
- goto fail_out;
+ cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL);
+ if (!cxt->pstore.buf) {
+ err = -ENOMEM;
+ goto fail_out;
+ }
}
cxt->pstore.data = cxt;
- cxt->pstore.flags = PSTORE_FLAGS_DMESG;
+ if (info->dmesg_size)
+ cxt->pstore.flags |= PSTORE_FLAGS_DMESG;
+ if (info->pmsg_size)
+ cxt->pstore.flags |= PSTORE_FLAGS_PMSG;

- pr_info("Registered %s as blkzone backend for %s%s\n", info->name,
+ pr_info("Registered %s as blkzone backend for %s%s%s\n", info->name,
cxt->dbzs && cxt->bzinfo->dump_oops ? "Oops " : "",
- cxt->dbzs && cxt->bzinfo->panic_write ? "Panic " : "");
+ cxt->dbzs && cxt->bzinfo->panic_write ? "Panic " : "",
+ cxt->pbz ? "Pmsg" : "");

err = pstore_register(&cxt->pstore);
if (err) {
@@ -1004,7 +1214,7 @@ void blkz_unregister(struct blkz_info *info)
spin_unlock(&cxt->bzinfo_lock);

blkz_free_zones(&cxt->dbzs, &cxt->dmesg_max_cnt);
-
+ blkz_free_zone(&cxt->pbz);
}
EXPORT_SYMBOL_GPL(blkz_unregister);

diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h
index 2d2ff97..9f2b9a9 100644
--- a/include/linux/pstore_blk.h
+++ b/include/linux/pstore_blk.h
@@ -69,6 +69,7 @@ struct blkz_info {
const char *blkdev;
unsigned long total_size;
unsigned long dmesg_size;
+ unsigned long pmsg_size;
int dump_oops;
blkz_read_op read;
blkz_write_op write;
--
1.9.1