diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-01 12:07:34 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-01 12:07:34 -0700 |
commit | 829f3b9401fe7cc3c1f3642bb2520751a42a87df (patch) | |
tree | 55182cd94384d7c26adb398954736d338733b1e0 | |
parent | 81e8c10dac62c427b25f6bbb07936806e4dd9e8a (diff) | |
parent | 78c08247b9d3e03192f8b359aa079024e805a948 (diff) | |
download | linux-829f3b9401fe7cc3c1f3642bb2520751a42a87df.tar.gz linux-829f3b9401fe7cc3c1f3642bb2520751a42a87df.tar.bz2 linux-829f3b9401fe7cc3c1f3642bb2520751a42a87df.zip |
Merge tag 'pstore-v5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
Pull pstore updates from Kees Cook:
"Fixes and new features for pstore.
This is a pretty big set of changes (relative to past pstore pulls),
but it has been in -next for a while. The biggest change here is the
ability to support a block device as a pstore backend, which has been
desired for a while. A lot of additional fixes and refactorings are
also included, mostly in support of the new features.
- refactor pstore locking for safer module unloading (Kees Cook)
- remove orphaned records from pstorefs when backend unloaded (Kees
Cook)
- refactor dump_oops parameter into max_reason (Pavel Tatashin)
- introduce pstore/zone for common code for contiguous storage
(WeiXiong Liao)
- introduce pstore/blk for block device backend (WeiXiong Liao)
- introduce mtd backend (WeiXiong Liao)"
* tag 'pstore-v5.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux: (35 commits)
mtd: Support kmsg dumper based on pstore/blk
pstore/blk: Introduce "best_effort" mode
pstore/blk: Support non-block storage devices
pstore/blk: Provide way to query pstore configuration
pstore/zone: Provide way to skip "broken" zone for MTD devices
Documentation: Add details for pstore/blk
pstore/zone,blk: Add ftrace frontend support
pstore/zone,blk: Add console frontend support
pstore/zone,blk: Add support for pmsg frontend
pstore/blk: Introduce backend for block devices
pstore/zone: Introduce common layer to manage storage zones
ramoops: Add "max-reason" optional field to ramoops DT node
pstore/ram: Introduce max_reason and convert dump_oops
pstore/platform: Pass max_reason to kmesg dump
printk: Introduce kmsg_dump_reason_str()
printk: honor the max_reason field in kmsg_dumper
printk: Collapse shutdown types into a single dump reason
pstore/ftrace: Provide ftrace log merging routine
pstore/ram: Refactor ftrace buffer merging
pstore/ram: Refactor DT size parsing
...
-rw-r--r-- | Documentation/admin-guide/pstore-blk.rst | 243 | ||||
-rw-r--r-- | Documentation/admin-guide/ramoops.rst | 14 | ||||
-rw-r--r-- | Documentation/devicetree/bindings/reserved-memory/ramoops.txt | 13 | ||||
-rw-r--r-- | MAINTAINERS | 1 | ||||
-rw-r--r-- | arch/powerpc/kernel/nvram_64.c | 4 | ||||
-rw-r--r-- | drivers/mtd/Kconfig | 10 | ||||
-rw-r--r-- | drivers/mtd/Makefile | 1 | ||||
-rw-r--r-- | drivers/mtd/mtdpstore.c | 578 | ||||
-rw-r--r-- | drivers/platform/chrome/chromeos_pstore.c | 2 | ||||
-rw-r--r-- | fs/pstore/Kconfig | 109 | ||||
-rw-r--r-- | fs/pstore/Makefile | 6 | ||||
-rw-r--r-- | fs/pstore/blk.c | 517 | ||||
-rw-r--r-- | fs/pstore/ftrace.c | 54 | ||||
-rw-r--r-- | fs/pstore/inode.c | 129 | ||||
-rw-r--r-- | fs/pstore/internal.h | 11 | ||||
-rw-r--r-- | fs/pstore/platform.c | 117 | ||||
-rw-r--r-- | fs/pstore/ram.c | 155 | ||||
-rw-r--r-- | fs/pstore/zone.c | 1465 | ||||
-rw-r--r-- | include/linux/kmsg_dump.h | 12 | ||||
-rw-r--r-- | include/linux/pstore.h | 9 | ||||
-rw-r--r-- | include/linux/pstore_blk.h | 118 | ||||
-rw-r--r-- | include/linux/pstore_ram.h | 2 | ||||
-rw-r--r-- | include/linux/pstore_zone.h | 60 | ||||
-rw-r--r-- | kernel/printk/printk.c | 32 | ||||
-rw-r--r-- | kernel/reboot.c | 6 | ||||
-rwxr-xr-x | tools/testing/selftests/pstore/pstore_tests | 2 |
26 files changed, 3464 insertions, 206 deletions
diff --git a/Documentation/admin-guide/pstore-blk.rst b/Documentation/admin-guide/pstore-blk.rst new file mode 100644 index 000000000000..296d5027787a --- /dev/null +++ b/Documentation/admin-guide/pstore-blk.rst @@ -0,0 +1,243 @@ +.. SPDX-License-Identifier: GPL-2.0 + +pstore block oops/panic logger +============================== + +Introduction +------------ + +pstore block (pstore/blk) is an oops/panic logger that writes its logs to a +block device and non-block device before the system crashes. You can get +these log files by mounting pstore filesystem like:: + + mount -t pstore pstore /sys/fs/pstore + + +pstore block concepts +--------------------- + +pstore/blk provides efficient configuration method for pstore/blk, which +divides all configurations into two parts, configurations for user and +configurations for driver. + +Configurations for user determine how pstore/blk works, such as pmsg_size, +kmsg_size and so on. All of them support both Kconfig and module parameters, +but module parameters have priority over Kconfig. + +Configurations for driver are all about block device and non-block device, +such as total_size of block device and read/write operations. + +Configurations for user +----------------------- + +All of these configurations support both Kconfig and module parameters, but +module parameters have priority over Kconfig. + +Here is an example for module parameters:: + + pstore_blk.blkdev=179:7 pstore_blk.kmsg_size=64 + +The detail of each configurations may be of interest to you. + +blkdev +~~~~~~ + +The block device to use. Most of the time, it is a partition of block device. +It's required for pstore/blk. It is also used for MTD device. + +It accepts the following variants for block device: + +1. <hex_major><hex_minor> device number in hexadecimal represents itself; no + leading 0x, for example b302. +#. /dev/<disk_name> represents the device number of disk +#. /dev/<disk_name><decimal> represents the device number of partition - device + number of disk plus the partition number +#. /dev/<disk_name>p<decimal> - same as the above; this form is used when disk + name of partitioned disk ends with a digit. +#. PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF represents the unique id of + a partition if the partition table provides it. The UUID may be either an + EFI/GPT UUID, or refer to an MSDOS partition using the format SSSSSSSS-PP, + where SSSSSSSS is a zero-filled hex representation of the 32-bit + "NT disk signature", and PP is a zero-filled hex representation of the + 1-based partition number. +#. PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to a + partition with a known unique id. +#. <major>:<minor> major and minor number of the device separated by a colon. + +It accepts the following variants for MTD device: + +1. <device name> MTD device name. "pstore" is recommended. +#. <device number> MTD device number. + +kmsg_size +~~~~~~~~~ + +The chunk size in KB for oops/panic front-end. It **MUST** be a multiple of 4. +It's optional if you do not care oops/panic log. + +There are multiple chunks for oops/panic front-end depending on the remaining +space except other pstore front-ends. + +pstore/blk will log to oops/panic chunks one by one, and always overwrite the +oldest chunk if there is no more free chunk. + +pmsg_size +~~~~~~~~~ + +The chunk size in KB for pmsg front-end. It **MUST** be a multiple of 4. +It's optional if you do not care pmsg log. + +Unlike oops/panic front-end, there is only one chunk for pmsg front-end. + +Pmsg is a user space accessible pstore object. Writes to */dev/pmsg0* are +appended to the chunk. On reboot the contents are available in +*/sys/fs/pstore/pmsg-pstore-blk-0*. + +console_size +~~~~~~~~~~~~ + +The chunk size in KB for console front-end. It **MUST** be a multiple of 4. +It's optional if you do not care console log. + +Similar to pmsg front-end, there is only one chunk for console front-end. + +All log of console will be appended to the chunk. On reboot the contents are +available in */sys/fs/pstore/console-pstore-blk-0*. + +ftrace_size +~~~~~~~~~~~ + +The chunk size in KB for ftrace front-end. It **MUST** be a multiple of 4. +It's optional if you do not care console log. + +Similar to oops front-end, there are multiple chunks for ftrace front-end +depending on the count of cpu processors. Each chunk size is equal to +ftrace_size / processors_count. + +All log of ftrace will be appended to the chunk. On reboot the contents are +combined and available in */sys/fs/pstore/ftrace-pstore-blk-0*. + +Persistent function tracing might be useful for debugging software or hardware +related hangs. Here is an example of usage:: + + # mount -t pstore pstore /sys/fs/pstore + # mount -t debugfs debugfs /sys/kernel/debug/ + # echo 1 > /sys/kernel/debug/pstore/record_ftrace + # reboot -f + [...] + # mount -t pstore pstore /sys/fs/pstore + # tail /sys/fs/pstore/ftrace-pstore-blk-0 + CPU:0 ts:5914676 c0063828 c0063b94 call_cpuidle <- cpu_startup_entry+0x1b8/0x1e0 + CPU:0 ts:5914678 c039ecdc c006385c cpuidle_enter_state <- call_cpuidle+0x44/0x48 + CPU:0 ts:5914680 c039e9a0 c039ecf0 cpuidle_enter_freeze <- cpuidle_enter_state+0x304/0x314 + CPU:0 ts:5914681 c0063870 c039ea30 sched_idle_set_state <- cpuidle_enter_state+0x44/0x314 + CPU:1 ts:5916720 c0160f59 c015ee04 kernfs_unmap_bin_file <- __kernfs_remove+0x140/0x204 + CPU:1 ts:5916721 c05ca625 c015ee0c __mutex_lock_slowpath <- __kernfs_remove+0x148/0x204 + CPU:1 ts:5916723 c05c813d c05ca630 yield_to <- __mutex_lock_slowpath+0x314/0x358 + CPU:1 ts:5916724 c05ca2d1 c05ca638 __ww_mutex_lock <- __mutex_lock_slowpath+0x31c/0x358 + +max_reason +~~~~~~~~~~ + +Limiting which kinds of kmsg dumps are stored can be controlled via +the ``max_reason`` value, as defined in include/linux/kmsg_dump.h's +``enum kmsg_dump_reason``. For example, to store both Oopses and Panics, +``max_reason`` should be set to 2 (KMSG_DUMP_OOPS), to store only Panics +``max_reason`` should be set to 1 (KMSG_DUMP_PANIC). Setting this to 0 +(KMSG_DUMP_UNDEF), means the reason filtering will be controlled by the +``printk.always_kmsg_dump`` boot param: if unset, it'll be KMSG_DUMP_OOPS, +otherwise KMSG_DUMP_MAX. + +Configurations for driver +------------------------- + +Only a block device driver cares about these configurations. A block device +driver uses ``register_pstore_blk`` to register to pstore/blk. + +.. kernel-doc:: fs/pstore/blk.c + :identifiers: register_pstore_blk + +A non-block device driver uses ``register_pstore_device`` with +``struct pstore_device_info`` to register to pstore/blk. + +.. kernel-doc:: fs/pstore/blk.c + :identifiers: register_pstore_device + +.. kernel-doc:: include/linux/pstore_blk.h + :identifiers: pstore_device_info + +Compression and header +---------------------- + +Block device is large enough for uncompressed oops data. Actually we do not +recommend data compression because pstore/blk will insert some information into +the first line of oops/panic data. For example:: + + Panic: Total 16 times + +It means that it's OOPS|Panic for the 16th time since the first booting. +Sometimes the number of occurrences of oops|panic since the first booting is +important to judge whether the system is stable. + +The following line is inserted by pstore filesystem. For example:: + + Oops#2 Part1 + +It means that it's OOPS for the 2nd time on the last boot. + +Reading the data +---------------- + +The dump data can be read from the pstore filesystem. The format for these +files is ``dmesg-pstore-blk-[N]`` for oops/panic front-end, +``pmsg-pstore-blk-0`` for pmsg front-end and so on. The timestamp of the +dump file records the trigger time. To delete a stored record from block +device, simply unlink the respective pstore file. + +Attentions in panic read/write APIs +----------------------------------- + +If on panic, the kernel is not going to run for much longer, the tasks will not +be scheduled and most kernel resources will be out of service. It +looks like a single-threaded program running on a single-core computer. + +The following points require special attention for panic read/write APIs: + +1. Can **NOT** allocate any memory. + If you need memory, just allocate while the block driver is initializing + rather than waiting until the panic. +#. Must be polled, **NOT** interrupt driven. + No task schedule any more. The block driver should delay to ensure the write + succeeds, but NOT sleep. +#. Can **NOT** take any lock. + There is no other task, nor any shared resource; you are safe to break all + locks. +#. Just use CPU to transfer. + Do not use DMA to transfer unless you are sure that DMA will not keep lock. +#. Control registers directly. + Please control registers directly rather than use Linux kernel resources. + Do I/O map while initializing rather than wait until a panic occurs. +#. Reset your block device and controller if necessary. + If you are not sure of the state of your block device and controller when + a panic occurs, you are safe to stop and reset them. + +pstore/blk supports psblk_blkdev_info(), which is defined in +*linux/pstore_blk.h*, to get information of using block device, such as the +device number, sector count and start sector of the whole disk. + +pstore block internals +---------------------- + +For developer reference, here are all the important structures and APIs: + +.. kernel-doc:: fs/pstore/zone.c + :internal: + +.. kernel-doc:: include/linux/pstore_zone.h + :internal: + +.. kernel-doc:: fs/pstore/blk.c + :export: + +.. kernel-doc:: include/linux/pstore_blk.h + :internal: diff --git a/Documentation/admin-guide/ramoops.rst b/Documentation/admin-guide/ramoops.rst index 6dbcc5481000..a60a96218ba9 100644 --- a/Documentation/admin-guide/ramoops.rst +++ b/Documentation/admin-guide/ramoops.rst @@ -32,11 +32,17 @@ memory to be mapped strongly ordered, and atomic operations on strongly ordered memory are implementation defined, and won't work on many ARMs such as omaps. The memory area is divided into ``record_size`` chunks (also rounded down to -power of two) and each oops/panic writes a ``record_size`` chunk of +power of two) and each kmesg dump writes a ``record_size`` chunk of information. -Dumping both oopses and panics can be done by setting 1 in the ``dump_oops`` -variable while setting 0 in that variable dumps only the panics. +Limiting which kinds of kmsg dumps are stored can be controlled via +the ``max_reason`` value, as defined in include/linux/kmsg_dump.h's +``enum kmsg_dump_reason``. For example, to store both Oopses and Panics, +``max_reason`` should be set to 2 (KMSG_DUMP_OOPS), to store only Panics +``max_reason`` should be set to 1 (KMSG_DUMP_PANIC). Setting this to 0 +(KMSG_DUMP_UNDEF), means the reason filtering will be controlled by the +``printk.always_kmsg_dump`` boot param: if unset, it'll be KMSG_DUMP_OOPS, +otherwise KMSG_DUMP_MAX. The module uses a counter to record multiple dumps but the counter gets reset on restart (i.e. new dumps after the restart will overwrite old ones). @@ -90,7 +96,7 @@ Setting the ramoops parameters can be done in several different manners: .mem_address = <...>, .mem_type = <...>, .record_size = <...>, - .dump_oops = <...>, + .max_reason = <...>, .ecc = <...>, }; diff --git a/Documentation/devicetree/bindings/reserved-memory/ramoops.txt b/Documentation/devicetree/bindings/reserved-memory/ramoops.txt index 0eba562fe5c6..b7886fea368c 100644 --- a/Documentation/devicetree/bindings/reserved-memory/ramoops.txt +++ b/Documentation/devicetree/bindings/reserved-memory/ramoops.txt @@ -30,7 +30,7 @@ Optional properties: - ecc-size: enables ECC support and specifies ECC buffer size in bytes (defaults to 0: no ECC) -- record-size: maximum size in bytes of each dump done on oops/panic +- record-size: maximum size in bytes of each kmsg dump. (defaults to 0: disabled) - console-size: size in bytes of log buffer reserved for kernel messages @@ -45,7 +45,16 @@ Optional properties: - unbuffered: if present, use unbuffered mappings to map the reserved region (defaults to buffered mappings) -- no-dump-oops: if present, only dump panics (defaults to panics and oops) +- max-reason: if present, sets maximum type of kmsg dump reasons to store + (defaults to 2: log Oopses and Panics). This can be set to INT_MAX to + store all kmsg dumps. See include/linux/kmsg_dump.h KMSG_DUMP_* for other + kmsg dump reason values. Setting this to 0 (KMSG_DUMP_UNDEF), means the + reason filtering will be controlled by the printk.always_kmsg_dump boot + param: if unset, it will be KMSG_DUMP_OOPS, otherwise KMSG_DUMP_MAX. + +- no-dump-oops: deprecated, use max_reason instead. If present, and + max_reason is not specified, it is equivalent to max_reason = 1 + (KMSG_DUMP_PANIC). - flags: if present, pass ramoops behavioral flags (defaults to 0, see include/linux/pstore_ram.h RAMOOPS_FLAG_* for flag values). diff --git a/MAINTAINERS b/MAINTAINERS index 2b17e667c52b..92ce8d21c925 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13715,6 +13715,7 @@ M: Tony Luck <tony.luck@intel.com> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/pstore F: Documentation/admin-guide/ramoops.rst +F: Documentation/admin-guide/pstore-blk.rst F: Documentation/devicetree/bindings/reserved-memory/ramoops.txt F: drivers/acpi/apei/erst.c F: drivers/firmware/efi/efi-pstore.c diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index fb4f61096613..0cd1c88bfc8b 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -655,9 +655,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, int rc = -1; switch (reason) { - case KMSG_DUMP_RESTART: - case KMSG_DUMP_HALT: - case KMSG_DUMP_POWEROFF: + case KMSG_DUMP_SHUTDOWN: /* These are almost always orderly shutdowns. */ return; case KMSG_DUMP_OOPS: diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig index 42d401ea60ee..6ddab796216d 100644 --- a/drivers/mtd/Kconfig +++ b/drivers/mtd/Kconfig @@ -170,6 +170,16 @@ config MTD_OOPS buffer in a flash partition where it can be read back at some later point. +config MTD_PSTORE + tristate "Log panic/oops to an MTD buffer based on pstore" + depends on PSTORE_BLK + help + This enables panic and oops messages to be logged to a circular + buffer in a flash partition where it can be read back as files after + mounting pstore filesystem. + + If unsure, say N. + config MTD_SWAP tristate "Swap on MTD device support" depends on MTD && SWAP diff --git a/drivers/mtd/Makefile b/drivers/mtd/Makefile index 56cc60ccc477..593d0593a038 100644 --- a/drivers/mtd/Makefile +++ b/drivers/mtd/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_RFD_FTL) += rfd_ftl.o obj-$(CONFIG_SSFDC) += ssfdc.o obj-$(CONFIG_SM_FTL) += sm_ftl.o obj-$(CONFIG_MTD_OOPS) += mtdoops.o +obj-$(CONFIG_MTD_PSTORE) += mtdpstore.o obj-$(CONFIG_MTD_SWAP) += mtdswap.o nftl-objs := nftlcore.o nftlmount.o diff --git a/drivers/mtd/mtdpstore.c b/drivers/mtd/mtdpstore.c new file mode 100644 index 000000000000..a4fe6060b960 --- /dev/null +++ b/drivers/mtd/mtdpstore.c @@ -0,0 +1,578 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define dev_fmt(fmt) "mtdoops-pstore: " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pstore_blk.h> +#include <linux/mtd/mtd.h> +#include <linux/bitops.h> + +static struct mtdpstore_context { + int index; + struct pstore_blk_config info; + struct pstore_device_info dev; + struct mtd_info *mtd; + unsigned long *rmmap; /* removed bit map */ + unsigned long *usedmap; /* used bit map */ + /* + * used for panic write + * As there are no block_isbad for panic case, we should keep this + * status before panic to ensure panic_write not failed. + */ + unsigned long *badmap; /* bad block bit map */ +} oops_cxt; + +static int mtdpstore_block_isbad(struct mtdpstore_context *cxt, loff_t off) +{ + int ret; + struct mtd_info *mtd = cxt->mtd; + u64 blknum; + + off = ALIGN_DOWN(off, mtd->erasesize); + blknum = div_u64(off, mtd->erasesize); + + if (test_bit(blknum, cxt->badmap)) + return true; + ret = mtd_block_isbad(mtd, off); + if (ret < 0) { + dev_err(&mtd->dev, "mtd_block_isbad failed, aborting\n"); + return ret; + } else if (ret > 0) { + set_bit(blknum, cxt->badmap); + return true; + } + return false; +} + +static inline int mtdpstore_panic_block_isbad(struct mtdpstore_context *cxt, + loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + u64 blknum; + + off = ALIGN_DOWN(off, mtd->erasesize); + blknum = div_u64(off, mtd->erasesize); + return test_bit(blknum, cxt->badmap); +} + +static inline void mtdpstore_mark_used(struct mtdpstore_context *cxt, + loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + u64 zonenum = div_u64(off, cxt->info.kmsg_size); + + dev_dbg(&mtd->dev, "mark zone %llu used\n", zonenum); + set_bit(zonenum, cxt->usedmap); +} + +static inline void mtdpstore_mark_unused(struct mtdpstore_context *cxt, + loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + u64 zonenum = div_u64(off, cxt->info.kmsg_size); + + dev_dbg(&mtd->dev, "mark zone %llu unused\n", zonenum); + clear_bit(zonenum, cxt->usedmap); +} + +static inline void mtdpstore_block_mark_unused(struct mtdpstore_context *cxt, + loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size; + u64 zonenum; + + off = ALIGN_DOWN(off, mtd->erasesize); + zonenum = div_u64(off, cxt->info.kmsg_size); + while (zonecnt > 0) { + dev_dbg(&mtd->dev, "mark zone %llu unused\n", zonenum); + clear_bit(zonenum, cxt->usedmap); + zonenum++; + zonecnt--; + } +} + +static inline int mtdpstore_is_used(struct mtdpstore_context *cxt, loff_t off) +{ + u64 zonenum = div_u64(off, cxt->info.kmsg_size); + u64 blknum = div_u64(off, cxt->mtd->erasesize); + + if (test_bit(blknum, cxt->badmap)) + return true; + return test_bit(zonenum, cxt->usedmap); +} + +static int mtdpstore_block_is_used(struct mtdpstore_context *cxt, + loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size; + u64 zonenum; + + off = ALIGN_DOWN(off, mtd->erasesize); + zonenum = div_u64(off, cxt->info.kmsg_size); + while (zonecnt > 0) { + if (test_bit(zonenum, cxt->usedmap)) + return true; + zonenum++; + zonecnt--; + } + return false; +} + +static int mtdpstore_is_empty(struct mtdpstore_context *cxt, char *buf, + size_t size) +{ + struct mtd_info *mtd = cxt->mtd; + size_t sz; + int i; + + sz = min_t(uint32_t, size, mtd->writesize / 4); + for (i = 0; i < sz; i++) { + if (buf[i] != (char)0xFF) + return false; + } + return true; +} + +static void mtdpstore_mark_removed(struct mtdpstore_context *cxt, loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + u64 zonenum = div_u64(off, cxt->info.kmsg_size); + + dev_dbg(&mtd->dev, "mark zone %llu removed\n", zonenum); + set_bit(zonenum, cxt->rmmap); +} + +static void mtdpstore_block_clear_removed(struct mtdpstore_context *cxt, + loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size; + u64 zonenum; + + off = ALIGN_DOWN(off, mtd->erasesize); + zonenum = div_u64(off, cxt->info.kmsg_size); + while (zonecnt > 0) { + clear_bit(zonenum, cxt->rmmap); + zonenum++; + zonecnt--; + } +} + +static int mtdpstore_block_is_removed(struct mtdpstore_context *cxt, + loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + u32 zonecnt = mtd->erasesize / cxt->info.kmsg_size; + u64 zonenum; + + off = ALIGN_DOWN(off, mtd->erasesize); + zonenum = div_u64(off, cxt->info.kmsg_size); + while (zonecnt > 0) { + if (test_bit(zonenum, cxt->rmmap)) + return true; + zonenum++; + zonecnt--; + } + return false; +} + +static int mtdpstore_erase_do(struct mtdpstore_context *cxt, loff_t off) +{ + struct mtd_info *mtd = cxt->mtd; + struct erase_info erase; + int ret; + + off = ALIGN_DOWN(off, cxt->mtd->erasesize); + dev_dbg(&mtd->dev, "try to erase off 0x%llx\n", off); + erase.len = cxt->mtd->erasesize; + erase.addr = off; + ret = mtd_erase(cxt->mtd, &erase); + if (!ret) + mtdpstore_block_clear_removed(cxt, off); + else + dev_err(&mtd->dev, "erase of region [0x%llx, 0x%llx] on \"%s\" failed\n", + (unsigned long long)erase.addr, + (unsigned long long)erase.len, cxt->info.device); + return ret; +} + +/* + * called while removing file + * + * Avoiding over erasing, do erase block only when the whole block is unused. + * If the block contains valid log, do erase lazily on flush_removed() when + * unregister. + */ +static ssize_t mtdpstore_erase(size_t size, loff_t off) +{ + struct mtdpstore_context *cxt = &oops_cxt; + + if (mtdpstore_block_isbad(cxt, off)) + return -EIO; + + mtdpstore_mark_unused(cxt, off); + + /* If the block still has valid data, mtdpstore do erase lazily */ + if (likely(mtdpstore_block_is_used(cxt, off))) { + mtdpstore_mark_removed(cxt, off); + return 0; + } + + /* all zones are unused, erase it */ + return mtdpstore_erase_do(cxt, off); +} + +/* + * What is security for mtdpstore? + * As there is no erase for panic case, we should ensure at least one zone + * is writable. Otherwise, panic write will fail. + * If zone is used, write operation will return -ENOMSG, which means that + * pstore/blk will try one by one until gets an empty zone. So, it is not + * needed to ensure the next zone is empty, but at least one. + */ +static int mtdpstore_security(struct mtdpstore_context *cxt, loff_t off) +{ + int ret = 0, i; + struct mtd_info *mtd = cxt->mtd; + u32 zonenum = (u32)div_u64(off, cxt->info.kmsg_size); + u32 zonecnt = (u32)div_u64(cxt->mtd->size, cxt->info.kmsg_size); + u32 blkcnt = (u32)div_u64(cxt->mtd->size, cxt->mtd->erasesize); + u32 erasesize = cxt->mtd->erasesize; + + for (i = 0; i < zonecnt; i++) { + u32 num = (zonenum + i) % zonecnt; + + /* found empty zone */ + if (!test_bit(num, cxt->usedmap)) + return 0; + } + + /* If there is no any empty zone, we have no way but to do erase */ + while (blkcnt--) { + div64_u64_rem(off + erasesize, cxt->mtd->size, (u64 *)&off); + + if (mtdpstore_block_isbad(cxt, off)) + continue; + + ret = mtdpstore_erase_do(cxt, off); + if (!ret) { + mtdpstore_block_mark_unused(cxt, off); + break; + } + } + + if (ret) + dev_err(&mtd->dev, "all blocks bad!\n"); + dev_dbg(&mtd->dev, "end security\n"); + return ret; +} + +static ssize_t mtdpstore_write(const char *buf, size_t size, loff_t off) +{ + struct mtdpstore_context *cxt = &oops_cxt; + struct mtd_info *mtd = cxt->mtd; + size_t retlen; + int ret; + + if (mtdpstore_block_isbad(cxt, off)) + return -ENOMSG; + + /* zone is used, please try next one */ + if (mtdpstore_is_used(cxt, off)) + return -ENOMSG; + + dev_dbg(&mtd->dev, "try to write off 0x%llx size %zu\n", off, size); + ret = mtd_write(cxt->mtd, off, size, &retlen, (u_char *)buf); + if (ret < 0 || retlen != size) { + dev_err(&mtd->dev, "write failure at %lld (%zu of %zu written), err %d\n", + off, retlen, size, ret); + return -EIO; + } + mtdpstore_mark_used(cxt, off); + + mtdpstore_security(cxt, off); + return retlen; +} + +static inline bool mtdpstore_is_io_error(int ret) +{ + return ret < 0 && !mtd_is_bitflip(ret) && !mtd_is_eccerr(ret); +} + +/* + * All zones will be read as pstore/blk will read zone one by one when do + * recover. + */ +static ssize_t mtdpstore_read(char *buf, size_t size, loff_t off) +{ + struct mtdpstore_context *cxt = &oops_cxt; + struct mtd_info *mtd = cxt->mtd; + size_t retlen, done; + int ret; + + if (mtdpstore_block_isbad(cxt, off)) + return -ENOMSG; + + dev_dbg(&mtd->dev, "try to read off 0x%llx size %zu\n", off, size); + for (done = 0, retlen = 0; done < size; done += retlen) { + retlen = 0; + + ret = mtd_read(cxt->mtd, off + done, size - done, &retlen, + (u_char *)buf + done); + if (mtdpstore_is_io_error(ret)) { + dev_err(&mtd->dev, "read failure at %lld (%zu of %zu read), err %d\n", + off + done, retlen, size - done, ret); + /* the zone may be broken, try next one */ + return -ENOMSG; + } + + /* + * ECC error. The impact on log data is so small. Maybe we can + * still read it and try to understand. So mtdpstore just hands + * over what it gets and user can judge whether the data is + * valid or not. + */ + if (mtd_is_eccerr(ret)) { + dev_err(&mtd->dev, "ecc error at %lld (%zu of %zu read), err %d\n", + off + done, retlen, size - done, ret); + /* driver may not set retlen when ecc error */ + retlen = retlen == 0 ? size - done : retlen; + } + } + + if (mtdpstore_is_empty(cxt, buf, size)) + mtdpstore_mark_unused(cxt, off); + else + mtdpstore_mark_used(cxt, off); + + mtdpstore_security(cxt, off); + return retlen; +} + +static ssize_t mtdpstore_panic_write(const char *buf, size_t size, loff_t off) +{ + struct mtdpstore_context *cxt = &oops_cxt; + struct mtd_info *mtd = cxt->mtd; + size_t retlen; + int ret; + + if (mtdpstore_panic_block_isbad(cxt, off)) + return -ENOMSG; + + /* zone is used, please try next one */ + if (mtdpstore_is_used(cxt, off)) + return -ENOMSG; + + ret = mtd_panic_write(cxt->mtd, off, size, &retlen, (u_char *)buf); + if (ret < 0 || size != retlen) { + dev_err(&mtd->dev, "panic write failure at %lld (%zu of %zu read), err %d\n", + off, retlen, size, ret); + return -EIO; + } + mtdpstore_mark_used(cxt, off); + + return retlen; +} + +static void mtdpstore_notify_add(struct mtd_info *mtd) +{ + int ret; + struct mtdpstore_context *cxt = &oops_cxt; + struct pstore_blk_config *info = &cxt->info; + unsigned long longcnt; + + if (!strcmp(mtd->name, info->device)) + cxt->index = mtd->index; + + if (mtd->index != cxt->index || cxt->index < 0) + return; + + dev_dbg(&mtd->dev, "found matching MTD device %s\n", mtd->name); + + if (mtd->size < info->kmsg_size * 2) { + dev_err(&mtd->dev, "MTD partition %d not big enough\n", + mtd->index); + return; + } + /* + * kmsg_size must be aligned to 4096 Bytes, which is limited by + * psblk. The default value of kmsg_size is 64KB. If kmsg_size + * is larger than erasesize, some errors will occur since mtdpsotre + * is designed on it. + */ + if (mtd->erasesize < info->kmsg_size) { + dev_err(&mtd->dev, "eraseblock size of MTD partition %d too small\n", + mtd->index); + return; + } + if (unlikely(info->kmsg_size % mtd->writesize)) { + dev_err(&mtd->dev, "record size %lu KB must align to write size %d KB\n", + info->kmsg_size / 1024, + mtd->writesize / 1024); + return; + } + + longcnt = BITS_TO_LONGS(div_u64(mtd->size, info->kmsg_size)); + cxt->rmmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL); + cxt->usedmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL); + + longcnt = BITS_TO_LONGS(div_u64(mtd->size, mtd->erasesize)); + cxt->badmap = kcalloc(longcnt, sizeof(long), GFP_KERNEL); + + cxt->dev.total_size = mtd->size; + /* just support dmesg right now */ + cxt->dev.flags = PSTORE_FLAGS_DMESG; + cxt->dev.read = mtdpstore_read; + cxt->dev.write = mtdpstore_write; + cxt->dev.erase = mtdpstore_erase; + cxt->dev.panic_write = mtdpstore_panic_write; + + ret = register_pstore_device(&cxt->dev); + if (ret) { + dev_err(&mtd->dev, "mtd%d register to psblk failed\n", + mtd->index); + return; + } + cxt->mtd = mtd; + dev_info(&mtd->dev, "Attached to MTD device %d\n", mtd->index); +} + +static int mtdpstore_flush_removed_do(struct mtdpstore_context *cxt, + loff_t off, size_t size) +{ + struct mtd_info *mtd = cxt->mtd; + u_char *buf; + int ret; + size_t retlen; + struct erase_info erase; + + buf = kmalloc(mtd->erasesize, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + /* 1st. read to cache */ + ret = mtd_read(mtd, off, mtd->erasesize, &retlen, buf); + if (mtdpstore_is_io_error(ret)) + goto free; + + /* 2nd. erase block */ + erase.len = mtd->erasesize; + erase.addr = off; + ret = mtd_erase(mtd, &erase); + if (ret) + goto free; + + /* 3rd. write back */ + while (size) { + unsigned int zonesize = cxt->info.kmsg_size; + + /* there is valid data on block, write back */ + if (mtdpstore_is_used(cxt, off)) { + ret = mtd_write(mtd, off, zonesize, &retlen, buf); + if (ret) + dev_err(&mtd->dev, "write failure at %lld (%zu of %u written), err %d\n", + off, retlen, zonesize, ret); + } + + off += zonesize; + size -= min_t(unsigned int, zonesize, size); + } + +free: + kfree(buf); + return ret; +} + +/* + * What does mtdpstore_flush_removed() do? + * When user remove any log file on pstore filesystem, mtdpstore should do + * something to ensure log file removed. If the whole block is no longer used, + * it's nice to erase the block. However if the block still contains valid log, + * what mtdpstore can do is to erase and write the valid log back. + */ +static int mtdpstore_flush_removed(struct mtdpstore_context *cxt) +{ + struct mtd_info *mtd = cxt->mtd; + int ret; + loff_t off; + u32 blkcnt = (u32)div_u64(mtd->size, mtd->erasesize); + + for (off = 0; blkcnt > 0; blkcnt--, off += mtd->erasesize) { + ret = mtdpstore_block_isbad(cxt, off); + if (ret) + continue; + + ret = mtdpstore_block_is_removed(cxt, off); + if (!ret) + continue; + + ret = mtdpstore_flush_removed_do(cxt, off, mtd->erasesize); + if (ret) + return ret; + } + return 0; +} + +static void mtdpstore_notify_remove(struct mtd_info *mtd) +{ + struct mtdpstore_context *cxt = &oops_cxt; + + if (mtd->index != cxt->index || cxt->index < 0) + return; + + mtdpstore_flush_removed(cxt); + + unregister_pstore_device(&cxt->dev); + kfree(cxt->badmap); + kfree(cxt->usedmap); + kfree(cxt->rmmap); + cxt->mtd = NULL; + cxt->index = -1; +} + +static struct mtd_notifier mtdpstore_notifier = { + .add = mtdpstore_notify_add, + .remove = mtdpstore_notify_remove, +}; + +static int __init mtdpstore_init(void) +{ + int ret; + struct mtdpstore_context *cxt = &oops_cxt; + struct pstore_blk_config *info = &cxt->info; + + ret = pstore_blk_get_config(info); + if (unlikely(ret)) + return ret; + + if (strlen(info->device) == 0) { + pr_err("mtd device must be supplied (device name is empty)\n"); + return -EINVAL; + } + if (!info->kmsg_size) { + pr_err("no backend enabled (kmsg_size is 0)\n"); + return -EINVAL; + } + + /* Setup the MTD device to use */ + ret = kstrtoint((char *)info->device, 0, &cxt->index); + if (ret) + cxt->index = -1; + + register_mtd_user(&mtdpstore_notifier); + return 0; +} +module_init(mtdpstore_init); + +static void __exit mtdpstore_exit(void) +{ + unregister_mtd_user(&mtdpstore_notifier); +} +module_exit(mtdpstore_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("WeiXiong Liao <liaoweixiong@allwinnertech.com>"); +MODULE_DESCRIPTION("MTD backend for pstore/blk"); diff --git a/drivers/platform/chrome/chromeos_pstore.c b/drivers/platform/chrome/chromeos_pstore.c index d13770785fb5..fa51153688b4 100644 --- a/drivers/platform/chrome/chromeos_pstore.c +++ b/drivers/platform/chrome/chromeos_pstore.c @@ -57,7 +57,7 @@ static struct ramoops_platform_data chromeos_ramoops_data = { .record_size = 0x40000, .console_size = 0x20000, .ftrace_size = 0x20000, - .dump_oops = 1, + .max_reason = KMSG_DUMP_OOPS, }; static struct platform_device chromeos_ramoops = { diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 8f0369aad22a..e16a49ebfe54 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -153,3 +153,112 @@ config PSTORE_RAM "ramoops.ko". For more information, see Documentation/admin-guide/ramoops.rst. + +config PSTORE_ZONE + tristate + depends on PSTORE + help + The common layer for pstore/blk (and pstore/ram in the future) + to manage storage in zones. + +config PSTORE_BLK + tristate "Log panic/oops to a block device" + depends on PSTORE + depends on BLOCK + select PSTORE_ZONE + default n + help + This enables panic and oops message to be logged to a block dev + where it can be read back at some later point. + + For more information, see Documentation/admin-guide/pstore-blk.rst + + If unsure, say N. + +config PSTORE_BLK_BLKDEV + string "block device identifier" + depends on PSTORE_BLK + default "" + help + Which block device should be used for pstore/blk. + + It accepts the following variants: + 1) <hex_major><hex_minor> device number in hexadecimal representation, + with no leading 0x, for example b302. + 2) /dev/<disk_name> represents the device name of disk + 3) /dev/<disk_name><decimal> represents the device name and number + of partition - device number of disk plus the partition number + 4) /dev/<disk_name>p<decimal> - same as the above, this form is + used when disk name of partitioned disk ends with a digit. + 5) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the + unique id of a partition if the partition table provides it. + The UUID may be either an EFI/GPT UUID, or refer to an MSDOS + partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero- + filled hex representation of the 32-bit "NT disk signature", and PP + is a zero-filled hex representation of the 1-based partition number. + 6) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation + to a partition with a known unique id. + 7) <major>:<minor> major and minor number of the device separated by + a colon. + + NOTE that, both Kconfig and module parameters can configure + pstore/blk, but module parameters have priority over Kconfig. + +config PSTORE_BLK_KMSG_SIZE + int "Size in Kbytes of kmsg dump log to store" + depends on PSTORE_BLK + default 64 + help + This just sets size of kmsg dump (oops, panic, etc) log for + pstore/blk. The size is in KB and must be a multiple of 4. + + NOTE that, both Kconfig and module parameters can configure + pstore/blk, but module parameters have priority over Kconfig. + +config PSTORE_BLK_MAX_REASON + int "Maximum kmsg dump reason to store" + depends on PSTORE_BLK + default 2 + help + The maximum reason for kmsg dumps to store. The default is + 2 (KMSG_DUMP_OOPS), see include/linux/kmsg_dump.h's + enum kmsg_dump_reason for more details. + + NOTE that, both Kconfig and module parameters can configure + pstore/blk, but module parameters have priority over Kconfig. + +config PSTORE_BLK_PMSG_SIZE + int "Size in Kbytes of pmsg to store" + depends on PSTORE_BLK + depends on PSTORE_PMSG + default 64 + help + This just sets size of pmsg (pmsg_size) for pstore/blk. The size is + in KB and must be a multiple of 4. + + NOTE that, both Kconfig and module parameters can configure + pstore/blk, but module parameters have priority over Kconfig. + +config PSTORE_BLK_CONSOLE_SIZE + int "Size in Kbytes of console log to store" + depends on PSTORE_BLK + depends on PSTORE_CONSOLE + default 64 + help + This just sets size of console log (console_size) to store via + pstore/blk. The size is in KB and must be a multiple of 4. + + NOTE that, both Kconfig and module parameters can configure + pstore/blk, but module parameters have priority over Kconfig. + +config PSTORE_BLK_FTRACE_SIZE + int "Size in Kbytes of ftrace log to store" + depends on PSTORE_BLK + depends on PSTORE_FTRACE + default 64 + help + This just sets size of ftrace log (ftrace_size) for pstore/blk. The + size is in KB and must be a multiple of 4. + + NOTE that, both Kconfig and module parameters can configure + pstore/blk, but module parameters have priority over Kconfig. diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile index 967b5891f325..c270467aeece 100644 --- a/fs/pstore/Makefile +++ b/fs/pstore/Makefile @@ -12,3 +12,9 @@ pstore-$(CONFIG_PSTORE_PMSG) += pmsg.o ramoops-objs += ram.o ram_core.o obj-$(CONFIG_PSTORE_RAM) += ramoops.o + +pstore_zone-objs += zone.o +obj-$(CONFIG_PSTORE_ZONE) += pstore_zone.o + +pstore_blk-objs += blk.o +obj-$(CONFIG_PSTORE_BLK) += pstore_blk.o diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c new file mode 100644 index 000000000000..fcd5563dde06 --- /dev/null +++ b/fs/pstore/blk.c @@ -0,0 +1,517 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Implements pstore backend driver that write to block (or non-block) storage + * devices, using the pstore/zone API. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include "../../block/blk.h" +#include <linux/blkdev.h> +#include <linux/string.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include <linux/pstore_blk.h> +#include <linux/mount.h> +#include <linux/uio.h> + +static long kmsg_size = CONFIG_PSTORE_BLK_KMSG_SIZE; +module_param(kmsg_size, long, 0400); +MODULE_PARM_DESC(kmsg_size, "kmsg dump record size in kbytes"); + +static int max_reason = CONFIG_PSTORE_BLK_MAX_REASON; +module_param(max_reason, int, 0400); +MODULE_PARM_DESC(max_reason, + "maximum reason for kmsg dump (default 2: Oops and Panic)"); + +#if IS_ENABLED(CONFIG_PSTORE_PMSG) +static long pmsg_size = CONFIG_PSTORE_BLK_PMSG_SIZE; +#else +static long pmsg_size = -1; +#endif +module_param(pmsg_size, long, 0400); +MODULE_PARM_DESC(pmsg_size, "pmsg size in kbytes"); + +#if IS_ENABLED(CONFIG_PSTORE_CONSOLE) +static long console_size = CONFIG_PSTORE_BLK_CONSOLE_SIZE; +#else +static long console_size = -1; +#endif +module_param(console_size, long, 0400); +MODULE_PARM_DESC(console_size, "console size in kbytes"); + +#if IS_ENABLED(CONFIG_PSTORE_FTRACE) +static long ftrace_size = CONFIG_PSTORE_BLK_FTRACE_SIZE; +#else +static long ftrace_size = -1; +#endif +module_param(ftrace_size, long, 0400); +MODULE_PARM_DESC(ftrace_size, "ftrace size in kbytes"); + +static bool best_effort; +module_param(best_effort, bool, 0400); +MODULE_PARM_DESC(best_effort, "use best effort to write (i.e. do not require storage driver pstore support, default: off)"); + +/* + * blkdev - the block device to use for pstore storage + * + * Usually, this will be a partition of a block device. + * + * blkdev accepts the following variants: + * 1) <hex_major><hex_minor> device number in hexadecimal representation, + * with no leading 0x, for example b302. + * 2) /dev/<disk_name> represents the device number of disk + * 3) /dev/<disk_name><decimal> represents the device number + * of partition - device number of disk plus the partition number + * 4) /dev/<disk_name>p<decimal> - same as the above, that form is + * used when disk name of partitioned disk ends on a digit. + * 5) PARTUUID=00112233-4455-6677-8899-AABBCCDDEEFF representing the + * unique id of a partition if the partition table provides it. + * The UUID may be either an EFI/GPT UUID, or refer to an MSDOS + * partition using the format SSSSSSSS-PP, where SSSSSSSS is a zero- + * filled hex representation of the 32-bit "NT disk signature", and PP + * is a zero-filled hex representation of the 1-based partition number. + * 6) PARTUUID=<UUID>/PARTNROFF=<int> to select a partition in relation to + * a partition with a known unique id. + * 7) <major>:<minor> major and minor number of the device separated by + * a colon. + */ +static char blkdev[80] = CONFIG_PSTORE_BLK_BLKDEV; +module_param_string(blkdev, blkdev, 80, 0400); +MODULE_PARM_DESC(blkdev, "block device for pstore storage"); + +/* + * All globals must only be accessed under the pstore_blk_lock + * during the register/unregister functions. + */ +static DEFINE_MUTEX(pstore_blk_lock); +static struct block_device *psblk_bdev; +static struct pstore_zone_info *pstore_zone_info; +static pstore_blk_panic_write_op blkdev_panic_write; + +struct bdev_info { + dev_t devt; + sector_t nr_sects; + sector_t start_sect; +}; + +#define check_size(name, alignsize) ({ \ + long _##name_ = (name); \ + _##name_ = _##name_ <= 0 ? 0 : (_##name_ * 1024); \ + if (_##name_ & ((alignsize) - 1)) { \ + pr_info(#name " must align to %d\n", \ + (alignsize)); \ + _##name_ = ALIGN(name, (alignsize)); \ + } \ + _##name_; \ +}) + +static int __register_pstore_device(struct pstore_device_info *dev) +{ + int ret; + + lockdep_assert_held(&pstore_blk_lock); + + if (!dev || !dev->total_size || !dev->read || !dev->write) + return -EINVAL; + + /* someone already registered before */ + if (pstore_zone_info) + return -EBUSY; + + pstore_zone_info = kzalloc(sizeof(struct pstore_zone_info), GFP_KERNEL); + if (!pstore_zone_info) + return -ENOMEM; + + /* zero means not limit on which backends to attempt to store. */ + if (!dev->flags) + dev->flags = UINT_MAX; + +#define verify_size(name, alignsize, enabled) { \ + long _##name_; \ + if (enabled) \ + _##name_ = check_size(name, alignsize); \ + else \ + _##name_ = 0; \ + name = _##name_ / 1024; \ + pstore_zone_info->name = _##name_; \ + } + + verify_size(kmsg_size, 4096, dev->flags & PSTORE_FLAGS_DMESG); + verify_size(pmsg_size, 4096, dev->flags & PSTORE_FLAGS_PMSG); + verify_size(console_size, 4096, dev->flags & PSTORE_FLAGS_CONSOLE); + verify_size(ftrace_size, 4096, dev->flags & PSTORE_FLAGS_FTRACE); +#undef verify_size + + pstore_zone_info->total_size = dev->total_size; + pstore_zone_info->max_reason = max_reason; + pstore_zone_info->read = dev->read; + pstore_zone_info->write = dev->write; + pstore_zone_info->erase = dev->erase; + pstore_zone_info->panic_write = dev->panic_write; + pstore_zone_info->name = KBUILD_MODNAME; + pstore_zone_info->owner = THIS_MODULE; + + ret = register_pstore_zone(pstore_zone_info); + if (ret) { + kfree(pstore_zone_info); + pstore_zone_info = NULL; + } + return ret; +} +/** + * register_pstore_device() - register non-block device to pstore/blk + * + * @dev: non-block device information + * + * Return: + * * 0 - OK + * * Others - something error. + */ +int register_pstore_device(struct pstore_device_info *dev) +{ + int ret; + + mutex_lock(&pstore_blk_lock); + ret = __register_pstore_device(dev); + mutex_unlock(&pstore_blk_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(register_pstore_device); + +static void __unregister_pstore_device(struct pstore_device_info *dev) +{ + lockdep_assert_held(&pstore_blk_lock); + if (pstore_zone_info && pstore_zone_info->read == dev->read) { + unregister_pstore_zone(pstore_zone_info); + kfree(pstore_zone_info); + pstore_zone_info = NULL; + } +} + +/** + * unregister_pstore_device() - unregister non-block device from pstore/blk + * + * @dev: non-block device information + */ +void unregister_pstore_device(struct pstore_device_info *dev) +{ + mutex_lock(&pstore_blk_lock); + __unregister_pstore_device(dev); + mutex_unlock(&pstore_blk_lock); +} +EXPORT_SYMBOL_GPL(unregister_pstore_device); + +/** + * psblk_get_bdev() - open block device + * + * @holder: Exclusive holder identifier + * @info: Information about bdev to fill in + * + * Return: pointer to block device on success and others on error. + * + * On success, the returned block_device has reference count of one. + */ +static struct block_device *psblk_get_bdev(void *holder, + struct bdev_info *info) +{ + struct block_device *bdev = ERR_PTR(-ENODEV); + fmode_t mode = FMODE_READ | FMODE_WRITE; + sector_t nr_sects; + + lockdep_assert_held(&pstore_blk_lock); + + if (pstore_zone_info) + return ERR_PTR(-EBUSY); + + if (!blkdev[0]) + return ERR_PTR(-ENODEV); + + if (holder) + mode |= FMODE_EXCL; + bdev = blkdev_get_by_path(blkdev, mode, holder); + if (IS_ERR(bdev)) { + dev_t devt; + + devt = name_to_dev_t(blkdev); + if (devt == 0) + return ERR_PTR(-ENODEV); + bdev = blkdev_get_by_dev(devt, mode, holder); + if (IS_ERR(bdev)) + return bdev; + } + + nr_sects = part_nr_sects_read(bdev->bd_part); + if (!nr_sects) { + pr_err("not enough space for '%s'\n", blkdev); + blkdev_put(bdev, mode); + return ERR_PTR(-ENOSPC); + } + + if (info) { + info->devt = bdev->bd_dev; + info->nr_sects = nr_sects; + info->start_sect = get_start_sect(bdev); + } + + return bdev; +} + +static void psblk_put_bdev(struct block_device *bdev, void *holder) +{ + fmode_t mode = FMODE_READ | FMODE_WRITE; + + lockdep_assert_held(&pstore_blk_lock); + + if (!bdev) + return; + + if (holder) + mode |= FMODE_EXCL; + blkdev_put(bdev, mode); +} + +static ssize_t psblk_generic_blk_read(char *buf, size_t bytes, loff_t pos) +{ + struct block_device *bdev = psblk_bdev; + struct file file; + struct kiocb kiocb; + struct iov_iter iter; + struct kvec iov = {.iov_base = buf, .iov_len = bytes}; + + if (!bdev) + return -ENODEV; + + memset(&file, 0, sizeof(struct file)); + file.f_mapping = bdev->bd_inode->i_mapping; + file.f_flags = O_DSYNC | __O_SYNC | O_NOATIME; + file.f_inode = bdev->bd_inode; + file_ra_state_init(&file.f_ra, file.f_mapping); + + init_sync_kiocb(&kiocb, &file); + kiocb.ki_pos = pos; + iov_iter_kvec(&iter, READ, &iov, 1, bytes); + + return generic_file_read_iter(&kiocb, &iter); +} + +static ssize_t psblk_generic_blk_write(const char *buf, size_t bytes, + loff_t pos) +{ + struct block_device *bdev = psblk_bdev; + struct iov_iter iter; + struct kiocb kiocb; + struct file file; + ssize_t ret; + struct kvec iov = {.iov_base = (void *)buf, .iov_len = bytes}; + + if (!bdev) + return -ENODEV; + + /* Console/Ftrace backend may handle buffer until flush dirty zones */ + if (in_interrupt() || irqs_disabled()) + return -EBUSY; + + memset(&file, 0, sizeof(struct file)); + file.f_mapping = bdev->bd_inode->i_mapping; + file.f_flags = O_DSYNC | __O_SYNC | O_NOATIME; + file.f_inode = bdev->bd_inode; + + init_sync_kiocb(&kiocb, &file); + kiocb.ki_pos = pos; + iov_iter_kvec(&iter, WRITE, &iov, 1, bytes); + + inode_lock(bdev->bd_inode); + ret = generic_write_checks(&kiocb, &iter); + if (ret > 0) + ret = generic_perform_write(&file, &iter, pos); + inode_unlock(bdev->bd_inode); + + if (likely(ret > 0)) { + const struct file_operations f_op = {.fsync = blkdev_fsync}; + + file.f_op = &f_op; + kiocb.ki_pos += ret; + ret = generic_write_sync(&kiocb, ret); + } + return ret; +} + +static ssize_t psblk_blk_panic_write(const char *buf, size_t size, + loff_t off) +{ + int ret; + + if (!blkdev_panic_write) + return -EOPNOTSUPP; + + /* size and off must align to SECTOR_SIZE for block device */ + ret = blkdev_panic_write(buf, off >> SECTOR_SHIFT, + size >> SECTOR_SHIFT); + /* try next zone */ + if (ret == -ENOMSG) + return ret; + return ret ? -EIO : size; +} + +static int __register_pstore_blk(struct pstore_blk_info *info) +{ + char bdev_name[BDEVNAME_SIZE]; + struct block_device *bdev; + struct pstore_device_info dev; + struct bdev_info binfo; + void *holder = blkdev; + int ret = -ENODEV; + + lockdep_assert_held(&pstore_blk_lock); + + /* hold bdev exclusively */ + memset(&binfo, 0, sizeof(binfo)); + bdev = psblk_get_bdev(holder, &binfo); + if (IS_ERR(bdev)) { + pr_err("failed to open '%s'!\n", blkdev); + return PTR_ERR(bdev); + } + + /* only allow driver matching the @blkdev */ + if (!binfo.devt || (!best_effort && + MAJOR(binfo.devt) != info->major)) { + pr_debug("invalid major %u (expect %u)\n", + info->major, MAJOR(binfo.devt)); + ret = -ENODEV; + goto err_put_bdev; + } + + /* psblk_bdev must be assigned before register to pstore/blk */ + psblk_bdev = bdev; + blkdev_panic_write = info->panic_write; + + /* Copy back block device details. */ + info->devt = binfo.devt; + info->nr_sects = binfo.nr_sects; + info->start_sect = binfo.start_sect; + + memset(&dev, 0, sizeof(dev)); + dev.total_size = info->nr_sects << SECTOR_SHIFT; + dev.flags = info->flags; + dev.read = psblk_generic_blk_read; + dev.write = psblk_generic_blk_write; + dev.erase = NULL; + dev.panic_write = info->panic_write ? psblk_blk_panic_write : NULL; + + ret = __register_pstore_device(&dev); + if (ret) + goto err_put_bdev; + + bdevname(bdev, bdev_name); + pr_info("attached %s%s\n", bdev_name, + info->panic_write ? "" : " (no dedicated panic_write!)"); + return 0; + +err_put_bdev: + psblk_bdev = NULL; + blkdev_panic_write = NULL; + psblk_put_bdev(bdev, holder); + return ret; +} + +/** + * register_pstore_blk() - register block device to pstore/blk + * + * @info: details on the desired block device interface + * + * Return: + * * 0 - OK + * * Others - something error. + */ +int register_pstore_blk(struct pstore_blk_info *info) +{ + int ret; + + mutex_lock(&pstore_blk_lock); + ret = __register_pstore_blk(info); + mutex_unlock(&pstore_blk_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(register_pstore_blk); + +static void __unregister_pstore_blk(unsigned int major) +{ + struct pstore_device_info dev = { .read = psblk_generic_blk_read }; + void *holder = blkdev; + + lockdep_assert_held(&pstore_blk_lock); + if (psblk_bdev && MAJOR(psblk_bdev->bd_dev) == major) { + __unregister_pstore_device(&dev); + psblk_put_bdev(psblk_bdev, holder); + blkdev_panic_write = NULL; + psblk_bdev = NULL; + } +} + +/** + * unregister_pstore_blk() - unregister block device from pstore/blk + * + * @major: the major device number of device + */ +void unregister_pstore_blk(unsigned int major) +{ + mutex_lock(&pstore_blk_lock); + __unregister_pstore_blk(major); + mutex_unlock(&pstore_blk_lock); +} +EXPORT_SYMBOL_GPL(unregister_pstore_blk); + +/* get information of pstore/blk */ +int pstore_blk_get_config(struct pstore_blk_config *info) +{ + strncpy(info->device, blkdev, 80); + info->max_reason = max_reason; + info->kmsg_size = check_size(kmsg_size, 4096); + info->pmsg_size = check_size(pmsg_size, 4096); + info->ftrace_size = check_size(ftrace_size, 4096); + info->console_size = check_size(console_size, 4096); + + return 0; +} +EXPORT_SYMBOL_GPL(pstore_blk_get_config); + +static int __init pstore_blk_init(void) +{ + struct pstore_blk_info info = { }; + int ret = 0; + + mutex_lock(&pstore_blk_lock); + if (!pstore_zone_info && best_effort && blkdev[0]) + ret = __register_pstore_blk(&info); + mutex_unlock(&pstore_blk_lock); + + return ret; +} +late_initcall(pstore_blk_init); + +static void __exit pstore_blk_exit(void) +{ + mutex_lock(&pstore_blk_lock); + if (psblk_bdev) + __unregister_pstore_blk(MAJOR(psblk_bdev->bd_dev)); + else { + struct pstore_device_info dev = { }; + + if (pstore_zone_info) + dev.read = pstore_zone_info->read; + __unregister_pstore_device(&dev); + } + mutex_unlock(&pstore_blk_lock); +} +module_exit(pstore_blk_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("WeiXiong Liao <liaoweixiong@allwinnertech.com>"); +MODULE_AUTHOR("Kees Cook <keescook@chromium.org>"); +MODULE_DESCRIPTION("pstore backend for block devices"); diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c index bfbfc2698070..5c0450701293 100644 --- a/fs/pstore/ftrace.c +++ b/fs/pstore/ftrace.c @@ -16,6 +16,7 @@ #include <linux/debugfs.h> #include <linux/err.h> #include <linux/cache.h> +#include <linux/slab.h> #include <asm/barrier.h> #include "internal.h" @@ -132,3 +133,56 @@ void pstore_unregister_ftrace(void) debugfs_remove_recursive(pstore_ftrace_dir); } + +ssize_t pstore_ftrace_combine_log(char **dest_log, size_t *dest_log_size, + const char *src_log, size_t src_log_size) +{ + size_t dest_size, src_size, total, dest_off, src_off; + size_t dest_idx = 0, src_idx = 0, merged_idx = 0; + void *merged_buf; + struct pstore_ftrace_record *drec, *srec, *mrec; + size_t record_size = sizeof(struct pstore_ftrace_record); + + dest_off = *dest_log_size % record_size; + dest_size = *dest_log_size - dest_off; + + src_off = src_log_size % record_size; + src_size = src_log_size - src_off; + + total = dest_size + src_size; + merged_buf = kmalloc(total, GFP_KERNEL); + if (!merged_buf) + return -ENOMEM; + + drec = (struct pstore_ftrace_record *)(*dest_log + dest_off); + srec = (struct pstore_ftrace_record *)(src_log + src_off); + mrec = (struct pstore_ftrace_record *)(merged_buf); + + while (dest_size > 0 && src_size > 0) { + if (pstore_ftrace_read_timestamp(&drec[dest_idx]) < + pstore_ftrace_read_timestamp(&srec[src_idx])) { + mrec[merged_idx++] = drec[dest_idx++]; + dest_size -= record_size; + } else { + mrec[merged_idx++] = srec[src_idx++]; + src_size -= record_size; + } + } + + while (dest_size > 0) { + mrec[merged_idx++] = drec[dest_idx++]; + dest_size -= record_size; + } + + while (src_size > 0) { + mrec[merged_idx++] = srec[src_idx++]; + src_size -= record_size; + } + + kfree(*dest_log); + *dest_log = merged_buf; + *dest_log_size = total; + + return 0; +} +EXPORT_SYMBOL_GPL(pstore_ftrace_combine_log); diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index d99b5d39aa90..c331efe8de95 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -22,18 +22,21 @@ #include <linux/magic.h> #include <linux/pstore.h> #include <linux/slab.h> -#include <linux/spinlock.h> #include <linux/uaccess.h> #include "internal.h" #define PSTORE_NAMELEN 64 -static DEFINE_SPINLOCK(allpstore_lock); -static LIST_HEAD(allpstore); +static DEFINE_MUTEX(records_list_lock); +static LIST_HEAD(records_list); + +static DEFINE_MUTEX(pstore_sb_lock); +static struct super_block *pstore_sb; struct pstore_private { struct list_head list; + struct dentry *dentry; struct pstore_record *record; size_t total_size; }; @@ -178,10 +181,22 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = d_inode(dentry)->i_private; struct pstore_record *record = p->record; + int rc = 0; if (!record->psi->erase) return -EPERM; + /* Make sure we can't race while removing this file. */ + mutex_lock(&records_list_lock); + if (!list_empty(&p->list)) + list_del_init(&p->list); + else + rc = -ENOENT; + p->dentry = NULL; + mutex_unlock(&records_list_lock); + if (rc) + return rc; + mutex_lock(&record->psi->read_mutex); record->psi->erase(record); mutex_unlock(&record->psi->read_mutex); @@ -192,15 +207,9 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) static void pstore_evict_inode(struct inode *inode) { struct pstore_private *p = inode->i_private; - unsigned long flags; clear_inode(inode); - if (p) { - spin_lock_irqsave(&allpstore_lock, flags); - list_del(&p->list); - spin_unlock_irqrestore(&allpstore_lock, flags); - free_pstore_private(p); - } + free_pstore_private(p); } static const struct inode_operations pstore_dir_inode_operations = { @@ -278,11 +287,54 @@ static const struct super_operations pstore_ops = { .show_options = pstore_show_options, }; -static struct super_block *pstore_sb; +static struct dentry *psinfo_lock_root(void) +{ + struct dentry *root; -bool pstore_is_mounted(void) + mutex_lock(&pstore_sb_lock); + /* + * Having no backend is fine -- no records appear. + * Not being mounted is fine -- nothing to do. + */ + if (!psinfo || !pstore_sb) { + mutex_unlock(&pstore_sb_lock); + return NULL; + } + + root = pstore_sb->s_root; + inode_lock(d_inode(root)); + mutex_unlock(&pstore_sb_lock); + + return root; +} + +int pstore_put_backend_records(struct pstore_info *psi) { - return pstore_sb != NULL; + struct pstore_private *pos, *tmp; + struct dentry *root; + int rc = 0; + + root = psinfo_lock_root(); + if (!root) + return 0; + + mutex_lock(&records_list_lock); + list_for_each_entry_safe(pos, tmp, &records_list, list) { + if (pos->record->psi == psi) { + list_del_init(&pos->list); + rc = simple_unlink(d_inode(root), pos->dentry); + if (WARN_ON(rc)) + break; + d_drop(pos->dentry); + dput(pos->dentry); + pos->dentry = NULL; + } + } + mutex_unlock(&records_list_lock); + + inode_unlock(d_inode(root)); + + return rc; } /* @@ -297,23 +349,20 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) int rc = 0; char name[PSTORE_NAMELEN]; struct pstore_private *private, *pos; - unsigned long flags; size_t size = record->size + record->ecc_notice_size; - WARN_ON(!inode_is_locked(d_inode(root))); + if (WARN_ON(!inode_is_locked(d_inode(root)))) + return -EINVAL; - spin_lock_irqsave(&allpstore_lock, flags); - list_for_each_entry(pos, &allpstore, list) { + rc = -EEXIST; + /* Skip records that are already present in the filesystem. */ + mutex_lock(&records_list_lock); + list_for_each_entry(pos, &records_list, list) { if (pos->record->type == record->type && pos->record->id == record->id && - pos->record->psi == record->psi) { - rc = -EEXIST; - break; - } + pos->record->psi == record->psi) + goto fail; } - spin_unlock_irqrestore(&allpstore_lock, flags); - if (rc) - return rc; rc = -ENOMEM; inode = pstore_get_inode(root->d_sb); @@ -334,6 +383,7 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) if (!dentry) goto fail_private; + private->dentry = dentry; private->record = record; inode->i_size = private->total_size = size; inode->i_private = private; @@ -343,9 +393,8 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) d_add(dentry, inode); - spin_lock_irqsave(&allpstore_lock, flags); - list_add(&private->list, &allpstore); - spin_unlock_irqrestore(&allpstore_lock, flags); + list_add(&private->list, &records_list); + mutex_unlock(&records_list_lock); return 0; @@ -353,8 +402,8 @@ fail_private: free_pstore_private(private); fail_inode: iput(inode); - fail: + mutex_unlock(&records_list_lock); return rc; } @@ -366,16 +415,13 @@ fail: */ void pstore_get_records(int quiet) { - struct pstore_info *psi = psinfo; struct dentry *root; - if (!psi || !pstore_sb) + root = psinfo_lock_root(); + if (!root) return; - root = pstore_sb->s_root; - - inode_lock(d_inode(root)); - pstore_get_backend_records(psi, root, quiet); + pstore_get_backend_records(psinfo, root, quiet); inode_unlock(d_inode(root)); } @@ -383,8 +429,6 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - pstore_sb = sb; - sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; @@ -405,6 +449,10 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) if (!sb->s_root) return -ENOMEM; + mutex_lock(&pstore_sb_lock); + pstore_sb = sb; + mutex_unlock(&pstore_sb_lock); + pstore_get_records(0); return 0; @@ -418,8 +466,17 @@ static struct dentry *pstore_mount(struct file_system_type *fs_type, static void pstore_kill_sb(struct super_block *sb) { + mutex_lock(&pstore_sb_lock); + WARN_ON(pstore_sb != sb); + kill_litter_super(sb); pstore_sb = NULL; + + mutex_lock(&records_list_lock); + INIT_LIST_HEAD(&records_list); + mutex_unlock(&records_list_lock); + + mutex_unlock(&pstore_sb_lock); } static struct file_system_type pstore_fs_type = { diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 7062ea4bc57c..7fb219042f13 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -12,9 +12,18 @@ extern unsigned long kmsg_bytes; #ifdef CONFIG_PSTORE_FTRACE extern void pstore_register_ftrace(void); extern void pstore_unregister_ftrace(void); +ssize_t pstore_ftrace_combine_log(char **dest_log, size_t *dest_log_size, + const char *src_log, size_t src_log_size); #else static inline void pstore_register_ftrace(void) {} static inline void pstore_unregister_ftrace(void) {} +static inline ssize_t +pstore_ftrace_combine_log(char **dest_log, size_t *dest_log_size, + const char *src_log, size_t src_log_size) +{ + *dest_log_size = 0; + return 0; +} #endif #ifdef CONFIG_PSTORE_PMSG @@ -31,9 +40,9 @@ extern void pstore_set_kmsg_bytes(int); extern void pstore_get_records(int); extern void pstore_get_backend_records(struct pstore_info *psi, struct dentry *root, int quiet); +extern int pstore_put_backend_records(struct pstore_info *psi); extern int pstore_mkfile(struct dentry *root, struct pstore_record *record); -extern bool pstore_is_mounted(void); extern void pstore_record_init(struct pstore_record *record, struct pstore_info *psi); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 408277ee3cdb..a9e297eefdff 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -44,7 +44,7 @@ static int pstore_update_ms = -1; module_param_named(update_ms, pstore_update_ms, int, 0600); MODULE_PARM_DESC(update_ms, "milliseconds before pstore updates its content " "(default is -1, which means runtime updates are disabled; " - "enabling this option is not safe, it may lead to further " + "enabling this option may not be safe; it may lead to further " "corruption on Oopses)"); /* Names should be in the same order as the enum pstore_type_id */ @@ -69,19 +69,25 @@ static void pstore_dowork(struct work_struct *); static DECLARE_WORK(pstore_work, pstore_dowork); /* - * pstore_lock just protects "psinfo" during - * calls to pstore_register() + * psinfo_lock protects "psinfo" during calls to + * pstore_register(), pstore_unregister(), and + * the filesystem mount/unmount routines. */ -static DEFINE_SPINLOCK(pstore_lock); +static DEFINE_MUTEX(psinfo_lock); struct pstore_info *psinfo; static char *backend; +module_param(backend, charp, 0444); +MODULE_PARM_DESC(backend, "specific backend to use"); + static char *compress = #ifdef CONFIG_PSTORE_COMPRESS_DEFAULT CONFIG_PSTORE_COMPRESS_DEFAULT; #else NULL; #endif +module_param(compress, charp, 0444); +MODULE_PARM_DESC(compress, "compression to use"); /* Compression parameters */ static struct crypto_comp *tfm; @@ -129,24 +135,12 @@ enum pstore_type_id pstore_name_to_type(const char *name) } EXPORT_SYMBOL_GPL(pstore_name_to_type); -static const char *get_reason_str(enum kmsg_dump_reason reason) +static void pstore_timer_kick(void) { - switch (reason) { - case KMSG_DUMP_PANIC: - return "Panic"; - case KMSG_DUMP_OOPS: - return "Oops"; - case KMSG_DUMP_EMERG: - return "Emergency"; - case KMSG_DUMP_RESTART: - return "Restart"; - case KMSG_DUMP_HALT: - return "Halt"; - case KMSG_DUMP_POWEROFF: - return "Poweroff"; - default: - return "Unknown"; - } + if (pstore_update_ms < 0) + return; + + mod_timer(&pstore_timer, jiffies + msecs_to_jiffies(pstore_update_ms)); } /* @@ -393,7 +387,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, unsigned int part = 1; int ret; - why = get_reason_str(reason); + why = kmsg_dump_reason_str(reason); if (down_trylock(&psinfo->buf_lock)) { /* Failed to acquire lock: give up if we cannot wait. */ @@ -459,8 +453,10 @@ static void pstore_dump(struct kmsg_dumper *dumper, } ret = psinfo->write(&record); - if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) + if (ret == 0 && reason == KMSG_DUMP_OOPS) { pstore_new_entry = 1; + pstore_timer_kick(); + } total += record.size; part++; @@ -503,14 +499,20 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) } static struct console pstore_console = { - .name = "pstore", .write = pstore_console_write, - .flags = CON_PRINTBUFFER | CON_ENABLED | CON_ANYTIME, .index = -1, }; static void pstore_register_console(void) { + /* Show which backend is going to get console writes. */ + strscpy(pstore_console.name, psinfo->name, + sizeof(pstore_console.name)); + /* + * Always initialize flags here since prior unregister_console() + * calls may have changed settings (specifically CON_ENABLED). + */ + pstore_console.flags = CON_PRINTBUFFER | CON_ENABLED | CON_ANYTIME; register_console(&pstore_console); } @@ -555,8 +557,6 @@ out: */ int pstore_register(struct pstore_info *psi) { - struct module *owner = psi->owner; - if (backend && strcmp(backend, psi->name)) { pr_warn("ignoring unexpected backend '%s'\n", psi->name); return -EPERM; @@ -576,11 +576,11 @@ int pstore_register(struct pstore_info *psi) return -EINVAL; } - spin_lock(&pstore_lock); + mutex_lock(&psinfo_lock); if (psinfo) { pr_warn("backend '%s' already loaded: ignoring '%s'\n", psinfo->name, psi->name); - spin_unlock(&pstore_lock); + mutex_unlock(&psinfo_lock); return -EBUSY; } @@ -589,21 +589,16 @@ int pstore_register(struct pstore_info *psi) psinfo = psi; mutex_init(&psinfo->read_mutex); sema_init(&psinfo->buf_lock, 1); - spin_unlock(&pstore_lock); - - if (owner && !try_module_get(owner)) { - psinfo = NULL; - return -EINVAL; - } if (psi->flags & PSTORE_FLAGS_DMESG) allocate_buf_for_compression(); - if (pstore_is_mounted()) - pstore_get_records(0); + pstore_get_records(0); - if (psi->flags & PSTORE_FLAGS_DMESG) + if (psi->flags & PSTORE_FLAGS_DMESG) { + pstore_dumper.max_reason = psinfo->max_reason; pstore_register_kmsg(); + } if (psi->flags & PSTORE_FLAGS_CONSOLE) pstore_register_console(); if (psi->flags & PSTORE_FLAGS_FTRACE) @@ -612,33 +607,36 @@ int pstore_register(struct pstore_info *psi) pstore_register_pmsg(); /* Start watching for new records, if desired. */ - if (pstore_update_ms >= 0) { - pstore_timer.expires = jiffies + - msecs_to_jiffies(pstore_update_ms); - add_timer(&pstore_timer); - } + pstore_timer_kick(); /* * Update the module parameter backend, so it is visible * through /sys/module/pstore/parameters/backend */ - backend = psi->name; + backend = kstrdup(psi->name, GFP_KERNEL); pr_info("Registered %s as persistent store backend\n", psi->name); - module_put(owner); - + mutex_unlock(&psinfo_lock); return 0; } EXPORT_SYMBOL_GPL(pstore_register); void pstore_unregister(struct pstore_info *psi) { - /* Stop timer and make sure all work has finished. */ - pstore_update_ms = -1; - del_timer_sync(&pstore_timer); - flush_work(&pstore_work); + /* It's okay to unregister nothing. */ + if (!psi) + return; + + mutex_lock(&psinfo_lock); + + /* Only one backend can be registered at a time. */ + if (WARN_ON(psi != psinfo)) { + mutex_unlock(&psinfo_lock); + return; + } + /* Unregister all callbacks. */ if (psi->flags & PSTORE_FLAGS_PMSG) pstore_unregister_pmsg(); if (psi->flags & PSTORE_FLAGS_FTRACE) @@ -648,10 +646,19 @@ void pstore_unregister(struct pstore_info *psi) if (psi->flags & PSTORE_FLAGS_DMESG) pstore_unregister_kmsg(); + /* Stop timer and make sure all work has finished. */ + del_timer_sync(&pstore_timer); + flush_work(&pstore_work); + + /* Remove all backend records from filesystem tree. */ + pstore_put_backend_records(psi); + free_buf_for_compression(); psinfo = NULL; + kfree(backend); backend = NULL; + mutex_unlock(&psinfo_lock); } EXPORT_SYMBOL_GPL(pstore_unregister); @@ -788,9 +795,7 @@ static void pstore_timefunc(struct timer_list *unused) schedule_work(&pstore_work); } - if (pstore_update_ms >= 0) - mod_timer(&pstore_timer, - jiffies + msecs_to_jiffies(pstore_update_ms)); + pstore_timer_kick(); } static void __init pstore_choose_compression(void) @@ -835,11 +840,5 @@ static void __exit pstore_exit(void) } module_exit(pstore_exit) -module_param(compress, charp, 0444); -MODULE_PARM_DESC(compress, "Pstore compression to use"); - -module_param(backend, charp, 0444); -MODULE_PARM_DESC(backend, "Pstore backend to use"); - MODULE_AUTHOR("Tony Luck <tony.luck@intel.com>"); MODULE_LICENSE("GPL"); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 795622190c01..ca6d8a867285 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -21,6 +21,7 @@ #include <linux/pstore_ram.h> #include <linux/of.h> #include <linux/of_address.h> +#include "internal.h" #define RAMOOPS_KERNMSG_HDR "====" #define MIN_MEM_SIZE 4096UL @@ -53,22 +54,27 @@ MODULE_PARM_DESC(mem_size, "size of reserved RAM used to store oops/panic logs"); static unsigned int mem_type; -module_param(mem_type, uint, 0600); +module_param(mem_type, uint, 0400); MODULE_PARM_DESC(mem_type, "set to 1 to try to use unbuffered memory (default 0)"); -static int dump_oops = 1; -module_param(dump_oops, int, 0600); -MODULE_PARM_DESC(dump_oops, - "set to 1 to dump oopses, 0 to only dump panics (default 1)"); +static int ramoops_max_reason = -1; +module_param_named(max_reason, ramoops_max_reason, int, 0400); +MODULE_PARM_DESC(max_reason, + "maximum reason for kmsg dump (default 2: Oops and Panic) "); static int ramoops_ecc; -module_param_named(ecc, ramoops_ecc, int, 0600); +module_param_named(ecc, ramoops_ecc, int, 0400); MODULE_PARM_DESC(ramoops_ecc, "if non-zero, the option enables ECC support and specifies " "ECC buffer size in bytes (1 is a special value, means 16 " "bytes ECC)"); +static int ramoops_dump_oops = -1; +module_param_named(dump_oops, ramoops_dump_oops, int, 0400); +MODULE_PARM_DESC(dump_oops, + "(deprecated: use max_reason instead) set to 1 to dump oopses & panics, 0 to only dump panics"); + struct ramoops_context { struct persistent_ram_zone **dprzs; /* Oops dump zones */ struct persistent_ram_zone *cprz; /* Console zone */ @@ -81,7 +87,6 @@ struct ramoops_context { size_t console_size; size_t ftrace_size; size_t pmsg_size; - int dump_oops; u32 flags; struct persistent_ram_ecc_info ecc_info; unsigned int max_dump_cnt; @@ -168,58 +173,6 @@ static bool prz_ok(struct persistent_ram_zone *prz) persistent_ram_ecc_string(prz, NULL, 0)); } -static ssize_t ftrace_log_combine(struct persistent_ram_zone *dest, - struct persistent_ram_zone *src) -{ - size_t dest_size, src_size, total, dest_off, src_off; - size_t dest_idx = 0, src_idx = 0, merged_idx = 0; - void *merged_buf; - struct pstore_ftrace_record *drec, *srec, *mrec; - size_t record_size = sizeof(struct pstore_ftrace_record); - - dest_off = dest->old_log_size % record_size; - dest_size = dest->old_log_size - dest_off; - - src_off = src->old_log_size % record_size; - src_size = src->old_log_size - src_off; - - total = dest_size + src_size; - merged_buf = kmalloc(total, GFP_KERNEL); - if (!merged_buf) - return -ENOMEM; - - drec = (struct pstore_ftrace_record *)(dest->old_log + dest_off); - srec = (struct pstore_ftrace_record *)(src->old_log + src_off); - mrec = (struct pstore_ftrace_record *)(merged_buf); - - while (dest_size > 0 && src_size > 0) { - if (pstore_ftrace_read_timestamp(&drec[dest_idx]) < - pstore_ftrace_read_timestamp(&srec[src_idx])) { - mrec[merged_idx++] = drec[dest_idx++]; - dest_size -= record_size; - } else { - mrec[merged_idx++] = srec[src_idx++]; - src_size -= record_size; - } - } - - while (dest_size > 0) { - mrec[merged_idx++] = drec[dest_idx++]; - dest_size -= record_size; - } - - while (src_size > 0) { - mrec[merged_idx++] = srec[src_idx++]; - src_size -= record_size; - } - - kfree(dest->old_log); - dest->old_log = merged_buf; - dest->old_log_size = total; - - return 0; -} - static ssize_t ramoops_pstore_read(struct pstore_record *record) { ssize_t size = 0; @@ -291,7 +244,12 @@ static ssize_t ramoops_pstore_read(struct pstore_record *record) tmp_prz->corrected_bytes += prz_next->corrected_bytes; tmp_prz->bad_blocks += prz_next->bad_blocks; - size = ftrace_log_combine(tmp_prz, prz_next); + + size = pstore_ftrace_combine_log( + &tmp_prz->old_log, + &tmp_prz->old_log_size, + prz_next->old_log, + prz_next->old_log_size); if (size) goto out; } @@ -382,16 +340,14 @@ static int notrace ramoops_pstore_write(struct pstore_record *record) return -EINVAL; /* - * Out of the various dmesg dump types, ramoops is currently designed - * to only store crash logs, rather than storing general kernel logs. + * We could filter on record->reason here if we wanted to (which + * would duplicate what happened before the "max_reason" setting + * was added), but that would defeat the purpose of a system + * changing printk.always_kmsg_dump, so instead log everything that + * the kmsg dumper sends us, since it should be doing the filtering + * based on the combination of printk.always_kmsg_dump and our + * requested "max_reason". */ - if (record->reason != KMSG_DUMP_OOPS && - record->reason != KMSG_DUMP_PANIC) - return -EINVAL; - - /* Skip Oopes when configured to do so. */ - if (record->reason == KMSG_DUMP_OOPS && !cxt->dump_oops) - return -EINVAL; /* * Explicitly only take the first part of any new crash. @@ -644,19 +600,25 @@ static int ramoops_init_prz(const char *name, return 0; } -static int ramoops_parse_dt_size(struct platform_device *pdev, - const char *propname, u32 *value) +/* Read a u32 from a dt property and make sure it's safe for an int. */ +static int ramoops_parse_dt_u32(struct platform_device *pdev, + const char *propname, + u32 default_value, u32 *value) { u32 val32 = 0; int ret; ret = of_property_read_u32(pdev->dev.of_node, propname, &val32); - if (ret < 0 && ret != -EINVAL) { + if (ret == -EINVAL) { + /* field is missing, use default value. */ + val32 = default_value; + } else if (ret < 0) { dev_err(&pdev->dev, "failed to parse property %s: %d\n", propname, ret); return ret; } + /* Sanity check our results. */ if (val32 > INT_MAX) { dev_err(&pdev->dev, "%s %u > INT_MAX\n", propname, val32); return -EOVERFLOW; @@ -687,23 +649,32 @@ static int ramoops_parse_dt(struct platform_device *pdev, pdata->mem_size = resource_size(res); pdata->mem_address = res->start; pdata->mem_type = of_property_read_bool(of_node, "unbuffered"); - pdata->dump_oops = !of_property_read_bool(of_node, "no-dump-oops"); - -#define parse_size(name, field) { \ - ret = ramoops_parse_dt_size(pdev, name, &value); \ + /* + * Setting "no-dump-oops" is deprecated and will be ignored if + * "max_reason" is also specified. + */ + if (of_property_read_bool(of_node, "no-dump-oops")) + pdata->max_reason = KMSG_DUMP_PANIC; + else + pdata->max_reason = KMSG_DUMP_OOPS; + +#define parse_u32(name, field, default_value) { \ + ret = ramoops_parse_dt_u32(pdev, name, default_value, \ + &value); \ if (ret < 0) \ return ret; \ field = value; \ } - parse_size("record-size", pdata->record_size); - parse_size("console-size", pdata->console_size); - parse_size("ftrace-size", pdata->ftrace_size); - parse_size("pmsg-size", pdata->pmsg_size); - parse_size("ecc-size", pdata->ecc_info.ecc_size); - parse_size("flags", pdata->flags); + parse_u32("record-size", pdata->record_size, 0); + parse_u32("console-size", pdata->console_size, 0); + parse_u32("ftrace-size", pdata->ftrace_size, 0); + parse_u32("pmsg-size", pdata->pmsg_size, 0); + parse_u32("ecc-size", pdata->ecc_info.ecc_size, 0); + parse_u32("flags", pdata->flags, 0); + parse_u32("max-reason", pdata->max_reason, pdata->max_reason); -#undef parse_size +#undef parse_u32 /* * Some old Chromebooks relied on the kernel setting the @@ -785,7 +756,6 @@ static int ramoops_probe(struct platform_device *pdev) cxt->console_size = pdata->console_size; cxt->ftrace_size = pdata->ftrace_size; cxt->pmsg_size = pdata->pmsg_size; - cxt->dump_oops = pdata->dump_oops; cxt->flags = pdata->flags; cxt->ecc_info = pdata->ecc_info; @@ -828,8 +798,10 @@ static int ramoops_probe(struct platform_device *pdev) * the single region size is how to check. */ cxt->pstore.flags = 0; - if (cxt->max_dump_cnt) + if (cxt->max_dump_cnt) { cxt->pstore.flags |= PSTORE_FLAGS_DMESG; + cxt->pstore.max_reason = pdata->max_reason; + } if (cxt->console_size) cxt->pstore.flags |= PSTORE_FLAGS_CONSOLE; if (cxt->max_ftrace_cnt) @@ -865,7 +837,7 @@ static int ramoops_probe(struct platform_device *pdev) mem_size = pdata->mem_size; mem_address = pdata->mem_address; record_size = pdata->record_size; - dump_oops = pdata->dump_oops; + ramoops_max_reason = pdata->max_reason; ramoops_console_size = pdata->console_size; ramoops_pmsg_size = pdata->pmsg_size; ramoops_ftrace_size = pdata->ftrace_size; @@ -948,7 +920,16 @@ static void __init ramoops_register_dummy(void) pdata.console_size = ramoops_console_size; pdata.ftrace_size = ramoops_ftrace_size; pdata.pmsg_size = ramoops_pmsg_size; - pdata.dump_oops = dump_oops; + /* If "max_reason" is set, its value has priority over "dump_oops". */ + if (ramoops_max_reason >= 0) + pdata.max_reason = ramoops_max_reason; + /* Otherwise, if "dump_oops" is set, parse it into "max_reason". */ + else if (ramoops_dump_oops != -1) + pdata.max_reason = ramoops_dump_oops ? KMSG_DUMP_OOPS + : KMSG_DUMP_PANIC; + /* And if neither are explicitly set, use the default. */ + else + pdata.max_reason = KMSG_DUMP_OOPS; pdata.flags = RAMOOPS_FLAG_FTRACE_PER_CPU; /* diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c new file mode 100644 index 000000000000..819428dfa32f --- /dev/null +++ b/fs/pstore/zone.c @@ -0,0 +1,1465 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide a pstore intermediate backend, organized into kernel memory + * allocated zones that are then mapped and flushed into a single + * contiguous region on a storage backend of some kind (block, mtd, etc). + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/mount.h> +#include <linux/printk.h> +#include <linux/fs.h> +#include <linux/pstore_zone.h> +#include <linux/kdev_t.h> +#include <linux/device.h> +#include <linux/namei.h> +#include <linux/fcntl.h> +#include <linux/uio.h> +#include <linux/writeback.h> +#include "internal.h" + +/** + * struct psz_head - header of zone to flush to storage + * + * @sig: signature to indicate header (PSZ_SIG xor PSZONE-type value) + * @datalen: length of data in @data + * @start: offset into @data where the beginning of the stored bytes begin + * @data: zone data. + */ +struct psz_buffer { +#define PSZ_SIG (0x43474244) /* DBGC */ + uint32_t sig; + atomic_t datalen; + atomic_t start; + uint8_t data[]; +}; + +/** + * struct psz_kmsg_header - kmsg dump-specific header to flush to storage + * + * @magic: magic num for kmsg dump header + * @time: kmsg dump trigger time + * @compressed: whether conpressed + * @counter: kmsg dump counter + * @reason: the kmsg dump reason (e.g. oops, panic, etc) + * @data: pointer to log data + * + * This is a sub-header for a kmsg dump, trailing after &psz_buffer. + */ +struct psz_kmsg_header { +#define PSTORE_KMSG_HEADER_MAGIC 0x4dfc3ae5 /* Just a random number */ + uint32_t magic; + struct timespec64 time; + bool compressed; + uint32_t counter; + enum kmsg_dump_reason reason; + uint8_t data[]; +}; + +/** + * struct pstore_zone - single stored buffer + * + * @off: zone offset of storage + * @type: front-end type for this zone + * @name: front-end name for this zone + * @buffer: pointer to data buffer managed by this zone + * @oldbuf: pointer to old data buffer + * @buffer_size: bytes in @buffer->data + * @should_recover: whether this zone should recover from storage + * @dirty: whether the data in @buffer dirty + * + * zone structure in memory. + */ +struct pstore_zone { + loff_t off; + const char *name; + enum pstore_type_id type; + + struct psz_buffer *buffer; + struct psz_buffer *oldbuf; + size_t buffer_size; + bool should_recover; + atomic_t dirty; +}; + +/** + * struct psz_context - all about running state of pstore/zone + * + * @kpszs: kmsg dump storage zones + * @ppsz: pmsg storage zone + * @cpsz: console storage zone + * @fpszs: ftrace storage zones + * @kmsg_max_cnt: max count of @kpszs + * @kmsg_read_cnt: counter of total read kmsg dumps + * @kmsg_write_cnt: counter of total kmsg dump writes + * @pmsg_read_cnt: counter of total read pmsg zone + * @console_read_cnt: counter of total read console zone + * @ftrace_max_cnt: max count of @fpszs + * @ftrace_read_cnt: counter of max read ftrace zone + * @oops_counter: counter of oops dumps + * @panic_counter: counter of panic dumps + * @recovered: whether finished recovering data from storage + * @on_panic: whether panic is happening + * @pstore_zone_info_lock: lock to @pstore_zone_info + * @pstore_zone_info: information from backend + * @pstore: structure for pstore + */ +struct psz_context { + struct pstore_zone **kpszs; + struct pstore_zone *ppsz; + struct pstore_zone *cpsz; + struct pstore_zone **fpszs; + unsigned int kmsg_max_cnt; + unsigned int kmsg_read_cnt; + unsigned int kmsg_write_cnt; + unsigned int pmsg_read_cnt; + unsigned int console_read_cnt; + unsigned int ftrace_max_cnt; + unsigned int ftrace_read_cnt; + /* + * These counters should be calculated during recovery. + * It records the oops/panic times after crashes rather than boots. + */ + unsigned int oops_counter; + unsigned int panic_counter; + atomic_t recovered; + atomic_t on_panic; + + /* + * pstore_zone_info_lock protects this entire structure during calls + * to register_pstore_zone()/unregister_pstore_zone(). + */ + struct mutex pstore_zone_info_lock; + struct pstore_zone_info *pstore_zone_info; + struct pstore_info pstore; +}; +static struct psz_context pstore_zone_cxt; + +static void psz_flush_all_dirty_zones(struct work_struct *); +static DECLARE_DELAYED_WORK(psz_cleaner, psz_flush_all_dirty_zones); + +/** + * enum psz_flush_mode - flush mode for psz_zone_write() + * + * @FLUSH_NONE: do not flush to storage but update data on memory + * @FLUSH_PART: just flush part of data including meta data to storage + * @FLUSH_META: just flush meta data of zone to storage + * @FLUSH_ALL: flush all of zone + */ +enum psz_flush_mode { + FLUSH_NONE = 0, + FLUSH_PART, + FLUSH_META, + FLUSH_ALL, +}; + +static inline int buffer_datalen(struct pstore_zone *zone) +{ + return atomic_read(&zone->buffer->datalen); +} + +static inline int buffer_start(struct pstore_zone *zone) +{ + return atomic_read(&zone->buffer->start); +} + +static inline bool is_on_panic(void) +{ + return atomic_read(&pstore_zone_cxt.on_panic); +} + +static ssize_t psz_zone_read_buffer(struct pstore_zone *zone, char *buf, + size_t len, unsigned long off) +{ + if (!buf || !zone || !zone->buffer) + return -EINVAL; + if (off > zone->buffer_size) + return -EINVAL; + len = min_t(size_t, len, zone->buffer_size - off); + memcpy(buf, zone->buffer->data + off, len); + return len; +} + +static int psz_zone_read_oldbuf(struct pstore_zone *zone, char *buf, + size_t len, unsigned long off) +{ + if (!buf || !zone || !zone->oldbuf) + return -EINVAL; + if (off > zone->buffer_size) + return -EINVAL; + len = min_t(size_t, len, zone->buffer_size - off); + memcpy(buf, zone->oldbuf->data + off, len); + return 0; +} + +static int psz_zone_write(struct pstore_zone *zone, + enum psz_flush_mode flush_mode, const char *buf, + size_t len, unsigned long off) +{ + struct pstore_zone_info *info = pstore_zone_cxt.pstore_zone_info; + ssize_t wcnt = 0; + ssize_t (*writeop)(const char *buf, size_t bytes, loff_t pos); + size_t wlen; + + if (off > zone->buffer_size) + return -EINVAL; + + wlen = min_t(size_t, len, zone->buffer_size - off); + if (buf && wlen) { + memcpy(zone->buffer->data + off, buf, wlen); + atomic_set(&zone->buffer->datalen, wlen + off); + } + + /* avoid to damage old records */ + if (!is_on_panic() && !atomic_read(&pstore_zone_cxt.recovered)) + goto dirty; + + writeop = is_on_panic() ? info->panic_write : info->write; + if (!writeop) + goto dirty; + + switch (flush_mode) { + case FLUSH_NONE: + if (unlikely(buf && wlen)) + goto dirty; + return 0; + case FLUSH_PART: + wcnt = writeop((const char *)zone->buffer->data + off, wlen, + zone->off + sizeof(*zone->buffer) + off); + if (wcnt != wlen) + goto dirty; + fallthrough; + case FLUSH_META: + wlen = sizeof(struct psz_buffer); + wcnt = writeop((const char *)zone->buffer, wlen, zone->off); + if (wcnt != wlen) + goto dirty; + break; + case FLUSH_ALL: + wlen = zone->buffer_size + sizeof(*zone->buffer); + wcnt = writeop((const char *)zone->buffer, wlen, zone->off); + if (wcnt != wlen) + goto dirty; + break; + } + + return 0; +dirty: + /* no need to mark dirty if going to try next zone */ + if (wcnt == -ENOMSG) + return -ENOMSG; + atomic_set(&zone->dirty, true); + /* flush dirty zones nicely */ + if (wcnt == -EBUSY && !is_on_panic()) + schedule_delayed_work(&psz_cleaner, msecs_to_jiffies(500)); + return -EBUSY; +} + +static int psz_flush_dirty_zone(struct pstore_zone *zone) +{ + int ret; + + if (unlikely(!zone)) + return -EINVAL; + + if (unlikely(!atomic_read(&pstore_zone_cxt.recovered))) + return -EBUSY; + + if (!atomic_xchg(&zone->dirty, false)) + return 0; + + ret = psz_zone_write(zone, FLUSH_ALL, NULL, 0, 0); + if (ret) + atomic_set(&zone->dirty, true); + return ret; +} + +static int psz_flush_dirty_zones(struct pstore_zone **zones, unsigned int cnt) +{ + int i, ret; + struct pstore_zone *zone; + + if (!zones) + return -EINVAL; + + for (i = 0; i < cnt; i++) { + zone = zones[i]; + if (!zone) + return -EINVAL; + ret = psz_flush_dirty_zone(zone); + if (ret) + return ret; + } + return 0; +} + +static int psz_move_zone(struct pstore_zone *old, struct pstore_zone *new) +{ + const char *data = (const char *)old->buffer->data; + int ret; + + ret = psz_zone_write(new, FLUSH_ALL, data, buffer_datalen(old), 0); + if (ret) { + atomic_set(&new->buffer->datalen, 0); + atomic_set(&new->dirty, false); + return ret; + } + atomic_set(&old->buffer->datalen, 0); + return 0; +} + +static void psz_flush_all_dirty_zones(struct work_struct *work) +{ + struct psz_context *cxt = &pstore_zone_cxt; + int ret = 0; + + if (cxt->ppsz) + ret |= psz_flush_dirty_zone(cxt->ppsz); + if (cxt->cpsz) + ret |= psz_flush_dirty_zone(cxt->cpsz); + if (cxt->kpszs) + ret |= psz_flush_dirty_zones(cxt->kpszs, cxt->kmsg_max_cnt); + if (cxt->fpszs) + ret |= psz_flush_dirty_zones(cxt->fpszs, cxt->ftrace_max_cnt); + if (ret && cxt->pstore_zone_info) + schedule_delayed_work(&psz_cleaner, msecs_to_jiffies(1000)); +} + +static int psz_kmsg_recover_data(struct psz_context *cxt) +{ + struct pstore_zone_info *info = cxt->pstore_zone_info; + struct pstore_zone *zone = NULL; + struct psz_buffer *buf; + unsigned long i; + ssize_t rcnt; + + if (!info->read) + return -EINVAL; + + for (i = 0; i < cxt->kmsg_max_cnt; i++) { + zone = cxt->kpszs[i]; + if (unlikely(!zone)) + return -EINVAL; + if (atomic_read(&zone->dirty)) { + unsigned int wcnt = cxt->kmsg_write_cnt; + struct pstore_zone *new = cxt->kpszs[wcnt]; + int ret; + + ret = psz_move_zone(zone, new); + if (ret) { + pr_err("move zone from %lu to %d failed\n", + i, wcnt); + return ret; + } + cxt->kmsg_write_cnt = (wcnt + 1) % cxt->kmsg_max_cnt; + } + if (!zone->should_recover) + continue; + buf = zone->buffer; + rcnt = info->read((char *)buf, zone->buffer_size + sizeof(*buf), + zone->off); + if (rcnt != zone->buffer_size + sizeof(*buf)) + return (int)rcnt < 0 ? (int)rcnt : -EIO; + } + return 0; +} + +static int psz_kmsg_recover_meta(struct psz_context *cxt) +{ + struct pstore_zone_info *info = cxt->pstore_zone_info; + struct pstore_zone *zone; + size_t rcnt, len; + struct psz_buffer *buf; + struct psz_kmsg_header *hdr; + struct timespec64 time = { }; + unsigned long i; + /* + * Recover may on panic, we can't allocate any memory by kmalloc. + * So, we use local array instead. + */ + char buffer_header[sizeof(*buf) + sizeof(*hdr)] = {0}; + + if (!info->read) + return -EINVAL; + + len = sizeof(*buf) + sizeof(*hdr); + buf = (struct psz_buffer *)buffer_header; + for (i = 0; i < cxt->kmsg_max_cnt; i++) { + zone = cxt->kpszs[i]; + if (unlikely(!zone)) + return -EINVAL; + + rcnt = info->read((char *)buf, len, zone->off); + if (rcnt == -ENOMSG) { + pr_debug("%s with id %lu may be broken, skip\n", + zone->name, i); + continue; + } else if (rcnt != len) { + pr_err("read %s with id %lu failed\n", zone->name, i); + return (int)rcnt < 0 ? (int)rcnt : -EIO; + } + + if (buf->sig != zone->buffer->sig) { + pr_debug("no valid data in kmsg dump zone %lu\n", i); + continue; + } + + if (zone->buffer_size < atomic_read(&buf->datalen)) { + pr_info("found overtop zone: %s: id %lu, off %lld, size %zu\n", + zone->name, i, zone->off, + zone->buffer_size); + continue; + } + + hdr = (struct psz_kmsg_header *)buf->data; + if (hdr->magic != PSTORE_KMSG_HEADER_MAGIC) { + pr_info("found invalid zone: %s: id %lu, off %lld, size %zu\n", + zone->name, i, zone->off, + zone->buffer_size); + continue; + } + + /* + * we get the newest zone, and the next one must be the oldest + * or unused zone, because we do write one by one like a circle. + */ + if (hdr->time.tv_sec >= time.tv_sec) { + time.tv_sec = hdr->time.tv_sec; + cxt->kmsg_write_cnt = (i + 1) % cxt->kmsg_max_cnt; + } + + if (hdr->reason == KMSG_DUMP_OOPS) + cxt->oops_counter = + max(cxt->oops_counter, hdr->counter); + else if (hdr->reason == KMSG_DUMP_PANIC) + cxt->panic_counter = + max(cxt->panic_counter, hdr->counter); + + if (!atomic_read(&buf->datalen)) { + pr_debug("found erased zone: %s: id %lu, off %lld, size %zu, datalen %d\n", + zone->name, i, zone->off, + zone->buffer_size, + atomic_read(&buf->datalen)); + continue; + } + + if (!is_on_panic()) + zone->should_recover = true; + pr_debug("found nice zone: %s: id %lu, off %lld, size %zu, datalen %d\n", + zone->name, i, zone->off, + zone->buffer_size, atomic_read(&buf->datalen)); + } + + return 0; +} + +static int psz_kmsg_recover(struct psz_context *cxt) +{ + int ret; + + if (!cxt->kpszs) + return 0; + + ret = psz_kmsg_recover_meta(cxt); + if (ret) + goto recover_fail; + + ret = psz_kmsg_recover_data(cxt); + if (ret) + goto recover_fail; + + return 0; +recover_fail: + pr_debug("psz_recover_kmsg failed\n"); + return ret; +} + +static int psz_recover_zone(struct psz_context *cxt, struct pstore_zone *zone) +{ + struct pstore_zone_info *info = cxt->pstore_zone_info; + struct psz_buffer *oldbuf, tmpbuf; + int ret = 0; + char *buf; + ssize_t rcnt, len, start, off; + + if (!zone || zone->oldbuf) + return 0; + + if (is_on_panic()) { + /* save data as much as possible */ + psz_flush_dirty_zone(zone); + return 0; + } + + if (unlikely(!info->read)) + return -EINVAL; + + len = sizeof(struct psz_buffer); + rcnt = info->read((char *)&tmpbuf, len, zone->off); + if (rcnt != len) { + pr_debug("read zone %s failed\n", zone->name); + return (int)rcnt < 0 ? (int)rcnt : -EIO; + } + + if (tmpbuf.sig != zone->buffer->sig) { + pr_debug("no valid data in zone %s\n", zone->name); + return 0; + } + + if (zone->buffer_size < atomic_read(&tmpbuf.datalen) || + zone->buffer_size < atomic_read(&tmpbuf.start)) { + pr_info("found overtop zone: %s: off %lld, size %zu\n", + zone->name, zone->off, zone->buffer_size); + /* just keep going */ + return 0; + } + + if (!atomic_read(&tmpbuf.datalen)) { + pr_debug("found erased zone: %s: off %lld, size %zu, datalen %d\n", + zone->name, zone->off, zone->buffer_size, + atomic_read(&tmpbuf.datalen)); + return 0; + } + + pr_debug("found nice zone: %s: off %lld, size %zu, datalen %d\n", + zone->name, zone->off, zone->buffer_size, + atomic_read(&tmpbuf.datalen)); + + len = atomic_read(&tmpbuf.datalen) + sizeof(*oldbuf); + oldbuf = kzalloc(len, GFP_KERNEL); + if (!oldbuf) + return -ENOMEM; + + memcpy(oldbuf, &tmpbuf, sizeof(*oldbuf)); + buf = (char *)oldbuf + sizeof(*oldbuf); + len = atomic_read(&oldbuf->datalen); + start = atomic_read(&oldbuf->start); + off = zone->off + sizeof(*oldbuf); + + /* get part of data */ + rcnt = info->read(buf, len - start, off + start); + if (rcnt != len - start) { + pr_err("read zone %s failed\n", zone->name); + ret = (int)rcnt < 0 ? (int)rcnt : -EIO; + goto free_oldbuf; + } + + /* get the rest of data */ + rcnt = info->read(buf + len - start, start, off); + if (rcnt != start) { + pr_err("read zone %s failed\n", zone->name); + ret = (int)rcnt < 0 ? (int)rcnt : -EIO; + goto free_oldbuf; + } + + zone->oldbuf = oldbuf; + psz_flush_dirty_zone(zone); + return 0; + +free_oldbuf: + kfree(oldbuf); + return ret; +} + +static int psz_recover_zones(struct psz_context *cxt, + struct pstore_zone **zones, unsigned int cnt) +{ + int ret; + unsigned int i; + struct pstore_zone *zone; + + if (!zones) + return 0; + + for (i = 0; i < cnt; i++) { + zone = zones[i]; + if (unlikely(!zone)) + continue; + ret = psz_recover_zone(cxt, zone); + if (ret) + goto recover_fail; + } + + return 0; +recover_fail: + pr_debug("recover %s[%u] failed\n", zone->name, i); + return ret; +} + +/** + * psz_recovery() - recover data from storage + * @cxt: the context of pstore/zone + * + * recovery means reading data back from storage after rebooting + * + * Return: 0 on success, others on failure. + */ +static inline int psz_recovery(struct psz_context *cxt) +{ + int ret; + + if (atomic_read(&cxt->recovered)) + return 0; + + ret = psz_kmsg_recover(cxt); + if (ret) + goto out; + + ret = psz_recover_zone(cxt, cxt->ppsz); + if (ret) + goto out; + + ret = psz_recover_zone(cxt, cxt->cpsz); + if (ret) + goto out; + + ret = psz_recover_zones(cxt, cxt->fpszs, cxt->ftrace_max_cnt); + +out: + if (unlikely(ret)) + pr_err("recover failed\n"); + else { + pr_debug("recover end!\n"); + atomic_set(&cxt->recovered, 1); + } + return ret; +} + +static int psz_pstore_open(struct pstore_info *psi) +{ + struct psz_context *cxt = psi->data; + + cxt->kmsg_read_cnt = 0; + cxt->pmsg_read_cnt = 0; + cxt->console_read_cnt = 0; + cxt->ftrace_read_cnt = 0; + return 0; +} + +static inline bool psz_old_ok(struct pstore_zone *zone) +{ + if (zone && zone->oldbuf && atomic_read(&zone->oldbuf->datalen)) + return true; + return false; +} + +static inline bool psz_ok(struct pstore_zone *zone) +{ + if (zone && zone->buffer && buffer_datalen(zone)) + return true; + return false; +} + +static inline int psz_kmsg_erase(struct psz_context *cxt, + struct pstore_zone *zone, struct pstore_record *record) +{ + struct psz_buffer *buffer = zone->buffer; + struct psz_kmsg_header *hdr = + (struct psz_kmsg_header *)buffer->data; + size_t size; + + if (unlikely(!psz_ok(zone))) + return 0; + + /* this zone is already updated, no need to erase */ + if (record->count != hdr->counter) + return 0; + + size = buffer_datalen(zone) + sizeof(*zone->buffer); + atomic_set(&zone->buffer->datalen, 0); + if (cxt->pstore_zone_info->erase) + return cxt->pstore_zone_info->erase(size, zone->off); + else + return psz_zone_write(zone, FLUSH_META, NULL, 0, 0); +} + +static inline int psz_record_erase(struct psz_context *cxt, + struct pstore_zone *zone) +{ + if (unlikely(!psz_old_ok(zone))) + return 0; + + kfree(zone->oldbuf); + zone->oldbuf = NULL; + /* + * if there are new data in zone buffer, that means the old data + * are already invalid. It is no need to flush 0 (erase) to + * block device. + */ + if (!buffer_datalen(zone)) + return psz_zone_write(zone, FLUSH_META, NULL, 0, 0); + psz_flush_dirty_zone(zone); + return 0; +} + +static int psz_pstore_erase(struct pstore_record *record) +{ + struct psz_context *cxt = record->psi->data; + + switch (record->type) { + case PSTORE_TYPE_DMESG: + if (record->id >= cxt->kmsg_max_cnt) + return -EINVAL; + return psz_kmsg_erase(cxt, cxt->kpszs[record->id], record); + case PSTORE_TYPE_PMSG: + return psz_record_erase(cxt, cxt->ppsz); + case PSTORE_TYPE_CONSOLE: + return psz_record_erase(cxt, cxt->cpsz); + case PSTORE_TYPE_FTRACE: + if (record->id >= cxt->ftrace_max_cnt) + return -EINVAL; + return psz_record_erase(cxt, cxt->fpszs[record->id]); + default: return -EINVAL; + } +} + +static void psz_write_kmsg_hdr(struct pstore_zone *zone, + struct pstore_record *record) +{ + struct psz_context *cxt = record->psi->data; + struct psz_buffer *buffer = zone->buffer; + struct psz_kmsg_header *hdr = + (struct psz_kmsg_header *)buffer->data; + + hdr->magic = PSTORE_KMSG_HEADER_MAGIC; + hdr->compressed = record->compressed; + hdr->time.tv_sec = record->time.tv_sec; + hdr->time.tv_nsec = record->time.tv_nsec; + hdr->reason = record->reason; + if (hdr->reason == KMSG_DUMP_OOPS) + hdr->counter = ++cxt->oops_counter; + else if (hdr->reason == KMSG_DUMP_PANIC) + hdr->counter = ++cxt->panic_counter; + else + hdr->counter = 0; +} + +/* + * In case zone is broken, which may occur to MTD device, we try each zones, + * start at cxt->kmsg_write_cnt. + */ +static inline int notrace psz_kmsg_write_record(struct psz_context *cxt, + struct pstore_record *record) +{ + size_t size, hlen; + struct pstore_zone *zone; + unsigned int i; + + for (i = 0; i < cxt->kmsg_max_cnt; i++) { + unsigned int zonenum, len; + int ret; + + zonenum = (cxt->kmsg_write_cnt + i) % cxt->kmsg_max_cnt; + zone = cxt->kpszs[zonenum]; + if (unlikely(!zone)) + return -ENOSPC; + + /* avoid destroying old data, allocate a new one */ + len = zone->buffer_size + sizeof(*zone->buffer); + zone->oldbuf = zone->buffer; + zone->buffer = kzalloc(len, GFP_KERNEL); + if (!zone->buffer) { + zone->buffer = zone->oldbuf; + return -ENOMEM; + } + zone->buffer->sig = zone->oldbuf->sig; + + pr_debug("write %s to zone id %d\n", zone->name, zonenum); + psz_write_kmsg_hdr(zone, record); + hlen = sizeof(struct psz_kmsg_header); + size = min_t(size_t, record->size, zone->buffer_size - hlen); + ret = psz_zone_write(zone, FLUSH_ALL, record->buf, size, hlen); + if (likely(!ret || ret != -ENOMSG)) { + cxt->kmsg_write_cnt = zonenum + 1; + cxt->kmsg_write_cnt %= cxt->kmsg_max_cnt; + /* no need to try next zone, free last zone buffer */ + kfree(zone->oldbuf); + zone->oldbuf = NULL; + return ret; + } + + pr_debug("zone %u may be broken, try next dmesg zone\n", + zonenum); + kfree(zone->buffer); + zone->buffer = zone->oldbuf; + zone->oldbuf = NULL; + } + + return -EBUSY; +} + +static int notrace psz_kmsg_write(struct psz_context *cxt, + struct pstore_record *record) +{ + int ret; + + /* + * Explicitly only take the first part of any new crash. + * If our buffer is larger than kmsg_bytes, this can never happen, + * and if our buffer is smaller than kmsg_bytes, we don't want the + * report split across multiple records. + */ + if (record->part != 1) + return -ENOSPC; + + if (!cxt->kpszs) + return -ENOSPC; + + ret = psz_kmsg_write_record(cxt, record); + if (!ret && is_on_panic()) { + /* ensure all data are flushed to storage when panic */ + pr_debug("try to flush other dirty zones\n"); + psz_flush_all_dirty_zones(NULL); + } + + /* always return 0 as we had handled it on buffer */ + return 0; +} + +static int notrace psz_record_write(struct pstore_zone *zone, + struct pstore_record *record) +{ + size_t start, rem; + bool is_full_data = false; + char *buf; + int cnt; + + if (!zone || !record) + return -ENOSPC; + + if (atomic_read(&zone->buffer->datalen) >= zone->buffer_size) + is_full_data = true; + + cnt = record->size; + buf = record->buf; + 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)) { + psz_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); + psz_zone_write(zone, FLUSH_PART, buf, cnt, start); + + /** + * psz_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); + psz_zone_write(zone, FLUSH_META, NULL, 0, 0); + } + return 0; +} + +static int notrace psz_pstore_write(struct pstore_record *record) +{ + struct psz_context *cxt = record->psi->data; + + if (record->type == PSTORE_TYPE_DMESG && + record->reason == KMSG_DUMP_PANIC) + atomic_set(&cxt->on_panic, 1); + + /* + * if on panic, do not write except panic records + * Fix case that panic_write prints log which wakes up console backend. + */ + if (is_on_panic() && record->type != PSTORE_TYPE_DMESG) + return -EBUSY; + + switch (record->type) { + case PSTORE_TYPE_DMESG: + return psz_kmsg_write(cxt, record); + case PSTORE_TYPE_CONSOLE: + return psz_record_write(cxt->cpsz, record); + case PSTORE_TYPE_PMSG: + return psz_record_write(cxt->ppsz, record); + case PSTORE_TYPE_FTRACE: { + int zonenum = smp_processor_id(); + + if (!cxt->fpszs) + return -ENOSPC; + return psz_record_write(cxt->fpszs[zonenum], record); + } + default: + return -EINVAL; + } +} + +static struct pstore_zone *psz_read_next_zone(struct psz_context *cxt) +{ + struct pstore_zone *zone = NULL; + + while (cxt->kmsg_read_cnt < cxt->kmsg_max_cnt) { + zone = cxt->kpszs[cxt->kmsg_read_cnt++]; + if (psz_ok(zone)) + return zone; + } + + if (cxt->ftrace_read_cnt < cxt->ftrace_max_cnt) + /* + * No need psz_old_ok(). Let psz_ftrace_read() do so for + * combination. psz_ftrace_read() should traverse over + * all zones in case of some zone without data. + */ + return cxt->fpszs[cxt->ftrace_read_cnt++]; + + if (cxt->pmsg_read_cnt == 0) { + cxt->pmsg_read_cnt++; + zone = cxt->ppsz; + if (psz_old_ok(zone)) + return zone; + } + + if (cxt->console_read_cnt == 0) { + cxt->console_read_cnt++; + zone = cxt->cpsz; + if (psz_old_ok(zone)) + return zone; + } + + return NULL; +} + +static int psz_kmsg_read_hdr(struct pstore_zone *zone, + struct pstore_record *record) +{ + struct psz_buffer *buffer = zone->buffer; + struct psz_kmsg_header *hdr = + (struct psz_kmsg_header *)buffer->data; + + if (hdr->magic != PSTORE_KMSG_HEADER_MAGIC) + return -EINVAL; + record->compressed = hdr->compressed; + record->time.tv_sec = hdr->time.tv_sec; + record->time.tv_nsec = hdr->time.tv_nsec; + record->reason = hdr->reason; + record->count = hdr->counter; + return 0; +} + +static ssize_t psz_kmsg_read(struct pstore_zone *zone, + struct pstore_record *record) +{ + ssize_t size, hlen = 0; + + size = buffer_datalen(zone); + /* Clear and skip this kmsg dump record if it has no valid header */ + if (psz_kmsg_read_hdr(zone, record)) { + atomic_set(&zone->buffer->datalen, 0); + atomic_set(&zone->dirty, 0); + return -ENOMSG; + } + size -= sizeof(struct psz_kmsg_header); + + if (!record->compressed) { + char *buf = kasprintf(GFP_KERNEL, "%s: Total %d times\n", + kmsg_dump_reason_str(record->reason), + record->count); + hlen = strlen(buf); + record->buf = krealloc(buf, hlen + size, GFP_KERNEL); + if (!record->buf) { + kfree(buf); + return -ENOMEM; + } + } else { + record->buf = kmalloc(size, GFP_KERNEL); + if (!record->buf) + return -ENOMEM; + } + + size = psz_zone_read_buffer(zone, record->buf + hlen, size, + sizeof(struct psz_kmsg_header)); + if (unlikely(size < 0)) { + kfree(record->buf); + return -ENOMSG; + } + + return size + hlen; +} + +/* try to combine all ftrace zones */ +static ssize_t psz_ftrace_read(struct pstore_zone *zone, + struct pstore_record *record) +{ + struct psz_context *cxt; + struct psz_buffer *buf; + int ret; + + if (!zone || !record) + return -ENOSPC; + + if (!psz_old_ok(zone)) + goto out; + + buf = (struct psz_buffer *)zone->oldbuf; + if (!buf) + return -ENOMSG; + + ret = pstore_ftrace_combine_log(&record->buf, &record->size, + (char *)buf->data, atomic_read(&buf->datalen)); + if (unlikely(ret)) + return ret; + +out: + cxt = record->psi->data; + if (cxt->ftrace_read_cnt < cxt->ftrace_max_cnt) + /* then, read next ftrace zone */ + return -ENOMSG; + record->id = 0; + return record->size ? record->size : -ENOMSG; +} + +static ssize_t psz_record_read(struct pstore_zone *zone, + struct pstore_record *record) +{ + size_t len; + struct psz_buffer *buf; + + if (!zone || !record) + return -ENOSPC; + + buf = (struct psz_buffer *)zone->oldbuf; + if (!buf) + return -ENOMSG; + + len = atomic_read(&buf->datalen); + record->buf = kmalloc(len, GFP_KERNEL); + if (!record->buf) + return -ENOMEM; + + if (unlikely(psz_zone_read_oldbuf(zone, record->buf, len, 0))) { + kfree(record->buf); + return -ENOMSG; + } + + return len; +} + +static ssize_t psz_pstore_read(struct pstore_record *record) +{ + struct psz_context *cxt = record->psi->data; + ssize_t (*readop)(struct pstore_zone *zone, + struct pstore_record *record); + struct pstore_zone *zone; + ssize_t ret; + + /* before read, we must recover from storage */ + ret = psz_recovery(cxt); + if (ret) + return ret; + +next_zone: + zone = psz_read_next_zone(cxt); + if (!zone) + return 0; + + record->type = zone->type; + switch (record->type) { + case PSTORE_TYPE_DMESG: + readop = psz_kmsg_read; + record->id = cxt->kmsg_read_cnt - 1; + break; + case PSTORE_TYPE_FTRACE: + readop = psz_ftrace_read; + break; + case PSTORE_TYPE_CONSOLE: + fallthrough; + case PSTORE_TYPE_PMSG: + readop = psz_record_read; + break; + default: + goto next_zone; + } + + ret = readop(zone, record); + if (ret == -ENOMSG) + goto next_zone; + return ret; +} + +static struct psz_context pstore_zone_cxt = { + .pstore_zone_info_lock = + __MUTEX_INITIALIZER(pstore_zone_cxt.pstore_zone_info_lock), + .recovered = ATOMIC_INIT(0), + .on_panic = ATOMIC_INIT(0), + .pstore = { + .owner = THIS_MODULE, + .open = psz_pstore_open, + .read = psz_pstore_read, + .write = psz_pstore_write, + .erase = psz_pstore_erase, + }, +}; + +static void psz_free_zone(struct pstore_zone **pszone) +{ + struct pstore_zone *zone = *pszone; + + if (!zone) + return; + + kfree(zone->buffer); + kfree(zone); + *pszone = NULL; +} + +static void psz_free_zones(struct pstore_zone ***pszones, unsigned int *cnt) +{ + struct pstore_zone **zones = *pszones; + + if (!zones) + return; + + while (*cnt > 0) { + (*cnt)--; + psz_free_zone(&(zones[*cnt])); + } + kfree(zones); + *pszones = NULL; +} + +static void psz_free_all_zones(struct psz_context *cxt) +{ + if (cxt->kpszs) + psz_free_zones(&cxt->kpszs, &cxt->kmsg_max_cnt); + if (cxt->ppsz) + psz_free_zone(&cxt->ppsz); + if (cxt->cpsz) + psz_free_zone(&cxt->cpsz); + if (cxt->fpszs) + psz_free_zones(&cxt->fpszs, &cxt->ftrace_max_cnt); +} + +static struct pstore_zone *psz_init_zone(enum pstore_type_id type, + loff_t *off, size_t size) +{ + struct pstore_zone_info *info = pstore_zone_cxt.pstore_zone_info; + struct pstore_zone *zone; + const char *name = pstore_type_to_name(type); + + if (!size) + return NULL; + + if (*off + size > info->total_size) { + pr_err("no room for %s (0x%zx@0x%llx over 0x%lx)\n", + name, size, *off, info->total_size); + return ERR_PTR(-ENOMEM); + } + + zone = kzalloc(sizeof(struct pstore_zone), GFP_KERNEL); + if (!zone) + return ERR_PTR(-ENOMEM); + + zone->buffer = kmalloc(size, GFP_KERNEL); + if (!zone->buffer) { + kfree(zone); + return ERR_PTR(-ENOMEM); + } + memset(zone->buffer, 0xFF, size); + zone->off = *off; + zone->name = name; + zone->type = type; + zone->buffer_size = size - sizeof(struct psz_buffer); + zone->buffer->sig = type ^ PSZ_SIG; + zone->oldbuf = NULL; + atomic_set(&zone->dirty, 0); + atomic_set(&zone->buffer->datalen, 0); + atomic_set(&zone->buffer->start, 0); + + *off += size; + + pr_debug("pszone %s: off 0x%llx, %zu header, %zu data\n", zone->name, + zone->off, sizeof(*zone->buffer), zone->buffer_size); + return zone; +} + +static struct pstore_zone **psz_init_zones(enum pstore_type_id type, + loff_t *off, size_t total_size, ssize_t record_size, + unsigned int *cnt) +{ + struct pstore_zone_info *info = pstore_zone_cxt.pstore_zone_info; + struct pstore_zone **zones, *zone; + const char *name = pstore_type_to_name(type); + int c, i; + + *cnt = 0; + if (!total_size || !record_size) + return NULL; + + if (*off + total_size > info->total_size) { + pr_err("no room for zones %s (0x%zx@0x%llx over 0x%lx)\n", + name, total_size, *off, info->total_size); + return ERR_PTR(-ENOMEM); + } + + c = total_size / record_size; + zones = kcalloc(c, sizeof(*zones), GFP_KERNEL); + if (!zones) { + pr_err("allocate for zones %s failed\n", name); + return ERR_PTR(-ENOMEM); + } + memset(zones, 0, c * sizeof(*zones)); + + for (i = 0; i < c; i++) { + zone = psz_init_zone(type, off, record_size); + if (!zone || IS_ERR(zone)) { + pr_err("initialize zones %s failed\n", name); + psz_free_zones(&zones, &i); + return (void *)zone; + } + zones[i] = zone; + } + + *cnt = c; + return zones; +} + +static int psz_alloc_zones(struct psz_context *cxt) +{ + struct pstore_zone_info *info = cxt->pstore_zone_info; + loff_t off = 0; + int err; + size_t off_size = 0; + + off_size += info->pmsg_size; + cxt->ppsz = psz_init_zone(PSTORE_TYPE_PMSG, &off, info->pmsg_size); + if (IS_ERR(cxt->ppsz)) { + err = PTR_ERR(cxt->ppsz); + cxt->ppsz = NULL; + goto free_out; + } + + off_size += info->console_size; + cxt->cpsz = psz_init_zone(PSTORE_TYPE_CONSOLE, &off, + info->console_size); + if (IS_ERR(cxt->cpsz)) { + err = PTR_ERR(cxt->cpsz); + cxt->cpsz = NULL; + goto free_out; + } + + off_size += info->ftrace_size; + cxt->fpszs = psz_init_zones(PSTORE_TYPE_FTRACE, &off, + info->ftrace_size, + info->ftrace_size / nr_cpu_ids, + &cxt->ftrace_max_cnt); + if (IS_ERR(cxt->fpszs)) { + err = PTR_ERR(cxt->fpszs); + cxt->fpszs = NULL; + goto free_out; + } + + cxt->kpszs = psz_init_zones(PSTORE_TYPE_DMESG, &off, + info->total_size - off_size, + info->kmsg_size, &cxt->kmsg_max_cnt); + if (IS_ERR(cxt->kpszs)) { + err = PTR_ERR(cxt->kpszs); + cxt->kpszs = NULL; + goto free_out; + } + + return 0; +free_out: + psz_free_all_zones(cxt); + return err; +} + +/** + * register_pstore_zone() - register to pstore/zone + * + * @info: back-end driver information. See &struct pstore_zone_info. + * + * Only one back-end at one time. + * + * Return: 0 on success, others on failure. + */ +int register_pstore_zone(struct pstore_zone_info *info) +{ + int err = -EINVAL; + struct psz_context *cxt = &pstore_zone_cxt; + + if (info->total_size < 4096) { + pr_warn("total_size must be >= 4096\n"); + return -EINVAL; + } + + if (!info->kmsg_size && !info->pmsg_size && !info->console_size && + !info->ftrace_size) { + pr_warn("at least one record size must be non-zero\n"); + return -EINVAL; + } + + if (!info->name || !info->name[0]) + return -EINVAL; + +#define check_size(name, size) { \ + if (info->name > 0 && info->name < (size)) { \ + pr_err(#name " must be over %d\n", (size)); \ + return -EINVAL; \ + } \ + if (info->name & (size - 1)) { \ + pr_err(#name " must be a multiple of %d\n", \ + (size)); \ + return -EINVAL; \ + } \ + } + + check_size(total_size, 4096); + check_size(kmsg_size, SECTOR_SIZE); + check_size(pmsg_size, SECTOR_SIZE); + check_size(console_size, SECTOR_SIZE); + check_size(ftrace_size, SECTOR_SIZE); + +#undef check_size + + /* + * the @read and @write must be applied. + * if no @read, pstore may mount failed. + * if no @write, pstore do not support to remove record file. + */ + if (!info->read || !info->write) { + pr_err("no valid general read/write interface\n"); + return -EINVAL; + } + + mutex_lock(&cxt->pstore_zone_info_lock); + if (cxt->pstore_zone_info) { + pr_warn("'%s' already loaded: ignoring '%s'\n", + cxt->pstore_zone_info->name, info->name); + mutex_unlock(&cxt->pstore_zone_info_lock); + return -EBUSY; + } + cxt->pstore_zone_info = info; + + pr_debug("register %s with properties:\n", info->name); + pr_debug("\ttotal size : %ld Bytes\n", info->total_size); + pr_debug("\tkmsg size : %ld Bytes\n", info->kmsg_size); + pr_debug("\tpmsg size : %ld Bytes\n", info->pmsg_size); + pr_debug("\tconsole size : %ld Bytes\n", info->console_size); + pr_debug("\tftrace size : %ld Bytes\n", info->ftrace_size); + + err = psz_alloc_zones(cxt); + if (err) { + pr_err("alloc zones failed\n"); + goto fail_out; + } + + if (info->kmsg_size) { + cxt->pstore.bufsize = cxt->kpszs[0]->buffer_size - + sizeof(struct psz_kmsg_header); + cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); + if (!cxt->pstore.buf) { + err = -ENOMEM; + goto fail_free; + } + } + cxt->pstore.data = cxt; + + pr_info("registered %s as backend for", info->name); + cxt->pstore.max_reason = info->max_reason; + cxt->pstore.name = info->name; + if (info->kmsg_size) { + cxt->pstore.flags |= PSTORE_FLAGS_DMESG; + pr_cont(" kmsg(%s", + kmsg_dump_reason_str(cxt->pstore.max_reason)); + if (cxt->pstore_zone_info->panic_write) + pr_cont(",panic_write"); + pr_cont(")"); + } + if (info->pmsg_size) { + cxt->pstore.flags |= PSTORE_FLAGS_PMSG; + pr_cont(" pmsg"); + } + if (info->console_size) { + cxt->pstore.flags |= PSTORE_FLAGS_CONSOLE; + pr_cont(" console"); + } + if (info->ftrace_size) { + cxt->pstore.flags |= PSTORE_FLAGS_FTRACE; + pr_cont(" ftrace"); + } + pr_cont("\n"); + + err = pstore_register(&cxt->pstore); + if (err) { + pr_err("registering with pstore failed\n"); + goto fail_free; + } + mutex_unlock(&pstore_zone_cxt.pstore_zone_info_lock); + + return 0; + +fail_free: + kfree(cxt->pstore.buf); + cxt->pstore.buf = NULL; + cxt->pstore.bufsize = 0; + psz_free_all_zones(cxt); +fail_out: + pstore_zone_cxt.pstore_zone_info = NULL; + mutex_unlock(&pstore_zone_cxt.pstore_zone_info_lock); + return err; +} +EXPORT_SYMBOL_GPL(register_pstore_zone); + +/** + * unregister_pstore_zone() - unregister to pstore/zone + * + * @info: back-end driver information. See struct pstore_zone_info. + */ +void unregister_pstore_zone(struct pstore_zone_info *info) +{ + struct psz_context *cxt = &pstore_zone_cxt; + + mutex_lock(&cxt->pstore_zone_info_lock); + if (!cxt->pstore_zone_info) { + mutex_unlock(&cxt->pstore_zone_info_lock); + return; + } + + /* Stop incoming writes from pstore. */ + pstore_unregister(&cxt->pstore); + + /* Flush any pending writes. */ + psz_flush_all_dirty_zones(NULL); + flush_delayed_work(&psz_cleaner); + + /* Clean up allocations. */ + kfree(cxt->pstore.buf); + cxt->pstore.buf = NULL; + cxt->pstore.bufsize = 0; + cxt->pstore_zone_info = NULL; + + psz_free_all_zones(cxt); + + /* Clear counters and zone state. */ + cxt->oops_counter = 0; + cxt->panic_counter = 0; + atomic_set(&cxt->recovered, 0); + atomic_set(&cxt->on_panic, 0); + + mutex_unlock(&cxt->pstore_zone_info_lock); +} +EXPORT_SYMBOL_GPL(unregister_pstore_zone); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("WeiXiong Liao <liaoweixiong@allwinnertech.com>"); +MODULE_AUTHOR("Kees Cook <keescook@chromium.org>"); +MODULE_DESCRIPTION("Storage Manager for pstore/blk"); diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 2e7a1e032c71..3378bcbe585e 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -25,9 +25,8 @@ enum kmsg_dump_reason { KMSG_DUMP_PANIC, KMSG_DUMP_OOPS, KMSG_DUMP_EMERG, - KMSG_DUMP_RESTART, - KMSG_DUMP_HALT, - KMSG_DUMP_POWEROFF, + KMSG_DUMP_SHUTDOWN, + KMSG_DUMP_MAX }; /** @@ -71,6 +70,8 @@ void kmsg_dump_rewind(struct kmsg_dumper *dumper); int kmsg_dump_register(struct kmsg_dumper *dumper); int kmsg_dump_unregister(struct kmsg_dumper *dumper); + +const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason); #else static inline void kmsg_dump(enum kmsg_dump_reason reason) { @@ -112,6 +113,11 @@ static inline int kmsg_dump_unregister(struct kmsg_dumper *dumper) { return -EINVAL; } + +static inline const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) +{ + return "Disabled"; +} #endif #endif /* _LINUX_KMSG_DUMP_H */ diff --git a/include/linux/pstore.h b/include/linux/pstore.h index e779441e6d26..eb93a54cff31 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -96,6 +96,12 @@ struct pstore_record { * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for + * @max_reason: Used when PSTORE_FLAGS_DMESG is set. Contains the + * kmsg_dump_reason enum value. KMSG_DUMP_UNDEF means + * "use existing kmsg_dump() filtering, based on the + * printk.always_kmsg_dump boot param" (which is either + * KMSG_DUMP_OOPS when false, or KMSG_DUMP_MAX when + * true); see printk.always_kmsg_dump for more details. * @data: backend-private pointer passed back during callbacks * * Callbacks: @@ -170,7 +176,7 @@ struct pstore_record { */ struct pstore_info { struct module *owner; - char *name; + const char *name; struct semaphore buf_lock; char *buf; @@ -179,6 +185,7 @@ struct pstore_info { struct mutex read_mutex; int flags; + int max_reason; void *data; int (*open)(struct pstore_info *psi); diff --git a/include/linux/pstore_blk.h b/include/linux/pstore_blk.h new file mode 100644 index 000000000000..61e914522b01 --- /dev/null +++ b/include/linux/pstore_blk.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PSTORE_BLK_H_ +#define __PSTORE_BLK_H_ + +#include <linux/types.h> +#include <linux/pstore.h> +#include <linux/pstore_zone.h> + +/** + * typedef pstore_blk_panic_write_op - panic write operation to block device + * + * @buf: the data to write + * @start_sect: start sector to block device + * @sects: sectors count on buf + * + * Return: On success, zero should be returned. Others excluding -ENOMSG + * mean error. -ENOMSG means to try next zone. + * + * Panic write to block device must be aligned to SECTOR_SIZE. + */ +typedef int (*pstore_blk_panic_write_op)(const char *buf, sector_t start_sect, + sector_t sects); + +/** + * struct pstore_blk_info - pstore/blk registration details + * + * @major: Which major device number to support with pstore/blk + * @flags: The supported PSTORE_FLAGS_* from linux/pstore.h. + * @panic_write:The write operation only used for the panic case. + * This can be NULL, but is recommended to avoid losing + * crash data if the kernel's IO path or work queues are + * broken during a panic. + * @devt: The dev_t that pstore/blk has attached to. + * @nr_sects: Number of sectors on @devt. + * @start_sect: Starting sector on @devt. + */ +struct pstore_blk_info { + unsigned int major; + unsigned int flags; + pstore_blk_panic_write_op panic_write; + + /* Filled in by pstore/blk after registration. */ + dev_t devt; + sector_t nr_sects; + sector_t start_sect; +}; + +int register_pstore_blk(struct pstore_blk_info *info); +void unregister_pstore_blk(unsigned int major); + +/** + * struct pstore_device_info - back-end pstore/blk driver structure. + * + * @total_size: The total size in bytes pstore/blk can use. It must be greater + * than 4096 and be multiple of 4096. + * @flags: Refer to macro starting with PSTORE_FLAGS defined in + * linux/pstore.h. It means what front-ends this device support. + * Zero means all backends for compatible. + * @read: The general read operation. Both of the function parameters + * @size and @offset are relative value to bock device (not the + * whole disk). + * On success, the number of bytes should be returned, others + * means error. + * @write: The same as @read, but the following error number: + * -EBUSY means try to write again later. + * -ENOMSG means to try next zone. + * @erase: The general erase operation for device with special removing + * job. Both of the function parameters @size and @offset are + * relative value to storage. + * Return 0 on success and others on failure. + * @panic_write:The write operation only used for panic case. It's optional + * if you do not care panic log. The parameters are relative + * value to storage. + * On success, the number of bytes should be returned, others + * excluding -ENOMSG mean error. -ENOMSG means to try next zone. + */ +struct pstore_device_info { + unsigned long total_size; + unsigned int flags; + pstore_zone_read_op read; + pstore_zone_write_op write; + pstore_zone_erase_op erase; + pstore_zone_write_op panic_write; +}; + +int register_pstore_device(struct pstore_device_info *dev); +void unregister_pstore_device(struct pstore_device_info *dev); + +/** + * struct pstore_blk_config - the pstore_blk backend configuration + * + * @device: Name of the desired block device + * @max_reason: Maximum kmsg dump reason to store to block device + * @kmsg_size: Total size of for kmsg dumps + * @pmsg_size: Total size of the pmsg storage area + * @console_size: Total size of the console storage area + * @ftrace_size: Total size for ftrace logging data (for all CPUs) + */ +struct pstore_blk_config { + char device[80]; + enum kmsg_dump_reason max_reason; + unsigned long kmsg_size; + unsigned long pmsg_size; + unsigned long console_size; + unsigned long ftrace_size; +}; + +/** + * pstore_blk_get_config - get a copy of the pstore_blk backend configuration + * + * @info: The sturct pstore_blk_config to be filled in + * + * Failure returns negative error code, and success returns 0. + */ +int pstore_blk_get_config(struct pstore_blk_config *info); + +#endif diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 9cb9b9067298..9f16afec7290 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -133,7 +133,7 @@ struct ramoops_platform_data { unsigned long console_size; unsigned long ftrace_size; unsigned long pmsg_size; - int dump_oops; + int max_reason; u32 flags; struct persistent_ram_ecc_info ecc_info; }; diff --git a/include/linux/pstore_zone.h b/include/linux/pstore_zone.h new file mode 100644 index 000000000000..1e35eaa33e5e --- /dev/null +++ b/include/linux/pstore_zone.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PSTORE_ZONE_H_ +#define __PSTORE_ZONE_H_ + +#include <linux/types.h> + +typedef ssize_t (*pstore_zone_read_op)(char *, size_t, loff_t); +typedef ssize_t (*pstore_zone_write_op)(const char *, size_t, loff_t); +typedef ssize_t (*pstore_zone_erase_op)(size_t, loff_t); +/** + * struct pstore_zone_info - pstore/zone back-end driver structure + * + * @owner: Module which is responsible for this back-end driver. + * @name: Name of the back-end driver. + * @total_size: The total size in bytes pstore/zone can use. It must be greater + * than 4096 and be multiple of 4096. + * @kmsg_size: The size of oops/panic zone. Zero means disabled, otherwise, + * it must be multiple of SECTOR_SIZE(512 Bytes). + * @max_reason: Maximum kmsg dump reason to store. + * @pmsg_size: The size of pmsg zone which is the same as @kmsg_size. + * @console_size:The size of console zone which is the same as @kmsg_size. + * @ftrace_size:The size of ftrace zone which is the same as @kmsg_size. + * @read: The general read operation. Both of the function parameters + * @size and @offset are relative value to storage. + * On success, the number of bytes should be returned, others + * mean error. + * @write: The same as @read, but the following error number: + * -EBUSY means try to write again later. + * -ENOMSG means to try next zone. + * @erase: The general erase operation for device with special removing + * job. Both of the function parameters @size and @offset are + * relative value to storage. + * Return 0 on success and others on failure. + * @panic_write:The write operation only used for panic case. It's optional + * if you do not care panic log. The parameters are relative + * value to storage. + * On success, the number of bytes should be returned, others + * excluding -ENOMSG mean error. -ENOMSG means to try next zone. + */ +struct pstore_zone_info { + struct module *owner; + const char *name; + + unsigned long total_size; + unsigned long kmsg_size; + int max_reason; + unsigned long pmsg_size; + unsigned long console_size; + unsigned long ftrace_size; + pstore_zone_read_op read; + pstore_zone_write_op write; + pstore_zone_erase_op erase; + pstore_zone_write_op panic_write; +}; + +extern int register_pstore_zone(struct pstore_zone_info *info); +extern void unregister_pstore_zone(struct pstore_zone_info *info); + +#endif diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 9a9b6156270b..14ca4d05d902 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3144,6 +3144,23 @@ EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static bool always_kmsg_dump; module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); +const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) +{ + switch (reason) { + case KMSG_DUMP_PANIC: + return "Panic"; + case KMSG_DUMP_OOPS: + return "Oops"; + case KMSG_DUMP_EMERG: + return "Emergency"; + case KMSG_DUMP_SHUTDOWN: + return "Shutdown"; + default: + return "Unknown"; + } +} +EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); + /** * kmsg_dump - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping @@ -3157,12 +3174,19 @@ void kmsg_dump(enum kmsg_dump_reason reason) struct kmsg_dumper *dumper; unsigned long flags; - if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump) - return; - rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { - if (dumper->max_reason && reason > dumper->max_reason) + enum kmsg_dump_reason max_reason = dumper->max_reason; + + /* + * If client has not provided a specific max_reason, default + * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set. + */ + if (max_reason == KMSG_DUMP_UNDEF) { + max_reason = always_kmsg_dump ? KMSG_DUMP_MAX : + KMSG_DUMP_OOPS; + } + if (reason > max_reason) continue; /* initialize iterator with data about the stored records */ diff --git a/kernel/reboot.c b/kernel/reboot.c index c4d472b7f1b4..491f1347bf43 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -250,7 +250,7 @@ void kernel_restart(char *cmd) pr_emerg("Restarting system\n"); else pr_emerg("Restarting system with command '%s'\n", cmd); - kmsg_dump(KMSG_DUMP_RESTART); + kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_restart(cmd); } EXPORT_SYMBOL_GPL(kernel_restart); @@ -274,7 +274,7 @@ void kernel_halt(void) migrate_to_reboot_cpu(); syscore_shutdown(); pr_emerg("System halted\n"); - kmsg_dump(KMSG_DUMP_HALT); + kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_halt(); } EXPORT_SYMBOL_GPL(kernel_halt); @@ -292,7 +292,7 @@ void kernel_power_off(void) migrate_to_reboot_cpu(); syscore_shutdown(); pr_emerg("Power down\n"); - kmsg_dump(KMSG_DUMP_POWEROFF); + kmsg_dump(KMSG_DUMP_SHUTDOWN); machine_power_off(); } EXPORT_SYMBOL_GPL(kernel_power_off); diff --git a/tools/testing/selftests/pstore/pstore_tests b/tools/testing/selftests/pstore/pstore_tests index 1cef54458aff..2aa9a3852a84 100755 --- a/tools/testing/selftests/pstore/pstore_tests +++ b/tools/testing/selftests/pstore/pstore_tests @@ -10,7 +10,7 @@ . ./common_tests prlog -n "Checking pstore console is registered ... " -dmesg | grep -q "console \[pstore" +dmesg | grep -Eq "console \[(pstore|${backend})" show_result $? prlog -n "Checking /dev/pmsg0 exists ... " |