diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX index e840b47613f7..bc5148757edb 100644 --- a/Documentation/block/00-INDEX +++ b/Documentation/block/00-INDEX @@ -26,3 +26,9 @@ switching-sched.txt - Switching I/O schedulers at runtime writeback_cache_control.txt - Control of volatile write back caches +mmc-max-speed.txt + - eMMC layer speed simulation, related to /sys/block/mmcblk*/ + attributes: + max_read_speed + max_write_speed + cache_size diff --git a/Documentation/block/mmc-max-speed.txt b/Documentation/block/mmc-max-speed.txt new file mode 100644 index 000000000000..3f052b9fb999 --- /dev/null +++ b/Documentation/block/mmc-max-speed.txt @@ -0,0 +1,38 @@ +eMMC Block layer simulation speed controls in /sys/block/mmcblk*/ +=============================================== + +Turned on with CONFIG_MMC_SIMULATE_MAX_SPEED which enables MMC device speed +limiting. Used to test and simulate the behavior of the system when +confronted with a slow MMC. + +Enables max_read_speed, max_write_speed and cache_size attributes and module +default parameters to control the write or read maximum KB/second speed +behaviors. + +NB: There is room for improving the algorithm for aspects tied directly to +eMMC specific behavior. For instance, wear leveling and stalls from an +exhausted erase pool. We would expect that if there was a need to provide +similar speed simulation controls to other types of block devices, aspects of +their behavior are modelled separately (e.g. head seek times, heat assist, +shingling and rotational latency). + +/sys/block/mmcblk0/max_read_speed: + +Number of KB/second reads allowed to the block device. Used to test and +simulate the behavior of the system when confronted with a slow reading MMC. +Set to 0 or "off" to place no speed limit. + +/sys/block/mmcblk0/max_write_speed: + +Number of KB/second writes allowed to the block device. Used to test and +simulate the behavior of the system when confronted with a slow writing MMC. +Set to 0 or "off" to place no speed limit. + +/sys/block/mmcblk0/cache_size: + +Number of MB of high speed memory or high speed SLC cache expected on the +eMMC device being simulated. Used to help simulate the write-back behavior +more accurately. The assumption is the cache has no delay, but draws down +in the background to the MLC/TLC primary store at the max_write_speed rate. +Any write speed delays will show up when the cache is full, or when an I/O +request to flush is issued. diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt index e15bc1a0fb98..89fd8f9a259f 100644 --- a/Documentation/device-mapper/verity.txt +++ b/Documentation/device-mapper/verity.txt @@ -18,11 +18,11 @@ Construction Parameters 0 is the original format used in the Chromium OS. The salt is appended when hashing, digests are stored continuously and - the rest of the block is padded with zeros. + the rest of the block is padded with zeroes. 1 is the current format that should be used for new devices. The salt is prepended when hashing and each digest is - padded with zeros to the power of two. + padded with zeroes to the power of two. This is the device containing data, the integrity of which needs to be @@ -79,6 +79,37 @@ restart_on_corruption not compatible with ignore_corruption and requires user space support to avoid restart loops. +ignore_zero_blocks + Do not verify blocks that are expected to contain zeroes and always return + zeroes instead. This may be useful if the partition contains unused blocks + that are not guaranteed to contain zeroes. + +use_fec_from_device + Use forward error correction (FEC) to recover from corruption if hash + verification fails. Use encoding data from the specified device. This + may be the same device where data and hash blocks reside, in which case + fec_start must be outside data and hash areas. + + If the encoding data covers additional metadata, it must be accessible + on the hash device after the hash blocks. + + Note: block sizes for data and hash devices must match. Also, if the + verity is encrypted the should be too. + +fec_roots + Number of generator roots. This equals to the number of parity bytes in + the encoding data. For example, in RS(M, N) encoding, the number of roots + is M-N. + +fec_blocks + The number of encoding data blocks on the FEC device. The block size for + the FEC device is . + +fec_start + This is the offset, in blocks, from the start of the + FEC device to the beginning of the encoding data. + + Theory of operation =================== @@ -98,6 +129,11 @@ per-block basis. This allows for a lightweight hash computation on first read into the page cache. Block hashes are stored linearly, aligned to the nearest block size. +If forward error correction (FEC) support is enabled any recovery of +corrupted data will be verified using the cryptographic hash of the +corresponding data. This is why combining error correction with +integrity checking is essential. + Hash Tree --------- diff --git a/android/configs/android-base.cfg b/android/configs/android-base.cfg index a4cffb1840d7..fa53af0c37ad 100644 --- a/android/configs/android-base.cfg +++ b/android/configs/android-base.cfg @@ -21,6 +21,7 @@ CONFIG_CGROUP_SCHED=y CONFIG_CP15_BARRIER_EMULATION=y CONFIG_DM_CRYPT=y CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y CONFIG_EMBEDDED=y CONFIG_FB=y CONFIG_HIGH_RES_TIMERS=y @@ -28,6 +29,7 @@ CONFIG_INET6_AH=y CONFIG_INET6_ESP=y CONFIG_INET6_IPCOMP=y CONFIG_INET=y +CONFIG_INET_DIAG_DESTROY=y CONFIG_INET_ESP=y CONFIG_INET_XFRM_MODE_TUNNEL=y CONFIG_IP6_NF_FILTER=y diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 4b4058db0781..66353caa35b9 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -173,7 +173,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 4c893b5189dd..232f787a088a 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -53,10 +53,10 @@ unsigned long arch_mmap_rnd(void) #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_32BIT)) - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 5c81fdd032c3..353037699512 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -146,7 +146,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int(); + rnd = get_random_long(); rnd <<= PAGE_SHIFT; if (TASK_IS_32BIT_ADDR) rnd &= 0xfffffful; @@ -174,7 +174,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) static inline unsigned long brk_rnd(void) { - unsigned long rnd = get_random_int(); + unsigned long rnd = get_random_long(); rnd = rnd << PAGE_SHIFT; /* 8MB for 32bit, 256MB for 64bit */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ef2ad2d682da..36795d1e7558 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1659,9 +1659,9 @@ static inline unsigned long brk_rnd(void) /* 8MB for 32bit, 1GB for 64bit */ if (is_32bit_task()) - rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT))); + rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT))); else - rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT))); + rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT))); return rnd << PAGE_SHIFT; } diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 0f0502e12f6c..4087705ba90f 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -59,9 +59,9 @@ unsigned long arch_mmap_rnd(void) /* 8MB for 32bit, 1GB for 64bit */ if (is_32bit_task()) - rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT)); + rnd = get_random_long() % (1<<(23-PAGE_SHIFT)); else - rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT)); + rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT)); return rnd << PAGE_SHIFT; } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index c690c8e16a96..b489e9759518 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -264,7 +264,7 @@ static unsigned long mmap_rnd(void) unsigned long rnd = 0UL; if (current->flags & PF_RANDOMIZE) { - unsigned long val = get_random_int(); + unsigned long val = get_random_long(); if (test_thread_flag(TIF_32BIT)) rnd = (val % (1UL << (23UL-PAGE_SHIFT))); else diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 96bd1e2bffaf..72bb52f93c3d 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -71,12 +71,12 @@ unsigned long arch_mmap_rnd(void) if (mmap_is_ia32()) #ifdef CONFIG_COMPAT - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); #else - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); #endif else - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index a54d810f2966..6ed8b9326629 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -35,6 +35,8 @@ #include #include +#include + #include "../base.h" #include "power.h" @@ -1412,7 +1414,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) goto Complete; data.dev = dev; - data.tsk = get_current(); + data.tsk = current; init_timer_on_stack(&timer); timer.expires = jiffies + HZ * 12; timer.function = dpm_drv_timeout; diff --git a/drivers/char/random.c b/drivers/char/random.c index d0da5d852d41..b583e5336630 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1818,6 +1818,28 @@ unsigned int get_random_int(void) } EXPORT_SYMBOL(get_random_int); +/* + * Same as get_random_int(), but returns unsigned long. + */ +unsigned long get_random_long(void) +{ + __u32 *hash; + unsigned long ret; + + if (arch_get_random_long(&ret)) + return ret; + + hash = get_cpu_var(get_random_int_hash); + + hash[0] += current->pid + jiffies + random_get_entropy(); + md5_transform(hash, random_int_secret); + ret = *(unsigned long *)hash; + put_cpu_var(get_random_int_hash); + + return ret; +} +EXPORT_SYMBOL(get_random_long); + /* * randomize_range() returns a start address such that * diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 92870cdb52d9..8efaa88329aa 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -218,7 +218,8 @@ int sensor_hub_set_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, goto done_proc; } - remaining_bytes = do_div(buffer_size, sizeof(__s32)); + remaining_bytes = buffer_size % sizeof(__s32); + buffer_size = buffer_size / sizeof(__s32); if (buffer_size) { for (i = 0; i < buffer_size; ++i) { hid_set_field(report->field[field_index], i, diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 8810c9fb981a..998bd1ec0415 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -475,6 +475,18 @@ config DM_VERITY If unsure, say N. +config DM_VERITY_FEC + bool "Verity forward error correction support" + depends on DM_VERITY + select REED_SOLOMON + select REED_SOLOMON_DEC8 + ---help--- + Add forward error correction support to dm-verity. This option + makes it possible to use pre-generated error correction data to + recover from corrupted blocks. + + If unsure, say N. + config DM_SWITCH tristate "Switch target support (EXPERIMENTAL)" depends on BLK_DEV_DM diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 02de7d19853e..d470143dcf40 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -16,6 +16,7 @@ dm-cache-mq-y += dm-cache-policy-mq.o dm-cache-smq-y += dm-cache-policy-smq.o dm-cache-cleaner-y += dm-cache-policy-cleaner.o dm-era-y += dm-era-target.o +dm-verity-y += dm-verity-target.o md-mod-y += md.o bitmap.o raid456-y += raid5.o raid5-cache.o @@ -64,3 +65,7 @@ obj-$(CONFIG_DM_REQ_CRYPT) += dm-req-crypt.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o endif + +ifeq ($(CONFIG_DM_VERITY_FEC),y) +dm-verity-objs += dm-verity-fec.o +endif diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 515f83e7d9ab..bb9b92ebbf8e 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -118,14 +118,12 @@ static void iot_io_end(struct io_tracker *iot, sector_t len) */ struct dm_hook_info { bio_end_io_t *bi_end_io; - void *bi_private; }; static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio, bio_end_io_t *bi_end_io, void *bi_private) { h->bi_end_io = bio->bi_end_io; - h->bi_private = bio->bi_private; bio->bi_end_io = bi_end_io; bio->bi_private = bi_private; @@ -134,7 +132,6 @@ static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio, static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio) { bio->bi_end_io = h->bi_end_io; - bio->bi_private = h->bi_private; } /*----------------------------------------------------------------*/ diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 3147c8d09ea8..e85bcae50f65 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1864,16 +1864,24 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ret = -ENOMEM; - cc->io_queue = alloc_workqueue("kcryptd_io", WQ_MEM_RECLAIM, 1); + cc->io_queue = alloc_workqueue("kcryptd_io", + WQ_HIGHPRI | + WQ_MEM_RECLAIM, + 1); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; } if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1); + cc->crypt_queue = alloc_workqueue("kcryptd", + WQ_HIGHPRI | + WQ_MEM_RECLAIM, 1); else - cc->crypt_queue = alloc_workqueue("kcryptd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, + cc->crypt_queue = alloc_workqueue("kcryptd", + WQ_HIGHPRI | + WQ_MEM_RECLAIM | + WQ_UNBOUND, num_online_cpus()); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index e108deebbaaa..e4d1bafe78c1 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -207,7 +207,6 @@ struct dm_snap_pending_exception { */ struct bio *full_bio; bio_end_io_t *full_bio_end_io; - void *full_bio_private; }; /* @@ -1495,10 +1494,8 @@ out: snapshot_bios = bio_list_get(&pe->snapshot_bios); origin_bios = bio_list_get(&pe->origin_bios); full_bio = pe->full_bio; - if (full_bio) { + if (full_bio) full_bio->bi_end_io = pe->full_bio_end_io; - full_bio->bi_private = pe->full_bio_private; - } increment_pending_exceptions_done_count(); up_write(&s->lock); @@ -1604,7 +1601,6 @@ static void start_full_bio(struct dm_snap_pending_exception *pe, pe->full_bio = bio; pe->full_bio_end_io = bio->bi_end_io; - pe->full_bio_private = bio->bi_private; callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client, copy_callback, pe); diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c new file mode 100644 index 000000000000..ad10d6d8ed28 --- /dev/null +++ b/drivers/md/dm-verity-fec.c @@ -0,0 +1,861 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * Author: Sami Tolvanen + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +#include "dm-verity-fec.h" +#include +#include + +#define DM_MSG_PREFIX "verity-fec" + +/* + * If error correction has been configured, returns true. + */ +bool verity_fec_is_enabled(struct dm_verity *v) +{ + return v->fec && v->fec->dev; +} + +/* + * Return a pointer to dm_verity_fec_io after dm_verity_io and its variable + * length fields. + */ +static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io) +{ + return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io); +} + +/* + * Return an interleaved offset for a byte in RS block. + */ +static inline u64 fec_interleave(struct dm_verity *v, u64 offset) +{ + u32 mod; + + mod = do_div(offset, v->fec->rsn); + return offset + mod * (v->fec->rounds << v->data_dev_block_bits); +} + +/* + * Decode an RS block using Reed-Solomon. + */ +static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, + u8 *data, u8 *fec, int neras) +{ + int i; + uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; + + for (i = 0; i < v->fec->roots; i++) + par[i] = fec[i]; + + return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras, + fio->erasures, 0, NULL); +} + +/* + * Read error-correcting codes for the requested RS block. Returns a pointer + * to the data block. Caller is responsible for releasing buf. + */ +static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, + unsigned *offset, struct dm_buffer **buf) +{ + u64 position, block; + u8 *res; + + position = (index + rsb) * v->fec->roots; + block = position >> v->data_dev_block_bits; + *offset = (unsigned)(position - (block << v->data_dev_block_bits)); + + res = dm_bufio_read(v->fec->bufio, v->fec->start + block, buf); + if (unlikely(IS_ERR(res))) { + DMERR("%s: FEC %llu: parity read failed (block %llu): %ld", + v->data_dev->name, (unsigned long long)rsb, + (unsigned long long)(v->fec->start + block), + PTR_ERR(res)); + *buf = NULL; + } + + return res; +} + +/* Loop over each preallocated buffer slot. */ +#define fec_for_each_prealloc_buffer(__i) \ + for (__i = 0; __i < DM_VERITY_FEC_BUF_PREALLOC; __i++) + +/* Loop over each extra buffer slot. */ +#define fec_for_each_extra_buffer(io, __i) \ + for (__i = DM_VERITY_FEC_BUF_PREALLOC; __i < DM_VERITY_FEC_BUF_MAX; __i++) + +/* Loop over each allocated buffer. */ +#define fec_for_each_buffer(io, __i) \ + for (__i = 0; __i < (io)->nbufs; __i++) + +/* Loop over each RS block in each allocated buffer. */ +#define fec_for_each_buffer_rs_block(io, __i, __j) \ + fec_for_each_buffer(io, __i) \ + for (__j = 0; __j < 1 << DM_VERITY_FEC_BUF_RS_BITS; __j++) + +/* + * Return a pointer to the current RS block when called inside + * fec_for_each_buffer_rs_block. + */ +static inline u8 *fec_buffer_rs_block(struct dm_verity *v, + struct dm_verity_fec_io *fio, + unsigned i, unsigned j) +{ + return &fio->bufs[i][j * v->fec->rsn]; +} + +/* + * Return an index to the current RS block when called inside + * fec_for_each_buffer_rs_block. + */ +static inline unsigned fec_buffer_rs_index(unsigned i, unsigned j) +{ + return (i << DM_VERITY_FEC_BUF_RS_BITS) + j; +} + +/* + * Decode all RS blocks from buffers and copy corrected bytes into fio->output + * starting from block_offset. + */ +static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio, + u64 rsb, int byte_index, unsigned block_offset, + int neras) +{ + int r, corrected = 0, res; + struct dm_buffer *buf; + unsigned n, i, offset; + u8 *par, *block; + + par = fec_read_parity(v, rsb, block_offset, &offset, &buf); + if (IS_ERR(par)) + return PTR_ERR(par); + + /* + * Decode the RS blocks we have in bufs. Each RS block results in + * one corrected target byte and consumes fec->roots parity bytes. + */ + fec_for_each_buffer_rs_block(fio, n, i) { + block = fec_buffer_rs_block(v, fio, n, i); + res = fec_decode_rs8(v, fio, block, &par[offset], neras); + if (res < 0) { + dm_bufio_release(buf); + + r = res; + goto error; + } + + corrected += res; + fio->output[block_offset] = block[byte_index]; + + block_offset++; + if (block_offset >= 1 << v->data_dev_block_bits) + goto done; + + /* read the next block when we run out of parity bytes */ + offset += v->fec->roots; + if (offset >= 1 << v->data_dev_block_bits) { + dm_bufio_release(buf); + + par = fec_read_parity(v, rsb, block_offset, &offset, &buf); + if (unlikely(IS_ERR(par))) + return PTR_ERR(par); + } + } +done: + r = corrected; +error: + if (r < 0 && neras) + DMERR_LIMIT("%s: FEC %llu: failed to correct: %d", + v->data_dev->name, (unsigned long long)rsb, r); + else if (r > 0) { + DMWARN_LIMIT("%s: FEC %llu: corrected %d errors", + v->data_dev->name, (unsigned long long)rsb, r); + atomic_add_unless(&v->fec->corrected, 1, INT_MAX); + } + + return r; +} + +/* + * Locate data block erasures using verity hashes. + */ +static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io, + u8 *want_digest, u8 *data) +{ + if (unlikely(verity_hash(v, verity_io_hash_desc(v, io), + data, 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io)))) + return 0; + + return memcmp(verity_io_real_digest(v, io), want_digest, + v->digest_size) != 0; +} + +/* + * Read data blocks that are part of the RS block and deinterleave as much as + * fits into buffers. Check for erasure locations if @neras is non-NULL. + */ +static int fec_read_bufs(struct dm_verity *v, struct dm_verity_io *io, + u64 rsb, u64 target, unsigned block_offset, + int *neras) +{ + bool is_zero; + int i, j, target_index = -1; + struct dm_buffer *buf; + struct dm_bufio_client *bufio; + struct dm_verity_fec_io *fio = fec_io(io); + u64 block, ileaved; + u8 *bbuf, *rs_block; + u8 want_digest[v->digest_size]; + unsigned n, k; + + if (neras) + *neras = 0; + + /* + * read each of the rsn data blocks that are part of the RS block, and + * interleave contents to available bufs + */ + for (i = 0; i < v->fec->rsn; i++) { + ileaved = fec_interleave(v, rsb * v->fec->rsn + i); + + /* + * target is the data block we want to correct, target_index is + * the index of this block within the rsn RS blocks + */ + if (ileaved == target) + target_index = i; + + block = ileaved >> v->data_dev_block_bits; + bufio = v->fec->data_bufio; + + if (block >= v->data_blocks) { + block -= v->data_blocks; + + /* + * blocks outside the area were assumed to contain + * zeros when encoding data was generated + */ + if (unlikely(block >= v->fec->hash_blocks)) + continue; + + block += v->hash_start; + bufio = v->bufio; + } + + bbuf = dm_bufio_read(bufio, block, &buf); + if (unlikely(IS_ERR(bbuf))) { + DMWARN_LIMIT("%s: FEC %llu: read failed (%llu): %ld", + v->data_dev->name, + (unsigned long long)rsb, + (unsigned long long)block, PTR_ERR(bbuf)); + + /* assume the block is corrupted */ + if (neras && *neras <= v->fec->roots) + fio->erasures[(*neras)++] = i; + + continue; + } + + /* locate erasures if the block is on the data device */ + if (bufio == v->fec->data_bufio && + verity_hash_for_block(v, io, block, want_digest, + &is_zero) == 0) { + /* skip known zero blocks entirely */ + if (is_zero) + continue; + + /* + * skip if we have already found the theoretical + * maximum number (i.e. fec->roots) of erasures + */ + if (neras && *neras <= v->fec->roots && + fec_is_erasure(v, io, want_digest, bbuf)) + fio->erasures[(*neras)++] = i; + } + + /* + * deinterleave and copy the bytes that fit into bufs, + * starting from block_offset + */ + fec_for_each_buffer_rs_block(fio, n, j) { + k = fec_buffer_rs_index(n, j) + block_offset; + + if (k >= 1 << v->data_dev_block_bits) + goto done; + + rs_block = fec_buffer_rs_block(v, fio, n, j); + rs_block[i] = bbuf[k]; + } +done: + dm_bufio_release(buf); + } + + return target_index; +} + +/* + * Allocate RS control structure and FEC buffers from preallocated mempools, + * and attempt to allocate as many extra buffers as available. + */ +static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) +{ + unsigned n; + + if (!fio->rs) { + fio->rs = mempool_alloc(v->fec->rs_pool, 0); + if (unlikely(!fio->rs)) { + DMERR("failed to allocate RS"); + return -ENOMEM; + } + } + + fec_for_each_prealloc_buffer(n) { + if (fio->bufs[n]) + continue; + + fio->bufs[n] = mempool_alloc(v->fec->prealloc_pool, GFP_NOIO); + if (unlikely(!fio->bufs[n])) { + DMERR("failed to allocate FEC buffer"); + return -ENOMEM; + } + } + + /* try to allocate the maximum number of buffers */ + fec_for_each_extra_buffer(fio, n) { + if (fio->bufs[n]) + continue; + + fio->bufs[n] = mempool_alloc(v->fec->extra_pool, GFP_NOIO); + /* we can manage with even one buffer if necessary */ + if (unlikely(!fio->bufs[n])) + break; + } + fio->nbufs = n; + + if (!fio->output) { + fio->output = mempool_alloc(v->fec->output_pool, GFP_NOIO); + + if (!fio->output) { + DMERR("failed to allocate FEC page"); + return -ENOMEM; + } + } + + return 0; +} + +/* + * Initialize buffers and clear erasures. fec_read_bufs() assumes buffers are + * zeroed before deinterleaving. + */ +static void fec_init_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) +{ + unsigned n; + + fec_for_each_buffer(fio, n) + memset(fio->bufs[n], 0, v->fec->rsn << DM_VERITY_FEC_BUF_RS_BITS); + + memset(fio->erasures, 0, sizeof(fio->erasures)); +} + +/* + * Decode all RS blocks in a single data block and return the target block + * (indicated by @offset) in fio->output. If @use_erasures is non-zero, uses + * hashes to locate erasures. + */ +static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, + struct dm_verity_fec_io *fio, u64 rsb, u64 offset, + bool use_erasures) +{ + int r, neras = 0; + unsigned pos; + + r = fec_alloc_bufs(v, fio); + if (unlikely(r < 0)) + return r; + + for (pos = 0; pos < 1 << v->data_dev_block_bits; ) { + fec_init_bufs(v, fio); + + r = fec_read_bufs(v, io, rsb, offset, pos, + use_erasures ? &neras : NULL); + if (unlikely(r < 0)) + return r; + + r = fec_decode_bufs(v, fio, rsb, r, pos, neras); + if (r < 0) + return r; + + pos += fio->nbufs << DM_VERITY_FEC_BUF_RS_BITS; + } + + /* Always re-validate the corrected block against the expected hash */ + r = verity_hash(v, verity_io_hash_desc(v, io), fio->output, + 1 << v->data_dev_block_bits, + verity_io_real_digest(v, io)); + if (unlikely(r < 0)) + return r; + + if (memcmp(verity_io_real_digest(v, io), verity_io_want_digest(v, io), + v->digest_size)) { + DMERR_LIMIT("%s: FEC %llu: failed to correct (%d erasures)", + v->data_dev->name, (unsigned long long)rsb, neras); + return -EILSEQ; + } + + return 0; +} + +static int fec_bv_copy(struct dm_verity *v, struct dm_verity_io *io, u8 *data, + size_t len) +{ + struct dm_verity_fec_io *fio = fec_io(io); + + memcpy(data, &fio->output[fio->output_pos], len); + fio->output_pos += len; + + return 0; +} + +/* + * Correct errors in a block. Copies corrected block to dest if non-NULL, + * otherwise to a bio_vec starting from iter. + */ +int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, + enum verity_block_type type, sector_t block, u8 *dest, + struct bvec_iter *iter) +{ + int r; + struct dm_verity_fec_io *fio = fec_io(io); + u64 offset, res, rsb; + + if (!verity_fec_is_enabled(v)) + return -EOPNOTSUPP; + + if (type == DM_VERITY_BLOCK_TYPE_METADATA) + block += v->data_blocks; + + /* + * For RS(M, N), the continuous FEC data is divided into blocks of N + * bytes. Since block size may not be divisible by N, the last block + * is zero padded when decoding. + * + * Each byte of the block is covered by a different RS(M, N) code, + * and each code is interleaved over N blocks to make it less likely + * that bursty corruption will leave us in unrecoverable state. + */ + + offset = block << v->data_dev_block_bits; + + res = offset; + div64_u64(res, v->fec->rounds << v->data_dev_block_bits); + + /* + * The base RS block we can feed to the interleaver to find out all + * blocks required for decoding. + */ + rsb = offset - res * (v->fec->rounds << v->data_dev_block_bits); + + /* + * Locating erasures is slow, so attempt to recover the block without + * them first. Do a second attempt with erasures if the corruption is + * bad enough. + */ + r = fec_decode_rsb(v, io, fio, rsb, offset, false); + if (r < 0) { + r = fec_decode_rsb(v, io, fio, rsb, offset, true); + if (r < 0) + return r; + } + + if (dest) + memcpy(dest, fio->output, 1 << v->data_dev_block_bits); + else if (iter) { + fio->output_pos = 0; + r = verity_for_bv_block(v, io, iter, fec_bv_copy); + } + + return r; +} + +/* + * Clean up per-bio data. + */ +void verity_fec_finish_io(struct dm_verity_io *io) +{ + unsigned n; + struct dm_verity_fec *f = io->v->fec; + struct dm_verity_fec_io *fio = fec_io(io); + + if (!verity_fec_is_enabled(io->v)) + return; + + mempool_free(fio->rs, f->rs_pool); + + fec_for_each_prealloc_buffer(n) + mempool_free(fio->bufs[n], f->prealloc_pool); + + fec_for_each_extra_buffer(fio, n) + mempool_free(fio->bufs[n], f->extra_pool); + + mempool_free(fio->output, f->output_pool); +} + +/* + * Initialize per-bio data. + */ +void verity_fec_init_io(struct dm_verity_io *io) +{ + struct dm_verity_fec_io *fio = fec_io(io); + + if (!verity_fec_is_enabled(io->v)) + return; + + fio->rs = NULL; + memset(fio->bufs, 0, sizeof(fio->bufs)); + fio->nbufs = 0; + fio->output = NULL; +} + +/* + * Append feature arguments and values to the status table. + */ +unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, + char *result, unsigned maxlen) +{ + if (!verity_fec_is_enabled(v)) + return sz; + + DMEMIT(" " DM_VERITY_OPT_FEC_DEV " %s " + DM_VERITY_OPT_FEC_BLOCKS " %llu " + DM_VERITY_OPT_FEC_START " %llu " + DM_VERITY_OPT_FEC_ROOTS " %d", + v->fec->dev->name, + (unsigned long long)v->fec->blocks, + (unsigned long long)v->fec->start, + v->fec->roots); + + return sz; +} + +void verity_fec_dtr(struct dm_verity *v) +{ + struct dm_verity_fec *f = v->fec; + struct kobject *kobj = &f->kobj_holder.kobj; + + if (!verity_fec_is_enabled(v)) + goto out; + + mempool_destroy(f->rs_pool); + mempool_destroy(f->prealloc_pool); + mempool_destroy(f->extra_pool); + kmem_cache_destroy(f->cache); + + if (f->data_bufio) + dm_bufio_client_destroy(f->data_bufio); + if (f->bufio) + dm_bufio_client_destroy(f->bufio); + + if (f->dev) + dm_put_device(v->ti, f->dev); + + if (kobj->state_initialized) { + kobject_put(kobj); + wait_for_completion(dm_get_completion_from_kobject(kobj)); + } + +out: + kfree(f); + v->fec = NULL; +} + +static void *fec_rs_alloc(gfp_t gfp_mask, void *pool_data) +{ + struct dm_verity *v = (struct dm_verity *)pool_data; + + return init_rs(8, 0x11d, 0, 1, v->fec->roots); +} + +static void fec_rs_free(void *element, void *pool_data) +{ + struct rs_control *rs = (struct rs_control *)element; + + if (rs) + free_rs(rs); +} + +bool verity_is_fec_opt_arg(const char *arg_name) +{ + return (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_START) || + !strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)); +} + +int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, + unsigned *argc, const char *arg_name) +{ + int r; + struct dm_target *ti = v->ti; + const char *arg_value; + unsigned long long num_ll; + unsigned char num_c; + char dummy; + + if (!*argc) { + ti->error = "FEC feature arguments require a value"; + return -EINVAL; + } + + arg_value = dm_shift_arg(as); + (*argc)--; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_DEV)) { + r = dm_get_device(ti, arg_value, FMODE_READ, &v->fec->dev); + if (r) { + ti->error = "FEC device lookup failed"; + return r; + } + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_BLOCKS)) { + if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 || + ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) + >> (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + v->fec->blocks = num_ll; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_START)) { + if (sscanf(arg_value, "%llu%c", &num_ll, &dummy) != 1 || + ((sector_t)(num_ll << (v->data_dev_block_bits - SECTOR_SHIFT)) >> + (v->data_dev_block_bits - SECTOR_SHIFT) != num_ll)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_START; + return -EINVAL; + } + v->fec->start = num_ll; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_FEC_ROOTS)) { + if (sscanf(arg_value, "%hhu%c", &num_c, &dummy) != 1 || !num_c || + num_c < (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MAX_RSN) || + num_c > (DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN)) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_ROOTS; + return -EINVAL; + } + v->fec->roots = num_c; + + } else { + ti->error = "Unrecognized verity FEC feature request"; + return -EINVAL; + } + + return 0; +} + +static ssize_t corrected_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct dm_verity_fec *f = container_of(kobj, struct dm_verity_fec, + kobj_holder.kobj); + + return sprintf(buf, "%d\n", atomic_read(&f->corrected)); +} + +static struct kobj_attribute attr_corrected = __ATTR_RO(corrected); + +static struct attribute *fec_attrs[] = { + &attr_corrected.attr, + NULL +}; + +static struct kobj_type fec_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = fec_attrs +}; + +/* + * Allocate dm_verity_fec for v->fec. Must be called before verity_fec_ctr. + */ +int verity_fec_ctr_alloc(struct dm_verity *v) +{ + struct dm_verity_fec *f; + + f = kzalloc(sizeof(struct dm_verity_fec), GFP_KERNEL); + if (!f) { + v->ti->error = "Cannot allocate FEC structure"; + return -ENOMEM; + } + v->fec = f; + + return 0; +} + +/* + * Validate arguments and preallocate memory. Must be called after arguments + * have been parsed using verity_fec_parse_opt_args. + */ +int verity_fec_ctr(struct dm_verity *v) +{ + int r; + struct dm_verity_fec *f = v->fec; + struct dm_target *ti = v->ti; + struct mapped_device *md = dm_table_get_md(ti->table); + u64 hash_blocks; + + if (!verity_fec_is_enabled(v)) { + verity_fec_dtr(v); + return 0; + } + + /* Create a kobject and sysfs attributes */ + init_completion(&f->kobj_holder.completion); + + r = kobject_init_and_add(&f->kobj_holder.kobj, &fec_ktype, + &disk_to_dev(dm_disk(md))->kobj, "%s", "fec"); + if (r) { + ti->error = "Cannot create kobject"; + return r; + } + + /* + * FEC is computed over data blocks, possible metadata, and + * hash blocks. In other words, FEC covers total of fec_blocks + * blocks consisting of the following: + * + * data blocks | hash blocks | metadata (optional) + * + * We allow metadata after hash blocks to support a use case + * where all data is stored on the same device and FEC covers + * the entire area. + * + * If metadata is included, we require it to be available on the + * hash device after the hash blocks. + */ + + hash_blocks = v->hash_blocks - v->hash_start; + + /* + * Require matching block sizes for data and hash devices for + * simplicity. + */ + if (v->data_dev_block_bits != v->hash_dev_block_bits) { + ti->error = "Block sizes must match to use FEC"; + return -EINVAL; + } + + if (!f->roots) { + ti->error = "Missing " DM_VERITY_OPT_FEC_ROOTS; + return -EINVAL; + } + f->rsn = DM_VERITY_FEC_RSM - f->roots; + + if (!f->blocks) { + ti->error = "Missing " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + + f->rounds = f->blocks; + if (sector_div(f->rounds, f->rsn)) + f->rounds++; + + /* + * Due to optional metadata, f->blocks can be larger than + * data_blocks and hash_blocks combined. + */ + if (f->blocks < v->data_blocks + hash_blocks || !f->rounds) { + ti->error = "Invalid " DM_VERITY_OPT_FEC_BLOCKS; + return -EINVAL; + } + + /* + * Metadata is accessed through the hash device, so we require + * it to be large enough. + */ + f->hash_blocks = f->blocks - v->data_blocks; + if (dm_bufio_get_device_size(v->bufio) < f->hash_blocks) { + ti->error = "Hash device is too small for " + DM_VERITY_OPT_FEC_BLOCKS; + return -E2BIG; + } + + f->bufio = dm_bufio_client_create(f->dev->bdev, + 1 << v->data_dev_block_bits, + 1, 0, NULL, NULL); + if (IS_ERR(f->bufio)) { + ti->error = "Cannot initialize FEC bufio client"; + return PTR_ERR(f->bufio); + } + + if (dm_bufio_get_device_size(f->bufio) < + ((f->start + f->rounds * f->roots) >> v->data_dev_block_bits)) { + ti->error = "FEC device is too small"; + return -E2BIG; + } + + f->data_bufio = dm_bufio_client_create(v->data_dev->bdev, + 1 << v->data_dev_block_bits, + 1, 0, NULL, NULL); + if (IS_ERR(f->data_bufio)) { + ti->error = "Cannot initialize FEC data bufio client"; + return PTR_ERR(f->data_bufio); + } + + if (dm_bufio_get_device_size(f->data_bufio) < v->data_blocks) { + ti->error = "Data device is too small"; + return -E2BIG; + } + + /* Preallocate an rs_control structure for each worker thread */ + f->rs_pool = mempool_create(num_online_cpus(), fec_rs_alloc, + fec_rs_free, (void *) v); + if (!f->rs_pool) { + ti->error = "Cannot allocate RS pool"; + return -ENOMEM; + } + + f->cache = kmem_cache_create("dm_verity_fec_buffers", + f->rsn << DM_VERITY_FEC_BUF_RS_BITS, + 0, 0, NULL); + if (!f->cache) { + ti->error = "Cannot create FEC buffer cache"; + return -ENOMEM; + } + + /* Preallocate DM_VERITY_FEC_BUF_PREALLOC buffers for each thread */ + f->prealloc_pool = mempool_create_slab_pool(num_online_cpus() * + DM_VERITY_FEC_BUF_PREALLOC, + f->cache); + if (!f->prealloc_pool) { + ti->error = "Cannot allocate FEC buffer prealloc pool"; + return -ENOMEM; + } + + f->extra_pool = mempool_create_slab_pool(0, f->cache); + if (!f->extra_pool) { + ti->error = "Cannot allocate FEC buffer extra pool"; + return -ENOMEM; + } + + /* Preallocate an output buffer for each thread */ + f->output_pool = mempool_create_kmalloc_pool(num_online_cpus(), + 1 << v->data_dev_block_bits); + if (!f->output_pool) { + ti->error = "Cannot allocate FEC output pool"; + return -ENOMEM; + } + + /* Reserve space for our per-bio data */ + ti->per_bio_data_size += sizeof(struct dm_verity_fec_io); + + return 0; +} diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h new file mode 100644 index 000000000000..8c4bee052a73 --- /dev/null +++ b/drivers/md/dm-verity-fec.h @@ -0,0 +1,155 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * Author: Sami Tolvanen + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +#ifndef DM_VERITY_FEC_H +#define DM_VERITY_FEC_H + +#include "dm.h" +#include "dm-verity.h" +#include + +/* Reed-Solomon(M, N) parameters */ +#define DM_VERITY_FEC_RSM 255 +#define DM_VERITY_FEC_MAX_RSN 253 +#define DM_VERITY_FEC_MIN_RSN 231 /* ~10% space overhead */ + +/* buffers for deinterleaving and decoding */ +#define DM_VERITY_FEC_BUF_PREALLOC 1 /* buffers to preallocate */ +#define DM_VERITY_FEC_BUF_RS_BITS 4 /* 1 << RS blocks per buffer */ +/* we need buffers for at most 1 << block size RS blocks */ +#define DM_VERITY_FEC_BUF_MAX \ + (1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS)) + +#define DM_VERITY_OPT_FEC_DEV "use_fec_from_device" +#define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks" +#define DM_VERITY_OPT_FEC_START "fec_start" +#define DM_VERITY_OPT_FEC_ROOTS "fec_roots" + +/* configuration */ +struct dm_verity_fec { + struct dm_dev *dev; /* parity data device */ + struct dm_bufio_client *data_bufio; /* for data dev access */ + struct dm_bufio_client *bufio; /* for parity data access */ + sector_t start; /* parity data start in blocks */ + sector_t blocks; /* number of blocks covered */ + sector_t rounds; /* number of interleaving rounds */ + sector_t hash_blocks; /* blocks covered after v->hash_start */ + unsigned char roots; /* number of parity bytes, M-N of RS(M, N) */ + unsigned char rsn; /* N of RS(M, N) */ + mempool_t *rs_pool; /* mempool for fio->rs */ + mempool_t *prealloc_pool; /* mempool for preallocated buffers */ + mempool_t *extra_pool; /* mempool for extra buffers */ + mempool_t *output_pool; /* mempool for output */ + struct kmem_cache *cache; /* cache for buffers */ + atomic_t corrected; /* corrected errors */ + struct dm_kobject_holder kobj_holder; /* for sysfs attributes */ +}; + +/* per-bio data */ +struct dm_verity_fec_io { + struct rs_control *rs; /* Reed-Solomon state */ + int erasures[DM_VERITY_FEC_MAX_RSN]; /* erasures for decode_rs8 */ + u8 *bufs[DM_VERITY_FEC_BUF_MAX]; /* bufs for deinterleaving */ + unsigned nbufs; /* number of buffers allocated */ + u8 *output; /* buffer for corrected output */ + size_t output_pos; +}; + +#ifdef CONFIG_DM_VERITY_FEC + +/* each feature parameter requires a value */ +#define DM_VERITY_OPTS_FEC 8 + +extern bool verity_fec_is_enabled(struct dm_verity *v); + +extern int verity_fec_decode(struct dm_verity *v, struct dm_verity_io *io, + enum verity_block_type type, sector_t block, + u8 *dest, struct bvec_iter *iter); + +extern unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, + char *result, unsigned maxlen); + +extern void verity_fec_finish_io(struct dm_verity_io *io); +extern void verity_fec_init_io(struct dm_verity_io *io); + +extern bool verity_is_fec_opt_arg(const char *arg_name); +extern int verity_fec_parse_opt_args(struct dm_arg_set *as, + struct dm_verity *v, unsigned *argc, + const char *arg_name); + +extern void verity_fec_dtr(struct dm_verity *v); + +extern int verity_fec_ctr_alloc(struct dm_verity *v); +extern int verity_fec_ctr(struct dm_verity *v); + +#else /* !CONFIG_DM_VERITY_FEC */ + +#define DM_VERITY_OPTS_FEC 0 + +static inline bool verity_fec_is_enabled(struct dm_verity *v) +{ + return false; +} + +static inline int verity_fec_decode(struct dm_verity *v, + struct dm_verity_io *io, + enum verity_block_type type, + sector_t block, u8 *dest, + struct bvec_iter *iter) +{ + return -EOPNOTSUPP; +} + +static inline unsigned verity_fec_status_table(struct dm_verity *v, + unsigned sz, char *result, + unsigned maxlen) +{ + return sz; +} + +static inline void verity_fec_finish_io(struct dm_verity_io *io) +{ +} + +static inline void verity_fec_init_io(struct dm_verity_io *io) +{ +} + +static inline bool verity_is_fec_opt_arg(const char *arg_name) +{ + return false; +} + +static inline int verity_fec_parse_opt_args(struct dm_arg_set *as, + struct dm_verity *v, + unsigned *argc, + const char *arg_name) +{ + return -EINVAL; +} + +static inline void verity_fec_dtr(struct dm_verity *v) +{ +} + +static inline int verity_fec_ctr_alloc(struct dm_verity *v) +{ + return 0; +} + +static inline int verity_fec_ctr(struct dm_verity *v) +{ + return 0; +} + +#endif /* CONFIG_DM_VERITY_FEC */ + +#endif /* DM_VERITY_FEC_H */ diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity-target.c similarity index 69% rename from drivers/md/dm-verity.c rename to drivers/md/dm-verity-target.c index ccf41886ebcf..5c5d30cb6ec5 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity-target.c @@ -14,12 +14,11 @@ * access behavior. */ -#include "dm-bufio.h" +#include "dm-verity.h" +#include "dm-verity-fec.h" #include -#include #include -#include #define DM_MSG_PREFIX "verity" @@ -28,83 +27,18 @@ #define DM_VERITY_DEFAULT_PREFETCH_SIZE 262144 -#define DM_VERITY_MAX_LEVELS 63 #define DM_VERITY_MAX_CORRUPTED_ERRS 100 #define DM_VERITY_OPT_LOGGING "ignore_corruption" #define DM_VERITY_OPT_RESTART "restart_on_corruption" +#define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks" + +#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC) static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR); -enum verity_mode { - DM_VERITY_MODE_EIO, - DM_VERITY_MODE_LOGGING, - DM_VERITY_MODE_RESTART -}; - -enum verity_block_type { - DM_VERITY_BLOCK_TYPE_DATA, - DM_VERITY_BLOCK_TYPE_METADATA -}; - -struct dm_verity { - struct dm_dev *data_dev; - struct dm_dev *hash_dev; - struct dm_target *ti; - struct dm_bufio_client *bufio; - char *alg_name; - struct crypto_shash *tfm; - u8 *root_digest; /* digest of the root block */ - u8 *salt; /* salt: its size is salt_size */ - unsigned salt_size; - sector_t data_start; /* data offset in 512-byte sectors */ - sector_t hash_start; /* hash start in blocks */ - sector_t data_blocks; /* the number of data blocks */ - sector_t hash_blocks; /* the number of hash blocks */ - unsigned char data_dev_block_bits; /* log2(data blocksize) */ - unsigned char hash_dev_block_bits; /* log2(hash blocksize) */ - unsigned char hash_per_block_bits; /* log2(hashes in hash block) */ - unsigned char levels; /* the number of tree levels */ - unsigned char version; - unsigned digest_size; /* digest size for the current hash algorithm */ - unsigned shash_descsize;/* the size of temporary space for crypto */ - int hash_failed; /* set to 1 if hash of any block failed */ - enum verity_mode mode; /* mode for handling verification errors */ - unsigned corrupted_errs;/* Number of errors for corrupted blocks */ - - struct workqueue_struct *verify_wq; - - /* starting blocks for each tree level. 0 is the lowest level. */ - sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; -}; - -struct dm_verity_io { - struct dm_verity *v; - - /* original values of bio->bi_end_io and bio->bi_private */ - bio_end_io_t *orig_bi_end_io; - void *orig_bi_private; - - sector_t block; - unsigned n_blocks; - - struct bvec_iter iter; - - struct work_struct work; - - /* - * Three variably-size fields follow this struct: - * - * u8 hash_desc[v->shash_descsize]; - * u8 real_digest[v->digest_size]; - * u8 want_digest[v->digest_size]; - * - * To access them use: io_hash_desc(), io_real_digest() and io_want_digest(). - */ -}; - struct dm_verity_prefetch_work { struct work_struct work; struct dm_verity *v; @@ -112,21 +46,6 @@ struct dm_verity_prefetch_work { unsigned n_blocks; }; -static struct shash_desc *io_hash_desc(struct dm_verity *v, struct dm_verity_io *io) -{ - return (struct shash_desc *)(io + 1); -} - -static u8 *io_real_digest(struct dm_verity *v, struct dm_verity_io *io) -{ - return (u8 *)(io + 1) + v->shash_descsize; -} - -static u8 *io_want_digest(struct dm_verity *v, struct dm_verity_io *io) -{ - return (u8 *)(io + 1) + v->shash_descsize + v->digest_size; -} - /* * Auxiliary structure appended to each dm-bufio buffer. If the value * hash_verified is nonzero, hash of the block has been verified. @@ -173,6 +92,84 @@ static sector_t verity_position_at_level(struct dm_verity *v, sector_t block, return block >> (level * v->hash_per_block_bits); } +/* + * Wrapper for crypto_shash_init, which handles verity salting. + */ +static int verity_hash_init(struct dm_verity *v, struct shash_desc *desc) +{ + int r; + + desc->tfm = v->tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + r = crypto_shash_init(desc); + + if (unlikely(r < 0)) { + DMERR("crypto_shash_init failed: %d", r); + return r; + } + + if (likely(v->version >= 1)) { + r = crypto_shash_update(desc, v->salt, v->salt_size); + + if (unlikely(r < 0)) { + DMERR("crypto_shash_update failed: %d", r); + return r; + } + } + + return 0; +} + +static int verity_hash_update(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len) +{ + int r = crypto_shash_update(desc, data, len); + + if (unlikely(r < 0)) + DMERR("crypto_shash_update failed: %d", r); + + return r; +} + +static int verity_hash_final(struct dm_verity *v, struct shash_desc *desc, + u8 *digest) +{ + int r; + + if (unlikely(!v->version)) { + r = crypto_shash_update(desc, v->salt, v->salt_size); + + if (r < 0) { + DMERR("crypto_shash_update failed: %d", r); + return r; + } + } + + r = crypto_shash_final(desc, digest); + + if (unlikely(r < 0)) + DMERR("crypto_shash_final failed: %d", r); + + return r; +} + +int verity_hash(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len, u8 *digest) +{ + int r; + + r = verity_hash_init(v, desc); + if (unlikely(r < 0)) + return r; + + r = verity_hash_update(v, desc, data, len); + if (unlikely(r < 0)) + return r; + + return verity_hash_final(v, desc, digest); +} + static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level, sector_t *hash_block, unsigned *offset) { @@ -246,17 +243,17 @@ out: * Verify hash of a metadata block pertaining to the specified data block * ("block" argument) at a specified level ("level" argument). * - * On successful return, io_want_digest(v, io) contains the hash value for - * a lower tree level or for the data block (if we're at the lowest leve). + * On successful return, verity_io_want_digest(v, io) contains the hash value + * for a lower tree level or for the data block (if we're at the lowest level). * * If "skip_unverified" is true, unverified buffer is skipped and 1 is returned. * If "skip_unverified" is false, unverified buffer is hashed and verified - * against current value of io_want_digest(v, io). + * against current value of verity_io_want_digest(v, io). */ -static int verity_verify_level(struct dm_verity_io *io, sector_t block, - int level, bool skip_unverified) +static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, int level, bool skip_unverified, + u8 *want_digest) { - struct dm_verity *v = io->v; struct dm_buffer *buf; struct buffer_aux *aux; u8 *data; @@ -273,172 +270,185 @@ static int verity_verify_level(struct dm_verity_io *io, sector_t block, aux = dm_bufio_get_aux_data(buf); if (!aux->hash_verified) { - struct shash_desc *desc; - u8 *result; - if (skip_unverified) { r = 1; goto release_ret_r; } - desc = io_hash_desc(v, io); - desc->tfm = v->tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - r = crypto_shash_init(desc); - if (r < 0) { - DMERR("crypto_shash_init failed: %d", r); + r = verity_hash(v, verity_io_hash_desc(v, io), + data, 1 << v->hash_dev_block_bits, + verity_io_real_digest(v, io)); + if (unlikely(r < 0)) goto release_ret_r; - } - if (likely(v->version >= 1)) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - } - - r = crypto_shash_update(desc, data, 1 << v->hash_dev_block_bits); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - - if (!v->version) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - goto release_ret_r; - } - } - - result = io_real_digest(v, io); - r = crypto_shash_final(desc, result); - if (r < 0) { - DMERR("crypto_shash_final failed: %d", r); - goto release_ret_r; - } - if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA, - hash_block)) { - r = -EIO; - goto release_ret_r; - } - } else + if (likely(memcmp(verity_io_real_digest(v, io), want_digest, + v->digest_size) == 0)) aux->hash_verified = 1; + else if (verity_fec_decode(v, io, + DM_VERITY_BLOCK_TYPE_METADATA, + hash_block, data, NULL) == 0) + aux->hash_verified = 1; + else if (verity_handle_err(v, + DM_VERITY_BLOCK_TYPE_METADATA, + hash_block)) { + r = -EIO; + goto release_ret_r; + } } data += offset; - - memcpy(io_want_digest(v, io), data, v->digest_size); - - dm_bufio_release(buf); - return 0; + memcpy(want_digest, data, v->digest_size); + r = 0; release_ret_r: dm_bufio_release(buf); + return r; +} + +/* + * Find a hash for a given block, write it to digest and verify the integrity + * of the hash tree if necessary. + */ +int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, u8 *digest, bool *is_zero) +{ + int r = 0, i; + + if (likely(v->levels)) { + /* + * First, we try to get the requested hash for + * the current block. If the hash block itself is + * verified, zero is returned. If it isn't, this + * function returns 1 and we fall back to whole + * chain verification. + */ + r = verity_verify_level(v, io, block, 0, true, digest); + if (likely(r <= 0)) + goto out; + } + + memcpy(digest, v->root_digest, v->digest_size); + + for (i = v->levels - 1; i >= 0; i--) { + r = verity_verify_level(v, io, block, i, false, digest); + if (unlikely(r)) + goto out; + } +out: + if (!r && v->zero_digest) + *is_zero = !memcmp(v->zero_digest, digest, v->digest_size); + else + *is_zero = false; return r; } +/* + * Calls function process for 1 << v->data_dev_block_bits bytes in the bio_vec + * starting from iter. + */ +int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter *iter, + int (*process)(struct dm_verity *v, + struct dm_verity_io *io, u8 *data, + size_t len)) +{ + unsigned todo = 1 << v->data_dev_block_bits; + struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size); + + do { + int r; + u8 *page; + unsigned len; + struct bio_vec bv = bio_iter_iovec(bio, *iter); + + page = kmap_atomic(bv.bv_page); + len = bv.bv_len; + + if (likely(len >= todo)) + len = todo; + + r = process(v, io, page + bv.bv_offset, len); + kunmap_atomic(page); + + if (r < 0) + return r; + + bio_advance_iter(bio, iter, len); + todo -= len; + } while (todo); + + return 0; +} + +static int verity_bv_hash_update(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + return verity_hash_update(v, verity_io_hash_desc(v, io), data, len); +} + +static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io, + u8 *data, size_t len) +{ + memset(data, 0, len); + return 0; +} + /* * Verify one "dm_verity_io" structure. */ static int verity_verify_io(struct dm_verity_io *io) { + bool is_zero; struct dm_verity *v = io->v; - struct bio *bio = dm_bio_from_per_bio_data(io, - v->ti->per_bio_data_size); + struct bvec_iter start; unsigned b; - int i; for (b = 0; b < io->n_blocks; b++) { - struct shash_desc *desc; - u8 *result; int r; - unsigned todo; + struct shash_desc *desc = verity_io_hash_desc(v, io); - if (likely(v->levels)) { + r = verity_hash_for_block(v, io, io->block + b, + verity_io_want_digest(v, io), + &is_zero); + if (unlikely(r < 0)) + return r; + + if (is_zero) { /* - * First, we try to get the requested hash for - * the current block. If the hash block itself is - * verified, zero is returned. If it isn't, this - * function returns 0 and we fall back to whole - * chain verification. + * If we expect a zero block, don't validate, just + * return zeros. */ - int r = verity_verify_level(io, io->block + b, 0, true); - if (likely(!r)) - goto test_block_hash; - if (r < 0) + r = verity_for_bv_block(v, io, &io->iter, + verity_bv_zero); + if (unlikely(r < 0)) return r; + + continue; } - memcpy(io_want_digest(v, io), v->root_digest, v->digest_size); - - for (i = v->levels - 1; i >= 0; i--) { - int r = verity_verify_level(io, io->block + b, i, false); - if (unlikely(r)) - return r; - } - -test_block_hash: - desc = io_hash_desc(v, io); - desc->tfm = v->tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - r = crypto_shash_init(desc); - if (r < 0) { - DMERR("crypto_shash_init failed: %d", r); + r = verity_hash_init(v, desc); + if (unlikely(r < 0)) return r; - } - if (likely(v->version >= 1)) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - } - todo = 1 << v->data_dev_block_bits; - do { - u8 *page; - unsigned len; - struct bio_vec bv = bio_iter_iovec(bio, io->iter); - - page = kmap_atomic(bv.bv_page); - len = bv.bv_len; - if (likely(len >= todo)) - len = todo; - r = crypto_shash_update(desc, page + bv.bv_offset, len); - kunmap_atomic(page); - - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - - bio_advance_iter(bio, &io->iter, len); - todo -= len; - } while (todo); - - if (!v->version) { - r = crypto_shash_update(desc, v->salt, v->salt_size); - if (r < 0) { - DMERR("crypto_shash_update failed: %d", r); - return r; - } - } - - result = io_real_digest(v, io); - r = crypto_shash_final(desc, result); - if (r < 0) { - DMERR("crypto_shash_final failed: %d", r); + start = io->iter; + r = verity_for_bv_block(v, io, &io->iter, verity_bv_hash_update); + if (unlikely(r < 0)) return r; - } - if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) { - if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, - io->block + b)) - return -EIO; - } + + r = verity_hash_final(v, desc, verity_io_real_digest(v, io)); + if (unlikely(r < 0)) + return r; + + if (likely(memcmp(verity_io_real_digest(v, io), + verity_io_want_digest(v, io), v->digest_size) == 0)) + continue; + else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b, NULL, &start) == 0) + continue; + else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, + io->block + b)) + return -EIO; } return 0; @@ -453,9 +463,10 @@ static void verity_finish_io(struct dm_verity_io *io, int error) struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_bio_data_size); bio->bi_end_io = io->orig_bi_end_io; - bio->bi_private = io->orig_bi_private; bio->bi_error = error; + verity_fec_finish_io(io); + bio_endio(bio); } @@ -470,7 +481,7 @@ static void verity_end_io(struct bio *bio) { struct dm_verity_io *io = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_error && !verity_fec_is_enabled(io->v)) { verity_finish_io(io, bio->bi_error); return; } @@ -566,7 +577,6 @@ static int verity_map(struct dm_target *ti, struct bio *bio) io = dm_per_bio_data(bio, ti->per_bio_data_size); io->v = v; io->orig_bi_end_io = bio->bi_end_io; - io->orig_bi_private = bio->bi_private; io->block = bio->bi_iter.bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT); io->n_blocks = bio->bi_iter.bi_size >> v->data_dev_block_bits; @@ -574,6 +584,8 @@ static int verity_map(struct dm_target *ti, struct bio *bio) bio->bi_private = io; io->iter = bio->bi_iter; + verity_fec_init_io(io); + verity_submit_prefetch(v, io); generic_make_request(bio); @@ -588,6 +600,7 @@ static void verity_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { struct dm_verity *v = ti->private; + unsigned args = 0; unsigned sz = 0; unsigned x; @@ -614,8 +627,17 @@ static void verity_status(struct dm_target *ti, status_type_t type, else for (x = 0; x < v->salt_size; x++) DMEMIT("%02x", v->salt[x]); + if (v->mode != DM_VERITY_MODE_EIO) + args++; + if (verity_fec_is_enabled(v)) + args += DM_VERITY_OPTS_FEC; + if (v->zero_digest) + args++; + if (!args) + return; + DMEMIT(" %u", args); if (v->mode != DM_VERITY_MODE_EIO) { - DMEMIT(" 1 "); + DMEMIT(" "); switch (v->mode) { case DM_VERITY_MODE_LOGGING: DMEMIT(DM_VERITY_OPT_LOGGING); @@ -627,6 +649,9 @@ static void verity_status(struct dm_target *ti, status_type_t type, BUG(); } } + if (v->zero_digest) + DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES); + sz = verity_fec_status_table(v, sz, result, maxlen); break; } } @@ -677,6 +702,7 @@ static void verity_dtr(struct dm_target *ti) kfree(v->salt); kfree(v->root_digest); + kfree(v->zero_digest); if (v->tfm) crypto_free_shash(v->tfm); @@ -689,9 +715,94 @@ static void verity_dtr(struct dm_target *ti) if (v->data_dev) dm_put_device(ti, v->data_dev); + verity_fec_dtr(v); + kfree(v); } +static int verity_alloc_zero_digest(struct dm_verity *v) +{ + int r = -ENOMEM; + struct shash_desc *desc; + u8 *zero_data; + + v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL); + + if (!v->zero_digest) + return r; + + desc = kmalloc(v->shash_descsize, GFP_KERNEL); + + if (!desc) + return r; /* verity_dtr will free zero_digest */ + + zero_data = kzalloc(1 << v->data_dev_block_bits, GFP_KERNEL); + + if (!zero_data) + goto out; + + r = verity_hash(v, desc, zero_data, 1 << v->data_dev_block_bits, + v->zero_digest); + +out: + kfree(desc); + kfree(zero_data); + + return r; +} + +static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v) +{ + int r; + unsigned argc; + struct dm_target *ti = v->ti; + const char *arg_name; + + static struct dm_arg _args[] = { + {0, DM_VERITY_OPTS_MAX, "Invalid number of feature args"}, + }; + + r = dm_read_arg_group(_args, as, &argc, &ti->error); + if (r) + return -EINVAL; + + if (!argc) + return 0; + + do { + arg_name = dm_shift_arg(as); + argc--; + + if (!strcasecmp(arg_name, DM_VERITY_OPT_LOGGING)) { + v->mode = DM_VERITY_MODE_LOGGING; + continue; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_RESTART)) { + v->mode = DM_VERITY_MODE_RESTART; + continue; + + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_IGN_ZEROES)) { + r = verity_alloc_zero_digest(v); + if (r) { + ti->error = "Cannot allocate zero digest"; + return r; + } + continue; + + } else if (verity_is_fec_opt_arg(arg_name)) { + r = verity_fec_parse_opt_args(as, v, &argc, arg_name); + if (r) + return r; + continue; + } + + ti->error = "Unrecognized verity feature request"; + return -EINVAL; + } while (argc && !r); + + return r; +} + /* * Target parameters: * The current format is version 1. @@ -710,18 +821,13 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) { struct dm_verity *v; struct dm_arg_set as; - const char *opt_string; - unsigned int num, opt_params; + unsigned int num; unsigned long long num_ll; int r; int i; sector_t hash_position; char dummy; - static struct dm_arg _args[] = { - {0, 1, "Invalid number of feature args"}, - }; - v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL); if (!v) { ti->error = "Cannot allocate verity structure"; @@ -730,6 +836,10 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->private = v; v->ti = ti; + r = verity_fec_ctr_alloc(v); + if (r) + goto bad; + if ((dm_table_get_mode(ti->table) & ~FMODE_READ)) { ti->error = "Device must be readonly"; r = -EINVAL; @@ -866,29 +976,9 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) as.argc = argc; as.argv = argv; - r = dm_read_arg_group(_args, &as, &opt_params, &ti->error); - if (r) + r = verity_parse_opt_args(&as, v); + if (r < 0) goto bad; - - while (opt_params) { - opt_params--; - opt_string = dm_shift_arg(&as); - if (!opt_string) { - ti->error = "Not enough feature arguments"; - r = -EINVAL; - goto bad; - } - - if (!strcasecmp(opt_string, DM_VERITY_OPT_LOGGING)) - v->mode = DM_VERITY_MODE_LOGGING; - else if (!strcasecmp(opt_string, DM_VERITY_OPT_RESTART)) - v->mode = DM_VERITY_MODE_RESTART; - else { - ti->error = "Invalid feature arguments"; - r = -EINVAL; - goto bad; - } - } } v->hash_per_block_bits = @@ -938,8 +1028,6 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } - ti->per_bio_data_size = roundup(sizeof(struct dm_verity_io) + v->shash_descsize + v->digest_size * 2, __alignof__(struct dm_verity_io)); - /* WQ_UNBOUND greatly improves performance when running on ramdisk */ v->verify_wq = alloc_workqueue("kverityd", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, num_online_cpus()); if (!v->verify_wq) { @@ -948,6 +1036,16 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } + ti->per_bio_data_size = sizeof(struct dm_verity_io) + + v->shash_descsize + v->digest_size * 2; + + r = verity_fec_ctr(v); + if (r) + goto bad; + + ti->per_bio_data_size = roundup(ti->per_bio_data_size, + __alignof__(struct dm_verity_io)); + return 0; bad: @@ -958,7 +1056,7 @@ bad: static struct target_type verity_target = { .name = "verity", - .version = {1, 2, 0}, + .version = {1, 3, 0}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h new file mode 100644 index 000000000000..fb419f422d73 --- /dev/null +++ b/drivers/md/dm-verity.h @@ -0,0 +1,129 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * Copyright (C) 2015 Google, Inc. + * + * Author: Mikulas Patocka + * + * Based on Chromium dm-verity driver (C) 2011 The Chromium OS Authors + * + * This file is released under the GPLv2. + */ + +#ifndef DM_VERITY_H +#define DM_VERITY_H + +#include "dm-bufio.h" +#include +#include + +#define DM_VERITY_MAX_LEVELS 63 + +enum verity_mode { + DM_VERITY_MODE_EIO, + DM_VERITY_MODE_LOGGING, + DM_VERITY_MODE_RESTART +}; + +enum verity_block_type { + DM_VERITY_BLOCK_TYPE_DATA, + DM_VERITY_BLOCK_TYPE_METADATA +}; + +struct dm_verity_fec; + +struct dm_verity { + struct dm_dev *data_dev; + struct dm_dev *hash_dev; + struct dm_target *ti; + struct dm_bufio_client *bufio; + char *alg_name; + struct crypto_shash *tfm; + u8 *root_digest; /* digest of the root block */ + u8 *salt; /* salt: its size is salt_size */ + u8 *zero_digest; /* digest for a zero block */ + unsigned salt_size; + sector_t data_start; /* data offset in 512-byte sectors */ + sector_t hash_start; /* hash start in blocks */ + sector_t data_blocks; /* the number of data blocks */ + sector_t hash_blocks; /* the number of hash blocks */ + unsigned char data_dev_block_bits; /* log2(data blocksize) */ + unsigned char hash_dev_block_bits; /* log2(hash blocksize) */ + unsigned char hash_per_block_bits; /* log2(hashes in hash block) */ + unsigned char levels; /* the number of tree levels */ + unsigned char version; + unsigned digest_size; /* digest size for the current hash algorithm */ + unsigned shash_descsize;/* the size of temporary space for crypto */ + int hash_failed; /* set to 1 if hash of any block failed */ + enum verity_mode mode; /* mode for handling verification errors */ + unsigned corrupted_errs;/* Number of errors for corrupted blocks */ + + struct workqueue_struct *verify_wq; + + /* starting blocks for each tree level. 0 is the lowest level. */ + sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; + + struct dm_verity_fec *fec; /* forward error correction */ +}; + +struct dm_verity_io { + struct dm_verity *v; + + /* original value of bio->bi_end_io */ + bio_end_io_t *orig_bi_end_io; + + sector_t block; + unsigned n_blocks; + + struct bvec_iter iter; + + struct work_struct work; + + /* + * Three variably-size fields follow this struct: + * + * u8 hash_desc[v->shash_descsize]; + * u8 real_digest[v->digest_size]; + * u8 want_digest[v->digest_size]; + * + * To access them use: verity_io_hash_desc(), verity_io_real_digest() + * and verity_io_want_digest(). + */ +}; + +static inline struct shash_desc *verity_io_hash_desc(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (struct shash_desc *)(io + 1); +} + +static inline u8 *verity_io_real_digest(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (u8 *)(io + 1) + v->shash_descsize; +} + +static inline u8 *verity_io_want_digest(struct dm_verity *v, + struct dm_verity_io *io) +{ + return (u8 *)(io + 1) + v->shash_descsize + v->digest_size; +} + +static inline u8 *verity_io_digest_end(struct dm_verity *v, + struct dm_verity_io *io) +{ + return verity_io_want_digest(v, io) + v->digest_size; +} + +extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, + struct bvec_iter *iter, + int (*process)(struct dm_verity *v, + struct dm_verity_io *io, + u8 *data, size_t len)); + +extern int verity_hash(struct dm_verity *v, struct shash_desc *desc, + const u8 *data, size_t len, u8 *digest); + +extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, + sector_t block, u8 *digest, bool *is_zero); + +#endif /* DM_VERITY_H */ diff --git a/drivers/misc/uid_stat.c b/drivers/misc/uid_stat.c new file mode 100644 index 000000000000..185c69c9738a --- /dev/null +++ b/drivers/misc/uid_stat.c @@ -0,0 +1,153 @@ +/* drivers/misc/uid_stat.c + * + * Copyright (C) 2008 - 2009 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_SPINLOCK(uid_lock); +static LIST_HEAD(uid_list); +static struct proc_dir_entry *parent; + +struct uid_stat { + struct list_head link; + uid_t uid; + atomic_t tcp_rcv; + atomic_t tcp_snd; +}; + +static struct uid_stat *find_uid_stat(uid_t uid) { + struct uid_stat *entry; + + list_for_each_entry(entry, &uid_list, link) { + if (entry->uid == uid) { + return entry; + } + } + return NULL; +} + +static int uid_stat_atomic_int_show(struct seq_file *m, void *v) +{ + unsigned int bytes; + atomic_t *counter = m->private; + + bytes = (unsigned int) (atomic_read(counter) + INT_MIN); + seq_printf(m, "%u\n", bytes); + return seq_has_overflowed(m) ? -ENOSPC : 0; +} + +static int uid_stat_read_atomic_int_open(struct inode *inode, struct file *file) +{ + return single_open(file, uid_stat_atomic_int_show, PDE_DATA(inode)); +} + +static const struct file_operations uid_stat_read_atomic_int_fops = { + .open = uid_stat_read_atomic_int_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +/* Create a new entry for tracking the specified uid. */ +static struct uid_stat *create_stat(uid_t uid) { + struct uid_stat *new_uid; + /* Create the uid stat struct and append it to the list. */ + new_uid = kmalloc(sizeof(struct uid_stat), GFP_ATOMIC); + if (!new_uid) + return NULL; + + new_uid->uid = uid; + /* Counters start at INT_MIN, so we can track 4GB of network traffic. */ + atomic_set(&new_uid->tcp_rcv, INT_MIN); + atomic_set(&new_uid->tcp_snd, INT_MIN); + + list_add_tail(&new_uid->link, &uid_list); + return new_uid; +} + +static void create_stat_proc(struct uid_stat *new_uid) +{ + char uid_s[32]; + struct proc_dir_entry *entry; + sprintf(uid_s, "%d", new_uid->uid); + entry = proc_mkdir(uid_s, parent); + + /* Keep reference to uid_stat so we know what uid to read stats from. */ + proc_create_data("tcp_snd", S_IRUGO, entry, + &uid_stat_read_atomic_int_fops, &new_uid->tcp_snd); + + proc_create_data("tcp_rcv", S_IRUGO, entry, + &uid_stat_read_atomic_int_fops, &new_uid->tcp_rcv); +} + +static struct uid_stat *find_or_create_uid_stat(uid_t uid) +{ + struct uid_stat *entry; + unsigned long flags; + spin_lock_irqsave(&uid_lock, flags); + entry = find_uid_stat(uid); + if (entry) { + spin_unlock_irqrestore(&uid_lock, flags); + return entry; + } + entry = create_stat(uid); + spin_unlock_irqrestore(&uid_lock, flags); + if (entry) + create_stat_proc(entry); + return entry; +} + +int uid_stat_tcp_snd(uid_t uid, int size) { + struct uid_stat *entry; + activity_stats_update(); + entry = find_or_create_uid_stat(uid); + if (!entry) + return -1; + atomic_add(size, &entry->tcp_snd); + return 0; +} + +int uid_stat_tcp_rcv(uid_t uid, int size) { + struct uid_stat *entry; + activity_stats_update(); + entry = find_or_create_uid_stat(uid); + if (!entry) + return -1; + atomic_add(size, &entry->tcp_rcv); + return 0; +} + +static int __init uid_stat_init(void) +{ + parent = proc_mkdir("uid_stat", NULL); + if (!parent) { + pr_err("uid_stat: failed to create proc entry\n"); + return -1; + } + return 0; +} + +__initcall(uid_stat_init); diff --git a/drivers/mmc/card/Kconfig b/drivers/mmc/card/Kconfig index 5562308699bc..6142ec1b9dfb 100644 --- a/drivers/mmc/card/Kconfig +++ b/drivers/mmc/card/Kconfig @@ -68,3 +68,15 @@ config MMC_TEST This driver is only of interest to those developing or testing a host driver. Most people should say N here. + +config MMC_SIMULATE_MAX_SPEED + bool "Turn on maximum speed control per block device" + depends on MMC_BLOCK + help + Say Y here to enable MMC device speed limiting. Used to test and + simulate the behavior of the system when confronted with a slow MMC. + + Enables max_read_speed, max_write_speed and cache_size attributes to + control the write or read maximum KB/second speed behaviors. + + If unsure, say N here. diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index b116122c5767..7547463928d6 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -38,7 +38,6 @@ #include #include -#define CREATE_TRACE_POINTS #include #include @@ -329,6 +328,249 @@ out: return ret; } +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + +static int max_read_speed, max_write_speed, cache_size = 4; + +module_param(max_read_speed, int, S_IRUSR | S_IRGRP); +MODULE_PARM_DESC(max_read_speed, "maximum KB/s read speed 0=off"); +module_param(max_write_speed, int, S_IRUSR | S_IRGRP); +MODULE_PARM_DESC(max_write_speed, "maximum KB/s write speed 0=off"); +module_param(cache_size, int, S_IRUSR | S_IRGRP); +MODULE_PARM_DESC(cache_size, "MB high speed memory or SLC cache"); + +/* + * helper macros and expectations: + * size - unsigned long number of bytes + * jiffies - unsigned long HZ timestamp difference + * speed - unsigned KB/s transfer rate + */ +#define size_and_speed_to_jiffies(size, speed) \ + ((size) * HZ / (speed) / 1024UL) +#define jiffies_and_speed_to_size(jiffies, speed) \ + (((speed) * (jiffies) * 1024UL) / HZ) +#define jiffies_and_size_to_speed(jiffies, size) \ + ((size) * HZ / (jiffies) / 1024UL) + +/* Limits to report warning */ +/* jiffies_and_size_to_speed(10*HZ, queue_max_hw_sectors(q) * 512UL) ~ 25 */ +#define MIN_SPEED(q) 250 /* 10 times faster than a floppy disk */ +#define MAX_SPEED(q) jiffies_and_size_to_speed(1, queue_max_sectors(q) * 512UL) + +#define speed_valid(speed) ((speed) > 0) + +static const char off[] = "off\n"; + +static int max_speed_show(int speed, char *buf) +{ + if (speed) + return scnprintf(buf, PAGE_SIZE, "%uKB/s\n", speed); + else + return scnprintf(buf, PAGE_SIZE, off); +} + +static int max_speed_store(const char *buf, struct request_queue *q) +{ + unsigned int limit, set = 0; + + if (!strncasecmp(off, buf, sizeof(off) - 2)) + return set; + if (kstrtouint(buf, 0, &set) || (set > INT_MAX)) + return -EINVAL; + if (set == 0) + return set; + limit = MAX_SPEED(q); + if (set > limit) + pr_warn("max speed %u ineffective above %u\n", set, limit); + limit = MIN_SPEED(q); + if (set < limit) + pr_warn("max speed %u painful below %u\n", set, limit); + return set; +} + +static ssize_t max_write_speed_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + int ret = max_speed_show(atomic_read(&md->queue.max_write_speed), buf); + + mmc_blk_put(md); + return ret; +} + +static ssize_t max_write_speed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + int set = max_speed_store(buf, md->queue.queue); + + if (set < 0) { + mmc_blk_put(md); + return set; + } + + atomic_set(&md->queue.max_write_speed, set); + mmc_blk_put(md); + return count; +} + +static const DEVICE_ATTR(max_write_speed, S_IRUGO | S_IWUSR, + max_write_speed_show, max_write_speed_store); + +static ssize_t max_read_speed_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + int ret = max_speed_show(atomic_read(&md->queue.max_read_speed), buf); + + mmc_blk_put(md); + return ret; +} + +static ssize_t max_read_speed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + int set = max_speed_store(buf, md->queue.queue); + + if (set < 0) { + mmc_blk_put(md); + return set; + } + + atomic_set(&md->queue.max_read_speed, set); + mmc_blk_put(md); + return count; +} + +static const DEVICE_ATTR(max_read_speed, S_IRUGO | S_IWUSR, + max_read_speed_show, max_read_speed_store); + +static ssize_t cache_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev)); + struct mmc_queue *mq = &md->queue; + int cache_size = atomic_read(&mq->cache_size); + int ret; + + if (!cache_size) + ret = scnprintf(buf, PAGE_SIZE, off); + else { + int speed = atomic_read(&mq->max_write_speed); + + if (!speed_valid(speed)) + ret = scnprintf(buf, PAGE_SIZE, "%uMB\n", cache_size); + else { /* We accept race between cache_jiffies and cache_used */ + unsigned long size = jiffies_and_speed_to_size( + jiffies - mq->cache_jiffies, speed); + long used = atomic_long_read(&mq->cache_used); + + if (size >= used) + size = 0; + else + size = (used - size) * 100 / cache_size + / 1024UL / 1024UL; + + ret = scnprintf(buf, PAGE_SIZE, "%uMB %lu%% used\n", + cache_size, size); + } + } + + mmc_blk_put(md); + return ret; +} + +static ssize_t cache_size_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mmc_blk_data *md; + unsigned int set = 0; + + if (strncasecmp(off, buf, sizeof(off) - 2) + && (kstrtouint(buf, 0, &set) || (set > INT_MAX))) + return -EINVAL; + + md = mmc_blk_get(dev_to_disk(dev)); + atomic_set(&md->queue.cache_size, set); + mmc_blk_put(md); + return count; +} + +static const DEVICE_ATTR(cache_size, S_IRUGO | S_IWUSR, + cache_size_show, cache_size_store); + +/* correct for write-back */ +static long mmc_blk_cache_used(struct mmc_queue *mq, unsigned long waitfor) +{ + long used = 0; + int speed = atomic_read(&mq->max_write_speed); + + if (speed_valid(speed)) { + unsigned long size = jiffies_and_speed_to_size( + waitfor - mq->cache_jiffies, speed); + used = atomic_long_read(&mq->cache_used); + + if (size >= used) + used = 0; + else + used -= size; + } + + atomic_long_set(&mq->cache_used, used); + mq->cache_jiffies = waitfor; + + return used; +} + +static void mmc_blk_simulate_delay( + struct mmc_queue *mq, + struct request *req, + unsigned long waitfor) +{ + int max_speed; + + if (!req) + return; + + max_speed = (rq_data_dir(req) == READ) + ? atomic_read(&mq->max_read_speed) + : atomic_read(&mq->max_write_speed); + if (speed_valid(max_speed)) { + unsigned long bytes = blk_rq_bytes(req); + + if (rq_data_dir(req) != READ) { + int cache_size = atomic_read(&mq->cache_size); + + if (cache_size) { + unsigned long size = cache_size * 1024L * 1024L; + long used = mmc_blk_cache_used(mq, waitfor); + + used += bytes; + atomic_long_set(&mq->cache_used, used); + bytes = 0; + if (used > size) + bytes = used - size; + } + } + waitfor += size_and_speed_to_jiffies(bytes, max_speed); + if (time_is_after_jiffies(waitfor)) { + long msecs = jiffies_to_msecs(waitfor - jiffies); + + if (likely(msecs > 0)) + msleep(msecs); + } + } +} + +#else + +#define mmc_blk_simulate_delay(mq, req, waitfor) + +#endif static ssize_t num_wr_reqs_to_start_packing_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1870,6 +2112,23 @@ static int mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req) } end_req: +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + else if (atomic_read(&mq->cache_size)) { + long used = mmc_blk_cache_used(mq, jiffies); + + if (used) { + int speed = atomic_read(&mq->max_write_speed); + + if (speed_valid(speed)) { + unsigned long msecs = jiffies_to_msecs( + size_and_speed_to_jiffies( + used, speed)); + if (msecs) + msleep(msecs); + } + } + } +#endif blk_end_request_all(req, ret); return ret ? 0 : 1; @@ -3346,6 +3605,9 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) struct mmc_async_req *areq; const u8 packed_nr = 2; u8 reqs = 0; +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + unsigned long waitfor = jiffies; +#endif if (!rqc && !mq->mqrq_prev->req) return 0; @@ -3396,6 +3658,8 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) */ mmc_blk_reset_success(md, type); + mmc_blk_simulate_delay(mq, rqc, waitfor); + if (mmc_packed_cmd(mq_rq->cmd_type)) { ret = mmc_blk_end_packed_req(mq_rq); break; @@ -3968,6 +4232,14 @@ static void mmc_blk_remove_req(struct mmc_blk_data *md) card->ext_csd.boot_ro_lockable) device_remove_file(disk_to_dev(md->disk), &md->power_ro_lock); +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + device_remove_file(disk_to_dev(md->disk), + &dev_attr_max_write_speed); + device_remove_file(disk_to_dev(md->disk), + &dev_attr_max_read_speed); + device_remove_file(disk_to_dev(md->disk), + &dev_attr_cache_size); +#endif del_gendisk(md->disk); } @@ -4003,6 +4275,24 @@ static int mmc_add_disk(struct mmc_blk_data *md) ret = device_create_file(disk_to_dev(md->disk), &md->force_ro); if (ret) goto force_ro_fail; +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + atomic_set(&md->queue.max_write_speed, max_write_speed); + ret = device_create_file(disk_to_dev(md->disk), + &dev_attr_max_write_speed); + if (ret) + goto max_write_speed_fail; + atomic_set(&md->queue.max_read_speed, max_read_speed); + ret = device_create_file(disk_to_dev(md->disk), + &dev_attr_max_read_speed); + if (ret) + goto max_read_speed_fail; + atomic_set(&md->queue.cache_size, cache_size); + atomic_long_set(&md->queue.cache_used, 0); + md->queue.cache_jiffies = jiffies; + ret = device_create_file(disk_to_dev(md->disk), &dev_attr_cache_size); + if (ret) + goto cache_size_fail; +#endif if ((md->area_type & MMC_BLK_DATA_AREA_BOOT) && card->ext_csd.boot_ro_lockable) { @@ -4056,6 +4346,14 @@ no_pack_for_random_fails: num_wr_reqs_to_start_packing_fail: device_remove_file(disk_to_dev(md->disk), &md->power_ro_lock); power_ro_lock_fail: +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + device_remove_file(disk_to_dev(md->disk), &dev_attr_cache_size); +cache_size_fail: + device_remove_file(disk_to_dev(md->disk), &dev_attr_max_read_speed); +max_read_speed_fail: + device_remove_file(disk_to_dev(md->disk), &dev_attr_max_write_speed); +max_write_speed_fail: +#endif device_remove_file(disk_to_dev(md->disk), &md->force_ro); force_ro_fail: del_gendisk(md->disk); diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index d8a33ac55c91..253979b51c84 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -77,6 +77,14 @@ struct mmc_queue { int (*err_check_fn) (struct mmc_card *, struct mmc_async_req *); void (*packed_test_fn) (struct request_queue *, struct mmc_queue_req *); void (*cmdq_shutdown)(struct mmc_queue *); +#ifdef CONFIG_MMC_SIMULATE_MAX_SPEED + atomic_t max_write_speed; + atomic_t max_read_speed; + atomic_t cache_size; + /* i/o tracking */ + atomic_long_t cache_used; + unsigned long cache_jiffies; +#endif }; extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *, diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index b76bb7a74049..3762f698e1ee 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -33,6 +33,7 @@ #include #include +#define CREATE_TRACE_POINTS #include #include @@ -51,6 +52,11 @@ #include "sd_ops.h" #include "sdio_ops.h" +EXPORT_TRACEPOINT_SYMBOL_GPL(mmc_blk_erase_start); +EXPORT_TRACEPOINT_SYMBOL_GPL(mmc_blk_erase_end); +EXPORT_TRACEPOINT_SYMBOL_GPL(mmc_blk_rw_start); +EXPORT_TRACEPOINT_SYMBOL_GPL(mmc_blk_rw_end); + /* If the device is not responding */ #define MMC_CORE_TIMEOUT_MS (10 * 60 * 1000) /* 10 minute timeout */ diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index 895dfbb7fbf5..e7ebc3cb8eda 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -22,6 +22,7 @@ #include "core.h" #include "bus.h" +#include "host.h" #include "sd.h" #include "sdio_bus.h" #include "mmc_ops.h" diff --git a/drivers/net/ppp/Kconfig b/drivers/net/ppp/Kconfig index e4cf44b1e815..282aec4860eb 100644 --- a/drivers/net/ppp/Kconfig +++ b/drivers/net/ppp/Kconfig @@ -150,7 +150,7 @@ config PPPOL2TP if TTY config PPPOLAC - bool "PPP on L2TP Access Concentrator" + tristate "PPP on L2TP Access Concentrator" depends on PPP && INET help L2TP (RFC 2661) is a tunneling protocol widely used in virtual private @@ -159,7 +159,7 @@ config PPPOLAC fairly simple and suited for clients. config PPPOPNS - bool "PPP on PPTP Network Server" + tristate "PPP on PPTP Network Server" depends on PPP && INET help PPTP (RFC 2637) is a tunneling protocol widely used in virtual private diff --git a/drivers/net/ppp/pppolac.c b/drivers/net/ppp/pppolac.c index 1b8180cc1d4d..0184c96579e9 100644 --- a/drivers/net/ppp/pppolac.c +++ b/drivers/net/ppp/pppolac.c @@ -206,11 +206,10 @@ static void pppolac_xmit_core(struct work_struct *delivery_work) while ((skb = skb_dequeue(&delivery_queue))) { struct sock *sk_udp = skb->sk; struct kvec iov = {.iov_base = skb->data, .iov_len = skb->len}; - struct msghdr msg = { - .msg_iov = (struct iovec *)&iov, - .msg_iovlen = 1, - .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT, - }; + struct msghdr msg = { 0 }; + + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, + skb->len); sk_udp->sk_prot->sendmsg(sk_udp, &msg, skb->len); kfree_skb(skb); } diff --git a/drivers/net/ppp/pppopns.c b/drivers/net/ppp/pppopns.c index 568bb45cfeac..d9e06039794e 100644 --- a/drivers/net/ppp/pppopns.c +++ b/drivers/net/ppp/pppopns.c @@ -189,11 +189,10 @@ static void pppopns_xmit_core(struct work_struct *delivery_work) while ((skb = skb_dequeue(&delivery_queue))) { struct sock *sk_raw = skb->sk; struct kvec iov = {.iov_base = skb->data, .iov_len = skb->len}; - struct msghdr msg = { - .msg_iov = (struct iovec *)&iov, - .msg_iovlen = 1, - .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT, - }; + struct msghdr msg = { 0 }; + + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, + skb->len); sk_raw->sk_prot->sendmsg(sk_raw, &msg, skb->len); kfree_skb(skb); } diff --git a/drivers/usb/gadget/function/f_accessory.c b/drivers/usb/gadget/function/f_accessory.c index 3908bc151c2b..2f6f393ba7c9 100644 --- a/drivers/usb/gadget/function/f_accessory.c +++ b/drivers/usb/gadget/function/f_accessory.c @@ -448,12 +448,19 @@ static void acc_hid_close(struct hid_device *hid) { } +static int acc_hid_raw_request(struct hid_device *hid, unsigned char reportnum, + __u8 *buf, size_t len, unsigned char rtype, int reqtype) +{ + return 0; +} + static struct hid_ll_driver acc_hid_ll_driver = { .parse = acc_hid_parse, .start = acc_hid_start, .stop = acc_hid_stop, .open = acc_hid_open, .close = acc_hid_close, + .raw_request = acc_hid_raw_request, }; static struct acc_hid_dev *acc_hid_new(struct acc_dev *dev, diff --git a/drivers/usb/gadget/function/f_audio_source.c b/drivers/usb/gadget/function/f_audio_source.c index 39645be93502..bcd817439dbf 100644 --- a/drivers/usb/gadget/function/f_audio_source.c +++ b/drivers/usb/gadget/function/f_audio_source.c @@ -583,6 +583,11 @@ static void audio_disable(struct usb_function *f) usb_ep_disable(audio->in_ep); } +static void audio_free_func(struct usb_function *f) +{ + /* no-op */ +} + /*-------------------------------------------------------------------------*/ static void audio_build_desc(struct audio_dev *audio) @@ -827,6 +832,7 @@ static struct audio_dev _audio_dev = { .set_alt = audio_set_alt, .setup = audio_setup, .disable = audio_disable, + .free_func = audio_free_func, }, .lock = __SPIN_LOCK_UNLOCKED(_audio_dev.lock), .idle_reqs = LIST_HEAD_INIT(_audio_dev.idle_reqs), diff --git a/drivers/usb/gadget/function/f_mtp.c b/drivers/usb/gadget/function/f_mtp.c index 3b3b1b011407..aa186781ef22 100644 --- a/drivers/usb/gadget/function/f_mtp.c +++ b/drivers/usb/gadget/function/f_mtp.c @@ -158,7 +158,7 @@ static struct usb_interface_descriptor ptp_interface_desc = { .bInterfaceProtocol = 1, }; -static struct usb_endpoint_descriptor mtp_superspeed_in_desc = { +static struct usb_endpoint_descriptor mtp_ss_in_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, .bEndpointAddress = USB_DIR_IN, @@ -166,8 +166,8 @@ static struct usb_endpoint_descriptor mtp_superspeed_in_desc = { .wMaxPacketSize = cpu_to_le16(1024), }; -static struct usb_ss_ep_comp_descriptor mtp_superspeed_in_comp_desc = { - .bLength = sizeof(mtp_superspeed_in_comp_desc), +static struct usb_ss_ep_comp_descriptor mtp_ss_in_comp_desc = { + .bLength = sizeof(mtp_ss_in_comp_desc), .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, /* the following 2 values can be tweaked if necessary */ @@ -175,7 +175,8 @@ static struct usb_ss_ep_comp_descriptor mtp_superspeed_in_comp_desc = { /* .bmAttributes = 0, */ }; -static struct usb_endpoint_descriptor mtp_superspeed_out_desc = { + +static struct usb_endpoint_descriptor mtp_ss_out_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, .bEndpointAddress = USB_DIR_OUT, @@ -183,8 +184,8 @@ static struct usb_endpoint_descriptor mtp_superspeed_out_desc = { .wMaxPacketSize = cpu_to_le16(1024), }; -static struct usb_ss_ep_comp_descriptor mtp_superspeed_out_comp_desc = { - .bLength = sizeof(mtp_superspeed_out_comp_desc), +static struct usb_ss_ep_comp_descriptor mtp_ss_out_comp_desc = { + .bLength = sizeof(mtp_ss_out_comp_desc), .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, /* the following 2 values can be tweaked if necessary */ @@ -231,8 +232,8 @@ static struct usb_endpoint_descriptor mtp_intr_desc = { .bInterval = 6, }; -static struct usb_ss_ep_comp_descriptor mtp_superspeed_intr_comp_desc = { - .bLength = sizeof(mtp_superspeed_intr_comp_desc), +static struct usb_ss_ep_comp_descriptor mtp_intr_ss_comp_desc = { + .bLength = sizeof(mtp_intr_ss_comp_desc), .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, /* the following 3 values can be tweaked if necessary */ @@ -259,12 +260,12 @@ static struct usb_descriptor_header *hs_mtp_descs[] = { static struct usb_descriptor_header *ss_mtp_descs[] = { (struct usb_descriptor_header *) &mtp_interface_desc, - (struct usb_descriptor_header *) &mtp_superspeed_in_desc, - (struct usb_descriptor_header *) &mtp_superspeed_in_comp_desc, - (struct usb_descriptor_header *) &mtp_superspeed_out_desc, - (struct usb_descriptor_header *) &mtp_superspeed_out_comp_desc, + (struct usb_descriptor_header *) &mtp_ss_in_desc, + (struct usb_descriptor_header *) &mtp_ss_in_comp_desc, + (struct usb_descriptor_header *) &mtp_ss_out_desc, + (struct usb_descriptor_header *) &mtp_ss_out_comp_desc, (struct usb_descriptor_header *) &mtp_intr_desc, - (struct usb_descriptor_header *) &mtp_superspeed_intr_comp_desc, + (struct usb_descriptor_header *) &mtp_intr_ss_comp_desc, NULL, }; @@ -286,12 +287,12 @@ static struct usb_descriptor_header *hs_ptp_descs[] = { static struct usb_descriptor_header *ss_ptp_descs[] = { (struct usb_descriptor_header *) &ptp_interface_desc, - (struct usb_descriptor_header *) &mtp_superspeed_in_desc, - (struct usb_descriptor_header *) &mtp_superspeed_in_comp_desc, - (struct usb_descriptor_header *) &mtp_superspeed_out_desc, - (struct usb_descriptor_header *) &mtp_superspeed_out_comp_desc, + (struct usb_descriptor_header *) &mtp_ss_in_desc, + (struct usb_descriptor_header *) &mtp_ss_in_comp_desc, + (struct usb_descriptor_header *) &mtp_ss_out_desc, + (struct usb_descriptor_header *) &mtp_ss_out_comp_desc, (struct usb_descriptor_header *) &mtp_intr_desc, - (struct usb_descriptor_header *) &mtp_superspeed_intr_comp_desc, + (struct usb_descriptor_header *) &mtp_intr_ss_comp_desc, NULL, }; @@ -352,7 +353,7 @@ struct ext_mtp_desc mtp_ext_config_desc = { .dwLength = __constant_cpu_to_le32(sizeof(mtp_ext_config_desc)), .bcdVersion = __constant_cpu_to_le16(0x0100), .wIndex = __constant_cpu_to_le16(4), - .bCount = __constant_cpu_to_le16(1), + .bCount = 1, }, .function = { .bFirstInterfaceNumber = 0, @@ -395,6 +396,8 @@ struct mtp_instance { struct usb_function_instance func_inst; const char *name; struct mtp_dev *dev; + char mtp_ext_compat_id[16]; + struct usb_os_desc mtp_os_desc; }; /* temporary variable used between mtp_open() and mtp_gadget_bind() */ @@ -1389,6 +1392,7 @@ mtp_function_bind(struct usb_configuration *c, struct usb_function *f) struct mtp_dev *dev = func_to_mtp(f); int id; int ret; + struct mtp_instance *fi_mtp; dev->cdev = cdev; DBG(cdev, "mtp_function_bind dev: %p\n", dev); @@ -1406,6 +1410,18 @@ mtp_function_bind(struct usb_configuration *c, struct usb_function *f) mtp_string_defs[INTERFACE_STRING_INDEX].id = ret; mtp_interface_desc.iInterface = ret; } + + fi_mtp = container_of(f->fi, struct mtp_instance, func_inst); + + if (cdev->use_os_string) { + f->os_desc_table = kzalloc(sizeof(*f->os_desc_table), + GFP_KERNEL); + if (!f->os_desc_table) + return -ENOMEM; + f->os_desc_n = 1; + f->os_desc_table[0].os_desc = &fi_mtp->mtp_os_desc; + } + /* allocate endpoints */ ret = mtp_create_bulk_endpoints(dev, &mtp_fullspeed_in_desc, &mtp_fullspeed_out_desc, &mtp_intr_desc); @@ -1419,18 +1435,32 @@ mtp_function_bind(struct usb_configuration *c, struct usb_function *f) mtp_highspeed_out_desc.bEndpointAddress = mtp_fullspeed_out_desc.bEndpointAddress; } + /* support super speed hardware */ + if (gadget_is_superspeed(c->cdev->gadget)) { + unsigned max_burst; + + /* Calculate bMaxBurst, we know packet size is 1024 */ + max_burst = min_t(unsigned, MTP_BULK_BUFFER_SIZE / 1024, 15); + mtp_ss_in_desc.bEndpointAddress = + mtp_fullspeed_in_desc.bEndpointAddress; + mtp_ss_in_comp_desc.bMaxBurst = max_burst; + mtp_ss_out_desc.bEndpointAddress = + mtp_fullspeed_out_desc.bEndpointAddress; + mtp_ss_out_comp_desc.bMaxBurst = max_burst; + } /* support super speed hardware */ if (gadget_is_superspeed(c->cdev->gadget)) { - mtp_superspeed_in_desc.bEndpointAddress = + mtp_ss_in_desc.bEndpointAddress = mtp_fullspeed_in_desc.bEndpointAddress; - mtp_superspeed_out_desc.bEndpointAddress = + mtp_ss_out_desc.bEndpointAddress = mtp_fullspeed_out_desc.bEndpointAddress; } DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n", - gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full", - f->name, dev->ep_in->name, dev->ep_out->name); + gadget_is_superspeed(c->cdev->gadget) ? "super" : + (gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full"), + f->name, dev->ep_in->name, dev->ep_out->name); return 0; } @@ -1449,6 +1479,8 @@ mtp_function_unbind(struct usb_configuration *c, struct usb_function *f) mtp_request_free(req, dev->ep_intr); dev->state = STATE_OFFLINE; dev->is_ptp = false; + kfree(f->os_desc_table); + f->os_desc_n = 0; } static int mtp_function_set_alt(struct usb_function *f, @@ -1748,6 +1780,7 @@ static void mtp_free_inst(struct usb_function_instance *fi) fi_mtp = to_fi_mtp(fi); kfree(fi_mtp->name); mtp_cleanup(); + kfree(fi_mtp->mtp_os_desc.group.default_groups); kfree(fi_mtp); } @@ -1755,6 +1788,8 @@ struct usb_function_instance *alloc_inst_mtp_ptp(bool mtp_config) { struct mtp_instance *fi_mtp; int ret = 0; + struct usb_os_desc *descs[1]; + char *names[1]; fi_mtp = kzalloc(sizeof(*fi_mtp), GFP_KERNEL); if (!fi_mtp) @@ -1762,6 +1797,13 @@ struct usb_function_instance *alloc_inst_mtp_ptp(bool mtp_config) fi_mtp->func_inst.set_inst_name = mtp_set_inst_name; fi_mtp->func_inst.free_func_inst = mtp_free_inst; + fi_mtp->mtp_os_desc.ext_compat_id = fi_mtp->mtp_ext_compat_id; + INIT_LIST_HEAD(&fi_mtp->mtp_os_desc.ext_prop); + descs[0] = &fi_mtp->mtp_os_desc; + names[0] = "MTP"; + usb_os_desc_prepare_interf_dir(&fi_mtp->func_inst.group, 1, + descs, names, THIS_MODULE); + if (mtp_config) { ret = mtp_setup_configfs(fi_mtp); if (ret) { diff --git a/drivers/video/adf/Kconfig b/drivers/video/adf/Kconfig index 33858b73d8bb..2777db48fae0 100644 --- a/drivers/video/adf/Kconfig +++ b/drivers/video/adf/Kconfig @@ -11,4 +11,4 @@ menuconfig ADF_FBDEV menuconfig ADF_MEMBLOCK depends on ADF depends on HAVE_MEMBLOCK - tristate "Helper for using memblocks as buffers in ADF drivers" + bool "Helper for using memblocks as buffers in ADF drivers" diff --git a/drivers/video/adf/Makefile b/drivers/video/adf/Makefile index 78d0915122f4..cdf34a666dc7 100644 --- a/drivers/video/adf/Makefile +++ b/drivers/video/adf/Makefile @@ -2,13 +2,15 @@ ccflags-y := -Idrivers/staging/android CFLAGS_adf.o := -I$(src) -obj-$(CONFIG_ADF) += adf.o \ +obj-$(CONFIG_ADF) += adf_core.o + +adf_core-y := adf.o \ adf_client.o \ adf_fops.o \ adf_format.o \ adf_sysfs.o -obj-$(CONFIG_COMPAT) += adf_fops32.o +adf_core-$(CONFIG_COMPAT) += adf_fops32.o obj-$(CONFIG_ADF_FBDEV) += adf_fbdev.o diff --git a/fs/Kconfig b/fs/Kconfig index 6ce72d8d1ee1..a5d2dc39ba07 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -199,6 +199,7 @@ if MISC_FILESYSTEMS source "fs/adfs/Kconfig" source "fs/affs/Kconfig" source "fs/ecryptfs/Kconfig" +source "fs/sdcardfs/Kconfig" source "fs/hfs/Kconfig" source "fs/hfsplus/Kconfig" source "fs/befs/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index 79f522575cba..3b54070cd629 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -3,7 +3,7 @@ # # 14 Sep 2000, Christoph Hellwig # Rewritten to use lists instead of if-statements. -# +# obj-y := open.o read_write.o file_table.o super.o \ char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ @@ -59,7 +59,7 @@ obj-y += devpts/ obj-$(CONFIG_PROFILING) += dcookies.o obj-$(CONFIG_DLM) += dlm/ - + # Do not add any filesystems before this line obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ @@ -81,6 +81,7 @@ obj-$(CONFIG_ISO9660_FS) += isofs/ obj-$(CONFIG_HFSPLUS_FS) += hfsplus/ # Before hfs to find wrapped HFS+ obj-$(CONFIG_HFS_FS) += hfs/ obj-$(CONFIG_ECRYPT_FS) += ecryptfs/ +obj-$(CONFIG_SDCARD_FS) += sdcardfs/ obj-$(CONFIG_VXFS_FS) += freevxfs/ obj-$(CONFIG_NFS_FS) += nfs/ obj-$(CONFIG_EXPORTFS) += exportfs/ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 3a93755e880f..0c52941dd62c 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -651,7 +651,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top) if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - random_variable = (unsigned long) get_random_int(); + random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } diff --git a/fs/dcache.c b/fs/dcache.c index 18effa378f97..240935d77844 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -3020,6 +3020,7 @@ char *d_absolute_path(const struct path *path, return ERR_PTR(error); return res; } +EXPORT_SYMBOL(d_absolute_path); /* * same as __d_path but appends "(deleted)" for unlinked files. diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index b8d08d0d0a4d..f72f3b25b3f2 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -702,6 +702,8 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, struct fsnotify_group *group; struct inode *inode; struct path path; + struct path alteredpath; + struct path *canonical_path = &path; struct fd f; int ret; unsigned flags = 0; @@ -741,13 +743,22 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, if (ret) goto fput_and_out; + /* support stacked filesystems */ + if(path.dentry && path.dentry->d_op) { + if (path.dentry->d_op->d_canonical_path) { + path.dentry->d_op->d_canonical_path(path.dentry, &alteredpath); + canonical_path = &alteredpath; + path_put(&path); + } + } + /* inode held in place by reference to path; group by fget on fd */ - inode = path.dentry->d_inode; + inode = canonical_path->dentry->d_inode; group = f.file->private_data; /* create/update an inode mark */ ret = inotify_update_watch(group, inode, mask); - path_put(&path); + path_put(canonical_path); fput_and_out: fdput(f); return ret; diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 2429c804cf78..414041342a99 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -554,7 +554,7 @@ static int ramoops_parse_dt(struct platform_device *pdev, static int ramoops_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct ramoops_platform_data *pdata = platform_get_drvdata(pdev); + struct ramoops_platform_data *pdata = pdev->dev.platform_data; struct ramoops_context *cxt = &oops_cxt; size_t dump_mem_sz; phys_addr_t paddr; @@ -666,7 +666,6 @@ static int ramoops_probe(struct platform_device *pdev) cxt->size, (unsigned long long)cxt->phys_addr, cxt->ecc_info.ecc_size, cxt->ecc_info.block_size); - platform_set_drvdata(pdev, pdata); return 0; fail_buf: diff --git a/fs/sdcardfs/Kconfig b/fs/sdcardfs/Kconfig new file mode 100644 index 000000000000..a1c103316ac7 --- /dev/null +++ b/fs/sdcardfs/Kconfig @@ -0,0 +1,13 @@ +config SDCARD_FS + tristate "sdcard file system" + depends on CONFIGFS_FS + default n + help + Sdcardfs is based on Wrapfs file system. + +config SDCARD_FS_FADV_NOACTIVE + bool "sdcardfs fadvise noactive support" + depends on FADV_NOACTIVE + default y + help + Sdcardfs supports fadvise noactive mode. diff --git a/fs/sdcardfs/Makefile b/fs/sdcardfs/Makefile new file mode 100644 index 000000000000..b84fbb2b45a4 --- /dev/null +++ b/fs/sdcardfs/Makefile @@ -0,0 +1,7 @@ +SDCARDFS_VERSION="0.1" + +EXTRA_CFLAGS += -DSDCARDFS_VERSION=\"$(SDCARDFS_VERSION)\" + +obj-$(CONFIG_SDCARD_FS) += sdcardfs.o + +sdcardfs-y := dentry.o file.o inode.o main.o super.o lookup.o mmap.o packagelist.o derived_perm.o diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c new file mode 100644 index 000000000000..ba165ef11e27 --- /dev/null +++ b/fs/sdcardfs/dentry.c @@ -0,0 +1,182 @@ +/* + * fs/sdcardfs/dentry.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include "linux/ctype.h" + +/* + * returns: -ERRNO if error (returned to user) + * 0: tell VFS to invalidate dentry + * 1: dentry is valid + */ +static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + int err = 1; + struct path parent_lower_path, lower_path; + struct dentry *parent_dentry = NULL; + struct dentry *parent_lower_dentry = NULL; + struct dentry *lower_cur_parent_dentry = NULL; + struct dentry *lower_dentry = NULL; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + spin_lock(&dentry->d_lock); + if (IS_ROOT(dentry)) { + spin_unlock(&dentry->d_lock); + return 1; + } + spin_unlock(&dentry->d_lock); + + /* check uninitialized obb_dentry and + * whether the base obbpath has been changed or not */ + if (is_obbpath_invalid(dentry)) { + d_drop(dentry); + return 0; + } + + parent_dentry = dget_parent(dentry); + sdcardfs_get_lower_path(parent_dentry, &parent_lower_path); + sdcardfs_get_real_lower(dentry, &lower_path); + parent_lower_dentry = parent_lower_path.dentry; + lower_dentry = lower_path.dentry; + lower_cur_parent_dentry = dget_parent(lower_dentry); + + spin_lock(&lower_dentry->d_lock); + if (d_unhashed(lower_dentry)) { + spin_unlock(&lower_dentry->d_lock); + d_drop(dentry); + err = 0; + goto out; + } + spin_unlock(&lower_dentry->d_lock); + + if (parent_lower_dentry != lower_cur_parent_dentry) { + d_drop(dentry); + err = 0; + goto out; + } + + if (dentry < lower_dentry) { + spin_lock(&dentry->d_lock); + spin_lock(&lower_dentry->d_lock); + } else { + spin_lock(&lower_dentry->d_lock); + spin_lock(&dentry->d_lock); + } + + if (dentry->d_name.len != lower_dentry->d_name.len) { + __d_drop(dentry); + err = 0; + } else if (strncasecmp(dentry->d_name.name, lower_dentry->d_name.name, + dentry->d_name.len) != 0) { + __d_drop(dentry); + err = 0; + } + + if (dentry < lower_dentry) { + spin_unlock(&lower_dentry->d_lock); + spin_unlock(&dentry->d_lock); + } else { + spin_unlock(&dentry->d_lock); + spin_unlock(&lower_dentry->d_lock); + } + +out: + dput(parent_dentry); + dput(lower_cur_parent_dentry); + sdcardfs_put_lower_path(parent_dentry, &parent_lower_path); + sdcardfs_put_real_lower(dentry, &lower_path); + return err; +} + +static void sdcardfs_d_release(struct dentry *dentry) +{ + /* release and reset the lower paths */ + if(has_graft_path(dentry)) { + sdcardfs_put_reset_orig_path(dentry); + } + sdcardfs_put_reset_lower_path(dentry); + free_dentry_private_data(dentry); + return; +} + +static int sdcardfs_hash_ci(const struct dentry *dentry, + struct qstr *qstr) +{ + /* + * This function is copy of vfat_hashi. + * FIXME Should we support national language? + * Refer to vfat_hashi() + * struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io; + */ + const unsigned char *name; + unsigned int len; + unsigned long hash; + + name = qstr->name; + //len = vfat_striptail_len(qstr); + len = qstr->len; + + hash = init_name_hash(); + while (len--) + //hash = partial_name_hash(nls_tolower(t, *name++), hash); + hash = partial_name_hash(tolower(*name++), hash); + qstr->hash = end_name_hash(hash); + + return 0; +} + +/* + * Case insensitive compare of two vfat names. + */ +static int sdcardfs_cmp_ci(const struct dentry *parent, + const struct dentry *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + /* This function is copy of vfat_cmpi */ + // FIXME Should we support national language? + //struct nls_table *t = MSDOS_SB(parent->d_sb)->nls_io; + //unsigned int alen, blen; + + /* A filename cannot end in '.' or we treat it like it has none */ + /* + alen = vfat_striptail_len(name); + blen = __vfat_striptail_len(len, str); + if (alen == blen) { + if (nls_strnicmp(t, name->name, str, alen) == 0) + return 0; + } + */ + if (name->len == len) { + if (strncasecmp(name->name, str, len) == 0) + return 0; + } + return 1; +} + +const struct dentry_operations sdcardfs_ci_dops = { + .d_revalidate = sdcardfs_d_revalidate, + .d_release = sdcardfs_d_release, + .d_hash = sdcardfs_hash_ci, + .d_compare = sdcardfs_cmp_ci, + .d_canonical_path = sdcardfs_get_real_lower, +}; + diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c new file mode 100644 index 000000000000..128b3e56851f --- /dev/null +++ b/fs/sdcardfs/derived_perm.c @@ -0,0 +1,265 @@ +/* + * fs/sdcardfs/derived_perm.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +/* copy derived state from parent inode */ +static void inherit_derived_state(struct inode *parent, struct inode *child) +{ + struct sdcardfs_inode_info *pi = SDCARDFS_I(parent); + struct sdcardfs_inode_info *ci = SDCARDFS_I(child); + + ci->perm = PERM_INHERIT; + ci->userid = pi->userid; + ci->d_uid = pi->d_uid; + ci->under_android = pi->under_android; +} + +/* helper function for derived state */ +void setup_derived_state(struct inode *inode, perm_t perm, + userid_t userid, uid_t uid, bool under_android) +{ + struct sdcardfs_inode_info *info = SDCARDFS_I(inode); + + info->perm = perm; + info->userid = userid; + info->d_uid = uid; + info->under_android = under_android; +} + +/* While renaming, there is a point where we want the path from dentry, but the name from newdentry */ +void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, struct dentry *newdentry) +{ + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct sdcardfs_inode_info *info = SDCARDFS_I(dentry->d_inode); + struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + appid_t appid; + + /* By default, each inode inherits from its parent. + * the properties are maintained on its private fields + * because the inode attributes will be modified with that of + * its lower inode. + * The derived state will be updated on the last + * stage of each system call by fix_derived_permission(inode). + */ + + inherit_derived_state(parent->d_inode, dentry->d_inode); + + /* Derive custom permissions based on parent and current node */ + switch (parent_info->perm) { + case PERM_INHERIT: + /* Already inherited above */ + break; + case PERM_PRE_ROOT: + /* Legacy internal layout places users at top level */ + info->perm = PERM_ROOT; + info->userid = simple_strtoul(newdentry->d_name.name, NULL, 10); + break; + case PERM_ROOT: + /* Assume masked off by default. */ + if (!strcasecmp(newdentry->d_name.name, "Android")) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID; + info->under_android = true; + } + break; + case PERM_ANDROID: + if (!strcasecmp(newdentry->d_name.name, "data")) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_DATA; + } else if (!strcasecmp(newdentry->d_name.name, "obb")) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_OBB; + /* Single OBB directory is always shared */ + } else if (!strcasecmp(newdentry->d_name.name, "media")) { + /* App-specific directories inside; let anyone traverse */ + info->perm = PERM_ANDROID_MEDIA; + } + break; + case PERM_ANDROID_DATA: + case PERM_ANDROID_OBB: + case PERM_ANDROID_MEDIA: + appid = get_appid(sbi->pkgl_id, newdentry->d_name.name); + if (appid != 0) { + info->d_uid = multiuser_get_uid(parent_info->userid, appid); + } + break; + } +} + +void get_derived_permission(struct dentry *parent, struct dentry *dentry) +{ + get_derived_permission_new(parent, dentry, dentry); +} + +void get_derive_permissions_recursive(struct dentry *parent) { + struct dentry *dentry; + list_for_each_entry(dentry, &parent->d_subdirs, d_child) { + if (dentry && dentry->d_inode) { + mutex_lock(&dentry->d_inode->i_mutex); + get_derived_permission(parent, dentry); + fix_derived_permission(dentry->d_inode); + get_derive_permissions_recursive(dentry); + mutex_unlock(&dentry->d_inode->i_mutex); + } + } +} + +/* main function for updating derived permission */ +inline void update_derived_permission_lock(struct dentry *dentry) +{ + struct dentry *parent; + + if(!dentry || !dentry->d_inode) { + printk(KERN_ERR "sdcardfs: %s: invalid dentry\n", __func__); + return; + } + /* FIXME: + * 1. need to check whether the dentry is updated or not + * 2. remove the root dentry update + */ + mutex_lock(&dentry->d_inode->i_mutex); + if(IS_ROOT(dentry)) { + //setup_default_pre_root_state(dentry->d_inode); + } else { + parent = dget_parent(dentry); + if(parent) { + get_derived_permission(parent, dentry); + dput(parent); + } + } + fix_derived_permission(dentry->d_inode); + mutex_unlock(&dentry->d_inode->i_mutex); +} + +int need_graft_path(struct dentry *dentry) +{ + int ret = 0; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + if(parent_info->perm == PERM_ANDROID && + !strcasecmp(dentry->d_name.name, "obb")) { + + /* /Android/obb is the base obbpath of DERIVED_UNIFIED */ + if(!(sbi->options.multiuser == false + && parent_info->userid == 0)) { + ret = 1; + } + } + dput(parent); + return ret; +} + +int is_obbpath_invalid(struct dentry *dent) +{ + int ret = 0; + struct sdcardfs_dentry_info *di = SDCARDFS_D(dent); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dent->d_sb); + char *path_buf, *obbpath_s; + + /* check the base obbpath has been changed. + * this routine can check an uninitialized obb dentry as well. + * regarding the uninitialized obb, refer to the sdcardfs_mkdir() */ + spin_lock(&di->lock); + if(di->orig_path.dentry) { + if(!di->lower_path.dentry) { + ret = 1; + } else { + path_get(&di->lower_path); + //lower_parent = lock_parent(lower_path->dentry); + + path_buf = kmalloc(PATH_MAX, GFP_ATOMIC); + if(!path_buf) { + ret = 1; + printk(KERN_ERR "sdcardfs: fail to allocate path_buf in %s.\n", __func__); + } else { + obbpath_s = d_path(&di->lower_path, path_buf, PATH_MAX); + if (d_unhashed(di->lower_path.dentry) || + strcasecmp(sbi->obbpath_s, obbpath_s)) { + ret = 1; + } + kfree(path_buf); + } + + //unlock_dir(lower_parent); + path_put(&di->lower_path); + } + } + spin_unlock(&di->lock); + return ret; +} + +int is_base_obbpath(struct dentry *dentry) +{ + int ret = 0; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_inode_info *parent_info= SDCARDFS_I(parent->d_inode); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + spin_lock(&SDCARDFS_D(dentry)->lock); + if (sbi->options.multiuser) { + if(parent_info->perm == PERM_PRE_ROOT && + !strcasecmp(dentry->d_name.name, "obb")) { + ret = 1; + } + } else if (parent_info->perm == PERM_ANDROID && + !strcasecmp(dentry->d_name.name, "obb")) { + ret = 1; + } + spin_unlock(&SDCARDFS_D(dentry)->lock); + return ret; +} + +/* The lower_path will be stored to the dentry's orig_path + * and the base obbpath will be copyed to the lower_path variable. + * if an error returned, there's no change in the lower_path + * returns: -ERRNO if error (0: no error) */ +int setup_obb_dentry(struct dentry *dentry, struct path *lower_path) +{ + int err = 0; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct path obbpath; + + /* A local obb dentry must have its own orig_path to support rmdir + * and mkdir of itself. Usually, we expect that the sbi->obbpath + * is avaiable on this stage. */ + sdcardfs_set_orig_path(dentry, lower_path); + + err = kern_path(sbi->obbpath_s, + LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &obbpath); + + if(!err) { + /* the obbpath base has been found */ + printk(KERN_INFO "sdcardfs: the sbi->obbpath is found\n"); + pathcpy(lower_path, &obbpath); + } else { + /* if the sbi->obbpath is not available, we can optionally + * setup the lower_path with its orig_path. + * but, the current implementation just returns an error + * because the sdcard daemon also regards this case as + * a lookup fail. */ + printk(KERN_INFO "sdcardfs: the sbi->obbpath is not available\n"); + } + return err; +} + + diff --git a/fs/sdcardfs/file.c b/fs/sdcardfs/file.c new file mode 100644 index 000000000000..c249fa982d3c --- /dev/null +++ b/fs/sdcardfs/file.c @@ -0,0 +1,356 @@ +/* + * fs/sdcardfs/file.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE +#include +#endif + +static ssize_t sdcardfs_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + int err; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE + struct backing_dev_info *bdi; +#endif + + lower_file = sdcardfs_lower_file(file); + +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE + if (file->f_mode & FMODE_NOACTIVE) { + if (!(lower_file->f_mode & FMODE_NOACTIVE)) { + bdi = lower_file->f_mapping->backing_dev_info; + lower_file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&lower_file->f_lock); + lower_file->f_mode |= FMODE_NOACTIVE; + spin_unlock(&lower_file->f_lock); + } + } +#endif + + err = vfs_read(lower_file, buf, count, ppos); + /* update our inode atime upon a successful lower read */ + if (err >= 0) + fsstack_copy_attr_atime(d_inode(dentry), + file_inode(lower_file)); + + return err; +} + +static ssize_t sdcardfs_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + int err; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + + /* check disk space */ + if (!check_min_free_space(dentry, count, 0)) { + printk(KERN_INFO "No minimum free space.\n"); + return -ENOSPC; + } + + lower_file = sdcardfs_lower_file(file); + err = vfs_write(lower_file, buf, count, ppos); + /* update our inode times+sizes upon a successful lower write */ + if (err >= 0) { + fsstack_copy_inode_size(d_inode(dentry), + file_inode(lower_file)); + fsstack_copy_attr_times(d_inode(dentry), + file_inode(lower_file)); + } + + return err; +} + +static int sdcardfs_readdir(struct file *file, struct dir_context *ctx) +{ + int err; + struct file *lower_file = NULL; + struct dentry *dentry = file->f_path.dentry; + + lower_file = sdcardfs_lower_file(file); + + lower_file->f_pos = file->f_pos; + err = iterate_dir(lower_file, ctx); + file->f_pos = lower_file->f_pos; + if (err >= 0) /* copy the atime */ + fsstack_copy_attr_atime(d_inode(dentry), + file_inode(lower_file)); + return err; +} + +static long sdcardfs_unlocked_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long err = -ENOTTY; + struct file *lower_file; + + lower_file = sdcardfs_lower_file(file); + + /* XXX: use vfs_ioctl if/when VFS exports it */ + if (!lower_file || !lower_file->f_op) + goto out; + if (lower_file->f_op->unlocked_ioctl) + err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg); + +out: + return err; +} + +#ifdef CONFIG_COMPAT +static long sdcardfs_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long err = -ENOTTY; + struct file *lower_file; + + lower_file = sdcardfs_lower_file(file); + + /* XXX: use vfs_ioctl if/when VFS exports it */ + if (!lower_file || !lower_file->f_op) + goto out; + if (lower_file->f_op->compat_ioctl) + err = lower_file->f_op->compat_ioctl(lower_file, cmd, arg); + +out: + return err; +} +#endif + +static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err = 0; + bool willwrite; + struct file *lower_file; + const struct vm_operations_struct *saved_vm_ops = NULL; + + /* this might be deferred to mmap's writepage */ + willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags); + + /* + * File systems which do not implement ->writepage may use + * generic_file_readonly_mmap as their ->mmap op. If you call + * generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL. + * But we cannot call the lower ->mmap op, so we can't tell that + * writeable mappings won't work. Therefore, our only choice is to + * check if the lower file system supports the ->writepage, and if + * not, return EINVAL (the same error that + * generic_file_readonly_mmap returns in that case). + */ + lower_file = sdcardfs_lower_file(file); + if (willwrite && !lower_file->f_mapping->a_ops->writepage) { + err = -EINVAL; + printk(KERN_ERR "sdcardfs: lower file system does not " + "support writeable mmap\n"); + goto out; + } + + /* + * find and save lower vm_ops. + * + * XXX: the VFS should have a cleaner way of finding the lower vm_ops + */ + if (!SDCARDFS_F(file)->lower_vm_ops) { + err = lower_file->f_op->mmap(lower_file, vma); + if (err) { + printk(KERN_ERR "sdcardfs: lower mmap failed %d\n", err); + goto out; + } + saved_vm_ops = vma->vm_ops; /* save: came from lower ->mmap */ + err = do_munmap(current->mm, vma->vm_start, + vma->vm_end - vma->vm_start); + if (err) { + printk(KERN_ERR "sdcardfs: do_munmap failed %d\n", err); + goto out; + } + } + + /* + * Next 3 lines are all I need from generic_file_mmap. I definitely + * don't want its test for ->readpage which returns -ENOEXEC. + */ + file_accessed(file); + vma->vm_ops = &sdcardfs_vm_ops; + + file->f_mapping->a_ops = &sdcardfs_aops; /* set our aops */ + if (!SDCARDFS_F(file)->lower_vm_ops) /* save for our ->fault */ + SDCARDFS_F(file)->lower_vm_ops = saved_vm_ops; + +out: + return err; +} + +static int sdcardfs_open(struct inode *inode, struct file *file) +{ + int err = 0; + struct file *lower_file = NULL; + struct path lower_path; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + const struct cred *saved_cred = NULL; + + /* don't open unhashed/deleted files */ + if (d_unhashed(dentry)) { + err = -ENOENT; + goto out_err; + } + + if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_err; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(sbi, saved_cred); + + file->private_data = + kzalloc(sizeof(struct sdcardfs_file_info), GFP_KERNEL); + if (!SDCARDFS_F(file)) { + err = -ENOMEM; + goto out_revert_cred; + } + + /* open lower object and link sdcardfs's file struct to lower's */ + sdcardfs_get_lower_path(file->f_path.dentry, &lower_path); + lower_file = dentry_open(&lower_path, file->f_flags, current_cred()); + path_put(&lower_path); + if (IS_ERR(lower_file)) { + err = PTR_ERR(lower_file); + lower_file = sdcardfs_lower_file(file); + if (lower_file) { + sdcardfs_set_lower_file(file, NULL); + fput(lower_file); /* fput calls dput for lower_dentry */ + } + } else { + sdcardfs_set_lower_file(file, lower_file); + } + + if (err) + kfree(SDCARDFS_F(file)); + else { + sdcardfs_copy_and_fix_attrs(inode, sdcardfs_lower_inode(inode)); + } + +out_revert_cred: + REVERT_CRED(saved_cred); +out_err: + dput(parent); + return err; +} + +static int sdcardfs_flush(struct file *file, fl_owner_t id) +{ + int err = 0; + struct file *lower_file = NULL; + + lower_file = sdcardfs_lower_file(file); + if (lower_file && lower_file->f_op && lower_file->f_op->flush) { + filemap_write_and_wait(file->f_mapping); + err = lower_file->f_op->flush(lower_file, id); + } + + return err; +} + +/* release all lower object references & free the file info structure */ +static int sdcardfs_file_release(struct inode *inode, struct file *file) +{ + struct file *lower_file; + + lower_file = sdcardfs_lower_file(file); + if (lower_file) { + sdcardfs_set_lower_file(file, NULL); + fput(lower_file); + } + + kfree(SDCARDFS_F(file)); + return 0; +} + +static int sdcardfs_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct file *lower_file; + struct path lower_path; + struct dentry *dentry = file->f_path.dentry; + + err = __generic_file_fsync(file, start, end, datasync); + if (err) + goto out; + + lower_file = sdcardfs_lower_file(file); + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_fsync_range(lower_file, start, end, datasync); + sdcardfs_put_lower_path(dentry, &lower_path); +out: + return err; +} + +static int sdcardfs_fasync(int fd, struct file *file, int flag) +{ + int err = 0; + struct file *lower_file = NULL; + + lower_file = sdcardfs_lower_file(file); + if (lower_file->f_op && lower_file->f_op->fasync) + err = lower_file->f_op->fasync(fd, lower_file, flag); + + return err; +} + +const struct file_operations sdcardfs_main_fops = { + .llseek = generic_file_llseek, + .read = sdcardfs_read, + .write = sdcardfs_write, + .unlocked_ioctl = sdcardfs_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = sdcardfs_compat_ioctl, +#endif + .mmap = sdcardfs_mmap, + .open = sdcardfs_open, + .flush = sdcardfs_flush, + .release = sdcardfs_file_release, + .fsync = sdcardfs_fsync, + .fasync = sdcardfs_fasync, +}; + +/* trimmed directory options */ +const struct file_operations sdcardfs_dir_fops = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate = sdcardfs_readdir, + .unlocked_ioctl = sdcardfs_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = sdcardfs_compat_ioctl, +#endif + .open = sdcardfs_open, + .release = sdcardfs_file_release, + .flush = sdcardfs_flush, + .fsync = sdcardfs_fsync, + .fasync = sdcardfs_fasync, +}; diff --git a/fs/sdcardfs/inode.c b/fs/sdcardfs/inode.c new file mode 100644 index 000000000000..2528da0d3ae1 --- /dev/null +++ b/fs/sdcardfs/inode.c @@ -0,0 +1,802 @@ +/* + * fs/sdcardfs/inode.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +/* Do not directly use this function. Use OVERRIDE_CRED() instead. */ +const struct cred * override_fsids(struct sdcardfs_sb_info* sbi) +{ + struct cred * cred; + const struct cred * old_cred; + + cred = prepare_creds(); + if (!cred) + return NULL; + + cred->fsuid = make_kuid(&init_user_ns, sbi->options.fs_low_uid); + cred->fsgid = make_kgid(&init_user_ns, sbi->options.fs_low_gid); + + old_cred = override_creds(cred); + + return old_cred; +} + +/* Do not directly use this function, use REVERT_CRED() instead. */ +void revert_fsids(const struct cred * old_cred) +{ + const struct cred * cur_cred; + + cur_cred = current->cred; + revert_creds(old_cred); + put_cred(cur_cred); +} + +static int sdcardfs_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool want_excl) +{ + int err; + struct dentry *lower_dentry; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + const struct cred *saved_cred = NULL; + + if(!check_caller_access_to_name(dir, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_parent_dentry = lock_parent(lower_dentry); + + /* set last 16bytes of mode field to 0664 */ + mode = (mode & S_IFMT) | 00664; + err = vfs_create(d_inode(lower_parent_dentry), lower_dentry, mode, want_excl); + if (err) + goto out; + + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, SDCARDFS_I(dir)->userid); + if (err) + goto out; + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + +out: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_link(struct dentry *old_dentry, struct inode *dir, + struct dentry *new_dentry) +{ + struct dentry *lower_old_dentry; + struct dentry *lower_new_dentry; + struct dentry *lower_dir_dentry; + u64 file_size_save; + int err; + struct path lower_old_path, lower_new_path; + + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb)); + + file_size_save = i_size_read(d_inode(old_dentry)); + sdcardfs_get_lower_path(old_dentry, &lower_old_path); + sdcardfs_get_lower_path(new_dentry, &lower_new_path); + lower_old_dentry = lower_old_path.dentry; + lower_new_dentry = lower_new_path.dentry; + lower_dir_dentry = lock_parent(lower_new_dentry); + + err = vfs_link(lower_old_dentry, d_inode(lower_dir_dentry), + lower_new_dentry, NULL); + if (err || !d_inode(lower_new_dentry)) + goto out; + + err = sdcardfs_interpose(new_dentry, dir->i_sb, &lower_new_path); + if (err) + goto out; + fsstack_copy_attr_times(dir, d_inode(lower_new_dentry)); + fsstack_copy_inode_size(dir, d_inode(lower_new_dentry)); + set_nlink(d_inode(old_dentry), + sdcardfs_lower_inode(d_inode(old_dentry))->i_nlink); + i_size_write(d_inode(new_dentry), file_size_save); +out: + unlock_dir(lower_dir_dentry); + sdcardfs_put_lower_path(old_dentry, &lower_old_path); + sdcardfs_put_lower_path(new_dentry, &lower_new_path); + REVERT_CRED(); + return err; +} +#endif + +static int sdcardfs_unlink(struct inode *dir, struct dentry *dentry) +{ + int err; + struct dentry *lower_dentry; + struct inode *lower_dir_inode = sdcardfs_lower_inode(dir); + struct dentry *lower_dir_dentry; + struct path lower_path; + const struct cred *saved_cred = NULL; + + if(!check_caller_access_to_name(dir, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + dget(lower_dentry); + lower_dir_dentry = lock_parent(lower_dentry); + + err = vfs_unlink(lower_dir_inode, lower_dentry, NULL); + + /* + * Note: unlinking on top of NFS can cause silly-renamed files. + * Trying to delete such files results in EBUSY from NFS + * below. Silly-renamed files will get deleted by NFS later on, so + * we just need to detect them here and treat such EBUSY errors as + * if the upper file was successfully deleted. + */ + if (err == -EBUSY && lower_dentry->d_flags & DCACHE_NFSFS_RENAMED) + err = 0; + if (err) + goto out; + fsstack_copy_attr_times(dir, lower_dir_inode); + fsstack_copy_inode_size(dir, lower_dir_inode); + set_nlink(d_inode(dentry), + sdcardfs_lower_inode(d_inode(dentry))->i_nlink); + d_inode(dentry)->i_ctime = dir->i_ctime; + d_drop(dentry); /* this is needed, else LTP fails (VFS won't do it) */ +out: + unlock_dir(lower_dir_dentry); + dput(lower_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_symlink(struct inode *dir, struct dentry *dentry, + const char *symname) +{ + int err; + struct dentry *lower_dentry; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb)); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_parent_dentry = lock_parent(lower_dentry); + + err = vfs_symlink(d_inode(lower_parent_dentry), lower_dentry, symname); + if (err) + goto out; + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path); + if (err) + goto out; + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + +out: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(); + return err; +} +#endif + +static int touch(char *abs_path, mode_t mode) { + struct file *filp = filp_open(abs_path, O_RDWR|O_CREAT|O_EXCL|O_NOFOLLOW, mode); + if (IS_ERR(filp)) { + if (PTR_ERR(filp) == -EEXIST) { + return 0; + } + else { + printk(KERN_ERR "sdcardfs: failed to open(%s): %ld\n", + abs_path, PTR_ERR(filp)); + return PTR_ERR(filp); + } + } + filp_close(filp, current->files); + return 0; +} + +static int sdcardfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int err; + int make_nomedia_in_obb = 0; + struct dentry *lower_dentry; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + const struct cred *saved_cred = NULL; + struct sdcardfs_inode_info *pi = SDCARDFS_I(dir); + char *page_buf; + char *nomedia_dir_name; + char *nomedia_fullpath; + int fullpath_namelen; + int touch_err = 0; + + if(!check_caller_access_to_name(dir, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + + /* check disk space */ + if (!check_min_free_space(dentry, 0, 1)) { + printk(KERN_INFO "sdcardfs: No minimum free space.\n"); + err = -ENOSPC; + goto out_revert; + } + + /* the lower_dentry is negative here */ + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_parent_dentry = lock_parent(lower_dentry); + + /* set last 16bytes of mode field to 0775 */ + mode = (mode & S_IFMT) | 00775; + err = vfs_mkdir(d_inode(lower_parent_dentry), lower_dentry, mode); + + if (err) + goto out; + + /* if it is a local obb dentry, setup it with the base obbpath */ + if(need_graft_path(dentry)) { + + err = setup_obb_dentry(dentry, &lower_path); + if(err) { + /* if the sbi->obbpath is not available, the lower_path won't be + * changed by setup_obb_dentry() but the lower path is saved to + * its orig_path. this dentry will be revalidated later. + * but now, the lower_path should be NULL */ + sdcardfs_put_reset_lower_path(dentry); + + /* the newly created lower path which saved to its orig_path or + * the lower_path is the base obbpath. + * therefore, an additional path_get is required */ + path_get(&lower_path); + } else + make_nomedia_in_obb = 1; + } + + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, pi->userid); + if (err) + goto out; + + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + /* update number of links on parent directory */ + set_nlink(dir, sdcardfs_lower_inode(dir)->i_nlink); + + if ((!sbi->options.multiuser) && (!strcasecmp(dentry->d_name.name, "obb")) + && (pi->perm == PERM_ANDROID) && (pi->userid == 0)) + make_nomedia_in_obb = 1; + + /* When creating /Android/data and /Android/obb, mark them as .nomedia */ + if (make_nomedia_in_obb || + ((pi->perm == PERM_ANDROID) && (!strcasecmp(dentry->d_name.name, "data")))) { + + page_buf = (char *)__get_free_page(GFP_KERNEL); + if (!page_buf) { + printk(KERN_ERR "sdcardfs: failed to allocate page buf\n"); + goto out; + } + + nomedia_dir_name = d_absolute_path(&lower_path, page_buf, PAGE_SIZE); + if (IS_ERR(nomedia_dir_name)) { + free_page((unsigned long)page_buf); + printk(KERN_ERR "sdcardfs: failed to get .nomedia dir name\n"); + goto out; + } + + fullpath_namelen = page_buf + PAGE_SIZE - nomedia_dir_name - 1; + fullpath_namelen += strlen("/.nomedia"); + nomedia_fullpath = kzalloc(fullpath_namelen + 1, GFP_KERNEL); + if (!nomedia_fullpath) { + free_page((unsigned long)page_buf); + printk(KERN_ERR "sdcardfs: failed to allocate .nomedia fullpath buf\n"); + goto out; + } + + strcpy(nomedia_fullpath, nomedia_dir_name); + free_page((unsigned long)page_buf); + strcat(nomedia_fullpath, "/.nomedia"); + touch_err = touch(nomedia_fullpath, 0664); + if (touch_err) { + printk(KERN_ERR "sdcardfs: failed to touch(%s): %d\n", + nomedia_fullpath, touch_err); + kfree(nomedia_fullpath); + goto out; + } + kfree(nomedia_fullpath); + } +out: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); +out_revert: + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +static int sdcardfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct dentry *lower_dentry; + struct dentry *lower_dir_dentry; + int err; + struct path lower_path; + const struct cred *saved_cred = NULL; + + if(!check_caller_access_to_name(dir, dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb), saved_cred); + + /* sdcardfs_get_real_lower(): in case of remove an user's obb dentry + * the dentry on the original path should be deleted. */ + sdcardfs_get_real_lower(dentry, &lower_path); + + lower_dentry = lower_path.dentry; + lower_dir_dentry = lock_parent(lower_dentry); + + err = vfs_rmdir(d_inode(lower_dir_dentry), lower_dentry); + if (err) + goto out; + + d_drop(dentry); /* drop our dentry on success (why not VFS's job?) */ + if (d_inode(dentry)) + clear_nlink(d_inode(dentry)); + fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry)); + fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry)); + set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink); + +out: + unlock_dir(lower_dir_dentry); + sdcardfs_put_real_lower(dentry, &lower_path); + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t dev) +{ + int err; + struct dentry *lower_dentry; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + + OVERRIDE_CRED(SDCARDFS_SB(dir->i_sb)); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_parent_dentry = lock_parent(lower_dentry); + + err = vfs_mknod(d_inode(lower_parent_dentry), lower_dentry, mode, dev); + if (err) + goto out; + + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path); + if (err) + goto out; + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + +out: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + REVERT_CRED(); + return err; +} +#endif + +/* + * The locking rules in sdcardfs_rename are complex. We could use a simpler + * superblock-level name-space lock for renames and copy-ups. + */ +static int sdcardfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + int err = 0; + struct dentry *lower_old_dentry = NULL; + struct dentry *lower_new_dentry = NULL; + struct dentry *lower_old_dir_dentry = NULL; + struct dentry *lower_new_dir_dentry = NULL; + struct dentry *trap = NULL; + struct dentry *new_parent = NULL; + struct path lower_old_path, lower_new_path; + const struct cred *saved_cred = NULL; + + if(!check_caller_access_to_name(old_dir, old_dentry->d_name.name) || + !check_caller_access_to_name(new_dir, new_dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " new_dentry: %s, task:%s\n", + __func__, new_dentry->d_name.name, current->comm); + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + OVERRIDE_CRED(SDCARDFS_SB(old_dir->i_sb), saved_cred); + + sdcardfs_get_real_lower(old_dentry, &lower_old_path); + sdcardfs_get_lower_path(new_dentry, &lower_new_path); + lower_old_dentry = lower_old_path.dentry; + lower_new_dentry = lower_new_path.dentry; + lower_old_dir_dentry = dget_parent(lower_old_dentry); + lower_new_dir_dentry = dget_parent(lower_new_dentry); + + trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + /* source should not be ancestor of target */ + if (trap == lower_old_dentry) { + err = -EINVAL; + goto out; + } + /* target should not be ancestor of source */ + if (trap == lower_new_dentry) { + err = -ENOTEMPTY; + goto out; + } + + err = vfs_rename(d_inode(lower_old_dir_dentry), lower_old_dentry, + d_inode(lower_new_dir_dentry), lower_new_dentry, + NULL, 0); + if (err) + goto out; + + /* Copy attrs from lower dir, but i_uid/i_gid */ + sdcardfs_copy_and_fix_attrs(new_dir, d_inode(lower_new_dir_dentry)); + fsstack_copy_inode_size(new_dir, d_inode(lower_new_dir_dentry)); + + if (new_dir != old_dir) { + sdcardfs_copy_and_fix_attrs(old_dir, d_inode(lower_old_dir_dentry)); + fsstack_copy_inode_size(old_dir, d_inode(lower_old_dir_dentry)); + + /* update the derived permission of the old_dentry + * with its new parent + */ + new_parent = dget_parent(new_dentry); + if(new_parent) { + if(d_inode(old_dentry)) { + update_derived_permission_lock(old_dentry); + } + dput(new_parent); + } + } + /* At this point, not all dentry information has been moved, so + * we pass along new_dentry for the name.*/ + mutex_lock(&d_inode(old_dentry)->i_mutex); + get_derived_permission_new(new_dentry->d_parent, old_dentry, new_dentry); + fix_derived_permission(d_inode(old_dentry)); + get_derive_permissions_recursive(old_dentry); + mutex_unlock(&d_inode(old_dentry)->i_mutex); +out: + unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + dput(lower_old_dir_dentry); + dput(lower_new_dir_dentry); + sdcardfs_put_real_lower(old_dentry, &lower_old_path); + sdcardfs_put_lower_path(new_dentry, &lower_new_path); + REVERT_CRED(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +{ + int err; + struct dentry *lower_dentry; + struct path lower_path; + /* XXX readlink does not requires overriding credential */ + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + if (!d_inode(lower_dentry)->i_op || + !d_inode(lower_dentry)->i_op->readlink) { + err = -EINVAL; + goto out; + } + + err = d_inode(lower_dentry)->i_op->readlink(lower_dentry, + buf, bufsiz); + if (err < 0) + goto out; + fsstack_copy_attr_atime(d_inode(dentry), d_inode(lower_dentry)); + +out: + sdcardfs_put_lower_path(dentry, &lower_path); + return err; +} +#endif + +#if 0 +static const char *sdcardfs_follow_link(struct dentry *dentry, void **cookie) +{ + char *buf; + int len = PAGE_SIZE, err; + mm_segment_t old_fs; + + /* This is freed by the put_link method assuming a successful call. */ + buf = kmalloc(len, GFP_KERNEL); + if (!buf) { + buf = ERR_PTR(-ENOMEM); + return buf; + } + + /* read the symlink, and then we will follow it */ + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = sdcardfs_readlink(dentry, buf, len); + set_fs(old_fs); + if (err < 0) { + kfree(buf); + buf = ERR_PTR(err); + } else { + buf[err] = '\0'; + } + return *cookie = buf; +} +#endif + +static int sdcardfs_permission(struct inode *inode, int mask) +{ + int err; + + /* + * Permission check on sdcardfs inode. + * Calling process should have AID_SDCARD_RW permission + */ + err = generic_permission(inode, mask); + + /* XXX + * Original sdcardfs code calls inode_permission(lower_inode,.. ) + * for checking inode permission. But doing such things here seems + * duplicated work, because the functions called after this func, + * such as vfs_create, vfs_unlink, vfs_rename, and etc, + * does exactly same thing, i.e., they calls inode_permission(). + * So we just let they do the things. + * If there are any security hole, just uncomment following if block. + */ +#if 0 + if (!err) { + /* + * Permission check on lower_inode(=EXT4). + * we check it with AID_MEDIA_RW permission + */ + struct inode *lower_inode; + OVERRIDE_CRED(SDCARDFS_SB(inode->sb)); + + lower_inode = sdcardfs_lower_inode(inode); + err = inode_permission(lower_inode, mask); + + REVERT_CRED(); + } +#endif + return err; + +} + +static int sdcardfs_setattr(struct dentry *dentry, struct iattr *ia) +{ + int err; + struct dentry *lower_dentry; + struct inode *inode; + struct inode *lower_inode; + struct path lower_path; + struct iattr lower_ia; + struct dentry *parent; + + inode = d_inode(dentry); + + /* + * Check if user has permission to change inode. We don't check if + * this user can change the lower inode: that should happen when + * calling notify_change on the lower inode. + */ + err = inode_change_ok(inode, ia); + + /* no vfs_XXX operations required, cred overriding will be skipped. wj*/ + if (!err) { + /* check the Android group ID */ + parent = dget_parent(dentry); + if(!check_caller_access_to_name(d_inode(parent), dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + err = -EACCES; + } + dput(parent); + } + + if (err) + goto out_err; + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_inode = sdcardfs_lower_inode(inode); + + /* prepare our own lower struct iattr (with the lower file) */ + memcpy(&lower_ia, ia, sizeof(lower_ia)); + if (ia->ia_valid & ATTR_FILE) + lower_ia.ia_file = sdcardfs_lower_file(ia->ia_file); + + lower_ia.ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE); + + /* + * If shrinking, first truncate upper level to cancel writing dirty + * pages beyond the new eof; and also if its' maxbytes is more + * limiting (fail with -EFBIG before making any change to the lower + * level). There is no need to vmtruncate the upper level + * afterwards in the other cases: we fsstack_copy_inode_size from + * the lower level. + */ + if (current->mm) + down_write(¤t->mm->mmap_sem); + if (ia->ia_valid & ATTR_SIZE) { + err = inode_newsize_ok(inode, ia->ia_size); + if (err) { + if (current->mm) + up_write(¤t->mm->mmap_sem); + goto out; + } + truncate_setsize(inode, ia->ia_size); + } + + /* + * mode change is for clearing setuid/setgid bits. Allow lower fs + * to interpret this in its own way. + */ + if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + lower_ia.ia_valid &= ~ATTR_MODE; + + /* notify the (possibly copied-up) lower inode */ + /* + * Note: we use d_inode(lower_dentry), because lower_inode may be + * unlinked (no inode->i_sb and i_ino==0. This happens if someone + * tries to open(), unlink(), then ftruncate() a file. + */ + mutex_lock(&d_inode(lower_dentry)->i_mutex); + err = notify_change(lower_dentry, &lower_ia, /* note: lower_ia */ + NULL); + mutex_unlock(&d_inode(lower_dentry)->i_mutex); + if (current->mm) + up_write(¤t->mm->mmap_sem); + if (err) + goto out; + + /* get attributes from the lower inode and update derived permissions */ + sdcardfs_copy_and_fix_attrs(inode, lower_inode); + + /* + * Not running fsstack_copy_inode_size(inode, lower_inode), because + * VFS should update our inode size, and notify_change on + * lower_inode should update its size. + */ + +out: + sdcardfs_put_lower_path(dentry, &lower_path); +out_err: + return err; +} + +static int sdcardfs_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct dentry *lower_dentry; + struct inode *inode; + struct inode *lower_inode; + struct path lower_path; + struct dentry *parent; + + parent = dget_parent(dentry); + if(!check_caller_access_to_name(d_inode(parent), dentry->d_name.name)) { + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + dput(parent); + return -EACCES; + } + dput(parent); + + inode = d_inode(dentry); + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_inode = sdcardfs_lower_inode(inode); + + + sdcardfs_copy_and_fix_attrs(inode, lower_inode); + fsstack_copy_inode_size(inode, lower_inode); + + + generic_fillattr(inode, stat); + sdcardfs_put_lower_path(dentry, &lower_path); + return 0; +} + +const struct inode_operations sdcardfs_symlink_iops = { + .permission = sdcardfs_permission, + .setattr = sdcardfs_setattr, + /* XXX Following operations are implemented, + * but FUSE(sdcard) or FAT does not support them + * These methods are *NOT* perfectly tested. + .readlink = sdcardfs_readlink, + .follow_link = sdcardfs_follow_link, + .put_link = kfree_put_link, + */ +}; + +const struct inode_operations sdcardfs_dir_iops = { + .create = sdcardfs_create, + .lookup = sdcardfs_lookup, +#if 0 + .permission = sdcardfs_permission, +#endif + .unlink = sdcardfs_unlink, + .mkdir = sdcardfs_mkdir, + .rmdir = sdcardfs_rmdir, + .rename = sdcardfs_rename, + .setattr = sdcardfs_setattr, + .getattr = sdcardfs_getattr, + /* XXX Following operations are implemented, + * but FUSE(sdcard) or FAT does not support them + * These methods are *NOT* perfectly tested. + .symlink = sdcardfs_symlink, + .link = sdcardfs_link, + .mknod = sdcardfs_mknod, + */ +}; + +const struct inode_operations sdcardfs_main_iops = { + .permission = sdcardfs_permission, + .setattr = sdcardfs_setattr, + .getattr = sdcardfs_getattr, +}; diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c new file mode 100644 index 000000000000..a01b06a514fd --- /dev/null +++ b/fs/sdcardfs/lookup.c @@ -0,0 +1,384 @@ +/* + * fs/sdcardfs/lookup.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include "linux/delay.h" + +/* The dentry cache is just so we have properly sized dentries */ +static struct kmem_cache *sdcardfs_dentry_cachep; + +int sdcardfs_init_dentry_cache(void) +{ + sdcardfs_dentry_cachep = + kmem_cache_create("sdcardfs_dentry", + sizeof(struct sdcardfs_dentry_info), + 0, SLAB_RECLAIM_ACCOUNT, NULL); + + return sdcardfs_dentry_cachep ? 0 : -ENOMEM; +} + +void sdcardfs_destroy_dentry_cache(void) +{ + if (sdcardfs_dentry_cachep) + kmem_cache_destroy(sdcardfs_dentry_cachep); +} + +void free_dentry_private_data(struct dentry *dentry) +{ + if (!dentry || !dentry->d_fsdata) + return; + kmem_cache_free(sdcardfs_dentry_cachep, dentry->d_fsdata); + dentry->d_fsdata = NULL; +} + +/* allocate new dentry private data */ +int new_dentry_private_data(struct dentry *dentry) +{ + struct sdcardfs_dentry_info *info = SDCARDFS_D(dentry); + + /* use zalloc to init dentry_info.lower_path */ + info = kmem_cache_zalloc(sdcardfs_dentry_cachep, GFP_ATOMIC); + if (!info) + return -ENOMEM; + + spin_lock_init(&info->lock); + dentry->d_fsdata = info; + + return 0; +} + +struct inode_data { + struct inode *lower_inode; + userid_t id; +}; + +static int sdcardfs_inode_test(struct inode *inode, void *candidate_data/*void *candidate_lower_inode*/) +{ + struct inode *current_lower_inode = sdcardfs_lower_inode(inode); + userid_t current_userid = SDCARDFS_I(inode)->userid; + if (current_lower_inode == ((struct inode_data *)candidate_data)->lower_inode && + current_userid == ((struct inode_data *)candidate_data)->id) + return 1; /* found a match */ + else + return 0; /* no match */ +} + +static int sdcardfs_inode_set(struct inode *inode, void *lower_inode) +{ + /* we do actual inode initialization in sdcardfs_iget */ + return 0; +} + +struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, userid_t id) +{ + struct sdcardfs_inode_info *info; + struct inode_data data; + struct inode *inode; /* the new inode to return */ + int err; + + data.id = id; + data.lower_inode = lower_inode; + inode = iget5_locked(sb, /* our superblock */ + /* + * hashval: we use inode number, but we can + * also use "(unsigned long)lower_inode" + * instead. + */ + lower_inode->i_ino, /* hashval */ + sdcardfs_inode_test, /* inode comparison function */ + sdcardfs_inode_set, /* inode init function */ + &data); /* data passed to test+set fxns */ + if (!inode) { + err = -EACCES; + iput(lower_inode); + return ERR_PTR(err); + } + /* if found a cached inode, then just return it */ + if (!(inode->i_state & I_NEW)) + return inode; + + /* initialize new inode */ + info = SDCARDFS_I(inode); + + inode->i_ino = lower_inode->i_ino; + if (!igrab(lower_inode)) { + err = -ESTALE; + return ERR_PTR(err); + } + sdcardfs_set_lower_inode(inode, lower_inode); + + inode->i_version++; + + /* use different set of inode ops for symlinks & directories */ + if (S_ISDIR(lower_inode->i_mode)) + inode->i_op = &sdcardfs_dir_iops; + else if (S_ISLNK(lower_inode->i_mode)) + inode->i_op = &sdcardfs_symlink_iops; + else + inode->i_op = &sdcardfs_main_iops; + + /* use different set of file ops for directories */ + if (S_ISDIR(lower_inode->i_mode)) + inode->i_fop = &sdcardfs_dir_fops; + else + inode->i_fop = &sdcardfs_main_fops; + + inode->i_mapping->a_ops = &sdcardfs_aops; + + inode->i_atime.tv_sec = 0; + inode->i_atime.tv_nsec = 0; + inode->i_mtime.tv_sec = 0; + inode->i_mtime.tv_nsec = 0; + inode->i_ctime.tv_sec = 0; + inode->i_ctime.tv_nsec = 0; + + /* properly initialize special inodes */ + if (S_ISBLK(lower_inode->i_mode) || S_ISCHR(lower_inode->i_mode) || + S_ISFIFO(lower_inode->i_mode) || S_ISSOCK(lower_inode->i_mode)) + init_special_inode(inode, lower_inode->i_mode, + lower_inode->i_rdev); + + /* all well, copy inode attributes */ + sdcardfs_copy_and_fix_attrs(inode, lower_inode); + fsstack_copy_inode_size(inode, lower_inode); + + unlock_new_inode(inode); + return inode; +} + +/* + * Connect a sdcardfs inode dentry/inode with several lower ones. This is + * the classic stackable file system "vnode interposition" action. + * + * @dentry: sdcardfs's dentry which interposes on lower one + * @sb: sdcardfs's super_block + * @lower_path: the lower path (caller does path_get/put) + */ +int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, + struct path *lower_path, userid_t id) +{ + int err = 0; + struct inode *inode; + struct inode *lower_inode; + struct super_block *lower_sb; + + lower_inode = lower_path->dentry->d_inode; + lower_sb = sdcardfs_lower_super(sb); + + /* check that the lower file system didn't cross a mount point */ + if (lower_inode->i_sb != lower_sb) { + err = -EXDEV; + goto out; + } + + /* + * We allocate our new inode below by calling sdcardfs_iget, + * which will initialize some of the new inode's fields + */ + + /* inherit lower inode number for sdcardfs's inode */ + inode = sdcardfs_iget(sb, lower_inode, id); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out; + } + + d_add(dentry, inode); + update_derived_permission_lock(dentry); +out: + return err; +} + +/* + * Main driver function for sdcardfs's lookup. + * + * Returns: NULL (ok), ERR_PTR if an error occurred. + * Fills in lower_parent_path with on success. + */ +static struct dentry *__sdcardfs_lookup(struct dentry *dentry, + unsigned int flags, struct path *lower_parent_path, userid_t id) +{ + int err = 0; + struct vfsmount *lower_dir_mnt; + struct dentry *lower_dir_dentry = NULL; + struct dentry *lower_dentry; + const char *name; + struct path lower_path; + struct qstr this; + struct sdcardfs_sb_info *sbi; + + sbi = SDCARDFS_SB(dentry->d_sb); + /* must initialize dentry operations */ + d_set_d_op(dentry, &sdcardfs_ci_dops); + + if (IS_ROOT(dentry)) + goto out; + + name = dentry->d_name.name; + + /* now start the actual lookup procedure */ + lower_dir_dentry = lower_parent_path->dentry; + lower_dir_mnt = lower_parent_path->mnt; + + /* Use vfs_path_lookup to check if the dentry exists or not */ + err = vfs_path_lookup(lower_dir_dentry, lower_dir_mnt, name, 0, + &lower_path); + + /* no error: handle positive dentries */ + if (!err) { + /* check if the dentry is an obb dentry + * if true, the lower_inode must be replaced with + * the inode of the graft path */ + + if(need_graft_path(dentry)) { + + /* setup_obb_dentry() + * The lower_path will be stored to the dentry's orig_path + * and the base obbpath will be copyed to the lower_path variable. + * if an error returned, there's no change in the lower_path + * returns: -ERRNO if error (0: no error) */ + err = setup_obb_dentry(dentry, &lower_path); + + if(err) { + /* if the sbi->obbpath is not available, we can optionally + * setup the lower_path with its orig_path. + * but, the current implementation just returns an error + * because the sdcard daemon also regards this case as + * a lookup fail. */ + printk(KERN_INFO "sdcardfs: base obbpath is not available\n"); + sdcardfs_put_reset_orig_path(dentry); + goto out; + } + } + + sdcardfs_set_lower_path(dentry, &lower_path); + err = sdcardfs_interpose(dentry, dentry->d_sb, &lower_path, id); + if (err) /* path_put underlying path on error */ + sdcardfs_put_reset_lower_path(dentry); + goto out; + } + + /* + * We don't consider ENOENT an error, and we want to return a + * negative dentry. + */ + if (err && err != -ENOENT) + goto out; + + /* instatiate a new negative dentry */ + this.name = name; + this.len = strlen(name); + this.hash = full_name_hash(this.name, this.len); + lower_dentry = d_lookup(lower_dir_dentry, &this); + if (lower_dentry) + goto setup_lower; + + lower_dentry = d_alloc(lower_dir_dentry, &this); + if (!lower_dentry) { + err = -ENOMEM; + goto out; + } + d_add(lower_dentry, NULL); /* instantiate and hash */ + +setup_lower: + lower_path.dentry = lower_dentry; + lower_path.mnt = mntget(lower_dir_mnt); + sdcardfs_set_lower_path(dentry, &lower_path); + + /* + * If the intent is to create a file, then don't return an error, so + * the VFS will continue the process of making this negative dentry + * into a positive one. + */ + if (flags & (LOOKUP_CREATE|LOOKUP_RENAME_TARGET)) + err = 0; + +out: + return ERR_PTR(err); +} + +/* + * On success: + * fills dentry object appropriate values and returns NULL. + * On fail (== error) + * returns error ptr + * + * @dir : Parent inode. It is locked (dir->i_mutex) + * @dentry : Target dentry to lookup. we should set each of fields. + * (dentry->d_name is initialized already) + * @nd : nameidata of parent inode + */ +struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct dentry *ret = NULL, *parent; + struct path lower_parent_path; + int err = 0; + const struct cred *saved_cred = NULL; + + parent = dget_parent(dentry); + + if(!check_caller_access_to_name(parent->d_inode, dentry->d_name.name)) { + ret = ERR_PTR(-EACCES); + printk(KERN_INFO "%s: need to check the caller's gid in packages.list\n" + " dentry: %s, task:%s\n", + __func__, dentry->d_name.name, current->comm); + goto out_err; + } + + /* save current_cred and override it */ + OVERRIDE_CRED_PTR(SDCARDFS_SB(dir->i_sb), saved_cred); + + sdcardfs_get_lower_path(parent, &lower_parent_path); + + /* allocate dentry private data. We free it in ->d_release */ + err = new_dentry_private_data(dentry); + if (err) { + ret = ERR_PTR(err); + goto out; + } + + ret = __sdcardfs_lookup(dentry, flags, &lower_parent_path, SDCARDFS_I(dir)->userid); + if (IS_ERR(ret)) + { + goto out; + } + if (ret) + dentry = ret; + if (dentry->d_inode) { + fsstack_copy_attr_times(dentry->d_inode, + sdcardfs_lower_inode(dentry->d_inode)); + /* get drived permission */ + mutex_lock(&dentry->d_inode->i_mutex); + get_derived_permission(parent, dentry); + fix_derived_permission(dentry->d_inode); + mutex_unlock(&dentry->d_inode->i_mutex); + } + /* update parent directory's atime */ + fsstack_copy_attr_atime(parent->d_inode, + sdcardfs_lower_inode(parent->d_inode)); + +out: + sdcardfs_put_lower_path(parent, &lower_parent_path); + REVERT_CRED(saved_cred); +out_err: + dput(parent); + return ret; +} diff --git a/fs/sdcardfs/main.c b/fs/sdcardfs/main.c new file mode 100644 index 000000000000..a6522286d731 --- /dev/null +++ b/fs/sdcardfs/main.c @@ -0,0 +1,402 @@ +/* + * fs/sdcardfs/main.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include +#include +#include + +enum { + Opt_fsuid, + Opt_fsgid, + Opt_gid, + Opt_debug, + Opt_lower_fs, + Opt_mask, + Opt_multiuser, // May need? + Opt_userid, + Opt_reserved_mb, + Opt_err, +}; + +static const match_table_t sdcardfs_tokens = { + {Opt_fsuid, "fsuid=%u"}, + {Opt_fsgid, "fsgid=%u"}, + {Opt_gid, "gid=%u"}, + {Opt_debug, "debug"}, + {Opt_mask, "mask=%u"}, + {Opt_userid, "userid=%d"}, + {Opt_multiuser, "multiuser"}, + {Opt_reserved_mb, "reserved_mb=%u"}, + {Opt_err, NULL} +}; + +static int parse_options(struct super_block *sb, char *options, int silent, + int *debug, struct sdcardfs_mount_options *opts) +{ + char *p; + substring_t args[MAX_OPT_ARGS]; + int option; + + /* by default, we use AID_MEDIA_RW as uid, gid */ + opts->fs_low_uid = AID_MEDIA_RW; + opts->fs_low_gid = AID_MEDIA_RW; + opts->mask = 0; + opts->multiuser = false; + opts->fs_user_id = 0; + opts->gid = 0; + /* by default, 0MB is reserved */ + opts->reserved_mb = 0; + + *debug = 0; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + if (!*p) + continue; + + token = match_token(p, sdcardfs_tokens, args); + + switch (token) { + case Opt_debug: + *debug = 1; + break; + case Opt_fsuid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_low_uid = option; + break; + case Opt_fsgid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_low_gid = option; + break; + case Opt_gid: + if (match_int(&args[0], &option)) + return 0; + opts->gid = option; + break; + case Opt_userid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_user_id = option; + break; + case Opt_mask: + if (match_int(&args[0], &option)) + return 0; + opts->mask = option; + break; + case Opt_multiuser: + opts->multiuser = true; + break; + case Opt_reserved_mb: + if (match_int(&args[0], &option)) + return 0; + opts->reserved_mb = option; + break; + /* unknown option */ + default: + if (!silent) { + printk( KERN_ERR "Unrecognized mount option \"%s\" " + "or missing value", p); + } + return -EINVAL; + } + } + + if (*debug) { + printk( KERN_INFO "sdcardfs : options - debug:%d\n", *debug); + printk( KERN_INFO "sdcardfs : options - uid:%d\n", + opts->fs_low_uid); + printk( KERN_INFO "sdcardfs : options - gid:%d\n", + opts->fs_low_gid); + } + + return 0; +} + +#if 0 +/* + * our custom d_alloc_root work-alike + * + * we can't use d_alloc_root if we want to use our own interpose function + * unchanged, so we simply call our own "fake" d_alloc_root + */ +static struct dentry *sdcardfs_d_alloc_root(struct super_block *sb) +{ + struct dentry *ret = NULL; + + if (sb) { + static const struct qstr name = { + .name = "/", + .len = 1 + }; + + ret = d_alloc(NULL, &name); + if (ret) { + d_set_d_op(ret, &sdcardfs_ci_dops); + ret->d_sb = sb; + ret->d_parent = ret; + } + } + return ret; +} +#endif + +DEFINE_MUTEX(sdcardfs_super_list_lock); +LIST_HEAD(sdcardfs_super_list); +EXPORT_SYMBOL_GPL(sdcardfs_super_list_lock); +EXPORT_SYMBOL_GPL(sdcardfs_super_list); + +/* + * There is no need to lock the sdcardfs_super_info's rwsem as there is no + * way anyone can have a reference to the superblock at this point in time. + */ +static int sdcardfs_read_super(struct super_block *sb, const char *dev_name, + void *raw_data, int silent) +{ + int err = 0; + int debug; + struct super_block *lower_sb; + struct path lower_path; + struct sdcardfs_sb_info *sb_info; + struct inode *inode; + + printk(KERN_INFO "sdcardfs version 2.0\n"); + + if (!dev_name) { + printk(KERN_ERR + "sdcardfs: read_super: missing dev_name argument\n"); + err = -EINVAL; + goto out; + } + + printk(KERN_INFO "sdcardfs: dev_name -> %s\n", dev_name); + printk(KERN_INFO "sdcardfs: options -> %s\n", (char *)raw_data); + + /* parse lower path */ + err = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, + &lower_path); + if (err) { + printk(KERN_ERR "sdcardfs: error accessing lower directory '%s'\n", dev_name); + goto out; + } + + /* allocate superblock private data */ + sb->s_fs_info = kzalloc(sizeof(struct sdcardfs_sb_info), GFP_KERNEL); + if (!SDCARDFS_SB(sb)) { + printk(KERN_CRIT "sdcardfs: read_super: out of memory\n"); + err = -ENOMEM; + goto out_free; + } + + sb_info = sb->s_fs_info; + /* parse options */ + err = parse_options(sb, raw_data, silent, &debug, &sb_info->options); + if (err) { + printk(KERN_ERR "sdcardfs: invalid options\n"); + goto out_freesbi; + } + + /* set the lower superblock field of upper superblock */ + lower_sb = lower_path.dentry->d_sb; + atomic_inc(&lower_sb->s_active); + sdcardfs_set_lower_super(sb, lower_sb); + + /* inherit maxbytes from lower file system */ + sb->s_maxbytes = lower_sb->s_maxbytes; + + /* + * Our c/m/atime granularity is 1 ns because we may stack on file + * systems whose granularity is as good. + */ + sb->s_time_gran = 1; + + sb->s_magic = SDCARDFS_SUPER_MAGIC; + sb->s_op = &sdcardfs_sops; + + /* get a new inode and allocate our root dentry */ + inode = sdcardfs_iget(sb, lower_path.dentry->d_inode, 0); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_sput; + } + sb->s_root = d_make_root(inode); + if (!sb->s_root) { + err = -ENOMEM; + goto out_iput; + } + d_set_d_op(sb->s_root, &sdcardfs_ci_dops); + + /* link the upper and lower dentries */ + sb->s_root->d_fsdata = NULL; + err = new_dentry_private_data(sb->s_root); + if (err) + goto out_freeroot; + + /* set the lower dentries for s_root */ + sdcardfs_set_lower_path(sb->s_root, &lower_path); + + /* + * No need to call interpose because we already have a positive + * dentry, which was instantiated by d_make_root. Just need to + * d_rehash it. + */ + d_rehash(sb->s_root); + + /* setup permission policy */ + sb_info->obbpath_s = kzalloc(PATH_MAX, GFP_KERNEL); + mutex_lock(&sdcardfs_super_list_lock); + if(sb_info->options.multiuser) { + setup_derived_state(sb->s_root->d_inode, PERM_PRE_ROOT, sb_info->options.fs_user_id, AID_ROOT, false); + snprintf(sb_info->obbpath_s, PATH_MAX, "%s/obb", dev_name); + /*err = prepare_dir(sb_info->obbpath_s, + sb_info->options.fs_low_uid, + sb_info->options.fs_low_gid, 00755);*/ + } else { + setup_derived_state(sb->s_root->d_inode, PERM_ROOT, sb_info->options.fs_low_uid, AID_ROOT, false); + snprintf(sb_info->obbpath_s, PATH_MAX, "%s/Android/obb", dev_name); + } + fix_derived_permission(sb->s_root->d_inode); + sb_info->sb = sb; + list_add(&sb_info->list, &sdcardfs_super_list); + mutex_unlock(&sdcardfs_super_list_lock); + + if (!silent) + printk(KERN_INFO "sdcardfs: mounted on top of %s type %s\n", + dev_name, lower_sb->s_type->name); + goto out; /* all is well */ + + /* no longer needed: free_dentry_private_data(sb->s_root); */ +out_freeroot: + dput(sb->s_root); +out_iput: + iput(inode); +out_sput: + /* drop refs we took earlier */ + atomic_dec(&lower_sb->s_active); +out_freesbi: + kfree(SDCARDFS_SB(sb)); + sb->s_fs_info = NULL; +out_free: + path_put(&lower_path); + +out: + return err; +} + +/* A feature which supports mount_nodev() with options */ +static struct dentry *mount_nodev_with_options(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, + int (*fill_super)(struct super_block *, const char *, void *, int)) + +{ + int error; + struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL); + + if (IS_ERR(s)) + return ERR_CAST(s); + + s->s_flags = flags; + + error = fill_super(s, dev_name, data, flags & MS_SILENT ? 1 : 0); + if (error) { + deactivate_locked_super(s); + return ERR_PTR(error); + } + s->s_flags |= MS_ACTIVE; + return dget(s->s_root); +} + +struct dentry *sdcardfs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + /* + * dev_name is a lower_path_name, + * raw_data is a option string. + */ + return mount_nodev_with_options(fs_type, flags, dev_name, + raw_data, sdcardfs_read_super); +} + +void sdcardfs_kill_sb(struct super_block *sb) { + struct sdcardfs_sb_info *sbi; + if (sb->s_magic == SDCARDFS_SUPER_MAGIC) { + sbi = SDCARDFS_SB(sb); + mutex_lock(&sdcardfs_super_list_lock); + list_del(&sbi->list); + mutex_unlock(&sdcardfs_super_list_lock); + } + generic_shutdown_super(sb); +} + +static struct file_system_type sdcardfs_fs_type = { + .owner = THIS_MODULE, + .name = SDCARDFS_NAME, + .mount = sdcardfs_mount, + .kill_sb = sdcardfs_kill_sb, + .fs_flags = 0, +}; + +static int __init init_sdcardfs_fs(void) +{ + int err; + + pr_info("Registering sdcardfs " SDCARDFS_VERSION "\n"); + + err = sdcardfs_init_inode_cache(); + if (err) + goto out; + err = sdcardfs_init_dentry_cache(); + if (err) + goto out; + err = packagelist_init(); + if (err) + goto out; + err = register_filesystem(&sdcardfs_fs_type); +out: + if (err) { + sdcardfs_destroy_inode_cache(); + sdcardfs_destroy_dentry_cache(); + packagelist_exit(); + } + return err; +} + +static void __exit exit_sdcardfs_fs(void) +{ + sdcardfs_destroy_inode_cache(); + sdcardfs_destroy_dentry_cache(); + packagelist_exit(); + unregister_filesystem(&sdcardfs_fs_type); + pr_info("Completed sdcardfs module unload\n"); +} + +MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University" + " (http://www.fsl.cs.sunysb.edu/)"); +MODULE_DESCRIPTION("Wrapfs " SDCARDFS_VERSION + " (http://wrapfs.filesystems.org/)"); +MODULE_LICENSE("GPL"); + +module_init(init_sdcardfs_fs); +module_exit(exit_sdcardfs_fs); diff --git a/fs/sdcardfs/mmap.c b/fs/sdcardfs/mmap.c new file mode 100644 index 000000000000..e21f64675a80 --- /dev/null +++ b/fs/sdcardfs/mmap.c @@ -0,0 +1,81 @@ +/* + * fs/sdcardfs/mmap.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +static int sdcardfs_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + int err; + struct file *file, *lower_file; + const struct vm_operations_struct *lower_vm_ops; + struct vm_area_struct lower_vma; + + memcpy(&lower_vma, vma, sizeof(struct vm_area_struct)); + file = lower_vma.vm_file; + lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops; + BUG_ON(!lower_vm_ops); + + lower_file = sdcardfs_lower_file(file); + /* + * XXX: vm_ops->fault may be called in parallel. Because we have to + * resort to temporarily changing the vma->vm_file to point to the + * lower file, a concurrent invocation of sdcardfs_fault could see a + * different value. In this workaround, we keep a different copy of + * the vma structure in our stack, so we never expose a different + * value of the vma->vm_file called to us, even temporarily. A + * better fix would be to change the calling semantics of ->fault to + * take an explicit file pointer. + */ + lower_vma.vm_file = lower_file; + err = lower_vm_ops->fault(&lower_vma, vmf); + return err; +} + +static ssize_t sdcardfs_direct_IO(struct kiocb *iocb, + struct iov_iter *iter, loff_t pos) +{ + /* + * This function returns zero on purpose in order to support direct IO. + * __dentry_open checks a_ops->direct_IO and returns EINVAL if it is null. + * + * However, this function won't be called by certain file operations + * including generic fs functions. * reads and writes are delivered to + * the lower file systems and the direct IOs will be handled by them. + * + * NOTE: exceptionally, on the recent kernels (since Linux 3.8.x), + * swap_writepage invokes this function directly. + */ + printk(KERN_INFO "%s, operation is not supported\n", __func__); + return 0; +} + +/* + * XXX: the default address_space_ops for sdcardfs is empty. We cannot set + * our inode->i_mapping->a_ops to NULL because too many code paths expect + * the a_ops vector to be non-NULL. + */ +const struct address_space_operations sdcardfs_aops = { + /* empty on purpose */ + .direct_IO = sdcardfs_direct_IO, +}; + +const struct vm_operations_struct sdcardfs_vm_ops = { + .fault = sdcardfs_fault, +}; diff --git a/fs/sdcardfs/multiuser.h b/fs/sdcardfs/multiuser.h new file mode 100644 index 000000000000..923ba101dfa9 --- /dev/null +++ b/fs/sdcardfs/multiuser.h @@ -0,0 +1,37 @@ +/* + * fs/sdcardfs/multiuser.h + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#define MULTIUSER_APP_PER_USER_RANGE 100000 + +typedef uid_t userid_t; +typedef uid_t appid_t; + +static inline userid_t multiuser_get_user_id(uid_t uid) { + return uid / MULTIUSER_APP_PER_USER_RANGE; +} + +static inline appid_t multiuser_get_app_id(uid_t uid) { + return uid % MULTIUSER_APP_PER_USER_RANGE; +} + +static inline uid_t multiuser_get_uid(userid_t userId, appid_t appId) { + return userId * MULTIUSER_APP_PER_USER_RANGE + (appId % MULTIUSER_APP_PER_USER_RANGE); +} + diff --git a/fs/sdcardfs/packagelist.c b/fs/sdcardfs/packagelist.c new file mode 100644 index 000000000000..10f0d6be718b --- /dev/null +++ b/fs/sdcardfs/packagelist.c @@ -0,0 +1,437 @@ +/* + * fs/sdcardfs/packagelist.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include +#include + + +#include +#include +#include + +#include + +#define STRING_BUF_SIZE (512) + +struct hashtable_entry { + struct hlist_node hlist; + void *key; + unsigned int value; +}; + +struct sb_list { + struct super_block *sb; + struct list_head list; +}; + +struct packagelist_data { + DECLARE_HASHTABLE(package_to_appid,8); + struct mutex hashtable_lock; + +}; + +static struct packagelist_data *pkgl_data_all; + +static struct kmem_cache *hashtable_entry_cachep; + +static unsigned int str_hash(const char *key) { + int i; + unsigned int h = strlen(key); + char *data = (char *)key; + + for (i = 0; i < strlen(key); i++) { + h = h * 31 + *data; + data++; + } + return h; +} + +appid_t get_appid(void *pkgl_id, const char *app_name) +{ + struct packagelist_data *pkgl_dat = pkgl_data_all; + struct hashtable_entry *hash_cur; + unsigned int hash = str_hash(app_name); + appid_t ret_id; + + mutex_lock(&pkgl_dat->hashtable_lock); + hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { + if (!strcasecmp(app_name, hash_cur->key)) { + ret_id = (appid_t)hash_cur->value; + mutex_unlock(&pkgl_dat->hashtable_lock); + return ret_id; + } + } + mutex_unlock(&pkgl_dat->hashtable_lock); + return 0; +} + +/* Kernel has already enforced everything we returned through + * derive_permissions_locked(), so this is used to lock down access + * even further, such as enforcing that apps hold sdcard_rw. */ +int check_caller_access_to_name(struct inode *parent_node, const char* name) { + + /* Always block security-sensitive files at root */ + if (parent_node && SDCARDFS_I(parent_node)->perm == PERM_ROOT) { + if (!strcasecmp(name, "autorun.inf") + || !strcasecmp(name, ".android_secure") + || !strcasecmp(name, "android_secure")) { + return 0; + } + } + + /* Root always has access; access for any other UIDs should always + * be controlled through packages.list. */ + if (from_kuid(&init_user_ns, current_fsuid()) == 0) { + return 1; + } + + /* No extra permissions to enforce */ + return 1; +} + +/* This function is used when file opening. The open flags must be + * checked before calling check_caller_access_to_name() */ +int open_flags_to_access_mode(int open_flags) { + if((open_flags & O_ACCMODE) == O_RDONLY) { + return 0; /* R_OK */ + } else if ((open_flags & O_ACCMODE) == O_WRONLY) { + return 1; /* W_OK */ + } else { + /* Probably O_RDRW, but treat as default to be safe */ + return 1; /* R_OK | W_OK */ + } +} + +static int insert_str_to_int_lock(struct packagelist_data *pkgl_dat, char *key, + unsigned int value) +{ + struct hashtable_entry *hash_cur; + struct hashtable_entry *new_entry; + unsigned int hash = str_hash(key); + + hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { + if (!strcasecmp(key, hash_cur->key)) { + hash_cur->value = value; + return 0; + } + } + new_entry = kmem_cache_alloc(hashtable_entry_cachep, GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->key = kstrdup(key, GFP_KERNEL); + new_entry->value = value; + hash_add(pkgl_dat->package_to_appid, &new_entry->hlist, hash); + return 0; +} + +static void fixup_perms(struct super_block *sb) { + if (sb && sb->s_magic == SDCARDFS_SUPER_MAGIC) { + mutex_lock(&sb->s_root->d_inode->i_mutex); + get_derive_permissions_recursive(sb->s_root); + mutex_unlock(&sb->s_root->d_inode->i_mutex); + } +} + +static int insert_str_to_int(struct packagelist_data *pkgl_dat, char *key, + unsigned int value) { + int ret; + struct sdcardfs_sb_info *sbinfo; + mutex_lock(&sdcardfs_super_list_lock); + mutex_lock(&pkgl_dat->hashtable_lock); + ret = insert_str_to_int_lock(pkgl_dat, key, value); + mutex_unlock(&pkgl_dat->hashtable_lock); + + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo) { + fixup_perms(sbinfo->sb); + } + } + mutex_unlock(&sdcardfs_super_list_lock); + return ret; +} + +static void remove_str_to_int_lock(struct hashtable_entry *h_entry) { + kfree(h_entry->key); + hash_del(&h_entry->hlist); + kmem_cache_free(hashtable_entry_cachep, h_entry); +} + +static void remove_str_to_int(struct packagelist_data *pkgl_dat, const char *key) +{ + struct sdcardfs_sb_info *sbinfo; + struct hashtable_entry *hash_cur; + unsigned int hash = str_hash(key); + mutex_lock(&sdcardfs_super_list_lock); + mutex_lock(&pkgl_dat->hashtable_lock); + hash_for_each_possible(pkgl_dat->package_to_appid, hash_cur, hlist, hash) { + if (!strcasecmp(key, hash_cur->key)) { + remove_str_to_int_lock(hash_cur); + break; + } + } + mutex_unlock(&pkgl_dat->hashtable_lock); + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo) { + fixup_perms(sbinfo->sb); + } + } + mutex_unlock(&sdcardfs_super_list_lock); + return; +} + +static void remove_all_hashentrys(struct packagelist_data *pkgl_dat) +{ + struct hashtable_entry *hash_cur; + struct hlist_node *h_t; + int i; + mutex_lock(&pkgl_dat->hashtable_lock); + hash_for_each_safe(pkgl_dat->package_to_appid, i, h_t, hash_cur, hlist) + remove_str_to_int_lock(hash_cur); + mutex_unlock(&pkgl_dat->hashtable_lock); + hash_init(pkgl_dat->package_to_appid); +} + +static struct packagelist_data * packagelist_create(void) +{ + struct packagelist_data *pkgl_dat; + + pkgl_dat = kmalloc(sizeof(*pkgl_dat), GFP_KERNEL | __GFP_ZERO); + if (!pkgl_dat) { + printk(KERN_ERR "sdcardfs: Failed to create hash\n"); + return ERR_PTR(-ENOMEM); + } + + mutex_init(&pkgl_dat->hashtable_lock); + hash_init(pkgl_dat->package_to_appid); + + return pkgl_dat; +} + +static void packagelist_destroy(struct packagelist_data *pkgl_dat) +{ + remove_all_hashentrys(pkgl_dat); + printk(KERN_INFO "sdcardfs: destroyed packagelist pkgld\n"); + kfree(pkgl_dat); +} + +struct package_appid { + struct config_item item; + int add_pid; +}; + +static inline struct package_appid *to_package_appid(struct config_item *item) +{ + return item ? container_of(item, struct package_appid, item) : NULL; +} + +static ssize_t package_appid_attr_show(struct config_item *item, + char *page) +{ + ssize_t count; + count = sprintf(page, "%d\n", get_appid(pkgl_data_all, item->ci_name)); + return count; +} + +static ssize_t package_appid_attr_store(struct config_item *item, + const char *page, size_t count) +{ + struct package_appid *package_appid = to_package_appid(item); + unsigned long tmp; + char *p = (char *) page; + int ret; + + tmp = simple_strtoul(p, &p, 10); + if (!p || (*p && (*p != '\n'))) + return -EINVAL; + + if (tmp > INT_MAX) + return -ERANGE; + ret = insert_str_to_int(pkgl_data_all, item->ci_name, (unsigned int)tmp); + package_appid->add_pid = tmp; + if (ret) + return ret; + + return count; +} + +static struct configfs_attribute package_appid_attr_add_pid = { + .ca_owner = THIS_MODULE, + .ca_name = "appid", + .ca_mode = S_IRUGO | S_IWUGO, + .show = package_appid_attr_show, + .store = package_appid_attr_store, +}; + +static struct configfs_attribute *package_appid_attrs[] = { + &package_appid_attr_add_pid, + NULL, +}; + +static void package_appid_release(struct config_item *item) +{ + printk(KERN_INFO "sdcardfs: removing %s\n", item->ci_dentry->d_name.name); + /* item->ci_name is freed already, so we rely on the dentry */ + remove_str_to_int(pkgl_data_all, item->ci_dentry->d_name.name); + kfree(to_package_appid(item)); +} + +static struct configfs_item_operations package_appid_item_ops = { + .release = package_appid_release, +}; + +static struct config_item_type package_appid_type = { + .ct_item_ops = &package_appid_item_ops, + .ct_attrs = package_appid_attrs, + .ct_owner = THIS_MODULE, +}; + + +struct sdcardfs_packages { + struct config_group group; +}; + +static inline struct sdcardfs_packages *to_sdcardfs_packages(struct config_item *item) +{ + return item ? container_of(to_config_group(item), struct sdcardfs_packages, group) : NULL; +} + +static struct config_item *sdcardfs_packages_make_item(struct config_group *group, const char *name) +{ + struct package_appid *package_appid; + + package_appid = kzalloc(sizeof(struct package_appid), GFP_KERNEL); + if (!package_appid) + return ERR_PTR(-ENOMEM); + + config_item_init_type_name(&package_appid->item, name, + &package_appid_type); + + package_appid->add_pid = 0; + + return &package_appid->item; +} + +static ssize_t packages_attr_show(struct config_item *item, + char *page) +{ + struct hashtable_entry *hash_cur; + struct hlist_node *h_t; + int i; + int count = 0; + mutex_lock(&pkgl_data_all->hashtable_lock); + hash_for_each_safe(pkgl_data_all->package_to_appid, i, h_t, hash_cur, hlist) + count += snprintf(page + count, PAGE_SIZE - count, "%s %d\n", (char *)hash_cur->key, hash_cur->value); + mutex_unlock(&pkgl_data_all->hashtable_lock); + + + return count; +} + +static struct configfs_attribute sdcardfs_packages_attr_description = { + .ca_owner = THIS_MODULE, + .ca_name = "packages_gid.list", + .ca_mode = S_IRUGO, + .show = packages_attr_show, +}; + +static struct configfs_attribute *sdcardfs_packages_attrs[] = { + &sdcardfs_packages_attr_description, + NULL, +}; + +static void sdcardfs_packages_release(struct config_item *item) +{ + + printk(KERN_INFO "sdcardfs: destroyed something?\n"); + kfree(to_sdcardfs_packages(item)); +} + +static struct configfs_item_operations sdcardfs_packages_item_ops = { + .release = sdcardfs_packages_release, +}; + +/* + * Note that, since no extra work is required on ->drop_item(), + * no ->drop_item() is provided. + */ +static struct configfs_group_operations sdcardfs_packages_group_ops = { + .make_item = sdcardfs_packages_make_item, +}; + +static struct config_item_type sdcardfs_packages_type = { + .ct_item_ops = &sdcardfs_packages_item_ops, + .ct_group_ops = &sdcardfs_packages_group_ops, + .ct_attrs = sdcardfs_packages_attrs, + .ct_owner = THIS_MODULE, +}; + +static struct configfs_subsystem sdcardfs_packages_subsys = { + .su_group = { + .cg_item = { + .ci_namebuf = "sdcardfs", + .ci_type = &sdcardfs_packages_type, + }, + }, +}; + +static int configfs_sdcardfs_init(void) +{ + int ret; + struct configfs_subsystem *subsys = &sdcardfs_packages_subsys; + + config_group_init(&subsys->su_group); + mutex_init(&subsys->su_mutex); + ret = configfs_register_subsystem(subsys); + if (ret) { + printk(KERN_ERR "Error %d while registering subsystem %s\n", + ret, + subsys->su_group.cg_item.ci_namebuf); + } + return ret; +} + +static void configfs_sdcardfs_exit(void) +{ + configfs_unregister_subsystem(&sdcardfs_packages_subsys); +} + +int packagelist_init(void) +{ + hashtable_entry_cachep = + kmem_cache_create("packagelist_hashtable_entry", + sizeof(struct hashtable_entry), 0, 0, NULL); + if (!hashtable_entry_cachep) { + printk(KERN_ERR "sdcardfs: failed creating pkgl_hashtable entry slab cache\n"); + return -ENOMEM; + } + + pkgl_data_all = packagelist_create(); + configfs_sdcardfs_init(); + return 0; +} + +void packagelist_exit(void) +{ + configfs_sdcardfs_exit(); + packagelist_destroy(pkgl_data_all); + if (hashtable_entry_cachep) + kmem_cache_destroy(hashtable_entry_cachep); +} diff --git a/fs/sdcardfs/sdcardfs.h b/fs/sdcardfs/sdcardfs.h new file mode 100644 index 000000000000..f111f898b630 --- /dev/null +++ b/fs/sdcardfs/sdcardfs.h @@ -0,0 +1,530 @@ +/* + * fs/sdcardfs/sdcardfs.h + * + * The sdcardfs v2.0 + * This file system replaces the sdcard daemon on Android + * On version 2.0, some of the daemon functions have been ported + * to support the multi-user concepts of Android 4.4 + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#ifndef _SDCARDFS_H_ +#define _SDCARDFS_H_ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "multiuser.h" + +/* the file system name */ +#define SDCARDFS_NAME "sdcardfs" + +/* sdcardfs root inode number */ +#define SDCARDFS_ROOT_INO 1 + +/* useful for tracking code reachability */ +#define UDBG printk(KERN_DEFAULT "DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__) + +#define SDCARDFS_DIRENT_SIZE 256 + +/* temporary static uid settings for development */ +#define AID_ROOT 0 /* uid for accessing /mnt/sdcard & extSdcard */ +#define AID_MEDIA_RW 1023 /* internal media storage write access */ + +#define AID_SDCARD_RW 1015 /* external storage write access */ +#define AID_SDCARD_R 1028 /* external storage read access */ +#define AID_SDCARD_PICS 1033 /* external storage photos access */ +#define AID_SDCARD_AV 1034 /* external storage audio/video access */ +#define AID_SDCARD_ALL 1035 /* access all users external storage */ + +#define AID_PACKAGE_INFO 1027 + +#define fix_derived_permission(x) \ + do { \ + (x)->i_uid = make_kuid(&init_user_ns, SDCARDFS_I(x)->d_uid); \ + (x)->i_gid = make_kgid(&init_user_ns, get_gid(SDCARDFS_I(x))); \ + (x)->i_mode = ((x)->i_mode & S_IFMT) | get_mode(SDCARDFS_I(x));\ + } while (0) + + +/* OVERRIDE_CRED() and REVERT_CRED() + * OVERRID_CRED() + * backup original task->cred + * and modifies task->cred->fsuid/fsgid to specified value. + * REVERT_CRED() + * restore original task->cred->fsuid/fsgid. + * These two macro should be used in pair, and OVERRIDE_CRED() should be + * placed at the beginning of a function, right after variable declaration. + */ +#define OVERRIDE_CRED(sdcardfs_sbi, saved_cred) \ + saved_cred = override_fsids(sdcardfs_sbi); \ + if (!saved_cred) { return -ENOMEM; } + +#define OVERRIDE_CRED_PTR(sdcardfs_sbi, saved_cred) \ + saved_cred = override_fsids(sdcardfs_sbi); \ + if (!saved_cred) { return ERR_PTR(-ENOMEM); } + +#define REVERT_CRED(saved_cred) revert_fsids(saved_cred) + +#define DEBUG_CRED() \ + printk("KAKJAGI: %s:%d fsuid %d fsgid %d\n", \ + __FUNCTION__, __LINE__, \ + (int)current->cred->fsuid, \ + (int)current->cred->fsgid); + +/* Android 5.0 support */ + +/* Permission mode for a specific node. Controls how file permissions + * are derived for children nodes. */ +typedef enum { + /* Nothing special; this node should just inherit from its parent. */ + PERM_INHERIT, + /* This node is one level above a normal root; used for legacy layouts + * which use the first level to represent user_id. */ + PERM_PRE_ROOT, + /* This node is "/" */ + PERM_ROOT, + /* This node is "/Android" */ + PERM_ANDROID, + /* This node is "/Android/data" */ + PERM_ANDROID_DATA, + /* This node is "/Android/obb" */ + PERM_ANDROID_OBB, + /* This node is "/Android/media" */ + PERM_ANDROID_MEDIA, +} perm_t; + +struct sdcardfs_sb_info; +struct sdcardfs_mount_options; + +/* Do not directly use this function. Use OVERRIDE_CRED() instead. */ +const struct cred * override_fsids(struct sdcardfs_sb_info* sbi); +/* Do not directly use this function, use REVERT_CRED() instead. */ +void revert_fsids(const struct cred * old_cred); + +/* operations vectors defined in specific files */ +extern const struct file_operations sdcardfs_main_fops; +extern const struct file_operations sdcardfs_dir_fops; +extern const struct inode_operations sdcardfs_main_iops; +extern const struct inode_operations sdcardfs_dir_iops; +extern const struct inode_operations sdcardfs_symlink_iops; +extern const struct super_operations sdcardfs_sops; +extern const struct dentry_operations sdcardfs_ci_dops; +extern const struct address_space_operations sdcardfs_aops, sdcardfs_dummy_aops; +extern const struct vm_operations_struct sdcardfs_vm_ops; + +extern int sdcardfs_init_inode_cache(void); +extern void sdcardfs_destroy_inode_cache(void); +extern int sdcardfs_init_dentry_cache(void); +extern void sdcardfs_destroy_dentry_cache(void); +extern int new_dentry_private_data(struct dentry *dentry); +extern void free_dentry_private_data(struct dentry *dentry); +extern struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags); +extern struct inode *sdcardfs_iget(struct super_block *sb, + struct inode *lower_inode, userid_t id); +extern int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, + struct path *lower_path, userid_t id); + +/* file private data */ +struct sdcardfs_file_info { + struct file *lower_file; + const struct vm_operations_struct *lower_vm_ops; +}; + +/* sdcardfs inode data in memory */ +struct sdcardfs_inode_info { + struct inode *lower_inode; + /* state derived based on current position in hierachy */ + perm_t perm; + userid_t userid; + uid_t d_uid; + bool under_android; + + struct inode vfs_inode; +}; + + +/* sdcardfs dentry data in memory */ +struct sdcardfs_dentry_info { + spinlock_t lock; /* protects lower_path */ + struct path lower_path; + struct path orig_path; +}; + +struct sdcardfs_mount_options { + uid_t fs_low_uid; + gid_t fs_low_gid; + userid_t fs_user_id; + gid_t gid; + mode_t mask; + bool multiuser; + unsigned int reserved_mb; +}; + +/* sdcardfs super-block data in memory */ +struct sdcardfs_sb_info { + struct super_block *sb; + struct super_block *lower_sb; + /* derived perm policy : some of options have been added + * to sdcardfs_mount_options (Android 4.4 support) */ + struct sdcardfs_mount_options options; + spinlock_t lock; /* protects obbpath */ + char *obbpath_s; + struct path obbpath; + void *pkgl_id; + struct list_head list; +}; + +/* + * inode to private data + * + * Since we use containers and the struct inode is _inside_ the + * sdcardfs_inode_info structure, SDCARDFS_I will always (given a non-NULL + * inode pointer), return a valid non-NULL pointer. + */ +static inline struct sdcardfs_inode_info *SDCARDFS_I(const struct inode *inode) +{ + return container_of(inode, struct sdcardfs_inode_info, vfs_inode); +} + +/* dentry to private data */ +#define SDCARDFS_D(dent) ((struct sdcardfs_dentry_info *)(dent)->d_fsdata) + +/* superblock to private data */ +#define SDCARDFS_SB(super) ((struct sdcardfs_sb_info *)(super)->s_fs_info) + +/* file to private Data */ +#define SDCARDFS_F(file) ((struct sdcardfs_file_info *)((file)->private_data)) + +/* file to lower file */ +static inline struct file *sdcardfs_lower_file(const struct file *f) +{ + return SDCARDFS_F(f)->lower_file; +} + +static inline void sdcardfs_set_lower_file(struct file *f, struct file *val) +{ + SDCARDFS_F(f)->lower_file = val; +} + +/* inode to lower inode. */ +static inline struct inode *sdcardfs_lower_inode(const struct inode *i) +{ + return SDCARDFS_I(i)->lower_inode; +} + +static inline void sdcardfs_set_lower_inode(struct inode *i, struct inode *val) +{ + SDCARDFS_I(i)->lower_inode = val; +} + +/* superblock to lower superblock */ +static inline struct super_block *sdcardfs_lower_super( + const struct super_block *sb) +{ + return SDCARDFS_SB(sb)->lower_sb; +} + +static inline void sdcardfs_set_lower_super(struct super_block *sb, + struct super_block *val) +{ + SDCARDFS_SB(sb)->lower_sb = val; +} + +/* path based (dentry/mnt) macros */ +static inline void pathcpy(struct path *dst, const struct path *src) +{ + dst->dentry = src->dentry; + dst->mnt = src->mnt; +} + +/* sdcardfs_get_pname functions calls path_get() + * therefore, the caller must call "proper" path_put functions + */ +#define SDCARDFS_DENT_FUNC(pname) \ +static inline void sdcardfs_get_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + pathcpy(pname, &SDCARDFS_D(dent)->pname); \ + path_get(pname); \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_put_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + path_put(pname); \ + return; \ +} \ +static inline void sdcardfs_set_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + pathcpy(&SDCARDFS_D(dent)->pname, pname); \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_reset_##pname(const struct dentry *dent) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + SDCARDFS_D(dent)->pname.dentry = NULL; \ + SDCARDFS_D(dent)->pname.mnt = NULL; \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_put_reset_##pname(const struct dentry *dent) \ +{ \ + struct path pname; \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + if(SDCARDFS_D(dent)->pname.dentry) { \ + pathcpy(&pname, &SDCARDFS_D(dent)->pname); \ + SDCARDFS_D(dent)->pname.dentry = NULL; \ + SDCARDFS_D(dent)->pname.mnt = NULL; \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + path_put(&pname); \ + } else \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} + +SDCARDFS_DENT_FUNC(lower_path) +SDCARDFS_DENT_FUNC(orig_path) + +static inline int get_gid(struct sdcardfs_inode_info *info) { + struct sdcardfs_sb_info *sb_info = SDCARDFS_SB(info->vfs_inode.i_sb); + if (sb_info->options.gid == AID_SDCARD_RW) { + /* As an optimization, certain trusted system components only run + * as owner but operate across all users. Since we're now handing + * out the sdcard_rw GID only to trusted apps, we're okay relaxing + * the user boundary enforcement for the default view. The UIDs + * assigned to app directories are still multiuser aware. */ + return AID_SDCARD_RW; + } else { + return multiuser_get_uid(info->userid, sb_info->options.gid); + } +} +static inline int get_mode(struct sdcardfs_inode_info *info) { + int owner_mode; + int filtered_mode; + struct sdcardfs_sb_info *sb_info = SDCARDFS_SB(info->vfs_inode.i_sb); + int visible_mode = 0775 & ~sb_info->options.mask; + + if (info->perm == PERM_PRE_ROOT) { + /* Top of multi-user view should always be visible to ensure + * secondary users can traverse inside. */ + visible_mode = 0711; + } else if (info->under_android) { + /* Block "other" access to Android directories, since only apps + * belonging to a specific user should be in there; we still + * leave +x open for the default view. */ + if (sb_info->options.gid == AID_SDCARD_RW) { + visible_mode = visible_mode & ~0006; + } else { + visible_mode = visible_mode & ~0007; + } + } + owner_mode = info->lower_inode->i_mode & 0700; + filtered_mode = visible_mode & (owner_mode | (owner_mode >> 3) | (owner_mode >> 6)); + return filtered_mode; +} + +static inline int has_graft_path(const struct dentry *dent) +{ + int ret = 0; + + spin_lock(&SDCARDFS_D(dent)->lock); + if (SDCARDFS_D(dent)->orig_path.dentry != NULL) + ret = 1; + spin_unlock(&SDCARDFS_D(dent)->lock); + + return ret; +} + +static inline void sdcardfs_get_real_lower(const struct dentry *dent, + struct path *real_lower) +{ + /* in case of a local obb dentry + * the orig_path should be returned + */ + if(has_graft_path(dent)) + sdcardfs_get_orig_path(dent, real_lower); + else + sdcardfs_get_lower_path(dent, real_lower); +} + +static inline void sdcardfs_put_real_lower(const struct dentry *dent, + struct path *real_lower) +{ + if(has_graft_path(dent)) + sdcardfs_put_orig_path(dent, real_lower); + else + sdcardfs_put_lower_path(dent, real_lower); +} + +extern struct mutex sdcardfs_super_list_lock; +extern struct list_head sdcardfs_super_list; + +/* for packagelist.c */ +extern appid_t get_appid(void *pkgl_id, const char *app_name); +extern int check_caller_access_to_name(struct inode *parent_node, const char* name); +extern int open_flags_to_access_mode(int open_flags); +extern int packagelist_init(void); +extern void packagelist_exit(void); + +/* for derived_perm.c */ +extern void setup_derived_state(struct inode *inode, perm_t perm, + userid_t userid, uid_t uid, bool under_android); +extern void get_derived_permission(struct dentry *parent, struct dentry *dentry); +extern void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, struct dentry *newdentry); +extern void get_derive_permissions_recursive(struct dentry *parent); + +extern void update_derived_permission_lock(struct dentry *dentry); +extern int need_graft_path(struct dentry *dentry); +extern int is_base_obbpath(struct dentry *dentry); +extern int is_obbpath_invalid(struct dentry *dentry); +extern int setup_obb_dentry(struct dentry *dentry, struct path *lower_path); + +/* locking helpers */ +static inline struct dentry *lock_parent(struct dentry *dentry) +{ + struct dentry *dir = dget_parent(dentry); + mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT); + return dir; +} + +static inline void unlock_dir(struct dentry *dir) +{ + mutex_unlock(&d_inode(dir)->i_mutex); + dput(dir); +} + +static inline int prepare_dir(const char *path_s, uid_t uid, gid_t gid, mode_t mode) +{ + int err; + struct dentry *dent; + struct iattr attrs; + struct path parent; + + dent = kern_path_locked(path_s, &parent); + if (IS_ERR(dent)) { + err = PTR_ERR(dent); + if (err == -EEXIST) + err = 0; + goto out_unlock; + } + + err = vfs_mkdir(d_inode(parent.dentry), dent, mode); + if (err) { + if (err == -EEXIST) + err = 0; + goto out_dput; + } + + attrs.ia_uid = make_kuid(&init_user_ns, uid); + attrs.ia_gid = make_kgid(&init_user_ns, gid); + attrs.ia_valid = ATTR_UID | ATTR_GID; + mutex_lock(&d_inode(dent)->i_mutex); + notify_change(dent, &attrs, NULL); + mutex_unlock(&d_inode(dent)->i_mutex); + +out_dput: + dput(dent); + +out_unlock: + /* parent dentry locked by lookup_create */ + mutex_unlock(&d_inode(parent.dentry)->i_mutex); + path_put(&parent); + return err; +} + +/* + * Return 1, if a disk has enough free space, otherwise 0. + * We assume that any files can not be overwritten. + */ +static inline int check_min_free_space(struct dentry *dentry, size_t size, int dir) +{ + int err; + struct path lower_path; + struct kstatfs statfs; + u64 avail; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + if (sbi->options.reserved_mb) { + /* Get fs stat of lower filesystem. */ + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_statfs(&lower_path, &statfs); + sdcardfs_put_lower_path(dentry, &lower_path); + + if (unlikely(err)) + return 0; + + /* Invalid statfs informations. */ + if (unlikely(statfs.f_bsize == 0)) + return 0; + + /* if you are checking directory, set size to f_bsize. */ + if (unlikely(dir)) + size = statfs.f_bsize; + + /* available size */ + avail = statfs.f_bavail * statfs.f_bsize; + + /* not enough space */ + if ((u64)size > avail) + return 0; + + /* enough space */ + if ((avail - size) > (sbi->options.reserved_mb * 1024 * 1024)) + return 1; + + return 0; + } else + return 1; +} + +/* Copies attrs and maintains sdcardfs managed attrs */ +static inline void sdcardfs_copy_and_fix_attrs(struct inode *dest, const struct inode *src) +{ + dest->i_mode = (src->i_mode & S_IFMT) | get_mode(SDCARDFS_I(dest)); + dest->i_uid = make_kuid(&init_user_ns, SDCARDFS_I(dest)->d_uid); + dest->i_gid = make_kgid(&init_user_ns, get_gid(SDCARDFS_I(dest))); + dest->i_rdev = src->i_rdev; + dest->i_atime = src->i_atime; + dest->i_mtime = src->i_mtime; + dest->i_ctime = src->i_ctime; + dest->i_blkbits = src->i_blkbits; + dest->i_flags = src->i_flags; + set_nlink(dest, src->i_nlink); +} +#endif /* not _SDCARDFS_H_ */ diff --git a/fs/sdcardfs/super.c b/fs/sdcardfs/super.c new file mode 100644 index 000000000000..1d6490128c99 --- /dev/null +++ b/fs/sdcardfs/super.c @@ -0,0 +1,222 @@ +/* + * fs/sdcardfs/super.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +/* + * The inode cache is used with alloc_inode for both our inode info and the + * vfs inode. + */ +static struct kmem_cache *sdcardfs_inode_cachep; + +/* final actions when unmounting a file system */ +static void sdcardfs_put_super(struct super_block *sb) +{ + struct sdcardfs_sb_info *spd; + struct super_block *s; + + spd = SDCARDFS_SB(sb); + if (!spd) + return; + + if(spd->obbpath_s) { + kfree(spd->obbpath_s); + path_put(&spd->obbpath); + } + + /* decrement lower super references */ + s = sdcardfs_lower_super(sb); + sdcardfs_set_lower_super(sb, NULL); + atomic_dec(&s->s_active); + + kfree(spd); + sb->s_fs_info = NULL; +} + +static int sdcardfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + int err; + struct path lower_path; + u32 min_blocks; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_statfs(&lower_path, buf); + sdcardfs_put_lower_path(dentry, &lower_path); + + if (sbi->options.reserved_mb) { + /* Invalid statfs informations. */ + if (buf->f_bsize == 0) { + printk(KERN_ERR "Returned block size is zero.\n"); + return -EINVAL; + } + + min_blocks = ((sbi->options.reserved_mb * 1024 * 1024)/buf->f_bsize); + buf->f_blocks -= min_blocks; + + if (buf->f_bavail > min_blocks) + buf->f_bavail -= min_blocks; + else + buf->f_bavail = 0; + + /* Make reserved blocks invisiable to media storage */ + buf->f_bfree = buf->f_bavail; + } + + /* set return buf to our f/s to avoid confusing user-level utils */ + buf->f_type = SDCARDFS_SUPER_MAGIC; + + return err; +} + +/* + * @flags: numeric mount options + * @options: mount options string + */ +static int sdcardfs_remount_fs(struct super_block *sb, int *flags, char *options) +{ + int err = 0; + + /* + * The VFS will take care of "ro" and "rw" flags among others. We + * can safely accept a few flags (RDONLY, MANDLOCK), and honor + * SILENT, but anything else left over is an error. + */ + if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT)) != 0) { + printk(KERN_ERR + "sdcardfs: remount flags 0x%x unsupported\n", *flags); + err = -EINVAL; + } + + return err; +} + +/* + * Called by iput() when the inode reference count reached zero + * and the inode is not hashed anywhere. Used to clear anything + * that needs to be, before the inode is completely destroyed and put + * on the inode free list. + */ +static void sdcardfs_evict_inode(struct inode *inode) +{ + struct inode *lower_inode; + + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); + /* + * Decrement a reference to a lower_inode, which was incremented + * by our read_inode when it was created initially. + */ + lower_inode = sdcardfs_lower_inode(inode); + sdcardfs_set_lower_inode(inode, NULL); + iput(lower_inode); +} + +static struct inode *sdcardfs_alloc_inode(struct super_block *sb) +{ + struct sdcardfs_inode_info *i; + + i = kmem_cache_alloc(sdcardfs_inode_cachep, GFP_KERNEL); + if (!i) + return NULL; + + /* memset everything up to the inode to 0 */ + memset(i, 0, offsetof(struct sdcardfs_inode_info, vfs_inode)); + + i->vfs_inode.i_version = 1; + return &i->vfs_inode; +} + +static void sdcardfs_destroy_inode(struct inode *inode) +{ + kmem_cache_free(sdcardfs_inode_cachep, SDCARDFS_I(inode)); +} + +/* sdcardfs inode cache constructor */ +static void init_once(void *obj) +{ + struct sdcardfs_inode_info *i = obj; + + inode_init_once(&i->vfs_inode); +} + +int sdcardfs_init_inode_cache(void) +{ + int err = 0; + + sdcardfs_inode_cachep = + kmem_cache_create("sdcardfs_inode_cache", + sizeof(struct sdcardfs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT, init_once); + if (!sdcardfs_inode_cachep) + err = -ENOMEM; + return err; +} + +/* sdcardfs inode cache destructor */ +void sdcardfs_destroy_inode_cache(void) +{ + if (sdcardfs_inode_cachep) + kmem_cache_destroy(sdcardfs_inode_cachep); +} + +/* + * Used only in nfs, to kill any pending RPC tasks, so that subsequent + * code can actually succeed and won't leave tasks that need handling. + */ +static void sdcardfs_umount_begin(struct super_block *sb) +{ + struct super_block *lower_sb; + + lower_sb = sdcardfs_lower_super(sb); + if (lower_sb && lower_sb->s_op && lower_sb->s_op->umount_begin) + lower_sb->s_op->umount_begin(lower_sb); +} + +static int sdcardfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(root->d_sb); + struct sdcardfs_mount_options *opts = &sbi->options; + + if (opts->fs_low_uid != 0) + seq_printf(m, ",uid=%u", opts->fs_low_uid); + if (opts->fs_low_gid != 0) + seq_printf(m, ",gid=%u", opts->fs_low_gid); + + if (opts->multiuser) + seq_printf(m, ",multiuser"); + + if (opts->reserved_mb != 0) + seq_printf(m, ",reserved=%uMB", opts->reserved_mb); + + return 0; +}; + +const struct super_operations sdcardfs_sops = { + .put_super = sdcardfs_put_super, + .statfs = sdcardfs_statfs, + .remount_fs = sdcardfs_remount_fs, + .evict_inode = sdcardfs_evict_inode, + .umount_begin = sdcardfs_umount_begin, + .show_options = sdcardfs_show_options, + .alloc_inode = sdcardfs_alloc_inode, + .destroy_inode = sdcardfs_destroy_inode, + .drop_inode = generic_delete_inode, +}; diff --git a/include/linux/dcache.h b/include/linux/dcache.h index f513dd855cb2..e4221f7c5b53 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -161,6 +161,7 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); struct inode *(*d_select_inode)(struct dentry *, unsigned); + void (*d_canonical_path)(const struct dentry *, struct path *); struct dentry *(*d_real)(struct dentry *, struct inode *); } ____cacheline_aligned; diff --git a/include/linux/namei.h b/include/linux/namei.h index d8c6334cd150..d53c25453aca 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -75,6 +75,8 @@ extern struct dentry *user_path_create(int, const char __user *, struct path *, extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); +extern int vfs_path_lookup(struct dentry *, struct vfsmount *, + const char *, unsigned int, struct path *); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); diff --git a/include/linux/random.h b/include/linux/random.h index a75840c1aa71..9c29122037f9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops; #endif unsigned int get_random_int(void); +unsigned long get_random_long(void); unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); u32 prandom_u32(void); diff --git a/include/linux/socket.h b/include/linux/socket.h index 18a8337c8959..5bf59c8493b7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -47,10 +47,6 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ -#if defined(CONFIG_PPPOLAC) || defined(CONFIG_PPPOPNS) - struct iovec *msg_iov; /* scatter/gather array */ - __kernel_size_t msg_iovlen; /* # elements in msg_iov */ -#endif struct iov_iter msg_iter; /* data */ void *msg_control; /* ancillary data */ __kernel_size_t msg_controllen; /* ancillary data buffer length */ diff --git a/include/linux/wakeup_reason.h b/include/linux/wakeup_reason.h index ad8b76936c7f..d84d8c301546 100644 --- a/include/linux/wakeup_reason.h +++ b/include/linux/wakeup_reason.h @@ -21,7 +21,12 @@ #define MAX_SUSPEND_ABORT_LEN 256 void log_wakeup_reason(int irq); -void log_suspend_abort_reason(const char *fmt, ...); int check_wakeup_reason(int irq); +#ifdef CONFIG_SUSPEND +void log_suspend_abort_reason(const char *fmt, ...); +#else +static inline void log_suspend_abort_reason(const char *fmt, ...) { } +#endif + #endif /* _LINUX_WAKEUP_REASON_H */ diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 44228e7238cc..2df03af6f328 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -135,7 +135,7 @@ TRACE_EVENT(cpu_frequency_limits, TP_fast_assign( __entry->min_freq = min_freq; - __entry->max_freq = min_freq; + __entry->max_freq = max_freq; __entry->cpu_id = cpu_id; ), diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index accb036bbc9c..cfb5c406f344 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -52,6 +52,8 @@ #define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs" #define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs" +#define SDCARDFS_SUPER_MAGIC 0xb550ca10 + #define SMB_SUPER_MAGIC 0x517B #define CGROUP_SUPER_MAGIC 0x27e0eb diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 84c480946fb2..6d6f63be1f9b 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -1,6 +1,7 @@ config SUSPEND bool "Suspend to RAM and standby" depends on ARCH_SUSPEND_POSSIBLE + select RTC_LIB default y ---help--- Allow the system to enter sleep states in which main memory is diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 9472691c1eb0..029da92fb712 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -121,7 +121,7 @@ static unsigned long soft_lockup_nmi_warn; unsigned int __read_mostly hardlockup_panic = CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; #ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI -static unsigned long hardlockup_allcpu_dumped; +static unsigned long __maybe_unused hardlockup_allcpu_dumped; #endif /* * We may not want to enable hard lockup detection by default in all cases, diff --git a/mm/mmap.c b/mm/mmap.c index 6c561acdca92..a089cca8d79a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2634,6 +2634,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len) return 0; } +EXPORT_SYMBOL(do_munmap); int vm_munmap(unsigned long start, size_t len) {