From 8a962db7eb067b098f261d11957480dbfe5d7e71 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 4 Dec 2018 16:46:54 -0800 Subject: [PATCH 001/116] UPSTREAM: crypto: adiantum - propagate CRYPTO_ALG_ASYNC flag to instance If the stream cipher implementation is asynchronous, then the Adiantum instance must be flagged as asynchronous as well. Otherwise someone asking for a synchronous algorithm can get an asynchronous algorithm. There are no asynchronous xchacha12 or xchacha20 implementations yet which makes this largely a theoretical issue, but it should be fixed. Fixes: 059c2a4d8e16 ("crypto: adiantum - add Adiantum support") Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu (cherry picked from commit b299362ee48db8eab34208302ee9730ff9d6091c) Test: Adiantum self-tests Change-Id: Ic7207e4036a0f03fba81375ffe36f511af2eb08c --- crypto/adiantum.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/crypto/adiantum.c b/crypto/adiantum.c index 2dfcf12fd452..ca27e0dc2958 100644 --- a/crypto/adiantum.c +++ b/crypto/adiantum.c @@ -590,6 +590,8 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb) hash_alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto out_drop_hash; + inst->alg.base.cra_flags = streamcipher_alg->base.cra_flags & + CRYPTO_ALG_ASYNC; inst->alg.base.cra_blocksize = BLOCKCIPHER_BLOCK_SIZE; inst->alg.base.cra_ctxsize = sizeof(struct adiantum_tfm_ctx); inst->alg.base.cra_alignmask = streamcipher_alg->base.cra_alignmask | From 188d82f4cc1b8355c67c589d70fc81146f0b2f20 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 6 Dec 2018 14:21:59 -0800 Subject: [PATCH 002/116] UPSTREAM: crypto: adiantum - adjust some comments to match latest paper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The 2018-11-28 revision of the Adiantum paper has revised some notation: - 'M' was replaced with 'L' (meaning "Left", for the left-hand part of the message) in the definition of Adiantum hashing, to avoid confusion with the full message - ε-almost-∆-universal is now abbreviated as ε-∆U instead of εA∆U - "block" is now used only to mean block cipher and Poly1305 blocks Also, Adiantum hashing was moved from the appendix to the main paper. To avoid confusion, update relevant comments in the code to match. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu (cherry picked from commit c6018e1a00b5c70610cdfb3650cc5622c917ed17) Test: Adiantum self-tests Change-Id: Idd371e46408a449f7ff2ba77af2d4414979aadbf --- crypto/adiantum.c | 35 +++++++++++++++++++---------------- crypto/nhpoly1305.c | 8 ++++---- 2 files changed, 23 insertions(+), 20 deletions(-) diff --git a/crypto/adiantum.c b/crypto/adiantum.c index ca27e0dc2958..e62e34f5e389 100644 --- a/crypto/adiantum.c +++ b/crypto/adiantum.c @@ -9,7 +9,7 @@ * Adiantum is a tweakable, length-preserving encryption mode designed for fast * and secure disk encryption, especially on CPUs without dedicated crypto * instructions. Adiantum encrypts each sector using the XChaCha12 stream - * cipher, two passes of an ε-almost-∆-universal (εA∆U) hash function based on + * cipher, two passes of an ε-almost-∆-universal (ε-∆U) hash function based on * NH and Poly1305, and an invocation of the AES-256 block cipher on a single * 16-byte block. See the paper for details: * @@ -21,12 +21,12 @@ * - Stream cipher: XChaCha12 or XChaCha20 * - Block cipher: any with a 128-bit block size and 256-bit key * - * This implementation doesn't currently allow other εA∆U hash functions, i.e. + * This implementation doesn't currently allow other ε-∆U hash functions, i.e. * HPolyC is not supported. This is because Adiantum is ~20% faster than HPolyC - * but still provably as secure, and also the εA∆U hash function of HBSH is + * but still provably as secure, and also the ε-∆U hash function of HBSH is * formally defined to take two inputs (tweak, message) which makes it difficult * to wrap with the crypto_shash API. Rather, some details need to be handled - * here. Nevertheless, if needed in the future, support for other εA∆U hash + * here. Nevertheless, if needed in the future, support for other ε-∆U hash * functions could be added here. */ @@ -41,7 +41,7 @@ #include "internal.h" /* - * Size of right-hand block of input data, in bytes; also the size of the block + * Size of right-hand part of input data, in bytes; also the size of the block * cipher's block size and the hash function's output. */ #define BLOCKCIPHER_BLOCK_SIZE 16 @@ -77,7 +77,7 @@ struct adiantum_tfm_ctx { struct adiantum_request_ctx { /* - * Buffer for right-hand block of data, i.e. + * Buffer for right-hand part of data, i.e. * * P_L => P_M => C_M => C_R when encrypting, or * C_R => C_M => P_M => P_L when decrypting. @@ -93,8 +93,8 @@ struct adiantum_request_ctx { bool enc; /* true if encrypting, false if decrypting */ /* - * The result of the Poly1305 εA∆U hash function applied to - * (message length, tweak). + * The result of the Poly1305 ε-∆U hash function applied to + * (bulk length, tweak) */ le128 header_hash; @@ -213,13 +213,16 @@ static inline void le128_sub(le128 *r, const le128 *v1, const le128 *v2) } /* - * Apply the Poly1305 εA∆U hash function to (message length, tweak) and save the - * result to rctx->header_hash. + * Apply the Poly1305 ε-∆U hash function to (bulk length, tweak) and save the + * result to rctx->header_hash. This is the calculation * - * This value is reused in both the first and second hash steps. Specifically, - * it's added to the result of an independently keyed εA∆U hash function (for - * equal length inputs only) taken over the message. This gives the overall - * Adiantum hash of the (tweak, message) pair. + * H_T ← Poly1305_{K_T}(bin_{128}(|L|) || T) + * + * from the procedure in section 6.4 of the Adiantum paper. The resulting value + * is reused in both the first and second hash steps. Specifically, it's added + * to the result of an independently keyed ε-∆U hash function (for equal length + * inputs only) taken over the left-hand part (the "bulk") of the message, to + * give the overall Adiantum hash of the (tweak, left-hand part) pair. */ static void adiantum_hash_header(struct skcipher_request *req) { @@ -248,7 +251,7 @@ static void adiantum_hash_header(struct skcipher_request *req) poly1305_core_emit(&state, &rctx->header_hash); } -/* Hash the left-hand block (the "bulk") of the message using NHPoly1305 */ +/* Hash the left-hand part (the "bulk") of the message using NHPoly1305 */ static int adiantum_hash_message(struct skcipher_request *req, struct scatterlist *sgl, le128 *digest) { @@ -550,7 +553,7 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb) goto out_drop_streamcipher; blockcipher_alg = ictx->blockcipher_spawn.alg; - /* NHPoly1305 εA∆U hash function */ + /* NHPoly1305 ε-∆U hash function */ _hash_alg = crypto_alg_mod_lookup(nhpoly1305_name, CRYPTO_ALG_TYPE_SHASH, CRYPTO_ALG_TYPE_MASK); diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c index c8385853f699..ec831a5594d8 100644 --- a/crypto/nhpoly1305.c +++ b/crypto/nhpoly1305.c @@ -9,15 +9,15 @@ * "NHPoly1305" is the main component of Adiantum hashing. * Specifically, it is the calculation * - * H_M ← Poly1305_{K_M}(NH_{K_N}(pad_{128}(M))) + * H_L ← Poly1305_{K_L}(NH_{K_N}(pad_{128}(L))) * - * from the procedure in section A.5 of the Adiantum paper [1]. It is an - * ε-almost-∆-universal (εA∆U) hash function for equal-length inputs over + * from the procedure in section 6.4 of the Adiantum paper [1]. It is an + * ε-almost-∆-universal (ε-∆U) hash function for equal-length inputs over * Z/(2^{128}Z), where the "∆" operation is addition. It hashes 1024-byte * chunks of the input with the NH hash function [2], reducing the input length * by 32x. The resulting NH digests are evaluated as a polynomial in * GF(2^{130}-5), like in the Poly1305 MAC [3]. Note that the polynomial - * evaluation by itself would suffice to achieve the εA∆U property; NH is used + * evaluation by itself would suffice to achieve the ε-∆U property; NH is used * for performance since it's over twice as fast as Poly1305. * * This is *not* a cryptographic hash function; do not use it as such! From ce3045a60dfc2a8f69c96cfdfbbb65b537e45677 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 10 Dec 2018 11:45:58 -0800 Subject: [PATCH 003/116] UPSTREAM: crypto: adiantum - fix leaking reference to hash algorithm crypto_alg_mod_lookup() takes a reference to the hash algorithm but crypto_init_shash_spawn() doesn't take ownership of it, hence the reference needs to be dropped in adiantum_create(). Fixes: 059c2a4d8e16 ("crypto: adiantum - add Adiantum support") Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu (cherry picked from commit 00c9fe37a7f27a306bcaa5737f0787fe139f8aba) Test: Adiantum self-tests Change-Id: Ic609144bc3c72cc2c4ccbbaf450168193f3df7db --- crypto/adiantum.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/crypto/adiantum.c b/crypto/adiantum.c index e62e34f5e389..6651e713c45d 100644 --- a/crypto/adiantum.c +++ b/crypto/adiantum.c @@ -564,10 +564,8 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb) hash_alg = __crypto_shash_alg(_hash_alg); err = crypto_init_shash_spawn(&ictx->hash_spawn, hash_alg, skcipher_crypto_instance(inst)); - if (err) { - crypto_mod_put(_hash_alg); - goto out_drop_blockcipher; - } + if (err) + goto out_put_hash; /* Check the set of algorithms */ if (!adiantum_supported_algorithms(streamcipher_alg, blockcipher_alg, @@ -624,10 +622,13 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb) if (err) goto out_drop_hash; + crypto_mod_put(_hash_alg); return 0; out_drop_hash: crypto_drop_shash(&ictx->hash_spawn); +out_put_hash: + crypto_mod_put(_hash_alg); out_drop_blockcipher: crypto_drop_spawn(&ictx->blockcipher_spawn); out_drop_streamcipher: From 7ae6788c68523baaa7cc0f538fb72d33f8dd2115 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 6 Jan 2019 12:46:05 -0800 Subject: [PATCH 004/116] UPSTREAM: crypto: adiantum - initialize crypto_spawn::inst crypto_grab_*() doesn't set crypto_spawn::inst, so templates must set it beforehand. Otherwise it will be left NULL, which causes a crash in certain cases where algorithms are dynamically loaded/unloaded. E.g. with CONFIG_CRYPTO_CHACHA20_X86_64=m, the following caused a crash: insmod chacha-x86_64.ko python -c 'import socket; socket.socket(socket.AF_ALG, 5, 0).bind(("skcipher", "adiantum(xchacha12,aes)"))' rmmod chacha-x86_64.ko python -c 'import socket; socket.socket(socket.AF_ALG, 5, 0).bind(("skcipher", "adiantum(xchacha12,aes)"))' Fixes: 059c2a4d8e16 ("crypto: adiantum - add Adiantum support") Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu (cherry picked from commit 6db43410179bc40419a9859ebb333f178a49829d) Test: Adiantum self-tests Change-Id: I248548c979b0ee9e63a35f8ae779741bb5967b6e --- crypto/adiantum.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/crypto/adiantum.c b/crypto/adiantum.c index 6651e713c45d..5564e73266a6 100644 --- a/crypto/adiantum.c +++ b/crypto/adiantum.c @@ -539,6 +539,8 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb) ictx = skcipher_instance_ctx(inst); /* Stream cipher, e.g. "xchacha12" */ + crypto_set_skcipher_spawn(&ictx->streamcipher_spawn, + skcipher_crypto_instance(inst)); err = crypto_grab_skcipher(&ictx->streamcipher_spawn, streamcipher_name, 0, crypto_requires_sync(algt->type, algt->mask)); @@ -547,6 +549,8 @@ static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb) streamcipher_alg = crypto_spawn_skcipher_alg(&ictx->streamcipher_spawn); /* Block cipher, e.g. "aes" */ + crypto_set_spawn(&ictx->blockcipher_spawn, + skcipher_crypto_instance(inst)); err = crypto_grab_spawn(&ictx->blockcipher_spawn, blockcipher_name, CRYPTO_ALG_TYPE_CIPHER, CRYPTO_ALG_TYPE_MASK); if (err) From c3b7c7080ec31a7cc86caae91391436b909fcc0b Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 14 Dec 2018 11:14:38 -0800 Subject: [PATCH 005/116] UPSTREAM: loop: drop caches if offset or block_size are changed If we don't drop caches used in old offset or block_size, we can get old data from new offset/block_size, which gives unexpected data to user. For example, Martijn found a loopback bug in the below scenario. 1) LOOP_SET_FD loads first two pages on loop file 2) LOOP_SET_STATUS64 changes the offset on the loop file 3) mount is failed due to the cached pages having wrong superblock Cc: Jens Axboe Cc: linux-block@vger.kernel.org Reported-by: Martijn Coenen Reviewed-by: Bart Van Assche Signed-off-by: Jaegeuk Kim Signed-off-by: Jens Axboe (cherry picked from commit 490b8c65b9db45896769e1095e78725775f47b3e) Change-Id: Iffb7e1f04ab587e1a8785bc862a425efb654be24 --- drivers/block/loop.c | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ea9debf59b22..f892fa9ad18b 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1127,6 +1127,12 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) return -EINVAL; + if (lo->lo_offset != info->lo_offset || + lo->lo_sizelimit != info->lo_sizelimit) { + sync_blockdev(lo->lo_device); + kill_bdev(lo->lo_device); + } + /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); @@ -1155,6 +1161,14 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { + /* kill_bdev should have truncated all the pages */ + if (lo->lo_device->bd_inode->i_mapping->nrpages) { + err = -EAGAIN; + pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + __func__, lo->lo_number, lo->lo_file_name, + lo->lo_device->bd_inode->i_mapping->nrpages); + goto exit; + } if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { err = -EFBIG; goto exit; @@ -1376,22 +1390,39 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg) static int loop_set_block_size(struct loop_device *lo, unsigned long arg) { + int err = 0; + if (lo->lo_state != Lo_bound) return -ENXIO; if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg)) return -EINVAL; + if (lo->lo_queue->limits.logical_block_size != arg) { + sync_blockdev(lo->lo_device); + kill_bdev(lo->lo_device); + } + blk_mq_freeze_queue(lo->lo_queue); + /* kill_bdev should have truncated all the pages */ + if (lo->lo_queue->limits.logical_block_size != arg && + lo->lo_device->bd_inode->i_mapping->nrpages) { + err = -EAGAIN; + pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + __func__, lo->lo_number, lo->lo_file_name, + lo->lo_device->bd_inode->i_mapping->nrpages); + goto out_unfreeze; + } + blk_queue_logical_block_size(lo->lo_queue, arg); blk_queue_physical_block_size(lo->lo_queue, arg); blk_queue_io_min(lo->lo_queue, arg); loop_update_dio(lo); - +out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); - return 0; + return err; } static int lo_ioctl(struct block_device *bdev, fmode_t mode, From 138993ea82080870141661ca2d35320b599558b4 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Fri, 11 Jan 2019 18:44:18 -0800 Subject: [PATCH 006/116] ANDROID: mnt: Propagate remount correctly This switches over to propagation_next to respect namepsace semantics. Test: Remounting to change the options of a fs with mount based options should propagate to all shared copies of that mount, and the slaves/indirect slaves of those. Bug: 122428178 Signed-off-by: Daniel Rosenberg Change-Id: Ic35cd2782a646435689f5bedfa1f218fe4ab8254 --- fs/pnode.c | 34 ++++++++-------------------------- 1 file changed, 8 insertions(+), 26 deletions(-) diff --git a/fs/pnode.c b/fs/pnode.c index 56f9a28a688b..681916df422c 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -608,36 +608,18 @@ int propagate_umount(struct list_head *list) return 0; } -/* - * Iterates over all slaves, and slaves of slaves. - */ -static struct mount *next_descendent(struct mount *root, struct mount *cur) -{ - if (!IS_MNT_NEW(cur) && !list_empty(&cur->mnt_slave_list)) - return first_slave(cur); - do { - struct mount *master = cur->mnt_master; - - if (!master || cur->mnt_slave.next != &master->mnt_slave_list) { - struct mount *next = next_slave(cur); - - return (next == root) ? NULL : next; - } - cur = master; - } while (cur != root); - return NULL; -} - void propagate_remount(struct mount *mnt) { - struct mount *m = mnt; + struct mount *parent = mnt->mnt_parent; + struct mount *p = mnt, *m; struct super_block *sb = mnt->mnt.mnt_sb; - if (sb->s_op->copy_mnt_data) { - m = next_descendent(mnt, m); - while (m) { + if (!sb->s_op->copy_mnt_data) + return; + for (p = propagation_next(parent, parent); p; + p = propagation_next(p, parent)) { + m = __lookup_mnt(&p->mnt, mnt->mnt_mountpoint); + if (m) sb->s_op->copy_mnt_data(m->mnt.data, mnt->mnt.data); - m = next_descendent(mnt, m); - } } } From afba79e8f73b80b61567a3e8d31bd587c7efde35 Mon Sep 17 00:00:00 2001 From: Cody Schuffelen Date: Mon, 14 Jan 2019 18:37:28 -0800 Subject: [PATCH 007/116] ANDROID: cuttlefish_defconfig: Enable vsock options Bug: 121166534 Test: Ran cuttlefish with common kernel + vsock adb tunnel Signed-off-by: Cody Schuffelen Change-Id: I8168a710052c7daada306a915c56230c961accd4 --- arch/arm64/configs/cuttlefish_defconfig | 2 ++ arch/x86/configs/x86_64_cuttlefish_defconfig | 2 ++ 2 files changed, 4 insertions(+) diff --git a/arch/arm64/configs/cuttlefish_defconfig b/arch/arm64/configs/cuttlefish_defconfig index 0b87fc685e8d..2c2212f42571 100644 --- a/arch/arm64/configs/cuttlefish_defconfig +++ b/arch/arm64/configs/cuttlefish_defconfig @@ -182,6 +182,8 @@ CONFIG_NET_CLS_BPF=y CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_U32=y CONFIG_NET_CLS_ACT=y +CONFIG_VSOCKETS=y +CONFIG_VIRTIO_VSOCKETS=y CONFIG_CFG80211=y # CONFIG_CFG80211_DEFAULT_PS is not set # CONFIG_CFG80211_CRDA_SUPPORT is not set diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig index f4544e8fec1b..a84110ca9aa2 100644 --- a/arch/x86/configs/x86_64_cuttlefish_defconfig +++ b/arch/x86/configs/x86_64_cuttlefish_defconfig @@ -187,6 +187,8 @@ CONFIG_NET_CLS_BPF=y CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_U32=y CONFIG_NET_CLS_ACT=y +CONFIG_VSOCKETS=y +CONFIG_VIRTIO_VSOCKETS=y CONFIG_CFG80211=y CONFIG_MAC80211=y CONFIG_RFKILL=y From 0c3de481f364cbd9404c481cc106ff5c13ddd2e9 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 28 Dec 2018 00:36:33 -0800 Subject: [PATCH 008/116] UPSTREAM: zram: fix lockdep warning of free block handling Patch series "zram idle page writeback", v3. Inherently, swap device has many idle pages which are rare touched since it was allocated. It is never problem if we use storage device as swap. However, it's just waste for zram-swap. This patchset supports zram idle page writeback feature. * Admin can define what is idle page "no access since X time ago" * Admin can define when zram should writeback them * Admin can define when zram should stop writeback to prevent wearout Details are in each patch's description. This patch (of 7): ================================ WARNING: inconsistent lock state 4.19.0+ #390 Not tainted -------------------------------- inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. zram_verify/2095 [HC0[0]:SC1[1]:HE1:SE0] takes: 00000000b1828693 (&(&zram->bitmap_lock)->rlock){+.?.}, at: put_entry_bdev+0x1e/0x50 {SOFTIRQ-ON-W} state was registered at: _raw_spin_lock+0x2c/0x40 zram_make_request+0x755/0xdc9 generic_make_request+0x373/0x6a0 submit_bio+0x6c/0x140 __swap_writepage+0x3a8/0x480 shrink_page_list+0x1102/0x1a60 shrink_inactive_list+0x21b/0x3f0 shrink_node_memcg.constprop.99+0x4f8/0x7e0 shrink_node+0x7d/0x2f0 do_try_to_free_pages+0xe0/0x300 try_to_free_pages+0x116/0x2b0 __alloc_pages_slowpath+0x3f4/0xf80 __alloc_pages_nodemask+0x2a2/0x2f0 __handle_mm_fault+0x42e/0xb50 handle_mm_fault+0x55/0xb0 __do_page_fault+0x235/0x4b0 page_fault+0x1e/0x30 irq event stamp: 228412 hardirqs last enabled at (228412): [] __slab_free+0x3e6/0x600 hardirqs last disabled at (228411): [] __slab_free+0x1c5/0x600 softirqs last enabled at (228396): [] __do_softirq+0x31e/0x427 softirqs last disabled at (228403): [] irq_exit+0xd1/0xe0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&zram->bitmap_lock)->rlock); lock(&(&zram->bitmap_lock)->rlock); *** DEADLOCK *** no locks held by zram_verify/2095. stack backtrace: CPU: 5 PID: 2095 Comm: zram_verify Not tainted 4.19.0+ #390 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 Call Trace: dump_stack+0x67/0x9b print_usage_bug+0x1bd/0x1d3 mark_lock+0x4aa/0x540 __lock_acquire+0x51d/0x1300 lock_acquire+0x90/0x180 _raw_spin_lock+0x2c/0x40 put_entry_bdev+0x1e/0x50 zram_free_page+0xf6/0x110 zram_slot_free_notify+0x42/0xa0 end_swap_bio_read+0x5b/0x170 blk_update_request+0x8f/0x340 scsi_end_request+0x2c/0x1e0 scsi_io_completion+0x98/0x650 blk_done_softirq+0x9e/0xd0 __do_softirq+0xcc/0x427 irq_exit+0xd1/0xe0 do_IRQ+0x93/0x120 common_interrupt+0xf/0xf With writeback feature, zram_slot_free_notify could be called in softirq context by end_swap_bio_read. However, bitmap_lock is not aware of that so lockdep yell out: get_entry_bdev spin_lock(bitmap->lock); irq softirq end_swap_bio_read zram_slot_free_notify zram_slot_lock <-- deadlock prone zram_free_page put_entry_bdev spin_lock(bitmap->lock); <-- deadlock prone With akpm's suggestion (i.e. bitmap operation is already atomic), we could remove bitmap lock. It might fail to find a empty slot if serious contention happens. However, it's not severe problem because huge page writeback has already possiblity to fail if there is severe memory pressure. Worst case is just keeping the incompressible in memory, not storage. The other problem is zram_slot_lock in zram_slot_slot_free_notify. To make it safe is this patch introduces zram_slot_trylock where zram_slot_free_notify uses it. Although it's rare to be contented, this patch adds new debug stat "miss_free" to keep monitoring how often it happens. Link: http://lkml.kernel.org/r/20181127055429.251614-2-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Reviewed-by: Joey Pabalinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 3c9959e025472122a61faebb208525cf26b305d1) Bug: 117683045 Change-Id: I4bd620b1ab41de7e0e7fd5f38804f1c22481f652 Signed-off-by: Srinivas Paladugu --- drivers/block/zram/zram_drv.c | 38 +++++++++++++++++++---------------- drivers/block/zram/zram_drv.h | 2 +- 2 files changed, 22 insertions(+), 18 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e19bf0a750cf..a65505db09e5 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -53,6 +53,11 @@ static size_t huge_class_size; static void zram_free_page(struct zram *zram, size_t index); +static int zram_slot_trylock(struct zram *zram, u32 index) +{ + return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].value); +} + static void zram_slot_lock(struct zram *zram, u32 index) { bit_spin_lock(ZRAM_LOCK, &zram->table[index].value); @@ -401,7 +406,6 @@ static ssize_t backing_dev_store(struct device *dev, goto out; reset_bdev(zram); - spin_lock_init(&zram->bitmap_lock); zram->old_block_size = old_block_size; zram->bdev = bdev; @@ -445,29 +449,24 @@ static ssize_t backing_dev_store(struct device *dev, static unsigned long get_entry_bdev(struct zram *zram) { - unsigned long entry; - - spin_lock(&zram->bitmap_lock); + unsigned long blk_idx = 1; +retry: /* skip 0 bit to confuse zram.handle = 0 */ - entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1); - if (entry == zram->nr_pages) { - spin_unlock(&zram->bitmap_lock); + blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, blk_idx); + if (blk_idx == zram->nr_pages) return 0; - } - set_bit(entry, zram->bitmap); - spin_unlock(&zram->bitmap_lock); + if (test_and_set_bit(blk_idx, zram->bitmap)) + goto retry; - return entry; + return blk_idx; } static void put_entry_bdev(struct zram *zram, unsigned long entry) { int was_set; - spin_lock(&zram->bitmap_lock); was_set = test_and_clear_bit(entry, zram->bitmap); - spin_unlock(&zram->bitmap_lock); WARN_ON_ONCE(!was_set); } @@ -888,9 +887,10 @@ static ssize_t debug_stat_show(struct device *dev, down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "version: %d\n%8llu\n", + "version: %d\n%8llu %8llu\n", version, - (u64)atomic64_read(&zram->stats.writestall)); + (u64)atomic64_read(&zram->stats.writestall), + (u64)atomic64_read(&zram->stats.miss_free)); up_read(&zram->init_lock); return ret; @@ -1402,10 +1402,14 @@ static void zram_slot_free_notify(struct block_device *bdev, zram = bdev->bd_disk->private_data; - zram_slot_lock(zram, index); + atomic64_inc(&zram->stats.notify_free); + if (!zram_slot_trylock(zram, index)) { + atomic64_inc(&zram->stats.miss_free); + return; + } + zram_free_page(zram, index); zram_slot_unlock(zram, index); - atomic64_inc(&zram->stats.notify_free); } static int zram_rw_page(struct block_device *bdev, sector_t sector, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 72c8584b6dff..d1095dfdffa8 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -79,6 +79,7 @@ struct zram_stats { atomic64_t pages_stored; /* no. of pages currently stored */ atomic_long_t max_used_pages; /* no. of maximum pages stored */ atomic64_t writestall; /* no. of write slow paths */ + atomic64_t miss_free; /* no. of missed free */ }; struct zram { @@ -110,7 +111,6 @@ struct zram { unsigned int old_block_size; unsigned long *bitmap; unsigned long nr_pages; - spinlock_t bitmap_lock; #endif #ifdef CONFIG_ZRAM_MEMORY_TRACKING struct dentry *debugfs_dir; From 4200a93eaccd48b83fe1232823b6ae3ddb5e4211 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 28 Dec 2018 00:36:40 -0800 Subject: [PATCH 009/116] UPSTREAM: zram: refactor flags and writeback stuff Rename some variables and restructure some code for better readability in writeback and zs_free_page. Link: http://lkml.kernel.org/r/20181127055429.251614-4-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Reviewed-by: Joey Pabalinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 7e5292831b346bacb05558ca385cae366187314c) Bug: 117683045 Change-Id: I4ff293133bbd2a6d43a4860220904c08bb381bd0 Signed-off-by: Srinivas Paladugu --- drivers/block/zram/zram_drv.c | 105 +++++++++++++--------------------- drivers/block/zram/zram_drv.h | 8 +-- 2 files changed, 44 insertions(+), 69 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index a65505db09e5..f4afa682a37e 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -55,17 +55,17 @@ static void zram_free_page(struct zram *zram, size_t index); static int zram_slot_trylock(struct zram *zram, u32 index) { - return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].value); + return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].flags); } static void zram_slot_lock(struct zram *zram, u32 index) { - bit_spin_lock(ZRAM_LOCK, &zram->table[index].value); + bit_spin_lock(ZRAM_LOCK, &zram->table[index].flags); } static void zram_slot_unlock(struct zram *zram, u32 index) { - bit_spin_unlock(ZRAM_LOCK, &zram->table[index].value); + bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags); } static inline bool init_done(struct zram *zram) @@ -76,7 +76,7 @@ static inline bool init_done(struct zram *zram) static inline bool zram_allocated(struct zram *zram, u32 index) { - return (zram->table[index].value >> (ZRAM_FLAG_SHIFT + 1)) || + return (zram->table[index].flags >> (ZRAM_FLAG_SHIFT + 1)) || zram->table[index].handle; } @@ -99,19 +99,19 @@ static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle) static bool zram_test_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { - return zram->table[index].value & BIT(flag); + return zram->table[index].flags & BIT(flag); } static void zram_set_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { - zram->table[index].value |= BIT(flag); + zram->table[index].flags |= BIT(flag); } static void zram_clear_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { - zram->table[index].value &= ~BIT(flag); + zram->table[index].flags &= ~BIT(flag); } static inline void zram_set_element(struct zram *zram, u32 index, @@ -127,15 +127,15 @@ static unsigned long zram_get_element(struct zram *zram, u32 index) static size_t zram_get_obj_size(struct zram *zram, u32 index) { - return zram->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1); + return zram->table[index].flags & (BIT(ZRAM_FLAG_SHIFT) - 1); } static void zram_set_obj_size(struct zram *zram, u32 index, size_t size) { - unsigned long flags = zram->table[index].value >> ZRAM_FLAG_SHIFT; + unsigned long flags = zram->table[index].flags >> ZRAM_FLAG_SHIFT; - zram->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size; + zram->table[index].flags = (flags << ZRAM_FLAG_SHIFT) | size; } #if PAGE_SIZE != 4096 @@ -282,16 +282,11 @@ static ssize_t mem_used_max_store(struct device *dev, } #ifdef CONFIG_ZRAM_WRITEBACK -static bool zram_wb_enabled(struct zram *zram) -{ - return zram->backing_dev; -} - static void reset_bdev(struct zram *zram) { struct block_device *bdev; - if (!zram_wb_enabled(zram)) + if (!zram->backing_dev) return; bdev = zram->bdev; @@ -318,7 +313,7 @@ static ssize_t backing_dev_show(struct device *dev, ssize_t ret; down_read(&zram->init_lock); - if (!zram_wb_enabled(zram)) { + if (!zram->backing_dev) { memcpy(buf, "none\n", 5); up_read(&zram->init_lock); return 5; @@ -447,7 +442,7 @@ static ssize_t backing_dev_store(struct device *dev, return err; } -static unsigned long get_entry_bdev(struct zram *zram) +static unsigned long alloc_block_bdev(struct zram *zram) { unsigned long blk_idx = 1; retry: @@ -462,11 +457,11 @@ static unsigned long get_entry_bdev(struct zram *zram) return blk_idx; } -static void put_entry_bdev(struct zram *zram, unsigned long entry) +static void free_block_bdev(struct zram *zram, unsigned long blk_idx) { int was_set; - was_set = test_and_clear_bit(entry, zram->bitmap); + was_set = test_and_clear_bit(blk_idx, zram->bitmap); WARN_ON_ONCE(!was_set); } @@ -579,7 +574,7 @@ static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, if (!bio) return -ENOMEM; - entry = get_entry_bdev(zram); + entry = alloc_block_bdev(zram); if (!entry) { bio_put(bio); return -ENOSPC; @@ -590,7 +585,7 @@ static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) { bio_put(bio); - put_entry_bdev(zram, entry); + free_block_bdev(zram, entry); return -EIO; } @@ -608,18 +603,7 @@ static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, return 0; } -static void zram_wb_clear(struct zram *zram, u32 index) -{ - unsigned long entry; - - zram_clear_flag(zram, index, ZRAM_WB); - entry = zram_get_element(zram, index); - zram_set_element(zram, index, 0); - put_entry_bdev(zram, entry); -} - #else -static bool zram_wb_enabled(struct zram *zram) { return false; } static inline void reset_bdev(struct zram *zram) {}; static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, u32 index, struct bio *parent, @@ -634,7 +618,8 @@ static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, { return -EIO; } -static void zram_wb_clear(struct zram *zram, u32 index) {} + +static void free_block_bdev(struct zram *zram, unsigned long blk_idx) {}; #endif #ifdef CONFIG_ZRAM_MEMORY_TRACKING @@ -656,11 +641,6 @@ static void zram_accessed(struct zram *zram, u32 index) zram->table[index].ac_time = ktime_get_boottime(); } -static void zram_reset_access(struct zram *zram, u32 index) -{ - zram->table[index].ac_time = 0; -} - static ssize_t read_block_state(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -741,7 +721,6 @@ static void zram_debugfs_unregister(struct zram *zram) static void zram_debugfs_create(void) {}; static void zram_debugfs_destroy(void) {}; static void zram_accessed(struct zram *zram, u32 index) {}; -static void zram_reset_access(struct zram *zram, u32 index) {}; static void zram_debugfs_register(struct zram *zram) {}; static void zram_debugfs_unregister(struct zram *zram) {}; #endif @@ -942,17 +921,18 @@ static void zram_free_page(struct zram *zram, size_t index) { unsigned long handle; - zram_reset_access(zram, index); - +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + zram->table[index].ac_time = 0; +#endif if (zram_test_flag(zram, index, ZRAM_HUGE)) { zram_clear_flag(zram, index, ZRAM_HUGE); atomic64_dec(&zram->stats.huge_pages); } - if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) { - zram_wb_clear(zram, index); - atomic64_dec(&zram->stats.pages_stored); - return; + if (zram_test_flag(zram, index, ZRAM_WB)) { + zram_clear_flag(zram, index, ZRAM_WB); + free_block_bdev(zram, zram_get_element(zram, index)); + goto out; } /* @@ -961,10 +941,8 @@ static void zram_free_page(struct zram *zram, size_t index) */ if (zram_test_flag(zram, index, ZRAM_SAME)) { zram_clear_flag(zram, index, ZRAM_SAME); - zram_set_element(zram, index, 0); atomic64_dec(&zram->stats.same_pages); - atomic64_dec(&zram->stats.pages_stored); - return; + goto out; } handle = zram_get_handle(zram, index); @@ -975,10 +953,11 @@ static void zram_free_page(struct zram *zram, size_t index) atomic64_sub(zram_get_obj_size(zram, index), &zram->stats.compr_data_size); +out: atomic64_dec(&zram->stats.pages_stored); - zram_set_handle(zram, index, 0); zram_set_obj_size(zram, index, 0); + WARN_ON_ONCE(zram->table[index].flags & ~(1UL << ZRAM_LOCK)); } static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, @@ -989,24 +968,20 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, unsigned int size; void *src, *dst; - if (zram_wb_enabled(zram)) { - zram_slot_lock(zram, index); - if (zram_test_flag(zram, index, ZRAM_WB)) { - struct bio_vec bvec; + zram_slot_lock(zram, index); + if (zram_test_flag(zram, index, ZRAM_WB)) { + struct bio_vec bvec; - zram_slot_unlock(zram, index); - - bvec.bv_page = page; - bvec.bv_len = PAGE_SIZE; - bvec.bv_offset = 0; - return read_from_bdev(zram, &bvec, - zram_get_element(zram, index), - bio, partial_io); - } zram_slot_unlock(zram, index); + + bvec.bv_page = page; + bvec.bv_len = PAGE_SIZE; + bvec.bv_offset = 0; + return read_from_bdev(zram, &bvec, + zram_get_element(zram, index), + bio, partial_io); } - zram_slot_lock(zram, index); handle = zram_get_handle(zram, index); if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) { unsigned long value; @@ -1118,7 +1093,7 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, if (unlikely(comp_len >= huge_class_size)) { comp_len = PAGE_SIZE; - if (zram_wb_enabled(zram) && allow_wb) { + if (zram->backing_dev && allow_wb) { zcomp_stream_put(zram->comp); ret = write_to_bdev(zram, bvec, index, bio, &element); if (!ret) { diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index d1095dfdffa8..4f83f1f14b0a 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -30,7 +30,7 @@ /* - * The lower ZRAM_FLAG_SHIFT bits of table.value is for + * The lower ZRAM_FLAG_SHIFT bits of table.flags is for * object size (excluding header), the higher bits is for * zram_pageflags. * @@ -41,7 +41,7 @@ */ #define ZRAM_FLAG_SHIFT 24 -/* Flags for zram pages (table[page_no].value) */ +/* Flags for zram pages (table[page_no].flags) */ enum zram_pageflags { /* zram slot is locked */ ZRAM_LOCK = ZRAM_FLAG_SHIFT, @@ -60,7 +60,7 @@ struct zram_table_entry { unsigned long handle; unsigned long element; }; - unsigned long value; + unsigned long flags; #ifdef CONFIG_ZRAM_MEMORY_TRACKING ktime_t ac_time; #endif @@ -105,8 +105,8 @@ struct zram { * zram is claimed so open request will be failed */ bool claim; /* Protected by bdev->bd_mutex */ -#ifdef CONFIG_ZRAM_WRITEBACK struct file *backing_dev; +#ifdef CONFIG_ZRAM_WRITEBACK struct block_device *bdev; unsigned int old_block_size; unsigned long *bitmap; From 4e44ef7e23e6f21f7df815084ee762d95919151e Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 28 Dec 2018 00:36:44 -0800 Subject: [PATCH 010/116] UPSTREAM: zram: introduce ZRAM_IDLE flag To support idle page writeback with upcoming patches, this patch introduces a new ZRAM_IDLE flag. Userspace can mark zram slots as "idle" via "echo all > /sys/block/zramX/idle" which marks every allocated zram slot as ZRAM_IDLE. User could see it by /sys/kernel/debug/zram/zram0/block_state. 300 75.033841 ...i 301 63.806904 s..i 302 63.806919 ..hi Once there is IO for the slot, the mark will be disappeared. 300 75.033841 ... 301 63.806904 s..i 302 63.806919 ..hi Therefore, 300th block is idle zpage. With this feature, user can how many zram has idle pages which are waste of memory. Link: http://lkml.kernel.org/r/20181127055429.251614-5-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Reviewed-by: Joey Pabalinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit e82592c4fd7eafe8dec12a70436e93e3afb28556) Bug: 117683045 Change-Id: Ie9545751de4cfce89885989cc6ee35a50691ff4e Signed-off-by: Srinivas Paladugu --- Documentation/ABI/testing/sysfs-block-zram | 8 +++ Documentation/blockdev/zram.txt | 10 ++-- drivers/block/zram/zram_drv.c | 57 ++++++++++++++++++++-- drivers/block/zram/zram_drv.h | 1 + 4 files changed, 69 insertions(+), 7 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index c1513c756af1..04c9a5980bc7 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -98,3 +98,11 @@ Description: The backing_dev file is read-write and set up backing device for zram to write incompressible pages. For using, user should enable CONFIG_ZRAM_WRITEBACK. + +What: /sys/block/zram/idle +Date: November 2018 +Contact: Minchan Kim +Description: + idle file is write-only and mark zram slot as idle. + If system has mounted debugfs, user can see which slots + are idle via /sys/kernel/debug/zram/zram/block_state diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 875b2b56b87f..0c7452dfbbfa 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -169,6 +169,7 @@ comp_algorithm RW show and change the compression algorithm compact WO trigger memory compaction debug_stat RO this file is used for zram debugging purposes backing_dev RW set up backend storage for zram to write out +idle WO mark allocated slot as idle User space is advised to use the following files to read the device statistics. @@ -251,16 +252,17 @@ pages of the process with*pagemap. If you enable the feature, you could see block state via /sys/kernel/debug/zram/zram0/block_state". The output is as follows, - 300 75.033841 .wh - 301 63.806904 s.. - 302 63.806919 ..h + 300 75.033841 .wh. + 301 63.806904 s... + 302 63.806919 ..hi First column is zram's block index. Second column is access time since the system was booted Third column is state of the block. (s: same page w: written page to backing store -h: huge page) +h: huge page +i: idle page) First line of above example says 300th block is accessed at 75.033841sec and the block's state is huge so it is written back to the backing diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index f4afa682a37e..bb54b2d9f536 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -281,6 +281,47 @@ static ssize_t mem_used_max_store(struct device *dev, return len; } +static ssize_t idle_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + int index; + char mode_buf[8]; + ssize_t sz; + + sz = strscpy(mode_buf, buf, sizeof(mode_buf)); + if (sz <= 0) + return -EINVAL; + + /* ignore trailing new line */ + if (mode_buf[sz - 1] == '\n') + mode_buf[sz - 1] = 0x00; + + if (strcmp(mode_buf, "all")) + return -EINVAL; + + down_read(&zram->init_lock); + if (!init_done(zram)) { + up_read(&zram->init_lock); + return -EINVAL; + } + + for (index = 0; index < nr_pages; index++) { + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index)) + goto next; + + zram_set_flag(zram, index, ZRAM_IDLE); +next: + zram_slot_unlock(zram, index); + } + + up_read(&zram->init_lock); + + return len; +} + #ifdef CONFIG_ZRAM_WRITEBACK static void reset_bdev(struct zram *zram) { @@ -638,6 +679,7 @@ static void zram_debugfs_destroy(void) static void zram_accessed(struct zram *zram, u32 index) { + zram_clear_flag(zram, index, ZRAM_IDLE); zram->table[index].ac_time = ktime_get_boottime(); } @@ -670,12 +712,13 @@ static ssize_t read_block_state(struct file *file, char __user *buf, ts = ktime_to_timespec64(zram->table[index].ac_time); copied = snprintf(kbuf + written, count, - "%12zd %12lld.%06lu %c%c%c\n", + "%12zd %12lld.%06lu %c%c%c%c\n", index, (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC, zram_test_flag(zram, index, ZRAM_SAME) ? 's' : '.', zram_test_flag(zram, index, ZRAM_WB) ? 'w' : '.', - zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.'); + zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.', + zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.'); if (count < copied) { zram_slot_unlock(zram, index); @@ -720,7 +763,10 @@ static void zram_debugfs_unregister(struct zram *zram) #else static void zram_debugfs_create(void) {}; static void zram_debugfs_destroy(void) {}; -static void zram_accessed(struct zram *zram, u32 index) {}; +static void zram_accessed(struct zram *zram, u32 index) +{ + zram_clear_flag(zram, index, ZRAM_IDLE); +}; static void zram_debugfs_register(struct zram *zram) {}; static void zram_debugfs_unregister(struct zram *zram) {}; #endif @@ -924,6 +970,9 @@ static void zram_free_page(struct zram *zram, size_t index) #ifdef CONFIG_ZRAM_MEMORY_TRACKING zram->table[index].ac_time = 0; #endif + if (zram_test_flag(zram, index, ZRAM_IDLE)) + zram_clear_flag(zram, index, ZRAM_IDLE); + if (zram_test_flag(zram, index, ZRAM_HUGE)) { zram_clear_flag(zram, index, ZRAM_HUGE); atomic64_dec(&zram->stats.huge_pages); @@ -1589,6 +1638,7 @@ static DEVICE_ATTR_RO(initstate); static DEVICE_ATTR_WO(reset); static DEVICE_ATTR_WO(mem_limit); static DEVICE_ATTR_WO(mem_used_max); +static DEVICE_ATTR_WO(idle); static DEVICE_ATTR_RW(max_comp_streams); static DEVICE_ATTR_RW(comp_algorithm); #ifdef CONFIG_ZRAM_WRITEBACK @@ -1602,6 +1652,7 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_compact.attr, &dev_attr_mem_limit.attr, &dev_attr_mem_used_max.attr, + &dev_attr_idle.attr, &dev_attr_max_comp_streams.attr, &dev_attr_comp_algorithm.attr, #ifdef CONFIG_ZRAM_WRITEBACK diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 4f83f1f14b0a..a84611b97867 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -48,6 +48,7 @@ enum zram_pageflags { ZRAM_SAME, /* Page consists the same element */ ZRAM_WB, /* page is stored on backing_device */ ZRAM_HUGE, /* Incompressible page */ + ZRAM_IDLE, /* not accessed page since last idle marking */ __NR_ZRAM_PAGEFLAGS, }; From 8a42676beef3de3b13ff23749c8934f5283e99c6 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 28 Dec 2018 00:36:47 -0800 Subject: [PATCH 011/116] UPSTREAM: zram: support idle/huge page writeback Add a new feature "zram idle/huge page writeback". In the zram-swap use case, zram usually has many idle/huge swap pages. It's pointless to keep them in memory (ie, zram). To solve this problem, this feature introduces idle/huge page writeback to the backing device so the goal is to save more memory space on embedded systems. Normal sequence to use idle/huge page writeback feature is as follows, while (1) { # mark allocated zram slot to idle echo all > /sys/block/zram0/idle # leave system working for several hours # Unless there is no access for some blocks on zram, # they are still IDLE marked pages. echo "idle" > /sys/block/zram0/writeback or/and echo "huge" > /sys/block/zram0/writeback # write the IDLE or/and huge marked slot into backing device # and free the memory. } Per the discussion at https://lore.kernel.org/lkml/20181122065926.GG3441@jagdpanzerIV/T/#u, This patch removes direct incommpressibe page writeback feature (d2afd25114f4 ("zram: write incompressible pages to backing device")). Below concerns from Sergey: == &< == "IDLE writeback" is superior to "incompressible writeback". "incompressible writeback" is completely unpredictable and uncontrollable; it depens on data patterns and compression algorithms. While "IDLE writeback" is predictable. I even suspect, that, *ideally*, we can remove "incompressible writeback". "IDLE pages" is a super set which also includes "incompressible" pages. So, technically, we still can do "incompressible writeback" from "IDLE writeback" path; but a much more reasonable one, based on a page idling period. I understand that you want to keep "direct incompressible writeback" around. ZRAM is especially popular on devices which do suffer from flash wearout, so I can see "incompressible writeback" path becoming a dead code, long term. == &< == Below concerns from Minchan: == &< == My concern is if we enable CONFIG_ZRAM_WRITEBACK in this implementation, both hugepage/idlepage writeck will turn on. However someuser want to enable only idlepage writeback so we need to introduce turn on/off knob for hugepage or new CONFIG_ZRAM_IDLEPAGE_WRITEBACK for those usecase. I don't want to make it complicated *if possible*. Long term, I imagine we need to make VM aware of new swap hierarchy a little bit different with as-is. For example, first high priority swap can return -EIO or -ENOCOMP, swap try to fallback to next lower priority swap device. With that, hugepage writeback will work tranparently. So we could regard it as regression because incompressible pages doesn't go to backing storage automatically. Instead, user should do it via "echo huge" > /sys/block/zram/writeback" manually. == &< == Link: http://lkml.kernel.org/r/20181127055429.251614-6-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: Joey Pabalinas Reviewed-by: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit a939888ec38bf1f33e4a903056677e92a4844244) Bug: 117683045 Change-Id: I82afe541fdb60b24cde74f42de4d6b3dd6d8266c Signed-off-by: Srinivas Paladugu --- Documentation/ABI/testing/sysfs-block-zram | 7 + Documentation/blockdev/zram.txt | 28 ++- drivers/block/zram/Kconfig | 5 +- drivers/block/zram/zram_drv.c | 247 +++++++++++++++------ drivers/block/zram/zram_drv.h | 1 + 5 files changed, 209 insertions(+), 79 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index 04c9a5980bc7..d1f80b077885 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -106,3 +106,10 @@ Description: idle file is write-only and mark zram slot as idle. If system has mounted debugfs, user can see which slots are idle via /sys/kernel/debug/zram/zram/block_state + +What: /sys/block/zram/writeback +Date: November 2018 +Contact: Minchan Kim +Description: + The writeback file is write-only and trigger idle and/or + huge page writeback to backing device. diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 0c7452dfbbfa..fe259b1ab1dc 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -238,11 +238,31 @@ line of text and contains the following stats separated by whitespace: = writeback -With incompressible pages, there is no memory saving with zram. -Instead, with CONFIG_ZRAM_WRITEBACK, zram can write incompressible page +With CONFIG_ZRAM_WRITEBACK, zram can write idle/incompressible page to backing storage rather than keeping it in memory. -User should set up backing device via /sys/block/zramX/backing_dev -before disksize setting. +To use the feature, admin should set up backing device via + + "echo /dev/sda5 > /sys/block/zramX/backing_dev" + +before disksize setting. It supports only partition at this moment. +If admin want to use incompressible page writeback, they could do via + + "echo huge > /sys/block/zramX/write" + +To use idle page writeback, first, user need to declare zram pages +as idle. + + "echo all > /sys/block/zramX/idle" + +From now on, any pages on zram are idle pages. The idle mark +will be removed until someone request access of the block. +IOW, unless there is access request, those pages are still idle pages. + +Admin can request writeback of those idle pages at right timing via + + "echo idle > /sys/block/zramX/writeback" + +With the command, zram writeback idle pages from memory to the storage. = memory tracking diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index 635235759a0a..99a2c60c7c6f 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -16,7 +16,7 @@ config ZRAM See Documentation/blockdev/zram.txt for more information. config ZRAM_WRITEBACK - bool "Write back incompressible page to backing device" + bool "Write back incompressible or idle page to backing device" depends on ZRAM default n help @@ -25,6 +25,9 @@ config ZRAM_WRITEBACK For this feature, admin should set up backing device via /sys/block/zramX/backing_dev. + With /sys/block/zramX/{idle,writeback}, application could ask + idle page's writeback to the backing device to save in memory. + See Documentation/blockdev/zram.txt for more information. config ZRAM_MEMORY_TRACKING diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index bb54b2d9f536..25099434c338 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -52,6 +52,9 @@ static unsigned int num_devices = 1; static size_t huge_class_size; static void zram_free_page(struct zram *zram, size_t index); +static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, + u32 index, int offset, struct bio *bio); + static int zram_slot_trylock(struct zram *zram, u32 index) { @@ -73,13 +76,6 @@ static inline bool init_done(struct zram *zram) return zram->disksize; } -static inline bool zram_allocated(struct zram *zram, u32 index) -{ - - return (zram->table[index].flags >> (ZRAM_FLAG_SHIFT + 1)) || - zram->table[index].handle; -} - static inline struct zram *dev_to_zram(struct device *dev) { return (struct zram *)dev_to_disk(dev)->private_data; @@ -138,6 +134,13 @@ static void zram_set_obj_size(struct zram *zram, zram->table[index].flags = (flags << ZRAM_FLAG_SHIFT) | size; } +static inline bool zram_allocated(struct zram *zram, u32 index) +{ + return zram_get_obj_size(zram, index) || + zram_test_flag(zram, index, ZRAM_SAME) || + zram_test_flag(zram, index, ZRAM_WB); +} + #if PAGE_SIZE != 4096 static inline bool is_partial_io(struct bio_vec *bvec) { @@ -308,10 +311,14 @@ static ssize_t idle_store(struct device *dev, } for (index = 0; index < nr_pages; index++) { + /* + * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race. + * See the comment in writeback_store. + */ zram_slot_lock(zram, index); - if (!zram_allocated(zram, index)) + if (!zram_allocated(zram, index) || + zram_test_flag(zram, index, ZRAM_UNDER_WB)) goto next; - zram_set_flag(zram, index, ZRAM_IDLE); next: zram_slot_unlock(zram, index); @@ -546,6 +553,158 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, return 1; } +#define HUGE_WRITEBACK 0x1 +#define IDLE_WRITEBACK 0x2 + +static ssize_t writeback_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + unsigned long index; + struct bio bio; + struct bio_vec bio_vec; + struct page *page; + ssize_t ret, sz; + char mode_buf[8]; + unsigned long mode = -1UL; + unsigned long blk_idx = 0; + + sz = strscpy(mode_buf, buf, sizeof(mode_buf)); + if (sz <= 0) + return -EINVAL; + + /* ignore trailing newline */ + if (mode_buf[sz - 1] == '\n') + mode_buf[sz - 1] = 0x00; + + if (!strcmp(mode_buf, "idle")) + mode = IDLE_WRITEBACK; + else if (!strcmp(mode_buf, "huge")) + mode = HUGE_WRITEBACK; + + if (mode == -1UL) + return -EINVAL; + + down_read(&zram->init_lock); + if (!init_done(zram)) { + ret = -EINVAL; + goto release_init_lock; + } + + if (!zram->backing_dev) { + ret = -ENODEV; + goto release_init_lock; + } + + page = alloc_page(GFP_KERNEL); + if (!page) { + ret = -ENOMEM; + goto release_init_lock; + } + + for (index = 0; index < nr_pages; index++) { + struct bio_vec bvec; + + bvec.bv_page = page; + bvec.bv_len = PAGE_SIZE; + bvec.bv_offset = 0; + + if (!blk_idx) { + blk_idx = alloc_block_bdev(zram); + if (!blk_idx) { + ret = -ENOSPC; + break; + } + } + + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index)) + goto next; + + if (zram_test_flag(zram, index, ZRAM_WB) || + zram_test_flag(zram, index, ZRAM_SAME) || + zram_test_flag(zram, index, ZRAM_UNDER_WB)) + goto next; + + if ((mode & IDLE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_IDLE)) && + (mode & HUGE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_HUGE))) + goto next; + /* + * Clearing ZRAM_UNDER_WB is duty of caller. + * IOW, zram_free_page never clear it. + */ + zram_set_flag(zram, index, ZRAM_UNDER_WB); + /* Need for hugepage writeback racing */ + zram_set_flag(zram, index, ZRAM_IDLE); + zram_slot_unlock(zram, index); + if (zram_bvec_read(zram, &bvec, index, 0, NULL)) { + zram_slot_lock(zram, index); + zram_clear_flag(zram, index, ZRAM_UNDER_WB); + zram_clear_flag(zram, index, ZRAM_IDLE); + zram_slot_unlock(zram, index); + continue; + } + + bio_init(&bio, &bio_vec, 1); + bio_set_dev(&bio, zram->bdev); + bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); + bio.bi_opf = REQ_OP_WRITE | REQ_SYNC; + + bio_add_page(&bio, bvec.bv_page, bvec.bv_len, + bvec.bv_offset); + /* + * XXX: A single page IO would be inefficient for write + * but it would be not bad as starter. + */ + ret = submit_bio_wait(&bio); + if (ret) { + zram_slot_lock(zram, index); + zram_clear_flag(zram, index, ZRAM_UNDER_WB); + zram_clear_flag(zram, index, ZRAM_IDLE); + zram_slot_unlock(zram, index); + continue; + } + + /* + * We released zram_slot_lock so need to check if the slot was + * changed. If there is freeing for the slot, we can catch it + * easily by zram_allocated. + * A subtle case is the slot is freed/reallocated/marked as + * ZRAM_IDLE again. To close the race, idle_store doesn't + * mark ZRAM_IDLE once it found the slot was ZRAM_UNDER_WB. + * Thus, we could close the race by checking ZRAM_IDLE bit. + */ + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index) || + !zram_test_flag(zram, index, ZRAM_IDLE)) { + zram_clear_flag(zram, index, ZRAM_UNDER_WB); + zram_clear_flag(zram, index, ZRAM_IDLE); + goto next; + } + + zram_free_page(zram, index); + zram_clear_flag(zram, index, ZRAM_UNDER_WB); + zram_set_flag(zram, index, ZRAM_WB); + zram_set_element(zram, index, blk_idx); + blk_idx = 0; + atomic64_inc(&zram->stats.pages_stored); +next: + zram_slot_unlock(zram, index); + } + + if (blk_idx) + free_block_bdev(zram, blk_idx); + ret = len; + __free_page(page); +release_init_lock: + up_read(&zram->init_lock); + + return ret; +} + struct zram_work { struct work_struct work; struct zram *zram; @@ -603,57 +762,8 @@ static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, else return read_from_bdev_async(zram, bvec, entry, parent); } - -static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, - u32 index, struct bio *parent, - unsigned long *pentry) -{ - struct bio *bio; - unsigned long entry; - - bio = bio_alloc(GFP_ATOMIC, 1); - if (!bio) - return -ENOMEM; - - entry = alloc_block_bdev(zram); - if (!entry) { - bio_put(bio); - return -ENOSPC; - } - - bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); - bio_set_dev(bio, zram->bdev); - if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, - bvec->bv_offset)) { - bio_put(bio); - free_block_bdev(zram, entry); - return -EIO; - } - - if (!parent) { - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC; - bio->bi_end_io = zram_page_end_io; - } else { - bio->bi_opf = parent->bi_opf; - bio_chain(bio, parent); - } - - submit_bio(bio); - *pentry = entry; - - return 0; -} - #else static inline void reset_bdev(struct zram *zram) {}; -static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, - u32 index, struct bio *parent, - unsigned long *pentry) - -{ - return -EIO; -} - static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, unsigned long entry, struct bio *parent, bool sync) { @@ -1006,7 +1116,8 @@ static void zram_free_page(struct zram *zram, size_t index) atomic64_dec(&zram->stats.pages_stored); zram_set_handle(zram, index, 0); zram_set_obj_size(zram, index, 0); - WARN_ON_ONCE(zram->table[index].flags & ~(1UL << ZRAM_LOCK)); + WARN_ON_ONCE(zram->table[index].flags & + ~(1UL << ZRAM_LOCK | 1UL << ZRAM_UNDER_WB)); } static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, @@ -1115,7 +1226,6 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, struct page *page = bvec->bv_page; unsigned long element = 0; enum zram_pageflags flags = 0; - bool allow_wb = true; mem = kmap_atomic(page); if (page_same_filled(mem, &element)) { @@ -1140,21 +1250,8 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, return ret; } - if (unlikely(comp_len >= huge_class_size)) { + if (comp_len >= huge_class_size) comp_len = PAGE_SIZE; - if (zram->backing_dev && allow_wb) { - zcomp_stream_put(zram->comp); - ret = write_to_bdev(zram, bvec, index, bio, &element); - if (!ret) { - flags = ZRAM_WB; - ret = 1; - goto out; - } - allow_wb = false; - goto compress_again; - } - } - /* * handle allocation has 2 paths: * a) fast path is executed with preemption disabled (for @@ -1643,6 +1740,7 @@ static DEVICE_ATTR_RW(max_comp_streams); static DEVICE_ATTR_RW(comp_algorithm); #ifdef CONFIG_ZRAM_WRITEBACK static DEVICE_ATTR_RW(backing_dev); +static DEVICE_ATTR_WO(writeback); #endif static struct attribute *zram_disk_attrs[] = { @@ -1657,6 +1755,7 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_comp_algorithm.attr, #ifdef CONFIG_ZRAM_WRITEBACK &dev_attr_backing_dev.attr, + &dev_attr_writeback.attr, #endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index a84611b97867..1ad74f030b6d 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -47,6 +47,7 @@ enum zram_pageflags { ZRAM_LOCK = ZRAM_FLAG_SHIFT, ZRAM_SAME, /* Page consists the same element */ ZRAM_WB, /* page is stored on backing_device */ + ZRAM_UNDER_WB, /* page is under writeback */ ZRAM_HUGE, /* Incompressible page */ ZRAM_IDLE, /* not accessed page since last idle marking */ From 63c8a466f6daa77a24759df12629d385c8c14a0f Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 28 Dec 2018 00:36:51 -0800 Subject: [PATCH 012/116] UPSTREAM: zram: add bd_stat statistics bd_stat represents things that happened in the backing device. Currently it supports bd_counts, bd_reads and bd_writes which are helpful to understand wearout of flash and memory saving. [minchan@kernel.org: v4] Link: http://lkml.kernel.org/r/20181203024045.153534-7-minchan@kernel.org Link: http://lkml.kernel.org/r/20181127055429.251614-7-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Joey Pabalinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 23eddf39b2c28c05cb8f8203d38e61807d701b38) Bug: 117683045 Change-Id: I9ae38c3b15876be9188dd40366caa0baa06742c0 Signed-off-by: Srinivas Paladugu --- Documentation/ABI/testing/sysfs-block-zram | 8 ++++++ Documentation/blockdev/zram.txt | 11 ++++++++ drivers/block/zram/zram_drv.c | 29 ++++++++++++++++++++++ drivers/block/zram/zram_drv.h | 5 ++++ 4 files changed, 53 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index d1f80b077885..65fc33b2f53b 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -113,3 +113,11 @@ Contact: Minchan Kim Description: The writeback file is write-only and trigger idle and/or huge page writeback to backing device. + +What: /sys/block/zram/bd_stat +Date: November 2018 +Contact: Minchan Kim +Description: + The bd_stat file is read-only and represents backing device's + statistics (bd_count, bd_reads, bd_writes) in a format + similar to block layer statistics file format. diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index fe259b1ab1dc..15a8c7201cf6 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -221,6 +221,17 @@ line of text and contains the following stats separated by whitespace: pages_compacted the number of pages freed during compaction huge_pages the number of incompressible pages +File /sys/block/zram/bd_stat + +The stat file represents device's backing device statistics. It consists of +a single line of text and contains the following stats separated by whitespace: + bd_count size of data written in backing device. + Unit: 4K bytes + bd_reads the number of reads from backing device + Unit: 4K bytes + bd_writes the number of writes to backing device + Unit: 4K bytes + 9) Deactivate: swapoff /dev/zram0 umount /dev/zram1 diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 25099434c338..469111317208 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -502,6 +502,7 @@ static unsigned long alloc_block_bdev(struct zram *zram) if (test_and_set_bit(blk_idx, zram->bitmap)) goto retry; + atomic64_inc(&zram->stats.bd_count); return blk_idx; } @@ -511,6 +512,7 @@ static void free_block_bdev(struct zram *zram, unsigned long blk_idx) was_set = test_and_clear_bit(blk_idx, zram->bitmap); WARN_ON_ONCE(!was_set); + atomic64_dec(&zram->stats.bd_count); } static void zram_page_end_io(struct bio *bio) @@ -668,6 +670,7 @@ static ssize_t writeback_store(struct device *dev, continue; } + atomic64_inc(&zram->stats.bd_writes); /* * We released zram_slot_lock so need to check if the slot was * changed. If there is freeing for the slot, we can catch it @@ -757,6 +760,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, unsigned long entry, struct bio *parent, bool sync) { + atomic64_inc(&zram->stats.bd_reads); if (sync) return read_from_bdev_sync(zram, bvec, entry, parent); else @@ -1013,6 +1017,25 @@ static ssize_t mm_stat_show(struct device *dev, return ret; } +#ifdef CONFIG_ZRAM_WRITEBACK +static ssize_t bd_stat_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct zram *zram = dev_to_zram(dev); + ssize_t ret; + + down_read(&zram->init_lock); + ret = scnprintf(buf, PAGE_SIZE, + "%8llu %8llu %8llu\n", + (u64)atomic64_read(&zram->stats.bd_count) * (PAGE_SHIFT - 12), + (u64)atomic64_read(&zram->stats.bd_reads) * (PAGE_SHIFT - 12), + (u64)atomic64_read(&zram->stats.bd_writes) * (PAGE_SHIFT - 12)); + up_read(&zram->init_lock); + + return ret; +} +#endif + static ssize_t debug_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -1033,6 +1056,9 @@ static ssize_t debug_stat_show(struct device *dev, static DEVICE_ATTR_RO(io_stat); static DEVICE_ATTR_RO(mm_stat); +#ifdef CONFIG_ZRAM_WRITEBACK +static DEVICE_ATTR_RO(bd_stat); +#endif static DEVICE_ATTR_RO(debug_stat); static void zram_meta_free(struct zram *zram, u64 disksize) @@ -1759,6 +1785,9 @@ static struct attribute *zram_disk_attrs[] = { #endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, +#ifdef CONFIG_ZRAM_WRITEBACK + &dev_attr_bd_stat.attr, +#endif &dev_attr_debug_stat.attr, NULL, }; diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 1ad74f030b6d..bc477803530d 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -82,6 +82,11 @@ struct zram_stats { atomic_long_t max_used_pages; /* no. of maximum pages stored */ atomic64_t writestall; /* no. of write slow paths */ atomic64_t miss_free; /* no. of missed free */ +#ifdef CONFIG_ZRAM_WRITEBACK + atomic64_t bd_count; /* no. of pages in backing device */ + atomic64_t bd_reads; /* no. of reads from backing device */ + atomic64_t bd_writes; /* no. of writes from backing device */ +#endif }; struct zram { From e610df0c90f1a74ca65d558d50642f1228a04a4c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 28 Dec 2018 00:36:54 -0800 Subject: [PATCH 013/116] UPSTREAM: zram: writeback throttle If there are lots of write IO with flash device, it could have a wearout problem of storage. To overcome the problem, admin needs to design write limitation to guarantee flash health for entire product life. This patch creates a new knob "writeback_limit" for zram. writeback_limit's default value is 0 so that it doesn't limit any writeback. If admin want to measure writeback count in a certain period, he could know it via /sys/block/zram0/bd_stat's 3rd column. If admin want to limit writeback as per-day 400M, he could do it like below. MB_SHIFT=20 4K_SHIFT=12 echo $((400<>4K_SHIFT)) > \ /sys/block/zram0/writeback_limit. If admin want to allow further write again, he could do it like below echo 0 > /sys/block/zram0/writeback_limit If admin want to see remaining writeback budget, cat /sys/block/zram0/writeback_limit The writeback_limit count will reset whenever you reset zram (e.g., system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of writeback happened until you reset the zram to allocate extra writeback budget in next setting is user's job. [minchan@kernel.org: v4] Link: http://lkml.kernel.org/r/20181203024045.153534-8-minchan@kernel.org Link: http://lkml.kernel.org/r/20181127055429.251614-8-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Joey Pabalinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit bb416d18b850faaa44bd3bb67c9728922c3cce98) Bug: 117683045 Change-Id: Ib82f76d1cecaf251e75584f8140c9b4949cd27b2 Signed-off-by: Srinivas Paladugu --- Documentation/ABI/testing/sysfs-block-zram | 9 ++++ Documentation/blockdev/zram.txt | 31 +++++++++++++ drivers/block/zram/zram_drv.c | 52 ++++++++++++++++++++-- drivers/block/zram/zram_drv.h | 2 + 4 files changed, 91 insertions(+), 3 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index 65fc33b2f53b..9d2339a485c8 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -121,3 +121,12 @@ Description: The bd_stat file is read-only and represents backing device's statistics (bd_count, bd_reads, bd_writes) in a format similar to block layer statistics file format. + +What: /sys/block/zram/writeback_limit +Date: November 2018 +Contact: Minchan Kim +Description: + The writeback_limit file is read-write and specifies the maximum + amount of writeback ZRAM can do. The limit could be changed + in run time and "0" means disable the limit. + No limit is the initial state. diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 15a8c7201cf6..1072a267fc10 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -164,6 +164,8 @@ reset WO trigger device reset mem_used_max WO reset the `mem_used_max' counter (see later) mem_limit WO specifies the maximum amount of memory ZRAM can use to store the compressed data +writeback_limit WO specifies the maximum amount of write IO zram can + write out to backing device as 4KB unit max_comp_streams RW the number of possible concurrent compress operations comp_algorithm RW show and change the compression algorithm compact WO trigger memory compaction @@ -275,6 +277,35 @@ Admin can request writeback of those idle pages at right timing via With the command, zram writeback idle pages from memory to the storage. +If there are lots of write IO with flash device, potentially, it has +flash wearout problem so that admin needs to design write limitation +to guarantee storage health for entire product life. +To overcome the concern, zram supports "writeback_limit". +The "writeback_limit"'s default value is 0 so that it doesn't limit +any writeback. If admin want to measure writeback count in a certain +period, he could know it via /sys/block/zram0/bd_stat's 3rd column. + +If admin want to limit writeback as per-day 400M, he could do it +like below. + + MB_SHIFT=20 + 4K_SHIFT=12 + echo $((400<>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit. + +If admin want to allow further write again, he could do it like below + + echo 0 > /sys/block/zram0/writeback_limit + +If admin want to see remaining writeback budget since he set, + + cat /sys/block/zram0/writeback_limit + +The writeback_limit count will reset whenever you reset zram(e.g., +system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of +writeback happened until you reset the zram to allocate extra writeback +budget in next setting is user's job. + = memory tracking With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 469111317208..ff0a6af97580 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -330,6 +330,39 @@ static ssize_t idle_store(struct device *dev, } #ifdef CONFIG_ZRAM_WRITEBACK +static ssize_t writeback_limit_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + u64 val; + ssize_t ret = -EINVAL; + + if (kstrtoull(buf, 10, &val)) + return ret; + + down_read(&zram->init_lock); + atomic64_set(&zram->stats.bd_wb_limit, val); + if (val == 0) + zram->stop_writeback = false; + up_read(&zram->init_lock); + ret = len; + + return ret; +} + +static ssize_t writeback_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u64 val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + val = atomic64_read(&zram->stats.bd_wb_limit); + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", val); +} + static void reset_bdev(struct zram *zram) { struct block_device *bdev; @@ -612,6 +645,11 @@ static ssize_t writeback_store(struct device *dev, bvec.bv_len = PAGE_SIZE; bvec.bv_offset = 0; + if (zram->stop_writeback) { + ret = -EIO; + break; + } + if (!blk_idx) { blk_idx = alloc_block_bdev(zram); if (!blk_idx) { @@ -694,6 +732,11 @@ static ssize_t writeback_store(struct device *dev, zram_set_element(zram, index, blk_idx); blk_idx = 0; atomic64_inc(&zram->stats.pages_stored); + if (atomic64_add_unless(&zram->stats.bd_wb_limit, + -1 << (PAGE_SHIFT - 12), 0)) { + if (atomic64_read(&zram->stats.bd_wb_limit) == 0) + zram->stop_writeback = true; + } next: zram_slot_unlock(zram, index); } @@ -1018,6 +1061,7 @@ static ssize_t mm_stat_show(struct device *dev, } #ifdef CONFIG_ZRAM_WRITEBACK +#define FOUR_K(x) ((x) * (1 << (PAGE_SHIFT - 12))) static ssize_t bd_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -1027,9 +1071,9 @@ static ssize_t bd_stat_show(struct device *dev, down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, "%8llu %8llu %8llu\n", - (u64)atomic64_read(&zram->stats.bd_count) * (PAGE_SHIFT - 12), - (u64)atomic64_read(&zram->stats.bd_reads) * (PAGE_SHIFT - 12), - (u64)atomic64_read(&zram->stats.bd_writes) * (PAGE_SHIFT - 12)); + FOUR_K((u64)atomic64_read(&zram->stats.bd_count)), + FOUR_K((u64)atomic64_read(&zram->stats.bd_reads)), + FOUR_K((u64)atomic64_read(&zram->stats.bd_writes))); up_read(&zram->init_lock); return ret; @@ -1767,6 +1811,7 @@ static DEVICE_ATTR_RW(comp_algorithm); #ifdef CONFIG_ZRAM_WRITEBACK static DEVICE_ATTR_RW(backing_dev); static DEVICE_ATTR_WO(writeback); +static DEVICE_ATTR_RW(writeback_limit); #endif static struct attribute *zram_disk_attrs[] = { @@ -1782,6 +1827,7 @@ static struct attribute *zram_disk_attrs[] = { #ifdef CONFIG_ZRAM_WRITEBACK &dev_attr_backing_dev.attr, &dev_attr_writeback.attr, + &dev_attr_writeback_limit.attr, #endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index bc477803530d..4bd3afd15e83 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -86,6 +86,7 @@ struct zram_stats { atomic64_t bd_count; /* no. of pages in backing device */ atomic64_t bd_reads; /* no. of reads from backing device */ atomic64_t bd_writes; /* no. of writes from backing device */ + atomic64_t bd_wb_limit; /* writeback limit of backing device */ #endif }; @@ -113,6 +114,7 @@ struct zram { */ bool claim; /* Protected by bdev->bd_mutex */ struct file *backing_dev; + bool stop_writeback; #ifdef CONFIG_ZRAM_WRITEBACK struct block_device *bdev; unsigned int old_block_size; From 5f5d7b0063773eebde60316c612d3de152c15056 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 8 Jan 2019 15:22:53 -0800 Subject: [PATCH 014/116] UPSTREAM: zram: idle writeback fixes and cleanup This patch includes some fixes and cleanup for idle-page writeback. 1. writeback_limit interface Now writeback_limit interface is rather conusing. For example, once writeback limit budget is exausted, admin can see 0 from /sys/block/zramX/writeback_limit which is same semantic with disable writeback_limit at this moment. IOW, admin cannot tell that zero came from disable writeback limit or exausted writeback limit. To make the interface clear, let's sepatate enable of writeback limit to another knob - /sys/block/zram0/writeback_limit_enable * before: while true : # to re-enable writeback limit once previous one is used up echo 0 > /sys/block/zram0/writeback_limit echo $((200<<20)) > /sys/block/zram0/writeback_limit .. .. # used up the writeback limit budget * new # To enable writeback limit, from the beginning, admin should # enable it. echo $((200<<20)) > /sys/block/zram0/writeback_limit echo 1 > /sys/block/zram/0/writeback_limit_enable while true : echo $((200<<20)) > /sys/block/zram0/writeback_limit .. .. # used up the writeback limit budget It's much strightforward. 2. fix condition check idle/huge writeback mode check The mode in writeback_store is not bit opeartion any more so no need to use bit operations. Furthermore, current condition check is broken in that it does writeback every pages regardless of huge/idle. 3. clean up idle_store No need to use goto. [minchan@kernel.org: missed spin_lock_init] Link: http://lkml.kernel.org/r/20190103001601.GA255139@google.com Link: http://lkml.kernel.org/r/20181224033529.19450-1-minchan@kernel.org Signed-off-by: Minchan Kim Suggested-by: John Dias Cc: Sergey Senozhatsky Cc: John Dias Cc: Srinivas Paladugu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds (cherry picked from commit 1d69a3f8ae77e3dbfdc1356225cce5ea9c366aec) Bug: 117683045 Change-Id: Ibdedcfd5fd886d6771f1300efb1caa039488a0ca Signed-off-by: Srinivas Paladugu --- Documentation/ABI/testing/sysfs-block-zram | 11 ++- Documentation/blockdev/zram.txt | 74 +++++++++++------- drivers/block/zram/zram_drv.c | 90 ++++++++++++++++------ drivers/block/zram/zram_drv.h | 5 +- 4 files changed, 125 insertions(+), 55 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index 9d2339a485c8..14b2bf2e5105 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -122,11 +122,18 @@ Description: statistics (bd_count, bd_reads, bd_writes) in a format similar to block layer statistics file format. +What: /sys/block/zram/writeback_limit_enable +Date: November 2018 +Contact: Minchan Kim +Description: + The writeback_limit_enable file is read-write and specifies + eanbe of writeback_limit feature. "1" means eable the feature. + No limit "0" is the initial state. + What: /sys/block/zram/writeback_limit Date: November 2018 Contact: Minchan Kim Description: The writeback_limit file is read-write and specifies the maximum amount of writeback ZRAM can do. The limit could be changed - in run time and "0" means disable the limit. - No limit is the initial state. + in run time. diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 1072a267fc10..6e5c2bb222c3 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -156,22 +156,23 @@ Per-device statistics are exported as various nodes under /sys/block/zram/ A brief description of exported device attributes. For more details please read Documentation/ABI/testing/sysfs-block-zram. -Name access description ----- ------ ----------- -disksize RW show and set the device's disk size -initstate RO shows the initialization state of the device -reset WO trigger device reset -mem_used_max WO reset the `mem_used_max' counter (see later) -mem_limit WO specifies the maximum amount of memory ZRAM can use - to store the compressed data -writeback_limit WO specifies the maximum amount of write IO zram can - write out to backing device as 4KB unit -max_comp_streams RW the number of possible concurrent compress operations -comp_algorithm RW show and change the compression algorithm -compact WO trigger memory compaction -debug_stat RO this file is used for zram debugging purposes -backing_dev RW set up backend storage for zram to write out -idle WO mark allocated slot as idle +Name access description +---- ------ ----------- +disksize RW show and set the device's disk size +initstate RO shows the initialization state of the device +reset WO trigger device reset +mem_used_max WO reset the `mem_used_max' counter (see later) +mem_limit WO specifies the maximum amount of memory ZRAM can use + to store the compressed data +writeback_limit WO specifies the maximum amount of write IO zram can + write out to backing device as 4KB unit +writeback_limit_enable RW show and set writeback_limit feature +max_comp_streams RW the number of possible concurrent compress operations +comp_algorithm RW show and change the compression algorithm +compact WO trigger memory compaction +debug_stat RO this file is used for zram debugging purposes +backing_dev RW set up backend storage for zram to write out +idle WO mark allocated slot as idle User space is advised to use the following files to read the device statistics. @@ -280,32 +281,51 @@ With the command, zram writeback idle pages from memory to the storage. If there are lots of write IO with flash device, potentially, it has flash wearout problem so that admin needs to design write limitation to guarantee storage health for entire product life. -To overcome the concern, zram supports "writeback_limit". -The "writeback_limit"'s default value is 0 so that it doesn't limit -any writeback. If admin want to measure writeback count in a certain -period, he could know it via /sys/block/zram0/bd_stat's 3rd column. + +To overcome the concern, zram supports "writeback_limit" feature. +The "writeback_limit_enable"'s default value is 0 so that it doesn't limit +any writeback. IOW, if admin want to apply writeback budget, he should +enable writeback_limit_enable via + + $ echo 1 > /sys/block/zramX/writeback_limit_enable + +Once writeback_limit_enable is set, zram doesn't allow any writeback +until admin set the budget via /sys/block/zramX/writeback_limit. + +(If admin doesn't enable writeback_limit_enable, writeback_limit's value +assigned via /sys/block/zramX/writeback_limit is meaninless.) If admin want to limit writeback as per-day 400M, he could do it like below. - MB_SHIFT=20 - 4K_SHIFT=12 - echo $((400<>4K_SHIFT)) > \ - /sys/block/zram0/writeback_limit. + $ MB_SHIFT=20 + $ 4K_SHIFT=12 + $ echo $((400<>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit. + $ echo 1 > /sys/block/zram0/writeback_limit_enable -If admin want to allow further write again, he could do it like below +If admin want to allow further write again once the bugdet is exausted, +he could do it like below - echo 0 > /sys/block/zram0/writeback_limit + $ echo $((400<>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit If admin want to see remaining writeback budget since he set, - cat /sys/block/zram0/writeback_limit + $ cat /sys/block/zramX/writeback_limit + +If admin want to disable writeback limit, he could do + + $ echo 0 > /sys/block/zramX/writeback_limit_enable The writeback_limit count will reset whenever you reset zram(e.g., system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of writeback happened until you reset the zram to allocate extra writeback budget in next setting is user's job. +If admin want to measure writeback count in a certain period, he could +know it via /sys/block/zram0/bd_stat's 3rd column. + = memory tracking With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index ff0a6af97580..e08422744d6b 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -316,11 +316,9 @@ static ssize_t idle_store(struct device *dev, * See the comment in writeback_store. */ zram_slot_lock(zram, index); - if (!zram_allocated(zram, index) || - zram_test_flag(zram, index, ZRAM_UNDER_WB)) - goto next; - zram_set_flag(zram, index, ZRAM_IDLE); -next: + if (zram_allocated(zram, index) && + !zram_test_flag(zram, index, ZRAM_UNDER_WB)) + zram_set_flag(zram, index, ZRAM_IDLE); zram_slot_unlock(zram, index); } @@ -330,6 +328,41 @@ static ssize_t idle_store(struct device *dev, } #ifdef CONFIG_ZRAM_WRITEBACK +static ssize_t writeback_limit_enable_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + u64 val; + ssize_t ret = -EINVAL; + + if (kstrtoull(buf, 10, &val)) + return ret; + + down_read(&zram->init_lock); + spin_lock(&zram->wb_limit_lock); + zram->wb_limit_enable = val; + spin_unlock(&zram->wb_limit_lock); + up_read(&zram->init_lock); + ret = len; + + return ret; +} + +static ssize_t writeback_limit_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + bool val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + spin_lock(&zram->wb_limit_lock); + val = zram->wb_limit_enable; + spin_unlock(&zram->wb_limit_lock); + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%d\n", val); +} + static ssize_t writeback_limit_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -341,9 +374,9 @@ static ssize_t writeback_limit_store(struct device *dev, return ret; down_read(&zram->init_lock); - atomic64_set(&zram->stats.bd_wb_limit, val); - if (val == 0) - zram->stop_writeback = false; + spin_lock(&zram->wb_limit_lock); + zram->bd_wb_limit = val; + spin_unlock(&zram->wb_limit_lock); up_read(&zram->init_lock); ret = len; @@ -357,7 +390,9 @@ static ssize_t writeback_limit_show(struct device *dev, struct zram *zram = dev_to_zram(dev); down_read(&zram->init_lock); - val = atomic64_read(&zram->stats.bd_wb_limit); + spin_lock(&zram->wb_limit_lock); + val = zram->bd_wb_limit; + spin_unlock(&zram->wb_limit_lock); up_read(&zram->init_lock); return scnprintf(buf, PAGE_SIZE, "%llu\n", val); @@ -588,8 +623,8 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, return 1; } -#define HUGE_WRITEBACK 0x1 -#define IDLE_WRITEBACK 0x2 +#define HUGE_WRITEBACK 1 +#define IDLE_WRITEBACK 2 static ssize_t writeback_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) @@ -602,7 +637,7 @@ static ssize_t writeback_store(struct device *dev, struct page *page; ssize_t ret, sz; char mode_buf[8]; - unsigned long mode = -1UL; + int mode = -1; unsigned long blk_idx = 0; sz = strscpy(mode_buf, buf, sizeof(mode_buf)); @@ -618,7 +653,7 @@ static ssize_t writeback_store(struct device *dev, else if (!strcmp(mode_buf, "huge")) mode = HUGE_WRITEBACK; - if (mode == -1UL) + if (mode == -1) return -EINVAL; down_read(&zram->init_lock); @@ -645,10 +680,13 @@ static ssize_t writeback_store(struct device *dev, bvec.bv_len = PAGE_SIZE; bvec.bv_offset = 0; - if (zram->stop_writeback) { + spin_lock(&zram->wb_limit_lock); + if (zram->wb_limit_enable && !zram->bd_wb_limit) { + spin_unlock(&zram->wb_limit_lock); ret = -EIO; break; } + spin_unlock(&zram->wb_limit_lock); if (!blk_idx) { blk_idx = alloc_block_bdev(zram); @@ -667,10 +705,11 @@ static ssize_t writeback_store(struct device *dev, zram_test_flag(zram, index, ZRAM_UNDER_WB)) goto next; - if ((mode & IDLE_WRITEBACK && - !zram_test_flag(zram, index, ZRAM_IDLE)) && - (mode & HUGE_WRITEBACK && - !zram_test_flag(zram, index, ZRAM_HUGE))) + if (mode == IDLE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_IDLE)) + goto next; + if (mode == HUGE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_HUGE)) goto next; /* * Clearing ZRAM_UNDER_WB is duty of caller. @@ -732,11 +771,10 @@ static ssize_t writeback_store(struct device *dev, zram_set_element(zram, index, blk_idx); blk_idx = 0; atomic64_inc(&zram->stats.pages_stored); - if (atomic64_add_unless(&zram->stats.bd_wb_limit, - -1 << (PAGE_SHIFT - 12), 0)) { - if (atomic64_read(&zram->stats.bd_wb_limit) == 0) - zram->stop_writeback = true; - } + spin_lock(&zram->wb_limit_lock); + if (zram->wb_limit_enable && zram->bd_wb_limit > 0) + zram->bd_wb_limit -= 1UL << (PAGE_SHIFT - 12); + spin_unlock(&zram->wb_limit_lock); next: zram_slot_unlock(zram, index); } @@ -1812,6 +1850,7 @@ static DEVICE_ATTR_RW(comp_algorithm); static DEVICE_ATTR_RW(backing_dev); static DEVICE_ATTR_WO(writeback); static DEVICE_ATTR_RW(writeback_limit); +static DEVICE_ATTR_RW(writeback_limit_enable); #endif static struct attribute *zram_disk_attrs[] = { @@ -1828,6 +1867,7 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_backing_dev.attr, &dev_attr_writeback.attr, &dev_attr_writeback_limit.attr, + &dev_attr_writeback_limit_enable.attr, #endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, @@ -1867,7 +1907,9 @@ static int zram_add(void) device_id = ret; init_rwsem(&zram->init_lock); - +#ifdef CONFIG_ZRAM_WRITEBACK + spin_lock_init(&zram->wb_limit_lock); +#endif queue = blk_alloc_queue(GFP_KERNEL); if (!queue) { pr_err("Error allocating disk queue for device %d\n", diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 4bd3afd15e83..f2fd46daa760 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -86,7 +86,6 @@ struct zram_stats { atomic64_t bd_count; /* no. of pages in backing device */ atomic64_t bd_reads; /* no. of reads from backing device */ atomic64_t bd_writes; /* no. of writes from backing device */ - atomic64_t bd_wb_limit; /* writeback limit of backing device */ #endif }; @@ -114,8 +113,10 @@ struct zram { */ bool claim; /* Protected by bdev->bd_mutex */ struct file *backing_dev; - bool stop_writeback; #ifdef CONFIG_ZRAM_WRITEBACK + spinlock_t wb_limit_lock; + bool wb_limit_enable; + u64 bd_wb_limit; struct block_device *bdev; unsigned int old_block_size; unsigned long *bitmap; From 028c13f7caf2c3c22932f44ef37a8cad43230517 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Thu, 1 Nov 2018 00:24:46 +0000 Subject: [PATCH 015/116] tty/ldsem: Wake up readers after timed out down_write() commit 231f8fd0cca078bd4396dd7e380db813ac5736e2 upstream. ldsem_down_read() will sleep if there is pending writer in the queue. If the writer times out, readers in the queue should be woken up, otherwise they may miss a chance to acquire the semaphore until the last active reader will do ldsem_up_read(). There was a couple of reports where there was one active reader and other readers soft locked up: Showing all locks held in the system: 2 locks held by khungtaskd/17: #0: (rcu_read_lock){......}, at: watchdog+0x124/0x6d1 #1: (tasklist_lock){.+.+..}, at: debug_show_all_locks+0x72/0x2d3 2 locks held by askfirst/123: #0: (&tty->ldisc_sem){.+.+.+}, at: ldsem_down_read+0x46/0x58 #1: (&ldata->atomic_read_lock){+.+...}, at: n_tty_read+0x115/0xbe4 Prevent readers wait for active readers to release ldisc semaphore. Link: lkml.kernel.org/r/20171121132855.ajdv4k6swzhvktl6@wfg-t540p.sh.intel.com Link: lkml.kernel.org/r/20180907045041.GF1110@shao2-debian Cc: Jiri Slaby Cc: Peter Zijlstra Cc: stable@vger.kernel.org Reported-by: kernel test robot Signed-off-by: Dmitry Safonov Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_ldsem.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c index 0c98d88f795a..b989ca26fc78 100644 --- a/drivers/tty/tty_ldsem.c +++ b/drivers/tty/tty_ldsem.c @@ -293,6 +293,16 @@ down_write_failed(struct ld_semaphore *sem, long count, long timeout) if (!locked) atomic_long_add_return(-LDSEM_WAIT_BIAS, &sem->count); list_del(&waiter.list); + + /* + * In case of timeout, wake up every reader who gave the right of way + * to writer. Prevent separation readers into two groups: + * one that helds semaphore and another that sleeps. + * (in case of no contention with a writer) + */ + if (!locked && list_empty(&sem->write_wait)) + __ldsem_wake_readers(sem); + raw_spin_unlock_irq(&sem->wait_lock); __set_current_state(TASK_RUNNING); From e6a4caa0b4dd966dc63d15390423cac1cc004c20 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Thu, 1 Nov 2018 00:24:47 +0000 Subject: [PATCH 016/116] tty: Hold tty_ldisc_lock() during tty_reopen() commit 83d817f41070c48bc3eb7ec18e43000a548fca5c upstream. tty_ldisc_reinit() doesn't race with neither tty_ldisc_hangup() nor set_ldisc() nor tty_ldisc_release() as they use tty lock. But it races with anyone who expects line discipline to be the same after hoding read semaphore in tty_ldisc_ref(). We've seen the following crash on v4.9.108 stable: BUG: unable to handle kernel paging request at 0000000000002260 IP: [..] n_tty_receive_buf_common+0x5f/0x86d Workqueue: events_unbound flush_to_ldisc Call Trace: [..] n_tty_receive_buf2 [..] tty_ldisc_receive_buf [..] flush_to_ldisc [..] process_one_work [..] worker_thread [..] kthread [..] ret_from_fork tty_ldisc_reinit() should be called with ldisc_sem hold for writing, which will protect any reader against line discipline changes. Cc: Jiri Slaby Cc: stable@vger.kernel.org # b027e2298bd5 ("tty: fix data race between tty_init_dev and flush of buf") Reviewed-by: Jiri Slaby Reported-by: syzbot+3aa9784721dfb90e984d@syzkaller.appspotmail.com Tested-by: Mark Rutland Tested-by: Tetsuo Handa Signed-off-by: Dmitry Safonov Tested-by: Tycho Andersen Signed-off-by: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index d6f42b528277..4f70b6b13073 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1267,15 +1267,20 @@ static int tty_reopen(struct tty_struct *tty) if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN)) return -EBUSY; - tty->count++; + retval = tty_ldisc_lock(tty, 5 * HZ); + if (retval) + return retval; + tty->count++; if (tty->ldisc) - return 0; + goto out_unlock; retval = tty_ldisc_reinit(tty, tty->termios.c_line); if (retval) tty->count--; +out_unlock: + tty_ldisc_unlock(tty); return retval; } From a42c97862837efa6f7d972bb1a81873c8cd5cc71 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Thu, 1 Nov 2018 00:24:49 +0000 Subject: [PATCH 017/116] tty: Simplify tty->count math in tty_reopen() commit cf62a1a13749db0d32b5cdd800ea91a4087319de upstream. As notted by Jiri, tty_ldisc_reinit() shouldn't rely on tty counter. Simplify math by increasing the counter after reinit success. Cc: Jiri Slaby Link: lkml.kernel.org/r/<20180829022353.23568-2-dima@arista.com> Suggested-by: Jiri Slaby Reviewed-by: Jiri Slaby Tested-by: Mark Rutland Signed-off-by: Dmitry Safonov Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 4f70b6b13073..c92b112a28d6 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1271,16 +1271,13 @@ static int tty_reopen(struct tty_struct *tty) if (retval) return retval; - tty->count++; - if (tty->ldisc) - goto out_unlock; - - retval = tty_ldisc_reinit(tty, tty->termios.c_line); - if (retval) - tty->count--; - -out_unlock: + if (!tty->ldisc) + retval = tty_ldisc_reinit(tty, tty->termios.c_line); tty_ldisc_unlock(tty); + + if (retval == 0) + tty->count++; + return retval; } From a13520e0d5f5cf2ad805a68b97e391194ada2047 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Wed, 9 Jan 2019 01:17:40 +0000 Subject: [PATCH 018/116] tty: Don't hold ldisc lock in tty_reopen() if ldisc present commit d3736d82e8169768218ee0ef68718875918091a0 upstream. Try to get reference for ldisc during tty_reopen(). If ldisc present, we don't need to do tty_ldisc_reinit() and lock the write side for line discipline semaphore. Effectively, it optimizes fast-path for tty_reopen(), but more importantly it won't interrupt ongoing IO on the tty as no ldisc change is needed. Fixes user-visible issue when tty_reopen() interrupted login process for user with a long password, observed and reported by Lukas. Fixes: c96cf923a98d ("tty: Don't block on IO when ldisc change is pending") Fixes: 83d817f41070 ("tty: Hold tty_ldisc_lock() during tty_reopen()") Cc: Jiri Slaby Reported-by: Lukas F. Hartmann Tested-by: Lukas F. Hartmann Cc: stable Signed-off-by: Dmitry Safonov Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index c92b112a28d6..052ec16a4e84 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1255,7 +1255,8 @@ static void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct * static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; - int retval; + struct tty_ldisc *ld; + int retval = 0; if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) @@ -1267,13 +1268,18 @@ static int tty_reopen(struct tty_struct *tty) if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN)) return -EBUSY; - retval = tty_ldisc_lock(tty, 5 * HZ); - if (retval) - return retval; + ld = tty_ldisc_ref_wait(tty); + if (ld) { + tty_ldisc_deref(ld); + } else { + retval = tty_ldisc_lock(tty, 5 * HZ); + if (retval) + return retval; - if (!tty->ldisc) - retval = tty_ldisc_reinit(tty, tty->termios.c_line); - tty_ldisc_unlock(tty); + if (!tty->ldisc) + retval = tty_ldisc_reinit(tty, tty->termios.c_line); + tty_ldisc_unlock(tty); + } if (retval == 0) tty->count++; From 8db82a6f2b76d42ec2615f8def6e797e064e7822 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 4 Jan 2019 15:55:26 +0100 Subject: [PATCH 019/116] can: gw: ensure DLC boundaries after CAN frame modification commit 0aaa81377c5a01f686bcdb8c7a6929a7bf330c68 upstream. Muyu Yu provided a POC where user root with CAP_NET_ADMIN can create a CAN frame modification rule that makes the data length code a higher value than the available CAN frame data size. In combination with a configured checksum calculation where the result is stored relatively to the end of the data (e.g. cgw_csum_xor_rel) the tail of the skb (e.g. frag_list pointer in skb_shared_info) can be rewritten which finally can cause a system crash. Michael Kubecek suggested to drop frames that have a DLC exceeding the available space after the modification process and provided a patch that can handle CAN FD frames too. Within this patch we also limit the length for the checksum calculations to the maximum of Classic CAN data length (8). CAN frames that are dropped by these additional checks are counted with the CGW_DELETED counter which indicates misconfigurations in can-gw rules. This fixes CVE-2019-3701. Reported-by: Muyu Yu Reported-by: Marcus Meissner Suggested-by: Michal Kubecek Tested-by: Muyu Yu Tested-by: Oliver Hartkopp Signed-off-by: Oliver Hartkopp Cc: linux-stable # >= v3.2 Signed-off-by: Marc Kleine-Budde Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/can/gw.c | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) diff --git a/net/can/gw.c b/net/can/gw.c index faa3da88a127..53859346dc9a 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -416,13 +416,29 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); - /* check for checksum updates when the CAN frame has been modified */ + /* Has the CAN frame been modified? */ if (modidx) { - if (gwj->mod.csumfunc.crc8) - (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + /* get available space for the processed CAN frame type */ + int max_len = nskb->len - offsetof(struct can_frame, data); + + /* dlc may have changed, make sure it fits to the CAN frame */ + if (cf->can_dlc > max_len) + goto out_delete; + + /* check for checksum updates in classic CAN length only */ + if (gwj->mod.csumfunc.crc8) { + if (cf->can_dlc > 8) + goto out_delete; + + (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + } + + if (gwj->mod.csumfunc.xor) { + if (cf->can_dlc > 8) + goto out_delete; - if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + } } /* clear the skb timestamp if not configured the other way */ @@ -434,6 +450,14 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) gwj->dropped_frames++; else gwj->handled_frames++; + + return; + + out_delete: + /* delete frame due to misconfiguration */ + gwj->deleted_frames++; + kfree_skb(nskb); + return; } static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj) From c5cbe95a4ba87c06cb25ff2324919a1304178439 Mon Sep 17 00:00:00 2001 From: Shawn Bohrer Date: Fri, 28 Dec 2018 01:24:42 +0100 Subject: [PATCH 020/116] netfilter: nf_conncount: replace CONNCOUNT_LOCK_SLOTS with CONNCOUNT_SLOTS commit c78e7818f16f687389174c4569243abbec8dc68f upstream. Most of the time these were the same value anyway, but when CONFIG_LOCKDEP was enabled we would use a smaller number of locks to reduce overhead. Unfortunately having two values is confusing and not worth the complexity. This fixes a bug where tree_gc_worker() would only GC up to CONNCOUNT_LOCK_SLOTS trees which meant when CONFIG_LOCKDEP was enabled not all trees would be GCed by tree_gc_worker(). Fixes: 5c789e131cbb9 ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search") Signed-off-by: Florian Westphal Signed-off-by: Shawn Bohrer Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conncount.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 9cd180bda092..3271a4e00500 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -33,12 +33,6 @@ #define CONNCOUNT_SLOTS 256U -#ifdef CONFIG_LOCKDEP -#define CONNCOUNT_LOCK_SLOTS 8U -#else -#define CONNCOUNT_LOCK_SLOTS 256U -#endif - #define CONNCOUNT_GC_MAX_NODES 8 #define MAX_KEYLEN 5 @@ -60,7 +54,7 @@ struct nf_conncount_rb { struct rcu_head rcu_head; }; -static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp; +static spinlock_t nf_conncount_locks[CONNCOUNT_SLOTS] __cacheline_aligned_in_smp; struct nf_conncount_data { unsigned int keylen; @@ -353,7 +347,7 @@ insert_tree(struct net *net, unsigned int count = 0, gc_count = 0; bool node_found = false; - spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); + spin_lock_bh(&nf_conncount_locks[hash]); parent = NULL; rbnode = &(root->rb_node); @@ -430,7 +424,7 @@ insert_tree(struct net *net, rb_link_node_rcu(&rbconn->node, parent, rbnode); rb_insert_color(&rbconn->node, root); out_unlock: - spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); + spin_unlock_bh(&nf_conncount_locks[hash]); return count; } @@ -499,7 +493,7 @@ static void tree_gc_worker(struct work_struct *work) struct rb_node *node; unsigned int tree, next_tree, gc_count = 0; - tree = data->gc_tree % CONNCOUNT_LOCK_SLOTS; + tree = data->gc_tree % CONNCOUNT_SLOTS; root = &data->root[tree]; rcu_read_lock(); @@ -621,10 +615,7 @@ static int __init nf_conncount_modinit(void) { int i; - BUILD_BUG_ON(CONNCOUNT_LOCK_SLOTS > CONNCOUNT_SLOTS); - BUILD_BUG_ON((CONNCOUNT_SLOTS % CONNCOUNT_LOCK_SLOTS) != 0); - - for (i = 0; i < CONNCOUNT_LOCK_SLOTS; ++i) + for (i = 0; i < CONNCOUNT_SLOTS; ++i) spin_lock_init(&nf_conncount_locks[i]); conncount_conn_cachep = kmem_cache_create("nf_conncount_tuple", From ef68fdb5179c9ac7efe4a8a18e9a6cf2034e475b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 Dec 2018 01:24:43 +0100 Subject: [PATCH 021/116] netfilter: nf_conncount: don't skip eviction when age is negative commit 4cd273bb91b3001f623f516ec726c49754571b1a upstream. age is signed integer, so result can be negative when the timestamps have a large delta. In this case we want to discard the entry. Instead of using age >= 2 || age < 0, just make it unsigned. Fixes: b36e4523d4d56 ("netfilter: nf_conncount: fix garbage collection confirm race") Reviewed-by: Shawn Bohrer Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conncount.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 3271a4e00500..8bb4ed85c262 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -155,7 +155,7 @@ find_or_evict(struct net *net, struct nf_conncount_list *list, const struct nf_conntrack_tuple_hash *found; unsigned long a, b; int cpu = raw_smp_processor_id(); - __s32 age; + u32 age; found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); if (found) From d6b3ff0222fba188a06ece5a3dff005690bdc076 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 Dec 2018 01:24:44 +0100 Subject: [PATCH 022/116] netfilter: nf_conncount: split gc in two phases commit f7fcc98dfc2d136722007fec0debbed761679b94 upstream. The lockless workqueue garbage collector can race with packet path garbage collector to delete list nodes, as it calls tree_nodes_free() with the addresses of nodes that might have been free'd already from another cpu. To fix this, split gc into two phases. One phase to perform gc on the connections: From a locking perspective, this is the same as count_tree(): we hold rcu lock, but we do not change the tree, we only change the nodes' contents. The second phase acquires the tree lock and reaps empty nodes. This avoids a race condition of the garbage collection vs. packet path: If a node has been free'd already, the second phase won't find it anymore. This second phase is, from locking perspective, same as insert_tree(). The former only modifies nodes (list content, count), latter modifies the tree itself (rb_erase or rb_insert). Fixes: 5c789e131cbb9 ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search") Reviewed-by: Shawn Bohrer Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conncount.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 8bb4ed85c262..753132e4afa8 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -500,16 +500,32 @@ static void tree_gc_worker(struct work_struct *work) for (node = rb_first(root); node != NULL; node = rb_next(node)) { rbconn = rb_entry(node, struct nf_conncount_rb, node); if (nf_conncount_gc_list(data->net, &rbconn->list)) - gc_nodes[gc_count++] = rbconn; + gc_count++; } rcu_read_unlock(); spin_lock_bh(&nf_conncount_locks[tree]); + if (gc_count < ARRAY_SIZE(gc_nodes)) + goto next; /* do not bother */ - if (gc_count) { - tree_nodes_free(root, gc_nodes, gc_count); + gc_count = 0; + node = rb_first(root); + while (node != NULL) { + rbconn = rb_entry(node, struct nf_conncount_rb, node); + node = rb_next(node); + + if (rbconn->list.count > 0) + continue; + + gc_nodes[gc_count++] = rbconn; + if (gc_count >= ARRAY_SIZE(gc_nodes)) { + tree_nodes_free(root, gc_nodes, gc_count); + gc_count = 0; + } } + tree_nodes_free(root, gc_nodes, gc_count); +next: clear_bit(tree, data->pending_trees); next_tree = (tree + 1) % CONNCOUNT_SLOTS; From 13c639424bc2eeacd1348bfbe17efd5fa275b119 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 Dec 2018 01:24:45 +0100 Subject: [PATCH 023/116] netfilter: nf_conncount: restart search when nodes have been erased commit e8cfb372b38a1b8979aa7f7631fb5e7b11c3793c upstream. Shawn Bohrer reported a following crash: |RIP: 0010:rb_erase+0xae/0x360 [..] Call Trace: nf_conncount_destroy+0x59/0xc0 [nf_conncount] cleanup_match+0x45/0x70 [ip_tables] ... Shawn tracked this down to bogus 'parent' pointer: Problem is that when we insert a new node, then there is a chance that the 'parent' that we found was also passed to tree_nodes_free() (because that node was empty) for erase+free. Instead of trying to be clever and detect when this happens, restart the search if we have evicted one or more nodes. To prevent frequent restarts, do not perform gc on the second round. Also, unconditionally schedule the gc worker. The condition gc_count > ARRAY_SIZE(gc_nodes)) cannot be true unless tree grows very large, as the height of the tree will be low even with hundreds of nodes present. Fixes: 5c789e131cbb9 ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search") Reported-by: Shawn Bohrer Reviewed-by: Shawn Bohrer Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conncount.c | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 753132e4afa8..0a83c694a8f1 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -346,9 +346,10 @@ insert_tree(struct net *net, struct nf_conncount_tuple *conn; unsigned int count = 0, gc_count = 0; bool node_found = false; + bool do_gc = true; spin_lock_bh(&nf_conncount_locks[hash]); - +restart: parent = NULL; rbnode = &(root->rb_node); while (*rbnode) { @@ -381,21 +382,16 @@ insert_tree(struct net *net, if (gc_count >= ARRAY_SIZE(gc_nodes)) continue; - if (nf_conncount_gc_list(net, &rbconn->list)) + if (do_gc && nf_conncount_gc_list(net, &rbconn->list)) gc_nodes[gc_count++] = rbconn; } if (gc_count) { tree_nodes_free(root, gc_nodes, gc_count); - /* tree_node_free before new allocation permits - * allocator to re-use newly free'd object. - * - * This is a rare event; in most cases we will find - * existing node to re-use. (or gc_count is 0). - */ - - if (gc_count >= ARRAY_SIZE(gc_nodes)) - schedule_gc_worker(data, hash); + schedule_gc_worker(data, hash); + gc_count = 0; + do_gc = false; + goto restart; } if (node_found) From bdc6c893ba378a1b391ddbb4acea24047b6373d0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 Dec 2018 01:24:46 +0100 Subject: [PATCH 024/116] netfilter: nf_conncount: merge lookup and add functions commit df4a902509766897f7371fdfa4c3bf8bc321b55d upstream. 'lookup' is always followed by 'add'. Merge both and make the list-walk part of nf_conncount_add(). This also avoids one unneeded unlock/re-lock pair. Extra care needs to be taken in count_tree, as we only hold rcu read lock, i.e. we can only insert to an existing tree node after acquiring its lock and making sure it has a nonzero count. As a zero count should be rare, just fall back to insert_tree() (which acquires tree lock). This issue and its solution were pointed out by Shawn Bohrer during patch review. Reviewed-by: Shawn Bohrer Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_conntrack_count.h | 18 +-- net/netfilter/nf_conncount.c | 146 ++++++++++----------- net/netfilter/nft_connlimit.c | 14 +- 3 files changed, 72 insertions(+), 106 deletions(-) diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index 4b2b2baf8ab4..aa66775c15f4 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -5,12 +5,6 @@ struct nf_conncount_data; -enum nf_conncount_list_add { - NF_CONNCOUNT_ADDED, /* list add was ok */ - NF_CONNCOUNT_ERR, /* -ENOMEM, must drop skb */ - NF_CONNCOUNT_SKIP, /* list is already reclaimed by gc */ -}; - struct nf_conncount_list { spinlock_t list_lock; struct list_head head; /* connections with the same filtering key */ @@ -29,18 +23,12 @@ unsigned int nf_conncount_count(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone); -void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone, - bool *addit); +int nf_conncount_add(struct net *net, struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone); void nf_conncount_list_init(struct nf_conncount_list *list); -enum nf_conncount_list_add -nf_conncount_add(struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone); - bool nf_conncount_gc_list(struct net *net, struct nf_conncount_list *list); diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 0a83c694a8f1..ce7f7d1212a6 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -83,38 +83,6 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -enum nf_conncount_list_add -nf_conncount_add(struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) -{ - struct nf_conncount_tuple *conn; - - if (WARN_ON_ONCE(list->count > INT_MAX)) - return NF_CONNCOUNT_ERR; - - conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); - if (conn == NULL) - return NF_CONNCOUNT_ERR; - - conn->tuple = *tuple; - conn->zone = *zone; - conn->cpu = raw_smp_processor_id(); - conn->jiffies32 = (u32)jiffies; - conn->dead = false; - spin_lock_bh(&list->list_lock); - if (list->dead == true) { - kmem_cache_free(conncount_conn_cachep, conn); - spin_unlock_bh(&list->list_lock); - return NF_CONNCOUNT_SKIP; - } - list_add_tail(&conn->node, &list->head); - list->count++; - spin_unlock_bh(&list->list_lock); - return NF_CONNCOUNT_ADDED; -} -EXPORT_SYMBOL_GPL(nf_conncount_add); - static void __conn_free(struct rcu_head *h) { struct nf_conncount_tuple *conn; @@ -177,11 +145,10 @@ find_or_evict(struct net *net, struct nf_conncount_list *list, return ERR_PTR(-EAGAIN); } -void nf_conncount_lookup(struct net *net, - struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone, - bool *addit) +static int __nf_conncount_add(struct net *net, + struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone) { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn, *conn_n; @@ -189,9 +156,6 @@ void nf_conncount_lookup(struct net *net, unsigned int collect = 0; bool free_entry = false; - /* best effort only */ - *addit = tuple ? true : false; - /* check the saved connections */ list_for_each_entry_safe(conn, conn_n, &list->head, node) { if (collect > CONNCOUNT_GC_MAX_NODES) @@ -201,21 +165,19 @@ void nf_conncount_lookup(struct net *net, if (IS_ERR(found)) { /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { - if (!tuple) - continue; - if (nf_ct_tuple_equal(&conn->tuple, tuple) && nf_ct_zone_id(&conn->zone, conn->zone.dir) == nf_ct_zone_id(zone, zone->dir)) - *addit = false; - } else if (PTR_ERR(found) == -ENOENT) + return 0; /* already exists */ + } else { collect++; + } continue; } found_ct = nf_ct_tuplehash_to_ctrack(found); - if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) && + if (nf_ct_tuple_equal(&conn->tuple, tuple) && nf_ct_zone_equal(found_ct, zone, zone->dir)) { /* * We should not see tuples twice unless someone hooks @@ -223,7 +185,8 @@ void nf_conncount_lookup(struct net *net, * * Attempt to avoid a re-add in this case. */ - *addit = false; + nf_ct_put(found_ct); + return 0; } else if (already_closed(found_ct)) { /* * we do not care about connections which are @@ -237,8 +200,38 @@ void nf_conncount_lookup(struct net *net, nf_ct_put(found_ct); } + + if (WARN_ON_ONCE(list->count > INT_MAX)) + return -EOVERFLOW; + + conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); + if (conn == NULL) + return -ENOMEM; + + conn->tuple = *tuple; + conn->zone = *zone; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; + list_add_tail(&conn->node, &list->head); + list->count++; + return 0; } -EXPORT_SYMBOL_GPL(nf_conncount_lookup); + +int nf_conncount_add(struct net *net, + struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone) +{ + int ret; + + /* check the saved connections */ + spin_lock_bh(&list->list_lock); + ret = __nf_conncount_add(net, list, tuple, zone); + spin_unlock_bh(&list->list_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(nf_conncount_add); void nf_conncount_list_init(struct nf_conncount_list *list) { @@ -339,13 +332,11 @@ insert_tree(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { - enum nf_conncount_list_add ret; struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES]; struct rb_node **rbnode, *parent; struct nf_conncount_rb *rbconn; struct nf_conncount_tuple *conn; unsigned int count = 0, gc_count = 0; - bool node_found = false; bool do_gc = true; spin_lock_bh(&nf_conncount_locks[hash]); @@ -363,20 +354,15 @@ insert_tree(struct net *net, } else if (diff > 0) { rbnode = &((*rbnode)->rb_right); } else { - /* unlikely: other cpu added node already */ - node_found = true; - ret = nf_conncount_add(&rbconn->list, tuple, zone); - if (ret == NF_CONNCOUNT_ERR) { + int ret; + + ret = nf_conncount_add(net, &rbconn->list, tuple, zone); + if (ret) count = 0; /* hotdrop */ - } else if (ret == NF_CONNCOUNT_ADDED) { + else count = rbconn->list.count; - } else { - /* NF_CONNCOUNT_SKIP, rbconn is already - * reclaimed by gc, insert a new tree node - */ - node_found = false; - } - break; + tree_nodes_free(root, gc_nodes, gc_count); + goto out_unlock; } if (gc_count >= ARRAY_SIZE(gc_nodes)) @@ -394,9 +380,6 @@ insert_tree(struct net *net, goto restart; } - if (node_found) - goto out_unlock; - /* expected case: match, insert new node */ rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC); if (rbconn == NULL) @@ -431,7 +414,6 @@ count_tree(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { - enum nf_conncount_list_add ret; struct rb_root *root; struct rb_node *parent; struct nf_conncount_rb *rbconn; @@ -444,7 +426,6 @@ count_tree(struct net *net, parent = rcu_dereference_raw(root->rb_node); while (parent) { int diff; - bool addit; rbconn = rb_entry(parent, struct nf_conncount_rb, node); @@ -454,24 +435,29 @@ count_tree(struct net *net, } else if (diff > 0) { parent = rcu_dereference_raw(parent->rb_right); } else { - /* same source network -> be counted! */ - nf_conncount_lookup(net, &rbconn->list, tuple, zone, - &addit); + int ret; - if (!addit) + if (!tuple) { + nf_conncount_gc_list(net, &rbconn->list); return rbconn->list.count; + } - ret = nf_conncount_add(&rbconn->list, tuple, zone); - if (ret == NF_CONNCOUNT_ERR) { - return 0; /* hotdrop */ - } else if (ret == NF_CONNCOUNT_ADDED) { - return rbconn->list.count; - } else { - /* NF_CONNCOUNT_SKIP, rbconn is already - * reclaimed by gc, insert a new tree node - */ + spin_lock_bh(&rbconn->list.list_lock); + /* Node might be about to be free'd. + * We need to defer to insert_tree() in this case. + */ + if (rbconn->list.count == 0) { + spin_unlock_bh(&rbconn->list.list_lock); break; } + + /* same source network -> be counted! */ + ret = __nf_conncount_add(net, &rbconn->list, tuple, zone); + spin_unlock_bh(&rbconn->list.list_lock); + if (ret) + return 0; /* hotdrop */ + else + return rbconn->list.count; } } diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index b90d96ba4a12..af1497ab9464 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -30,7 +30,6 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, enum ip_conntrack_info ctinfo; const struct nf_conn *ct; unsigned int count; - bool addit; tuple_ptr = &tuple; @@ -44,19 +43,12 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, return; } - nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone, - &addit); - count = priv->list.count; - - if (!addit) - goto out; - - if (nf_conncount_add(&priv->list, tuple_ptr, zone) == NF_CONNCOUNT_ERR) { + if (nf_conncount_add(nft_net(pkt), &priv->list, tuple_ptr, zone)) { regs->verdict.code = NF_DROP; return; } - count++; -out: + + count = priv->list.count; if ((count > priv->limit) ^ priv->invert) { regs->verdict.code = NFT_BREAK; From aea1d19594e68d3beaf5cc11e4b5f5b9059abdb7 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 28 Dec 2018 01:24:47 +0100 Subject: [PATCH 025/116] netfilter: nf_conncount: move all list iterations under spinlock commit 2f971a8f425545da52ca0e6bee81f5b1ea0ccc5f upstream. Two CPUs may race to remove a connection from the list, the existing conn->dead will result in a use-after-free. Use the per-list spinlock to protect list iterations. As all accesses to the list now happen while holding the per-list lock, we no longer need to delay free operations with rcu. Joint work with Florian. Fixes: 5c789e131cbb9 ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search") Reviewed-by: Shawn Bohrer Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conncount.c | 46 ++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 26 deletions(-) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index ce7f7d1212a6..d0fd195b19a8 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -43,8 +43,6 @@ struct nf_conncount_tuple { struct nf_conntrack_zone zone; int cpu; u32 jiffies32; - bool dead; - struct rcu_head rcu_head; }; struct nf_conncount_rb { @@ -83,36 +81,21 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -static void __conn_free(struct rcu_head *h) -{ - struct nf_conncount_tuple *conn; - - conn = container_of(h, struct nf_conncount_tuple, rcu_head); - kmem_cache_free(conncount_conn_cachep, conn); -} - static bool conn_free(struct nf_conncount_list *list, struct nf_conncount_tuple *conn) { bool free_entry = false; - spin_lock_bh(&list->list_lock); - - if (conn->dead) { - spin_unlock_bh(&list->list_lock); - return free_entry; - } + lockdep_assert_held(&list->list_lock); list->count--; - conn->dead = true; - list_del_rcu(&conn->node); + list_del(&conn->node); if (list->count == 0) { list->dead = true; free_entry = true; } - spin_unlock_bh(&list->list_lock); - call_rcu(&conn->rcu_head, __conn_free); + kmem_cache_free(conncount_conn_cachep, conn); return free_entry; } @@ -242,7 +225,7 @@ void nf_conncount_list_init(struct nf_conncount_list *list) } EXPORT_SYMBOL_GPL(nf_conncount_list_init); -/* Return true if the list is empty */ +/* Return true if the list is empty. Must be called with BH disabled. */ bool nf_conncount_gc_list(struct net *net, struct nf_conncount_list *list) { @@ -253,12 +236,18 @@ bool nf_conncount_gc_list(struct net *net, bool free_entry = false; bool ret = false; + /* don't bother if other cpu is already doing GC */ + if (!spin_trylock(&list->list_lock)) + return false; + list_for_each_entry_safe(conn, conn_n, &list->head, node) { found = find_or_evict(net, list, conn, &free_entry); if (IS_ERR(found)) { if (PTR_ERR(found) == -ENOENT) { - if (free_entry) + if (free_entry) { + spin_unlock(&list->list_lock); return true; + } collected++; } continue; @@ -271,23 +260,24 @@ bool nf_conncount_gc_list(struct net *net, * closed already -> ditch it */ nf_ct_put(found_ct); - if (conn_free(list, conn)) + if (conn_free(list, conn)) { + spin_unlock(&list->list_lock); return true; + } collected++; continue; } nf_ct_put(found_ct); if (collected > CONNCOUNT_GC_MAX_NODES) - return false; + break; } - spin_lock_bh(&list->list_lock); if (!list->count) { list->dead = true; ret = true; } - spin_unlock_bh(&list->list_lock); + spin_unlock(&list->list_lock); return ret; } @@ -478,6 +468,7 @@ static void tree_gc_worker(struct work_struct *work) tree = data->gc_tree % CONNCOUNT_SLOTS; root = &data->root[tree]; + local_bh_disable(); rcu_read_lock(); for (node = rb_first(root); node != NULL; node = rb_next(node)) { rbconn = rb_entry(node, struct nf_conncount_rb, node); @@ -485,6 +476,9 @@ static void tree_gc_worker(struct work_struct *work) gc_count++; } rcu_read_unlock(); + local_bh_enable(); + + cond_resched(); spin_lock_bh(&nf_conncount_locks[tree]); if (gc_count < ARRAY_SIZE(gc_nodes)) From b01b92417d09b298ec6c29b8b560abced1e2ff97 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 28 Dec 2018 01:24:48 +0100 Subject: [PATCH 026/116] netfilter: nf_conncount: speculative garbage collection on empty lists commit c80f10bc973af2ace6b1414724eeff61eaa71837 upstream. Instead of removing a empty list node that might be reintroduced soon thereafter, tentatively place the empty list node on the list passed to tree_nodes_free(), then re-check if the list is empty again before erasing it from the tree. [ Florian: rebase on top of pending nf_conncount fixes ] Fixes: 5c789e131cbb9 ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search") Reviewed-by: Shawn Bohrer Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- include/net/netfilter/nf_conntrack_count.h | 1 - net/netfilter/nf_conncount.c | 47 +++++++--------------- 2 files changed, 15 insertions(+), 33 deletions(-) diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index aa66775c15f4..f32fc8289473 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -9,7 +9,6 @@ struct nf_conncount_list { spinlock_t list_lock; struct list_head head; /* connections with the same filtering key */ unsigned int count; /* length of list */ - bool dead; }; struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index d0fd195b19a8..f0b05dfebc6e 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -81,27 +81,20 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -static bool conn_free(struct nf_conncount_list *list, +static void conn_free(struct nf_conncount_list *list, struct nf_conncount_tuple *conn) { - bool free_entry = false; - lockdep_assert_held(&list->list_lock); list->count--; list_del(&conn->node); - if (list->count == 0) { - list->dead = true; - free_entry = true; - } kmem_cache_free(conncount_conn_cachep, conn); - return free_entry; } static const struct nf_conntrack_tuple_hash * find_or_evict(struct net *net, struct nf_conncount_list *list, - struct nf_conncount_tuple *conn, bool *free_entry) + struct nf_conncount_tuple *conn) { const struct nf_conntrack_tuple_hash *found; unsigned long a, b; @@ -121,7 +114,7 @@ find_or_evict(struct net *net, struct nf_conncount_list *list, */ age = a - b; if (conn->cpu == cpu || age >= 2) { - *free_entry = conn_free(list, conn); + conn_free(list, conn); return ERR_PTR(-ENOENT); } @@ -137,14 +130,13 @@ static int __nf_conncount_add(struct net *net, struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collect = 0; - bool free_entry = false; /* check the saved connections */ list_for_each_entry_safe(conn, conn_n, &list->head, node) { if (collect > CONNCOUNT_GC_MAX_NODES) break; - found = find_or_evict(net, list, conn, &free_entry); + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { @@ -221,7 +213,6 @@ void nf_conncount_list_init(struct nf_conncount_list *list) spin_lock_init(&list->list_lock); INIT_LIST_HEAD(&list->head); list->count = 0; - list->dead = false; } EXPORT_SYMBOL_GPL(nf_conncount_list_init); @@ -233,7 +224,6 @@ bool nf_conncount_gc_list(struct net *net, struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collected = 0; - bool free_entry = false; bool ret = false; /* don't bother if other cpu is already doing GC */ @@ -241,15 +231,10 @@ bool nf_conncount_gc_list(struct net *net, return false; list_for_each_entry_safe(conn, conn_n, &list->head, node) { - found = find_or_evict(net, list, conn, &free_entry); + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { - if (PTR_ERR(found) == -ENOENT) { - if (free_entry) { - spin_unlock(&list->list_lock); - return true; - } + if (PTR_ERR(found) == -ENOENT) collected++; - } continue; } @@ -260,10 +245,7 @@ bool nf_conncount_gc_list(struct net *net, * closed already -> ditch it */ nf_ct_put(found_ct); - if (conn_free(list, conn)) { - spin_unlock(&list->list_lock); - return true; - } + conn_free(list, conn); collected++; continue; } @@ -273,10 +255,8 @@ bool nf_conncount_gc_list(struct net *net, break; } - if (!list->count) { - list->dead = true; + if (!list->count) ret = true; - } spin_unlock(&list->list_lock); return ret; @@ -291,6 +271,7 @@ static void __tree_nodes_free(struct rcu_head *h) kmem_cache_free(conncount_rb_cachep, rbconn); } +/* caller must hold tree nf_conncount_locks[] lock */ static void tree_nodes_free(struct rb_root *root, struct nf_conncount_rb *gc_nodes[], unsigned int gc_count) @@ -300,8 +281,10 @@ static void tree_nodes_free(struct rb_root *root, while (gc_count) { rbconn = gc_nodes[--gc_count]; spin_lock(&rbconn->list.list_lock); - rb_erase(&rbconn->node, root); - call_rcu(&rbconn->rcu_head, __tree_nodes_free); + if (!rbconn->list.count) { + rb_erase(&rbconn->node, root); + call_rcu(&rbconn->rcu_head, __tree_nodes_free); + } spin_unlock(&rbconn->list.list_lock); } } @@ -318,7 +301,6 @@ insert_tree(struct net *net, struct rb_root *root, unsigned int hash, const u32 *key, - u8 keylen, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { @@ -327,6 +309,7 @@ insert_tree(struct net *net, struct nf_conncount_rb *rbconn; struct nf_conncount_tuple *conn; unsigned int count = 0, gc_count = 0; + u8 keylen = data->keylen; bool do_gc = true; spin_lock_bh(&nf_conncount_locks[hash]); @@ -454,7 +437,7 @@ count_tree(struct net *net, if (!tuple) return 0; - return insert_tree(net, data, root, hash, key, keylen, tuple, zone); + return insert_tree(net, data, root, hash, key, tuple, zone); } static void tree_gc_worker(struct work_struct *work) From 6567515e4a7c42931aefd2c503882839570b7546 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 Dec 2018 01:24:49 +0100 Subject: [PATCH 027/116] netfilter: nf_conncount: fix argument order to find_next_bit commit a007232066f6839d6f256bab21e825d968f1a163 upstream. Size and 'next bit' were swapped, this bug could cause worker to reschedule itself even if system was idle. Fixes: 5c789e131cbb9 ("netfilter: nf_conncount: Add list lock and gc worker, and RCU for init tree search") Reviewed-by: Shawn Bohrer Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/netfilter/nf_conncount.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index f0b05dfebc6e..7554c56b2e63 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -488,7 +488,7 @@ static void tree_gc_worker(struct work_struct *work) clear_bit(tree, data->pending_trees); next_tree = (tree + 1) % CONNCOUNT_SLOTS; - next_tree = find_next_bit(data->pending_trees, next_tree, CONNCOUNT_SLOTS); + next_tree = find_next_bit(data->pending_trees, CONNCOUNT_SLOTS, next_tree); if (next_tree < CONNCOUNT_SLOTS) { data->gc_tree = next_tree; From e276420e4828de216d04d073662b38ff0854299a Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 4 Dec 2018 13:25:32 +0100 Subject: [PATCH 028/116] mmc: sdhci-msm: Disable CDR function on TX commit a89e7bcb18081c611eb6cf50edd440fa4983a71a upstream. The Clock Data Recovery (CDR) circuit allows to automatically adjust the RX sampling-point/phase for high frequency cards (SDR104, HS200...). CDR is automatically enabled during DLL configuration. However, according to the APQ8016 reference manual, this function must be disabled during TX and tuning phase in order to prevent any interferences during tuning challenges and unexpected phase alteration during TX transfers. This patch enables/disables CDR according to the current transfer mode. This fixes sporadic write transfer issues observed with some SDR104 and HS200 cards. Inspired by sdhci-msm downstream patch: https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/432516/ Reported-by: Leonid Segal Reported-by: Manabu Igusa Signed-off-by: Loic Poulain Acked-by: Adrian Hunter Acked-by: Georgi Djakov Signed-off-by: Ulf Hansson [georgi: backport to v4.19+] Signed-off-by: Georgi Djakov Signed-off-by: Greg Kroah-Hartman --- drivers/mmc/host/sdhci-msm.c | 43 +++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 3cc8bfee6c18..8594659cb592 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -258,6 +258,8 @@ struct sdhci_msm_host { bool mci_removed; const struct sdhci_msm_variant_ops *var_ops; const struct sdhci_msm_offset *offset; + bool use_cdr; + u32 transfer_mode; }; static const struct sdhci_msm_offset *sdhci_priv_msm_offset(struct sdhci_host *host) @@ -1025,6 +1027,26 @@ static int sdhci_msm_hs400_dll_calibration(struct sdhci_host *host) return ret; } +static void sdhci_msm_set_cdr(struct sdhci_host *host, bool enable) +{ + const struct sdhci_msm_offset *msm_offset = sdhci_priv_msm_offset(host); + u32 config, oldconfig = readl_relaxed(host->ioaddr + + msm_offset->core_dll_config); + + config = oldconfig; + if (enable) { + config |= CORE_CDR_EN; + config &= ~CORE_CDR_EXT_EN; + } else { + config &= ~CORE_CDR_EN; + config |= CORE_CDR_EXT_EN; + } + + if (config != oldconfig) + writel_relaxed(config, host->ioaddr + + msm_offset->core_dll_config); +} + static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode) { struct sdhci_host *host = mmc_priv(mmc); @@ -1042,8 +1064,14 @@ static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode) if (host->clock <= CORE_FREQ_100MHZ || !(ios.timing == MMC_TIMING_MMC_HS400 || ios.timing == MMC_TIMING_MMC_HS200 || - ios.timing == MMC_TIMING_UHS_SDR104)) + ios.timing == MMC_TIMING_UHS_SDR104)) { + msm_host->use_cdr = false; + sdhci_msm_set_cdr(host, false); return 0; + } + + /* Clock-Data-Recovery used to dynamically adjust RX sampling point */ + msm_host->use_cdr = true; /* * For HS400 tuning in HS200 timing requires: @@ -1525,6 +1553,19 @@ static int __sdhci_msm_check_write(struct sdhci_host *host, u16 val, int reg) case SDHCI_POWER_CONTROL: req_type = !val ? REQ_BUS_OFF : REQ_BUS_ON; break; + case SDHCI_TRANSFER_MODE: + msm_host->transfer_mode = val; + break; + case SDHCI_COMMAND: + if (!msm_host->use_cdr) + break; + if ((msm_host->transfer_mode & SDHCI_TRNS_READ) && + SDHCI_GET_CMD(val) != MMC_SEND_TUNING_BLOCK_HS200 && + SDHCI_GET_CMD(val) != MMC_SEND_TUNING_BLOCK) + sdhci_msm_set_cdr(host, true); + else + sdhci_msm_set_cdr(host, false); + break; } if (req_type) { From ec98b3f39feb36045409755467a1bec659f5a8be Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Mon, 14 Jan 2019 09:59:28 -0500 Subject: [PATCH 029/116] Revert "scsi: target: iscsi: cxgbit: fix csk leak" This reverts commit c9cef2c71a89a2c926dae8151f9497e72f889315. A wrong commit message was used for the stable commit because of a human error (and duplicate commit subject lines). This patch reverts this error, and the following patches add the two upstream commits. Signed-off-by: Sasha Levin --- drivers/target/iscsi/cxgbit/cxgbit_cm.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index b289b90ae6dc..8de16016b6de 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -631,11 +631,8 @@ static void cxgbit_send_halfclose(struct cxgbit_sock *csk) static void cxgbit_arp_failure_discard(void *handle, struct sk_buff *skb) { - struct cxgbit_sock *csk = handle; - pr_debug("%s cxgbit_device %p\n", __func__, handle); kfree_skb(skb); - cxgbit_put_csk(csk); } static void cxgbit_abort_arp_failure(void *handle, struct sk_buff *skb) @@ -1193,7 +1190,7 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req) rpl5->opt0 = cpu_to_be64(opt0); rpl5->opt2 = cpu_to_be32(opt2); set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->ctrlq_idx); - t4_set_arp_err_handler(skb, csk, cxgbit_arp_failure_discard); + t4_set_arp_err_handler(skb, NULL, cxgbit_arp_failure_discard); cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t); } From 25c0f7a24a4cc99a3eacf569f47ab1633dccccc9 Mon Sep 17 00:00:00 2001 From: Varun Prakash Date: Wed, 19 Sep 2018 19:44:57 +0530 Subject: [PATCH 030/116] scsi: target: iscsi: cxgbit: fix csk leak [ Upstream commit 801df68d617e3cb831f531c99fa6003620e6b343 ] csk leak can happen if a new TCP connection gets established after cxgbit_accept_np() returns, to fix this leak free remaining csk in cxgbit_free_np(). Signed-off-by: Varun Prakash Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/iscsi/cxgbit/cxgbit_cm.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index 8de16016b6de..71888b979ab5 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -598,9 +598,12 @@ static void cxgbit_free_cdev_np(struct cxgbit_np *cnp) mutex_unlock(&cdev_list_lock); } +static void __cxgbit_free_conn(struct cxgbit_sock *csk); + void cxgbit_free_np(struct iscsi_np *np) { struct cxgbit_np *cnp = np->np_context; + struct cxgbit_sock *csk, *tmp; cnp->com.state = CSK_STATE_DEAD; if (cnp->com.cdev) @@ -608,6 +611,13 @@ void cxgbit_free_np(struct iscsi_np *np) else cxgbit_free_all_np(cnp); + spin_lock_bh(&cnp->np_accept_lock); + list_for_each_entry_safe(csk, tmp, &cnp->np_accept_list, accept_node) { + list_del_init(&csk->accept_node); + __cxgbit_free_conn(csk); + } + spin_unlock_bh(&cnp->np_accept_lock); + np->np_context = NULL; cxgbit_put_cnp(cnp); } @@ -705,9 +715,9 @@ void cxgbit_abort_conn(struct cxgbit_sock *csk) csk->tid, 600, __func__); } -void cxgbit_free_conn(struct iscsi_conn *conn) +static void __cxgbit_free_conn(struct cxgbit_sock *csk) { - struct cxgbit_sock *csk = conn->context; + struct iscsi_conn *conn = csk->conn; bool release = false; pr_debug("%s: state %d\n", @@ -716,7 +726,7 @@ void cxgbit_free_conn(struct iscsi_conn *conn) spin_lock_bh(&csk->lock); switch (csk->com.state) { case CSK_STATE_ESTABLISHED: - if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) { + if (conn && (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT)) { csk->com.state = CSK_STATE_CLOSING; cxgbit_send_halfclose(csk); } else { @@ -741,6 +751,11 @@ void cxgbit_free_conn(struct iscsi_conn *conn) cxgbit_put_csk(csk); } +void cxgbit_free_conn(struct iscsi_conn *conn) +{ + __cxgbit_free_conn(conn->context); +} + static void cxgbit_set_emss(struct cxgbit_sock *csk, u16 opt) { csk->emss = csk->com.cdev->lldi.mtus[TCPOPT_MSS_G(opt)] - @@ -803,6 +818,7 @@ void _cxgbit_free_csk(struct kref *kref) spin_unlock_bh(&cdev->cskq.lock); cxgbit_free_skb(csk); + cxgbit_put_cnp(csk->cnp); cxgbit_put_cdev(cdev); kfree(csk); @@ -1351,6 +1367,7 @@ cxgbit_pass_accept_req(struct cxgbit_device *cdev, struct sk_buff *skb) goto rel_skb; } + cxgbit_get_cnp(cnp); cxgbit_get_cdev(cdev); spin_lock(&cdev->cskq.lock); From a200574da87b9c2f9398e2d4b7a87897454b5cf1 Mon Sep 17 00:00:00 2001 From: Varun Prakash Date: Fri, 9 Nov 2018 20:59:01 +0530 Subject: [PATCH 031/116] scsi: target: iscsi: cxgbit: fix csk leak [ Upstream commit ed076c55b359cc9982ca8b065bcc01675f7365f6 ] In case of arp failure call cxgbit_put_csk() to free csk. Signed-off-by: Varun Prakash Signed-off-by: Martin K. Petersen Signed-off-by: Sasha Levin --- drivers/target/iscsi/cxgbit/cxgbit_cm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index 71888b979ab5..b19c960d5490 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -641,8 +641,11 @@ static void cxgbit_send_halfclose(struct cxgbit_sock *csk) static void cxgbit_arp_failure_discard(void *handle, struct sk_buff *skb) { + struct cxgbit_sock *csk = handle; + pr_debug("%s cxgbit_device %p\n", __func__, handle); kfree_skb(skb); + cxgbit_put_csk(csk); } static void cxgbit_abort_arp_failure(void *handle, struct sk_buff *skb) @@ -1206,7 +1209,7 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req) rpl5->opt0 = cpu_to_be64(opt0); rpl5->opt2 = cpu_to_be32(opt2); set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->ctrlq_idx); - t4_set_arp_err_handler(skb, NULL, cxgbit_arp_failure_discard); + t4_set_arp_err_handler(skb, csk, cxgbit_arp_failure_discard); cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t); } From a31edd1c1b7b3a4f2d6b93691fbcff9dfd8a0231 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 7 Dec 2018 18:39:21 +0000 Subject: [PATCH 032/116] arm64/kvm: consistently handle host HCR_EL2 flags [ Upstream commit 4eaed6aa2c628101246bcabc91b203bfac1193f8 ] In KVM we define the configuration of HCR_EL2 for a VHE HOST in HCR_HOST_VHE_FLAGS, but we don't have a similar definition for the non-VHE host flags, and open-code HCR_RW. Further, in head.S we open-code the flags for VHE and non-VHE configurations. In future, we're going to want to configure more flags for the host, so lets add a HCR_HOST_NVHE_FLAGS defintion, and consistently use both HCR_HOST_VHE_FLAGS and HCR_HOST_NVHE_FLAGS in the kvm code and head.S. We now use mov_q to generate the HCR_EL2 value, as we use when configuring other registers in head.S. Reviewed-by: Marc Zyngier Reviewed-by: Richard Henderson Signed-off-by: Mark Rutland Signed-off-by: Kristina Martsenko Reviewed-by: Christoffer Dall Cc: Catalin Marinas Cc: Marc Zyngier Cc: Will Deacon Cc: kvmarm@lists.cs.columbia.edu Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/include/asm/kvm_arm.h | 1 + arch/arm64/kernel/head.S | 5 ++--- arch/arm64/kvm/hyp/switch.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 95e3fa7ded8b..2297284e33f2 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -87,6 +87,7 @@ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ HCR_FMO | HCR_IMO) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) +#define HCR_HOST_NVHE_FLAGS (HCR_RW) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) /* TCR_EL2 Registers bits */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b0853069702f..651a06b1980f 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -494,10 +494,9 @@ ENTRY(el2_setup) #endif /* Hyp configuration. */ - mov x0, #HCR_RW // 64-bit EL1 + mov_q x0, HCR_HOST_NVHE_FLAGS cbz x2, set_hcr - orr x0, x0, #HCR_TGE // Enable Host Extensions - orr x0, x0, #HCR_E2H + mov_q x0, HCR_HOST_VHE_FLAGS set_hcr: msr hcr_el2, x0 isb diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index ca46153d7915..a1c32c1f2267 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -157,7 +157,7 @@ static void __hyp_text __deactivate_traps_nvhe(void) mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; write_sysreg(mdcr_el2, mdcr_el2); - write_sysreg(HCR_RW, hcr_el2); + write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2); write_sysreg(CPTR_EL2_DEFAULT, cptr_el2); } From d29d3891c00956c660452868766655b8447bd8a8 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 7 Dec 2018 18:39:23 +0000 Subject: [PATCH 033/116] arm64: Don't trap host pointer auth use to EL2 [ Upstream commit b3669b1e1c09890d61109a1a8ece2c5b66804714 ] To allow EL0 (and/or EL1) to use pointer authentication functionality, we must ensure that pointer authentication instructions and accesses to pointer authentication keys are not trapped to EL2. This patch ensures that HCR_EL2 is configured appropriately when the kernel is booted at EL2. For non-VHE kernels we set HCR_EL2.{API,APK}, ensuring that EL1 can access keys and permit EL0 use of instructions. For VHE kernels host EL0 (TGE && E2H) is unaffected by these settings, and it doesn't matter how we configure HCR_EL2.{API,APK}, so we don't bother setting them. This does not enable support for KVM guests, since KVM manages HCR_EL2 itself when running VMs. Reviewed-by: Richard Henderson Signed-off-by: Mark Rutland Signed-off-by: Kristina Martsenko Acked-by: Christoffer Dall Cc: Catalin Marinas Cc: Marc Zyngier Cc: Will Deacon Cc: kvmarm@lists.cs.columbia.edu Signed-off-by: Will Deacon Signed-off-by: Sasha Levin --- arch/arm64/include/asm/kvm_arm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 2297284e33f2..8b284cbf8162 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -24,6 +24,8 @@ /* Hyp Configuration Register (HCR) bits */ #define HCR_FWB (UL(1) << 46) +#define HCR_API (UL(1) << 41) +#define HCR_APK (UL(1) << 40) #define HCR_TEA (UL(1) << 37) #define HCR_TERR (UL(1) << 36) #define HCR_TLOR (UL(1) << 35) @@ -87,7 +89,7 @@ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ HCR_FMO | HCR_IMO) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) -#define HCR_HOST_NVHE_FLAGS (HCR_RW) +#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) /* TCR_EL2 Registers bits */ From c0e1392e37e1f4f1e325a0a8ad75e5832f168450 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Jan 2019 04:06:14 -0800 Subject: [PATCH 034/116] ipv6: fix kernel-infoleak in ipv6_local_error() [ Upstream commit 7d033c9f6a7fd3821af75620a0257db87c2b552a ] This patch makes sure the flow label in the IPv6 header forged in ipv6_local_error() is initialized. BUG: KMSAN: kernel-infoleak in _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 CPU: 1 PID: 24675 Comm: syz-executor1 Not tainted 4.20.0-rc7+ #4 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613 kmsan_internal_check_memory+0x455/0xb00 mm/kmsan/kmsan.c:675 kmsan_copy_to_user+0xab/0xc0 mm/kmsan/kmsan_hooks.c:601 _copy_to_user+0x16b/0x1f0 lib/usercopy.c:32 copy_to_user include/linux/uaccess.h:177 [inline] move_addr_to_user+0x2e9/0x4f0 net/socket.c:227 ___sys_recvmsg+0x5d7/0x1140 net/socket.c:2284 __sys_recvmsg net/socket.c:2327 [inline] __do_sys_recvmsg net/socket.c:2337 [inline] __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x457ec9 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f8750c06c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002f RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457ec9 RDX: 0000000000002000 RSI: 0000000020000400 RDI: 0000000000000005 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f8750c076d4 R13: 00000000004c4a60 R14: 00000000004d8140 R15: 00000000ffffffff Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline] kmsan_save_stack mm/kmsan/kmsan.c:219 [inline] kmsan_internal_chain_origin+0x134/0x230 mm/kmsan/kmsan.c:439 __msan_chain_origin+0x70/0xe0 mm/kmsan/kmsan_instr.c:200 ipv6_recv_error+0x1e3f/0x1eb0 net/ipv6/datagram.c:475 udpv6_recvmsg+0x398/0x2ab0 net/ipv6/udp.c:335 inet_recvmsg+0x4fb/0x600 net/ipv4/af_inet.c:830 sock_recvmsg_nosec net/socket.c:794 [inline] sock_recvmsg+0x1d1/0x230 net/socket.c:801 ___sys_recvmsg+0x4d5/0x1140 net/socket.c:2278 __sys_recvmsg net/socket.c:2327 [inline] __do_sys_recvmsg net/socket.c:2337 [inline] __se_sys_recvmsg+0x2fa/0x450 net/socket.c:2334 __x64_sys_recvmsg+0x4a/0x70 net/socket.c:2334 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2759 [inline] __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383 __kmalloc_reserve net/core/skbuff.c:137 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:205 alloc_skb include/linux/skbuff.h:998 [inline] ipv6_local_error+0x1a7/0x9e0 net/ipv6/datagram.c:334 __ip6_append_data+0x129f/0x4fd0 net/ipv6/ip6_output.c:1311 ip6_make_skb+0x6cc/0xcf0 net/ipv6/ip6_output.c:1775 udpv6_sendmsg+0x3f8e/0x45d0 net/ipv6/udp.c:1384 inet_sendmsg+0x54a/0x720 net/ipv4/af_inet.c:798 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] __sys_sendto+0x8c4/0xac0 net/socket.c:1788 __do_sys_sendto net/socket.c:1800 [inline] __se_sys_sendto+0x107/0x130 net/socket.c:1796 __x64_sys_sendto+0x6e/0x90 net/socket.c:1796 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 Bytes 4-7 of 28 are uninitialized Memory access of size 28 starts at ffff8881937bfce0 Data copied to user address 0000000020000000 Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/datagram.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 1ede7a16a0be..7b090578f044 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -341,6 +341,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; + ip6_flow_hdr(iph, 0, 0); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; From 54cbcff82d5eb7fd00d964a6c534362735460d19 Mon Sep 17 00:00:00 2001 From: JianJhen Chen Date: Sun, 6 Jan 2019 11:28:13 +0800 Subject: [PATCH 035/116] net: bridge: fix a bug on using a neighbour cache entry without checking its state [ Upstream commit 4c84edc11b76590859b1e45dd676074c59602dc4 ] When handling DNAT'ed packets on a bridge device, the neighbour cache entry from lookup was used without checking its state. It means that a cache entry in the NUD_STALE state will be used directly instead of entering the NUD_DELAY state to confirm the reachability of the neighbor. This problem becomes worse after commit 2724680bceee ("neigh: Keep neighbour cache entries if number of them is small enough."), since all neighbour cache entries in the NUD_STALE state will be kept in the neighbour table as long as the number of cache entries does not exceed the value specified in gc_thresh1. This commit validates the state of a neighbour cache entry before using the entry. Signed-off-by: JianJhen Chen Reviewed-by: JinLin Chen Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/bridge/br_netfilter_hooks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 37278dc280eb..e07a7e62c705 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -278,7 +278,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); int ret; - if (neigh->hh.hh_len) { + if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; ret = br_handle_frame_finish(net, sk, skb); From 3dc241b8fa94650ce5712283334109493516b713 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 8 Jan 2019 23:27:06 +0000 Subject: [PATCH 036/116] packet: Do not leak dev refcounts on error exit [ Upstream commit d972f3dce8d161e2142da0ab1ef25df00e2f21a9 ] 'dev' is non NULL when the addr_len check triggers so it must goto a label that does the dev_put otherwise dev will have a leaked refcount. This bug causes the ib_ipoib module to become unloadable when using systemd-network as it triggers this check on InfiniBand links. Fixes: 99137b7888f4 ("packet: validate address length") Reported-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe Acked-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/packet/af_packet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 0541cfc93440..b6ea0fadb34f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2628,7 +2628,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) addr = saddr->sll_halen ? saddr->sll_addr : NULL; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (addr && dev && saddr->sll_halen < dev->addr_len) - goto out; + goto out_put; } err = -ENXIO; @@ -2828,7 +2828,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) addr = saddr->sll_halen ? saddr->sll_addr : NULL; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (addr && dev && saddr->sll_halen < dev->addr_len) - goto out; + goto out_unlock; } err = -ENXIO; From d7fe54c17aa3995a62345946d6ff8ddc03c17d2a Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 8 Jan 2019 18:14:28 -0800 Subject: [PATCH 037/116] tcp: change txhash on SYN-data timeout [ Upstream commit c5715b8fabfca0ef85903f8bad2189940ed41cc8 ] Previously upon SYN timeouts the sender recomputes the txhash to try a different path. However this does not apply on the initial timeout of SYN-data (active Fast Open). Therefore an active IPv6 Fast Open connection may incur one second RTO penalty to take on a new path after the second SYN retransmission uses a new flow label. This patch removes this undesirable behavior so Fast Open changes the flow label just like the regular connections. This also helps avoid falsely disabling Fast Open on the sender which triggers after two consecutive SYN timeouts on Fast Open. Signed-off-by: Yuchung Cheng Reviewed-by: Neal Cardwell Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 57eae8d70ba1..b1b5a648def6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -224,7 +224,7 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) { dst_negative_advice(sk); - } else if (!tp->syn_data && !tp->syn_fastopen) { + } else { sk_rethink_txhash(sk); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; From 08be4b72f36206213a0cd3fe8b356fd1f4c03854 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 7 Jan 2019 13:38:38 -0800 Subject: [PATCH 038/116] tun: publish tfile after it's fully initialized [ Upstream commit 0b7959b6257322f7693b08a459c505d4938646f2 ] BUG: unable to handle kernel NULL pointer dereference at 00000000000000d1 Call Trace: ? napi_gro_frags+0xa7/0x2c0 tun_get_user+0xb50/0xf20 tun_chr_write_iter+0x53/0x70 new_sync_write+0xff/0x160 vfs_write+0x191/0x1e0 __x64_sys_write+0x5e/0xd0 do_syscall_64+0x47/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 I think there is a subtle race between sending a packet via tap and attaching it: CPU0: CPU1: tun_chr_ioctl(TUNSETIFF) tun_set_iff tun_attach rcu_assign_pointer(tfile->tun, tun); tun_fops->write_iter() tun_chr_write_iter tun_napi_alloc_frags napi_get_frags napi->skb = napi_alloc_skb tun_napi_init netif_napi_add napi->skb = NULL napi->skb is NULL here napi_gro_frags napi_frags_skb skb = napi->skb skb_reset_mac_header(skb) panic() Move rcu_assign_pointer(tfile->tun) and rcu_assign_pointer(tun->tfiles) to be the last thing we do in tun_attach(); this should guarantee that when we call tun_get() we always get an initialized object. v2 changes: * remove extra napi_mutex locks/unlocks for napi operations Reported-by: syzbot Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver") Signed-off-by: Stanislav Fomichev Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/tun.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8c1abcba4cbd..33978b0cdac8 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -859,10 +859,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file, err = 0; } - rcu_assign_pointer(tfile->tun, tun); - rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); - tun->numqueues++; - if (tfile->detached) { tun_enable_queue(tfile); } else { @@ -876,6 +872,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file, * refcnt. */ + /* Publish tfile->tun and tun->tfiles only after we've fully + * initialized tfile; otherwise we risk using half-initialized + * object. + */ + rcu_assign_pointer(tfile->tun, tun); + rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); + tun->numqueues++; out: return err; } From f352903d5d785339623a7d77a60239c76b80eb6e Mon Sep 17 00:00:00 2001 From: Bryan Whitehead Date: Mon, 7 Jan 2019 14:00:09 -0500 Subject: [PATCH 039/116] lan743x: Remove phy_read from link status change function [ Upstream commit a0071840d2040ea1b27e5a008182b09b88defc15 ] It has been noticed that some phys do not have the registers required by the previous implementation. To fix this, instead of using phy_read, the required information is extracted from the phy_device structure. fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver") Signed-off-by: Bryan Whitehead Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/microchip/lan743x_main.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 1393252c6e3c..42f5bfa33694 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -962,13 +962,10 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) memset(&ksettings, 0, sizeof(ksettings)); phy_ethtool_get_link_ksettings(netdev, &ksettings); - local_advertisement = phy_read(phydev, MII_ADVERTISE); - if (local_advertisement < 0) - return; - - remote_advertisement = phy_read(phydev, MII_LPA); - if (remote_advertisement < 0) - return; + local_advertisement = + ethtool_adv_to_mii_adv_t(phydev->advertising); + remote_advertisement = + ethtool_adv_to_mii_adv_t(phydev->lp_advertising); lan743x_phy_update_flowcontrol(adapter, ksettings.base.duplex, From 8dc262df0c6f304657a0d6db071a7287390307af Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 5 Jan 2019 23:45:26 -0800 Subject: [PATCH 040/116] smc: move unhash as early as possible in smc_release() [ Upstream commit 26d92e951fe0a44ee4aec157cabb65a818cc8151 ] In smc_release() we release smc->clcsock before unhash the smc sock, but a parallel smc_diag_dump() may be still reading smc->clcsock, therefore this could cause a use-after-free as reported by syzbot. Reported-and-tested-by: syzbot+fbd1e5476e4c94c7b34e@syzkaller.appspotmail.com Fixes: 51f1de79ad8e ("net/smc: replace sock_put worker by socket refcounting") Cc: Ursula Braun Signed-off-by: Cong Wang Reported-by: syzbot+0bf2e01269f1274b4b03@syzkaller.appspotmail.com Reported-by: syzbot+e3132895630f957306bc@syzkaller.appspotmail.com Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/smc/af_smc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 2b8f95290627..e6e506b2db99 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -144,6 +144,9 @@ static int smc_release(struct socket *sock) sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; } + + sk->sk_prot->unhash(sk); + if (smc->clcsock) { if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { /* wake up clcsock accept */ @@ -168,7 +171,6 @@ static int smc_release(struct socket *sock) smc_conn_free(&smc->conn); release_sock(sk); - sk->sk_prot->unhash(sk); sock_put(sk); /* final sock_put */ out: return rc; From d976151a51c8e3fd92d49f106430a92a4528ecd6 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 6 Jan 2019 20:44:00 +0100 Subject: [PATCH 041/116] r8169: don't try to read counters if chip is in a PCI power-save state [ Upstream commit 10262b0b53666cbc506989b17a3ead1e9c3b43b4 ] Avoid log spam caused by trying to read counters from the chip whilst it is in a PCI power-save state. Reference: https://bugzilla.kernel.org/show_bug.cgi?id=107421 Fixes: 1ef7286e7f36 ("r8169: Dereference MMIO address immediately before use") Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/realtek/r8169.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 9fc8a2bc0ff1..b4bca27b460f 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1730,11 +1730,13 @@ static bool rtl8169_reset_counters(struct rtl8169_private *tp) static bool rtl8169_update_counters(struct rtl8169_private *tp) { + u8 val = RTL_R8(tp, ChipCmd); + /* * Some chips are unable to dump tally counters when the receiver - * is disabled. + * is disabled. If 0xff chip may be in a PCI power-save state. */ - if ((RTL_R8(tp, ChipCmd) & CmdRxEnb) == 0) + if (!(val & CmdRxEnb) || val == 0xff) return true; return rtl8169_do_counters(tp, CounterDump); From d2898aae0da6beb34cc00336a7017fec78c8b663 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 8 Jan 2019 12:32:42 -0500 Subject: [PATCH 042/116] bonding: update nest level on unlink [ Upstream commit 001e465f09a18857443489a57e74314a3368c805 ] A network device stack with multiple layers of bonding devices can trigger a false positive lockdep warning. Adding lockdep nest levels fixes this. Update the level on both enslave and unlink, to avoid the following series of events .. ip netns add test ip netns exec test bash ip link set dev lo addr 00:11:22:33:44:55 ip link set dev lo down ip link add dev bond1 type bond ip link add dev bond2 type bond ip link set dev lo master bond1 ip link set dev bond1 master bond2 ip link set dev bond1 nomaster ip link set dev bond2 master bond1 .. from still generating a splat: [ 193.652127] ====================================================== [ 193.658231] WARNING: possible circular locking dependency detected [ 193.664350] 4.20.0 #8 Not tainted [ 193.668310] ------------------------------------------------------ [ 193.674417] ip/15577 is trying to acquire lock: [ 193.678897] 00000000a40e3b69 (&(&bond->stats_lock)->rlock#3/3){+.+.}, at: bond_get_stats+0x58/0x290 [ 193.687851] but task is already holding lock: [ 193.693625] 00000000807b9d9f (&(&bond->stats_lock)->rlock#2/2){+.+.}, at: bond_get_stats+0x58/0x290 [..] [ 193.851092] lock_acquire+0xa7/0x190 [ 193.855138] _raw_spin_lock_nested+0x2d/0x40 [ 193.859878] bond_get_stats+0x58/0x290 [ 193.864093] dev_get_stats+0x5a/0xc0 [ 193.868140] bond_get_stats+0x105/0x290 [ 193.872444] dev_get_stats+0x5a/0xc0 [ 193.876493] rtnl_fill_stats+0x40/0x130 [ 193.880797] rtnl_fill_ifinfo+0x6c5/0xdc0 [ 193.885271] rtmsg_ifinfo_build_skb+0x86/0xe0 [ 193.890091] rtnetlink_event+0x5b/0xa0 [ 193.894320] raw_notifier_call_chain+0x43/0x60 [ 193.899225] netdev_change_features+0x50/0xa0 [ 193.904044] bond_compute_features.isra.46+0x1ab/0x270 [ 193.909640] bond_enslave+0x141d/0x15b0 [ 193.913946] do_set_master+0x89/0xa0 [ 193.918016] do_setlink+0x37c/0xda0 [ 193.921980] __rtnl_newlink+0x499/0x890 [ 193.926281] rtnl_newlink+0x48/0x70 [ 193.930238] rtnetlink_rcv_msg+0x171/0x4b0 [ 193.934801] netlink_rcv_skb+0xd1/0x110 [ 193.939103] rtnetlink_rcv+0x15/0x20 [ 193.943151] netlink_unicast+0x3b5/0x520 [ 193.947544] netlink_sendmsg+0x2fd/0x3f0 [ 193.951942] sock_sendmsg+0x38/0x50 [ 193.955899] ___sys_sendmsg+0x2ba/0x2d0 [ 193.960205] __x64_sys_sendmsg+0xad/0x100 [ 193.964687] do_syscall_64+0x5a/0x460 [ 193.968823] entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: 7e2556e40026 ("bonding: avoid lockdep confusion in bond_get_stats()") Reported-by: syzbot Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/bonding/bond_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 3c597569cfae..a6fcc5c96070 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1947,6 +1947,9 @@ static int __bond_release_one(struct net_device *bond_dev, if (!bond_has_slaves(bond)) { bond_set_carrier(bond); eth_hw_addr_random(bond_dev); + bond->nest_level = SINGLE_DEPTH_NESTING; + } else { + bond->nest_level = dev_get_nest_level(bond_dev) + 1; } unblock_netpoll_tx(); From eb02c17fcce5e6862b42bf0058cc26d225bbc165 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 7 Jan 2019 16:47:33 -0500 Subject: [PATCH 043/116] ip: on queued skb use skb_header_pointer instead of pskb_may_pull [ Upstream commit 4a06fa67c4da20148803525151845276cdb995c1 ] Commit 2efd4fca703a ("ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull") avoided a read beyond the end of the skb linear segment by calling pskb_may_pull. That function can trigger a BUG_ON in pskb_expand_head if the skb is shared, which it is when when peeking. It can also return ENOMEM. Avoid both by switching to safer skb_header_pointer. Fixes: 2efd4fca703a ("ip: in cmsg IP(V6)_ORIGDSTADDR call pskb_may_pull") Reported-by: syzbot Suggested-by: Eric Dumazet Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_sockglue.c | 12 +++++------- net/ipv6/datagram.c | 10 ++++------ 2 files changed, 9 insertions(+), 13 deletions(-) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 26c36cccabdc..b7a26120d552 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -148,19 +148,17 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { + __be16 _ports[2], *ports; struct sockaddr_in sin; - __be16 *ports; - int end; - - end = skb_transport_offset(skb) + 4; - if (end > 0 && !pskb_may_pull(skb, end)) - return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ - ports = (__be16 *)skb_transport_header(skb); + ports = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_ports), &_ports); + if (!ports) + return; sin.sin_family = AF_INET; sin.sin_addr.s_addr = ip_hdr(skb)->daddr; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 7b090578f044..cb24850d2c7f 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -701,17 +701,15 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports; - int end; + __be16 _ports[2], *ports; - end = skb_transport_offset(skb) + 4; - if (end <= 0 || pskb_may_pull(skb, end)) { + ports = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_ports), &_ports); + if (ports) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ - ports = (__be16 *)skb_transport_header(skb); - sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; sin6.sin6_port = ports[1]; From 6e09bef3cbe2c0ad2f387ce1dbfd877c97d6a029 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 7 Jan 2019 21:49:09 +0100 Subject: [PATCH 044/116] r8169: load Realtek PHY driver module before r8169 [ Upstream commit 11287b693d03830010356339e4ceddf47dee34fa ] This soft dependency works around an issue where sometimes the genphy driver is used instead of the dedicated PHY driver. The root cause of the issue isn't clear yet. People reported the unloading/re-loading module r8169 helps, and also configuring this soft dependency in the modprobe config files. Important just seems to be that the realtek module is loaded before r8169. Once this has been applied preliminary fix 38af4b903210 ("net: phy: add workaround for issue where PHY driver doesn't bind to the device") will be removed. Fixes: f1e911d5d0df ("r8169: add basic phylib support") Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/realtek/r8169.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index b4bca27b460f..07f3080eca18 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -717,6 +717,7 @@ module_param(use_dac, int, 0); MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI slot."); module_param_named(debug, debug.msg_enable, int, 0); MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)"); +MODULE_SOFTDEP("pre: realtek"); MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_8168D_1); MODULE_FIRMWARE(FIRMWARE_8168D_2); From 68afc7c36461a5989b91ca88f82bbcd90dece24d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 8 Jan 2019 22:12:41 -0800 Subject: [PATCH 045/116] crypto: sm3 - fix undefined shift by >= width of value commit d45a90cb5d061fa7d411b974b950fe0b8bc5f265 upstream. sm3_compress() calls rol32() with shift >= 32, which causes undefined behavior. This is easily detected by enabling CONFIG_UBSAN. Explicitly AND with 31 to make the behavior well defined. Fixes: 4f0fc1600edb ("crypto: sm3 - add OSCCA SM3 secure hash") Cc: # v4.15+ Cc: Gilad Ben-Yossef Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/sm3_generic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/sm3_generic.c b/crypto/sm3_generic.c index 9a5c60f08aad..c0cf87ae7ef6 100644 --- a/crypto/sm3_generic.c +++ b/crypto/sm3_generic.c @@ -100,7 +100,7 @@ static void sm3_compress(u32 *w, u32 *wt, u32 *m) for (i = 0; i <= 63; i++) { - ss1 = rol32((rol32(a, 12) + e + rol32(t(i), i)), 7); + ss1 = rol32((rol32(a, 12) + e + rol32(t(i), i & 31)), 7); ss2 = ss1 ^ rol32(a, 12); From 9107b2f4343280e507a2041a33d40d66186dd54d Mon Sep 17 00:00:00 2001 From: Aymen Sghaier Date: Wed, 19 Dec 2018 16:36:44 +0200 Subject: [PATCH 046/116] crypto: caam - fix zero-length buffer DMA mapping MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 04e6d25c5bb244c1a37eb9fe0b604cc11a04e8c5 upstream. Recent changes - probably DMA API related (generic and/or arm64-specific) - exposed a case where driver maps a zero-length buffer: ahash_init()->ahash_update()->ahash_final() with a zero-length string to hash kernel BUG at kernel/dma/swiotlb.c:475! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP Modules linked in: CPU: 2 PID: 1823 Comm: cryptomgr_test Not tainted 4.20.0-rc1-00108-g00c9fe37a7f2 #1 Hardware name: LS1046A RDB Board (DT) pstate: 80000005 (Nzcv daif -PAN -UAO) pc : swiotlb_tbl_map_single+0x170/0x2b8 lr : swiotlb_map_page+0x134/0x1f8 sp : ffff00000f79b8f0 x29: ffff00000f79b8f0 x28: 0000000000000000 x27: ffff0000093d0000 x26: 0000000000000000 x25: 00000000001f3ffe x24: 0000000000200000 x23: 0000000000000000 x22: 00000009f2c538c0 x21: ffff800970aeb410 x20: 0000000000000001 x19: ffff800970aeb410 x18: 0000000000000007 x17: 000000000000000e x16: 0000000000000001 x15: 0000000000000019 x14: c32cb8218a167fe8 x13: ffffffff00000000 x12: ffff80097fdae348 x11: 0000800976bca000 x10: 0000000000000010 x9 : 0000000000000000 x8 : ffff0000091fd6c8 x7 : 0000000000000000 x6 : 00000009f2c538bf x5 : 0000000000000000 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 00000009f2c538c0 x1 : 00000000f9fff000 x0 : 0000000000000000 Process cryptomgr_test (pid: 1823, stack limit = 0x(____ptrval____)) Call trace: swiotlb_tbl_map_single+0x170/0x2b8 swiotlb_map_page+0x134/0x1f8 ahash_final_no_ctx+0xc4/0x6cc ahash_final+0x10/0x18 crypto_ahash_op+0x30/0x84 crypto_ahash_final+0x14/0x1c __test_hash+0x574/0xe0c test_hash+0x28/0x80 __alg_test_hash+0x84/0xd0 alg_test_hash+0x78/0x144 alg_test.part.30+0x12c/0x2b4 alg_test+0x3c/0x68 cryptomgr_test+0x44/0x4c kthread+0xfc/0x128 ret_from_fork+0x10/0x18 Code: d34bfc18 2a1a03f7 1a9f8694 35fff89a (d4210000) Cc: Signed-off-by: Aymen Sghaier Signed-off-by: Horia Geantă Reviewed-by: Christoph Hellwig Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/caam/caamhash.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index 43975ab5f09c..f84ca2ff61de 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -1131,13 +1131,16 @@ static int ahash_final_no_ctx(struct ahash_request *req) desc = edesc->hw_desc; - state->buf_dma = dma_map_single(jrdev, buf, buflen, DMA_TO_DEVICE); - if (dma_mapping_error(jrdev, state->buf_dma)) { - dev_err(jrdev, "unable to map src\n"); - goto unmap; - } + if (buflen) { + state->buf_dma = dma_map_single(jrdev, buf, buflen, + DMA_TO_DEVICE); + if (dma_mapping_error(jrdev, state->buf_dma)) { + dev_err(jrdev, "unable to map src\n"); + goto unmap; + } - append_seq_in_ptr(desc, state->buf_dma, buflen, 0); + append_seq_in_ptr(desc, state->buf_dma, buflen, 0); + } edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result, digestsize); From 6590803766398525f9854dea4f8e44651d1d96b1 Mon Sep 17 00:00:00 2001 From: Harsh Jain Date: Thu, 3 Jan 2019 14:21:05 +0530 Subject: [PATCH 047/116] crypto: authencesn - Avoid twice completion call in decrypt path commit a7773363624b034ab198c738661253d20a8055c2 upstream. Authencesn template in decrypt path unconditionally calls aead_request_complete after ahash_verify which leads to following kernel panic in after decryption. [ 338.539800] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 [ 338.548372] PGD 0 P4D 0 [ 338.551157] Oops: 0000 [#1] SMP PTI [ 338.554919] CPU: 0 PID: 0 Comm: swapper/0 Kdump: loaded Tainted: G W I 4.19.7+ #13 [ 338.564431] Hardware name: Supermicro X8ST3/X8ST3, BIOS 2.0 07/29/10 [ 338.572212] RIP: 0010:esp_input_done2+0x350/0x410 [esp4] [ 338.578030] Code: ff 0f b6 68 10 48 8b 83 c8 00 00 00 e9 8e fe ff ff 8b 04 25 04 00 00 00 83 e8 01 48 98 48 8b 3c c5 10 00 00 00 e9 f7 fd ff ff <8b> 04 25 04 00 00 00 83 e8 01 48 98 4c 8b 24 c5 10 00 00 00 e9 3b [ 338.598547] RSP: 0018:ffff911c97803c00 EFLAGS: 00010246 [ 338.604268] RAX: 0000000000000002 RBX: ffff911c4469ee00 RCX: 0000000000000000 [ 338.612090] RDX: 0000000000000000 RSI: 0000000000000130 RDI: ffff911b87c20400 [ 338.619874] RBP: 0000000000000000 R08: ffff911b87c20498 R09: 000000000000000a [ 338.627610] R10: 0000000000000001 R11: 0000000000000004 R12: 0000000000000000 [ 338.635402] R13: ffff911c89590000 R14: ffff911c91730000 R15: 0000000000000000 [ 338.643234] FS: 0000000000000000(0000) GS:ffff911c97800000(0000) knlGS:0000000000000000 [ 338.652047] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 338.658299] CR2: 0000000000000004 CR3: 00000001ec20a000 CR4: 00000000000006f0 [ 338.666382] Call Trace: [ 338.669051] [ 338.671254] esp_input_done+0x12/0x20 [esp4] [ 338.675922] chcr_handle_resp+0x3b5/0x790 [chcr] [ 338.680949] cpl_fw6_pld_handler+0x37/0x60 [chcr] [ 338.686080] chcr_uld_rx_handler+0x22/0x50 [chcr] [ 338.691233] uldrx_handler+0x8c/0xc0 [cxgb4] [ 338.695923] process_responses+0x2f0/0x5d0 [cxgb4] [ 338.701177] ? bitmap_find_next_zero_area_off+0x3a/0x90 [ 338.706882] ? matrix_alloc_area.constprop.7+0x60/0x90 [ 338.712517] ? apic_update_irq_cfg+0x82/0xf0 [ 338.717177] napi_rx_handler+0x14/0xe0 [cxgb4] [ 338.722015] net_rx_action+0x2aa/0x3e0 [ 338.726136] __do_softirq+0xcb/0x280 [ 338.730054] irq_exit+0xde/0xf0 [ 338.733504] do_IRQ+0x54/0xd0 [ 338.736745] common_interrupt+0xf/0xf Fixes: 104880a6b470 ("crypto: authencesn - Convert to new AEAD...") Signed-off-by: Harsh Jain Cc: stable@vger.kernel.org Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/authencesn.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crypto/authencesn.c b/crypto/authencesn.c index 50b804747e20..4eff4be6bd12 100644 --- a/crypto/authencesn.c +++ b/crypto/authencesn.c @@ -279,7 +279,7 @@ static void authenc_esn_verify_ahash_done(struct crypto_async_request *areq, struct aead_request *req = areq->data; err = err ?: crypto_authenc_esn_decrypt_tail(req, 0); - aead_request_complete(req, err); + authenc_esn_request_complete(req, err); } static int crypto_authenc_esn_decrypt(struct aead_request *req) From 93242fa04d87294f3265d6b488caa5d13867b1f4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 16 Dec 2018 23:23:24 -0800 Subject: [PATCH 048/116] crypto: ccree - convert to use crypto_authenc_extractkeys() commit dc95b5350a8f07d73d6bde3a79ef87289698451d upstream. Convert the ccree crypto driver to use crypto_authenc_extractkeys() so that it picks up the fix for broken validation of rtattr::rta_len. Fixes: ff27e85a85bb ("crypto: ccree - add AEAD support") Cc: # v4.17+ Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/ccree/cc_aead.c | 40 ++++++++++++++++------------------ 1 file changed, 19 insertions(+), 21 deletions(-) diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c index 01b82b82f8b8..5852d29ae2da 100644 --- a/drivers/crypto/ccree/cc_aead.c +++ b/drivers/crypto/ccree/cc_aead.c @@ -540,13 +540,12 @@ static int cc_aead_setkey(struct crypto_aead *tfm, const u8 *key, unsigned int keylen) { struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm); - struct rtattr *rta = (struct rtattr *)key; struct cc_crypto_req cc_req = {}; - struct crypto_authenc_key_param *param; struct cc_hw_desc desc[MAX_AEAD_SETKEY_SEQ]; - int rc = -EINVAL; unsigned int seq_len = 0; struct device *dev = drvdata_to_dev(ctx->drvdata); + const u8 *enckey, *authkey; + int rc; dev_dbg(dev, "Setting key in context @%p for %s. key=%p keylen=%u\n", ctx, crypto_tfm_alg_name(crypto_aead_tfm(tfm)), key, keylen); @@ -554,35 +553,33 @@ static int cc_aead_setkey(struct crypto_aead *tfm, const u8 *key, /* STAT_PHASE_0: Init and sanity checks */ if (ctx->auth_mode != DRV_HASH_NULL) { /* authenc() alg. */ - if (!RTA_OK(rta, keylen)) + struct crypto_authenc_keys keys; + + rc = crypto_authenc_extractkeys(&keys, key, keylen); + if (rc) goto badkey; - if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM) - goto badkey; - if (RTA_PAYLOAD(rta) < sizeof(*param)) - goto badkey; - param = RTA_DATA(rta); - ctx->enc_keylen = be32_to_cpu(param->enckeylen); - key += RTA_ALIGN(rta->rta_len); - keylen -= RTA_ALIGN(rta->rta_len); - if (keylen < ctx->enc_keylen) - goto badkey; - ctx->auth_keylen = keylen - ctx->enc_keylen; + enckey = keys.enckey; + authkey = keys.authkey; + ctx->enc_keylen = keys.enckeylen; + ctx->auth_keylen = keys.authkeylen; if (ctx->cipher_mode == DRV_CIPHER_CTR) { /* the nonce is stored in bytes at end of key */ + rc = -EINVAL; if (ctx->enc_keylen < (AES_MIN_KEY_SIZE + CTR_RFC3686_NONCE_SIZE)) goto badkey; /* Copy nonce from last 4 bytes in CTR key to * first 4 bytes in CTR IV */ - memcpy(ctx->ctr_nonce, key + ctx->auth_keylen + - ctx->enc_keylen - CTR_RFC3686_NONCE_SIZE, - CTR_RFC3686_NONCE_SIZE); + memcpy(ctx->ctr_nonce, enckey + ctx->enc_keylen - + CTR_RFC3686_NONCE_SIZE, CTR_RFC3686_NONCE_SIZE); /* Set CTR key size */ ctx->enc_keylen -= CTR_RFC3686_NONCE_SIZE; } } else { /* non-authenc - has just one key */ + enckey = key; + authkey = NULL; ctx->enc_keylen = keylen; ctx->auth_keylen = 0; } @@ -594,13 +591,14 @@ static int cc_aead_setkey(struct crypto_aead *tfm, const u8 *key, /* STAT_PHASE_1: Copy key to ctx */ /* Get key material */ - memcpy(ctx->enckey, key + ctx->auth_keylen, ctx->enc_keylen); + memcpy(ctx->enckey, enckey, ctx->enc_keylen); if (ctx->enc_keylen == 24) memset(ctx->enckey + 24, 0, CC_AES_KEY_SIZE_MAX - 24); if (ctx->auth_mode == DRV_HASH_XCBC_MAC) { - memcpy(ctx->auth_state.xcbc.xcbc_keys, key, ctx->auth_keylen); + memcpy(ctx->auth_state.xcbc.xcbc_keys, authkey, + ctx->auth_keylen); } else if (ctx->auth_mode != DRV_HASH_NULL) { /* HMAC */ - rc = cc_get_plain_hmac_key(tfm, key, ctx->auth_keylen); + rc = cc_get_plain_hmac_key(tfm, authkey, ctx->auth_keylen); if (rc) goto badkey; } From 97a6662b035c20d073ce6ebc660d57fc1e492ad3 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 16 Dec 2018 23:23:23 -0800 Subject: [PATCH 049/116] crypto: bcm - convert to use crypto_authenc_extractkeys() commit ab57b33525c3221afaebd391458fa0cbcd56903d upstream. Convert the bcm crypto driver to use crypto_authenc_extractkeys() so that it picks up the fix for broken validation of rtattr::rta_len. This also fixes the DES weak key check to actually be done on the right key. (It was checking the authentication key, not the encryption key...) Fixes: 9d12ba86f818 ("crypto: brcm - Add Broadcom SPU driver") Cc: # v4.11+ Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/Kconfig | 1 + drivers/crypto/bcm/cipher.c | 44 +++++++++++-------------------------- 2 files changed, 14 insertions(+), 31 deletions(-) diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig index a8c4ce07fc9d..a825b6444459 100644 --- a/drivers/crypto/Kconfig +++ b/drivers/crypto/Kconfig @@ -681,6 +681,7 @@ config CRYPTO_DEV_BCM_SPU depends on ARCH_BCM_IPROC depends on MAILBOX default m + select CRYPTO_AUTHENC select CRYPTO_DES select CRYPTO_MD5 select CRYPTO_SHA1 diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c index 2d1f1db9f807..cd464637b0cb 100644 --- a/drivers/crypto/bcm/cipher.c +++ b/drivers/crypto/bcm/cipher.c @@ -2845,44 +2845,28 @@ static int aead_authenc_setkey(struct crypto_aead *cipher, struct spu_hw *spu = &iproc_priv.spu; struct iproc_ctx_s *ctx = crypto_aead_ctx(cipher); struct crypto_tfm *tfm = crypto_aead_tfm(cipher); - struct rtattr *rta = (void *)key; - struct crypto_authenc_key_param *param; - const u8 *origkey = key; - const unsigned int origkeylen = keylen; - - int ret = 0; + struct crypto_authenc_keys keys; + int ret; flow_log("%s() aead:%p key:%p keylen:%u\n", __func__, cipher, key, keylen); flow_dump(" key: ", key, keylen); - if (!RTA_OK(rta, keylen)) - goto badkey; - if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM) - goto badkey; - if (RTA_PAYLOAD(rta) < sizeof(*param)) + ret = crypto_authenc_extractkeys(&keys, key, keylen); + if (ret) goto badkey; - param = RTA_DATA(rta); - ctx->enckeylen = be32_to_cpu(param->enckeylen); - - key += RTA_ALIGN(rta->rta_len); - keylen -= RTA_ALIGN(rta->rta_len); - - if (keylen < ctx->enckeylen) - goto badkey; - if (ctx->enckeylen > MAX_KEY_SIZE) + if (keys.enckeylen > MAX_KEY_SIZE || + keys.authkeylen > MAX_KEY_SIZE) goto badkey; - ctx->authkeylen = keylen - ctx->enckeylen; + ctx->enckeylen = keys.enckeylen; + ctx->authkeylen = keys.authkeylen; - if (ctx->authkeylen > MAX_KEY_SIZE) - goto badkey; - - memcpy(ctx->enckey, key + ctx->authkeylen, ctx->enckeylen); + memcpy(ctx->enckey, keys.enckey, keys.enckeylen); /* May end up padding auth key. So make sure it's zeroed. */ memset(ctx->authkey, 0, sizeof(ctx->authkey)); - memcpy(ctx->authkey, key, ctx->authkeylen); + memcpy(ctx->authkey, keys.authkey, keys.authkeylen); switch (ctx->alg->cipher_info.alg) { case CIPHER_ALG_DES: @@ -2890,7 +2874,7 @@ static int aead_authenc_setkey(struct crypto_aead *cipher, u32 tmp[DES_EXPKEY_WORDS]; u32 flags = CRYPTO_TFM_RES_WEAK_KEY; - if (des_ekey(tmp, key) == 0) { + if (des_ekey(tmp, keys.enckey) == 0) { if (crypto_aead_get_flags(cipher) & CRYPTO_TFM_REQ_WEAK_KEY) { crypto_aead_set_flags(cipher, flags); @@ -2905,7 +2889,7 @@ static int aead_authenc_setkey(struct crypto_aead *cipher, break; case CIPHER_ALG_3DES: if (ctx->enckeylen == (DES_KEY_SIZE * 3)) { - const u32 *K = (const u32 *)key; + const u32 *K = (const u32 *)keys.enckey; u32 flags = CRYPTO_TFM_RES_BAD_KEY_SCHED; if (!((K[0] ^ K[2]) | (K[1] ^ K[3])) || @@ -2956,9 +2940,7 @@ static int aead_authenc_setkey(struct crypto_aead *cipher, ctx->fallback_cipher->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK; ctx->fallback_cipher->base.crt_flags |= tfm->crt_flags & CRYPTO_TFM_REQ_MASK; - ret = - crypto_aead_setkey(ctx->fallback_cipher, origkey, - origkeylen); + ret = crypto_aead_setkey(ctx->fallback_cipher, key, keylen); if (ret) { flow_log(" fallback setkey() returned:%d\n", ret); tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK; From 44c67402c3f738b7048de4464c02461bc8d0fd37 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sun, 16 Dec 2018 23:23:22 -0800 Subject: [PATCH 050/116] crypto: authenc - fix parsing key with misaligned rta_len commit 8f9c469348487844328e162db57112f7d347c49f upstream. Keys for "authenc" AEADs are formatted as an rtattr containing a 4-byte 'enckeylen', followed by an authentication key and an encryption key. crypto_authenc_extractkeys() parses the key to find the inner keys. However, it fails to consider the case where the rtattr's payload is longer than 4 bytes but not 4-byte aligned, and where the key ends before the next 4-byte aligned boundary. In this case, 'keylen -= RTA_ALIGN(rta->rta_len);' underflows to a value near UINT_MAX. This causes a buffer overread and crash during crypto_ahash_setkey(). Fix it by restricting the rtattr payload to the expected size. Reproducer using AF_ALG: #include #include #include int main() { int fd; struct sockaddr_alg addr = { .salg_type = "aead", .salg_name = "authenc(hmac(sha256),cbc(aes))", }; struct { struct rtattr attr; __be32 enckeylen; char keys[1]; } __attribute__((packed)) key = { .attr.rta_len = sizeof(key), .attr.rta_type = 1 /* CRYPTO_AUTHENC_KEYA_PARAM */, }; fd = socket(AF_ALG, SOCK_SEQPACKET, 0); bind(fd, (void *)&addr, sizeof(addr)); setsockopt(fd, SOL_ALG, ALG_SET_KEY, &key, sizeof(key)); } It caused: BUG: unable to handle kernel paging request at ffff88007ffdc000 PGD 2e01067 P4D 2e01067 PUD 2e04067 PMD 2e05067 PTE 0 Oops: 0000 [#1] SMP CPU: 0 PID: 883 Comm: authenc Not tainted 4.20.0-rc1-00108-g00c9fe37a7f27 #13 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-20181126_142135-anatol 04/01/2014 RIP: 0010:sha256_ni_transform+0xb3/0x330 arch/x86/crypto/sha256_ni_asm.S:155 [...] Call Trace: sha256_ni_finup+0x10/0x20 arch/x86/crypto/sha256_ssse3_glue.c:321 crypto_shash_finup+0x1a/0x30 crypto/shash.c:178 shash_digest_unaligned+0x45/0x60 crypto/shash.c:186 crypto_shash_digest+0x24/0x40 crypto/shash.c:202 hmac_setkey+0x135/0x1e0 crypto/hmac.c:66 crypto_shash_setkey+0x2b/0xb0 crypto/shash.c:66 shash_async_setkey+0x10/0x20 crypto/shash.c:223 crypto_ahash_setkey+0x2d/0xa0 crypto/ahash.c:202 crypto_authenc_setkey+0x68/0x100 crypto/authenc.c:96 crypto_aead_setkey+0x2a/0xc0 crypto/aead.c:62 aead_setkey+0xc/0x10 crypto/algif_aead.c:526 alg_setkey crypto/af_alg.c:223 [inline] alg_setsockopt+0xfe/0x130 crypto/af_alg.c:256 __sys_setsockopt+0x6d/0xd0 net/socket.c:1902 __do_sys_setsockopt net/socket.c:1913 [inline] __se_sys_setsockopt net/socket.c:1910 [inline] __x64_sys_setsockopt+0x1f/0x30 net/socket.c:1910 do_syscall_64+0x4a/0x180 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: e236d4a89a2f ("[CRYPTO] authenc: Move enckeylen into key itself") Cc: # v2.6.25+ Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- crypto/authenc.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/crypto/authenc.c b/crypto/authenc.c index 4fa8d40d947b..3ee10fc25aff 100644 --- a/crypto/authenc.c +++ b/crypto/authenc.c @@ -58,14 +58,22 @@ int crypto_authenc_extractkeys(struct crypto_authenc_keys *keys, const u8 *key, return -EINVAL; if (rta->rta_type != CRYPTO_AUTHENC_KEYA_PARAM) return -EINVAL; - if (RTA_PAYLOAD(rta) < sizeof(*param)) + + /* + * RTA_OK() didn't align the rtattr's payload when validating that it + * fits in the buffer. Yet, the keys should start on the next 4-byte + * aligned boundary. To avoid confusion, require that the rtattr + * payload be exactly the param struct, which has a 4-byte aligned size. + */ + if (RTA_PAYLOAD(rta) != sizeof(*param)) return -EINVAL; + BUILD_BUG_ON(sizeof(*param) % RTA_ALIGNTO); param = RTA_DATA(rta); keys->enckeylen = be32_to_cpu(param->enckeylen); - key += RTA_ALIGN(rta->rta_len); - keylen -= RTA_ALIGN(rta->rta_len); + key += rta->rta_len; + keylen -= rta->rta_len; if (keylen < keys->enckeylen) return -EINVAL; From c6578f509312e4b6503f423b54bf6b9784b782ea Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 8 Jan 2019 06:56:46 +0000 Subject: [PATCH 051/116] crypto: talitos - reorder code in talitos_edesc_alloc() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit c56c2e173773097a248fd3bace91ac8f6fc5386d upstream. This patch moves the mapping of IV after the kmalloc(). This avoids having to unmap in case kmalloc() fails. Signed-off-by: Christophe Leroy Reviewed-by: Horia Geantă Cc: stable@vger.kernel.org Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/talitos.c | 25 +++++++------------------ 1 file changed, 7 insertions(+), 18 deletions(-) diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 6988012deca4..921967587fc5 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -1361,23 +1361,18 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev, struct talitos_private *priv = dev_get_drvdata(dev); bool is_sec1 = has_ftr_sec1(priv); int max_len = is_sec1 ? TALITOS1_MAX_DATA_LEN : TALITOS2_MAX_DATA_LEN; - void *err; if (cryptlen + authsize > max_len) { dev_err(dev, "length exceeds h/w max limit\n"); return ERR_PTR(-EINVAL); } - if (ivsize) - iv_dma = dma_map_single(dev, iv, ivsize, DMA_TO_DEVICE); - if (!dst || dst == src) { src_len = assoclen + cryptlen + authsize; src_nents = sg_nents_for_len(src, src_len); if (src_nents < 0) { dev_err(dev, "Invalid number of src SG.\n"); - err = ERR_PTR(-EINVAL); - goto error_sg; + return ERR_PTR(-EINVAL); } src_nents = (src_nents == 1) ? 0 : src_nents; dst_nents = dst ? src_nents : 0; @@ -1387,16 +1382,14 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev, src_nents = sg_nents_for_len(src, src_len); if (src_nents < 0) { dev_err(dev, "Invalid number of src SG.\n"); - err = ERR_PTR(-EINVAL); - goto error_sg; + return ERR_PTR(-EINVAL); } src_nents = (src_nents == 1) ? 0 : src_nents; dst_len = assoclen + cryptlen + (encrypt ? authsize : 0); dst_nents = sg_nents_for_len(dst, dst_len); if (dst_nents < 0) { dev_err(dev, "Invalid number of dst SG.\n"); - err = ERR_PTR(-EINVAL); - goto error_sg; + return ERR_PTR(-EINVAL); } dst_nents = (dst_nents == 1) ? 0 : dst_nents; } @@ -1425,10 +1418,10 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev, alloc_len += sizeof(struct talitos_desc); edesc = kmalloc(alloc_len, GFP_DMA | flags); - if (!edesc) { - err = ERR_PTR(-ENOMEM); - goto error_sg; - } + if (!edesc) + return ERR_PTR(-ENOMEM); + if (ivsize) + iv_dma = dma_map_single(dev, iv, ivsize, DMA_TO_DEVICE); memset(&edesc->desc, 0, sizeof(edesc->desc)); edesc->src_nents = src_nents; @@ -1445,10 +1438,6 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev, DMA_BIDIRECTIONAL); } return edesc; -error_sg: - if (iv_dma) - dma_unmap_single(dev, iv_dma, ivsize, DMA_TO_DEVICE); - return err; } static struct talitos_edesc *aead_edesc_alloc(struct aead_request *areq, u8 *iv, From 64e986444138374f71ff5722493ae0c8ce642691 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 8 Jan 2019 06:56:48 +0000 Subject: [PATCH 052/116] crypto: talitos - fix ablkcipher for CONFIG_VMAP_STACK MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1bea445b0a022ee126ca328b3705cd4df18ebc14 upstream. [ 2.364486] WARNING: CPU: 0 PID: 60 at ./arch/powerpc/include/asm/io.h:837 dma_nommu_map_page+0x44/0xd4 [ 2.373579] CPU: 0 PID: 60 Comm: cryptomgr_test Tainted: G W 4.20.0-rc5-00560-g6bfb52e23a00-dirty #531 [ 2.384740] NIP: c000c540 LR: c000c584 CTR: 00000000 [ 2.389743] REGS: c95abab0 TRAP: 0700 Tainted: G W (4.20.0-rc5-00560-g6bfb52e23a00-dirty) [ 2.400042] MSR: 00029032 CR: 24042204 XER: 00000000 [ 2.406669] [ 2.406669] GPR00: c02f2244 c95abb60 c6262990 c95abd80 0000256a 00000001 00000001 00000001 [ 2.406669] GPR08: 00000000 00002000 00000010 00000010 24042202 00000000 00000100 c95abd88 [ 2.406669] GPR16: 00000000 c05569d4 00000001 00000010 c95abc88 c0615664 00000004 00000000 [ 2.406669] GPR24: 00000010 c95abc88 c95abc88 00000000 c61ae210 c7ff6d40 c61ae210 00003d68 [ 2.441559] NIP [c000c540] dma_nommu_map_page+0x44/0xd4 [ 2.446720] LR [c000c584] dma_nommu_map_page+0x88/0xd4 [ 2.451762] Call Trace: [ 2.454195] [c95abb60] [82000808] 0x82000808 (unreliable) [ 2.459572] [c95abb80] [c02f2244] talitos_edesc_alloc+0xbc/0x3c8 [ 2.465493] [c95abbb0] [c02f2600] ablkcipher_edesc_alloc+0x4c/0x5c [ 2.471606] [c95abbd0] [c02f4ed0] ablkcipher_encrypt+0x20/0x64 [ 2.477389] [c95abbe0] [c02023b0] __test_skcipher+0x4bc/0xa08 [ 2.483049] [c95abe00] [c0204b60] test_skcipher+0x2c/0xcc [ 2.488385] [c95abe20] [c0204c48] alg_test_skcipher+0x48/0xbc [ 2.494064] [c95abe40] [c0205cec] alg_test+0x164/0x2e8 [ 2.499142] [c95abf00] [c0200dec] cryptomgr_test+0x48/0x50 [ 2.504558] [c95abf10] [c0039ff4] kthread+0xe4/0x110 [ 2.509471] [c95abf40] [c000e1d0] ret_from_kernel_thread+0x14/0x1c [ 2.515532] Instruction dump: [ 2.518468] 7c7e1b78 7c9d2378 7cbf2b78 41820054 3d20c076 8089c200 3d20c076 7c84e850 [ 2.526127] 8129c204 7c842e70 7f844840 419c0008 <0fe00000> 2f9e0000 54847022 7c84fa14 [ 2.533960] ---[ end trace bf78d94af73fe3b8 ]--- [ 2.539123] talitos ff020000.crypto: master data transfer error [ 2.544775] talitos ff020000.crypto: TEA error: ISR 0x20000000_00000040 [ 2.551625] alg: skcipher: encryption failed on test 1 for ecb-aes-talitos: ret=22 IV cannot be on stack when CONFIG_VMAP_STACK is selected because the stack cannot be DMA mapped anymore. This patch copies the IV into the extended descriptor. Fixes: 4de9d0b547b9 ("crypto: talitos - Add ablkcipher algorithms") Cc: stable@vger.kernel.org Signed-off-by: Christophe Leroy Reviewed-by: Horia Geantă Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/talitos.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 921967587fc5..f4f3e9a5851e 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -1416,12 +1416,15 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev, /* if its a ahash, add space for a second desc next to the first one */ if (is_sec1 && !dst) alloc_len += sizeof(struct talitos_desc); + alloc_len += ivsize; edesc = kmalloc(alloc_len, GFP_DMA | flags); if (!edesc) return ERR_PTR(-ENOMEM); - if (ivsize) + if (ivsize) { + iv = memcpy(((u8 *)edesc) + alloc_len - ivsize, iv, ivsize); iv_dma = dma_map_single(dev, iv, ivsize, DMA_TO_DEVICE); + } memset(&edesc->desc, 0, sizeof(edesc->desc)); edesc->src_nents = src_nents; From 4432362af3a3dc7ef6ee68adf5e8ebc41e67a4c5 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 14 Jan 2019 13:44:13 +0100 Subject: [PATCH 053/116] xen: Fix x86 sched_clock() interface for xen commit 867cefb4cb1012f42cada1c7d1f35ac8dd276071 upstream. Commit f94c8d11699759 ("sched/clock, x86/tsc: Rework the x86 'unstable' sched_clock() interface") broke Xen guest time handling across migration: [ 187.249951] Freezing user space processes ... (elapsed 0.001 seconds) done. [ 187.251137] OOM killer disabled. [ 187.251137] Freezing remaining freezable tasks ... (elapsed 0.001 seconds) done. [ 187.252299] suspending xenstore... [ 187.266987] xen:grant_table: Grant tables using version 1 layout [18446743811.706476] OOM killer enabled. [18446743811.706478] Restarting tasks ... done. [18446743811.720505] Setting capacity to 16777216 Fix that by setting xen_sched_clock_offset at resume time to ensure a monotonic clock value. [boris: replaced pr_info() with pr_info_once() in xen_callback_vector() to avoid printing with incorrect timestamp during resume (as we haven't re-adjusted the clock yet)] Fixes: f94c8d11699759 ("sched/clock, x86/tsc: Rework the x86 'unstable' sched_clock() interface") Cc: # 4.11 Reported-by: Hans van Kranenburg Signed-off-by: Juergen Gross Tested-by: Hans van Kranenburg Signed-off-by: Boris Ostrovsky Signed-off-by: Greg Kroah-Hartman --- arch/x86/xen/time.c | 12 +++++++++--- drivers/xen/events/events_base.c | 2 +- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index c84f1e039d84..01dcccf9185f 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -361,8 +361,6 @@ void xen_timer_resume(void) { int cpu; - pvclock_resume(); - if (xen_clockevent != &xen_vcpuop_clockevent) return; @@ -379,12 +377,15 @@ static const struct pv_time_ops xen_time_ops __initconst = { }; static struct pvclock_vsyscall_time_info *xen_clock __read_mostly; +static u64 xen_clock_value_saved; void xen_save_time_memory_area(void) { struct vcpu_register_time_memory_area t; int ret; + xen_clock_value_saved = xen_clocksource_read() - xen_sched_clock_offset; + if (!xen_clock) return; @@ -404,7 +405,7 @@ void xen_restore_time_memory_area(void) int ret; if (!xen_clock) - return; + goto out; t.addr.v = &xen_clock->pvti; @@ -421,6 +422,11 @@ void xen_restore_time_memory_area(void) if (ret != 0) pr_notice("Cannot restore secondary vcpu_time_info (err %d)", ret); + +out: + /* Need pvclock_resume() before using xen_clocksource_read(). */ + pvclock_resume(); + xen_sched_clock_offset = xen_clocksource_read() - xen_clock_value_saved; } static void xen_setup_vsyscall_time_info(void) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index e6c1934734b7..fe1f16351f94 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -1650,7 +1650,7 @@ void xen_callback_vector(void) xen_have_vector_callback = 0; return; } - pr_info("Xen HVM callback vector for event delivery is enabled\n"); + pr_info_once("Xen HVM callback vector for event delivery is enabled\n"); alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, xen_hvm_callback_vector); } From 4675f90ef892b7071c09e30f80565adf628fff3b Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 9 Jan 2019 15:02:23 +0100 Subject: [PATCH 054/116] Revert "btrfs: balance dirty metadata pages in btrfs_finish_ordered_io" commit 77b7aad195099e7c6da11e94b7fa6ef5e6fb0025 upstream. This reverts commit e73e81b6d0114d4a303205a952ab2e87c44bd279. This patch causes a few problems: - adds latency to btrfs_finish_ordered_io - as btrfs_finish_ordered_io is used for free space cache, generating more work from btrfs_btree_balance_dirty_nodelay could end up in the same workque, effectively deadlocking 12260 kworker/u96:16+btrfs-freespace-write D [<0>] balance_dirty_pages+0x6e6/0x7ad [<0>] balance_dirty_pages_ratelimited+0x6bb/0xa90 [<0>] btrfs_finish_ordered_io+0x3da/0x770 [<0>] normal_work_helper+0x1c5/0x5a0 [<0>] process_one_work+0x1ee/0x5a0 [<0>] worker_thread+0x46/0x3d0 [<0>] kthread+0xf5/0x130 [<0>] ret_from_fork+0x24/0x30 [<0>] 0xffffffffffffffff Transaction commit will wait on the freespace cache: 838 btrfs-transacti D [<0>] btrfs_start_ordered_extent+0x154/0x1e0 [<0>] btrfs_wait_ordered_range+0xbd/0x110 [<0>] __btrfs_wait_cache_io+0x49/0x1a0 [<0>] btrfs_write_dirty_block_groups+0x10b/0x3b0 [<0>] commit_cowonly_roots+0x215/0x2b0 [<0>] btrfs_commit_transaction+0x37e/0x910 [<0>] transaction_kthread+0x14d/0x180 [<0>] kthread+0xf5/0x130 [<0>] ret_from_fork+0x24/0x30 [<0>] 0xffffffffffffffff And then writepages ends up waiting on transaction commit: 9520 kworker/u96:13+flush-btrfs-1 D [<0>] wait_current_trans+0xac/0xe0 [<0>] start_transaction+0x21b/0x4b0 [<0>] cow_file_range_inline+0x10b/0x6b0 [<0>] cow_file_range.isra.69+0x329/0x4a0 [<0>] run_delalloc_range+0x105/0x3c0 [<0>] writepage_delalloc+0x119/0x180 [<0>] __extent_writepage+0x10c/0x390 [<0>] extent_write_cache_pages+0x26f/0x3d0 [<0>] extent_writepages+0x4f/0x80 [<0>] do_writepages+0x17/0x60 [<0>] __writeback_single_inode+0x59/0x690 [<0>] writeback_sb_inodes+0x291/0x4e0 [<0>] __writeback_inodes_wb+0x87/0xb0 [<0>] wb_writeback+0x3bb/0x500 [<0>] wb_workfn+0x40d/0x610 [<0>] process_one_work+0x1ee/0x5a0 [<0>] worker_thread+0x1e0/0x3d0 [<0>] kthread+0xf5/0x130 [<0>] ret_from_fork+0x24/0x30 [<0>] 0xffffffffffffffff Eventually, we have every process in the system waiting on balance_dirty_pages(), and nobody is able to make progress on page writeback. The original patch tried to fix an OOM condition, that happened on 4.4 but no success reproducing that on later kernels (4.19 and 4.20). This is more likely a problem in OOM itself. Link: https://lore.kernel.org/linux-btrfs/20180528054821.9092-1-ethanlien@synology.com/ Reported-by: Chris Mason CC: stable@vger.kernel.org # 4.18+ CC: ethanlien Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/inode.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 14c85e61134d..4f6dc56b4f4d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3151,9 +3151,6 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) /* once for the tree */ btrfs_put_ordered_extent(ordered_extent); - /* Try to release some metadata so we don't get an OOM but don't wait */ - btrfs_btree_balance_dirty_nodelay(fs_info); - return ret; } From 01634ac56393272de45f1f88be9d28f52f91a272 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 21 Nov 2018 14:05:45 -0500 Subject: [PATCH 055/116] btrfs: wait on ordered extents on abort cleanup commit 74d5d229b1bf60f93bff244b2dfc0eb21ec32a07 upstream. If we flip read-only before we initiate writeback on all dirty pages for ordered extents we've created then we'll have ordered extents left over on umount, which results in all sorts of bad things happening. Fix this by making sure we wait on ordered extents if we have to do the aborted transaction cleanup stuff. generic/475 can produce this warning: [ 8531.177332] WARNING: CPU: 2 PID: 11997 at fs/btrfs/disk-io.c:3856 btrfs_free_fs_root+0x95/0xa0 [btrfs] [ 8531.183282] CPU: 2 PID: 11997 Comm: umount Tainted: G W 5.0.0-rc1-default+ #394 [ 8531.185164] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),BIOS rel-1.11.2-0-gf9626cc-prebuilt.qemu-project.org 04/01/2014 [ 8531.187851] RIP: 0010:btrfs_free_fs_root+0x95/0xa0 [btrfs] [ 8531.193082] RSP: 0018:ffffb1ab86163d98 EFLAGS: 00010286 [ 8531.194198] RAX: ffff9f3449494d18 RBX: ffff9f34a2695000 RCX:0000000000000000 [ 8531.195629] RDX: 0000000000000002 RSI: 0000000000000001 RDI:0000000000000000 [ 8531.197315] RBP: ffff9f344e930000 R08: 0000000000000001 R09:0000000000000000 [ 8531.199095] R10: 0000000000000000 R11: ffff9f34494d4ff8 R12:ffffb1ab86163dc0 [ 8531.200870] R13: ffff9f344e9300b0 R14: ffffb1ab86163db8 R15:0000000000000000 [ 8531.202707] FS: 00007fc68e949fc0(0000) GS:ffff9f34bd800000(0000)knlGS:0000000000000000 [ 8531.204851] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8531.205942] CR2: 00007ffde8114dd8 CR3: 000000002dfbd000 CR4:00000000000006e0 [ 8531.207516] Call Trace: [ 8531.208175] btrfs_free_fs_roots+0xdb/0x170 [btrfs] [ 8531.210209] ? wait_for_completion+0x5b/0x190 [ 8531.211303] close_ctree+0x157/0x350 [btrfs] [ 8531.212412] generic_shutdown_super+0x64/0x100 [ 8531.213485] kill_anon_super+0x14/0x30 [ 8531.214430] btrfs_kill_super+0x12/0xa0 [btrfs] [ 8531.215539] deactivate_locked_super+0x29/0x60 [ 8531.216633] cleanup_mnt+0x3b/0x70 [ 8531.217497] task_work_run+0x98/0xc0 [ 8531.218397] exit_to_usermode_loop+0x83/0x90 [ 8531.219324] do_syscall_64+0x15b/0x180 [ 8531.220192] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 8531.221286] RIP: 0033:0x7fc68e5e4d07 [ 8531.225621] RSP: 002b:00007ffde8116608 EFLAGS: 00000246 ORIG_RAX:00000000000000a6 [ 8531.227512] RAX: 0000000000000000 RBX: 00005580c2175970 RCX:00007fc68e5e4d07 [ 8531.229098] RDX: 0000000000000001 RSI: 0000000000000000 RDI:00005580c2175b80 [ 8531.230730] RBP: 0000000000000000 R08: 00005580c2175ba0 R09:00007ffde8114e80 [ 8531.232269] R10: 0000000000000000 R11: 0000000000000246 R12:00005580c2175b80 [ 8531.233839] R13: 00007fc68eac61c4 R14: 00005580c2175a68 R15:0000000000000000 Leaving a tree in the rb-tree: 3853 void btrfs_free_fs_root(struct btrfs_root *root) 3854 { 3855 iput(root->ino_cache_inode); 3856 WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); CC: stable@vger.kernel.org Reviewed-by: Nikolay Borisov Signed-off-by: Josef Bacik [ add stacktrace ] Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/disk-io.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index d4a7f7ca4145..d96d1390068a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4155,6 +4155,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->ordered_root_lock); } spin_unlock(&fs_info->ordered_root_lock); + + /* + * We need this here because if we've been flipped read-only we won't + * get sync() from the umount, so we need to make sure any ordered + * extents that haven't had their dirty pages IO start writeout yet + * actually get run and error out properly. + */ + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, From b955a2c75675102b8270fd06c6c2730913994ce7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 16 Jan 2019 10:31:09 -0800 Subject: [PATCH 056/116] Yama: Check for pid death before checking ancestry commit 9474f4e7cd71a633fa1ef93b7daefd44bbdfd482 upstream. It's possible that a pid has died before we take the rcu lock, in which case we can't walk the ancestry list as it may be detached. Instead, check for death first before doing the walk. Reported-by: syzbot+a9ac39bf55329e206219@syzkaller.appspotmail.com Fixes: 2d514487faf1 ("security: Yama LSM") Cc: stable@vger.kernel.org Suggested-by: Oleg Nesterov Signed-off-by: Kees Cook Signed-off-by: James Morris Signed-off-by: Greg Kroah-Hartman --- security/yama/yama_lsm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index ffda91a4a1aa..02514fe558b4 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -368,7 +368,9 @@ static int yama_ptrace_access_check(struct task_struct *child, break; case YAMA_SCOPE_RELATIONAL: rcu_read_lock(); - if (!task_is_descendant(current, child) && + if (!pid_alive(child)) + rc = -EPERM; + if (!rc && !task_is_descendant(current, child) && !ptracer_exception_found(current, child) && !ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE)) rc = -EPERM; From d368f540ac3e3ad0f5531457eb827f7cb8d63fa7 Mon Sep 17 00:00:00 2001 From: Stanley Chu Date: Thu, 3 Jan 2019 22:08:05 +0800 Subject: [PATCH 057/116] scsi: core: Synchronize request queue PM status only on successful resume commit 3f7e62bba0003f9c68f599f5997c4647ef5b4f4e upstream. The commit 356fd2663cff ("scsi: Set request queue runtime PM status back to active on resume") fixed up the inconsistent RPM status between request queue and device. However changing request queue RPM status shall be done only on successful resume, otherwise status may be still inconsistent as below, Request queue: RPM_ACTIVE Device: RPM_SUSPENDED This ends up soft lockup because requests can be submitted to underlying devices but those devices and their required resource are not resumed. For example, After above inconsistent status happens, IO request can be submitted to UFS device driver but required resource (like clock) is not resumed yet thus lead to warning as below call stack, WARN_ON(hba->clk_gating.state != CLKS_ON); ufshcd_queuecommand scsi_dispatch_cmd scsi_request_fn __blk_run_queue cfq_insert_request __elv_add_request blk_flush_plug_list blk_finish_plug jbd2_journal_commit_transaction kjournald2 We may see all behind IO requests hang because of no response from storage host or device and then soft lockup happens in system. In the end, system may crash in many ways. Fixes: 356fd2663cff (scsi: Set request queue runtime PM status back to active on resume) Cc: stable@vger.kernel.org Signed-off-by: Stanley Chu Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/scsi_pm.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c index b44c1bb687a2..ebc193f7f7dd 100644 --- a/drivers/scsi/scsi_pm.c +++ b/drivers/scsi/scsi_pm.c @@ -79,8 +79,22 @@ static int scsi_dev_type_resume(struct device *dev, if (err == 0) { pm_runtime_disable(dev); - pm_runtime_set_active(dev); + err = pm_runtime_set_active(dev); pm_runtime_enable(dev); + + /* + * Forcibly set runtime PM status of request queue to "active" + * to make sure we can again get requests from the queue + * (see also blk_pm_peek_request()). + * + * The resume hook will correct runtime PM status of the disk. + */ + if (!err && scsi_is_sdev_device(dev)) { + struct scsi_device *sdev = to_scsi_device(dev); + + if (sdev->request_queue->dev) + blk_set_runtime_active(sdev->request_queue); + } } return err; @@ -139,16 +153,6 @@ static int scsi_bus_resume_common(struct device *dev, else fn = NULL; - /* - * Forcibly set runtime PM status of request queue to "active" to - * make sure we can again get requests from the queue (see also - * blk_pm_peek_request()). - * - * The resume hook will correct runtime PM status of the disk. - */ - if (scsi_is_sdev_device(dev) && pm_runtime_suspended(dev)) - blk_set_runtime_active(to_scsi_device(dev)->request_queue); - if (fn) { async_schedule_domain(fn, dev, &scsi_sd_pm_domain); From 9d37f4a046c27c7c86598f128bbc470d17befc20 Mon Sep 17 00:00:00 2001 From: Ivan Mironov Date: Sun, 23 Dec 2018 12:41:58 +0500 Subject: [PATCH 058/116] scsi: sd: Fix cache_type_store() commit 44759979a49bfd2d20d789add7fa81a21eb1a4ab upstream. Changing of caching mode via /sys/devices/.../scsi_disk/.../cache_type may fail if device responds to MODE SENSE command with DPOFUA flag set, and then checks this flag to be not set on MODE SELECT command. In this scenario, when trying to change cache_type, write always fails: # echo "none" >cache_type bash: echo: write error: Invalid argument And following appears in dmesg: [13007.865745] sd 1:0:1:0: [sda] Sense Key : Illegal Request [current] [13007.865753] sd 1:0:1:0: [sda] Add. Sense: Invalid field in parameter list From SBC-4 r15, 6.5.1 "Mode pages overview", description of DEVICE-SPECIFIC PARAMETER field in the mode parameter header: ... The write protect (WP) bit for mode data sent with a MODE SELECT command shall be ignored by the device server. ... The DPOFUA bit is reserved for mode data sent with a MODE SELECT command. ... The remaining bits in the DEVICE-SPECIFIC PARAMETER byte are also reserved and shall be set to zero. [mkp: shuffled commentary to commit description] Cc: stable@vger.kernel.org Signed-off-by: Ivan Mironov Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman --- drivers/scsi/sd.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 5c9acb634ff7..0a27917263aa 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -205,6 +205,12 @@ cache_type_store(struct device *dev, struct device_attribute *attr, sp = buffer_data[0] & 0x80 ? 1 : 0; buffer_data[0] &= ~0x80; + /* + * Ensure WP, DPOFUA, and RESERVED fields are cleared in + * received mode parameter buffer before doing MODE SELECT. + */ + data.device_specific = 0; + if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT, SD_MAX_RETRIES, &data, &sshdr)) { if (scsi_sense_valid(&sshdr)) From 8f469dc0e6dcc4189972a2dbe0a3aeeb3eb8c9c2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 10 Jan 2019 17:24:31 +0100 Subject: [PATCH 059/116] mips: fix n32 compat_ipc_parse_version commit 5a9372f751b5350e0ce3d2ee91832f1feae2c2e5 upstream. While reading through the sysvipc implementation, I noticed that the n32 semctl/shmctl/msgctl system calls behave differently based on whether o32 support is enabled or not: Without o32, the IPC_64 flag passed by user space is rejected but calls without that flag get IPC_64 behavior. As far as I can tell, this was inadvertently changed by a cleanup patch but never noticed by anyone, possibly nobody has tried using sysvipc on n32 after linux-3.19. Change it back to the old behavior now. Fixes: 78aaf956ba3a ("MIPS: Compat: Fix build error if CONFIG_MIPS32_COMPAT but no compat ABI.") Signed-off-by: Arnd Bergmann Signed-off-by: Paul Burton Cc: linux-mips@vger.kernel.org Cc: stable@vger.kernel.org # 3.19+ Signed-off-by: Greg Kroah-Hartman --- arch/mips/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 35511999156a..154b811d5894 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -3149,6 +3149,7 @@ config MIPS32_O32 config MIPS32_N32 bool "Kernel support for n32 binaries" depends on 64BIT + select ARCH_WANT_COMPAT_IPC_PARSE_VERSION select COMPAT select MIPS32_COMPAT select SYSVIPC_COMPAT if SYSVIPC From 19f41f32a4b44b6087b795d5e182e48d8f2c4199 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 3 Jan 2019 08:34:17 +0100 Subject: [PATCH 060/116] MIPS: BCM47XX: Setup struct device for the SoC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 321c46b91550adc03054125fa7a1639390608e1a upstream. So far we never had any device registered for the SoC. This resulted in some small issues that we kept ignoring like: 1) Not working GPIOLIB_IRQCHIP (gpiochip_irqchip_add_key() failing) 2) Lack of proper tree in the /sys/devices/ 3) mips_dma_alloc_coherent() silently handling empty coherent_dma_mask Kernel 4.19 came with a lot of DMA changes and caused a regression on bcm47xx. Starting with the commit f8c55dc6e828 ("MIPS: use generic dma noncoherent ops for simple noncoherent platforms") DMA coherent allocations just fail. Example: [ 1.114914] bgmac_bcma bcma0:2: Allocation of TX ring 0x200 failed [ 1.121215] bgmac_bcma bcma0:2: Unable to alloc memory for DMA [ 1.127626] bgmac_bcma: probe of bcma0:2 failed with error -12 [ 1.133838] bgmac_bcma: Broadcom 47xx GBit MAC driver loaded The bgmac driver also triggers a WARNING: [ 0.959486] ------------[ cut here ]------------ [ 0.964387] WARNING: CPU: 0 PID: 1 at ./include/linux/dma-mapping.h:516 bgmac_enet_probe+0x1b4/0x5c4 [ 0.973751] Modules linked in: [ 0.976913] CPU: 0 PID: 1 Comm: swapper Not tainted 4.19.9 #0 [ 0.982750] Stack : 804a0000 804597c4 00000000 00000000 80458fd8 8381bc2c 838282d4 80481a47 [ 0.991367] 8042e3ec 00000001 804d38f0 00000204 83980000 00000065 8381bbe0 6f55b24f [ 0.999975] 00000000 00000000 80520000 00002018 00000000 00000075 00000007 00000000 [ 1.008583] 00000000 80480000 000ee811 00000000 00000000 00000000 80432c00 80248db8 [ 1.017196] 00000009 00000204 83980000 803ad7b0 00000000 801feeec 00000000 804d0000 [ 1.025804] ... [ 1.028325] Call Trace: [ 1.030875] [<8000aef8>] show_stack+0x58/0x100 [ 1.035513] [<8001f8b4>] __warn+0xe4/0x118 [ 1.039708] [<8001f9a4>] warn_slowpath_null+0x48/0x64 [ 1.044935] [<80248db8>] bgmac_enet_probe+0x1b4/0x5c4 [ 1.050101] [<802498e0>] bgmac_probe+0x558/0x590 [ 1.054906] [<80252fd0>] bcma_device_probe+0x38/0x70 [ 1.060017] [<8020e1e8>] really_probe+0x170/0x2e8 [ 1.064891] [<8020e714>] __driver_attach+0xa4/0xec [ 1.069784] [<8020c1e0>] bus_for_each_dev+0x58/0xb0 [ 1.074833] [<8020d590>] bus_add_driver+0xf8/0x218 [ 1.079731] [<8020ef24>] driver_register+0xcc/0x11c [ 1.084804] [<804b54cc>] bgmac_init+0x1c/0x44 [ 1.089258] [<8000121c>] do_one_initcall+0x7c/0x1a0 [ 1.094343] [<804a1d34>] kernel_init_freeable+0x150/0x218 [ 1.099886] [<803a082c>] kernel_init+0x10/0x104 [ 1.104583] [<80005878>] ret_from_kernel_thread+0x14/0x1c [ 1.110107] ---[ end trace f441c0d873d1fb5b ]--- This patch setups a "struct device" (and passes it to the bcma) which allows fixing all the mentioned problems. It'll also require a tiny bcma patch which will follow through the wireless tree & its maintainer. Fixes: f8c55dc6e828 ("MIPS: use generic dma noncoherent ops for simple noncoherent platforms") Signed-off-by: Rafał Miłecki Signed-off-by: Paul Burton Acked-by: Hauke Mehrtens Cc: Christoph Hellwig Cc: Linus Walleij Cc: linux-wireless@vger.kernel.org Cc: Ralf Baechle Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Greg Kroah-Hartman --- arch/mips/bcm47xx/setup.c | 31 +++++++++++++++++++++++++++++++ include/linux/bcma/bcma_soc.h | 1 + 2 files changed, 32 insertions(+) diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 6054d49e608e..fe3773539eff 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -173,6 +173,31 @@ void __init plat_mem_setup(void) pm_power_off = bcm47xx_machine_halt; } +#ifdef CONFIG_BCM47XX_BCMA +static struct device * __init bcm47xx_setup_device(void) +{ + struct device *dev; + int err; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return NULL; + + err = dev_set_name(dev, "bcm47xx_soc"); + if (err) { + pr_err("Failed to set SoC device name: %d\n", err); + kfree(dev); + return NULL; + } + + err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32)); + if (err) + pr_err("Failed to set SoC DMA mask: %d\n", err); + + return dev; +} +#endif + /* * This finishes bus initialization doing things that were not possible without * kmalloc. Make sure to call it late enough (after mm_init). @@ -183,6 +208,10 @@ void __init bcm47xx_bus_setup(void) if (bcm47xx_bus_type == BCM47XX_BUS_TYPE_BCMA) { int err; + bcm47xx_bus.bcma.dev = bcm47xx_setup_device(); + if (!bcm47xx_bus.bcma.dev) + panic("Failed to setup SoC device\n"); + err = bcma_host_soc_init(&bcm47xx_bus.bcma); if (err) panic("Failed to initialize BCMA bus (err %d)", err); @@ -235,6 +264,8 @@ static int __init bcm47xx_register_bus_complete(void) #endif #ifdef CONFIG_BCM47XX_BCMA case BCM47XX_BUS_TYPE_BCMA: + if (device_register(bcm47xx_bus.bcma.dev)) + pr_err("Failed to register SoC device\n"); bcma_bus_register(&bcm47xx_bus.bcma.bus); break; #endif diff --git a/include/linux/bcma/bcma_soc.h b/include/linux/bcma/bcma_soc.h index 7cca5f859a90..f3c43519baa7 100644 --- a/include/linux/bcma/bcma_soc.h +++ b/include/linux/bcma/bcma_soc.h @@ -6,6 +6,7 @@ struct bcma_soc { struct bcma_bus bus; + struct device *dev; }; int __init bcma_host_soc_register(struct bcma_soc *soc); From 434b1b91573cf1cc11569a6338b535122d43b51e Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sun, 6 Jan 2019 19:44:11 +0100 Subject: [PATCH 061/116] MIPS: lantiq: Fix IPI interrupt handling commit 2b4dba55b04b212a7fd1f0395b41d79ee3a9801b upstream. This makes SMP on the vrx200 work again, by removing all the MIPS CPU interrupt specific code and making it fully use the generic MIPS CPU interrupt controller. The mti,cpu-interrupt-controller from irq-mips-cpu.c now handles the CPU interrupts and also the IPI interrupts which are used to communication between the CPUs in a SMP system. The generic interrupt code was already used before but the interrupt vectors were overwritten again when we called set_vi_handler() in the lantiq interrupt driver and we also provided our own plat_irq_dispatch() function which overwrote the weak generic implementation. Now the code uses the generic handler for the MIPS CPU interrupts including the IPI interrupts and registers a handler for the CPU interrupts which are handled by the lantiq ICU with irq_set_chained_handler() which was already called before. Calling the set_c0_status() function is also not needed any more because the generic MIPS CPU interrupt already activates the needed bits. Fixes: 1eed40043579 ("MIPS: smp-mt: Use CPU interrupt controller IPI IRQ domain support") Cc: stable@kernel.org # v4.12 Signed-off-by: Hauke Mehrtens Signed-off-by: Paul Burton Cc: jhogan@kernel.org Cc: ralf@linux-mips.org Cc: john@phrozen.org Cc: linux-mips@linux-mips.org Cc: linux-mips@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- arch/mips/lantiq/irq.c | 68 ++++-------------------------------------- 1 file changed, 5 insertions(+), 63 deletions(-) diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c index f0bc3312ed11..c4ef1c31e0c4 100644 --- a/arch/mips/lantiq/irq.c +++ b/arch/mips/lantiq/irq.c @@ -224,9 +224,11 @@ static struct irq_chip ltq_eiu_type = { .irq_set_type = ltq_eiu_settype, }; -static void ltq_hw_irqdispatch(int module) +static void ltq_hw_irq_handler(struct irq_desc *desc) { + int module = irq_desc_get_irq(desc) - 2; u32 irq; + int hwirq; irq = ltq_icu_r32(module, LTQ_ICU_IM0_IOSR); if (irq == 0) @@ -237,7 +239,8 @@ static void ltq_hw_irqdispatch(int module) * other bits might be bogus */ irq = __fls(irq); - do_IRQ((int)irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module)); + hwirq = irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module); + generic_handle_irq(irq_linear_revmap(ltq_domain, hwirq)); /* if this is a EBU irq, we need to ack it or get a deadlock */ if ((irq == LTQ_ICU_EBU_IRQ) && (module == 0) && LTQ_EBU_PCC_ISTAT) @@ -245,49 +248,6 @@ static void ltq_hw_irqdispatch(int module) LTQ_EBU_PCC_ISTAT); } -#define DEFINE_HWx_IRQDISPATCH(x) \ - static void ltq_hw ## x ## _irqdispatch(void) \ - { \ - ltq_hw_irqdispatch(x); \ - } -DEFINE_HWx_IRQDISPATCH(0) -DEFINE_HWx_IRQDISPATCH(1) -DEFINE_HWx_IRQDISPATCH(2) -DEFINE_HWx_IRQDISPATCH(3) -DEFINE_HWx_IRQDISPATCH(4) - -#if MIPS_CPU_TIMER_IRQ == 7 -static void ltq_hw5_irqdispatch(void) -{ - do_IRQ(MIPS_CPU_TIMER_IRQ); -} -#else -DEFINE_HWx_IRQDISPATCH(5) -#endif - -static void ltq_hw_irq_handler(struct irq_desc *desc) -{ - ltq_hw_irqdispatch(irq_desc_get_irq(desc) - 2); -} - -asmlinkage void plat_irq_dispatch(void) -{ - unsigned int pending = read_c0_status() & read_c0_cause() & ST0_IM; - int irq; - - if (!pending) { - spurious_interrupt(); - return; - } - - pending >>= CAUSEB_IP; - while (pending) { - irq = fls(pending) - 1; - do_IRQ(MIPS_CPU_IRQ_BASE + irq); - pending &= ~BIT(irq); - } -} - static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { struct irq_chip *chip = <q_irq_type; @@ -343,28 +303,10 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent) for (i = 0; i < MAX_IM; i++) irq_set_chained_handler(i + 2, ltq_hw_irq_handler); - if (cpu_has_vint) { - pr_info("Setting up vectored interrupts\n"); - set_vi_handler(2, ltq_hw0_irqdispatch); - set_vi_handler(3, ltq_hw1_irqdispatch); - set_vi_handler(4, ltq_hw2_irqdispatch); - set_vi_handler(5, ltq_hw3_irqdispatch); - set_vi_handler(6, ltq_hw4_irqdispatch); - set_vi_handler(7, ltq_hw5_irqdispatch); - } - ltq_domain = irq_domain_add_linear(node, (MAX_IM * INT_NUM_IM_OFFSET) + MIPS_CPU_IRQ_CASCADE, &irq_domain_ops, 0); -#ifndef CONFIG_MIPS_MT_SMP - set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 | - IE_IRQ3 | IE_IRQ4 | IE_IRQ5); -#else - set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ0 | IE_IRQ1 | - IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5); -#endif - /* tell oprofile which irq to use */ ltq_perfcount_irq = irq_create_mapping(ltq_domain, LTQ_PERF_IRQ); From ac8b9e8e7ddd69f3efa91e8a99312de5729382c0 Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Fri, 11 Jan 2019 13:58:53 +0800 Subject: [PATCH 062/116] drm/i915/gvt: Fix mmap range check commit 51b00d8509dc69c98740da2ad07308b630d3eb7d upstream. This is to fix missed mmap range check on vGPU bar2 region and only allow to map vGPU allocated GMADDR range, which means user space should support sparse mmap to get proper offset for mmap vGPU aperture. And this takes care of actual pgoff in mmap request as original code always does from beginning of vGPU aperture. Fixes: 659643f7d814 ("drm/i915/gvt/kvmgt: add vfio/mdev support to KVMGT") Cc: "Monroy, Rodrigo Axel" Cc: "Orrala Contreras, Alfredo" Cc: stable@vger.kernel.org # v4.10+ Reviewed-by: Hang Yuan Signed-off-by: Zhenyu Wang Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gvt/kvmgt.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 9ad89e38f6c0..12e4203c06db 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -996,7 +996,7 @@ static int intel_vgpu_mmap(struct mdev_device *mdev, struct vm_area_struct *vma) { unsigned int index; u64 virtaddr; - unsigned long req_size, pgoff = 0; + unsigned long req_size, pgoff, req_start; pgprot_t pg_prot; struct intel_vgpu *vgpu = mdev_get_drvdata(mdev); @@ -1014,7 +1014,17 @@ static int intel_vgpu_mmap(struct mdev_device *mdev, struct vm_area_struct *vma) pg_prot = vma->vm_page_prot; virtaddr = vma->vm_start; req_size = vma->vm_end - vma->vm_start; - pgoff = vgpu_aperture_pa_base(vgpu) >> PAGE_SHIFT; + pgoff = vma->vm_pgoff & + ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); + req_start = pgoff << PAGE_SHIFT; + + if (!intel_vgpu_in_aperture(vgpu, req_start)) + return -EINVAL; + if (req_start + req_size > + vgpu_aperture_offset(vgpu) + vgpu_aperture_sz(vgpu)) + return -EINVAL; + + pgoff = (gvt_aperture_pa_base(vgpu->gvt) >> PAGE_SHIFT) + pgoff; return remap_pfn_range(vma, virtaddr, pgoff, req_size, pg_prot); } From a752c6d6de8038c74b5fabd7b65f3b4f37efcceb Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sun, 13 Jan 2019 10:44:50 +0100 Subject: [PATCH 063/116] OF: properties: add missing of_node_put commit 28b170e88bc0c7509e6724717c15cb4b5686026e upstream. Add an of_node_put when the result of of_graph_get_remote_port_parent is not available. The semantic match that finds this problem is as follows (http://coccinelle.lip6.fr): // @r exists@ local idexpression e; expression x; @@ e = of_graph_get_remote_port_parent(...); ... when != x = e when != true e == NULL when != of_node_put(e) when != of_fwnode_handle(e) ( return e; | *return ...; ) // Signed-off-by: Julia Lawall Cc: stable@vger.kernel.org Signed-off-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/of/property.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/of/property.c b/drivers/of/property.c index f46828e3b082..43720c2de138 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -806,6 +806,7 @@ struct device_node *of_graph_get_remote_node(const struct device_node *node, if (!of_device_is_available(remote)) { pr_debug("not available for remote node\n"); + of_node_put(remote); return NULL; } From d846f48c1dd54e8d3f3e339d660b90ed935ef30f Mon Sep 17 00:00:00 2001 From: Jonathan Hunter Date: Tue, 13 Nov 2018 08:56:31 +0000 Subject: [PATCH 064/116] mfd: tps6586x: Handle interrupts on suspend commit ac4ca4b9f4623ba5e1ea7a582f286567c611e027 upstream. The tps6586x driver creates an irqchip that is used by its various child devices for managing interrupts. The tps6586x-rtc device is one of its children that uses the tps6586x irqchip. When using the tps6586x-rtc as a wake-up device from suspend, the following is seen: PM: Syncing filesystems ... done. Freezing user space processes ... (elapsed 0.001 seconds) done. OOM killer disabled. Freezing remaining freezable tasks ... (elapsed 0.000 seconds) done. Disabling non-boot CPUs ... Entering suspend state LP1 Enabling non-boot CPUs ... CPU1 is up tps6586x 3-0034: failed to read interrupt status tps6586x 3-0034: failed to read interrupt status The reason why the tps6586x interrupt status cannot be read is because the tps6586x interrupt is not masked during suspend and when the tps6586x-rtc interrupt occurs, to wake-up the device, the interrupt is seen before the i2c controller has been resumed in order to read the tps6586x interrupt status. The tps6586x-rtc driver sets it's interrupt as a wake-up source during suspend, which gets propagated to the parent tps6586x interrupt. However, the tps6586x-rtc driver cannot disable it's interrupt during suspend otherwise we would never be woken up and so the tps6586x must disable it's interrupt instead. Prevent the tps6586x interrupt handler from executing on exiting suspend before the i2c controller has been resumed by disabling the tps6586x interrupt on entering suspend and re-enabling it on resuming from suspend. Cc: stable@vger.kernel.org Signed-off-by: Jon Hunter Reviewed-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Acked-by: Thierry Reding Signed-off-by: Lee Jones Signed-off-by: Greg Kroah-Hartman --- drivers/mfd/tps6586x.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c index b89379782741..9c7925ca13cf 100644 --- a/drivers/mfd/tps6586x.c +++ b/drivers/mfd/tps6586x.c @@ -592,6 +592,29 @@ static int tps6586x_i2c_remove(struct i2c_client *client) return 0; } +static int __maybe_unused tps6586x_i2c_suspend(struct device *dev) +{ + struct tps6586x *tps6586x = dev_get_drvdata(dev); + + if (tps6586x->client->irq) + disable_irq(tps6586x->client->irq); + + return 0; +} + +static int __maybe_unused tps6586x_i2c_resume(struct device *dev) +{ + struct tps6586x *tps6586x = dev_get_drvdata(dev); + + if (tps6586x->client->irq) + enable_irq(tps6586x->client->irq); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(tps6586x_pm_ops, tps6586x_i2c_suspend, + tps6586x_i2c_resume); + static const struct i2c_device_id tps6586x_id_table[] = { { "tps6586x", 0 }, { }, @@ -602,6 +625,7 @@ static struct i2c_driver tps6586x_driver = { .driver = { .name = "tps6586x", .of_match_table = of_match_ptr(tps6586x_of_match), + .pm = &tps6586x_pm_ops, }, .probe = tps6586x_i2c_probe, .remove = tps6586x_i2c_remove, From 8f4a0e7d8befe681050465d91ad89250d10b57ec Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 10 Jan 2019 09:24:26 -0500 Subject: [PATCH 065/116] media: v4l: ioctl: Validate num_planes for debug messages commit 7fe9f01c04c2673bd6662c35b664f0f91888b96f upstream. The num_planes field in struct v4l2_pix_format_mplane is used in a loop before validating it. As the use is printing a debug message in this case, just cap the value to the maximum allowed. Signed-off-by: Sakari Ailus Cc: stable@vger.kernel.org Reviewed-by: Thierry Reding Signed-off-by: Hans Verkuil Cc: # for v4.12 and up Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/v4l2-core/v4l2-ioctl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 54afc9c7ee6e..a4d3e94a400c 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -286,6 +286,7 @@ static void v4l_print_format(const void *arg, bool write_only) const struct v4l2_window *win; const struct v4l2_sdr_format *sdr; const struct v4l2_meta_format *meta; + u32 planes; unsigned i; pr_cont("type=%s", prt_names(p->type, v4l2_type_names)); @@ -316,7 +317,8 @@ static void v4l_print_format(const void *arg, bool write_only) prt_names(mp->field, v4l2_field_names), mp->colorspace, mp->num_planes, mp->flags, mp->ycbcr_enc, mp->quantization, mp->xfer_func); - for (i = 0; i < mp->num_planes; i++) + planes = min_t(u32, mp->num_planes, VIDEO_MAX_PLANES); + for (i = 0; i < planes; i++) printk(KERN_DEBUG "plane %u: bytesperline=%u sizeimage=%u\n", i, mp->plane_fmt[i].bytesperline, mp->plane_fmt[i].sizeimage); From 836edf22ffd1bd3616683c00677f94e881fa2a20 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 24 Dec 2018 11:05:16 +0200 Subject: [PATCH 066/116] RDMA/nldev: Don't expose unsafe global rkey to regular user commit a9666c1cae8dbcd1a9aacd08a778bf2a28eea300 upstream. Unsafe global rkey is considered dangerous because it exposes memory registered for all memory in the system. Only users with a QP on the same PD can use the rkey, and generally those QPs will already know the value. However, out of caution, do not expose the value to unprivleged users on the local system. Require CAP_NET_ADMIN instead. Cc: # 4.16 Fixes: 29cf1351d450 ("RDMA/nldev: provide detailed PD information") Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/core/nldev.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 0385ab438320..f6fa9b115fda 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -579,10 +579,6 @@ static int fill_res_pd_entry(struct sk_buff *msg, struct netlink_callback *cb, if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_USECNT, atomic_read(&pd->usecnt), RDMA_NLDEV_ATTR_PAD)) goto err; - if ((pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) && - nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY, - pd->unsafe_global_rkey)) - goto err; if (fill_res_name_pid(msg, res)) goto err; From ec485378a4c48c5c08bcc95b3d71233f88db4066 Mon Sep 17 00:00:00 2001 From: Adit Ranadive Date: Wed, 9 Jan 2019 23:08:49 +0000 Subject: [PATCH 067/116] RDMA/vmw_pvrdma: Return the correct opcode when creating WR commit 6325e01b6cdf4636b721cf7259c1616e3cf28ce2 upstream. Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA device opcodes explicitly. Reported-by: Ruishuang Wang Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum") Cc: stable@vger.kernel.org Reviewed-by: Bryan Tan Reviewed-by: Ruishuang Wang Reviewed-by: Vishnu Dasa Signed-off-by: Adit Ranadive Signed-off-by: Jason Gunthorpe Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/vmw_pvrdma/pvrdma.h | 35 +++++++++++++++++++- drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c | 6 ++++ include/uapi/rdma/vmw_pvrdma-abi.h | 1 + 3 files changed, 41 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h index 42b8685c997e..3c633ab58052 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h @@ -427,7 +427,40 @@ static inline enum ib_qp_state pvrdma_qp_state_to_ib(enum pvrdma_qp_state state) static inline enum pvrdma_wr_opcode ib_wr_opcode_to_pvrdma(enum ib_wr_opcode op) { - return (enum pvrdma_wr_opcode)op; + switch (op) { + case IB_WR_RDMA_WRITE: + return PVRDMA_WR_RDMA_WRITE; + case IB_WR_RDMA_WRITE_WITH_IMM: + return PVRDMA_WR_RDMA_WRITE_WITH_IMM; + case IB_WR_SEND: + return PVRDMA_WR_SEND; + case IB_WR_SEND_WITH_IMM: + return PVRDMA_WR_SEND_WITH_IMM; + case IB_WR_RDMA_READ: + return PVRDMA_WR_RDMA_READ; + case IB_WR_ATOMIC_CMP_AND_SWP: + return PVRDMA_WR_ATOMIC_CMP_AND_SWP; + case IB_WR_ATOMIC_FETCH_AND_ADD: + return PVRDMA_WR_ATOMIC_FETCH_AND_ADD; + case IB_WR_LSO: + return PVRDMA_WR_LSO; + case IB_WR_SEND_WITH_INV: + return PVRDMA_WR_SEND_WITH_INV; + case IB_WR_RDMA_READ_WITH_INV: + return PVRDMA_WR_RDMA_READ_WITH_INV; + case IB_WR_LOCAL_INV: + return PVRDMA_WR_LOCAL_INV; + case IB_WR_REG_MR: + return PVRDMA_WR_FAST_REG_MR; + case IB_WR_MASKED_ATOMIC_CMP_AND_SWP: + return PVRDMA_WR_MASKED_ATOMIC_CMP_AND_SWP; + case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD: + return PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD; + case IB_WR_REG_SIG_MR: + return PVRDMA_WR_REG_SIG_MR; + default: + return PVRDMA_WR_ERROR; + } } static inline enum ib_wc_status pvrdma_wc_status_to_ib( diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c index 60083c0363a5..9aeb33093279 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c @@ -721,6 +721,12 @@ int pvrdma_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM) wqe_hdr->ex.imm_data = wr->ex.imm_data; + if (unlikely(wqe_hdr->opcode == PVRDMA_WR_ERROR)) { + *bad_wr = wr; + ret = -EINVAL; + goto out; + } + switch (qp->ibqp.qp_type) { case IB_QPT_GSI: case IB_QPT_UD: diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h index d13fd490b66d..6e73f0274e41 100644 --- a/include/uapi/rdma/vmw_pvrdma-abi.h +++ b/include/uapi/rdma/vmw_pvrdma-abi.h @@ -78,6 +78,7 @@ enum pvrdma_wr_opcode { PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD, PVRDMA_WR_BIND_MW, PVRDMA_WR_REG_SIG_MR, + PVRDMA_WR_ERROR, }; enum pvrdma_wc_status { From 0098f2e791d72bc6407459c856fec14470783fba Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Fri, 11 Jan 2019 19:06:44 +0000 Subject: [PATCH 068/116] kbuild: Disable LD_DEAD_CODE_DATA_ELIMINATION with ftrace & GCC <= 4.7 commit 16fd20aa98080c2fa666dc384036ec08c80af710 upstream. When building using GCC 4.7 or older, -ffunction-sections & the -pg flag used by ftrace are incompatible. This causes warnings or build failures (where -Werror applies) such as the following: arch/mips/generic/init.c: error: -ffunction-sections disabled; it makes profiling impossible This used to be taken into account by the ordering of calls to cc-option from within the top-level Makefile, which was introduced by commit 90ad4052e85c ("kbuild: avoid conflict between -ffunction-sections and -pg on gcc-4.7"). Unfortunately this was broken when the CONFIG_LD_DEAD_CODE_DATA_ELIMINATION cc-option check was moved to Kconfig in commit e85d1d65cd8a ("kbuild: test dead code/data elimination support in Kconfig"), because the flags used by this check no longer include -pg. Fix this by not allowing CONFIG_LD_DEAD_CODE_DATA_ELIMINATION to be enabled at the same time as ftrace/CONFIG_FUNCTION_TRACER when building using GCC 4.7 or older. Signed-off-by: Paul Burton Fixes: e85d1d65cd8a ("kbuild: test dead code/data elimination support in Kconfig") Reported-by: Geert Uytterhoeven Cc: Nicholas Piggin Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Masahiro Yamada Signed-off-by: Greg Kroah-Hartman --- init/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/init/Kconfig b/init/Kconfig index 317d5ccb5191..864af10bb1b9 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1102,6 +1102,7 @@ config LD_DEAD_CODE_DATA_ELIMINATION bool "Dead code and data elimination (EXPERIMENTAL)" depends on HAVE_LD_DEAD_CODE_DATA_ELIMINATION depends on EXPERT + depends on !(FUNCTION_TRACER && CC_IS_GCC && GCC_VERSION < 40800) depends on $(cc-option,-ffunction-sections -fdata-sections) depends on $(ld-option,--gc-sections) help From a10cabbf7a7615ab1d868780f15a64b732ea360e Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 16 Jan 2019 11:27:08 +0100 Subject: [PATCH 069/116] net: dsa: realtek-smi: fix OF child-node lookup commit 3f1bb6abdf19cfa89860b3bc9e7f31b44b6a0ba1 upstream. Use the new of_get_compatible_child() helper to look up child nodes to avoid ever matching non-child nodes elsewhere in the tree. Also fix up the related struct device_node leaks. Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver") Cc: stable # 4.19: 36156f9241cb0 Cc: Linus Walleij Signed-off-by: Johan Hovold Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/dsa/realtek-smi.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/net/dsa/realtek-smi.c b/drivers/net/dsa/realtek-smi.c index b4b839a1d095..ad41ec63cc9f 100644 --- a/drivers/net/dsa/realtek-smi.c +++ b/drivers/net/dsa/realtek-smi.c @@ -347,16 +347,17 @@ int realtek_smi_setup_mdio(struct realtek_smi *smi) struct device_node *mdio_np; int ret; - mdio_np = of_find_compatible_node(smi->dev->of_node, NULL, - "realtek,smi-mdio"); + mdio_np = of_get_compatible_child(smi->dev->of_node, "realtek,smi-mdio"); if (!mdio_np) { dev_err(smi->dev, "no MDIO bus node\n"); return -ENODEV; } smi->slave_mii_bus = devm_mdiobus_alloc(smi->dev); - if (!smi->slave_mii_bus) - return -ENOMEM; + if (!smi->slave_mii_bus) { + ret = -ENOMEM; + goto err_put_node; + } smi->slave_mii_bus->priv = smi; smi->slave_mii_bus->name = "SMI slave MII"; smi->slave_mii_bus->read = realtek_smi_mdio_read; @@ -371,10 +372,15 @@ int realtek_smi_setup_mdio(struct realtek_smi *smi) if (ret) { dev_err(smi->dev, "unable to register MDIO bus %s\n", smi->slave_mii_bus->id); - of_node_put(mdio_np); + goto err_put_node; } return 0; + +err_put_node: + of_node_put(mdio_np); + + return ret; } static int realtek_smi_probe(struct platform_device *pdev) @@ -457,6 +463,8 @@ static int realtek_smi_remove(struct platform_device *pdev) struct realtek_smi *smi = dev_get_drvdata(&pdev->dev); dsa_unregister_switch(smi->ds); + if (smi->slave_mii_bus) + of_node_put(smi->slave_mii_bus->dev.of_node); gpiod_set_value(smi->reset, 1); return 0; From 483ac8e65a8a645d0ba31ab7077ac50debeb4127 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sun, 20 Jan 2019 14:33:34 -0800 Subject: [PATCH 070/116] pstore/ram: Avoid allocation and leak of platform data commit 5631e8576a3caf606cdc375f97425a67983b420c upstream. Yue Hu noticed that when parsing device tree the allocated platform data was never freed. Since it's not used beyond the function scope, this switches to using a stack variable instead. Reported-by: Yue Hu Fixes: 35da60941e44 ("pstore/ram: add Device Tree bindings") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Greg Kroah-Hartman --- fs/pstore/ram.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 03cd59375abe..eb67bb7f04de 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -713,18 +713,15 @@ static int ramoops_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct ramoops_platform_data *pdata = dev->platform_data; + struct ramoops_platform_data pdata_local; struct ramoops_context *cxt = &oops_cxt; size_t dump_mem_sz; phys_addr_t paddr; int err = -EINVAL; if (dev_of_node(dev) && !pdata) { - pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) { - pr_err("cannot allocate platform data buffer\n"); - err = -ENOMEM; - goto fail_out; - } + pdata = &pdata_local; + memset(pdata, 0, sizeof(*pdata)); err = ramoops_parse_dt(pdev, pdata); if (err < 0) From ca8080c308f461080e4af429e41e583ee044b5c4 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 15 Jan 2019 20:47:07 +0100 Subject: [PATCH 071/116] arm64: kaslr: ensure randomized quantities are clean to the PoC commit 1598ecda7b239e9232dda032bfddeed9d89fab6c upstream. kaslr_early_init() is called with the kernel mapped at its link time offset, and if it returns with a non-zero offset, the kernel is unmapped and remapped again at the randomized offset. During its execution, kaslr_early_init() also randomizes the base of the module region and of the linear mapping of DRAM, and sets two variables accordingly. However, since these variables are assigned with the caches on, they may get lost during the cache maintenance that occurs when unmapping and remapping the kernel, so ensure that these values are cleaned to the PoC. Acked-by: Catalin Marinas Fixes: f80fb3a3d508 ("arm64: add support for kernel ASLR") Cc: # v4.6+ Signed-off-by: Ard Biesheuvel Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/kaslr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index f0e6ab8abe9c..ba6b41790fcd 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -14,6 +14,7 @@ #include #include +#include #include #include #include @@ -43,7 +44,7 @@ static __init u64 get_kaslr_seed(void *fdt) return ret; } -static __init const u8 *get_cmdline(void *fdt) +static __init const u8 *kaslr_get_cmdline(void *fdt) { static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE; @@ -109,7 +110,7 @@ u64 __init kaslr_early_init(u64 dt_phys) * Check if 'nokaslr' appears on the command line, and * return 0 if that is the case. */ - cmdline = get_cmdline(fdt); + cmdline = kaslr_get_cmdline(fdt); str = strstr(cmdline, "nokaslr"); if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) return 0; @@ -169,5 +170,8 @@ u64 __init kaslr_early_init(u64 dt_phys) module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21; module_alloc_base &= PAGE_MASK; + __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base)); + __flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed)); + return offset; } From 3832c115bf806baa991c51474a93909a89024525 Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Fri, 21 Dec 2018 17:45:03 +0100 Subject: [PATCH 072/116] arm64: dts: marvell: armada-ap806: reserve PSCI area commit 132ac39cffbcfed80ada38ef0fc6d34d95da7be6 upstream. The memory area [0x4000000-0x4200000[ is occupied by the PSCI firmware. Any attempt to access it from Linux leads to an immediate crash. So let's make the same memory reservation as the vendor kernel. [gregory: added as comment that this region matches the mainline U-boot] Signed-off-by: Heinrich Schuchardt Signed-off-by: Gregory CLEMENT Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/marvell/armada-ap806.dtsi | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi index 176e38d54872..ec0da5b3d7fd 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi @@ -27,6 +27,23 @@ method = "smc"; }; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + /* + * This area matches the mapping done with a + * mainline U-Boot, and should be updated by the + * bootloader. + */ + + psci-area@4000000 { + reg = <0x0 0x4000000 0x0 0x200000>; + no-map; + }; + }; + ap806 { #address-cells = <2>; #size-cells = <2>; From 89a9f049f8b9755d8422c8e6ac6adb6fef437908 Mon Sep 17 00:00:00 2001 From: YunQiang Su Date: Tue, 8 Jan 2019 13:45:10 +0800 Subject: [PATCH 073/116] Disable MSI also when pcie-octeon.pcie_disable on commit a214720cbf50cd8c3f76bbb9c3f5c283910e9d33 upstream. Octeon has an boot-time option to disable pcie. Since MSI depends on PCI-E, we should also disable MSI also with this option is on in order to avoid inadvertently accessing PCIe registers. Signed-off-by: YunQiang Su Signed-off-by: Paul Burton Cc: pburton@wavecomp.com Cc: linux-mips@vger.kernel.org Cc: aaro.koskinen@iki.fi Cc: stable@vger.kernel.org # v3.3+ Signed-off-by: Greg Kroah-Hartman --- arch/mips/pci/msi-octeon.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c index 2a5bb849b10e..288b58b00dc8 100644 --- a/arch/mips/pci/msi-octeon.c +++ b/arch/mips/pci/msi-octeon.c @@ -369,7 +369,9 @@ int __init octeon_msi_initialize(void) int irq; struct irq_chip *msi; - if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) { + if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) { + return 0; + } else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) { msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0; msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1; msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2; From 328f3de2ef766cc27f9a85b20691493642a51417 Mon Sep 17 00:00:00 2001 From: Florian La Roche Date: Sat, 19 Jan 2019 16:14:50 +0100 Subject: [PATCH 074/116] fix int_sqrt64() for very large numbers commit fbfaf851902cd9293f392f3a1735e0543016d530 upstream. If an input number x for int_sqrt64() has the highest bit set, then fls64(x) is 64. (1UL << 64) is an overflow and breaks the algorithm. Subtracting 1 is a better guess for the initial value of m anyway and that's what also done in int_sqrt() implicitly [*]. [*] Note how int_sqrt() uses __fls() with two underscores, which already returns the proper raw bit number. In contrast, int_sqrt64() used fls64(), and that returns bit numbers illogically starting at 1, because of error handling for the "no bits set" case. Will points out that he bug probably is due to a copy-and-paste error from the regular int_sqrt() case. Signed-off-by: Florian La Roche Acked-by: Will Deacon Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- lib/int_sqrt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/int_sqrt.c b/lib/int_sqrt.c index 14436f4ca6bd..30e0f9770f88 100644 --- a/lib/int_sqrt.c +++ b/lib/int_sqrt.c @@ -52,7 +52,7 @@ u32 int_sqrt64(u64 x) if (x <= ULONG_MAX) return int_sqrt((unsigned long) x); - m = 1ULL << (fls64(x) & ~1ULL); + m = 1ULL << ((fls64(x) - 1) & ~1ULL); while (m != 0) { b = y + m; y >>= 1; From 4190c5fd8a7f370513f4215ee617203a7d75cc57 Mon Sep 17 00:00:00 2001 From: Vlad Tsyrklevich Date: Fri, 11 Jan 2019 14:34:38 +0100 Subject: [PATCH 075/116] omap2fb: Fix stack memory disclosure commit a01421e4484327fe44f8e126793ed5a48a221e24 upstream. Using [1] for static analysis I found that the OMAPFB_QUERY_PLANE, OMAPFB_GET_COLOR_KEY, OMAPFB_GET_DISPLAY_INFO, and OMAPFB_GET_VRAM_INFO cases could all leak uninitialized stack memory--either due to uninitialized padding or 'reserved' fields. Fix them by clearing the shared union used to store copied out data. [1] https://github.com/vlad902/kernel-uninitialized-memory-checker Signed-off-by: Vlad Tsyrklevich Reviewed-by: Kees Cook Fixes: b39a982ddecf ("OMAP: DSS2: omapfb driver") Cc: security@kernel.org [b.zolnierkie: prefix patch subject with "omap2fb: "] Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Greg Kroah-Hartman --- drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c index a3edb20ea4c3..a846d32ee653 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c @@ -609,6 +609,8 @@ int omapfb_ioctl(struct fb_info *fbi, unsigned int cmd, unsigned long arg) int r = 0; + memset(&p, 0, sizeof(p)); + switch (cmd) { case OMAPFB_SYNC_GFX: DBG("ioctl SYNC_GFX\n"); From 4497ce43a5d0b8210b289684c2e0c5a887b753a3 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 29 Oct 2018 06:15:31 -0400 Subject: [PATCH 076/116] media: vivid: fix error handling of kthread_run commit 701f49bc028edb19ffccd101997dd84f0d71e279 upstream. kthread_run returns an error pointer, but elsewhere in the code dev->kthread_vid_cap/out is checked against NULL. If kthread_run returns an error, then set the pointer to NULL. I chose this method over changing all kthread_vid_cap/out tests elsewhere since this is more robust. Signed-off-by: Hans Verkuil Reported-by: syzbot+53d5b2df0d9744411e2e@syzkaller.appspotmail.com Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/vivid/vivid-kthread-cap.c | 5 ++++- drivers/media/platform/vivid/vivid-kthread-out.c | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c index f06003bb8e42..2a92e5aac9ed 100644 --- a/drivers/media/platform/vivid/vivid-kthread-cap.c +++ b/drivers/media/platform/vivid/vivid-kthread-cap.c @@ -865,8 +865,11 @@ int vivid_start_generating_vid_cap(struct vivid_dev *dev, bool *pstreaming) "%s-vid-cap", dev->v4l2_dev.name); if (IS_ERR(dev->kthread_vid_cap)) { + int err = PTR_ERR(dev->kthread_vid_cap); + + dev->kthread_vid_cap = NULL; v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n"); - return PTR_ERR(dev->kthread_vid_cap); + return err; } *pstreaming = true; vivid_grab_controls(dev, true); diff --git a/drivers/media/platform/vivid/vivid-kthread-out.c b/drivers/media/platform/vivid/vivid-kthread-out.c index 9981e7548019..488590594150 100644 --- a/drivers/media/platform/vivid/vivid-kthread-out.c +++ b/drivers/media/platform/vivid/vivid-kthread-out.c @@ -236,8 +236,11 @@ int vivid_start_generating_vid_out(struct vivid_dev *dev, bool *pstreaming) "%s-vid-out", dev->v4l2_dev.name); if (IS_ERR(dev->kthread_vid_out)) { + int err = PTR_ERR(dev->kthread_vid_out); + + dev->kthread_vid_out = NULL; v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n"); - return PTR_ERR(dev->kthread_vid_out); + return err; } *pstreaming = true; vivid_grab_controls(dev, true); From d9c249a302cbc3c40218343dc9d342ca49408bb1 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 29 Oct 2018 13:32:38 -0400 Subject: [PATCH 077/116] media: vivid: set min width/height to a value > 0 commit 9729d6d282a6d7ce88e64c9119cecdf79edf4e88 upstream. The capture DV timings capabilities allowed for a minimum width and height of 0. So passing a timings struct with 0 values is allowed and will later cause a division by zero. Ensure that the width and height must be >= 16 to avoid this. Signed-off-by: Hans Verkuil Reported-by: syzbot+57c3d83d71187054d56f@syzkaller.appspotmail.com Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/platform/vivid/vivid-vid-common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/platform/vivid/vivid-vid-common.c b/drivers/media/platform/vivid/vivid-vid-common.c index be531caa2cdf..2079861d2270 100644 --- a/drivers/media/platform/vivid/vivid-vid-common.c +++ b/drivers/media/platform/vivid/vivid-vid-common.c @@ -21,7 +21,7 @@ const struct v4l2_dv_timings_cap vivid_dv_timings_cap = { .type = V4L2_DV_BT_656_1120, /* keep this initialization for compatibility with GCC < 4.4.6 */ .reserved = { 0 }, - V4L2_INIT_BT_TIMINGS(0, MAX_WIDTH, 0, MAX_HEIGHT, 14000000, 775000000, + V4L2_INIT_BT_TIMINGS(16, MAX_WIDTH, 16, MAX_HEIGHT, 14000000, 775000000, V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_CVT | V4L2_DV_BT_STD_GTF, V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_INTERLACED) From 341906cb25f9b8355183518769c14e9ea240aa52 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 15 Jan 2019 20:19:22 -0500 Subject: [PATCH 078/116] bpf: in __bpf_redirect_no_mac pull mac only if present commit e7c87bd6cc4ec7b0ac1ed0a88a58f8206c577488 upstream. Syzkaller was able to construct a packet of negative length by redirecting from bpf_prog_test_run_skb with BPF_PROG_TYPE_LWT_XMIT: BUG: KASAN: slab-out-of-bounds in memcpy include/linux/string.h:345 [inline] BUG: KASAN: slab-out-of-bounds in skb_copy_from_linear_data include/linux/skbuff.h:3421 [inline] BUG: KASAN: slab-out-of-bounds in __pskb_copy_fclone+0x2dd/0xeb0 net/core/skbuff.c:1395 Read of size 4294967282 at addr ffff8801d798009c by task syz-executor2/12942 kasan_report.cold.9+0x242/0x309 mm/kasan/report.c:412 check_memory_region_inline mm/kasan/kasan.c:260 [inline] check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267 memcpy+0x23/0x50 mm/kasan/kasan.c:302 memcpy include/linux/string.h:345 [inline] skb_copy_from_linear_data include/linux/skbuff.h:3421 [inline] __pskb_copy_fclone+0x2dd/0xeb0 net/core/skbuff.c:1395 __pskb_copy include/linux/skbuff.h:1053 [inline] pskb_copy include/linux/skbuff.h:2904 [inline] skb_realloc_headroom+0xe7/0x120 net/core/skbuff.c:1539 ipip6_tunnel_xmit net/ipv6/sit.c:965 [inline] sit_tunnel_xmit+0xe1b/0x30d0 net/ipv6/sit.c:1029 __netdev_start_xmit include/linux/netdevice.h:4325 [inline] netdev_start_xmit include/linux/netdevice.h:4334 [inline] xmit_one net/core/dev.c:3219 [inline] dev_hard_start_xmit+0x295/0xc90 net/core/dev.c:3235 __dev_queue_xmit+0x2f0d/0x3950 net/core/dev.c:3805 dev_queue_xmit+0x17/0x20 net/core/dev.c:3838 __bpf_tx_skb net/core/filter.c:2016 [inline] __bpf_redirect_common net/core/filter.c:2054 [inline] __bpf_redirect+0x5cf/0xb20 net/core/filter.c:2061 ____bpf_clone_redirect net/core/filter.c:2094 [inline] bpf_clone_redirect+0x2f6/0x490 net/core/filter.c:2066 bpf_prog_41f2bcae09cd4ac3+0xb25/0x1000 The generated test constructs a packet with mac header, network header, skb->data pointing to network header and skb->len 0. Redirecting to a sit0 through __bpf_redirect_no_mac pulls the mac length, even though skb->data already is at skb->network_header. bpf_prog_test_run_skb has already pulled it as LWT_XMIT !is_l2. Update the offset calculation to pull only if skb->data differs from skb->network_header, which is not true in this case. The test itself can be run only from commit 1cf1cae963c2 ("bpf: introduce BPF_PROG_TEST_RUN command"), but the same type of packets with skb at network header could already be built from lwt xmit hooks, so this fix is more relevant to that commit. Also set the mac header on redirect from LWT_XMIT, as even after this change to __bpf_redirect_no_mac that field is expected to be set, but is not yet in ip_finish_output2. Fixes: 3a0af8fd61f9 ("bpf: BPF for lightweight tunnel infrastructure") Reported-by: syzbot Signed-off-by: Willem de Bruijn Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Signed-off-by: Greg Kroah-Hartman --- net/core/filter.c | 21 +++++++++++---------- net/core/lwt_bpf.c | 1 + 2 files changed, 12 insertions(+), 10 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 5e00f2b85a56..8c2411fb2509 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2018,18 +2018,19 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, u32 flags) { - /* skb->mac_len is not set on normal egress */ - unsigned int mlen = skb->network_header - skb->mac_header; + unsigned int mlen = skb_network_offset(skb); - __skb_pull(skb, mlen); + if (mlen) { + __skb_pull(skb, mlen); - /* At ingress, the mac header has already been pulled once. - * At egress, skb_pospull_rcsum has to be done in case that - * the skb is originated from ingress (i.e. a forwarded skb) - * to ensure that rcsum starts at net header. - */ - if (!skb_at_tc_ingress(skb)) - skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); + /* At ingress, the mac header has already been pulled once. + * At egress, skb_pospull_rcsum has to be done in case that + * the skb is originated from ingress (i.e. a forwarded skb) + * to ensure that rcsum starts at net header. + */ + if (!skb_at_tc_ingress(skb)) + skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); + } skb_pop_mac_header(skb); skb_reset_mac_len(skb); return flags & BPF_F_INGRESS ? diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 3e85437f7106..a648568c5e8f 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -63,6 +63,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, lwt->name ? : ""); ret = BPF_OK; } else { + skb_reset_mac_header(skb); ret = skb_do_redirect(skb); if (ret == 0) ret = BPF_REDIRECT; From a72e572f8a2d61db2f4d17e1de17fb92573870ef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Jan 2019 11:00:00 -0800 Subject: [PATCH 079/116] ipv6: make icmp6_send() robust against null skb->dev commit 8d933670452107e41165bea70a30dffbd281bef1 upstream. syzbot was able to crash one host with the following stack trace : kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 8625 Comm: syz-executor4 Not tainted 4.20.0+ #8 RIP: 0010:dev_net include/linux/netdevice.h:2169 [inline] RIP: 0010:icmp6_send+0x116/0x2d30 net/ipv6/icmp.c:426 icmpv6_send smack_socket_sock_rcv_skb security_sock_rcv_skb sk_filter_trim_cap __sk_receive_skb dccp_v6_do_rcv release_sock This is because a RX packet found socket owned by user and was stored into socket backlog. Before leaving RCU protected section, skb->dev was cleared in __sk_receive_skb(). When socket backlog was finally handled at release_sock() time, skb was fed to smack_socket_sock_rcv_skb() then icmp6_send() We could fix the bug in smack_socket_sock_rcv_skb(), or simply make icmp6_send() more robust against such possibility. In the future we might provide to icmp6_send() the net pointer instead of infering it. Fixes: d66a8acbda92 ("Smack: Inform peer that IPv6 traffic has been blocked") Signed-off-by: Eric Dumazet Cc: Piotr Sawicki Cc: Casey Schaufler Reported-by: syzbot Acked-by: Casey Schaufler Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/icmp.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index c9c53ade55c3..6d14cbe443f8 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -421,10 +421,10 @@ static int icmp6_iif(const struct sk_buff *skb) static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr) { - struct net *net = dev_net(skb->dev); struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; + struct net *net; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; struct dst_entry *dst; @@ -435,12 +435,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - u32 mark = IP6_REPLY_MARK(net, skb->mark); + u32 mark; if ((u8 *)hdr < skb->head || (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; + if (!skb->dev) + return; + net = dev_net(skb->dev); + mark = IP6_REPLY_MARK(net, skb->mark); /* * Make sure we respect the rules * i.e. RFC 1885 2.4(e) From a19aedf1a77c2e426c9810aece80646283cc2808 Mon Sep 17 00:00:00 2001 From: James Morris Date: Wed, 16 Jan 2019 15:41:11 -0800 Subject: [PATCH 080/116] LSM: Check for NULL cred-security on free commit a5795fd38ee8194451ba3f281f075301a3696ce2 upstream. From: Casey Schaufler Check that the cred security blob has been set before trying to clean it up. There is a case during credential initialization that could result in this. Signed-off-by: Casey Schaufler Acked-by: John Johansen Signed-off-by: James Morris Reported-by: syzbot+69ca07954461f189e808@syzkaller.appspotmail.com Signed-off-by: Greg Kroah-Hartman --- security/security.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/security/security.c b/security/security.c index 736e78da1ab9..5ce2448f3a45 100644 --- a/security/security.c +++ b/security/security.c @@ -1003,6 +1003,13 @@ int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) void security_cred_free(struct cred *cred) { + /* + * There is a failure case in prepare_creds() that + * may result in a call here with ->security being NULL. + */ + if (unlikely(cred->security == NULL)) + return; + call_void_hook(cred_free, cred); } From c4f39cba6fd08def0a4491f57566582823751568 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 13 Nov 2018 09:06:46 -0500 Subject: [PATCH 081/116] media: vb2: vb2_mmap: move lock up commit cd26d1c4d1bc947b56ae404998ae2276df7b39b7 upstream. If a filehandle is dup()ped, then it is possible to close it from one fd and call mmap from the other. This creates a race condition in vb2_mmap where it is using queue data that __vb2_queue_free (called from close()) is in the process of releasing. By moving up the mutex_lock(mmap_lock) in vb2_mmap this race is avoided since __vb2_queue_free is called with the same mutex locked. So vb2_mmap now reads consistent buffer data. Signed-off-by: Hans Verkuil Reported-by: syzbot+be93025dd45dccd8923c@syzkaller.appspotmail.com Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/common/videobuf2/videobuf2-core.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 1faa64abc74f..07629e7c15be 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -1933,9 +1933,13 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) return -EINVAL; } } + + mutex_lock(&q->mmap_lock); + if (vb2_fileio_is_active(q)) { dprintk(1, "mmap: file io in progress\n"); - return -EBUSY; + ret = -EBUSY; + goto unlock; } /* @@ -1943,7 +1947,7 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) - return ret; + goto unlock; vb = q->bufs[buffer]; @@ -1959,8 +1963,9 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) return -EINVAL; } - mutex_lock(&q->mmap_lock); ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma); + +unlock: mutex_unlock(&q->mmap_lock); if (ret) return ret; From 61b29bed90103d1a0fc052fb15027c33cee551f8 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 20 Dec 2018 10:35:11 -0500 Subject: [PATCH 082/116] sunrpc: handle ENOMEM in rpcb_getport_async commit 81c88b18de1f11f70c97f28ced8d642c00bb3955 upstream. If we ignore the error we'll hit a null dereference a little later. Reported-by: syzbot+4b98281f2401ab849f4b@syzkaller.appspotmail.com Signed-off-by: J. Bruce Fields Signed-off-by: Anna Schumaker Signed-off-by: Greg Kroah-Hartman --- net/sunrpc/rpcb_clnt.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index c7872bc13860..08b5fa4a2852 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -771,6 +771,12 @@ void rpcb_getport_async(struct rpc_task *task) case RPCBVERS_3: map->r_netid = xprt->address_strings[RPC_DISPLAY_NETID]; map->r_addr = rpc_sockaddr2uaddr(sap, GFP_ATOMIC); + if (!map->r_addr) { + status = -ENOMEM; + dprintk("RPC: %5u %s: no memory available\n", + task->tk_pid, __func__); + goto bailout_free_args; + } map->r_owner = ""; break; case RPCBVERS_2: @@ -793,6 +799,8 @@ void rpcb_getport_async(struct rpc_task *task) rpc_put_task(child); return; +bailout_free_args: + kfree(map); bailout_release_client: rpc_release_client(rpcb_clnt); bailout_nofree: From 2663bcba075f4faec98aee7b24bf11aa748316b3 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 2 Jan 2019 19:14:31 -0800 Subject: [PATCH 083/116] netfilter: ebtables: account ebt_table_info to kmemcg commit e2c8d550a973bb34fc28bc8d0ec996f84562fb8a upstream. The [ip,ip6,arp]_tables use x_tables_info internally and the underlying memory is already accounted to kmemcg. Do the same for ebtables. The syzbot, by using setsockopt(EBT_SO_SET_ENTRIES), was able to OOM the whole system from a restricted memcg, a potential DoS. By accounting the ebt_table_info, the memory used for ebt_table_info can be contained within the memcg of the allocating process. However the lifetime of ebt_table_info is independent of the allocating process and is tied to the network namespace. So, the oom-killer will not be able to relieve the memory pressure due to ebt_table_info memory. The memory for ebt_table_info is allocated through vmalloc. Currently vmalloc does not handle the oom-killed allocating process correctly and one large allocation can bypass memcg limit enforcement. So, with this patch, at least the small allocations will be contained. For large allocations, we need to fix vmalloc. Reported-by: syzbot+7713f3aa67be76b1552c@syzkaller.appspotmail.com Signed-off-by: Shakeel Butt Reviewed-by: Kirill Tkhai Signed-off-by: Pablo Neira Ayuso Signed-off-by: Greg Kroah-Hartman --- net/bridge/netfilter/ebtables.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 491828713e0b..5e55cef0cec3 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1137,14 +1137,16 @@ static int do_replace(struct net *net, const void __user *user, tmp.name[sizeof(tmp.name) - 1] = 0; countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; - newinfo = vmalloc(sizeof(*newinfo) + countersize); + newinfo = __vmalloc(sizeof(*newinfo) + countersize, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo) return -ENOMEM; if (countersize) memset(newinfo->counters, 0, countersize); - newinfo->entries = vmalloc(tmp.entries_size); + newinfo->entries = __vmalloc(tmp.entries_size, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo->entries) { ret = -ENOMEM; goto free_newinfo; From 4cc66cc4f81fb8b1d6e83548fa79005dcc93ee2a Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Wed, 28 Nov 2018 16:42:01 +0800 Subject: [PATCH 084/116] block: use rcu_work instead of call_rcu to avoid sleep in softirq commit 94a2c3a32b62e868dc1e3d854326745a7f1b8c7a upstream. We recently got a stack by syzkaller like this: BUG: sleeping function called from invalid context at mm/slab.h:361 in_atomic(): 1, irqs_disabled(): 0, pid: 6644, name: blkid INFO: lockdep is turned off. CPU: 1 PID: 6644 Comm: blkid Not tainted 4.4.163-514.55.6.9.x86_64+ #76 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 0000000000000000 5ba6a6b879e50c00 ffff8801f6b07b10 ffffffff81cb2194 0000000041b58ab3 ffffffff833c7745 ffffffff81cb2080 5ba6a6b879e50c00 0000000000000000 0000000000000001 0000000000000004 0000000000000000 Call Trace: [] __dump_stack lib/dump_stack.c:15 [inline] [] dump_stack+0x114/0x1a0 lib/dump_stack.c:51 [] ___might_sleep+0x291/0x490 kernel/sched/core.c:7675 [] __might_sleep+0xb3/0x270 kernel/sched/core.c:7637 [] slab_pre_alloc_hook mm/slab.h:361 [inline] [] slab_alloc_node mm/slub.c:2610 [inline] [] slab_alloc mm/slub.c:2692 [inline] [] kmem_cache_alloc_trace+0x2c3/0x5c0 mm/slub.c:2709 [] kmalloc include/linux/slab.h:479 [inline] [] kzalloc include/linux/slab.h:623 [inline] [] kobject_uevent_env+0x2c7/0x1150 lib/kobject_uevent.c:227 [] kobject_uevent+0x1f/0x30 lib/kobject_uevent.c:374 [] kobject_cleanup lib/kobject.c:633 [inline] [] kobject_release+0x229/0x440 lib/kobject.c:675 [] kref_sub include/linux/kref.h:73 [inline] [] kref_put include/linux/kref.h:98 [inline] [] kobject_put+0x72/0xd0 lib/kobject.c:692 [] put_device+0x25/0x30 drivers/base/core.c:1237 [] delete_partition_rcu_cb+0x1d4/0x2f0 block/partition-generic.c:232 [] __rcu_reclaim kernel/rcu/rcu.h:118 [inline] [] rcu_do_batch kernel/rcu/tree.c:2705 [inline] [] invoke_rcu_callbacks kernel/rcu/tree.c:2973 [inline] [] __rcu_process_callbacks kernel/rcu/tree.c:2940 [inline] [] rcu_process_callbacks+0x59c/0x1c70 kernel/rcu/tree.c:2957 [] __do_softirq+0x299/0xe20 kernel/softirq.c:273 [] invoke_softirq kernel/softirq.c:350 [inline] [] irq_exit+0x216/0x2c0 kernel/softirq.c:391 [] exiting_irq arch/x86/include/asm/apic.h:652 [inline] [] smp_apic_timer_interrupt+0x8b/0xc0 arch/x86/kernel/apic/apic.c:926 [] apic_timer_interrupt+0xa5/0xb0 arch/x86/entry/entry_64.S:746 [] ? audit_kill_trees+0x180/0x180 [] fd_install+0x57/0x80 fs/file.c:626 [] do_sys_open+0x45e/0x550 fs/open.c:1043 [] SYSC_open fs/open.c:1055 [inline] [] SyS_open+0x32/0x40 fs/open.c:1050 [] entry_SYSCALL_64_fastpath+0x1e/0x9a In softirq context, we call rcu callback function delete_partition_rcu_cb(), which may allocate memory by kzalloc with GFP_KERNEL flag. If the allocation cannot be satisfied, it may sleep. However, That is not allowed in softirq contex. Although we found this problem on linux 4.4, the latest kernel version seems to have this problem as well. And it is very similar to the previous one: https://lkml.org/lkml/2018/7/9/391 Fix it by using RCU workqueue, which allows sleep. Reviewed-by: Paul E. McKenney Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- block/partition-generic.c | 8 +++++--- include/linux/genhd.h | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/block/partition-generic.c b/block/partition-generic.c index d3d14e81fb12..5f8db5c5140f 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -249,9 +249,10 @@ struct device_type part_type = { .uevent = part_uevent, }; -static void delete_partition_rcu_cb(struct rcu_head *head) +static void delete_partition_work_fn(struct work_struct *work) { - struct hd_struct *part = container_of(head, struct hd_struct, rcu_head); + struct hd_struct *part = container_of(to_rcu_work(work), struct hd_struct, + rcu_work); part->start_sect = 0; part->nr_sects = 0; @@ -262,7 +263,8 @@ static void delete_partition_rcu_cb(struct rcu_head *head) void __delete_partition(struct percpu_ref *ref) { struct hd_struct *part = container_of(ref, struct hd_struct, ref); - call_rcu(&part->rcu_head, delete_partition_rcu_cb); + INIT_RCU_WORK(&part->rcu_work, delete_partition_work_fn); + queue_rcu_work(system_wq, &part->rcu_work); } /* diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 25c08c6c7f99..f767293b00e6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -129,7 +129,7 @@ struct hd_struct { struct disk_stats dkstats; #endif struct percpu_ref ref; - struct rcu_head rcu_head; + struct rcu_work rcu_work; }; #define GENHD_FL_REMOVABLE 1 From 5a79e71e0bc85045606a34641170c560362d8c84 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Wed, 9 Jan 2019 10:55:10 -0500 Subject: [PATCH 085/116] selinux: fix GPF on invalid policy commit 5b0e7310a2a33c06edc7eb81ffc521af9b2c5610 upstream. levdatum->level can be NULL if we encounter an error while loading the policy during sens_read prior to initializing it. Make sure sens_destroy handles that case correctly. Reported-by: syzbot+6664500f0f18f07a5c0e@syzkaller.appspotmail.com Signed-off-by: Stephen Smalley Signed-off-by: Paul Moore Signed-off-by: Greg Kroah-Hartman --- security/selinux/ss/policydb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index b63ef865ce1e..d31a52e56b9e 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -732,7 +732,8 @@ static int sens_destroy(void *key, void *datum, void *p) kfree(key); if (datum) { levdatum = datum; - ebitmap_destroy(&levdatum->level->cat); + if (levdatum->level) + ebitmap_destroy(&levdatum->level->cat); kfree(levdatum->level); } kfree(datum); From 1e11b1d630f8fdbca3843259e581fdec0941dc03 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 14 Jan 2019 09:48:10 +0100 Subject: [PATCH 086/116] blockdev: Fix livelocks on loop device commit 04906b2f542c23626b0ef6219b808406f8dddbe9 upstream. bd_set_size() updates also block device's block size. This is somewhat unexpected from its name and at this point, only blkdev_open() uses this functionality. Furthermore, this can result in changing block size under a filesystem mounted on a loop device which leads to livelocks inside __getblk_gfp() like: Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 10863 Comm: syz-executor0 Not tainted 4.18.0-rc5+ #151 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__sanitizer_cov_trace_pc+0x3f/0x50 kernel/kcov.c:106 ... Call Trace: init_page_buffers+0x3e2/0x530 fs/buffer.c:904 grow_dev_page fs/buffer.c:947 [inline] grow_buffers fs/buffer.c:1009 [inline] __getblk_slow fs/buffer.c:1036 [inline] __getblk_gfp+0x906/0xb10 fs/buffer.c:1313 __bread_gfp+0x2d/0x310 fs/buffer.c:1347 sb_bread include/linux/buffer_head.h:307 [inline] fat12_ent_bread+0x14e/0x3d0 fs/fat/fatent.c:75 fat_ent_read_block fs/fat/fatent.c:441 [inline] fat_alloc_clusters+0x8ce/0x16e0 fs/fat/fatent.c:489 fat_add_cluster+0x7a/0x150 fs/fat/inode.c:101 __fat_get_block fs/fat/inode.c:148 [inline] ... Trivial reproducer for the problem looks like: truncate -s 1G /tmp/image losetup /dev/loop0 /tmp/image mkfs.ext4 -b 1024 /dev/loop0 mount -t ext4 /dev/loop0 /mnt losetup -c /dev/loop0 l /mnt Fix the problem by moving initialization of a block device block size into a separate function and call it when needed. Thanks to Tetsuo Handa for help with debugging the problem. Reported-by: syzbot+9933e4476f365f5d5a1b@syzkaller.appspotmail.com Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- fs/block_dev.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 38b8ce05cbc7..cdbb888a8d4a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -104,6 +104,20 @@ void invalidate_bdev(struct block_device *bdev) } EXPORT_SYMBOL(invalidate_bdev); +static void set_init_blocksize(struct block_device *bdev) +{ + unsigned bsize = bdev_logical_block_size(bdev); + loff_t size = i_size_read(bdev->bd_inode); + + while (bsize < PAGE_SIZE) { + if (size & bsize) + break; + bsize <<= 1; + } + bdev->bd_block_size = bsize; + bdev->bd_inode->i_blkbits = blksize_bits(bsize); +} + int set_blocksize(struct block_device *bdev, int size) { /* Size must be a power of two, and between 512 and PAGE_SIZE */ @@ -1408,18 +1422,9 @@ EXPORT_SYMBOL(check_disk_change); void bd_set_size(struct block_device *bdev, loff_t size) { - unsigned bsize = bdev_logical_block_size(bdev); - inode_lock(bdev->bd_inode); i_size_write(bdev->bd_inode, size); inode_unlock(bdev->bd_inode); - while (bsize < PAGE_SIZE) { - if (size & bsize) - break; - bsize <<= 1; - } - bdev->bd_block_size = bsize; - bdev->bd_inode->i_blkbits = blksize_bits(bsize); } EXPORT_SYMBOL(bd_set_size); @@ -1496,8 +1501,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret) + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); + set_init_blocksize(bdev); + } /* * If the device is invalidated, rescan partition @@ -1532,6 +1539,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); + set_init_blocksize(bdev); } if (bdev->bd_bdi == &noop_backing_dev_info) From 7f902f7c146c7f293118767d99144de1b3ad00ed Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 14 Jan 2019 18:34:02 +0800 Subject: [PATCH 087/116] sctp: allocate sctp_sockaddr_entry with kzalloc commit 400b8b9a2a17918f8ce00786f596f530e7f30d50 upstream. The similar issue as fixed in Commit 4a2eb0c37b47 ("sctp: initialize sin6_flowinfo for ipv6 addrs in sctp_inet6addr_event") also exists in sctp_inetaddr_event, as Alexander noticed. To fix it, allocate sctp_sockaddr_entry with kzalloc for both sctp ipv4 and ipv6 addresses, as does in sctp_v4/6_copy_addrlist(). Reported-by: Alexander Potapenko Signed-off-by: Xin Long Reported-by: syzbot+ae0c70c0c2d40c51bb92@syzkaller.appspotmail.com Acked-by: Marcelo Ricardo Leitner Acked-by: Neil Horman Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/sctp/ipv6.c | 5 +---- net/sctp/protocol.c | 4 +--- 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 7f0539db5604..0bae07e9c9e7 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -97,11 +97,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, switch (ev) { case NETDEV_UP: - addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); + addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v6.sin6_family = AF_INET6; - addr->a.v6.sin6_port = 0; - addr->a.v6.sin6_flowinfo = 0; addr->a.v6.sin6_addr = ifa->addr; addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex; addr->valid = 1; @@ -431,7 +429,6 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v6.sin6_family = AF_INET6; - addr->a.v6.sin6_port = 0; addr->a.v6.sin6_addr = ifp->addr; addr->a.v6.sin6_scope_id = dev->ifindex; addr->valid = 1; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e948db29ab53..d4352111e69d 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -101,7 +101,6 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist, addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; - addr->a.v4.sin_port = 0; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; addr->valid = 1; INIT_LIST_HEAD(&addr->list); @@ -776,10 +775,9 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, switch (ev) { case NETDEV_UP: - addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); + addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; - addr->a.v4.sin_port = 0; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; addr->valid = 1; spin_lock_bh(&net->sctp.local_addr_lock); From 9277333652145159098d44a05bb67e9b9cbdfb12 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 14 Jan 2019 17:22:24 +0800 Subject: [PATCH 088/116] tipc: fix uninit-value in in tipc_conn_rcv_sub commit a88289f4ddee4165d5f796bd99e09eec3133c16b upstream. syzbot reported: BUG: KMSAN: uninit-value in tipc_conn_rcv_sub+0x184/0x950 net/tipc/topsrv.c:373 CPU: 0 PID: 66 Comm: kworker/u4:4 Not tainted 4.17.0-rc3+ #88 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: tipc_rcv tipc_conn_recv_work Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:113 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:683 tipc_conn_rcv_sub+0x184/0x950 net/tipc/topsrv.c:373 tipc_conn_rcv_from_sock net/tipc/topsrv.c:409 [inline] tipc_conn_recv_work+0x3cd/0x560 net/tipc/topsrv.c:424 process_one_work+0x12c6/0x1f60 kernel/workqueue.c:2145 worker_thread+0x113c/0x24f0 kernel/workqueue.c:2279 kthread+0x539/0x720 kernel/kthread.c:239 ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:412 Local variable description: ----s.i@tipc_conn_recv_work Variable was created at: tipc_conn_recv_work+0x65/0x560 net/tipc/topsrv.c:419 process_one_work+0x12c6/0x1f60 kernel/workqueue.c:2145 In tipc_conn_rcv_from_sock(), it always supposes the length of message received from sock_recvmsg() is not smaller than the size of struct tipc_subscr. However, this assumption is false. Especially when the length of received message is shorter than struct tipc_subscr size, we will end up touching uninitialized fields in tipc_conn_rcv_sub(). Reported-by: syzbot+8951a3065ee7fd6d6e23@syzkaller.appspotmail.com Reported-by: syzbot+75e6e042c5bbf691fc82@syzkaller.appspotmail.com Signed-off-by: Ying Xue Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tipc/topsrv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index b84c0059214f..d65eed88c495 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -404,7 +404,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); if (ret == -EWOULDBLOCK) return -EWOULDBLOCK; - if (ret > 0) { + if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); From 1d61caf05721bbf570efaef3dcd3fbf61c724c7f Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 14 Jan 2019 17:22:25 +0800 Subject: [PATCH 089/116] tipc: fix uninit-value in tipc_nl_compat_link_reset_stats commit 8b66fee7f8ee18f9c51260e7a43ab37db5177a05 upstream. syzbot reports following splat: BUG: KMSAN: uninit-value in strlen+0x3b/0xa0 lib/string.c:486 CPU: 1 PID: 11057 Comm: syz-executor0 Not tainted 4.20.0-rc7+ #2 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:295 strlen+0x3b/0xa0 lib/string.c:486 nla_put_string include/net/netlink.h:1154 [inline] tipc_nl_compat_link_reset_stats+0x1f0/0x360 net/tipc/netlink_compat.c:760 __tipc_nl_compat_doit net/tipc/netlink_compat.c:311 [inline] tipc_nl_compat_doit+0x3aa/0xaf0 net/tipc/netlink_compat.c:344 tipc_nl_compat_handle net/tipc/netlink_compat.c:1107 [inline] tipc_nl_compat_recv+0x14d7/0x2760 net/tipc/netlink_compat.c:1210 genl_family_rcv_msg net/netlink/genetlink.c:601 [inline] genl_rcv_msg+0x185f/0x1a60 net/netlink/genetlink.c:626 netlink_rcv_skb+0x444/0x640 net/netlink/af_netlink.c:2477 genl_rcv+0x63/0x80 net/netlink/genetlink.c:637 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0xf40/0x1020 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x127f/0x1300 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x305/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x457ec9 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f2557338c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000457ec9 RDX: 0000000000000000 RSI: 00000000200001c0 RDI: 0000000000000003 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f25573396d4 R13: 00000000004cb478 R14: 00000000004d86c8 R15: 00000000ffffffff Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:204 [inline] kmsan_internal_poison_shadow+0x92/0x150 mm/kmsan/kmsan.c:158 kmsan_kmalloc+0xa6/0x130 mm/kmsan/kmsan_hooks.c:176 kmsan_slab_alloc+0xe/0x10 mm/kmsan/kmsan_hooks.c:185 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2759 [inline] __kmalloc_node_track_caller+0xe18/0x1030 mm/slub.c:4383 __kmalloc_reserve net/core/skbuff.c:137 [inline] __alloc_skb+0x309/0xa20 net/core/skbuff.c:205 alloc_skb include/linux/skbuff.h:998 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1182 [inline] netlink_sendmsg+0xb82/0x1300 net/netlink/af_netlink.c:1892 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x305/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 The uninitialised access happened in tipc_nl_compat_link_reset_stats: nla_put_string(skb, TIPC_NLA_LINK_NAME, name) This is because name string is not validated before it's used. Reported-by: syzbot+e01d94b5a4c266be6e4c@syzkaller.appspotmail.com Signed-off-by: Ying Xue Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tipc/netlink_compat.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 6376467e78f8..3c11d629eb92 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -87,6 +87,11 @@ static int tipc_skb_tailroom(struct sk_buff *skb) return limit; } +static inline int TLV_GET_DATA_LEN(struct tlv_desc *tlv) +{ + return TLV_GET_LEN(tlv) - TLV_SPACE(0); +} + static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len) { struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb); @@ -166,6 +171,11 @@ static struct sk_buff *tipc_get_err_tlv(char *str) return buf; } +static inline bool string_is_valid(char *s, int len) +{ + return memchr(s, '\0', len) ? true : false; +} + static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg, struct sk_buff *arg) @@ -750,6 +760,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, { char *name; struct nlattr *link; + int len; name = (char *)TLV_DATA(msg->req); @@ -757,6 +768,10 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, if (!link) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name)) return -EMSGSIZE; From 7960fb71aad9c346685ae2fc91e9b08b17cf2969 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 14 Jan 2019 17:22:26 +0800 Subject: [PATCH 090/116] tipc: fix uninit-value in tipc_nl_compat_bearer_enable commit 0762216c0ad2a2fccd63890648eca491f2c83d9a upstream. syzbot reported: BUG: KMSAN: uninit-value in strlen+0x3b/0xa0 lib/string.c:484 CPU: 1 PID: 6371 Comm: syz-executor652 Not tainted 4.19.0-rc8+ #70 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x306/0x460 lib/dump_stack.c:113 kmsan_report+0x1a2/0x2e0 mm/kmsan/kmsan.c:917 __msan_warning+0x7c/0xe0 mm/kmsan/kmsan_instr.c:500 strlen+0x3b/0xa0 lib/string.c:484 nla_put_string include/net/netlink.h:1011 [inline] tipc_nl_compat_bearer_enable+0x238/0x7b0 net/tipc/netlink_compat.c:389 __tipc_nl_compat_doit net/tipc/netlink_compat.c:311 [inline] tipc_nl_compat_doit+0x39f/0xae0 net/tipc/netlink_compat.c:344 tipc_nl_compat_recv+0x147c/0x2760 net/tipc/netlink_compat.c:1107 genl_family_rcv_msg net/netlink/genetlink.c:601 [inline] genl_rcv_msg+0x185c/0x1a20 net/netlink/genetlink.c:626 netlink_rcv_skb+0x394/0x640 net/netlink/af_netlink.c:2454 genl_rcv+0x63/0x80 net/netlink/genetlink.c:637 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x166d/0x1720 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x1391/0x1420 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xe47/0x1200 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x307/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbe/0x100 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x440179 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fffef7beee8 EFLAGS: 00000213 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000440179 RDX: 0000000000000000 RSI: 0000000020000100 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000000 R09: 00000000004002c8 R10: 0000000000000000 R11: 0000000000000213 R12: 0000000000401a00 R13: 0000000000401a90 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:255 [inline] kmsan_internal_poison_shadow+0xc8/0x1d0 mm/kmsan/kmsan.c:180 kmsan_kmalloc+0xa4/0x120 mm/kmsan/kmsan_hooks.c:104 kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan_hooks.c:113 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2727 [inline] __kmalloc_node_track_caller+0xb43/0x1400 mm/slub.c:4360 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x422/0xe90 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:996 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1189 [inline] netlink_sendmsg+0xcaf/0x1420 net/netlink/af_netlink.c:1883 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xe47/0x1200 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x307/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbe/0x100 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 The root cause is that we don't validate whether bear name is a valid string in tipc_nl_compat_bearer_enable(). Meanwhile, we also fix the same issue in the following functions: tipc_nl_compat_bearer_disable() tipc_nl_compat_link_stat_dump() tipc_nl_compat_media_set() tipc_nl_compat_bearer_set() Reported-by: syzbot+b33d5cae0efd35dbfe77@syzkaller.appspotmail.com Signed-off-by: Ying Xue Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tipc/netlink_compat.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 3c11d629eb92..0965ca208900 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -389,6 +389,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, struct nlattr *prop; struct nlattr *bearer; struct tipc_bearer_config *b; + int len; b = (struct tipc_bearer_config *)TLV_DATA(msg->req); @@ -396,6 +397,10 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); + if (!string_is_valid(b->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name)) return -EMSGSIZE; @@ -421,6 +426,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, { char *name; struct nlattr *bearer; + int len; name = (char *)TLV_DATA(msg->req); @@ -428,6 +434,10 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name)) return -EMSGSIZE; @@ -488,6 +498,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, struct nlattr *prop[TIPC_NLA_PROP_MAX + 1]; struct nlattr *stats[TIPC_NLA_STATS_MAX + 1]; int err; + int len; if (!attrs[TIPC_NLA_LINK]) return -EINVAL; @@ -514,6 +525,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, return err; name = (char *)TLV_DATA(msg->req); + + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0) return 0; @@ -654,6 +670,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, struct nlattr *prop; struct nlattr *media; struct tipc_link_config *lc; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); @@ -661,6 +678,10 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, if (!media) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name)) return -EMSGSIZE; @@ -681,6 +702,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, struct nlattr *prop; struct nlattr *bearer; struct tipc_link_config *lc; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); @@ -688,6 +710,10 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, if (!bearer) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name)) return -EMSGSIZE; From 04d87429738a20e6443fdbaa25b97d79cc7dc0ce Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 14 Jan 2019 17:22:27 +0800 Subject: [PATCH 091/116] tipc: fix uninit-value in tipc_nl_compat_link_set commit edf5ff04a45750ac8ce2435974f001dc9cfbf055 upstream. syzbot reports following splat: BUG: KMSAN: uninit-value in strlen+0x3b/0xa0 lib/string.c:486 CPU: 1 PID: 9306 Comm: syz-executor172 Not tainted 4.20.0-rc7+ #2 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x173/0x1d0 lib/dump_stack.c:113 kmsan_report+0x12e/0x2a0 mm/kmsan/kmsan.c:613 __msan_warning+0x82/0xf0 mm/kmsan/kmsan_instr.c:313 strlen+0x3b/0xa0 lib/string.c:486 nla_put_string include/net/netlink.h:1154 [inline] __tipc_nl_compat_link_set net/tipc/netlink_compat.c:708 [inline] tipc_nl_compat_link_set+0x929/0x1220 net/tipc/netlink_compat.c:744 __tipc_nl_compat_doit net/tipc/netlink_compat.c:311 [inline] tipc_nl_compat_doit+0x3aa/0xaf0 net/tipc/netlink_compat.c:344 tipc_nl_compat_handle net/tipc/netlink_compat.c:1107 [inline] tipc_nl_compat_recv+0x14d7/0x2760 net/tipc/netlink_compat.c:1210 genl_family_rcv_msg net/netlink/genetlink.c:601 [inline] genl_rcv_msg+0x185f/0x1a60 net/netlink/genetlink.c:626 netlink_rcv_skb+0x444/0x640 net/netlink/af_netlink.c:2477 genl_rcv+0x63/0x80 net/netlink/genetlink.c:637 netlink_unicast_kernel net/netlink/af_netlink.c:1310 [inline] netlink_unicast+0xf40/0x1020 net/netlink/af_netlink.c:1336 netlink_sendmsg+0x127f/0x1300 net/netlink/af_netlink.c:1917 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xdb9/0x11b0 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x305/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 The uninitialised access happened in nla_put_string(skb, TIPC_NLA_LINK_NAME, lc->name) This is because lc->name string is not validated before it's used. Reported-by: syzbot+d78b8a29241a195aefb8@syzkaller.appspotmail.com Signed-off-by: Ying Xue Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tipc/netlink_compat.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 0965ca208900..0c82edebeb2c 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -762,9 +762,14 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, struct tipc_link_config *lc; struct tipc_bearer *bearer; struct tipc_media *media; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + media = tipc_media_find(lc->name); if (media) { cmd->doit = &__tipc_nl_media_set; From 2d5fc1d492d194aa2986c5a9d8a48a60e9143a72 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 14 Jan 2019 17:22:28 +0800 Subject: [PATCH 092/116] tipc: fix uninit-value in tipc_nl_compat_name_table_dump commit 974cb0e3e7c963ced06c4e32c5b2884173fa5e01 upstream. syzbot reported: BUG: KMSAN: uninit-value in __arch_swab32 arch/x86/include/uapi/asm/swab.h:10 [inline] BUG: KMSAN: uninit-value in __fswab32 include/uapi/linux/swab.h:59 [inline] BUG: KMSAN: uninit-value in tipc_nl_compat_name_table_dump+0x4a8/0xba0 net/tipc/netlink_compat.c:826 CPU: 0 PID: 6290 Comm: syz-executor848 Not tainted 4.19.0-rc8+ #70 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x306/0x460 lib/dump_stack.c:113 kmsan_report+0x1a2/0x2e0 mm/kmsan/kmsan.c:917 __msan_warning+0x7c/0xe0 mm/kmsan/kmsan_instr.c:500 __arch_swab32 arch/x86/include/uapi/asm/swab.h:10 [inline] __fswab32 include/uapi/linux/swab.h:59 [inline] tipc_nl_compat_name_table_dump+0x4a8/0xba0 net/tipc/netlink_compat.c:826 __tipc_nl_compat_dumpit+0x59e/0xdb0 net/tipc/netlink_compat.c:205 tipc_nl_compat_dumpit+0x63a/0x820 net/tipc/netlink_compat.c:270 tipc_nl_compat_handle net/tipc/netlink_compat.c:1151 [inline] tipc_nl_compat_recv+0x1402/0x2760 net/tipc/netlink_compat.c:1210 genl_family_rcv_msg net/netlink/genetlink.c:601 [inline] genl_rcv_msg+0x185c/0x1a20 net/netlink/genetlink.c:626 netlink_rcv_skb+0x394/0x640 net/netlink/af_netlink.c:2454 genl_rcv+0x63/0x80 net/netlink/genetlink.c:637 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x166d/0x1720 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x1391/0x1420 net/netlink/af_netlink.c:1908 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xe47/0x1200 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x307/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbe/0x100 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x440179 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffecec49318 EFLAGS: 00000213 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000440179 RDX: 0000000000000000 RSI: 0000000020000100 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000000 R09: 00000000004002c8 R10: 0000000000000000 R11: 0000000000000213 R12: 0000000000401a00 R13: 0000000000401a90 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:255 [inline] kmsan_internal_poison_shadow+0xc8/0x1d0 mm/kmsan/kmsan.c:180 kmsan_kmalloc+0xa4/0x120 mm/kmsan/kmsan_hooks.c:104 kmsan_slab_alloc+0x10/0x20 mm/kmsan/kmsan_hooks.c:113 slab_post_alloc_hook mm/slab.h:446 [inline] slab_alloc_node mm/slub.c:2727 [inline] __kmalloc_node_track_caller+0xb43/0x1400 mm/slub.c:4360 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x422/0xe90 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:996 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1189 [inline] netlink_sendmsg+0xcaf/0x1420 net/netlink/af_netlink.c:1883 sock_sendmsg_nosec net/socket.c:621 [inline] sock_sendmsg net/socket.c:631 [inline] ___sys_sendmsg+0xe47/0x1200 net/socket.c:2116 __sys_sendmsg net/socket.c:2154 [inline] __do_sys_sendmsg net/socket.c:2163 [inline] __se_sys_sendmsg+0x307/0x460 net/socket.c:2161 __x64_sys_sendmsg+0x4a/0x70 net/socket.c:2161 do_syscall_64+0xbe/0x100 arch/x86/entry/common.c:291 entry_SYSCALL_64_after_hwframe+0x63/0xe7 We cannot take for granted the thing that the length of data contained in TLV is longer than the size of struct tipc_name_table_query in tipc_nl_compat_name_table_dump(). Reported-by: syzbot+06e771a754829716a327@syzkaller.appspotmail.com Signed-off-by: Ying Xue Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tipc/netlink_compat.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 0c82edebeb2c..d0603028bac4 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -824,6 +824,8 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg) }; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); + if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query)) + return -EINVAL; depth = ntohl(ntq->depth); From 21172412a727d37b4a28e367f5a68fdc1af36b11 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 14 Jan 2019 17:22:29 +0800 Subject: [PATCH 093/116] tipc: fix uninit-value in tipc_nl_compat_doit commit 2753ca5d9009c180dbfd4c802c80983b4b6108d1 upstream. BUG: KMSAN: uninit-value in tipc_nl_compat_doit+0x404/0xa10 net/tipc/netlink_compat.c:335 CPU: 0 PID: 4514 Comm: syz-executor485 Not tainted 4.16.0+ #87 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:683 tipc_nl_compat_doit+0x404/0xa10 net/tipc/netlink_compat.c:335 tipc_nl_compat_recv+0x164b/0x2700 net/tipc/netlink_compat.c:1153 genl_family_rcv_msg net/netlink/genetlink.c:599 [inline] genl_rcv_msg+0x1686/0x1810 net/netlink/genetlink.c:624 netlink_rcv_skb+0x378/0x600 net/netlink/af_netlink.c:2447 genl_rcv+0x63/0x80 net/netlink/genetlink.c:635 netlink_unicast_kernel net/netlink/af_netlink.c:1311 [inline] netlink_unicast+0x166b/0x1740 net/netlink/af_netlink.c:1337 netlink_sendmsg+0x1048/0x1310 net/netlink/af_netlink.c:1900 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmsg net/socket.c:2080 [inline] SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091 SyS_sendmsg+0x54/0x80 net/socket.c:2087 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x43fda9 RSP: 002b:00007ffd0c184ba8 EFLAGS: 00000213 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 000000000043fda9 RDX: 0000000000000000 RSI: 0000000020023000 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 00000000004002c8 R09: 00000000004002c8 R10: 00000000004002c8 R11: 0000000000000213 R12: 00000000004016d0 R13: 0000000000401760 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmsan_slab_alloc+0x11/0x20 mm/kmsan/kmsan.c:321 slab_post_alloc_hook mm/slab.h:445 [inline] slab_alloc_node mm/slub.c:2737 [inline] __kmalloc_node_track_caller+0xaed/0x11c0 mm/slub.c:4369 __kmalloc_reserve net/core/skbuff.c:138 [inline] __alloc_skb+0x2cf/0x9f0 net/core/skbuff.c:206 alloc_skb include/linux/skbuff.h:984 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1183 [inline] netlink_sendmsg+0x9a6/0x1310 net/netlink/af_netlink.c:1875 sock_sendmsg_nosec net/socket.c:630 [inline] sock_sendmsg net/socket.c:640 [inline] ___sys_sendmsg+0xec0/0x1310 net/socket.c:2046 __sys_sendmsg net/socket.c:2080 [inline] SYSC_sendmsg+0x2a3/0x3d0 net/socket.c:2091 SyS_sendmsg+0x54/0x80 net/socket.c:2087 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 In tipc_nl_compat_recv(), when the len variable returned by nlmsg_attrlen() is 0, the message is still treated as a valid one, which is obviously unresonable. When len is zero, it means the message not only doesn't contain any valid TLV payload, but also TLV header is not included. Under this stituation, tlv_type field in TLV header is still accessed in tipc_nl_compat_dumpit() or tipc_nl_compat_doit(), but the field space is obviously illegal. Of course, it is not initialized. Reported-by: syzbot+bca0dc46634781f08b38@syzkaller.appspotmail.com Reported-by: syzbot+6bdb590321a7ae40c1a6@syzkaller.appspotmail.com Signed-off-by: Ying Xue Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/tipc/netlink_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index d0603028bac4..0b21187d74df 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -1249,7 +1249,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) } len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (len && !TLV_OK(msg.req, len)) { + if (!len || !TLV_OK(msg.req, len)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send; From f5d3c785c1d3a0beb84f1ac66f06a8d61a689a77 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 8 Nov 2018 14:01:01 +0100 Subject: [PATCH 094/116] block/loop: Don't grab "struct file" for vfs_getattr() operation. commit b1ab5fa309e6c49e4e06270ec67dd7b3e9971d04 upstream. vfs_getattr() needs "struct path" rather than "struct file". Let's use path_get()/path_put() rather than get_file()/fput(). Signed-off-by: Tetsuo Handa Reviewed-by: Jan Kara Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ea9debf59b22..50c81ff44ae2 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1205,7 +1205,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) static int loop_get_status(struct loop_device *lo, struct loop_info64 *info) { - struct file *file; + struct path path; struct kstat stat; int ret; @@ -1230,16 +1230,16 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) } /* Drop lo_ctl_mutex while we call into the filesystem. */ - file = get_file(lo->lo_backing_file); + path = lo->lo_backing_file->f_path; + path_get(&path); mutex_unlock(&lo->lo_ctl_mutex); - ret = vfs_getattr(&file->f_path, &stat, STATX_INO, - AT_STATX_SYNC_AS_STAT); + ret = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); if (!ret) { info->lo_device = huge_encode_dev(stat.dev); info->lo_inode = stat.ino; info->lo_rdevice = huge_encode_dev(stat.rdev); } - fput(file); + path_put(&path); return ret; } From 342b3360aeb1d1639cac996a042016ee063845e9 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 8 Nov 2018 14:01:02 +0100 Subject: [PATCH 095/116] block/loop: Use global lock for ioctl() operation. commit 310ca162d779efee8a2dc3731439680f3e9c1e86 upstream. syzbot is reporting NULL pointer dereference [1] which is caused by race condition between ioctl(loop_fd, LOOP_CLR_FD, 0) versus ioctl(other_loop_fd, LOOP_SET_FD, loop_fd) due to traversing other loop devices at loop_validate_file() without holding corresponding lo->lo_ctl_mutex locks. Since ioctl() request on loop devices is not frequent operation, we don't need fine grained locking. Let's use global lock in order to allow safe traversal at loop_validate_file(). Note that syzbot is also reporting circular locking dependency between bdev->bd_mutex and lo->lo_ctl_mutex [2] which is caused by calling blkdev_reread_part() with lock held. This patch does not address it. [1] https://syzkaller.appspot.com/bug?id=f3cfe26e785d85f9ee259f385515291d21bd80a3 [2] https://syzkaller.appspot.com/bug?id=bf154052f0eea4bc7712499e4569505907d15889 Signed-off-by: Tetsuo Handa Reported-by: syzbot Reviewed-by: Jan Kara Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 58 ++++++++++++++++++++++---------------------- drivers/block/loop.h | 1 - 2 files changed, 29 insertions(+), 30 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 50c81ff44ae2..d0f1b7106572 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -84,6 +84,7 @@ static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_index_mutex); +static DEFINE_MUTEX(loop_ctl_mutex); static int max_part; static int part_shift; @@ -1047,7 +1048,7 @@ static int loop_clr_fd(struct loop_device *lo) */ if (atomic_read(&lo->lo_refcnt) > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return 0; } @@ -1100,12 +1101,12 @@ static int loop_clr_fd(struct loop_device *lo) if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; loop_unprepare_queue(lo); - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); /* - * Need not hold lo_ctl_mutex to fput backing file. - * Calling fput holding lo_ctl_mutex triggers a circular + * Need not hold loop_ctl_mutex to fput backing file. + * Calling fput holding loop_ctl_mutex triggers a circular * lock dependency possibility warning as fput can take - * bd_mutex which is usually taken before lo_ctl_mutex. + * bd_mutex which is usually taken before loop_ctl_mutex. */ fput(filp); return 0; @@ -1210,7 +1211,7 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) int ret; if (lo->lo_state != Lo_bound) { - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return -ENXIO; } @@ -1229,10 +1230,10 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) lo->lo_encrypt_key_size); } - /* Drop lo_ctl_mutex while we call into the filesystem. */ + /* Drop loop_ctl_mutex while we call into the filesystem. */ path = lo->lo_backing_file->f_path; path_get(&path); - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); ret = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); if (!ret) { info->lo_device = huge_encode_dev(stat.dev); @@ -1324,7 +1325,7 @@ loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) { int err; if (!arg) { - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return -EINVAL; } err = loop_get_status(lo, &info64); @@ -1342,7 +1343,7 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { int err; if (!arg) { - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return -EINVAL; } err = loop_get_status(lo, &info64); @@ -1400,7 +1401,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, struct loop_device *lo = bdev->bd_disk->private_data; int err; - err = mutex_lock_killable_nested(&lo->lo_ctl_mutex, 1); + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); if (err) goto out_unlocked; @@ -1412,7 +1413,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, err = loop_change_fd(lo, bdev, arg); break; case LOOP_CLR_FD: - /* loop_clr_fd would have unlocked lo_ctl_mutex on success */ + /* loop_clr_fd would have unlocked loop_ctl_mutex on success */ err = loop_clr_fd(lo); if (!err) goto out_unlocked; @@ -1425,7 +1426,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, break; case LOOP_GET_STATUS: err = loop_get_status_old(lo, (struct loop_info __user *) arg); - /* loop_get_status() unlocks lo_ctl_mutex */ + /* loop_get_status() unlocks loop_ctl_mutex */ goto out_unlocked; case LOOP_SET_STATUS64: err = -EPERM; @@ -1435,7 +1436,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, break; case LOOP_GET_STATUS64: err = loop_get_status64(lo, (struct loop_info64 __user *) arg); - /* loop_get_status() unlocks lo_ctl_mutex */ + /* loop_get_status() unlocks loop_ctl_mutex */ goto out_unlocked; case LOOP_SET_CAPACITY: err = -EPERM; @@ -1455,7 +1456,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); out_unlocked: return err; @@ -1572,7 +1573,7 @@ loop_get_status_compat(struct loop_device *lo, int err; if (!arg) { - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return -EINVAL; } err = loop_get_status(lo, &info64); @@ -1589,19 +1590,19 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, switch(cmd) { case LOOP_SET_STATUS: - err = mutex_lock_killable(&lo->lo_ctl_mutex); + err = mutex_lock_killable(&loop_ctl_mutex); if (!err) { err = loop_set_status_compat(lo, (const struct compat_loop_info __user *)arg); - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); } break; case LOOP_GET_STATUS: - err = mutex_lock_killable(&lo->lo_ctl_mutex); + err = mutex_lock_killable(&loop_ctl_mutex); if (!err) { err = loop_get_status_compat(lo, (struct compat_loop_info __user *)arg); - /* loop_get_status() unlocks lo_ctl_mutex */ + /* loop_get_status() unlocks loop_ctl_mutex */ } break; case LOOP_SET_CAPACITY: @@ -1648,7 +1649,7 @@ static void __lo_release(struct loop_device *lo) if (atomic_dec_return(&lo->lo_refcnt)) return; - mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex); if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { /* * In autoclear mode, stop the loop thread @@ -1666,7 +1667,7 @@ static void __lo_release(struct loop_device *lo) blk_mq_unfreeze_queue(lo->lo_queue); } - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); } static void lo_release(struct gendisk *disk, fmode_t mode) @@ -1712,10 +1713,10 @@ static int unregister_transfer_cb(int id, void *ptr, void *data) struct loop_device *lo = ptr; struct loop_func_table *xfer = data; - mutex_lock(&lo->lo_ctl_mutex); + mutex_lock(&loop_ctl_mutex); if (lo->lo_encryption == xfer) loop_release_xfer(lo); - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); return 0; } @@ -1896,7 +1897,6 @@ static int loop_add(struct loop_device **l, int i) if (!part_shift) disk->flags |= GENHD_FL_NO_PART_SCAN; disk->flags |= GENHD_FL_EXT_DEVT; - mutex_init(&lo->lo_ctl_mutex); atomic_set(&lo->lo_refcnt, 0); lo->lo_number = i; spin_lock_init(&lo->lo_lock); @@ -2009,21 +2009,21 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, ret = loop_lookup(&lo, parm); if (ret < 0) break; - ret = mutex_lock_killable(&lo->lo_ctl_mutex); + ret = mutex_lock_killable(&loop_ctl_mutex); if (ret) break; if (lo->lo_state != Lo_unbound) { ret = -EBUSY; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); break; } if (atomic_read(&lo->lo_refcnt) > 0) { ret = -EBUSY; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); break; } lo->lo_disk->private_data = NULL; - mutex_unlock(&lo->lo_ctl_mutex); + mutex_unlock(&loop_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); loop_remove(lo); break; diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 4d42c7af7de7..af75a5ee4094 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -54,7 +54,6 @@ struct loop_device { spinlock_t lo_lock; int lo_state; - struct mutex lo_ctl_mutex; struct kthread_worker worker; struct task_struct *worker_task; bool use_dio; From 38d9cce3d61fe8d6ba24413eba74b4c8d24797f9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:03 +0100 Subject: [PATCH 096/116] loop: Fold __loop_release into loop_release commit 967d1dc144b50ad005e5eecdfadfbcfb399ffff6 upstream. __loop_release() has a single call site. Fold it there. This is currently not a huge win but it will make following replacement of loop_index_mutex more obvious. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d0f1b7106572..cc43d835fe6f 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1642,12 +1642,15 @@ static int lo_open(struct block_device *bdev, fmode_t mode) return err; } -static void __lo_release(struct loop_device *lo) +static void lo_release(struct gendisk *disk, fmode_t mode) { + struct loop_device *lo; int err; + mutex_lock(&loop_index_mutex); + lo = disk->private_data; if (atomic_dec_return(&lo->lo_refcnt)) - return; + goto unlock_index; mutex_lock(&loop_ctl_mutex); if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { @@ -1657,7 +1660,7 @@ static void __lo_release(struct loop_device *lo) */ err = loop_clr_fd(lo); if (!err) - return; + goto unlock_index; } else if (lo->lo_state == Lo_bound) { /* * Otherwise keep thread (if running) and config, @@ -1668,12 +1671,7 @@ static void __lo_release(struct loop_device *lo) } mutex_unlock(&loop_ctl_mutex); -} - -static void lo_release(struct gendisk *disk, fmode_t mode) -{ - mutex_lock(&loop_index_mutex); - __lo_release(disk->private_data); +unlock_index: mutex_unlock(&loop_index_mutex); } From ea5df5077091cbe9dda6b39b728c387055b6a548 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:04 +0100 Subject: [PATCH 097/116] loop: Get rid of loop_index_mutex commit 0a42e99b58a208839626465af194cfe640ef9493 upstream. Now that loop_ctl_mutex is global, just get rid of loop_index_mutex as there is no good reason to keep these two separate and it just complicates the locking. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 41 ++++++++++++++++++++--------------------- 1 file changed, 20 insertions(+), 21 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index cc43d835fe6f..3fa5e63944a4 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -83,7 +83,6 @@ #include static DEFINE_IDR(loop_index_idr); -static DEFINE_MUTEX(loop_index_mutex); static DEFINE_MUTEX(loop_ctl_mutex); static int max_part; @@ -1627,9 +1626,11 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, static int lo_open(struct block_device *bdev, fmode_t mode) { struct loop_device *lo; - int err = 0; + int err; - mutex_lock(&loop_index_mutex); + err = mutex_lock_killable(&loop_ctl_mutex); + if (err) + return err; lo = bdev->bd_disk->private_data; if (!lo) { err = -ENXIO; @@ -1638,7 +1639,7 @@ static int lo_open(struct block_device *bdev, fmode_t mode) atomic_inc(&lo->lo_refcnt); out: - mutex_unlock(&loop_index_mutex); + mutex_unlock(&loop_ctl_mutex); return err; } @@ -1647,12 +1648,11 @@ static void lo_release(struct gendisk *disk, fmode_t mode) struct loop_device *lo; int err; - mutex_lock(&loop_index_mutex); + mutex_lock(&loop_ctl_mutex); lo = disk->private_data; if (atomic_dec_return(&lo->lo_refcnt)) - goto unlock_index; + goto out_unlock; - mutex_lock(&loop_ctl_mutex); if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { /* * In autoclear mode, stop the loop thread @@ -1660,7 +1660,7 @@ static void lo_release(struct gendisk *disk, fmode_t mode) */ err = loop_clr_fd(lo); if (!err) - goto unlock_index; + return; } else if (lo->lo_state == Lo_bound) { /* * Otherwise keep thread (if running) and config, @@ -1670,9 +1670,8 @@ static void lo_release(struct gendisk *disk, fmode_t mode) blk_mq_unfreeze_queue(lo->lo_queue); } +out_unlock: mutex_unlock(&loop_ctl_mutex); -unlock_index: - mutex_unlock(&loop_index_mutex); } static const struct block_device_operations lo_fops = { @@ -1973,7 +1972,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data) struct kobject *kobj; int err; - mutex_lock(&loop_index_mutex); + mutex_lock(&loop_ctl_mutex); err = loop_lookup(&lo, MINOR(dev) >> part_shift); if (err < 0) err = loop_add(&lo, MINOR(dev) >> part_shift); @@ -1981,7 +1980,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data) kobj = NULL; else kobj = get_disk_and_module(lo->lo_disk); - mutex_unlock(&loop_index_mutex); + mutex_unlock(&loop_ctl_mutex); *part = 0; return kobj; @@ -1991,9 +1990,13 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, unsigned long parm) { struct loop_device *lo; - int ret = -ENOSYS; + int ret; - mutex_lock(&loop_index_mutex); + ret = mutex_lock_killable(&loop_ctl_mutex); + if (ret) + return ret; + + ret = -ENOSYS; switch (cmd) { case LOOP_CTL_ADD: ret = loop_lookup(&lo, parm); @@ -2007,9 +2010,6 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, ret = loop_lookup(&lo, parm); if (ret < 0) break; - ret = mutex_lock_killable(&loop_ctl_mutex); - if (ret) - break; if (lo->lo_state != Lo_unbound) { ret = -EBUSY; mutex_unlock(&loop_ctl_mutex); @@ -2021,7 +2021,6 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, break; } lo->lo_disk->private_data = NULL; - mutex_unlock(&loop_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); loop_remove(lo); break; @@ -2031,7 +2030,7 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, break; ret = loop_add(&lo, -1); } - mutex_unlock(&loop_index_mutex); + mutex_unlock(&loop_ctl_mutex); return ret; } @@ -2115,10 +2114,10 @@ static int __init loop_init(void) THIS_MODULE, loop_probe, NULL, NULL); /* pre-create number of devices given by config or max_loop */ - mutex_lock(&loop_index_mutex); + mutex_lock(&loop_ctl_mutex); for (i = 0; i < nr; i++) loop_add(&lo, i); - mutex_unlock(&loop_index_mutex); + mutex_unlock(&loop_ctl_mutex); printk(KERN_INFO "loop: module loaded\n"); return 0; From b8463897a29464d185cb7d3732da15e51cf086a3 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:05 +0100 Subject: [PATCH 098/116] loop: Push lo_ctl_mutex down into individual ioctls commit a13165441d58b216adbd50252a9cc829d78a6bce upstream. Push acquisition of lo_ctl_mutex down into individual ioctl handling branches. This is a preparatory step for pushing the lock down into individual ioctl handling functions so that they can release the lock as they need it. We also factor out some simple ioctl handlers that will not need any special handling to reduce unnecessary code duplication. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 88 +++++++++++++++++++++++++++++++------------- 1 file changed, 63 insertions(+), 25 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 3fa5e63944a4..b7b3b4ae0896 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1394,70 +1394,108 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) return 0; } +static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, + unsigned long arg) +{ + int err; + + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; + switch (cmd) { + case LOOP_SET_CAPACITY: + err = loop_set_capacity(lo); + break; + case LOOP_SET_DIRECT_IO: + err = loop_set_dio(lo, arg); + break; + case LOOP_SET_BLOCK_SIZE: + err = loop_set_block_size(lo, arg); + break; + default: + err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; + } + mutex_unlock(&loop_ctl_mutex); + return err; +} + static int lo_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; int err; - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); - if (err) - goto out_unlocked; - switch (cmd) { case LOOP_SET_FD: + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; err = loop_set_fd(lo, mode, bdev, arg); + mutex_unlock(&loop_ctl_mutex); break; case LOOP_CHANGE_FD: + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; err = loop_change_fd(lo, bdev, arg); + mutex_unlock(&loop_ctl_mutex); break; case LOOP_CLR_FD: + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; /* loop_clr_fd would have unlocked loop_ctl_mutex on success */ err = loop_clr_fd(lo); - if (!err) - goto out_unlocked; + if (err) + mutex_unlock(&loop_ctl_mutex); break; case LOOP_SET_STATUS: err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; err = loop_set_status_old(lo, (struct loop_info __user *)arg); + mutex_unlock(&loop_ctl_mutex); + } break; case LOOP_GET_STATUS: + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; err = loop_get_status_old(lo, (struct loop_info __user *) arg); /* loop_get_status() unlocks loop_ctl_mutex */ - goto out_unlocked; + break; case LOOP_SET_STATUS64: err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; err = loop_set_status64(lo, (struct loop_info64 __user *) arg); + mutex_unlock(&loop_ctl_mutex); + } break; case LOOP_GET_STATUS64: + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; err = loop_get_status64(lo, (struct loop_info64 __user *) arg); /* loop_get_status() unlocks loop_ctl_mutex */ - goto out_unlocked; + break; case LOOP_SET_CAPACITY: - err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_capacity(lo); - break; case LOOP_SET_DIRECT_IO: - err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_dio(lo, arg); - break; case LOOP_SET_BLOCK_SIZE: - err = -EPERM; - if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) - err = loop_set_block_size(lo, arg); - break; + if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* Fall through */ default: - err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; + err = lo_simple_ioctl(lo, cmd, arg); + break; } - mutex_unlock(&loop_ctl_mutex); -out_unlocked: return err; } From 18974320825eba3d303b23cf7ef220714e4d6b5b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:06 +0100 Subject: [PATCH 099/116] loop: Split setting of lo_state from loop_clr_fd commit a2505b799a496b7b84d9a4a14ec870ff9e42e11b upstream. Move setting of lo_state to Lo_rundown out into the callers. That will allow us to unlock loop_ctl_mutex while the loop device is protected from other changes by its special state. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 52 ++++++++++++++++++++++++++------------------ 1 file changed, 31 insertions(+), 21 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index b7b3b4ae0896..2410921bd9ff 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -976,7 +976,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, loop_reread_partitions(lo, bdev); /* Grab the block_device to prevent its destruction after we - * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev). + * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). */ bdgrab(bdev); return 0; @@ -1026,31 +1026,15 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, return err; } -static int loop_clr_fd(struct loop_device *lo) +static int __loop_clr_fd(struct loop_device *lo) { struct file *filp = lo->lo_backing_file; gfp_t gfp = lo->old_gfp_mask; struct block_device *bdev = lo->lo_device; - if (lo->lo_state != Lo_bound) + if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) return -ENXIO; - /* - * If we've explicitly asked to tear down the loop device, - * and it has an elevated reference count, set it for auto-teardown when - * the last reference goes away. This stops $!~#$@ udev from - * preventing teardown because it decided that it needs to run blkid on - * the loopback device whenever they appear. xfstests is notorious for - * failing tests because blkid via udev races with a losetup - * /do something like mkfs/losetup -d causing the losetup -d - * command to fail with EBUSY. - */ - if (atomic_read(&lo->lo_refcnt) > 1) { - lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - mutex_unlock(&loop_ctl_mutex); - return 0; - } - if (filp == NULL) return -EINVAL; @@ -1058,7 +1042,6 @@ static int loop_clr_fd(struct loop_device *lo) blk_mq_freeze_queue(lo->lo_queue); spin_lock_irq(&lo->lo_lock); - lo->lo_state = Lo_rundown; lo->lo_backing_file = NULL; spin_unlock_irq(&lo->lo_lock); @@ -1111,6 +1094,30 @@ static int loop_clr_fd(struct loop_device *lo) return 0; } +static int loop_clr_fd(struct loop_device *lo) +{ + if (lo->lo_state != Lo_bound) + return -ENXIO; + /* + * If we've explicitly asked to tear down the loop device, + * and it has an elevated reference count, set it for auto-teardown when + * the last reference goes away. This stops $!~#$@ udev from + * preventing teardown because it decided that it needs to run blkid on + * the loopback device whenever they appear. xfstests is notorious for + * failing tests because blkid via udev races with a losetup + * /do something like mkfs/losetup -d causing the losetup -d + * command to fail with EBUSY. + */ + if (atomic_read(&lo->lo_refcnt) > 1) { + lo->lo_flags |= LO_FLAGS_AUTOCLEAR; + mutex_unlock(&loop_ctl_mutex); + return 0; + } + lo->lo_state = Lo_rundown; + + return __loop_clr_fd(lo); +} + static int loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { @@ -1692,11 +1699,14 @@ static void lo_release(struct gendisk *disk, fmode_t mode) goto out_unlock; if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { + if (lo->lo_state != Lo_bound) + goto out_unlock; + lo->lo_state = Lo_rundown; /* * In autoclear mode, stop the loop thread * and remove configuration after last close. */ - err = loop_clr_fd(lo); + err = __loop_clr_fd(lo); if (!err) return; } else if (lo->lo_state == Lo_bound) { From ed87dc6601712a8ff8783acee8701954bc40fbca Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:07 +0100 Subject: [PATCH 100/116] loop: Push loop_ctl_mutex down into loop_clr_fd() commit 7ccd0791d98531df7cd59e92d55e4f063d48a070 upstream. loop_clr_fd() has a weird locking convention that is expects loop_ctl_mutex held, releases it on success and keeps it on failure. Untangle the mess by moving locking of loop_ctl_mutex into loop_clr_fd(). Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 49 ++++++++++++++++++++++++++------------------ 1 file changed, 29 insertions(+), 20 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 2410921bd9ff..be41d5dcecd2 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1028,15 +1028,22 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, static int __loop_clr_fd(struct loop_device *lo) { - struct file *filp = lo->lo_backing_file; + struct file *filp = NULL; gfp_t gfp = lo->old_gfp_mask; struct block_device *bdev = lo->lo_device; + int err = 0; - if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) - return -ENXIO; + mutex_lock(&loop_ctl_mutex); + if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { + err = -ENXIO; + goto out_unlock; + } - if (filp == NULL) - return -EINVAL; + filp = lo->lo_backing_file; + if (filp == NULL) { + err = -EINVAL; + goto out_unlock; + } /* freeze request queue during the transition */ blk_mq_freeze_queue(lo->lo_queue); @@ -1083,6 +1090,7 @@ static int __loop_clr_fd(struct loop_device *lo) if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; loop_unprepare_queue(lo); +out_unlock: mutex_unlock(&loop_ctl_mutex); /* * Need not hold loop_ctl_mutex to fput backing file. @@ -1090,14 +1098,22 @@ static int __loop_clr_fd(struct loop_device *lo) * lock dependency possibility warning as fput can take * bd_mutex which is usually taken before loop_ctl_mutex. */ - fput(filp); - return 0; + if (filp) + fput(filp); + return err; } static int loop_clr_fd(struct loop_device *lo) { - if (lo->lo_state != Lo_bound) + int err; + + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; + if (lo->lo_state != Lo_bound) { + mutex_unlock(&loop_ctl_mutex); return -ENXIO; + } /* * If we've explicitly asked to tear down the loop device, * and it has an elevated reference count, set it for auto-teardown when @@ -1114,6 +1130,7 @@ static int loop_clr_fd(struct loop_device *lo) return 0; } lo->lo_state = Lo_rundown; + mutex_unlock(&loop_ctl_mutex); return __loop_clr_fd(lo); } @@ -1448,14 +1465,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, mutex_unlock(&loop_ctl_mutex); break; case LOOP_CLR_FD: - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); - if (err) - return err; - /* loop_clr_fd would have unlocked loop_ctl_mutex on success */ - err = loop_clr_fd(lo); - if (err) - mutex_unlock(&loop_ctl_mutex); - break; + return loop_clr_fd(lo); case LOOP_SET_STATUS: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { @@ -1691,7 +1701,6 @@ static int lo_open(struct block_device *bdev, fmode_t mode) static void lo_release(struct gendisk *disk, fmode_t mode) { struct loop_device *lo; - int err; mutex_lock(&loop_ctl_mutex); lo = disk->private_data; @@ -1702,13 +1711,13 @@ static void lo_release(struct gendisk *disk, fmode_t mode) if (lo->lo_state != Lo_bound) goto out_unlock; lo->lo_state = Lo_rundown; + mutex_unlock(&loop_ctl_mutex); /* * In autoclear mode, stop the loop thread * and remove configuration after last close. */ - err = __loop_clr_fd(lo); - if (!err) - return; + __loop_clr_fd(lo); + return; } else if (lo->lo_state == Lo_bound) { /* * Otherwise keep thread (if running) and config, From 8de64127b2aad1c4926e67d545655b659fbbf65e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:08 +0100 Subject: [PATCH 101/116] loop: Push loop_ctl_mutex down to loop_get_status() commit 4a5ce9ba5877e4640200d84a735361306ad1a1b8 upstream. Push loop_ctl_mutex down to loop_get_status() to avoid the unusual convention that the function gets called with loop_ctl_mutex held and releases it. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 37 ++++++++++--------------------------- 1 file changed, 10 insertions(+), 27 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index be41d5dcecd2..cb4eeff91238 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1233,6 +1233,9 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) struct kstat stat; int ret; + ret = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (ret) + return ret; if (lo->lo_state != Lo_bound) { mutex_unlock(&loop_ctl_mutex); return -ENXIO; @@ -1347,10 +1350,8 @@ loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) { struct loop_info64 info64; int err; - if (!arg) { - mutex_unlock(&loop_ctl_mutex); + if (!arg) return -EINVAL; - } err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_old(&info64, &info); @@ -1365,10 +1366,8 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { struct loop_info64 info64; int err; - if (!arg) { - mutex_unlock(&loop_ctl_mutex); + if (!arg) return -EINVAL; - } err = loop_get_status(lo, &info64); if (!err && copy_to_user(arg, &info64, sizeof(info64))) err = -EFAULT; @@ -1478,12 +1477,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, } break; case LOOP_GET_STATUS: - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); - if (err) - return err; - err = loop_get_status_old(lo, (struct loop_info __user *) arg); - /* loop_get_status() unlocks loop_ctl_mutex */ - break; + return loop_get_status_old(lo, (struct loop_info __user *) arg); case LOOP_SET_STATUS64: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { @@ -1496,12 +1490,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, } break; case LOOP_GET_STATUS64: - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); - if (err) - return err; - err = loop_get_status64(lo, (struct loop_info64 __user *) arg); - /* loop_get_status() unlocks loop_ctl_mutex */ - break; + return loop_get_status64(lo, (struct loop_info64 __user *) arg); case LOOP_SET_CAPACITY: case LOOP_SET_DIRECT_IO: case LOOP_SET_BLOCK_SIZE: @@ -1626,10 +1615,8 @@ loop_get_status_compat(struct loop_device *lo, struct loop_info64 info64; int err; - if (!arg) { - mutex_unlock(&loop_ctl_mutex); + if (!arg) return -EINVAL; - } err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_compat(&info64, arg); @@ -1652,12 +1639,8 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, } break; case LOOP_GET_STATUS: - err = mutex_lock_killable(&loop_ctl_mutex); - if (!err) { - err = loop_get_status_compat(lo, - (struct compat_loop_info __user *)arg); - /* loop_get_status() unlocks loop_ctl_mutex */ - } + err = loop_get_status_compat(lo, + (struct compat_loop_info __user *)arg); break; case LOOP_SET_CAPACITY: case LOOP_CLR_FD: From 90386ad72fcfd9e6b0d60e0aef7d0f1ef2366f6d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:09 +0100 Subject: [PATCH 102/116] loop: Push loop_ctl_mutex down to loop_set_status() commit 550df5fdacff94229cde0ed9b8085155654c1696 upstream. Push loop_ctl_mutex down to loop_set_status(). We will need this to be able to call loop_reread_partitions() without loop_ctl_mutex. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 51 ++++++++++++++++++++++---------------------- 1 file changed, 25 insertions(+), 26 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index cb4eeff91238..5661489d11a7 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1142,46 +1142,55 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) struct loop_func_table *xfer; kuid_t uid = current_uid(); + err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (err) + return err; if (lo->lo_encrypt_key_size && !uid_eq(lo->lo_key_owner, uid) && - !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (lo->lo_state != Lo_bound) - return -ENXIO; - if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) - return -EINVAL; + !capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto out_unlock; + } + if (lo->lo_state != Lo_bound) { + err = -ENXIO; + goto out_unlock; + } + if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) { + err = -EINVAL; + goto out_unlock; + } /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); err = loop_release_xfer(lo); if (err) - goto exit; + goto out_unfreeze; if (info->lo_encrypt_type) { unsigned int type = info->lo_encrypt_type; if (type >= MAX_LO_CRYPT) { err = -EINVAL; - goto exit; + goto out_unfreeze; } xfer = xfer_funcs[type]; if (xfer == NULL) { err = -EINVAL; - goto exit; + goto out_unfreeze; } } else xfer = NULL; err = loop_init_xfer(lo, xfer, info); if (err) - goto exit; + goto out_unfreeze; if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { err = -EFBIG; - goto exit; + goto out_unfreeze; } } @@ -1213,7 +1222,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) /* update dio if lo_offset or transfer is changed */ __loop_update_dio(lo, lo->use_dio); - exit: +out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) && @@ -1222,6 +1231,8 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; loop_reread_partitions(lo, lo->lo_device); } +out_unlock: + mutex_unlock(&loop_ctl_mutex); return err; } @@ -1468,12 +1479,8 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, case LOOP_SET_STATUS: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); - if (err) - return err; err = loop_set_status_old(lo, (struct loop_info __user *)arg); - mutex_unlock(&loop_ctl_mutex); } break; case LOOP_GET_STATUS: @@ -1481,12 +1488,8 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, case LOOP_SET_STATUS64: err = -EPERM; if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) { - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); - if (err) - return err; err = loop_set_status64(lo, (struct loop_info64 __user *) arg); - mutex_unlock(&loop_ctl_mutex); } break; case LOOP_GET_STATUS64: @@ -1631,12 +1634,8 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, switch(cmd) { case LOOP_SET_STATUS: - err = mutex_lock_killable(&loop_ctl_mutex); - if (!err) { - err = loop_set_status_compat(lo, - (const struct compat_loop_info __user *)arg); - mutex_unlock(&loop_ctl_mutex); - } + err = loop_set_status_compat(lo, + (const struct compat_loop_info __user *)arg); break; case LOOP_GET_STATUS: err = loop_get_status_compat(lo, From 9218b108062e159278c45a50f1c81094e30acf86 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:10 +0100 Subject: [PATCH 103/116] loop: Push loop_ctl_mutex down to loop_set_fd() commit 757ecf40b7e029529768eb5f9562d5eeb3002106 upstream. Push lo_ctl_mutex down to loop_set_fd(). We will need this to be able to call loop_reread_partitions() without lo_ctl_mutex. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 5661489d11a7..b4500d82238d 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -919,13 +919,17 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!file) goto out; + error = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (error) + goto out_putf; + error = -EBUSY; if (lo->lo_state != Lo_unbound) - goto out_putf; + goto out_unlock; error = loop_validate_file(file, bdev); if (error) - goto out_putf; + goto out_unlock; mapping = file->f_mapping; inode = mapping->host; @@ -937,10 +941,10 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, error = -EFBIG; size = get_loop_size(lo, file); if ((loff_t)(sector_t)size != size) - goto out_putf; + goto out_unlock; error = loop_prepare_queue(lo); if (error) - goto out_putf; + goto out_unlock; error = 0; @@ -979,11 +983,14 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). */ bdgrab(bdev); + mutex_unlock(&loop_ctl_mutex); return 0; - out_putf: +out_unlock: + mutex_unlock(&loop_ctl_mutex); +out_putf: fput(file); - out: +out: /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return error; @@ -1461,12 +1468,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, switch (cmd) { case LOOP_SET_FD: - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); - if (err) - return err; - err = loop_set_fd(lo, mode, bdev, arg); - mutex_unlock(&loop_ctl_mutex); - break; + return loop_set_fd(lo, mode, bdev, arg); case LOOP_CHANGE_FD: err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); if (err) From dc717408cef0f97455d3850de348987cb7cc7e6f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:11 +0100 Subject: [PATCH 104/116] loop: Push loop_ctl_mutex down to loop_change_fd() commit c371077000f4138ee3c15fbed50101ff24bdc91d upstream. Push loop_ctl_mutex down to loop_change_fd(). We will need this to be able to call loop_reread_partitions() without loop_ctl_mutex. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index b4500d82238d..c53ad5e88a7d 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -692,19 +692,22 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, struct file *file, *old_file; int error; + error = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + if (error) + return error; error = -ENXIO; if (lo->lo_state != Lo_bound) - goto out; + goto out_unlock; /* the loop device has to be read-only */ error = -EINVAL; if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) - goto out; + goto out_unlock; error = -EBADF; file = fget(arg); if (!file) - goto out; + goto out_unlock; error = loop_validate_file(file, bdev); if (error) @@ -731,11 +734,13 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, fput(old_file); if (lo->lo_flags & LO_FLAGS_PARTSCAN) loop_reread_partitions(lo, bdev); + mutex_unlock(&loop_ctl_mutex); return 0; - out_putf: +out_putf: fput(file); - out: +out_unlock: + mutex_unlock(&loop_ctl_mutex); return error; } @@ -1470,12 +1475,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, case LOOP_SET_FD: return loop_set_fd(lo, mode, bdev, arg); case LOOP_CHANGE_FD: - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); - if (err) - return err; - err = loop_change_fd(lo, bdev, arg); - mutex_unlock(&loop_ctl_mutex); - break; + return loop_change_fd(lo, bdev, arg); case LOOP_CLR_FD: return loop_clr_fd(lo); case LOOP_SET_STATUS: From ed281a7230c979660fdc8cb6d6ff08e3507aba22 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:12 +0100 Subject: [PATCH 105/116] loop: Move special partition reread handling in loop_clr_fd() commit d57f3374ba4817f7c8d26fae8a13d20ac8d31b92 upstream. The call of __blkdev_reread_part() from loop_reread_partition() happens only when we need to invalidate partitions from loop_release(). Thus move a detection for this into loop_clr_fd() and simplify loop_reread_partition(). This makes loop_reread_partition() safe to use without loop_ctl_mutex because we use only lo->lo_number and lo->lo_file_name in case of error for reporting purposes (thus possibly reporting outdate information is not a big deal) and we are safe from 'lo' going away under us by elevated lo->lo_refcnt. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index c53ad5e88a7d..db73fb5f16c7 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -631,18 +631,7 @@ static void loop_reread_partitions(struct loop_device *lo, { int rc; - /* - * bd_mutex has been held already in release path, so don't - * acquire it if this function is called in such case. - * - * If the reread partition isn't from release path, lo_refcnt - * must be at least one and it can only become zero when the - * current holder is released. - */ - if (!atomic_read(&lo->lo_refcnt)) - rc = __blkdev_reread_part(bdev); - else - rc = blkdev_reread_part(bdev); + rc = blkdev_reread_part(bdev); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); @@ -1096,8 +1085,24 @@ static int __loop_clr_fd(struct loop_device *lo) module_put(THIS_MODULE); blk_mq_unfreeze_queue(lo->lo_queue); - if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev) - loop_reread_partitions(lo, bdev); + if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev) { + /* + * bd_mutex has been held already in release path, so don't + * acquire it if this function is called in such case. + * + * If the reread partition isn't from release path, lo_refcnt + * must be at least one and it can only become zero when the + * current holder is released. + */ + if (!atomic_read(&lo->lo_refcnt)) + err = __blkdev_reread_part(bdev); + else + err = blkdev_reread_part(bdev); + pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", + __func__, lo->lo_number, err); + /* Device is gone, no point in returning error */ + err = 0; + } lo->lo_flags = 0; if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; From 6e0d6935309579b98249b3b8ffebf49b78bbd771 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:13 +0100 Subject: [PATCH 106/116] loop: Move loop_reread_partitions() out of loop_ctl_mutex commit 85b0a54a82e4fbceeb1aebb7cb6909edd1a24668 upstream. Calling loop_reread_partitions() under loop_ctl_mutex causes lockdep to complain about circular lock dependency between bdev->bd_mutex and lo->lo_ctl_mutex. The problem is that on loop device open or close lo_open() and lo_release() get called with bdev->bd_mutex held and they need to acquire loop_ctl_mutex. OTOH when loop_reread_partitions() is called with loop_ctl_mutex held, it will call blkdev_reread_part() which acquires bdev->bd_mutex. See syzbot report for details [1]. Move all calls of loop_rescan_partitions() out of loop_ctl_mutex to avoid lockdep warning and fix deadlock possibility. [1] https://syzkaller.appspot.com/bug?id=bf154052f0eea4bc7712499e4569505907d1588 Reported-by: syzbot Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index db73fb5f16c7..0d54c3ee3a96 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -680,6 +680,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, { struct file *file, *old_file; int error; + bool partscan; error = mutex_lock_killable_nested(&loop_ctl_mutex, 1); if (error) @@ -721,9 +722,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, blk_mq_unfreeze_queue(lo->lo_queue); fput(old_file); - if (lo->lo_flags & LO_FLAGS_PARTSCAN) - loop_reread_partitions(lo, bdev); + partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; mutex_unlock(&loop_ctl_mutex); + if (partscan) + loop_reread_partitions(lo, bdev); return 0; out_putf: @@ -904,6 +906,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, int lo_flags = 0; int error; loff_t size; + bool partscan; /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); @@ -970,14 +973,15 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->lo_state = Lo_bound; if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; - if (lo->lo_flags & LO_FLAGS_PARTSCAN) - loop_reread_partitions(lo, bdev); + partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; /* Grab the block_device to prevent its destruction after we * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev). */ bdgrab(bdev); mutex_unlock(&loop_ctl_mutex); + if (partscan) + loop_reread_partitions(lo, bdev); return 0; out_unlock: @@ -1158,6 +1162,8 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) int err; struct loop_func_table *xfer; kuid_t uid = current_uid(); + struct block_device *bdev; + bool partscan = false; err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); if (err) @@ -1246,10 +1252,13 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) !(lo->lo_flags & LO_FLAGS_PARTSCAN)) { lo->lo_flags |= LO_FLAGS_PARTSCAN; lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; - loop_reread_partitions(lo, lo->lo_device); + bdev = lo->lo_device; + partscan = true; } out_unlock: mutex_unlock(&loop_ctl_mutex); + if (partscan) + loop_reread_partitions(lo, bdev); return err; } From 5f0db37d916bece442472e0714de75e330c439e8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:14 +0100 Subject: [PATCH 107/116] loop: Fix deadlock when calling blkdev_reread_part() commit 0da03cab87e6323ff2e05b14bc7d5c6fcc531efd upstream. Calling blkdev_reread_part() under loop_ctl_mutex causes lockdep to complain about circular lock dependency between bdev->bd_mutex and lo->lo_ctl_mutex. The problem is that on loop device open or close lo_open() and lo_release() get called with bdev->bd_mutex held and they need to acquire loop_ctl_mutex. OTOH when loop_reread_partitions() is called with loop_ctl_mutex held, it will call blkdev_reread_part() which acquires bdev->bd_mutex. See syzbot report for details [1]. Move call to blkdev_reread_part() in __loop_clr_fd() from under loop_ctl_mutex to finish fixing of the lockdep warning and the possible deadlock. [1] https://syzkaller.appspot.com/bug?id=bf154052f0eea4bc7712499e4569505907d1588 Reported-by: syzbot Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 0d54c3ee3a96..d6b3fac25040 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1031,12 +1031,14 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, return err; } -static int __loop_clr_fd(struct loop_device *lo) +static int __loop_clr_fd(struct loop_device *lo, bool release) { struct file *filp = NULL; gfp_t gfp = lo->old_gfp_mask; struct block_device *bdev = lo->lo_device; int err = 0; + bool partscan = false; + int lo_number; mutex_lock(&loop_ctl_mutex); if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { @@ -1089,7 +1091,15 @@ static int __loop_clr_fd(struct loop_device *lo) module_put(THIS_MODULE); blk_mq_unfreeze_queue(lo->lo_queue); - if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev) { + partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev; + lo_number = lo->lo_number; + lo->lo_flags = 0; + if (!part_shift) + lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; + loop_unprepare_queue(lo); +out_unlock: + mutex_unlock(&loop_ctl_mutex); + if (partscan) { /* * bd_mutex has been held already in release path, so don't * acquire it if this function is called in such case. @@ -1098,21 +1108,15 @@ static int __loop_clr_fd(struct loop_device *lo) * must be at least one and it can only become zero when the * current holder is released. */ - if (!atomic_read(&lo->lo_refcnt)) + if (release) err = __blkdev_reread_part(bdev); else err = blkdev_reread_part(bdev); pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", - __func__, lo->lo_number, err); + __func__, lo_number, err); /* Device is gone, no point in returning error */ err = 0; } - lo->lo_flags = 0; - if (!part_shift) - lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; - loop_unprepare_queue(lo); -out_unlock: - mutex_unlock(&loop_ctl_mutex); /* * Need not hold loop_ctl_mutex to fput backing file. * Calling fput holding loop_ctl_mutex triggers a circular @@ -1153,7 +1157,7 @@ static int loop_clr_fd(struct loop_device *lo) lo->lo_state = Lo_rundown; mutex_unlock(&loop_ctl_mutex); - return __loop_clr_fd(lo); + return __loop_clr_fd(lo, false); } static int @@ -1714,7 +1718,7 @@ static void lo_release(struct gendisk *disk, fmode_t mode) * In autoclear mode, stop the loop thread * and remove configuration after last close. */ - __loop_clr_fd(lo); + __loop_clr_fd(lo, true); return; } else if (lo->lo_state == Lo_bound) { /* From 5c684c250bf3b918eb4ce87f64d074c3e0306a6f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:15 +0100 Subject: [PATCH 108/116] loop: Avoid circular locking dependency between loop_ctl_mutex and bd_mutex commit 1dded9acf6dc9a34cd27fcf8815507e4e65b3c4f upstream. Code in loop_change_fd() drops reference to the old file (and also the new file in a failure case) under loop_ctl_mutex. Similarly to a situation in loop_set_fd() this can create a circular locking dependency if this was the last reference holding the file open. Delay dropping of the file reference until we have released loop_ctl_mutex. Reported-by: Tetsuo Handa Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d6b3fac25040..a517247a32fa 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -678,7 +678,7 @@ static int loop_validate_file(struct file *file, struct block_device *bdev) static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, unsigned int arg) { - struct file *file, *old_file; + struct file *file = NULL, *old_file; int error; bool partscan; @@ -687,21 +687,21 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, return error; error = -ENXIO; if (lo->lo_state != Lo_bound) - goto out_unlock; + goto out_err; /* the loop device has to be read-only */ error = -EINVAL; if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) - goto out_unlock; + goto out_err; error = -EBADF; file = fget(arg); if (!file) - goto out_unlock; + goto out_err; error = loop_validate_file(file, bdev); if (error) - goto out_putf; + goto out_err; old_file = lo->lo_backing_file; @@ -709,7 +709,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, /* size of the new backing store needs to be the same */ if (get_loop_size(lo, file) != get_loop_size(lo, old_file)) - goto out_putf; + goto out_err; /* and ... switch */ blk_mq_freeze_queue(lo->lo_queue); @@ -720,18 +720,22 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue); - - fput(old_file); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; mutex_unlock(&loop_ctl_mutex); + /* + * We must drop file reference outside of loop_ctl_mutex as dropping + * the file ref can take bd_mutex which creates circular locking + * dependency. + */ + fput(old_file); if (partscan) loop_reread_partitions(lo, bdev); return 0; -out_putf: - fput(file); -out_unlock: +out_err: mutex_unlock(&loop_ctl_mutex); + if (file) + fput(file); return error; } From b42e24aa3b8811df6f733fd6e033350e0d406847 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Nov 2018 14:01:16 +0100 Subject: [PATCH 109/116] loop: Get rid of 'nested' acquisition of loop_ctl_mutex commit c28445fa06a3a54e06938559b9514c5a7f01c90f upstream. The nested acquisition of loop_ctl_mutex (->lo_ctl_mutex back then) has been introduced by commit f028f3b2f987e "loop: fix circular locking in loop_clr_fd()" to fix lockdep complains about bd_mutex being acquired after lo_ctl_mutex during partition rereading. Now that these are properly fixed, let's stop fooling lockdep. Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a517247a32fa..ec083665f1fd 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -682,7 +682,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, int error; bool partscan; - error = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + error = mutex_lock_killable(&loop_ctl_mutex); if (error) return error; error = -ENXIO; @@ -920,7 +920,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!file) goto out; - error = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + error = mutex_lock_killable(&loop_ctl_mutex); if (error) goto out_putf; @@ -1136,7 +1136,7 @@ static int loop_clr_fd(struct loop_device *lo) { int err; - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; if (lo->lo_state != Lo_bound) { @@ -1173,7 +1173,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) struct block_device *bdev; bool partscan = false; - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; if (lo->lo_encrypt_key_size && @@ -1278,7 +1278,7 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) struct kstat stat; int ret; - ret = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + ret = mutex_lock_killable(&loop_ctl_mutex); if (ret) return ret; if (lo->lo_state != Lo_bound) { @@ -1467,7 +1467,7 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, { int err; - err = mutex_lock_killable_nested(&loop_ctl_mutex, 1); + err = mutex_lock_killable(&loop_ctl_mutex); if (err) return err; switch (cmd) { From 30805ece50683025ecf06b1d18d540e305550409 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 12 Nov 2018 08:42:14 -0700 Subject: [PATCH 110/116] loop: Fix double mutex_unlock(&loop_ctl_mutex) in loop_control_ioctl() commit 628bd85947091830a8c4872adfd5ed1d515a9cf2 upstream. Commit 0a42e99b58a20883 ("loop: Get rid of loop_index_mutex") forgot to remove mutex_unlock(&loop_ctl_mutex) from loop_control_ioctl() when replacing loop_index_mutex with loop_ctl_mutex. Fixes: 0a42e99b58a20883 ("loop: Get rid of loop_index_mutex") Reported-by: syzbot Reviewed-by: Ming Lei Reviewed-by: Jan Kara Signed-off-by: Tetsuo Handa Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ec083665f1fd..e0802d15ace0 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -2075,12 +2075,10 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, break; if (lo->lo_state != Lo_unbound) { ret = -EBUSY; - mutex_unlock(&loop_ctl_mutex); break; } if (atomic_read(&lo->lo_refcnt) > 0) { ret = -EBUSY; - mutex_unlock(&loop_ctl_mutex); break; } lo->lo_disk->private_data = NULL; From 8868a72d4201e58f30eabd629067058926993efd Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Wed, 9 Jan 2019 19:17:14 -0800 Subject: [PATCH 111/116] loop: drop caches if offset or block_size are changed commit 5db470e229e22b7eda6e23b5566e532c96fb5bc3 upstream. If we don't drop caches used in old offset or block_size, we can get old data from new offset/block_size, which gives unexpected data to user. For example, Martijn found a loopback bug in the below scenario. 1) LOOP_SET_FD loads first two pages on loop file 2) LOOP_SET_STATUS64 changes the offset on the loop file 3) mount is failed due to the cached pages having wrong superblock Cc: Jens Axboe Cc: linux-block@vger.kernel.org Reported-by: Martijn Coenen Reviewed-by: Bart Van Assche Signed-off-by: Jaegeuk Kim Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/loop.c | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index e0802d15ace0..c9c2bcc36e26 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1191,6 +1191,12 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) goto out_unlock; } + if (lo->lo_offset != info->lo_offset || + lo->lo_sizelimit != info->lo_sizelimit) { + sync_blockdev(lo->lo_device); + kill_bdev(lo->lo_device); + } + /* I/O need to be drained during transfer transition */ blk_mq_freeze_queue(lo->lo_queue); @@ -1219,6 +1225,14 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { + /* kill_bdev should have truncated all the pages */ + if (lo->lo_device->bd_inode->i_mapping->nrpages) { + err = -EAGAIN; + pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + __func__, lo->lo_number, lo->lo_file_name, + lo->lo_device->bd_inode->i_mapping->nrpages); + goto out_unfreeze; + } if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { err = -EFBIG; goto out_unfreeze; @@ -1444,22 +1458,39 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg) static int loop_set_block_size(struct loop_device *lo, unsigned long arg) { + int err = 0; + if (lo->lo_state != Lo_bound) return -ENXIO; if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg)) return -EINVAL; + if (lo->lo_queue->limits.logical_block_size != arg) { + sync_blockdev(lo->lo_device); + kill_bdev(lo->lo_device); + } + blk_mq_freeze_queue(lo->lo_queue); + /* kill_bdev should have truncated all the pages */ + if (lo->lo_queue->limits.logical_block_size != arg && + lo->lo_device->bd_inode->i_mapping->nrpages) { + err = -EAGAIN; + pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", + __func__, lo->lo_number, lo->lo_file_name, + lo->lo_device->bd_inode->i_mapping->nrpages); + goto out_unfreeze; + } + blk_queue_logical_block_size(lo->lo_queue, arg); blk_queue_physical_block_size(lo->lo_queue, arg); blk_queue_io_min(lo->lo_queue, arg); loop_update_dio(lo); - +out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue); - return 0; + return err; } static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, From 241e514850a1c76b080691077145b67f3a4e8918 Mon Sep 17 00:00:00 2001 From: Ivan Mironov Date: Tue, 8 Jan 2019 12:23:53 +0500 Subject: [PATCH 112/116] drm/fb-helper: Ignore the value of fb_var_screeninfo.pixclock commit 66a8d5bfb518f9f12d47e1d2dce1732279f9451e upstream. Strict requirement of pixclock to be zero breaks support of SDL 1.2 which contains hardcoded table of supported video modes with non-zero pixclock values[1]. To better understand which pixclock values are considered valid and how driver should handle these values, I briefly examined few existing fbdev drivers and documentation in Documentation/fb/. And it looks like there are no strict rules on that and actual behaviour varies: * some drivers treat (pixclock == 0) as "use defaults" (uvesafb.c); * some treat (pixclock == 0) as invalid value which leads to -EINVAL (clps711x-fb.c); * some pass converted pixclock value to hardware (uvesafb.c); * some are trying to find nearest value from predefined table (vga16fb.c, video_gx.c). Given this, I believe that it should be safe to just ignore this value if changing is not supported. It seems that any portable fbdev application which was not written only for one specific device working under one specific kernel version should not rely on any particular behaviour of pixclock anyway. However, while enabling SDL1 applications to work out of the box when there is no /etc/fb.modes with valid settings, this change affects the video mode choosing logic in SDL. Depending on current screen resolution, contents of /etc/fb.modes and resolution requested by application, this may lead to user-visible difference (not always): image will be displayed in a right way, but it will be aligned to the left instead of center. There is no "right behaviour" here as well, as emulated fbdev, opposing to old fbdev drivers, simply ignores any requsts of video mode changes with resolutions smaller than current. The easiest way to reproduce this problem is to install sdl-sopwith[2], remove /etc/fb.modes file if it exists, and then try to run sopwith from console without X. At least in Fedora 29, sopwith may be simply installed from standard repositories. [1] SDL 1.2.15 source code, src/video/fbcon/SDL_fbvideo.c, vesa_timings [2] http://sdl-sopwith.sourceforge.net/ Signed-off-by: Ivan Mironov Cc: stable@vger.kernel.org Fixes: 79e539453b34e ("DRM: i915: add mode setting support") Fixes: 771fe6b912fca ("drm/radeon: introduce kernel modesetting for radeon hardware") Fixes: 785b93ef8c309 ("drm/kms: move driver specific fb common code to helper functions (v2)") Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20190108072353.28078-3-mironov.ivan@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/drm_fb_helper.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index b5b9f15549c2..1bda809a7289 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1690,9 +1690,14 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, struct drm_fb_helper *fb_helper = info->par; struct drm_framebuffer *fb = fb_helper->fb; - if (var->pixclock != 0 || in_dbg_master()) + if (in_dbg_master()) return -EINVAL; + if (var->pixclock != 0) { + DRM_DEBUG("fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n"); + var->pixclock = 0; + } + /* * Changes struct fb_var_screeninfo are currently not pushed back * to KMS, hence fail if different settings are requested. From 7696248f9b5a4670f1e66c26f88a61669f0f95c9 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 12 Dec 2018 20:25:14 -0700 Subject: [PATCH 113/116] selftests: Fix test errors related to lib.mk khdr target commit 211929fd3f7c8de4d541b1cc243b82830e5ea1e8 upstream. Commit b2d35fa5fc80 ("selftests: add headers_install to lib.mk") added khdr target to run headers_install target from the main Makefile. The logic uses KSFT_KHDR_INSTALL and top_srcdir as controls to initialize variables and include files to run headers_install from the top level Makefile. There are a few problems with this logic. 1. Exposes top_srcdir to all tests 2. Common logic impacts all tests 3. Uses KSFT_KHDR_INSTALL, top_srcdir, and khdr in an adhoc way. Tests add "khdr" dependency in their Makefiles to TEST_PROGS_EXTENDED in some cases, and STATIC_LIBS in other cases. This makes this framework confusing to use. The common logic that runs for all tests even when KSFT_KHDR_INSTALL isn't defined by the test. top_srcdir is initialized to a default value when test doesn't initialize it. It works for all tests without a sub-dir structure and tests with sub-dir structure fail to build. e.g: make -C sparc64/drivers/ or make -C drivers/dma-buf ../../lib.mk:20: ../../../../scripts/subarch.include: No such file or directory make: *** No rule to make target '../../../../scripts/subarch.include'. Stop. There is no reason to require all tests to define top_srcdir and there is no need to require tests to add khdr dependency using adhoc changes to TEST_* and other variables. Fix it with a consistent use of KSFT_KHDR_INSTALL and top_srcdir from tests that have the dependency on headers_install. Change common logic to include khdr target define and "all" target with dependency on khdr when KSFT_KHDR_INSTALL is defined. Only tests that have dependency on headers_install have to define just the KSFT_KHDR_INSTALL, and top_srcdir variables and there is no need to specify khdr dependency in the test Makefiles. Fixes: b2d35fa5fc80 ("selftests: add headers_install to lib.mk") Cc: stable@vger.kernel.org Signed-off-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/android/Makefile | 2 +- tools/testing/selftests/futex/functional/Makefile | 1 + tools/testing/selftests/gpio/Makefile | 1 + tools/testing/selftests/kvm/Makefile | 2 +- tools/testing/selftests/lib.mk | 8 ++++---- tools/testing/selftests/networking/timestamping/Makefile | 1 + tools/testing/selftests/vm/Makefile | 1 + 7 files changed, 10 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile index d9a725478375..72c25a3cb658 100644 --- a/tools/testing/selftests/android/Makefile +++ b/tools/testing/selftests/android/Makefile @@ -6,7 +6,7 @@ TEST_PROGS := run.sh include ../lib.mk -all: khdr +all: @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index ad1eeb14fda7..30996306cabc 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -19,6 +19,7 @@ TEST_GEN_FILES := \ TEST_PROGS := run.sh top_srcdir = ../../../../.. +KSFT_KHDR_INSTALL := 1 include ../../lib.mk $(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 4665cdbf1a8d..59ea4c461978 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -9,6 +9,7 @@ EXTRA_OBJS := ../gpiogpio-event-mon-in.o ../gpiogpio-event-mon.o EXTRA_OBJS += ../gpiogpio-hammer-in.o ../gpiogpio-utils.o ../gpiolsgpio-in.o EXTRA_OBJS += ../gpiolsgpio.o +KSFT_KHDR_INSTALL := 1 include ../lib.mk all: $(BINARIES) diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index ec32dad3c3f0..cc83e2fd3787 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -1,6 +1,7 @@ all: top_srcdir = ../../../../ +KSFT_KHDR_INSTALL := 1 UNAME_M := $(shell uname -m) LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c @@ -40,4 +41,3 @@ $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) -$(STATIC_LIBS):| khdr diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 0a8e75886224..8b0f16409ed7 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -16,18 +16,18 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) +ifdef KSFT_KHDR_INSTALL top_srcdir ?= ../../../.. include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) -all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) - .PHONY: khdr khdr: make ARCH=$(ARCH) -C $(top_srcdir) headers_install -ifdef KSFT_KHDR_INSTALL -$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr +all: khdr $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +else +all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) endif .ONESHELL: diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index 14cfcf006936..c46c0eefab9e 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -6,6 +6,7 @@ TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp all: $(TEST_PROGS) top_srcdir = ../../../../.. +KSFT_KHDR_INSTALL := 1 include ../../lib.mk clean: diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index e94b7b14bcb2..dc68340a6a96 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -24,6 +24,7 @@ TEST_GEN_FILES += virtual_address_range TEST_PROGS := run_vmtests +KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/userfaultfd: LDLIBS += -lpthread From 685cc9c3ee488ed5a1218b9c8294f65000bbbc86 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 23 Nov 2018 07:05:58 -0500 Subject: [PATCH 114/116] media: vb2: be sure to unlock mutex on errors commit c06ef2e9acef4cda1feee2ce055b8086e33d251a upstream. As reported by smatch: drivers/media/common/videobuf2/videobuf2-core.c: drivers/media/common/videobuf2/videobuf2-core.c:2159 vb2_mmap() warn: inconsistent returns 'mutex:&q->mmap_lock'. Locked on: line 2148 Unlocked on: line 2100 line 2108 line 2113 line 2118 line 2156 line 2159 There is one error condition that doesn't unlock a mutex. Fixes: cd26d1c4d1bc ("media: vb2: vb2_mmap: move lock up") Reviewed-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Greg Kroah-Hartman --- drivers/media/common/videobuf2/videobuf2-core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 07629e7c15be..6889c25c62cb 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -1960,7 +1960,8 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) if (length < (vma->vm_end - vma->vm_start)) { dprintk(1, "MMAP invalid, as it would overflow buffer length\n"); - return -EINVAL; + ret = -EINVAL; + goto unlock; } ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma); From 9a9c3c02eacecf4bfde74b08ed32749a4929a2cf Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 14 Jan 2019 09:48:09 +0100 Subject: [PATCH 115/116] nbd: Use set_blocksize() to set device blocksize commit c8a83a6b54d0ca078de036aafb3f6af58c1dc5eb upstream. NBD can update block device block size implicitely through bd_set_size(). Make it explicitely set blocksize with set_blocksize() as this behavior of bd_set_size() is going away. CC: Josef Bacik Signed-off-by: Jan Kara Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- drivers/block/nbd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 14a51254c3db..c13a6d1796a7 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -288,9 +288,10 @@ static void nbd_size_update(struct nbd_device *nbd) blk_queue_physical_block_size(nbd->disk->queue, config->blksize); set_capacity(nbd->disk, config->bytesize >> 9); if (bdev) { - if (bdev->bd_disk) + if (bdev->bd_disk) { bd_set_size(bdev, config->bytesize); - else + set_blocksize(bdev, config->blksize); + } else bdev->bd_invalidated = 1; bdput(bdev); } From 23b6b8bf9011dc714e7c66ada789c665261607ac Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 22 Jan 2019 21:40:38 +0100 Subject: [PATCH 116/116] Linux 4.19.17 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e8cb4875b86d..4b0bce87a36b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 19 -SUBLEVEL = 16 +SUBLEVEL = 17 EXTRAVERSION = NAME = "People's Front"