From ee69d4be8fd064cd08270b4808d2dfece3614ee0 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Thu, 7 Apr 2022 15:33:22 +0800 Subject: [PATCH 1/7] xtensa: patch_text: Fixup last cpu should be master These patch_text implementations are using stop_machine_cpuslocked infrastructure with atomic cpu_count. The original idea: When the master CPU patch_text, the others should wait for it. But current implementation is using the first CPU as master, which couldn't guarantee the remaining CPUs are waiting. This patch changes the last CPU as the master to solve the potential risk. Fixes: 64711f9a47d4 ("xtensa: implement jump_label support") Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Max Filippov Reviewed-by: Masami Hiramatsu Cc: Message-Id: <20220407073323.743224-4-guoren@kernel.org> Signed-off-by: Max Filippov --- arch/xtensa/kernel/jump_label.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/kernel/jump_label.c b/arch/xtensa/kernel/jump_label.c index 0dde21e0d3de..ad1841cecdfb 100644 --- a/arch/xtensa/kernel/jump_label.c +++ b/arch/xtensa/kernel/jump_label.c @@ -40,7 +40,7 @@ static int patch_text_stop_machine(void *data) { struct patch *patch = data; - if (atomic_inc_return(&patch->cpu_count) == 1) { + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { local_patch_text(patch->addr, patch->data, patch->sz); atomic_inc(&patch->cpu_count); } else { From eb5adc70754d26a260f8b42d39db42da0d0af500 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Thu, 7 Apr 2022 23:44:30 +0800 Subject: [PATCH 2/7] arch: xtensa: platforms: Fix deadlock in rs_close() There is a deadlock in rs_close(), which is shown below: (Thread 1) | (Thread 2) | rs_open() rs_close() | mod_timer() spin_lock_bh() //(1) | (wait a time) ... | rs_poll() del_timer_sync() | spin_lock() //(2) (wait timer to stop) | ... We hold timer_lock in position (1) of thread 1 and use del_timer_sync() to wait timer to stop, but timer handler also need timer_lock in position (2) of thread 2. As a result, rs_close() will block forever. This patch deletes the redundant timer_lock in order to prevent the deadlock. Because there is no race condition between rs_close, rs_open and rs_poll. Signed-off-by: Duoming Zhou Message-Id: <20220407154430.22387-1-duoming@zju.edu.cn> Signed-off-by: Max Filippov --- arch/xtensa/platforms/iss/console.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 81d7c7e8f7e9..10b79d3c74e0 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -36,24 +36,19 @@ static void rs_poll(struct timer_list *); static struct tty_driver *serial_driver; static struct tty_port serial_port; static DEFINE_TIMER(serial_timer, rs_poll); -static DEFINE_SPINLOCK(timer_lock); static int rs_open(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock_bh(&timer_lock); return 0; } static void rs_close(struct tty_struct *tty, struct file * filp) { - spin_lock_bh(&timer_lock); if (tty->count == 1) del_timer_sync(&serial_timer); - spin_unlock_bh(&timer_lock); } @@ -73,8 +68,6 @@ static void rs_poll(struct timer_list *unused) int rd = 1; unsigned char c; - spin_lock(&timer_lock); - while (simc_poll(0)) { rd = simc_read(0, &c, 1); if (rd <= 0) @@ -87,7 +80,6 @@ static void rs_poll(struct timer_list *unused) tty_flip_buffer_push(port); if (rd) mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); - spin_unlock(&timer_lock); } From 60b30050116c0351b90154044345c1b53ae1f323 Mon Sep 17 00:00:00 2001 From: Hongyu Jin Date: Fri, 1 Apr 2022 19:55:27 +0800 Subject: [PATCH 3/7] erofs: fix use-after-free of on-stack io[] The root cause is the race as follows: Thread #1 Thread #2(irq ctx) z_erofs_runqueue() struct z_erofs_decompressqueue io_A[]; submit bio A z_erofs_decompress_kickoff(,,1) z_erofs_decompressqueue_endio(bio A) z_erofs_decompress_kickoff(,,-1) spin_lock_irqsave() atomic_add_return() io_wait_event() -> pending_bios is already 0 [end of function] wake_up_locked(io_A[]) // crash Referenced backtrace in kernel 5.4: [ 10.129422] Unable to handle kernel paging request at virtual address eb0454a4 [ 10.364157] CPU: 0 PID: 709 Comm: getprop Tainted: G WC O 5.4.147-ab09225 #1 [ 11.556325] [] (__wake_up_common) from [] (__wake_up_locked+0x40/0x48) [ 11.565487] [] (__wake_up_locked) from [] (z_erofs_vle_unzip_kickoff+0x6c/0xc0) [ 11.575438] [] (z_erofs_vle_unzip_kickoff) from [] (z_erofs_vle_read_endio+0x16c/0x17c) [ 11.586082] [] (z_erofs_vle_read_endio) from [] (clone_endio+0xb4/0x1d0) [ 11.595428] [] (clone_endio) from [] (blk_update_request+0x150/0x4dc) [ 11.604516] [] (blk_update_request) from [] (mmc_blk_cqe_complete_rq+0x144/0x15c) [ 11.614640] [] (mmc_blk_cqe_complete_rq) from [] (blk_done_softirq+0xb0/0xcc) [ 11.624419] [] (blk_done_softirq) from [] (__do_softirq+0x184/0x56c) [ 11.633419] [] (__do_softirq) from [] (irq_exit+0xd4/0x138) [ 11.641640] [] (irq_exit) from [] (__handle_domain_irq+0x94/0xd0) [ 11.650381] [] (__handle_domain_irq) from [] (gic_handle_irq+0x50/0xd4) [ 11.659641] [] (gic_handle_irq) from [] (__irq_svc+0x70/0xb0) Signed-off-by: Hongyu Jin Reviewed-by: Gao Xiang Reviewed-by: Chao Yu Link: https://lore.kernel.org/r/20220401115527.4935-1-hongyu.jin.cn@gmail.com Signed-off-by: Gao Xiang --- fs/erofs/zdata.c | 12 ++++-------- fs/erofs/zdata.h | 2 +- 2 files changed, 5 insertions(+), 9 deletions(-) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 0ed880f42525..e6dea6dfca16 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1066,12 +1066,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, /* wake up the caller thread for sync decompression */ if (sync) { - unsigned long flags; - - spin_lock_irqsave(&io->u.wait.lock, flags); if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); + complete(&io->u.done); + return; } @@ -1217,7 +1214,7 @@ jobqueue_init(struct super_block *sb, } else { fg_out: q = fgq; - init_waitqueue_head(&fgq->u.wait); + init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); } q->sb = sb; @@ -1419,8 +1416,7 @@ static void z_erofs_runqueue(struct super_block *sb, return; /* wait until all bios are completed */ - io_wait_event(io[JQ_SUBMIT].u.wait, - !atomic_read(&io[JQ_SUBMIT].pending_bios)); + wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index e043216b545f..800b11c53f57 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -97,7 +97,7 @@ struct z_erofs_decompressqueue { z_erofs_next_pcluster_t head; union { - wait_queue_head_t wait; + struct completion done; struct work_struct work; } u; }; From 8b1ac84dcf2cf0fc86f29e92e5c63c4862de6e55 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 24 Mar 2022 17:59:18 +0100 Subject: [PATCH 4/7] Documentation/ABI: sysfs-fs-erofs: Fix Sphinx errors Fix the following warnings from "make htmldocs": Documentation/ABI/testing/sysfs-fs-erofs:10: ERROR: Unexpected indentation. WARNING: Block quote ends without a blank line; unexpected unindent. Signed-off-by: Hans de Goede Acked-by: Gao Xiang Link: https://lore.kernel.org/r/20220324165918.22005-4-hdegoede@redhat.com Signed-off-by: Gao Xiang --- Documentation/ABI/testing/sysfs-fs-erofs | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-fs-erofs b/Documentation/ABI/testing/sysfs-fs-erofs index 05482374a741..bb4681a01811 100644 --- a/Documentation/ABI/testing/sysfs-fs-erofs +++ b/Documentation/ABI/testing/sysfs-fs-erofs @@ -9,8 +9,9 @@ Description: Shows all enabled kernel features. What: /sys/fs/erofs//sync_decompress Date: November 2021 Contact: "Huang Jianan" -Description: Control strategy of sync decompression +Description: Control strategy of sync decompression: + - 0 (default, auto): enable for readpage, and enable for - readahead on atomic contexts only, + readahead on atomic contexts only. - 1 (force on): enable for readpage and readahead. - 2 (force off): disable for all situations. From 839769c35477d4acc2369e45000ca7b0b6af39a7 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Wed, 13 Apr 2022 22:44:36 -0700 Subject: [PATCH 5/7] xtensa: fix a7 clobbering in coprocessor context load/store Fast coprocessor exception handler saves a3..a6, but coprocessor context load/store code uses a4..a7 as temporaries, potentially clobbering a7. 'Potentially' because coprocessor state load/store macros may not use all four temporary registers (and neither FPU nor HiFi macros do). Use a3..a6 as intended. Cc: stable@vger.kernel.org Fixes: c658eac628aa ("[XTENSA] Add support for configurable registers and coprocessors") Signed-off-by: Max Filippov --- arch/xtensa/kernel/coprocessor.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index 45cc0ae0af6f..c7b9f12896f2 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -29,7 +29,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lsave_cp_regs_cp##x: \ - xchal_cp##x##_store a2 a4 a5 a6 a7; \ + xchal_cp##x##_store a2 a3 a4 a5 a6; \ jx a0; \ .endif @@ -46,7 +46,7 @@ .if XTENSA_HAVE_COPROCESSOR(x); \ .align 4; \ .Lload_cp_regs_cp##x: \ - xchal_cp##x##_load a2 a4 a5 a6 a7; \ + xchal_cp##x##_load a2 a3 a4 a5 a6; \ jx a0; \ .endif From a6823e4e360fe975bd3da4ab156df7c74c8b07f3 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 19 Apr 2022 09:56:23 -0400 Subject: [PATCH 6/7] x86: __memcpy_flushcache: fix wrong alignment if size > 2^32 The first "if" condition in __memcpy_flushcache is supposed to align the "dest" variable to 8 bytes and copy data up to this alignment. However, this condition may misbehave if "size" is greater than 4GiB. The statement min_t(unsigned, size, ALIGN(dest, 8) - dest); casts both arguments to unsigned int and selects the smaller one. However, the cast truncates high bits in "size" and it results in misbehavior. For example: suppose that size == 0x100000001, dest == 0x200000002 min_t(unsigned, size, ALIGN(dest, 8) - dest) == min_t(0x1, 0xe) == 0x1; ... dest += 0x1; so we copy just one byte "and" dest remains unaligned. This patch fixes the bug by replacing unsigned with size_t. Signed-off-by: Mikulas Patocka Signed-off-by: Linus Torvalds --- arch/x86/lib/usercopy_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 0402a749f3a0..0ae6cf804197 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -119,7 +119,7 @@ void __memcpy_flushcache(void *_dst, const void *_src, size_t size) /* cache copy and flush to align dest */ if (!IS_ALIGNED(dest, 8)) { - unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest); + size_t len = min_t(size_t, size, ALIGN(dest, 8) - dest); memcpy((void *) dest, (void *) source, len); clean_cache_range((void *) dest, len); From 906f904097359d059623ca8d3511d9f341080f2c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 20 Apr 2022 12:07:53 -0700 Subject: [PATCH 7/7] Revert "fs/pipe: use kvcalloc to allocate a pipe_buffer array" This reverts commit 5a519c8fe4d620912385f94372fc8472fa98c662. It turns out that making the pipe almost arbitrarily large has some rather unexpected downsides. The kernel test robot reports a kernel warning that is due to pipe->max_usage now growing to the point where the iter_file_splice_write() buffer allocation can no longer be satisfied as a slab allocation, and the int nbufs = pipe->max_usage; struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); code sequence there will now always fail as a result. That code could be modified to use kvcalloc() too, but I feel very uncomfortable making those kinds of changes for a very niche use case that really should have other options than make these kinds of fundamental changes to pipe behavior. Maybe the CRIU process dumping should be multi-threaded, and use multiple pipes and multiple cores, rather than try to use one larger pipe to minimize splice() calls. Reported-by: kernel test robot Link: https://lore.kernel.org/all/20220420073717.GD16310@xsang-OptiPlex-9020/ Cc: Andrei Vagin Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Alexander Viro Cc: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/pipe.c b/fs/pipe.c index 9648ac15164a..e140ea150bbb 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -804,7 +804,7 @@ struct pipe_inode_info *alloc_pipe_info(void) if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; - pipe->bufs = kvcalloc(pipe_bufs, sizeof(struct pipe_buffer), + pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { @@ -849,7 +849,7 @@ void free_pipe_info(struct pipe_inode_info *pipe) #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); - kvfree(pipe->bufs); + kfree(pipe->bufs); kfree(pipe); } @@ -1264,7 +1264,8 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) if (nr_slots < n) return -EBUSY; - bufs = kvcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT); + bufs = kcalloc(nr_slots, sizeof(*bufs), + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; @@ -1291,7 +1292,7 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) head = n; tail = 0; - kvfree(pipe->bufs); + kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots)