- Kernel - mailweb.openeuler.org

[PATCH kernel-4.19] block: error out if blk_get_queue() failed in blk_init_rl()
by Yang Yingliang 20 Jul '21

20 Jul '21

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: 174635 CVE: NA ----------------------------------------------- If blkg creation concurrent with device removal, queue ref might be unbalanced: t1 t2 t3 cgroup_file_write blkg_conf_prep q = disk->queue dm_ctl_ioctl dev_remove blk_cleanup_queue queue_flag_set(QUEUE_FLAG_DYING, q) blkg_alloc blk_init_cl blk_get_queue -> failed blk_exit_queue blkcg_exit_queue blkg_destroy_all blkg_destroy call_rcu(&blkg->rcu_head, __blkg_release_rcu); __blkg_release_rcu blkg_free blk_exit_rl blk_put_queue -> extra put Thus error out if blk_get_queue() failed in blk_init_rl(), since there is no need to create blkg while queue is dying. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 93970be37c17c..4b63336465306 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -888,8 +888,11 @@ int blk_init_rl(struct request_list *rl, struct request_queue *q, if (!rl->rq_pool) return -ENOMEM; - if (rl != &q->root_rl) - WARN_ON_ONCE(!blk_get_queue(q)); + if (rl != &q->root_rl && !blk_get_queue(q)) { + mempool_destroy(rl->rq_pool); + rl->rq_pool = NULL; + return -ENODEV; + } return 0; } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] Revert "vt: Fix character height handling with VT_RESIZEX"
by Yang Yingliang 20 Jul '21

20 Jul '21

hulk inclusion category: bugfix bugzilla: NA CVE: NA -------------------------------- This reverts commit cb173fc207d51b6781dc059c84b3f3a4fa309b56 to avoid kabi broken. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/tty/vt/vt_ioctl.c | 6 ++--- drivers/video/console/vgacon.c | 44 +++++++++++++++++----------------- include/linux/console_struct.h | 1 - 3 files changed, 25 insertions(+), 26 deletions(-) diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index ce6c7dd7bc126..2e959563af534 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -895,17 +895,17 @@ int vt_ioctl(struct tty_struct *tty, if (vcp) { int ret; int save_scan_lines = vcp->vc_scan_lines; - int save_cell_height = vcp->vc_cell_height; + int save_font_height = vcp->vc_font.height; if (v.v_vlin) vcp->vc_scan_lines = v.v_vlin; if (v.v_clin) - vcp->vc_cell_height = v.v_clin; + vcp->vc_font.height = v.v_clin; vcp->vc_resize_user = 1; ret = vc_resize(vcp, v.v_cols, v.v_rows); if (ret) { vcp->vc_scan_lines = save_scan_lines; - vcp->vc_cell_height = save_cell_height; + vcp->vc_font.height = save_font_height; console_unlock(); return ret; } diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index a992d922b3a71..4509d0547087a 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -384,7 +384,7 @@ static void vgacon_init(struct vc_data *c, int init) vc_resize(c, vga_video_num_columns, vga_video_num_lines); c->vc_scan_lines = vga_scan_lines; - c->vc_font.height = c->vc_cell_height = vga_video_font_height; + c->vc_font.height = vga_video_font_height; c->vc_complement_mask = 0x7700; if (vga_512_chars) c->vc_hi_font_mask = 0x0800; @@ -517,32 +517,32 @@ static void vgacon_cursor(struct vc_data *c, int mode) switch (c->vc_cursor_type & 0x0f) { case CUR_UNDERLINE: vgacon_set_cursor_size(c->vc_x, - c->vc_cell_height - - (c->vc_cell_height < + c->vc_font.height - + (c->vc_font.height < 10 ? 2 : 3), - c->vc_cell_height - - (c->vc_cell_height < + c->vc_font.height - + (c->vc_font.height < 10 ? 1 : 2)); break; case CUR_TWO_THIRDS: vgacon_set_cursor_size(c->vc_x, - c->vc_cell_height / 3, - c->vc_cell_height - - (c->vc_cell_height < + c->vc_font.height / 3, + c->vc_font.height - + (c->vc_font.height < 10 ? 1 : 2)); break; case CUR_LOWER_THIRD: vgacon_set_cursor_size(c->vc_x, - (c->vc_cell_height * 2) / 3, - c->vc_cell_height - - (c->vc_cell_height < + (c->vc_font.height * 2) / 3, + c->vc_font.height - + (c->vc_font.height < 10 ? 1 : 2)); break; case CUR_LOWER_HALF: vgacon_set_cursor_size(c->vc_x, - c->vc_cell_height / 2, - c->vc_cell_height - - (c->vc_cell_height < + c->vc_font.height / 2, + c->vc_font.height - + (c->vc_font.height < 10 ? 1 : 2)); break; case CUR_NONE: @@ -553,7 +553,7 @@ static void vgacon_cursor(struct vc_data *c, int mode) break; default: vgacon_set_cursor_size(c->vc_x, 1, - c->vc_cell_height); + c->vc_font.height); break; } break; @@ -564,13 +564,13 @@ static int vgacon_doresize(struct vc_data *c, unsigned int width, unsigned int height) { unsigned long flags; - unsigned int scanlines = height * c->vc_cell_height; + unsigned int scanlines = height * c->vc_font.height; u8 scanlines_lo = 0, r7 = 0, vsync_end = 0, mode, max_scan; raw_spin_lock_irqsave(&vga_lock, flags); vgacon_xres = width * VGA_FONTWIDTH; - vgacon_yres = height * c->vc_cell_height; + vgacon_yres = height * c->vc_font.height; if (vga_video_type >= VIDEO_TYPE_VGAC) { outb_p(VGA_CRTC_MAX_SCAN, vga_video_port_reg); max_scan = inb_p(vga_video_port_val); @@ -625,9 +625,9 @@ static int vgacon_doresize(struct vc_data *c, static int vgacon_switch(struct vc_data *c) { int x = c->vc_cols * VGA_FONTWIDTH; - int y = c->vc_rows * c->vc_cell_height; + int y = c->vc_rows * c->vc_font.height; int rows = screen_info.orig_video_lines * vga_default_font_height/ - c->vc_cell_height; + c->vc_font.height; /* * We need to save screen size here as it's the only way * we can spot the screen has been resized and we need to @@ -1058,7 +1058,7 @@ static int vgacon_adjust_height(struct vc_data *vc, unsigned fontheight) cursor_size_lastto = 0; c->vc_sw->con_cursor(c, CM_DRAW); } - c->vc_font.height = c->vc_cell_height = fontheight; + c->vc_font.height = fontheight; vc_resize(c, 0, rows); /* Adjust console size */ } } @@ -1113,12 +1113,12 @@ static int vgacon_resize(struct vc_data *c, unsigned int width, */ screen_info.orig_video_cols = width; screen_info.orig_video_lines = height; - vga_default_font_height = c->vc_cell_height; + vga_default_font_height = c->vc_font.height; return 0; } if (width % 2 || width > screen_info.orig_video_cols || height > (screen_info.orig_video_lines * vga_default_font_height)/ - c->vc_cell_height) + c->vc_font.height) return -EINVAL; if (con_is_visible(c) && !vga_is_gfx) /* who knows */ diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 8b5bc3a47bf5f..fea64f2692a05 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -62,7 +62,6 @@ struct vc_data { unsigned int vc_rows; unsigned int vc_size_row; /* Bytes per row */ unsigned int vc_scan_lines; /* # of scan lines */ - unsigned int vc_cell_height; /* CRTC character cell height */ unsigned long vc_origin; /* [!] Start of real screen */ unsigned long vc_scr_end; /* [!] End of real screen */ unsigned long vc_visible_origin; /* [!] Top of visible window */ -- 2.25.1

1 1

[PATCH kernel-4.19] block: only call sched requeue_request() for scheduled requests
by Yang Yingliang 20 Jul '21

20 Jul '21

From: Omar Sandoval <osandov(a)fb.com> mainline inclusion from mainline-5.9-rc5 commit e8a8a185051a460e3eb0617dca33f996f4e31516 category: bugfix bugzilla: 172928 CVE: NA --------------------------- Yang Yang reported the following crash caused by requeueing a flush request in Kyber: [ 2.517297] Unable to handle kernel paging request at virtual address ffffffd8071c0b00 ... [ 2.517468] pc : clear_bit+0x18/0x2c [ 2.517502] lr : sbitmap_queue_clear+0x40/0x228 [ 2.517503] sp : ffffff800832bc60 pstate : 00c00145 ... [ 2.517599] Process ksoftirqd/5 (pid: 51, stack limit = 0xffffff8008328000) [ 2.517602] Call trace: [ 2.517606] clear_bit+0x18/0x2c [ 2.517619] kyber_finish_request+0x74/0x80 [ 2.517627] blk_mq_requeue_request+0x3c/0xc0 [ 2.517637] __scsi_queue_insert+0x11c/0x148 [ 2.517640] scsi_softirq_done+0x114/0x130 [ 2.517643] blk_done_softirq+0x7c/0xb0 [ 2.517651] __do_softirq+0x208/0x3bc [ 2.517657] run_ksoftirqd+0x34/0x60 [ 2.517663] smpboot_thread_fn+0x1c4/0x2c0 [ 2.517667] kthread+0x110/0x120 [ 2.517669] ret_from_fork+0x10/0x18 This happens because Kyber doesn't track flush requests, so kyber_finish_request() reads a garbage domain token. Only call the scheduler's requeue_request() hook if RQF_ELVPRIV is set (like we do for the finish_request() hook in blk_mq_free_request()). Now that we're handling it in blk-mq, also remove the check from BFQ. Reported-by: Yang Yang <yang.yang(a)vivo.com> Signed-off-by: Omar Sandoval <osandov(a)fb.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflicts: block/blk-mq-sched.h [ Cleanup patch 67cae4c948("blk-mq: cleanup and improve list insertion") is not applied. ] Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/bfq-iosched.c | 12 ------------ block/blk-mq-sched.h | 2 +- 2 files changed, 1 insertion(+), 13 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index a214c95f071ad..c15e2c112ea8a 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4867,18 +4867,6 @@ static void bfq_finish_requeue_request(struct request *rq) struct bfq_queue *bfqq = RQ_BFQQ(rq); struct bfq_data *bfqd; - /* - * Requeue and finish hooks are invoked in blk-mq without - * checking whether the involved request is actually still - * referenced in the scheduler. To handle this fact, the - * following two checks make this function exit in case of - * spurious invocations, for which there is nothing to do. - * - * First, check whether rq has nothing to do with an elevator. - */ - if (unlikely(!(rq->rq_flags & RQF_ELVPRIV))) - return; - /* * rq either is not associated with any icq, or is an already * requeued request that has not (yet) been re-inserted into diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index fe660764b8d13..011445f7852bf 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -72,7 +72,7 @@ static inline void blk_mq_sched_requeue_request(struct request *rq) struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; - if (e && e->type->ops.mq.requeue_request) + if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.mq.requeue_request) e->type->ops.mq.requeue_request(rq); } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] KVM: arm/arm64: Drop the WARN_ON() in probe_hisi_cpu_type()
by Zenghui Yu 19 Jul '21

19 Jul '21

virt inclusion category: bugfix bugzilla: NA CVE: NA ----------------------------------------------- I used WARN_ON(hi_cpu_type == UNKNOWN_HI_TYPE) to catch some probing issues about 2 years ago, when the HiSilicon servers are the only available arm64 boxes to me. However it's obvious that this can be hit if we're playing with other kinds of boards (or with L1 guests in NV), which ends up with a boot failure if warn_on_panic is set. Given that hi_cpu_type is only used in the probing of (HiSilicon specific) ncsnp (and there's already a hint for it in probe_hisi_ncsnp_support()), let's drop the unnecessary WARN_ON() and use a kvm_debug() instead. Reported-by: zou_wei(a)huawei.com Signed-off-by: Zenghui Yu <yuzenghui(a)huawei.com> --- virt/kvm/arm/hisi_cpu_model.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/virt/kvm/arm/hisi_cpu_model.c b/virt/kvm/arm/hisi_cpu_model.c index b0f7e0d7ef1c..6fd91b538100 100644 --- a/virt/kvm/arm/hisi_cpu_model.c +++ b/virt/kvm/arm/hisi_cpu_model.c @@ -78,7 +78,8 @@ void probe_hisi_cpu_type(void) else of_get_hw_cpu_type(); - WARN_ON(hi_cpu_type == UNKNOWN_HI_TYPE); + /* UNKNOWN_HI_TYPE is not fatal */ + kvm_debug("HiSilicon CPU type [%u] detected\n", hi_cpu_type); } #define NCSNP_MMIO_BASE 0x20107E238 -- 2.19.1

1 0

[PATCH openEuler-1.0-LTS 01/60] efi: Allow EFI_MEMORY_XP and EFI_MEMORY_RO both to be cleared
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Heiner Kallweit <hkallweit1(a)gmail.com> stable inclusion from linux-4.19.194 commit 5fdb418b14e41b33880b949db64b18f1f448916b -------------------------------- [ Upstream commit 45add3cc99feaaf57d4b6f01d52d532c16a1caee ] UEFI spec 2.9, p.108, table 4-1 lists the scenario that both attributes are cleared with the description "No memory access protection is possible for Entry". So we can have valid entries where both attributes are cleared, so remove the check. Signed-off-by: Heiner Kallweit <hkallweit1(a)gmail.com> Fixes: 10f0d2f577053 ("efi: Implement generic support for the Memory Attributes table") Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/firmware/efi/memattr.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index aac972b056d91..e0889922cc6d7 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -69,11 +69,6 @@ static bool entry_is_valid(const efi_memory_desc_t *in, efi_memory_desc_t *out) return false; } - if (!(in->attribute & (EFI_MEMORY_RO | EFI_MEMORY_XP))) { - pr_warn("Entry attributes invalid: RO and XP bits both cleared\n"); - return false; - } - if (PAGE_SIZE > EFI_PAGE_SIZE && (!PAGE_ALIGNED(in->phys_addr) || !PAGE_ALIGNED(in->num_pages << EFI_PAGE_SHIFT))) { -- 2.25.1

1 59

【Meeting Notice】openEuler kernel 技术分享第八期 & 双周例会 Time: 2021-07-23 14:00-18:00
by Meeting Book 19 Jul '21

19 Jul '21

1 0

[PATCH kernel-4.19] lib/clear_user: ensure loop in __arch_clear_user cache-aligned
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Cheng Jian <cj.chengjian(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I3OX0C CVE: #682 -------------------------------- We must ensure that the following four instructions are cache-aligned. Otherwise, it will cause problems with the performance of libMicro pread. 1: # uao_user_alternative 9f, str, sttr, xzr, x0, 8 str xzr, [x0], #8 nop subs x1, x1, #8 b.pl 1b with this patch: prc thr usecs/call samples errors cnt/samp size pread_z100 1 1 5.88400 807 0 1 102400 The result of pread can range from 5 to 9 depending on the alignment performance of this function. Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/lib/clear_user.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 4374020c824a0..9ebc5d84e6154 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -20,7 +20,7 @@ #include <asm/asm-uaccess.h> .text - + .align 6 /* Prototype: int __arch_clear_user(void *addr, size_t sz) * Purpose : clear some user memory * Params : addr - user memory address to clear -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/3] ext4: fix WARN_ON_ONCE(!buffer_uptodate) after an error writing the superblock
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v5.14-rc1 commit 558d6450c7755aa005d89021204b6cdcae5e848f category: bugfix bugzilla: 109280 CVE: NA ----------------------------------------------- If a writeback of the superblock fails with an I/O error, the buffer is marked not uptodate. However, this can cause a WARN_ON to trigger when we attempt to write superblock a second time. (Which might succeed this time, for cerrtain types of block devices such as iSCSI devices over a flaky network.) Try to detect this case in flush_stashed_error_work(), and also change __ext4_handle_dirty_metadata() so we always set the uptodate flag, not just in the nojournal case. Before this commit, this problem can be repliciated via: 1. dmsetup create dust1 --table '0 2097152 dust /dev/sdc 0 4096' 2. mount /dev/mapper/dust1 /home/test 3. dmsetup message dust1 0 addbadblock 0 10 4. cd /home/test 5. echo "XXXXXXX" > t After a few seconds, we got following warning: [ 80.654487] end_buffer_async_write: bh=0xffff88842f18bdd0 [ 80.656134] Buffer I/O error on dev dm-0, logical block 0, lost async page write [ 85.774450] EXT4-fs error (device dm-0): ext4_check_bdev_write_error:193: comm kworker/u16:8: Error while async write back metadata [ 91.415513] mark_buffer_dirty: bh=0xffff88842f18bdd0 [ 91.417038] ------------[ cut here ]------------ [ 91.418450] WARNING: CPU: 1 PID: 1944 at fs/buffer.c:1092 mark_buffer_dirty.cold+0x1c/0x5e [ 91.440322] Call Trace: [ 91.440652] __jbd2_journal_temp_unlink_buffer+0x135/0x220 [ 91.441354] __jbd2_journal_unfile_buffer+0x24/0x90 [ 91.441981] __jbd2_journal_refile_buffer+0x134/0x1d0 [ 91.442628] jbd2_journal_commit_transaction+0x249a/0x3240 [ 91.443336] ? put_prev_entity+0x2a/0x200 [ 91.443856] ? kjournald2+0x12e/0x510 [ 91.444324] kjournald2+0x12e/0x510 [ 91.444773] ? woken_wake_function+0x30/0x30 [ 91.445326] kthread+0x150/0x1b0 [ 91.445739] ? commit_timeout+0x20/0x20 [ 91.446258] ? kthread_flush_worker+0xb0/0xb0 [ 91.446818] ret_from_fork+0x1f/0x30 [ 91.447293] ---[ end trace 66f0b6bf3d1abade ]--- Signed-off-by: Ye Bin <yebin10(a)huawei.com> Link: https://lore.kernel.org/r/20210615090537.3423231-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/ext4_jbd2.c | 2 +- fs/ext4/super.c | 12 ++++++++++-- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index fd7c41da1f8f9..022ab8afd9499 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -304,6 +304,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, set_buffer_meta(bh); set_buffer_prio(bh); + set_buffer_uptodate(bh); if (ext4_handle_valid(handle)) { err = jbd2_journal_dirty_metadata(handle, bh); /* Errors can only happen due to aborted journal or a nasty bug */ @@ -332,7 +333,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, err); } } else { - set_buffer_uptodate(bh); if (inode) mark_buffer_dirty_inode(bh, inode); else diff --git a/fs/ext4/super.c b/fs/ext4/super.c index fd67f3037fb8e..dd96627ec6ae4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -695,15 +695,23 @@ static void flush_stashed_error_work(struct work_struct *work) * ext4 error handling code during handling of previous errors. */ if (!sb_rdonly(sbi->s_sb) && journal) { + struct buffer_head *sbh = sbi->s_sbh; handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; - if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) { + if (jbd2_journal_get_write_access(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } ext4_update_super(sbi->s_sb); - if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) { + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { + ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " + "superblock detected"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } + + if (jbd2_journal_dirty_metadata(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } -- 2.25.1

1 2

[PATCH kernel-4.19 1/3] ext4: fix WARN_ON_ONCE(!buffer_uptodate) after an error writing the superblock
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v5.14-rc1 commit 558d6450c7755aa005d89021204b6cdcae5e848f category: bugfix bugzilla: 109280 CVE: NA ----------------------------------------------- If a writeback of the superblock fails with an I/O error, the buffer is marked not uptodate. However, this can cause a WARN_ON to trigger when we attempt to write superblock a second time. (Which might succeed this time, for cerrtain types of block devices such as iSCSI devices over a flaky network.) Try to detect this case in flush_stashed_error_work(), and also change __ext4_handle_dirty_metadata() so we always set the uptodate flag, not just in the nojournal case. Before this commit, this problem can be repliciated via: 1. dmsetup create dust1 --table '0 2097152 dust /dev/sdc 0 4096' 2. mount /dev/mapper/dust1 /home/test 3. dmsetup message dust1 0 addbadblock 0 10 4. cd /home/test 5. echo "XXXXXXX" > t After a few seconds, we got following warning: [ 80.654487] end_buffer_async_write: bh=0xffff88842f18bdd0 [ 80.656134] Buffer I/O error on dev dm-0, logical block 0, lost async page write [ 85.774450] EXT4-fs error (device dm-0): ext4_check_bdev_write_error:193: comm kworker/u16:8: Error while async write back metadata [ 91.415513] mark_buffer_dirty: bh=0xffff88842f18bdd0 [ 91.417038] ------------[ cut here ]------------ [ 91.418450] WARNING: CPU: 1 PID: 1944 at fs/buffer.c:1092 mark_buffer_dirty.cold+0x1c/0x5e [ 91.440322] Call Trace: [ 91.440652] __jbd2_journal_temp_unlink_buffer+0x135/0x220 [ 91.441354] __jbd2_journal_unfile_buffer+0x24/0x90 [ 91.441981] __jbd2_journal_refile_buffer+0x134/0x1d0 [ 91.442628] jbd2_journal_commit_transaction+0x249a/0x3240 [ 91.443336] ? put_prev_entity+0x2a/0x200 [ 91.443856] ? kjournald2+0x12e/0x510 [ 91.444324] kjournald2+0x12e/0x510 [ 91.444773] ? woken_wake_function+0x30/0x30 [ 91.445326] kthread+0x150/0x1b0 [ 91.445739] ? commit_timeout+0x20/0x20 [ 91.446258] ? kthread_flush_worker+0xb0/0xb0 [ 91.446818] ret_from_fork+0x1f/0x30 [ 91.447293] ---[ end trace 66f0b6bf3d1abade ]--- Signed-off-by: Ye Bin <yebin10(a)huawei.com> Link: https://lore.kernel.org/r/20210615090537.3423231-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/ext4_jbd2.c | 2 +- fs/ext4/super.c | 12 ++++++++++-- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index fd7c41da1f8f9..022ab8afd9499 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -304,6 +304,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, set_buffer_meta(bh); set_buffer_prio(bh); + set_buffer_uptodate(bh); if (ext4_handle_valid(handle)) { err = jbd2_journal_dirty_metadata(handle, bh); /* Errors can only happen due to aborted journal or a nasty bug */ @@ -332,7 +333,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, err); } } else { - set_buffer_uptodate(bh); if (inode) mark_buffer_dirty_inode(bh, inode); else diff --git a/fs/ext4/super.c b/fs/ext4/super.c index fd67f3037fb8e..dd96627ec6ae4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -695,15 +695,23 @@ static void flush_stashed_error_work(struct work_struct *work) * ext4 error handling code during handling of previous errors. */ if (!sb_rdonly(sbi->s_sb) && journal) { + struct buffer_head *sbh = sbi->s_sbh; handle = jbd2_journal_start(journal, 1); if (IS_ERR(handle)) goto write_directly; - if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) { + if (jbd2_journal_get_write_access(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } ext4_update_super(sbi->s_sb); - if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) { + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { + ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " + "superblock detected"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } + + if (jbd2_journal_dirty_metadata(handle, sbh)) { jbd2_journal_stop(handle); goto write_directly; } -- 2.25.1

1 2

[PATCH kernel-4.19] arm64/config: Set CONFIG_TXGBE=m by default
by Yang Yingliang 19 Jul '21

19 Jul '21

From: zhenpengzheng <zhenpengzheng(a)net-swift.com> hulk inclusion category: feature bugzilla: 50777 CVE: NA ------------------------------------------------------------------------- Ensure the netswift 10G NIC driver ko can be distributed in ISO on X86. Signed-off-by: zhenpengzheng <zhenpengzheng(a)net-swift.com> Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 1e1f7f3201028..8cfe2c3cd7dde 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -2489,6 +2489,8 @@ CONFIG_HNS3_CAE=m CONFIG_NET_VENDOR_HUAWEI=y CONFIG_HINIC=m CONFIG_BMA=m +CONFIG_NET_VENDOR_NETSWIFT=y +CONFIG_TXGBE=m # CONFIG_NET_VENDOR_I825XX is not set CONFIG_NET_VENDOR_INTEL=y # CONFIG_E100 is not set -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/4] Add traffic policy for low cache available.
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Xu Wei <xuwei56(a)huawei.com> euleros inclusion category: feature bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=327 CVE: NA When cache available is low, bcache turn to writethrough mode. Therefore, All write IO will be directly sent to backend device, which is usually HDD. At same time, cache device flush dirty data to the backend device in the bcache writeback process. So write IO from user will damage the sequentiality of writeback. And if there is lots of IO from writeback, user's write IO may be block. This patch add traffic policy in bcache to solve the problem and improve the performance for bcache when cache available is low. Signed-off-by: qinghaixiang <xuweiqhx(a)163.com> Signed-off-by: Xu Wei <xuwei56(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Reviewed-by: Li Ruilin <liruilin4(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/md/bcache/bcache.h | 49 ++++++++++++ drivers/md/bcache/btree.h | 6 +- drivers/md/bcache/request.c | 143 +++++++++++++++++++++++++++++++++- drivers/md/bcache/request.h | 2 + drivers/md/bcache/super.c | 35 +++++++++ drivers/md/bcache/sysfs.c | 56 +++++++++++++ drivers/md/bcache/writeback.c | 11 ++- drivers/md/bcache/writeback.h | 6 +- 8 files changed, 300 insertions(+), 8 deletions(-) diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 99d12fce876b2..70fbde8ca70c9 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -399,6 +399,28 @@ struct cached_dev { unsigned int offline_seconds; char backing_dev_name[BDEVNAME_SIZE]; + + /* Count the front and writeback io bandwidth per second */ + atomic_t writeback_sector_size; + atomic_t writeback_io_num; + atomic_t front_io_num; + unsigned int writeback_sector_size_per_sec; + unsigned int writeback_io_num_per_sec; + unsigned int front_io_num_per_sec; + struct timer_list io_stat_timer; + + unsigned int writeback_state; +#define WRITEBACK_DEFAULT 0 +#define WRITEBACK_QUICK 1 +#define WRITEBACK_SLOW 2 + + /* realize for token bucket */ + spinlock_t token_lock; + unsigned int max_sector_size; + unsigned int max_io_num; + unsigned int write_token_sector_size; + unsigned int write_token_io_num; + struct timer_list token_assign_timer; }; enum alloc_reserve { @@ -717,6 +739,10 @@ struct cache_set { #define BUCKET_HASH_BITS 12 struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS]; + unsigned int cutoff_writeback_sync; + bool traffic_policy_start; + bool force_write_through; + unsigned int gc_sectors; }; struct bbio { @@ -732,6 +758,29 @@ struct bbio { struct bio bio; }; +struct get_bcache_status { + unsigned int writeback_sector_size_per_sec; + unsigned int writeback_io_num_per_sec; + unsigned int front_io_num_per_sec; + uint64_t dirty_rate; + unsigned int available; +}; + +struct set_bcache_status { + unsigned int write_token_sector_size; + unsigned int write_token_io_num; + bool traffic_policy_start; + bool force_write_through; + bool copy_gc_enabled; + bool trigger_gc; + unsigned int writeback_state; + unsigned int gc_sectors; + unsigned int cutoff_writeback_sync; +}; +#define BCACHE_MAJOR 'B' +#define BCACHE_GET_WRITE_STATUS _IOR(BCACHE_MAJOR, 0x0, struct get_bcache_status) +#define BCACHE_SET_WRITE_STATUS _IOW(BCACHE_MAJOR, 0x1, struct set_bcache_status) + #define BTREE_PRIO USHRT_MAX #define INITIAL_PRIO 32768U diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 4d0cca145f699..7ddadcc485ea6 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -193,7 +193,11 @@ static inline unsigned int bset_block_offset(struct btree *b, struct bset *i) static inline void set_gc_sectors(struct cache_set *c) { - atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 16); + if (c->gc_sectors == 0) + atomic_set(&c->sectors_to_gc, + c->sb.bucket_size * c->nbuckets / 16); + else + atomic_set(&c->sectors_to_gc, c->gc_sectors); } void bkey_put(struct cache_set *c, struct bkey *k); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 6d89e56a4a410..c05544e07722e 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -28,6 +28,7 @@ struct kmem_cache *bch_search_cache; static void bch_data_insert_start(struct closure *cl); +static void alloc_token(struct cached_dev *dc, unsigned int sectors); static unsigned int cache_mode(struct cached_dev *dc) { @@ -396,7 +397,8 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) goto skip; if (mode == CACHE_MODE_NONE || - (mode == CACHE_MODE_WRITEAROUND && + ((mode == CACHE_MODE_WRITEAROUND || + c->force_write_through == true) && op_is_write(bio_op(bio)))) goto skip; @@ -858,6 +860,10 @@ static void cached_dev_read_done(struct closure *cl) if (s->iop.bio && (!dc->read_bypass || s->prefetch) && !test_bit(CACHE_SET_STOPPING, &s->iop.c->flags)) { BUG_ON(!s->iop.replace); + if ((dc->disk.c->traffic_policy_start == true) && + (dc->disk.c->force_write_through != true)) { + alloc_token(dc, bio_sectors(s->iop.bio)); + } closure_call(&s->iop.cl, bch_data_insert, NULL, cl); } @@ -1000,6 +1006,35 @@ static void cached_dev_write_complete(struct closure *cl) continue_at(cl, cached_dev_bio_complete, NULL); } +static void alloc_token(struct cached_dev *dc, unsigned int sectors) +{ + int count = 0; + + spin_lock_bh(&dc->token_lock); + + while ((dc->write_token_sector_size < sectors) && + (dc->write_token_io_num == 0)) { + spin_unlock_bh(&dc->token_lock); + schedule_timeout_interruptible(msecs_to_jiffies(10)); + count++; + if ((dc->disk.c->traffic_policy_start != true) || + (cache_mode(dc) != CACHE_MODE_WRITEBACK) || + (count > 100)) + return; + spin_lock_bh(&dc->token_lock); + } + + if (dc->write_token_sector_size >= sectors) + dc->write_token_sector_size -= sectors; + else + dc->write_token_sector_size = 0; + + if (dc->write_token_io_num > 0) + dc->write_token_io_num--; + + spin_unlock_bh(&dc->token_lock); +} + static void cached_dev_write(struct cached_dev *dc, struct search *s) { struct closure *cl = &s->cl; @@ -1247,6 +1282,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, cached_dev_nodata, bcache_wq); } else { + atomic_inc(&dc->front_io_num); s->iop.bypass = check_should_bypass(dc, bio); if (!s->iop.bypass && bio->bi_iter.bi_size && !rw) { @@ -1258,10 +1294,17 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, save_circ_item(&s->smp); } - if (rw) + if (rw) { + if ((s->iop.bypass == false) && + (dc->disk.c->traffic_policy_start == true) && + (cache_mode(dc) == CACHE_MODE_WRITEBACK) && + (bio_op(bio) != REQ_OP_DISCARD)) { + alloc_token(dc, bio_sectors(bio)); + } cached_dev_write(dc, s); - else + } else { cached_dev_read(dc, s); + } } } else /* I/O request sent to backing device */ @@ -1270,6 +1313,65 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, return BLK_QC_T_NONE; } +static int bcache_get_write_status(struct cached_dev *dc, unsigned long arg) +{ + struct get_bcache_status a; + uint64_t cache_sectors; + struct cache_set *c = dc->disk.c; + + if (c == NULL) + return -ENODEV; + + a.writeback_sector_size_per_sec = dc->writeback_sector_size_per_sec; + a.writeback_io_num_per_sec = dc->writeback_io_num_per_sec; + a.front_io_num_per_sec = dc->front_io_num_per_sec; + cache_sectors = c->nbuckets * c->sb.bucket_size - + atomic_long_read(&c->flash_dev_dirty_sectors); + a.dirty_rate = div64_u64(bcache_dev_sectors_dirty(&dc->disk) * 100, + cache_sectors); + a.available = 100 - c->gc_stats.in_use; + if (copy_to_user((struct get_bcache_status *)arg, &a, + sizeof(struct get_bcache_status))) + return -EFAULT; + return 0; +} + +static int bcache_set_write_status(struct cached_dev *dc, unsigned long arg) +{ + struct set_bcache_status a; + struct cache_set *c = dc->disk.c; + + if (c == NULL) + return -ENODEV; + if (copy_from_user(&a, (struct set_bcache_status *)arg, + sizeof(struct set_bcache_status))) + return -EFAULT; + + if (c->traffic_policy_start != a.traffic_policy_start) + pr_info("%s traffic policy %s", dc->disk.disk->disk_name, + (a.traffic_policy_start == true) ? "enable" : "disable"); + if (c->force_write_through != a.force_write_through) + pr_info("%s force write through %s", dc->disk.disk->disk_name, + (a.force_write_through == true) ? "enable" : "disable"); + if (a.trigger_gc) { + pr_info("trigger %s gc", dc->disk.disk->disk_name); + atomic_set(&c->sectors_to_gc, -1); + wake_up_gc(c); + } + if ((a.cutoff_writeback_sync >= MIN_CUTOFF_WRITEBACK_SYNC) && + (a.cutoff_writeback_sync <= MAX_CUTOFF_WRITEBACK_SYNC)) { + c->cutoff_writeback_sync = a.cutoff_writeback_sync; + } + + dc->max_sector_size = a.write_token_sector_size; + dc->max_io_num = a.write_token_io_num; + c->traffic_policy_start = a.traffic_policy_start; + c->force_write_through = a.force_write_through; + c->gc_sectors = a.gc_sectors; + dc->writeback_state = a.writeback_state; + return 0; +} + static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1278,7 +1380,14 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, if (dc->io_disable) return -EIO; - return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + switch (cmd) { + case BCACHE_GET_WRITE_STATUS: + return bcache_get_write_status(dc, arg); + case BCACHE_SET_WRITE_STATUS: + return bcache_set_write_status(dc, arg); + default: + return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + } } static int cached_dev_congested(void *data, int bits) @@ -1438,3 +1547,29 @@ int __init bch_request_init(void) return 0; } + +static void token_assign(struct timer_list *t) +{ + struct cached_dev *dc = from_timer(dc, t, token_assign_timer); + + dc->token_assign_timer.expires = jiffies + HZ / 8; + add_timer(&dc->token_assign_timer); + + spin_lock(&dc->token_lock); + dc->write_token_sector_size = dc->max_sector_size / 8; + dc->write_token_io_num = dc->max_io_num / 8; + dc->write_token_io_num = + (dc->write_token_io_num == 0) ? 1 : dc->write_token_io_num; + spin_unlock(&dc->token_lock); +} + +void bch_traffic_policy_init(struct cached_dev *dc) +{ + spin_lock_init(&dc->token_lock); + dc->write_token_sector_size = 0; + dc->write_token_io_num = 0; + + timer_setup(&dc->token_assign_timer, token_assign, 0); + dc->token_assign_timer.expires = jiffies + HZ / 8; + add_timer(&dc->token_assign_timer); +} diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 3667bc5390dfe..f677ba8704940 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -41,6 +41,8 @@ void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); void bch_flash_dev_request_init(struct bcache_device *d); +void bch_traffic_policy_init(struct cached_dev *dc); + extern struct kmem_cache *bch_search_cache, *bch_passthrough_cache; struct search { diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index e7f7a0f038682..3f858de9e9602 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1210,6 +1210,8 @@ static void cached_dev_free(struct closure *cl) { struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl); + del_timer_sync(&dc->io_stat_timer); + del_timer_sync(&dc->token_assign_timer); if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)) cancel_writeback_rate_update_dwork(dc); @@ -1250,6 +1252,36 @@ static void cached_dev_flush(struct closure *cl) continue_at(cl, cached_dev_free, system_wq); } +static void cached_dev_io_stat(struct timer_list *t) +{ + struct cached_dev *dc = from_timer(dc, t, io_stat_timer); + + dc->io_stat_timer.expires = jiffies + HZ; + add_timer(&dc->io_stat_timer); + + dc->writeback_sector_size_per_sec = + atomic_read(&dc->writeback_sector_size); + dc->writeback_io_num_per_sec = atomic_read(&dc->writeback_io_num); + dc->front_io_num_per_sec = atomic_read(&dc->front_io_num); + atomic_set(&dc->writeback_sector_size, 0); + atomic_set(&dc->writeback_io_num, 0); + atomic_set(&dc->front_io_num, 0); +} + +static void cached_dev_timer_init(struct cached_dev *dc) +{ + dc->writeback_sector_size_per_sec = 0; + dc->writeback_io_num_per_sec = 0; + dc->front_io_num_per_sec = 0; + atomic_set(&dc->writeback_sector_size, 0); + atomic_set(&dc->writeback_io_num, 0); + atomic_set(&dc->front_io_num, 0); + + timer_setup(&dc->io_stat_timer, cached_dev_io_stat, 0); + dc->io_stat_timer.expires = jiffies + HZ; + add_timer(&dc->io_stat_timer); +} + static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) { int ret; @@ -1266,6 +1298,8 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) INIT_LIST_HEAD(&dc->io_lru); spin_lock_init(&dc->io_lock); bch_cache_accounting_init(&dc->accounting, &dc->disk.cl); + cached_dev_timer_init(dc); + bch_traffic_policy_init(dc); dc->sequential_cutoff = 4 << 20; dc->inflight_block_enable = 1; @@ -1774,6 +1808,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->congested_read_threshold_us = 2000; c->congested_write_threshold_us = 20000; c->error_limit = DEFAULT_IO_ERROR_LIMIT; + c->cutoff_writeback_sync = MIN_CUTOFF_WRITEBACK_SYNC; WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags)); return c; diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 706d3a245dba6..4c693ac29b0e0 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -51,6 +51,13 @@ static const char * const error_actions[] = { NULL }; +static const char * const writeback_state[] = { + "default", + "quick", + "slow", + NULL +}; + write_attribute(attach); write_attribute(detach); write_attribute(unregister); @@ -96,6 +103,9 @@ read_attribute(io_errors); read_attribute(congested); rw_attribute(congested_read_threshold_us); rw_attribute(congested_write_threshold_us); +rw_attribute(gc_sectors); +rw_attribute(traffic_policy_start); +rw_attribute(force_write_through); rw_attribute(sequential_cutoff); rw_attribute(read_bypass); @@ -114,7 +124,13 @@ rw_attribute(writeback_rate_update_seconds); rw_attribute(writeback_rate_i_term_inverse); rw_attribute(writeback_rate_p_term_inverse); rw_attribute(writeback_rate_minimum); +rw_attribute(writeback_state); +read_attribute(writeback_sector_size_per_sec); +read_attribute(writeback_io_num_per_sec); +read_attribute(front_io_num_per_sec); read_attribute(writeback_rate_debug); +read_attribute(write_token_sector_size); +read_attribute(write_token_io_num); read_attribute(stripe_size); read_attribute(partial_stripes_expensive); @@ -169,6 +185,11 @@ SHOW(__bch_cached_dev) bch_cache_modes, BDEV_CACHE_MODE(&dc->sb)); + if (attr == &sysfs_writeback_state) + return bch_snprint_string_list(buf, PAGE_SIZE, + writeback_state, + dc->writeback_state); + if (attr == &sysfs_readahead_cache_policy) return bch_snprint_string_list(buf, PAGE_SIZE, bch_reada_cache_policies, @@ -186,6 +207,9 @@ SHOW(__bch_cached_dev) var_printf(writeback_metadata, "%i"); var_printf(writeback_running, "%i"); var_print(writeback_delay); + var_print(writeback_sector_size_per_sec); + var_print(writeback_io_num_per_sec); + var_print(front_io_num_per_sec); var_print(writeback_percent); sysfs_hprint(writeback_rate, wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0); @@ -248,6 +272,8 @@ SHOW(__bch_cached_dev) sysfs_print(running, atomic_read(&dc->running)); sysfs_print(state, states[BDEV_STATE(&dc->sb)]); + var_print(write_token_sector_size); + var_print(write_token_io_num); if (attr == &sysfs_label) { memcpy(buf, dc->sb.label, SB_LABEL_SIZE); @@ -346,6 +372,15 @@ STORE(__cached_dev) } } + if (attr == &sysfs_writeback_state) { + v = __sysfs_match_string(writeback_state, -1, buf); + + if (v < 0) + return v; + + dc->writeback_state = v; + } + if (attr == &sysfs_readahead_cache_policy) { v = __sysfs_match_string(bch_reada_cache_policies, -1, buf); if (v < 0) @@ -448,11 +483,14 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_data_csum, #endif &sysfs_cache_mode, + &sysfs_writeback_state, &sysfs_readahead_cache_policy, &sysfs_stop_when_cache_set_failed, &sysfs_writeback_metadata, &sysfs_writeback_running, &sysfs_writeback_delay, + &sysfs_writeback_sector_size_per_sec, + &sysfs_writeback_io_num_per_sec, &sysfs_writeback_percent, &sysfs_writeback_rate, &sysfs_writeback_rate_update_seconds, @@ -460,6 +498,9 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_writeback_rate_p_term_inverse, &sysfs_writeback_rate_minimum, &sysfs_writeback_rate_debug, + &sysfs_write_token_sector_size, + &sysfs_write_token_io_num, + &sysfs_front_io_num_per_sec, &sysfs_io_errors, &sysfs_io_error_limit, &sysfs_io_disable, @@ -714,6 +755,12 @@ SHOW(__bch_cache_set) c->congested_read_threshold_us); sysfs_print(congested_write_threshold_us, c->congested_write_threshold_us); + sysfs_print(gc_sectors, + c->gc_sectors); + sysfs_print(traffic_policy_start, + c->traffic_policy_start); + sysfs_print(force_write_through, + c->force_write_through); sysfs_print(active_journal_entries, fifo_used(&c->journal.pin)); sysfs_printf(verify, "%i", c->verify); @@ -800,6 +847,12 @@ STORE(__bch_cache_set) c->congested_read_threshold_us); sysfs_strtoul(congested_write_threshold_us, c->congested_write_threshold_us); + sysfs_strtoul(gc_sectors, + c->gc_sectors); + sysfs_strtoul(traffic_policy_start, + c->traffic_policy_start); + sysfs_strtoul(force_write_through, + c->force_write_through); if (attr == &sysfs_errors) { v = __sysfs_match_string(error_actions, -1, buf); @@ -926,6 +979,9 @@ static struct attribute *bch_cache_set_internal_files[] = { &sysfs_btree_shrinker_disabled, &sysfs_copy_gc_enabled, &sysfs_io_disable, + &sysfs_gc_sectors, + &sysfs_traffic_policy_start, + &sysfs_force_write_through, NULL }; KTYPE(bch_cache_set_internal); diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index b5fc3c6c7178e..901ad8bae7614 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -222,7 +222,13 @@ static unsigned int writeback_delay(struct cached_dev *dc, !dc->writeback_percent) return 0; - return bch_next_delay(&dc->writeback_rate, sectors); + if (dc->writeback_state == WRITEBACK_DEFAULT) { + return bch_next_delay(&dc->writeback_rate, sectors); + } else if (dc->writeback_state == WRITEBACK_QUICK) { + return 0; + } else { + return msecs_to_jiffies(1000); + } } struct dirty_io { @@ -287,6 +293,9 @@ static void write_dirty_finish(struct closure *cl) : &dc->disk.c->writeback_keys_done); } + atomic_add(KEY_SIZE(&w->key), &dc->writeback_sector_size); + atomic_inc(&dc->writeback_io_num); + bch_keybuf_del(&dc->writeback_keys, w); up(&dc->in_flight); diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index e75dc33339f6f..a3151c0e96609 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -3,7 +3,8 @@ #define _BCACHE_WRITEBACK_H #define CUTOFF_WRITEBACK 40 -#define CUTOFF_WRITEBACK_SYNC 70 +#define MIN_CUTOFF_WRITEBACK_SYNC 70 +#define MAX_CUTOFF_WRITEBACK_SYNC 90 #define MAX_WRITEBACKS_IN_PASS 5 #define MAX_WRITESIZE_IN_PASS 5000 /* *512b */ @@ -57,10 +58,11 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, unsigned int cache_mode, bool would_skip) { unsigned int in_use = dc->disk.c->gc_stats.in_use; + unsigned int cutoff = dc->disk.c->cutoff_writeback_sync; if (cache_mode != CACHE_MODE_WRITEBACK || test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || - in_use > CUTOFF_WRITEBACK_SYNC) + in_use > cutoff) return false; if (bio_op(bio) == REQ_OP_DISCARD) -- 2.25.1

1 3

[PATCH kernel-4.19 1/4] Add traffic policy for low cache available.
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Xu Wei <xuwei56(a)huawei.com> euleros inclusion category: feature bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=327 CVE: NA When cache available is low, bcache turn to writethrough mode. Therefore, All write IO will be directly sent to backend device, which is usually HDD. At same time, cache device flush dirty data to the backend device in the bcache writeback process. So write IO from user will damage the sequentiality of writeback. And if there is lots of IO from writeback, user's write IO may be block. This patch add traffic policy in bcache to solve the problem and improve the performance for bcache when cache available is low. Signed-off-by: qinghaixiang <xuweiqhx(a)163.com> Signed-off-by: Xu Wei <xuwei56(a)huawei.com> Acked-by: Xie XiuQi <xiexiuqi(a)huawei.com> Reviewed-by: Li Ruilin <liruilin4(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/md/bcache/bcache.h | 49 ++++++++++++ drivers/md/bcache/btree.h | 6 +- drivers/md/bcache/request.c | 145 ++++++++++++++++++++++++++++++++-- drivers/md/bcache/request.h | 2 + drivers/md/bcache/super.c | 36 +++++++++ drivers/md/bcache/sysfs.c | 56 +++++++++++++ drivers/md/bcache/writeback.c | 11 ++- drivers/md/bcache/writeback.h | 3 +- 8 files changed, 300 insertions(+), 8 deletions(-) diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 3340f59117112..aa9e85dc04872 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -400,6 +400,28 @@ struct cached_dev { unsigned int offline_seconds; char backing_dev_name[BDEVNAME_SIZE]; + + /* Count the front and writeback io bandwidth per second */ + atomic_t writeback_sector_size; + atomic_t writeback_io_num; + atomic_t front_io_num; + unsigned int writeback_sector_size_per_sec; + unsigned int writeback_io_num_per_sec; + unsigned int front_io_num_per_sec; + struct timer_list io_stat_timer; + + unsigned int writeback_state; +#define WRITEBACK_DEFAULT 0 +#define WRITEBACK_QUICK 1 +#define WRITEBACK_SLOW 2 + + /* realize for token bucket */ + spinlock_t token_lock; + unsigned int max_sector_size; + unsigned int max_io_num; + unsigned int write_token_sector_size; + unsigned int write_token_io_num; + struct timer_list token_assign_timer; }; enum alloc_reserve { @@ -739,6 +761,10 @@ struct cache_set { #define BUCKET_HASH_BITS 12 struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS]; + unsigned int cutoff_writeback_sync; + bool traffic_policy_start; + bool force_write_through; + unsigned int gc_sectors; }; struct bbio { @@ -754,6 +780,29 @@ struct bbio { struct bio bio; }; +struct get_bcache_status { + unsigned int writeback_sector_size_per_sec; + unsigned int writeback_io_num_per_sec; + unsigned int front_io_num_per_sec; + uint64_t dirty_rate; + unsigned int available; +}; + +struct set_bcache_status { + unsigned int write_token_sector_size; + unsigned int write_token_io_num; + bool traffic_policy_start; + bool force_write_through; + bool copy_gc_enabled; + bool trigger_gc; + unsigned int writeback_state; + unsigned int gc_sectors; + unsigned int cutoff_writeback_sync; +}; +#define BCACHE_MAJOR 'B' +#define BCACHE_GET_WRITE_STATUS _IOR(BCACHE_MAJOR, 0x0, struct get_bcache_status) +#define BCACHE_SET_WRITE_STATUS _IOW(BCACHE_MAJOR, 0x1, struct set_bcache_status) + #define BTREE_PRIO USHRT_MAX #define INITIAL_PRIO 32768U diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h index 76cfd121a4861..7c5f7c235c533 100644 --- a/drivers/md/bcache/btree.h +++ b/drivers/md/bcache/btree.h @@ -193,7 +193,11 @@ static inline unsigned int bset_block_offset(struct btree *b, struct bset *i) static inline void set_gc_sectors(struct cache_set *c) { - atomic_set(&c->sectors_to_gc, c->sb.bucket_size * c->nbuckets / 16); + if (c->gc_sectors == 0) + atomic_set(&c->sectors_to_gc, + c->sb.bucket_size * c->nbuckets / 16); + else + atomic_set(&c->sectors_to_gc, c->gc_sectors); } void bkey_put(struct cache_set *c, struct bkey *k); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 2f3ecd8fc5801..50303841dd45b 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -28,6 +28,7 @@ struct kmem_cache *bch_search_cache; static void bch_data_insert_start(struct closure *cl); +static void alloc_token(struct cached_dev *dc, unsigned int sectors); static unsigned int cache_mode(struct cached_dev *dc) { @@ -384,8 +385,9 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) goto skip; if (mode == CACHE_MODE_NONE || - (mode == CACHE_MODE_WRITEAROUND && - op_is_write(bio_op(bio)))) + ((mode == CACHE_MODE_WRITEAROUND || + c->force_write_through == true) && + op_is_write(bio_op(bio)))) goto skip; /* @@ -863,6 +865,10 @@ static void cached_dev_read_done(struct closure *cl) if (s->iop.bio && (!dc->read_bypass || s->prefetch) && !test_bit(CACHE_SET_STOPPING, &s->iop.c->flags)) { BUG_ON(!s->iop.replace); + if ((dc->disk.c->traffic_policy_start == true) && + (dc->disk.c->force_write_through != true)) { + alloc_token(dc, bio_sectors(s->iop.bio)); + } closure_call(&s->iop.cl, bch_data_insert, NULL, cl); } @@ -1005,6 +1011,35 @@ static void cached_dev_write_complete(struct closure *cl) continue_at(cl, cached_dev_bio_complete, NULL); } +static void alloc_token(struct cached_dev *dc, unsigned int sectors) +{ + int count = 0; + + spin_lock_bh(&dc->token_lock); + + while ((dc->write_token_sector_size < sectors) && + (dc->write_token_io_num == 0)) { + spin_unlock_bh(&dc->token_lock); + schedule_timeout_interruptible(msecs_to_jiffies(10)); + count++; + if ((dc->disk.c->traffic_policy_start != true) || + (cache_mode(dc) != CACHE_MODE_WRITEBACK) || + (count > 100)) + return; + spin_lock_bh(&dc->token_lock); + } + + if (dc->write_token_sector_size >= sectors) + dc->write_token_sector_size -= sectors; + else + dc->write_token_sector_size = 0; + + if (dc->write_token_io_num > 0) + dc->write_token_io_num--; + + spin_unlock_bh(&dc->token_lock); +} + static void cached_dev_write(struct cached_dev *dc, struct search *s) { struct closure *cl = &s->cl; @@ -1252,6 +1287,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, cached_dev_nodata, bcache_wq); } else { + atomic_inc(&dc->front_io_num); s->iop.bypass = check_should_bypass(dc, bio); if (!s->iop.bypass && bio->bi_iter.bi_size && !rw) { @@ -1263,10 +1299,17 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, save_circ_item(&s->smp); } - if (rw) + if (rw) { + if ((s->iop.bypass == false) && + (dc->disk.c->traffic_policy_start == true) && + (cache_mode(dc) == CACHE_MODE_WRITEBACK) && + (bio_op(bio) != REQ_OP_DISCARD)) { + alloc_token(dc, bio_sectors(bio)); + } cached_dev_write(dc, s); - else + } else { cached_dev_read(dc, s); + } } } else /* I/O request sent to backing device */ @@ -1275,6 +1318,65 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, return BLK_QC_T_NONE; } +static int bcache_get_write_status(struct cached_dev *dc, unsigned long arg) +{ + struct get_bcache_status a; + uint64_t cache_sectors; + struct cache_set *c = dc->disk.c; + + if (c == NULL) + return -ENODEV; + + a.writeback_sector_size_per_sec = dc->writeback_sector_size_per_sec; + a.writeback_io_num_per_sec = dc->writeback_io_num_per_sec; + a.front_io_num_per_sec = dc->front_io_num_per_sec; + cache_sectors = c->nbuckets * c->sb.bucket_size - + atomic_long_read(&c->flash_dev_dirty_sectors); + a.dirty_rate = div64_u64(bcache_dev_sectors_dirty(&dc->disk) * 100, + cache_sectors); + a.available = 100 - c->gc_stats.in_use; + if (copy_to_user((struct get_bcache_status *)arg, &a, + sizeof(struct get_bcache_status))) + return -EFAULT; + return 0; +} + +static int bcache_set_write_status(struct cached_dev *dc, unsigned long arg) +{ + struct set_bcache_status a; + struct cache_set *c = dc->disk.c; + + if (c == NULL) + return -ENODEV; + if (copy_from_user(&a, (struct set_bcache_status *)arg, + sizeof(struct set_bcache_status))) + return -EFAULT; + + if (c->traffic_policy_start != a.traffic_policy_start) + pr_info("%s traffic policy %s", dc->disk.disk->disk_name, + (a.traffic_policy_start == true) ? "enable" : "disable"); + if (c->force_write_through != a.force_write_through) + pr_info("%s force write through %s", dc->disk.disk->disk_name, + (a.force_write_through == true) ? "enable" : "disable"); + if (a.trigger_gc) { + pr_info("trigger %s gc", dc->disk.disk->disk_name); + atomic_set(&c->sectors_to_gc, -1); + wake_up_gc(c); + } + if ((a.cutoff_writeback_sync >= CUTOFF_WRITEBACK_SYNC) && + (a.cutoff_writeback_sync <= CUTOFF_WRITEBACK_SYNC_MAX)) { + c->cutoff_writeback_sync = a.cutoff_writeback_sync; + } + + dc->max_sector_size = a.write_token_sector_size; + dc->max_io_num = a.write_token_io_num; + c->traffic_policy_start = a.traffic_policy_start; + c->force_write_through = a.force_write_through; + c->gc_sectors = a.gc_sectors; + dc->writeback_state = a.writeback_state; + return 0; +} + static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1283,7 +1385,14 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, if (dc->io_disable) return -EIO; - return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + switch (cmd) { + case BCACHE_GET_WRITE_STATUS: + return bcache_get_write_status(dc, arg); + case BCACHE_SET_WRITE_STATUS: + return bcache_set_write_status(dc, arg); + default: + return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); + } } static int cached_dev_congested(void *data, int bits) @@ -1443,3 +1552,29 @@ int __init bch_request_init(void) return 0; } + +static void token_assign(struct timer_list *t) +{ + struct cached_dev *dc = from_timer(dc, t, token_assign_timer); + + dc->token_assign_timer.expires = jiffies + HZ / 8; + add_timer(&dc->token_assign_timer); + + spin_lock(&dc->token_lock); + dc->write_token_sector_size = dc->max_sector_size / 8; + dc->write_token_io_num = dc->max_io_num / 8; + dc->write_token_io_num = + (dc->write_token_io_num == 0) ? 1 : dc->write_token_io_num; + spin_unlock(&dc->token_lock); +} + +void bch_traffic_policy_init(struct cached_dev *dc) +{ + spin_lock_init(&dc->token_lock); + dc->write_token_sector_size = 0; + dc->write_token_io_num = 0; + + timer_setup(&dc->token_assign_timer, token_assign, 0); + dc->token_assign_timer.expires = jiffies + HZ / 8; + add_timer(&dc->token_assign_timer); +} diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 7682630db73f6..8e2ab8071b5bf 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -41,6 +41,8 @@ void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); void bch_flash_dev_request_init(struct bcache_device *d); +void bch_traffic_policy_init(struct cached_dev *dc); + extern struct kmem_cache *bch_search_cache; struct search { diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 754e88895738b..e2828c762edc5 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1260,6 +1260,9 @@ static void cached_dev_free(struct closure *cl) { struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl); + del_timer_sync(&dc->io_stat_timer); + del_timer_sync(&dc->token_assign_timer); + if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags)) cancel_writeback_rate_update_dwork(dc); @@ -1303,6 +1306,36 @@ static void cached_dev_flush(struct closure *cl) continue_at(cl, cached_dev_free, system_wq); } +static void cached_dev_io_stat(struct timer_list *t) +{ + struct cached_dev *dc = from_timer(dc, t, io_stat_timer); + + dc->io_stat_timer.expires = jiffies + HZ; + add_timer(&dc->io_stat_timer); + + dc->writeback_sector_size_per_sec = + atomic_read(&dc->writeback_sector_size); + dc->writeback_io_num_per_sec = atomic_read(&dc->writeback_io_num); + dc->front_io_num_per_sec = atomic_read(&dc->front_io_num); + atomic_set(&dc->writeback_sector_size, 0); + atomic_set(&dc->writeback_io_num, 0); + atomic_set(&dc->front_io_num, 0); +} + +static void cached_dev_timer_init(struct cached_dev *dc) +{ + dc->writeback_sector_size_per_sec = 0; + dc->writeback_io_num_per_sec = 0; + dc->front_io_num_per_sec = 0; + atomic_set(&dc->writeback_sector_size, 0); + atomic_set(&dc->writeback_io_num, 0); + atomic_set(&dc->front_io_num, 0); + + timer_setup(&dc->io_stat_timer, cached_dev_io_stat, 0); + dc->io_stat_timer.expires = jiffies + HZ; + add_timer(&dc->io_stat_timer); +} + static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) { int ret; @@ -1319,6 +1352,8 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) INIT_LIST_HEAD(&dc->io_lru); spin_lock_init(&dc->io_lock); bch_cache_accounting_init(&dc->accounting, &dc->disk.cl); + cached_dev_timer_init(dc); + bch_traffic_policy_init(dc); dc->sequential_cutoff = 4 << 20; dc->inflight_block_enable = 1; @@ -1837,6 +1872,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->congested_read_threshold_us = 2000; c->congested_write_threshold_us = 20000; c->error_limit = DEFAULT_IO_ERROR_LIMIT; + c->cutoff_writeback_sync = bch_cutoff_writeback_sync; c->idle_max_writeback_rate_enabled = 1; WARN_ON(test_and_clear_bit(CACHE_SET_IO_DISABLE, &c->flags)); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index e23c426229399..097560389760c 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -53,6 +53,13 @@ static const char * const error_actions[] = { NULL }; +static const char * const writeback_state[] = { + "default", + "quick", + "slow", + NULL +}; + write_attribute(attach); write_attribute(detach); write_attribute(unregister); @@ -102,6 +109,9 @@ read_attribute(cutoff_writeback); read_attribute(cutoff_writeback_sync); rw_attribute(congested_read_threshold_us); rw_attribute(congested_write_threshold_us); +rw_attribute(gc_sectors); +rw_attribute(traffic_policy_start); +rw_attribute(force_write_through); rw_attribute(sequential_cutoff); rw_attribute(read_bypass); @@ -120,7 +130,13 @@ rw_attribute(writeback_rate_update_seconds); rw_attribute(writeback_rate_i_term_inverse); rw_attribute(writeback_rate_p_term_inverse); rw_attribute(writeback_rate_minimum); +rw_attribute(writeback_state); +read_attribute(writeback_sector_size_per_sec); +read_attribute(writeback_io_num_per_sec); +read_attribute(front_io_num_per_sec); read_attribute(writeback_rate_debug); +read_attribute(write_token_sector_size); +read_attribute(write_token_io_num); read_attribute(stripe_size); read_attribute(partial_stripes_expensive); @@ -177,6 +193,11 @@ SHOW(__bch_cached_dev) bch_cache_modes, BDEV_CACHE_MODE(&dc->sb)); + if (attr == &sysfs_writeback_state) + return bch_snprint_string_list(buf, PAGE_SIZE, + writeback_state, + dc->writeback_state); + if (attr == &sysfs_readahead_cache_policy) return bch_snprint_string_list(buf, PAGE_SIZE, bch_reada_cache_policies, @@ -194,6 +215,9 @@ SHOW(__bch_cached_dev) var_printf(writeback_metadata, "%i"); var_printf(writeback_running, "%i"); var_print(writeback_delay); + var_print(writeback_sector_size_per_sec); + var_print(writeback_io_num_per_sec); + var_print(front_io_num_per_sec); var_print(writeback_percent); sysfs_hprint(writeback_rate, wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0); @@ -256,6 +280,8 @@ SHOW(__bch_cached_dev) sysfs_print(running, atomic_read(&dc->running)); sysfs_print(state, states[BDEV_STATE(&dc->sb)]); + var_print(write_token_sector_size); + var_print(write_token_io_num); if (attr == &sysfs_label) { memcpy(buf, dc->sb.label, SB_LABEL_SIZE); @@ -375,6 +401,15 @@ STORE(__cached_dev) } } + if (attr == &sysfs_writeback_state) { + v = __sysfs_match_string(writeback_state, -1, buf); + + if (v < 0) + return v; + + dc->writeback_state = v; + } + if (attr == &sysfs_readahead_cache_policy) { v = __sysfs_match_string(bch_reada_cache_policies, -1, buf); if (v < 0) @@ -498,11 +533,14 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_data_csum, #endif &sysfs_cache_mode, + &sysfs_writeback_state, &sysfs_readahead_cache_policy, &sysfs_stop_when_cache_set_failed, &sysfs_writeback_metadata, &sysfs_writeback_running, &sysfs_writeback_delay, + &sysfs_writeback_sector_size_per_sec, + &sysfs_writeback_io_num_per_sec, &sysfs_writeback_percent, &sysfs_writeback_rate, &sysfs_writeback_rate_update_seconds, @@ -510,6 +548,9 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_writeback_rate_p_term_inverse, &sysfs_writeback_rate_minimum, &sysfs_writeback_rate_debug, + &sysfs_write_token_sector_size, + &sysfs_write_token_io_num, + &sysfs_front_io_num_per_sec, &sysfs_io_errors, &sysfs_io_error_limit, &sysfs_io_disable, @@ -770,6 +811,12 @@ SHOW(__bch_cache_set) c->congested_read_threshold_us); sysfs_print(congested_write_threshold_us, c->congested_write_threshold_us); + sysfs_print(gc_sectors, + c->gc_sectors); + sysfs_print(traffic_policy_start, + c->traffic_policy_start); + sysfs_print(force_write_through, + c->force_write_through); sysfs_print(cutoff_writeback, bch_cutoff_writeback); sysfs_print(cutoff_writeback_sync, bch_cutoff_writeback_sync); @@ -855,6 +902,12 @@ STORE(__bch_cache_set) sysfs_strtoul_clamp(congested_write_threshold_us, c->congested_write_threshold_us, 0, UINT_MAX); + sysfs_strtoul(gc_sectors, + c->gc_sectors); + sysfs_strtoul(traffic_policy_start, + c->traffic_policy_start); + sysfs_strtoul(force_write_through, + c->force_write_through); if (attr == &sysfs_errors) { v = __sysfs_match_string(error_actions, -1, buf); @@ -997,6 +1050,9 @@ static struct attribute *bch_cache_set_internal_files[] = { &sysfs_idle_max_writeback_rate, &sysfs_gc_after_writeback, &sysfs_io_disable, + &sysfs_gc_sectors, + &sysfs_traffic_policy_start, + &sysfs_force_write_through, &sysfs_cutoff_writeback, &sysfs_cutoff_writeback_sync, NULL diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 25a66e54f7ba5..1e3041f6363c7 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -239,7 +239,13 @@ static unsigned int writeback_delay(struct cached_dev *dc, !dc->writeback_percent) return 0; - return bch_next_delay(&dc->writeback_rate, sectors); + if (dc->writeback_state == WRITEBACK_DEFAULT) { + return bch_next_delay(&dc->writeback_rate, sectors); + } else if (dc->writeback_state == WRITEBACK_QUICK) { + return 0; + } else { + return msecs_to_jiffies(1000); + } } struct dirty_io { @@ -304,6 +310,9 @@ static void write_dirty_finish(struct closure *cl) : &dc->disk.c->writeback_keys_done); } + atomic_add(KEY_SIZE(&w->key), &dc->writeback_sector_size); + atomic_inc(&dc->writeback_io_num); + bch_keybuf_del(&dc->writeback_keys, w); up(&dc->in_flight); diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index c4ff76037227b..912b1a146cea2 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -80,10 +80,11 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, unsigned int cache_mode, bool would_skip) { unsigned int in_use = dc->disk.c->gc_stats.in_use; + unsigned int cutoff = dc->disk.c->cutoff_writeback_sync; if (cache_mode != CACHE_MODE_WRITEBACK || test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || - in_use > bch_cutoff_writeback_sync) + in_use > cutoff) return false; if (bio_op(bio) == REQ_OP_DISCARD) -- 2.25.1

1 3

[PATCH openEuler-20.03-LTS-tag] kernel.spec: fix rpmbuild error with patch
by Gou Hao 19 Jul '21

19 Jul '21

From: gouhao <gouhao(a)uniontech.com> kernel.spec: fix rpmbuild error with patch uniontech inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I3ZNR0 CVE: NA -------------------------------------------------------------- When %{with_patch} is 1, the second compilation will fail when compiling with rpmbuild, and the failure message is: Reversed (or previously applied) patch detected! rpm package compilation usually deletes the source directory in ~/rpmbuild/BUILD in the %prep stage, but in our spec, in the %prep stage, if %{with patch} is 1 and vanilla-%{TarballVer} exists, there is no delete the source code directory and enter it directly， it will cause this bug. Signed-off-by: gouhao <gouhao(a)uniontech.com> --- kernel.spec | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/kernel.spec b/kernel.spec index e00a323..11c76aa 100644 --- a/kernel.spec +++ b/kernel.spec @@ -205,20 +205,14 @@ package or when debugging this package.\ %endif %prep -%if 0%{?with_patch} -if [ ! -d kernel-%{version}/vanilla-%{TarballVer} ];then -%setup -q -n kernel-%{version} -a 9998 -c - mv linux-%{TarballVer} vanilla-%{TarballVer} -else - cd kernel-%{version} -fi -cp -rl vanilla-%{TarballVer} linux-%{KernelVer} -%else + %setup -q -n kernel-%{version} -c -mv kernel linux-%{version} -cp -rl linux-%{version} linux-%{KernelVer} + +%if 0%{?with_patch} +tar -xjf %{SOURCE9998} %endif +mv linux-%{version} linux-%{KernelVer} cd linux-%{KernelVer} %if 0%{?with_patch} -- 2.20.1

1 0

[PATCH kernel-4.19] igmp: Add ip_mc_list lock in ip_check_mc_rcu
by Yang Yingliang 19 Jul '21

19 Jul '21

From: Liu Jian <liujian56(a)huawei.com> mainline inclusion from mainline-net-next commit 23d2b94043ca8835bd1e67749020e839f396a1c2 category: bugfix bugzilla: NA CVE: NA -------------------------------- I got below panic when doing fuzz test: Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 4056 Comm: syz-executor.3 Tainted: G B 5.14.0-rc1-00195-gcff5c4254439-dirty #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x7a/0x9b panic+0x2cd/0x5af end_report.cold+0x5a/0x5a kasan_report+0xec/0x110 ip_check_mc_rcu+0x556/0x5d0 __mkroute_output+0x895/0x1740 ip_route_output_key_hash_rcu+0x2d0/0x1050 ip_route_output_key_hash+0x182/0x2e0 ip_route_output_flow+0x28/0x130 udp_sendmsg+0x165d/0x2280 udpv6_sendmsg+0x121e/0x24f0 inet6_sendmsg+0xf7/0x140 sock_sendmsg+0xe9/0x180 ____sys_sendmsg+0x2b8/0x7a0 ___sys_sendmsg+0xf0/0x160 __sys_sendmmsg+0x17e/0x3c0 __x64_sys_sendmmsg+0x9e/0x100 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x462eb9 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 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 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f3df5af1c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 000000000073bf00 RCX: 0000000000462eb9 RDX: 0000000000000312 RSI: 0000000020001700 RDI: 0000000000000007 RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f3df5af26bc R13: 00000000004c372d R14: 0000000000700b10 R15: 00000000ffffffff It is one use-after-free in ip_check_mc_rcu. In ip_mc_del_src, the ip_sf_list of pmc has been freed under pmc->lock protection. But access to ip_sf_list in ip_check_mc_rcu is not protected by the lock. Signed-off-by: Liu Jian <liujian56(a)huawei.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/ipv4/igmp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index ffa847fc96194..1a0953b2b1396 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2736,6 +2736,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { + spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; @@ -2746,6 +2747,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; + spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] memcg: fix unsuitable null check after alloc memory
by Yang Yingliang 18 Jul '21

18 Jul '21

From: Lu Jialin <lujialin4(a)huawei.com> hulk inclusion category: bugfix bugzilla: 51815, https://gitee.com/openeuler/kernel/issues/I3IJ9I CVE: NA -------- Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/memcontrol.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 713a839013f72..e55b46d5d0fcb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4850,8 +4850,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; pn_ext = kzalloc_node(sizeof(*pn_ext), GFP_KERNEL, tmp); - pn = &pn_ext->pn; - if (!pn) + if (!pn_ext) return 1; pn_ext->lruvec_stat_local = alloc_percpu(struct lruvec_stat); @@ -4860,6 +4859,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) return 1; } + pn = &pn_ext->pn; pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat); if (!pn->lruvec_stat_cpu) { free_percpu(pn_ext->lruvec_stat_local); @@ -4927,10 +4927,10 @@ static struct mem_cgroup *mem_cgroup_alloc(void) size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); memcg_ext = kzalloc(size, GFP_KERNEL); - memcg = &memcg_ext->memcg; - if (!memcg) + if (!memcg_ext) return NULL; + memcg = &memcg_ext->memcg; memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX, GFP_KERNEL); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] config: enable KASAN and UBSAN by default
by Yang Yingliang 16 Jul '21

16 Jul '21

hulk inclusion category: bugfix bugzilla: NA CVE: NA -------------------------------- Enable KASAN and UBSAN by default for test. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/configs/hulk_defconfig | 10 ++++++++-- arch/x86/configs/hulk_defconfig | 10 ++++++++-- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/arch/arm64/configs/hulk_defconfig b/arch/arm64/configs/hulk_defconfig index 741b33fab4e9c..6a3937a4017dd 100644 --- a/arch/arm64/configs/hulk_defconfig +++ b/arch/arm64/configs/hulk_defconfig @@ -5504,7 +5504,10 @@ CONFIG_ARCH_HAS_DEBUG_VIRTUAL=y CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_PER_CPU_MAPS is not set CONFIG_HAVE_ARCH_KASAN=y -# CONFIG_KASAN is not set +CONFIG_KASAN=y +# CONFIG_KASAN_OUTLINE is not set +CONFIG_KASAN_INLINE=y +# CONFIG_TEST_KASAN is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_CC_HAS_SANCOV_TRACE_PC=y # CONFIG_KCOV is not set @@ -5668,7 +5671,10 @@ CONFIG_KDB_DEFAULT_ENABLE=0x0 CONFIG_KDB_KEYBOARD=y CONFIG_KDB_CONTINUE_CATASTROPHIC=0 CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y -# CONFIG_UBSAN is not set +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_TEST_UBSAN is not set CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y CONFIG_STRICT_DEVMEM=y CONFIG_IO_STRICT_DEVMEM=y diff --git a/arch/x86/configs/hulk_defconfig b/arch/x86/configs/hulk_defconfig index 6ea79ca8a8a1e..f43f5ead30fa4 100644 --- a/arch/x86/configs/hulk_defconfig +++ b/arch/x86/configs/hulk_defconfig @@ -7331,7 +7331,10 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_HAVE_DEBUG_STACKOVERFLOW=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_HAVE_ARCH_KASAN=y -# CONFIG_KASAN is not set +CONFIG_KASAN=y +# CONFIG_KASAN_OUTLINE is not set +CONFIG_KASAN_INLINE=y +# CONFIG_TEST_KASAN is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_DEBUG_SHIRQ=y @@ -7504,7 +7507,10 @@ CONFIG_KDB_DEFAULT_ENABLE=0x0 CONFIG_KDB_KEYBOARD=y CONFIG_KDB_CONTINUE_CATASTROPHIC=0 CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y -# CONFIG_UBSAN is not set +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_TEST_UBSAN is not set CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y CONFIG_STRICT_DEVMEM=y # CONFIG_IO_STRICT_DEVMEM is not set -- 2.25.1

1 0

[PATCH kernel-4.19] config: enable KASAN and UBSAN by default
by Yang Yingliang 16 Jul '21

16 Jul '21

hulk inclusion category: bugfix bugzilla: NA CVE: NA -------------------------------- Enable KASAN and UBSAN by default for test. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/configs/hulk_defconfig | 10 ++++++++-- arch/x86/configs/hulk_defconfig | 10 ++++++++-- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/arch/arm64/configs/hulk_defconfig b/arch/arm64/configs/hulk_defconfig index 59069097da854..6e9b7ff0bf2dc 100644 --- a/arch/arm64/configs/hulk_defconfig +++ b/arch/arm64/configs/hulk_defconfig @@ -5542,7 +5542,10 @@ CONFIG_ARCH_HAS_DEBUG_VIRTUAL=y CONFIG_DEBUG_MEMORY_INIT=y # CONFIG_DEBUG_PER_CPU_MAPS is not set CONFIG_HAVE_ARCH_KASAN=y -# CONFIG_KASAN is not set +CONFIG_KASAN=y +# CONFIG_KASAN_OUTLINE is not set +CONFIG_KASAN_INLINE=y +# CONFIG_TEST_KASAN is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_CC_HAS_SANCOV_TRACE_PC=y # CONFIG_KCOV is not set @@ -5708,7 +5711,10 @@ CONFIG_KDB_DEFAULT_ENABLE=0x0 CONFIG_KDB_KEYBOARD=y CONFIG_KDB_CONTINUE_CATASTROPHIC=0 CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y -# CONFIG_UBSAN is not set +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_TEST_UBSAN is not set CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y CONFIG_STRICT_DEVMEM=y CONFIG_IO_STRICT_DEVMEM=y diff --git a/arch/x86/configs/hulk_defconfig b/arch/x86/configs/hulk_defconfig index b0e92300198c2..38ac853d4e31c 100644 --- a/arch/x86/configs/hulk_defconfig +++ b/arch/x86/configs/hulk_defconfig @@ -7320,7 +7320,10 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_HAVE_DEBUG_STACKOVERFLOW=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_HAVE_ARCH_KASAN=y -# CONFIG_KASAN is not set +CONFIG_KASAN=y +# CONFIG_KASAN_OUTLINE is not set +CONFIG_KASAN_INLINE=y +# CONFIG_TEST_KASAN is not set CONFIG_ARCH_HAS_KCOV=y CONFIG_CC_HAS_SANCOV_TRACE_PC=y # CONFIG_KCOV is not set @@ -7495,7 +7498,10 @@ CONFIG_KDB_DEFAULT_ENABLE=0x0 CONFIG_KDB_KEYBOARD=y CONFIG_KDB_CONTINUE_CATASTROPHIC=0 CONFIG_ARCH_HAS_UBSAN_SANITIZE_ALL=y -# CONFIG_UBSAN is not set +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +# CONFIG_UBSAN_ALIGNMENT is not set +# CONFIG_TEST_UBSAN is not set CONFIG_ARCH_HAS_DEVMEM_IS_ALLOWED=y CONFIG_STRICT_DEVMEM=y # CONFIG_IO_STRICT_DEVMEM is not set -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] cpuidle: fix a build error when compiling haltpoll into module
by GONG, Ruiqi 16 Jul '21

16 Jul '21

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZURN CVE: NA -------- Kernel build would fail in case of CONFIG_HALTPOLL_CPUIDLE=m, caused by haltpoll_switch_governor() not marked as an exported symbol. Fix this by complementing the EXPORT_SYMBOL statement. Fixes: 97c227885e0a ("cpuidle: fix container_of err in cpuidle_device and cpuidle_driver") Signed-off-by: GONG, Ruiqi <gongruiqi1(a)huawei.com> Cc: Jiajun Chen <chenjiajun8(a)huawei.com> --- drivers/cpuidle/driver.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 484d0e9655fc..c97d08c90655 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -260,6 +260,8 @@ void haltpoll_switch_governor(struct cpuidle_driver *drv) } } +EXPORT_SYMBOL_GPL(haltpoll_switch_governor); + /** * cpuidle_register_driver - registers a driver * @drv: a pointer to a valid struct cpuidle_driver -- 2.27.0

3 2

[PATCH openEuler-1.0-LTS 1/6] KVM: cpuid: do_cpuid_ent works on a whole CPUID function
by Yang Yingliang 16 Jul '21

16 Jul '21

From: Paolo Bonzini <pbonzini(a)redhat.com> mainline inclusion from mainline-v5.3-rc1 commit ab8bcf64971180e1344ce2c7e70c49b0f24f6b0d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3YAEG CVE: NA ----------------------------- Rename it as well as __do_cpuid_ent and __do_cpuid_ent_emulated to have "func" in its name, and drop the index parameter which is always 0. Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Jingyi Wang <wangjingyi11(a)huawei.com> Reviewed-by: Keqian Zhu <zhukeqian1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/kvm/cpuid.c | 105 +++++++++++++++++++++---------------------- 1 file changed, 50 insertions(+), 55 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1a0b5843b0e34..fe925f146773a 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -287,14 +287,19 @@ static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, { entry->function = function; entry->index = index; + entry->flags = 0; + cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - entry->flags = 0; } -static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, - u32 func, u32 index, int *nent, int maxnent) +static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, int *nent, int maxnent) { + entry->function = func; + entry->index = 0; + entry->flags = 0; + switch (func) { case 0: entry->eax = 7; @@ -306,21 +311,18 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, break; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - if (index == 0) - entry->ecx = F(RDPID); + entry->eax = 0; + entry->ecx = F(RDPID); ++*nent; default: break; } - entry->function = func; - entry->index = index; - return 0; } -static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, + int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -423,7 +425,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (WARN_ON(*nent >= maxnent)) goto out; - do_cpuid_1_ent(entry, function, index); + do_cpuid_1_ent(entry, function, 0); ++*nent; switch (function) { @@ -486,42 +488,36 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, break; case 7: { entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* Mask ebx against host capability word 9 */ - if (index == 0) { - entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_7_0_EBX); - // TSC_ADJUST is emulated - entry->ebx |= F(TSC_ADJUST); - entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; - f_la57 = entry->ecx & F(LA57); - cpuid_mask(&entry->ecx, CPUID_7_ECX); - /* Set LA57 based on hardware capability. */ - entry->ecx |= f_la57; - entry->ecx |= f_umip; - /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) - entry->ecx &= ~F(PKU); - - entry->edx &= kvm_cpuid_7_0_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_7_EDX); - if (boot_cpu_has(X86_FEATURE_IBPB) && - boot_cpu_has(X86_FEATURE_IBRS)) - entry->edx |= F(SPEC_CTRL); - if (boot_cpu_has(X86_FEATURE_STIBP)) - entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) - entry->edx |= F(SPEC_CTRL_SSBD); - /* - * We emulate ARCH_CAPABILITIES in software even - * if the host doesn't support it. - */ - entry->edx |= F(ARCH_CAPABILITIES); - } else { - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - } entry->eax = 0; + /* Mask ebx against host capability word 9 */ + entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_7_0_EBX); + // TSC_ADJUST is emulated + entry->ebx |= F(TSC_ADJUST); + entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; + f_la57 = entry->ecx & F(LA57); + cpuid_mask(&entry->ecx, CPUID_7_ECX); + /* Set LA57 based on hardware capability. */ + entry->ecx |= f_la57; + entry->ecx |= f_umip; + /* PKU is not yet implemented for shadow paging. */ + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) + entry->ecx &= ~F(PKU); + + entry->edx &= kvm_cpuid_7_0_edx_x86_features; + cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && + boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); + /* + * We emulate ARCH_CAPABILITIES in software even + * if the host doesn't support it. + */ + entry->edx |= F(ARCH_CAPABILITIES); break; } case 9: @@ -727,23 +723,22 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, return r; } -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, - u32 idx, int *nent, int maxnent, unsigned int type) +static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, + int *nent, int maxnent, unsigned int type) { if (*nent >= maxnent) return -E2BIG; if (type == KVM_GET_EMULATED_CPUID) - return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + return __do_cpuid_func_emulated(entry, func, nent, maxnent); - return __do_cpuid_ent(entry, func, idx, nent, maxnent); + return __do_cpuid_func(entry, func, nent, maxnent); } #undef F struct kvm_cpuid_param { u32 func; - u32 idx; bool has_leaf_count; bool (*qualifier)(const struct kvm_cpuid_param *param); }; @@ -816,8 +811,8 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (ent->qualifier && !ent->qualifier(ent)) continue; - r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], ent->func, + &nent, cpuid->nent, type); if (r) goto out_free; @@ -827,8 +822,8 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) - r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], func, + &nent, cpuid->nent, type); if (r) goto out_free; -- 2.25.1

1 5

[PATCH kernel-4.19 1/6] KVM: cpuid: do_cpuid_ent works on a whole CPUID function
by Yang Yingliang 15 Jul '21

15 Jul '21

From: Paolo Bonzini <pbonzini(a)redhat.com> mainline inclusion from mainline-v5.3-rc1 commit ab8bcf64971180e1344ce2c7e70c49b0f24f6b0d category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3YAEG CVE: NA ----------------------------- Rename it as well as __do_cpuid_ent and __do_cpuid_ent_emulated to have "func" in its name, and drop the index parameter which is always 0. Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: Jingyi Wang <wangjingyi11(a)huawei.com> Reviewed-by: Keqian Zhu <zhukeqian1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/kvm/cpuid.c | 107 +++++++++++++++++++++---------------------- 1 file changed, 51 insertions(+), 56 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 85f439bd02f34..6775b9bd82911 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -287,14 +287,19 @@ static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, { entry->function = function; entry->index = index; + entry->flags = 0; + cpuid_count(entry->function, entry->index, &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - entry->flags = 0; } -static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, - u32 func, u32 index, int *nent, int maxnent) +static int __do_cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, int *nent, int maxnent) { + entry->function = func; + entry->index = 0; + entry->flags = 0; + switch (func) { case 0: entry->eax = 7; @@ -306,21 +311,18 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, break; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - if (index == 0) - entry->ecx = F(RDPID); + entry->eax = 0; + entry->ecx = F(RDPID); ++*nent; default: break; } - entry->function = func; - entry->index = index; - return 0; } -static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, + int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -423,7 +425,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, if (WARN_ON(*nent >= maxnent)) goto out; - do_cpuid_1_ent(entry, function, index); + do_cpuid_1_ent(entry, function, 0); ++*nent; switch (function) { @@ -486,43 +488,37 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, break; case 7: { entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* Mask ebx against host capability word 9 */ - if (index == 0) { - entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; - cpuid_mask(&entry->ebx, CPUID_7_0_EBX); - // TSC_ADJUST is emulated - entry->ebx |= F(TSC_ADJUST); - entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; - f_la57 = entry->ecx & F(LA57); - cpuid_mask(&entry->ecx, CPUID_7_ECX); - /* Set LA57 based on hardware capability. */ - entry->ecx |= f_la57; - entry->ecx |= f_umip; - /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) - entry->ecx &= ~F(PKU); - - entry->edx &= kvm_cpuid_7_0_edx_x86_features; - cpuid_mask(&entry->edx, CPUID_7_EDX); - if (boot_cpu_has(X86_FEATURE_IBPB) && - boot_cpu_has(X86_FEATURE_IBRS)) - entry->edx |= F(SPEC_CTRL); - if (boot_cpu_has(X86_FEATURE_STIBP)) - entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - boot_cpu_has(X86_FEATURE_AMD_SSBD)) - entry->edx |= F(SPEC_CTRL_SSBD); - /* - * We emulate ARCH_CAPABILITIES in software even - * if the host doesn't support it. - */ - entry->edx |= F(ARCH_CAPABILITIES); - } else { - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - } entry->eax = 0; + /* Mask ebx against host capability word 9 */ + entry->ebx &= kvm_cpuid_7_0_ebx_x86_features; + cpuid_mask(&entry->ebx, CPUID_7_0_EBX); + // TSC_ADJUST is emulated + entry->ebx |= F(TSC_ADJUST); + entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; + f_la57 = entry->ecx & F(LA57); + cpuid_mask(&entry->ecx, CPUID_7_ECX); + /* Set LA57 based on hardware capability. */ + entry->ecx |= f_la57; + entry->ecx |= f_umip; + /* PKU is not yet implemented for shadow paging. */ + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) + entry->ecx &= ~F(PKU); + + entry->edx &= kvm_cpuid_7_0_edx_x86_features; + cpuid_mask(&entry->edx, CPUID_7_EDX); + if (boot_cpu_has(X86_FEATURE_IBPB) && + boot_cpu_has(X86_FEATURE_IBRS)) + entry->edx |= F(SPEC_CTRL); + if (boot_cpu_has(X86_FEATURE_STIBP)) + entry->edx |= F(INTEL_STIBP); + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + entry->edx |= F(SPEC_CTRL_SSBD); + /* + * We emulate ARCH_CAPABILITIES in software even + * if the host doesn't support it. + */ + entry->edx |= F(ARCH_CAPABILITIES); break; } case 9: @@ -728,23 +724,22 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, return r; } -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, - u32 idx, int *nent, int maxnent, unsigned int type) +static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func, + int *nent, int maxnent, unsigned int type) { if (*nent >= maxnent) return -E2BIG; if (type == KVM_GET_EMULATED_CPUID) - return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + return __do_cpuid_func_emulated(entry, func, nent, maxnent); - return __do_cpuid_ent(entry, func, idx, nent, maxnent); + return __do_cpuid_func(entry, func, nent, maxnent); } #undef F struct kvm_cpuid_param { u32 func; - u32 idx; bool has_leaf_count; bool (*qualifier)(const struct kvm_cpuid_param *param); }; @@ -817,8 +812,8 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (ent->qualifier && !ent->qualifier(ent)) continue; - r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], ent->func, + &nent, cpuid->nent, type); if (r) goto out_free; @@ -828,8 +823,8 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) - r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent, type); + r = do_cpuid_func(&cpuid_entries[nent], func, + &nent, cpuid->nent, type); if (r) goto out_free; -- 2.25.1

1 5

[PATCH openEuler-1.0-LTS 1/6] Revert "sched/membarrier: fix NULL poiner in membarrier_global_expedited"
by Yang Yingliang 15 Jul '21

15 Jul '21

From: Li Hua <hucool.lihua(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I3UKOW CVE: NA ------------------------------------------------- This reverts commit 281caf306accfea76683f1dabc86749cc1de616a. Remove the work aroud to fix NULL poiner in membarrier_global_expedited, so as to prepare to introduce formal bug fix solution. Signed-off-by: Li Hua <hucool.lihua(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Reviewed-by: Zhang Qiao <zhangqiao22(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/sched/membarrier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index ea888ddb914f6..c4ea07e857985 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -115,7 +115,7 @@ static int membarrier_global_expedited(void) * scheduling a kthread. */ p = task_rcu_dereference(&cpu_rq(cpu)->curr); - if (p && p->flags & PF_KTHREAD) + if (p->flags & PF_KTHREAD) continue; __cpumask_set_cpu(cpu, tmpmask); -- 2.25.1

1 5

[PATCH OLK-5.10] patchwork test
by Zheng Zengkai 14 Jul '21

14 Jul '21

From: Xiaofei Tan <tanxiaofei(a)huawei.com> mainline inclusion from mainline-5.13-rc2 commit ccb5ecdc2ddeaff744ee075b54cdff8a689e8fa7 category: bugfix bugzilla: 167378 DTS: #525 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- Before commit 8fcc4ae6faf8 ("arm64: acpi: Make apei_claim_sea() synchronise with APEI's irq work"), do_sea() would unconditionally signal the affected task from the arch code. Since that change, the GHES driver sends the signals. This exposes a problem as errors the GHES driver doesn't understand or doesn't handle effectively are silently ignored. It will cause the errors get taken again, and circulate endlessly. User-space task get stuck in this loop. Existing firmware on Kunpeng9xx systems reports cache errors with the 'ARM Processor Error' CPER records. Do memory failure handling for ARM Processor Error Section just like for Memory Error Section. Fixes: 8fcc4ae6faf8 ("arm64: acpi: Make apei_claim_sea() synchronise with APEI's irq work") Signed-off-by: Xiaofei Tan <tanxiaofei(a)huawei.com> Reviewed-by: James Morse <james.morse(a)arm.com> [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Patchwork Links: http://patchwork.huawei.com/project/hulk5.10/list/?series=16359 --- drivers/acpi/apei/ghes.c | 81 +++++++++++++++++++++++++++++++--------- 1 file changed, 64 insertions(+), 17 deletions(-) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index fce7ade2aba9..0c8330ed1ffd 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -441,28 +441,35 @@ static void ghes_kick_task_work(struct callback_head *head) gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len); } -static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, - int sev) +static bool ghes_do_memory_failure(u64 physical_addr, int flags) { unsigned long pfn; - int flags = -1; - int sec_sev = ghes_severity(gdata->error_severity); - struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE)) return false; - if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) - return false; - - pfn = mem_err->physical_addr >> PAGE_SHIFT; + pfn = PHYS_PFN(physical_addr); if (!pfn_valid(pfn)) { pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid address in generic error data: %#llx\n", - mem_err->physical_addr); + physical_addr); return false; } + memory_failure_queue(pfn, flags); + return true; +} + +static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, + int sev) +{ + int flags = -1; + int sec_sev = ghes_severity(gdata->error_severity); + struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); + + if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) + return false; + /* iff following two events can be handled properly by now */ if (sec_sev == GHES_SEV_CORRECTED && (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED)) @@ -470,14 +477,56 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE) flags = 0; - if (flags != -1) { - memory_failure_queue(pfn, flags); - return true; - } + if (flags != -1) + return ghes_do_memory_failure(mem_err->physical_addr, flags); return false; } +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev) +{ + struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); + bool queued = false; + int sec_sev, i; + char *p; + + log_arm_hw_error(err); + + sec_sev = ghes_severity(gdata->error_severity); + if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE) + return false; + + p = (char *)(err + 1); + for (i = 0; i < err->err_info_num; i++) { + struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p; + bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR); + bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR); + const char *error_type = "unknown error"; + + /* + * The field (err_info->error_info & BIT(26)) is fixed to set to + * 1 in some old firmware of HiSilicon Kunpeng920. We assume that + * firmware won't mix corrected errors in an uncorrected section, + * and don't filter out 'corrected' error here. + */ + if (is_cache && has_pa) { + queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0); + p += err_info->length; + continue; + } + + if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs)) + error_type = cper_proc_error_type_strs[err_info->type]; + + pr_warn_ratelimited(FW_WARN GHES_PFX + "Unhandled processor error type: %s\n", + error_type); + p += err_info->length; + } + + return queued; +} + /* * PCIe AER errors need to be sent to the AER driver for reporting and * recovery. The GHES severities map to the following AER severities and @@ -605,9 +654,7 @@ static bool ghes_do_proc(struct ghes *ghes, ghes_handle_aer(gdata); } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { - struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); - - log_arm_hw_error(err); + queued = ghes_handle_arm_hw_error(gdata, sev); } else { void *err = acpi_hest_get_payload(gdata); -- 2.20.1

1 0

[PATCH openEuler-1.0-LTS] cifs: Fix leak when handling lease break for cached root fid
by Yang Yingliang 14 Jul '21

14 Jul '21

From: Paul Aurich <paul(a)darkrain42.org> mainline inclusion from mainline-5.9-rc1 commit baf57b56d3604880ccb3956ec6c62ea894f5de99 category: bugfix bugzilla: 40791 CVE: NA --------------------------- Handling a lease break for the cached root didn't free the smb2_lease_break_work allocation, resulting in a leak: unreferenced object 0xffff98383a5af480 (size 128): comm "cifsd", pid 684, jiffies 4294936606 (age 534.868s) hex dump (first 32 bytes): c0 ff ff ff 1f 00 00 00 88 f4 5a 3a 38 98 ff ff ..........Z:8... 88 f4 5a 3a 38 98 ff ff 80 88 d6 8a ff ff ff ff ..Z:8........... backtrace: [<0000000068957336>] smb2_is_valid_oplock_break+0x1fa/0x8c0 [<0000000073b70b9e>] cifs_demultiplex_thread+0x73d/0xcc0 [<00000000905fa372>] kthread+0x11c/0x150 [<0000000079378e4e>] ret_from_fork+0x22/0x30 Avoid this leak by only allocating when necessary. Fixes: a93864d93977 ("cifs: add lease tracking to the cached root fid") Signed-off-by: Paul Aurich <paul(a)darkrain42.org> CC: Stable <stable(a)vger.kernel.org> # v4.18+ Reviewed-by: Aurelien Aptel <aaptel(a)suse.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/smb2misc.c [ Not apply 9bd4540836("CIFS: Properly process SMB3 lease breaks") ] Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/cifs/smb2misc.c | 73 +++++++++++++++++++++++++++++++++------------- 1 file changed, 52 insertions(+), 21 deletions(-) diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 3b2c1f2ac9563..5236636f71b54 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -509,15 +509,31 @@ cifs_ses_oplock_break(struct work_struct *work) kfree(lw); } +static void +smb2_queue_pending_open_break(struct tcon_link *tlink, __u8 *lease_key, + __le32 new_lease_state) +{ + struct smb2_lease_break_work *lw; + + lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); + if (!lw) { + cifs_put_tlink(tlink); + return; + } + + INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); + lw->tlink = tlink; + lw->lease_state = new_lease_state; + memcpy(lw->lease_key, lease_key, SMB2_LEASE_KEY_SIZE); + queue_work(cifsiod_wq, &lw->lease_break); +} + static bool -smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, - struct smb2_lease_break_work *lw) +smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp) { - bool found; __u8 lease_state; struct list_head *tmp; struct cifsFileInfo *cfile; - struct cifs_pending_open *open; struct cifsInodeInfo *cinode; int ack_req = le32_to_cpu(rsp->Flags & SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); @@ -556,22 +572,29 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, &cinode->flags); cifs_queue_oplock_break(cfile); - kfree(lw); return true; } - found = false; + return false; +} + +static struct cifs_pending_open * +smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon, + struct smb2_lease_break *rsp) +{ + __u8 lease_state = le32_to_cpu(rsp->NewLeaseState); + int ack_req = le32_to_cpu(rsp->Flags & + SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED); + struct cifs_pending_open *open; + struct cifs_pending_open *found = NULL; + list_for_each_entry(open, &tcon->pending_opens, olist) { if (memcmp(open->lease_key, rsp->LeaseKey, SMB2_LEASE_KEY_SIZE)) continue; if (!found && ack_req) { - found = true; - memcpy(lw->lease_key, open->lease_key, - SMB2_LEASE_KEY_SIZE); - lw->tlink = cifs_get_tlink(open->tlink); - queue_work(cifsiod_wq, &lw->lease_break); + found = open; } cifs_dbg(FYI, "found in the pending open list\n"); @@ -592,14 +615,7 @@ smb2_is_valid_lease_break(char *buffer) struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - struct smb2_lease_break_work *lw; - - lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL); - if (!lw) - return false; - - INIT_WORK(&lw->lease_break, cifs_ses_oplock_break); - lw->lease_state = rsp->NewLeaseState; + struct cifs_pending_open *open; cifs_dbg(FYI, "Checking for lease break\n"); @@ -617,11 +633,27 @@ smb2_is_valid_lease_break(char *buffer) spin_lock(&tcon->open_file_lock); cifs_stats_inc( &tcon->stats.cifs_stats.num_oplock_brks); - if (smb2_tcon_has_lease(tcon, rsp, lw)) { + if (smb2_tcon_has_lease(tcon, rsp)) { spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); return true; } + open = smb2_tcon_find_pending_open_lease(tcon, + rsp); + if (open) { + __u8 lease_key[SMB2_LEASE_KEY_SIZE]; + struct tcon_link *tlink; + + tlink = cifs_get_tlink(open->tlink); + memcpy(lease_key, open->lease_key, + SMB2_LEASE_KEY_SIZE); + spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_tcp_ses_lock); + smb2_queue_pending_open_break(tlink, + lease_key, + rsp->NewLeaseState); + return true; + } spin_unlock(&tcon->open_file_lock); if (tcon->crfid.is_valid && @@ -639,7 +671,6 @@ smb2_is_valid_lease_break(char *buffer) } } spin_unlock(&cifs_tcp_ses_lock); - kfree(lw); cifs_dbg(FYI, "Can not process lease break - no lease matched\n"); return false; } -- 2.25.1

1 0

[PATCH kernel-4.19 1/6] nbd: handle device refs for DESTROY_ON_DISCONNECT properly
by Yang Yingliang 14 Jul '21

14 Jul '21

From: Josef Bacik <josef(a)toxicpanda.com> mainline inclusion from mainline-5.12-rc1 commit c9a2f90f4d6b category: bugfix bugzilla: 50455 CVE: NA ------------------------------------------------- There exists a race where we can be attempting to create a new nbd configuration while a previous configuration is going down, both configured with DESTROY_ON_DISCONNECT. Normally devices all have a reference of 1, as they won't be cleaned up until the module is torn down. However with DESTROY_ON_DISCONNECT we'll make sure that there is only 1 reference (generally) on the device for the config itself, and then once the config is dropped, the device is torn down. The race that exists looks like this TASK1 TASK2 nbd_genl_connect() idr_find() refcount_inc_not_zero(nbd) * count is 2 here ^^ nbd_config_put() nbd_put(nbd) (count is 1) setup new config check DESTROY_ON_DISCONNECT put_dev = true if (put_dev) nbd_put(nbd) * free'd here ^^ In nbd_genl_connect() we assume that the nbd ref count will be 2, however clearly that won't be true if the nbd device had been setup as DESTROY_ON_DISCONNECT with its prior configuration. Fix this by getting rid of the runtime flag to check if we need to mess with the nbd device refcount, and use the device NBD_DESTROY_ON_DISCONNECT flag to check if we need to adjust the ref counts. This was reported by syzkaller with the following kasan dump BUG: KASAN: use-after-free in instrument_atomic_read include/linux/instrumented.h:71 [inline] BUG: KASAN: use-after-free in atomic_read include/asm-generic/atomic-instrumented.h:27 [inline] BUG: KASAN: use-after-free in refcount_dec_not_one+0x71/0x1e0 lib/refcount.c:76 Read of size 4 at addr ffff888143bf71a0 by task systemd-udevd/8451 CPU: 0 PID: 8451 Comm: systemd-udevd Not tainted 5.11.0-rc7-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x107/0x163 lib/dump_stack.c:120 print_address_description.constprop.0.cold+0x5b/0x2f8 mm/kasan/report.c:230 __kasan_report mm/kasan/report.c:396 [inline] kasan_report.cold+0x79/0xd5 mm/kasan/report.c:413 check_memory_region_inline mm/kasan/generic.c:179 [inline] check_memory_region+0x13d/0x180 mm/kasan/generic.c:185 instrument_atomic_read include/linux/instrumented.h:71 [inline] atomic_read include/asm-generic/atomic-instrumented.h:27 [inline] refcount_dec_not_one+0x71/0x1e0 lib/refcount.c:76 refcount_dec_and_mutex_lock+0x19/0x140 lib/refcount.c:115 nbd_put drivers/block/nbd.c:248 [inline] nbd_release+0x116/0x190 drivers/block/nbd.c:1508 __blkdev_put+0x548/0x800 fs/block_dev.c:1579 blkdev_put+0x92/0x570 fs/block_dev.c:1632 blkdev_close+0x8c/0xb0 fs/block_dev.c:1640 __fput+0x283/0x920 fs/file_table.c:280 task_work_run+0xdd/0x190 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:174 [inline] exit_to_user_mode_prepare+0x249/0x250 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fc1e92b5270 Code: 73 01 c3 48 8b 0d 38 7d 20 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 59 c1 20 00 00 75 10 b8 03 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 ee fb ff ff 48 89 04 24 RSP: 002b:00007ffe8beb2d18 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000000000000007 RCX: 00007fc1e92b5270 RDX: 000000000aba9500 RSI: 0000000000000000 RDI: 0000000000000007 RBP: 00007fc1ea16f710 R08: 000000000000004a R09: 0000000000000008 R10: 0000562f8cb0b2a8 R11: 0000000000000246 R12: 0000000000000000 R13: 0000562f8cb0afd0 R14: 0000000000000003 R15: 000000000000000e Allocated by task 1: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:401 [inline] ____kasan_kmalloc.constprop.0+0x82/0xa0 mm/kasan/common.c:429 kmalloc include/linux/slab.h:552 [inline] kzalloc include/linux/slab.h:682 [inline] nbd_dev_add+0x44/0x8e0 drivers/block/nbd.c:1673 nbd_init+0x250/0x271 drivers/block/nbd.c:2394 do_one_initcall+0x103/0x650 init/main.c:1223 do_initcall_level init/main.c:1296 [inline] do_initcalls init/main.c:1312 [inline] do_basic_setup init/main.c:1332 [inline] kernel_init_freeable+0x605/0x689 init/main.c:1533 kernel_init+0xd/0x1b8 init/main.c:1421 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 Freed by task 8451: kasan_save_stack+0x1b/0x40 mm/kasan/common.c:38 kasan_set_track+0x1c/0x30 mm/kasan/common.c:46 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:356 ____kasan_slab_free+0xe1/0x110 mm/kasan/common.c:362 kasan_slab_free include/linux/kasan.h:192 [inline] slab_free_hook mm/slub.c:1547 [inline] slab_free_freelist_hook+0x5d/0x150 mm/slub.c:1580 slab_free mm/slub.c:3143 [inline] kfree+0xdb/0x3b0 mm/slub.c:4139 nbd_dev_remove drivers/block/nbd.c:243 [inline] nbd_put.part.0+0x180/0x1d0 drivers/block/nbd.c:251 nbd_put drivers/block/nbd.c:295 [inline] nbd_config_put+0x6dd/0x8c0 drivers/block/nbd.c:1242 nbd_release+0x103/0x190 drivers/block/nbd.c:1507 __blkdev_put+0x548/0x800 fs/block_dev.c:1579 blkdev_put+0x92/0x570 fs/block_dev.c:1632 blkdev_close+0x8c/0xb0 fs/block_dev.c:1640 __fput+0x283/0x920 fs/file_table.c:280 task_work_run+0xdd/0x190 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:174 [inline] exit_to_user_mode_prepare+0x249/0x250 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff888143bf7000 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 416 bytes inside of 1024-byte region [ffff888143bf7000, ffff888143bf7400) The buggy address belongs to the page: page:000000005238f4ce refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x143bf0 head:000000005238f4ce order:3 compound_mapcount:0 compound_pincount:0 flags: 0x57ff00000010200(slab|head) raw: 057ff00000010200 ffffea00004b1400 0000000300000003 ffff888010c41140 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888143bf7080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888143bf7100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff888143bf7180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888143bf7200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Reported-and-tested-by: syzbot+429d3f82d757c211bff3(a)syzkaller.appspotmail.com Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Luo Meng <luomeng12(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/block/nbd.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 55552f719b25b..01bede097ed25 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -76,8 +76,7 @@ struct link_dead_args { #define NBD_RT_HAS_PID_FILE 3 #define NBD_RT_HAS_CONFIG_REF 4 #define NBD_RT_BOUND 5 -#define NBD_RT_DESTROY_ON_DISCONNECT 6 -#define NBD_RT_DISCONNECT_ON_CLOSE 7 +#define NBD_RT_DISCONNECT_ON_CLOSE 6 #define NBD_DESTROY_ON_DISCONNECT 0 #define NBD_DISCONNECT_REQUESTED 1 @@ -1894,12 +1893,21 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) { u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]); if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) { - set_bit(NBD_RT_DESTROY_ON_DISCONNECT, - &config->runtime_flags); - set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags); - put_dev = true; + /* + * We have 1 ref to keep the device around, and then 1 + * ref for our current operation here, which will be + * inherited by the config. If we already have + * DESTROY_ON_DISCONNECT set then we know we don't have + * that extra ref already held so we don't need the + * put_dev. + */ + if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT, + &nbd->flags)) + put_dev = true; } else { - clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags); + if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT, + &nbd->flags)) + refcount_inc(&nbd->refs); } if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { set_bit(NBD_RT_DISCONNECT_ON_CLOSE, @@ -2067,15 +2075,13 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) { u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]); if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) { - if (!test_and_set_bit(NBD_RT_DESTROY_ON_DISCONNECT, - &config->runtime_flags)) + if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT, + &nbd->flags)) put_dev = true; - set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags); } else { - if (test_and_clear_bit(NBD_RT_DESTROY_ON_DISCONNECT, - &config->runtime_flags)) + if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT, + &nbd->flags)) refcount_inc(&nbd->refs); - clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags); } if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { -- 2.25.1

1 5

[PATCH kernel-4.19 00/33] backport linux-4.19.197
by Yang Yingliang 14 Jul '21

14 Jul '21

Alex Shi (1): mm: add VM_WARN_ON_ONCE_PAGE() macro Alper Gun (1): KVM: SVM: Call SEV Guest Decommission if ASID binding fails Anson Huang (1): ARM: dts: imx6qdl-sabresd: Remove incorrect power supply assignment Christian König (1): drm/nouveau: fix dma_address check for CPU/GPU sync Greg Kroah-Hartman (1): Linux 4.19.197 Hugh Dickins (16): mm/thp: fix __split_huge_pmd_locked() on shmem migration entry mm/thp: make is_huge_zero_pmd() safe and quicker mm/thp: try_to_unmap() use TTU_SYNC for safe splitting mm/thp: fix vma_address() if virtual address below file offset mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page() mm: page_vma_mapped_walk(): use page for pvmw->page mm: page_vma_mapped_walk(): settle PageHuge on entry mm: page_vma_mapped_walk(): use pmde for *pvmw->pmd mm: page_vma_mapped_walk(): prettify PVMW_MIGRATION block mm: page_vma_mapped_walk(): crossing page table boundary mm: page_vma_mapped_walk(): add a level of indentation mm: page_vma_mapped_walk(): use goto instead of while (1) mm: page_vma_mapped_walk(): get vma_address_end() earlier mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk() mm, futex: fix shared futex pgoff on shmem huge page Jue Wang (1): mm/thp: fix page_address_in_vma() on file THP tails Juergen Gross (1): xen/events: reset active flag for lateeoi events later ManYi Li (1): scsi: sr: Return appropriate error code when disk is ejected Miaohe Lin (2): mm/rmap: remove unneeded semicolon in page_not_mapped() mm/rmap: use page_not_mapped in try_to_unmap() Petr Mladek (2): kthread_worker: split code for canceling the delayed work timer kthread: prevent deadlock when kthread_mod_delayed_work() races with kthread_cancel_delayed_work_sync() Tony Lindgren (3): clocksource/drivers/timer-ti-dm: Add clockevent and clocksource support clocksource/drivers/timer-ti-dm: Prepare to handle dra7 timer wrap issue clocksource/drivers/timer-ti-dm: Handle dra7 timer wrap errata i940 Yang Shi (1): mm: thp: replace DEBUG_VM BUG with VM_WARN when unmap fails for split afzal mohammed (1): ARM: OMAP: replace setup_irq() by request_irq() Makefile | 2 +- arch/arm/boot/dts/dra7.dtsi | 11 ++ arch/arm/boot/dts/imx6qdl-sabresd.dtsi | 4 - arch/arm/mach-omap1/pm.c | 13 +- arch/arm/mach-omap1/time.c | 10 +- arch/arm/mach-omap1/timer32k.c | 10 +- arch/arm/mach-omap2/board-generic.c | 4 +- arch/arm/mach-omap2/timer.c | 181 +++++++++++++++++-------- arch/x86/kvm/svm.c | 32 +++-- drivers/clk/ti/clk-7xx.c | 1 + drivers/gpu/drm/nouveau/nouveau_bo.c | 4 +- drivers/scsi/sr.c | 2 + drivers/xen/events/events_base.c | 23 +++- include/linux/cpuhotplug.h | 1 + include/linux/huge_mm.h | 8 +- include/linux/hugetlb.h | 16 --- include/linux/mm.h | 3 + include/linux/mmdebug.h | 13 ++ include/linux/pagemap.h | 13 +- include/linux/rmap.h | 3 +- kernel/futex.c | 2 +- kernel/kthread.c | 77 +++++++---- mm/huge_memory.c | 56 ++++---- mm/hugetlb.c | 5 +- mm/internal.h | 53 ++++++-- mm/memory.c | 41 ++++++ mm/page_vma_mapped.c | 160 +++++++++++++--------- mm/pgtable-generic.c | 4 +- mm/rmap.c | 48 ++++--- mm/truncate.c | 43 +++--- 30 files changed, 541 insertions(+), 302 deletions(-) -- 2.25.1

1 33

[PATCH openEuler-1.0-LTS] mm/memcontrol.c: fix kasan slab-out-of-bounds in mem_cgroup_css_alloc
by Yang Yingliang 12 Jul '21

12 Jul '21

From: Lu Jialin <lujialin4(a)huawei.com> hulk inclusion category: bugfix bugzilla: 51815, https://gitee.com/openeuler/kernel/issues/I3IJ9I CVE: NA -------- static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { ... pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp); if (!pn) return 1; pnext = to_mgpn_ext(pn); pnext->lruvec_stat_local = alloc_percpu(struct lruvec_stat); } the size of pnext is larger than pn, so pnext->lruvec_stat_local is out of bounds Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/memcontrol.h | 12 +++++----- mm/memcontrol.c | 48 +++++++++++++++++++------------------- 2 files changed, 30 insertions(+), 30 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c7c7c0a418771..b4a25979ee8c7 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -609,11 +609,11 @@ static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, { long x = 0; int cpu; - struct mem_cgroup_extension *mgext; + struct mem_cgroup_extension *memcg_ext; - mgext = to_memcg_ext(memcg); + memcg_ext = to_memcg_ext(memcg); for_each_possible_cpu(cpu) - x += per_cpu(mgext->vmstats_local->count[idx], cpu); + x += per_cpu(memcg_ext->vmstats_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; @@ -687,7 +687,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; - struct mem_cgroup_per_node_extension *pnext; + struct mem_cgroup_per_node_extension *pn_ext; long x = 0; int cpu; @@ -695,9 +695,9 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - pnext = to_mgpn_ext(pn); + pn_ext = to_mgpn_ext(pn); for_each_possible_cpu(cpu) - x += per_cpu(pnext->lruvec_stat_local->count[idx], cpu); + x += per_cpu(pn_ext->lruvec_stat_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index da10300a6e7d7..713a839013f72 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -698,14 +698,14 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) x = val + __this_cpu_read(memcg->stat_cpu->count[idx]); if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) { struct mem_cgroup *mi; - struct mem_cgroup_extension *mgext; + struct mem_cgroup_extension *memcg_ext; /* * Batch local counters to keep them in sync with * the hierarchical ones. */ - mgext = to_memcg_ext(memcg); - __this_cpu_add(mgext->vmstats_local->count[idx], x); + memcg_ext = to_memcg_ext(memcg); + __this_cpu_add(memcg_ext->vmstats_local->count[idx], x); for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) atomic_long_add(x, &mi->stat[idx]); x = 0; @@ -739,7 +739,7 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, { pg_data_t *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup_per_node *pn; - struct mem_cgroup_per_node_extension *pnext; + struct mem_cgroup_per_node_extension *pn_ext; struct mem_cgroup *memcg; long x; @@ -756,8 +756,8 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, __mod_memcg_state(memcg, idx, val); /* Update lruvec */ - pnext = to_mgpn_ext(pn); - __this_cpu_add(pnext->lruvec_stat_local->count[idx], val); + pn_ext = to_mgpn_ext(pn); + __this_cpu_add(pn_ext->lruvec_stat_local->count[idx], val); x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]); if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) { @@ -787,14 +787,14 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, x = count + __this_cpu_read(memcg->stat_cpu->events[idx]); if (unlikely(x > MEMCG_CHARGE_BATCH)) { struct mem_cgroup *mi; - struct mem_cgroup_extension *mgext; + struct mem_cgroup_extension *memcg_ext; /* * Batch local counters to keep them in sync with * the hierarchical ones. */ - mgext = to_memcg_ext(memcg); - __this_cpu_add(mgext->vmstats_local->events[idx], x); + memcg_ext = to_memcg_ext(memcg); + __this_cpu_add(memcg_ext->vmstats_local->events[idx], x); for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) atomic_long_add(x, &mi->events[idx]); x = 0; @@ -811,11 +811,11 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) { long x = 0; int cpu; - struct mem_cgroup_extension *mgext; + struct mem_cgroup_extension *memcg_ext; - mgext = to_memcg_ext(memcg); + memcg_ext = to_memcg_ext(memcg); for_each_possible_cpu(cpu) - x += per_cpu(mgext->vmstats_local->events[event], cpu); + x += per_cpu(memcg_ext->vmstats_local->events[event], cpu); return x; } @@ -4837,7 +4837,7 @@ struct mem_cgroup *mem_cgroup_from_id(unsigned short id) static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; - struct mem_cgroup_per_node_extension *pnext; + struct mem_cgroup_per_node_extension *pn_ext; int tmp = node; /* * This routine is called against possible nodes. @@ -4849,21 +4849,21 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) */ if (!node_state(node, N_NORMAL_MEMORY)) tmp = -1; - pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp); + pn_ext = kzalloc_node(sizeof(*pn_ext), GFP_KERNEL, tmp); + pn = &pn_ext->pn; if (!pn) return 1; - pnext = to_mgpn_ext(pn); - pnext->lruvec_stat_local = alloc_percpu(struct lruvec_stat); - if (!pnext->lruvec_stat_local) { - kfree(pnext); + pn_ext->lruvec_stat_local = alloc_percpu(struct lruvec_stat); + if (!pn_ext->lruvec_stat_local) { + kfree(pn_ext); return 1; } pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat); if (!pn->lruvec_stat_cpu) { - free_percpu(pnext->lruvec_stat_local); - kfree(pn); + free_percpu(pn_ext->lruvec_stat_local); + kfree(pn_ext); return 1; } @@ -4879,15 +4879,15 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; - struct mem_cgroup_per_node_extension *pnext; + struct mem_cgroup_per_node_extension *pn_ext; if (!pn) return; + pn_ext = to_mgpn_ext(pn); free_percpu(pn->lruvec_stat_cpu); - pnext = to_mgpn_ext(pn); - free_percpu(pnext->lruvec_stat_local); - kfree(pn); + free_percpu(pn_ext->lruvec_stat_local); + kfree(pn_ext); } static void __mem_cgroup_free(struct mem_cgroup *memcg) -- 2.25.1

1 0

[PATCH kernel-4.19] btrfs: allow btrfs_truncate_block() to fallback to nocow for data space reservation
by Yang Yingliang 12 Jul '21

12 Jul '21

From: Qu Wenruo <wqu(a)suse.com> mainline inclusion from mainline-v5.13-rc5 commit 6d4572a9d71d5fc2affee0258d8582d39859188c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I39MZM CVE: NA ------------------------------------------------------ [BUG] When the data space is exhausted, even if the inode has NOCOW attribute, we will still refuse to truncate unaligned range due to ENOSPC. The following script can reproduce it pretty easily: #!/bin/bash dev=/dev/test/test mnt=/mnt/btrfs umount $dev &> /dev/null umount $mnt &> /dev/null mkfs.btrfs -f $dev -b 1G mount -o nospace_cache $dev $mnt touch $mnt/foobar chattr +C $mnt/foobar xfs_io -f -c "pwrite -b 4k 0 4k" $mnt/foobar > /dev/null xfs_io -f -c "pwrite -b 4k 0 1G" $mnt/padding &> /dev/null sync xfs_io -c "fpunch 0 2k" $mnt/foobar umount $mnt Currently this will fail at the fpunch part. [CAUSE] Because btrfs_truncate_block() always reserves space without checking the NOCOW attribute. Since the writeback path follows NOCOW bit, we only need to bother the space reservation code in btrfs_truncate_block(). [FIX] Make btrfs_truncate_block() follow btrfs_buffered_write() to try to reserve data space first, and fall back to NOCOW check only when we don't have enough space. Such always-try-reserve is an optimization introduced in btrfs_buffered_write(), to avoid expensive btrfs_check_can_nocow() call. This patch will export check_can_nocow() as btrfs_check_can_nocow(), and use it in btrfs_truncate_block() to fix the problem. Reference: https://patchwork.kernel.org/project/linux-btrfs/patch/20200130052822.11765… Reported-by: Martin Doucha <martin.doucha(a)suse.com> Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: Anand Jain <anand.jain(a)oracle.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Conflicts: fs/btrfs/file.c fs/btrfs/inode.c Signed-off-by: Gou Hao <gouhao(a)uniontech.com> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Jiao Fenfang <jiaofenfang(a)uniontech.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/btrfs/ctree.h | 3 ++- fs/btrfs/file.c | 8 ++++---- fs/btrfs/inode.c | 39 +++++++++++++++++++++++++++++++++------ 3 files changed, 39 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4d1c12faada89..4f5c58d40a79f 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3271,7 +3271,8 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); int btrfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); - +int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, struct btrfs_root *root); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 41ad37f8062a9..3cd05edca30ce 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1536,8 +1536,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, return ret; } -static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) +int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1647,7 +1647,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, if (ret < 0) { if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && - check_can_nocow(BTRFS_I(inode), pos, + btrfs_check_can_nocow(BTRFS_I(inode), pos, &write_bytes) > 0) { /* * For nodata cow case, no need to reserve @@ -1925,7 +1925,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, */ if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { + btrfs_check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { inode_unlock(inode); return -EAGAIN; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index bf0e0e3e09c5d..9e3e003e4488e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4958,11 +4958,13 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; char *kaddr; + bool only_release_metadata = false; u32 blocksize = fs_info->sectorsize; pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (blocksize - 1); struct page *page; gfp_t mask = btrfs_alloc_write_mask(mapping); + size_t write_bytes = blocksize; int ret = 0; u64 block_start; u64 block_end; @@ -4974,10 +4976,26 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, block_start = round_down(from, blocksize); block_end = block_start + blocksize - 1; - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, - block_start, blocksize); - if (ret) + ret = btrfs_check_data_free_space(inode, &data_reserved, + block_start, blocksize); + if (ret < 0) { + if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) && + btrfs_check_can_nocow(BTRFS_I(inode), block_start, + &write_bytes) > 0) { + /* For nocow case, no need to reserve data space */ + only_release_metadata = true; + } else { + goto out; + } + } + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize); + if (ret < 0) { + if (!only_release_metadata) + btrfs_free_reserved_data_space(inode, data_reserved, + block_start, blocksize); goto out; + } again: page = find_or_create_page(mapping, index, mask); @@ -5048,10 +5066,19 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, set_page_dirty(page); unlock_extent_cached(io_tree, block_start, block_end, &cached_state); + if (only_release_metadata) + set_extent_bit(&BTRFS_I(inode)->io_tree, block_start, + block_end, EXTENT_NORESERVE, NULL, NULL, + GFP_NOFS); out_unlock: - if (ret) - btrfs_delalloc_release_space(inode, data_reserved, block_start, - blocksize, true); + if (ret) { + if (only_release_metadata) + btrfs_delalloc_release_metadata(BTRFS_I(inode), + blocksize, true); + else + btrfs_delalloc_release_space(inode, data_reserved, + block_start, blocksize, true); + } btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); unlock_page(page); put_page(page); -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] module: limit enabling module.sig_enforce
by Yang Yingliang 12 Jul '21

12 Jul '21

From: Mimi Zohar <zohar(a)linux.ibm.com> stable inclusion from linux-4.19.196 commit ff660863628fb144badcb3395cde7821c82c13a6 CVE: CVE-2021-35039 -------------------------------- [ Upstream commit 0c18f29aae7ce3dadd26d8ee3505d07cc982df75 ] Irrespective as to whether CONFIG_MODULE_SIG is configured, specifying "module.sig_enforce=1" on the boot command line sets "sig_enforce". Only allow "sig_enforce" to be set when CONFIG_MODULE_SIG is configured. This patch makes the presence of /sys/module/module/parameters/sig_enforce dependent on CONFIG_MODULE_SIG=y. Fixes: fda784e50aac ("module: export module signature enforcement status") Reported-by: Nayna Jain <nayna(a)linux.ibm.com> Tested-by: Mimi Zohar <zohar(a)linux.ibm.com> Tested-by: Jessica Yu <jeyu(a)kernel.org> Signed-off-by: Mimi Zohar <zohar(a)linux.ibm.com> Signed-off-by: Jessica Yu <jeyu(a)kernel.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/module.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/kernel/module.c b/kernel/module.c index ad4c1d7b7a956..82c83cbf6ce6c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -268,9 +268,18 @@ static void module_assert_mutex_or_preempt(void) #endif } +#ifdef CONFIG_MODULE_SIG static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); module_param(sig_enforce, bool_enable_only, 0644); +void set_module_sig_enforced(void) +{ + sig_enforce = true; +} +#else +#define sig_enforce false +#endif + /* * Export sig_enforce kernel cmdline parameter to allow other subsystems rely * on that instead of directly to CONFIG_MODULE_SIG_FORCE config. -- 2.25.1

1 0

[PATCH kernel-4.19 1/4] xfs: let writable tracepoint enable to clear flag of f_mode
by Yang Yingliang 12 Jul '21

12 Jul '21

From: Yufen Yu <yuyufen(a)huawei.com> hulk inclusion category: feature bugzilla: 173267 CVE: NA --------------------------- Adding a new member clear_f_mode into struct xfs_writable_file, then we can clear some flag of file->f_mode. Signed-off-by: Yufen Yu <yuyufen(a)huawei.com> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/xfs/xfs_file.c | 10 +++++++--- include/linux/fs.h | 9 ++++++--- include/uapi/linux/xfs.h | 4 +++- tools/include/uapi/linux/xfs.h | 2 +- 4 files changed, 17 insertions(+), 8 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ffc388c8b4523..bd8ae4df20042 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -35,6 +35,8 @@ #include <linux/mman.h> #include <linux/fadvise.h> +#define FMODE_MASK (FMODE_RANDOM | FMODE_WILLNEED | FMODE_SPC_READAHEAD) + static const struct vm_operations_struct xfs_file_vm_ops; int @@ -238,15 +240,17 @@ xfs_file_buffered_aio_read( struct xfs_writable_file file; file.name = file_dentry(filp)->d_name.name; + file.clear_f_mode = 0; file.f_mode = 0; file.i_size = file_inode(filp)->i_size; - file.prev_pos = filp->f_ra.prev_pos; + file.prev_pos = filp->f_ra.prev_pos >> PAGE_SHIFT; + file.pos = iocb->ki_pos >> PAGE_SHIFT; trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos); trace_xfs_file_read(&file, ip, iov_iter_count(to), iocb->ki_pos); - if (file.f_mode) - filp->f_mode |= file.f_mode; + filp->f_mode |= file.f_mode & FMODE_MASK; + filp->f_mode &= ~(file.clear_f_mode & FMODE_MASK); if (iocb->ki_flags & IOCB_NOWAIT) { if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) diff --git a/include/linux/fs.h b/include/linux/fs.h index f5bc43ac95035..394da46d143c2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -160,6 +160,12 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) +/* File will try to read head of the file into pagecache */ +#define FMODE_WILLNEED ((__force fmode_t)0x400000) + +/* File will do specail readahead */ +#define FMODE_SPC_READAHEAD ((__force fmode_t)0x800000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -169,9 +175,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) -/* File will try to read head of the file into pagecache */ -#define FMODE_WILLNEED ((__force fmode_t)0x40000000) - /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are diff --git a/include/uapi/linux/xfs.h b/include/uapi/linux/xfs.h index 635a83914273b..0a11c2344e5a3 100644 --- a/include/uapi/linux/xfs.h +++ b/include/uapi/linux/xfs.h @@ -7,9 +7,11 @@ struct xfs_writable_file { const unsigned char *name; + unsigned int clear_f_mode; /* can be cleared from file->f_mode */ unsigned int f_mode; /* can be set into file->f_mode */ long long i_size; /* file size */ - long long prev_pos; /* ra->prev_pos */ + long long prev_pos; /* ra->prev_pos page index */ + long long pos; /* iocb->ki_pos page index */ }; #endif /* _UAPI_LINUX_XFS_H */ diff --git a/tools/include/uapi/linux/xfs.h b/tools/include/uapi/linux/xfs.h index f333a2eb74074..2c4c61d5ba539 100644 --- a/tools/include/uapi/linux/xfs.h +++ b/tools/include/uapi/linux/xfs.h @@ -5,7 +5,7 @@ #include <linux/types.h> #define FMODE_RANDOM (0x1000) -#define FMODE_WILLNEED (0x40000000) +#define FMODE_WILLNEED (0x400000) struct xfs_writable_file { const unsigned char *name; -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS] jbd2: fix kabi broken in struct journal_s
by Yang Yingliang 09 Jul '21

09 Jul '21

From: yangerkun <yangerkun(a)huawei.com> hulk inclusion category: bugfix bugzilla: 172974 CVE: NA --------------------------- 72c9e4df6a99 ('jbd2: ensure abort the journal if detect IO error when writing original buffer back') will add 'j_atomic_flags' which can lead lots of kabi broken like jbd2_journal_destroy/jbd2_journal_abort and so on. Fix it by add a wrapper. Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/jbd2/checkpoint.c | 5 ++++- fs/jbd2/journal.c | 19 +++++++++++++------ include/linux/jbd2.h | 23 ++++++++++++++++++----- 3 files changed, 35 insertions(+), 12 deletions(-) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index b1af15ad36dcb..f2c36c9c58be3 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -562,6 +562,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) struct transaction_chp_stats_s *stats; transaction_t *transaction; journal_t *journal; + journal_wrapper_t *journal_wrapper; struct buffer_head *bh = jh2bh(jh); JBUFFER_TRACE(jh, "entry"); @@ -572,6 +573,8 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) return 0; } journal = transaction->t_journal; + journal_wrapper = container_of(journal, journal_wrapper_t, + jw_journal); JBUFFER_TRACE(jh, "removing from transaction"); @@ -583,7 +586,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) * journal here and we abort the journal later from a better context. */ if (buffer_write_io_error(bh)) - set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags); + set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal_wrapper->j_atomic_flags); __buffer_unlink(jh); jh->b_cp_transaction = NULL; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 89fad4c3e13cb..ef9a942fc9a1a 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1129,14 +1129,17 @@ static journal_t *journal_init_common(struct block_device *bdev, { static struct lock_class_key jbd2_trans_commit_key; journal_t *journal; + journal_wrapper_t *journal_wrapper; int err; struct buffer_head *bh; int n; - journal = kzalloc(sizeof(*journal), GFP_KERNEL); - if (!journal) + journal_wrapper = kzalloc(sizeof(*journal_wrapper), GFP_KERNEL); + if (!journal_wrapper) return NULL; + journal = &(journal_wrapper->jw_journal); + init_waitqueue_head(&journal->j_wait_transaction_locked); init_waitqueue_head(&journal->j_wait_done_commit); init_waitqueue_head(&journal->j_wait_commit); @@ -1195,7 +1198,7 @@ static journal_t *journal_init_common(struct block_device *bdev, err_cleanup: kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); - kfree(journal); + kfree(journal_wrapper); return NULL; } @@ -1425,11 +1428,13 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, unsigned long tail_block, int write_op) { journal_superblock_t *sb = journal->j_superblock; + journal_wrapper_t *journal_wrapper = container_of(journal, + journal_wrapper_t, jw_journal); int ret; if (is_journal_aborted(journal)) return -EIO; - if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) { + if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal_wrapper->j_atomic_flags)) { jbd2_journal_abort(journal, -EIO); return -EIO; } @@ -1754,6 +1759,8 @@ int jbd2_journal_load(journal_t *journal) int jbd2_journal_destroy(journal_t *journal) { int err = 0; + journal_wrapper_t *journal_wrapper = container_of(journal, + journal_wrapper_t, jw_journal); /* Wait for the commit thread to wake up and die. */ journal_kill_thread(journal); @@ -1795,7 +1802,7 @@ int jbd2_journal_destroy(journal_t *journal) * may become inconsistent. */ if (!is_journal_aborted(journal) && - test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) + test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal_wrapper->j_atomic_flags)) jbd2_journal_abort(journal, -EIO); if (journal->j_sb_buffer) { @@ -1823,7 +1830,7 @@ int jbd2_journal_destroy(journal_t *journal) if (journal->j_chksum_driver) crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_wbuf); - kfree(journal); + kfree(journal_wrapper); return err; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 5c0446f22bee1..ef213666c3a3b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -105,6 +105,8 @@ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ + +typedef struct journal_wrapper_s journal_wrapper_t; #endif /* @@ -780,11 +782,6 @@ struct journal_s */ unsigned long j_flags; - /** - * @j_atomic_flags: Atomic journaling state flags. - */ - unsigned long j_atomic_flags; - /** * @j_errno: * @@ -1199,6 +1196,22 @@ struct journal_s #endif }; +/** + * struct journal_wrapper_s - The wrapper of journal_s to fix KABI. + */ +struct journal_wrapper_s +{ + /** + * @jw_journal: real journal. + */ + journal_t jw_journal; + + /** + * @j_atomic_flags: Atomic journaling state flags. + */ + unsigned long j_atomic_flags; +}; + #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ -- 2.25.1

1 0

[PATCH OLK-5.10] x86/perf: Add uncore performance monitor support for Zhaoxin CPUs
by LeoLiuoc 09 Jul '21

09 Jul '21

Zhaoxin CPUs have already provided a performance monitoring unit on hardware for uncore, but this feature has not been used. Therefore, add support for Zhaoxin CPUs to make it available to monitor the uncore performance. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/events/zhaoxin/Makefile | 1 + arch/x86/events/zhaoxin/uncore.c | 1123 ++++++++++++++++++++++++++++++ arch/x86/events/zhaoxin/uncore.h | 311 +++++++++ 3 files changed, 1435 insertions(+) create mode 100644 arch/x86/events/zhaoxin/uncore.c create mode 100644 arch/x86/events/zhaoxin/uncore.h diff --git a/arch/x86/events/zhaoxin/Makefile b/arch/x86/events/zhaoxin/Makefile index 642c1174d662..767d6212bac1 100644 --- a/arch/x86/events/zhaoxin/Makefile +++ b/arch/x86/events/zhaoxin/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-y += core.o +obj-y += uncore.o diff --git a/arch/x86/events/zhaoxin/uncore.c b/arch/x86/events/zhaoxin/uncore.c new file mode 100644 index 000000000000..96771063a61e --- /dev/null +++ b/arch/x86/events/zhaoxin/uncore.c @@ -0,0 +1,1123 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <asm/cpu_device_id.h> +#include "uncore.h" + +static struct zhaoxin_uncore_type *empty_uncore[] = { NULL, }; +static struct zhaoxin_uncore_type **uncore_msr_uncores = empty_uncore; + +/* mask of cpus that collect uncore events */ +static cpumask_t uncore_cpu_mask; + +/* constraint for the fixed counter */ +static struct event_constraint uncore_constraint_fixed = + EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL); + +static int max_packages; + +/* CHX event control */ +#define CHX_UNC_CTL_EV_SEL_MASK 0x000000ff +#define CHX_UNC_CTL_UMASK_MASK 0x0000ff00 +#define CHX_UNC_CTL_EDGE_DET (1 << 18) +#define CHX_UNC_CTL_EN (1 << 22) +#define CHX_UNC_CTL_INVERT (1 << 23) +#define CHX_UNC_CTL_CMASK_MASK 0xff000000 +#define CHX_UNC_FIXED_CTR_CTL_EN (1 << 0) + +#define CHX_UNC_RAW_EVENT_MASK (CHX_UNC_CTL_EV_SEL_MASK | \ + CHX_UNC_CTL_UMASK_MASK | \ + CHX_UNC_CTL_EDGE_DET | \ + CHX_UNC_CTL_INVERT | \ + CHX_UNC_CTL_CMASK_MASK) + +/* CHX global control register */ +#define CHX_UNC_PERF_GLOBAL_CTL 0x391 +#define CHX_UNC_FIXED_CTR 0x394 +#define CHX_UNC_FIXED_CTR_CTRL 0x395 + +/* CHX uncore global control */ +#define CHX_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 4) - 1) +#define CHX_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) + +/* CHX uncore register */ +#define CHX_UNC_PERFEVTSEL0 0x3c0 +#define CHX_UNC_UNCORE_PMC0 0x3b0 + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); + +ssize_t zx_uncore_event_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct uncore_event_desc *event = + container_of(attr, struct uncore_event_desc, attr); + return sprintf(buf, "%s", event->config); +} + +/*chx uncore support */ +static void chx_uncore_msr_disable_event(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static u64 uncore_msr_read_counter(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + u64 count; + + rdmsrl(event->hw.event_base, count); + + return count; +} + +static void chx_uncore_msr_disable_box(struct zhaoxin_uncore_box *box) +{ + wrmsrl(CHX_UNC_PERF_GLOBAL_CTL, 0); +} + +static void chx_uncore_msr_enable_box(struct zhaoxin_uncore_box *box) +{ + wrmsrl(CHX_UNC_PERF_GLOBAL_CTL, CHX_UNC_GLOBAL_CTL_EN_PC_ALL | CHX_UNC_GLOBAL_CTL_EN_FC); +} + +static void chx_uncore_msr_enable_event(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | CHX_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, CHX_UNC_FIXED_CTR_CTL_EN); +} + +static struct attribute *chx_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask8.attr, + NULL, +}; + +static struct attribute_group chx_uncore_format_group = { + .name = "format", + .attrs = chx_uncore_formats_attr, +}; + +static struct uncore_event_desc chx_uncore_events[] = { + { /* end: all zeroes */ }, +}; + +static struct zhaoxin_uncore_ops chx_uncore_msr_ops = { + .disable_box = chx_uncore_msr_disable_box, + .enable_box = chx_uncore_msr_enable_box, + .disable_event = chx_uncore_msr_disable_event, + .enable_event = chx_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct zhaoxin_uncore_type chx_uncore_box = { + .name = "", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .event_ctl = CHX_UNC_PERFEVTSEL0, + .perf_ctr = CHX_UNC_UNCORE_PMC0, + .fixed_ctr = CHX_UNC_FIXED_CTR, + .fixed_ctl = CHX_UNC_FIXED_CTR_CTRL, + .event_mask = CHX_UNC_RAW_EVENT_MASK, + .event_descs = chx_uncore_events, + .ops = &chx_uncore_msr_ops, + .format_group = &chx_uncore_format_group, +}; + +static struct zhaoxin_uncore_type *chx_msr_uncores[] = { + &chx_uncore_box, + NULL, +}; + +static struct zhaoxin_uncore_box *uncore_pmu_to_box(struct zhaoxin_uncore_pmu *pmu, int cpu) +{ + unsigned int package_id = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return package_id < max_packages ? pmu->boxes[package_id] : NULL; +} + +static void uncore_assign_hw_event(struct zhaoxin_uncore_box *box, + struct perf_event *event, int idx) +{ + struct hw_perf_event *hwc = &event->hw; + + hwc->idx = idx; + hwc->last_tag = ++box->tags[idx]; + + if (uncore_pmc_fixed(hwc->idx)) { + hwc->event_base = uncore_fixed_ctr(box); + hwc->config_base = uncore_fixed_ctl(box); + return; + } + + hwc->config_base = uncore_event_ctl(box, hwc->idx); + hwc->event_base = uncore_perf_ctr(box, hwc->idx); +} + +void uncore_perf_event_update(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + u64 prev_count, new_count, delta; + int shift; + + if (uncore_pmc_fixed(event->hw.idx)) + shift = 64 - uncore_fixed_ctr_bits(box); + else + shift = 64 - uncore_perf_ctr_bits(box); + + /* the hrtimer might modify the previous event value */ +again: + prev_count = local64_read(&event->hw.prev_count); + new_count = uncore_read_counter(box, event); + if (local64_xchg(&event->hw.prev_count, new_count) != prev_count) + goto again; + + delta = (new_count << shift) - (prev_count << shift); + delta >>= shift; + + local64_add(delta, &event->count); +} + +static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) +{ + struct zhaoxin_uncore_box *box; + struct perf_event *event; + unsigned long flags; + int bit; + + box = container_of(hrtimer, struct zhaoxin_uncore_box, hrtimer); + if (!box->n_active || box->cpu != smp_processor_id()) + return HRTIMER_NORESTART; + /* + * disable local interrupt to prevent uncore_pmu_event_start/stop + * to interrupt the update process + */ + local_irq_save(flags); + + /* + * handle boxes with an active event list as opposed to active + * counters + */ + list_for_each_entry(event, &box->active_list, active_entry) { + uncore_perf_event_update(box, event); + } + + for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX) + uncore_perf_event_update(box, box->events[bit]); + + local_irq_restore(flags); + + hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration)); + return HRTIMER_RESTART; +} + +static void uncore_pmu_start_hrtimer(struct zhaoxin_uncore_box *box) +{ + hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration), + HRTIMER_MODE_REL_PINNED); +} + +static void uncore_pmu_cancel_hrtimer(struct zhaoxin_uncore_box *box) +{ + hrtimer_cancel(&box->hrtimer); +} + +static void uncore_pmu_init_hrtimer(struct zhaoxin_uncore_box *box) +{ + hrtimer_init(&box->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + box->hrtimer.function = uncore_pmu_hrtimer; +} + +static struct zhaoxin_uncore_box *uncore_alloc_box(struct zhaoxin_uncore_type *type, + int node) +{ + int i, size, numshared = type->num_shared_regs; + struct zhaoxin_uncore_box *box; + + size = sizeof(*box) + numshared * sizeof(struct zhaoxin_uncore_extra_reg); + + box = kzalloc_node(size, GFP_KERNEL, node); + if (!box) + return NULL; + + for (i = 0; i < numshared; i++) + raw_spin_lock_init(&box->shared_regs[i].lock); + + uncore_pmu_init_hrtimer(box); + box->cpu = -1; + box->package_id = -1; + + /* set default hrtimer timeout */ + box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL; + + INIT_LIST_HEAD(&box->active_list); + + return box; +} + +static bool is_box_event(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + return &box->pmu->pmu == event->pmu; +} + +static struct event_constraint * +uncore_get_event_constraint(struct zhaoxin_uncore_box *box, struct perf_event *event) +{ + struct zhaoxin_uncore_type *type = box->pmu->type; + struct event_constraint *c; + + if (type->ops->get_constraint) { + c = type->ops->get_constraint(box, event); + if (c) + return c; + } + + if (event->attr.config == UNCORE_FIXED_EVENT) + return &uncore_constraint_fixed; + + if (type->constraints) { + for_each_event_constraint(c, type->constraints) { + if ((event->hw.config & c->cmask) == c->code) + return c; + } + } + + return &type->unconstrainted; +} + +static void uncore_put_event_constraint(struct zhaoxin_uncore_box *box, + struct perf_event *event) +{ + if (box->pmu->type->ops->put_constraint) + box->pmu->type->ops->put_constraint(box, event); +} + +static int uncore_assign_events(struct zhaoxin_uncore_box *box, int assign[], int n) +{ + unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; + struct event_constraint *c; + int i, wmin, wmax, ret = 0; + struct hw_perf_event *hwc; + + bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX); + + for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) { + c = uncore_get_event_constraint(box, box->event_list[i]); + box->event_constraint[i] = c; + wmin = min(wmin, c->weight); + wmax = max(wmax, c->weight); + } + + /* fastpath, try to reuse previous register */ + for (i = 0; i < n; i++) { + hwc = &box->event_list[i]->hw; + c = box->event_constraint[i]; + + /* never assigned */ + if (hwc->idx == -1) + break; + + /* constraint still honored */ + if (!test_bit(hwc->idx, c->idxmsk)) + break; + + /* not already used */ + if (test_bit(hwc->idx, used_mask)) + break; + + __set_bit(hwc->idx, used_mask); + if (assign) + assign[i] = hwc->idx; + } + /* slow path */ + if (i != n) + ret = perf_assign_events(box->event_constraint, n, + wmin, wmax, n, assign); + + if (!assign || ret) { + for (i = 0; i < n; i++) + uncore_put_event_constraint(box, box->event_list[i]); + } + return ret ? -EINVAL : 0; +} + +static void uncore_pmu_event_start(struct perf_event *event, int flags) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + int idx = event->hw.idx; + + + if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX)) + return; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + box->events[idx] = event; + box->n_active++; + __set_bit(idx, box->active_mask); + + local64_set(&event->hw.prev_count, uncore_read_counter(box, event)); + uncore_enable_event(box, event); + + if (box->n_active == 1) + uncore_pmu_start_hrtimer(box); +} + +static void uncore_pmu_event_stop(struct perf_event *event, int flags) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (__test_and_clear_bit(hwc->idx, box->active_mask)) { + uncore_disable_event(box, event); + box->n_active--; + box->events[hwc->idx] = NULL; + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + if (box->n_active == 0) + uncore_pmu_cancel_hrtimer(box); + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + uncore_perf_event_update(box, event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int +uncore_collect_events(struct zhaoxin_uncore_box *box, struct perf_event *leader, + bool dogrp) +{ + struct perf_event *event; + int n, max_count; + + max_count = box->pmu->type->num_counters; + if (box->pmu->type->fixed_ctl) + max_count++; + + if (box->n_events >= max_count) + return -EINVAL; + + n = box->n_events; + + if (is_box_event(box, leader)) { + box->event_list[n] = leader; + n++; + } + + if (!dogrp) + return n; + + for_each_sibling_event(event, leader) { + if (!is_box_event(box, event) || + event->state <= PERF_EVENT_STATE_OFF) + continue; + + if (n >= max_count) + return -EINVAL; + + box->event_list[n] = event; + n++; + } + return n; +} + +static int uncore_pmu_event_add(struct perf_event *event, int flags) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + int assign[UNCORE_PMC_IDX_MAX]; + int i, n, ret; + + if (!box) + return -ENODEV; + + ret = n = uncore_collect_events(box, event, false); + if (ret < 0) + return ret; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; + + ret = uncore_assign_events(box, assign, n); + if (ret) + return ret; + + /* save events moving to new counters */ + for (i = 0; i < box->n_events; i++) { + event = box->event_list[i]; + hwc = &event->hw; + + if (hwc->idx == assign[i] && + hwc->last_tag == box->tags[assign[i]]) + continue; + /* + * Ensure we don't accidentally enable a stopped + * counter simply because we rescheduled. + */ + if (hwc->state & PERF_HES_STOPPED) + hwc->state |= PERF_HES_ARCH; + + uncore_pmu_event_stop(event, PERF_EF_UPDATE); + } + + /* reprogram moved events into new counters */ + for (i = 0; i < n; i++) { + event = box->event_list[i]; + hwc = &event->hw; + + if (hwc->idx != assign[i] || + hwc->last_tag != box->tags[assign[i]]) + uncore_assign_hw_event(box, event, assign[i]); + else if (i < box->n_events) + continue; + + if (hwc->state & PERF_HES_ARCH) + continue; + + uncore_pmu_event_start(event, 0); + } + box->n_events = n; + + return 0; +} + +static int uncore_validate_group(struct zhaoxin_uncore_pmu *pmu, + struct perf_event *event) +{ + struct perf_event *leader = event->group_leader; + struct zhaoxin_uncore_box *fake_box; + int ret = -EINVAL, n; + + fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE); + if (!fake_box) + return -ENOMEM; + + fake_box->pmu = pmu; + /* + * the event is not yet connected with its + * siblings therefore we must first collect + * existing siblings, then add the new event + * before we can simulate the scheduling + */ + n = uncore_collect_events(fake_box, leader, true); + if (n < 0) + goto out; + + fake_box->n_events = n; + n = uncore_collect_events(fake_box, event, false); + if (n < 0) + goto out; + + fake_box->n_events = n; + + ret = uncore_assign_events(fake_box, NULL, n); +out: + kfree(fake_box); + return ret; +} + +static void uncore_pmu_event_del(struct perf_event *event, int flags) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + int i; + + uncore_pmu_event_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < box->n_events; i++) { + if (event == box->event_list[i]) { + uncore_put_event_constraint(box, event); + + for (++i; i < box->n_events; i++) + box->event_list[i - 1] = box->event_list[i]; + + --box->n_events; + break; + } + } + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; +} + +static void uncore_pmu_event_read(struct perf_event *event) +{ + struct zhaoxin_uncore_box *box = uncore_event_to_box(event); + + uncore_perf_event_update(box, event); +} + +static int uncore_pmu_event_init(struct perf_event *event) +{ + struct zhaoxin_uncore_pmu *pmu; + struct zhaoxin_uncore_box *box; + struct hw_perf_event *hwc = &event->hw; + int ret; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + pmu = uncore_event_to_pmu(event); + /* no device found for this pmu */ + if (pmu->func_id < 0) + return -ENOENT; + + /* Sampling not supported yet */ + if (hwc->sample_period) + return -EINVAL; + + /* + * Place all uncore events for a particular physical package + * onto a single cpu + */ + if (event->cpu < 0) + return -EINVAL; + box = uncore_pmu_to_box(pmu, event->cpu); + if (!box || box->cpu < 0) + return -EINVAL; + event->cpu = box->cpu; + event->pmu_private = box; + + event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; + event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; + + if (event->attr.config == UNCORE_FIXED_EVENT) { + /* no fixed counter */ + if (!pmu->type->fixed_ctl) + return -EINVAL; + /* + * if there is only one fixed counter, only the first pmu + * can access the fixed counter + */ + if (pmu->type->single_fixed && pmu->pmu_idx > 0) + return -EINVAL; + + /* fixed counters have event field hardcoded to zero */ + hwc->config = 0ULL; + } else { + hwc->config = event->attr.config & + (pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32)); + if (pmu->type->ops->hw_config) { + ret = pmu->type->ops->hw_config(box, event); + if (ret) + return ret; + } + } + + if (event->group_leader != event) + ret = uncore_validate_group(pmu, event); + else + ret = 0; + + return ret; +} + +static void uncore_pmu_enable(struct pmu *pmu) +{ + struct zhaoxin_uncore_pmu *uncore_pmu; + struct zhaoxin_uncore_box *box; + + uncore_pmu = container_of(pmu, struct zhaoxin_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->enable_box) + uncore_pmu->type->ops->enable_box(box); +} + +static void uncore_pmu_disable(struct pmu *pmu) +{ + struct zhaoxin_uncore_pmu *uncore_pmu; + struct zhaoxin_uncore_box *box; + + uncore_pmu = container_of(pmu, struct zhaoxin_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->disable_box) + uncore_pmu->type->ops->disable_box(box); +} + +static ssize_t uncore_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &uncore_cpu_mask); +} + +static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL); + +static struct attribute *uncore_pmu_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static const struct attribute_group uncore_pmu_attr_group = { + .attrs = uncore_pmu_attrs, +}; + +static void uncore_pmu_unregister(struct zhaoxin_uncore_pmu *pmu) +{ + if (!pmu->registered) + return; + perf_pmu_unregister(&pmu->pmu); + pmu->registered = false; +} + +static void uncore_free_boxes(struct zhaoxin_uncore_pmu *pmu) +{ + int package; + + for (package = 0; package < max_packages; package++) + kfree(pmu->boxes[package]); + kfree(pmu->boxes); +} + +static void uncore_type_exit(struct zhaoxin_uncore_type *type) +{ + struct zhaoxin_uncore_pmu *pmu = type->pmus; + int i; + + if (pmu) { + for (i = 0; i < type->num_boxes; i++, pmu++) { + uncore_pmu_unregister(pmu); + uncore_free_boxes(pmu); + } + kfree(type->pmus); + type->pmus = NULL; + } + kfree(type->events_group); + type->events_group = NULL; +} + +static void uncore_types_exit(struct zhaoxin_uncore_type **types) +{ + for (; *types; types++) + uncore_type_exit(*types); +} + +static int __init uncore_type_init(struct zhaoxin_uncore_type *type, bool setid) +{ + struct zhaoxin_uncore_pmu *pmus; + size_t size; + int i, j; + + pmus = kcalloc(type->num_boxes, sizeof(*pmus), GFP_KERNEL); + if (!pmus) + return -ENOMEM; + + size = max_packages*sizeof(struct zhaoxin_uncore_box *); + + for (i = 0; i < type->num_boxes; i++) { + pmus[i].func_id = setid ? i : -1; + pmus[i].pmu_idx = i; + pmus[i].type = type; + pmus[i].boxes = kzalloc(size, GFP_KERNEL); + if (!pmus[i].boxes) + goto err; + } + + type->pmus = pmus; + type->unconstrainted = (struct event_constraint) + __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, + 0, type->num_counters, 0, 0); + + if (type->event_descs) { + struct { + struct attribute_group group; + struct attribute *attrs[]; + } *attr_group; + for (i = 0; type->event_descs[i].attr.attr.name; i++) + ; + + attr_group = kzalloc(struct_size(attr_group, attrs, i + 1), GFP_KERNEL); + if (!attr_group) + goto err; + + attr_group->group.name = "events"; + attr_group->group.attrs = attr_group->attrs; + + for (j = 0; j < i; j++) + attr_group->attrs[j] = &type->event_descs[j].attr.attr; + + type->events_group = &attr_group->group; + } + + type->pmu_group = &uncore_pmu_attr_group; + + return 0; + +err: + for (i = 0; i < type->num_boxes; i++) + kfree(pmus[i].boxes); + kfree(pmus); + + return -ENOMEM; +} + +static int __init +uncore_types_init(struct zhaoxin_uncore_type **types, bool setid) +{ + int ret; + + for (; *types; types++) { + ret = uncore_type_init(*types, setid); + if (ret) + return ret; + } + return 0; +} + +static void uncore_change_type_ctx(struct zhaoxin_uncore_type *type, int old_cpu, + int new_cpu) +{ + struct zhaoxin_uncore_pmu *pmu = type->pmus; + struct zhaoxin_uncore_box *box; + int i, package; + + package = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu); + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[package]; + if (!box) + continue; + + if (old_cpu < 0) { + WARN_ON_ONCE(box->cpu != -1); + box->cpu = new_cpu; + continue; + } + + WARN_ON_ONCE(box->cpu != old_cpu); + box->cpu = -1; + if (new_cpu < 0) + continue; + + uncore_pmu_cancel_hrtimer(box); + perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu); + box->cpu = new_cpu; + } +} + +static void uncore_change_context(struct zhaoxin_uncore_type **uncores, + int old_cpu, int new_cpu) +{ + for (; *uncores; uncores++) + uncore_change_type_ctx(*uncores, old_cpu, new_cpu); +} + +static void uncore_box_unref(struct zhaoxin_uncore_type **types, int id) +{ + struct zhaoxin_uncore_type *type; + struct zhaoxin_uncore_pmu *pmu; + struct zhaoxin_uncore_box *box; + int i; + + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[id]; + if (box && atomic_dec_return(&box->refcnt) == 0) + uncore_box_exit(box); + } + } +} + +static int uncore_event_cpu_offline(unsigned int cpu) +{ + int package, target; + + /* Check if exiting cpu is used for collecting uncore events */ + if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) + goto unref; + /* Find a new cpu to collect uncore events */ + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); + + /* Migrate uncore events to the new target */ + if (target < nr_cpu_ids) + cpumask_set_cpu(target, &uncore_cpu_mask); + else + target = -1; + + uncore_change_context(uncore_msr_uncores, cpu, target); + +unref: + /* Clear the references */ + package = topology_logical_package_id(cpu); + uncore_box_unref(uncore_msr_uncores, package); + return 0; +} + +static int allocate_boxes(struct zhaoxin_uncore_type **types, + unsigned int package, unsigned int cpu) +{ + struct zhaoxin_uncore_box *box, *tmp; + struct zhaoxin_uncore_type *type; + struct zhaoxin_uncore_pmu *pmu; + LIST_HEAD(allocated); + int i; + + /* Try to allocate all required boxes */ + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + if (pmu->boxes[package]) + continue; + box = uncore_alloc_box(type, cpu_to_node(cpu)); + if (!box) + goto cleanup; + box->pmu = pmu; + box->package_id = package; + list_add(&box->active_list, &allocated); + } + } + /* Install them in the pmus */ + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + box->pmu->boxes[package] = box; + } + return 0; + +cleanup: + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + kfree(box); + } + return -ENOMEM; +} + +static int uncore_box_ref(struct zhaoxin_uncore_type **types, + int id, unsigned int cpu) +{ + struct zhaoxin_uncore_type *type; + struct zhaoxin_uncore_pmu *pmu; + struct zhaoxin_uncore_box *box; + int i, ret; + + ret = allocate_boxes(types, id, cpu); + if (ret) + return ret; + + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[id]; + if (box && atomic_inc_return(&box->refcnt) == 1) + uncore_box_init(box); + } + } + return 0; +} + +static int uncore_event_cpu_online(unsigned int cpu) +{ + int package, target, msr_ret; + + package = topology_logical_package_id(cpu); + msr_ret = uncore_box_ref(uncore_msr_uncores, package, cpu); + + if (msr_ret) + return -ENOMEM; + + /* + * Check if there is an online cpu in the package + * which collects uncore events already. + */ + target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu)); + if (target < nr_cpu_ids) + return 0; + + cpumask_set_cpu(cpu, &uncore_cpu_mask); + + if (!msr_ret) + uncore_change_context(uncore_msr_uncores, -1, cpu); + + return 0; +} + +static int uncore_pmu_register(struct zhaoxin_uncore_pmu *pmu) +{ + int ret; + + if (!pmu->type->pmu) { + pmu->pmu = (struct pmu) { + .attr_groups = pmu->type->attr_groups, + .task_ctx_nr = perf_invalid_context, + .pmu_enable = uncore_pmu_enable, + .pmu_disable = uncore_pmu_disable, + .event_init = uncore_pmu_event_init, + .add = uncore_pmu_event_add, + .del = uncore_pmu_event_del, + .start = uncore_pmu_event_start, + .stop = uncore_pmu_event_stop, + .read = uncore_pmu_event_read, + .module = THIS_MODULE, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + }; + } else { + pmu->pmu = *pmu->type->pmu; + pmu->pmu.attr_groups = pmu->type->attr_groups; + } + + if (pmu->type->num_boxes == 1) { + if (strlen(pmu->type->name) > 0) + sprintf(pmu->name, "uncore_%s", pmu->type->name); + else + sprintf(pmu->name, "uncore"); + } else { + sprintf(pmu->name, "uncore_%s_%d", pmu->type->name, + pmu->pmu_idx); + } + + ret = perf_pmu_register(&pmu->pmu, pmu->name, -1); + if (!ret) + pmu->registered = true; + return ret; +} + +static int __init type_pmu_register(struct zhaoxin_uncore_type *type) +{ + int i, ret; + + for (i = 0; i < type->num_boxes; i++) { + ret = uncore_pmu_register(&type->pmus[i]); + if (ret) + return ret; + } + return 0; +} + +static int __init uncore_msr_pmus_register(void) +{ + struct zhaoxin_uncore_type **types = uncore_msr_uncores; + int ret; + + for (; *types; types++) { + ret = type_pmu_register(*types); + if (ret) + return ret; + } + return 0; +} + +static int __init uncore_cpu_init(void) +{ + int ret; + + ret = uncore_types_init(uncore_msr_uncores, true); + if (ret) + goto err; + + ret = uncore_msr_pmus_register(); + if (ret) + goto err; + return 0; +err: + uncore_types_exit(uncore_msr_uncores); + uncore_msr_uncores = empty_uncore; + return ret; +} + +struct zhaoxin_uncore_init_fun { + void (*cpu_init)(void); +}; + +void chx_uncore_cpu_init(void) +{ + uncore_msr_uncores = chx_msr_uncores; +} + +static const struct zhaoxin_uncore_init_fun chx_uncore_init __initconst = { + .cpu_init = chx_uncore_cpu_init, +}; + +static const struct x86_cpu_id zhaoxin_uncore_match[] __initconst = { + X86_MATCH_VENDOR_FAM_MODEL(ZHAOXIN, 7, ZHAOXIN_FAM7_ZXD, &chx_uncore_init), + X86_MATCH_VENDOR_FAM_MODEL(ZHAOXIN, 7, ZHAOXIN_FAM7_ZXE, &chx_uncore_init), + X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 7, ZHAOXIN_FAM7_ZXD, &chx_uncore_init), + X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 7, ZHAOXIN_FAM7_ZXE, &chx_uncore_init), + {}, +}; + +MODULE_DEVICE_TABLE(x86cpu, zhaoxin_uncore_match); + +static int __init zhaoxin_uncore_init(void) +{ + const struct x86_cpu_id *id; + struct zhaoxin_uncore_init_fun *uncore_init; + int cret = 0, ret; + + id = x86_match_cpu(zhaoxin_uncore_match); + + if (!id) + return -ENODEV; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + + max_packages = topology_max_packages(); + + pr_info("welcome to uncore!\n"); + + uncore_init = (struct zhaoxin_uncore_init_fun *)id->driver_data; + + if (uncore_init->cpu_init) { + uncore_init->cpu_init(); + cret = uncore_cpu_init(); + } + + if (cret) + return -ENODEV; + + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, + "perf/x86/zhaoxin/uncore:online", + uncore_event_cpu_online, + uncore_event_cpu_offline); + pr_info("zhaoxin uncore init success!\n"); + if (ret) + goto err; + return 0; + +err: + uncore_types_exit(uncore_msr_uncores); + return ret; +} +module_init(zhaoxin_uncore_init); + +static void __exit zhaoxin_uncore_exit(void) +{ + cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE); + uncore_types_exit(uncore_msr_uncores); +} +module_exit(zhaoxin_uncore_exit); diff --git a/arch/x86/events/zhaoxin/uncore.h b/arch/x86/events/zhaoxin/uncore.h new file mode 100644 index 000000000000..e0f4ec340725 --- /dev/null +++ b/arch/x86/events/zhaoxin/uncore.h @@ -0,0 +1,311 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Zhaoxin PMU; like Intel Architectural PerfMon-v2 + */ +#include <linux/slab.h> +#include <linux/pci.h> +#include <asm/apicdef.h> +#include <linux/io-64-nonatomic-lo-hi.h> + +#include <linux/perf_event.h> +#include "../perf_event.h" + +#define ZHAOXIN_FAM7_ZXD 0x1b +#define ZHAOXIN_FAM7_ZXE 0x3b + +#define UNCORE_PMU_NAME_LEN 32 +#define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) +#define UNCORE_CHX_IMC_HRTIMER_INTERVAL (5ULL * NSEC_PER_SEC) + + +#define UNCORE_FIXED_EVENT 0xff +#define UNCORE_PMC_IDX_MAX_GENERIC 4 +#define UNCORE_PMC_IDX_MAX_FIXED 1 +#define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC + +#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1) + +struct zhaoxin_uncore_ops; +struct zhaoxin_uncore_pmu; +struct zhaoxin_uncore_box; +struct uncore_event_desc; + +struct zhaoxin_uncore_type { + const char *name; + int num_counters; + int num_boxes; + int perf_ctr_bits; + int fixed_ctr_bits; + unsigned int perf_ctr; + unsigned int event_ctl; + unsigned int event_mask; + unsigned int event_mask_ext; + unsigned int fixed_ctr; + unsigned int fixed_ctl; + unsigned int box_ctl; + unsigned int msr_offset; + unsigned int num_shared_regs:8; + unsigned int single_fixed:1; + unsigned int pair_ctr_ctl:1; + unsigned int *msr_offsets; + struct event_constraint unconstrainted; + struct event_constraint *constraints; + struct zhaoxin_uncore_pmu *pmus; + struct zhaoxin_uncore_ops *ops; + struct uncore_event_desc *event_descs; + const struct attribute_group *attr_groups[4]; + struct pmu *pmu; /* for custom pmu ops */ +}; + +#define pmu_group attr_groups[0] +#define format_group attr_groups[1] +#define events_group attr_groups[2] + +struct zhaoxin_uncore_ops { + void (*init_box)(struct zhaoxin_uncore_box *); + void (*exit_box)(struct zhaoxin_uncore_box *); + void (*disable_box)(struct zhaoxin_uncore_box *); + void (*enable_box)(struct zhaoxin_uncore_box *); + void (*disable_event)(struct zhaoxin_uncore_box *, struct perf_event *); + void (*enable_event)(struct zhaoxin_uncore_box *, struct perf_event *); + u64 (*read_counter)(struct zhaoxin_uncore_box *, struct perf_event *); + int (*hw_config)(struct zhaoxin_uncore_box *, struct perf_event *); + struct event_constraint *(*get_constraint)(struct zhaoxin_uncore_box *, + struct perf_event *); + void (*put_constraint)(struct zhaoxin_uncore_box *, struct perf_event *); +}; + +struct zhaoxin_uncore_pmu { + struct pmu pmu; + char name[UNCORE_PMU_NAME_LEN]; + int pmu_idx; + int func_id; + bool registered; + atomic_t activeboxes; + struct zhaoxin_uncore_type *type; + struct zhaoxin_uncore_box **boxes; +}; + +struct zhaoxin_uncore_extra_reg { + raw_spinlock_t lock; + u64 config, config1, config2; + atomic_t ref; +}; + +struct zhaoxin_uncore_box { + int pci_phys_id; + int package_id; /*Package ID */ + int n_active; /* number of active events */ + int n_events; + int cpu; /* cpu to collect events */ + unsigned long flags; + atomic_t refcnt; + struct perf_event *events[UNCORE_PMC_IDX_MAX]; + struct perf_event *event_list[UNCORE_PMC_IDX_MAX]; + struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX]; + unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; + u64 tags[UNCORE_PMC_IDX_MAX]; + struct pci_dev *pci_dev; + struct zhaoxin_uncore_pmu *pmu; + u64 hrtimer_duration; /* hrtimer timeout for this box */ + struct hrtimer hrtimer; + struct list_head list; + struct list_head active_list; + void __iomem *io_addr; + struct zhaoxin_uncore_extra_reg shared_regs[0]; +}; + +#define UNCORE_BOX_FLAG_INITIATED 0 + +struct uncore_event_desc { + struct device_attribute attr; + const char *config; +}; + +ssize_t zx_uncore_event_show(struct device *dev, + struct device_attribute *attr, char *buf); + +#define ZHAOXIN_UNCORE_EVENT_DESC(_name, _config) \ +{ \ + .attr = __ATTR(_name, 0444, zx_uncore_event_show, NULL), \ + .config = _config, \ +} + +#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __uncore_##_var##_show(struct device *dev, \ + struct device_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct device_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __uncore_##_var##_show, NULL) + +static inline bool uncore_pmc_fixed(int idx) +{ + return idx == UNCORE_PMC_IDX_FIXED; +} + +static inline unsigned int uncore_msr_box_offset(struct zhaoxin_uncore_box *box) +{ + struct zhaoxin_uncore_pmu *pmu = box->pmu; + + return pmu->type->msr_offsets ? + pmu->type->msr_offsets[pmu->pmu_idx] : + pmu->type->msr_offset * pmu->pmu_idx; +} + +static inline unsigned int uncore_msr_box_ctl(struct zhaoxin_uncore_box *box) +{ + if (!box->pmu->type->box_ctl) + return 0; + return box->pmu->type->box_ctl + uncore_msr_box_offset(box); +} + +static inline unsigned int uncore_msr_fixed_ctl(struct zhaoxin_uncore_box *box) +{ + if (!box->pmu->type->fixed_ctl) + return 0; + return box->pmu->type->fixed_ctl + uncore_msr_box_offset(box); +} + +static inline unsigned int uncore_msr_fixed_ctr(struct zhaoxin_uncore_box *box) +{ + return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box); +} + +static inline +unsigned int uncore_msr_event_ctl(struct zhaoxin_uncore_box *box, int idx) +{ + return box->pmu->type->event_ctl + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + + uncore_msr_box_offset(box); +} + +static inline +unsigned int uncore_msr_perf_ctr(struct zhaoxin_uncore_box *box, int idx) +{ + return box->pmu->type->perf_ctr + + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + + uncore_msr_box_offset(box); +} + +static inline +unsigned int uncore_fixed_ctl(struct zhaoxin_uncore_box *box) +{ + return uncore_msr_fixed_ctl(box); +} + +static inline +unsigned int uncore_fixed_ctr(struct zhaoxin_uncore_box *box) +{ + return uncore_msr_fixed_ctr(box); +} + +static inline +unsigned int uncore_event_ctl(struct zhaoxin_uncore_box *box, int idx) +{ + return uncore_msr_event_ctl(box, idx); +} + +static inline +unsigned int uncore_perf_ctr(struct zhaoxin_uncore_box *box, int idx) +{ + return uncore_msr_perf_ctr(box, idx); +} + +static inline int uncore_perf_ctr_bits(struct zhaoxin_uncore_box *box) +{ + return box->pmu->type->perf_ctr_bits; +} + +static inline int uncore_fixed_ctr_bits(struct zhaoxin_uncore_box *box) +{ + return box->pmu->type->fixed_ctr_bits; +} + +static inline int uncore_num_counters(struct zhaoxin_uncore_box *box) +{ + return box->pmu->type->num_counters; +} + +static inline void uncore_disable_box(struct zhaoxin_uncore_box *box) +{ + if (box->pmu->type->ops->disable_box) + box->pmu->type->ops->disable_box(box); +} + +static inline void uncore_enable_box(struct zhaoxin_uncore_box *box) +{ + if (box->pmu->type->ops->enable_box) + box->pmu->type->ops->enable_box(box); +} + +static inline void uncore_disable_event(struct zhaoxin_uncore_box *box, + struct perf_event *event) +{ + box->pmu->type->ops->disable_event(box, event); +} + +static inline void uncore_enable_event(struct zhaoxin_uncore_box *box, + struct perf_event *event) +{ + box->pmu->type->ops->enable_event(box, event); +} + +static inline u64 uncore_read_counter(struct zhaoxin_uncore_box *box, + struct perf_event *event) +{ + return box->pmu->type->ops->read_counter(box, event); +} + +static inline void uncore_box_init(struct zhaoxin_uncore_box *box) +{ + if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->init_box) + box->pmu->type->ops->init_box(box); + } +} + +static inline void uncore_box_exit(struct zhaoxin_uncore_box *box) +{ + if (test_and_clear_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->exit_box) + box->pmu->type->ops->exit_box(box); + } +} + +static inline bool uncore_box_is_fake(struct zhaoxin_uncore_box *box) +{ + return (box->package_id < 0); +} + +static inline struct zhaoxin_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct zhaoxin_uncore_pmu, pmu); +} + +static inline struct zhaoxin_uncore_box *uncore_event_to_box(struct perf_event *event) +{ + return event->pmu_private; +} + + +static struct zhaoxin_uncore_box *uncore_pmu_to_box(struct zhaoxin_uncore_pmu *pmu, int cpu); +static u64 uncore_msr_read_counter(struct zhaoxin_uncore_box *box, struct perf_event *event); + +static void uncore_pmu_start_hrtimer(struct zhaoxin_uncore_box *box); +static void uncore_pmu_cancel_hrtimer(struct zhaoxin_uncore_box *box); +static void uncore_pmu_event_start(struct perf_event *event, int flags); +static void uncore_pmu_event_stop(struct perf_event *event, int flags); +static int uncore_pmu_event_add(struct perf_event *event, int flags); +static void uncore_pmu_event_del(struct perf_event *event, int flags); +static void uncore_pmu_event_read(struct perf_event *event); +static void uncore_perf_event_update(struct zhaoxin_uncore_box *box, struct perf_event *event); +struct event_constraint * +uncore_get_constraint(struct zhaoxin_uncore_box *box, struct perf_event *event); +void uncore_put_constraint(struct zhaoxin_uncore_box *box, struct perf_event *event); +u64 uncore_shared_reg_config(struct zhaoxin_uncore_box *box, int idx); + +void chx_uncore_cpu_init(void); -- 2.20.1

1 0

[PATCH OLK-5.10] iommu/vt-d:Add support for detecting ACPI device in RMRR
by LeoLiuoc 09 Jul '21

09 Jul '21

Some ACPI devices need to issue dma requests to access the reserved memory area.BIOS uses the device scope type ACPI_NAMESPACE_DEVICE in RMRR to report these ACPI devices. This patch add support for detecting ACPI devices in RMRR and in order to distinguish it from PCI device, some interface functions are modified. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/iommu/intel/dmar.c | 77 +++++++++++++++++++-------------- drivers/iommu/intel/iommu.c | 86 ++++++++++++++++++++++++++++++++++--- drivers/iommu/iommu.c | 6 +++ include/linux/dmar.h | 11 ++++- include/linux/iommu.h | 3 ++ 5 files changed, 142 insertions(+), 41 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index b8d0b56a7575..1d705589fe21 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -215,7 +215,7 @@ static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus, } /* Return: > 0 if match found, 0 if no match found, < 0 if error happens */ -int dmar_insert_dev_scope(struct dmar_pci_notify_info *info, +int dmar_pci_insert_dev_scope(struct dmar_pci_notify_info *info, void *start, void*end, u16 segment, struct dmar_dev_scope *devices, int devices_cnt) @@ -304,7 +304,7 @@ static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info) drhd = container_of(dmaru->hdr, struct acpi_dmar_hardware_unit, header); - ret = dmar_insert_dev_scope(info, (void *)(drhd + 1), + ret = dmar_pci_insert_dev_scope(info, (void *)(drhd + 1), ((void *)drhd) + drhd->header.length, dmaru->segment, dmaru->devices, dmaru->devices_cnt); @@ -719,47 +719,58 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev) return dmaru; } -static void __init dmar_acpi_insert_dev_scope(u8 device_number, - struct acpi_device *adev) +/* Return: > 0 if match found, 0 if no match found */ +bool dmar_acpi_insert_dev_scope(u8 device_number, + struct acpi_device *adev, + void *start, void *end, + struct dmar_dev_scope *devices, + int devices_cnt) { - struct dmar_drhd_unit *dmaru; - struct acpi_dmar_hardware_unit *drhd; struct acpi_dmar_device_scope *scope; struct device *tmp; int i; struct acpi_dmar_pci_path *path; + for (; start < end; start += scope->length) { + scope = start; + if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_NAMESPACE) + continue; + if (scope->enumeration_id != device_number) + continue; + path = (void *)(scope + 1); + for_each_dev_scope(devices, devices_cnt, i, tmp) + if (tmp == NULL) { + devices[i].bus = scope->bus; + devices[i].devfn = PCI_DEVFN(path->device, path->function); + rcu_assign_pointer(devices[i].dev, + get_device(&adev->dev)); + return true; + } + WARN_ON(i >= devices_cnt); + } + return false; +} + +static int dmar_acpi_bus_add_dev(u8 device_number, struct acpi_device *adev) +{ + struct dmar_drhd_unit *dmaru; + struct acpi_dmar_hardware_unit *drhd; + int ret; + for_each_drhd_unit(dmaru) { drhd = container_of(dmaru->hdr, struct acpi_dmar_hardware_unit, header); - - for (scope = (void *)(drhd + 1); - (unsigned long)scope < ((unsigned long)drhd) + drhd->header.length; - scope = ((void *)scope) + scope->length) { - if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_NAMESPACE) - continue; - if (scope->enumeration_id != device_number) - continue; - - path = (void *)(scope + 1); - pr_info("ACPI device \"%s\" under DMAR at %llx as %02x:%02x.%d\n", - dev_name(&adev->dev), dmaru->reg_base_addr, - scope->bus, path->device, path->function); - for_each_dev_scope(dmaru->devices, dmaru->devices_cnt, i, tmp) - if (tmp == NULL) { - dmaru->devices[i].bus = scope->bus; - dmaru->devices[i].devfn = PCI_DEVFN(path->device, - path->function); - rcu_assign_pointer(dmaru->devices[i].dev, - get_device(&adev->dev)); - return; - } - BUG_ON(i >= dmaru->devices_cnt); - } + ret = dmar_acpi_insert_dev_scope(device_number, adev, (void *)(drhd+1), + ((void *)drhd)+drhd->header.length, + dmaru->devices, dmaru->devices_cnt); + if (ret) + break; } - pr_warn("No IOMMU scope found for ANDD enumeration ID %d (%s)\n", - device_number, dev_name(&adev->dev)); + if (ret > 0) + ret = dmar_rmrr_add_acpi_dev(device_number, adev); + + return ret; } static int __init dmar_acpi_dev_scope_init(void) @@ -788,7 +799,7 @@ static int __init dmar_acpi_dev_scope_init(void) andd->device_name); continue; } - dmar_acpi_insert_dev_scope(andd->device_number, adev); + dmar_acpi_bus_add_dev(andd->device_number, adev); } } return 0; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 6cc6ef585aa4..5f2b7a64d2c7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4600,6 +4600,25 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev) return ret; } +int dmar_rmrr_add_acpi_dev(u8 device_number, struct acpi_device *adev) +{ + int ret; + struct dmar_rmrr_unit *rmrru; + struct acpi_dmar_reserved_memory *rmrr; + + list_for_each_entry(rmrru, &dmar_rmrr_units, list) { + rmrr = container_of(rmrru->hdr, + struct acpi_dmar_reserved_memory, + header); + ret = dmar_acpi_insert_dev_scope(device_number, adev, (void *)(rmrr + 1), + ((void *)rmrr) + rmrr->header.length, + rmrru->devices, rmrru->devices_cnt); + if (ret) + break; + } + return 0; +} + int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) { int ret; @@ -4615,7 +4634,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) rmrr = container_of(rmrru->hdr, struct acpi_dmar_reserved_memory, header); if (info->event == BUS_NOTIFY_ADD_DEVICE) { - ret = dmar_insert_dev_scope(info, (void *)(rmrr + 1), + ret = dmar_pci_insert_dev_scope(info, (void *)(rmrr + 1), ((void *)rmrr) + rmrr->header.length, rmrr->segment, rmrru->devices, rmrru->devices_cnt); @@ -4633,7 +4652,7 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header); if (info->event == BUS_NOTIFY_ADD_DEVICE) { - ret = dmar_insert_dev_scope(info, (void *)(atsr + 1), + ret = dmar_pci_insert_dev_scope(info, (void *)(atsr + 1), (void *)atsr + atsr->header.length, atsr->segment, atsru->devices, atsru->devices_cnt); @@ -4872,6 +4891,22 @@ static int __init platform_optin_force_iommu(void) return 1; } +static int acpi_device_create_direct_mappings(struct device *pn_dev, struct device *acpi_device) +{ + struct iommu_group *group; + + acpi_device->bus->iommu_ops = &intel_iommu_ops; + group = iommu_group_get(pn_dev); + if (!group) { + pr_warn("ACPI name space devices create direct mappings wrong!\n"); + return -EINVAL; + } + printk(KERN_INFO "pn_dev:%s enter to %s\n", dev_name(pn_dev), __func__); + __acpi_device_create_direct_mappings(group, acpi_device); + + return 0; +} + static int __init probe_acpi_namespace_devices(void) { struct dmar_drhd_unit *drhd; @@ -4879,6 +4914,7 @@ static int __init probe_acpi_namespace_devices(void) struct intel_iommu *iommu __maybe_unused; struct device *dev; int i, ret = 0; + u8 bus, devfn; for_each_active_iommu(iommu, drhd) { for_each_active_dev_scope(drhd->devices, @@ -4887,6 +4923,8 @@ static int __init probe_acpi_namespace_devices(void) struct iommu_group *group; struct acpi_device *adev; + struct device *pn_dev = NULL; + struct device_domain_info *info = NULL; if (dev->bus != &acpi_bus_type) continue; @@ -4896,19 +4934,53 @@ static int __init probe_acpi_namespace_devices(void) &adev->physical_node_list, node) { group = iommu_group_get(pn->dev); if (group) { + pn_dev = pn->dev; iommu_group_put(group); continue; } - pn->dev->bus->iommu_ops = &intel_iommu_ops; - ret = iommu_probe_device(pn->dev); - if (ret) - break; + iommu = device_to_iommu(dev, &bus, &devfn); + if (!iommu) + return -ENODEV; + info = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn); + if (!info) { + pn->dev->bus->iommu_ops = &intel_iommu_ops; + ret = iommu_probe_device(pn->dev); + if (ret) { + pr_err("pn->dev:%s probe fail! ret:%d\n", + dev_name(pn->dev), ret); + goto unlock; + } + } + pn_dev = pn->dev; + } + if (!pn_dev) { + iommu = device_to_iommu(dev, &bus, &devfn); + if (!iommu) + return -ENODEV; + info = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn); + if (!info) { + dev->bus->iommu_ops = &intel_iommu_ops; + ret = iommu_probe_device(dev); + if (ret) { + pr_err("dev:%s probe fail! ret:%d\n", + dev_name(dev), ret); + goto unlock; + } + goto unlock; + } } + if (!info) + ret = acpi_device_create_direct_mappings(pn_dev, dev); + else + ret = acpi_device_create_direct_mappings(info->dev, dev); +unlock: mutex_unlock(&adev->physical_node_lock); - if (ret) + if (ret) { + pr_err("%s fail! ret:%d\n", __func__, ret); return ret; + } } } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 86e3dbdfb7bd..6212eb1856f5 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -814,6 +814,12 @@ static bool iommu_is_attach_deferred(struct iommu_domain *domain, return false; } +void __acpi_device_create_direct_mappings(struct iommu_group *group, struct device *acpi_device) +{ + iommu_create_device_direct_mappings(group, acpi_device); +} +EXPORT_SYMBOL_GPL(__acpi_device_create_direct_mappings); + /** * iommu_group_add_device - add a device to an iommu group * @group: the group into which to add the device (reference should be held) diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 65565820328a..248e3c2feeae 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -113,10 +113,13 @@ extern int dmar_parse_dev_scope(void *start, void *end, int *cnt, struct dmar_dev_scope **devices, u16 segment); extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt); extern void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt); -extern int dmar_insert_dev_scope(struct dmar_pci_notify_info *info, +extern int dmar_pci_insert_dev_scope(struct dmar_pci_notify_info *info, void *start, void*end, u16 segment, struct dmar_dev_scope *devices, int devices_cnt); +extern bool dmar_acpi_insert_dev_scope(u8 device_number, + struct acpi_device *adev, void *start, void *end, + struct dmar_dev_scope *devices, int devices_cnt); extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment, struct dmar_dev_scope *devices, int count); @@ -140,6 +143,7 @@ extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg); extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg); extern int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg); extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert); +extern int dmar_rmrr_add_acpi_dev(u8 device_number, struct acpi_device *adev); extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info); #else /* !CONFIG_INTEL_IOMMU: */ static inline int intel_iommu_init(void) { return -ENODEV; } @@ -150,6 +154,11 @@ static inline void intel_iommu_shutdown(void) { } #define dmar_check_one_atsr dmar_res_noop #define dmar_release_one_atsr dmar_res_noop +static inline int dmar_rmrr_add_acpi_dev(u8 device_number, struct acpi_device *adev) +{ + return 0; +} + static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) { return 0; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 3ff424d4f481..66ae2b7d65de 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -546,6 +546,9 @@ extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); +extern void __acpi_device_create_direct_mappings(struct iommu_group *group, + struct device *acpi_device); + static inline void iommu_flush_iotlb_all(struct iommu_domain *domain) { if (domain->ops->flush_iotlb_all) -- 2.20.1

1 0

[PATCH OLK-5.10] USB:Fix kernel NULL pointer when unbind UHCI form vfio-pci
by LeoLiuoc 09 Jul '21

09 Jul '21

This bug is found in Zhaoxin platform, but it's a commom code bug. Fail sequence: step1: Unbind UHCI controller from native driver; step2: Bind UHCI controller to vfio-pci, which will put UHCI controller in one vfio group's device list and set UHCI's dev->driver_data to struct vfio-pci(for UHCI) step3: Unbind EHCI controller from native driver, will try to tell UHCI native driver that "I'm removed by set companion_hcd->self.hs_companion to NULL. However, companion_hcd get from UHCI's dev->driver_data that has modified by vfio-pci already.So, the vfio-pci structure will be damaged! step4: Bind EHCI controller to vfio-pci driver, which will put EHCI controller in the same vfio group as UHCI controller; ... ... step5: Unbind UHCI controller from vfio-pci, which will delete UHCI from vfio group' device list that has been damaged in step 3. So,delete operation can random result into a NULL pointer dereference with the below stack dump. step6: Bind UHCI controller to native driver; step7: Unbind EHCI controller from vfio-pci, which will try to remove EHCI controller from the vfio group; step8: Bind EHCI controller to native driver; [ 929.114641] uhci_hcd 0000:00:10.0: remove, state 1 [ 929.114652] usb usb1: USB disconnect, device number 1 [ 929.114655] usb 1-1: USB disconnect, device number 2 [ 929.270313] usb 1-2: USB disconnect, device number 3 [ 929.318404] uhci_hcd 0000:00:10.0: USB bus 1 deregistered [ 929.343029] uhci_hcd 0000:00:10.1: remove, state 4 [ 929.343045] usb usb3: USB disconnect, device number 1 [ 929.343685] uhci_hcd 0000:00:10.1: USB bus 3 deregistered [ 929.369087] ehci-pci 0000:00:10.7: remove, state 4 [ 929.369102] usb usb4: USB disconnect, device number 1 [ 929.370325] ehci-pci 0000:00:10.7: USB bus 4 deregistered [ 932.398494] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [ 932.398496] PGD 42a67d067 P4D 42a67d067 PUD 42a65f067 PMD 0 [ 932.398502] Oops: 0002 [#2] SMP NOPTI [ 932.398505] CPU: 2 PID: 7824 Comm: vfio_unbind.sh Tainted: P D 4.19.65-2020051917-rainos #1 [ 932.398506] Hardware name: Shanghai Zhaoxin Semiconductor Co., Ltd. HX002EH/HX002EH, BIOS HX002EH0_01_R480_R_200408 04/08/2020 [ 932.398513] RIP: 0010:vfio_device_put+0x31/0xa0 [vfio] [ 932.398515] Code: 89 e5 41 54 53 4c 8b 67 18 48 89 fb 49 8d 74 24 30 e8 e3 0e f3 de 84 c0 74 67 48 8b 53 20 48 8b 43 28 48 8b 7b 18 48 89 42 08 <48> 89 10 48 b8 00 01 00 00 00 00 ad de 48 89 43 20 48 b8 00 02 00 [ 932.398516] RSP: 0018:ffffbbfd04cffc18 EFLAGS: 00010202 [ 932.398518] RAX: 0000000000000000 RBX: ffff92c7ea717880 RCX: 0000000000000000 [ 932.398519] RDX: ffff92c7ea713620 RSI: ffff92c7ea713630 RDI: ffff92c7ea713600 [ 932.398521] RBP: ffffbbfd04cffc28 R08: ffff92c7f02a8080 R09: ffff92c7efc03980 [ 932.398522] R10: ffffbbfd04cff9a8 R11: 0000000000000000 R12: ffff92c7ea713600 [ 932.398523] R13: ffff92c7ed8bb0a8 R14: ffff92c7ea717880 R15: 0000000000000000 [ 932.398525] FS: 00007f3031500740(0000) GS:ffff92c7f0280000(0000) knlGS:0000000000000000 [ 932.398526] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 932.398527] CR2: 0000000000000000 CR3: 0000000428626004 CR4: 0000000000160ee0 [ 932.398528] Call Trace: [ 932.398534] vfio_del_group_dev+0xe8/0x2a0 [vfio] [ 932.398539] ? __blocking_notifier_call_chain+0x52/0x60 [ 932.398542] ? do_wait_intr_irq+0x90/0x90 [ 932.398546] ? iommu_bus_notifier+0x75/0x100 [ 932.398551] vfio_pci_remove+0x20/0xa0 [vfio_pci] [ 932.398554] pci_device_remove+0x3e/0xc0 [ 932.398557] device_release_driver_internal+0x17a/0x240 [ 932.398560] device_release_driver+0x12/0x20 [ 932.398561] unbind_store+0xee/0x180 [ 932.398564] drv_attr_store+0x27/0x40 [ 932.398567] sysfs_kf_write+0x3c/0x50 [ 932.398568] kernfs_fop_write+0x125/0x1a0 [ 932.398572] __vfs_write+0x3a/0x190 [ 932.398575] ? apparmor_file_permission+0x1a/0x20 [ 932.398577] ? security_file_permission+0x3b/0xc0 [ 932.398581] ? _cond_resched+0x1a/0x50 [ 932.398582] vfs_write+0xb8/0x1b0 [ 932.398584] ksys_write+0x5c/0xe0 [ 932.398586] __x64_sys_write+0x1a/0x20 [ 932.398589] do_syscall_64+0x5a/0x110 [ 932.398592] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Using virt-manager/qemu to boot guest os, we can see the same fail sequence! Fix this by determine whether the PCI Driver of the USB controller is a kernel native driver. If not, do not let it modify UHCI's dev->driver_data. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/core/hcd-pci.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index ec0d6c50610c..000ee7a6731f 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -49,6 +49,7 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd, struct pci_dev *companion; struct usb_hcd *companion_hcd; unsigned int slot = PCI_SLOT(pdev->devfn); + struct pci_driver *drv; /* * Iterate through other PCI functions in the same slot. @@ -61,6 +62,15 @@ static void for_each_companion(struct pci_dev *pdev, struct usb_hcd *hcd, PCI_SLOT(companion->devfn) != slot) continue; + drv = companion->driver; + if (!drv) + continue; + + if (strncmp(drv->name, "uhci_hcd", sizeof("uhci_hcd") - 1) && + strncmp(drv->name, "ooci_hcd", sizeof("uhci_hcd") - 1) && + strncmp(drv->name, "ehci_hcd", sizeof("uhci_hcd") - 1)) + continue; + /* * Companion device should be either UHCI,OHCI or EHCI host * controller, otherwise skip. -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: fix issue with resume from system Sx state
by LeoLiuoc 09 Jul '21

09 Jul '21

On Zhaoxin ZX-100 project, xHCI can't work normally after resume from system Sx state. To fix this issue, when resume from system sx state, reinitialize xHCI instead of restore. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/xhci-pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 471cf3e96032..44dd77343cc1 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -307,6 +307,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_TI && pdev->device == 0x8241) xhci->quirks |= XHCI_LIMIT_ENDPOINT_INTERVAL_7; + if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN && pdev->device == 0x9202) + xhci->quirks |= XHCI_RESET_ON_RESUME; + if ((pdev->vendor == PCI_VENDOR_ID_BROADCOM || pdev->vendor == PCI_VENDOR_ID_CAVIUM) && pdev->device == 0x9026) -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: Adjust the UHCI Controllers bit value
by LeoLiuoc 09 Jul '21

09 Jul '21

Over Current condition is not standardized in the UHCI spec. Zhaoxin UHCI controllers report Over Current active off. Intel controllers report it active on, so we'll adjust the bit value. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/uhci-pci.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 9b88745d247f..d90c391d4899 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -134,6 +134,9 @@ static int uhci_pci_init(struct usb_hcd *hcd) if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_INTEL) device_set_wakeup_capable(uhci_dev(uhci), true); + if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_ZHAOXIN) + uhci->oc_low = 1; + /* Set up pointers to PCI-specific functions */ uhci->reset_hc = uhci_pci_reset_hc; uhci->check_and_reset_hc = uhci_pci_check_and_reset_hc; -- 2.20.1

1 0

[PATCH OLK-5.10 3/3] ALSA: hda: Add support of Zhaoxin NB HDAC codec
by LeoLiuoc 09 Jul '21

09 Jul '21

Add Zhaoxin NB HDAC codec support. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- sound/pci/hda/patch_hdmi.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 6d2a4dfcfe43..f541aeb4ecca 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4249,6 +4249,20 @@ static int patch_via_hdmi(struct hda_codec *codec) return patch_simple_hdmi(codec, VIAHDMI_CVT_NID, VIAHDMI_PIN_NID); } +/* ZHAOXIN HDMI Implementation */ +static int patch_zx_hdmi(struct hda_codec *codec) +{ + int err; + + err = patch_generic_hdmi(codec); + codec->no_sticky_stream = 1; + + if (err) + return err; + + return 0; +} + /* * patch entries */ @@ -4342,6 +4356,12 @@ HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f81, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f84, "VX11 HDMI/DP", patch_generic_hdmi), HDA_CODEC_ENTRY(0x11069f85, "VX11 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x11069f86, "CND001 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x11069f87, "CND001 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x11069f88, "CHX001 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x11069f89, "CHX001 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x11069f8a, "CHX002 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x11069f8b, "CHX002 HDMI/DP", patch_zx_hdmi), HDA_CODEC_ENTRY(0x80860054, "IbexPeak HDMI", patch_i915_cpt_hdmi), HDA_CODEC_ENTRY(0x80862800, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x80862801, "Bearlake HDMI", patch_generic_hdmi), @@ -4369,6 +4389,12 @@ HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi), HDA_CODEC_ENTRY(0x808629fb, "Crestline HDMI", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x1d179f86, "CND001 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x1d179f87, "CND001 HDMI/DP", patch_generic_hdmi), +HDA_CODEC_ENTRY(0x1d179f88, "CHX001 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x1d179f89, "CHX001 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x1d179f8a, "CHX002 HDMI/DP", patch_zx_hdmi), +HDA_CODEC_ENTRY(0x1d179f8b, "CHX002 HDMI/DP", patch_zx_hdmi), /* special ID for generic HDMI */ HDA_CODEC_ENTRY(HDA_CODEC_ID_GENERIC_HDMI, "Generic HDMI", patch_generic_hdmi), {} /* terminator */ -- 2.20.1

1 0

[PATCH OLK-5.10 2/3] ALSA: hda: Add support of Zhaoxin NB HDAC
by LeoLiuoc 09 Jul '21

09 Jul '21

Add the new PCI ID 0x1d17 0x9141/0x9142/0x9144 Zhaoxin NB HDAC support. And add some special initialization for Zhaoxin NB HDAC. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- sound/pci/hda/hda_controller.c | 17 ++++++++++- sound/pci/hda/hda_controller.h | 2 ++ sound/pci/hda/hda_intel.c | 53 +++++++++++++++++++++++++++++++++- 3 files changed, 70 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index b972d59eb1ec..d6de0b1fcb66 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1057,6 +1057,16 @@ void azx_stop_chip(struct azx *chip) } EXPORT_SYMBOL_GPL(azx_stop_chip); +static void azx_rirb_zxdelay(struct azx *chip, int enable) +{ + if (chip->remap_diu_addr) { + if (!enable) + writel(0x0, (char *)chip->remap_diu_addr + 0x490a8); + else + writel(0x1000000, (char *)chip->remap_diu_addr + 0x490a8); + } +} + /* * interrupt handler */ @@ -1116,9 +1126,14 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); active = true; if (status & RIRB_INT_RESPONSE) { - if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) + if ((chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) || + (chip->driver_caps & AZX_DCAPS_RIRB_PRE_DELAY)) { + azx_rirb_zxdelay(chip, 1); udelay(80); + } snd_hdac_bus_update_rirb(bus); + if (chip->driver_caps & AZX_DCAPS_RIRB_PRE_DELAY) + azx_rirb_zxdelay(chip, 0); } } } while (active && ++repeat < 10); diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index 68f9668788ea..543b9f75cf42 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -45,6 +45,7 @@ #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */ #define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */ #define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */ +#define AZX_DCAPS_RIRB_PRE_DELAY (1 << 31) enum { AZX_SNOOP_TYPE_NONE, @@ -147,6 +148,7 @@ struct azx { /* GTS present */ unsigned int gts_present:1; + void __iomem *remap_diu_addr; #ifdef CONFIG_SND_HDA_DSP_LOADER struct azx_dev saved_azx_dev; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 8ff7902ec6e6..5ac2e95fd5fa 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -241,7 +241,8 @@ MODULE_SUPPORTED_DEVICE("{{Intel, ICH6}," "{VIA, VT8251}," "{VIA, VT8237A}," "{ULI, M5461}," - "{ZX, ZhaoxinHDA}}"); + "{ZX, ZhaoxinHDA}," + "{ZX, ZhaoxinHDMI}}"); MODULE_DESCRIPTION("Intel HDA driver"); #if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO) @@ -273,6 +274,7 @@ enum { AZX_DRIVER_CTHDA, AZX_DRIVER_CMEDIA, AZX_DRIVER_ZHAOXIN, + AZX_DRIVER_ZXHDMI, AZX_DRIVER_GENERIC, AZX_NUM_DRIVERS, /* keep this as last entry */ }; @@ -390,6 +392,7 @@ static const char * const driver_short_names[] = { [AZX_DRIVER_CTHDA] = "HDA Creative", [AZX_DRIVER_CMEDIA] = "HDA C-Media", [AZX_DRIVER_ZHAOXIN] = "HDA Zhaoxin", + [AZX_DRIVER_ZXHDMI] = "HDA Zhaoxin GFX", [AZX_DRIVER_GENERIC] = "HD-Audio Generic", }; @@ -411,6 +414,29 @@ static void update_pci_byte(struct pci_dev *pci, unsigned int reg, pci_write_config_byte(pci, reg, data); } +static int azx_init_chip_zx(struct azx *chip) +{ + struct snd_card *card = chip->card; + unsigned int diu_reg; + struct pci_dev *diu_pci = NULL; + + diu_pci = pci_get_device(0x1d17, 0x3a03, NULL); + if (!diu_pci) { + dev_err(card->dev, "hda no chx001 device.\n"); + return -ENXIO; + } + pci_read_config_dword(diu_pci, PCI_BASE_ADDRESS_0, &diu_reg); + chip->remap_diu_addr = ioremap(diu_reg, 0x50000); + dev_info(card->dev, "hda %x %p\n", diu_reg, chip->remap_diu_addr); + return 0; +} + +static void azx_free_chip_zx(struct azx *chip) +{ + if (chip->remap_diu_addr) + iounmap(chip->remap_diu_addr); +} + static void azx_init_pci(struct azx *chip) { int snoop_type = azx_get_snoop_type(chip); @@ -1386,6 +1412,9 @@ static void azx_free(struct azx *chip) hda->init_failed = 1; /* to be sure */ complete_all(&hda->probe_wait); + if (chip->driver_type == AZX_DRIVER_ZXHDMI) + azx_free_chip_zx(chip); + if (use_vga_switcheroo(hda)) { if (chip->disabled && hda->probe_continued) snd_hda_unlock_devices(&chip->bus); @@ -1786,6 +1815,8 @@ static int default_bdl_pos_adj(struct azx *chip) case AZX_DRIVER_ICH: case AZX_DRIVER_PCH: return 1; + case AZX_DRIVER_ZXHDMI: + return 128; default: return 32; } @@ -1903,6 +1934,11 @@ static int azx_first_init(struct azx *chip) } #endif + chip->remap_diu_addr = NULL; + + if (chip->driver_type == AZX_DRIVER_ZXHDMI) + azx_init_chip_zx(chip); + err = pci_request_regions(pci, "ICH HD audio"); if (err < 0) return err; @@ -2011,6 +2047,7 @@ static int azx_first_init(struct azx *chip) chip->playback_streams = ATIHDMI_NUM_PLAYBACK; chip->capture_streams = ATIHDMI_NUM_CAPTURE; break; + case AZX_DRIVER_ZXHDMI: case AZX_DRIVER_GENERIC: default: chip->playback_streams = ICH6_NUM_PLAYBACK; @@ -2732,6 +2769,13 @@ static const struct pci_device_id azx_ids[] = { { PCI_DEVICE(0x1106, 0x9170), .driver_data = AZX_DRIVER_GENERIC }, /* VIA GFX VT6122/VX11 */ { PCI_DEVICE(0x1106, 0x9140), .driver_data = AZX_DRIVER_GENERIC }, + { PCI_DEVICE(0x1106, 0x9141), .driver_data = AZX_DRIVER_GENERIC }, + { PCI_DEVICE(0x1106, 0x9142), + .driver_data = AZX_DRIVER_ZXHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_RIRB_PRE_DELAY }, + { PCI_DEVICE(0x1106, 0x9144), + .driver_data = AZX_DRIVER_ZXHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_RIRB_PRE_DELAY }, /* SIS966 */ { PCI_DEVICE(0x1039, 0x7502), .driver_data = AZX_DRIVER_SIS }, /* ULI M5461 */ @@ -2787,6 +2831,13 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_HDMI }, /* Zhaoxin */ { PCI_DEVICE(0x1d17, 0x3288), .driver_data = AZX_DRIVER_ZHAOXIN }, + { PCI_DEVICE(0x1d17, 0x9141), .driver_data = AZX_DRIVER_GENERIC }, + { PCI_DEVICE(0x1d17, 0x9142), + .driver_data = AZX_DRIVER_ZXHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_RIRB_PRE_DELAY }, + { PCI_DEVICE(0x1d17, 0x9144), + .driver_data = AZX_DRIVER_ZXHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_RIRB_PRE_DELAY }, { 0, } }; MODULE_DEVICE_TABLE(pci, azx_ids); -- 2.20.1

1 0

[PATCH OLK-5.10 1/3] ALSA: hda: Add Zhaoxin SB HDAC non snoop path support
by LeoLiuoc 09 Jul '21

09 Jul '21

Add Zhaoxin SB HDAC non snoop path support. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- sound/pci/hda/hda_intel.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 4c8b281c3992..8ff7902ec6e6 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -240,8 +240,8 @@ MODULE_SUPPORTED_DEVICE("{{Intel, ICH6}," "{ATI, RV770}," "{VIA, VT8251}," "{VIA, VT8237A}," - "{SiS, SIS966}," - "{ULI, M5461}}"); + "{ULI, M5461}," + "{ZX, ZhaoxinHDA}}"); MODULE_DESCRIPTION("Intel HDA driver"); #if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO) @@ -1744,6 +1744,15 @@ static void azx_check_snoop_available(struct azx *chip) snoop = false; } + if (azx_get_snoop_type(chip) == AZX_SNOOP_TYPE_NONE && + chip->driver_type == AZX_DRIVER_ZHAOXIN) { + u8 val1; + + pci_read_config_byte(chip->pci, 0x42, &val1); + if (!(val1 & 0x80) && chip->pci->revision == 0x20) + snoop = false; + } + if (chip->driver_caps & AZX_DCAPS_SNOOP_OFF) snoop = false; -- 2.20.1

1 0

[PATCH OLK-5.10 0/3] Add support of Zhaoxin HDAC and codec
by LeoLiuoc 09 Jul '21

09 Jul '21

Zhaoxin have new SB & NB HDAC controller. And have new NB HDAC codec. This patch set add support for them. LeoLiu-oc (3): ALSA: hda: Add Zhaoxin SB HDAC non snoop path support ALSA: hda: Add support of Zhaoxin NB HDAC ALSA: hda: Add support of Zhaoxin NB HDAC codec sound/pci/hda/hda_controller.c | 17 ++++++++- sound/pci/hda/hda_controller.h | 2 ++ sound/pci/hda/hda_intel.c | 64 ++++++++++++++++++++++++++++++++-- sound/pci/hda/patch_hdmi.c | 26 ++++++++++++++ 4 files changed, 106 insertions(+), 3 deletions(-) -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: Show Zhaoxin XHCI root hub speed correctly
by LeoLiuoc 09 Jul '21

09 Jul '21

Some Zhaoxin xHCI controllers follow usb3.1 spec, but only support gen1 speed 5G. While in Linux kernel, if xHCI suspport usb3.1,root hub speed will show on 10G. To fix this issue, read usb speed ID supported by xHCI to determine root hub speed. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/xhci.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index a834f3927bee..e9d67ee299d9 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -5186,6 +5186,7 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) */ struct device *dev = hcd->self.sysdev; unsigned int minor_rev; + u8 i, j; int retval; /* Accept arbitrarily long scatter-gather lists */ @@ -5240,6 +5241,24 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) hcd->self.root_hub->speed = USB_SPEED_SUPER_PLUS; break; } + + /* usb3.1 has gen1 and gen2, Some zx's xHCI controller that follow usb3.1 spec + * but only support gen1 + */ + if (xhci->quirks & XHCI_ZHAOXIN_HOST) { + minor_rev = 0; + for (j = 0; j < xhci->num_port_caps; j++) { + for (i = 0; i < xhci->port_caps[j].psi_count; i++) { + if (XHCI_EXT_PORT_PSIV(xhci->port_caps[j].psi[i]) >= 5) + minor_rev = 1; + } + if (minor_rev != 1) { + hcd->speed = HCD_USB3; + hcd->self.root_hub->speed = USB_SPEED_SUPER; + } + } + } + xhci_info(xhci, "Host supports USB 3.%x %sSuperSpeed\n", minor_rev, minor_rev ? "Enhanced " : ""); -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: fix issue of cross page boundary in TRB prefetch
by LeoLiuoc 09 Jul '21

09 Jul '21

On some Zhaoxin platforms, xHCI will prefetch TRB for performance improvement. However this TRB prefetch mechanism may cross page boundary, which may access memory not belong to xHCI. In order to fix this issue, using two pages for TRB allocate and only the first page will be used. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/xhci-mem.c | 10 +++++++++- drivers/usb/host/xhci-pci.c | 5 +++++ drivers/usb/host/xhci.h | 1 + 3 files changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 8ce043e6ed87..67329b4188cf 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -2458,8 +2458,16 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) * and our use of dma addresses in the trb_address_map radix tree needs * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need. */ - xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, + /* With xHCI TRB prefetch patch:To fix cross page boundary access issue + * in IOV environment + */ + if (xhci->quirks & XHCI_ZHAOXIN_TRB_FETCH) { + xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, + TRB_SEGMENT_SIZE*2, TRB_SEGMENT_SIZE*2, xhci->page_size*2); + } else { + xhci->segment_pool = dma_pool_create("xHCI ring segments", dev, TRB_SEGMENT_SIZE, TRB_SEGMENT_SIZE, xhci->page_size); + } /* See Table 46 and Note on Figure 55 */ xhci->device_pool = dma_pool_create("xHCI input/output contexts", dev, diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index e78316ed99d4..471cf3e96032 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -281,6 +281,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == 0x3483) xhci->quirks |= XHCI_LPM_SUPPORT; + if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN && + (pdev->device == 0x9202 || + pdev->device == 0x9203)) + xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH; + if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA && pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) xhci->quirks |= XHCI_BROKEN_STREAMS; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 576cafb5d873..e215431f927a 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1881,6 +1881,7 @@ struct xhci_hcd { #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) #define XHCI_ZHAOXIN_HOST BIT_ULL(41) +#define XHCI_ZHAOXIN_TRB_FETCH BIT_ULL(42) unsigned int num_active_eps; unsigned int limit_active_eps; -- 2.20.1

1 0

[PATCH OLK-5.10] xhci: Add Zhaoxin xHCI LPM U1/U2 feature support
by LeoLiuoc 09 Jul '21

09 Jul '21

Add LPM u1/u2 feature support for xHCI of zhaoxin Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/usb/host/xhci-pci.c | 4 ++++ drivers/usb/host/xhci.c | 34 ++++++++++++++++++++++++++++++++-- drivers/usb/host/xhci.h | 1 + 3 files changed, 37 insertions(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 7bc18cf8042c..e78316ed99d4 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -268,6 +268,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) } if (pdev->vendor == PCI_VENDOR_ID_VIA) xhci->quirks |= XHCI_RESET_ON_RESUME; + if (pdev->vendor == PCI_VENDOR_ID_ZHAOXIN) { + xhci->quirks |= XHCI_LPM_SUPPORT; + xhci->quirks |= XHCI_ZHAOXIN_HOST; + } /* See https://bugzilla.kernel.org/show_bug.cgi?id=79511 */ if (pdev->vendor == PCI_VENDOR_ID_VIA && diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index a8d97e23f601..a834f3927bee 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -4666,7 +4666,7 @@ static u16 xhci_calculate_u1_timeout(struct xhci_hcd *xhci, { unsigned long long timeout_ns; - if (xhci->quirks & XHCI_INTEL_HOST) + if (xhci->quirks & (XHCI_INTEL_HOST | XHCI_ZHAOXIN_HOST)) timeout_ns = xhci_calculate_intel_u1_timeout(udev, desc); else timeout_ns = udev->u1_params.sel; @@ -4730,7 +4730,7 @@ static u16 xhci_calculate_u2_timeout(struct xhci_hcd *xhci, { unsigned long long timeout_ns; - if (xhci->quirks & XHCI_INTEL_HOST) + if (xhci->quirks & (XHCI_INTEL_HOST | XHCI_ZHAOXIN_HOST)) timeout_ns = xhci_calculate_intel_u2_timeout(udev, desc); else timeout_ns = udev->u2_params.sel; @@ -4835,12 +4835,42 @@ static int xhci_check_intel_tier_policy(struct usb_device *udev, return -E2BIG; } +static int xhci_check_zhaoxin_tier_policy(struct usb_device *udev, + enum usb3_link_state state) +{ + struct usb_device *parent; + unsigned int num_hubs; + char *state_name; + + if (state == USB3_LPM_U1) + state_name = "U1"; + else if (state == USB3_LPM_U2) + state_name = "U2"; + else + state_name = "Unknown"; + /* Don't enable U1/U2 if the device is on an external hub*/ + for (parent = udev->parent, num_hubs = 0; parent->parent; + parent = parent->parent) + num_hubs++; + + if (num_hubs < 1) + return 0; + + dev_dbg(&udev->dev, "Disabling %s link state for device" + " below external hub.\n", state_name); + dev_dbg(&udev->dev, "Plug device into root port " + "to decrease power consumption.\n"); + return -E2BIG; +} + static int xhci_check_tier_policy(struct xhci_hcd *xhci, struct usb_device *udev, enum usb3_link_state state) { if (xhci->quirks & XHCI_INTEL_HOST) return xhci_check_intel_tier_policy(udev, state); + else if (xhci->quirks & XHCI_ZHAOXIN_HOST) + return xhci_check_zhaoxin_tier_policy(udev, state); else return 0; } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index d01241f1daf3..576cafb5d873 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1880,6 +1880,7 @@ struct xhci_hcd { #define XHCI_DISABLE_SPARSE BIT_ULL(38) #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) +#define XHCI_ZHAOXIN_HOST BIT_ULL(41) unsigned int num_active_eps; unsigned int limit_active_eps; -- 2.20.1

1 0

[PATCH OLK-5.10] ata: sata_zhaoxin: Add support for Zhaoxin Serial ATA
by LeoLiuoc 09 Jul '21

09 Jul '21

Add Zhaoxin Serial ATA support for Zhaoxin CPUs. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- drivers/ata/Kconfig | 8 + drivers/ata/Makefile | 1 + drivers/ata/sata_zhaoxin.c | 384 +++++++++++++++++++++++++++++++++++++ 3 files changed, 393 insertions(+) create mode 100644 drivers/ata/sata_zhaoxin.c diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 030cb32da980..5f62dcdc546b 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -552,6 +552,14 @@ config SATA_VITESSE If unsure, say N. +config SATA_ZHAOXIN + tristate "ZhaoXin SATA support" + depends on PCI + help + This option enables support for ZhaoXin Serial ATA. + + If unsure, say N. + comment "PATA SFF controllers with BMDMA" config PATA_ALI diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile index b8aebfb14e82..9a3ce171d9e8 100644 --- a/drivers/ata/Makefile +++ b/drivers/ata/Makefile @@ -46,6 +46,7 @@ obj-$(CONFIG_SATA_SVW) += sata_svw.o obj-$(CONFIG_SATA_ULI) += sata_uli.o obj-$(CONFIG_SATA_VIA) += sata_via.o obj-$(CONFIG_SATA_VITESSE) += sata_vsc.o +obj-$(CONFIG_SATA_ZHAOXIN) += sata_zhaoxin.o # SFF PATA w/ BMDMA obj-$(CONFIG_PATA_ALI) += pata_ali.o diff --git a/drivers/ata/sata_zhaoxin.c b/drivers/ata/sata_zhaoxin.c new file mode 100644 index 000000000000..8e30a6525f54 --- /dev/null +++ b/drivers/ata/sata_zhaoxin.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * sata_zhaoxin.c - ZhaoXin Serial ATA controllers + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/blkdev.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_host.h> +#include <linux/libata.h> + +#define DRV_NAME "sata_zx" +#define DRV_VERSION "2.6.1" + +enum board_ids_enum { + cnd001, +}; + +enum { + SATA_CHAN_ENAB = 0x40, /* SATA channel enable */ + SATA_INT_GATE = 0x41, /* SATA interrupt gating */ + SATA_NATIVE_MODE = 0x42, /* Native mode enable */ + PATA_UDMA_TIMING = 0xB3, /* PATA timing for DMA/ cable detect */ + PATA_PIO_TIMING = 0xAB, /* PATA timing register */ + + PORT0 = (1 << 1), + PORT1 = (1 << 0), + ALL_PORTS = PORT0 | PORT1, + + NATIVE_MODE_ALL = (1 << 7) | (1 << 6) | (1 << 5) | (1 << 4), + + SATA_EXT_PHY = (1 << 6), /* 0==use PATA, 1==ext phy */ +}; + +static int szx_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); +static int cnd001_scr_read(struct ata_link *link, unsigned int scr, u32 *val); +static int cnd001_scr_write(struct ata_link *link, unsigned int scr, u32 val); +static int szx_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline); + +static void szx_tf_load(struct ata_port *ap, const struct ata_taskfile *tf); + +static const struct pci_device_id szx_pci_tbl[] = { + { PCI_VDEVICE(ZHAOXIN, 0x9002), cnd001 }, + { PCI_VDEVICE(ZHAOXIN, 0x9003), cnd001 }, + + { } /* terminate list */ +}; + +static struct pci_driver szx_pci_driver = { + .name = DRV_NAME, + .id_table = szx_pci_tbl, + .probe = szx_init_one, +#ifdef CONFIG_PM_SLEEP + .suspend = ata_pci_device_suspend, + .resume = ata_pci_device_resume, +#endif + .remove = ata_pci_remove_one, +}; + +static struct scsi_host_template szx_sht = { + ATA_BMDMA_SHT(DRV_NAME), +}; + +static struct ata_port_operations szx_base_ops = { + .inherits = &ata_bmdma_port_ops, + .sff_tf_load = szx_tf_load, +}; + +static struct ata_port_operations cnd001_ops = { + .inherits = &szx_base_ops, + .hardreset = szx_hardreset, + .scr_read = cnd001_scr_read, + .scr_write = cnd001_scr_write, +}; + +static struct ata_port_info cnd001_port_info = { + .flags = ATA_FLAG_SATA | ATA_FLAG_SLAVE_POSS, + .pio_mask = ATA_PIO4, + .mwdma_mask = ATA_MWDMA2, + .udma_mask = ATA_UDMA6, + .port_ops = &cnd001_ops, +}; + + +static int szx_hardreset(struct ata_link *link, unsigned int *class, + unsigned long deadline) +{ + int rc; + + rc = sata_std_hardreset(link, class, deadline); + if (!rc || rc == -EAGAIN) { + struct ata_port *ap = link->ap; + int pmp = link->pmp; + int tmprc; + + if (pmp) { + ap->ops->sff_dev_select(ap, pmp); + tmprc = ata_sff_wait_ready(&ap->link, deadline); + } else { + tmprc = ata_sff_wait_ready(link, deadline); + } + if (tmprc) + ata_link_err(link, "COMRESET failed for wait (errno=%d)\n", + rc); + else + ata_link_err(link, "wait for bsy success\n"); + + ata_link_err(link, "COMRESET success (errno=%d) ap=%d link %d\n", + rc, link->ap->port_no, link->pmp); + } else { + ata_link_err(link, "COMRESET failed (errno=%d) ap=%d link %d\n", + rc, link->ap->port_no, link->pmp); + } + return rc; +} + +static int cnd001_scr_read(struct ata_link *link, unsigned int scr, u32 *val) +{ + static const u8 ipm_tbl[] = { 1, 2, 6, 0 }; + struct pci_dev *pdev = to_pci_dev(link->ap->host->dev); + int slot = 2 * link->ap->port_no + link->pmp; + u32 v = 0; + u8 raw; + + switch (scr) { + case SCR_STATUS: + pci_read_config_byte(pdev, 0xA0 + slot, &raw); + + /* read the DET field, bit0 and 1 of the config byte */ + v |= raw & 0x03; + + /* read the SPD field, bit4 of the configure byte */ + v |= raw & 0x30; + + /* read the IPM field, bit2 and 3 of the config byte */ + v |= ((ipm_tbl[(raw >> 2) & 0x3])<<8); + break; + + case SCR_ERROR: + /* devices other than 5287 uses 0xA8 as base */ + WARN_ON(pdev->device != 0x9002 && pdev->device != 0x9003); + pci_write_config_byte(pdev, 0x42, slot); + pci_read_config_dword(pdev, 0xA8, &v); + break; + + case SCR_CONTROL: + pci_read_config_byte(pdev, 0xA4 + slot, &raw); + + /* read the DET field, bit0 and bit1 */ + v |= ((raw & 0x02) << 1) | (raw & 0x01); + + /* read the IPM field, bit2 and bit3 */ + v |= ((raw >> 2) & 0x03) << 8; + + break; + + default: + return -EINVAL; + } + + *val = v; + return 0; +} + +static int cnd001_scr_write(struct ata_link *link, unsigned int scr, u32 val) +{ + struct pci_dev *pdev = to_pci_dev(link->ap->host->dev); + int slot = 2 * link->ap->port_no + link->pmp; + u32 v = 0; + + WARN_ON(pdev == NULL); + + switch (scr) { + case SCR_ERROR: + /* devices 0x9002 uses 0xA8 as base */ + WARN_ON(pdev->device != 0x9002 && pdev->device != 0x9003); + pci_write_config_byte(pdev, 0x42, slot); + pci_write_config_dword(pdev, 0xA8, val); + return 0; + + case SCR_CONTROL: + /* set the DET field */ + v |= ((val & 0x4) >> 1) | (val & 0x1); + + /* set the IPM field */ + v |= ((val >> 8) & 0x3) << 2; + + + pci_write_config_byte(pdev, 0xA4 + slot, v); + + + return 0; + + default: + return -EINVAL; + } +} + + +/** + * szx_tf_load - send taskfile registers to host controller + * @ap: Port to which output is sent + * @tf: ATA taskfile register set + * + * Outputs ATA taskfile to standard ATA host controller. + * + * This is to fix the internal bug of zx chipsets, which will + * reset the device register after changing the IEN bit on ctl + * register. + */ +static void szx_tf_load(struct ata_port *ap, const struct ata_taskfile *tf) +{ + struct ata_taskfile ttf; + + if (tf->ctl != ap->last_ctl) { + ttf = *tf; + ttf.flags |= ATA_TFLAG_DEVICE; + tf = &ttf; + } + ata_sff_tf_load(ap, tf); +} + +static const unsigned int szx_bar_sizes[] = { + 8, 4, 8, 4, 16, 256 +}; + +static const unsigned int cnd001_bar_sizes0[] = { + 8, 4, 8, 4, 16, 0 +}; + +static const unsigned int cnd001_bar_sizes1[] = { + 8, 4, 0, 0, 16, 0 +}; + +static int cnd001_prepare_host(struct pci_dev *pdev, struct ata_host **r_host) +{ + const struct ata_port_info *ppi0[] = { + &cnd001_port_info, NULL + }; + const struct ata_port_info *ppi1[] = { + &cnd001_port_info, &ata_dummy_port_info + }; + struct ata_host *host; + int i, rc; + + if (pdev->device == 0x9002) + rc = ata_pci_bmdma_prepare_host(pdev, ppi0, &host); + else if (pdev->device == 0x9003) + rc = ata_pci_bmdma_prepare_host(pdev, ppi1, &host); + else + rc = -EINVAL; + + if (rc) + return rc; + + *r_host = host; + + /* cnd001 9002 hosts four sata ports as M/S of the two channels */ + /* cnd001 9003 hosts two sata ports as M/S of the one channel */ + for (i = 0; i < host->n_ports; i++) + ata_slave_link_init(host->ports[i]); + + return 0; +} + +static void szx_configure(struct pci_dev *pdev, int board_id) +{ + u8 tmp8; + + pci_read_config_byte(pdev, PCI_INTERRUPT_LINE, &tmp8); + dev_info(&pdev->dev, "routed to hard irq line %d\n", + (int) (tmp8 & 0xf0) == 0xf0 ? 0 : tmp8 & 0x0f); + + /* make sure SATA channels are enabled */ + pci_read_config_byte(pdev, SATA_CHAN_ENAB, &tmp8); + if ((tmp8 & ALL_PORTS) != ALL_PORTS) { + dev_dbg(&pdev->dev, "enabling SATA channels (0x%x)\n", + (int)tmp8); + tmp8 |= ALL_PORTS; + pci_write_config_byte(pdev, SATA_CHAN_ENAB, tmp8); + } + + /* make sure interrupts for each channel sent to us */ + pci_read_config_byte(pdev, SATA_INT_GATE, &tmp8); + if ((tmp8 & ALL_PORTS) != ALL_PORTS) { + dev_dbg(&pdev->dev, "enabling SATA channel interrupts (0x%x)\n", + (int) tmp8); + tmp8 |= ALL_PORTS; + pci_write_config_byte(pdev, SATA_INT_GATE, tmp8); + } + + /* make sure native mode is enabled */ + pci_read_config_byte(pdev, SATA_NATIVE_MODE, &tmp8); + if ((tmp8 & NATIVE_MODE_ALL) != NATIVE_MODE_ALL) { + dev_dbg(&pdev->dev, + "enabling SATA channel native mode (0x%x)\n", + (int) tmp8); + tmp8 |= NATIVE_MODE_ALL; + pci_write_config_byte(pdev, SATA_NATIVE_MODE, tmp8); + } +} + +static int szx_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + unsigned int i; + int rc; + struct ata_host *host = NULL; + int board_id = (int) ent->driver_data; + const unsigned int *bar_sizes; + int legacy_mode = 0; + + ata_print_version_once(&pdev->dev, DRV_VERSION); + + if (pdev->device == 0x9002 || pdev->device == 0x9003) { + if ((pdev->class >> 8) == PCI_CLASS_STORAGE_IDE) { + u8 tmp8, mask; + + /* TODO: What if one channel is in native mode ... */ + pci_read_config_byte(pdev, PCI_CLASS_PROG, &tmp8); + mask = (1 << 2) | (1 << 0); + if ((tmp8 & mask) != mask) + legacy_mode = 1; + } + if (legacy_mode) + return -EINVAL; + } + + rc = pcim_enable_device(pdev); + if (rc) + return rc; + + if (board_id == cnd001 && pdev->device == 0x9002) + bar_sizes = &cnd001_bar_sizes0[0]; + else if (board_id == cnd001 && pdev->device == 0x9003) + bar_sizes = &cnd001_bar_sizes1[0]; + else + bar_sizes = &szx_bar_sizes[0]; + + for (i = 0; i < ARRAY_SIZE(szx_bar_sizes); i++) { + if ((pci_resource_start(pdev, i) == 0) || + (pci_resource_len(pdev, i) < bar_sizes[i])) { + if (bar_sizes[i] == 0) + continue; + + dev_err(&pdev->dev, + "invalid PCI BAR %u (sz 0x%llx, val 0x%llx)\n", + i, + (unsigned long long)pci_resource_start(pdev, i), + (unsigned long long)pci_resource_len(pdev, i)); + + return -ENODEV; + } + } + + switch (board_id) { + case cnd001: + rc = cnd001_prepare_host(pdev, &host); + break; + default: + rc = -EINVAL; + } + if (rc) + return rc; + + szx_configure(pdev, board_id); + + pci_set_master(pdev); + return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt, + IRQF_SHARED, &szx_sht); +} + +module_pci_driver(szx_pci_driver); + +MODULE_AUTHOR("Yanchen:YanchenSun@zhaoxin.com"); +MODULE_DESCRIPTION("SCSI low-level driver for ZX SATA controllers"); +MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(pci, szx_pci_tbl); +MODULE_VERSION(DRV_VERSION); -- 2.20.1

1 0

[PATCH OLK-5.10] crypto: x86/crc32c-intel - Don't match some Zhaoxin CPUs
by LeoLiuoc 09 Jul '21

09 Jul '21

The driver crc32c-intel match CPUs supporting X86_FEATURE_XMM4_2. On platforms with Zhaoxin CPUs supporting this X86 feature, when crc32c-intel and crc32c-generic are both registered, system will use crc32c-intel because its .cra_priority is greater than crc32c-generic. When doing lmbench3 Create and Delete file test on partitions with ext4 enabling metadata checksum, found using crc32c-generic driver could get about 20% performance gain than using the driver crc32c-intel on some Zhaoxin CPUs. This case expect to use crc32c-generic driver for these Zhaoxin CPUs to get performance gain, so remove these Zhaoxin CPUs support from crc32c-intel. This patch was submitted to mainline kernel but not accepted by upstream maintainer whose reason is "Then create a BUG flag for it,". We think this is not a CPU bug for Zhaoxin CPUs. So should patch the crc32c driver for Zhaoxin CPUs but not report a BUG. https://lkml.org/lkml/2020/12/11/308 Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/crypto/crc32c-intel_glue.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index feccb5254c7e..2d7fe5d24f5f 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -222,8 +222,16 @@ MODULE_DEVICE_TABLE(x86cpu, crc32c_cpu_id); static int __init crc32c_intel_mod_init(void) { + struct cpuinfo_x86 *c = &boot_cpu_data; + if (!x86_match_cpu(crc32c_cpu_id)) return -ENODEV; + + if ((c->x86_vendor == X86_VENDOR_ZHAOXIN || c->x86_vendor == X86_VENDOR_CENTAUR) && + (c->x86 <= 7 && c->x86_model <= 59)) { + return -ENODEV; + } + #ifdef CONFIG_X86_64 if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) { alg.update = crc32c_pcl_intel_update; -- 2.20.1

1 0

[PATCH OLK-5.10] Add MCA supprot for X86_VENDOR_CENTAUR CPUs
by LeoLiuoc 09 Jul '21

09 Jul '21

Add MCA support for some Zhaoxin CPUs which use X86_VENDOR_CENTAUR as vendor ID. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/kernel/cpu/mce/core.c | 39 ++++++++++++--------------------- arch/x86/kernel/cpu/mce/intel.c | 3 ++- 2 files changed, 16 insertions(+), 26 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index b7a27589dfa0..aca6ab19726f 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -538,7 +538,8 @@ int mce_usable_address(struct mce *m) /* Checks after this one are Intel/Zhaoxin-specific: */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && - boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 1; if (!(m->status & MCI_STATUS_MISCV)) @@ -562,6 +563,7 @@ bool mce_is_memory_error(struct mce *m) return amd_mce_is_memory_error(m); case X86_VENDOR_INTEL: + case X86_VENDOR_CENTAUR: case X86_VENDOR_ZHAOXIN: /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -1155,7 +1157,8 @@ static noinstr bool mce_check_crashing_cpu(void) mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS); - if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) { + if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR || + boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) { if (mcgstatus & MCG_STATUS_LMCES) return false; } @@ -1358,7 +1361,8 @@ noinstr void do_machine_check(struct pt_regs *regs) * on Intel, Zhaoxin only. */ if (m.cpuvendor == X86_VENDOR_INTEL || - m.cpuvendor == X86_VENDOR_ZHAOXIN) + m.cpuvendor == X86_VENDOR_CENTAUR || + m.cpuvendor == X86_VENDOR_ZHAOXIN) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* @@ -1786,7 +1790,8 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) quirk_no_way_out = quirk_sandybridge_ifu; } - if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { + if (c->x86_vendor == X86_VENDOR_CENTAUR || + c->x86_vendor == X86_VENDOR_ZHAOXIN) { /* * All newer Zhaoxin CPUs support MCE broadcasting. Enable * synchronization with a one second timeout. @@ -1846,21 +1851,6 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) } } -static void mce_centaur_feature_init(struct cpuinfo_x86 *c) -{ - struct mca_config *cfg = &mca_cfg; - - /* - * All newer Centaur CPUs support MCE broadcasting. Enable - * synchronization with a one second timeout. - */ - if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) || - c->x86 > 6) { - if (cfg->monarch_timeout < 0) - cfg->monarch_timeout = USEC_PER_SEC; - } -} - static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c) { struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); @@ -1908,9 +1898,6 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; case X86_VENDOR_CENTAUR: - mce_centaur_feature_init(c); - break; - case X86_VENDOR_ZHAOXIN: mce_zhaoxin_feature_init(c); break; @@ -1927,6 +1914,7 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) mce_intel_feature_clear(c); break; + case X86_VENDOR_CENTAUR: case X86_VENDOR_ZHAOXIN: mce_zhaoxin_feature_clear(c); break; @@ -2233,9 +2221,10 @@ static void vendor_disable_error_reporting(void) * controller (iMC), etc. */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || - boot_cpu_data.x86_vendor == X86_VENDOR_AMD || - boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || + boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR || + boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) return; mce_disable_error_reporting(); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index abe9fe0fb851..26d521ac5f7d 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -86,7 +86,8 @@ static int cmci_supported(int *banks) * makes sure none of the backdoors are entered otherwise. */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && - boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) + boot_cpu_data.x86_vendor != X86_VENDOR_CENTAUR && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) return 0; if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) -- 2.20.1

1 0

[PATCH OLK-5.10 1/2] Get locgical processors numbers bits per package
by LeoLiuoc 09 Jul '21

09 Jul '21

Get locgical processors numbers bits per package by cpuid instruction for some Zhaoxin CPUs which vendor is Centaur Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/kernel/cpu/centaur.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 345f7d905db6..3d1e87b6a657 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -109,6 +109,19 @@ static void early_init_centaur(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); } + + if (c->cpuid_level >= 0x00000001) { + u32 eax, ebx, ecx, edx; + + cpuid(0x00000001, &eax, &ebx, &ecx, &edx); + /* + * If HTT (EDX[28]) is set EBX[16:23] contain the number of + * apicids which are reserved per package. Store the resulting + * shift value for the package management code. + */ + if (edx & (1U << 28)) + c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); + } } static void init_centaur(struct cpuinfo_x86 *c) -- 2.20.1

1 0

[PATCH OLK-5.10 2/2] Add support for extended topology detection,of Zhaoxin CPUs
by LeoLiuoc 09 Jul '21

09 Jul '21

Newer Zhaoxin CPUs support get extended topology from CPUID leaf B/1F, So add support for it. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- arch/x86/kernel/cpu/centaur.c | 8 +++++++- arch/x86/kernel/cpu/zhaoxin.c | 7 ++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 3d1e87b6a657..dacac9135681 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -122,6 +122,9 @@ static void early_init_centaur(struct cpuinfo_x86 *c) if (edx & (1U << 28)) c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); } + + if (detect_extended_topology_early(c) < 0) + detect_ht_early(c); } static void init_centaur(struct cpuinfo_x86 *c) @@ -140,11 +143,14 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, 0*32+31); #endif early_init_centaur(c); + detect_extended_topology(c); init_intel_cacheinfo(c); - detect_num_cpu_cores(c); + if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { + detect_num_cpu_cores(c); #ifdef CONFIG_X86_32 detect_ht(c); #endif + } if (c->cpuid_level > 9) { unsigned int eax = cpuid_eax(10); diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index 05fa4ef63490..2126b10de796 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -79,16 +79,21 @@ static void early_init_zhaoxin(struct cpuinfo_x86 *c) c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); } + if (detect_extended_topology_early(c) < 0) + detect_ht_early(c); } static void init_zhaoxin(struct cpuinfo_x86 *c) { early_init_zhaoxin(c); + detect_extended_topology(c); init_intel_cacheinfo(c); - detect_num_cpu_cores(c); + if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { + detect_num_cpu_cores(c); #ifdef CONFIG_X86_32 detect_ht(c); #endif + } if (c->cpuid_level > 9) { unsigned int eax = cpuid_eax(10); -- 2.20.1

1 0

[PATCH OLK-5.10 0/2] New Zhaoxin CPU vendor ID/FMS patch
by LeoLiuoc 09 Jul '21

09 Jul '21

This set of patches is to add support for Zhaoxin Family 7 CPUs. With these patches, the kernel can identify Zhaoxin CPUs topology information. LeoLiu-oc (2): Get locgical processors numbers bits per package Add support for extended topology detection of Zhaoxin CPUs arch/x86/kernel/cpu/centaur.c | 21 ++++++++++++++++++++- arch/x86/kernel/cpu/zhaoxin.c | 7 ++++++- 2 files changed, 26 insertions(+), 2 deletions(-) -- 2.20.1

1 0

[PATCH openEuler-1.0-LTS] NFSv4.1: fix kabi for struct rpc_xprt
by Yang Yingliang 09 Jul '21

09 Jul '21

From: ChenXiaoSong <chenxiaosong2(a)huawei.com> hulk inclusion category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- commit a2ff6d97547e ("NFSv4.1: Don't rebind to the same source port when reconnecting to the server") add new member into struct rpc_xprt, which will break KABI. This patch try to fix it. Signed-off-by: ChenXiaoSong <chenxiaosong2(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/sunrpc/xprt.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 36a944dda1957..ccfacca1eba9d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -200,8 +200,12 @@ struct rpc_xprt { unsigned int min_reqs; /* min number of slots */ unsigned int num_reqs; /* total slots */ unsigned long state; /* transport state */ +#ifdef __GENKSYMS__ + unsigned char resvport : 1; /* use a reserved port */ +#else unsigned char resvport : 1, /* use a reserved port */ reuseport : 1; /* reuse port on reconnect */ +#endif atomic_t swapper; /* we're swapping over this transport */ unsigned int bind_index; /* bind function index */ -- 2.25.1

1 0

[PATCH kernel-4.19] usb: gadget: rndis: Fix info leak of rndis
by Yang Yingliang 08 Jul '21

08 Jul '21

From: Wang Hai <wanghai38(a)huawei.com> hulk inclusion category: bugfix bugzilla: 172330 CVE: NA -------------------------------- We can construct some special USB packets that cause kernel info leak by the following steps of rndis. 1. construct the packet to make rndis call gen_ndis_set_resp(). In gen_ndis_set_resp(), BufOffset comes from the USB packet and it is not checked so that BufOffset can be any value. Therefore, if OID is RNDIS_OID_GEN_CURRENT_PACKET_FILTER, then *params->filter can get data at any address. 2. construct the packet to make rndis call rndis_query_response(). In rndis_query_response(), if OID is RNDIS_OID_GEN_CURRENT_PACKET_FILTER, then the data of *params->filter is fetched and returned, resulting in info leak. Therefore, we need to check the BufOffset to prevent info leak. Here, buf size is USB_COMP_EP0_BUFSIZ, as long as "8 + BufOffset + BufLength" is less than USB_COMP_EP0_BUFSIZ, it will be considered legal. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Wang Hai <wanghai38(a)huawei.com> Reviewed-by: Wei Yongjun <weiyongjun1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/usb/gadget/composite.c | 2 +- drivers/usb/gadget/function/rndis.c | 37 +++++++++++++++++++++++++---- 2 files changed, 34 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d85bb3ba8263f..ef545934ce086 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2143,7 +2143,7 @@ int composite_dev_prepare(struct usb_composite_driver *composite, if (!cdev->req) return -ENOMEM; - cdev->req->buf = kmalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL); + cdev->req->buf = kzalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL); if (!cdev->req->buf) goto fail; diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 04c142c130759..7686b55ccf133 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -506,6 +506,10 @@ static int gen_ndis_set_resp(struct rndis_params *params, u32 OID, switch (OID) { case RNDIS_OID_GEN_CURRENT_PACKET_FILTER: + if (buf_len < 2) { + pr_err("%s:Not support for buf_len < 2\n", __func__); + break; + } /* these NDIS_PACKET_TYPE_* bitflags are shared with * cdc_filter; it's not RNDIS-specific @@ -592,6 +596,7 @@ static int rndis_query_response(struct rndis_params *params, rndis_query_msg_type *buf) { rndis_query_cmplt_type *resp; + u32 BufOffset, BufLength; rndis_resp_t *r; /* pr_debug("%s: OID = %08X\n", __func__, cpu_to_le32(buf->OID)); */ @@ -612,12 +617,25 @@ static int rndis_query_response(struct rndis_params *params, resp->MessageType = cpu_to_le32(RNDIS_MSG_QUERY_C); resp->RequestID = buf->RequestID; /* Still LE in msg buffer */ + BufOffset = le32_to_cpu(buf->InformationBufferOffset); + BufLength = le32_to_cpu(buf->InformationBufferLength); + + /* + * If the address of the buf to be accessed exceeds the valid + * range of the buf, then return RNDIS_STATUS_NOT_SUPPORTED. + */ + if (8 + BufOffset + BufLength >= USB_COMP_EP0_BUFSIZ) { + resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); + resp->MessageLength = cpu_to_le32(sizeof(*resp)); + resp->InformationBufferLength = cpu_to_le32(0); + resp->InformationBufferOffset = cpu_to_le32(0); + params->resp_avail(params->v); + return 0; + } if (gen_ndis_query_resp(params, le32_to_cpu(buf->OID), - le32_to_cpu(buf->InformationBufferOffset) - + 8 + (u8 *)buf, - le32_to_cpu(buf->InformationBufferLength), - r)) { + BufOffset + 8 + (u8 *)buf, BufLength, + r)) { /* OID not supported */ resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); resp->MessageLength = cpu_to_le32(sizeof *resp); @@ -660,6 +678,17 @@ static int rndis_set_response(struct rndis_params *params, resp->MessageType = cpu_to_le32(RNDIS_MSG_SET_C); resp->MessageLength = cpu_to_le32(16); resp->RequestID = buf->RequestID; /* Still LE in msg buffer */ + + /* + * If the address of the buf to be accessed exceeds the valid + * range of the buf, then return RNDIS_STATUS_NOT_SUPPORTED. + */ + if (8 + BufOffset + BufLength >= USB_COMP_EP0_BUFSIZ) { + resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); + params->resp_avail(params->v); + return 0; + } + if (gen_ndis_set_resp(params, le32_to_cpu(buf->OID), ((u8 *)buf) + 8 + BufOffset, BufLength, r)) resp->Status = cpu_to_le32(RNDIS_STATUS_NOT_SUPPORTED); -- 2.25.1

1 0

【Meeting Notice】openEuler kernel 双周例会 Time: 2021-07-09 14:00-18:00
by Meeting Book 08 Jul '21

08 Jul '21

1 0

【kernel-sig例会议题申报】openEuler 21.09新特性简述
by Zheng Zengkai 08 Jul '21

08 Jul '21

*背景：* openEuler 21.09版本已启动开发，欢迎openEuler kernel开发者贡献补丁。申报一个议题： openEuler 21.09版本当前计划合入的特性简述。

1 0

[PATCH OLK-5.10 0/2] Add config switch and kernel parameter for CPU0
by Zheng Zengkai 05 Jul '21

05 Jul '21

Add config switch and kernel parameter for CPU0 hotplug. Besides, disable config ARM64_BOOTPARAM_HOTPLUG_CPU0 in openeuler_defconfig by default. Zheng Zengkai (2): arm64: Add config switch and kernel parameter for CPU0 hotplug config: disable config ARM64_BOOTPARAM_HOTPLUG_CPU0 by default .../admin-guide/kernel-parameters.txt | 8 ++++++ arch/arm64/Kconfig | 28 +++++++++++++++++++ arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/kernel/setup.c | 18 +++++++++++- 4 files changed, 54 insertions(+), 1 deletion(-) -- 2.20.1

1 2

[PATCH kernel-4.19] once: Fix panic when module unload
by Yang Yingliang 05 Jul '21

05 Jul '21

From: Kefeng Wang <wangkefeng.wang(a)huawei.com> hulk inclusion category: bugfix bugzilla: 172153 CVE: NA ------------------------------------------------- DO_ONCE DEFINE_STATIC_KEY_TRUE(___once_key); __do_once_done once_disable_jump(once_key); INIT_WORK(&w->work, once_deferred); struct once_work *w; w->key = key; schedule_work(&w->work); module unload //*the key is destroy* process_one_work once_deferred BUG_ON(!static_key_enabled(work->key)); static_key_count((struct static_key *)x) //*access key, crash* When module uses DO_ONCE mechanism, it could crash due to the above concurrency problem, we could reproduce it with link[1]. Fix it by add/put module refcount in the once work process. [1] https://lore.kernel.org/netdev/eaa6c371-465e-57eb-6be9-f4b16b9d7cbf@huawei.… Cc: Hannes Frederic Sowa <hannes(a)stressinduktion.org> Cc: Daniel Borkmann <daniel(a)iogearbox.net> Cc: David S. Miller <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Reported-by: Minmin chen <chenmingmin(a)huawei.com> Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- lib/once.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/lib/once.c b/lib/once.c index 8b7d6235217ee..959f8db41ccfa 100644 --- a/lib/once.c +++ b/lib/once.c @@ -3,10 +3,12 @@ #include <linux/spinlock.h> #include <linux/once.h> #include <linux/random.h> +#include <linux/module.h> struct once_work { struct work_struct work; struct static_key_true *key; + struct module *module; }; static void once_deferred(struct work_struct *w) @@ -16,11 +18,24 @@ static void once_deferred(struct work_struct *w) work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); + module_put(work->module); kfree(work); } +static struct module *find_module_by_key(struct static_key_true *key) +{ + struct module *mod; + + preempt_disable(); + mod = __module_address((unsigned long)key); + preempt_enable(); + + return mod; +} + static void once_disable_jump(struct static_key_true *key) { + struct module *mod = find_module_by_key(key); struct once_work *w; w = kmalloc(sizeof(*w), GFP_ATOMIC); @@ -29,6 +44,8 @@ static void once_disable_jump(struct static_key_true *key) INIT_WORK(&w->work, once_deferred); w->key = key; + w->module = mod; + __module_get(mod); schedule_work(&w->work); } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 01/11] bpf: fix up selftests after backports were fixed
by Yang Yingliang 05 Jul '21

05 Jul '21

From: Ovidiu Panait <ovidiu.panait(a)windriver.com> stable inclusion from linux-4.19.193 commit b190383c714a379002b00bc8de43371e78d291d8 -------------------------------- After the backport of the changes to fix CVE 2019-7308, the selftests also need to be fixed up, as was done originally in mainline 80c9b2fae87b ("bpf: add various test cases to selftests"). This is a backport of upstream commit 80c9b2fae87b ("bpf: add various test cases to selftests") adapted to 4.19 in order to fix the selftests that began to fail after CVE-2019-7308 fixes. Suggested-by: Frank van der Linden <fllinden(a)amazon.com> Signed-off-by: Ovidiu Panait <ovidiu.panait(a)windriver.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- tools/testing/selftests/bpf/test_verifier.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 9db5a7378f40f..fef1c9e3c4b81 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -2448,6 +2448,7 @@ static struct bpf_test tests[] = { }, .result = REJECT, .errstr = "invalid stack off=-79992 size=8", + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", }, { "PTR_TO_STACK store/load - out of bounds high", @@ -2844,6 +2845,8 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -7457,6 +7460,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7481,6 +7485,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7507,6 +7512,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7532,6 +7538,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7580,6 +7587,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7651,6 +7659,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7702,6 +7711,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7729,6 +7739,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7755,6 +7766,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7784,6 +7796,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R7 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7814,6 +7827,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 4 }, .errstr = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -7842,6 +7856,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, .result_unpriv = REJECT, }, @@ -7894,6 +7909,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8266,6 +8282,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "pointer offset 1073741822", + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .result = REJECT }, { @@ -8287,6 +8304,7 @@ static struct bpf_test tests[] = { }, .fixup_map1 = { 3 }, .errstr = "pointer offset -1073741822", + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .result = REJECT }, { @@ -8458,6 +8476,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN() }, .errstr = "fp pointer offset 1073741822", + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", .result = REJECT }, { -- 2.25.1

1 10

[PATCH kernel-4.19 1/2] SUNRPC: Fix the batch tasks count wraparound.
by Yang Yingliang 05 Jul '21

05 Jul '21

From: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> mainline inclusion from mainline-v5.14 commit fcb170a9d825d7db4a3fb870b0300f5a40a8d096 category: bugfix bugzilla: 51898 CVE: NA --------------------------- The 'queue->nr' will wraparound from 0 to 255 when only current priority queue has tasks. This maybe lead a deadlock same as commit dfe1fe75e00e ("NFSv4: Fix deadlock between nfs4_evict_inode() and nfs4_opendata_get_inode()"): Privileged delegreturn task is queued to privileged list because all the slots are assigned. When non-privileged task complete and release the slot, a non-privileged maybe picked out. It maybe allocate slot failed when the session on draining. If the 'queue->nr' has wraparound to 255, and no enough slot to service it, then the privileged delegreturn will lost to wake up. So we should avoid the wraparound on 'queue->nr'. Reported-by: Hulk Robot <hulkci(a)huawei.com> Fixes: 5fcdfacc01f3 ("NFSv4: Return delegations synchronously in evict_inode") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable(a)vger.kernel.org Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/sunrpc/sched.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 8d204d5a76187..8cffcf58e6386 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -506,7 +506,8 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q * Service a batch of tasks from a single owner. */ q = &queue->tasks[queue->priority]; - if (!list_empty(q) && --queue->nr) { + if (!list_empty(q) && queue->nr) { + queue->nr--; task = list_first_entry(q, struct rpc_task, u.tk_wait.list); goto out; } -- 2.25.1

1 1

[PATCH kernel-4.19 1/3] bpf: Inherit expanded/patched seen count from old aux data
by Yang Yingliang 05 Jul '21

05 Jul '21

From: Daniel Borkmann <daniel(a)iogearbox.net> mainline inclusion from mainline-v5.13-rc7 commit d203b0fd863a2261e5d00b97f3d060c4c2a6db71 category: bugfix bugzilla: NA CVE: CVE-2021-33624 -------------------------------- Instead of relying on current env->pass_cnt, use the seen count from the old aux data in adjust_insn_aux_data(), and expand it to the new range of patched instructions. This change is valid given we always expand 1:n with n>=1, so what applies to the old/original instruction needs to apply for the replacement as well. Not relying on env->pass_cnt is a prerequisite for a later change where we want to avoid marking an instruction seen when verified under speculative execution path. Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Reviewed-by: John Fastabend <john.fastabend(a)gmail.com> Reviewed-by: Benedict Schlueter <benedict.schlueter(a)rub.de> Reviewed-by: Piotr Krysiuk <piotras(a)gmail.com> Acked-by: Alexei Starovoitov <ast(a)kernel.org> Conflicts: kernel/bpf/verifier.c seen of bpf_insn_aux_data is bool in kernel-4.19. Signed-off-by: He Fengqing <hefengqing(a)huawei.com> Reviewed-by: Kuohai Xu <xukuohai(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/bpf/verifier.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ac02469d0f154..6b919fba40c00 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5853,6 +5853,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, u32 off, u32 cnt) { struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; + bool old_seen = old_data[off].seen; int i; if (cnt == 1) @@ -5864,8 +5865,10 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len, memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); - for (i = off; i < off + cnt - 1; i++) - new_data[i].seen = true; + for (i = off; i < off + cnt - 1; i++) { + /* Expand insni[off]'s seen count to the patched range. */ + new_data[i].seen = old_seen; + } env->insn_aux_data = new_data; vfree(old_data); return 0; -- 2.25.1

1 2

[PATCH kernel-4.19] nvme-rdma: avoid request double completion for concurrent nvme_rdma_timeout
by Yang Yingliang 02 Jul '21

02 Jul '21

From: Chao Leng <lengchao(a)huawei.com> mainline inclusion from mainline-v5.11-rc5 commit 7674073b2ed35ac951a49c425dec6b39d5a57140 category: bugfix bugzilla: NA CVE: NA Link: https://gitee.com/openeuler/kernel/issues/I1WGZE ------------------------------------------------- A crash happens when inject completing request long time(nearly 30s). Each name space has a request queue, when inject completing request long time, multi request queues may have time out requests at the same time, nvme_rdma_timeout will execute concurrently. Multi requests in different request queues may be queued in the same rdma queue, multi nvme_rdma_timeout may call nvme_rdma_stop_queue at the same time. The first nvme_rdma_timeout will clear NVME_RDMA_Q_LIVE and continue stopping the rdma queue(drain qp), but the others check NVME_RDMA_Q_LIVE is already cleared, and then directly complete the requests, complete request before the qp is fully drained may lead to a use-after-free condition. Add a multex lock to serialize nvme_rdma_stop_queue. Signed-off-by: Chao Leng <lengchao(a)huawei.com> Tested-by: Israel Rukshin <israelr(a)nvidia.com> Reviewed-by: Israel Rukshin <israelr(a)nvidia.com> Signed-off-by: Christoph Hellwig <hch(a)lst.de> conflicts: drivers/nvme/host/rdma.c [lrz: adjust context] Signed-off-by: Ruozhu Li <liruozhu(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/nvme/host/rdma.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 158d7417bcea6..91ff9262f6729 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -93,6 +93,7 @@ struct nvme_rdma_queue { struct rdma_cm_id *cm_id; int cm_error; struct completion cm_done; + struct mutex queue_lock; }; struct nvme_rdma_ctrl { @@ -503,6 +504,7 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, int ret; queue = &ctrl->queues[idx]; + mutex_init(&queue->queue_lock); queue->ctrl = ctrl; init_completion(&queue->cm_done); @@ -518,7 +520,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, if (IS_ERR(queue->cm_id)) { dev_info(ctrl->ctrl.device, "failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id)); - return PTR_ERR(queue->cm_id); + ret = PTR_ERR(queue->cm_id); + goto out_destroy_mutex; } if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR) @@ -548,6 +551,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl, out_destroy_cm_id: rdma_destroy_id(queue->cm_id); nvme_rdma_destroy_queue_ib(queue); +out_destroy_mutex: + mutex_destroy(&queue->queue_lock); return ret; } @@ -559,10 +564,10 @@ static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) { - if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) - return; - - __nvme_rdma_stop_queue(queue); + mutex_lock(&queue->queue_lock); + if (test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) + __nvme_rdma_stop_queue(queue); + mutex_unlock(&queue->queue_lock); } static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) @@ -572,6 +577,7 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue) nvme_rdma_destroy_queue_ib(queue); rdma_destroy_id(queue->cm_id); + mutex_destroy(&queue->queue_lock); } static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl) -- 2.25.1

1 0

[PATCH kernel-4.19] binfmt: Move install_exec_creds after setup_new_exec to match binfmt_elf
by Yang Yingliang 02 Jul '21

02 Jul '21

From: "Eric W. Biederman" <ebiederm(a)xmission.com> mainline inclusion from mainline-v5.8-rc1 commit e7f7785449a1f459a4a3ca92f82f56fb054dd2b9 category: bugfix bugzilla: 36868 CVE: NA ----------------------------------------------- In 2016 Linus moved install_exec_creds immediately after setup_new_exec, in binfmt_elf as a cleanup and as part of closing a potential information leak. Perform the same cleanup for the other binary formats. Different binary formats doing the same things the same way makes exec easier to reason about and easier to maintain. Greg Ungerer reports: > I tested the the whole series on non-MMU m68k and non-MMU arm > (exercising binfmt_flat) and it all tested out with no problems, > so for the binfmt_flat changes: Tested-by: Greg Ungerer <gerg(a)linux-m68k.org> Ref: 9f834ec18def ("binfmt_elf: switch to new creds when switching to new mm") Reviewed-by: Kees Cook <keescook(a)chromium.org> Reviewed-by: Greg Ungerer <gerg(a)linux-m68k.org> Signed-off-by: "Eric W. Biederman" <ebiederm(a)xmission.com> Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/ia32/ia32_aout.c | 3 +-- fs/binfmt_aout.c | 2 +- fs/binfmt_elf_fdpic.c | 2 +- fs/binfmt_flat.c | 3 +-- 4 files changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 7dbbe9ffda173..8d78ea00d75fe 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -298,6 +298,7 @@ static int load_aout_binary(struct linux_binprm *bprm) set_personality_ia32(false); setup_new_exec(bprm); + install_exec_creds(bprm); regs->cs = __USER32_CS; regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = @@ -314,8 +315,6 @@ static int load_aout_binary(struct linux_binprm *bprm) if (retval < 0) return retval; - install_exec_creds(bprm); - if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index ca9725f18e005..af09b55d5ac52 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -244,6 +244,7 @@ static int load_aout_binary(struct linux_binprm * bprm) set_personality(PER_LINUX); #endif setup_new_exec(bprm); + install_exec_creds(bprm); current->mm->end_code = ex.a_text + (current->mm->start_code = N_TXTADDR(ex)); @@ -256,7 +257,6 @@ static int load_aout_binary(struct linux_binprm * bprm) if (retval < 0) return retval; - install_exec_creds(bprm); if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index b53bb3729ac1e..60896c16f103c 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -357,6 +357,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->personality |= READ_IMPLIES_EXEC; setup_new_exec(bprm); + install_exec_creds(bprm); set_binfmt(&elf_fdpic_format); @@ -438,7 +439,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->mm->start_stack = current->mm->start_brk + stack_size; #endif - install_exec_creds(bprm); if (create_elf_fdpic_tables(bprm, current->mm, &exec_params, &interp_params) < 0) goto error; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index e4b59e76afb0d..bbeff9385d609 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -517,6 +517,7 @@ static int load_flat_file(struct linux_binprm *bprm, /* OK, This is the point of no return */ set_personality(PER_LINUX_32BIT); setup_new_exec(bprm); + install_exec_creds(bprm); } /* @@ -940,8 +941,6 @@ static int load_flat_binary(struct linux_binprm *bprm) } } - install_exec_creds(bprm); - set_binfmt(&flat_format); #ifdef CONFIG_MMU -- 2.25.1

1 0

[PATCH kernel-4.19 000/106] backport linux-4.19.196
by Yang Yingliang 02 Jul '21

02 Jul '21

Andreas Gruenbacher (1): gfs2: Prevent direct-I/O write fallback errors from getting lost Andrew Lunn (1): usb: core: hub: Disable autosuspend for Cypress CY7C65632 Andrew Morton (1): mm/slub.c: include swab.h Anirudh Rayabharam (1): HID: usbhid: fix info leak in hid_submit_ctrl Antti Järvinen (1): PCI: Mark TI C667X to avoid bus reset Arnaldo Carvalho de Melo (1): tools headers UAPI: Sync linux/in.h copy with the kernel sources Arnd Bergmann (1): ARM: 9081/1: fix gcc-10 thumb2-kernel regression Austin Kim (1): net: ethtool: clear heap allocations for ethtool function Aya Levin (1): net/mlx5e: Block offload of outer header csum for UDP tunnels Bixuan Cui (1): HID: gt683r: add missing MODULE_DEVICE_TABLE Bumyong Lee (1): dmaengine: pl330: fix wrong usage of spinlock flags in dma_cyclc Changbin Du (1): net: make get_net_ns return error if NET_NS is disabled Chen Li (1): radeon: use memcpy_to/fromio for UVD fw upload Chengyang Fan (1): net: ipv4: fix memory leak in ip_mc_add1_src Christian König (2): drm/nouveau: wait for moving fence after pinning v2 drm/radeon: wait for moving fence after pinning Christophe JAILLET (4): alx: Fix an error handling path in 'alx_probe()' qlcnic: Fix an error handling path in 'qlcnic_probe()' netxen_nic: Fix an error handling path in 'netxen_nic_probe()' be2net: Fix an error handling path in 'be_probe()' Dan Carpenter (1): afs: Fix an IS_ERR() vs NULL check Dan Robertson (1): net: ieee802154: fix null deref in parse dev addr Dongliang Mu (1): net: usb: fix possible use-after-free in smsc75xx_bind Du Cheng (1): cfg80211: call cfg80211_leave_ocb when switching away from OCB Eric Auger (1): KVM: arm/arm64: Fix KVM_VGIC_V3_ADDR_TYPE_REDIST read Eric Dumazet (5): net/af_unix: fix a data-race in unix_dgram_sendmsg / unix_release_sock inet: use bigger hash table for IP ID generation inet: annotate date races around sk->sk_txhash net/packet: annotate accesses to po->bind net/packet: annotate accesses to po->ifindex Esben Haabendal (1): net: ll_temac: Avoid ndo_start_xmit returning NETDEV_TX_BUSY Ewan D. Milne (1): scsi: scsi_devinfo: Add blacklist entry for HPE OPEN-V Fabien Dessenne (1): pinctrl: stm32: fix the reported number of GPIO lines per bank Fuad Tabba (1): KVM: selftests: Fix kvm_check_cap() assertion Fugang Duan (1): net: fec_ptp: add clock rate zero check Hannes Reinecke (3): nvme-loop: reset queue count to 1 in nvme_loop_destroy_io_queues() nvme-loop: clear NVME_LOOP_Q_LIVE when nvme_loop_configure_admin_queue() fails nvme-loop: check for NVME_LOOP_Q_LIVE in nvme_loop_destroy_admin_queue() Hillf Danton (1): gfs2: Fix use-after-free in gfs2_glock_shrink_scan Huy Nguyen (1): net/mlx5e: Remove dependency in IPsec initialization flows Ido Schimmel (1): rtnetlink: Fix regression in bridge VLAN configuration Jack Pham (1): usb: dwc3: debugfs: Add and remove endpoint dirs dynamically Jack Yu (1): ASoC: rt5659: Fix the lost powers for the HDA header Jakub Kicinski (1): ptp: improve max_adj check against unreasonable values Jiapeng Chong (2): ethernet: myri10ge: Fix missing error code in myri10ge_probe() rtnetlink: Fix missing error code in rtnl_bridge_notify() Jisheng Zhang (1): net: stmmac: dwmac1000: Fix extended MAC address registers definition Joakim Zhang (1): net: fec_ptp: fix issue caused by refactor the fec_devtype Johan Hovold (1): i2c: robotfuzz-osif: fix control-request directions Johannes Berg (3): cfg80211: make certificate generation more robust mac80211: remove warning in ieee80211_get_sband() mac80211: drop multicast fragments Josh Triplett (1): net: ipconfig: Don't override command-line hostnames or domains Kees Cook (5): mm/slub: clarify verification reporting r8152: Avoid memcpy() over-reading of ETH_SS_STATS sh_eth: Avoid memcpy() over-reading of ETH_SS_STATS r8169: Avoid memcpy() over-reading of ETH_SS_STATS net: qed: Fix memcpy() overflow of qed_dcbx_params() Linyu Yuan (1): net: cdc_eem: fix tx fixup skb leak Maciej Żenczykowski (1): net: cdc_ncm: switch to eth%d interface naming Mark Bolhuis (1): HID: Add BUS_VIRTUAL to hid_connect logging Maurizio Lombardi (1): scsi: target: core: Fix warning on realtime kernels Maxim Mikityanskiy (2): netfilter: synproxy: Fix out of bounds when parsing TCP options sch_cake: Fix out of bounds when parsing TCP options and header Mikel Rychliski (1): PCI: Add AMD RS690 quirk to enable 64-bit DMA Mimi Zohar (1): module: limit enabling module.sig_enforce Nanyong Sun (1): net: ipv4: fix memory leak in netlbl_cipsov4_add_std Nathan Chancellor (2): Makefile: Move -Wno-unused-but-set-variable out of GCC only block MIPS: generic: Update node names to avoid unit addresses Nikolay Aleksandrov (2): net: bridge: fix vlan tunnel dst null pointer dereference net: bridge: fix vlan tunnel dst refcnt when egressing Nirenjan Krishnan (1): HID: quirks: Set INCREMENT_USAGE_ON_DUPLICATE for Saitek X65 Paolo Abeni (1): udp: fix race between close() and udp_abort() Pavel Skripkin (7): net: rds: fix memory leak in rds_recvmsg net: qrtr: fix OOB Read in qrtr_endpoint_post net: hamradio: fix memory leak in mkiss_close net: ethernet: fix potential use-after-free in ec_bhf_remove can: mcba_usb: fix memory leak in mcba_usb net: caif: fix memory leak in ldisc_open nilfs2: fix memory leak in nilfs_sysfs_delete_device_group Pedro Tammela (1): net: add documentation to socket.c Peter Chen (1): usb: dwc3: core: fix kernel panic when do reboot Rafael J. Wysocki (1): Revert "PCI: PM: Do not read power state in pci_enable_device_flags()" Randy Dunlap (2): dmaengine: ALTERA_MSGDMA depends on HAS_IOMEM dmaengine: QCOM_HIDMA_MGMT depends on HAS_IOMEM Riwen Lu (1): hwmon: (scpi-hwmon) shows the negative temperature properly Sasha Levin (1): Linux 4.19.196 Sergio Paracuellos (1): pinctrl: ralink: rt2880: avoid to error in calls is pin is already enabled Shalom Toledo (1): ptp: ptp_clock: Publish scaled_ppm_to_ppb Shanker Donthineni (1): PCI: Mark some NVIDIA GPUs to avoid bus reset Sriharsha Basavapatna (1): PCI: Add ACS quirk for Broadcom BCM57414 NIC Srinivas Pandruvada (1): HID: hid-sensor-hub: Return error for hid_set_field() failure Steven Rostedt (VMware) (3): tracing: Do not stop recording cmdlines when tracing is off tracing: Do not stop recording comms if the trace file is being read tracing: Do no increment trace_clock_global() by one Sven Eckelmann (1): batman-adv: Avoid WARN_ON timing related checks Tetsuo Handa (1): can: bcm/raw/isotp: use per module netdevice notifier Thomas Gleixner (1): x86/fpu: Reset state for all signal restore failures Toke Høiland-Jørgensen (1): icmp: don't send out ICMP messages with a source address of 0.0.0.0 Vineet Gupta (1): ARCv2: save ABI registers across signal handling Yang Yingliang (1): dmaengine: stedma40: add missing iounmap() on error in d40_probe() Yongqiang Liu (1): ARM: OMAP2+: Fix build warning when mmc_omap is not built Zheng Yongjun (4): net/x25: Return the correct errno code net: Return the correct errno code fib: Return the correct errno code ping: Check return value of function 'ping_queue_rcv_skb' Documentation/vm/slub.rst | 10 +- Makefile | 5 +- arch/arc/include/uapi/asm/sigcontext.h | 1 + arch/arc/kernel/signal.c | 43 +++ arch/arm/kernel/setup.c | 16 +- arch/arm/mach-omap2/board-n8x0.c | 2 +- arch/mips/generic/board-boston.its.S | 10 +- arch/mips/generic/board-ni169445.its.S | 10 +- arch/mips/generic/board-xilfpga.its.S | 10 +- arch/mips/generic/vmlinux.its.S | 10 +- arch/x86/kernel/fpu/signal.c | 31 +- arch/x86/pci/fixup.c | 44 +++ drivers/dma/Kconfig | 1 + drivers/dma/pl330.c | 6 +- drivers/dma/qcom/Kconfig | 1 + drivers/dma/ste_dma40.c | 3 + drivers/gpu/drm/nouveau/nouveau_prime.c | 17 +- drivers/gpu/drm/radeon/radeon_prime.c | 16 +- drivers/gpu/drm/radeon/radeon_uvd.c | 4 +- drivers/hid/hid-core.c | 3 + drivers/hid/hid-gt683r.c | 1 + drivers/hid/hid-ids.h | 1 + drivers/hid/hid-quirks.c | 1 + drivers/hid/hid-sensor-hub.c | 13 +- drivers/hid/usbhid/hid-core.c | 2 +- drivers/hwmon/scpi-hwmon.c | 9 + drivers/i2c/busses/i2c-robotfuzz-osif.c | 4 +- drivers/net/caif/caif_serial.c | 1 + drivers/net/can/usb/mcba_usb.c | 17 +- drivers/net/ethernet/atheros/alx/main.c | 1 + drivers/net/ethernet/ec_bhf.c | 4 +- drivers/net/ethernet/emulex/benet/be_main.c | 1 + drivers/net/ethernet/freescale/fec_ptp.c | 8 +- .../mellanox/mlx5/core/en_accel/ipsec.c | 3 - .../net/ethernet/mellanox/mlx5/core/en_main.c | 7 +- .../net/ethernet/myricom/myri10ge/myri10ge.c | 1 + .../ethernet/qlogic/netxen/netxen_nic_main.c | 2 + drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 4 +- .../net/ethernet/qlogic/qlcnic/qlcnic_main.c | 1 + drivers/net/ethernet/realtek/r8169.c | 2 +- drivers/net/ethernet/renesas/sh_eth.c | 2 +- .../net/ethernet/stmicro/stmmac/dwmac1000.h | 8 +- drivers/net/ethernet/xilinx/ll_temac_main.c | 5 + drivers/net/hamradio/mkiss.c | 1 + drivers/net/usb/cdc_eem.c | 2 +- drivers/net/usb/cdc_ncm.c | 2 +- drivers/net/usb/r8152.c | 2 +- drivers/net/usb/smsc75xx.c | 10 +- drivers/nvme/target/loop.c | 5 +- drivers/pci/pci.c | 16 +- drivers/pci/quirks.c | 24 ++ drivers/pinctrl/stm32/pinctrl-stm32.c | 9 +- drivers/ptp/ptp_clock.c | 7 +- drivers/scsi/scsi_devinfo.c | 1 + .../staging/mt7621-pinctrl/pinctrl-rt2880.c | 2 +- drivers/target/target_core_transport.c | 4 +- drivers/usb/core/hub.c | 7 + drivers/usb/dwc3/core.c | 2 +- drivers/usb/dwc3/debug.h | 3 + drivers/usb/dwc3/debugfs.c | 21 +- drivers/usb/dwc3/gadget.c | 3 + fs/afs/main.c | 4 +- fs/gfs2/file.c | 5 +- fs/gfs2/glock.c | 2 +- fs/nilfs2/sysfs.c | 1 + include/linux/hid.h | 3 +- include/linux/net.h | 6 + include/linux/ptp_clock_kernel.h | 8 + include/linux/socket.h | 14 +- include/net/net_namespace.h | 7 + include/net/sock.h | 10 +- include/uapi/linux/in.h | 3 + kernel/module.c | 9 + kernel/trace/trace.c | 11 - kernel/trace/trace_clock.c | 6 +- mm/slub.c | 15 +- net/batman-adv/bat_iv_ogm.c | 4 +- net/bridge/br_private.h | 4 +- net/bridge/br_vlan_tunnel.c | 38 ++- net/can/bcm.c | 59 +++- net/can/raw.c | 62 +++- net/compat.c | 2 +- net/core/ethtool.c | 10 +- net/core/fib_rules.c | 2 +- net/core/net_namespace.c | 12 + net/core/rtnetlink.c | 4 + net/ieee802154/nl802154.c | 9 +- net/ipv4/cipso_ipv4.c | 1 + net/ipv4/icmp.c | 7 + net/ipv4/igmp.c | 1 + net/ipv4/ipconfig.c | 13 +- net/ipv4/ping.c | 12 +- net/ipv4/route.c | 42 ++- net/ipv4/udp.c | 10 + net/ipv6/udp.c | 3 + net/mac80211/ieee80211_i.h | 2 +- net/mac80211/rx.c | 9 +- net/netfilter/nf_synproxy_core.c | 5 + net/packet/af_packet.c | 32 +- net/qrtr/qrtr.c | 2 +- net/rds/recv.c | 2 +- net/sched/sch_cake.c | 6 +- net/socket.c | 276 ++++++++++++++++-- net/unix/af_unix.c | 7 +- net/wireless/Makefile | 2 +- net/wireless/util.c | 3 + net/x25/af_x25.c | 2 +- sound/soc/codecs/rt5659.c | 26 +- tools/include/uapi/linux/in.h | 3 + tools/testing/selftests/kvm/lib/kvm_util.c | 2 +- virt/kvm/arm/vgic/vgic-kvm-device.c | 4 +- 111 files changed, 942 insertions(+), 302 deletions(-) -- 2.25.1

1 106

[PATCH kernel-4.19] ext4: fix memory leak in ext4_fill_super
by Yang Yingliang 01 Jul '21

01 Jul '21

From: Pavel Skripkin <paskripkin(a)gmail.com> mainline inclusion from mainline-5.14 commit 618f003199c6188e01472b03cdbba227f1dc5f24 category: bugfix bugzilla: 167360 CVE: NA ------------------------------------------------- static int kthread(void *_create) will return -ENOMEM or -EINTR in case of internal failure or kthread_stop() call happens before threadfn call. To prevent fancy error checking and make code more straightforward we moved all cleanup code out of kmmpd threadfn. Also, dropped struct mmpd_data at all. Now struct super_block is a threadfn data and struct buffer_head embedded into struct ext4_sb_info. Reported-by: syzbot+d9e482e303930fa4f6ff(a)syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin <paskripkin(a)gmail.com> Link: https://lore.kernel.org/r/20210430185046.15742-1-paskripkin@gmail.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Conflicts: fs/ext4/ext4.h fs/ext4/super.c Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/ext4.h | 4 ++++ fs/ext4/mmp.c | 28 +++++++++++++--------------- fs/ext4/super.c | 11 +++++------ 3 files changed, 22 insertions(+), 21 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d4e98941c5ad4..b3e3f93385684 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1407,6 +1407,7 @@ struct ext4_sb_info { struct kobject s_kobj; struct completion s_kobj_unregister; struct super_block *s_sb; + struct buffer_head *s_mmp_bh; /* Journaling */ struct journal_s *s_journal; @@ -3391,6 +3392,9 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io, /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); +/* mmp.c */ +extern void ext4_stop_mmpd(struct ext4_sb_info *sbi); + /* * Add new method to test whether block and inode bitmaps are properly * initialized. With uninit_bg reading the block from disk is not enough diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 795c3ff2907c2..623bad399612f 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -127,9 +127,9 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, */ static int kmmpd(void *data) { - struct super_block *sb = ((struct mmpd_data *) data)->sb; - struct buffer_head *bh = ((struct mmpd_data *) data)->bh; + struct super_block *sb = (struct super_block *) data; struct ext4_super_block *es = EXT4_SB(sb)->s_es; + struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh; struct mmp_struct *mmp; ext4_fsblk_t mmp_block; u32 seq = 0; @@ -245,12 +245,18 @@ static int kmmpd(void *data) retval = write_mmp_block(sb, bh); exit_thread: - EXT4_SB(sb)->s_mmp_tsk = NULL; - kfree(data); - brelse(bh); return retval; } +void ext4_stop_mmpd(struct ext4_sb_info *sbi) +{ + if (sbi->s_mmp_tsk) { + kthread_stop(sbi->s_mmp_tsk); + brelse(sbi->s_mmp_bh); + sbi->s_mmp_tsk = NULL; + } +} + /* * Get a random new sequence number but make sure it is not greater than * EXT4_MMP_SEQ_MAX. @@ -275,7 +281,6 @@ int ext4_multi_mount_protect(struct super_block *sb, struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct buffer_head *bh = NULL; struct mmp_struct *mmp = NULL; - struct mmpd_data *mmpd_data; u32 seq; unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval); unsigned int wait_time = 0; @@ -364,24 +369,17 @@ int ext4_multi_mount_protect(struct super_block *sb, goto failed; } - mmpd_data = kmalloc(sizeof(*mmpd_data), GFP_KERNEL); - if (!mmpd_data) { - ext4_warning(sb, "not enough memory for mmpd_data"); - goto failed; - } - mmpd_data->sb = sb; - mmpd_data->bh = bh; + EXT4_SB(sb)->s_mmp_bh = bh; /* * Start a kernel thread to update the MMP block periodically. */ - EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s", + EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s", (int)sizeof(mmp->mmp_bdevname), bdevname(bh->b_bdev, mmp->mmp_bdevname)); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { EXT4_SB(sb)->s_mmp_tsk = NULL; - kfree(mmpd_data); ext4_warning(sb, "Unable to create kmmpd thread for %s.", sb->s_id); goto failed; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f66bbe73d1a94..ef7b7267b2ae8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1225,8 +1225,9 @@ static void ext4_put_super(struct super_block *sb) ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; } - if (sbi->s_mmp_tsk) - kthread_stop(sbi->s_mmp_tsk); + + ext4_stop_mmpd(sbi); + brelse(sbi->s_sbh); sb->s_fs_info = NULL; /* @@ -4851,8 +4852,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) failed_mount3: flush_work(&sbi->s_error_work); del_timer_sync(&sbi->s_err_report); - if (sbi->s_mmp_tsk) - kthread_stop(sbi->s_mmp_tsk); + ext4_stop_mmpd(sbi); failed_mount2: rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); @@ -5647,8 +5647,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) */ ext4_mark_recovery_complete(sb, es); } - if (sbi->s_mmp_tsk) - kthread_stop(sbi->s_mmp_tsk); + ext4_stop_mmpd(sbi); } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || -- 2.25.1

1 0

[PATCH kernel-4.19 01/13] RDMA/verbs: Add a DMA iterator to return aligned contiguous memory blocks
by Yang Yingliang 01 Jul '21

01 Jul '21

From: Xi Wang <wangxi11(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA This helper iterates over a DMA-mapped SGL and returns contiguous memory blocks aligned to a HW supported page size. Suggested-by: Jason Gunthorpe <jgg(a)ziepe.ca> Signed-off-by: Shiraz Saleem <shiraz.saleem(a)intel.com> Signed-off-by: Jason Gunthorpe <jgg(a)mellanox.com> Signed-off-by: Xi Wang <wangxi11(a)huawei.com> Signed-off-by: Shunfeng Yang <yangshunfeng2(a)huawei.com> Reviewed-by: chunzhi hu <huchunzhi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/infiniband/core/verbs.c | 34 ++++++++++++++++++++++++ include/rdma/ib_verbs.h | 47 +++++++++++++++++++++++++++++++++ 2 files changed, 81 insertions(+) diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index e1ecd4682c096..6467645c84d09 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2628,3 +2628,37 @@ void ib_drain_qp(struct ib_qp *qp) ib_drain_rq(qp); } EXPORT_SYMBOL(ib_drain_qp); + +void __rdma_block_iter_start(struct ib_block_iter *biter, + struct scatterlist *sglist, unsigned int nents, + unsigned long pgsz) +{ + memset(biter, 0, sizeof(struct ib_block_iter)); + biter->__sg = sglist; + biter->__sg_nents = nents; + + /* Driver provides best block size to use */ + biter->__pg_bit = __fls(pgsz); +} +EXPORT_SYMBOL(__rdma_block_iter_start); + +bool __rdma_block_iter_next(struct ib_block_iter *biter) +{ + unsigned int block_offset; + + if (!biter->__sg_nents || !biter->__sg) + return false; + + biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance; + block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1); + biter->__sg_advance += BIT_ULL(biter->__pg_bit) - block_offset; + + if (biter->__sg_advance >= sg_dma_len(biter->__sg)) { + biter->__sg_advance = 0; + biter->__sg = sg_next(biter->__sg); + biter->__sg_nents--; + } + + return true; +} +EXPORT_SYMBOL(__rdma_block_iter_next); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index c1c1a61d81f6e..43a7426b43a15 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2629,6 +2629,21 @@ struct ib_client { struct list_head list; }; +/* + * IB block DMA iterator + * + * Iterates the DMA-mapped SGL in contiguous memory blocks aligned + * to a HW supported page size. + */ +struct ib_block_iter { + /* internal states */ + struct scatterlist *__sg; /* sg holding the current aligned block */ + dma_addr_t __dma_addr; /* unaligned DMA address of this block */ + unsigned int __sg_nents; /* number of SG entries */ + unsigned int __sg_advance; /* number of bytes to advance in sg in next step */ + unsigned int __pg_bit; /* alignment of current block */ +}; + struct ib_device *ib_alloc_device(size_t size); void ib_dealloc_device(struct ib_device *device); @@ -2642,6 +2657,38 @@ void ib_unregister_device(struct ib_device *device); int ib_register_client (struct ib_client *client); void ib_unregister_client(struct ib_client *client); +void __rdma_block_iter_start(struct ib_block_iter *biter, + struct scatterlist *sglist, + unsigned int nents, + unsigned long pgsz); +bool __rdma_block_iter_next(struct ib_block_iter *biter); + +/** + * rdma_block_iter_dma_address - get the aligned dma address of the current + * block held by the block iterator. + * @biter: block iterator holding the memory block + */ +static inline dma_addr_t +rdma_block_iter_dma_address(struct ib_block_iter *biter) +{ + return biter->__dma_addr & ~(BIT_ULL(biter->__pg_bit) - 1); +} + +/** + * rdma_for_each_block - iterate over contiguous memory blocks of the sg list + * @sglist: sglist to iterate over + * @biter: block iterator holding the memory block + * @nents: maximum number of sg entries to iterate over + * @pgsz: best HW supported page size to use + * + * Callers may use rdma_block_iter_dma_address() to get each + * blocks aligned DMA address. + */ +#define rdma_for_each_block(sglist, biter, nents, pgsz) \ + for (__rdma_block_iter_start(biter, sglist, nents, \ + pgsz); \ + __rdma_block_iter_next(biter);) + void *ib_get_client_data(struct ib_device *device, struct ib_client *client); void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data); -- 2.25.1

1 12

[PATCH kernel-4.19] can: bcm: delay release of struct bcm_op after synchronize_rcu()
by Yang Yingliang 01 Jul '21

01 Jul '21

From: Thadeu Lima de Souza Cascardo <cascardo(a)canonical.com> mainline inclusion from mainline-v5.14-rc1 commit d5f9023fa61ee8b94f37a93f08e94b136cf1e463 category: bugfix bugzilla: NA CVE: CVE-2021-3609 -------------------------------- can_rx_register() callbacks may be called concurrently to the call to can_rx_unregister(). The callbacks and callback data, though, are protected by RCU and the struct sock reference count. So the callback data is really attached to the life of sk, meaning that it should be released on sk_destruct. However, bcm_remove_op() calls tasklet_kill(), and RCU callbacks may be called under RCU softirq, so that cannot be used on kernels before the introduction of HRTIMER_MODE_SOFT. However, bcm_rx_handler() is called under RCU protection, so after calling can_rx_unregister(), we may call synchronize_rcu() in order to wait for any RCU read-side critical sections to finish. That is, bcm_rx_handler() won't be called anymore for those ops. So, we only free them, after we do that synchronize_rcu(). Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol") Link: https://lore.kernel.org/r/20210619161813.2098382-1-cascardo@canonical.com Cc: linux-stable <stable(a)vger.kernel.org> Reported-by: syzbot+0f7e7e5e2f4f40fa89c0(a)syzkaller.appspotmail.com Reported-by: Norbert Slusarek <nslusarek(a)gmx.net> Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo(a)canonical.com> Acked-by: Oliver Hartkopp <socketcan(a)hartkopp.net> Signed-off-by: Marc Kleine-Budde <mkl(a)pengutronix.de> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/can/bcm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/can/bcm.c b/net/can/bcm.c index 0f09838ebef6e..e66377e764ba9 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -824,6 +824,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, bcm_rx_handler, op); list_del(&op->list); + synchronize_rcu(); bcm_remove_op(op); return 1; /* done */ } @@ -1557,9 +1558,13 @@ static int bcm_release(struct socket *sock) REGMASK(op->can_id), bcm_rx_handler, op); - bcm_remove_op(op); } + synchronize_rcu(); + + list_for_each_entry_safe(op, next, &bo->rx_ops, list) + bcm_remove_op(op); + #if IS_ENABLED(CONFIG_PROC_FS) /* remove procfs entry */ if (net->can.bcmproc_dir && bo->bcm_proc_read) -- 2.25.1

1 0

[PATCH kernel-4.19] etmem_scan: fix memleak in vm_idle_read
by Yang Yingliang 01 Jul '21

01 Jul '21

From: Kemeng Shi <shikemeng(a)huawei.com> euleros inclusion category: bugfix bugzilla: NA ------------------------------ Struct page_idle_ctrl is alloced at beginning of vm_idle_read, but it's not freed when vm_idle_read ends. Fixes: 2ca27c4642db5 ("etmem: add etmem-scan feature") Signed-off-by: Kemeng Shi <shikemeng(a)huawei.com> Reviewed-by: Jing Xiangfeng<jingxiangfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/proc/etmem_scan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/proc/etmem_scan.c b/fs/proc/etmem_scan.c index 94bf125de6072..2bac5ecd53164 100644 --- a/fs/proc/etmem_scan.c +++ b/fs/proc/etmem_scan.c @@ -753,6 +753,7 @@ static ssize_t vm_idle_read(struct file *file, char *buf, ret = pic->bytes_copied; *ppos = pic->next_hva; out_kvm: + kfree(pic); return ret; } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] x86/uprobes: Do not use prefixes.nbytes when looping over prefixes.bytes
by Yang Yingliang 01 Jul '21

01 Jul '21

From: Masami Hiramatsu <mhiramat(a)kernel.org> stable inclusion from linux-4.19.163 commit 6bb78b3fff90fcf76991f689822ae58a4feee36d -------------------------------- commit 4e9a5ae8df5b3365183150f6df49e49dece80d8c upstream. Since insn.prefixes.nbytes can be bigger than the size of insn.prefixes.bytes[] when a prefix is repeated, the proper check must be insn.prefixes.bytes[i] != 0 and i < 4 instead of using insn.prefixes.nbytes. Introduce a for_each_insn_prefix() macro for this purpose. Debugged by Kees Cook <keescook(a)chromium.org>. [ bp: Massage commit message, sync with the respective header in tools/ and drop "we". ] Fixes: 2b1444983508 ("uprobes, mm, x86: Add the ability to install and remove uprobes breakpoints") Reported-by: syzbot+9b64b619f10f19d19a7c(a)syzkaller.appspotmail.com Signed-off-by: Masami Hiramatsu <mhiramat(a)kernel.org> Signed-off-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Srikar Dronamraju <srikar(a)linux.vnet.ibm.com> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/160697103739.3146288.7437620795200799020.stgit@de… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/x86/include/asm/insn.h | 15 +++++++++++++++ arch/x86/kernel/uprobes.c | 10 ++++++---- tools/objtool/arch/x86/include/asm/insn.h | 15 +++++++++++++++ tools/perf/util/intel-pt-decoder/insn.h | 15 +++++++++++++++ 4 files changed, 51 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index c2c01f84df75f..3e0e18d376d2c 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -208,6 +208,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 420aa7d3a2e6b..ae9e806a11def 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -268,12 +268,13 @@ static volatile u32 good_2byte_insns[256 / 32] = { static bool is_prefix_bad(struct insn *insn) { + insn_byte_t p; int i; - for (i = 0; i < insn->prefixes.nbytes; i++) { + for_each_insn_prefix(insn, i, p) { insn_attr_t attr; - attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]); + attr = inat_get_opcode_attribute(p); switch (attr) { case INAT_MAKE_PREFIX(INAT_PFX_ES): case INAT_MAKE_PREFIX(INAT_PFX_CS): @@ -728,6 +729,7 @@ static const struct uprobe_xol_ops push_xol_ops = { static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) { u8 opc1 = OPCODE1(insn); + insn_byte_t p; int i; switch (opc1) { @@ -758,8 +760,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix. * No one uses these insns, reject any branch insns with such prefix. */ - for (i = 0; i < insn->prefixes.nbytes; i++) { - if (insn->prefixes.bytes[i] == 0x66) + for_each_insn_prefix(insn, i, p) { + if (p == 0x66) return -ENOTSUPP; } diff --git a/tools/objtool/arch/x86/include/asm/insn.h b/tools/objtool/arch/x86/include/asm/insn.h index c2c01f84df75f..3e0e18d376d2c 100644 --- a/tools/objtool/arch/x86/include/asm/insn.h +++ b/tools/objtool/arch/x86/include/asm/insn.h @@ -208,6 +208,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h index 2669c9f748e4d..1a01d0a41ab8e 100644 --- a/tools/perf/util/intel-pt-decoder/insn.h +++ b/tools/perf/util/intel-pt-decoder/insn.h @@ -208,6 +208,21 @@ static inline int insn_offset_immediate(struct insn *insn) return insn_offset_displacement(insn) + insn->displacement.nbytes; } +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @idx: Index storage. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, idx, prefix) \ + for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + #define POP_SS_OPCODE 0x1f #define MOV_SREG_OPCODE 0x8e -- 2.25.1

1 0

[PATCH kernel-4.19] share_pool: Fix memleak of concurrent sp_free and sp_group_add_task
by Yang Yingliang 30 Jun '21

30 Jun '21

From: Tang Yizhou <tangyizhou(a)huawei.com> ascend inclusion category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- We found a concurrency problem of sp_group_add_task and sp_free which lead to memory leak. After process A calls __sp_free and vfs_fallocate but before calling __sp_area_drop, process B is being added to the same group by a manager process, the *dead* spa freed by sp_free may be mapped into process B again, then do_mm_populate is called. When sp_group_add_task is finished, this spa is dropped and can't be seen in /proc/sharepool/spa_stat, but the memory of spa still reside in the group. It can only be freed when the group is dead. To fix the problem, we add a member is_dead in spa. We can access it when spg->rw_lock is held. This may sound a little strange if not realizing the life cycle of spa has a direct relation with sp group. Suggested-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Tang Yizhou <tangyizhou(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huwei.com> Reviewed-by: 为珑陈 <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 37 +++++++++++++++++++++++++------------ 1 file changed, 25 insertions(+), 12 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index 61bbbd772c847..3e4e05f20c5ce 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -233,6 +233,7 @@ struct sp_area { unsigned long region_vstart; /* belong to normal region or DVPP region */ unsigned long flags; bool is_hugepage; + bool is_dead; atomic_t use_count; /* How many vmas use this VA region */ struct rb_node rb_node; /* address sorted rbtree */ struct list_head link; /* link to the spg->head */ @@ -736,6 +737,10 @@ int sp_group_add_task(int pid, int spg_id) prev = spa; atomic_inc(&spa->use_count); + + if (spa->is_dead == true) + continue; + spin_unlock(&sp_area_lock); if (spa->type == SPA_TYPE_K2SPG && spa->kva) { @@ -970,6 +975,7 @@ static struct sp_area *sp_alloc_area(unsigned long size, unsigned long flags, spa->region_vstart = vstart; spa->flags = flags; spa->is_hugepage = (flags & SP_HUGEPAGE); + spa->is_dead = false; spa->spg = spg; atomic_set(&spa->use_count, 1); spa->type = type; @@ -1271,10 +1277,14 @@ int sp_free(unsigned long addr) goto drop_spa; } - if (!spg_valid(spa->spg)) + down_write(&spa->spg->rw_lock); + if (!spg_valid(spa->spg)) { + up_write(&spa->spg->rw_lock); goto drop_spa; - - sp_dump_stack(); + } + /* the life cycle of spa has a direct relation with sp group */ + spa->is_dead = true; + up_write(&spa->spg->rw_lock); down_read(&spa->spg->rw_lock); @@ -1303,6 +1313,7 @@ int sp_free(unsigned long addr) drop_spa: __sp_area_drop(spa); out: + sp_dump_stack(); sp_try_to_compact(); return ret; } @@ -2362,15 +2373,6 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp goto out_drop_area; } - down_read(&spa->spg->rw_lock); - if (!spg_valid(spa->spg)) { - up_read(&spa->spg->rw_lock); - pr_info_ratelimited("share pool: no need to unshare uva(to group), " - "sp group of spa is dead\n"); - goto out_clr_flag; - } - up_read(&spa->spg->rw_lock); - /* alway allow kthread and dvpp channel destroy procedure */ if (current->mm && current->mm->sp_group != spa->spg) { pr_err_ratelimited("share pool: unshare uva(to group) failed, " @@ -2379,6 +2381,17 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp goto out_drop_area; } + down_write(&spa->spg->rw_lock); + if (!spg_valid(spa->spg)) { + up_write(&spa->spg->rw_lock); + pr_info_ratelimited("share pool: no need to unshare uva(to group), " + "sp group of spa is dead\n"); + goto out_clr_flag; + } + /* the life cycle of spa has a direct relation with sp group */ + spa->is_dead = true; + up_write(&spa->spg->rw_lock); + down_read(&spa->spg->rw_lock); __sp_free(spa->spg, uva_aligned, size_aligned, NULL); up_read(&spa->spg->rw_lock); -- 2.25.1

1 0

[PATCH kernel-4.19 01/23] net: hns3: configure promisc mode for VF asynchronously
by Yang Yingliang 30 Jun '21

30 Jun '21

From: Jian Shen <shenjian15(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------- Currently, when host set VF untrusted, the driver will disable the promisc mode of VF. It may be conflicted when the VF requests the host to set promisc mode. So fix it by change promisc mode for VF asynchronously. With this change, the promisc mode of VF can be restored when the VF being trusted again. Fixes: 5c1f0ff21058 ("net: hns3: add support for setting VF trust") Signed-off-by: Jian Shen <shenjian15(a)huawei.com> Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: li yongxin <liyongxin1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- .../hisilicon/hns3/hns3pf/hclge_main.c | 42 +++++++++++++------ .../hisilicon/hns3/hns3pf/hclge_main.h | 6 ++- .../hisilicon/hns3/hns3pf/hclge_mbx.c | 40 ++++-------------- 3 files changed, 42 insertions(+), 46 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index f3d728aa54bf3..23273f08ab50f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -10639,8 +10639,6 @@ static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable) struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; u32 new_trusted = enable ? 1 : 0; - bool en_bc_pmc; - int ret; vport = hclge_get_vf_vport(hdev, vf); if (!vport) @@ -10649,19 +10647,11 @@ static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable) if (vport->vf_info.trusted == new_trusted) return 0; - /* Disable promisc mode for VF if it is not trusted any more. */ - if (!enable && vport->vf_info.promisc_enable) { - en_bc_pmc = hdev->pdev->revision != 0x20; - ret = hclge_set_vport_promisc_mode(vport, false, false, - en_bc_pmc); - if (ret) - return ret; - vport->vf_info.promisc_enable = 0; - hclge_inform_vf_promisc_info(vport); - } - vport->vf_info.trusted = new_trusted; + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state); + hclge_task_schedule(hdev, 0); + return 0; } @@ -11535,6 +11525,7 @@ static void hclge_sync_promisc_mode(struct hclge_dev *hdev) u8 tmp_flags = 0; bool vlan_en; int ret; + int i; if (vport->last_promisc_flags != vport->overflow_promisc_flags) { set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); @@ -11555,6 +11546,31 @@ static void hclge_sync_promisc_mode(struct hclge_dev *hdev) hclge_enable_vlan_filter(handle, vlan_en); } } + + for (i = 1; i < hdev->num_alloc_vport; i++) { + bool uc_en = false; + bool mc_en = false; + bool bc_en; + + vport = &hdev->vport[i]; + + if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, + &vport->state)) + continue; + + if (vport->vf_info.trusted) { + uc_en = vport->vf_info.request_uc_en > 0; + mc_en = vport->vf_info.request_mc_en > 0; + } + bc_en = vport->vf_info.request_bc_en > 0; + + ret = hclge_set_vport_promisc_mode(vport, uc_en, mc_en, bc_en); + if (ret) { + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, + &vport->state); + return; + } + } } static bool hclge_module_existed(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 8e7dff25cbfd5..4a664801fbe92 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -904,6 +904,7 @@ struct hclge_rss_tuple_cfg { enum HCLGE_VPORT_STATE { HCLGE_VPORT_STATE_ALIVE, HCLGE_VPORT_STATE_MAC_TBL_CHANGE, + HCLGE_VPORT_STATE_PROMISC_CHANGE, HCLGE_VPORT_STATE_MAX }; @@ -926,7 +927,9 @@ struct hclge_vf_info { u32 spoofchk; u32 max_tx_rate; u32 trusted; - u16 promisc_enable; + u8 request_uc_en; + u8 request_mc_en; + u8 request_bc_en; }; struct hclge_vport { @@ -1051,7 +1054,6 @@ int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc); void hclge_report_hw_error(struct hclge_dev *hdev, enum hnae3_hw_error_type type); -void hclge_inform_vf_promisc_info(struct hclge_vport *vport); void hclge_dbg_dump_rst_info(struct hclge_dev *hdev); bool hclge_vf_vlan_need_enable(struct hclge_vport *vport); int hclge_push_vf_link_status(struct hclge_vport *vport); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index e998322d59aae..d2bfa5f7f22f1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -321,35 +321,17 @@ static int hclge_get_vf_ring_vector_map(struct hclge_vport *vport, return ret; } -static int hclge_set_vf_promisc_mode(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *req) +static void hclge_set_vf_promisc_mode(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *req) { - bool en_bc = req->msg.en_bc ? true : false; - bool en_uc = req->msg.en_uc ? true : false; - bool en_mc = req->msg.en_mc ? true : false; - int ret; - - if (!vport->vf_info.trusted) { - en_uc = false; - en_mc = false; - } - - ret = hclge_set_vport_promisc_mode(vport, en_uc, en_mc, en_bc); - - vport->vf_info.promisc_enable = (en_uc || en_mc) ? 1 : 0; - - return ret; -} - -void hclge_inform_vf_promisc_info(struct hclge_vport *vport) -{ - u8 dest_vfid = (u8)vport->vport_id; - u8 msg_data[2]; + struct hclge_dev *hdev = vport->back; - memcpy(&msg_data[0], &vport->vf_info.promisc_enable, sizeof(u16)); + vport->vf_info.request_uc_en = req->msg.en_uc; + vport->vf_info.request_mc_en = req->msg.en_mc; + vport->vf_info.request_bc_en = req->msg.en_bc; - hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), - HCLGE_MBX_PUSH_PROMISC_INFO, dest_vfid); + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state); + hclge_task_schedule(hdev, 0); } static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport, @@ -837,11 +819,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev) ret); break; case HCLGE_MBX_SET_PROMISC_MODE: - ret = hclge_set_vf_promisc_mode(vport, req); - if (ret) - dev_err(&hdev->pdev->dev, - "PF fail(%d) to set VF promisc mode\n", - ret); + hclge_set_vf_promisc_mode(vport, req); break; case HCLGE_MBX_SET_UNICAST: ret = hclge_set_vf_uc_mac_addr(vport, req); -- 2.25.1

1 22

[PATCH kernel-4.19 1/2] kabi: update kabi list for arm64
by Yang Yingliang 30 Jun '21

30 Jun '21

hulk inclusion category: other bugzilla: NA CVE: NA --------------------------- It's from https://gitee.com/src-openeuler/kernel/blob/openEuler-20.03-LTS-SP2/kabi_wh… Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kabi/2019-V1/kabi-list.arm64 | 718 ++++++++++++++++++++++++++++++++++- 1 file changed, 713 insertions(+), 5 deletions(-) diff --git a/kabi/2019-V1/kabi-list.arm64 b/kabi/2019-V1/kabi-list.arm64 index af8f6a3085356..e9617085311e4 100644 --- a/kabi/2019-V1/kabi-list.arm64 +++ b/kabi/2019-V1/kabi-list.arm64 @@ -1,13 +1,32 @@ # kabi compatibility list for arm64 +acpi_bus_get_device +acpi_check_dsm acpi_dev_found +acpi_disabled +acpi_dma_configure acpi_evaluate_dsm acpi_evaluate_object +acpi_format_exception +acpi_gbl_FADT +acpi_get_devices +acpi_get_handle +acpi_get_name +acpi_get_table +acpi_gsi_to_irq +acpi_handle_printk +acpi_has_method +acpi_lid_open acpi_match_device __acpi_node_get_property_reference +acpi_os_map_memory acpi_os_unmap_generic_address +acpi_os_unmap_memory +acpi_register_gsi +acpi_unregister_gsi add_timer add_wait_queue add_wait_queue_exclusive +admin_timeout alloc_chrdev_region alloc_cpu_rmap __alloc_disk_node @@ -23,51 +42,73 @@ anon_inode_getfd apei_hest_parse apei_map_generic_address apei_read +__arch_clear_user __arch_copy_from_user +__arch_copy_in_user __arch_copy_to_user +arch_timer_read_counter +arch_wb_cache_pmem arm64_const_caps_ready arp_tbl async_schedule ata_link_next ata_tf_to_fis _atomic_dec_and_lock +atomic_notifier_call_chain atomic_notifier_chain_register atomic_notifier_chain_unregister attribute_container_find_class_device autoremove_wake_function +backlight_device_register +backlight_device_unregister +backlight_force_update bdevname +bdev_read_only bdget_disk +_bin2bcd bin2hex bio_add_page bio_alloc_bioset bio_chain +bio_clone_fast bio_devname bio_endio +bio_free_pages bio_init bio_integrity_add_page bio_integrity_alloc bio_put +bioset_exit +bioset_init __bitmap_and __bitmap_andnot __bitmap_clear +__bitmap_complement __bitmap_equal bitmap_find_free_region bitmap_find_next_zero_area_off bitmap_free __bitmap_intersects +__bitmap_or __bitmap_parse +bitmap_parselist bitmap_print_to_pagebuf bitmap_release_region __bitmap_set __bitmap_weight +__bitmap_xor bitmap_zalloc bit_wait blk_alloc_queue +blk_check_plugged blk_cleanup_queue blkdev_get_by_path __blkdev_issue_discard +blkdev_issue_discard blkdev_issue_flush +blkdev_issue_write_same __blkdev_issue_zeroout +blkdev_issue_zeroout blkdev_put blk_execute_rq blk_execute_rq_nowait @@ -93,6 +134,7 @@ blk_mq_pci_map_queues blk_mq_quiesce_queue blk_mq_rdma_map_queues blk_mq_requeue_request +blk_mq_run_hw_queues blk_mq_start_request blk_mq_tagset_busy_iter blk_mq_tag_to_rq @@ -102,8 +144,10 @@ blk_mq_unquiesce_queue blk_mq_update_nr_hw_queues blk_poll blk_put_queue +blk_put_request blk_queue_bounce_limit blk_queue_chunk_sectors +blk_queue_dma_alignment blk_queue_flag_clear blk_queue_flag_set blk_queue_flag_test_and_set @@ -116,21 +160,29 @@ blk_queue_max_discard_segments blk_queue_max_hw_sectors blk_queue_max_segments blk_queue_max_segment_size +blk_queue_max_write_same_sectors blk_queue_max_write_zeroes_sectors blk_queue_physical_block_size +blk_queue_rq_timeout blk_queue_segment_boundary +blk_queue_split +blk_queue_stack_limits blk_queue_update_dma_alignment blk_queue_virt_boundary blk_queue_write_cache +blk_rq_append_bio blk_rq_count_integrity_sg blk_rq_map_integrity_sg blk_rq_map_kern blk_rq_map_sg blk_rq_map_user +blk_rq_map_user_iov blk_rq_unmap_user blk_set_queue_dying +blk_set_stacking_limits blk_start_plug blk_status_to_errno +blk_verify_command blocking_notifier_call_chain blocking_notifier_chain_register blocking_notifier_chain_unregister @@ -140,6 +192,7 @@ bpf_prog_put bpf_prog_sub bpf_trace_run1 bpf_trace_run2 +bpf_trace_run3 bpf_trace_run5 bpf_warn_invalid_xdp_action bsg_job_done @@ -155,8 +208,10 @@ btree_remove btree_update build_skb bus_find_device +cache_line_size call_netdevice_notifiers call_rcu_sched +call_srcu call_usermodehelper cancel_delayed_work cancel_delayed_work_sync @@ -168,6 +223,8 @@ cdev_device_add cdev_device_del cdev_init cgroup_attach_task_all +__chash_table_copy_in +__chash_table_copy_out __check_object_size __class_create class_destroy @@ -184,13 +241,20 @@ clk_unprepare clk_unregister __close_fd commit_creds +compat_alloc_user_space complete +complete_all complete_and_exit +completion_done +component_add +component_del _cond_resched configfs_register_subsystem configfs_unregister_subsystem config_group_init config_group_init_type_name +console_lock +console_unlock __const_udelay consume_skb _copy_from_iter @@ -217,11 +281,15 @@ cpus_read_unlock crc32c __crc32c_le_shift crc32_le +crc8 +crc8_populate_msb +crc_t10dif crypto_ahash_digest crypto_ahash_final crypto_ahash_setkey crypto_alloc_ahash crypto_alloc_akcipher +crypto_alloc_shash crypto_destroy_tfm crypto_inc __crypto_memneq @@ -230,6 +298,8 @@ crypto_register_alg crypto_register_kpp crypto_register_shash crypto_register_skciphers +crypto_shash_final +crypto_shash_update crypto_unregister_akcipher crypto_unregister_alg crypto_unregister_kpp @@ -243,16 +313,23 @@ dcb_getapp dcb_ieee_delapp dcb_ieee_getapp_mask dcb_ieee_setapp +dcbnl_cee_notify dcb_setapp +debugfs_create_atomic_t debugfs_create_dir debugfs_create_file debugfs_create_regset32 +debugfs_create_symlink +debugfs_create_u16 +debugfs_create_u32 debugfs_create_u64 debugfs_create_u8 debugfs_initialized +debugfs_lookup debugfs_remove -debugfs_remove_recursive +default_llseek default_wake_function +__delay delayed_work_timer_fn del_gendisk del_timer @@ -263,6 +340,7 @@ dev_addr_add dev_addr_del dev_alloc_name dev_attr_phy_event_threshold +dev_base_lock dev_change_flags dev_close dev_disable_lro @@ -275,6 +353,7 @@ dev_get_by_index_rcu __dev_get_by_name dev_get_by_name dev_get_flags +dev_get_iflink dev_get_stats device_add device_add_disk @@ -287,6 +366,7 @@ device_for_each_child device_get_mac_address device_get_next_child_node device_initialize +device_link_add device_property_present device_property_read_string device_property_read_string_array @@ -297,6 +377,7 @@ device_release_driver device_remove_file device_remove_file_self device_reprobe +device_set_wakeup_capable device_set_wakeup_enable device_unregister _dev_info @@ -309,9 +390,11 @@ devlink_param_driverinit_value_set devlink_params_register devlink_params_unregister devlink_param_value_changed +devlink_port_attrs_set devlink_port_register devlink_port_type_clear devlink_port_type_eth_set +devlink_port_type_ib_set devlink_port_unregister devlink_region_create devlink_region_destroy @@ -319,6 +402,9 @@ devlink_region_shapshot_id_get devlink_region_snapshot_create devlink_register devlink_unregister +dev_mc_add +dev_mc_add_excl +dev_mc_del devm_clk_get devm_free_irq devm_hwmon_device_register_with_groups @@ -328,6 +414,7 @@ devm_ioremap_resource devm_iounmap devm_kfree devm_kmalloc +devm_kmemdup devm_mdiobus_alloc_size devm_request_threaded_irq _dev_notice @@ -339,128 +426,370 @@ dev_printk dev_queue_xmit dev_remove_pack dev_set_mac_address +dev_set_mtu dev_set_name dev_set_promiscuity dev_trans_start dev_uc_add +dev_uc_add_excl +dev_uc_del _dev_warn d_find_alias disable_irq disable_irq_nosync dma_alloc_from_dev_coherent +dma_common_get_sgtable dma_common_mmap +dma_fence_add_callback +dma_fence_array_create +dma_fence_context_alloc +dma_fence_free +dma_fence_get_status +dma_fence_init +dma_fence_release +dma_fence_signal +dma_fence_signal_locked +dma_fence_wait_any_timeout +dma_fence_wait_timeout dma_get_required_mask dmam_alloc_coherent +dmam_free_coherent dmam_pool_create dma_pool_alloc dma_pool_create dma_pool_destroy dma_pool_free dma_release_from_dev_coherent +dmi_check_system +dmi_get_system_info dmi_match -do_gettimeofday __do_once_done __do_once_start +do_wait_intr down downgrade_write down_interruptible down_read down_read_trylock +down_timeout down_trylock down_write +down_write_killable down_write_trylock d_path dput dql_completed dql_reset +drain_workqueue +driver_create_file +driver_for_each_device driver_register +driver_remove_file driver_unregister +drm_add_edid_modes drm_add_modes_noedid +drm_atomic_add_affected_connectors +drm_atomic_add_affected_planes +drm_atomic_commit +drm_atomic_get_connector_state drm_atomic_get_crtc_state +drm_atomic_get_plane_state drm_atomic_helper_check +drm_atomic_helper_check_modeset +drm_atomic_helper_check_planes +drm_atomic_helper_check_plane_state +drm_atomic_helper_cleanup_planes drm_atomic_helper_commit +drm_atomic_helper_commit_cleanup_done +drm_atomic_helper_commit_hw_done +__drm_atomic_helper_connector_destroy_state drm_atomic_helper_connector_destroy_state +__drm_atomic_helper_connector_duplicate_state drm_atomic_helper_connector_duplicate_state +__drm_atomic_helper_connector_reset drm_atomic_helper_connector_reset +__drm_atomic_helper_crtc_destroy_state drm_atomic_helper_crtc_destroy_state +__drm_atomic_helper_crtc_duplicate_state drm_atomic_helper_crtc_duplicate_state drm_atomic_helper_crtc_reset drm_atomic_helper_disable_plane +drm_atomic_helper_legacy_gamma_set drm_atomic_helper_page_flip +__drm_atomic_helper_plane_destroy_state drm_atomic_helper_plane_destroy_state +__drm_atomic_helper_plane_duplicate_state drm_atomic_helper_plane_duplicate_state drm_atomic_helper_plane_reset +drm_atomic_helper_prepare_planes drm_atomic_helper_resume drm_atomic_helper_set_config +drm_atomic_helper_setup_commit drm_atomic_helper_shutdown drm_atomic_helper_suspend +drm_atomic_helper_swap_state +drm_atomic_helper_update_legacy_modeset_state drm_atomic_helper_update_plane +drm_atomic_helper_wait_for_dependencies +drm_atomic_helper_wait_for_fences +drm_atomic_helper_wait_for_flip_done +drm_atomic_state_alloc +drm_atomic_state_default_clear +drm_atomic_state_default_release +__drm_atomic_state_free +drm_atomic_state_init +drm_calc_vbltimestamp_from_scanoutpos +drm_color_lut_extract drm_compat_ioctl drm_connector_attach_encoder drm_connector_cleanup drm_connector_init +drm_connector_list_iter_begin +drm_connector_list_iter_end +drm_connector_list_iter_next +drm_connector_register +drm_connector_set_path_property +drm_connector_unregister +drm_connector_update_edid_property +drm_crtc_accurate_vblank_count +drm_crtc_add_crc_entry +drm_crtc_arm_vblank_event drm_crtc_cleanup +__drm_crtc_commit_free +drm_crtc_enable_color_mgmt +drm_crtc_force_disable_all +drm_crtc_from_index +drm_crtc_handle_vblank +drm_crtc_helper_set_config +drm_crtc_helper_set_mode +drm_crtc_init drm_crtc_init_with_planes drm_crtc_send_vblank_event +drm_crtc_vblank_count +drm_crtc_vblank_get drm_crtc_vblank_off drm_crtc_vblank_on +drm_crtc_vblank_put +drm_cvt_mode drm_dbg +drm_debugfs_create_files +drm_detect_hdmi_monitor +drm_detect_monitor_audio drm_dev_alloc +drm_dev_put drm_dev_register drm_dev_unref drm_dev_unregister +drm_dp_atomic_find_vcpi_slots +drm_dp_atomic_release_vcpi_slots +drm_dp_aux_register +drm_dp_aux_unregister +drm_dp_bw_code_to_link_rate +drm_dp_calc_pbn_mode +drm_dp_channel_eq_ok +drm_dp_check_act_status +drm_dp_clock_recovery_ok +drm_dp_dpcd_read +drm_dp_dpcd_read_link_status +drm_dp_dpcd_write +drm_dp_find_vcpi_slots +drm_dp_get_adjust_request_pre_emphasis +drm_dp_get_adjust_request_voltage +drm_dp_link_rate_to_bw_code +drm_dp_link_train_channel_eq_delay +drm_dp_link_train_clock_recovery_delay +drm_dp_mst_allocate_vcpi +drm_dp_mst_deallocate_vcpi +drm_dp_mst_detect_port +drm_dp_mst_get_edid +drm_dp_mst_hpd_irq +drm_dp_mst_reset_vcpi_slots +drm_dp_mst_topology_mgr_destroy +drm_dp_mst_topology_mgr_init +drm_dp_mst_topology_mgr_resume +drm_dp_mst_topology_mgr_set_mst +drm_dp_mst_topology_mgr_suspend +drm_dp_update_payload_part1 +drm_dp_update_payload_part2 +drm_edid_header_is_valid +drm_edid_is_valid +drm_edid_to_sad +drm_edid_to_speaker_allocation drm_encoder_cleanup drm_encoder_init drm_err +drm_fb_helper_add_one_connector drm_fb_helper_alloc_fbi drm_fb_helper_blank +drm_fb_helper_cfb_copyarea +drm_fb_helper_cfb_fillrect +drm_fb_helper_cfb_imageblit drm_fb_helper_check_var +drm_fb_helper_debug_enter +drm_fb_helper_debug_leave drm_fb_helper_fill_fix drm_fb_helper_fill_var drm_fb_helper_fini +drm_fb_helper_hotplug_event drm_fb_helper_init drm_fb_helper_initial_config +drm_fb_helper_ioctl +drm_fb_helper_lastclose +drm_fb_helper_output_poll_changed drm_fb_helper_pan_display drm_fb_helper_prepare +drm_fb_helper_remove_one_connector drm_fb_helper_setcmap drm_fb_helper_set_par +drm_fb_helper_set_suspend +drm_fb_helper_set_suspend_unlocked drm_fb_helper_single_add_all_connectors drm_fb_helper_sys_copyarea drm_fb_helper_sys_fillrect drm_fb_helper_sys_imageblit drm_fb_helper_unregister_fbi +drm_format_plane_cpp drm_framebuffer_cleanup drm_framebuffer_init +drm_framebuffer_unregister_private +drm_gem_dmabuf_kmap +drm_gem_dmabuf_kunmap +drm_gem_dmabuf_mmap +drm_gem_dmabuf_release +drm_gem_dmabuf_vmap +drm_gem_dmabuf_vunmap +drm_gem_fb_create_handle +drm_gem_fb_destroy drm_gem_handle_create +drm_gem_handle_delete +drm_gem_map_attach +drm_gem_map_detach +drm_gem_map_dma_buf drm_gem_object_init drm_gem_object_lookup drm_gem_object_put_unlocked drm_gem_object_release +drm_gem_prime_export +drm_gem_prime_fd_to_handle +drm_gem_prime_handle_to_fd +drm_gem_prime_import +drm_gem_private_object_init +drm_gem_unmap_dma_buf +drm_get_edid +drm_get_edid_switcheroo +drm_get_format_name +drm_get_max_iomem drm_global_item_ref drm_global_item_unref drm_handle_vblank +drm_hdmi_avi_infoframe_from_display_mode +drm_hdmi_vendor_infoframe_from_display_mode +drm_helper_connector_dpms +drm_helper_disable_unused_functions +drm_helper_hpd_irq_event drm_helper_mode_fill_fb_struct drm_helper_probe_single_connector_modes +drm_helper_resume_force_mode +drm_i2c_encoder_detect +drm_i2c_encoder_init +drm_i2c_encoder_mode_fixup +drm_i2c_encoder_restore +drm_i2c_encoder_save +drm_invalid_op drm_ioctl drm_irq_install drm_irq_uninstall +drm_is_current_master +drm_kms_helper_hotplug_event +drm_kms_helper_is_poll_worker drm_kms_helper_poll_disable drm_kms_helper_poll_enable +drm_kms_helper_poll_fini +drm_kms_helper_poll_init +drm_match_cea_mode +drm_mm_init +drm_mm_insert_node_in_range +drm_mm_print +drm_mm_remove_node +drm_mm_takedown drm_mode_config_cleanup drm_mode_config_init drm_mode_config_reset +drm_mode_copy +drm_mode_create_dvi_i_properties +drm_mode_create_scaling_mode_property +drm_mode_create_tv_properties drm_mode_crtc_set_gamma_size +drm_mode_debug_printmodeline +drm_mode_destroy +drm_mode_duplicate +drm_mode_equal +drm_mode_get_hv_timing +drm_mode_is_420_only drm_mode_legacy_fb_format drm_mode_object_find drm_mode_object_put +drm_mode_probed_add +drm_mode_set_crtcinfo +drm_modeset_lock +drm_modeset_lock_all +drm_modeset_lock_all_ctx +drm_mode_set_name +drm_modeset_unlock +drm_modeset_unlock_all +drm_mode_vrefresh +drm_object_attach_property +drm_object_property_set_value drm_open drm_plane_cleanup +drm_plane_create_alpha_property +drm_plane_create_color_properties +drm_plane_create_zpos_immutable_property +drm_plane_create_zpos_property +drm_plane_force_disable +drm_plane_init drm_poll +drm_primary_helper_destroy +drm_primary_helper_funcs +drm_prime_gem_destroy +drm_prime_pages_to_sg +drm_prime_sg_to_page_addr_arrays +drm_printf +__drm_printfn_seq_file +drm_property_add_enum +drm_property_create +drm_property_create_enum +drm_property_create_range +__drm_puts_seq_file drm_read drm_release +drm_scdc_read +drm_scdc_write +drm_sched_dependency_optimized +drm_sched_entity_destroy +drm_sched_entity_fini +drm_sched_entity_flush +drm_sched_entity_init +drm_sched_entity_push_job +drm_sched_entity_set_rq +drm_sched_fini +drm_sched_hw_job_reset +drm_sched_init +drm_sched_job_init +drm_sched_job_recovery +drm_send_event_locked +drm_syncobj_create +drm_syncobj_find +drm_syncobj_find_fence +drm_syncobj_free +drm_syncobj_get_fd +drm_syncobj_get_handle +drm_syncobj_replace_fence drm_universal_plane_init drm_vblank_init +drm_vma_node_allow drm_vma_node_is_allowed +drm_vma_node_revoke dst_init dst_release dummy_dma_ops @@ -469,17 +798,21 @@ __dynamic_dev_dbg __dynamic_netdev_dbg __dynamic_pr_debug elfcorehdr_addr +emergency_restart enable_irq +errno_to_blk_status ether_setup eth_get_headlen eth_mac_addr eth_platform_get_mac_address ethtool_convert_legacy_u32_to_link_mode ethtool_convert_link_mode_to_legacy_u32 +ethtool_intersect_link_masks ethtool_op_get_link ethtool_op_get_ts_info eth_type_trans eth_validate_addr +eventfd_ctx_fdget eventfd_ctx_fileget eventfd_ctx_put eventfd_fget @@ -491,6 +824,7 @@ fc_block_scsi_eh fc_eh_timed_out fc_get_event_number fc_host_post_event +fc_host_post_vendor_event fc_release_transport fc_remote_port_add fc_remote_port_delete @@ -503,12 +837,15 @@ fget filemap_fault filp_close filp_open +find_get_pid find_last_bit find_next_bit find_next_zero_bit find_pid_ns find_vma finish_wait +firmware_request_nowarn +fixed_size_llseek flex_array_alloc flex_array_free flex_array_get @@ -522,6 +859,7 @@ flush_workqueue force_sig fortify_panic fput +free_fib_info free_irq free_irq_cpu_rmap free_netdev @@ -537,30 +875,49 @@ __f_setown fwnode_property_read_string fwnode_property_read_u32_array fwnode_property_read_u8_array +gcd +generate_random_uuid +generic_end_io_acct generic_file_llseek +generic_handle_irq +generic_make_request +generic_start_io_acct genlmsg_put genl_notify genl_register_family genl_unregister_family genphy_read_status genphy_restart_aneg +gen_pool_add_virt +gen_pool_alloc +gen_pool_create +gen_pool_destroy +gen_pool_free +gen_pool_virt_to_phys get_cpu_idle_time_us get_cpu_iowait_time_us get_device __get_free_pages +get_gendisk get_phy_device +get_pid_task get_random_bytes -get_seconds +__get_task_comm get_task_mm +get_unused_fd_flags get_user_pages get_user_pages_fast get_user_pages_remote get_zeroed_page +gic_pmr_sync gre_add_protocol gre_del_protocol groups_alloc groups_free guid_parse +handle_simple_irq +hdmi_avi_infoframe_pack +hdmi_infoframe_pack hest_disable hex_to_bin hrtimer_cancel @@ -570,50 +927,104 @@ hrtimer_start_range_ns hrtimer_try_to_cancel __hw_addr_sync_dev __hw_addr_unsync_dev +hwmon_device_register +hwmon_device_register_with_groups +hwmon_device_register_with_info +hwmon_device_unregister +i2c_add_adapter i2c_add_numbered_adapter +i2c_bit_add_bus +i2c_bit_algo i2c_del_adapter i2c_generic_scl_recovery +i2c_new_device i2c_recover_bus +i2c_smbus_read_byte_data +i2c_smbus_write_byte_data +i2c_transfer +i2c_unregister_device __ib_alloc_cq ib_alloc_device +ib_alloc_odp_umem __ib_alloc_pd +__ib_alloc_xrcd __ib_create_cq +ib_create_qp +ib_create_send_mad ib_create_srq ib_dealloc_device ib_dealloc_pd +ib_dereg_mr ib_destroy_cq ib_destroy_qp ib_destroy_srq ib_dispatch_event ib_drain_qp ib_event_msg +ib_find_cached_pkey ib_free_cq +ib_free_send_mad +ib_get_cached_pkey +ib_get_eth_speed +ib_get_gids_from_rdma_hdr +ib_get_rdma_header_version ib_map_mr_sg +ib_modify_qp ib_modify_qp_is_ok ib_mr_pool_destroy ib_mr_pool_get ib_mr_pool_init ib_mr_pool_put +ib_post_send_mad +ib_process_cq_direct +ib_query_pkey ib_query_port +ib_query_qp ib_register_client ib_register_device +ib_register_mad_agent +ib_sa_cancel_query +ib_sa_guid_info_rec_query +ib_sa_register_client +ib_sa_unregister_client ib_sg_to_pages +ib_ud_header_init +ib_ud_header_pack +ib_ud_ip4_csum +ib_umem_copy_from ib_umem_get +ib_umem_odp_map_dma_pages +ib_umem_odp_unmap_dma_pages ib_umem_page_count ib_umem_release ib_unregister_client ib_unregister_device +ib_unregister_mad_agent +ib_uverbs_get_ucontext ib_wc_status_msg ida_alloc_range ida_destroy ida_free +idr_alloc +idr_alloc_cyclic +idr_alloc_u32 +idr_destroy +idr_find +idr_for_each +idr_get_next +idr_get_next_ul +idr_preload +idr_remove +idr_replace in4_pton in6_pton in_aton in_dev_finish_destroy in_egroup_p +__inet6_lookup_established inet_addr_is_any inet_get_local_port_range +__inet_lookup_established inet_proto_csum_replace16 inet_proto_csum_replace4 inet_pton_with_scope @@ -632,6 +1043,10 @@ input_register_handle input_register_handler input_unregister_handle input_unregister_handler +interval_tree_insert +interval_tree_iter_first +interval_tree_iter_next +interval_tree_remove int_to_scsilun invalidate_partition iomem_resource @@ -639,6 +1054,9 @@ iommu_get_domain_for_dev iommu_group_get iommu_group_id iommu_group_put +iommu_iova_to_phys +iommu_map +iommu_unmap __ioremap ioremap_cache io_schedule @@ -648,15 +1066,20 @@ iov_iter_advance iov_iter_bvec iov_iter_init iov_iter_npages +__iowrite32_copy __iowrite64_copy ip6_dst_hoplimit ip6_local_out +ip6_route_output_flags +ip_compute_csum ip_defrag +__ip_dev_find ip_do_fragment ip_local_out ipmi_create_user ipmi_destroy_user -ipmi_register_smi +ipmi_free_recv_msg +ipmi_poll_interface ipmi_request_settime ipmi_set_gets_events ipmi_set_my_address @@ -668,17 +1091,30 @@ __ip_select_ident ip_send_check ip_set_get_byname ip_set_put_byindex +ip_tos2prio ip_tunnel_get_stats64 iput __ipv6_addr_type +ipv6_chk_addr ipv6_ext_hdr ipv6_find_hdr ipv6_skip_exthdr ipv6_stub ip_vs_proto_name irq_cpu_rmap_add +irq_create_mapping +__irq_domain_add +irq_domain_remove +irq_find_mapping +irq_get_irq_data +irq_poll_complete +irq_poll_disable +irq_poll_enable +irq_poll_init +irq_poll_sched irq_set_affinity_hint irq_set_affinity_notifier +irq_set_chip_and_handler_name irq_to_desc is_acpi_data_node is_acpi_device_node @@ -743,6 +1179,8 @@ kasprintf kernel_bind kernel_connect kernel_cpustat +kernel_recvmsg +kernel_sendmsg kernel_setsockopt kernel_sock_shutdown kernel_write @@ -754,6 +1192,8 @@ kfree_const kfree_skb kfree_skb_list kfree_skb_partial +kgdb_active +kgdb_breakpoint kill_fasync kimage_voffset __kmalloc @@ -773,10 +1213,12 @@ kmemdup kobject_add kobject_create_and_add kobject_del +kobject_get kobject_init kobject_init_and_add kobject_put kobject_set_name +kobject_uevent kobject_uevent_env krealloc kset_create_and_add @@ -785,6 +1227,7 @@ kset_register kset_unregister ksize kstrdup +kstrdup_const kstrndup kstrtobool kstrtobool_from_user @@ -800,10 +1243,13 @@ kstrtoull kstrtoull_from_user kthread_bind kthread_create_on_node +kthread_park kthread_should_stop kthread_stop +kthread_unpark ktime_get ktime_get_coarse_real_ts64 +ktime_get_raw ktime_get_raw_ts64 ktime_get_real_seconds ktime_get_real_ts64 @@ -815,15 +1261,22 @@ kvfree kvmalloc_node kzfree lcm +led_classdev_resume +led_classdev_suspend +led_classdev_unregister __list_add_valid __list_del_entry_valid list_sort +llist_add_batch __ll_sc_atomic64_add +__ll_sc_atomic64_add_return __ll_sc_atomic64_andnot +__ll_sc_atomic64_fetch_add __ll_sc_atomic64_fetch_andnot __ll_sc_atomic64_fetch_andnot_release __ll_sc_atomic64_fetch_or __ll_sc_atomic64_fetch_or_acquire +__ll_sc_atomic64_fetch_xor __ll_sc_atomic64_or __ll_sc_atomic64_sub __ll_sc_atomic64_sub_return @@ -839,6 +1292,7 @@ __ll_sc___cmpxchg_case_mb_8 __local_bh_enable_ip __lock_page lock_page_memcg +lockref_get lock_sock_nested logic_inw logic_outw @@ -849,6 +1303,7 @@ mark_page_accessed match_hex match_int match_strdup +match_string match_token match_u64 _mcount @@ -857,9 +1312,13 @@ mdev_from_dev mdev_get_drvdata mdev_parent_dev mdev_register_device +mdev_register_driver mdev_set_drvdata mdev_unregister_device +mdev_unregister_driver mdio45_probe +mdiobus_alloc_size +mdiobus_free mdiobus_get_phy mdiobus_read __mdiobus_register @@ -889,15 +1348,17 @@ mempool_kmalloc memscan mem_section memset +__memset_io memstart_addr memzero_explicit +metadata_dst_alloc misc_deregister misc_register -mlxfw_firmware_flash mmput __mmu_notifier_register mmu_notifier_register mmu_notifier_unregister +mmu_notifier_unregister_no_release mod_delayed_work_on mod_timer mod_timer_pending @@ -932,15 +1393,21 @@ __ndelay ndo_dflt_bridge_getlink ndo_dflt_fdb_add __neigh_create +neigh_destroy +__neigh_event_send +neigh_lookup +netdev_alloc_frag __netdev_alloc_skb netdev_bind_sb_channel_queue netdev_crit netdev_err netdev_features_change netdev_info +netdev_lower_get_next netdev_master_upper_dev_get netdev_master_upper_dev_get_rcu netdev_master_upper_dev_link +netdev_notice netdev_printk netdev_reset_tc netdev_rss_key_fill @@ -959,6 +1426,7 @@ netif_carrier_off netif_carrier_on netif_device_attach netif_device_detach +netif_get_num_default_rss_queues netif_napi_add netif_napi_del netif_receive_skb @@ -970,6 +1438,7 @@ netif_set_real_num_tx_queues netif_set_xps_queue netif_tx_stop_all_queues netif_tx_wake_queue +netlink_ack netlink_broadcast __netlink_dump_start netlink_has_listeners @@ -1066,12 +1535,53 @@ nr_irqs nr_node_ids ns_capable nsecs_to_jiffies +ns_to_timespec ns_to_timespec64 ns_to_timeval numa_node +nvme_alloc_request +nvme_cancel_request +nvme_change_ctrl_state +nvme_cleanup_cmd +nvme_complete_async_event +nvme_complete_rq +nvme_disable_ctrl +nvme_enable_ctrl +nvme_fc_register_localport +nvme_fc_register_remoteport +nvme_fc_set_remoteport_devloss +nvme_fc_unregister_localport +nvme_fc_unregister_remoteport +nvme_init_ctrl +nvme_init_identify +nvme_io_timeout +nvme_kill_queues +nvme_remove_namespaces +nvme_reset_ctrl +nvme_reset_ctrl_sync +nvme_set_queue_count +nvme_setup_cmd +nvme_shutdown_ctrl +nvme_start_ctrl +nvme_start_freeze +nvme_start_queues +nvme_stop_ctrl +nvme_stop_queues +nvme_submit_sync_cmd +nvmet_fc_rcv_fcp_abort +nvmet_fc_rcv_fcp_req +nvmet_fc_rcv_ls_req +nvmet_fc_register_targetport +nvmet_fc_unregister_targetport +nvme_unfreeze +nvme_uninit_ctrl +nvme_wait_freeze +nvme_wait_freeze_timeout +nvme_wq of_device_is_compatible of_find_device_by_node of_fwnode_ops +of_led_classdev_register of_match_node of_mdiobus_register of_node_put @@ -1079,6 +1589,7 @@ of_parse_phandle of_parse_phandle_with_fixed_args of_phy_find_device on_each_cpu +orderly_poweroff out_of_line_wait_on_bit override_creds __page_file_index @@ -1113,14 +1624,23 @@ param_set_int path_get path_put pci_alloc_irq_vectors_affinity +pci_assign_unassigned_bus_resources pcibios_resource_to_bus +pci_bus_read_config_dword +pci_bus_resource_n pci_bus_type +pci_cfg_access_lock +pci_cfg_access_unlock +pci_check_and_mask_intx pci_choose_state pci_cleanup_aer_uncorrect_error_status pci_clear_master pci_clear_mwi +pci_d3cold_disable +pci_dev_driver pci_dev_get pci_device_is_present +pci_dev_present pci_dev_put pci_disable_device pci_disable_link_state @@ -1130,43 +1650,64 @@ pci_disable_pcie_error_reporting pci_disable_rom pci_disable_sriov pcie_bandwidth_available +pcie_capability_clear_and_set_word pcie_capability_read_dword pcie_capability_read_word pcie_capability_write_word pcie_flr +pcie_get_speed_cap +pcie_get_width_cap +pci_enable_atomic_ops_to_root pci_enable_device pci_enable_device_mem pci_enable_msi pci_enable_msix_range pci_enable_pcie_error_reporting +pci_enable_rom pci_enable_sriov pci_enable_wake pcie_print_link_status +pcie_relaxed_ordering_enabled pcie_set_readrq pci_find_capability pci_find_ext_capability pci_free_irq pci_free_irq_vectors +pci_get_class pci_get_device pci_get_domain_bus_and_slot +pci_get_slot +pci_ignore_hotplug +pci_intx pci_iomap pci_ioremap_bar pci_irq_get_affinity pci_irq_vector +pci_map_rom pci_match_id +pcim_enable_device pcim_iomap +pcim_iomap_regions +pcim_iomap_table pcim_iounmap +pci_msi_mask_irq +pci_msi_unmask_irq pci_num_vf +pci_platform_rom pci_prepare_to_sleep pci_read_config_byte pci_read_config_dword pci_read_config_word +pci_read_vpd __pci_register_driver pci_release_regions +pci_release_resource pci_release_selected_regions pci_request_irq pci_request_regions pci_request_selected_regions +pci_rescan_bus +pci_resize_resource pci_restore_state pci_save_state pci_select_bars @@ -1176,10 +1717,15 @@ pci_set_power_state pci_sriov_configure_simple pci_sriov_get_totalvfs pci_sriov_set_totalvfs +pci_stop_and_remove_bus_device pci_stop_and_remove_bus_device_locked pci_try_set_mwi +pci_unmap_rom pci_unregister_driver pci_vfs_assigned +pci_vpd_find_info_keyword +pci_vpd_find_tag +pci_wait_for_pending_transaction pci_wake_from_d3 pci_write_config_byte pci_write_config_dword @@ -1194,6 +1740,8 @@ perf_trace_buf_alloc perf_trace_run_bpf_submit pfn_valid phy_attach_direct +phy_attached_info +phy_connect phy_connect_direct phy_device_free phy_device_register @@ -1209,6 +1757,7 @@ phy_start_aneg phy_stop phy_suspend pid_task +pid_vnr platform_bus_type platform_device_register platform_device_register_full @@ -1218,6 +1767,8 @@ platform_driver_unregister platform_get_irq platform_get_resource platform_get_resource_byname +pm_power_off +pm_runtime_allow __pm_runtime_disable pm_runtime_enable pm_runtime_forbid @@ -1225,7 +1776,11 @@ __pm_runtime_idle __pm_runtime_resume pm_runtime_set_autosuspend_delay __pm_runtime_set_status +__pm_runtime_suspend __pm_runtime_use_autosuspend +pm_schedule_suspend +power_supply_is_system_supplied +prandom_bytes prandom_u32 prepare_creds prepare_to_wait @@ -1258,6 +1813,8 @@ __put_net __put_page __put_task_struct put_unused_fd +qed_get_eth_ops +qed_put_eth_ops queue_delayed_work_on queued_read_lock_slowpath queued_spin_lock_slowpath @@ -1271,6 +1828,7 @@ radix_tree_lookup radix_tree_next_chunk __radix_tree_next_slot radix_tree_preload +radix_tree_tagged radix_tree_tag_set raid_class_attach raid_class_release @@ -1279,28 +1837,46 @@ raw_notifier_call_chain raw_notifier_chain_register raw_notifier_chain_unregister rb_erase +__rb_erase_color rb_first +rb_first_postorder +__rb_insert_augmented rb_insert_color rb_next +rb_next_postorder +rb_replace_node +rbt_ib_umem_for_each_in_range +rbt_ib_umem_lookup rcu_barrier __rdma_accept rdma_bind_addr rdma_connect rdma_consumer_reject_data +rdma_copy_ah_attr +rdma_create_ah __rdma_create_id rdma_create_qp +rdma_destroy_ah +rdma_destroy_ah_attr rdma_destroy_id rdma_destroy_qp rdma_disconnect rdma_event_msg +rdma_is_zero_gid rdma_listen rdma_nl_put_driver_u32 rdma_nl_put_driver_u64 rdma_notify +rdma_port_get_link_layer +rdma_query_ah +rdma_query_gid rdma_reject rdma_reject_msg rdma_resolve_addr rdma_resolve_route +rdma_restrack_get +rdma_restrack_put +rdma_roce_rescan_device rdma_rw_ctx_destroy rdma_rw_ctx_init rdma_rw_ctx_post @@ -1308,23 +1884,29 @@ rdma_rw_ctx_wrs rdma_set_afonly read_cache_pages recalc_sigpending +refcount_dec_and_mutex_lock refcount_dec_and_test_checked refcount_dec_checked refcount_dec_if_one refcount_inc_checked refcount_inc_not_zero_checked register_acpi_hed_notifier +register_acpi_notifier register_blkdev __register_chrdev register_chrdev_region register_console register_die_notifier +register_fib_notifier +register_inet6addr_notifier +register_inetaddr_notifier register_ip_vs_scheduler register_kprobe register_module_notifier register_netdev register_netdevice register_netdevice_notifier +register_netevent_notifier register_oom_notifier register_pernet_device register_pernet_subsys @@ -1333,16 +1915,25 @@ register_sysctl_table regmap_read regmap_write release_firmware +release_pages __release_region release_sock remap_pfn_range +remove_conflicting_framebuffers remove_proc_entry remove_wait_queue request_firmware request_firmware_direct +request_firmware_nowait __request_module __request_region request_threaded_irq +reservation_object_add_excl_fence +reservation_object_add_shared_fence +reservation_object_get_fences_rcu +reservation_object_reserve_shared +reservation_object_wait_timeout_rcu +reservation_ww_class reset_devices revalidate_disk revert_creds @@ -1350,6 +1941,11 @@ rhashtable_destroy rhashtable_free_and_destroy rhashtable_init rhashtable_insert_slow +rhashtable_walk_enter +rhashtable_walk_exit +rhashtable_walk_next +rhashtable_walk_start_check +rhashtable_walk_stop rhltable_init rht_bucket_nested rht_bucket_nested_insert @@ -1397,6 +1993,7 @@ sas_port_add_phy sas_port_alloc_num sas_port_delete sas_port_delete_phy +sas_port_free sas_prep_resume_ha sas_queuecommand sas_read_port_mode_page @@ -1411,11 +2008,15 @@ sas_suspend_ha sas_target_alloc sas_target_destroy sas_unregister_ha +save_stack_trace save_stack_trace_tsk sbitmap_queue_clear __sbitmap_queue_get scatterwalk_map_and_copy +sched_clock +sched_setscheduler schedule +schedule_hrtimeout schedule_hrtimeout_range schedule_timeout schedule_timeout_interruptible @@ -1429,15 +2030,19 @@ scsi_build_sense_buffer scsi_change_queue_depth scsi_cmd_get_serial scsi_command_normalize_sense +scsi_device_get scsi_device_lookup scsi_device_put scsi_device_set_state +scsi_device_type scsi_dma_map scsi_dma_unmap +__scsi_execute scsi_get_vpd_page scsi_host_alloc scsi_host_busy scsi_host_get +scsi_host_lookup scsi_host_put scsi_internal_device_block_nowait scsi_internal_device_unblock_nowait @@ -1446,17 +2051,23 @@ scsi_is_host_device scsi_is_sdev_device __scsi_iterate_devices scsilun_to_int +scsi_normalize_sense scsi_print_command scsi_queue_work +scsi_register_driver scsi_remove_device scsi_remove_host scsi_remove_target +scsi_sanitize_inquiry_string scsi_scan_host scsi_sense_key_string scsi_unblock_requests sdev_prefix_printk __secpath_destroy secpath_dup +secure_tcp_seq +secure_tcpv6_seq +security_d_instantiate security_release_secctx security_secid_to_secctx security_tun_dev_alloc_security @@ -1469,11 +2080,14 @@ send_sig seq_list_next seq_list_start seq_lseek +seq_open seq_printf seq_putc seq_put_decimal_ull seq_puts seq_read +seq_release +seq_write set_cpus_allowed_ptr set_current_groups set_device_ro @@ -1484,12 +2098,17 @@ set_page_dirty set_page_dirty_lock set_user_nice sg_alloc_table_chained +sg_alloc_table_from_pages sg_copy_from_buffer sg_copy_to_buffer +sg_free_table sg_free_table_chained sg_init_table sgl_alloc sgl_free +sg_miter_next +sg_miter_start +sg_miter_stop sg_nents sg_next __sg_page_iter_next @@ -1499,6 +2118,10 @@ sg_pcopy_to_buffer sg_zero_buffer sigprocmask si_meminfo +simple_attr_open +simple_attr_read +simple_attr_release +simple_attr_write simple_open simple_read_from_buffer simple_strtol @@ -1527,6 +2150,7 @@ skb_ensure_writable __skb_flow_dissect __skb_get_hash __skb_gso_segment +skb_gso_validate_mac_len __skb_pad skb_partial_csum_set skb_pull @@ -1539,6 +2163,7 @@ skb_realloc_headroom __skb_recv_datagram skb_scrub_packet skb_set_owner_w +skb_store_bits skb_trim skb_try_coalesce skb_tstamp_tx @@ -1559,14 +2184,18 @@ snprintf sock_alloc_send_pskb sock_create sock_create_kern +sock_edemux sockfd_lookup sock_init_data +sock_queue_err_skb sock_recv_errqueue sock_release sock_zerocopy_callback +softnet_data sort sprintf sprint_symbol +srcu_barrier __srcu_read_lock __srcu_read_unlock sscanf @@ -1596,8 +2225,13 @@ strsep strspn strstr submit_bio +__sw_hweight32 __sw_hweight64 __sw_hweight8 +swiotlb_nr_tbl +switchdev_port_same_parent_id +__symbol_put +sync_file_create synchronize_irq synchronize_net synchronize_rcu_bh @@ -1618,6 +2252,7 @@ sysfs_remove_group sysfs_remove_link sysfs_streq system_state +system_unbound_wq system_wq sys_tz t10_pi_complete @@ -1625,15 +2260,24 @@ t10_pi_prepare t10_pi_type1_crc t10_pi_type3_crc tap_get_socket +task_active_pid_ns tasklet_init tasklet_kill __tasklet_schedule __task_pid_nr_ns tcf_block_cb_register tcf_block_cb_unregister +tcp_gro_complete +tcp_hashinfo +tc_setup_cb_egdev_register +tc_setup_cb_egdev_unregister +time64_to_tm timecounter_cyc2time timecounter_init timecounter_read +tls_get_record +tls_validate_xmit_skb +to_drm_sched_fence totalram_pages trace_define_field trace_event_buffer_commit @@ -1642,7 +2286,9 @@ trace_event_ignore_this_pid trace_event_raw_init trace_event_reg trace_handle_return +__tracepoint_dma_fence_emit __tracepoint_xdp_exception +trace_print_array_seq trace_print_flags_seq trace_print_symbols_seq trace_raw_output_prep @@ -1651,38 +2297,75 @@ trace_seq_putc try_module_get try_wait_for_completion ttm_bo_add_to_lru +ttm_bo_clean_mm ttm_bo_del_sub_from_lru ttm_bo_device_init ttm_bo_device_release ttm_bo_dma_acc_size +ttm_bo_eviction_valuable +ttm_bo_evict_mm ttm_bo_global_init ttm_bo_global_release ttm_bo_init ttm_bo_init_mm +ttm_bo_init_reserved ttm_bo_kmap ttm_bo_kunmap +ttm_bo_lock_delayed_workqueue ttm_bo_manager_func +ttm_bo_mem_put +ttm_bo_mem_space ttm_bo_mmap +ttm_bo_move_accel_cleanup +ttm_bo_move_memcpy +ttm_bo_move_to_lru_tail +ttm_bo_move_ttm +ttm_bo_pipeline_move +ttm_bo_put +ttm_bo_unlock_delayed_workqueue ttm_bo_unref ttm_bo_validate +ttm_bo_wait +ttm_dma_page_alloc_debugfs +ttm_dma_populate +ttm_dma_tt_fini +ttm_dma_tt_init +ttm_dma_unpopulate +ttm_eu_backoff_reservation +ttm_eu_fence_buffer_objects +ttm_eu_reserve_buffers +ttm_fbdev_mmap ttm_mem_global_init ttm_mem_global_release +ttm_page_alloc_debugfs +ttm_pool_populate +ttm_pool_unpopulate +ttm_populate_and_map_pages +ttm_sg_tt_init +ttm_tt_bind ttm_tt_fini ttm_tt_init +ttm_tt_set_placement_caching +ttm_unmap_and_unpopulate_pages __udelay udp4_hwcsum udp_encap_enable +uio_event_notify __uio_register_device uio_unregister_device unlock_page unlock_page_memcg unmap_mapping_range unregister_acpi_hed_notifier +unregister_acpi_notifier unregister_blkdev __unregister_chrdev unregister_chrdev_region unregister_console unregister_die_notifier +unregister_fib_notifier +unregister_inet6addr_notifier +unregister_inetaddr_notifier unregister_ip_vs_scheduler unregister_kprobe unregister_module_notifier @@ -1690,6 +2373,7 @@ unregister_netdev unregister_netdevice_many unregister_netdevice_notifier unregister_netdevice_queue +unregister_netevent_notifier unregister_oom_notifier unregister_pernet_device unregister_pernet_subsys @@ -1705,6 +2389,13 @@ usleep_range uuid_gen uuid_null uuid_parse +_uverbs_alloc +uverbs_copy_to +uverbs_destroy_def_handler +uverbs_fd_class +uverbs_get_flags32 +uverbs_get_flags64 +uverbs_idr_class vfio_register_iommu_driver vfio_unregister_iommu_driver vfree @@ -1712,13 +2403,16 @@ vfs_fallocate vfs_fsync vfs_getattr vfs_statfs +vga_client_register vlan_dev_real_dev vlan_dev_vlan_id +vlan_dev_vlan_proto vmalloc __vmalloc vmalloc_node vmalloc_to_page vmap +vm_insert_page vm_mmap vm_munmap vm_zone_stat @@ -1730,27 +2424,41 @@ vunmap vzalloc vzalloc_node wait_for_completion +wait_for_completion_interruptible wait_for_completion_interruptible_timeout wait_for_completion_io_timeout +wait_for_completion_killable wait_for_completion_timeout wait_on_page_bit __wake_up wake_up_bit +__wake_up_locked wake_up_process __wake_up_sync_key __warn_printk +work_busy write_cache_pages +ww_mutex_lock ww_mutex_lock_interruptible ww_mutex_unlock xdp_do_flush_map xdp_do_redirect xdp_return_frame xdp_return_frame_rx_napi +xdp_rxq_info_is_reg xdp_rxq_info_reg xdp_rxq_info_reg_mem_model xdp_rxq_info_unreg xdp_rxq_info_unused +xfrm_replay_seqhi +xz_dec_end +xz_dec_init +xz_dec_run yield zap_vma_ptes zerocopy_sg_from_iter zgid +zlib_inflate +zlib_inflateEnd +zlib_inflateInit2 +zlib_inflate_workspacesize -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 001/149] iommu/vt-d: Duplicate iommu_resv_region objects per device list
by Yang Yingliang 30 Jun '21

30 Jun '21

From: Eric Auger <eric.auger(a)redhat.com> [ Upstream commit 5f64ce5411b467f1cfea6c63e2494c22b773582b ] intel_iommu_get_resv_regions() aims to return the list of reserved regions accessible by a given @device. However several devices can access the same reserved memory region and when building the list it is not safe to use a single iommu_resv_region object, whose container is the RMRR. This iommu_resv_region must be duplicated per device reserved region list. Let's remove the struct iommu_resv_region from the RMRR unit and allocate the iommu_resv_region directly in intel_iommu_get_resv_regions(). We hold the dmar_global_lock instead of the rcu-lock to allow sleeping. Fixes: 0659b8dc45a6 ("iommu/vt-d: Implement reserved region get/put callbacks") Signed-off-by: Eric Auger <eric.auger(a)redhat.com> Reviewed-by: Lu Baolu <baolu.lu(a)linux.intel.com> Signed-off-by: Joerg Roedel <jroedel(a)suse.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/intel-iommu.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index d62fb1c31749b..58614c469db4f 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -387,7 +387,6 @@ struct dmar_rmrr_unit { u64 end_address; /* reserved end address */ struct dmar_dev_scope *devices; /* target devices */ int devices_cnt; /* target device count */ - struct iommu_resv_region *resv; /* reserved region handle */ }; struct dmar_atsr_unit { @@ -4214,7 +4213,6 @@ static inline void init_iommu_pm_ops(void) {} int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg) { struct acpi_dmar_reserved_memory *rmrr; - int prot = DMA_PTE_READ|DMA_PTE_WRITE; struct dmar_rmrr_unit *rmrru; size_t length; @@ -4228,22 +4226,16 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg) rmrru->end_address = rmrr->end_address; length = rmrr->end_address - rmrr->base_address + 1; - rmrru->resv = iommu_alloc_resv_region(rmrr->base_address, length, prot, - IOMMU_RESV_DIRECT); - if (!rmrru->resv) - goto free_rmrru; rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1), ((void *)rmrr) + rmrr->header.length, &rmrru->devices_cnt); if (rmrru->devices_cnt && rmrru->devices == NULL) - goto free_all; + goto free_rmrru; list_add(&rmrru->list, &dmar_rmrr_units); return 0; -free_all: - kfree(rmrru->resv); free_rmrru: kfree(rmrru); out: @@ -4461,7 +4453,6 @@ static void intel_iommu_free_dmars(void) list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) { list_del(&rmrru->list); dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt); - kfree(rmrru->resv); kfree(rmrru); } @@ -5258,22 +5249,33 @@ static void intel_iommu_remove_device(struct device *dev) static void intel_iommu_get_resv_regions(struct device *device, struct list_head *head) { + int prot = DMA_PTE_READ | DMA_PTE_WRITE; struct iommu_resv_region *reg; struct dmar_rmrr_unit *rmrr; struct device *i_dev; int i; - rcu_read_lock(); + down_read(&dmar_global_lock); for_each_rmrr_units(rmrr) { for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt, i, i_dev) { + struct iommu_resv_region *resv; + size_t length; + if (i_dev != device) continue; - list_add_tail(&rmrr->resv->list, head); + length = rmrr->end_address - rmrr->base_address + 1; + resv = iommu_alloc_resv_region(rmrr->base_address, + length, prot, + IOMMU_RESV_DIRECT); + if (!resv) + break; + + list_add_tail(&resv->list, head); } } - rcu_read_unlock(); + up_read(&dmar_global_lock); reg = iommu_alloc_resv_region(IOAPIC_RANGE_START, IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1, @@ -5288,10 +5290,8 @@ static void intel_iommu_put_resv_regions(struct device *dev, { struct iommu_resv_region *entry, *next; - list_for_each_entry_safe(entry, next, head, list) { - if (entry->type == IOMMU_RESV_MSI) - kfree(entry); - } + list_for_each_entry_safe(entry, next, head, list) + kfree(entry); } #ifdef CONFIG_INTEL_IOMMU_SVM -- 2.25.1

1 148

[PATCH openEuler-1.0-LTS 01/27] mm, oom: reorganize the oom report in dump_header
by Yang Yingliang 30 Jun '21

30 Jun '21

From: yuzhoujian <yuzhoujian(a)didichuxing.com> mainline inclusion from mainline-5.0-rc1 commit ef8444ea01d7442652f8e1b8a8b94278cb57eafd category: bugfix bugzilla: 51815, https://gitee.com/openeuler/kernel/issues/I3IJ9I CVE: NA ------------------------------------------------- OOM report contains several sections. The first one is the allocation context that has triggered the OOM. Then we have cpuset context followed by the stack trace of the OOM path. The tird one is the OOM memory information. Followed by the current memory state of all system tasks. At last, we will show oom eligible tasks and the information about the chosen oom victim. One thing that makes parsing more awkward than necessary is that we do not have a single and easily parsable line about the oom context. This patch is reorganizing the oom report to 1) who invoked oom and what was the allocation request [ 515.902945] tuned invoked oom-killer: gfp_mask=0x6200ca(GFP_HIGHUSER_MOVABLE), order=0, oom_score_adj=0 2) OOM stack trace [ 515.904273] CPU: 24 PID: 1809 Comm: tuned Not tainted 4.20.0-rc3+ #3 [ 515.905518] Hardware name: Inspur SA5212M4/YZMB-00370-107, BIOS 4.1.10 11/14/2016 [ 515.906821] Call Trace: [ 515.908062] dump_stack+0x5a/0x73 [ 515.909311] dump_header+0x55/0x28c [ 515.914260] oom_kill_process+0x2d8/0x300 [ 515.916708] out_of_memory+0x145/0x4a0 [ 515.917932] __alloc_pages_slowpath+0x7d2/0xa16 [ 515.919157] __alloc_pages_nodemask+0x277/0x290 [ 515.920367] filemap_fault+0x3d0/0x6c0 [ 515.921529] ? filemap_map_pages+0x2b8/0x420 [ 515.922709] ext4_filemap_fault+0x2c/0x40 [ext4] [ 515.923884] __do_fault+0x20/0x80 [ 515.925032] __handle_mm_fault+0xbc0/0xe80 [ 515.926195] handle_mm_fault+0xfa/0x210 [ 515.927357] __do_page_fault+0x233/0x4c0 [ 515.928506] do_page_fault+0x32/0x140 [ 515.929646] ? page_fault+0x8/0x30 [ 515.930770] page_fault+0x1e/0x30 3) OOM memory information [ 515.958093] Mem-Info: [ 515.959647] active_anon:26501758 inactive_anon:1179809 isolated_anon:0 active_file:4402672 inactive_file:483963 isolated_file:1344 unevictable:0 dirty:4886753 writeback:0 unstable:0 slab_reclaimable:148442 slab_unreclaimable:18741 mapped:1347 shmem:1347 pagetables:58669 bounce:0 free:88663 free_pcp:0 free_cma:0 ... 4) current memory state of all system tasks [ 516.079544] [ 744] 0 744 9211 1345 114688 82 0 systemd-journal [ 516.082034] [ 787] 0 787 31764 0 143360 92 0 lvmetad [ 516.084465] [ 792] 0 792 10930 1 110592 208 -1000 systemd-udevd [ 516.086865] [ 1199] 0 1199 13866 0 131072 112 -1000 auditd [ 516.089190] [ 1222] 0 1222 31990 1 110592 157 0 smartd [ 516.091477] [ 1225] 0 1225 4864 85 81920 43 0 irqbalance [ 516.093712] [ 1226] 0 1226 52612 0 258048 426 0 abrtd [ 516.112128] [ 1280] 0 1280 109774 55 299008 400 0 NetworkManager [ 516.113998] [ 1295] 0 1295 28817 37 69632 24 0 ksmtuned [ 516.144596] [ 10718] 0 10718 2622484 1721372 15998976 267219 0 panic [ 516.145792] [ 10719] 0 10719 2622484 1164767 9818112 53576 0 panic [ 516.146977] [ 10720] 0 10720 2622484 1174361 9904128 53709 0 panic [ 516.148163] [ 10721] 0 10721 2622484 1209070 10194944 54824 0 panic [ 516.149329] [ 10722] 0 10722 2622484 1745799 14774272 91138 0 panic 5) oom context (contrains and the chosen victim). oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=/,mems_allowed=0-1,task=panic,pid=10737,uid=0 An admin can easily get the full oom context at a single line which makes parsing much easier. Link: http://lkml.kernel.org/r/1542799799-36184-1-git-send-email-ufo19890607@gmai… Signed-off-by: yuzhoujian <yuzhoujian(a)didichuxing.com> Acked-by: Michal Hocko <mhocko(a)suse.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: David Rientjes <rientjes(a)google.com> Cc: "Kirill A . Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: Roman Gushchin <guro(a)fb.com> Cc: Tetsuo Handa <penguin-kernel(a)i-love.sakura.ne.jp> Cc: Yang Shi <yang.s(a)alibaba-inc.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> (cherry picked from commit ef8444ea01d7442652f8e1b8a8b94278cb57eafd) Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> (cherry picked from commit 985eab72d54b5ac73189d609486526b5e30125ac) Signed-off-by: Lu Jialin <lujialin4(a)huawei.com> Reviewed-by: Jing Xiangfeng <jingxiangfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/oom.h | 10 ++++++++++ kernel/cgroup/cpuset.c | 4 ++-- mm/oom_kill.c | 29 ++++++++++++++++++++--------- mm/page_alloc.c | 4 ++-- 4 files changed, 34 insertions(+), 13 deletions(-) diff --git a/include/linux/oom.h b/include/linux/oom.h index 2b2a40cc19bf4..123538b89dc8d 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -15,6 +15,13 @@ struct notifier_block; struct mem_cgroup; struct task_struct; +enum oom_constraint { + CONSTRAINT_NONE, + CONSTRAINT_CPUSET, + CONSTRAINT_MEMORY_POLICY, + CONSTRAINT_MEMCG, +}; + /* * Details of the page allocation that triggered the oom killer that are used to * determine what should be killed. @@ -42,6 +49,9 @@ struct oom_control { unsigned long totalpages; struct task_struct *chosen; unsigned long chosen_points; + + /* Used to print the constraint info. */ + enum oom_constraint constraint; }; extern struct mutex oom_lock; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a4ce9474a078c..feb91177247c8 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2681,9 +2681,9 @@ void cpuset_print_current_mems_allowed(void) rcu_read_lock(); cgrp = task_cs(current)->css.cgroup; - pr_info("%s cpuset=", current->comm); + pr_cont(",cpuset="); pr_cont_cgroup_name(cgrp); - pr_cont(" mems_allowed=%*pbl\n", + pr_cont(",mems_allowed=%*pbl", nodemask_pr_args(&current->mems_allowed)); rcu_read_unlock(); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 2e09b03432c08..51104048b4e7f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -250,11 +250,11 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, return points > 0 ? points : 1; } -enum oom_constraint { - CONSTRAINT_NONE, - CONSTRAINT_CPUSET, - CONSTRAINT_MEMORY_POLICY, - CONSTRAINT_MEMCG, +static const char * const oom_constraint_text[] = { + [CONSTRAINT_NONE] = "CONSTRAINT_NONE", + [CONSTRAINT_CPUSET] = "CONSTRAINT_CPUSET", + [CONSTRAINT_MEMORY_POLICY] = "CONSTRAINT_MEMORY_POLICY", + [CONSTRAINT_MEMCG] = "CONSTRAINT_MEMCG", }; /* @@ -483,16 +483,25 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) rcu_read_unlock(); } +static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim) +{ + /* one line summary of the oom killer context. */ + pr_info("oom-kill:constraint=%s,nodemask=%*pbl", + oom_constraint_text[oc->constraint], + nodemask_pr_args(oc->nodemask)); + cpuset_print_current_mems_allowed(); + pr_cont(",task=%s,pid=%d,uid=%d\n", victim->comm, victim->pid, + from_kuid(&init_user_ns, task_uid(victim))); +} + static void dump_header(struct oom_control *oc, struct task_struct *p) { - pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), nodemask=%*pbl, order=%d, oom_score_adj=%hd\n", - current->comm, oc->gfp_mask, &oc->gfp_mask, - nodemask_pr_args(oc->nodemask), oc->order, + pr_warn("%s invoked oom-killer: gfp_mask=%#x(%pGg), order=%d, oom_score_adj=%hd\n", + current->comm, oc->gfp_mask, &oc->gfp_mask, oc->order, current->signal->oom_score_adj); if (!IS_ENABLED(CONFIG_COMPACTION) && oc->order) pr_warn("COMPACTION is disabled!!!\n"); - cpuset_print_current_mems_allowed(); dump_stack(); if (is_memcg_oom(oc)) mem_cgroup_print_oom_info(oc->memcg, p); @@ -503,6 +512,8 @@ static void dump_header(struct oom_control *oc, struct task_struct *p) } if (sysctl_oom_dump_tasks) dump_tasks(oc->memcg, oc->nodemask); + if (p) + dump_oom_summary(oc, p); } /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6bf3d4461430e..2b5a60a856680 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3529,13 +3529,13 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl\n", + pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl", current->comm, &vaf, gfp_mask, &gfp_mask, nodemask_pr_args(nodemask)); va_end(args); cpuset_print_current_mems_allowed(); - + pr_cont("\n"); dump_stack(); warn_alloc_show_mem(gfp_mask, nodemask); } -- 2.25.1

1 26

[PATCH openEuler-1.0-LTS 1/5] memcg: support priority for oom
by Yang Yingliang 30 Jun '21

30 Jun '21

From: Jing Xiangfeng <jingxiangfeng(a)huawei.com> hulk inclusion category: feature bugzilla: 51827 CVE: NA -------------------------------------- We first kill the process from the low priority memcg if OOM occurs. If the process is not found, then fallback to normal handle. Signed-off-by: Jing Xiangfeng <jingxiangfeng(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/memcontrol.h | 12 ++++ mm/Kconfig | 12 ++++ mm/memcontrol.c | 127 +++++++++++++++++++++++++++++++++++++ mm/oom_kill.c | 52 ++++++++++++++- 4 files changed, 202 insertions(+), 1 deletion(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f354e76221db2..c4d4658c7d6df 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -287,6 +287,12 @@ struct mem_cgroup { bool tcpmem_active; int tcpmem_pressure; +#ifdef CONFIG_MEMCG_QOS + /* Currently support 0 and -1. + * in the future it can expand to other value. + */ + int memcg_priority; +#endif #ifdef CONFIG_MEMCG_KMEM /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; @@ -321,6 +327,12 @@ struct mem_cgroup_extension { struct mem_cgroup memcg; }; +#ifdef CONFIG_MEMCG_QOS +bool memcg_low_priority_scan_tasks(int (*)(struct task_struct *, void *), + void *); +void memcg_print_bad_task(void *arg, int ret); +#endif + /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. diff --git a/mm/Kconfig b/mm/Kconfig index 92be0a1ad61f7..7edf3c4c1252b 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -512,6 +512,18 @@ config USERSWAP Support for User Swap. This is based on userfaultfd. We can implement our own swapout and swapin functions in usersapce. +config MEMCG_QOS + bool "Enable Memory Cgroup Priority" + depends on MEMCG + depends on X86 || ARM64 + default y + help + MEMCG_QOS means that we first kill the process from the low priority + memcg if OOM occurs. If the process is not found, then fallback to + normal handle. + + If unsure, say "n". + config CMA bool "Contiguous Memory Allocator" depends on HAVE_MEMBLOCK && MMU diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f401be9d45a5c..31352be988114 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1105,6 +1105,9 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, break; } } +#ifdef CONFIG_MEMCG_QOS + memcg_print_bad_task(arg, ret); +#endif return ret; } @@ -3400,6 +3403,119 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, } #endif +#ifdef CONFIG_MEMCG_QOS +static void memcg_qos_init(struct mem_cgroup *memcg) +{ + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + + if (!parent) + return; + + if (parent->memcg_priority && parent->use_hierarchy) + memcg->memcg_priority = parent->memcg_priority; +} + +static s64 memcg_qos_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return mem_cgroup_from_css(css)->memcg_priority; +} + +static int memcg_qos_write(struct cgroup_subsys_state *css, + struct cftype *cft, s64 val) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + if (val >= 0) + memcg->memcg_priority = 0; + else + memcg->memcg_priority = -1; + + return 0; +} + +static struct mem_cgroup *memcg_find_max_usage(struct mem_cgroup *last) +{ + struct mem_cgroup *iter, *max_memcg = NULL; + struct cgroup_subsys_state *css; + unsigned long usage, max_usage = 0; + + rcu_read_lock(); + css_for_each_descendant_pre(css, &root_mem_cgroup->css) { + iter = mem_cgroup_from_css(css); + + if (!iter->memcg_priority || iter == root_mem_cgroup || + iter == last) + continue; + + usage = mem_cgroup_usage(iter, false); + if (usage > max_usage) { + max_usage = usage; + max_memcg = iter; + } + } + rcu_read_unlock(); + + return max_memcg; +} + +bool memcg_low_priority_scan_tasks(int (*fn)(struct task_struct *, void *), + void *arg) +{ + struct mem_cgroup *max, *last = NULL; + struct oom_control *oc = arg; + struct css_task_iter it; + struct task_struct *task; + int ret = 0; + bool retry = true; + +retry: + max = memcg_find_max_usage(last); + if (!max) + return false; + + css_task_iter_start(&max->css, 0, &it); + while (!ret && (task = css_task_iter_next(&it))) { + if (test_tsk_thread_flag(task, TIF_MEMDIE)) { + pr_info("task %s is dying.\n", task->comm); + continue; + } + + ret = fn(task, arg); + } + css_task_iter_end(&it); + + if (ret) + return false; + + if (!oc->chosen && retry) { + last = max; + retry = false; + goto retry; + } + + if (oc->chosen) + pr_info("The bad task [%d:%s] is from low-priority memcg.\n", + oc->chosen->pid, oc->chosen->comm); + + return oc->chosen ? true : false; +} + +void memcg_print_bad_task(void *arg, int ret) +{ + struct oom_control *oc = arg; + + if (!ret && oc->chosen) { + struct mem_cgroup *memcg; + + memcg = mem_cgroup_from_task(oc->chosen); + if (memcg->memcg_priority) + pr_info("The bad task [%d:%s] is from low-priority memcg.\n", + oc->chosen->pid, oc->chosen->comm); + } +} +#endif + #ifdef CONFIG_NUMA static int memcg_numa_stat_show(struct seq_file *m, void *v) { @@ -4324,6 +4440,13 @@ static struct cftype mem_cgroup_legacy_files[] = { { .name = "pressure_level", }, +#ifdef CONFIG_MEMCG_QOS + { + .name = "qos_level", + .read_s64 = memcg_qos_read, + .write_s64 = memcg_qos_write, + }, +#endif #ifdef CONFIG_NUMA { .name = "numa_stat", @@ -4657,6 +4780,10 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) return -ENOMEM; } +#ifdef CONFIG_MEMCG_QOS + memcg_qos_init(memcg); +#endif + /* Online state pins memcg ID, memcg ID pins CSS */ atomic_set(&memcg->id.ref, 1); css_get(css); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 1c8236cbb9022..22a6f88d1f4d9 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -317,6 +317,49 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc) return CONSTRAINT_NONE; } +#ifdef CONFIG_MEMCG_QOS +/** + * We choose the task in low-priority memcg firstly. For the same state, we + * choose the task with the highest number of 'points'. + */ +static bool oom_next_task(struct task_struct *task, struct oom_control *oc, + unsigned long points) +{ + struct mem_cgroup *cur_memcg; + struct mem_cgroup *oc_memcg; + + + if (!points) + return true; + + if (!oc->chosen) + return false; + + oc_memcg = mem_cgroup_from_task(oc->chosen); + cur_memcg = mem_cgroup_from_task(task); + + if (cur_memcg->memcg_priority == oc_memcg->memcg_priority) { + if (points < oc->chosen_points) + return true; + return false; + } + /* if oc is low-priority, so skip the task */ + if (oc_memcg->memcg_priority) + return true; + + return false; +} +#else +static inline bool oom_next_task(struct task_struct *task, + struct oom_control *oc, unsigned long points) +{ + if (!points || points < oc->chosen_points) + return true; + + return false; +} +#endif + static int oom_evaluate_task(struct task_struct *task, void *arg) { struct oom_control *oc = arg; @@ -347,7 +390,7 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) } points = oom_badness(task, NULL, oc->nodemask, oc->totalpages); - if (!points || points < oc->chosen_points) + if (oom_next_task(task, oc, points)) goto next; select: @@ -376,6 +419,13 @@ static void select_bad_process(struct oom_control *oc) else { struct task_struct *p; +#ifdef CONFIG_MEMCG_QOS + if (memcg_low_priority_scan_tasks(oom_evaluate_task, oc)) { + oc->chosen_points = + oc->chosen_points * 1000 / oc->totalpages; + return; + } +#endif rcu_read_lock(); for_each_process(p) if (oom_evaluate_task(p, oc)) -- 2.25.1

1 4

[PATCH kernel-4.19 1/4] memcg: support priority for oom
by Yang Yingliang 30 Jun '21

30 Jun '21

From: Jing Xiangfeng <jingxiangfeng(a)huawei.com> hulk inclusion category: feature bugzilla: 51827 CVE: NA -------------------------------------- We first kill the process from the low priority memcg if OOM occurs. If the process is not found, then fallback to normal handle. Signed-off-by: Jing Xiangfeng <jingxiangfeng(a)huawei.com> Reviewed-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/memcontrol.h | 12 ++++ mm/Kconfig | 12 ++++ mm/memcontrol.c | 127 +++++++++++++++++++++++++++++++++++++ mm/oom_kill.c | 49 +++++++++++++- 4 files changed, 199 insertions(+), 1 deletion(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0a55493f41da0..d59ce25206de4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -296,6 +296,12 @@ struct mem_cgroup { bool tcpmem_active; int tcpmem_pressure; +#ifdef CONFIG_MEMCG_QOS + /* Currently support 0 and -1. + * in the future it can expand to other value. + */ + int memcg_priority; +#endif #ifdef CONFIG_MEMCG_KMEM /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; @@ -327,6 +333,12 @@ struct mem_cgroup { /* WARNING: nodeinfo must be the last member here */ }; +#ifdef CONFIG_MEMCG_QOS +bool memcg_low_priority_scan_tasks(int (*)(struct task_struct *, void *), + void *); +void memcg_print_bad_task(void *arg, int ret); +#endif + /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. diff --git a/mm/Kconfig b/mm/Kconfig index 8225489c6439d..12601505c4a4a 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -516,6 +516,18 @@ config USERSWAP Support for User Swap. This is based on userfaultfd. We can implement our own swapout and swapin functions in usersapce. +config MEMCG_QOS + bool "Enable Memory Cgroup Priority" + depends on MEMCG + depends on X86 || ARM64 + default y + help + MEMCG_QOS means that we first kill the process from the low priority + memcg if OOM occurs. If the process is not found, then fallback to + normal handle. + + If unsure, say "n". + config CMA bool "Contiguous Memory Allocator" depends on HAVE_MEMBLOCK && MMU diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6b4b487f6ce75..5b90dd9871878 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1240,6 +1240,9 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, break; } } +#ifdef CONFIG_MEMCG_QOS + memcg_print_bad_task(arg, ret); +#endif return ret; } @@ -3641,6 +3644,119 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, } #endif +#ifdef CONFIG_MEMCG_QOS +static void memcg_qos_init(struct mem_cgroup *memcg) +{ + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + + if (!parent) + return; + + if (parent->memcg_priority && parent->use_hierarchy) + memcg->memcg_priority = parent->memcg_priority; +} + +static s64 memcg_qos_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return mem_cgroup_from_css(css)->memcg_priority; +} + +static int memcg_qos_write(struct cgroup_subsys_state *css, + struct cftype *cft, s64 val) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + if (val >= 0) + memcg->memcg_priority = 0; + else + memcg->memcg_priority = -1; + + return 0; +} + +static struct mem_cgroup *memcg_find_max_usage(struct mem_cgroup *last) +{ + struct mem_cgroup *iter, *max_memcg = NULL; + struct cgroup_subsys_state *css; + unsigned long usage, max_usage = 0; + + rcu_read_lock(); + css_for_each_descendant_pre(css, &root_mem_cgroup->css) { + iter = mem_cgroup_from_css(css); + + if (!iter->memcg_priority || iter == root_mem_cgroup || + iter == last) + continue; + + usage = mem_cgroup_usage(iter, false); + if (usage > max_usage) { + max_usage = usage; + max_memcg = iter; + } + } + rcu_read_unlock(); + + return max_memcg; +} + +bool memcg_low_priority_scan_tasks(int (*fn)(struct task_struct *, void *), + void *arg) +{ + struct mem_cgroup *max, *last = NULL; + struct oom_control *oc = arg; + struct css_task_iter it; + struct task_struct *task; + int ret = 0; + bool retry = true; + +retry: + max = memcg_find_max_usage(last); + if (!max) + return false; + + css_task_iter_start(&max->css, 0, &it); + while (!ret && (task = css_task_iter_next(&it))) { + if (test_tsk_thread_flag(task, TIF_MEMDIE)) { + pr_info("task %s is dying.\n", task->comm); + continue; + } + + ret = fn(task, arg); + } + css_task_iter_end(&it); + + if (ret) + return false; + + if (!oc->chosen && retry) { + last = max; + retry = false; + goto retry; + } + + if (oc->chosen) + pr_info("The bad task [%d:%s] is from low-priority memcg.\n", + oc->chosen->pid, oc->chosen->comm); + + return oc->chosen ? true : false; +} + +void memcg_print_bad_task(void *arg, int ret) +{ + struct oom_control *oc = arg; + + if (!ret && oc->chosen) { + struct mem_cgroup *memcg; + + memcg = mem_cgroup_from_task(oc->chosen); + if (memcg->memcg_priority) + pr_info("The bad task [%d:%s] is from low-priority memcg.\n", + oc->chosen->pid, oc->chosen->comm); + } +} +#endif + #ifdef CONFIG_NUMA #define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE)) @@ -4596,6 +4712,13 @@ static struct cftype mem_cgroup_legacy_files[] = { { .name = "pressure_level", }, +#ifdef CONFIG_MEMCG_QOS + { + .name = "qos_level", + .read_s64 = memcg_qos_read, + .write_s64 = memcg_qos_write, + }, +#endif #ifdef CONFIG_NUMA { .name = "numa_stat", @@ -4947,6 +5070,10 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) return -ENOMEM; } +#ifdef CONFIG_MEMCG_QOS + memcg_qos_init(memcg); +#endif + /* Online state pins memcg ID, memcg ID pins CSS */ atomic_set(&memcg->id.ref, 1); css_get(css); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 0dbd6d2a31733..f46c8fa9a1254 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -318,6 +318,49 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc) return CONSTRAINT_NONE; } +#ifdef CONFIG_MEMCG_QOS +/** + * We choose the task in low-priority memcg firstly. For the same state, we + * choose the task with the highest number of 'points'. + */ +static bool oom_next_task(struct task_struct *task, struct oom_control *oc, + unsigned long points) +{ + struct mem_cgroup *cur_memcg; + struct mem_cgroup *oc_memcg; + + + if (!points) + return true; + + if (!oc->chosen) + return false; + + oc_memcg = mem_cgroup_from_task(oc->chosen); + cur_memcg = mem_cgroup_from_task(task); + + if (cur_memcg->memcg_priority == oc_memcg->memcg_priority) { + if (points < oc->chosen_points) + return true; + return false; + } + /* if oc is low-priority, so skip the task */ + if (oc_memcg->memcg_priority) + return true; + + return false; +} +#else +static inline bool oom_next_task(struct task_struct *task, + struct oom_control *oc, unsigned long points) +{ + if (!points || points < oc->chosen_points) + return true; + + return false; +} +#endif + static int oom_evaluate_task(struct task_struct *task, void *arg) { struct oom_control *oc = arg; @@ -348,7 +391,7 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) } points = oom_badness(task, NULL, oc->nodemask, oc->totalpages); - if (!points || points < oc->chosen_points) + if (oom_next_task(task, oc, points)) goto next; select: @@ -377,6 +420,10 @@ static void select_bad_process(struct oom_control *oc) else { struct task_struct *p; +#ifdef CONFIG_MEMCG_QOS + if (memcg_low_priority_scan_tasks(oom_evaluate_task, oc)) + return; +#endif rcu_read_lock(); for_each_process(p) if (oom_evaluate_task(p, oc)) -- 2.25.1

1 3

[PATCH kernel-4.19 1/6] share_pool: Set initial value to variable node_id
by Yang Yingliang 30 Jun '21

30 Jun '21

From: Peng Wu <wupeng58(a)huawei.com> ascend inclusion category: bugfix bugzilla: NA CVE: NA ------------------------------------------- Setting an initial value to variable node_id in function shmem_getpage_gfp. Otherwise, Oops is triggered in some scenarios. [20987.530901] Internal error: Oops: 96000007 [#1] SMP [20987.541162] Modules linked in: cfg80211 rfkill ib_isert iscsi_target_mod rpcrdma ib_srpt target_core_mod dm_mirror dm_region_hash ib_srp scsi_transport_srp dm_log sunrpc dm_mod ib_ipoib rdma_ucm ib_uverbs ib_iser ib_umad rdma_cm ib_cm iw_cm aes_ce_blk crypto_simd cryptd hns_roce_hw_v2 aes_ce_cipher ghash_ce hns_roce sha1_ce ib_core sg ipmi_ssif hi_sfc sbsa_gwdt mtd sch_fq_codel ip_tables realtek hclge hinic sha2_ce sha256_arm64 hns3 ipmi_si hisi_sas_v3_hw hibmc_drm host_edma_drv hnae3 hisi_sas_main ipmi_devintf ipmi_msghandler [20987.639396] Process move_pages03 (pid: 40173, stack limit = 0x00000000804b9d00) [20987.654773] CPU: 50 PID: 40173 Comm: move_pages03 Kdump: loaded Not tainted 4.19.195+ #1 [20987.671794] Hardware name: Huawei TaiShan 2280 V2/BC82AMDD, BIOS 1.08 12/14/2019 [20987.687355] pstate: 80400009 (Nzcv daif +PAN -UAO) [20987.697433] pc : __alloc_pages_nodemask+0x7c/0xdc0 [20987.707510] lr : alloc_pages_vma+0xac/0x318 [20987.716304] sp : ffff0001537cb690 [20987.723268] x29: ffff0001537cb690 x28: 00000000006200ca [20987.734439] x27: 0000000000000000 x26: ffff802fd24439c8 [20987.745610] x25: 0000000000000000 x24: 00000000ffff0000 [20987.756782] x23: 0000000000000000 x22: 0000000000000000 [20987.767952] x21: 00000000ffff0000 x20: ffff000009b69000 [20987.779123] x19: ffff802fd24439c8 x18: 0000000000000000 [20987.790294] x17: 0000000000000000 x16: 0000000000000000 [20987.801466] x15: 0000000000000000 x14: 0000000000000000 [20987.812637] x13: 0000000000000000 x12: 0000000000000000 [20987.823808] x11: ffff000009b69748 x10: 0000000000000040 [20987.834978] x9 : 0000000000000000 x8 : ffff0001537cb978 [20987.846149] x7 : 0000000000000000 x6 : 000000000000003f [20987.857320] x5 : 0000000000000000 x4 : 00000000007fffff [20987.868491] x3 : ffff000009b6c998 x2 : 0000000000000000 [20987.879662] x1 : 0000000000250015 x0 : ffff000009b69788 [20987.890833] Call trace: [20987.895970] __alloc_pages_nodemask+0x7c/0xdc0 [20987.905312] alloc_pages_vma+0xac/0x318 [20987.913374] shmem_alloc_page+0x6c/0xc0 [20987.921436] shmem_alloc_and_acct_page+0x124/0x1f8 [20987.931510] shmem_getpage_gfp+0x16c/0x1028 [20987.940305] shmem_fault+0x94/0x2a0 [20987.947636] __do_fault+0x50/0x220 [20987.954784] do_shared_fault+0x28/0x228 [20987.962846] __handle_mm_fault+0x610/0x8f0 [20987.971457] handle_mm_fault+0xe4/0x1d8 [20987.979520] do_page_fault+0x210/0x4f8 [20987.987398] do_translation_fault+0xa8/0xbc [20987.996192] do_mem_abort+0x68/0x118 [20988.003706] el0_da+0x24/0x28 [20988.009941] Code: b9404c64 72a004a1 b9401062 0a04039c (f875d800) Fixes: d3edfd4f60bae ("share_pool: Alloc shared memory on a specified memory node") Signed-off-by: Peng Wu <wupeng58(a)huawei.com> Reviewed-by: 为珑陈 <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/shmem.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index f08d5ce17a092..4522348cfc189 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1737,7 +1737,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, int error; int once = 0; int alloced = 0; - int node_id; + int node_id = shmem_node_id(vma); if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; @@ -1889,7 +1889,6 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, goto alloc_nohuge; } - node_id = shmem_node_id(vma); alloc_huge: page = shmem_alloc_and_acct_page(gfp, inode, index, true, -- 2.25.1

1 5

[PATCH openEuler-1.0-LTS] io_uring: NULL files dereference by SQPOLL
by Yang Yingliang 30 Jun '21

30 Jun '21

From: Pavel Begunkov <asml.silence(a)gmail.com> mainline inclusion from mainline-5.11-rc1 commit 1a38ffc9cbca361cc274d6e234f5ef8922f0b6d9 category: bugfix bugzilla: 167380 CVE: NA --------------------------- SQPOLL task may find sqo_task->files == NULL and __io_sq_thread_acquire_files() would leave it unset, so following fget_many() and others try to dereference NULL and fault. Propagate an error files are missing. [ 118.962785] BUG: kernel NULL pointer dereference, address: 0000000000000020 [ 118.963812] #PF: supervisor read access in kernel mode [ 118.964534] #PF: error_code(0x0000) - not-present page [ 118.969029] RIP: 0010:__fget_files+0xb/0x80 [ 119.005409] Call Trace: [ 119.005651] fget_many+0x2b/0x30 [ 119.005964] io_file_get+0xcf/0x180 [ 119.006315] io_submit_sqes+0x3a4/0x950 [ 119.007481] io_sq_thread+0x1de/0x6a0 [ 119.007828] kthread+0x114/0x150 [ 119.008963] ret_from_fork+0x22/0x30 Reported-by: Josef Grieb <josef.grieb(a)gmail.com> Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflicts: fs/io_uring.c [ aa1a90087b("io_uring: allow non-fixed files with SQPOLL") merge conflicts. ] Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/io_uring.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index f661231cdfad6..c944a27178a48 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -978,7 +978,7 @@ static void io_sq_thread_drop_mm_files(void) } } -static void __io_sq_thread_acquire_files(struct io_ring_ctx *ctx) +static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx) { if (!current->files) { struct files_struct *files; @@ -988,7 +988,7 @@ static void __io_sq_thread_acquire_files(struct io_ring_ctx *ctx) files = ctx->sqo_task->files; if (!files) { task_unlock(ctx->sqo_task); - return; + return -EOWNERDEAD; } atomic_inc(&files->count); get_nsproxy(ctx->sqo_task->nsproxy); @@ -1000,6 +1000,7 @@ static void __io_sq_thread_acquire_files(struct io_ring_ctx *ctx) current->nsproxy = nsproxy; task_unlock(current); } + return 0; } static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx) @@ -1031,15 +1032,19 @@ static int io_sq_thread_acquire_mm_files(struct io_ring_ctx *ctx, struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; + int ret; if (def->needs_mm) { - int ret = __io_sq_thread_acquire_mm(ctx); + ret = __io_sq_thread_acquire_mm(ctx); if (unlikely(ret)) return ret; } - if (def->needs_file || def->file_table) - __io_sq_thread_acquire_files(ctx); + if (def->needs_file || def->file_table) { + ret = __io_sq_thread_acquire_files(ctx); + if (unlikely(ret)) + return ret; + } return 0; } @@ -1878,8 +1883,8 @@ static void __io_req_task_submit(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - if (!__io_sq_thread_acquire_mm(ctx)) { - __io_sq_thread_acquire_files(ctx); + if (!__io_sq_thread_acquire_mm(ctx) && + !__io_sq_thread_acquire_files(ctx)) { mutex_lock(&ctx->uring_lock); __io_queue_sqe(req, NULL, NULL); mutex_unlock(&ctx->uring_lock); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] vgacon: remove software scrollback support
by Yang Yingliang 29 Jun '21

29 Jun '21

From: Linus Torvalds <torvalds(a)linux-foundation.org> stable inclusion from linux-4.19.146 commit f5fa64c8daf7b97280865c73903edc0a3eea819e CVE: CVE-2020-28097 -------------------------------- commit 973c096f6a85e5b5f2a295126ba6928d9a6afd45 upstream. Yunhai Zhang recently fixed a VGA software scrollback bug in commit ebfdfeeae8c0 ("vgacon: Fix for missing check in scrollback handling"), but that then made people look more closely at some of this code, and there were more problems on the vgacon side, but also the fbcon software scrollback. We don't really have anybody who maintains this code - probably because nobody actually _uses_ it any more. Sure, people still use both VGA and the framebuffer consoles, but they are no longer the main user interfaces to the kernel, and haven't been for decades, so these kinds of extra features end up bitrotting and not really being used. So rather than try to maintain a likely unused set of code, I'll just aggressively remove it, and see if anybody even notices. Maybe there are people who haven't jumped on the whole GUI badnwagon yet, and think it's just a fad. And maybe those people use the scrollback code. If that turns out to be the case, we can resurrect this again, once we've found the sucker^Wmaintainer for it who actually uses it. Reported-by: NopNop Nop <nopitydays(a)gmail.com> Tested-by: Willy Tarreau <w(a)1wt.eu> Cc: 张云海 <zhangyunhai(a)nsfocus.com> Acked-by: Andy Lutomirski <luto(a)amacapital.net> Acked-by: Willy Tarreau <w(a)1wt.eu> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/powerpc/configs/pasemi_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/x86/configs/i386_defconfig | 1 - arch/x86/configs/x86_64_defconfig | 1 - drivers/video/console/Kconfig | 46 ------ drivers/video/console/vgacon.c | 221 +------------------------- 6 files changed, 1 insertion(+), 270 deletions(-) diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 6daa56f8895cb..5f743db4c9f8c 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -111,7 +111,6 @@ CONFIG_FB_NVIDIA=y CONFIG_FB_NVIDIA_I2C=y CONFIG_FB_RADEON=y # CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y CONFIG_SOUND=y CONFIG_SND=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 7ee736f207740..533db43431727 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -780,7 +780,6 @@ CONFIG_FB_TRIDENT=m CONFIG_FB_SM501=m CONFIG_FB_IBM_GXT4500=y CONFIG_LCD_PLATFORM=m -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 0eb9f92f37179..7aab9c4f86a9f 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -217,7 +217,6 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y # CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index e32fc1f274d85..7484a27861d4c 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -213,7 +213,6 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y # CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig index 787792c3d08d6..40d5fea8513cf 100644 --- a/drivers/video/console/Kconfig +++ b/drivers/video/console/Kconfig @@ -21,52 +21,6 @@ config VGA_CONSOLE Say Y. -config VGACON_SOFT_SCROLLBACK - bool "Enable Scrollback Buffer in System RAM" - depends on VGA_CONSOLE - default n - help - The scrollback buffer of the standard VGA console is located in - the VGA RAM. The size of this RAM is fixed and is quite small. - If you require a larger scrollback buffer, this can be placed in - System RAM which is dynamically allocated during initialization. - Placing the scrollback buffer in System RAM will slightly slow - down the console. - - If you want this feature, say 'Y' here and enter the amount of - RAM to allocate for this buffer. If unsure, say 'N'. - -config VGACON_SOFT_SCROLLBACK_SIZE - int "Scrollback Buffer Size (in KB)" - depends on VGACON_SOFT_SCROLLBACK - range 1 1024 - default "64" - help - Enter the amount of System RAM to allocate for scrollback - buffers of VGA consoles. Each 64KB will give you approximately - 16 80x25 screenfuls of scrollback buffer. - -config VGACON_SOFT_SCROLLBACK_PERSISTENT_ENABLE_BY_DEFAULT - bool "Persistent Scrollback History for each console by default" - depends on VGACON_SOFT_SCROLLBACK - default n - help - Say Y here if the scrollback history should persist by default when - switching between consoles. Otherwise, the scrollback history will be - flushed each time the console is switched. This feature can also be - enabled using the boot command line parameter - 'vgacon.scrollback_persistent=1'. - - This feature might break your tool of choice to flush the scrollback - buffer, e.g. clear(1) will work fine but Debian's clear_console(1) - will be broken, which might cause security issues. - You can use the escape sequence \e[3J instead if this feature is - activated. - - Note that a buffer of VGACON_SOFT_SCROLLBACK_SIZE is taken for each - created tty device. - So if you use a RAM-constrained system, say N here. - config MDA_CONSOLE depends on !M68K && !PARISC && ISA tristate "MDA text console (dual-headed)" diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index e079b910feb24..55507df335bdd 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -165,214 +165,6 @@ static inline void vga_set_mem_top(struct vc_data *c) write_vga(12, (c->vc_visible_origin - vga_vram_base) / 2); } -#ifdef CONFIG_VGACON_SOFT_SCROLLBACK -/* software scrollback */ -struct vgacon_scrollback_info { - void *data; - int tail; - int size; - int rows; - int cnt; - int cur; - int save; - int restore; -}; - -static struct vgacon_scrollback_info *vgacon_scrollback_cur; -static struct vgacon_scrollback_info vgacon_scrollbacks[MAX_NR_CONSOLES]; -static bool scrollback_persistent = \ - IS_ENABLED(CONFIG_VGACON_SOFT_SCROLLBACK_PERSISTENT_ENABLE_BY_DEFAULT); -module_param_named(scrollback_persistent, scrollback_persistent, bool, 0000); -MODULE_PARM_DESC(scrollback_persistent, "Enable persistent scrollback for all vga consoles"); - -static void vgacon_scrollback_reset(int vc_num, size_t reset_size) -{ - struct vgacon_scrollback_info *scrollback = &vgacon_scrollbacks[vc_num]; - - if (scrollback->data && reset_size > 0) - memset(scrollback->data, 0, reset_size); - - scrollback->cnt = 0; - scrollback->tail = 0; - scrollback->cur = 0; -} - -static void vgacon_scrollback_init(int vc_num) -{ - int pitch = vga_video_num_columns * 2; - size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024; - int rows = size / pitch; - void *data; - - data = kmalloc_array(CONFIG_VGACON_SOFT_SCROLLBACK_SIZE, 1024, - GFP_NOWAIT); - - vgacon_scrollbacks[vc_num].data = data; - vgacon_scrollback_cur = &vgacon_scrollbacks[vc_num]; - - vgacon_scrollback_cur->rows = rows - 1; - vgacon_scrollback_cur->size = rows * pitch; - - vgacon_scrollback_reset(vc_num, size); -} - -static void vgacon_scrollback_switch(int vc_num) -{ - if (!scrollback_persistent) - vc_num = 0; - - if (!vgacon_scrollbacks[vc_num].data) { - vgacon_scrollback_init(vc_num); - } else { - if (scrollback_persistent) { - vgacon_scrollback_cur = &vgacon_scrollbacks[vc_num]; - } else { - size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024; - - vgacon_scrollback_reset(vc_num, size); - } - } -} - -static void vgacon_scrollback_startup(void) -{ - vgacon_scrollback_cur = &vgacon_scrollbacks[0]; - vgacon_scrollback_init(0); -} - -static void vgacon_scrollback_update(struct vc_data *c, int t, int count) -{ - void *p; - - if (!vgacon_scrollback_cur->data || !vgacon_scrollback_cur->size || - c->vc_num != fg_console) - return; - - p = (void *) (c->vc_origin + t * c->vc_size_row); - - while (count--) { - if ((vgacon_scrollback_cur->tail + c->vc_size_row) > - vgacon_scrollback_cur->size) - vgacon_scrollback_cur->tail = 0; - - scr_memcpyw(vgacon_scrollback_cur->data + - vgacon_scrollback_cur->tail, - p, c->vc_size_row); - - vgacon_scrollback_cur->cnt++; - p += c->vc_size_row; - vgacon_scrollback_cur->tail += c->vc_size_row; - - if (vgacon_scrollback_cur->tail >= vgacon_scrollback_cur->size) - vgacon_scrollback_cur->tail = 0; - - if (vgacon_scrollback_cur->cnt > vgacon_scrollback_cur->rows) - vgacon_scrollback_cur->cnt = vgacon_scrollback_cur->rows; - - vgacon_scrollback_cur->cur = vgacon_scrollback_cur->cnt; - } -} - -static void vgacon_restore_screen(struct vc_data *c) -{ - c->vc_origin = c->vc_visible_origin; - vgacon_scrollback_cur->save = 0; - - if (!vga_is_gfx && !vgacon_scrollback_cur->restore) { - scr_memcpyw((u16 *) c->vc_origin, (u16 *) c->vc_screenbuf, - c->vc_screenbuf_size > vga_vram_size ? - vga_vram_size : c->vc_screenbuf_size); - vgacon_scrollback_cur->restore = 1; - vgacon_scrollback_cur->cur = vgacon_scrollback_cur->cnt; - } -} - -static void vgacon_scrolldelta(struct vc_data *c, int lines) -{ - int start, end, count, soff; - - if (!lines) { - vgacon_restore_screen(c); - return; - } - - if (!vgacon_scrollback_cur->data) - return; - - if (!vgacon_scrollback_cur->save) { - vgacon_cursor(c, CM_ERASE); - vgacon_save_screen(c); - c->vc_origin = (unsigned long)c->vc_screenbuf; - vgacon_scrollback_cur->save = 1; - } - - vgacon_scrollback_cur->restore = 0; - start = vgacon_scrollback_cur->cur + lines; - end = start + abs(lines); - - if (start < 0) - start = 0; - - if (start > vgacon_scrollback_cur->cnt) - start = vgacon_scrollback_cur->cnt; - - if (end < 0) - end = 0; - - if (end > vgacon_scrollback_cur->cnt) - end = vgacon_scrollback_cur->cnt; - - vgacon_scrollback_cur->cur = start; - count = end - start; - soff = vgacon_scrollback_cur->tail - - ((vgacon_scrollback_cur->cnt - end) * c->vc_size_row); - soff -= count * c->vc_size_row; - - if (soff < 0) - soff += vgacon_scrollback_cur->size; - - count = vgacon_scrollback_cur->cnt - start; - - if (count > c->vc_rows) - count = c->vc_rows; - - if (count) { - int copysize; - - int diff = c->vc_rows - count; - void *d = (void *) c->vc_visible_origin; - void *s = (void *) c->vc_screenbuf; - - count *= c->vc_size_row; - /* how much memory to end of buffer left? */ - copysize = min(count, vgacon_scrollback_cur->size - soff); - scr_memcpyw(d, vgacon_scrollback_cur->data + soff, copysize); - d += copysize; - count -= copysize; - - if (count) { - scr_memcpyw(d, vgacon_scrollback_cur->data, count); - d += count; - } - - if (diff) - scr_memcpyw(d, s, diff * c->vc_size_row); - } else - vgacon_cursor(c, CM_MOVE); -} - -static void vgacon_flush_scrollback(struct vc_data *c) -{ - size_t size = CONFIG_VGACON_SOFT_SCROLLBACK_SIZE * 1024; - - vgacon_scrollback_reset(c->vc_num, size); -} -#else -#define vgacon_scrollback_startup(...) do { } while (0) -#define vgacon_scrollback_init(...) do { } while (0) -#define vgacon_scrollback_update(...) do { } while (0) -#define vgacon_scrollback_switch(...) do { } while (0) - static void vgacon_restore_screen(struct vc_data *c) { if (c->vc_origin != c->vc_visible_origin) @@ -386,11 +178,6 @@ static void vgacon_scrolldelta(struct vc_data *c, int lines) vga_set_mem_top(c); } -static void vgacon_flush_scrollback(struct vc_data *c) -{ -} -#endif /* CONFIG_VGACON_SOFT_SCROLLBACK */ - static const char *vgacon_startup(void) { const char *display_desc = NULL; @@ -573,10 +360,7 @@ static const char *vgacon_startup(void) vgacon_xres = screen_info.orig_video_cols * VGA_FONTWIDTH; vgacon_yres = vga_scan_lines; - if (!vga_init_done) { - vgacon_scrollback_startup(); - vga_init_done = true; - } + vga_init_done = true; return display_desc; } @@ -867,7 +651,6 @@ static int vgacon_switch(struct vc_data *c) vgacon_doresize(c, c->vc_cols, c->vc_rows); } - vgacon_scrollback_switch(c->vc_num); return 0; /* Redrawing not needed */ } @@ -1384,7 +1167,6 @@ static bool vgacon_scroll(struct vc_data *c, unsigned int t, unsigned int b, oldo = c->vc_origin; delta = lines * c->vc_size_row; if (dir == SM_UP) { - vgacon_scrollback_update(c, t, lines); if (c->vc_scr_end + delta >= vga_vram_end) { scr_memcpyw((u16 *) vga_vram_base, (u16 *) (oldo + delta), @@ -1448,7 +1230,6 @@ const struct consw vga_con = { .con_save_screen = vgacon_save_screen, .con_build_attr = vgacon_build_attr, .con_invert_region = vgacon_invert_region, - .con_flush_scrollback = vgacon_flush_scrollback, }; EXPORT_SYMBOL(vga_con); -- 2.25.1

1 0

openEuler 任务打榜赛6月21日-6月28日周榜单来啦
by Marketing openEuler 29 Jun '21

29 Jun '21

openEuler 任务打榜赛6月21日-6月28日周榜单来啦，快来看看有没有你的名字吧。这里提醒已领取赛题但是还没有加群的小伙伴赶紧联系小助手加群呀。好啦~，下面让我们看一下有哪些开发者上榜吧！ gitee用户账号积分值解决issue/pr数量 yaozc701 20 4 dada5208 16 5 shuyao13 14 4 houlibao 12 3 liuerwuliu 12 3 hw999666 8 2 gc7500 8 2 weidongkl 6 1 shao1112 6 2 wss1235 2 1 恭喜以上开发者，请联系小助手领奖。没有上榜的小伙伴不要灰心，请再接再历。周榜、月榜前十名均有奖励，期待在榜单上早点见到你。添加小助手微信（SoftCorePro）回复“*任务打榜赛*”进入交流群 *了解更多* - 官网：https://openeuler.org/zh/interaction/hdc/2021-developer.html - 我要报名： https://competition.huaweicloud.com/information/1000041420/introduction - 我要做题： https://gitee.com/organizations/src-openeuler/issues?assignee_id=&author_id…

1 0

[PATCH kernel-4.19] vhost_net: avoid tx queue stuck when sendmsg fails
by Yang Yingliang 28 Jun '21

28 Jun '21

From: Yunjian Wang <wangyunjian(a)huawei.com> mainline inclusion from mainline-5.12-rc1 commit dc9c9e72ff3ba01ae63e6263ac26234ba1869cd7 category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- Currently the driver doesn't drop a packet which can't be sent by tun (e.g bad packet). In this case, the driver will always process the same packet lead to the tx queue stuck. To fix this issue: 1. in the case of persistent failure (e.g bad packet), the driver can skip this descriptor by ignoring the error. 2. in the case of transient failure (e.g -ENOBUFS, -EAGAIN and -ENOMEM), the driver schedules the worker to try again. Signed-off-by: Yunjian Wang <wangyunjian(a)huawei.com> Acked-by: Jason Wang <jasowang(a)redhat.com> Acked-by: Willem de Bruijn <willemb(a)google.com> Acked-by: Michael S. Tsirkin <mst(a)redhat.com> Link: https://lore.kernel.org/r/1610685980-38608-1-git-send-email-wangyunjian@hua… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/vhost/net.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 0c7bbc92b22a9..1d99f5c443eeb 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -580,14 +580,15 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) else msg.msg_flags &= ~MSG_MORE; - /* TODO: Check specific error and bomb out unless ENOBUFS? */ err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { - vhost_discard_vq_desc(vq, 1); - vhost_net_enable_vq(net, vq); - break; - } - if (err != len) + if (err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS) { + vhost_discard_vq_desc(vq, 1); + vhost_net_enable_vq(net, vq); + break; + } + pr_debug("Fail to send packet: err %d", err); + } else if (unlikely(err != len)) pr_debug("Truncated TX packet: len %d != %zd\n", err, len); if (++nvq->done_idx >= VHOST_NET_BATCH) @@ -670,7 +671,6 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) msg.msg_flags &= ~MSG_MORE; } - /* TODO: Check specific error and bomb out unless ENOBUFS? */ err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { if (zcopy_used) { @@ -679,11 +679,13 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) nvq->upend_idx = ((unsigned)nvq->upend_idx - 1) % UIO_MAXIOV; } - vhost_discard_vq_desc(vq, 1); - vhost_net_enable_vq(net, vq); - break; - } - if (err != len) + if (err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS) { + vhost_discard_vq_desc(vq, 1); + vhost_net_enable_vq(net, vq); + break; + } + pr_debug("Fail to send packet: err %d", err); + } else if (unlikely(err != len)) pr_debug("Truncated TX packet: " " len %d != %zd\n", err, len); if (!zcopy_used) -- 2.25.1

1 0

[PATCH hulk-4.19-next] itrace: add missing itrace_hardirqs_ignore() calls
by Bixuan Cui 28 Jun '21

28 Jun '21

From: Bixuan Cui <c00283067(a)huawei.com> ascend inclusion category: feature bugzilla: NA DTS: #601 CVE: NA --------------------------------------------- There is an anomalous statistics in itrace irqsoff: max_time:3945(us) caller:__do_softirq+0x8c/0x310 max_time:7996(us) caller:__do_softirq+0x8c/0x310 Use function tracer to trace: stress-ng-cpu-3723 [011] d... 2817.510377: rcu_nmi_exit <-rcu_irq_exit stress-ng-cpu-3723 [011] d... 2817.510377: rcu_dynticks_curr_cpu_in_eqs <-rcu_nmi_exit stress-ng-cpu-3723 [011] d... 2817.514356: gic_handle_irq <-el0_irq_naked stress-ng-cpu-3723 [011] d... 2817.514356: __handle_domain_irq <-gic_handle_irq ... The per-cpu interrupt is enabled after irq_handler in el0_irq_naked() is executed. However, the itrace does not add the irqsoff monitoring to el0_irq_naked. The same omission appears in the following files: arch/arm64/include/asm/daifflags.h arch/arm64/kernel/entry.S arch/arm64/kernel/syscall.c arch/arm64/mm/fault.c Add missing itrace_hardirqs_ignore() calls into it. Signed-off-by: Bixuan Cui <cuibixuan(a)huawei.com> --- arch/arm64/include/asm/daifflags.h | 3 +++ arch/arm64/kernel/entry.S | 9 +++++++++ arch/arm64/kernel/syscall.c | 3 +++ arch/arm64/mm/fault.c | 6 +++++- 4 files changed, 20 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 1230923b032d..1d832814eae8 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -72,6 +72,9 @@ static inline void local_daif_restore(unsigned long flags) if (!irq_disabled) { trace_hardirqs_on(); +#ifdef CONFIG_ITRACE_IRQSOFF + itrace_hardirqs_ignore(); +#endif if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2eb1b657de2f..2c9b8d94d367 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -718,6 +718,9 @@ alternative_else_nop_endif #endif bl trace_hardirqs_on 1: +#endif +#ifdef CONFIG_ITRACE_IRQSOFF + bl itrace_hardirqs_ignore #endif kernel_exit 1 @@ -954,6 +957,9 @@ el0_irq_naked: #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_on +#endif +#ifdef CONFIG_ITRACE_IRQSOFF + bl itrace_hardirqs_ignore #endif b ret_to_user ENDPROC(el0_irq) @@ -989,6 +995,9 @@ work_pending: bl do_notify_resume #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_on // enabled while in userspace +#endif +#ifdef CONFIG_ITRACE_IRQSOFF + bl itrace_hardirqs_ignore #endif ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for single-step b finish_ret_to_user diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index f2d2dbbbfca2..964df44d7429 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -131,6 +131,9 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, * the SPSR. */ trace_hardirqs_on(); +#ifdef CONFIG_ITRACE_IRQSOFF + itrace_hardirqs_ignore(); +#endif return; } local_daif_restore(DAIF_PROCCTX); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 6cd448d9835c..9f30be41bb87 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -934,8 +934,12 @@ asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint, rv = 0; } - if (interrupts_enabled(regs)) + if (interrupts_enabled(regs)) { trace_hardirqs_on(); +#ifdef CONFIG_ITRACE_IRQSOFF + itrace_hardirqs_ignore(); +#endif + } return rv; } -- 2.17.1

1 1

[PATCH kernel-4.19 1/2] mm: vmalloc: prevent use after free in _vm_unmap_aliases
by Yang Yingliang 28 Jun '21

28 Jun '21

From: Vijayanand Jitta <vjitta(a)codeaurora.org> mainline inclusion from mainline-5.13-rc1 commit ad216c0316ad6391d90f4de0a7f59396b2925a06 category: feature bugzilla: NA CVE: NA --------------------------- A potential use after free can occur in _vm_unmap_aliases where an already freed vmap_area could be accessed, Consider the following scenario: Process 1 Process 2 __vm_unmap_aliases __vm_unmap_aliases purge_fragmented_blocks_allcpus rcu_read_lock() rcu_read_lock() list_del_rcu(&vb->free_list) list_for_each_entry_rcu(vb .. ) __purge_vmap_area_lazy kmem_cache_free(va) va_start = vb->va->va_start Here Process 1 is in purge path and it does list_del_rcu on vmap_block and later frees the vmap_area, since Process 2 was holding the rcu lock at this time vmap_block will still be present in and Process 2 accesse it and thereby it tries to access vmap_area of that vmap_block which was already freed by Process 1 and this results in use after free. Fix this by adding a check for vb->dirty before accessing vmap_area structure since vb->dirty will be set to VMAP_BBMAP_BITS in purge path checking for this will prevent the use after free. Link: https://lkml.kernel.org/r/1616062105-23263-1-git-send-email-vjitta@codeauro… Signed-off-by: Vijayanand Jitta <vjitta(a)codeaurora.org> Reviewed-by: Uladzislau Rezki (Sony) <urezki(a)gmail.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Rui Xiang <rui.xiang(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/vmalloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 8c70131e0b078..011a84ebec04d 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1953,7 +1953,7 @@ void vm_unmap_aliases(void) rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { spin_lock(&vb->lock); - if (vb->dirty) { + if (vb->dirty && vb->dirty != VMAP_BBMAP_BITS) { unsigned long va_start = vb->va->va_start; unsigned long s, e; -- 2.25.1

1 1

[PATCH kernel-4.19 1/4] iommu/vt-d: Add support for ACPI device use physical, node as pci device to establish identity mapping
by Yang Yingliang 28 Jun '21

28 Jun '21

From: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> zhaoxin inclusion category: feature bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=19 CVE: NA ---------------------------------------------------------------- When using ACPI device to create identity mapping, if the physical node of the ACPI device is a pci device, domain_1 will be created for these two devices. But if the pci device and other pci devices belong to another domain_2, this will happen conflict and destroy another domain. Such as PCI devices under the PCIE-to-PCI bridge. Therefore, when the physical node of the ACPI device is a PCI device, this patch uses the PCI device to create the domain. In this way, there is only one domain. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> Reviewed-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/iommu/intel-iommu.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 18e0be8e05a53..3e5e1791abbb3 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2756,6 +2756,27 @@ static int domain_prepare_identity_map(struct device *dev, return iommu_domain_identity_map(domain, start, end); } +static struct device *acpi_dev_find_pci_dev(struct device *dev) +{ + struct acpi_device_physical_node *pn; + struct acpi_device *adev; + + if (dev->bus == &acpi_bus_type) { + adev = to_acpi_device(dev); + + mutex_lock(&adev->physical_node_lock); + list_for_each_entry(pn, &adev->physical_node_list, node) { + if (dev_is_pci(pn->dev)) { + mutex_unlock(&adev->physical_node_lock); + return pn->dev; + } + } + mutex_unlock(&adev->physical_node_lock); + } + + return dev; +} + static int iommu_prepare_identity_map(struct device *dev, unsigned long long start, unsigned long long end) @@ -2763,6 +2784,8 @@ static int iommu_prepare_identity_map(struct device *dev, struct dmar_domain *domain; int ret; + dev = acpi_dev_find_pci_dev(dev); + domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH); if (!domain) return -ENOMEM; -- 2.25.1

1 3

Re: SMMU Cmdq Related Patch Unable to Reproduce Performance Improvement
by Leizhen (ThunderTown) 28 Jun '21

28 Jun '21

On 2021/6/26 22:33, 李泽斌 wrote: > > Hi all > > I am recently curious about a patch mentioned in OpenEuler Kernel Meeting about SMMU. The patch name is "iommu/arm-smmu-v3: Reduce contention during command-queue insertion", and it has been merged, the commit link is here(https://github.com/torvalds/linux/commit/587e6c10a7ce89a5924fdbeff2ec5…. > > But I find it difficult to reproduce the huge performance improvement, and I notice that there is an evaluation result figure in the meeting. So I turn to you guys for help. I wonder if you can provide more evaluation details to reproduce the improvement. TIA First，it only works in strict mode on ARM64, so please make sure: "iommu.passthrough=1" or "iommu.strict=0" is not set. Second, only some high-end peripherals have this performance bottleneck. For example: 1) 100Gb/s or higher NIC interconnection (direct connection), use command 'iperf' to test it 2) Attach more than 12 SSDs or NVMEs to the PCI expander, use command 'fio' to test it For most low-speed devices, their performance in strict mode is close to iommu.passthrough=1. There is no room for further optimization. > > > Best Regards > > Zebin Li > > . >

1 0

[PATCH kernel-4.19] block: dio: ensure the memory order between bi_private and bi_css
by Yang Yingliang 26 Jun '21

26 Jun '21

From: Hou Tao <houtao1(a)huawei.com> hulk inclusion category: bugfix bugzilla: 167067 CVE: NA -------------------------------- In __blkdev_direct_IO_simple(), when bi_private is NULL, it assumes bi_css must be NULL as showed below: CPU 1: CPU 2: __blkdev_direct_IO_simple submit_bio bio_endio bio_uninit(bio) css_put(bi_css) bi_css = NULL set_current_state(TASK_UNINTERRUPTIBLE) bio->bi_end_io blkdev_bio_end_io_simple bio->bi_private = NULL // bi_private is NULL READ_ONCE(bio->bi_private) wake_up_process smp_mb__after_spinlock bio_unint(bio) // read bi_css as no-NULL css_put(bi_css) Because there is no memory barrier between the reading and the writing of these two variables, the assumption is wrong under weak-memory model machine (e.g. arm64). bi_css will be put twice and leads to the following warning: percpu_ref_switch_to_atomic_rcu: percpu ref (css_release) <= 0 (-3) after switching to atomic There is a similar problem in __blkdev_direct_IO() which occurs between dio->waiter and bio.bi_status. Fixing it by adding a smp_rmb() between the reads of two variables, and a corresponding smp_wmb() between the writes. Signed-off-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/block_dev.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 786d105692e85..30dd7b19bd2e3 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -195,6 +195,11 @@ static void blkdev_bio_end_io_simple(struct bio *bio) { struct task_struct *waiter = bio->bi_private; + /* + * Paired with smp_rmb() after reading bio->bi_private + * in __blkdev_direct_IO_simple() + */ + smp_wmb(); WRITE_ONCE(bio->bi_private, NULL); wake_up_process(waiter); } @@ -251,8 +256,14 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, qc = submit_bio(&bio); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - if (!READ_ONCE(bio.bi_private)) + if (!READ_ONCE(bio.bi_private)) { + /* + * Paired with smp_wmb() in + * blkdev_bio_end_io_simple() + */ + smp_rmb(); break; + } if (!(iocb->ki_flags & IOCB_HIPRI) || !blk_poll(bdev_get_queue(bdev), qc)) io_schedule(); @@ -317,6 +328,12 @@ static void blkdev_bio_end_io(struct bio *bio) } else { struct task_struct *waiter = dio->waiter; + if (!dio->multi_bio) + /* + * Paired with smp_rmb() after reading + * dio->waiter in __blkdev_direct_IO() + */ + smp_wmb(); WRITE_ONCE(dio->waiter, NULL); wake_up_process(waiter); } @@ -417,8 +434,11 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - if (!READ_ONCE(dio->waiter)) + if (!READ_ONCE(dio->waiter)) { + /* Paired with smp_wmb() in blkdev_bio_end_io() */ + smp_rmb(); break; + } if (!(iocb->ki_flags & IOCB_HIPRI) || !blk_poll(bdev_get_queue(bdev), qc)) -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] btrfs: allow btrfs_truncate_block() to fallback to nocow for data space reservation
by Cheng Jian 25 Jun '21

25 Jun '21

From: Qu Wenruo <wqu(a)suse.com> mainline inclusion from mainline-5.13.0-rc5 commit 6d4572a9d71d5fc2affee0258d8582d39859188c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I39MZM CVE: NA ------------------------------------------------------ From: Gou Hao <gouhao(a)uniontech.com> btrfs: make btrfs_truncate_block check NOCOW attribute For the modification of the main line, there are two places not merge. The mainline code adds the parameter nowait in btrfs_check_can_nocow, during the round, it only changes the name of check_can_nocow. The code of the main line calls the btrfs_drew_write_unlock function at the end of btrfs_truncate_block, and 4.19 kernel of the code does not have this function. In the Reference address, the two codes were not merge too. ------------------------------------------------------ btrfs: allow btrfs_truncate_block() to fallback to nocow for data space reservation [BUG] When the data space is exhausted, even if the inode has NOCOW attribute, we will still refuse to truncate unaligned range due to ENOSPC. The following script can reproduce it pretty easily: #!/bin/bash dev=/dev/test/test mnt=/mnt/btrfs umount $dev &> /dev/null umount $mnt &> /dev/null mkfs.btrfs -f $dev -b 1G mount -o nospace_cache $dev $mnt touch $mnt/foobar chattr +C $mnt/foobar xfs_io -f -c "pwrite -b 4k 0 4k" $mnt/foobar > /dev/null xfs_io -f -c "pwrite -b 4k 0 1G" $mnt/padding &> /dev/null sync xfs_io -c "fpunch 0 2k" $mnt/foobar umount $mnt Currently this will fail at the fpunch part. [CAUSE] Because btrfs_truncate_block() always reserves space without checking the NOCOW attribute. Since the writeback path follows NOCOW bit, we only need to bother the space reservation code in btrfs_truncate_block(). [FIX] Make btrfs_truncate_block() follow btrfs_buffered_write() to try to reserve data space first, and fall back to NOCOW check only when we don't have enough space. Such always-try-reserve is an optimization introduced in btrfs_buffered_write(), to avoid expensive btrfs_check_can_nocow() call. This patch will export check_can_nocow() as btrfs_check_can_nocow(), and use it in btrfs_truncate_block() to fix the problem. Reference: https://patchwork.kernel.org/project/linux-btrfs/patch/20200130052822.11765… Reported-by: Martin Doucha <martin.doucha(a)suse.com> Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: Anand Jain <anand.jain(a)oracle.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Gou Hao <gouhao(a)uniontech.com> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> --- fs/btrfs/ctree.h | 3 ++- fs/btrfs/file.c | 8 ++++---- fs/btrfs/inode.c | 39 +++++++++++++++++++++++++++++++++------ 3 files changed, 39 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 49ef2e48a8c6..3d8c699e44ea 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3273,7 +3273,8 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); int btrfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); - +int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, struct btrfs_root *root); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index d9d90f0b66d2..f0600b1c6d90 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1536,8 +1536,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, return ret; } -static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) +int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos, + size_t *write_bytes) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1647,7 +1647,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, if (ret < 0) { if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && - check_can_nocow(BTRFS_I(inode), pos, + btrfs_check_can_nocow(BTRFS_I(inode), pos, &write_bytes) > 0) { /* * For nodata cow case, no need to reserve @@ -1923,7 +1923,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, */ if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { + btrfs_check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { inode_unlock(inode); return -EAGAIN; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 69e376d27bcc..52da573741ed 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4901,11 +4901,13 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, struct extent_state *cached_state = NULL; struct extent_changeset *data_reserved = NULL; char *kaddr; + bool only_release_metadata = false; u32 blocksize = fs_info->sectorsize; pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (blocksize - 1); struct page *page; gfp_t mask = btrfs_alloc_write_mask(mapping); + size_t write_bytes = blocksize; int ret = 0; u64 block_start; u64 block_end; @@ -4917,10 +4919,26 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, block_start = round_down(from, blocksize); block_end = block_start + blocksize - 1; - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, - block_start, blocksize); - if (ret) + ret = btrfs_check_data_free_space(inode, &data_reserved, + block_start, blocksize); + if (ret < 0) { + if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) && + btrfs_check_can_nocow(BTRFS_I(inode), block_start, + &write_bytes) > 0) { + /* For nocow case, no need to reserve data space */ + only_release_metadata = true; + } else { + goto out; + } + } + ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize); + if (ret < 0) { + if (!only_release_metadata) + btrfs_free_reserved_data_space(inode, data_reserved, + block_start, blocksize); goto out; + } again: page = find_or_create_page(mapping, index, mask); @@ -4991,10 +5009,19 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, set_page_dirty(page); unlock_extent_cached(io_tree, block_start, block_end, &cached_state); + if (only_release_metadata) + set_extent_bit(&BTRFS_I(inode)->io_tree, block_start, + block_end, EXTENT_NORESERVE, NULL, NULL, + GFP_NOFS); out_unlock: - if (ret) - btrfs_delalloc_release_space(inode, data_reserved, block_start, - blocksize, true); + if (ret) { + if (only_release_metadata) + btrfs_delalloc_release_metadata(BTRFS_I(inode), + blocksize, true); + else + btrfs_delalloc_release_space(inode, data_reserved, + block_start, blocksize, true); + } btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize); unlock_page(page); put_page(page); -- 2.25.1

1 0

【Meeting Notice】openEuler kernel 技术分享第七期 & 双周例会 Time: 2021-06-25 14:00-18:00
by Meeting Book 25 Jun '21

25 Jun '21

1 0

[PATCH kernel-4.19] ext4: fix memory leak in ext4_fill_super
by Yang Yingliang 24 Jun '21

24 Jun '21

From: Alexey Makhalov <amakhalov(a)vmware.com> mainline inclusion from mainline-v5.13-rc5 commit afd09b617db3786b6ef3dc43e28fe728cfea84df category: bugfix bugzilla: 148443 CVE: NA ----------------------------------------------- Buffer head references must be released before calling kill_bdev(); otherwise the buffer head (and its page referenced by b_data) will not be freed by kill_bdev, and subsequently that bh will be leaked. If blocksizes differ, sb_set_blocksize() will kill current buffers and page cache by using kill_bdev(). And then super block will be reread again but using correct blocksize this time. sb_set_blocksize() didn't fully free superblock page and buffer head, and being busy, they were not freed and instead leaked. This can easily be reproduced by calling an infinite loop of: systemctl start <ext4_on_lvm>.mount, and systemctl stop <ext4_on_lvm>.mount ... since systemd creates a cgroup for each slice which it mounts, and the bh leak get amplified by a dying memory cgroup that also never gets freed, and memory consumption is much more easily noticed. Fixes: ce40733ce93d ("ext4: Check for return value from sb_set_blocksize") Fixes: ac27a0ec112a ("ext4: initial copy of files from ext3") Link: https://lore.kernel.org/r/20210521075533.95732-1-amakhalov@vmware.com Signed-off-by: Alexey Makhalov <amakhalov(a)vmware.com> Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org conflicts: fs/ext4/super.c Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/super.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a964ed63601c6..f66bbe73d1a94 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4179,14 +4179,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (sb->s_blocksize != blocksize) { + /* + * bh must be released before kill_bdev(), otherwise + * it won't be freed and its page also. kill_bdev() + * is called by sb_set_blocksize(). + */ + brelse(bh); /* Validate the filesystem blocksize */ if (!sb_set_blocksize(sb, blocksize)) { ext4_msg(sb, KERN_ERR, "bad block size %d", blocksize); + bh = NULL; goto failed_mount; } - brelse(bh); logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE; offset = do_div(logical_sb_block, blocksize); bh = ext4_sb_bread_unmovable(sb, logical_sb_block); @@ -4861,8 +4867,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) for (i = 0; i < EXT4_MAXQUOTAS; i++) kfree(sbi->s_qf_names[i]); #endif - ext4_blkdev_remove(sbi); + /* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */ brelse(bh); + ext4_blkdev_remove(sbi); out_fail: sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); -- 2.25.1

1 0

【Meeting Notice】openEuler kernel 技术分享第七期 & 双周例会 Time: 2021-06-25 14:00-18:00
by Meeting Book 24 Jun '21

24 Jun '21

2 1

快来看你是否上榜~！openEuler 任务打榜赛5月榜单出炉
by Marketing openEuler 24 Jun '21

24 Jun '21

经过一个月的角逐，openEuler 任务打榜赛5月榜单来啦。在这一个月的时间里，开发者参加任务打榜赛的热情高涨：总计有*38*人领取*118*道赛题，赛道交流群成员*70*个，这里 *提醒领取赛题但是还没有加群的小伙伴赶紧联系小助手加群*呀。好啦~，下面让我们看一下5月份有哪些开发者上榜吧！ gitee用户账号 gitee邮箱积分值解决issue/pr数量 li-kaiyuan66666 likaiyuan7(a)huawei.com 6 1 yanxiaobing2020 yanxiaobing(a)huawei.com 2 1 zhu-yuncheng zhuyuncheng(a)huawei.com 6 1 polite2anyone zhangyao05(a)outlook.com 10 2 yaozc701 yaozc7(a)chinaunicom.cn 18 2 恭喜以上开发者，请中奖的开发者联系小助手*领奖*。没有上榜的小伙伴不要灰心请再接再历，周榜、月榜前十名均有奖励，期待在榜单上早点见到你。让我们共同期待6月的榜单。 [image: image.png] 添加小助手微信回复“*任务打榜赛*”进入交流群 *了解更多* - 官网：https://openeuler.org/zh/interaction/hdc/2021-developer.html - 我要报名： https://competition.huaweicloud.com/information/1000041420/introduction - 我要做题： https://gitee.com/organizations/src-openeuler/issues?assignee_id=&author_id…

1 1

[PATCH openEuler-21.03] net: hns3: fix incorrect resp_msg issue
by moyu 23 Jun '21

23 Jun '21

From: Jiaran Zhang <zhangjiaran(a)huawei.com> table inclusion from stable-5.12.9 commit d207c1e8e3fb82aca5ffd14c33d0848b6b820efc bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=205 CVE: NA -------------------------------- [ Upstream commit a710b9ffbebaf713f7dbd4dbd9524907e5d66f33 ] In hclge_mbx_handler(), if there are two consecutive mailbox messages that requires resp_msg, the resp_msg is not cleared after processing the first message, which will cause the resp_msg data of second message incorrect. Fix it by clearing the resp_msg before processing every mailbox message. Fixes: bb5790b71bad ("net: hns3: refactor mailbox response scheme between PF and VF") Signed-off-by: Jiaran Zhang <zhangjiaran(a)huawei.com> Signed-off-by: Huazhong Tan <tanhuazhong(a)huawei.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: moyu <xiahua.991116(a)qq.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 3ab6db2588d3..324d150d2b22 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -657,7 +657,6 @@ void hclge_mbx_handler(struct hclge_dev *hdev) unsigned int flag; int ret = 0; - memset(&resp_msg, 0, sizeof(resp_msg)); /* handle all the mailbox requests in the queue */ while (!hclge_cmd_crq_empty(&hdev->hw)) { if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) { @@ -685,6 +684,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev) trace_hclge_pf_mbx_get(hdev, req); + /* clear the resp_msg before processing every mailbox message */ + memset(&resp_msg, 0, sizeof(resp_msg)); + switch (req->msg.code) { case HCLGE_MBX_MAP_RING_TO_VECTOR: ret = hclge_map_unmap_ring_to_vf_vector(vport, true, -- 2.23.0

1 0

[PATCH openEuler-21.03] net: hns3: fix incorrect resp_msg issue table inclusion from stable-5.12.9 commit d207c1e8e3fb82aca5ffd14c33d0848b6b820efc bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=205 CVE: NA
by moyu 23 Jun '21

23 Jun '21

From: Jiaran Zhang <zhangjiaran(a)huawei.com> -------------------------------- [ Upstream commit a710b9ffbebaf713f7dbd4dbd9524907e5d66f33 ] In hclge_mbx_handler(), if there are two consecutive mailbox messages that requires resp_msg, the resp_msg is not cleared after processing the first message, which will cause the resp_msg data of second message incorrect. Fix it by clearing the resp_msg before processing every mailbox message. Fixes: bb5790b71bad ("net: hns3: refactor mailbox response scheme between PF and VF") Signed-off-by: Jiaran Zhang <zhangjiaran(a)huawei.com> Signed-off-by: Huazhong Tan <tanhuazhong(a)huawei.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: moyu <xiahua.991116(a)qq.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 3ab6db2588d3..324d150d2b22 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -657,7 +657,6 @@ void hclge_mbx_handler(struct hclge_dev *hdev) unsigned int flag; int ret = 0; - memset(&resp_msg, 0, sizeof(resp_msg)); /* handle all the mailbox requests in the queue */ while (!hclge_cmd_crq_empty(&hdev->hw)) { if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) { @@ -685,6 +684,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev) trace_hclge_pf_mbx_get(hdev, req); + /* clear the resp_msg before processing every mailbox message */ + memset(&resp_msg, 0, sizeof(resp_msg)); + switch (req->msg.code) { case HCLGE_MBX_MAP_RING_TO_VECTOR: ret = hclge_map_unmap_ring_to_vf_vector(vport, true, -- 2.23.0

1 0

[PATCH openEuler-1.0-LTS 1/4] RDMA/ucma: Put a lock around every call to the rdma_cm layer
by Yang Yingliang 23 Jun '21

23 Jun '21

From: Jason Gunthorpe <jgg(a)mellanox.com> stable inclusion from linux-4.19.115 commit abc4ea7f1345398261295345fd9b30243e4f4f8e prepare for fixing CVE-2020-36385 -------------------------------- commit 7c11910783a1ea17e88777552ef146cace607b3c upstream. The rdma_cm must be used single threaded. This appears to be a bug in the design, as it does have lots of locking that seems like it should allow concurrency. However, when it is all said and done every single place that uses the cma_exch() scheme is broken, and all the unlocked reads from the ucma of the cm_id data are wrong too. syzkaller has been finding endless bugs related to this. Fixing this in any elegant way is some enormous amount of work. Take a very big hammer and put a mutex around everything to do with the ucma_context at the top of every syscall. Fixes: 75216638572f ("RDMA/cma: Export rdma cm interface to userspace") Link: https://lore.kernel.org/r/20200218210432.GA31966@ziepe.ca Reported-by: syzbot+adb15cf8c2798e4e0db4(a)syzkaller.appspotmail.com Reported-by: syzbot+e5579222b6a3edd96522(a)syzkaller.appspotmail.com Reported-by: syzbot+4b628fcc748474003457(a)syzkaller.appspotmail.com Reported-by: syzbot+29ee8f76017ce6cf03da(a)syzkaller.appspotmail.com Reported-by: syzbot+6956235342b7317ec564(a)syzkaller.appspotmail.com Reported-by: syzbot+b358909d8d01556b790b(a)syzkaller.appspotmail.com Reported-by: syzbot+6b46b135602a3f3ac99e(a)syzkaller.appspotmail.com Reported-by: syzbot+8458d13b13562abf6b77(a)syzkaller.appspotmail.com Reported-by: syzbot+bd034f3fdc0402e942ed(a)syzkaller.appspotmail.com Reported-by: syzbot+c92378b32760a4eef756(a)syzkaller.appspotmail.com Reported-by: syzbot+68b44a1597636e0b342c(a)syzkaller.appspotmail.com Signed-off-by: Jason Gunthorpe <jgg(a)mellanox.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/infiniband/core/ucma.c | 49 ++++++++++++++++++++++++++++++++-- 1 file changed, 47 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 01d68ed46c1b6..2acc30c3d5b2d 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -89,6 +89,7 @@ struct ucma_context { struct ucma_file *file; struct rdma_cm_id *cm_id; + struct mutex mutex; u64 uid; struct list_head list; @@ -215,6 +216,7 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) init_completion(&ctx->comp); INIT_LIST_HEAD(&ctx->mc_list); ctx->file = file; + mutex_init(&ctx->mutex); mutex_lock(&mut); ctx->id = idr_alloc(&ctx_idr, ctx, 0, 0, GFP_KERNEL); @@ -596,6 +598,7 @@ static int ucma_free_ctx(struct ucma_context *ctx) } events_reported = ctx->events_reported; + mutex_destroy(&ctx->mutex); kfree(ctx); return events_reported; } @@ -665,7 +668,10 @@ static ssize_t ucma_bind_ip(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr); + mutex_unlock(&ctx->mutex); + ucma_put_ctx(ctx); return ret; } @@ -688,7 +694,9 @@ static ssize_t ucma_bind(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -712,8 +720,10 @@ static ssize_t ucma_resolve_ip(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr, (struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -738,8 +748,10 @@ static ssize_t ucma_resolve_addr(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr, (struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -759,7 +771,9 @@ static ssize_t ucma_resolve_route(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_resolve_route(ctx->cm_id, cmd.timeout_ms); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -848,6 +862,7 @@ static ssize_t ucma_query_route(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); memset(&resp, 0, sizeof resp); addr = (struct sockaddr *) &ctx->cm_id->route.addr.src_addr; memcpy(&resp.src_addr, addr, addr->sa_family == AF_INET ? @@ -871,6 +886,7 @@ static ssize_t ucma_query_route(struct ucma_file *file, ucma_copy_iw_route(&resp, &ctx->cm_id->route); out: + mutex_unlock(&ctx->mutex); if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) ret = -EFAULT; @@ -1022,6 +1038,7 @@ static ssize_t ucma_query(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); switch (cmd.option) { case RDMA_USER_CM_QUERY_ADDR: ret = ucma_query_addr(ctx, response, out_len); @@ -1036,6 +1053,7 @@ static ssize_t ucma_query(struct ucma_file *file, ret = -ENOSYS; break; } + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; @@ -1076,7 +1094,9 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf, return PTR_ERR(ctx); ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param); + mutex_lock(&ctx->mutex); ret = rdma_connect(ctx->cm_id, &conn_param); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -1097,7 +1117,9 @@ static ssize_t ucma_listen(struct ucma_file *file, const char __user *inbuf, ctx->backlog = cmd.backlog > 0 && cmd.backlog < max_backlog ? cmd.backlog : max_backlog; + mutex_lock(&ctx->mutex); ret = rdma_listen(ctx->cm_id, ctx->backlog); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -1120,13 +1142,17 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, if (cmd.conn_param.valid) { ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param); mutex_lock(&file->mut); + mutex_lock(&ctx->mutex); ret = __rdma_accept(ctx->cm_id, &conn_param, NULL); + mutex_unlock(&ctx->mutex); if (!ret) ctx->uid = cmd.uid; mutex_unlock(&file->mut); - } else + } else { + mutex_lock(&ctx->mutex); ret = __rdma_accept(ctx->cm_id, NULL, NULL); - + mutex_unlock(&ctx->mutex); + } ucma_put_ctx(ctx); return ret; } @@ -1145,7 +1171,9 @@ static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_reject(ctx->cm_id, cmd.private_data, cmd.private_data_len); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -1164,7 +1192,9 @@ static ssize_t ucma_disconnect(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_disconnect(ctx->cm_id); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -1195,7 +1225,9 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file, resp.qp_attr_mask = 0; memset(&qp_attr, 0, sizeof qp_attr); qp_attr.qp_state = cmd.qp_state; + mutex_lock(&ctx->mutex); ret = rdma_init_qp_attr(ctx->cm_id, &qp_attr, &resp.qp_attr_mask); + mutex_unlock(&ctx->mutex); if (ret) goto out; @@ -1274,9 +1306,13 @@ static int ucma_set_ib_path(struct ucma_context *ctx, struct sa_path_rec opa; sa_convert_path_ib_to_opa(&opa, &sa_path); + mutex_lock(&ctx->mutex); ret = rdma_set_ib_path(ctx->cm_id, &opa); + mutex_unlock(&ctx->mutex); } else { + mutex_lock(&ctx->mutex); ret = rdma_set_ib_path(ctx->cm_id, &sa_path); + mutex_unlock(&ctx->mutex); } if (ret) return ret; @@ -1309,7 +1345,9 @@ static int ucma_set_option_level(struct ucma_context *ctx, int level, switch (level) { case RDMA_OPTION_ID: + mutex_lock(&ctx->mutex); ret = ucma_set_option_id(ctx, optname, optval, optlen); + mutex_unlock(&ctx->mutex); break; case RDMA_OPTION_IB: ret = ucma_set_option_ib(ctx, optname, optval, optlen); @@ -1369,8 +1407,10 @@ static ssize_t ucma_notify(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); if (ctx->cm_id->device) ret = rdma_notify(ctx->cm_id, (enum ib_event_type)cmd.event); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; @@ -1413,8 +1453,10 @@ static ssize_t ucma_process_join(struct ucma_file *file, mc->join_state = join_state; mc->uid = cmd->uid; memcpy(&mc->addr, addr, cmd->addr_size); + mutex_lock(&ctx->mutex); ret = rdma_join_multicast(ctx->cm_id, (struct sockaddr *)&mc->addr, join_state, mc); + mutex_unlock(&ctx->mutex); if (ret) goto err2; @@ -1518,7 +1560,10 @@ static ssize_t ucma_leave_multicast(struct ucma_file *file, goto out; } + mutex_lock(&mc->ctx->mutex); rdma_leave_multicast(mc->ctx->cm_id, (struct sockaddr *) &mc->addr); + mutex_unlock(&mc->ctx->mutex); + mutex_lock(&mc->ctx->file->mut); ucma_cleanup_mc_events(mc); list_del(&mc->list); -- 2.25.1

1 3

【Meeting Notice】openEuler kernel 技术分享第七期 & 双周例会 Time: 2021-06-25 14:00-18:00
by Meeting Book 23 Jun '21

23 Jun '21

1 0

[PATCH openEuler-1.0-LTS 1/4] RDMA/ucma: Put a lock around every call to the rdma_cm layer
by Yang Yingliang 23 Jun '21

23 Jun '21

From: Jason Gunthorpe <jgg(a)mellanox.com> stable inclusion from linux-4.19.115 commit abc4ea7f1345398261295345fd9b30243e4f4f8e prepare for fixing CVE-2021-32078 -------------------------------- commit 7c11910783a1ea17e88777552ef146cace607b3c upstream. The rdma_cm must be used single threaded. This appears to be a bug in the design, as it does have lots of locking that seems like it should allow concurrency. However, when it is all said and done every single place that uses the cma_exch() scheme is broken, and all the unlocked reads from the ucma of the cm_id data are wrong too. syzkaller has been finding endless bugs related to this. Fixing this in any elegant way is some enormous amount of work. Take a very big hammer and put a mutex around everything to do with the ucma_context at the top of every syscall. Fixes: 75216638572f ("RDMA/cma: Export rdma cm interface to userspace") Link: https://lore.kernel.org/r/20200218210432.GA31966@ziepe.ca Reported-by: syzbot+adb15cf8c2798e4e0db4(a)syzkaller.appspotmail.com Reported-by: syzbot+e5579222b6a3edd96522(a)syzkaller.appspotmail.com Reported-by: syzbot+4b628fcc748474003457(a)syzkaller.appspotmail.com Reported-by: syzbot+29ee8f76017ce6cf03da(a)syzkaller.appspotmail.com Reported-by: syzbot+6956235342b7317ec564(a)syzkaller.appspotmail.com Reported-by: syzbot+b358909d8d01556b790b(a)syzkaller.appspotmail.com Reported-by: syzbot+6b46b135602a3f3ac99e(a)syzkaller.appspotmail.com Reported-by: syzbot+8458d13b13562abf6b77(a)syzkaller.appspotmail.com Reported-by: syzbot+bd034f3fdc0402e942ed(a)syzkaller.appspotmail.com Reported-by: syzbot+c92378b32760a4eef756(a)syzkaller.appspotmail.com Reported-by: syzbot+68b44a1597636e0b342c(a)syzkaller.appspotmail.com Signed-off-by: Jason Gunthorpe <jgg(a)mellanox.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/infiniband/core/ucma.c | 49 ++++++++++++++++++++++++++++++++-- 1 file changed, 47 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 01d68ed46c1b6..2acc30c3d5b2d 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -89,6 +89,7 @@ struct ucma_context { struct ucma_file *file; struct rdma_cm_id *cm_id; + struct mutex mutex; u64 uid; struct list_head list; @@ -215,6 +216,7 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) init_completion(&ctx->comp); INIT_LIST_HEAD(&ctx->mc_list); ctx->file = file; + mutex_init(&ctx->mutex); mutex_lock(&mut); ctx->id = idr_alloc(&ctx_idr, ctx, 0, 0, GFP_KERNEL); @@ -596,6 +598,7 @@ static int ucma_free_ctx(struct ucma_context *ctx) } events_reported = ctx->events_reported; + mutex_destroy(&ctx->mutex); kfree(ctx); return events_reported; } @@ -665,7 +668,10 @@ static ssize_t ucma_bind_ip(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr); + mutex_unlock(&ctx->mutex); + ucma_put_ctx(ctx); return ret; } @@ -688,7 +694,9 @@ static ssize_t ucma_bind(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -712,8 +720,10 @@ static ssize_t ucma_resolve_ip(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr, (struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -738,8 +748,10 @@ static ssize_t ucma_resolve_addr(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr, (struct sockaddr *) &cmd.dst_addr, cmd.timeout_ms); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -759,7 +771,9 @@ static ssize_t ucma_resolve_route(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_resolve_route(ctx->cm_id, cmd.timeout_ms); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -848,6 +862,7 @@ static ssize_t ucma_query_route(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); memset(&resp, 0, sizeof resp); addr = (struct sockaddr *) &ctx->cm_id->route.addr.src_addr; memcpy(&resp.src_addr, addr, addr->sa_family == AF_INET ? @@ -871,6 +886,7 @@ static ssize_t ucma_query_route(struct ucma_file *file, ucma_copy_iw_route(&resp, &ctx->cm_id->route); out: + mutex_unlock(&ctx->mutex); if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) ret = -EFAULT; @@ -1022,6 +1038,7 @@ static ssize_t ucma_query(struct ucma_file *file, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); switch (cmd.option) { case RDMA_USER_CM_QUERY_ADDR: ret = ucma_query_addr(ctx, response, out_len); @@ -1036,6 +1053,7 @@ static ssize_t ucma_query(struct ucma_file *file, ret = -ENOSYS; break; } + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; @@ -1076,7 +1094,9 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf, return PTR_ERR(ctx); ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param); + mutex_lock(&ctx->mutex); ret = rdma_connect(ctx->cm_id, &conn_param); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -1097,7 +1117,9 @@ static ssize_t ucma_listen(struct ucma_file *file, const char __user *inbuf, ctx->backlog = cmd.backlog > 0 && cmd.backlog < max_backlog ? cmd.backlog : max_backlog; + mutex_lock(&ctx->mutex); ret = rdma_listen(ctx->cm_id, ctx->backlog); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -1120,13 +1142,17 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, if (cmd.conn_param.valid) { ucma_copy_conn_param(ctx->cm_id, &conn_param, &cmd.conn_param); mutex_lock(&file->mut); + mutex_lock(&ctx->mutex); ret = __rdma_accept(ctx->cm_id, &conn_param, NULL); + mutex_unlock(&ctx->mutex); if (!ret) ctx->uid = cmd.uid; mutex_unlock(&file->mut); - } else + } else { + mutex_lock(&ctx->mutex); ret = __rdma_accept(ctx->cm_id, NULL, NULL); - + mutex_unlock(&ctx->mutex); + } ucma_put_ctx(ctx); return ret; } @@ -1145,7 +1171,9 @@ static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_reject(ctx->cm_id, cmd.private_data, cmd.private_data_len); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -1164,7 +1192,9 @@ static ssize_t ucma_disconnect(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); ret = rdma_disconnect(ctx->cm_id); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; } @@ -1195,7 +1225,9 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file, resp.qp_attr_mask = 0; memset(&qp_attr, 0, sizeof qp_attr); qp_attr.qp_state = cmd.qp_state; + mutex_lock(&ctx->mutex); ret = rdma_init_qp_attr(ctx->cm_id, &qp_attr, &resp.qp_attr_mask); + mutex_unlock(&ctx->mutex); if (ret) goto out; @@ -1274,9 +1306,13 @@ static int ucma_set_ib_path(struct ucma_context *ctx, struct sa_path_rec opa; sa_convert_path_ib_to_opa(&opa, &sa_path); + mutex_lock(&ctx->mutex); ret = rdma_set_ib_path(ctx->cm_id, &opa); + mutex_unlock(&ctx->mutex); } else { + mutex_lock(&ctx->mutex); ret = rdma_set_ib_path(ctx->cm_id, &sa_path); + mutex_unlock(&ctx->mutex); } if (ret) return ret; @@ -1309,7 +1345,9 @@ static int ucma_set_option_level(struct ucma_context *ctx, int level, switch (level) { case RDMA_OPTION_ID: + mutex_lock(&ctx->mutex); ret = ucma_set_option_id(ctx, optname, optval, optlen); + mutex_unlock(&ctx->mutex); break; case RDMA_OPTION_IB: ret = ucma_set_option_ib(ctx, optname, optval, optlen); @@ -1369,8 +1407,10 @@ static ssize_t ucma_notify(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + mutex_lock(&ctx->mutex); if (ctx->cm_id->device) ret = rdma_notify(ctx->cm_id, (enum ib_event_type)cmd.event); + mutex_unlock(&ctx->mutex); ucma_put_ctx(ctx); return ret; @@ -1413,8 +1453,10 @@ static ssize_t ucma_process_join(struct ucma_file *file, mc->join_state = join_state; mc->uid = cmd->uid; memcpy(&mc->addr, addr, cmd->addr_size); + mutex_lock(&ctx->mutex); ret = rdma_join_multicast(ctx->cm_id, (struct sockaddr *)&mc->addr, join_state, mc); + mutex_unlock(&ctx->mutex); if (ret) goto err2; @@ -1518,7 +1560,10 @@ static ssize_t ucma_leave_multicast(struct ucma_file *file, goto out; } + mutex_lock(&mc->ctx->mutex); rdma_leave_multicast(mc->ctx->cm_id, (struct sockaddr *) &mc->addr); + mutex_unlock(&mc->ctx->mutex); + mutex_lock(&mc->ctx->file->mut); ucma_cleanup_mc_events(mc); list_del(&mc->list); -- 2.25.1

1 3

[PATCH kernel-4.19] mm/memory-failure: make sure wait for page writeback in memory_failure
by Yang Yingliang 22 Jun '21

22 Jun '21

From: yangerkun <yangerkun(a)huawei.com> mainline inclusion from mainline-5.13-rc7 commit e8675d291ac007e1c636870db880f837a9ea112a category: bugfix bugzilla: 51807 CVE: NA --------------------------- Our syzkaller trigger the "BUG_ON(!list_empty(&inode->i_wb_list))" in clear_inode: kernel BUG at fs/inode.c:519! Internal error: Oops - BUG: 0 [#1] SMP Modules linked in: Process syz-executor.0 (pid: 249, stack limit = 0x00000000a12409d7) CPU: 1 PID: 249 Comm: syz-executor.0 Not tainted 4.19.95 Hardware name: linux,dummy-virt (DT) pstate: 80000005 (Nzcv daif -PAN -UAO) pc : clear_inode+0x280/0x2a8 lr : clear_inode+0x280/0x2a8 Call trace: clear_inode+0x280/0x2a8 ext4_clear_inode+0x38/0xe8 ext4_free_inode+0x130/0xc68 ext4_evict_inode+0xb20/0xcb8 evict+0x1a8/0x3c0 iput+0x344/0x460 do_unlinkat+0x260/0x410 __arm64_sys_unlinkat+0x6c/0xc0 el0_svc_common+0xdc/0x3b0 el0_svc_handler+0xf8/0x160 el0_svc+0x10/0x218 Kernel panic - not syncing: Fatal exception A crash dump of this problem show that someone called __munlock_pagevec to clear page LRU without lock_page: do_mmap -> mmap_region -> do_munmap -> munlock_vma_pages_range -> __munlock_pagevec. As a result memory_failure will call identify_page_state without wait_on_page_writeback. And after truncate_error_page clear the mapping of this page. end_page_writeback won't call sb_clear_inode_writeback to clear inode->i_wb_list. That will trigger BUG_ON in clear_inode! Fix it by checking PageWriteback too to help determine should we skip wait_on_page_writeback. Link: https://lkml.kernel.org/r/20210604084705.3729204-1-yangerkun@huawei.com Fixes: 0bc1f8b0682c ("hwpoison: fix the handling path of the victimized page frame that belong to non-LRU") Signed-off-by: yangerkun <yangerkun(a)huawei.com> Acked-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Cc: Jan Kara <jack(a)suse.cz> Cc: Theodore Ts'o <tytso(a)mit.edu> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Yu Kuai <yukuai3(a)huawei.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/memory-failure.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 6fc0695f70e7c..145262227bb08 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1387,7 +1387,12 @@ int memory_failure(unsigned long pfn, int flags) return 0; } - if (!PageTransTail(p) && !PageLRU(p)) + /* + * __munlock_pagevec may clear a writeback page's LRU flag without + * page_lock. We need wait writeback completion for this page or it + * may trigger vfs BUG while evict inode. + */ + if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p)) goto identify_page_state; /* -- 2.25.1

1 0

[PATCH kernel-4.19] can: bcm: fix infoleak in struct bcm_msg_head
by Yang Yingliang 21 Jun '21

21 Jun '21

From: Norbert Slusarek <nslusarek(a)gmx.net> mainline inclusion from mainline-v5.13-rc7 commit 5e87ddbe3942e27e939bdc02deb8579b0cbd8ecc category: bugfix bugzilla: NA CVE: CVE-2021-34693 -------------------------------- On 64-bit systems, struct bcm_msg_head has an added padding of 4 bytes between struct members count and ival1. Even though all struct members are initialized, the 4-byte hole will contain data from the kernel stack. This patch zeroes out struct bcm_msg_head before usage, preventing infoleaks to userspace. Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol") Link: https://lore.kernel.org/r/trinity-7c1b2e82-e34f-4885-8060-2cd7a13769ce-1623… Cc: linux-stable <stable(a)vger.kernel.org> Signed-off-by: Norbert Slusarek <nslusarek(a)gmx.net> Acked-by: Oliver Hartkopp <socketcan(a)hartkopp.net> Signed-off-by: Marc Kleine-Budde <mkl(a)pengutronix.de> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/can/bcm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/can/bcm.c b/net/can/bcm.c index f5f97d9c17d20..0f09838ebef6e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -393,6 +393,7 @@ static void bcm_tx_timeout_tsklet(unsigned long data) if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; @@ -440,6 +441,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) /* this element is not throttled anymore */ data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV); + memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; @@ -554,6 +556,7 @@ static void bcm_rx_timeout_tsklet(unsigned long data) struct bcm_msg_head msg_head; /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS v2] iommu/vt-d: Add support for ACPI device use physical, node as pci device to establish identity mapping
by LeoLiuoc 21 Jun '21

21 Jun '21

When using ACPI device to create identity mapping, if the physical node of the ACPI device is a pci device, domain_1 will be created for these two devices. But if the pci device and other pci devices belong to another domain_2, this will happen conflict and destroy another domain. Such as PCI devices under the PCIE-to-PCI bridge. Therefore, when the physical node of the ACPI device is a PCI device, this patch uses the PCI device to create the domain. In this way, there is only one domain. Signed-off-by: LeoLiu-oc <LeoLiu-oc(a)zhaoxin.com> --- v1->v2: fix some logic mistake drivers/iommu/intel-iommu.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index e111e5d6d269..453ec0eb3a4f 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2736,12 +2736,33 @@ static int domain_prepare_identity_map(struct device *dev, return iommu_domain_identity_map(domain, start, end); } +static struct device *acpi_dev_find_pci_dev(struct device *dev) +{ + struct acpi_device_physical_node *pn; + struct acpi_device *adev; + + if (dev->bus == &acpi_bus_type) { + adev = to_acpi_device(dev); + mutex_lock(&adev->physical_node_lock); + list_for_each_entry(pn, &adev->physical_node_list, node) { + if (dev_is_pci(pn->dev)) { + mutex_unlock(&adev->physical_node_lock); + return pn->dev; + } + } + mutex_unlock(&adev->physical_node_lock); + } + + return dev; +} + static int iommu_prepare_identity_map(struct device *dev, unsigned long long start, unsigned long long end) { struct dmar_domain *domain; int ret; + dev = acpi_dev_find_pci_dev(dev); domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH); if (!domain) -- 2.20.1

2 1

[PATCH openEuler-21.03] neighbour: allow NUD_NOARP entries to be forced GCed
by qingyouzijin 19 Jun '21

19 Jun '21

From: David Ahern <dsahern(a)kernel.org> stable inclusion from stable-5.12.10 commit ddf088d7aaaaacfc836104f2e632b29b1d383cfc bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=326 CVE: NA -------------------------------- commit 7a6b1ab7475fd6478eeaf5c9d1163e7a18125c8f upstream. IFF_POINTOPOINT interfaces use NUD_NOARP entries for IPv6. It's possible to fill up the neighbour table with enough entries that it will overflow for valid connections after that. This behaviour is more prevalent after commit 58956317c8de ("neighbor: Improve garbage collection") is applied, as it prevents removal from entries that are not NUD_FAILED, unless they are more than 5s old. Fixes: 58956317c8de (neighbor: Improve garbage collection) Reported-by: Kasper Dupont <kasperd(a)gjkwv.06.feb.2021.kasperd.net> Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo(a)canonical.com> Signed-off-by: David Ahern <dsahern(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: qingyouzijin <2645753614(a)qq.com> --- net/core/neighbour.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2fe4bbb6b80c..d7f61d532371 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -235,6 +235,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || + (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || time_after(tref, n->updated)) -- 2.23.0

1 0

[PATCH openEuler-21.03] mt76: mt76x0e: fix device hang during suspend/resume stable inclusion from stable-5.12.10 commit d207c1e8e3fb82aca5ffd14c33d0848b6b820efc bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=205 CVE: NA
by moyu 19 Jun '21

19 Jun '21

From: Lorenzo Bianconi <lorenzo(a)kernel.org> ----------------------------------- [ Upstream commit 509559c35bcd23d5a046624b225cb3e99a9f1481 ] Similar to usb device, re-initialize mt76x0e device after resume in order to fix mt7630e hang during suspend/resume Reported-by: Luca Trombin <luca.trombin(a)gmail.com> Fixes: c2a4d9fbabfb9 ("mt76x0: inital split between pci and usb") Signed-off-by: Lorenzo Bianconi <lorenzo(a)kernel.org> Signed-off-by: Kalle Valo <kvalo(a)codeaurora.org> Link: https://lore.kernel.org/r/4812f9611624b34053c1592fd9c175b67d4ffcb4.16204060… Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: guodongxiu <xiahua.991116(a)qq.com> --- .../net/wireless/mediatek/mt76/mt76x0/pci.c | 81 ++++++++++++++++++- 1 file changed, 77 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c index b87d8e136cb9..a594ae11b1f7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c @@ -87,7 +87,7 @@ static const struct ieee80211_ops mt76x0e_ops = { .reconfig_complete = mt76x02_reconfig_complete, }; -static int mt76x0e_register_device(struct mt76x02_dev *dev) +static int mt76x0e_init_hardware(struct mt76x02_dev *dev, bool resume) { int err; @@ -100,9 +100,11 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) if (err < 0) return err; - err = mt76x02_dma_init(dev); - if (err < 0) - return err; + if (!resume) { + err = mt76x02_dma_init(dev); + if (err < 0) + return err; + } err = mt76x0_init_hardware(dev); if (err < 0) @@ -123,6 +125,17 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) mt76_clear(dev, 0x110, BIT(9)); mt76_set(dev, MT_MAX_LEN_CFG, BIT(13)); + return 0; +} + +static int mt76x0e_register_device(struct mt76x02_dev *dev) +{ + int err; + + err = mt76x0e_init_hardware(dev, false); + if (err < 0) + return err; + err = mt76x0_register_device(dev); if (err < 0) return err; @@ -167,6 +180,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) return ret; + mt76_pci_disable_aspm(pdev); + mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt76x0e_ops, &drv_ops); if (!mdev) @@ -220,6 +235,60 @@ mt76x0e_remove(struct pci_dev *pdev) mt76_free_device(mdev); } +#ifdef CONFIG_PM +static int mt76x0e_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct mt76_dev *mdev = pci_get_drvdata(pdev); + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + int i; + + mt76_worker_disable(&mdev->tx_worker); + for (i = 0; i < ARRAY_SIZE(mdev->phy.q_tx); i++) + mt76_queue_tx_cleanup(dev, mdev->phy.q_tx[i], true); + for (i = 0; i < ARRAY_SIZE(mdev->q_mcu); i++) + mt76_queue_tx_cleanup(dev, mdev->q_mcu[i], true); + napi_disable(&mdev->tx_napi); + + mt76_for_each_q_rx(mdev, i) + napi_disable(&mdev->napi[i]); + + mt76x02_dma_disable(dev); + mt76x02_mcu_cleanup(dev); + mt76x0_chip_onoff(dev, false, false); + + pci_enable_wake(pdev, pci_choose_state(pdev, state), true); + pci_save_state(pdev); + + return pci_set_power_state(pdev, pci_choose_state(pdev, state)); +} + +static int mt76x0e_resume(struct pci_dev *pdev) +{ + struct mt76_dev *mdev = pci_get_drvdata(pdev); + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + int err, i; + + err = pci_set_power_state(pdev, PCI_D0); + if (err) + return err; + + pci_restore_state(pdev); + + mt76_worker_enable(&mdev->tx_worker); + + mt76_for_each_q_rx(mdev, i) { + mt76_queue_rx_reset(dev, i); + napi_enable(&mdev->napi[i]); + napi_schedule(&mdev->napi[i]); + } + + napi_enable(&mdev->tx_napi); + napi_schedule(&mdev->tx_napi); + + return mt76x0e_init_hardware(dev, true); +} +#endif /* CONFIG_PM */ + static const struct pci_device_id mt76x0e_device_table[] = { { PCI_DEVICE(0x14c3, 0x7610) }, { PCI_DEVICE(0x14c3, 0x7630) }, @@ -237,6 +306,10 @@ static struct pci_driver mt76x0e_driver = { .id_table = mt76x0e_device_table, .probe = mt76x0e_probe, .remove = mt76x0e_remove, +#ifdef CONFIG_PM + .suspend = mt76x0e_suspend, + .resume = mt76x0e_resume, +#endif /* CONFIG_PM */ }; module_pci_driver(mt76x0e_driver); -- 2.23.0

1 0

[PATCH openEuler-21.03] mt76: mt76x0e: fix device hang during suspend/resume stable inclusion from stable-5.12.10 commit d207c1e8e3fb82aca5ffd14c33d0848b6b820efc bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=205 CVE: NA [ Upstream commit 509559c35bcd23d5a046624b225cb3e99a9f1481 ]
by guodongxiu 19 Jun '21

19 Jun '21

From: Lorenzo Bianconi <lorenzo(a)kernel.org> Similar to usb device, re-initialize mt76x0e device after resume in order to fix mt7630e hang during suspend/resume Reported-by: Luca Trombin <luca.trombin(a)gmail.com> Fixes: c2a4d9fbabfb9 ("mt76x0: inital split between pci and usb") Signed-off-by: Lorenzo Bianconi <lorenzo(a)kernel.org> Signed-off-by: Kalle Valo <kvalo(a)codeaurora.org> Link: https://lore.kernel.org/r/4812f9611624b34053c1592fd9c175b67d4ffcb4.16204060… Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: guodongxiu <xiahua.991116(a)qq.com> --- .../net/wireless/mediatek/mt76/mt76x0/pci.c | 81 ++++++++++++++++++- 1 file changed, 77 insertions(+), 4 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c index b87d8e136cb9..a594ae11b1f7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c @@ -87,7 +87,7 @@ static const struct ieee80211_ops mt76x0e_ops = { .reconfig_complete = mt76x02_reconfig_complete, }; -static int mt76x0e_register_device(struct mt76x02_dev *dev) +static int mt76x0e_init_hardware(struct mt76x02_dev *dev, bool resume) { int err; @@ -100,9 +100,11 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) if (err < 0) return err; - err = mt76x02_dma_init(dev); - if (err < 0) - return err; + if (!resume) { + err = mt76x02_dma_init(dev); + if (err < 0) + return err; + } err = mt76x0_init_hardware(dev); if (err < 0) @@ -123,6 +125,17 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) mt76_clear(dev, 0x110, BIT(9)); mt76_set(dev, MT_MAX_LEN_CFG, BIT(13)); + return 0; +} + +static int mt76x0e_register_device(struct mt76x02_dev *dev) +{ + int err; + + err = mt76x0e_init_hardware(dev, false); + if (err < 0) + return err; + err = mt76x0_register_device(dev); if (err < 0) return err; @@ -167,6 +180,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) return ret; + mt76_pci_disable_aspm(pdev); + mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt76x0e_ops, &drv_ops); if (!mdev) @@ -220,6 +235,60 @@ mt76x0e_remove(struct pci_dev *pdev) mt76_free_device(mdev); } +#ifdef CONFIG_PM +static int mt76x0e_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct mt76_dev *mdev = pci_get_drvdata(pdev); + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + int i; + + mt76_worker_disable(&mdev->tx_worker); + for (i = 0; i < ARRAY_SIZE(mdev->phy.q_tx); i++) + mt76_queue_tx_cleanup(dev, mdev->phy.q_tx[i], true); + for (i = 0; i < ARRAY_SIZE(mdev->q_mcu); i++) + mt76_queue_tx_cleanup(dev, mdev->q_mcu[i], true); + napi_disable(&mdev->tx_napi); + + mt76_for_each_q_rx(mdev, i) + napi_disable(&mdev->napi[i]); + + mt76x02_dma_disable(dev); + mt76x02_mcu_cleanup(dev); + mt76x0_chip_onoff(dev, false, false); + + pci_enable_wake(pdev, pci_choose_state(pdev, state), true); + pci_save_state(pdev); + + return pci_set_power_state(pdev, pci_choose_state(pdev, state)); +} + +static int mt76x0e_resume(struct pci_dev *pdev) +{ + struct mt76_dev *mdev = pci_get_drvdata(pdev); + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + int err, i; + + err = pci_set_power_state(pdev, PCI_D0); + if (err) + return err; + + pci_restore_state(pdev); + + mt76_worker_enable(&mdev->tx_worker); + + mt76_for_each_q_rx(mdev, i) { + mt76_queue_rx_reset(dev, i); + napi_enable(&mdev->napi[i]); + napi_schedule(&mdev->napi[i]); + } + + napi_enable(&mdev->tx_napi); + napi_schedule(&mdev->tx_napi); + + return mt76x0e_init_hardware(dev, true); +} +#endif /* CONFIG_PM */ + static const struct pci_device_id mt76x0e_device_table[] = { { PCI_DEVICE(0x14c3, 0x7610) }, { PCI_DEVICE(0x14c3, 0x7630) }, @@ -237,6 +306,10 @@ static struct pci_driver mt76x0e_driver = { .id_table = mt76x0e_device_table, .probe = mt76x0e_probe, .remove = mt76x0e_remove, +#ifdef CONFIG_PM + .suspend = mt76x0e_suspend, + .resume = mt76x0e_resume, +#endif /* CONFIG_PM */ }; module_pci_driver(mt76x0e_driver); -- 2.23.0

1 0

[PATCH openEuler-21.03] netfilter: nf_tables: missing error reporting for not selected expressions table inclusion from stable-21.03 commit 2682184605848ae28866bf71c7d4774bda7badfc bugzilla:https://bugzilla.openeuler.org/show_bug.cgi?id=324 CVE: NA
by fanxingin 19 Jun '21

19 Jun '21

From: Pablo Neira Ayuso <pablo(a)netfilter.org> -------------------------------- commit c781471d67a56d7d4c113669a11ede0463b5c719 upstream. Sometimes users forget to turn on nftables extensions from Kconfig that they need. In such case, the error reporting from userspace is misleading: $ sudo nft add rule x y counter Error: Could not process rule: No such file or directory add rule x y counter ^^^^^^^^^^^^^^^^^^^^ Add missing NL_SET_BAD_ATTR() to provide a hint: $ nft add rule x y counter Error: Could not process rule: No such file or directory add rule x y counter ^^^^^^^ Fixes: 83d9dcba06c5 ("netfilter: nf_tables: extended netlink error reporting for expressions") Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: fanxingin <fanxingin(a)qq.com> --- net/netfilter/nf_tables_api.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9a080767667b..168c87c1ac75 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3263,8 +3263,10 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, if (n == NFT_RULE_MAXEXPRS) goto err1; err = nf_tables_expr_parse(&ctx, tmp, &info[n]); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, tmp); goto err1; + } size += info[n].ops->size; n++; } -- 2.23.0

1 0

[PATCH openEuler-21.03] net: hns3: fix incorrect resp_msg issue
by lovelonelytime 19 Jun '21

19 Jun '21

From: Jiaran Zhang <zhangjiaran(a)huawei.com> stable inclusion from stable-21.03 commit d207c1e8e3fb82aca5ffd14c33d0848b6b820efc bugzilla: https://bugzilla.openeuler.org/show_bug.cgi?id=205 CVE: NA [ Upstream commit a710b9ffbebaf713f7dbd4dbd9524907e5d66f33 ] In hclge_mbx_handler(), if there are two consecutive mailbox messages that requires resp_msg, the resp_msg is not cleared after processing the first message, which will cause the resp_msg data of second message incorrect. Fix it by clearing the resp_msg before processing every mailbox message. Fixes: bb5790b71bad ("net: hns3: refactor mailbox response scheme between PF and VF") Signed-off-by: Jiaran Zhang <zhangjiaran(a)huawei.com> Signed-off-by: Huazhong Tan <tanhuazhong(a)huawei.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: lovelonelytime <1390751361(a)qq.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 3ab6db2588d3..324d150d2b22 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -657,7 +657,6 @@ void hclge_mbx_handler(struct hclge_dev *hdev) unsigned int flag; int ret = 0; - memset(&resp_msg, 0, sizeof(resp_msg)); /* handle all the mailbox requests in the queue */ while (!hclge_cmd_crq_empty(&hdev->hw)) { if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) { @@ -685,6 +684,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev) trace_hclge_pf_mbx_get(hdev, req); + /* clear the resp_msg before processing every mailbox message */ + memset(&resp_msg, 0, sizeof(resp_msg)); + switch (req->msg.code) { case HCLGE_MBX_MAP_RING_TO_VECTOR: ret = hclge_map_unmap_ring_to_vf_vector(vport, true, -- 2.23.0

1 0