From 7b20238d28da46f394d37d4d51cc420e1ff9414a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sun, 27 Oct 2019 22:10:36 +0300 Subject: io_uring: Fix leaked shadow_req io_queue_link_head() owns shadow_req after taking it as an argument. By not freeing it in case of an error, it can leak the request along with taken ctx->refs. Reviewed-by: Jackie Liu Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index a30c4f622cb3..ba1431046c98 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2413,6 +2413,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req, if (ret) { if (ret != -EIOCBQUEUED) { io_free_req(req); + __io_free_req(shadow); io_cqring_add_event(ctx, s->sqe->user_data, ret); return 0; } -- cgit From 044c1ab399afbe9f2ebef49a3204ef1509826dc7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 28 Oct 2019 09:15:33 -0600 Subject: io_uring: don't touch ctx in setup after ring fd install syzkaller reported an issue where it looks like a malicious app can trigger a use-after-free of reading the ctx ->sq_array and ->rings value right after having installed the ring fd in the process file table. Defer ring fd installation until after we're done reading those values. Fixes: 75b28affdd6a ("io_uring: allocate the two rings together") Reported-by: syzbot+6f03d895a6cd0d06187f@syzkaller.appspotmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index ba1431046c98..c11c4157a4c2 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3829,10 +3829,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret) goto err; - ret = io_uring_get_fd(ctx); - if (ret < 0) - goto err; - memset(&p->sq_off, 0, sizeof(p->sq_off)); p->sq_off.head = offsetof(struct io_rings, sq.head); p->sq_off.tail = offsetof(struct io_rings, sq.tail); @@ -3850,6 +3846,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); p->cq_off.cqes = offsetof(struct io_rings, cqes); + /* + * Install ring fd as the very last thing, so we don't risk someone + * having closed it before we finish setup + */ + ret = io_uring_get_fd(ctx); + if (ret < 0) + goto err; + p->features = IORING_FEAT_SINGLE_MMAP; return ret; err: -- cgit From af8fd0424713a2adb812d10d55e86718152cf656 Mon Sep 17 00:00:00 2001 From: Anton Eidelman Date: Fri, 18 Oct 2019 11:32:50 -0700 Subject: nvme-multipath: fix possible io hang after ctrl reconnect The following scenario results in an IO hang: 1) ctrl completes a request with NVME_SC_ANA_TRANSITION. NVME_NS_ANA_PENDING bit in ns->flags is set and ana_work is triggered. 2) ana_work: nvme_read_ana_log() tries to get the ANA log page from the ctrl. This fails because ctrl disconnects. Therefore nvme_update_ns_ana_state() is not called and NVME_NS_ANA_PENDING bit in ns->flags is not cleared. 3) ctrl reconnects: nvme_mpath_init(ctrl,...) calls nvme_read_ana_log(ctrl, groups_only=true). However, nvme_update_ana_state() does not update namespaces because nr_nsids = 0 (due to groups_only mode). 4) scan_work calls nvme_validate_ns() finds the ns and re-validates OK. Result: The ctrl is now live but NVME_NS_ANA_PENDING bit in ns->flags is still set. Consequently ctrl will never be considered a viable path by __nvme_find_path(). IO will hang if ctrl is the only or the last path to the namespace. More generally, while ctrl is reconnecting, its ANA state may change. And because nvme_mpath_init() requests ANA log in groups_only mode, these changes are not propagated to the existing ctrl namespaces. This may result in a mal-function or an IO hang. Solution: nvme_mpath_init() will nvme_read_ana_log() with groups_only set to false. This will not harm the new ctrl case (no namespaces present), and will make sure the ANA state of namespaces gets updated after reconnect. Note: Another option would be for nvme_mpath_init() to invoke nvme_parse_ana_log(..., nvme_set_ns_ana_state) for each existing namespace. Reviewed-by: Sagi Grimberg Signed-off-by: Anton Eidelman Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- drivers/nvme/host/multipath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 30de7efef003..d320684d25b2 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -715,7 +715,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) goto out; } - error = nvme_read_ana_log(ctrl, true); + error = nvme_read_ana_log(ctrl, false); if (error) goto out_free_ana_log_buf; return 0; -- cgit From 86cccfbf773fafb88898c5627aa3727b02bc4708 Mon Sep 17 00:00:00 2001 From: Anton Eidelman Date: Fri, 18 Oct 2019 11:32:51 -0700 Subject: nvme-multipath: remove unused groups_only mode in ana log groups_only mode in nvme_read_ana_log() is no longer used: remove it. Reviewed-by: Sagi Grimberg Signed-off-by: Anton Eidelman Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- drivers/nvme/host/multipath.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index d320684d25b2..fc99a40c1ec4 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -522,14 +522,13 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl, return 0; } -static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only) +static int nvme_read_ana_log(struct nvme_ctrl *ctrl) { u32 nr_change_groups = 0; int error; mutex_lock(&ctrl->ana_lock); - error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, - groups_only ? NVME_ANA_LOG_RGO : 0, + error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0, ctrl->ana_log_buf, ctrl->ana_log_size, 0); if (error) { dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error); @@ -565,7 +564,7 @@ static void nvme_ana_work(struct work_struct *work) { struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work); - nvme_read_ana_log(ctrl, false); + nvme_read_ana_log(ctrl); } static void nvme_anatt_timeout(struct timer_list *t) @@ -715,7 +714,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) goto out; } - error = nvme_read_ana_log(ctrl, false); + error = nvme_read_ana_log(ctrl); if (error) goto out_free_ana_log_buf; return 0; -- cgit From d848074b2f1eb11a38691285f7366bce83087014 Mon Sep 17 00:00:00 2001 From: Anton Ivanov Date: Tue, 29 Oct 2019 09:13:34 +0000 Subject: um-ubd: Entrust re-queue to the upper layers Fixes crashes due to ubd requeue logic conflicting with the block-mq logic. Crash is reproducible in 5.0 - 5.3. Fixes: 53766defb8c8 ("um: Clean-up command processing in UML UBD driver") Cc: stable@vger.kernel.org # v5.0+ Signed-off-by: Anton Ivanov Signed-off-by: Jens Axboe --- arch/um/drivers/ubd_kern.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 612535cd9706..6627d7c30f37 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1403,8 +1403,12 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, spin_unlock_irq(&ubd_dev->lock); - if (ret < 0) - blk_mq_requeue_request(req, true); + if (ret < 0) { + if (ret == -ENOMEM) + res = BLK_STS_RESOURCE; + else + res = BLK_STS_DEV_RESOURCE; + } return res; } -- cgit From 6873e0bd6a9cb14ecfadd89d9ed9698ff1761902 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 30 Oct 2019 13:53:09 -0600 Subject: io_uring: ensure we clear io_kiocb->result before each issue We use io_kiocb->result == -EAGAIN as a way to know if we need to re-submit a polled request, as -EAGAIN reporting happens out-of-line for IO submission failures. This field is cleared when we originally allocate the request, but it isn't reset when we retry the submission from async context. This can cause issues where we think something needs a re-issue, but we're really just reading stale data. Reset ->result whenever we re-prep a request for polled submission. Cc: stable@vger.kernel.org Fixes: 9e645e1105ca ("io_uring: add support for sqe links") Reported-by: Bijan Mottahedeh Signed-off-by: Jens Axboe --- fs/io_uring.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/io_uring.c b/fs/io_uring.c index c11c4157a4c2..f9a38998f2fc 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1124,6 +1124,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, kiocb->ki_flags |= IOCB_HIPRI; kiocb->ki_complete = io_complete_rw_iopoll; + req->result = 0; } else { if (kiocb->ki_flags & IOCB_HIPRI) return -EINVAL; -- cgit From 41591a51f00d2dc7bb9dc6e9bedf56c5cf6f2392 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 31 Oct 2019 13:53:41 +0300 Subject: iocost: don't nest spin_lock_irq in ioc_weight_write() This code causes a static analysis warning: block/blk-iocost.c:2113 ioc_weight_write() error: double lock 'irq' We disable IRQs in blkg_conf_prep() and re-enable them in blkg_conf_finish(). IRQ disable/enable should not be nested because that means the IRQs will be enabled at the first unlock instead of the second one. Fixes: 7caa47151ab2 ("blkcg: implement blk-iocost") Acked-by: Tejun Heo Signed-off-by: Dan Carpenter Signed-off-by: Jens Axboe --- block/blk-iocost.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 2a3db80c1dce..a7ed434eae03 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2110,10 +2110,10 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf, goto einval; } - spin_lock_irq(&iocg->ioc->lock); + spin_lock(&iocg->ioc->lock); iocg->cfg_weight = v; weight_updated(iocg); - spin_unlock_irq(&iocg->ioc->lock); + spin_unlock(&iocg->ioc->lock); blkg_conf_finish(&ctx); return nbytes; -- cgit