From f482aa98652795846cc55da98ebe331eb74f3d0b Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Wed, 3 Aug 2022 15:23:43 -0700 Subject: audit, io_uring, io-wq: Fix memory leak in io_sq_thread() and io_wqe_worker() Currently @audit_context is allocated twice for io_uring workers: 1. copy_process() calls audit_alloc(); 2. io_sq_thread() or io_wqe_worker() calls audit_alloc_kernel() (which is effectively audit_alloc()) and overwrites @audit_context, causing: BUG: memory leak unreferenced object 0xffff888144547400 (size 1024): <...> hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 01 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] audit_alloc+0x133/0x210 [] copy_process+0xcd3/0x2340 [] create_io_thread+0x63/0x90 [] create_io_worker+0xb4/0x230 [] io_wqe_enqueue+0x248/0x3b0 [] io_queue_iowq+0xba/0x200 [] io_queue_async+0x113/0x180 [] io_req_task_submit+0x18f/0x1a0 [] io_apoll_task_func+0xdd/0x120 [] tctx_task_work+0x11f/0x570 [] task_work_run+0x7e/0xc0 [] get_signal+0xc18/0xf10 [] arch_do_signal_or_restart+0x2b/0x730 [] exit_to_user_mode_prepare+0x5e/0x180 [] syscall_exit_to_user_mode+0x12/0x20 [] do_syscall_64+0x40/0x80 Then, 3. io_sq_thread() or io_wqe_worker() frees @audit_context using audit_free(); 4. do_exit() eventually calls audit_free() again, which is okay because audit_free() does a NULL check. As suggested by Paul Moore, fix it by deleting audit_alloc_kernel() and redundant audit_free() calls. Fixes: 5bd2182d58e9 ("audit,io_uring,io-wq: add some basic audit support to io_uring") Suggested-by: Paul Moore Cc: stable@vger.kernel.org Signed-off-by: Peilin Ye Acked-by: Paul Moore Link: https://lore.kernel.org/r/20220803222343.31673-1-yepeilin.cs@gmail.com Signed-off-by: Jens Axboe --- include/linux/audit.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 00f7a80f1a3e..3608992848d3 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -285,7 +285,6 @@ static inline int audit_signal_info(int sig, struct task_struct *t) /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); -extern int audit_alloc_kernel(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_uring_entry(u8 op); extern void __audit_uring_exit(int success, long code); @@ -578,10 +577,6 @@ static inline int audit_alloc(struct task_struct *task) { return 0; } -static inline int audit_alloc_kernel(struct task_struct *task) -{ - return 0; -} static inline void audit_free(struct task_struct *task) { } static inline void audit_uring_entry(u8 op) -- cgit v1.2.3 From 46dae32fe625a75f549c3a70edc77b778197bb05 Mon Sep 17 00:00:00 2001 From: Youngmin Nam Date: Tue, 12 Jul 2022 18:47:15 +0900 Subject: time: Correct the prototype of ns_to_kernel_old_timeval and ns_to_timespec64 In ns_to_kernel_old_timeval() definition, the function argument is defined with const identifier in kernel/time/time.c, but the prototype in include/linux/time32.h looks different. - The function is defined in kernel/time/time.c as below: struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec) - The function is decalared in include/linux/time32.h as below: extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec); Because the variable of arithmethic types isn't modified in the calling scope, there's no need to mark arguments as const, which was already mentioned during review (Link[1) of the original patch. Likewise remove the "const" keyword in both definition and declaration of ns_to_timespec64() as requested by Arnd (Link[2]). Fixes: a84d1169164b ("y2038: Introduce struct __kernel_old_timeval") Signed-off-by: Youngmin Nam Signed-off-by: Thomas Gleixner Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/all/20220712094715.2918823-1-youngmin.nam@samsung.com Link[1]: https://lore.kernel.org/all/20180310081123.thin6wphgk7tongy@gmail.com/ Link[2]: https://lore.kernel.org/all/CAK8P3a3nknJgEDESGdJH91jMj6R_xydFqWASd8r5BbesdvMBgA@mail.gmail.com/ --- include/linux/time64.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/time64.h b/include/linux/time64.h index 2fb8232cff1d..f1bcea8c124a 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -145,7 +145,7 @@ static inline s64 timespec64_to_ns(const struct timespec64 *ts) * * Returns the timespec64 representation of the nsec parameter. */ -extern struct timespec64 ns_to_timespec64(const s64 nsec); +extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 -- cgit v1.2.3 From c2a052a4a949df53f50a5024843432d2234cb824 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Fri, 24 Jun 2022 10:55:41 +0800 Subject: remoteproc: rename len of rpoc_vring to num Rename the member len in the structure rpoc_vring to num. And remove 'in bytes' from the comment of it. This is misleading. Because this actually refers to the size of the virtio vring to be created. The unit is not bytes. Signed-off-by: Xuan Zhuo Message-Id: <20220624025621.128843-2-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/remoteproc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 7c943f0a2fc4..aea79c77db0f 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -597,7 +597,7 @@ struct rproc_subdev { /** * struct rproc_vring - remoteproc vring state * @va: virtual address - * @len: length, in bytes + * @num: vring size * @da: device address * @align: vring alignment * @notifyid: rproc-specific unique vring index @@ -606,7 +606,7 @@ struct rproc_subdev { */ struct rproc_vring { void *va; - int len; + int num; u32 da; u32 align; int notifyid; -- cgit v1.2.3 From da802961832f9852886304290135457519815497 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:21 +0800 Subject: virtio: record the maximum queue num supported by the device. virtio-net can display the maximum (supported by hardware) ring size in ethtool -g eth0. When the subsequent patch implements vring reset, it can judge whether the ring size passed by the driver is legal based on this. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-2-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index d8fdf170637c..129bde7521e3 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -19,6 +19,7 @@ * @priv: a pointer for the virtqueue implementation to use. * @index: the zero-based ordinal number for this queue. * @num_free: number of elements we expect to be able to fit. + * @num_max: the maximum number of elements supported by the device. * * A note on @num_free: with indirect buffers, each buffer needs one * element in the queue, otherwise a buffer will need one element per @@ -31,6 +32,7 @@ struct virtqueue { struct virtio_device *vdev; unsigned int index; unsigned int num_free; + unsigned int num_max; void *priv; }; -- cgit v1.2.3 From 3086e9fc9173166774652a488467e4176ee1c81b Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:22 +0800 Subject: virtio: struct virtio_config_ops add callbacks for queue_reset reset can be divided into the following four steps (example): 1. transport: notify the device to reset the queue 2. vring: recycle the buffer submitted 3. vring: reset/resize the vring (may re-alloc) 4. transport: mmap vring to device, and enable the queue In order to support queue reset, add two callbacks in struct virtio_config_ops to implement steps 1 and 4. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-3-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index b47c2e7ed0ee..36ec7be1f480 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -78,6 +78,18 @@ struct virtio_shm_region { * @set_vq_affinity: set the affinity for a virtqueue (optional). * @get_vq_affinity: get the affinity for a virtqueue (optional). * @get_shm_region: get a shared memory region based on the index. + * @disable_vq_and_reset: reset a queue individually (optional). + * vq: the virtqueue + * Returns 0 on success or error status + * disable_vq_and_reset will guarantee that the callbacks are disabled and + * synchronized. + * Except for the callback, the caller should guarantee that the vring is + * not accessed by any functions of virtqueue. + * @enable_vq_after_reset: enable a reset queue + * vq: the virtqueue + * Returns 0 on success or error status + * If disable_vq_and_reset is set, then enable_vq_after_reset must also be + * set. */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { @@ -104,6 +116,8 @@ struct virtio_config_ops { int index); bool (*get_shm_region)(struct virtio_device *vdev, struct virtio_shm_region *region, u8 id); + int (*disable_vq_and_reset)(struct virtqueue *vq); + int (*enable_vq_after_reset)(struct virtqueue *vq); }; /* If driver didn't advertise the feature, it will never appear. */ -- cgit v1.2.3 From 07d9629d49584b6f79faa6158cd7aef7e6919703 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:27 +0800 Subject: virtio_ring: split: stop __vring_new_virtqueue as export symbol There is currently only one place to reference __vring_new_virtqueue() directly from the outside of virtio core. And here vring_new_virtqueue() can be used instead. Subsequent patches will modify __vring_new_virtqueue, so stop it as an export symbol for now. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-8-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_ring.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index b485b13fa50b..8b8af1a38991 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -76,16 +76,6 @@ struct virtqueue *vring_create_virtqueue(unsigned int index, void (*callback)(struct virtqueue *vq), const char *name); -/* Creates a virtqueue with a custom layout. */ -struct virtqueue *__vring_new_virtqueue(unsigned int index, - struct vring vring, - struct virtio_device *vdev, - bool weak_barriers, - bool ctx, - bool (*notify)(struct virtqueue *), - void (*callback)(struct virtqueue *), - const char *name); - /* * Creates a virtqueue with a standard layout but a caller-allocated * ring. -- cgit v1.2.3 From c790e8e1817f1a17c05e64f1c4f16f231b8529d5 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:44 +0800 Subject: virtio_ring: introduce virtqueue_resize() Introduce virtqueue_resize() to implement the resize of vring. Based on these, the driver can dynamically adjust the size of the vring. For example: ethtool -G. virtqueue_resize() implements resize based on the vq reset function. In case of failure to allocate a new vring, it will give up resize and use the original vring. During this process, if the re-enable reset vq fails, the vq can no longer be used. Although the probability of this situation is not high. The parameter recycle is used to recycle the buffer that is no longer used. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-25-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 129bde7521e3..62e31bca5602 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -91,6 +91,9 @@ dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq); dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq); dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq); +int virtqueue_resize(struct virtqueue *vq, u32 num, + void (*recycle)(struct virtqueue *vq, void *buf)); + /** * virtio_device - representation of a device using virtio * @index: unique position on the virtio bus -- cgit v1.2.3 From ea024594b1dc5b6719c1400ae154690f5c203996 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:45 +0800 Subject: virtio_pci: struct virtio_pci_common_cfg add queue_notify_data Add queue_notify_data in struct virtio_pci_common_cfg, which comes from here https://github.com/oasis-tcs/virtio-spec/issues/89 In order not to affect the API, add a dedicated structure struct virtio_pci_modern_common_cfg to virtio_pci_modern.h. Since I want to add queue_reset after queue_notify_data, I submitted this patch first. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-26-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_pci_modern.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index eb2bd9b4077d..41f5a018bd94 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -5,6 +5,13 @@ #include #include +struct virtio_pci_modern_common_cfg { + struct virtio_pci_common_cfg cfg; + + __le16 queue_notify_data; /* read-write */ + __le16 padding; +}; + struct virtio_pci_modern_device { struct pci_dev *pci_dev; -- cgit v1.2.3 From 3251063155032729b8793ac3957136ae25c0bafa Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:46 +0800 Subject: virtio: allow to unbreak/break virtqueue individually This patch allows the new introduced __virtqueue_break()/__virtqueue_unbreak() to break/unbreak the virtqueue. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-27-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 62e31bca5602..d45ee82a4470 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -138,6 +138,9 @@ bool is_virtio_device(struct device *dev); void virtio_break_device(struct virtio_device *dev); void __virtio_unbreak_device(struct virtio_device *dev); +void __virtqueue_break(struct virtqueue *_vq); +void __virtqueue_unbreak(struct virtqueue *_vq); + void virtio_config_changed(struct virtio_device *dev); #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); -- cgit v1.2.3 From 4913e85441b40386c4bb093f188b955d8165f1b7 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:48 +0800 Subject: virtio_ring: struct virtqueue introduce reset Introduce a new member reset to the structure virtqueue to determine whether the current vq is in the reset state. Subsequent patches will use it. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-29-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index d45ee82a4470..a3f73bb6733e 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -20,6 +20,7 @@ * @index: the zero-based ordinal number for this queue. * @num_free: number of elements we expect to be able to fit. * @num_max: the maximum number of elements supported by the device. + * @reset: vq is in reset state or not. * * A note on @num_free: with indirect buffers, each buffer needs one * element in the queue, otherwise a buffer will need one element per @@ -34,6 +35,7 @@ struct virtqueue { unsigned int num_free; unsigned int num_max; void *priv; + bool reset; }; int virtqueue_add_outbuf(struct virtqueue *vq, -- cgit v1.2.3 From 0cdd450e70510c9e13af8099e9f6c1467e6a0b91 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:49 +0800 Subject: virtio_pci: struct virtio_pci_common_cfg add queue_reset Add queue_reset in virtio_pci_modern_common_cfg. https://github.com/oasis-tcs/virtio-spec/issues/124 https://github.com/oasis-tcs/virtio-spec/issues/139 Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-30-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_pci_modern.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index 41f5a018bd94..05123b9a606f 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -9,7 +9,7 @@ struct virtio_pci_modern_common_cfg { struct virtio_pci_common_cfg cfg; __le16 queue_notify_data; /* read-write */ - __le16 padding; + __le16 queue_reset; /* read-write */ }; struct virtio_pci_modern_device { -- cgit v1.2.3 From 0b50cece0b7857732d2055f2c77f8730c10f9196 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:50 +0800 Subject: virtio_pci: introduce helper to get/set queue reset Introduce new helpers to implement queue reset and get queue reset status. https://github.com/oasis-tcs/virtio-spec/issues/124 https://github.com/oasis-tcs/virtio-spec/issues/139 Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-31-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_pci_modern.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h index 05123b9a606f..c4eeb79b0139 100644 --- a/include/linux/virtio_pci_modern.h +++ b/include/linux/virtio_pci_modern.h @@ -113,4 +113,6 @@ void __iomem * vp_modern_map_vq_notify(struct virtio_pci_modern_device *mdev, u16 index, resource_size_t *pa); int vp_modern_probe(struct virtio_pci_modern_device *mdev); void vp_modern_remove(struct virtio_pci_modern_device *mdev); +int vp_modern_get_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); +void vp_modern_set_queue_reset(struct virtio_pci_modern_device *mdev, u16 index); #endif -- cgit v1.2.3 From a10fba0377145fccefea4dc4dd5915b7ed87e546 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:53 +0800 Subject: virtio: find_vqs() add arg sizes find_vqs() adds a new parameter sizes to specify the size of each vq vring. NULL as sizes means that all queues in find_vqs() use the maximum size. A value in the array is 0, which means that the corresponding queue uses the maximum size. In the split scenario, the meaning of size is the largest size, because it may be limited by memory, the virtio core will try a smaller size. And the size is power of 2. Signed-off-by: Xuan Zhuo Acked-by: Hans de Goede Reviewed-by: Mathieu Poirier Acked-by: Jason Wang Message-Id: <20220801063902.129329-34-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 36ec7be1f480..888f7e96f0c7 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -55,6 +55,7 @@ struct virtio_shm_region { * include a NULL entry for vqs that do not need a callback * names: array of virtqueue names (mainly for debugging) * include a NULL entry for vqs unused by driver + * sizes: array of virtqueue sizes * Returns 0 on success or error status * @del_vqs: free virtqueues found by find_vqs(). * @synchronize_cbs: synchronize with the virtqueue callbacks (optional) @@ -103,7 +104,9 @@ struct virtio_config_ops { void (*reset)(struct virtio_device *vdev); int (*find_vqs)(struct virtio_device *, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], const bool *ctx, + const char * const names[], + u32 sizes[], + const bool *ctx, struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); void (*synchronize_cbs)(struct virtio_device *); @@ -212,7 +215,7 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev, const char *names[] = { n }; struct virtqueue *vq; int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL, - NULL); + NULL, NULL); if (err < 0) return ERR_PTR(err); return vq; @@ -224,7 +227,8 @@ int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs, const char * const names[], struct irq_affinity *desc) { - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc); + return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, + NULL, desc); } static inline @@ -233,8 +237,8 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, const char * const names[], const bool *ctx, struct irq_affinity *desc) { - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, - desc); + return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, + ctx, desc); } /** -- cgit v1.2.3 From fe3dc04e31aa51f91dc7f741a5f76cc4817eb5b4 Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Mon, 1 Aug 2022 14:38:56 +0800 Subject: virtio: add helper virtio_find_vqs_ctx_size() Introduce helper virtio_find_vqs_ctx_size() to call find_vqs and specify the maximum size of each vq ring. Signed-off-by: Xuan Zhuo Acked-by: Jason Wang Message-Id: <20220801063902.129329-37-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 888f7e96f0c7..6adff09f7170 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -241,6 +241,18 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, ctx, desc); } +static inline +int virtio_find_vqs_ctx_size(struct virtio_device *vdev, u32 nvqs, + struct virtqueue *vqs[], + vq_callback_t *callbacks[], + const char * const names[], + u32 sizes[], + const bool *ctx, struct irq_affinity *desc) +{ + return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, sizes, + ctx, desc); +} + /** * virtio_synchronize_cbs - synchronize with virtqueue callbacks * @vdev: the device -- cgit v1.2.3 From cae15c2ed8e6e058bd5e32de292ab7982640161e Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Thu, 14 Jul 2022 14:39:26 +0300 Subject: vdpa/mlx5: Implement susupend virtqueue callback Implement the suspend callback allowing to suspend the virtqueues so they stop processing descriptors. This is required to allow to query a consistent state of the virtqueue while live migration is taking place. Signed-off-by: Eli Cohen Message-Id: <20220714113927.85729-2-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/mlx5/mlx5_ifc_vdpa.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index 4414ed5b6ed2..9becdc3fa503 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -150,6 +150,14 @@ enum { MLX5_VIRTIO_NET_Q_OBJECT_STATE_ERR = 0x3, }; +/* This indicates that the object was not created or has already + * been desroyed. It is very safe to assume that this object will never + * have so many states + */ +enum { + MLX5_VIRTIO_NET_Q_OBJECT_NONE = 0xffffffff +}; + enum { MLX5_RQTC_LIST_Q_TYPE_RQ = 0x0, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q = 0x1, -- cgit v1.2.3 From 848ecea184e1253758423b37cbfc1ed732ccf5b4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= Date: Wed, 10 Aug 2022 19:15:09 +0200 Subject: vdpa: Add suspend operation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This operation is optional: It it's not implemented, backend feature bit will not be exposed. Signed-off-by: Eugenio Pérez Message-Id: <20220810171512.2343333-2-eperezma@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 7b4a13d3bd91..d282f464d2f1 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -218,6 +218,9 @@ struct vdpa_map_file { * @reset: Reset device * @vdev: vdpa device * Returns integer: success (0) or error (< 0) + * @suspend: Suspend or resume the device (optional) + * @vdev: vdpa device + * Returns integer: success (0) or error (< 0) * @get_config_size: Get the size of the configuration space includes * fields that are conditional on feature bits. * @vdev: vdpa device @@ -319,6 +322,7 @@ struct vdpa_config_ops { u8 (*get_status)(struct vdpa_device *vdev); void (*set_status)(struct vdpa_device *vdev, u8 status); int (*reset)(struct vdpa_device *vdev); + int (*suspend)(struct vdpa_device *vdev); size_t (*get_config_size)(struct vdpa_device *vdev); void (*get_config)(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); -- cgit v1.2.3 From addebd9ac9ca0ef8b3764907bf8018e48caffc64 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 12 Aug 2022 15:56:33 -0700 Subject: fs: don't randomize struct kiocb fields This is a size sensitive structure and randomizing can introduce extra padding that breaks io_uring's fixed size expectations. There are few fields here as it is, half of which need a fixed order to optimally pack, so the randomization isn't providing much. Suggested-by: Linus Torvalds Signed-off-by: Keith Busch Link: https://lore.kernel.org/io-uring/b6f508ca-b1b2-5f40-7998-e4cff1cf7212@kernel.dk/ Signed-off-by: Jens Axboe --- include/linux/fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9f131e559d05..daf69a6504b6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -339,17 +339,12 @@ enum rw_hint { struct kiocb { struct file *ki_filp; - - /* The 'ki_filp' pointer is shared in a union for aio */ - randomized_struct_fields_start - loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ struct wait_page_queue *ki_waitq; /* for async buffered IO */ - randomized_struct_fields_end }; static inline bool is_sync_kiocb(struct kiocb *kiocb) -- cgit v1.2.3 From f2ccb5aed7bce1d8b3ed5b3385759a5509663028 Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher Date: Thu, 11 Aug 2022 09:11:15 +0200 Subject: io_uring: make io_kiocb_to_cmd() typesafe We need to make sure (at build time) that struct io_cmd_data is not casted to a structure that's larger. Signed-off-by: Stefan Metzmacher Link: https://lore.kernel.org/r/c024cdf25ae19fc0319d4180e2298bade8ed17b8.1660201408.git.metze@samba.org Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index f7fab3758cb9..677a25d44d7f 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -491,7 +491,14 @@ struct io_cmd_data { __u8 data[56]; }; -#define io_kiocb_to_cmd(req) ((void *) &(req)->cmd) +static inline void io_kiocb_cmd_sz_check(size_t cmd_sz) +{ + BUILD_BUG_ON(cmd_sz > sizeof(struct io_cmd_data)); +} +#define io_kiocb_to_cmd(req, cmd_type) ( \ + io_kiocb_cmd_sz_check(sizeof(cmd_type)) , \ + ((cmd_type *)&(req)->cmd) \ +) #define cmd_to_io_kiocb(ptr) ((struct io_kiocb *) ptr) struct io_kiocb { -- cgit v1.2.3 From 9f162193d6e48eb4ff51c2ea3612f1daebca1b7e Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 11 Aug 2022 22:34:25 -0700 Subject: radix-tree: replace gfp.h inclusion with gfp_types.h Radix tree header includes gfp.h for __GFP_BITS_SHIFT only. Now we have gfp_types.h for this. Fixes powerpc allmodconfig build: In file included from include/linux/nodemask.h:97, from include/linux/mmzone.h:17, from include/linux/gfp.h:7, from include/linux/radix-tree.h:12, from include/linux/idr.h:15, from include/linux/kernfs.h:12, from include/linux/sysfs.h:16, from include/linux/kobject.h:20, from include/linux/pci.h:35, from arch/powerpc/kernel/prom_init.c:24: include/linux/random.h: In function 'add_latent_entropy': >> include/linux/random.h:25:46: error: 'latent_entropy' undeclared (first use in this function); did you mean 'add_latent_entropy'? 25 | add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); | ^~~~~~~~~~~~~~ | add_latent_entropy include/linux/random.h:25:46: note: each undeclared identifier is reported only once for each function it appears in Reported-by: kernel test robot CC: Andy Shevchenko CC: Andrew Morton CC: Jason A. Donenfeld Signed-off-by: Yury Norov Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index f7c1d21c2f39..eae67015ce51 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -9,7 +9,7 @@ #define _LINUX_RADIX_TREE_H #include -#include +#include #include #include #include -- cgit v1.2.3 From 484b9fa4886bd9377969aad5e9ea17efda4ecda6 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 16 Aug 2022 01:36:31 -0400 Subject: virtio: Revert "virtio: add helper virtio_find_vqs_ctx_size()" This reverts commit fe3dc04e31aa51f91dc7f741a5f76cc4817eb5b4: the API is now unused and in fact can't be implemented on top of a legacy device. Fixes: fe3dc04e31aa ("virtio: add helper virtio_find_vqs_ctx_size()") Cc: "Xuan Zhuo" Signed-off-by: Michael S. Tsirkin Message-Id: <20220816053602.173815-3-mst@redhat.com> --- include/linux/virtio_config.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 6adff09f7170..888f7e96f0c7 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -241,18 +241,6 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, ctx, desc); } -static inline -int virtio_find_vqs_ctx_size(struct virtio_device *vdev, u32 nvqs, - struct virtqueue *vqs[], - vq_callback_t *callbacks[], - const char * const names[], - u32 sizes[], - const bool *ctx, struct irq_affinity *desc) -{ - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, sizes, - ctx, desc); -} - /** * virtio_synchronize_cbs - synchronize with virtqueue callbacks * @vdev: the device -- cgit v1.2.3 From 9993a4f989c7ca5e227329b2878f65d05c9fc20f Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 16 Aug 2022 01:36:58 -0400 Subject: virtio: Revert "virtio: find_vqs() add arg sizes" This reverts commit a10fba0377145fccefea4dc4dd5915b7ed87e546: the proposed API isn't supported on all transports but no effort was made to address this. It might not be hard to fix if we want to: maybe just rename size to size_hint and make sure legacy transports ignore the hint. But it's not sure what the benefit is in any case, so let's drop it. Fixes: a10fba037714 ("virtio: find_vqs() add arg sizes") Signed-off-by: Michael S. Tsirkin Message-Id: <20220816053602.173815-8-mst@redhat.com> --- include/linux/virtio_config.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 888f7e96f0c7..36ec7be1f480 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -55,7 +55,6 @@ struct virtio_shm_region { * include a NULL entry for vqs that do not need a callback * names: array of virtqueue names (mainly for debugging) * include a NULL entry for vqs unused by driver - * sizes: array of virtqueue sizes * Returns 0 on success or error status * @del_vqs: free virtqueues found by find_vqs(). * @synchronize_cbs: synchronize with the virtqueue callbacks (optional) @@ -104,9 +103,7 @@ struct virtio_config_ops { void (*reset)(struct virtio_device *vdev); int (*find_vqs)(struct virtio_device *, unsigned nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], - u32 sizes[], - const bool *ctx, + const char * const names[], const bool *ctx, struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); void (*synchronize_cbs)(struct virtio_device *); @@ -215,7 +212,7 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev, const char *names[] = { n }; struct virtqueue *vq; int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL, - NULL, NULL); + NULL); if (err < 0) return ERR_PTR(err); return vq; @@ -227,8 +224,7 @@ int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs, const char * const names[], struct irq_affinity *desc) { - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, - NULL, desc); + return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc); } static inline @@ -237,8 +233,8 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, const char * const names[], const bool *ctx, struct irq_affinity *desc) { - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, - ctx, desc); + return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, + desc); } /** -- cgit v1.2.3 From 5c669c4a4c6aa0489848093c93b8029f5c5c75ec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo?= Date: Wed, 10 Aug 2022 11:40:03 +0200 Subject: virtio: kerneldocs fixes and enhancements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix variable names in some kerneldocs, naming in others. Add kerneldocs for struct vring_desc and vring_interrupt. Signed-off-by: Ricardo Cañuelo Message-Id: <20220810094004.1250-2-ricardo.canuelo@collabora.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/linux/virtio.h | 6 +++--- include/linux/virtio_config.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index a3f73bb6733e..dcab9c7e8784 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -11,7 +11,7 @@ #include /** - * virtqueue - a queue to register buffers for sending or receiving. + * struct virtqueue - a queue to register buffers for sending or receiving. * @list: the chain of virtqueues for this device * @callback: the function to call when buffers are consumed (can be NULL). * @name: the name of this virtqueue (mainly for debugging) @@ -97,7 +97,7 @@ int virtqueue_resize(struct virtqueue *vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf)); /** - * virtio_device - representation of a device using virtio + * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) * @config_enabled: configuration change reporting enabled @@ -156,7 +156,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev); list_for_each_entry(vq, &vdev->vqs, list) /** - * virtio_driver - operations for a virtio I/O driver + * struct virtio_driver - operations for a virtio I/O driver * @driver: underlying device driver (populate name and owner). * @id_table: the ids serviced by this driver. * @feature_table: an array of feature numbers supported by this driver. diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 36ec7be1f480..4b517649cfe8 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -239,7 +239,7 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, /** * virtio_synchronize_cbs - synchronize with virtqueue callbacks - * @vdev: the device + * @dev: the virtio device */ static inline void virtio_synchronize_cbs(struct virtio_device *dev) @@ -258,7 +258,7 @@ void virtio_synchronize_cbs(struct virtio_device *dev) /** * virtio_device_ready - enable vq use in probe function - * @vdev: the device + * @dev: the virtio device * * Driver must call this to use vqs in the probe function. * @@ -306,7 +306,7 @@ const char *virtio_bus_name(struct virtio_device *vdev) /** * virtqueue_set_affinity - setting affinity for a virtqueue * @vq: the virtqueue - * @cpu: the cpu no. + * @cpu_mask: the cpu mask * * Pay attention the function are best-effort: the affinity hint may not be set * due to config support, irq type and sharing. -- cgit v1.2.3