- Linux-stable-mirror - lists.linaro.org

[PATCH net] netkit: Ensure current->bpf_net_context is set in netkit_xmit()

by Jordan Rife

When operating Cilium in netkit mode with BPF-based host routing, calls to bpf_redirect() cause a kernel panic. [ 52.247646] BUG: kernel NULL pointer dereference, address: 0000000000000038 ... [ 52.247727] RIP: 0010:bpf_redirect+0x18/0x80 ... [ 52.247986] Call Trace: [ 52.247990] <TASK> [ 52.248002] ? show_regs+0x6c/0x80 [ 52.248024] ? __die+0x24/0x80 [ 52.248029] ? page_fault_oops+0x155/0x570 [ 52.248047] ? fib_rules_lookup+0x112/0x270 [ 52.248056] ? do_user_addr_fault+0x4b2/0x870 [ 52.248063] ? exc_page_fault+0x82/0x1b0 [ 52.248090] ? asm_exc_page_fault+0x27/0x30 [ 52.248103] ? bpf_redirect+0x18/0x80 [ 52.248109] bpf_prog_f0698aabaf44c832_tail_handle_ipv4+0x173f/0x2707 [ 52.248119] ? sbitmap_find_bit+0xe3/0x270 [ 52.248129] netkit_xmit+0x177/0x3c0 [ 52.248139] dev_hard_start_xmit+0x62/0x1d0 [ 52.248149] __dev_queue_xmit+0x241/0xf30 [ 52.248155] ? alloc_skb_with_frags+0x60/0x280 [ 52.248164] ? __check_object_size+0x2a2/0x310 [ 52.248173] ? ip_generic_getfrag+0x63/0x110 [ 52.248181] ip_finish_output2+0x2cf/0x560 [ 52.248187] __ip_finish_output+0xb6/0x180 [ 52.248193] ip_finish_output+0x29/0x120 [ 52.248198] ip_output+0x5f/0x100 [ 52.248204] ? __pfx_ip_finish_output+0x10/0x10 [ 52.248210] ip_send_skb+0x98/0xb0 [ 52.248215] udp_send_skb+0x146/0x370 Setting a breakpoint inside bpf_net_ctx_get_ri() confirms that current->bpf_net_context is NULL right before the panic. (gdb) p $lx_current().bpf_net_context $4 = (struct bpf_net_context *) 0x0 <fixed_percpu_data> (gdb) disassemble bpf_redirect Dump of assembler code for function bpf_redirect: 0xffffffff81f085e0 <+0>: nopl 0x0(%rax,%rax,1) 0xffffffff81f085e5 <+5>: mov %gs:0x7e12d593(%rip),%rax 0xffffffff81f085ed <+13>: push %rbp 0xffffffff81f085ee <+14>: mov 0x23d0(%rax),%rax => 0xffffffff81f085f5 <+21>: mov %rsp,%rbp 0xffffffff81f085f8 <+24>: mov 0x38(%rax),%edx ... (gdb) continue Continuing. Thread 1 hit Breakpoint 1, panic ... 288 { (gdb) commit 401cb7dae813 ("net: Reference bpf_redirect_info via task_struct on PREEMPT_RT.") recently moved bpf_redirect_info into bpf_net_context, a new member of task_struct. Currently, current->bpf_net_context is set and then cleared inside sch_handle_egress() where tcx_run() and tc_run() execute, but it looks like netkit_xmit() was missed leaving current->bpf_net_context uninitialized when it runs. This patch ensures that current->bpf_net_context is initialized while running netkit_xmit(). Signed-off-by: Jordan Rife <jrife(a)google.com> Fixes: 401cb7dae813 ("net: Reference bpf_redirect_info via task_struct on PREEMPT_RT.") Cc: stable(a)vger.kernel.org --- drivers/net/netkit.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index d0036a856039..92ac0cb5a327 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -65,6 +65,7 @@ static struct netkit *netkit_priv(const struct net_device *dev) static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct netkit *nk = netkit_priv(dev); enum netkit_action ret = READ_ONCE(nk->policy); netdev_tx_t ret_dev = NET_XMIT_SUCCESS; @@ -73,6 +74,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) int len = skb->len; rcu_read_lock(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); peer = rcu_dereference(nk->peer); if (unlikely(!peer || !(peer->flags & IFF_UP) || !pskb_may_pull(skb, ETH_HLEN) || @@ -109,6 +111,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) ret_dev = NET_XMIT_DROP; break; } + bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); return ret_dev; } -- 2.46.0.662.g92d0881bb0-goog

1 year

2
1
0 0

[PATCH v2] i3c: master: svc: Fix use after free vulnerability in svc_i3c_master Driver Due to Race Condition

by Kaixin Wang

In the svc_i3c_master_probe function, &master->hj_work is bound with svc_i3c_master_hj_work, &master->ibi_work is bound with svc_i3c_master_ibi_work. And svc_i3c_master_ibi_work can start the hj_work, svc_i3c_master_irq_handler can start the ibi_work. If we remove the module which will call svc_i3c_master_remove to make cleanup, it will free master->base through i3c_master_unregister while the work mentioned above will be used. The sequence of operations that may lead to a UAF bug is as follows: CPU0 CPU1 | svc_i3c_master_hj_work svc_i3c_master_remove | i3c_master_unregister(&master->base)| device_unregister(&master->dev) | device_release | //free master->base | | i3c_master_do_daa(&master->base) | //use master->base Fix it by ensuring that the work is canceled before proceeding with the cleanup in svc_i3c_master_remove. Fixes: 0f74f8b6675c ("i3c: Make i3c_master_unregister() return void") Signed-off-by: Kaixin Wang <kxwang23(a)m.fudan.edu.cn> Reviewed-by: Miquel Raynal <miquel.raynal(a)bootlin.com> --- v2: - add fixes tag and cc stable, suggested by Frank - add Reviewed-by label from Miquel - Link to v1: https://lore.kernel.org/r/20240911150135.839946-1-kxwang23@m.fudan.edu.cn --- drivers/i3c/master/svc-i3c-master.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index 0a68fd1b81d4..e084ba648b4a 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -1775,6 +1775,7 @@ static void svc_i3c_master_remove(struct platform_device *pdev) { struct svc_i3c_master *master = platform_get_drvdata(pdev); + cancel_work_sync(&master->hj_work); i3c_master_unregister(&master->base); pm_runtime_dont_use_autosuspend(&pdev->dev); -- 2.39.1.windows.1

1 year

2
1
0 0

[PATCH 0/7] iio: light: veml6030: fix issues and add support for veml6035

by Javier Carrasco

This series updates the driver for the veml6030 ALS and adds support for the veml6035, which shares most of its functionality with the former. The most relevant updates for the veml6030 are the resolution correction to meet the datasheet update that took place with Rev 1.7, 28-Nov-2023, and a fix to avoid a segmentation fault when reading the in_illuminance_period_available attribute. Vishay does not host the Product Information Notification where the resolution correction was introduced, but it can still be found online[1], and the corrected value is the one listed on the latest version of the datasheet[2] (Rev. 1.7, 28-Nov-2023) and application note[3] (Rev. 17-Jan-2024). Link: https://www.farnell.com/datasheets/4379688.pdf [1] Link: https://www.vishay.com/docs/84366/veml6030.pdf [2] Link: https://www.vishay.com/docs/84367/designingveml6030.pdf [3] Signed-off-by: Javier Carrasco <javier.carrasco.cruz(a)gmail.com> --- Javier Carrasco (7): dt-bindings: iio: light: veml6030: rename to add manufacturer dt-bindings: iio: light: veml6030: add veml6035 iio: light: veml6030: fix IIO device retrieval from embedded device iio: light: veml6030: make use of regmap_set_bits() iio: light: veml6030: update sensor resolution iio: light: veml6030: add set up delay after any power on sequence iio: light: veml6030: add support for veml6035 .../light/{veml6030.yaml => vishay,veml6030.yaml} | 42 ++- drivers/iio/light/veml6030.c | 323 ++++++++++++++++++--- 2 files changed, 319 insertions(+), 46 deletions(-) --- base-commit: 5acd9952f95fb4b7da6d09a3be39195a80845eb6 change-id: 20240903-veml6035-7a91bc088c6f Best regards, -- Javier Carrasco <javier.carrasco.cruz(a)gmail.com>

1 year

2
2
0 0

[PATCH] power: supply: sysfs: enable is_writeable check during sysfs creation

by Andreas Kemnade

The files in sysfs are created during device_add(). psy->use_cnt is not incremented yet. So attributes are created readonly without checking desc->property_is_writeable() and writeable files are readonly. To fix this, revert back to calling desc->property_is_writeable() directly without using the helper. Fixes: be6299c6e55e ("power: supply: sysfs: use power_supply_property_is_writeable()") Signed-off-by: Andreas Kemnade <andreas(a)kemnade.info> Cc: stable(a)vger.kernel.org # 6.11 --- drivers/power/supply/power_supply_sysfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index 3e63d165b2f70..b86e11bdc07ef 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -379,7 +379,8 @@ static umode_t power_supply_attr_is_visible(struct kobject *kobj, int property = psy->desc->properties[i]; if (property == attrno) { - if (power_supply_property_is_writeable(psy, property) > 0) + if (psy->desc->property_is_writeable && + psy->desc->property_is_writeable(psy, property) > 0) mode |= S_IWUSR; return mode; -- 2.39.2

1 year

2
1
0 0

[PATCH v3 3/3] block: fix ordering between checking BLK_MQ_S_STOPPED and adding requests

by Muchun Song

Supposing first scenario with a virtio_blk driver. CPU0 CPU1 blk_mq_try_issue_directly() __blk_mq_issue_directly() q->mq_ops->queue_rq() virtio_queue_rq() blk_mq_stop_hw_queue() virtblk_done() blk_mq_request_bypass_insert() 1) store blk_mq_start_stopped_hw_queue() clear_bit(BLK_MQ_S_STOPPED) 3) store blk_mq_run_hw_queue() if (!blk_mq_hctx_has_pending()) 4) load return blk_mq_sched_dispatch_requests() blk_mq_run_hw_queue() if (!blk_mq_hctx_has_pending()) return blk_mq_sched_dispatch_requests() if (blk_mq_hctx_stopped()) 2) load return __blk_mq_sched_dispatch_requests() Supposing another scenario. CPU0 CPU1 blk_mq_requeue_work() blk_mq_insert_request() 1) store virtblk_done() blk_mq_start_stopped_hw_queue() blk_mq_run_hw_queues() clear_bit(BLK_MQ_S_STOPPED) 3) store blk_mq_run_hw_queue() if (!blk_mq_hctx_has_pending()) 4) load return blk_mq_sched_dispatch_requests() if (blk_mq_hctx_stopped()) 2) load continue blk_mq_run_hw_queue() Both scenarios are similar, the full memory barrier should be inserted between 1) and 2), as well as between 3) and 4) to make sure that either CPU0 sees BLK_MQ_S_STOPPED is cleared or CPU1 sees dispatch list. Otherwise, either CPU will not rerun the hardware queue causing starvation of the request. The easy way to fix it is to add the essential full memory barrier into helper of blk_mq_hctx_stopped(). In order to not affect the fast path (hardware queue is not stopped most of the time), we only insert the barrier into the slow path. Actually, only slow path needs to care about missing of dispatching the request to the low-level device driver. Fixes: 320ae51feed5 ("blk-mq: new multi-queue block IO queueing mechanism") Cc: stable(a)vger.kernel.org Cc: Muchun Song <muchun.song(a)linux.dev> Signed-off-by: Muchun Song <songmuchun(a)bytedance.com> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> --- block/blk-mq.c | 6 ++++++ block/blk-mq.h | 13 +++++++++++++ 2 files changed, 19 insertions(+) diff --git a/block/blk-mq.c b/block/blk-mq.c index ff6df6c7eeb25..b90c1680cb780 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2413,6 +2413,12 @@ void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) return; clear_bit(BLK_MQ_S_STOPPED, &hctx->state); + /* + * Pairs with the smp_mb() in blk_mq_hctx_stopped() to order the + * clearing of BLK_MQ_S_STOPPED above and the checking of dispatch + * list in the subsequent routine. + */ + smp_mb__after_atomic(); blk_mq_run_hw_queue(hctx, async); } EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue); diff --git a/block/blk-mq.h b/block/blk-mq.h index 260beea8e332c..f36f3bff70d86 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -228,6 +228,19 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) { + /* Fast path: hardware queue is not stopped most of the time. */ + if (likely(!test_bit(BLK_MQ_S_STOPPED, &hctx->state))) + return false; + + /* + * This barrier is used to order adding of dispatch list before and + * the test of BLK_MQ_S_STOPPED below. Pairs with the memory barrier + * in blk_mq_start_stopped_hw_queue() so that dispatch code could + * either see BLK_MQ_S_STOPPED is cleared or dispatch list is not + * empty to avoid missing dispatching requests. + */ + smp_mb(); + return test_bit(BLK_MQ_S_STOPPED, &hctx->state); } -- 2.20.1

1 year

1
0
0 0

[PATCH v3 2/3] block: fix ordering between checking QUEUE_FLAG_QUIESCED and adding requests

by Muchun Song

Supposing the following scenario. CPU0 CPU1 blk_mq_insert_request() 1) store blk_mq_unquiesce_queue() blk_queue_flag_clear() 3) store blk_mq_run_hw_queues() blk_mq_run_hw_queue() if (!blk_mq_hctx_has_pending()) 4) load return blk_mq_run_hw_queue() if (blk_queue_quiesced()) 2) load return blk_mq_sched_dispatch_requests() The full memory barrier should be inserted between 1) and 2), as well as between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is cleared or CPU1 sees dispatch list or setting of bitmap of software queue. Otherwise, either CPU will not rerun the hardware queue causing starvation. So the first solution is to 1) add a pair of memory barrier to fix the problem, another solution is to 2) use hctx->queue->queue_lock to synchronize QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not easy to be maintained. Fixes: f4560ffe8cec ("blk-mq: use QUEUE_FLAG_QUIESCED to quiesce queue") Cc: stable(a)vger.kernel.org Cc: Muchun Song <muchun.song(a)linux.dev> Signed-off-by: Muchun Song <songmuchun(a)bytedance.com> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> --- block/blk-mq.c | 47 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 34 insertions(+), 13 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index b2d0f22de0c7f..ff6df6c7eeb25 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx) +{ + bool need_run; + + /* + * When queue is quiesced, we may be switching io scheduler, or + * updating nr_hw_queues, or other things, and we can't run queue + * any more, even blk_mq_hctx_has_pending() can't be called safely. + * + * And queue will be rerun in blk_mq_unquiesce_queue() if it is + * quiesced. + */ + __blk_mq_run_dispatch_ops(hctx->queue, false, + need_run = !blk_queue_quiesced(hctx->queue) && + blk_mq_hctx_has_pending(hctx)); + return need_run; +} + /** * blk_mq_run_hw_queue - Start to run a hardware queue. * @hctx: Pointer to the hardware queue to run. @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING); - /* - * When queue is quiesced, we may be switching io scheduler, or - * updating nr_hw_queues, or other things, and we can't run queue - * any more, even __blk_mq_hctx_has_pending() can't be called safely. - * - * And queue will be rerun in blk_mq_unquiesce_queue() if it is - * quiesced. - */ - __blk_mq_run_dispatch_ops(hctx->queue, false, - need_run = !blk_queue_quiesced(hctx->queue) && - blk_mq_hctx_has_pending(hctx)); + need_run = blk_mq_hw_queue_need_run(hctx); + if (!need_run) { + unsigned long flags; - if (!need_run) - return; + /* + * Synchronize with blk_mq_unquiesce_queue(), because we check + * if hw queue is quiesced locklessly above, we need the use + * ->queue_lock to make sure we see the up-to-date status to + * not miss rerunning the hw queue. + */ + spin_lock_irqsave(&hctx->queue->queue_lock, flags); + need_run = blk_mq_hw_queue_need_run(hctx); + spin_unlock_irqrestore(&hctx->queue->queue_lock, flags); + + if (!need_run) + return; + } if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) { blk_mq_delay_run_hw_queue(hctx, 0); -- 2.20.1

1 year

1
0
0 0

[PATCH v3 1/3] block: fix missing dispatching request when queue is started or unquiesced

by Muchun Song

Supposing the following scenario with a virtio_blk driver. CPU0 CPU1 CPU2 blk_mq_try_issue_directly() __blk_mq_issue_directly() q->mq_ops->queue_rq() virtio_queue_rq() blk_mq_stop_hw_queue() virtblk_done() blk_mq_try_issue_directly() if (blk_mq_hctx_stopped()) blk_mq_request_bypass_insert() blk_mq_run_hw_queue() blk_mq_run_hw_queue() blk_mq_run_hw_queue() blk_mq_insert_request() return After CPU0 has marked the queue as stopped, CPU1 will see the queue is stopped. But before CPU1 puts the request on the dispatch list, CPU2 receives the interrupt of completion of request, so it will run the hardware queue and marks the queue as non-stopped. Meanwhile, CPU1 also runs the same hardware queue. After both CPU1 and CPU2 complete blk_mq_run_hw_queue(), CPU1 just puts the request to the same hardware queue and returns. It misses dispatching a request. Fix it by running the hardware queue explicitly. And blk_mq_request_issue_directly() should handle a similar situation. Fix it as well. Fixes: d964f04a8fde ("blk-mq: fix direct issue") Cc: stable(a)vger.kernel.org Cc: Muchun Song <muchun.song(a)linux.dev> Signed-off-by: Muchun Song <songmuchun(a)bytedance.com> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> --- block/blk-mq.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block/blk-mq.c b/block/blk-mq.c index e3c3c0c21b553..b2d0f22de0c7f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2619,6 +2619,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) { blk_mq_insert_request(rq, 0); + blk_mq_run_hw_queue(hctx, false); return; } @@ -2649,6 +2650,7 @@ static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) { blk_mq_insert_request(rq, 0); + blk_mq_run_hw_queue(hctx, false); return BLK_STS_OK; } -- 2.20.1

1 year

1
0
0 0

FAILED: patch "[PATCH] drm/amd/amdgpu: apply command submission parser for JPEG v1" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 8409fb50ce48d66cf9dc5391f03f05c56c430605 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024091428-stagnant-sesame-feb3@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: 8409fb50ce48 ("drm/amd/amdgpu: apply command submission parser for JPEG v1") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8409fb50ce48d66cf9dc5391f03f05c56c430605 Mon Sep 17 00:00:00 2001 From: "David (Ming Qiang) Wu" <David.Wu3(a)amd.com> Date: Thu, 5 Sep 2024 16:57:28 -0400 Subject: [PATCH] drm/amd/amdgpu: apply command submission parser for JPEG v1 Similar to jpeg_v2_dec_ring_parse_cs() but it has different register ranges and a few other registers access. Acked-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: David (Ming Qiang) Wu <David.Wu3(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> (cherry picked from commit 3d5adbdf1d01708777f2eda375227cbf7a98b9fe) Cc: stable(a)vger.kernel.org diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index 71f43a5c7f72..6e0e88076224 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -23,6 +23,7 @@ #include "amdgpu.h" #include "amdgpu_jpeg.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "vcn_v1_0.h" @@ -34,6 +35,9 @@ static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring); +static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val) { @@ -300,7 +304,10 @@ static void jpeg_v1_0_decode_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + if (ring->funcs->parse_cs) + amdgpu_ring_write(ring, 0); + else + amdgpu_ring_write(ring, (vmid | (vmid << 4))); amdgpu_ring_write(ring, PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0)); @@ -554,6 +561,7 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = { .get_rptr = jpeg_v1_0_decode_ring_get_rptr, .get_wptr = jpeg_v1_0_decode_ring_get_wptr, .set_wptr = jpeg_v1_0_decode_ring_set_wptr, + .parse_cs = jpeg_v1_dec_ring_parse_cs, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + @@ -611,3 +619,69 @@ static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); } + +/** + * jpeg_v1_dec_ring_parse_cs - command submission parser + * + * @parser: Command submission parser context + * @job: the job to parse + * @ib: the IB to parse + * + * Parse the command stream, return -EINVAL for invalid packet, + * 0 otherwise + */ +static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + u32 i, reg, res, cond, type; + int ret = 0; + struct amdgpu_device *adev = parser->adev; + + for (i = 0; i < ib->length_dw ; i += 2) { + reg = CP_PACKETJ_GET_REG(ib->ptr[i]); + res = CP_PACKETJ_GET_RES(ib->ptr[i]); + cond = CP_PACKETJ_GET_COND(ib->ptr[i]); + type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); + + if (res || cond != PACKETJ_CONDITION_CHECK0) /* only allow 0 for now */ + return -EINVAL; + + if (reg >= JPEG_V1_REG_RANGE_START && reg <= JPEG_V1_REG_RANGE_END) + continue; + + switch (type) { + case PACKETJ_TYPE0: + if (reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH && + reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW && + reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH && + reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW && + reg != JPEG_V1_REG_CTX_INDEX && + reg != JPEG_V1_REG_CTX_DATA) { + ret = -EINVAL; + } + break; + case PACKETJ_TYPE1: + if (reg != JPEG_V1_REG_CTX_DATA) + ret = -EINVAL; + break; + case PACKETJ_TYPE3: + if (reg != JPEG_V1_REG_SOFT_RESET) + ret = -EINVAL; + break; + case PACKETJ_TYPE6: + if (ib->ptr[i] != CP_PACKETJ_NOP) + ret = -EINVAL; + break; + default: + ret = -EINVAL; + } + + if (ret) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + break; + } + } + + return ret; +} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h index bbf33a6a3972..9654d22e0376 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h @@ -29,4 +29,15 @@ int jpeg_v1_0_sw_init(void *handle); void jpeg_v1_0_sw_fini(void *handle); void jpeg_v1_0_start(struct amdgpu_device *adev, int mode); +#define JPEG_V1_REG_RANGE_START 0x8000 +#define JPEG_V1_REG_RANGE_END 0x803f + +#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH 0x8238 +#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW 0x8239 +#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH 0x825a +#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW 0x825b +#define JPEG_V1_REG_CTX_INDEX 0x8328 +#define JPEG_V1_REG_CTX_DATA 0x8329 +#define JPEG_V1_REG_SOFT_RESET 0x83a0 + #endif /*__JPEG_V1_0_H__*/

1 year

1
0
0 0

FAILED: patch "[PATCH] drm/amd/amdgpu: apply command submission parser for JPEG v1" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 8409fb50ce48d66cf9dc5391f03f05c56c430605 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024091428-baffling-wound-9fa1@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 8409fb50ce48 ("drm/amd/amdgpu: apply command submission parser for JPEG v1") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8409fb50ce48d66cf9dc5391f03f05c56c430605 Mon Sep 17 00:00:00 2001 From: "David (Ming Qiang) Wu" <David.Wu3(a)amd.com> Date: Thu, 5 Sep 2024 16:57:28 -0400 Subject: [PATCH] drm/amd/amdgpu: apply command submission parser for JPEG v1 Similar to jpeg_v2_dec_ring_parse_cs() but it has different register ranges and a few other registers access. Acked-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: David (Ming Qiang) Wu <David.Wu3(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> (cherry picked from commit 3d5adbdf1d01708777f2eda375227cbf7a98b9fe) Cc: stable(a)vger.kernel.org diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index 71f43a5c7f72..6e0e88076224 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -23,6 +23,7 @@ #include "amdgpu.h" #include "amdgpu_jpeg.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "vcn_v1_0.h" @@ -34,6 +35,9 @@ static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring); +static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val) { @@ -300,7 +304,10 @@ static void jpeg_v1_0_decode_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + if (ring->funcs->parse_cs) + amdgpu_ring_write(ring, 0); + else + amdgpu_ring_write(ring, (vmid | (vmid << 4))); amdgpu_ring_write(ring, PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0)); @@ -554,6 +561,7 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = { .get_rptr = jpeg_v1_0_decode_ring_get_rptr, .get_wptr = jpeg_v1_0_decode_ring_get_wptr, .set_wptr = jpeg_v1_0_decode_ring_set_wptr, + .parse_cs = jpeg_v1_dec_ring_parse_cs, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + @@ -611,3 +619,69 @@ static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); } + +/** + * jpeg_v1_dec_ring_parse_cs - command submission parser + * + * @parser: Command submission parser context + * @job: the job to parse + * @ib: the IB to parse + * + * Parse the command stream, return -EINVAL for invalid packet, + * 0 otherwise + */ +static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + u32 i, reg, res, cond, type; + int ret = 0; + struct amdgpu_device *adev = parser->adev; + + for (i = 0; i < ib->length_dw ; i += 2) { + reg = CP_PACKETJ_GET_REG(ib->ptr[i]); + res = CP_PACKETJ_GET_RES(ib->ptr[i]); + cond = CP_PACKETJ_GET_COND(ib->ptr[i]); + type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); + + if (res || cond != PACKETJ_CONDITION_CHECK0) /* only allow 0 for now */ + return -EINVAL; + + if (reg >= JPEG_V1_REG_RANGE_START && reg <= JPEG_V1_REG_RANGE_END) + continue; + + switch (type) { + case PACKETJ_TYPE0: + if (reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH && + reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW && + reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH && + reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW && + reg != JPEG_V1_REG_CTX_INDEX && + reg != JPEG_V1_REG_CTX_DATA) { + ret = -EINVAL; + } + break; + case PACKETJ_TYPE1: + if (reg != JPEG_V1_REG_CTX_DATA) + ret = -EINVAL; + break; + case PACKETJ_TYPE3: + if (reg != JPEG_V1_REG_SOFT_RESET) + ret = -EINVAL; + break; + case PACKETJ_TYPE6: + if (ib->ptr[i] != CP_PACKETJ_NOP) + ret = -EINVAL; + break; + default: + ret = -EINVAL; + } + + if (ret) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + break; + } + } + + return ret; +} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h index bbf33a6a3972..9654d22e0376 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h @@ -29,4 +29,15 @@ int jpeg_v1_0_sw_init(void *handle); void jpeg_v1_0_sw_fini(void *handle); void jpeg_v1_0_start(struct amdgpu_device *adev, int mode); +#define JPEG_V1_REG_RANGE_START 0x8000 +#define JPEG_V1_REG_RANGE_END 0x803f + +#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH 0x8238 +#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW 0x8239 +#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH 0x825a +#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW 0x825b +#define JPEG_V1_REG_CTX_INDEX 0x8328 +#define JPEG_V1_REG_CTX_DATA 0x8329 +#define JPEG_V1_REG_SOFT_RESET 0x83a0 + #endif /*__JPEG_V1_0_H__*/

1 year

1
0
0 0

FAILED: patch "[PATCH] drm/amd/amdgpu: apply command submission parser for JPEG v1" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 8409fb50ce48d66cf9dc5391f03f05c56c430605 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024091427-vanilla-breath-c5f2@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 8409fb50ce48 ("drm/amd/amdgpu: apply command submission parser for JPEG v1") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8409fb50ce48d66cf9dc5391f03f05c56c430605 Mon Sep 17 00:00:00 2001 From: "David (Ming Qiang) Wu" <David.Wu3(a)amd.com> Date: Thu, 5 Sep 2024 16:57:28 -0400 Subject: [PATCH] drm/amd/amdgpu: apply command submission parser for JPEG v1 Similar to jpeg_v2_dec_ring_parse_cs() but it has different register ranges and a few other registers access. Acked-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: David (Ming Qiang) Wu <David.Wu3(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> (cherry picked from commit 3d5adbdf1d01708777f2eda375227cbf7a98b9fe) Cc: stable(a)vger.kernel.org diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index 71f43a5c7f72..6e0e88076224 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -23,6 +23,7 @@ #include "amdgpu.h" #include "amdgpu_jpeg.h" +#include "amdgpu_cs.h" #include "soc15.h" #include "soc15d.h" #include "vcn_v1_0.h" @@ -34,6 +35,9 @@ static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring); +static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib); static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val) { @@ -300,7 +304,10 @@ static void jpeg_v1_0_decode_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + if (ring->funcs->parse_cs) + amdgpu_ring_write(ring, 0); + else + amdgpu_ring_write(ring, (vmid | (vmid << 4))); amdgpu_ring_write(ring, PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0)); @@ -554,6 +561,7 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = { .get_rptr = jpeg_v1_0_decode_ring_get_rptr, .get_wptr = jpeg_v1_0_decode_ring_get_wptr, .set_wptr = jpeg_v1_0_decode_ring_set_wptr, + .parse_cs = jpeg_v1_dec_ring_parse_cs, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + @@ -611,3 +619,69 @@ static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); } + +/** + * jpeg_v1_dec_ring_parse_cs - command submission parser + * + * @parser: Command submission parser context + * @job: the job to parse + * @ib: the IB to parse + * + * Parse the command stream, return -EINVAL for invalid packet, + * 0 otherwise + */ +static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + u32 i, reg, res, cond, type; + int ret = 0; + struct amdgpu_device *adev = parser->adev; + + for (i = 0; i < ib->length_dw ; i += 2) { + reg = CP_PACKETJ_GET_REG(ib->ptr[i]); + res = CP_PACKETJ_GET_RES(ib->ptr[i]); + cond = CP_PACKETJ_GET_COND(ib->ptr[i]); + type = CP_PACKETJ_GET_TYPE(ib->ptr[i]); + + if (res || cond != PACKETJ_CONDITION_CHECK0) /* only allow 0 for now */ + return -EINVAL; + + if (reg >= JPEG_V1_REG_RANGE_START && reg <= JPEG_V1_REG_RANGE_END) + continue; + + switch (type) { + case PACKETJ_TYPE0: + if (reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH && + reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW && + reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH && + reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW && + reg != JPEG_V1_REG_CTX_INDEX && + reg != JPEG_V1_REG_CTX_DATA) { + ret = -EINVAL; + } + break; + case PACKETJ_TYPE1: + if (reg != JPEG_V1_REG_CTX_DATA) + ret = -EINVAL; + break; + case PACKETJ_TYPE3: + if (reg != JPEG_V1_REG_SOFT_RESET) + ret = -EINVAL; + break; + case PACKETJ_TYPE6: + if (ib->ptr[i] != CP_PACKETJ_NOP) + ret = -EINVAL; + break; + default: + ret = -EINVAL; + } + + if (ret) { + dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]); + break; + } + } + + return ret; +} diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h index bbf33a6a3972..9654d22e0376 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h @@ -29,4 +29,15 @@ int jpeg_v1_0_sw_init(void *handle); void jpeg_v1_0_sw_fini(void *handle); void jpeg_v1_0_start(struct amdgpu_device *adev, int mode); +#define JPEG_V1_REG_RANGE_START 0x8000 +#define JPEG_V1_REG_RANGE_END 0x803f + +#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH 0x8238 +#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW 0x8239 +#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH 0x825a +#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW 0x825b +#define JPEG_V1_REG_CTX_INDEX 0x8328 +#define JPEG_V1_REG_CTX_DATA 0x8329 +#define JPEG_V1_REG_SOFT_RESET 0x83a0 + #endif /*__JPEG_V1_0_H__*/

1 year

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror