July 2023 - Linux-stable-mirror

[for-linus][PATCH 1/5] samples: ftrace: Save required argument registers in sample trampolines

by Steven Rostedt

From: Florent Revest <revest(a)chromium.org> The ftrace-direct-too sample traces the handle_mm_fault function whose signature changed since the introduction of the sample. Since: commit bce617edecad ("mm: do page fault accounting in handle_mm_fault") handle_mm_fault now has 4 arguments. Therefore, the sample trampoline should save 4 argument registers. s390 saves all argument registers already so it does not need a change but x86_64 needs an extra push and pop. This also evolves the signature of the tracing function to make it mirror the signature of the traced function. Link: https://lkml.kernel.org/r/20230427140700.625241-2-revest@chromium.org Cc: stable(a)vger.kernel.org Fixes: bce617edecad ("mm: do page fault accounting in handle_mm_fault") Reviewed-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> Reviewed-by: Mark Rutland <mark.rutland(a)arm.com> Acked-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Florent Revest <revest(a)chromium.org> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- samples/ftrace/ftrace-direct-too.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c index a05bc2cc2261..7986033887f6 100644 --- a/samples/ftrace/ftrace-direct-too.c +++ b/samples/ftrace/ftrace-direct-too.c @@ -5,14 +5,14 @@ #include <linux/ftrace.h> #include <asm/asm-offsets.h> -extern void my_direct_func(struct vm_area_struct *vma, - unsigned long address, unsigned int flags); +extern void my_direct_func(struct vm_area_struct *vma, unsigned long address, + unsigned int flags, struct pt_regs *regs); -void my_direct_func(struct vm_area_struct *vma, - unsigned long address, unsigned int flags) +void my_direct_func(struct vm_area_struct *vma, unsigned long address, + unsigned int flags, struct pt_regs *regs) { - trace_printk("handle mm fault vma=%p address=%lx flags=%x\n", - vma, address, flags); + trace_printk("handle mm fault vma=%p address=%lx flags=%x regs=%p\n", + vma, address, flags, regs); } extern void my_tramp(void *); @@ -34,7 +34,9 @@ asm ( " pushq %rdi\n" " pushq %rsi\n" " pushq %rdx\n" +" pushq %rcx\n" " call my_direct_func\n" +" popq %rcx\n" " popq %rdx\n" " popq %rsi\n" " popq %rdi\n" -- 2.40.1

2 years, 2 months

1
0
0 0

[PATCH] HID: logitech-hidpp: rework one more time the retries attempts

by Benjamin Tissoires

Make the code looks less like Pascal. Extract the internal code inside a helper function, fix the initialization of the parameters used in the helper function (`hidpp->answer_available` was not reset and `*response` wasn't too), and use a `do {...} while();` loop. Fixes: 586e8fede795 ("HID: logitech-hidpp: Retry commands when device is busy") Cc: stable(a)vger.kernel.org Signed-off-by: Benjamin Tissoires <benjamin.tissoires(a)redhat.com> --- as requested by https://lore.kernel.org/all/CAHk-=wiMbF38KCNhPFiargenpSBoecSXTLQACKS2UMyo_V… This is a rewrite of that particular piece of code. --- drivers/hid/hid-logitech-hidpp.c | 102 +++++++++++++++++++++++---------------- 1 file changed, 61 insertions(+), 41 deletions(-) diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index dfe8e09a18de..3d1ffe199f08 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -275,21 +275,20 @@ static int __hidpp_send_report(struct hid_device *hdev, } /* - * hidpp_send_message_sync() returns 0 in case of success, and something else - * in case of a failure. - * - If ' something else' is positive, that means that an error has been raised - * by the protocol itself. - * - If ' something else' is negative, that means that we had a classic error - * (-ENOMEM, -EPIPE, etc...) + * Effectively send the message to the device, waiting for its answer. + * + * Must be called with hidpp->send_mutex locked + * + * Same return protocol than hidpp_send_message_sync(): + * - success on 0 + * - negative error means transport error + * - positive value means protocol error */ -static int hidpp_send_message_sync(struct hidpp_device *hidpp, +static int __do_hidpp_send_message_sync(struct hidpp_device *hidpp, struct hidpp_report *message, struct hidpp_report *response) { - int ret = -1; - int max_retries = 3; - - mutex_lock(&hidpp->send_mutex); + int ret; hidpp->send_receive_buf = response; hidpp->answer_available = false; @@ -300,41 +299,62 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, */ *response = *message; - for (; max_retries != 0 && ret; max_retries--) { - ret = __hidpp_send_report(hidpp->hid_dev, message); + ret = __hidpp_send_report(hidpp->hid_dev, message); + if (ret) { + dbg_hid("__hidpp_send_report returned err: %d\n", ret); + memset(response, 0, sizeof(struct hidpp_report)); + return ret; + } - if (ret) { - dbg_hid("__hidpp_send_report returned err: %d\n", ret); - memset(response, 0, sizeof(struct hidpp_report)); - break; - } + if (!wait_event_timeout(hidpp->wait, hidpp->answer_available, + 5*HZ)) { + dbg_hid("%s:timeout waiting for response\n", __func__); + memset(response, 0, sizeof(struct hidpp_report)); + return -ETIMEDOUT; + } - if (!wait_event_timeout(hidpp->wait, hidpp->answer_available, - 5*HZ)) { - dbg_hid("%s:timeout waiting for response\n", __func__); - memset(response, 0, sizeof(struct hidpp_report)); - ret = -ETIMEDOUT; - break; - } + if (response->report_id == REPORT_ID_HIDPP_SHORT && + response->rap.sub_id == HIDPP_ERROR) { + ret = response->rap.params[1]; + dbg_hid("%s:got hidpp error %02X\n", __func__, ret); + return ret; + } - if (response->report_id == REPORT_ID_HIDPP_SHORT && - response->rap.sub_id == HIDPP_ERROR) { - ret = response->rap.params[1]; - dbg_hid("%s:got hidpp error %02X\n", __func__, ret); + if ((response->report_id == REPORT_ID_HIDPP_LONG || + response->report_id == REPORT_ID_HIDPP_VERY_LONG) && + response->fap.feature_index == HIDPP20_ERROR) { + ret = response->fap.params[1]; + dbg_hid("%s:got hidpp 2.0 error %02X\n", __func__, ret); + return ret; + } + + return 0; +} + +/* + * hidpp_send_message_sync() returns 0 in case of success, and something else + * in case of a failure. + * - If ' something else' is positive, that means that an error has been raised + * by the protocol itself. + * - If ' something else' is negative, that means that we had a classic error + * (-ENOMEM, -EPIPE, etc...) + */ +static int hidpp_send_message_sync(struct hidpp_device *hidpp, + struct hidpp_report *message, + struct hidpp_report *response) +{ + int ret; + int max_retries = 3; + + mutex_lock(&hidpp->send_mutex); + + do { + ret = __do_hidpp_send_message_sync(hidpp, message, response); + if (ret != HIDPP20_ERROR_BUSY) break; - } - if ((response->report_id == REPORT_ID_HIDPP_LONG || - response->report_id == REPORT_ID_HIDPP_VERY_LONG) && - response->fap.feature_index == HIDPP20_ERROR) { - ret = response->fap.params[1]; - if (ret != HIDPP20_ERROR_BUSY) { - dbg_hid("%s:got hidpp 2.0 error %02X\n", __func__, ret); - break; - } - dbg_hid("%s:got busy hidpp 2.0 error %02X, retrying\n", __func__, ret); - } - } + dbg_hid("%s:got busy hidpp 2.0 error %02X, retrying\n", __func__, ret); + } while (--max_retries); mutex_unlock(&hidpp->send_mutex); return ret; --- base-commit: b98ec211af5508457e2b1c4cc99373630a83fa81 change-id: 20230621-logitech-fixes-a4c0e66ea2ad Best regards, -- Benjamin Tissoires <benjamin.tissoires(a)redhat.com>

2 years, 2 months

4
9
0 0

[PATCH v4 00/17] Venus QoL / maintainability fixes

by Konrad Dybcio

v3 -> v4: - Rebase on Stanimir's venus-for-next-v6.5 - Collapse 2 identical if-statements in "Sanitize venus_boot_core() per-VPU-version" - Reword "Assign registers based on VPU version" - Check for IS_IRIS2_1() instead of wrongly checking for core->use_tz, update commit msg in "media: venus: firmware: Correct IS_V6() checks" - Access correct struct fields in "Use newly-introduced hfi_buffer_requirements accessors", drop Bryan's r-b v3: https://lore.kernel.org/r/20230228-topic-venus-v3-0-6092ae43b58f@linaro.org v2 -> v3: - Rephrase "Write to VIDC_CTRL_INIT after unmasking interrupts" commit msg - Drop "Remap bufreq fields on HFI6XX" - Rephrase "Introduce VPU version distinction" commit msg - Better explain "Leave a clue for homegrown porters" - Drop incorrect fixes tags/rephrase version check alternations - Drop AR50L/IRIS1 from if-conditions, they'll be introduced separately - pick up tags - rebase on next-20230517 (no effective changes) v2: https://lore.kernel.org/r/20230228-topic-venus-v2-0-d95d14949c79@linaro.org v1 -> v2: - Move "Write to VIDC_CTRL_INIT after unmasking interrupts" up and add a Fixes tag & Cc stable - Reword the comment in "Correct IS_V6() checks" - Move up "media: venus: Remap bufreq fields on HFI6XX", add Fixes and Cc stable - Use better English in "Use newly-introduced hfi_buffer_requirements accessors" commit message - Mention "Restrict writing SCIACMDARG3 to Venus V1/V2" doesn't seem to regress SM8250 in the commit message - Pick up tags (note: I capitalized the R in Dikshita's 'reviewed-by' and removed one occurrence of random '**' to make sure review tools like b4 don't go crazy) - Handle AR50_LITE in "Assign registers based on VPU version" - Drop /* VPUn */ comments, they're invalid as explained by Vikash - Take a different approach to the sys_idle problem in patch 1 v1: https://lore.kernel.org/r/20230228-topic-venus-v1-0-58c2c88384e9@linaro.org Currently upstream assumes all (well, almost all - see 7280 or CrOS specific checks) Venus implementations using the same version of the Hardware Firmware Interface can be treated the same way. This is however not the case. This series tries to introduce the groundwork to start differentiating them based on the VPU (Video Processing Unit) hardware type, fixes a couple of issues that were an effect of that generalized assumption and lays the foundation for supporting 8150 (IRIS1) and SM6115/QCM2290 (AR50 Lite), which will hopefully come soon. Tested on 8250, but pretty please test it on your boards too! Signed-off-by: Konrad Dybcio <konrad.dybcio(a)linaro.org> --- Konrad Dybcio (17): media: venus: hfi_venus: Only consider sys_idle_indicator on V1 media: venus: hfi_venus: Write to VIDC_CTRL_INIT after unmasking interrupts media: venus: Introduce VPU version distinction media: venus: Add vpu_version to most SoCs media: venus: firmware: Leave a clue about obtaining CP VARs media: venus: hfi_venus: Sanitize venus_boot_core() per-VPU-version media: venus: core: Assign registers based on VPU version media: venus: hfi_venus: Sanitize venus_halt_axi() per-VPU-version media: venus: hfi_venus: Sanitize venus_isr() per-VPU-version media: venus: hfi_venus: Sanitize venus_cpu_and_video_core_idle() per-VPU-version media: venus: hfi_venus: Sanitize venus_cpu_idle_and_pc_ready() per-VPU-version media: venus: firmware: Sanitize per-VPU-version media: venus: hfi_platform: Check vpu_version instead of device compatible media: venus: vdec: Sanitize vdec_set_work_route() per-VPU-version media: venus: Introduce accessors for remapped hfi_buffer_reqs members media: venus: Use newly-introduced hfi_buffer_requirements accessors media: venus: hfi_venus: Restrict writing SCIACMDARG3 to Venus V1/V2 drivers/media/platform/qcom/venus/core.c | 7 ++- drivers/media/platform/qcom/venus/core.h | 15 ++++++ drivers/media/platform/qcom/venus/firmware.c | 18 +++++-- drivers/media/platform/qcom/venus/helpers.c | 7 +-- drivers/media/platform/qcom/venus/hfi_helper.h | 61 +++++++++++++++++++--- drivers/media/platform/qcom/venus/hfi_msgs.c | 2 +- .../media/platform/qcom/venus/hfi_plat_bufs_v6.c | 22 ++++---- drivers/media/platform/qcom/venus/hfi_platform.c | 2 +- drivers/media/platform/qcom/venus/hfi_venus.c | 42 +++++++-------- drivers/media/platform/qcom/venus/vdec.c | 10 ++-- drivers/media/platform/qcom/venus/vdec_ctrls.c | 2 +- drivers/media/platform/qcom/venus/venc.c | 4 +- drivers/media/platform/qcom/venus/venc_ctrls.c | 2 +- 13 files changed, 133 insertions(+), 61 deletions(-) --- base-commit: 9f9f8ca6f012d25428f8605cb36369a449db8508 change-id: 20230228-topic-venus-70ea3bc76688 Best regards, -- Konrad Dybcio <konrad.dybcio(a)linaro.org>

2 years, 2 months

2
3
0 0

[PATCH 1/2] drm/client: Fix memory leak in drm_client_target_cloned

by Jocelyn Falempe

dmt_mode is allocated and never freed in this function. It was found with the ast driver, but most drivers using generic fbdev setup are probably affected. This fixes the following kmemleak report: backtrace: [<00000000b391296d>] drm_mode_duplicate+0x45/0x220 [drm] [<00000000e45bb5b3>] drm_client_target_cloned.constprop.0+0x27b/0x480 [drm] [<00000000ed2d3a37>] drm_client_modeset_probe+0x6bd/0xf50 [drm] [<0000000010e5cc9d>] __drm_fb_helper_initial_config_and_unlock+0xb4/0x2c0 [drm_kms_helper] [<00000000909f82ca>] drm_fbdev_client_hotplug+0x2bc/0x4d0 [drm_kms_helper] [<00000000063a69aa>] drm_client_register+0x169/0x240 [drm] [<00000000a8c61525>] ast_pci_probe+0x142/0x190 [ast] [<00000000987f19bb>] local_pci_probe+0xdc/0x180 [<000000004fca231b>] work_for_cpu_fn+0x4e/0xa0 [<0000000000b85301>] process_one_work+0x8b7/0x1540 [<000000003375b17c>] worker_thread+0x70a/0xed0 [<00000000b0d43cd9>] kthread+0x29f/0x340 [<000000008d770833>] ret_from_fork+0x1f/0x30 unreferenced object 0xff11000333089a00 (size 128): cc: <stable(a)vger.kernel.org> Fixes: 1d42bbc8f7f9 ("drm/fbdev: fix cloning on fbcon") Reported-by: Zhang Yi <yizhan(a)redhat.com> Signed-off-by: Jocelyn Falempe <jfalempe(a)redhat.com> --- drivers/gpu/drm/drm_client_modeset.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 1b12a3c201a3..a4a62aa99984 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -311,6 +311,9 @@ static bool drm_client_target_cloned(struct drm_device *dev, can_clone = true; dmt_mode = drm_mode_find_dmt(dev, 1024, 768, 60, false); + if (!dmt_mode) + goto fail; + for (i = 0; i < connector_count; i++) { if (!enabled[i]) continue; @@ -326,11 +329,13 @@ static bool drm_client_target_cloned(struct drm_device *dev, if (!modes[i]) can_clone = false; } + kfree(dmt_mode); if (can_clone) { DRM_DEBUG_KMS("can clone using 1024x768\n"); return true; } +fail: DRM_INFO("kms: can't enable cloning when we probably wanted to.\n"); return false; } -- 2.41.0

2 years, 2 months

3
2
0 0

[PATCH 2/2] drm/client: Fix memory leak in drm_client_modeset_probe

by Jocelyn Falempe

When a new mode is set to modeset->mode, the previous mode should be freed. This fixes the following kmemleak report: drm_mode_duplicate+0x45/0x220 [drm] drm_client_modeset_probe+0x944/0xf50 [drm] __drm_fb_helper_initial_config_and_unlock+0xb4/0x2c0 [drm_kms_helper] drm_fbdev_client_hotplug+0x2bc/0x4d0 [drm_kms_helper] drm_client_register+0x169/0x240 [drm] ast_pci_probe+0x142/0x190 [ast] local_pci_probe+0xdc/0x180 work_for_cpu_fn+0x4e/0xa0 process_one_work+0x8b7/0x1540 worker_thread+0x70a/0xed0 kthread+0x29f/0x340 ret_from_fork+0x1f/0x30 cc: <stable(a)vger.kernel.org> Reported-by: Zhang Yi <yizhan(a)redhat.com> Signed-off-by: Jocelyn Falempe <jfalempe(a)redhat.com> --- drivers/gpu/drm/drm_client_modeset.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index a4a62aa99984..5d4703b4648a 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -867,6 +867,9 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, break; } + if (modeset->mode) + kfree(modeset->mode); + modeset->mode = drm_mode_duplicate(dev, mode); drm_connector_get(connector); modeset->connectors[modeset->num_connectors++] = connector; -- 2.41.0

2 years, 2 months

3
2
0 0

[PATCH V2 1/3] nvme: fix possible hang when removing a controller during error recovery

by Ming Lei

Error recovery can be interrupted by controller removal, then the controller is left as quiesced, and IO hang can be caused. Fix the issue by unquiescing controller unconditionally when removing namespaces. This way is reasonable and safe given forward progress can be made when removing namespaces. Reviewed-by: Keith Busch <kbusch(a)kernel.org> Reviewed-by: Sagi Grimberg <sagi(a)grimberg.me> Reported-by: Chunguang Xu <brookxu.cn(a)gmail.com> Closes: https://lore.kernel.org/linux-nvme/cover.1685350577.git.chunguang.xu@shopee… Cc: stable(a)vger.kernel.org Signed-off-by: Ming Lei <ming.lei(a)redhat.com> --- drivers/nvme/host/core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 47d7ba2827ff..98fa8315bc65 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3903,6 +3903,12 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) */ nvme_mpath_clear_ctrl_paths(ctrl); + /* + * Unquiesce io queues so any pending IO won't hang, especially + * those submitted from scan work + */ + nvme_unquiesce_io_queues(ctrl); + /* prevent racing with ns scanning */ flush_work(&ctrl->scan_work); @@ -3912,10 +3918,8 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) * removing the namespaces' disks; fail all the queues now to avoid * potentially having to clean up the failed sync later. */ - if (ctrl->state == NVME_CTRL_DEAD) { + if (ctrl->state == NVME_CTRL_DEAD) nvme_mark_namespaces_dead(ctrl); - nvme_unquiesce_io_queues(ctrl); - } /* this is a no-op when called from the controller reset handler */ nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO); -- 2.40.1

2 years, 2 months

1
0
0 0

[PATCH v3] drm/amdgpu/vkms: relax timer deactivation by hrtimer_try_to_cancel

by Guchun Chen

In below thousands of screen rotation loop tests with virtual display enabled, a CPU hard lockup issue may happen, leading system to unresponsive and crash. do { xrandr --output Virtual --rotate inverted xrandr --output Virtual --rotate right xrandr --output Virtual --rotate left xrandr --output Virtual --rotate normal } while (1); NMI watchdog: Watchdog detected hard LOCKUP on cpu 1 ? hrtimer_run_softirq+0x140/0x140 ? store_vblank+0xe0/0xe0 [drm] hrtimer_cancel+0x15/0x30 amdgpu_vkms_disable_vblank+0x15/0x30 [amdgpu] drm_vblank_disable_and_save+0x185/0x1f0 [drm] drm_crtc_vblank_off+0x159/0x4c0 [drm] ? record_print_text.cold+0x11/0x11 ? wait_for_completion_timeout+0x232/0x280 ? drm_crtc_wait_one_vblank+0x40/0x40 [drm] ? bit_wait_io_timeout+0xe0/0xe0 ? wait_for_completion_interruptible+0x1d7/0x320 ? mutex_unlock+0x81/0xd0 amdgpu_vkms_crtc_atomic_disable It's caused by a stuck in lock dependency in such scenario on different CPUs. CPU1 CPU2 drm_crtc_vblank_off hrtimer_interrupt grab event_lock (irq disabled) __hrtimer_run_queues grab vbl_lock/vblank_time_block amdgpu_vkms_vblank_simulate amdgpu_vkms_disable_vblank drm_handle_vblank hrtimer_cancel grab dev->event_lock So CPU1 stucks in hrtimer_cancel as timer callback is running endless on current clock base, as that timer queue on CPU2 has no chance to finish it because of failing to hold the lock. So NMI watchdog will throw the errors after its threshold, and all later CPUs are impacted/blocked. So use hrtimer_try_to_cancel to fix this, as disable_vblank callback does not need to wait the handler to finish. And also it's not necessary to check the return value of hrtimer_try_to_cancel, because even if it's -1 which means current timer callback is running, it will be reprogrammed in hrtimer_start with calling enable_vblank to make it works. v2: only re-arm timer when vblank is enabled (Christian) and add a Fixes tag as well v3: drop warn printing (Christian) Fixes: 84ec374bd580("drm/amdgpu: create amdgpu_vkms (v4)") Cc: stable(a)vger.kernel.org Suggested-by: Christian König <christian.koenig(a)amd.com> Signed-off-by: Guchun Chen <guchun.chen(a)amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 53ff91fc6cf6..b870c827cbaa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -46,7 +46,10 @@ static enum hrtimer_restart amdgpu_vkms_vblank_simulate(struct hrtimer *timer) struct amdgpu_crtc *amdgpu_crtc = container_of(timer, struct amdgpu_crtc, vblank_timer); struct drm_crtc *crtc = &amdgpu_crtc->base; struct amdgpu_vkms_output *output = drm_crtc_to_amdgpu_vkms_output(crtc); + struct drm_vblank_crtc *vblank; + struct drm_device *dev; u64 ret_overrun; + unsigned int pipe; bool ret; ret_overrun = hrtimer_forward_now(&amdgpu_crtc->vblank_timer, @@ -54,9 +57,13 @@ static enum hrtimer_restart amdgpu_vkms_vblank_simulate(struct hrtimer *timer) if (ret_overrun != 1) DRM_WARN("%s: vblank timer overrun\n", __func__); + dev = crtc->dev; + pipe = drm_crtc_index(crtc); + vblank = &dev->vblank[pipe]; ret = drm_crtc_handle_vblank(crtc); - if (!ret) - DRM_ERROR("amdgpu_vkms failure on handling vblank"); + /* Don't queue timer again when vblank is disabled. */ + if (!ret && !READ_ONCE(vblank->enabled)) + return HRTIMER_NORESTART; return HRTIMER_RESTART; } @@ -81,7 +88,7 @@ static void amdgpu_vkms_disable_vblank(struct drm_crtc *crtc) { struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - hrtimer_cancel(&amdgpu_crtc->vblank_timer); + hrtimer_try_to_cancel(&amdgpu_crtc->vblank_timer); } static bool amdgpu_vkms_get_vblank_timestamp(struct drm_crtc *crtc, -- 2.25.1

2 years, 2 months

3
4
0 0

[PATCH v2 0/2] docs: stable-kernel-rules: add delayed backporting option and a few tweaks

by Thorsten Leemhuis

I only set down to create the first of the two patches. But while doing so I noticed a few things that seemed odd for me with my background on writing and editing texts. So I just quickly performed a few additional changes to fix those to see if the stable team would appreciate them, as this document is clearly their domain. v2: [this mail] * a few small tweaks after feedback from v1 submission * drop patch 3 for now * drop RFC v1: https://lore.kernel.org/linux-doc/d30686781c47c83927e0a41f6a1167a679fa822c.… Thorsten Leemhuis (2): docs: stable-kernel-rules: mention other usages for stable tag comments docs: stable-kernel-rules: make rule section more straight forward Documentation/process/stable-kernel-rules.rst | 60 ++++++++++++------- 1 file changed, 37 insertions(+), 23 deletions(-) base-commit: 016571b6d52deb473676fb4d24baf8ed3667ae21 -- 2.40.1

2 years, 2 months

1
2
0 0

Linux 6.4.3

by Greg Kroah-Hartman

I'm announcing the release of the 6.4.3 kernel. All users of the 6.4 kernel series must upgrade. The updated 6.4.y git tree can be found at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git linux-6.4.y and can be browsed at the normal kernel.org git web browser: https://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git;a=summary thanks, greg k-h ------------ Makefile | 2 +- include/linux/bootmem_info.h | 2 ++ kernel/fork.c | 1 + mm/memory.c | 7 +++++++ mm/mmap.c | 6 ++++++ 5 files changed, 17 insertions(+), 1 deletion(-) Greg Kroah-Hartman (1): Linux 6.4.3 Hugh Dickins (1): mm: lock newly mapped VMA with corrected ordering Liu Shixin (1): bootmem: remove the vmemmap pages from kmemleak in free_bootmem_page Peter Collingbourne (1): mm: call arch_swap_restore() from do_swap_page() Suren Baghdasaryan (3): mm: lock a vma before stack expansion mm: lock newly mapped VMA which can be modified after it becomes visible fork: lock VMAs of the parent process when forking

2 years, 2 months

1
1
0 0

[PATCH V2 net] net: mana: Configure hwc timeout from hardware

by Souradeep Chakrabarti

At present hwc timeout value is a fixed value. This patch sets the hwc timeout from the hardware. Signed-off-by: Souradeep Chakrabarti <schakrabarti(a)linux.microsoft.com> --- V1 -> V2: * Added return check for mana_gd_query_hwc_timeout * Removed dev_err from mana_gd_query_hwc_timeout --- .../net/ethernet/microsoft/mana/gdma_main.c | 30 ++++++++++++++++++- .../net/ethernet/microsoft/mana/hw_channel.c | 25 +++++++++++++++- include/net/mana/gdma.h | 20 ++++++++++++- include/net/mana/hw_channel.h | 5 ++++ 4 files changed, 77 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 8f3f78b68592..949c927c3a7e 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -106,6 +106,27 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev) return 0; } +static int mana_gd_query_hwc_timeout(struct pci_dev *pdev, u32 *timeout_val) +{ + struct gdma_context *gc = pci_get_drvdata(pdev); + struct gdma_query_hwc_timeout_req req = {}; + struct gdma_query_hwc_timeout_resp resp = {}; + int err; + + mana_gd_init_req_hdr(&req.hdr, GDMA_QUERY_HWC_TIMEOUT, + sizeof(req), sizeof(resp)); + req.timeout_ms = *timeout_val; + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); + if (err || resp.hdr.status) + return err ? err : -EPROTO; + + *timeout_val = resp.timeout_ms; + dev_info(gc->dev, "Successfully changed the timeout value %u\n", + *timeout_val); + + return 0; +} + static int mana_gd_detect_devices(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); @@ -879,6 +900,7 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev) struct gdma_context *gc = pci_get_drvdata(pdev); struct gdma_verify_ver_resp resp = {}; struct gdma_verify_ver_req req = {}; + struct hw_channel_context *hwc = gc->hwc.driver_data; int err; mana_gd_init_req_hdr(&req.hdr, GDMA_VERIFY_VF_DRIVER_VERSION, @@ -907,7 +929,13 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev) err, resp.hdr.status); return err ? err : -EPROTO; } - + if (resp.pf_cap_flags1 & GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) { + err = mana_gd_query_hwc_timeout(pdev, &hwc->hwc_timeout); + if (err) { + dev_err(gc->dev, "Failed to set the hwc timeout %d\n", err); + return err; + } + } return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 2bd1d74021f7..db433501e5e6 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -174,7 +174,25 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, complete(&hwc->hwc_init_eqe_comp); break; + case GDMA_EQE_HWC_SOC_RECONFIG_DATA: + type_data.as_uint32 = event->details[0]; + type = type_data.type; + val = type_data.value; + + switch (type) { + case HWC_DATA_CFG_HWC_TIMEOUT: + hwc->hwc_timeout = val; + break; + + default: + dev_warn(hwc->dev, "Received unknown reconfig type %u\n", type); + break; + } + + break; + default: + dev_warn(hwc->dev, "Received unknown gdma event %u\n", event->type); /* Ignore unknown events, which should never happen. */ break; } @@ -704,6 +722,7 @@ int mana_hwc_create_channel(struct gdma_context *gc) gd->pdid = INVALID_PDID; gd->doorbell = INVALID_DOORBELL; + hwc->hwc_timeout = HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS; /* mana_hwc_init_queues() only creates the required data structures, * and doesn't touch the HWC device. */ @@ -770,6 +789,8 @@ void mana_hwc_destroy_channel(struct gdma_context *gc) hwc->gdma_dev->doorbell = INVALID_DOORBELL; hwc->gdma_dev->pdid = INVALID_PDID; + hwc->hwc_timeout = 0; + kfree(hwc); gc->hwc.driver_data = NULL; gc->hwc.gdma_context = NULL; @@ -818,6 +839,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, dest_vrq = hwc->pf_dest_vrq_id; dest_vrcq = hwc->pf_dest_vrcq_id; } + dev_err(hwc->dev, "HWC: timeout %u ms\n", hwc->hwc_timeout); err = mana_hwc_post_tx_wqe(txq, tx_wr, dest_vrq, dest_vrcq, false); if (err) { @@ -825,7 +847,8 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, goto out; } - if (!wait_for_completion_timeout(&ctx->comp_event, 30 * HZ)) { + if (!wait_for_completion_timeout(&ctx->comp_event, + (hwc->hwc_timeout / 1000) * HZ)) { dev_err(hwc->dev, "HWC: Request timed out!\n"); err = -ETIMEDOUT; goto out; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 96c120160f15..88b6ef7ce1a6 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -33,6 +33,7 @@ enum gdma_request_type { GDMA_DESTROY_PD = 30, GDMA_CREATE_MR = 31, GDMA_DESTROY_MR = 32, + GDMA_QUERY_HWC_TIMEOUT = 84, /* 0x54 */ }; #define GDMA_RESOURCE_DOORBELL_PAGE 27 @@ -57,6 +58,8 @@ enum gdma_eqe_type { GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, GDMA_EQE_HWC_INIT_DATA = 130, GDMA_EQE_HWC_INIT_DONE = 131, + GDMA_EQE_HWC_SOC_RECONFIG = 132, + GDMA_EQE_HWC_SOC_RECONFIG_DATA = 133, }; enum { @@ -531,10 +534,12 @@ enum { * so the driver is able to reliably support features like busy_poll. */ #define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2) +#define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3) #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ - GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX) + GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ + GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) #define GDMA_DRV_CAP_FLAGS2 0 @@ -664,6 +669,19 @@ struct gdma_disable_queue_req { u32 alloc_res_id_on_creation; }; /* HW DATA */ +/* GDMA_QUERY_HWC_TIMEOUT */ +struct gdma_query_hwc_timeout_req { + struct gdma_req_hdr hdr; + u32 timeout_ms; + u32 reserved; +}; + +struct gdma_query_hwc_timeout_resp { + struct gdma_resp_hdr hdr; + u32 timeout_ms; + u32 reserved; +}; + enum atb_page_size { ATB_PAGE_SIZE_4K, ATB_PAGE_SIZE_8K, diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h index 6a757a6e2732..3d3b5c881bc1 100644 --- a/include/net/mana/hw_channel.h +++ b/include/net/mana/hw_channel.h @@ -23,6 +23,10 @@ #define HWC_INIT_DATA_PF_DEST_RQ_ID 10 #define HWC_INIT_DATA_PF_DEST_CQ_ID 11 +#define HWC_DATA_CFG_HWC_TIMEOUT 1 + +#define HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS 30000 + /* Structures labeled with "HW DATA" are exchanged with the hardware. All of * them are naturally aligned and hence don't need __packed. */ @@ -182,6 +186,7 @@ struct hw_channel_context { u32 pf_dest_vrq_id; u32 pf_dest_vrcq_id; + u32 hwc_timeout; struct hwc_caller_ctx *caller_ctx; }; -- 2.34.1

2 years, 2 months

5
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2023