March 2025 - Linux-stable-mirror

[PATCH v1] HID: usbhid: Eliminate recurrent out-of-bounds bug in usbhid_parse()

by Terry Junge

Update struct hid_descriptor to better reflect the mandatory and optional parts of the HID Descriptor as per USB HID 1.11 specification. Note: the kernel currently does not parse any optional HID class descriptors, only the mandatory report descriptor. Update all references to member element desc[0] to rpt_desc. Add test to verify bLength and bNumDescriptors values are valid. Replace the for loop with direct access to the mandatory HID class descriptor member for the report descriptor. This eliminates the possibility of getting an out-of-bounds fault. Add a warning message if the HID descriptor contains any unsupported optional HID class descriptors. Reported-by: syzbot+c52569baf0c843f35495(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=c52569baf0c843f35495 Fixes: f043bfc98c19 ("HID: usbhid: fix out-of-bounds bug") Cc: stable(a)vger.kernel.org Signed-off-by: Terry Junge <linuxhid(a)cosmicgizmosystems.com> --- v1: Remove unnecessary for loop searching for the report descriptor size. base-commit: 58c9bf3363e596d744f56616d407278ef5f97f5a P.S. This is an alternative to the solution proposed by Nikita Zhandarovich <n.zhandarovich(a)fintech.ru> Link: https://lore.kernel.org/all/20250131151600.410242-1-n.zhandarovich@fintech.… include/linux/hid.h | 3 ++- drivers/usb/gadget/function/f_hid.c | 12 ++++++------ drivers/hid/hid-hyperv.c | 4 ++-- drivers/hid/usbhid/hid-core.c | 25 ++++++++++++++----------- 4 files changed, 24 insertions(+), 20 deletions(-) diff --git a/include/linux/hid.h b/include/linux/hid.h index cdc0dc13c87f..7abc8c74bdd5 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -738,8 +738,9 @@ struct hid_descriptor { __le16 bcdHID; __u8 bCountryCode; __u8 bNumDescriptors; + struct hid_class_descriptor rpt_desc; - struct hid_class_descriptor desc[1]; + struct hid_class_descriptor opt_descs[]; } __attribute__ ((packed)); #define HID_DEVICE(b, g, ven, prod) \ diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 740311c4fa24..c7a05f842745 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -144,8 +144,8 @@ static struct hid_descriptor hidg_desc = { .bcdHID = cpu_to_le16(0x0101), .bCountryCode = 0x00, .bNumDescriptors = 0x1, - /*.desc[0].bDescriptorType = DYNAMIC */ - /*.desc[0].wDescriptorLenght = DYNAMIC */ + /*.rpt_desc.bDescriptorType = DYNAMIC */ + /*.rpt_desc.wDescriptorLength = DYNAMIC */ }; /* Super-Speed Support */ @@ -939,8 +939,8 @@ static int hidg_setup(struct usb_function *f, struct hid_descriptor hidg_desc_copy = hidg_desc; VDBG(cdev, "USB_REQ_GET_DESCRIPTOR: HID\n"); - hidg_desc_copy.desc[0].bDescriptorType = HID_DT_REPORT; - hidg_desc_copy.desc[0].wDescriptorLength = + hidg_desc_copy.rpt_desc.bDescriptorType = HID_DT_REPORT; + hidg_desc_copy.rpt_desc.wDescriptorLength = cpu_to_le16(hidg->report_desc_length); length = min_t(unsigned short, length, @@ -1210,8 +1210,8 @@ static int hidg_bind(struct usb_configuration *c, struct usb_function *f) * We can use hidg_desc struct here but we should not relay * that its content won't change after returning from this function. */ - hidg_desc.desc[0].bDescriptorType = HID_DT_REPORT; - hidg_desc.desc[0].wDescriptorLength = + hidg_desc.rpt_desc.bDescriptorType = HID_DT_REPORT; + hidg_desc.rpt_desc.wDescriptorLength = cpu_to_le16(hidg->report_desc_length); hidg_hs_in_ep_desc.bEndpointAddress = diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index 0fb210e40a41..9eafff0b6ea4 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -192,7 +192,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device, goto cleanup; input_device->report_desc_size = le16_to_cpu( - desc->desc[0].wDescriptorLength); + desc->rpt_desc.wDescriptorLength); if (input_device->report_desc_size == 0) { input_device->dev_info_status = -EINVAL; goto cleanup; @@ -210,7 +210,7 @@ static void mousevsc_on_receive_device_info(struct mousevsc_dev *input_device, memcpy(input_device->report_desc, ((unsigned char *)desc) + desc->bLength, - le16_to_cpu(desc->desc[0].wDescriptorLength)); + le16_to_cpu(desc->rpt_desc.wDescriptorLength)); /* Send the ack */ memset(&ack, 0, sizeof(struct mousevsc_prt_msg)); diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index a6eb6fe6130d..e668143b559d 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -983,12 +983,11 @@ static int usbhid_parse(struct hid_device *hid) struct usb_host_interface *interface = intf->cur_altsetting; struct usb_device *dev = interface_to_usbdev (intf); struct hid_descriptor *hdesc; + struct hid_class_descriptor *hcdesc; u32 quirks = 0; unsigned int rsize = 0; char *rdesc; - int ret, n; - int num_descriptors; - size_t offset = offsetof(struct hid_descriptor, desc); + int ret; quirks = hid_lookup_quirk(hid); @@ -1010,20 +1009,19 @@ static int usbhid_parse(struct hid_device *hid) return -ENODEV; } - if (hdesc->bLength < sizeof(struct hid_descriptor)) { - dbg_hid("hid descriptor is too short\n"); + if (!hdesc->bNumDescriptors || + hdesc->bLength != sizeof(*hdesc) + + (hdesc->bNumDescriptors - 1) * sizeof(*hcdesc)) { + dbg_hid("hid descriptor invalid, bLen=%hhu bNum=%hhu\n", + hdesc->bLength, hdesc->bNumDescriptors); return -EINVAL; } hid->version = le16_to_cpu(hdesc->bcdHID); hid->country = hdesc->bCountryCode; - num_descriptors = min_t(int, hdesc->bNumDescriptors, - (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor)); - - for (n = 0; n < num_descriptors; n++) - if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT) - rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength); + if (hdesc->rpt_desc.bDescriptorType == HID_DT_REPORT) + rsize = le16_to_cpu(hdesc->rpt_desc.wDescriptorLength); if (!rsize || rsize > HID_MAX_DESCRIPTOR_SIZE) { dbg_hid("weird size of report descriptor (%u)\n", rsize); @@ -1051,6 +1049,11 @@ static int usbhid_parse(struct hid_device *hid) goto err; } + if (hdesc->bNumDescriptors > 1) + hid_warn(intf, + "%hhu unsupported optional hid class descriptors\n", + hdesc->bNumDescriptors - 1); + hid->quirks |= quirks; return 0; -- 2.43.0

2 months, 1 week

4
4
0 0

[PATCH v4 5/6] media: mt9m114: Fix deadlock in get_frame_interval/set_frame_interval

by Mathis Foerst

Getting / Setting the frame interval using the V4L2 subdev pad ops get_frame_interval/set_frame_interval causes a deadlock, as the subdev state is locked in the [1] but also in the driver itself. In [2] it's described that the caller is responsible to acquire and release the lock in this case. Therefore, acquiring the lock in the driver is wrong. Remove the lock acquisitions/releases from mt9m114_ifp_get_frame_interval() and mt9m114_ifp_set_frame_interval(). [1] drivers/media/v4l2-core/v4l2-subdev.c - line 1129 [2] Documentation/driver-api/media/v4l2-subdev.rst Fixes: 24d756e914fc ("media: i2c: Add driver for onsemi MT9M114 camera sensor") Cc: stable(a)vger.kernel.org Signed-off-by: Mathis Foerst <mathis.foerst(a)mt.com> --- drivers/media/i2c/mt9m114.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/media/i2c/mt9m114.c b/drivers/media/i2c/mt9m114.c index 65b9124e464f..79c97ab19be9 100644 --- a/drivers/media/i2c/mt9m114.c +++ b/drivers/media/i2c/mt9m114.c @@ -1644,13 +1644,9 @@ static int mt9m114_ifp_get_frame_interval(struct v4l2_subdev *sd, if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) return -EINVAL; - mutex_lock(sensor->ifp.hdl.lock); - ival->numerator = 1; ival->denominator = sensor->ifp.frame_rate; - mutex_unlock(sensor->ifp.hdl.lock); - return 0; } @@ -1669,8 +1665,6 @@ static int mt9m114_ifp_set_frame_interval(struct v4l2_subdev *sd, if (interval->which != V4L2_SUBDEV_FORMAT_ACTIVE) return -EINVAL; - mutex_lock(sensor->ifp.hdl.lock); - if (ival->numerator != 0 && ival->denominator != 0) sensor->ifp.frame_rate = min_t(unsigned int, ival->denominator / ival->numerator, @@ -1684,8 +1678,6 @@ static int mt9m114_ifp_set_frame_interval(struct v4l2_subdev *sd, if (sensor->streaming) ret = mt9m114_set_frame_rate(sensor); - mutex_unlock(sensor->ifp.hdl.lock); - return ret; } -- 2.34.1

2 months, 1 week

2
1
0 0

FAILED: patch "[PATCH] mmc: sdhci-brcmstb: add cqhci suspend/resume to PM ops" 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 723ef0e20dbb2aa1b5406d2bb75374fc48187daa # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025032414-unsheathe-greedily-1d17@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 723ef0e20dbb2aa1b5406d2bb75374fc48187daa Mon Sep 17 00:00:00 2001 From: Kamal Dasu <kamal.dasu(a)broadcom.com> Date: Tue, 11 Mar 2025 12:59:35 -0400 Subject: [PATCH] mmc: sdhci-brcmstb: add cqhci suspend/resume to PM ops cqhci timeouts observed on brcmstb platforms during suspend: ... [ 164.832853] mmc0: cqhci: timeout for tag 18 ... Adding cqhci_suspend()/resume() calls to disable cqe in sdhci_brcmstb_suspend()/resume() respectively to fix CQE timeouts seen on PM suspend. Fixes: d46ba2d17f90 ("mmc: sdhci-brcmstb: Add support for Command Queuing (CQE)") Cc: stable(a)vger.kernel.org Signed-off-by: Kamal Dasu <kamal.dasu(a)broadcom.com> Reviewed-by: Florian Fainelli <florian.fainelli(a)broadcom.com> Link: https://lore.kernel.org/r/20250311165946.28190-1-kamal.dasu@broadcom.com Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org> diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c index 0ef4d578ade8..48cdcba0f39c 100644 --- a/drivers/mmc/host/sdhci-brcmstb.c +++ b/drivers/mmc/host/sdhci-brcmstb.c @@ -503,8 +503,15 @@ static int sdhci_brcmstb_suspend(struct device *dev) struct sdhci_host *host = dev_get_drvdata(dev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host); + int ret; clk_disable_unprepare(priv->base_clk); + if (host->mmc->caps2 & MMC_CAP2_CQE) { + ret = cqhci_suspend(host->mmc); + if (ret) + return ret; + } + return sdhci_pltfm_suspend(dev); } @@ -529,6 +536,9 @@ static int sdhci_brcmstb_resume(struct device *dev) ret = clk_set_rate(priv->base_clk, priv->base_freq_hz); } + if (host->mmc->caps2 & MMC_CAP2_CQE) + ret = cqhci_resume(host->mmc); + return ret; } #endif

2 months, 1 week

3
7
0 0

FAILED: patch "[PATCH] mmc: sdhci-brcmstb: add cqhci suspend/resume to PM ops" 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 723ef0e20dbb2aa1b5406d2bb75374fc48187daa # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025032413-email-washer-d578@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 723ef0e20dbb2aa1b5406d2bb75374fc48187daa Mon Sep 17 00:00:00 2001 From: Kamal Dasu <kamal.dasu(a)broadcom.com> Date: Tue, 11 Mar 2025 12:59:35 -0400 Subject: [PATCH] mmc: sdhci-brcmstb: add cqhci suspend/resume to PM ops cqhci timeouts observed on brcmstb platforms during suspend: ... [ 164.832853] mmc0: cqhci: timeout for tag 18 ... Adding cqhci_suspend()/resume() calls to disable cqe in sdhci_brcmstb_suspend()/resume() respectively to fix CQE timeouts seen on PM suspend. Fixes: d46ba2d17f90 ("mmc: sdhci-brcmstb: Add support for Command Queuing (CQE)") Cc: stable(a)vger.kernel.org Signed-off-by: Kamal Dasu <kamal.dasu(a)broadcom.com> Reviewed-by: Florian Fainelli <florian.fainelli(a)broadcom.com> Link: https://lore.kernel.org/r/20250311165946.28190-1-kamal.dasu@broadcom.com Signed-off-by: Ulf Hansson <ulf.hansson(a)linaro.org> diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c index 0ef4d578ade8..48cdcba0f39c 100644 --- a/drivers/mmc/host/sdhci-brcmstb.c +++ b/drivers/mmc/host/sdhci-brcmstb.c @@ -503,8 +503,15 @@ static int sdhci_brcmstb_suspend(struct device *dev) struct sdhci_host *host = dev_get_drvdata(dev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host); + int ret; clk_disable_unprepare(priv->base_clk); + if (host->mmc->caps2 & MMC_CAP2_CQE) { + ret = cqhci_suspend(host->mmc); + if (ret) + return ret; + } + return sdhci_pltfm_suspend(dev); } @@ -529,6 +536,9 @@ static int sdhci_brcmstb_resume(struct device *dev) ret = clk_set_rate(priv->base_clk, priv->base_freq_hz); } + if (host->mmc->caps2 & MMC_CAP2_CQE) + ret = cqhci_resume(host->mmc); + return ret; } #endif

2 months, 1 week

3
8
0 0

[PATCH] media: imagination: fix a potential memory leak in e5010_probe()

by Haoxiang Li

Add video_device_release() to release the memory allocated by video_device_alloc() if something goes wrong. Fixes: a1e294045885 ("media: imagination: Add E5010 JPEG Encoder driver") Cc: stable(a)vger.kernel.org Signed-off-by: Haoxiang Li <haoxiang_li2024(a)163.com> --- drivers/media/platform/imagination/e5010-jpeg-enc.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/media/platform/imagination/e5010-jpeg-enc.c b/drivers/media/platform/imagination/e5010-jpeg-enc.c index c194f830577f..53e501b5ac0a 100644 --- a/drivers/media/platform/imagination/e5010-jpeg-enc.c +++ b/drivers/media/platform/imagination/e5010-jpeg-enc.c @@ -1057,8 +1057,11 @@ static int e5010_probe(struct platform_device *pdev) e5010->vdev->lock = &e5010->mutex; ret = v4l2_device_register(dev, &e5010->v4l2_dev); - if (ret) - return dev_err_probe(dev, ret, "failed to register v4l2 device\n"); + if (ret) { + dev_err_probe(dev, ret, "failed to register v4l2 device\n"); + goto fail_after_video_device_alloc; + } + e5010->m2m_dev = v4l2_m2m_init(&e5010_m2m_ops); if (IS_ERR(e5010->m2m_dev)) { @@ -1118,6 +1121,8 @@ static int e5010_probe(struct platform_device *pdev) v4l2_m2m_release(e5010->m2m_dev); fail_after_v4l2_register: v4l2_device_unregister(&e5010->v4l2_dev); +fail_after_video_device_alloc: + video_device_release(e5010->vdev); return ret; } -- 2.25.1

2 months, 1 week

2
1
0 0

[PATCH 5.15.y] fs/ntfs3: Fixed overflow check in mi_enum_attr()

by bin.lan.cn＠windriver.com

From: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> [ Upstream commit 652cfeb43d6b9aba5c7c4902bed7a7340df131fb ] Reported-by: Robert Morris <rtm(a)csail.mit.edu> Signed-off-by: Konstantin Komarov <almaz.alexandrovich(a)paragon-software.com> Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Build test passed. --- fs/ntfs3/record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 383fc3437f02..fb0683c983cf 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -263,7 +263,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; t32 = le32_to_cpu(attr->res.data_size); - if (t16 + t32 > asize) + if (t32 > asize - t16) return NULL; if (attr->name_len && -- 2.34.1

2 months, 1 week

3
2
0 0

[PATCH 6.1&6.6 V3 0/3] sign-file,extract-cert: switch to PROVIDER API for OpenSSL >= 3.0

by Huacai Chen

Backport this series to 6.1&6.6 because we get build errors with GCC14 and OpenSSL3 (or later): certs/extract-cert.c: In function 'main': certs/extract-cert.c:124:17: error: implicit declaration of function 'ENGINE_load_builtin_engines' [-Wimplicit-function-declaration] 124 | ENGINE_load_builtin_engines(); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ certs/extract-cert.c:126:21: error: implicit declaration of function 'ENGINE_by_id' [-Wimplicit-function-declaration] 126 | e = ENGINE_by_id("pkcs11"); | ^~~~~~~~~~~~ certs/extract-cert.c:126:19: error: assignment to 'ENGINE *' {aka 'struct engine_st *'} from 'int' makes pointer from integer without a cast [-Wint-conversion] 126 | e = ENGINE_by_id("pkcs11"); | ^ certs/extract-cert.c:128:21: error: implicit declaration of function 'ENGINE_init' [-Wimplicit-function-declaration] 128 | if (ENGINE_init(e)) | ^~~~~~~~~~~ certs/extract-cert.c:133:30: error: implicit declaration of function 'ENGINE_ctrl_cmd_string' [-Wimplicit-function-declaration] 133 | ERR(!ENGINE_ctrl_cmd_string(e, "PIN", key_pass, 0), "Set PKCS#11 PIN"); | ^~~~~~~~~~~~~~~~~~~~~~ certs/extract-cert.c:64:32: note: in definition of macro 'ERR' 64 | bool __cond = (cond); \ | ^~~~ certs/extract-cert.c:134:17: error: implicit declaration of function 'ENGINE_ctrl_cmd' [-Wimplicit-function-declaration] 134 | ENGINE_ctrl_cmd(e, "LOAD_CERT_CTRL", 0, &parms, NULL, 1); | ^~~~~~~~~~~~~~~ In theory 5.4&5.10&5.15 also need this, but they need more efforts because file paths are different. The ENGINE interface has its limitations and it has been superseded by the PROVIDER API, it is deprecated in OpenSSL version 3.0. Some distros have started removing it from header files. Update sign-file and extract-cert to use PROVIDER API for OpenSSL Major >= 3. Tested on F39 with openssl-3.1.1, pkcs11-provider-0.5-2, openssl-pkcs11-0.4.12-4 and softhsm-2.6.1-5 by using same key/cert as PEM and PKCS11 and comparing that the result is identical. V1 -> V2: Add upstream commit id. V2 -> V3: Add correct version id. Jan Stancek (3): sign-file,extract-cert: move common SSL helper functions to a header sign-file,extract-cert: avoid using deprecated ERR_get_error_line() sign-file,extract-cert: use pkcs11 provider for OPENSSL MAJOR >= 3 Signed-off-by: Jan Stancek <jstancek(a)redhat.com> Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn> --- MAINTAINERS | 1 + certs/Makefile | 2 +- certs/extract-cert.c | 138 +++++++++++++++++++++++-------------------- scripts/sign-file.c | 134 +++++++++++++++++++++-------------------- scripts/ssl-common.h | 32 ++++++++++ 5 files changed, 178 insertions(+), 129 deletions(-) create mode 100644 scripts/ssl-common.h --- 2.27.0

2 months, 1 week

5
16
0 0

FAILED: patch "[PATCH] block: fix ordering between checking QUEUE_FLAG_QUIESCED" 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 6bda857bcbb86fb9d0e54fbef93a093d51172acc # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120342-monsoon-wildcat-d0a1@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 6bda857bcbb86fb9d0e54fbef93a093d51172acc Mon Sep 17 00:00:00 2001 From: Muchun Song <muchun.song(a)linux.dev> Date: Mon, 14 Oct 2024 17:29:33 +0800 Subject: [PATCH] block: fix ordering between checking QUEUE_FLAG_QUIESCED request adding 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> Link: https://lore.kernel.org/r/20241014092934.53630-3-songmuchun@bytedance.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/block/blk-mq.c b/block/blk-mq.c index 5deb9dffca0a..bb4ee2380dce 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2227,6 +2227,24 @@ 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. @@ -2247,20 +2265,23 @@ 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 months, 1 week

4
6
0 0

FAILED: patch "[PATCH] block: fix missing dispatching request when queue is started" 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 2003ee8a9aa14d766b06088156978d53c2e9be3d # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024120323-snowiness-subway-3844@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2003ee8a9aa14d766b06088156978d53c2e9be3d Mon Sep 17 00:00:00 2001 From: Muchun Song <muchun.song(a)linux.dev> Date: Mon, 14 Oct 2024 17:29:32 +0800 Subject: [PATCH] block: fix missing dispatching request when queue is started or unquiesced 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> Link: https://lore.kernel.org/r/20241014092934.53630-2-songmuchun@bytedance.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/block/blk-mq.c b/block/blk-mq.c index 7d05a56e3639..5deb9dffca0a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2647,6 +2647,7 @@ 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; } @@ -2677,6 +2678,7 @@ 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 months, 1 week

4
6
0 0

[PATCH 1/1] virtio_console: fix missing byte order handling for cols and rows

by Halil Pasic

As per virtio spec the fields cols and rows are specified as little endian. Although there is no legacy interface requirement that would state that cols and rows need to be handled as native endian when legacy interface is used, unlike for the fields of the adjacent struct virtio_console_control, I decided to err on the side of caution based on some non-conclusive virtio spec repo archaeology and opt for using virtio16_to_cpu() much like for virtio_console_control.event. Strictly by the letter of the spec virtio_le_to_cpu() would have been sufficient. But when the legacy interface is not used, it boils down to the same. And when using the legacy interface, the device formatting these as little endian when the guest is big endian would surprise me more than it using guest native byte order (which would make it compatible with the current implementation). Nevertheless somebody trying to implement the spec following it to the letter could end up forcing little endian byte order when the legacy interface is in use. So IMHO this ultimately needs a judgement call by the maintainers. Fixes: 8345adbf96fc1 ("virtio: console: Accept console size along with resize control message") Signed-off-by: Halil Pasic <pasic(a)linux.ibm.com> Cc: stable(a)vger.kernel.org # v2.6.35+ --- @Michael: I think it would be nice to add a clarification on the byte order to be used for cols and rows when the legacy interface is used to the spec, regardless of what we decide the right byte order is. If it is native endian that shall be stated much like it is stated for virtio_console_control. If it is little endian, I would like to add a sentence that states that unlike for the fields of virtio_console_control the byte order of the fields of struct virtio_console_resize is little endian also when the legacy interface is used. @Maximilian: Would you mind giving this a spin with your implementation on the device side of things in QEMU? --- drivers/char/virtio_console.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 18f92dd44d45..fc698e2b1da1 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1579,8 +1579,8 @@ static void handle_control_message(struct virtio_device *vdev, break; case VIRTIO_CONSOLE_RESIZE: { struct { - __u16 rows; - __u16 cols; + __virtio16 rows; + __virtio16 cols; } size; if (!is_console_port(port)) @@ -1588,7 +1588,8 @@ static void handle_control_message(struct virtio_device *vdev, memcpy(&size, buf->buf + buf->offset + sizeof(*cpkt), sizeof(size)); - set_console_size(port, size.rows, size.cols); + set_console_size(port, virtio16_to_cpu(vdev, size.rows), + virtio16_to_cpu(vdev, size.cols)); port->cons.hvc->irq_requested = 1; resize_console(port); base-commit: b3ee1e4609512dfff642a96b34d7e5dfcdc92d05 -- 2.45.2

2 months, 1 week

4
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror March 2025