From 0c60eb0cc320fffbb8b10329d276af14f6f5e6bf Mon Sep 17 00:00:00 2001 From: Kyoungrul Kim Date: Wed, 10 Jul 2024 08:25:20 +0900 Subject: scsi: ufs: core: Check LSDBS cap when !mcq If the user sets use_mcq_mode to 0, the host will try to activate the LSDB mode unconditionally even when the LSDBS of device HCI cap is 1. This makes commands time out and causes device probing to fail. To prevent that problem, check the LSDBS cap when MCQ is not supported. Signed-off-by: Kyoungrul Kim Link: https://lore.kernel.org/r/20240709232520epcms2p8ebdb5c4fccc30a6221390566589bf122@epcms2p8 Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/ufs/ufshcd.h | 1 + include/ufs/ufshci.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index a43b14276bc3..cac0cdb9a916 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1109,6 +1109,7 @@ struct ufs_hba { bool ext_iid_sup; bool scsi_host_added; bool mcq_sup; + bool lsdb_sup; bool mcq_enabled; struct ufshcd_res_info res[RES_MAX]; void __iomem *mcq_base; diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h index 38fe97971a65..9917c7743d80 100644 --- a/include/ufs/ufshci.h +++ b/include/ufs/ufshci.h @@ -77,6 +77,7 @@ enum { MASK_OUT_OF_ORDER_DATA_DELIVERY_SUPPORT = 0x02000000, MASK_UIC_DME_TEST_MODE_SUPPORT = 0x04000000, MASK_CRYPTO_SUPPORT = 0x10000000, + MASK_LSDB_SUPPORT = 0x20000000, MASK_MCQ_SUPPORT = 0x40000000, }; -- cgit v1.2.3 From af22bbe1f4a514c80b89a27252beef033168f4e9 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 16 Jul 2024 13:35:48 +0200 Subject: virtio: create admin queues alongside other virtqueues Admin virtqueue is just another virtqueue nothing that special about it. The current implementation treats it somehow separate though in terms of creation and deletion. Unify the admin virtqueue creation and deletion flows to be aligned with the rest of virtqueues, creating it from vp_find_vqs_*() helpers. Let the admin virtqueue to be deleted by vp_del_vqs() as the rest. Call vp_find_one_vq_msix() with slow_path argument being "true" to make sure that in case of limited interrupt vectors the config vector is used for admin queue. Signed-off-by: Jiri Pirko Message-Id: <20240716113552.80599-10-jiri@resnulli.us> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio.c | 28 ++--------------- drivers/virtio/virtio_pci_common.c | 43 ++++++++++++++++++++++++-- drivers/virtio/virtio_pci_common.h | 4 +-- drivers/virtio/virtio_pci_modern.c | 63 ++------------------------------------ include/linux/virtio_config.h | 4 --- 5 files changed, 46 insertions(+), 96 deletions(-) (limited to 'include') diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 396d3cd49a1b..835cfbcb59c8 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -305,15 +305,9 @@ static int virtio_dev_probe(struct device *_d) if (err) goto err; - if (dev->config->create_avq) { - err = dev->config->create_avq(dev); - if (err) - goto err; - } - err = drv->probe(dev); if (err) - goto err_probe; + goto err; /* If probe didn't do it, mark device DRIVER_OK ourselves. */ if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) @@ -326,9 +320,6 @@ static int virtio_dev_probe(struct device *_d) return 0; -err_probe: - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return err; @@ -344,9 +335,6 @@ static void virtio_dev_remove(struct device *_d) drv->remove(dev); - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); - /* Driver should have reset device. */ WARN_ON_ONCE(dev->config->get_status(dev)); @@ -524,9 +512,6 @@ int virtio_device_freeze(struct virtio_device *dev) } } - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); - return 0; } EXPORT_SYMBOL_GPL(virtio_device_freeze); @@ -562,16 +547,10 @@ int virtio_device_restore(struct virtio_device *dev) if (ret) goto err; - if (dev->config->create_avq) { - ret = dev->config->create_avq(dev); - if (ret) - goto err; - } - if (drv->restore) { ret = drv->restore(dev); if (ret) - goto err_restore; + goto err; } /* If restore didn't do it, mark device DRIVER_OK ourselves. */ @@ -582,9 +561,6 @@ int virtio_device_restore(struct virtio_device *dev) return 0; -err_restore: - if (dev->config->destroy_avq) - dev->config->destroy_avq(dev); err: virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED); return ret; diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 7c5516ae1f8a..267643bb1cd5 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -262,9 +262,6 @@ void vp_del_vqs(struct virtio_device *vdev) int i; list_for_each_entry_safe(vq, n, &vdev->vqs, list) { - if (vp_dev->is_avq && vp_dev->is_avq(vdev, vq->index)) - continue; - if (vp_dev->per_vq_vectors) { int v = vp_dev->vqs[vq->index]->msix_vector; @@ -371,14 +368,23 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, struct irq_affinity *desc) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; struct virtqueue_info *vqi; int i, err, nvectors, allocated_vectors, queue_idx = 0; + struct virtqueue *vq; bool per_vq_vectors; + u16 avq_num = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; + if (vp_dev->avq_index) { + err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num); + if (err) + goto error_find; + } + per_vq_vectors = vector_policy != VP_VQ_VECTOR_POLICY_SHARED; if (per_vq_vectors) { @@ -415,6 +421,18 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, goto error_find; } } + + if (!avq_num) + return 0; + sprintf(avq->name, "avq.%u", avq->vq_index); + vq = vp_find_one_vq_msix(vdev, avq->vq_index, NULL, avq->name, false, + true, &allocated_vectors, vector_policy, + &vp_dev->admin_vq.info); + if (IS_ERR(vq)) { + err = PTR_ERR(vq); + goto error_find; + } + return 0; error_find: @@ -427,12 +445,21 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue_info vqs_info[]) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; int i, err, queue_idx = 0; + struct virtqueue *vq; + u16 avq_num = 0; vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL); if (!vp_dev->vqs) return -ENOMEM; + if (vp_dev->avq_index) { + err = vp_dev->avq_index(vdev, &avq->vq_index, &avq_num); + if (err) + goto out_del_vqs; + } + err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED, dev_name(&vdev->dev), vp_dev); if (err) @@ -456,6 +483,16 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, } } + if (!avq_num) + return 0; + sprintf(avq->name, "avq.%u", avq->vq_index); + vq = vp_setup_vq(vdev, queue_idx++, NULL, avq->name, false, + VIRTIO_MSI_NO_VECTOR, &vp_dev->admin_vq.info); + if (IS_ERR(vq)) { + err = PTR_ERR(vq); + goto out_del_vqs; + } + return 0; out_del_vqs: vp_del_vqs(vdev); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index aa43875b6353..de59bb06ec3c 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -44,7 +44,7 @@ struct virtio_pci_vq_info { struct virtio_pci_admin_vq { /* Virtqueue info associated with this admin queue. */ - struct virtio_pci_vq_info info; + struct virtio_pci_vq_info *info; /* serializing admin commands execution. */ struct mutex cmd_lock; u64 supported_cmds; @@ -105,7 +105,7 @@ struct virtio_pci_device { void (*del_vq)(struct virtio_pci_vq_info *info); u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector); - bool (*is_avq)(struct virtio_device *vdev, unsigned int index); + int (*avq_index)(struct virtio_device *vdev, u16 *index, u16 *num); }; /* Constants for MSI-X */ diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index d704947b1aec..5ceb4b2c18df 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -63,7 +63,7 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, struct virtqueue *vq; int ret, len; - vq = admin_vq->info.vq; + vq = admin_vq->info->vq; if (!vq) return -EIO; @@ -203,27 +203,12 @@ end: static void vp_modern_avq_activate(struct virtio_device *vdev) { - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; - if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) return; - __virtqueue_unbreak(admin_vq->info.vq); virtio_pci_admin_cmd_list_init(vdev); } -static void vp_modern_avq_deactivate(struct virtio_device *vdev) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; - - if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) - return; - - __virtqueue_break(admin_vq->info.vq); -} - static void vp_transport_features(struct virtio_device *vdev, u64 features) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -418,8 +403,6 @@ static void vp_reset(struct virtio_device *vdev) while (vp_modern_get_status(mdev)) msleep(1); - vp_modern_avq_deactivate(vdev); - /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } @@ -595,9 +578,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, goto err; } - if (is_avq) - vp_dev->admin_vq.info.vq = vq; - return vq; err: @@ -741,41 +721,6 @@ static bool vp_get_shm_region(struct virtio_device *vdev, return true; } -static int vp_modern_create_avq(struct virtio_device *vdev) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - struct virtio_pci_admin_vq *avq = &vp_dev->admin_vq; - struct virtqueue *vq; - u16 num; - int err; - - err = vp_avq_index(vdev, &avq->vq_index, &num); - if (err || !num) - return err; - - sprintf(avq->name, "avq.%u", avq->vq_index); - vq = vp_dev->setup_vq(vp_dev, &vp_dev->admin_vq.info, avq->vq_index, NULL, - avq->name, NULL, VIRTIO_MSI_NO_VECTOR); - if (IS_ERR(vq)) { - dev_err(&vdev->dev, "failed to setup admin virtqueue, err=%ld", - PTR_ERR(vq)); - return PTR_ERR(vq); - } - - vp_modern_set_queue_enable(&vp_dev->mdev, avq->info.vq->index, true); - return 0; -} - -static void vp_modern_destroy_avq(struct virtio_device *vdev) -{ - struct virtio_pci_device *vp_dev = to_vp_device(vdev); - - if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) - return; - - vp_dev->del_vq(&vp_dev->admin_vq.info); -} - static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get = NULL, .set = NULL, @@ -794,8 +739,6 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, - .create_avq = vp_modern_create_avq, - .destroy_avq = vp_modern_destroy_avq, }; static const struct virtio_config_ops virtio_pci_config_ops = { @@ -816,8 +759,6 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, - .create_avq = vp_modern_create_avq, - .destroy_avq = vp_modern_destroy_avq, }; /* the PCI probing function */ @@ -841,7 +782,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) vp_dev->config_vector = vp_config_vector; vp_dev->setup_vq = setup_vq; vp_dev->del_vq = del_vq; - vp_dev->is_avq = vp_is_avq; + vp_dev->avq_index = vp_avq_index; vp_dev->isr = mdev->isr; vp_dev->vdev.id = mdev->id; diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index ab4b9a3fef6b..169c7d367fac 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -104,8 +104,6 @@ struct virtqueue_info { * Returns 0 on success or error status * If disable_vq_and_reset is set, then enable_vq_after_reset must also be * set. - * @create_avq: create admin virtqueue resource. - * @destroy_avq: destroy admin virtqueue resource. */ struct virtio_config_ops { void (*get)(struct virtio_device *vdev, unsigned offset, @@ -133,8 +131,6 @@ struct virtio_config_ops { struct virtio_shm_region *region, u8 id); int (*disable_vq_and_reset)(struct virtqueue *vq); int (*enable_vq_after_reset)(struct virtqueue *vq); - int (*create_avq)(struct virtio_device *vdev); - void (*destroy_avq)(struct virtio_device *vdev); }; /* If driver didn't advertise the feature, it will never appear. */ -- cgit v1.2.3 From 4c3b54af907e709609d3d8beca92d65e2f0cfd83 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 16 Jul 2024 13:35:51 +0200 Subject: virtio_pci_modern: use completion instead of busy loop to wait on admin cmd result Currently, the code waits in a busy loop on every admin virtqueue issued command to get a reply. That prevents callers from issuing multiple commands in parallel. To overcome this limitation, introduce a virtqueue event callback for admin virtqueue. For every issued command, use completion mechanism to wait on a reply. In the event callback, trigger the completion is done for every incoming reply. Alongside with that, introduce a spin lock to protect the admin virtqueue operations. Signed-off-by: Jiri Pirko Message-Id: <20240716113552.80599-13-jiri@resnulli.us> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_pci_common.c | 13 ++++--- drivers/virtio/virtio_pci_common.h | 3 ++ drivers/virtio/virtio_pci_modern.c | 74 ++++++++++++++++++++++++++++++++------ include/linux/virtio.h | 3 ++ 4 files changed, 77 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 267643bb1cd5..c44d8ba00c02 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -395,6 +395,8 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, if (vqi->name && vqi->callback) ++nvectors; } + if (avq_num && vector_policy == VP_VQ_VECTOR_POLICY_EACH) + ++nvectors; } else { /* Second best: one for change, shared for all vqs. */ nvectors = 2; @@ -425,9 +427,9 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned int nvqs, if (!avq_num) return 0; sprintf(avq->name, "avq.%u", avq->vq_index); - vq = vp_find_one_vq_msix(vdev, avq->vq_index, NULL, avq->name, false, - true, &allocated_vectors, vector_policy, - &vp_dev->admin_vq.info); + vq = vp_find_one_vq_msix(vdev, avq->vq_index, vp_modern_avq_done, + avq->name, false, true, &allocated_vectors, + vector_policy, &vp_dev->admin_vq.info); if (IS_ERR(vq)) { err = PTR_ERR(vq); goto error_find; @@ -486,8 +488,9 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned int nvqs, if (!avq_num) return 0; sprintf(avq->name, "avq.%u", avq->vq_index); - vq = vp_setup_vq(vdev, queue_idx++, NULL, avq->name, false, - VIRTIO_MSI_NO_VECTOR, &vp_dev->admin_vq.info); + vq = vp_setup_vq(vdev, queue_idx++, vp_modern_avq_done, avq->name, + false, VIRTIO_MSI_NO_VECTOR, + &vp_dev->admin_vq.info); if (IS_ERR(vq)) { err = PTR_ERR(vq); goto out_del_vqs; diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index de59bb06ec3c..90df381fbbcf 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -47,6 +47,8 @@ struct virtio_pci_admin_vq { struct virtio_pci_vq_info *info; /* serializing admin commands execution. */ struct mutex cmd_lock; + /* Protects virtqueue access. */ + spinlock_t lock; u64 supported_cmds; /* Name of the admin queue: avq.$vq_index. */ char name[10]; @@ -178,6 +180,7 @@ struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev); #define VIRTIO_ADMIN_CMD_BITMAP 0 #endif +void vp_modern_avq_done(struct virtqueue *vq); int vp_modern_admin_cmd_exec(struct virtio_device *vdev, struct virtio_admin_cmd *cmd); diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 0fd344d1eaf9..608df3263df1 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -53,6 +53,23 @@ static bool vp_is_avq(struct virtio_device *vdev, unsigned int index) return index == vp_dev->admin_vq.vq_index; } +void vp_modern_avq_done(struct virtqueue *vq) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); + struct virtio_pci_admin_vq *admin_vq = &vp_dev->admin_vq; + struct virtio_admin_cmd *cmd; + unsigned long flags; + unsigned int len; + + spin_lock_irqsave(&admin_vq->lock, flags); + do { + virtqueue_disable_cb(vq); + while ((cmd = virtqueue_get_buf(vq, &len))) + complete(&cmd->completion); + } while (!virtqueue_enable_cb(vq)); + spin_unlock_irqrestore(&admin_vq->lock, flags); +} + static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, u16 opcode, struct scatterlist **sgs, @@ -61,7 +78,8 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, struct virtio_admin_cmd *cmd) { struct virtqueue *vq; - int ret, len; + unsigned long flags; + int ret; vq = admin_vq->info->vq; if (!vq) @@ -72,21 +90,33 @@ static int virtqueue_exec_admin_cmd(struct virtio_pci_admin_vq *admin_vq, !((1ULL << opcode) & admin_vq->supported_cmds)) return -EOPNOTSUPP; - ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_KERNEL); - if (ret < 0) - return -EIO; + init_completion(&cmd->completion); - if (unlikely(!virtqueue_kick(vq))) +again: + if (virtqueue_is_broken(vq)) return -EIO; - while (!virtqueue_get_buf(vq, &len) && - !virtqueue_is_broken(vq)) - cpu_relax(); + spin_lock_irqsave(&admin_vq->lock, flags); + ret = virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_KERNEL); + if (ret < 0) { + if (ret == -ENOSPC) { + spin_unlock_irqrestore(&admin_vq->lock, flags); + cpu_relax(); + goto again; + } + goto unlock_err; + } + if (!virtqueue_kick(vq)) + goto unlock_err; + spin_unlock_irqrestore(&admin_vq->lock, flags); - if (virtqueue_is_broken(vq)) - return -EIO; + wait_for_completion(&cmd->completion); - return 0; + return cmd->ret; + +unlock_err: + spin_unlock_irqrestore(&admin_vq->lock, flags); + return -EIO; } int vp_modern_admin_cmd_exec(struct virtio_device *vdev, @@ -209,6 +239,25 @@ static void vp_modern_avq_activate(struct virtio_device *vdev) virtio_pci_admin_cmd_list_init(vdev); } +static void vp_modern_avq_cleanup(struct virtio_device *vdev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(vdev); + struct virtio_admin_cmd *cmd; + struct virtqueue *vq; + + if (!virtio_has_feature(vdev, VIRTIO_F_ADMIN_VQ)) + return; + + vq = vp_dev->vqs[vp_dev->admin_vq.vq_index]->vq; + if (!vq) + return; + + while ((cmd = virtqueue_detach_unused_buf(vq))) { + cmd->ret = -EIO; + complete(&cmd->completion); + } +} + static void vp_transport_features(struct virtio_device *vdev, u64 features) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); @@ -403,6 +452,8 @@ static void vp_reset(struct virtio_device *vdev) while (vp_modern_get_status(mdev)) msleep(1); + vp_modern_avq_cleanup(vdev); + /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } @@ -785,6 +836,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) vp_dev->isr = mdev->isr; vp_dev->vdev.id = mdev->id; + spin_lock_init(&vp_dev->admin_vq.lock); mutex_init(&vp_dev->admin_vq.cmd_lock); return 0; } diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 96fea920873b..999ff5934392 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -10,6 +10,7 @@ #include #include #include +#include /** * struct virtqueue - a queue to register buffers for sending or receiving. @@ -109,6 +110,8 @@ struct virtio_admin_cmd { __le64 group_member_id; struct scatterlist *data_sg; struct scatterlist *result_sg; + struct completion completion; + int ret; }; /** -- cgit v1.2.3 From 564429a6bd8d26065b2cccffcaa9485359f74de7 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:47 -0400 Subject: KVM: rename CONFIG_HAVE_KVM_GMEM_* to CONFIG_HAVE_KVM_ARCH_GMEM_* Add "ARCH" to the symbols; shortly, the "prepare" phase will include both the arch-independent step to clear out contents left in the page by the host, and the arch-dependent step enabled by CONFIG_HAVE_KVM_GMEM_PREPARE. For consistency do the same for CONFIG_HAVE_KVM_GMEM_INVALIDATE as well. Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- arch/x86/kvm/Kconfig | 4 ++-- arch/x86/kvm/x86.c | 4 ++-- include/linux/kvm_host.h | 4 ++-- virt/kvm/Kconfig | 4 ++-- virt/kvm/guest_memfd.c | 6 +++--- 5 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 4287a8071a3a..472a1537b7a9 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -141,8 +141,8 @@ config KVM_AMD_SEV depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) select ARCH_HAS_CC_PLATFORM select KVM_GENERIC_PRIVATE_MEM - select HAVE_KVM_GMEM_PREPARE - select HAVE_KVM_GMEM_INVALIDATE + select HAVE_KVM_ARCH_GMEM_PREPARE + select HAVE_KVM_ARCH_GMEM_INVALIDATE help Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 52778689cef4..4db18924b2f2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13644,7 +13644,7 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_arch_no_poll); -#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE bool kvm_arch_gmem_prepare_needed(struct kvm *kvm) { return kvm->arch.vm_type == KVM_X86_SNP_VM; @@ -13656,7 +13656,7 @@ int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_ord } #endif -#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end) { kvm_x86_call(gmem_invalidate)(start, end); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 689e8be873a7..344d90771844 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2445,7 +2445,7 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm, } #endif /* CONFIG_KVM_PRIVATE_MEM */ -#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); bool kvm_arch_gmem_prepare_needed(struct kvm *kvm); #endif @@ -2477,7 +2477,7 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque); -#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); #endif diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index b14e14cdbfb9..fd6a3010afa8 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -113,10 +113,10 @@ config KVM_GENERIC_PRIVATE_MEM select KVM_PRIVATE_MEM bool -config HAVE_KVM_GMEM_PREPARE +config HAVE_KVM_ARCH_GMEM_PREPARE bool depends on KVM_PRIVATE_MEM -config HAVE_KVM_GMEM_INVALIDATE +config HAVE_KVM_ARCH_GMEM_INVALIDATE bool depends on KVM_PRIVATE_MEM diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 5221b584288f..76139332f2f3 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -27,7 +27,7 @@ static inline kvm_pfn_t folio_file_pfn(struct folio *folio, pgoff_t index) static int kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct folio *folio) { -#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE struct list_head *gmem_list = &inode->i_mapping->i_private_list; struct kvm_gmem *gmem; @@ -353,7 +353,7 @@ static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *fol return MF_DELAYED; } -#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE static void kvm_gmem_free_folio(struct folio *folio) { struct page *page = folio_page(folio, 0); @@ -368,7 +368,7 @@ static const struct address_space_operations kvm_gmem_aops = { .dirty_folio = noop_dirty_folio, .migrate_folio = kvm_gmem_migrate_folio, .error_remove_folio = kvm_gmem_error_folio, -#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE .free_folio = kvm_gmem_free_folio, #endif }; -- cgit v1.2.3 From 7239ed74677af143857d1a96d402476446a0995a Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:51 -0400 Subject: KVM: remove kvm_arch_gmem_prepare_needed() It is enough to return 0 if a guest need not do any preparation. This is in fact how sev_gmem_prepare() works for non-SNP guests, and it extends naturally to Intel hosts: the x86 callback for gmem_prepare is optional and returns 0 if not defined. Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 5 ----- include/linux/kvm_host.h | 1 - virt/kvm/guest_memfd.c | 13 +++---------- 3 files changed, 3 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4db18924b2f2..ef3d3511e4af 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13645,11 +13645,6 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvm_arch_no_poll); #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE -bool kvm_arch_gmem_prepare_needed(struct kvm *kvm) -{ - return kvm->arch.vm_type == KVM_X86_SNP_VM; -} - int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order) { return kvm_x86_call(gmem_prepare)(kvm, pfn, gfn, max_order); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 344d90771844..45373d42f314 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2447,7 +2447,6 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm, #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); -bool kvm_arch_gmem_prepare_needed(struct kvm *kvm); #endif /** diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 444ded162154..191fd42067c0 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -29,16 +29,9 @@ static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slo pgoff_t index, struct folio *folio) { #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE - kvm_pfn_t pfn; - gfn_t gfn; - int rc; - - if (!kvm_arch_gmem_prepare_needed(kvm)) - return 0; - - pfn = folio_file_pfn(folio, index); - gfn = slot->base_gfn + index - slot->gmem.pgoff; - rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio)); + kvm_pfn_t pfn = folio_file_pfn(folio, index); + gfn_t gfn = slot->base_gfn + index - slot->gmem.pgoff; + int rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio)); if (rc) { pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx GFN %llx PFN %llx error %d.\n", index, gfn, pfn, rc); -- cgit v1.2.3 From 4b5f67120a88c713b82907d55a767693382e9e9d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:54 -0400 Subject: KVM: extend kvm_range_has_memory_attributes() to check subset of attributes While currently there is no other attribute than KVM_MEMORY_ATTRIBUTE_PRIVATE, KVM code such as kvm_mem_is_private() is written to expect their existence. Allow using kvm_range_has_memory_attributes() as a multi-page version of kvm_mem_is_private(), without it breaking later when more attributes are introduced. Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 2 +- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 13 +++++++------ 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 26ef5b6ac3c1..43a02891babb 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -7513,7 +7513,7 @@ static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); if (level == PG_LEVEL_2M) - return kvm_range_has_memory_attributes(kvm, start, end, attrs); + return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs); for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { if (hugepage_test_mixed(slot, gfn, level - 1) || diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 45373d42f314..c223b97df03e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2414,7 +2414,7 @@ static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn } bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long attrs); + unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 30328ff2d840..92901656a0d4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2408,21 +2408,21 @@ static u64 kvm_supported_mem_attributes(struct kvm *kvm) /* * Returns true if _all_ gfns in the range [@start, @end) have attributes - * matching @attrs. + * such that the bits in @mask match @attrs. */ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long attrs) + unsigned long mask, unsigned long attrs) { XA_STATE(xas, &kvm->mem_attr_array, start); - unsigned long mask = kvm_supported_mem_attributes(kvm); unsigned long index; void *entry; + mask &= kvm_supported_mem_attributes(kvm); if (attrs & ~mask) return false; if (end == start + 1) - return kvm_get_memory_attributes(kvm, start) == attrs; + return (kvm_get_memory_attributes(kvm, start) & mask) == attrs; guard(rcu)(); if (!attrs) @@ -2433,7 +2433,8 @@ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, entry = xas_next(&xas); } while (xas_retry(&xas, entry)); - if (xas.xa_index != index || xa_to_value(entry) != attrs) + if (xas.xa_index != index || + (xa_to_value(entry) & mask) != attrs) return false; } @@ -2532,7 +2533,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, mutex_lock(&kvm->slots_lock); /* Nothing to do if the entire range as the desired attributes. */ - if (kvm_range_has_memory_attributes(kvm, start, end, attributes)) + if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes)) goto out_unlock; /* -- cgit v1.2.3 From e4ee5447927377c55777b73fe497a2455a25f948 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Jul 2024 18:27:55 -0400 Subject: KVM: guest_memfd: let kvm_gmem_populate() operate only on private gfns This check is currently performed by sev_gmem_post_populate(), but it applies to all callers of kvm_gmem_populate(): the point of the function is that the memory is being encrypted and some work has to be done on all the gfns in order to encrypt them. Therefore, check the KVM_MEMORY_ATTRIBUTE_PRIVATE attribute prior to invoking the callback, and stop the operation if a shared page is encountered. Because CONFIG_KVM_PRIVATE_MEM in principle does not require attributes, this makes kvm_gmem_populate() depend on CONFIG_KVM_GENERIC_PRIVATE_MEM (which does require them). Reviewed-by: Michael Roth Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 7 ------- include/linux/kvm_host.h | 2 ++ virt/kvm/guest_memfd.c | 12 ++++++++++++ 3 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 752d2fff0f10..532df12b43c5 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2279,13 +2279,6 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn_start, kvm_pfn_t pf bool assigned; int level; - if (!kvm_mem_is_private(kvm, gfn)) { - pr_debug("%s: Failed to ensure GFN 0x%llx has private memory attribute set\n", - __func__, gfn); - ret = -EINVAL; - goto err; - } - ret = snp_lookup_rmpentry((u64)pfn + i, &assigned, &level); if (ret || assigned) { pr_debug("%s: Failed to ensure GFN 0x%llx RMP entry is initial shared state, ret: %d assigned: %d\n", diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c223b97df03e..79a6b1a63027 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2449,6 +2449,7 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm, int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); #endif +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM /** * kvm_gmem_populate() - Populate/prepare a GPA range with guest data * @@ -2475,6 +2476,7 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque); +#endif #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 319ec491ca47..95e338a29910 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -612,6 +612,7 @@ out: } EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn); +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque) { @@ -665,11 +666,21 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long (npages - i) < (1 << max_order)) max_order = 0; + ret = -EINVAL; + while (!kvm_range_has_memory_attributes(kvm, gfn, gfn + (1 << max_order), + KVM_MEMORY_ATTRIBUTE_PRIVATE, + KVM_MEMORY_ATTRIBUTE_PRIVATE)) { + if (!max_order) + goto put_folio_and_exit; + max_order--; + } + p = src ? src + i * PAGE_SIZE : NULL; ret = post_populate(kvm, gfn, pfn, p, max_order, opaque); if (!ret) folio_mark_uptodate(folio); +put_folio_and_exit: folio_put(folio); if (ret) break; @@ -681,3 +692,4 @@ long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long return ret && !i ? ret : i; } EXPORT_SYMBOL_GPL(kvm_gmem_populate); +#endif -- cgit v1.2.3 From 1a251f52cfdc417c84411a056bc142cbd77baef4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Jul 2024 15:49:18 -0700 Subject: minmax: make generic MIN() and MAX() macros available everywhere This just standardizes the use of MIN() and MAX() macros, with the very traditional semantics. The goal is to use these for C constant expressions and for top-level / static initializers, and so be able to simplify the min()/max() macros. These macro names were used by various kernel code - they are very traditional, after all - and all such users have been fixed up, with a few different approaches: - trivial duplicated macro definitions have been removed Note that 'trivial' here means that it's obviously kernel code that already included all the major kernel headers, and thus gets the new generic MIN/MAX macros automatically. - non-trivial duplicated macro definitions are guarded with #ifndef This is the "yes, they define their own versions, but no, the include situation is not entirely obvious, and maybe they don't get the generic version automatically" case. - strange use case #1 A couple of drivers decided that the way they want to describe their versioning is with #define MAJ 1 #define MIN 2 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) which adds zero value and I just did my Alexander the Great impersonation, and rewrote that pointless Gordian knot as #define DRV_VERSION "1.2" instead. - strange use case #2 A couple of drivers thought that it's a good idea to have a random 'MIN' or 'MAX' define for a value or index into a table, rather than the traditional macro that takes arguments. These values were re-written as C enum's instead. The new function-line macros only expand when followed by an open parenthesis, and thus don't clash with enum use. Happily, there weren't really all that many of these cases, and a lot of users already had the pattern of using '#ifndef' guarding (or in one case just using '#undef MIN') before defining their own private version that does the same thing. I left such cases alone. Cc: David Laight Cc: Lorenzo Stoakes Signed-off-by: Linus Torvalds --- arch/um/drivers/mconsole_user.c | 2 ++ drivers/edac/skx_common.h | 1 - drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 2 ++ .../gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c | 2 ++ drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h | 14 +++++++++---- drivers/gpu/drm/radeon/evergreen_cs.c | 2 ++ drivers/hwmon/adt7475.c | 24 +++++++++++----------- drivers/media/dvb-frontends/stv0367_priv.h | 3 +++ drivers/net/fjes/fjes_main.c | 4 +--- drivers/nfc/pn544/i2c.c | 2 -- drivers/platform/x86/sony-laptop.c | 1 - drivers/scsi/isci/init.c | 6 +----- .../pci/hive_isp_css_include/math_support.h | 5 ----- include/linux/minmax.h | 2 ++ kernel/trace/preemptirq_delay_test.c | 2 -- lib/btree.c | 1 - lib/decompress_unlzma.c | 2 ++ mm/zsmalloc.c | 2 -- tools/testing/selftests/mm/mremap_test.c | 2 ++ tools/testing/selftests/seccomp/seccomp_bpf.c | 2 ++ 20 files changed, 43 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/arch/um/drivers/mconsole_user.c b/arch/um/drivers/mconsole_user.c index e24298a734be..a04cd13c6315 100644 --- a/arch/um/drivers/mconsole_user.c +++ b/arch/um/drivers/mconsole_user.c @@ -71,7 +71,9 @@ static struct mconsole_command *mconsole_parse(struct mc_request *req) return NULL; } +#ifndef MIN #define MIN(a,b) ((a)<(b) ? (a):(b)) +#endif #define STRINGX(x) #x #define STRING(x) STRINGX(x) diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index 11faf1db4fa4..473421ba7a18 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -45,7 +45,6 @@ #define I10NM_NUM_CHANNELS MAX(I10NM_NUM_DDR_CHANNELS, I10NM_NUM_HBM_CHANNELS) #define I10NM_NUM_DIMMS MAX(I10NM_NUM_DDR_DIMMS, I10NM_NUM_HBM_DIMMS) -#define MAX(a, b) ((a) > (b) ? (a) : (b)) #define NUM_IMC MAX(SKX_NUM_IMC, I10NM_NUM_IMC) #define NUM_CHANNELS MAX(SKX_NUM_CHANNELS, I10NM_NUM_CHANNELS) #define NUM_DIMMS MAX(SKX_NUM_DIMMS, I10NM_NUM_DIMMS) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index be2638c763d7..9a406d74c0dd 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -35,8 +35,10 @@ #include "dc_stream_priv.h" #define DC_LOGGER dc->ctx->logger +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) #define MAX(x, y) ((x > y) ? x : y) +#endif /******************************************************************************* * Private functions diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c index 7ecf76aea950..6e064e6ae949 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c @@ -25,7 +25,9 @@ #include "hdcp.h" +#ifndef MIN #define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif #define HDCP_I2C_ADDR 0x3a /* 0x74 >> 1*/ #define KSV_READ_SIZE 0xf /* 0x6803b - 0x6802c */ #define HDCP_MAX_AUX_TRANSACTION_SIZE 16 diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h index 6f54c410c2f9..409aeec6baa9 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppevvmath.h @@ -22,12 +22,18 @@ */ #include -#define SHIFT_AMOUNT 16 /* We multiply all original integers with 2^SHIFT_AMOUNT to get the fInt representation */ +enum ppevvmath_constants { + /* We multiply all original integers with 2^SHIFT_AMOUNT to get the fInt representation */ + SHIFT_AMOUNT = 16, -#define PRECISION 5 /* Change this value to change the number of decimal places in the final output - 5 is a good default */ + /* Change this value to change the number of decimal places in the final output - 5 is a good default */ + PRECISION = 5, -#define SHIFTED_2 (2 << SHIFT_AMOUNT) -#define MAX (1 << (SHIFT_AMOUNT - 1)) - 1 /* 32767 - Might change in the future */ + SHIFTED_2 = (2 << SHIFT_AMOUNT), + + /* 32767 - Might change in the future */ + MAX = (1 << (SHIFT_AMOUNT - 1)) - 1, +}; /* ------------------------------------------------------------------------------- * NEW TYPE - fINT diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 1fe6e0d883c7..e5577d2a19ef 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -33,8 +33,10 @@ #include "evergreen_reg_safe.h" #include "cayman_reg_safe.h" +#ifndef MIN #define MAX(a, b) (((a) > (b)) ? (a) : (b)) #define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif #define REG_SAFE_BM_SIZE ARRAY_SIZE(evergreen_reg_safe_bm) diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index bc186c61a2c0..382a2bb9168a 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -22,23 +22,23 @@ #include /* Indexes for the sysfs hooks */ - -#define INPUT 0 -#define MIN 1 -#define MAX 2 -#define CONTROL 3 -#define OFFSET 3 -#define AUTOMIN 4 -#define THERM 5 -#define HYSTERSIS 6 - +enum adt_sysfs_id { + INPUT = 0, + MIN = 1, + MAX = 2, + CONTROL = 3, + OFFSET = 3, // Dup + AUTOMIN = 4, + THERM = 5, + HYSTERSIS = 6, /* * These are unique identifiers for the sysfs functions - unlike the * numbers above, these are not also indexes into an array */ + ALARM = 9, + FAULT = 10, +}; -#define ALARM 9 -#define FAULT 10 /* 7475 Common Registers */ diff --git a/drivers/media/dvb-frontends/stv0367_priv.h b/drivers/media/dvb-frontends/stv0367_priv.h index 617f605947b2..7f056d1cce82 100644 --- a/drivers/media/dvb-frontends/stv0367_priv.h +++ b/drivers/media/dvb-frontends/stv0367_priv.h @@ -25,8 +25,11 @@ #endif /* MACRO definitions */ +#ifndef MIN #define MAX(X, Y) ((X) >= (Y) ? (X) : (Y)) #define MIN(X, Y) ((X) <= (Y) ? (X) : (Y)) +#endif + #define INRANGE(X, Y, Z) \ ((((X) <= (Y)) && ((Y) <= (Z))) || \ (((Z) <= (Y)) && ((Y) <= (X))) ? 1 : 0) diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index b3ddc9a629d9..fad5b6564464 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -14,9 +14,7 @@ #include "fjes.h" #include "fjes_trace.h" -#define MAJ 1 -#define MIN 2 -#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) +#define DRV_VERSION "1.2" #define DRV_NAME "fjes" char fjes_driver_name[] = DRV_NAME; char fjes_driver_version[] = DRV_VERSION; diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 9fe664960b38..e2a6575b9ff7 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -126,8 +126,6 @@ struct pn544_i2c_fw_secure_blob { #define PN544_FW_CMD_RESULT_COMMAND_REJECTED 0xE0 #define PN544_FW_CMD_RESULT_CHUNK_ERROR 0xE6 -#define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) - #define PN544_FW_WRITE_BUFFER_MAX_LEN 0x9f7 #define PN544_FW_I2C_MAX_PAYLOAD PN544_HCI_I2C_LLC_MAX_SIZE #define PN544_FW_I2C_WRITE_FRAME_HEADER_LEN 8 diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index 3e94fdd1ea52..3197aaa69da7 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -757,7 +757,6 @@ static union acpi_object *__call_snc_method(acpi_handle handle, char *method, return result; } -#define MIN(a, b) (a > b ? b : a) static int sony_nc_buffer_call(acpi_handle handle, char *name, u64 *value, void *buffer, size_t buflen) { diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c index d31884f82f2a..73085d2f5c43 100644 --- a/drivers/scsi/isci/init.c +++ b/drivers/scsi/isci/init.c @@ -65,11 +65,7 @@ #include "task.h" #include "probe_roms.h" -#define MAJ 1 -#define MIN 2 -#define BUILD 0 -#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ - __stringify(BUILD) +#define DRV_VERSION "1.2.0" MODULE_VERSION(DRV_VERSION); diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h b/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h index 7349943bba2b..160c496784b7 100644 --- a/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h +++ b/drivers/staging/media/atomisp/pci/hive_isp_css_include/math_support.h @@ -22,11 +22,6 @@ /* force a value to a lower even value */ #define EVEN_FLOOR(x) ((x) & ~1) -/* for preprocessor and array sizing use MIN and MAX - otherwise use min and max */ -#define MAX(a, b) (((a) > (b)) ? (a) : (b)) -#define MIN(a, b) (((a) < (b)) ? (a) : (b)) - #define CEIL_DIV(a, b) (((b) != 0) ? ((a) + (b) - 1) / (b) : 0) #define CEIL_MUL(a, b) (CEIL_DIV(a, b) * (b)) #define CEIL_MUL2(a, b) (((a) + (b) - 1) & ~((b) - 1)) diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 9c2848abc804..fc384714da45 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -277,6 +277,8 @@ static inline bool in_range32(u32 val, u32 start, u32 len) * Use these carefully: no type checking, and uses the arguments * multiple times. Use for obvious constants only. */ +#define MIN(a,b) __cmp(min,a,b) +#define MAX(a,b) __cmp(max,a,b) #define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b)) #define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b)) diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index cb0871fbdb07..314ffc143039 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -34,8 +34,6 @@ MODULE_PARM_DESC(cpu_affinity, "Cpu num test is running on"); static struct completion done; -#define MIN(x, y) ((x) < (y) ? (x) : (y)) - static void busy_wait(ulong time) { u64 start, end; diff --git a/lib/btree.c b/lib/btree.c index 49420cae3a83..bb81d3393ac5 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -43,7 +43,6 @@ #include #include -#define MAX(a, b) ((a) > (b) ? (a) : (b)) #define NODESIZE MAX(L1_CACHE_BYTES, 128) struct btree_geo { diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c index 20a858031f12..9d34d35908da 100644 --- a/lib/decompress_unlzma.c +++ b/lib/decompress_unlzma.c @@ -37,7 +37,9 @@ #include +#ifndef MIN #define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif static long long INIT read_int(unsigned char *ptr, int size) { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 5d6581ab7c07..2d3163e4da96 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -120,8 +120,6 @@ #define CLASS_BITS 8 #define MAGIC_VAL_BITS 8 -#define MAX(a, b) ((a) >= (b) ? (a) : (b)) - #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(CONFIG_ZSMALLOC_CHAIN_SIZE, UL)) /* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */ diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 1b03bcfaefdf..5a3a9bcba640 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -22,8 +22,10 @@ #define VALIDATION_DEFAULT_THRESHOLD 4 /* 4MB */ #define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) #define MAX(X, Y) ((X) > (Y) ? (X) : (Y)) +#endif #define SIZE_MB(m) ((size_t)m * (1024 * 1024)) #define SIZE_KB(k) ((size_t)k * 1024) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index e3f97f90d8db..8c3a73461475 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -60,7 +60,9 @@ #define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) #endif +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#endif #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 -- cgit v1.2.3 From dc1c8034e31b14a2e5e212104ec508aec44ce1b9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Jul 2024 20:24:12 -0700 Subject: minmax: simplify min()/max()/clamp() implementation Now that we no longer have any C constant expression contexts (ie array size declarations or static initializers) that use min() or max(), we can simpify the implementation by not having to worry about the result staying as a C constant expression. So now we can unconditionally just use temporary variables of the right type, and get rid of the excessive expansion that used to come from the use of __builtin_choose_expr(__is_constexpr(...), .. to pick the specialized code for constant expressions. Another expansion simplification is to pass the temporary variables (in addition to the original expression) to our __types_ok() macro. That may superficially look like it complicates the macro, but when we only want the type of the expression, expanding the temporary variable names is much simpler and smaller than expanding the potentially complicated original expression. As a result, on my machine, doing a $ time make drivers/staging/media/atomisp/pci/isp/kernels/ynr/ynr_1.0/ia_css_ynr.host.i goes from real 0m16.621s user 0m15.360s sys 0m1.221s to real 0m2.532s user 0m2.091s sys 0m0.452s because the token expansion goes down dramatically. In particular, the longest line expansion (which was line 71 of that 'ia_css_ynr.host.c' file) shrinks from 23,338kB (yes, 23MB for one single line) to "just" 1,444kB (now "only" 1.4MB). And yes, that line is still the line from hell, because it's doing multiple levels of "min()/max()" expansion thanks to some of them being hidden inside the uDIGIT_FITTING() macro. Lorenzo has a nice cleanup patch that makes that driver use inline functions instead of macros for sDIGIT_FITTING() and uDIGIT_FITTING(), which will fix that line once and for all, but the 16-fold reduction in this case does show why we need to simplify these helpers. Cc: David Laight Cc: Lorenzo Stoakes Signed-off-by: Linus Torvalds --- include/linux/minmax.h | 43 ++++++++++++++++++++----------------------- 1 file changed, 20 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/minmax.h b/include/linux/minmax.h index fc384714da45..e3e4353df983 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -35,10 +35,10 @@ #define __is_noneg_int(x) \ (__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0) -#define __types_ok(x, y) \ - (__is_signed(x) == __is_signed(y) || \ - __is_signed((x) + 0) == __is_signed((y) + 0) || \ - __is_noneg_int(x) || __is_noneg_int(y)) +#define __types_ok(x, y, ux, uy) \ + (__is_signed(ux) == __is_signed(uy) || \ + __is_signed((ux) + 0) == __is_signed((uy) + 0) || \ + __is_noneg_int(x) || __is_noneg_int(y)) #define __cmp_op_min < #define __cmp_op_max > @@ -51,34 +51,31 @@ #define __cmp_once(op, type, x, y) \ __cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) -#define __careful_cmp_once(op, x, y) ({ \ - static_assert(__types_ok(x, y), \ +#define __careful_cmp_once(op, x, y, ux, uy) ({ \ + __auto_type ux = (x); __auto_type uy = (y); \ + static_assert(__types_ok(x, y, ux, uy), \ #op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \ - __cmp_once(op, __auto_type, x, y); }) + __cmp(op, ux, uy); }) -#define __careful_cmp(op, x, y) \ - __builtin_choose_expr(__is_constexpr((x) - (y)), \ - __cmp(op, x, y), __careful_cmp_once(op, x, y)) +#define __careful_cmp(op, x, y) \ + __careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) #define __clamp(val, lo, hi) \ ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) -#define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({ \ - typeof(val) unique_val = (val); \ - typeof(lo) unique_lo = (lo); \ - typeof(hi) unique_hi = (hi); \ +#define __clamp_once(val, lo, hi, uval, ulo, uhi) ({ \ + __auto_type uval = (val); \ + __auto_type ulo = (lo); \ + __auto_type uhi = (hi); \ static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), \ (lo) <= (hi), true), \ "clamp() low limit " #lo " greater than high limit " #hi); \ - static_assert(__types_ok(val, lo), "clamp() 'lo' signedness error"); \ - static_assert(__types_ok(val, hi), "clamp() 'hi' signedness error"); \ - __clamp(unique_val, unique_lo, unique_hi); }) - -#define __careful_clamp(val, lo, hi) ({ \ - __builtin_choose_expr(__is_constexpr((val) - (lo) + (hi)), \ - __clamp(val, lo, hi), \ - __clamp_once(val, lo, hi, __UNIQUE_ID(__val), \ - __UNIQUE_ID(__lo), __UNIQUE_ID(__hi))); }) + static_assert(__types_ok(uval, lo, uval, ulo), "clamp() 'lo' signedness error"); \ + static_assert(__types_ok(uval, hi, uval, uhi), "clamp() 'hi' signedness error"); \ + __clamp(uval, ulo, uhi); }) + +#define __careful_clamp(val, lo, hi) \ + __clamp_once(val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_)) /** * min - return minimum of two values of the same or compatible types -- cgit v1.2.3 From 8cd44dd1d17a23d5cc8c443c659ca57aa76e2fa5 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Wed, 15 Feb 2023 09:18:02 +0900 Subject: btrfs: zoned: fix zone_unusable accounting on making block group read-write again When btrfs makes a block group read-only, it adds all free regions in the block group to space_info->bytes_readonly. That free space excludes reserved and pinned regions. OTOH, when btrfs makes the block group read-write again, it moves all the unused regions into the block group's zone_unusable. That unused region includes reserved and pinned regions. As a result, it counts too much zone_unusable bytes. Fortunately (or unfortunately), having erroneous zone_unusable does not affect the calculation of space_info->bytes_readonly, because free space (num_bytes in btrfs_dec_block_group_ro) calculation is done based on the erroneous zone_unusable and it reduces the num_bytes just to cancel the error. This behavior can be easily discovered by adding a WARN_ON to check e.g, "bg->pinned > 0" in btrfs_dec_block_group_ro(), and running fstests test case like btrfs/282. Fix it by properly considering pinned and reserved in btrfs_dec_block_group_ro(). Also, add a WARN_ON and introduce btrfs_space_info_update_bytes_zone_unusable() to catch a similar mistake. Fixes: 169e0da91a21 ("btrfs: zoned: track unusable bytes for zones") CC: stable@vger.kernel.org # 5.15+ Signed-off-by: Naohiro Aota Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 13 ++++++++----- fs/btrfs/extent-tree.c | 3 ++- fs/btrfs/free-space-cache.c | 4 +++- fs/btrfs/space-info.c | 2 +- fs/btrfs/space-info.h | 1 + include/trace/events/btrfs.h | 8 ++++++++ 6 files changed, 23 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 498442d0c216..2e49d978f504 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1223,8 +1223,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, block_group->space_info->total_bytes -= block_group->length; block_group->space_info->bytes_readonly -= (block_group->length - block_group->zone_unusable); - block_group->space_info->bytes_zone_unusable -= - block_group->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info, + -block_group->zone_unusable); block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); @@ -1396,7 +1396,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes to readonly */ sinfo->bytes_readonly += cache->zone_unusable; - sinfo->bytes_zone_unusable -= cache->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, + -cache->zone_unusable); cache->zone_unusable = 0; } cache->ro++; @@ -3056,9 +3057,11 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes back */ cache->zone_unusable = - (cache->alloc_offset - cache->used) + + (cache->alloc_offset - cache->used - cache->pinned - + cache->reserved) + (cache->length - cache->zone_capacity); - sinfo->bytes_zone_unusable += cache->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, + cache->zone_unusable); sinfo->bytes_readonly -= cache->zone_unusable; } num_bytes = cache->length - cache->reserved - diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d77498e7671c..ff9f0d41987e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2793,7 +2793,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, readonly = true; } else if (btrfs_is_zoned(fs_info)) { /* Need reset before reusing in a zoned block group */ - space_info->bytes_zone_unusable += len; + btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info, + len); readonly = true; } spin_unlock(&cache->lock); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 3f9b7507543a..f5996a43db24 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2723,8 +2723,10 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, * If the block group is read-only, we should account freed space into * bytes_readonly. */ - if (!block_group->ro) + if (!block_group->ro) { block_group->zone_unusable += to_unusable; + WARN_ON(block_group->zone_unusable > block_group->length); + } spin_unlock(&ctl->tree_lock); if (!used) { spin_lock(&block_group->lock); diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index c1d9d3664400..68e14fd48638 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -316,7 +316,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, found->bytes_used += block_group->used; found->disk_used += block_group->used * factor; found->bytes_readonly += block_group->bytes_super; - found->bytes_zone_unusable += block_group->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable); if (block_group->length > 0) found->full = 0; btrfs_try_granting_tickets(info, found); diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 4db8a0267c16..88b44221ce97 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -249,6 +249,7 @@ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \ DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info"); DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); +DECLARE_SPACE_INFO_UPDATE(bytes_zone_unusable, "zone_unusable"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index eeb56975bee7..de55a555d95b 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -2383,6 +2383,14 @@ DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned, TP_ARGS(fs_info, sinfo, old, diff) ); +DEFINE_EVENT(btrfs__space_info_update, update_bytes_zone_unusable, + + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo, u64 old, s64 diff), + + TP_ARGS(fs_info, sinfo, old, diff) +); + DECLARE_EVENT_CLASS(btrfs_raid56_bio, TP_PROTO(const struct btrfs_raid_bio *rbio, -- cgit v1.2.3 From 2accfdb7eff65f390c4308b0e9cb7c3fe48ad63c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 29 Jul 2024 10:58:28 -0700 Subject: profiling: attempt to remove per-cpu profile flip buffer This is the really old legacy kernel profiling code, which has long since been obviated by "real profiling" (ie 'prof' and company), and mainly remains as a source of syzbot reports. There are anecdotal reports that people still use it for boot-time profiling, but it's unlikely that such use would care about the old NUMA optimizations in this code from 2004 (commit ad02973d42: "profile: 512x Altix timer interrupt livelock fix" in the BK import archive at [1]) So in order to head off future syzbot reports, let's try to simplify this code and get rid of the per-cpu profile buffers that are quite a large portion of the complexity footprint of this thing (including CPU hotplug callbacks etc). It's unlikely anybody will actually notice, or possibly, as Thomas put it: "Only people who indulge in nostalgia will notice :)". That said, if it turns out that this code is actually actively used by somebody, we can always revert this removal. Thus the "attempt" in the summary line. [ Note: in a small nod to "the profiling code can cause NUMA problems", this also removes the "increment the last entry in the profiling array on any unknown hits" logic. That would account any program counter in a module to that single counter location, and might exacerbate any NUMA cacheline bouncing issues ] Link: https://lore.kernel.org/all/CAHk-=wgs52BxT4Zjmjz8aNvHWKxf5_ThBY4bYL1Y6CTaNL2dTw@mail.gmail.com/ Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git [1] Cc: Thomas Gleixner Cc: Tetsuo Handa Signed-off-by: Linus Torvalds --- include/linux/cpuhotplug.h | 1 - kernel/profile.c | 183 +-------------------------------------------- 2 files changed, 2 insertions(+), 182 deletions(-) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 51ba681b915a..affdd890899e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -100,7 +100,6 @@ enum cpuhp_state { CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, - CPUHP_PROFILE_PREPARE, CPUHP_X2APIC_PREPARE, CPUHP_SMPCFD_PREPARE, CPUHP_RELAY_PREPARE, diff --git a/kernel/profile.c b/kernel/profile.c index 4654c6cd984e..2dfb0f4e755c 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -129,180 +129,13 @@ int __ref profile_init(void) return -ENOMEM; } -#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) -/* - * Each cpu has a pair of open-addressed hashtables for pending - * profile hits. read_profile() IPI's all cpus to request them - * to flip buffers and flushes their contents to prof_buffer itself. - * Flip requests are serialized by the profile_flip_mutex. The sole - * use of having a second hashtable is for avoiding cacheline - * contention that would otherwise happen during flushes of pending - * profile hits required for the accuracy of reported profile hits - * and so resurrect the interrupt livelock issue. - * - * The open-addressed hashtables are indexed by profile buffer slot - * and hold the number of pending hits to that profile buffer slot on - * a cpu in an entry. When the hashtable overflows, all pending hits - * are accounted to their corresponding profile buffer slots with - * atomic_add() and the hashtable emptied. As numerous pending hits - * may be accounted to a profile buffer slot in a hashtable entry, - * this amortizes a number of atomic profile buffer increments likely - * to be far larger than the number of entries in the hashtable, - * particularly given that the number of distinct profile buffer - * positions to which hits are accounted during short intervals (e.g. - * several seconds) is usually very small. Exclusion from buffer - * flipping is provided by interrupt disablement (note that for - * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from - * process context). - * The hash function is meant to be lightweight as opposed to strong, - * and was vaguely inspired by ppc64 firmware-supported inverted - * pagetable hash functions, but uses a full hashtable full of finite - * collision chains, not just pairs of them. - * - * -- nyc - */ -static void __profile_flip_buffers(void *unused) -{ - int cpu = smp_processor_id(); - - per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu); -} - -static void profile_flip_buffers(void) -{ - int i, j, cpu; - - mutex_lock(&profile_flip_mutex); - j = per_cpu(cpu_profile_flip, get_cpu()); - put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 1); - for_each_online_cpu(cpu) { - struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j]; - for (i = 0; i < NR_PROFILE_HIT; ++i) { - if (!hits[i].hits) { - if (hits[i].pc) - hits[i].pc = 0; - continue; - } - atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); - hits[i].hits = hits[i].pc = 0; - } - } - mutex_unlock(&profile_flip_mutex); -} - -static void profile_discard_flip_buffers(void) -{ - int i, cpu; - - mutex_lock(&profile_flip_mutex); - i = per_cpu(cpu_profile_flip, get_cpu()); - put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 1); - for_each_online_cpu(cpu) { - struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i]; - memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit)); - } - mutex_unlock(&profile_flip_mutex); -} - -static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) -{ - unsigned long primary, secondary, flags, pc = (unsigned long)__pc; - int i, j, cpu; - struct profile_hit *hits; - - pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); - i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; - secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; - cpu = get_cpu(); - hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)]; - if (!hits) { - put_cpu(); - return; - } - /* - * We buffer the global profiler buffer into a per-CPU - * queue and thus reduce the number of global (and possibly - * NUMA-alien) accesses. The write-queue is self-coalescing: - */ - local_irq_save(flags); - do { - for (j = 0; j < PROFILE_GRPSZ; ++j) { - if (hits[i + j].pc == pc) { - hits[i + j].hits += nr_hits; - goto out; - } else if (!hits[i + j].hits) { - hits[i + j].pc = pc; - hits[i + j].hits = nr_hits; - goto out; - } - } - i = (i + secondary) & (NR_PROFILE_HIT - 1); - } while (i != primary); - - /* - * Add the current hit(s) and flush the write-queue out - * to the global buffer: - */ - atomic_add(nr_hits, &prof_buffer[pc]); - for (i = 0; i < NR_PROFILE_HIT; ++i) { - atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); - hits[i].pc = hits[i].hits = 0; - } -out: - local_irq_restore(flags); - put_cpu(); -} - -static int profile_dead_cpu(unsigned int cpu) -{ - struct page *page; - int i; - - for (i = 0; i < 2; i++) { - if (per_cpu(cpu_profile_hits, cpu)[i]) { - page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]); - per_cpu(cpu_profile_hits, cpu)[i] = NULL; - __free_page(page); - } - } - return 0; -} - -static int profile_prepare_cpu(unsigned int cpu) -{ - int i, node = cpu_to_mem(cpu); - struct page *page; - - per_cpu(cpu_profile_flip, cpu) = 0; - - for (i = 0; i < 2; i++) { - if (per_cpu(cpu_profile_hits, cpu)[i]) - continue; - - page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); - if (!page) { - profile_dead_cpu(cpu); - return -ENOMEM; - } - per_cpu(cpu_profile_hits, cpu)[i] = page_address(page); - - } - return 0; -} - -#else /* !CONFIG_SMP */ -#define profile_flip_buffers() do { } while (0) -#define profile_discard_flip_buffers() do { } while (0) - static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long pc; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; - atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); + if (pc < prof_len) + atomic_add(nr_hits, &prof_buffer[pc]); } -#endif /* !CONFIG_SMP */ void profile_hits(int type, void *__pc, unsigned int nr_hits) { @@ -340,7 +173,6 @@ read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) char *pnt; unsigned long sample_step = 1UL << prof_shift; - profile_flip_buffers(); if (p >= (prof_len+1)*sizeof(unsigned int)) return 0; if (count > (prof_len+1)*sizeof(unsigned int) - p) @@ -386,7 +218,6 @@ static ssize_t write_profile(struct file *file, const char __user *buf, return -EINVAL; } #endif - profile_discard_flip_buffers(); memset(prof_buffer, 0, prof_len * sizeof(atomic_t)); return count; } @@ -404,20 +235,10 @@ int __ref create_proc_profile(void) if (!prof_on) return 0; -#ifdef CONFIG_SMP - err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE", - profile_prepare_cpu, profile_dead_cpu); - if (err) - return err; -#endif entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &profile_proc_ops); if (entry) proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); -#ifdef CONFIG_SMP - else - cpuhp_remove_state(CPUHP_PROFILE_PREPARE); -#endif return err; } subsys_initcall(create_proc_profile); -- cgit v1.2.3 From b6a66e521a2032f7fcba2af5a9bcbaeaa19b7ca3 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Sat, 27 Jul 2024 12:01:23 +0200 Subject: mptcp: sched: check both directions for backup The 'mptcp_subflow_context' structure has two items related to the backup flags: - 'backup': the subflow has been marked as backup by the other peer - 'request_bkup': the backup flag has been set by the host Before this patch, the scheduler was only looking at the 'backup' flag. That can make sense in some cases, but it looks like that's not what we wanted for the general use, because either the path-manager was setting both of them when sending an MP_PRIO, or the receiver was duplicating the 'backup' flag in the subflow request. Note that the use of these two flags in the path-manager are going to be fixed in the next commits, but this change here is needed not to modify the behaviour. Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni --- include/trace/events/mptcp.h | 2 +- net/mptcp/protocol.c | 10 ++++++---- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 09e72215b9f9..085b749cdd97 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -34,7 +34,7 @@ TRACE_EVENT(mptcp_subflow_get_send, struct sock *ssk; __entry->active = mptcp_subflow_active(subflow); - __entry->backup = subflow->backup; + __entry->backup = subflow->backup || subflow->request_bkup; if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock)) __entry->free = sk_stream_memory_free(subflow->tcp_sock); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a26c2c840fd9..a2fc54ed68c0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } mptcp_for_each_subflow(msk, subflow) { + bool backup = subflow->backup || subflow->request_bkup; + trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); - nr_active += !subflow->backup; + nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ @@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); - if (linger_time < send_info[subflow->backup].linger_time) { - send_info[subflow->backup].ssk = ssk; - send_info[subflow->backup].linger_time = linger_time; + if (linger_time < send_info[backup].linger_time) { + send_info[backup].ssk = ssk; + send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); -- cgit v1.2.3 From 22f5468731491e53356ba7c028f0fdea20b18e2c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 30 Jul 2024 10:36:47 -0700 Subject: minmax: improve macro expansion and type checking This clarifies the rules for min()/max()/clamp() type checking and makes them a much more efficient macro expansion. In particular, we now look at the type and range of the inputs to see whether they work together, generating a mask of acceptable comparisons, and then just verifying that the inputs have a shared case: - an expression with a signed type can be used for (1) signed comparisons (2) unsigned comparisons if it is statically known to have a non-negative value - an expression with an unsigned type can be used for (3) unsigned comparison (4) signed comparisons if the type is smaller than 'int' and thus the C integer promotion rules will make it signed anyway Here rule (1) and (3) are obvious, and rule (2) is important in order to allow obvious trivial constants to be used together with unsigned values. Rule (4) is not necessarily a good idea, but matches what we used to do, and we have extant cases of this situation in the kernel. Notably with bcachefs having an expression like min(bch2_bucket_sectors_dirty(a), ca->mi.bucket_size) where bch2_bucket_sectors_dirty() returns an 's64', and 'ca->mi.bucket_size' is of type 'u16'. Technically that bcachefs comparison is clearly sensible on a C type level, because the 'u16' will go through the normal C integer promotion, and become 'int', and then we're comparing two signed values and everything looks sane. However, it's not entirely clear that a 'min(s64,u16)' operation makes a lot of conceptual sense, and it's possible that we will remove rule (4). After all, the _reason_ we have these complicated type checks is exactly that the C type promotion rules are not very intuitive. But at least for now the rule is in place for backwards compatibility. Also note that rule (2) existed before, but is hugely relaxed by this commit. It used to be true only for the simplest compile-time non-negative integer constants. The new macro model will allow cases where the compiler can trivially see that an expression is non-negative even if it isn't necessarily a constant. For example, the amdgpu driver does min_t(size_t, sizeof(fru_info->serial), pia[addr] & 0x3F)); because our old 'min()' macro would see that 'pia[addr] & 0x3F' is of type 'int' and clearly not a C constant expression, so doing a 'min()' with a 'size_t' is a signedness violation. Our new 'min()' macro still sees that 'pia[addr] & 0x3F' is of type 'int', but is smart enough to also see that it is clearly non-negative, and thus would allow that case without any complaints. Cc: Arnd Bergmann Cc: David Laight Cc: Lorenzo Stoakes Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 9 ++++++ include/linux/minmax.h | 74 ++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 68 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 2594553bb30b..2df665fa2964 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -296,6 +296,15 @@ static inline void *offset_to_ptr(const int *off) #define is_signed_type(type) (((type)(-1)) < (__force type)1) #define is_unsigned_type(type) (!is_signed_type(type)) +/* + * Useful shorthand for "is this condition known at compile-time?" + * + * Note that the condition may involve non-constant values, + * but the compiler may know enough about the details of the + * values to determine that the condition is statically true. + */ +#define statically_true(x) (__builtin_constant_p(x) && (x)) + /* * This is needed in functions which generate the stack canary, see * arch/x86/kernel/smpboot.c::start_secondary() for an example. diff --git a/include/linux/minmax.h b/include/linux/minmax.h index e3e4353df983..41da6f85a407 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -26,19 +26,63 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* is_signed_type() isn't a constexpr for pointer types */ -#define __is_signed(x) \ - __builtin_choose_expr(__is_constexpr(is_signed_type(typeof(x))), \ - is_signed_type(typeof(x)), 0) +/* + * __sign_use for integer expressions: + * bit #0 set if ok for unsigned comparisons + * bit #1 set if ok for signed comparisons + * + * In particular, statically non-negative signed integer + * expressions are ok for both. + * + * NOTE! Unsigned types smaller than 'int' are implicitly + * converted to 'int' in expressions, and are accepted for + * signed conversions for now. This is debatable. + * + * Note that 'x' is the original expression, and 'ux' is + * the unique variable that contains the value. + * + * We use 'ux' for pure type checking, and 'x' for when + * we need to look at the value (but without evaluating + * it for side effects! Careful to only ever evaluate it + * with sizeof() or __builtin_constant_p() etc). + * + * Pointers end up being checked by the normal C type + * rules at the actual comparison, and these expressions + * only need to be careful to not cause warnings for + * pointer use. + */ +#define __signed_type_use(x,ux) (2+__is_nonneg(x,ux)) +#define __unsigned_type_use(x,ux) (1+2*(sizeof(ux)<4)) +#define __sign_use(x,ux) (is_signed_type(typeof(ux))? \ + __signed_type_use(x,ux):__unsigned_type_use(x,ux)) + +/* + * To avoid warnings about casting pointers to integers + * of different sizes, we need that special sign type. + * + * On 64-bit we can just always use 'long', since any + * integer or pointer type can just be cast to that. + * + * This does not work for 128-bit signed integers since + * the cast would truncate them, but we do not use s128 + * types in the kernel (we do use 'u128', but they will + * be handled by the !is_signed_type() case). + * + * NOTE! The cast is there only to avoid any warnings + * from when values that aren't signed integer types. + */ +#ifdef CONFIG_64BIT + #define __signed_type(ux) long +#else + #define __signed_type(ux) typeof(__builtin_choose_expr(sizeof(ux)>4,1LL,1L)) +#endif +#define __is_nonneg(x,ux) statically_true((__signed_type(ux))(x)>=0) -/* True for a non-negative signed int constant */ -#define __is_noneg_int(x) \ - (__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0) +#define __types_ok(x,y,ux,uy) \ + (__sign_use(x,ux) & __sign_use(y,uy)) -#define __types_ok(x, y, ux, uy) \ - (__is_signed(ux) == __is_signed(uy) || \ - __is_signed((ux) + 0) == __is_signed((uy) + 0) || \ - __is_noneg_int(x) || __is_noneg_int(y)) +#define __types_ok3(x,y,z,ux,uy,uz) \ + (__sign_use(x,ux) & __sign_use(y,uy) & __sign_use(z,uz)) #define __cmp_op_min < #define __cmp_op_max > @@ -53,8 +97,8 @@ #define __careful_cmp_once(op, x, y, ux, uy) ({ \ __auto_type ux = (x); __auto_type uy = (y); \ - static_assert(__types_ok(x, y, ux, uy), \ - #op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \ + BUILD_BUG_ON_MSG(!__types_ok(x,y,ux,uy), \ + #op"("#x", "#y") signedness error"); \ __cmp(op, ux, uy); }) #define __careful_cmp(op, x, y) \ @@ -70,8 +114,8 @@ static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), \ (lo) <= (hi), true), \ "clamp() low limit " #lo " greater than high limit " #hi); \ - static_assert(__types_ok(uval, lo, uval, ulo), "clamp() 'lo' signedness error"); \ - static_assert(__types_ok(uval, hi, uval, uhi), "clamp() 'hi' signedness error"); \ + BUILD_BUG_ON_MSG(!__types_ok3(val,lo,hi,uval,ulo,uhi), \ + "clamp("#val", "#lo", "#hi") signedness error"); \ __clamp(uval, ulo, uhi); }) #define __careful_clamp(val, lo, hi) \ -- cgit v1.2.3 From 89add40066f9ed9abe5f7f886fe5789ff7e0c50e Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 29 Jul 2024 16:10:12 -0400 Subject: net: drop bad gso csum_start and offset in virtio_net_hdr Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb for GSO packets. The function already checks that a checksum requested with VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets this might not hold for segs after segmentation. Syzkaller demonstrated to reach this warning in skb_checksum_help offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (WARN_ON_ONCE(offset >= skb_headlen(skb))) By injecting a TSO packet: WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0 ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774 ip_finish_output_gso net/ipv4/ip_output.c:279 [inline] __ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301 iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4850 [inline] netdev_start_xmit include/linux/netdevice.h:4864 [inline] xmit_one net/core/dev.c:3595 [inline] dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611 __dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261 packet_snd net/packet/af_packet.c:3073 [inline] The geometry of the bad input packet at tcp_gso_segment: [ 52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0 [ 52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244 [ 52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0)) [ 52.003050][ T8403] csum(0x60000c7 start=199 offset=1536 ip_summed=3 complete_sw=0 valid=0 level=0) Mitigate with stricter input validation. csum_offset: for GSO packets, deduce the correct value from gso_type. This is already done for USO. Extend it to TSO. Let UFO be: udp[46]_ufo_fragment ignores these fields and always computes the checksum in software. csum_start: finding the real offset requires parsing to the transport header. Do not add a parser, use existing segmentation parsing. Thanks to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded. Again test both TSO and USO. Do not test UFO for the above reason, and do not test UDP tunnel offload. GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit from devices with no checksum offload"), but then still these fields are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no need to test for ip_summed == CHECKSUM_PARTIAL first. This revises an existing fix mentioned in the Fixes tag, which broke small packets with GSO offload, as detected by kselftests. Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871 Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org Fixes: e269d79c7d35 ("net: missing check virtio") Cc: stable@vger.kernel.org Signed-off-by: Willem de Bruijn Link: https://patch.msgid.link/20240729201108.1615114-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/virtio_net.h | 16 +++++----------- net/ipv4/tcp_offload.c | 3 +++ net/ipv4/udp_offload.c | 4 ++++ 3 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index d1d7825318c3..6c395a2600e8 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; - u64 ret, remainder, gso_size; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); - if (hdr->gso_size) { - gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); - ret = div64_u64_rem(skb->len, gso_size, &remainder); - if (!(ret && (hdr->gso_size > needed) && - ((remainder > needed) || (remainder == 0)))) { - return -EINVAL; - } - skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG; - } - if (!pskb_may_pull(skb, needed)) return -EINVAL; @@ -182,6 +171,11 @@ retry: if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + if (skb->csum_offset != offsetof(struct tcphdr, check)) + return -EINVAL; + break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 4b791e74529e..e4ad3311e148 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (thlen < sizeof(*th)) goto out; + if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) + goto out; + if (!pskb_may_pull(skb, thlen)) goto out; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index aa2e0a28ca61..bc8a9da750fe 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb))) + return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), -- cgit v1.2.3 From e6ce8a28c768dbbad3f818db286cd0f4c7a921a8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 31 Jul 2024 15:05:22 +0200 Subject: ALSA: ump: Transmit RPN/NRPN message at each MSB/LSB data reception The UMP 1.1 spec says that an RPN/NRPN should be sent when one of the following occurs: * a CC 38 is received * a subsequent CC 6 is received * a CC 98, 99, 100, and 101 is received, indicating the last RPN/NRPN message has ended and a new one has started That said, we should send a partial data even if it's not fully filled. Let's change the UMP conversion helper code to follow that rule. Link: https://patch.msgid.link/20240731130528.12600-2-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/ump_convert.h | 1 + sound/core/ump_convert.c | 49 +++++++++++++++++++++++++++++---------------- 2 files changed, 33 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/sound/ump_convert.h b/include/sound/ump_convert.h index 28c364c63245..d099ae27f849 100644 --- a/include/sound/ump_convert.h +++ b/include/sound/ump_convert.h @@ -13,6 +13,7 @@ struct ump_cvt_to_ump_bank { unsigned char cc_nrpn_msb, cc_nrpn_lsb; unsigned char cc_data_msb, cc_data_lsb; unsigned char cc_bank_msb, cc_bank_lsb; + bool cc_data_msb_set, cc_data_lsb_set; }; /* context for converting from MIDI1 byte stream to UMP packet */ diff --git a/sound/core/ump_convert.c b/sound/core/ump_convert.c index f67c44c83fde..5d1b85e7ac16 100644 --- a/sound/core/ump_convert.c +++ b/sound/core/ump_convert.c @@ -287,25 +287,37 @@ static int cvt_legacy_system_to_ump(struct ump_cvt_to_ump *cvt, return 4; } -static void fill_rpn(struct ump_cvt_to_ump_bank *cc, - union snd_ump_midi2_msg *midi2) +static int fill_rpn(struct ump_cvt_to_ump_bank *cc, + union snd_ump_midi2_msg *midi2, + bool flush) { + if (!(cc->cc_data_lsb_set || cc->cc_data_msb_set)) + return 0; // skip + /* when not flushing, wait for complete data set */ + if (!flush && (!cc->cc_data_lsb_set || !cc->cc_data_msb_set)) + return 0; // skip + if (cc->rpn_set) { midi2->rpn.status = UMP_MSG_STATUS_RPN; midi2->rpn.bank = cc->cc_rpn_msb; midi2->rpn.index = cc->cc_rpn_lsb; - cc->rpn_set = 0; - cc->cc_rpn_msb = cc->cc_rpn_lsb = 0; - } else { + } else if (cc->nrpn_set) { midi2->rpn.status = UMP_MSG_STATUS_NRPN; midi2->rpn.bank = cc->cc_nrpn_msb; midi2->rpn.index = cc->cc_nrpn_lsb; - cc->nrpn_set = 0; - cc->cc_nrpn_msb = cc->cc_nrpn_lsb = 0; + } else { + return 0; // skip } + midi2->rpn.data = upscale_14_to_32bit((cc->cc_data_msb << 7) | cc->cc_data_lsb); + + cc->rpn_set = 0; + cc->nrpn_set = 0; + cc->cc_rpn_msb = cc->cc_rpn_lsb = 0; cc->cc_data_msb = cc->cc_data_lsb = 0; + cc->cc_data_msb_set = cc->cc_data_lsb_set = 0; + return 1; } /* convert to a MIDI 1.0 Channel Voice message */ @@ -318,6 +330,7 @@ static int cvt_legacy_cmd_to_ump(struct ump_cvt_to_ump *cvt, struct ump_cvt_to_ump_bank *cc; union snd_ump_midi2_msg *midi2 = (union snd_ump_midi2_msg *)data; unsigned char status, channel; + int ret; BUILD_BUG_ON(sizeof(union snd_ump_midi1_msg) != 4); BUILD_BUG_ON(sizeof(union snd_ump_midi2_msg) != 8); @@ -358,24 +371,29 @@ static int cvt_legacy_cmd_to_ump(struct ump_cvt_to_ump *cvt, case UMP_MSG_STATUS_CC: switch (buf[1]) { case UMP_CC_RPN_MSB: + ret = fill_rpn(cc, midi2, true); cc->rpn_set = 1; cc->cc_rpn_msb = buf[2]; - return 0; // skip + return ret; case UMP_CC_RPN_LSB: + ret = fill_rpn(cc, midi2, true); cc->rpn_set = 1; cc->cc_rpn_lsb = buf[2]; - return 0; // skip + return ret; case UMP_CC_NRPN_MSB: + ret = fill_rpn(cc, midi2, true); cc->nrpn_set = 1; cc->cc_nrpn_msb = buf[2]; - return 0; // skip + return ret; case UMP_CC_NRPN_LSB: + ret = fill_rpn(cc, midi2, true); cc->nrpn_set = 1; cc->cc_nrpn_lsb = buf[2]; - return 0; // skip + return ret; case UMP_CC_DATA: + cc->cc_data_msb_set = 1; cc->cc_data_msb = buf[2]; - return 0; // skip + return fill_rpn(cc, midi2, false); case UMP_CC_BANK_SELECT: cc->bank_set = 1; cc->cc_bank_msb = buf[2]; @@ -385,12 +403,9 @@ static int cvt_legacy_cmd_to_ump(struct ump_cvt_to_ump *cvt, cc->cc_bank_lsb = buf[2]; return 0; // skip case UMP_CC_DATA_LSB: + cc->cc_data_lsb_set = 1; cc->cc_data_lsb = buf[2]; - if (cc->rpn_set || cc->nrpn_set) - fill_rpn(cc, midi2); - else - return 0; // skip - break; + return fill_rpn(cc, midi2, false); default: midi2->cc.index = buf[1]; midi2->cc.data = upscale_7_to_32bit(buf[2]); -- cgit v1.2.3 From 21b136cc63d2a9ddd60d4699552b69c214b32964 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 30 Jul 2024 15:44:16 -0700 Subject: minmax: fix up min3() and max3() too David Laight pointed out that we should deal with the min3() and max3() mess too, which still does excessive expansion. And our current macros are actually rather broken. In particular, the macros did this: #define min3(x, y, z) min((typeof(x))min(x, y), z) #define max3(x, y, z) max((typeof(x))max(x, y), z) and that not only is a nested expansion of possibly very complex arguments with all that involves, the typing with that "typeof()" cast is completely wrong. For example, imagine what happens in max3() if 'x' happens to be a 'unsigned char', but 'y' and 'z' are 'unsigned long'. The types are compatible, and there's no warning - but the result is just random garbage. No, I don't think we've ever hit that issue in practice, but since we now have sane infrastructure for doing this right, let's just use it. It fixes any excessive expansion, and also avoids these kinds of broken type issues. Requested-by: David Laight Acked-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/minmax.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 41da6f85a407..98008dd92153 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -152,13 +152,20 @@ #define umax(x, y) \ __careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull) +#define __careful_op3(op, x, y, z, ux, uy, uz) ({ \ + __auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\ + BUILD_BUG_ON_MSG(!__types_ok3(x,y,z,ux,uy,uz), \ + #op"3("#x", "#y", "#z") signedness error"); \ + __cmp(op, ux, __cmp(op, uy, uz)); }) + /** * min3 - return minimum of three values * @x: first value * @y: second value * @z: third value */ -#define min3(x, y, z) min((typeof(x))min(x, y), z) +#define min3(x, y, z) \ + __careful_op3(min, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * max3 - return maximum of three values @@ -166,7 +173,8 @@ * @y: second value * @z: third value */ -#define max3(x, y, z) max((typeof(x))max(x, y), z) +#define max3(x, y, z) \ + __careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * min_not_zero - return the minimum that is _not_ zero, unless both are zero -- cgit v1.2.3 From 3908ba2e0b2476e2ec13e15967bf6a37e449f2af Mon Sep 17 00:00:00 2001 From: Nick Hu Date: Wed, 17 Jul 2024 11:17:14 +0800 Subject: RISC-V: Enable the IPI before workqueue_online_cpu() Sometimes the hotplug cpu stalls at the arch_cpu_idle() for a while after workqueue_online_cpu(). When cpu stalls at the idle loop, the reschedule IPI is pending. However the enable bit is not enabled yet so the cpu stalls at WFI until watchdog timeout. Therefore enable the IPI before the workqueue_online_cpu() to fix the issue. Fixes: 63c5484e7495 ("workqueue: Add multiple affinity scopes and interface to select them") Signed-off-by: Nick Hu Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20240717031714.1946036-1-nick.hu@sifive.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/sbi-ipi.c | 2 +- include/linux/cpuhotplug.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/arch/riscv/kernel/sbi-ipi.c b/arch/riscv/kernel/sbi-ipi.c index 1026e22955cc..0cc5559c08d8 100644 --- a/arch/riscv/kernel/sbi-ipi.c +++ b/arch/riscv/kernel/sbi-ipi.c @@ -71,7 +71,7 @@ void __init sbi_ipi_init(void) * the masking/unmasking of virtual IPIs is done * via generic IPI-Mux */ - cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + cpuhp_setup_state(CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING, "irqchip/sbi-ipi:starting", sbi_ipi_starting_cpu, NULL); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 51ba681b915a..e30d93b807d5 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -148,6 +148,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_LOONGARCH_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, + CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, -- cgit v1.2.3 From c8a132e2e032b00828d51141ab34f9aeb24f44ae Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 2 Aug 2024 11:57:32 +0100 Subject: ASoC: soc-component: Add new snd_soc_component_get_kcontrol() helpers Add new helper functions snd_soc_component_get_kcontrol() and snd_soc_component_get_kcontrol_locked() that returns a kcontrol by name, but will factor in the components name_prefix, to handle situations where multiple components are present with the same controls. Signed-off-by: Charles Keepax Link: https://patch.msgid.link/20240802105734.2309788-3-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc-component.h | 5 +++++ sound/soc/soc-component.c | 42 ++++++++++++++++++++++++++++++++++-------- 2 files changed, 39 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index ceca69b46a82..bf2e381cd124 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -462,6 +462,11 @@ int snd_soc_component_force_enable_pin_unlocked( const char *pin); /* component controls */ +struct snd_kcontrol *snd_soc_component_get_kcontrol(struct snd_soc_component *component, + const char * const ctl); +struct snd_kcontrol * +snd_soc_component_get_kcontrol_locked(struct snd_soc_component *component, + const char * const ctl); int snd_soc_component_notify_control(struct snd_soc_component *component, const char * const ctl); diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c index 4d7c2e3c929a..42f481321919 100644 --- a/sound/soc/soc-component.c +++ b/sound/soc/soc-component.c @@ -236,19 +236,45 @@ int snd_soc_component_force_enable_pin_unlocked( } EXPORT_SYMBOL_GPL(snd_soc_component_force_enable_pin_unlocked); -int snd_soc_component_notify_control(struct snd_soc_component *component, - const char * const ctl) +static void soc_get_kcontrol_name(struct snd_soc_component *component, + char *buf, int size, const char * const ctl) { - char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - struct snd_kcontrol *kctl; - /* When updating, change also snd_soc_dapm_widget_name_cmp() */ if (component->name_prefix) - snprintf(name, ARRAY_SIZE(name), "%s %s", component->name_prefix, ctl); + snprintf(buf, size, "%s %s", component->name_prefix, ctl); else - snprintf(name, ARRAY_SIZE(name), "%s", ctl); + snprintf(buf, size, "%s", ctl); +} + +struct snd_kcontrol *snd_soc_component_get_kcontrol(struct snd_soc_component *component, + const char * const ctl) +{ + char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; + + soc_get_kcontrol_name(component, name, ARRAY_SIZE(name), ctl); + + return snd_soc_card_get_kcontrol(component->card, name); +} +EXPORT_SYMBOL_GPL(snd_soc_component_get_kcontrol); + +struct snd_kcontrol * +snd_soc_component_get_kcontrol_locked(struct snd_soc_component *component, + const char * const ctl) +{ + char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; + + soc_get_kcontrol_name(component, name, ARRAY_SIZE(name), ctl); + + return snd_soc_card_get_kcontrol_locked(component->card, name); +} +EXPORT_SYMBOL_GPL(snd_soc_component_get_kcontrol_locked); + +int snd_soc_component_notify_control(struct snd_soc_component *component, + const char * const ctl) +{ + struct snd_kcontrol *kctl; - kctl = snd_soc_card_get_kcontrol(component->card, name); + kctl = snd_soc_component_get_kcontrol(component, ctl); if (!kctl) return soc_component_ret(component, -EINVAL); -- cgit v1.2.3 From 54233a4254036efca91b9bffbd398ecf39e90555 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 30 Jul 2024 17:30:40 +0200 Subject: uretprobe: change syscall number, again Despite multiple attempts to get the syscall number assignment right for the newly added uretprobe syscall, we ended up with a bit of a mess: - The number is defined as 467 based on the assumption that the xattrat family of syscalls would use 463 through 466, but those did not make it into 6.11. - The include/uapi/asm-generic/unistd.h file still lists the number 463, but the new scripts/syscall.tbl that was supposed to have the same data lists 467 instead as the number for arc, arm64, csky, hexagon, loongarch, nios2, openrisc and riscv. None of these architectures actually provide a uretprobe syscall. - All the other architectures (powerpc, arm, mips, ...) don't list this syscall at all. There are two ways to make it consistent again: either list it with the same syscall number on all architectures, or only list it on x86 but not in scripts/syscall.tbl and asm-generic/unistd.h. Based on the most recent discussion, it seems like we won't need it anywhere else, so just remove the inconsistent assignment and instead move the x86 number to the next available one in the architecture specific range, which is 335. Fixes: 5c28424e9a34 ("syscalls: Fix to add sys_uretprobe to syscall.tbl") Fixes: 190fec72df4a ("uprobe: Wire up uretprobe system call") Fixes: 63ded110979b ("uprobe: Change uretprobe syscall scope and number") Acked-by: Masami Hiramatsu (Google) Reviewed-by: Jiri Olsa Signed-off-by: Arnd Bergmann --- arch/x86/entry/syscalls/syscall_64.tbl | 2 +- include/uapi/asm-generic/unistd.h | 5 +---- scripts/syscall.tbl | 1 - tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 2 +- 4 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 83073fa3c989..7093ee21c0d1 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -344,6 +344,7 @@ 332 common statx sys_statx 333 common io_pgetevents sys_io_pgetevents 334 common rseq sys_rseq +335 common uretprobe sys_uretprobe # don't use numbers 387 through 423, add new calls after the last # 'common' entry 424 common pidfd_send_signal sys_pidfd_send_signal @@ -385,7 +386,6 @@ 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules 462 common mseal sys_mseal -467 common uretprobe sys_uretprobe # # Due to a historical design error, certain syscalls are numbered differently diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 985a262d0f9e..5bf6148cac2b 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -841,11 +841,8 @@ __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) #define __NR_mseal 462 __SYSCALL(__NR_mseal, sys_mseal) -#define __NR_uretprobe 463 -__SYSCALL(__NR_uretprobe, sys_uretprobe) - #undef __NR_syscalls -#define __NR_syscalls 464 +#define __NR_syscalls 463 /* * 32 bit systems traditionally used different diff --git a/scripts/syscall.tbl b/scripts/syscall.tbl index 591d85e8ca7e..797e20ea99a2 100644 --- a/scripts/syscall.tbl +++ b/scripts/syscall.tbl @@ -402,4 +402,3 @@ 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules 462 common mseal sys_mseal -467 common uretprobe sys_uretprobe diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c index bd8c75b620c2..5f78edca6540 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c @@ -216,7 +216,7 @@ static void test_uretprobe_regs_change(void) } #ifndef __NR_uretprobe -#define __NR_uretprobe 467 +#define __NR_uretprobe 335 #endif __naked unsigned long uretprobe_syscall_call_1(void) -- cgit v1.2.3 From 90ec3a8a7fd0d43026fcca979713e077d4883b56 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Fri, 2 Aug 2024 16:22:13 +0100 Subject: spi: Add empty versions of ACPI functions Provide empty versions of acpi_spi_count_resources(), acpi_spi_device_alloc() and acpi_spi_find_controller_by_adev() if the real functions are not being built. This commit fixes two problems with the original definitions: 1) There wasn't an empty version of these functions 2) The #if only depended on CONFIG_ACPI. But the functions are implemented in the core spi.c so CONFIG_SPI_MASTER must also be enabled for the real functions to exist. Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20240802152215.20831-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e4f3f3d30a03..d47d5f14ff99 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -902,12 +902,29 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); -#if IS_ENABLED(CONFIG_ACPI) +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SPI_MASTER) extern struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev); extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, struct acpi_device *adev, int index); int acpi_spi_count_resources(struct acpi_device *adev); +#else +static inline struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev) +{ + return NULL; +} + +static inline struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, + struct acpi_device *adev, + int index) +{ + return ERR_PTR(-ENODEV); +} + +static inline int acpi_spi_count_resources(struct acpi_device *adev) +{ + return 0; +} #endif /* -- cgit v1.2.3 From b6547e54864b998af21fdcaa0a88cf8e7efe641a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 2 Aug 2024 18:12:06 -0700 Subject: runtime constants: deal with old decrepit linkers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The runtime constants linker script depended on documented linker behavior [1]: "If an output section’s name is the same as the input section’s name and is representable as a C identifier, then the linker will automatically PROVIDE two symbols: __start_SECNAME and __stop_SECNAME, where SECNAME is the name of the section. These indicate the start address and end address of the output section respectively" to just automatically define the symbol names for the bounds of the runtime constant arrays. It turns out that this isn't actually something we can rely on, with old linkers not generating these automatic symbols. It looks to have been introduced in binutils-2.29 back in 2017, and we still support building with versions all the way back to binutils-2.25 (from 2015). And yes, Oleg actually seems to be using such ancient versions of binutils. So instead of depending on the implicit symbols from "section names match and are representable C identifiers", just do this all manually. It's not like it causes us any extra pain, we already have to do that for all the other sections that we use that often have special characters in them. Reported-and-tested-by: Oleg Nesterov Link: https://sourceware.org/binutils/docs/ld/Input-Section-Example.html [1] Link: https://lore.kernel.org/all/20240802114518.GA20924@redhat.com/ Signed-off-by: Linus Torvalds --- include/asm-generic/vmlinux.lds.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index ad6afc5c4918..1ae44793132a 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -911,13 +911,12 @@ #define CON_INITCALL \ BOUNDED_SECTION_POST_LABEL(.con_initcall.init, __con_initcall, _start, _end) -#define RUNTIME_NAME(t,x) runtime_##t##_##x +#define NAMED_SECTION(name) \ + . = ALIGN(8); \ + name : AT(ADDR(name) - LOAD_OFFSET) \ + { BOUNDED_SECTION_PRE_LABEL(name, name, __start_, __stop_) } -#define RUNTIME_CONST(t,x) \ - . = ALIGN(8); \ - RUNTIME_NAME(t,x) : AT(ADDR(RUNTIME_NAME(t,x)) - LOAD_OFFSET) { \ - *(RUNTIME_NAME(t,x)); \ - } +#define RUNTIME_CONST(t,x) NAMED_SECTION(runtime_##t##_##x) /* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */ #define KUNIT_TABLE() \ -- cgit v1.2.3 From f17c06c6608ad4ecd2ccf321753fb511812d821b Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Fri, 2 Aug 2024 16:22:14 +0100 Subject: i2c: Fix conditional for substituting empty ACPI functions Add IS_ENABLED(CONFIG_I2C) to the conditional around a bunch of ACPI functions. The conditional around these functions depended only on CONFIG_ACPI. But the functions are implemented in I2C core, so are only present if CONFIG_I2C is enabled. Signed-off-by: Richard Fitzgerald Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 07e33bbc9256..7eedd0c662da 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1066,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev, struct acpi_resource; struct acpi_resource_i2c_serialbus; -#if IS_ENABLED(CONFIG_ACPI) +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); -- cgit v1.2.3 From b88f55389ad27f05ed84af9e1026aa64dbfabc9a Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 4 Aug 2024 18:48:10 +0900 Subject: profiling: remove profile=sleep support The kernel sleep profile is no longer working due to a recursive locking bug introduced by commit 42a20f86dc19 ("sched: Add wrapper for get_wchan() to keep task blocked") Booting with the 'profile=sleep' kernel command line option added or executing # echo -n sleep > /sys/kernel/profiling after boot causes the system to lock up. Lockdep reports kthreadd/3 is trying to acquire lock: ffff93ac82e08d58 (&p->pi_lock){....}-{2:2}, at: get_wchan+0x32/0x70 but task is already holding lock: ffff93ac82e08d58 (&p->pi_lock){....}-{2:2}, at: try_to_wake_up+0x53/0x370 with the call trace being lock_acquire+0xc8/0x2f0 get_wchan+0x32/0x70 __update_stats_enqueue_sleeper+0x151/0x430 enqueue_entity+0x4b0/0x520 enqueue_task_fair+0x92/0x6b0 ttwu_do_activate+0x73/0x140 try_to_wake_up+0x213/0x370 swake_up_locked+0x20/0x50 complete+0x2f/0x40 kthread+0xfb/0x180 However, since nobody noticed this regression for more than two years, let's remove 'profile=sleep' support based on the assumption that nobody needs this functionality. Fixes: 42a20f86dc19 ("sched: Add wrapper for get_wchan() to keep task blocked") Cc: stable@vger.kernel.org # v5.16+ Signed-off-by: Tetsuo Handa Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 4 +--- include/linux/profile.h | 1 - kernel/profile.c | 11 +---------- kernel/sched/stats.c | 10 ---------- 4 files changed, 2 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f1384c7b59c9..09126bb8cc9f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4798,11 +4798,9 @@ profile= [KNL] Enable kernel profiling via /proc/profile Format: [,] - Param: : "schedule", "sleep", or "kvm" + Param: : "schedule" or "kvm" [defaults to kernel profiling] Param: "schedule" - profile schedule points. - Param: "sleep" - profile D-state sleeping (millisecs). - Requires CONFIG_SCHEDSTATS Param: "kvm" - profile VM exits. Param: - step/bucket size as a power of 2 for statistical time based profiling. diff --git a/include/linux/profile.h b/include/linux/profile.h index 2fb487f61d12..3f53cdb0c27c 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -10,7 +10,6 @@ #define CPU_PROFILING 1 #define SCHED_PROFILING 2 -#define SLEEP_PROFILING 3 #define KVM_PROFILING 4 struct proc_dir_entry; diff --git a/kernel/profile.c b/kernel/profile.c index ff68d3816182..1fcf1adcf4eb 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -50,20 +50,11 @@ EXPORT_SYMBOL_GPL(prof_on); int profile_setup(char *str) { static const char schedstr[] = "schedule"; - static const char sleepstr[] = "sleep"; static const char kvmstr[] = "kvm"; const char *select = NULL; int par; - if (!strncmp(str, sleepstr, strlen(sleepstr))) { -#ifdef CONFIG_SCHEDSTATS - force_schedstat_enabled(); - prof_on = SLEEP_PROFILING; - select = sleepstr; -#else - pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n"); -#endif /* CONFIG_SCHEDSTATS */ - } else if (!strncmp(str, schedstr, strlen(schedstr))) { + if (!strncmp(str, schedstr, strlen(schedstr))) { prof_on = SCHED_PROFILING; select = schedstr; } else if (!strncmp(str, kvmstr, strlen(kvmstr))) { diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index 78e48f5426ee..eb0cdcd4d921 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -92,16 +92,6 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p, trace_sched_stat_blocked(p, delta); - /* - * Blocking time is in units of nanosecs, so shift by - * 20 to get a milliseconds-range estimation of the - * amount of time that the task spent sleeping: - */ - if (unlikely(prof_on == SLEEP_PROFILING)) { - profile_hits(SLEEP_PROFILING, - (void *)get_wchan(p), - delta >> 20); - } account_scheduler_latency(p, delta >> 10, 0); } } -- cgit v1.2.3 From 0e8b53979ac86eddb3fd76264025a70071a25574 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 5 Aug 2024 14:01:21 +0900 Subject: bpf: kprobe: remove unused declaring of bpf_kprobe_override After the commit 66665ad2f102 ("tracing/kprobe: bpf: Compare instruction pointer with original one"), "bpf_kprobe_override" is not used anywhere anymore, and we can remove it now. Link: https://lore.kernel.org/all/20240710085939.11520-1-dongml2@chinatelecom.cn/ Fixes: 66665ad2f102 ("tracing/kprobe: bpf: Compare instruction pointer with original one") Signed-off-by: Menglong Dong Acked-by: Jiri Olsa Signed-off-by: Masami Hiramatsu (Google) --- include/linux/trace_events.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 9df3e2973626..9435185c10ef 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -880,7 +880,6 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); -- cgit v1.2.3 From e42066df07c0fcedebb32ed56f8bc39b4bf86337 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 5 Aug 2024 15:08:39 +0100 Subject: ASoC: cs35l56: Handle OTP read latency over SoundWire Use the late-read buffer in the CS35L56 SoundWire interface to read OTP memory. The OTP memory has a longer access latency than chip registers and cannot guarantee to return the data value in the SoundWire control response if the bus clock is >4.8 MHz. The Cirrus SoundWire peripheral IP exposes the bridge-to-bus read buffer and status bits. For a read from OTP the bridge status bits are polled to wait for the OTP data to be loaded into the read buffer and the data is then read from there. Signed-off-by: Richard Fitzgerald Fixes: e1830f66f6c6 ("ASoC: cs35l56: Add helper functions for amp calibration") Link: https://patch.msgid.link/20240805140839.26042-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/cs35l56.h | 5 +++ sound/soc/codecs/cs35l56-sdw.c | 77 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 82 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h index a6aa112e5741..a51acefa785f 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -277,6 +277,11 @@ static inline int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_ba return 0; } +static inline bool cs35l56_is_otp_register(unsigned int reg) +{ + return (reg >> 16) == 3; +} + extern struct regmap_config cs35l56_regmap_i2c; extern struct regmap_config cs35l56_regmap_spi; extern struct regmap_config cs35l56_regmap_sdw; diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c index fc03bb7ecae1..7c9a17fe2195 100644 --- a/sound/soc/codecs/cs35l56-sdw.c +++ b/sound/soc/codecs/cs35l56-sdw.c @@ -23,6 +23,79 @@ /* Register addresses are offset when sent over SoundWire */ #define CS35L56_SDW_ADDR_OFFSET 0x8000 +/* Cirrus bus bridge registers */ +#define CS35L56_SDW_MEM_ACCESS_STATUS 0xd0 +#define CS35L56_SDW_MEM_READ_DATA 0xd8 + +#define CS35L56_SDW_LAST_LATE BIT(3) +#define CS35L56_SDW_CMD_IN_PROGRESS BIT(2) +#define CS35L56_SDW_RDATA_RDY BIT(0) + +#define CS35L56_LATE_READ_POLL_US 10 +#define CS35L56_LATE_READ_TIMEOUT_US 1000 + +static int cs35l56_sdw_poll_mem_status(struct sdw_slave *peripheral, + unsigned int mask, + unsigned int match) +{ + int ret, val; + + ret = read_poll_timeout(sdw_read_no_pm, val, + (val < 0) || ((val & mask) == match), + CS35L56_LATE_READ_POLL_US, CS35L56_LATE_READ_TIMEOUT_US, + false, peripheral, CS35L56_SDW_MEM_ACCESS_STATUS); + if (ret < 0) + return ret; + + if (val < 0) + return val; + + return 0; +} + +static int cs35l56_sdw_slow_read(struct sdw_slave *peripheral, unsigned int reg, + u8 *buf, size_t val_size) +{ + int ret, i; + + reg += CS35L56_SDW_ADDR_OFFSET; + + for (i = 0; i < val_size; i += sizeof(u32)) { + /* Poll for bus bridge idle */ + ret = cs35l56_sdw_poll_mem_status(peripheral, + CS35L56_SDW_CMD_IN_PROGRESS, + 0); + if (ret < 0) { + dev_err(&peripheral->dev, "!CMD_IN_PROGRESS fail: %d\n", ret); + return ret; + } + + /* Reading LSByte triggers read of register to holding buffer */ + sdw_read_no_pm(peripheral, reg + i); + + /* Wait for data available */ + ret = cs35l56_sdw_poll_mem_status(peripheral, + CS35L56_SDW_RDATA_RDY, + CS35L56_SDW_RDATA_RDY); + if (ret < 0) { + dev_err(&peripheral->dev, "RDATA_RDY fail: %d\n", ret); + return ret; + } + + /* Read data from buffer */ + ret = sdw_nread_no_pm(peripheral, CS35L56_SDW_MEM_READ_DATA, + sizeof(u32), &buf[i]); + if (ret) { + dev_err(&peripheral->dev, "Late read @%#x failed: %d\n", reg + i, ret); + return ret; + } + + swab32s((u32 *)&buf[i]); + } + + return 0; +} + static int cs35l56_sdw_read_one(struct sdw_slave *peripheral, unsigned int reg, void *buf) { int ret; @@ -48,6 +121,10 @@ static int cs35l56_sdw_read(void *context, const void *reg_buf, int ret; reg = le32_to_cpu(*(const __le32 *)reg_buf); + + if (cs35l56_is_otp_register(reg)) + return cs35l56_sdw_slow_read(peripheral, reg, buf8, val_size); + reg += CS35L56_SDW_ADDR_OFFSET; if (val_size == 4) -- cgit v1.2.3 From f91f7ac900e7342e0fd66093dfbf7cb8cb585a99 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Wed, 17 Jul 2024 15:00:23 +0200 Subject: refcount: Report UAF for refcount_sub_and_test(0) when counter==0 When a reference counter is at zero and refcount_sub_and_test() is invoked to subtract zero, the function accepts this request without any warning and returns true. This behavior does not seem ideal because the counter being already at zero indicates a use-after-free. Furthermore, returning true by refcount_sub_and_test() in this case potentially results in a double-free done by its caller. Modify the underlying function __refcount_sub_and_test() to warn about this case as a use-after-free and have it return false to avoid the potential double-free. Signed-off-by: Petr Pavlu Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20240717130023.5675-1-petr.pavlu@suse.com Signed-off-by: Kees Cook --- drivers/misc/lkdtm/refcount.c | 16 ++++++++++++++++ include/linux/refcount.h | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/misc/lkdtm/refcount.c b/drivers/misc/lkdtm/refcount.c index 5cd488f54cfa..8f744bee6fbd 100644 --- a/drivers/misc/lkdtm/refcount.c +++ b/drivers/misc/lkdtm/refcount.c @@ -182,6 +182,21 @@ static void lkdtm_REFCOUNT_SUB_AND_TEST_NEGATIVE(void) check_negative(&neg, 3); } +/* + * A refcount_sub_and_test() by zero when the counter is at zero should act like + * refcount_sub_and_test() above when going negative. + */ +static void lkdtm_REFCOUNT_SUB_AND_TEST_ZERO(void) +{ + refcount_t neg = REFCOUNT_INIT(0); + + pr_info("attempting bad refcount_sub_and_test() at zero\n"); + if (refcount_sub_and_test(0, &neg)) + pr_warn("Weird: refcount_sub_and_test() reported zero\n"); + + check_negative(&neg, 0); +} + static void check_from_zero(refcount_t *ref) { switch (refcount_read(ref)) { @@ -400,6 +415,7 @@ static struct crashtype crashtypes[] = { CRASHTYPE(REFCOUNT_DEC_NEGATIVE), CRASHTYPE(REFCOUNT_DEC_AND_TEST_NEGATIVE), CRASHTYPE(REFCOUNT_SUB_AND_TEST_NEGATIVE), + CRASHTYPE(REFCOUNT_SUB_AND_TEST_ZERO), CRASHTYPE(REFCOUNT_INC_ZERO), CRASHTYPE(REFCOUNT_ADD_ZERO), CRASHTYPE(REFCOUNT_INC_SATURATED), diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 59b3b752394d..35f039ecb272 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -266,12 +266,12 @@ bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) if (oldp) *oldp = old; - if (old == i) { + if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } - if (unlikely(old < 0 || old - i < 0)) + if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; -- cgit v1.2.3 From 9a2fa1472083580b6c66bdaf291f591e1170123a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 3 Aug 2024 18:02:00 -0400 Subject: fix bitmap corruption on close_range() with CLOSE_RANGE_UNSHARE copy_fd_bitmaps(new, old, count) is expected to copy the first count/BITS_PER_LONG bits from old->full_fds_bits[] and fill the rest with zeroes. What it does is copying enough words (BITS_TO_LONGS(count/BITS_PER_LONG)), then memsets the rest. That works fine, *if* all bits past the cutoff point are clear. Otherwise we are risking garbage from the last word we'd copied. For most of the callers that is true - expand_fdtable() has count equal to old->max_fds, so there's no open descriptors past count, let alone fully occupied words in ->open_fds[], which is what bits in ->full_fds_bits[] correspond to. The other caller (dup_fd()) passes sane_fdtable_size(old_fdt, max_fds), which is the smallest multiple of BITS_PER_LONG that covers all opened descriptors below max_fds. In the common case (copying on fork()) max_fds is ~0U, so all opened descriptors will be below it and we are fine, by the same reasons why the call in expand_fdtable() is safe. Unfortunately, there is a case where max_fds is less than that and where we might, indeed, end up with junk in ->full_fds_bits[] - close_range(from, to, CLOSE_RANGE_UNSHARE) with * descriptor table being currently shared * 'to' being above the current capacity of descriptor table * 'from' being just under some chunk of opened descriptors. In that case we end up with observably wrong behaviour - e.g. spawn a child with CLONE_FILES, get all descriptors in range 0..127 open, then close_range(64, ~0U, CLOSE_RANGE_UNSHARE) and watch dup(0) ending up with descriptor #128, despite #64 being observably not open. The minimally invasive fix would be to deal with that in dup_fd(). If this proves to add measurable overhead, we can go that way, but let's try to fix copy_fd_bitmaps() first. * new helper: bitmap_copy_and_expand(to, from, bits_to_copy, size). * make copy_fd_bitmaps() take the bitmap size in words, rather than bits; it's 'count' argument is always a multiple of BITS_PER_LONG, so we are not losing any information, and that way we can use the same helper for all three bitmaps - compiler will see that count is a multiple of BITS_PER_LONG for the large ones, so it'll generate plain memcpy()+memset(). Reproducer added to tools/testing/selftests/core/close_range_test.c Cc: stable@vger.kernel.org Signed-off-by: Al Viro --- fs/file.c | 30 +++++++++------------ include/linux/bitmap.h | 12 +++++++++ tools/testing/selftests/core/close_range_test.c | 35 +++++++++++++++++++++++++ 3 files changed, 60 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/fs/file.c b/fs/file.c index a11e59b5d602..655338effe9c 100644 --- a/fs/file.c +++ b/fs/file.c @@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu) #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) +#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ -static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, - unsigned int count) +static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, + unsigned int copy_words) { - unsigned int cpy, set; - - cpy = count / BITS_PER_BYTE; - set = (nfdt->max_fds - count) / BITS_PER_BYTE; - memcpy(nfdt->open_fds, ofdt->open_fds, cpy); - memset((char *)nfdt->open_fds + cpy, 0, set); - memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); - memset((char *)nfdt->close_on_exec + cpy, 0, set); - - cpy = BITBIT_SIZE(count); - set = BITBIT_SIZE(nfdt->max_fds) - cpy; - memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); - memset((char *)nfdt->full_fds_bits + cpy, 0, set); + unsigned int nwords = fdt_words(nfdt); + + bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, + copy_words, nwords); } /* @@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); - copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); + copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* @@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int open_files = sane_fdtable_size(old_fdt, max_fds); } - copy_fd_bitmaps(new_fdt, old_fdt, open_files); + copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 8c4768c44a01..d3b66d77df7a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } +static inline void bitmap_copy_and_extend(unsigned long *to, + const unsigned long *from, + unsigned int count, unsigned int size) +{ + unsigned int copy = BITS_TO_LONGS(count); + + memcpy(to, from, copy * sizeof(long)); + if (count % BITS_PER_LONG) + to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); + memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); +} + /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 991c473e3859..12b4eb9d0434 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot) EXPECT_EQ(close(fd3), 0); } +TEST(close_range_bitmap_corruption) +{ + pid_t pid; + int status; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* get the first 128 descriptors open */ + for (int i = 2; i < 128; i++) + EXPECT_GE(dup2(0, i), 0); + + /* get descriptor table shared */ + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* unshare and truncate descriptor table down to 64 */ + if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE)) + exit(EXIT_FAILURE); + + ASSERT_EQ(fcntl(64, F_GETFD), -1); + /* ... and verify that the range 64..127 is not + stuck "fully used" according to secondary bitmap */ + EXPECT_EQ(dup(0), 64) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + TEST_HARNESS_MAIN -- cgit v1.2.3 From 6e2fdceffdc6bd7b8ba314a1d1b976721533c8f9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 26 Jul 2024 14:42:08 -0400 Subject: tracing: Use refcount for trace_event_file reference counter Instead of using an atomic counter for the trace_event_file reference counter, use the refcount interface. It has various checks to make sure the reference counting is correct, and will warn if it detects an error (like refcount_inc() on '0'). Cc: Mathieu Desnoyers Link: https://lore.kernel.org/20240726144208.687cce24@rorschach.local.home Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 2 +- kernel/trace/trace_events.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 9df3e2973626..fed58e54f15e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -680,7 +680,7 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; - atomic_t ref; /* ref count for opened files */ + refcount_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f08fbaf8cad6..7266ec2a4eea 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -992,18 +992,18 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) void event_file_get(struct trace_event_file *file) { - atomic_inc(&file->ref); + refcount_inc(&file->ref); } void event_file_put(struct trace_event_file *file) { - if (WARN_ON_ONCE(!atomic_read(&file->ref))) { + if (WARN_ON_ONCE(!refcount_read(&file->ref))) { if (file->flags & EVENT_FILE_FL_FREED) kmem_cache_free(file_cachep, file); return; } - if (atomic_dec_and_test(&file->ref)) { + if (refcount_dec_and_test(&file->ref)) { /* Count should only go to zero when it is freed */ if (WARN_ON_ONCE(!(file->flags & EVENT_FILE_FL_FREED))) return; @@ -3003,7 +3003,7 @@ trace_create_new_event(struct trace_event_call *call, atomic_set(&file->tm_ref, 0); INIT_LIST_HEAD(&file->triggers); list_add(&file->list, &tr->events); - event_file_get(file); + refcount_set(&file->ref, 1); return file; } -- cgit v1.2.3 From d507ae0dc83b7f43cdf6760b8f1a30aac4fc405a Mon Sep 17 00:00:00 2001 From: Arunpravin Paneer Selvam Date: Fri, 2 Aug 2024 11:13:19 +0530 Subject: drm/buddy: Add start address support to trim function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Add a new start parameter in trim function to specify exact address from where to start the trimming. This would help us in situations like if drivers would like to do address alignment for specific requirements. - Add a new flag DRM_BUDDY_TRIM_DISABLE. Drivers can use this flag to disable the allocator trimming part. This patch enables the drivers control trimming and they can do it themselves based on the application requirements. v1:(Matthew) - check new_start alignment with min chunk_size - use range_overflows() Signed-off-by: Arunpravin Paneer Selvam Acked-by: Alex Deucher Acked-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit db65eb46de135338d6177f8853e0fd208f19d63e) --- drivers/gpu/drm/drm_buddy.c | 25 +++++++++++++++++++++++-- drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 2 +- include/drm/drm_buddy.h | 2 ++ 3 files changed, 26 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 6a8e45e9d0ec..103c185bb1c8 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -851,6 +851,7 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm, * drm_buddy_block_trim - free unused pages * * @mm: DRM buddy manager + * @start: start address to begin the trimming. * @new_size: original size requested * @blocks: Input and output list of allocated blocks. * MUST contain single block as input to be trimmed. @@ -866,11 +867,13 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm, * 0 on success, error code on failure. */ int drm_buddy_block_trim(struct drm_buddy *mm, + u64 *start, u64 new_size, struct list_head *blocks) { struct drm_buddy_block *parent; struct drm_buddy_block *block; + u64 block_start, block_end; LIST_HEAD(dfs); u64 new_start; int err; @@ -882,6 +885,9 @@ int drm_buddy_block_trim(struct drm_buddy *mm, struct drm_buddy_block, link); + block_start = drm_buddy_block_offset(block); + block_end = block_start + drm_buddy_block_size(mm, block); + if (WARN_ON(!drm_buddy_block_is_allocated(block))) return -EINVAL; @@ -894,6 +900,20 @@ int drm_buddy_block_trim(struct drm_buddy *mm, if (new_size == drm_buddy_block_size(mm, block)) return 0; + new_start = block_start; + if (start) { + new_start = *start; + + if (new_start < block_start) + return -EINVAL; + + if (!IS_ALIGNED(new_start, mm->chunk_size)) + return -EINVAL; + + if (range_overflows(new_start, new_size, block_end)) + return -EINVAL; + } + list_del(&block->link); mark_free(mm, block); mm->avail += drm_buddy_block_size(mm, block); @@ -904,7 +924,6 @@ int drm_buddy_block_trim(struct drm_buddy *mm, parent = block->parent; block->parent = NULL; - new_start = drm_buddy_block_offset(block); list_add(&block->tmp_link, &dfs); err = __alloc_range(mm, &dfs, new_start, new_size, blocks, NULL); if (err) { @@ -1066,7 +1085,8 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, } while (1); /* Trim the allocated block to the required size */ - if (original_size != size) { + if (!(flags & DRM_BUDDY_TRIM_DISABLE) && + original_size != size) { struct list_head *trim_list; LIST_HEAD(temp); u64 trim_size; @@ -1083,6 +1103,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, } drm_buddy_block_trim(mm, + NULL, trim_size, trim_list); diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c index fe3779fdba2c..423b261ea743 100644 --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c @@ -150,7 +150,7 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man, } while (remaining_size); if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { - if (!drm_buddy_block_trim(mm, vres->base.size, &vres->blocks)) + if (!drm_buddy_block_trim(mm, NULL, vres->base.size, &vres->blocks)) size = vres->base.size; } diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index 2a74fa9d0ce5..9689a7c5dd36 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -27,6 +27,7 @@ #define DRM_BUDDY_CONTIGUOUS_ALLOCATION BIT(2) #define DRM_BUDDY_CLEAR_ALLOCATION BIT(3) #define DRM_BUDDY_CLEARED BIT(4) +#define DRM_BUDDY_TRIM_DISABLE BIT(5) struct drm_buddy_block { #define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12) @@ -155,6 +156,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, unsigned long flags); int drm_buddy_block_trim(struct drm_buddy *mm, + u64 *start, u64 new_size, struct list_head *blocks); -- cgit v1.2.3 From 58f7e4d7ba32758b861807e77535853cacc1f426 Mon Sep 17 00:00:00 2001 From: Jianhui Zhou <912460177@qq.com> Date: Mon, 5 Aug 2024 19:36:31 +0800 Subject: ring-buffer: Remove unused function ring_buffer_nr_pages() Because ring_buffer_nr_pages() is not an inline function and user accesses buffer->buffers[cpu]->nr_pages directly, the function ring_buffer_nr_pages is removed. Signed-off-by: Jianhui Zhou <912460177@qq.com> Link: https://lore.kernel.org/tencent_F4A7E9AB337F44E0F4B858D07D19EF460708@qq.com Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 1 - kernel/trace/ring_buffer.c | 12 ------------ 2 files changed, 13 deletions(-) (limited to 'include') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 96d2140b471e..fd35d4ec12e1 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -193,7 +193,6 @@ void ring_buffer_set_clock(struct trace_buffer *buffer, void ring_buffer_set_time_stamp_abs(struct trace_buffer *buffer, bool abs); bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); -size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); struct buffer_data_read_page; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 28853966aa9a..cebd879a30cb 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -692,18 +692,6 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, return ts; } -/** - * ring_buffer_nr_pages - get the number of buffer pages in the ring buffer - * @buffer: The ring_buffer to get the number of pages from - * @cpu: The cpu of the ring_buffer to get the number of pages from - * - * Returns the number of pages used by a per_cpu buffer of the ring buffer. - */ -size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu) -{ - return buffer->buffers[cpu]->nr_pages; -} - /** * ring_buffer_nr_dirty_pages - get the number of used pages in the ring buffer * @buffer: The ring_buffer to get the number of pages from -- cgit v1.2.3 From b54de55990b0467538c6bb33523b28816384958a Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Wed, 7 Aug 2024 17:06:12 +0100 Subject: net: ethtool: fix off-by-one error in max RSS context IDs Both ethtool_ops.rxfh_max_context_id and the default value used when it's not specified are supposed to be exclusive maxima (the former is documented as such; the latter, U32_MAX, cannot be used as an ID since it equals ETH_RXFH_CONTEXT_ALLOC), but xa_alloc() expects an inclusive maximum. Subtract one from 'limit' to produce an inclusive maximum, and pass that to xa_alloc(). Increase bnxt's max by one to prevent a (very minor) regression, as BNXT_MAX_ETH_RSS_CTX is an inclusive max. This is safe since bnxt is not actually hard-limited; BNXT_MAX_ETH_RSS_CTX is just a leftover from old driver code that managed context IDs itself. Rename rxfh_max_context_id to rxfh_max_num_contexts to make its semantics (hopefully) more obvious. Fixes: 847a8ab18676 ("net: ethtool: let the core choose RSS context IDs") Signed-off-by: Edward Cree Link: https://patch.msgid.link/5a2d11a599aa5b0cc6141072c01accfb7758650c.1723045898.git.ecree.xilinx@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- include/linux/ethtool.h | 10 +++++----- net/ethtool/ioctl.c | 5 +++-- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index ab8e3f197e7b..9dadc89378f0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -5290,7 +5290,7 @@ void bnxt_ethtool_free(struct bnxt *bp) const struct ethtool_ops bnxt_ethtool_ops = { .cap_link_lanes_supported = 1, .cap_rss_ctx_supported = 1, - .rxfh_max_context_id = BNXT_MAX_ETH_RSS_CTX, + .rxfh_max_num_contexts = BNXT_MAX_ETH_RSS_CTX + 1, .rxfh_indir_space = BNXT_MAX_RSS_TABLE_ENTRIES_P5, .rxfh_priv_size = sizeof(struct bnxt_rss_ctx), .supported_coalesce_params = ETHTOOL_COALESCE_USECS | diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 303fda54ef17..989c94eddb2b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -736,10 +736,10 @@ struct kernel_ethtool_ts_info { * @rxfh_key_space: same as @rxfh_indir_space, but for the key. * @rxfh_priv_size: size of the driver private data area the core should * allocate for an RSS context (in &struct ethtool_rxfh_context). - * @rxfh_max_context_id: maximum (exclusive) supported RSS context ID. If this - * is zero then the core may choose any (nonzero) ID, otherwise the core - * will only use IDs strictly less than this value, as the @rss_context - * argument to @create_rxfh_context and friends. + * @rxfh_max_num_contexts: maximum (exclusive) supported RSS context ID. + * If this is zero then the core may choose any (nonzero) ID, otherwise + * the core will only use IDs strictly less than this value, as the + * @rss_context argument to @create_rxfh_context and friends. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Modern drivers no @@ -954,7 +954,7 @@ struct ethtool_ops { u32 rxfh_indir_space; u16 rxfh_key_space; u16 rxfh_priv_size; - u32 rxfh_max_context_id; + u32 rxfh_max_num_contexts; u32 supported_coalesce_params; u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 8ca13208d240..a8e276ecf723 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1449,12 +1449,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, } if (ops->create_rxfh_context) { - u32 limit = ops->rxfh_max_context_id ?: U32_MAX; + u32 limit = ops->rxfh_max_num_contexts ?: U32_MAX; u32 ctx_id; /* driver uses new API, core allocates ID */ ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx, - XA_LIMIT(1, limit), GFP_KERNEL_ACCOUNT); + XA_LIMIT(1, limit - 1), + GFP_KERNEL_ACCOUNT); if (ret < 0) { kfree(ctx); goto out; -- cgit v1.2.3 From 5819e464a17587e6830cfab05f3e91a9a8753a41 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 8 Aug 2024 14:08:08 +1000 Subject: cpumask: Fix crash on updating CPU enabled mask The CPU enabled mask instead of the CPU possible mask should be used by set_cpu_enabled(). Otherwise, we run into crash due to write to the read-only CPU possible mask when vCPU is hot added on ARM64. (qemu) device_add host-arm-cpu,id=cpu1,socket-id=1 Unable to handle kernel write to read-only memory at virtual address ffff800080fa7190 : Call trace: register_cpu+0x1a4/0x2e8 arch_register_cpu+0x84/0xd8 acpi_processor_add+0x480/0x5b0 acpi_bus_attach+0x1c4/0x300 acpi_dev_for_one_check+0x3c/0x50 device_for_each_child+0x68/0xc8 acpi_dev_for_each_child+0x48/0x80 acpi_bus_attach+0x84/0x300 acpi_bus_scan+0x74/0x220 acpi_scan_rescan_bus+0x54/0x88 acpi_device_hotplug+0x208/0x478 acpi_hotplug_work_fn+0x2c/0x50 process_one_work+0x15c/0x3c0 worker_thread+0x2ec/0x400 kthread+0x120/0x130 ret_from_fork+0x10/0x20 Fix it by passing the CPU enabled mask instead of the CPU possible mask to set_cpu_enabled(). Fixes: 51c4767503d5 ("Merge tag 'bitmap-6.11-rc1' of https://github.com:/norov/linux") Signed-off-by: Gavin Shan Reviewed-by: Jonathan Cameron Signed-off-by: Yury Norov --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 801a7e524113..53158de44b83 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -1037,7 +1037,7 @@ void init_cpu_online(const struct cpumask *src); assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) -#define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_possible_mask, (enabled)) +#define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) -- cgit v1.2.3 From 42b0f8da3acc87953161baeb24f756936eb4d4b2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 31 Jul 2024 07:47:27 +0200 Subject: nsfs: fix ioctl declaration The kernel is writing an object of type __u64, so the ioctl has to be defined to _IOR(NSIO, 0x5, __u64) instead of _IO(NSIO, 0x5). Reported-by: Dmitry V. Levin Link: https://lore.kernel.org/r/20240730164554.GA18486@altlinux.org Signed-off-by: Christian Brauner --- include/uapi/linux/nsfs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index b133211331f6..5fad3d0fcd70 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -3,6 +3,7 @@ #define __LINUX_NSFS_H #include +#include #define NSIO 0xb7 @@ -16,7 +17,7 @@ /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) /* Get the id for a mount namespace */ -#define NS_GET_MNTNS_ID _IO(NSIO, 0x5) +#define NS_GET_MNTNS_ID _IOR(NSIO, 0x5, __u64) /* Translate pid from target pid namespace into the caller's pid namespace. */ #define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int) /* Return thread-group leader id of pid in the callers pid namespace. */ -- cgit v1.2.3 From 86509e38a80da34d7800985fa2be183475242c8c Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 9 Aug 2024 15:50:35 +0200 Subject: file: fix typo in take_fd() comment The explanatory comment above take_fd() contains a typo, fix that to not confuse readers. Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20240809135035.748109-1-minipli@grsecurity.net Signed-off-by: Christian Brauner --- include/linux/file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/file.h b/include/linux/file.h index 237931f20739..59b146a14dca 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -110,7 +110,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) - * return PTR_ERR(fd); + * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); -- cgit v1.2.3 From 8e5ced7804cb9184c4a23f8054551240562a8eda Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2024 17:01:40 +0100 Subject: netfs, ceph: Revert "netfs: Remove deprecated use of PG_private_2 as a second writeback flag" This reverts commit ae678317b95e760607c7b20b97c9cd4ca9ed6e1a. Revert the patch that removes the deprecated use of PG_private_2 in netfslib for the moment as Ceph is actually still using this to track data copied to the cache. Fixes: ae678317b95e ("netfs: Remove deprecated use of PG_private_2 as a second writeback flag") Reported-by: Max Kellermann Signed-off-by: David Howells cc: Ilya Dryomov cc: Xiubo Li cc: Jeff Layton cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org https: //lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk Signed-off-by: Christian Brauner --- fs/ceph/addr.c | 19 +++++- fs/netfs/buffered_read.c | 8 ++- fs/netfs/io.c | 144 +++++++++++++++++++++++++++++++++++++++++++ include/trace/events/netfs.h | 1 + 4 files changed, 170 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c16bc5250ef..73b5a07bf94d 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -498,6 +498,11 @@ const struct netfs_request_ops ceph_netfs_ops = { }; #ifdef CONFIG_CEPH_FSCACHE +static void ceph_set_page_fscache(struct page *page) +{ + folio_start_private_2(page_folio(page)); /* [DEPRECATED] */ +} + static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async) { struct inode *inode = priv; @@ -515,6 +520,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b ceph_fscache_write_terminated, inode, true, caching); } #else +static inline void ceph_set_page_fscache(struct page *page) +{ +} + static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) { } @@ -706,6 +715,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) len = wlen; set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); ceph_fscache_write_to_cache(inode, page_off, len, caching); if (IS_ENCRYPTED(inode)) { @@ -789,6 +800,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) return AOP_WRITEPAGE_ACTIVATE; } + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ + err = writepage_nounlock(page, wbc); if (err == -ERESTARTSYS) { /* direct memory reclaimer was killed by SIGKILL. return 0 @@ -1062,7 +1075,8 @@ get_more_pages: unlock_page(page); break; } - if (PageWriteback(page)) { + if (PageWriteback(page) || + PagePrivate2(page) /* [DEPRECATED] */) { if (wbc->sync_mode == WB_SYNC_NONE) { doutc(cl, "%p under writeback\n", page); unlock_page(page); @@ -1070,6 +1084,7 @@ get_more_pages: } doutc(cl, "waiting on writeback %p\n", page); wait_on_page_writeback(page); + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ } if (!clear_page_dirty_for_io(page)) { @@ -1254,6 +1269,8 @@ new_request: } set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); len += thp_size(page); } ceph_fscache_write_to_cache(inode, offset, len, caching); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index a688d4c75d99..424048f9ed1f 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -466,7 +466,7 @@ retry: if (!netfs_is_cache_enabled(ctx) && netfs_skip_folio_read(folio, pos, len, false)) { netfs_stat(&netfs_n_rh_write_zskip); - goto have_folio; + goto have_folio_no_wait; } rreq = netfs_alloc_request(mapping, file, @@ -507,6 +507,12 @@ retry: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); have_folio: + if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) { + ret = folio_wait_private_2_killable(folio); + if (ret < 0) + goto error; + } +have_folio_no_wait: *_folio = folio; _leave(" = 0"); return 0; diff --git a/fs/netfs/io.c b/fs/netfs/io.c index c93851b98368..c179a1c73fa7 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -98,6 +98,146 @@ static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete); } +/* + * [DEPRECATED] Deal with the completion of writing the data to the cache. We + * have to clear the PG_fscache bits on the folios involved and release the + * caller's ref. + * + * May be called in softirq mode and we inherit a ref from the caller. + */ +static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, + bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t unlocked = 0; + bool have_unlocked = false; + + rcu_read_lock(); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); + + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + if (xas_retry(&xas, folio)) + continue; + + /* We might have multiple writes from the same huge + * folio, but we mustn't unlock a folio more than once. + */ + if (have_unlocked && folio->index <= unlocked) + continue; + unlocked = folio_next_index(folio) - 1; + trace_netfs_folio(folio, netfs_folio_trace_end_copy); + folio_end_private_2(folio); + have_unlocked = true; + } + } + + rcu_read_unlock(); + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) /* [DEPRECATED] */ +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) { + netfs_stat(&netfs_n_rh_write_failed); + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_copy_to_cache); + } else { + netfs_stat(&netfs_n_rh_write_done); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); + + /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} + +/* + * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref + * from the caller. + */ +static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct netfs_io_subrequest *subreq, *next, *p; + struct iov_iter iter; + int ret; + + trace_netfs_rreq(rreq, netfs_rreq_trace_copy); + + /* We don't want terminating writes trying to wake us up whilst we're + * still going through the list. + */ + atomic_inc(&rreq->nr_copy_ops); + + list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + list_del_init(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_no_copy); + } + } + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + /* Amalgamate adjacent writes */ + while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + next = list_next_entry(subreq, rreq_link); + if (next->start != subreq->start + subreq->len) + break; + subreq->len += next->len; + list_del_init(&next->rreq_link); + netfs_put_subrequest(next, false, + netfs_sreq_trace_put_merged); + } + + ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, + subreq->len, rreq->i_size, true); + if (ret < 0) { + trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); + trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); + continue; + } + + iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages, + subreq->start, subreq->len); + + atomic_inc(&rreq->nr_copy_ops); + netfs_stat(&netfs_n_rh_write); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); + trace_netfs_sreq(subreq, netfs_sreq_trace_write); + cres->ops->write(cres, subreq->start, &iter, + netfs_rreq_copy_terminated, subreq); + } + + /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, false); +} + +static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */ +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_rreq_do_write_to_cache(rreq); +} + +static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */ +{ + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); +} + /* * Handle a short read. */ @@ -275,6 +415,10 @@ again: clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) && + test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) + return netfs_rreq_write_to_cache(rreq); + netfs_rreq_completed(rreq, was_async); } diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index da23484268df..24ec3434d32e 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -145,6 +145,7 @@ EM(netfs_folio_trace_clear_g, "clear-g") \ EM(netfs_folio_trace_clear_s, "clear-s") \ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ + EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ EM(netfs_folio_trace_kill, "kill") \ EM(netfs_folio_trace_kill_cc, "kill-cc") \ -- cgit v1.2.3 From 7b589a9b45ae32aa9d7bece597490e141198d7a6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Aug 2024 19:38:46 +0100 Subject: netfs: Fix handling of USE_PGPRIV2 and WRITE_TO_CACHE flags The NETFS_RREQ_USE_PGPRIV2 and NETFS_RREQ_WRITE_TO_CACHE flags aren't used correctly. The problem is that we try to set them up in the request initialisation, but we the cache may be in the process of setting up still, and so the state may not be correct. Further, we secondarily sample the cache state and make contradictory decisions later. The issue arises because we set up the cache resources, which allows the cache's ->prepare_read() to switch on NETFS_SREQ_COPY_TO_CACHE - which triggers cache writing even if we didn't set the flags when allocating. Fix this in the following way: (1) Drop NETFS_ICTX_USE_PGPRIV2 and instead set NETFS_RREQ_USE_PGPRIV2 in ->init_request() rather than trying to juggle that in netfs_alloc_request(). (2) Repurpose NETFS_RREQ_USE_PGPRIV2 to merely indicate that if caching is to be done, then PG_private_2 is to be used rather than only setting it if we decide to cache and then having netfs_rreq_unlock_folios() set the non-PG_private_2 writeback-to-cache if it wasn't set. (3) Split netfs_rreq_unlock_folios() into two functions, one of which contains the deprecated code for using PG_private_2 to avoid accidentally doing the writeback path - and always use it if USE_PGPRIV2 is set. (4) As NETFS_ICTX_USE_PGPRIV2 is removed, make netfs_write_begin() always wait for PG_private_2. This function is deprecated and only used by ceph anyway, and so label it so. (5) Drop the NETFS_RREQ_WRITE_TO_CACHE flag and use fscache_operation_valid() on the cache_resources instead. This has the advantage of picking up the result of netfs_begin_cache_read() and fscache_begin_write_operation() - which are called after the object is initialised and will wait for the cache to come to a usable state. Just reverting ae678317b95e[1] isn't a sufficient fix, so this need to be applied on top of that. Without this as well, things like: rcu: INFO: rcu_sched detected expedited stalls on CPUs/tasks: { and: WARNING: CPU: 13 PID: 3621 at fs/ceph/caps.c:3386 may happen, along with some UAFs due to PG_private_2 not getting used to wait on writeback completion. Fixes: 2ff1e97587f4 ("netfs: Replace PG_fscache by setting folio->private and marking dirty") Reported-by: Max Kellermann Signed-off-by: David Howells cc: Ilya Dryomov cc: Xiubo Li cc: Hristo Venev cc: Jeff Layton cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org Link: https://lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk/ [1] Link: https://lore.kernel.org/r/1173209.1723152682@warthog.procyon.org.uk Signed-off-by: Christian Brauner --- fs/ceph/addr.c | 3 ++ fs/ceph/inode.c | 2 - fs/netfs/buffered_read.c | 125 ++++++++++++++++++++++++++++++++++++------- fs/netfs/objects.c | 10 ---- fs/netfs/write_issue.c | 4 +- fs/nfs/fscache.c | 2 + fs/nfs/fscache.h | 2 - include/linux/netfs.h | 3 -- include/trace/events/netfs.h | 1 + 9 files changed, 116 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 73b5a07bf94d..cc0a2240de98 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -424,6 +424,9 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) struct ceph_netfs_request_data *priv; int ret = 0; + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); + if (rreq->origin != NETFS_READAHEAD) return 0; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 8f8de8f33abb..71cd70514efa 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -577,8 +577,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) /* Set parameters for the netfs library */ netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &ci->netfs.flags); spin_lock_init(&ci->i_ceph_lock); diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 424048f9ed1f..27c750d39476 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -9,6 +9,97 @@ #include #include "internal.h" +/* + * [DEPRECATED] Unlock the folios in a read operation for when the filesystem + * is using PG_private_2 and direct writing to the cache from here rather than + * marking the page for writeback. + * + * Note that we don't touch folio->private in this code. + */ +static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq, + size_t *account) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + loff_t pg_end; + bool pg_failed = false; + bool folio_started = false; + + if (xas_retry(&xas, folio)) + continue; + + pg_end = folio_pos(folio) + folio_size(folio) - 1; + + for (;;) { + loff_t sreq_end; + + if (!subreq) { + pg_failed = true; + break; + } + + if (!folio_started && + test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) && + fscache_operation_valid(&rreq->cache_resources)) { + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + folio_started = true; + } + + pg_failed |= subreq_failed; + sreq_end = subreq->start + subreq->len - 1; + if (pg_end < sreq_end) + break; + + *account += subreq->transferred; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + + if (pg_end == sreq_end) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio->index == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); +} + /* * Unlock the folios in a read operation. We need to set PG_writeback on any * folios we're going to write back before we unlock them. @@ -35,6 +126,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } } + /* Handle deprecated PG_private_2 case. */ + if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + netfs_rreq_unlock_folios_pgpriv2(rreq, &account); + goto out; + } + /* Walk through the pagecache and the I/O request lists simultaneously. * We may have a mixture of cached and uncached sections and we only * really want to write out the uncached sections. This is slightly @@ -52,7 +149,6 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) loff_t pg_end; bool pg_failed = false; bool wback_to_cache = false; - bool folio_started = false; if (xas_retry(&xas, folio)) continue; @@ -66,17 +162,8 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) pg_failed = true; break; } - if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, - &subreq->flags)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folio_started = true; - } - } else { - wback_to_cache |= - test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - } + + wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); pg_failed |= subreq_failed; sreq_end = subreq->start + subreq->len - 1; if (pg_end < sreq_end) @@ -124,6 +211,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } rcu_read_unlock(); +out: task_io_account_read(account); if (rreq->netfs_ops->done) rreq->netfs_ops->done(rreq); @@ -395,7 +483,7 @@ zero_out: } /** - * netfs_write_begin - Helper to prepare for writing + * netfs_write_begin - Helper to prepare for writing [DEPRECATED] * @ctx: The netfs context * @file: The file to read from * @mapping: The mapping to read from @@ -426,6 +514,9 @@ zero_out: * inode before calling this. * * This is usable whether or not caching is enabled. + * + * Note that this should be considered deprecated and netfs_perform_write() + * used instead. */ int netfs_write_begin(struct netfs_inode *ctx, struct file *file, struct address_space *mapping, @@ -507,11 +598,9 @@ retry: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); have_folio: - if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) { - ret = folio_wait_private_2_killable(folio); - if (ret < 0) - goto error; - } + ret = folio_wait_private_2_killable(folio); + if (ret < 0) + goto error; have_folio_no_wait: *_folio = folio; _leave(" = 0"); diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index f4a642727479..0294df70c3ff 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -24,10 +24,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct netfs_io_request *rreq; mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool; struct kmem_cache *cache = mempool->pool_data; - bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE || - origin == NETFS_DIO_READ || - origin == NETFS_DIO_WRITE); - bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx); int ret; for (;;) { @@ -56,12 +52,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, refcount_set(&rreq->ref, 1); __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - if (cached) { - __set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) - /* Filesystem uses deprecated PG_private_2 marking. */ - __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); - } if (file && file->f_flags & O_NONBLOCK) __set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags); if (rreq->netfs_ops->init_request) { diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 9258d30cffe3..3f7e37e50c7d 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -94,6 +94,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, { struct netfs_io_request *wreq; struct netfs_inode *ictx; + bool is_buffered = (origin == NETFS_WRITEBACK || + origin == NETFS_WRITETHROUGH); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -102,7 +104,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, _enter("R=%x", wreq->debug_id); ictx = netfs_inode(wreq->inode); - if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags)) + if (is_buffered && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); wreq->contiguity = wreq->start; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 7202ce84d0eb..bf29a65c5027 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -265,6 +265,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi { rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); return 0; } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index fbed0027996f..e8adae1bc260 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -81,8 +81,6 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) { netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &nfsi->netfs.flags); } extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr); extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5d0288938cc2..983816608f15 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -73,8 +73,6 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark - * write to cache on read */ }; /* @@ -269,7 +267,6 @@ struct netfs_io_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ -#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 24ec3434d32e..606b4a0f92da 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -51,6 +51,7 @@ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_set_pause, "PAUSE ") \ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ + EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ -- cgit v1.2.3 From fdad456cbcca739bae1849549c7a999857c56f88 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Sun, 28 Jul 2024 19:46:11 +0800 Subject: bpf: Fix updating attached freplace prog in prog_array map MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The commit f7866c358733 ("bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT") fixed a NULL pointer dereference panic, but didn't fix the issue that fails to update attached freplace prog to prog_array map. Since commit 1c123c567fb1 ("bpf: Resolve fext program type when checking map compatibility"), freplace prog and its target prog are able to tail call each other. And the commit 3aac1ead5eb6 ("bpf: Move prog->aux->linked_prog and trampoline into bpf_link on attach") sets prog->aux->dst_prog as NULL after attaching freplace prog to its target prog. After loading freplace the prog_array's owner type is BPF_PROG_TYPE_SCHED_CLS. Then, after attaching freplace its prog->aux->dst_prog is NULL. Then, while updating freplace in prog_array the bpf_prog_map_compatible() incorrectly returns false because resolve_prog_type() returns BPF_PROG_TYPE_EXT instead of BPF_PROG_TYPE_SCHED_CLS. After this patch the resolve_prog_type() returns BPF_PROG_TYPE_SCHED_CLS and update to prog_array can succeed. Fixes: f7866c358733 ("bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT") Cc: Toke Høiland-Jørgensen Cc: Martin KaFai Lau Acked-by: Yonghong Song Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20240728114612.48486-2-leon.hwang@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6503c85b10a3..7b776dae36e5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -856,8 +856,8 @@ static inline u32 type_flag(u32 type) /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { - return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ? - prog->aux->dst_prog->type : prog->type; + return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) -- cgit v1.2.3 From 92567a5f92bc947fb7aa4351979db1b7b71a554c Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 8 Aug 2024 22:06:19 +0800 Subject: iommu: Remove unused declaration iommu_sva_unbind_gpasid() Commit 0c9f17877891 ("iommu: Remove guest pasid related interfaces and definitions") removed the implementation but leave declaration. Signed-off-by: Yue Haibing Reviewed-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20240808140619.2498535-1-yuehaibing@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 4d47f2c33311..04cbdae0052e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -795,8 +795,6 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, -- cgit v1.2.3 From 58a63729c957621f1990c3494c702711188ca347 Mon Sep 17 00:00:00 2001 From: Long Li Date: Fri, 9 Aug 2024 08:58:58 -0700 Subject: net: mana: Fix doorbell out of order violation and avoid unnecessary doorbell rings After napi_complete_done() is called when NAPI is polling in the current process context, another NAPI may be scheduled and start running in softirq on another CPU and may ring the doorbell before the current CPU does. When combined with unnecessary rings when there is no need to arm the CQ, it triggers error paths in the hardware. This patch fixes this by calling napi_complete_done() after doorbell rings. It limits the number of unnecessary rings when there is no need to arm. MANA hardware specifies that there must be one doorbell ring every 8 CQ wraparounds. This driver guarantees one doorbell ring as soon as the number of consumed CQEs exceeds 4 CQ wraparounds. In practical workloads, the 4 CQ wraparounds proves to be big enough that it rarely exceeds this limit before all the napi weight is consumed. To implement this, add a per-CQ counter cq->work_done_since_doorbell, and make sure the CQ is armed as soon as passing 4 wraparounds of the CQ. Cc: stable@vger.kernel.org Fixes: e1b5683ff62e ("net: mana: Move NAPI from EQ to CQ") Reviewed-by: Haiyang Zhang Signed-off-by: Long Li Link: https://patch.msgid.link/1723219138-29887-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/microsoft/mana/mana_en.c | 24 +++++++++++++++--------- include/net/mana/mana.h | 1 + 2 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index ae717d06e66f..39f56973746d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1792,7 +1792,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; - u8 arm_bit; int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1803,16 +1802,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_poll_tx_cq(cq); w = cq->work_done; - - if (w < cq->budget && - napi_complete_done(&cq->napi, w)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; + cq->work_done_since_doorbell += w; + + if (w < cq->budget) { + mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); + cq->work_done_since_doorbell = 0; + napi_complete_done(&cq->napi, w); + } else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + /* MANA hardware requires at least one doorbell ring every 8 + * wraparounds of CQ even if there is no need to arm the CQ. + * This driver rings the doorbell as soon as we have exceeded + * 4 wraparounds. + */ + mana_gd_ring_cq(gdma_queue, 0); + cq->work_done_since_doorbell = 0; } - mana_gd_ring_cq(gdma_queue, arm_bit); - return w; } diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6439fd8b437b..7caa334f4888 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -275,6 +275,7 @@ struct mana_cq { /* NAPI data */ struct napi_struct napi; int work_done; + int work_done_since_doorbell; int budget; }; -- cgit v1.2.3 From 779bac9994452f6a894524f70c00cfb0cd4b6364 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Aug 2024 15:08:04 +0200 Subject: Revert "ACPI: EC: Evaluate orphan _REG under EC device" This reverts commit 0e6b6dedf168 ("Revert "ACPI: EC: Evaluate orphan _REG under EC device") because the problem addressed by it will be addressed differently in what follows. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hans de Goede Cc: All applicable Link: https://patch.msgid.link/3236716.5fSG56mABF@rjwysocki.net --- drivers/acpi/acpica/acevents.h | 4 ---- drivers/acpi/acpica/evregion.c | 6 ++++- drivers/acpi/acpica/evxfregn.c | 54 ------------------------------------------ drivers/acpi/ec.c | 3 --- include/acpi/acpixf.h | 4 ---- 5 files changed, 5 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index 2133085deda7..ddd072cbc738 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -191,10 +191,6 @@ void acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, acpi_adr_space_type space_id, u32 function); -void -acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node, - acpi_adr_space_type space_id); - acpi_status acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function); diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index dc6004daf624..18fdf2bc2d49 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -20,6 +20,10 @@ extern u8 acpi_gbl_default_address_spaces[]; /* Local prototypes */ +static void +acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, + acpi_adr_space_type space_id); + static acpi_status acpi_ev_reg_run(acpi_handle obj_handle, u32 level, void *context, void **return_value); @@ -814,7 +818,7 @@ acpi_ev_reg_run(acpi_handle obj_handle, * ******************************************************************************/ -void +static void acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, acpi_adr_space_type space_id) { diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 624361a5f34d..3197e6303c5b 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -306,57 +306,3 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) } ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods) - -/******************************************************************************* - * - * FUNCTION: acpi_execute_orphan_reg_method - * - * PARAMETERS: device - Handle for the device - * space_id - The address space ID - * - * RETURN: Status - * - * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI - * device. This is a _REG method that has no corresponding region - * within the device's scope. - * - ******************************************************************************/ -acpi_status -acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id) -{ - struct acpi_namespace_node *node; - acpi_status status; - - ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method); - - /* Parameter validation */ - - if (!device) { - return_ACPI_STATUS(AE_BAD_PARAMETER); - } - - status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); - if (ACPI_FAILURE(status)) { - return_ACPI_STATUS(status); - } - - /* Convert and validate the device handle */ - - node = acpi_ns_validate_handle(device); - if (node) { - - /* - * If an "orphan" _REG method is present in the device's scope - * for the given address space ID, run it. - */ - - acpi_ev_execute_orphan_reg_method(node, space_id); - } else { - status = AE_BAD_PARAMETER; - } - - (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); - return_ACPI_STATUS(status); -} - -ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 299ec653388c..68dd17f96f63 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1507,9 +1507,6 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); - if (scope_handle != ec->handle) - acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC); - set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 80dc36f9d527..94d0fc3bd412 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -662,10 +662,6 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)) -ACPI_EXTERNAL_RETURN_STATUS(acpi_status - acpi_execute_orphan_reg_method(acpi_handle device, - acpi_adr_space_type - space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_remove_address_space_handler(acpi_handle device, -- cgit v1.2.3 From cdf65d73e001fde600b18d7e45afadf559425ce5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 12 Aug 2024 15:11:42 +0200 Subject: ACPICA: Add a depth argument to acpi_execute_reg_methods() A subsequent change will need to pass a depth argument to acpi_execute_reg_methods(), so prepare that function for it. No intentional functional changes. Signed-off-by: Rafael J. Wysocki Reviewed-by: Hans de Goede Cc: All applicable Link: https://patch.msgid.link/8451567.NyiUUSuA9g@rjwysocki.net --- drivers/acpi/acpica/acevents.h | 2 +- drivers/acpi/acpica/evregion.c | 6 ++++-- drivers/acpi/acpica/evxfregn.c | 10 +++++++--- drivers/acpi/ec.c | 2 +- include/acpi/acpixf.h | 1 + 5 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index ddd072cbc738..1c5218b79fc2 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -188,7 +188,7 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj, u8 acpi_ns_is_locked); void -acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth, acpi_adr_space_type space_id, u32 function); acpi_status diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 18fdf2bc2d49..cf53b9535f18 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -65,6 +65,7 @@ acpi_status acpi_ev_initialize_op_regions(void) acpi_gbl_default_address_spaces [i])) { acpi_ev_execute_reg_methods(acpi_gbl_root_node, + ACPI_UINT32_MAX, acpi_gbl_default_address_spaces [i], ACPI_REG_CONNECT); } @@ -672,6 +673,7 @@ cleanup1: * FUNCTION: acpi_ev_execute_reg_methods * * PARAMETERS: node - Namespace node for the device + * max_depth - Depth to which search for _REG * space_id - The address space ID * function - Passed to _REG: On (1) or Off (0) * @@ -683,7 +685,7 @@ cleanup1: ******************************************************************************/ void -acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth, acpi_adr_space_type space_id, u32 function) { struct acpi_reg_walk_info info; @@ -717,7 +719,7 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, * regions and _REG methods. (i.e. handlers must be installed for all * regions of this Space ID before we can run any _REG methods) */ - (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX, + (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, max_depth, ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run, NULL, &info, NULL); diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 3197e6303c5b..95f78383bbdb 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -85,7 +85,8 @@ acpi_install_address_space_handler_internal(acpi_handle device, /* Run all _REG methods for this address space */ if (run_reg) { - acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT); + acpi_ev_execute_reg_methods(node, ACPI_UINT32_MAX, space_id, + ACPI_REG_CONNECT); } unlock_and_exit: @@ -263,6 +264,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler) * FUNCTION: acpi_execute_reg_methods * * PARAMETERS: device - Handle for the device + * max_depth - Depth to which search for _REG * space_id - The address space ID * * RETURN: Status @@ -271,7 +273,8 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler) * ******************************************************************************/ acpi_status -acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) +acpi_execute_reg_methods(acpi_handle device, u32 max_depth, + acpi_adr_space_type space_id) { struct acpi_namespace_node *node; acpi_status status; @@ -296,7 +299,8 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) /* Run all _REG methods for this address space */ - acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT); + acpi_ev_execute_reg_methods(node, max_depth, space_id, + ACPI_REG_CONNECT); } else { status = AE_BAD_PARAMETER; } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 68dd17f96f63..d9c12db80f11 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1506,7 +1506,7 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, } if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { - acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); + acpi_execute_reg_methods(scope_handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 94d0fc3bd412..9f1c1d225e32 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -660,6 +660,7 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status void *context)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_execute_reg_methods(acpi_handle device, + u32 nax_depth, acpi_adr_space_type space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status -- cgit v1.2.3 From 2a0629834cd82f05d424bbc193374f9a43d1f87d Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Fri, 9 Aug 2024 11:16:28 +0800 Subject: vfs: Don't evict inode under the inode lru traversing context MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The inode reclaiming process(See function prune_icache_sb) collects all reclaimable inodes and mark them with I_FREEING flag at first, at that time, other processes will be stuck if they try getting these inodes (See function find_inode_fast), then the reclaiming process destroy the inodes by function dispose_list(). Some filesystems(eg. ext4 with ea_inode feature, ubifs with xattr) may do inode lookup in the inode evicting callback function, if the inode lookup is operated under the inode lru traversing context, deadlock problems may happen. Case 1: In function ext4_evict_inode(), the ea inode lookup could happen if ea_inode feature is enabled, the lookup process will be stuck under the evicting context like this: 1. File A has inode i_reg and an ea inode i_ea 2. getfattr(A, xattr_buf) // i_ea is added into lru // lru->i_ea 3. Then, following three processes running like this: PA PB echo 2 > /proc/sys/vm/drop_caches shrink_slab prune_dcache_sb // i_reg is added into lru, lru->i_ea->i_reg prune_icache_sb list_lru_walk_one inode_lru_isolate i_ea->i_state |= I_FREEING // set inode state inode_lru_isolate __iget(i_reg) spin_unlock(&i_reg->i_lock) spin_unlock(lru_lock) rm file A i_reg->nlink = 0 iput(i_reg) // i_reg->nlink is 0, do evict ext4_evict_inode ext4_xattr_delete_inode ext4_xattr_inode_dec_ref_all ext4_xattr_inode_iget ext4_iget(i_ea->i_ino) iget_locked find_inode_fast __wait_on_freeing_inode(i_ea) ----→ AA deadlock dispose_list // cannot be executed by prune_icache_sb wake_up_bit(&i_ea->i_state) Case 2: In deleted inode writing function ubifs_jnl_write_inode(), file deleting process holds BASEHD's wbuf->io_mutex while getting the xattr inode, which could race with inode reclaiming process(The reclaiming process could try locking BASEHD's wbuf->io_mutex in inode evicting function), then an ABBA deadlock problem would happen as following: 1. File A has inode ia and a xattr(with inode ixa), regular file B has inode ib and a xattr. 2. getfattr(A, xattr_buf) // ixa is added into lru // lru->ixa 3. Then, following three processes running like this: PA PB PC echo 2 > /proc/sys/vm/drop_caches shrink_slab prune_dcache_sb // ib and ia are added into lru, lru->ixa->ib->ia prune_icache_sb list_lru_walk_one inode_lru_isolate ixa->i_state |= I_FREEING // set inode state inode_lru_isolate __iget(ib) spin_unlock(&ib->i_lock) spin_unlock(lru_lock) rm file B ib->nlink = 0 rm file A iput(ia) ubifs_evict_inode(ia) ubifs_jnl_delete_inode(ia) ubifs_jnl_write_inode(ia) make_reservation(BASEHD) // Lock wbuf->io_mutex ubifs_iget(ixa->i_ino) iget_locked find_inode_fast __wait_on_freeing_inode(ixa) | iput(ib) // ib->nlink is 0, do evict | ubifs_evict_inode | ubifs_jnl_delete_inode(ib) ↓ ubifs_jnl_write_inode ABBA deadlock ←-----make_reservation(BASEHD) dispose_list // cannot be executed by prune_icache_sb wake_up_bit(&ixa->i_state) Fix the possible deadlock by using new inode state flag I_LRU_ISOLATING to pin the inode in memory while inode_lru_isolate() reclaims its pages instead of using ordinary inode reference. This way inode deletion cannot be triggered from inode_lru_isolate() thus avoiding the deadlock. evict() is made to wait for I_LRU_ISOLATING to be cleared before proceeding with inode cleanup. Link: https://lore.kernel.org/all/37c29c42-7685-d1f0-067d-63582ffac405@huaweicloud.com/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=219022 Fixes: e50e5129f384 ("ext4: xattr-in-inode support") Fixes: 7959cf3a7506 ("ubifs: journal: Handle xattrs like files") Cc: stable@vger.kernel.org Signed-off-by: Zhihao Cheng Link: https://lore.kernel.org/r/20240809031628.1069873-1-chengzhihao@huaweicloud.com Reviewed-by: Jan Kara Suggested-by: Jan Kara Suggested-by: Mateusz Guzik Signed-off-by: Christian Brauner --- fs/inode.c | 39 +++++++++++++++++++++++++++++++++++++-- include/linux/fs.h | 5 +++++ 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/fs/inode.c b/fs/inode.c index 86670941884b..10c4619faeef 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -488,6 +488,39 @@ static void inode_lru_list_del(struct inode *inode) this_cpu_dec(nr_unused); } +static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode->i_state |= I_LRU_ISOLATING; +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); + inode->i_state &= ~I_LRU_ISOLATING; + smp_mb(); + wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (inode->i_state & I_LRU_ISOLATING) { + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_LRU_ISOLATING); + } + spin_unlock(&inode->i_lock); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add @@ -657,6 +690,8 @@ static void evict(struct inode *inode) inode_sb_list_del(inode); + inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { @@ -867,7 +902,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } - iput(inode); + inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } diff --git a/include/linux/fs.h b/include/linux/fs.h index fd34b5755c0b..fb0426f349fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2392,6 +2392,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2415,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) -- cgit v1.2.3 From bcc954c6caba01fca143162d5fbb90e46aa1ad80 Mon Sep 17 00:00:00 2001 From: Ryo Takakura Date: Mon, 12 Aug 2024 16:27:03 +0900 Subject: printk/panic: Allow cpu backtraces to be written into ringbuffer during panic commit 779dbc2e78d7 ("printk: Avoid non-panic CPUs writing to ringbuffer") disabled non-panic CPUs to further write messages to ringbuffer after panicked. Since the commit, non-panicked CPU's are not allowed to write to ring buffer after panicked and CPU backtrace which is triggered after panicked to sample non-panicked CPUs' backtrace no longer serves its function as it has nothing to print. Fix the issue by allowing non-panicked CPUs to write into ringbuffer while CPU backtrace is in flight. Fixes: 779dbc2e78d7 ("printk: Avoid non-panic CPUs writing to ringbuffer") Signed-off-by: Ryo Takakura Reviewed-by: Petr Mladek Link: https://lore.kernel.org/r/20240812072703.339690-1-takakura@valinux.co.jp Signed-off-by: Petr Mladek --- include/linux/panic.h | 1 + kernel/panic.c | 8 +++++++- kernel/printk/printk.c | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/panic.h b/include/linux/panic.h index 3130e0b5116b..54d90b6c5f47 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -16,6 +16,7 @@ extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void); +extern bool panic_triggering_all_cpu_backtrace; extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; diff --git a/kernel/panic.c b/kernel/panic.c index f861bedc1925..2a0449144f82 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -64,6 +64,8 @@ unsigned long panic_on_taint; bool panic_on_taint_nousertaint = false; static unsigned int warn_limit __read_mostly; +bool panic_triggering_all_cpu_backtrace; + int panic_timeout = CONFIG_PANIC_TIMEOUT; EXPORT_SYMBOL_GPL(panic_timeout); @@ -253,8 +255,12 @@ void check_panic_on_warn(const char *origin) */ static void panic_other_cpus_shutdown(bool crash_kexec) { - if (panic_print & PANIC_PRINT_ALL_CPU_BT) + if (panic_print & PANIC_PRINT_ALL_CPU_BT) { + /* Temporary allow non-panic CPUs to write their backtraces. */ + panic_triggering_all_cpu_backtrace = true; trigger_all_cpu_backtrace(); + panic_triggering_all_cpu_backtrace = false; + } /* * Note that smp_send_stop() is the usual SMP shutdown function, diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 054c0e7784fd..c22b07049c38 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2316,7 +2316,7 @@ asmlinkage int vprintk_emit(int facility, int level, * non-panic CPUs are generating any messages, they will be * silently dropped. */ - if (other_cpu_in_panic()) + if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace) return 0; if (level == LOGLEVEL_SCHED) { -- cgit v1.2.3 From 66155de93bcf4f2967e602a4b3bf7ebe58f34b11 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 9 Aug 2024 12:02:58 -0700 Subject: KVM: x86: Disallow read-only memslots for SEV-ES and SEV-SNP (and TDX) Disallow read-only memslots for SEV-{ES,SNP} VM types, as KVM can't directly emulate instructions for ES/SNP, and instead the guest must explicitly request emulation. Unless the guest explicitly requests emulation without accessing memory, ES/SNP relies on KVM creating an MMIO SPTE, with the subsequent #NPF being reflected into the guest as a #VC. But for read-only memslots, KVM deliberately doesn't create MMIO SPTEs, because except for ES/SNP, doing so requires setting reserved bits in the SPTE, i.e. the SPTE can't be readable while also generating a #VC on writes. Because KVM never creates MMIO SPTEs and jumps directly to emulation, the guest never gets a #VC. And since KVM simply resumes the guest if ES/SNP guests trigger emulation, KVM effectively puts the vCPU into an infinite #NPF loop if the vCPU attempts to write read-only memory. Disallow read-only memory for all VMs with protected state, i.e. for upcoming TDX VMs as well as ES/SNP VMs. For TDX, it's actually possible to support read-only memory, as TDX uses EPT Violation #VE to reflect the fault into the guest, e.g. KVM could configure read-only SPTEs with RX protections and SUPPRESS_VE=0. But there is no strong use case for supporting read-only memslots on TDX, e.g. the main historical usage is to emulate option ROMs, but TDX disallows executing from shared memory. And if someone comes along with a legitimate, strong use case, the restriction can always be lifted for TDX. Don't bother trying to retroactively apply the restriction to SEV-ES VMs that are created as type KVM_X86_DEFAULT_VM. Read-only memslots can't possibly work for SEV-ES, i.e. disallowing such memslots is really just means reporting an error to userspace instead of silently hanging vCPUs. Trying to deal with the ordering between KVM_SEV_INIT and memslot creation isn't worth the marginal benefit it would provide userspace. Fixes: 26c44aa9e076 ("KVM: SEV: define VM types for SEV and SEV-ES") Fixes: 1dfe571c12cf ("KVM: SEV: Add initial SEV-SNP support") Cc: Peter Gonda Cc: Michael Roth Cc: Vishal Annapurve Cc: Ackerly Tng Signed-off-by: Sean Christopherson Message-ID: <20240809190319.1710470-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 ++ include/linux/kvm_host.h | 7 +++++++ virt/kvm/kvm_main.c | 5 ++--- 3 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 94e7b5a4fafe..4a68cb3eba78 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2192,6 +2192,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, #define kvm_arch_has_private_mem(kvm) false #endif +#define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state) + static inline u16 kvm_read_ldt(void) { u16 ldt; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 79a6b1a63027..b23c6d48392f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -715,6 +715,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm) } #endif +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 92901656a0d4..cb2b78e92910 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1578,15 +1578,14 @@ static int check_memory_region_flags(struct kvm *kvm, if (mem->flags & KVM_MEM_GUEST_MEMFD) valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; -#ifdef CONFIG_HAVE_KVM_READONLY_MEM /* * GUEST_MEMFD is incompatible with read-only memslots, as writes to * read-only memslots have emulated MMIO, not page fault, semantics, * and KVM doesn't allow emulated MMIO for private memory. */ - if (!(mem->flags & KVM_MEM_GUEST_MEMFD)) + if (kvm_arch_has_readonly_mem(kvm) && + !(mem->flags & KVM_MEM_GUEST_MEMFD)) valid_flags |= KVM_MEM_READONLY; -#endif if (mem->flags & ~valid_flags) return -EINVAL; -- cgit v1.2.3 From 1c0e5881691a787a9399a99bff4d56ead6e75e91 Mon Sep 17 00:00:00 2001 From: Amit Shah Date: Wed, 14 Aug 2024 10:31:13 +0200 Subject: KVM: SEV: uapi: fix typo in SEV_RET_INVALID_CONFIG "INVALID" is misspelt in "SEV_RET_INAVLID_CONFIG". Since this is part of the UAPI, keep the current definition and add a new one with the fix. Fix-suggested-by: Marc Zyngier Signed-off-by: Amit Shah Message-ID: <20240814083113.21622-1-amit@kernel.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/psp-sev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 2289b7c76c59..832c15d9155b 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -51,6 +51,7 @@ typedef enum { SEV_RET_INVALID_PLATFORM_STATE, SEV_RET_INVALID_GUEST_STATE, SEV_RET_INAVLID_CONFIG, + SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG, SEV_RET_INVALID_LEN, SEV_RET_ALREADY_OWNED, SEV_RET_INVALID_CERTIFICATE, -- cgit v1.2.3 From 71833e79a42178d8a50b5081c98c78ace9325628 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 14 Aug 2024 13:16:49 +0100 Subject: i2c: Use IS_REACHABLE() for substituting empty ACPI functions Replace IS_ENABLED() with IS_REACHABLE() to substitute empty stubs for: i2c_acpi_get_i2c_resource() i2c_acpi_client_count() i2c_acpi_find_bus_speed() i2c_acpi_new_device_by_fwnode() i2c_adapter *i2c_acpi_find_adapter_by_handle() i2c_acpi_waive_d0_probe() commit f17c06c6608a ("i2c: Fix conditional for substituting empty ACPI functions") partially fixed this conditional to depend on CONFIG_I2C, but used IS_ENABLED(), which is wrong since CONFIG_I2C is tristate. CONFIG_ACPI is boolean but let's also change it to use IS_REACHABLE() to future-proof it against becoming tristate. Somehow despite testing various combinations of CONFIG_I2C and CONFIG_ACPI we missed the combination CONFIG_I2C=m, CONFIG_ACPI=y. Signed-off-by: Richard Fitzgerald Fixes: f17c06c6608a ("i2c: Fix conditional for substituting empty ACPI functions") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408141333.gYnaitcV-lkp@intel.com/ Reviewed-by: Takashi Iwai Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7eedd0c662da..377def497298 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1066,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev, struct acpi_resource; struct acpi_resource_i2c_serialbus; -#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_I2C) +#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); -- cgit v1.2.3 From 924fc22c282edbf93869b150d9e1b47e0b10485e Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 31 Jul 2024 09:44:57 +0200 Subject: firmware: qcom: qseecom: remove unused functions qseecom_scm_dev(), qseecom_dma_alloc() and qseecom_dma_free() are no longer used following the conversion to using tzmem. Remove them. Fixes: 6612103ec35a ("firmware: qcom: qseecom: convert to using the TZ allocator") Reviewed-by: Andrew Halaney Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20240731-tzmem-efivars-fix-v2-2-f0e84071ec07@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/firmware/qcom/qcom_qseecom.h | 45 ------------------------------ 1 file changed, 45 deletions(-) (limited to 'include') diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 1dc5b3b50aa9..3387897bf368 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -25,51 +25,6 @@ struct qseecom_client { u32 app_id; }; -/** - * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. - * @client: The QSEECOM client device. - * - * Returns the SCM device under which the provided QSEECOM client device - * operates. This function is intended to be used for DMA allocations. - */ -static inline struct device *qseecom_scm_dev(struct qseecom_client *client) -{ - return client->aux_dev.dev.parent->parent; -} - -/** - * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. - * @client: The QSEECOM client to allocate the memory for. - * @size: The number of bytes to allocate. - * @dma_handle: Pointer to where the DMA address should be stored. - * @gfp: Allocation flags. - * - * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for - * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. - */ -static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) -{ - return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); -} - -/** - * dma_free_coherent() - Free QSEECOM DMA memory. - * @client: The QSEECOM client for which the memory has been allocated. - * @size: The number of bytes allocated. - * @cpu_addr: Virtual memory address to free. - * @dma_handle: DMA memory address to free. - * - * Wrapper function for dma_free_coherent(), freeing memory previously - * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for - * details. - */ -static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, - void *cpu_addr, dma_addr_t dma_handle) -{ - return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); -} - /** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. -- cgit v1.2.3 From 69139d2919dd4aa9a553c8245e7c63e82613e3fc Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 11 Aug 2024 19:21:53 -0700 Subject: vsock: fix recursive ->recvmsg calls After a vsock socket has been added to a BPF sockmap, its prot->recvmsg has been replaced with vsock_bpf_recvmsg(). Thus the following recursiion could happen: vsock_bpf_recvmsg() -> __vsock_recvmsg() -> vsock_connectible_recvmsg() -> prot->recvmsg() -> vsock_bpf_recvmsg() again We need to fix it by calling the original ->recvmsg() without any BPF sockmap logic in __vsock_recvmsg(). Fixes: 634f1a7110b4 ("vsock: support sockmap") Reported-by: syzbot+bdb4bd87b5e22058e2a4@syzkaller.appspotmail.com Tested-by: syzbot+bdb4bd87b5e22058e2a4@syzkaller.appspotmail.com Cc: Bobby Eshleman Cc: Michael S. Tsirkin Cc: Stefano Garzarella Signed-off-by: Cong Wang Acked-by: Michael S. Tsirkin Link: https://patch.msgid.link/20240812022153.86512-1-xiyou.wangcong@gmail.com Signed-off-by: Paolo Abeni --- include/net/af_vsock.h | 4 ++++ net/vmw_vsock/af_vsock.c | 50 +++++++++++++++++++++++++++-------------------- net/vmw_vsock/vsock_bpf.c | 4 ++-- 3 files changed, 35 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 535701efc1e5..24d970f7a4fa 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -230,8 +230,12 @@ struct vsock_tap { int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); +int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4b040285aa78..0ff9b2dd86ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1270,25 +1270,28 @@ out: return err; } +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk; - sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif - return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); @@ -2174,15 +2177,12 @@ out: } int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err; sk = sock->sk; @@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } -#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2250,6 +2242,22 @@ out: release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84..c42c5cc18f32 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE; -- cgit v1.2.3 From 9bb5e74b2bf88fbb024bb15ded3b011e02c673be Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Thu, 15 Aug 2024 11:49:20 +0200 Subject: Revert "misc: fastrpc: Restrict untrusted app to attach to privileged PD" This reverts commit bab2f5e8fd5d2f759db26b78d9db57412888f187. Joel reported that this commit breaks userspace and stops sensors in SDM845 from working. Also breaks other qcom SoC devices running postmarketOS. Cc: stable Cc: Ekansh Gupta Cc: Dmitry Baryshkov Reported-by: Joel Selvaraj Link: https://lore.kernel.org/r/9a9f5646-a554-4b65-8122-d212bb665c81@umsystem.edu Signed-off-by: Griffin Kroah-Hartman Acked-by: Srinivas Kandagatla Fixes: bab2f5e8fd5d ("misc: fastrpc: Restrict untrusted app to attach to privileged PD") Link: https://lore.kernel.org/r/20240815094920.8242-1-griffin@kroah.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 22 +++------------------- include/uapi/misc/fastrpc.h | 3 --- 2 files changed, 3 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 5204fda51da3..339d126414d4 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -2085,16 +2085,6 @@ err_invoke: return err; } -static int is_attach_rejected(struct fastrpc_user *fl) -{ - /* Check if the device node is non-secure */ - if (!fl->is_secure_dev) { - dev_dbg(&fl->cctx->rpdev->dev, "untrusted app trying to attach to privileged DSP PD\n"); - return -EACCES; - } - return 0; -} - static long fastrpc_device_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -2107,19 +2097,13 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd, err = fastrpc_invoke(fl, argp); break; case FASTRPC_IOCTL_INIT_ATTACH: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_attach(fl, ROOT_PD); + err = fastrpc_init_attach(fl, ROOT_PD); break; case FASTRPC_IOCTL_INIT_ATTACH_SNS: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_attach(fl, SENSORS_PD); + err = fastrpc_init_attach(fl, SENSORS_PD); break; case FASTRPC_IOCTL_INIT_CREATE_STATIC: - err = is_attach_rejected(fl); - if (!err) - err = fastrpc_init_create_static_process(fl, argp); + err = fastrpc_init_create_static_process(fl, argp); break; case FASTRPC_IOCTL_INIT_CREATE: err = fastrpc_init_create_process(fl, argp); diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index 91583690bddc..f33d914d8f46 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -8,14 +8,11 @@ #define FASTRPC_IOCTL_ALLOC_DMA_BUFF _IOWR('R', 1, struct fastrpc_alloc_dma_buf) #define FASTRPC_IOCTL_FREE_DMA_BUFF _IOWR('R', 2, __u32) #define FASTRPC_IOCTL_INVOKE _IOWR('R', 3, struct fastrpc_invoke) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_ATTACH _IO('R', 4) #define FASTRPC_IOCTL_INIT_CREATE _IOWR('R', 5, struct fastrpc_init_create) #define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap) #define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static) #define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map) #define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap) -- cgit v1.2.3 From aae6b81260fd9a7224f7eb4fc440d625852245bb Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 12 Aug 2024 10:43:48 -0400 Subject: Bluetooth: HCI: Invert LE State quirk to be opt-out rather then opt-in This inverts the LE State quirk so by default we assume the controllers would report valid states rather than invalid which is how quirks normally behave, also this would result in HCI command failing it the LE States are really broken thus exposing the controllers that are really broken in this respect. Link: https://github.com/bluez/bluez/issues/584 Fixes: 220915857e29 ("Bluetooth: Adding driver and quirk defs for multi-role LE") Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel.c | 10 ---------- drivers/bluetooth/btintel_pcie.c | 3 --- drivers/bluetooth/btmtksdio.c | 3 --- drivers/bluetooth/btrtl.c | 1 - drivers/bluetooth/btusb.c | 4 ++-- drivers/bluetooth/hci_qca.c | 4 ++-- drivers/bluetooth/hci_vhci.c | 2 -- include/net/bluetooth/hci.h | 17 ++++++++++------- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_event.c | 2 +- 10 files changed, 16 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 2ebc970e6573..7d5e4de64e3c 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2945,9 +2945,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) INTEL_ROM_LEGACY_NO_WBS_SUPPORT)) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22) - set_bit(HCI_QUIRK_VALID_LE_STATES, - &hdev->quirks); err = btintel_legacy_rom_setup(hdev, &ver); break; @@ -2956,7 +2953,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) case 0x12: /* ThP */ case 0x13: /* HrP */ case 0x14: /* CcP */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); fallthrough; case 0x0c: /* WsP */ /* Apply the device specific HCI quirks @@ -3048,9 +3044,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) /* These variants don't seem to support LE Coded PHY */ set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); - /* Set Valid LE States quirk */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, ver.hw_variant); @@ -3076,9 +3069,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - /* Apply LE States quirk from solar onwards */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 0d1a0415557b..1c7631f22c52 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1180,9 +1180,6 @@ static int btintel_pcie_setup(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - /* Apply LE States quirk from solar onwards */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index 39d6898497a4..497e4c87f5be 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -1148,9 +1148,6 @@ static int btmtksdio_setup(struct hci_dev *hdev) } } - /* Valid LE States quirk for MediaTek 7921 */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - break; case 0x7663: case 0x7668: diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index f2f37143c454..fd7991ea7672 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1287,7 +1287,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) case CHIP_ID_8852C: case CHIP_ID_8851B: case CHIP_ID_8852BT: - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); /* RTL8852C needs to transmit mSBC data continuously without diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index acdba5d77694..51d9d4532dda 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -3956,8 +3956,8 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_WIDEBAND_SPEECH) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (id->driver_info & BTUSB_VALID_LE_STATES) - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); + if (!(id->driver_info & BTUSB_VALID_LE_STATES)) + set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); if (id->driver_info & BTUSB_DIGIANSWER) { data->cmdreq_type = USB_TYPE_VENDOR; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 45adc1560d94..4b1ad7ea5b95 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2474,8 +2474,8 @@ static int qca_serdev_probe(struct serdev_device *serdev) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (data->capabilities & QCA_CAP_VALID_LE_STATES) - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); + if (!(data->capabilities & QCA_CAP_VALID_LE_STATES)) + set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); } return 0; diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index c4046f8f1985..43e9ac5a3324 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -425,8 +425,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) if (opcode & 0x80) set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); hci_free_dev(hdev); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e372a88e8c3f..d1d073089f38 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -206,14 +206,17 @@ enum { */ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - /* When this quirk is set, the controller has validated that - * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are - * valid. This mechanism is necessary as many controllers have - * been seen has having trouble initiating a connectable - * advertisement despite the state combination being reported as - * supported. + /* When this quirk is set, the LE states reported through the + * HCI_LE_READ_SUPPORTED_STATES are invalid/broken. + * + * This mechanism is necessary as many controllers have been seen has + * having trouble initiating a connectable advertisement despite the + * state combination being reported as supported. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. */ - HCI_QUIRK_VALID_LE_STATES, + HCI_QUIRK_BROKEN_LE_STATES, /* When this quirk is set, then erroneous data reporting * is ignored. This is mainly due to the fact that the HCI diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 31020891fc68..e449dba698f3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -825,7 +825,7 @@ extern struct mutex hci_cb_list_lock; } while (0) #define hci_dev_le_state_simultaneous(hdev) \ - (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \ + (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \ (hdev->le_states[4] & 0x08) && /* Central */ \ (hdev->le_states[4] & 0x40) && /* Peripheral */ \ (hdev->le_states[3] & 0x10)) /* Simultaneous */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d0c118c47f6c..1c82dcdf6e8f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5920,7 +5920,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && - (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || + (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL; -- cgit v1.2.3 From 5f75cfbd6bb02295ddaed48adf667b6c828ce07b Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 1 Aug 2024 22:47:48 +0200 Subject: mm/hugetlb: fix hugetlb vs. core-mm PT locking We recently made GUP's common page table walking code to also walk hugetlb VMAs without most hugetlb special-casing, preparing for the future of having less hugetlb-specific page table walking code in the codebase. Turns out that we missed one page table locking detail: page table locking for hugetlb folios that are not mapped using a single PMD/PUD. Assume we have hugetlb folio that spans multiple PTEs (e.g., 64 KiB hugetlb folios on arm64 with 4 KiB base page size). GUP, as it walks the page tables, will perform a pte_offset_map_lock() to grab the PTE table lock. However, hugetlb that concurrently modifies these page tables would actually grab the mm->page_table_lock: with USE_SPLIT_PTE_PTLOCKS, the locks would differ. Something similar can happen right now with hugetlb folios that span multiple PMDs when USE_SPLIT_PMD_PTLOCKS. This issue can be reproduced [1], for example triggering: [ 3105.936100] ------------[ cut here ]------------ [ 3105.939323] WARNING: CPU: 31 PID: 2732 at mm/gup.c:142 try_grab_folio+0x11c/0x188 [ 3105.944634] Modules linked in: [...] [ 3105.974841] CPU: 31 PID: 2732 Comm: reproducer Not tainted 6.10.0-64.eln141.aarch64 #1 [ 3105.980406] Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-4.fc40 05/24/2024 [ 3105.986185] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 3105.991108] pc : try_grab_folio+0x11c/0x188 [ 3105.994013] lr : follow_page_pte+0xd8/0x430 [ 3105.996986] sp : ffff80008eafb8f0 [ 3105.999346] x29: ffff80008eafb900 x28: ffffffe8d481f380 x27: 00f80001207cff43 [ 3106.004414] x26: 0000000000000001 x25: 0000000000000000 x24: ffff80008eafba48 [ 3106.009520] x23: 0000ffff9372f000 x22: ffff7a54459e2000 x21: ffff7a546c1aa978 [ 3106.014529] x20: ffffffe8d481f3c0 x19: 0000000000610041 x18: 0000000000000001 [ 3106.019506] x17: 0000000000000001 x16: ffffffffffffffff x15: 0000000000000000 [ 3106.024494] x14: ffffb85477fdfe08 x13: 0000ffff9372ffff x12: 0000000000000000 [ 3106.029469] x11: 1fffef4a88a96be1 x10: ffff7a54454b5f0c x9 : ffffb854771b12f0 [ 3106.034324] x8 : 0008000000000000 x7 : ffff7a546c1aa980 x6 : 0008000000000080 [ 3106.038902] x5 : 00000000001207cf x4 : 0000ffff9372f000 x3 : ffffffe8d481f000 [ 3106.043420] x2 : 0000000000610041 x1 : 0000000000000001 x0 : 0000000000000000 [ 3106.047957] Call trace: [ 3106.049522] try_grab_folio+0x11c/0x188 [ 3106.051996] follow_pmd_mask.constprop.0.isra.0+0x150/0x2e0 [ 3106.055527] follow_page_mask+0x1a0/0x2b8 [ 3106.058118] __get_user_pages+0xf0/0x348 [ 3106.060647] faultin_page_range+0xb0/0x360 [ 3106.063651] do_madvise+0x340/0x598 Let's make huge_pte_lockptr() effectively use the same PT locks as any core-mm page table walker would. Add ptep_lockptr() to obtain the PTE page table lock using a pte pointer -- unfortunately we cannot convert pte_lockptr() because virt_to_page() doesn't work with kmap'ed page tables we can have with CONFIG_HIGHPTE. Handle CONFIG_PGTABLE_LEVELS correctly by checking in reverse order, such that when e.g., CONFIG_PGTABLE_LEVELS==2 with PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE will work as expected. Document why that works. There is one ugly case: powerpc 8xx, whereby we have an 8 MiB hugetlb folio being mapped using two PTE page tables. While hugetlb wants to take the PMD table lock, core-mm would grab the PTE table lock of one of both PTE page tables. In such corner cases, we have to make sure that both locks match, which is (fortunately!) currently guaranteed for 8xx as it does not support SMP and consequently doesn't use split PT locks. [1] https://lore.kernel.org/all/1bbfcc7f-f222-45a5-ac44-c5a1381c596d@redhat.com/ Link: https://lkml.kernel.org/r/20240801204748.99107-1-david@redhat.com Fixes: 9cb28da54643 ("mm/gup: handle hugetlb in the generic follow_page_mask code") Signed-off-by: David Hildenbrand Acked-by: Peter Xu Reviewed-by: Baolin Wang Tested-by: Baolin Wang Cc: Peter Xu Cc: Oscar Salvador Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 33 ++++++++++++++++++++++++++++++--- include/linux/mm.h | 11 +++++++++++ 2 files changed, 41 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c9bf68c239a0..45bf05ad5c53 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -944,10 +944,37 @@ static inline bool htlb_allow_alloc_fallback(int reason) static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { - if (huge_page_size(h) == PMD_SIZE) + const unsigned long size = huge_page_size(h); + + VM_WARN_ON(size == PAGE_SIZE); + + /* + * hugetlb must use the exact same PT locks as core-mm page table + * walkers would. When modifying a PTE table, hugetlb must take the + * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD + * PT lock etc. + * + * The expectation is that any hugetlb folio smaller than a PMD is + * always mapped into a single PTE table and that any hugetlb folio + * smaller than a PUD (but at least as big as a PMD) is always mapped + * into a single PMD table. + * + * If that does not hold for an architecture, then that architecture + * must disable split PT locks such that all *_lockptr() functions + * will give us the same result: the per-MM PT lock. + * + * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where + * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() + * and core-mm would use pmd_lockptr(). However, in such configurations + * split PMD locks are disabled -- they don't make sense on a single + * PGDIR page table -- and the end result is the same. + */ + if (size >= PUD_SIZE) + return pud_lockptr(mm, (pud_t *) pte); + else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); - VM_BUG_ON(huge_page_size(h) == PAGE_SIZE); - return &mm->page_table_lock; + /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ + return ptep_lockptr(mm, pte); } #ifndef hugepages_supported diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..6549d0979b28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2920,6 +2920,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); + BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); + return ptlock_ptr(virt_to_ptdesc(pte)); +} + static inline bool ptlock_init(struct ptdesc *ptdesc) { /* @@ -2944,6 +2951,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + return &mm->page_table_lock; +} static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} -- cgit v1.2.3 From f4cb78af91e3b2b7aa76dbf8213b898fa8811b12 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 8 Aug 2024 21:34:35 +0000 Subject: mm: add system wide stats items category /proc/vmstat contains events and stats, events can only grow, but stats can grow and shrink. vmstat has the following: ------------------------- NR_VM_ZONE_STAT_ITEMS: per-zone stats NR_VM_NUMA_EVENT_ITEMS: per-numa events NR_VM_NODE_STAT_ITEMS: per-numa stats NR_VM_WRITEBACK_STAT_ITEMS: system-wide background-writeback and dirty-throttling tresholds. NR_VM_EVENT_ITEMS: system-wide events ------------------------- Rename NR_VM_WRITEBACK_STAT_ITEMS to NR_VM_STAT_ITEMS, to track the system-wide stats, we are going to add per-page metadata stats to this category in the next patch. Also delete unused writeback_stat_name(). Link: https://lkml.kernel.org/r/20240809191020.1142142-2-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240808213437.682006-3-pasha.tatashin@soleen.com Fixes: 15995a352474 ("mm: report per-page metadata information") Signed-off-by: Pasha Tatashin Suggested-by: Yosry Ahmed Tested-by: Alison Schofield Acked-by: David Hildenbrand Acked-by: David Rientjes Cc: Dan Williams Cc: Domenico Cerasuolo Cc: Joel Granados Cc: Johannes Weiner Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport Cc: Muchun Song Cc: Nhat Pham Cc: Sourav Panda Cc: Vlastimil Babka Cc: Yi Zhang Cc: Fan Ni Signed-off-by: Andrew Morton --- include/linux/vmstat.h | 15 ++++----------- mm/vmstat.c | 6 +++--- 2 files changed, 7 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 23cd17942036..9ab4fa5e09b5 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -34,10 +34,11 @@ struct reclaim_stat { unsigned nr_lazyfree_fail; }; -enum writeback_stat_item { +/* Stat data for system wide items */ +enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, + NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -514,21 +515,13 @@ static inline const char *lru_list_name(enum lru_list lru) return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } -static inline const char *writeback_stat_name(enum writeback_stat_item item) -{ - return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_EVENT_ITEMS + - NR_VM_NODE_STAT_ITEMS + - item]; -} - #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + - NR_VM_WRITEBACK_STAT_ITEMS + + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ diff --git a/mm/vmstat.c b/mm/vmstat.c index 04a1cb6cc636..6f8aa4766f16 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1257,7 +1257,7 @@ const char * const vmstat_text[] = { "pgdemote_khugepaged", "nr_memmap", "nr_memmap_boot", - /* enum writeback_stat_item counters */ + /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", @@ -1790,7 +1790,7 @@ static const struct seq_operations zoneinfo_op = { #define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ NR_VM_NUMA_EVENT_ITEMS + \ NR_VM_NODE_STAT_ITEMS + \ - NR_VM_WRITEBACK_STAT_ITEMS + \ + NR_VM_STAT_ITEMS + \ (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ NR_VM_EVENT_ITEMS : 0)) @@ -1827,7 +1827,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); - v += NR_VM_WRITEBACK_STAT_ITEMS; + v += NR_VM_STAT_ITEMS; #ifdef CONFIG_VM_EVENT_COUNTERS all_vm_events(v); -- cgit v1.2.3 From 9d85731110241fb8ca9445ea4177d816041a8825 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 8 Aug 2024 21:34:36 +0000 Subject: mm: don't account memmap per-node Fix invalid access to pgdat during hot-remove operation: ndctl users reported a GPF when trying to destroy a namespace: $ ndctl destroy-namespace all -r all -f Segmentation fault dmesg: Oops: general protection fault, probably for non-canonical address 0xdffffc0000005650: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: probably user-memory-access in range [0x000000000002b280-0x000000000002b287] CPU: 26 UID: 0 PID: 1868 Comm: ndctl Not tainted 6.11.0-rc1 #1 Hardware name: Dell Inc. PowerEdge R640/08HT8T, BIOS 2.20.1 09/13/2023 RIP: 0010:mod_node_page_state+0x2a/0x110 cxl-test users report a GPF when trying to unload the test module: $ modrpobe -r cxl-test dmesg BUG: unable to handle page fault for address: 0000000000004200 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 UID: 0 PID: 1076 Comm: modprobe Tainted: G O N 6.11.0-rc1 #197 Tainted: [O]=OOT_MODULE, [N]=TEST Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/15 RIP: 0010:mod_node_page_state+0x6/0x90 Currently, when memory is hot-plugged or hot-removed the accounting is done based on the assumption that memmap is allocated from the same node as the hot-plugged/hot-removed memory, which is not always the case. In addition, there are challenges with keeping the node id of the memory that is being remove to the time when memmap accounting is actually performed: since this is done after remove_pfn_range_from_zone(), and also after remove_memory_block_devices(). Meaning that we cannot use pgdat nor walking though memblocks to get the nid. Given all of that, account the memmap overhead system wide instead. For this we are going to be using global atomic counters, but given that memmap size is rarely modified, and normally is only modified either during early boot when there is only one CPU, or under a hotplug global mutex lock, therefore there is no need for per-cpu optimizations. Also, while we are here rename nr_memmap to nr_memmap_pages, and nr_memmap_boot to nr_memmap_boot_pages to be self explanatory that the units are in page count. [pasha.tatashin@soleen.com: address a few nits from David Hildenbrand] Link: https://lkml.kernel.org/r/20240809191020.1142142-4-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240809191020.1142142-4-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20240808213437.682006-4-pasha.tatashin@soleen.com Fixes: 15995a352474 ("mm: report per-page metadata information") Signed-off-by: Pasha Tatashin Reported-by: Yi Zhang Closes: https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com Reported-by: Alison Schofield Closes: https://lore.kernel.org/linux-mm/Zq0tPd2h6alFz8XF@aschofie-mobl2/#t Tested-by: Dan Williams Tested-by: Alison Schofield Acked-by: David Hildenbrand Acked-by: David Rientjes Tested-by: Yi Zhang Cc: Domenico Cerasuolo Cc: Fan Ni Cc: Joel Granados Cc: Johannes Weiner Cc: Li Zhijian Cc: Matthew Wilcox (Oracle) Cc: Mike Rapoport Cc: Muchun Song Cc: Nhat Pham Cc: Sourav Panda Cc: Vlastimil Babka Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 -- include/linux/vmstat.h | 7 ++++--- mm/hugetlb_vmemmap.c | 8 ++++---- mm/mm_init.c | 3 +-- mm/page_alloc.c | 1 - mm/page_ext.c | 18 ++++-------------- mm/sparse-vmemmap.c | 11 ++++------- mm/sparse.c | 5 ++--- mm/vmstat.c | 46 ++++++++++++++++++++++------------------------ 9 files changed, 41 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 41458892bc8a..1dc6248feb83 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,8 +220,6 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, - NR_MEMMAP, /* page metadata allocated through buddy allocator */ - NR_MEMMAP_BOOT, /* page metadata allocated through boot allocator */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9ab4fa5e09b5..9eb77c9007e6 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -38,6 +38,8 @@ struct reclaim_stat { enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, + NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; @@ -618,7 +620,6 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } -void __meminit mod_node_early_perpage_metadata(int nid, long delta); -void __meminit store_early_perpage_metadata(void); - +void memmap_boot_pages_add(long delta); +void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 4f51e0596197..0c3f56b3578e 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -185,11 +185,11 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end, static inline void free_vmemmap_page(struct page *page) { if (PageReserved(page)) { + memmap_boot_pages_add(-1); free_bootmem_page(page); - mod_node_page_state(page_pgdat(page), NR_MEMMAP_BOOT, -1); } else { + memmap_pages_add(-1); __free_page(page); - mod_node_page_state(page_pgdat(page), NR_MEMMAP, -1); } } @@ -341,7 +341,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end, copy_page(page_to_virt(walk.reuse_page), (void *)walk.reuse_addr); list_add(&walk.reuse_page->lru, vmemmap_pages); - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, 1); + memmap_pages_add(1); } /* @@ -396,7 +396,7 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, goto out; list_add(&page->lru, list); } - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, nr_pages); + memmap_pages_add(nr_pages); return 0; out: diff --git a/mm/mm_init.c b/mm/mm_init.c index 75c3bd42799b..f9a60ffc5532 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1623,8 +1623,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) panic("Failed to allocate %ld bytes for node %d memory map\n", size, pgdat->node_id); pgdat->node_mem_map = map + offset; - mod_node_early_perpage_metadata(pgdat->node_id, - DIV_ROUND_UP(size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 28f80daf5c04..875d76e8684a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5755,7 +5755,6 @@ void __init setup_per_cpu_pageset(void) for_each_online_pgdat(pgdat) pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); - store_early_perpage_metadata(); } __meminit void zone_pcp_init(struct zone *zone) diff --git a/mm/page_ext.c b/mm/page_ext.c index c191e490c401..641d93f6af4c 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -214,8 +214,7 @@ static int __init alloc_node_page_ext(int nid) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - DIV_ROUND_UP(table_size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } @@ -275,10 +274,8 @@ static void *__meminit alloc_page_ext(size_t size, int nid) else addr = vzalloc_node(size, nid); - if (addr) { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(size, PAGE_SIZE)); - } + if (addr) + memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } @@ -323,25 +320,18 @@ static void free_page_ext(void *addr) { size_t table_size; struct page *page; - struct pglist_data *pgdat; table_size = page_ext_size * PAGES_PER_SECTION; + memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); if (is_vmalloc_addr(addr)) { - page = vmalloc_to_page(addr); - pgdat = page_pgdat(page); vfree(addr); } else { page = virt_to_page(addr); - pgdat = page_pgdat(page); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } - - mod_node_page_state(pgdat, NR_MEMMAP, - -1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); - } static void __free_page_ext(unsigned long pfn) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 1dda6c53370b..edcc7a6b0f6f 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -469,13 +469,10 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, if (r < 0) return NULL; - if (system_state == SYSTEM_BOOTING) { - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(end - start, - PAGE_SIZE)); - } else { - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP, - DIV_ROUND_UP(end - start, PAGE_SIZE)); - } + if (system_state == SYSTEM_BOOTING) + memmap_boot_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE)); + else + memmap_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE)); return pfn_to_page(pfn); } diff --git a/mm/sparse.c b/mm/sparse.c index e4b830091d13..0f018c6f9ec5 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -463,7 +463,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true); sparsemap_buf_end = sparsemap_buf + size; #ifndef CONFIG_SPARSEMEM_VMEMMAP - mod_node_early_perpage_metadata(nid, DIV_ROUND_UP(size, PAGE_SIZE)); + memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); #endif } @@ -643,8 +643,7 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, unsigned long start = (unsigned long) pfn_to_page(pfn); unsigned long end = start + nr_pages * sizeof(struct page); - mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP, - -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); + memmap_pages_add(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); vmemmap_free(start, end, altmap); } static void free_map_bootmem(struct page *memmap) diff --git a/mm/vmstat.c b/mm/vmstat.c index 6f8aa4766f16..e875f2a4915f 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1033,6 +1033,24 @@ unsigned long node_page_state(struct pglist_data *pgdat, } #endif +/* + * Count number of pages "struct page" and "struct page_ext" consume. + * nr_memmap_boot_pages: # of pages allocated by boot allocator + * nr_memmap_pages: # of pages that were allocated by buddy allocator + */ +static atomic_long_t nr_memmap_boot_pages = ATOMIC_LONG_INIT(0); +static atomic_long_t nr_memmap_pages = ATOMIC_LONG_INIT(0); + +void memmap_boot_pages_add(long delta) +{ + atomic_long_add(delta, &nr_memmap_boot_pages); +} + +void memmap_pages_add(long delta) +{ + atomic_long_add(delta, &nr_memmap_pages); +} + #ifdef CONFIG_COMPACTION struct contig_page_info { @@ -1255,11 +1273,11 @@ const char * const vmstat_text[] = { "pgdemote_kswapd", "pgdemote_direct", "pgdemote_khugepaged", - "nr_memmap", - "nr_memmap_boot", /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", + "nr_memmap_pages", + "nr_memmap_boot_pages", #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) /* enum vm_event_item counters */ @@ -1827,6 +1845,8 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); + v[NR_MEMMAP_PAGES] = atomic_long_read(&nr_memmap_pages); + v[NR_MEMMAP_BOOT_PAGES] = atomic_long_read(&nr_memmap_boot_pages); v += NR_VM_STAT_ITEMS; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -2285,25 +2305,3 @@ static int __init extfrag_debug_init(void) module_init(extfrag_debug_init); #endif - -/* - * Page metadata size (struct page and page_ext) in pages - */ -static unsigned long early_perpage_metadata[MAX_NUMNODES] __meminitdata; - -void __meminit mod_node_early_perpage_metadata(int nid, long delta) -{ - early_perpage_metadata[nid] += delta; -} - -void __meminit store_early_perpage_metadata(void) -{ - int nid; - struct pglist_data *pgdat; - - for_each_online_pgdat(pgdat) { - nid = pgdat->node_id; - mod_node_page_state(NODE_DATA(nid), NR_MEMMAP_BOOT, - early_perpage_metadata[nid]); - } -} -- cgit v1.2.3 From a8fc28dad6d574582cdf2f7e78c73c59c623df30 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 13 Aug 2024 08:07:56 -0700 Subject: alloc_tag: introduce clear_page_tag_ref() helper function In several cases we are freeing pages which were not allocated using common page allocators. For such cases, in order to keep allocation accounting correct, we should clear the page tag to indicate that the page being freed is expected to not have a valid allocation tag. Introduce clear_page_tag_ref() helper function to be used for this. Link: https://lkml.kernel.org/r/20240813150758.855881-1-surenb@google.com Fixes: d224eb0287fb ("codetag: debug: mark codetags for reserved pages as empty") Signed-off-by: Suren Baghdasaryan Suggested-by: David Hildenbrand Acked-by: David Hildenbrand Reviewed-by: Pasha Tatashin Cc: Kees Cook Cc: Kent Overstreet Cc: Sourav Panda Cc: Vlastimil Babka Cc: [6.10] Signed-off-by: Andrew Morton --- include/linux/pgalloc_tag.h | 13 +++++++++++++ mm/mm_init.c | 10 +--------- mm/page_alloc.c | 9 +-------- 3 files changed, 15 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 18cd0c0c73d9..207f0c83c8e9 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -43,6 +43,18 @@ static inline void put_page_tag_ref(union codetag_ref *ref) page_ext_put(page_ext_from_codetag_ref(ref)); } +static inline void clear_page_tag_ref(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } +} + static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) { @@ -126,6 +138,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } static inline void put_page_tag_ref(union codetag_ref *ref) {} +static inline void clear_page_tag_ref(struct page *page) {} static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} diff --git a/mm/mm_init.c b/mm/mm_init.c index f9a60ffc5532..adc3127573cd 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2459,15 +2459,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, } /* pages were reserved and not allocated */ - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } - + clear_page_tag_ref(page); __free_pages_core(page, order, MEMINIT_EARLY); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8747087acee3..c565de8f48e9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5815,14 +5815,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char void free_reserved_page(struct page *page) { - if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); - } - } + clear_page_tag_ref(page); ClearPageReserved(page); init_page_count(page); __free_page(page); -- cgit v1.2.3 From 67c3ca2c5cfe6a50772514e3349b5e7b3b0fac03 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:02 +0300 Subject: net: mscc: ocelot: use ocelot_xmit_get_vlan_info() also for FDMA and register injection Problem description ------------------- On an NXP LS1028A (felix DSA driver) with the following configuration: - ocelot-8021q tagging protocol - VLAN-aware bridge (with STP) spanning at least swp0 and swp1 - 8021q VLAN upper interfaces on swp0 and swp1: swp0.700, swp1.700 - ptp4l on swp0.700 and swp1.700 we see that the ptp4l instances do not see each other's traffic, and they all go to the grand master state due to the ANNOUNCE_RECEIPT_TIMEOUT_EXPIRES condition. Jumping to the conclusion for the impatient ------------------------------------------- There is a zero-day bug in the ocelot switchdev driver in the way it handles VLAN-tagged packet injection. The correct logic already exists in the source code, in function ocelot_xmit_get_vlan_info() added by commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). But it is used only for normal NPI-based injection with the DSA "ocelot" tagging protocol. The other injection code paths (register-based and FDMA-based) roll their own wrong logic. This affects and was noticed on the DSA "ocelot-8021q" protocol because it uses register-based injection. By moving ocelot_xmit_get_vlan_info() to a place that's common for both the DSA tagger and the ocelot switch library, it can also be called from ocelot_port_inject_frame() in ocelot.c. We need to touch the lines with ocelot_ifh_port_set()'s prototype anyway, so let's rename it to something clearer regarding what it does, and add a kernel-doc. ocelot_ifh_set_basic() should do. Investigation notes ------------------- Debugging reveals that PTP event (aka those carrying timestamps, like Sync) frames injected into swp0.700 (but also swp1.700) hit the wire with two VLAN tags: 00000000: 01 1b 19 00 00 00 00 01 02 03 04 05 81 00 02 bc ~~~~~~~~~~~ 00000010: 81 00 02 bc 88 f7 00 12 00 2c 00 00 02 00 00 00 ~~~~~~~~~~~ 00000020: 00 00 00 00 00 00 00 00 00 00 00 01 02 ff fe 03 00000030: 04 05 00 01 00 04 00 00 00 00 00 00 00 00 00 00 00000040: 00 00 The second (unexpected) VLAN tag makes felix_check_xtr_pkt() -> ptp_classify_raw() fail to see these as PTP packets at the link partner's receiving end, and return PTP_CLASS_NONE (because the BPF classifier is not written to expect 2 VLAN tags). The reason why packets have 2 VLAN tags is because the transmission code treats VLAN incorrectly. Neither ocelot switchdev, nor felix DSA, declare the NETIF_F_HW_VLAN_CTAG_TX feature. Therefore, at xmit time, all VLANs should be in the skb head, and none should be in the hwaccel area. This is done by: static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } But ocelot_port_inject_frame() handles things incorrectly: ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); void ocelot_ifh_port_set(struct sk_buff *skb, void *ifh, int port, u32 rew_op) { (...) if (vlan_tag) ocelot_ifh_set_vlan_tci(ifh, vlan_tag); (...) } The way __vlan_hwaccel_push_inside() pushes the tag inside the skb head is by calling: static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_present = 0; } which does _not_ zero out skb->vlan_tci as seen by skb_vlan_tag_get(). This means that ocelot, when it calls skb_vlan_tag_get(), sees (and uses) a residual skb->vlan_tci, while the same VLAN tag is _already_ in the skb head. The trivial fix for double VLAN headers is to replace the content of ocelot_ifh_port_set() with: if (skb_vlan_tag_present(skb)) ocelot_ifh_set_vlan_tci(ifh, skb_vlan_tag_get(skb)); but this would not be correct either, because, as mentioned, vlan_hw_offload_capable() is false for us, so we'd be inserting dead code and we'd always transmit packets with VID=0 in the injection frame header. I can't actually test the ocelot switchdev driver and rely exclusively on code inspection, but I don't think traffic from 8021q uppers has ever been injected properly, and not double-tagged. Thus I'm blaming the introduction of VLAN fields in the injection header - early driver code. As hinted at in the early conclusion, what we _want_ to happen for VLAN transmission was already described once in commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). ocelot_xmit_get_vlan_info() intends to ensure that if the port through which we're transmitting is under a VLAN-aware bridge, the outer VLAN tag from the skb head is stripped from there and inserted into the injection frame header (so that the packet is processed in hardware through that actual VLAN). And in all other cases, the packet is sent with VID=0 in the injection frame header, since the port is VLAN-unaware and has logic to strip this VID on egress (making it invisible to the wire). Fixes: 08d02364b12f ("net: mscc: fix the injection header") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 29 +++++++++++++++----- drivers/net/ethernet/mscc/ocelot_fdma.c | 2 +- include/linux/dsa/ocelot.h | 47 +++++++++++++++++++++++++++++++++ include/soc/mscc/ocelot.h | 3 ++- net/dsa/tag_ocelot.c | 37 ++------------------------ 5 files changed, 75 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index ed2fb44500b0..69a4e5a90475 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1193,17 +1193,34 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) } EXPORT_SYMBOL(ocelot_can_inject); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag) +/** + * ocelot_ifh_set_basic - Set basic information in Injection Frame Header + * @ifh: Pointer to Injection Frame Header memory + * @ocelot: Switch private data structure + * @port: Egress port number + * @rew_op: Egress rewriter operation for PTP + * @skb: Pointer to socket buffer (packet) + * + * Populate the Injection Frame Header with basic information for this skb: the + * analyzer bypass bit, destination port, VLAN info, egress rewriter info. + */ +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + u64 vlan_tci, tag_type; + + ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, + &tag_type); + ocelot_ifh_set_bypass(ifh, 1); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); - ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - if (vlan_tag) - ocelot_ifh_set_vlan_tci(ifh, vlan_tag); + ocelot_ifh_set_tag_type(ifh, tag_type); + ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) ocelot_ifh_set_rew_op(ifh, rew_op); } -EXPORT_SYMBOL(ocelot_ifh_port_set); +EXPORT_SYMBOL(ocelot_ifh_set_basic); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) @@ -1214,7 +1231,7 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); for (i = 0; i < OCELOT_TAG_LEN / 4; i++) ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 312a46832154..87b59cc5e441 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -666,7 +666,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); memset(ifh, 0, OCELOT_TAG_LEN); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); return 0; } diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index dca2969015d8..6fbfbde68a37 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,6 +5,8 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H +#include +#include #include #include #include @@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) return rew_op; } +/** + * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame + * @skb: Pointer to socket buffer + * @br: Pointer to bridge device that the port is under, if any + * @vlan_tci: + * @tag_type: + * + * If the port is under a VLAN-aware bridge, remove the VLAN header from the + * payload and move it into the DSA tag, which will make the switch classify + * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, + * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not + * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()). + * Anyway, VID 0 is fine because it is stripped on egress for these port modes, + * and source address learning is not performed for packets injected from the + * CPU anyway, so it doesn't matter that the VID is "wrong". + */ +static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb, + struct net_device *br, + u64 *vlan_tci, u64 *tag_type) +{ + struct vlan_ethhdr *hdr; + u16 proto, tci; + + if (!br || !br_vlan_enabled(br)) { + *vlan_tci = 0; + *tag_type = IFH_TAG_TYPE_C; + return; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + br_vlan_get_proto(br, &proto); + + if (ntohs(hdr->h_vlan_proto) == proto) { + vlan_remove_tag(skb, &tci); + *vlan_tci = tci; + } else { + rcu_read_lock(); + br_vlan_get_pvid_rcu(br, &tci); + rcu_read_unlock(); + *vlan_tci = tci; + } + + *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; +} + #endif diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6a37b29f4b4c..ed18e6bafc8d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -969,7 +969,8 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag); +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3..bf6608fc6be7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville" -/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class; - ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type); qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; -- cgit v1.2.3 From c5e12ac3beb0dd3a718296b2d8af5528e9ab728e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:04 +0300 Subject: net: mscc: ocelot: serialize access to the injection/extraction groups As explained by Horatiu Vultur in commit 603ead96582d ("net: sparx5: Add spinlock for frame transmission from CPU") which is for a similar hardware design, multiple CPUs can simultaneously perform injection or extraction. There are only 2 register groups for injection and 2 for extraction, and the driver only uses one of each. So we'd better serialize access using spin locks, otherwise frame corruption is possible. Note that unlike in sparx5, FDMA in ocelot does not have this issue because struct ocelot_fdma_tx_ring already contains an xmit_lock. I guess this is mostly a problem for NXP LS1028A, as that is dual core. I don't think VSC7514 is. So I'm blaming the commit where LS1028A (aka the felix DSA driver) started using register-based packet injection and extraction. Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 11 +++++++ drivers/net/ethernet/mscc/ocelot.c | 52 ++++++++++++++++++++++++++++++ drivers/net/ethernet/mscc/ocelot_vsc7514.c | 4 +++ include/soc/mscc/ocelot.h | 9 ++++++ 4 files changed, 76 insertions(+) (limited to 'include') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index e554699f06d4..8d31ff18c5c7 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -528,7 +528,9 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds) * so we need to be careful that there are no extra frames to be * dequeued over MMIO, since we would never know to discard them. */ + ocelot_lock_xtr_grp_bh(ocelot, 0); ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp_bh(ocelot, 0); return 0; } @@ -1518,6 +1520,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work) int port = xmit_work->dp->index; int retries = 10; + ocelot_lock_inj_grp(ocelot, 0); + do { if (ocelot_can_inject(ocelot, 0)) break; @@ -1526,6 +1530,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work) } while (--retries); if (!retries) { + ocelot_unlock_inj_grp(ocelot, 0); dev_err(ocelot->dev, "port %d failed to inject skb\n", port); ocelot_port_purge_txtstamp_skb(ocelot, port, skb); @@ -1535,6 +1540,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work) ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + ocelot_unlock_inj_grp(ocelot, 0); + consume_skb(skb); kfree(xmit_work); } @@ -1694,6 +1701,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot) if (!felix->info->quirk_no_xtr_irq) return false; + ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; unsigned int type; @@ -1730,6 +1739,8 @@ out: ocelot_drain_cpu_queue(ocelot, 0); } + ocelot_unlock_xtr_grp(ocelot, grp); + return true; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 9301716e21d5..f4e027a6fe95 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1099,6 +1099,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, } EXPORT_SYMBOL(ocelot_ptp_rx_timestamp); +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp); + +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp); + +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp); + +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp); + +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __acquires(&ocelot->xtr_lock) +{ + spin_lock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh); + +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __releases(&ocelot->xtr_lock) +{ + spin_unlock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh); + int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) { u64 timestamp, src_port, len; @@ -1109,6 +1151,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) u32 val, *buf; int err; + lockdep_assert_held(&ocelot->xtr_lock); + err = ocelot_xtr_poll_xfh(ocelot, grp, xfh); if (err) return err; @@ -1184,6 +1228,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) { u32 val = ocelot_read(ocelot, QS_INJ_STATUS); + lockdep_assert_held(&ocelot->inj_lock); + if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp)))) return false; if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp))) @@ -1236,6 +1282,8 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 ifh[OCELOT_TAG_LEN / 4]; unsigned int i, count, last; + lockdep_assert_held(&ocelot->inj_lock); + ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); @@ -1272,6 +1320,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) { + lockdep_assert_held(&ocelot->xtr_lock); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) ocelot_read_rix(ocelot, QS_XTR_RD, grp); } @@ -2954,6 +3004,8 @@ int ocelot_init(struct ocelot *ocelot) mutex_init(&ocelot->fwd_domain_lock); spin_lock_init(&ocelot->ptp_clock_lock); spin_lock_init(&ocelot->ts_id_lock); + spin_lock_init(&ocelot->inj_lock); + spin_lock_init(&ocelot->xtr_lock); ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0); if (!ocelot->owq) diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 993212c3a7da..c09dd2e3343c 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) struct ocelot *ocelot = arg; int grp = 0, err; + ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; @@ -69,6 +71,8 @@ out: if (err < 0) ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp(ocelot, grp); + return IRQ_HANDLED; } diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index ed18e6bafc8d..462c653e1017 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -813,6 +813,9 @@ struct ocelot { const u32 *const *map; struct list_head stats_regions; + spinlock_t inj_lock; + spinlock_t xtr_lock; + u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; int packet_buffer_size; int num_frame_refs; @@ -966,6 +969,12 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, u32 val, u32 reg, u32 offset); /* Packet I/O */ +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp); bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); -- cgit v1.2.3 From 93e4649efa964201c73b0a03c35c04a0d6fc809f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:05 +0300 Subject: net: dsa: provide a software untagging function on RX for VLAN-aware bridges Through code analysis, I realized that the ds->untag_bridge_pvid logic is contradictory - see the newly added FIXME above the kernel-doc for dsa_software_untag_vlan_unaware_bridge(). Moreover, for the Felix driver, I need something very similar, but which is actually _not_ contradictory: untag the bridge PVID on RX, but for VLAN-aware bridges. The existing logic does it for VLAN-unaware bridges. Since I don't want to change the functionality of drivers which were supposedly properly tested with the ds->untag_bridge_pvid flag, I have introduced a new one: ds->untag_vlan_aware_bridge_pvid, and I have refactored the DSA reception code into a common path for both flags. TODO: both flags should be unified under a single ds->software_vlan_untag, which users of both current flags should set. This is not something that can be carried out right away. It needs very careful examination of all drivers which make use of this functionality, since some of them actually get this wrong in the first place. For example, commit 9130c2d30c17 ("net: dsa: microchip: ksz8795: Use software untagging on CPU port") uses this in a driver which has ds->configure_vlan_while_not_filtering = true. The latter mechanism has been known for many years to be broken by design: https://lore.kernel.org/netdev/CABumfLzJmXDN_W-8Z=p9KyKUVi_HhS7o_poBkeKHS2BkAiyYpw@mail.gmail.com/ and we have the situation of 2 bugs canceling each other. There is no private VLAN, and the port follows the PVID of the VLAN-unaware bridge. So, it's kinda ok for that driver to use the ds->untag_bridge_pvid mechanism, in a broken way. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 16 ++++--- net/dsa/tag.c | 5 +- net/dsa/tag.h | 135 ++++++++++++++++++++++++++++++++++++++++++------------ 3 files changed, 118 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b06f97ae3da1..d7a6c2930277 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -403,14 +403,18 @@ struct dsa_switch { */ u32 configure_vlan_while_not_filtering:1; - /* If the switch driver always programs the CPU port as egress tagged - * despite the VLAN configuration indicating otherwise, then setting - * @untag_bridge_pvid will force the DSA receive path to pop the - * bridge's default_pvid VLAN tagged frames to offer a consistent - * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge - * device. + /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. + * DEPRECATED: Do NOT set this field in new drivers. Instead look at + * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; + /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. + * Useful if the switch cannot preserve the VLAN tag as seen on the + * wire for user port ingress, and chooses to send all frames as + * VLAN-tagged to the CPU, including those which were originally + * untagged. + */ + u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. diff --git a/net/dsa/tag.c b/net/dsa/tag.c index 6e402d49afd3..79ad105902d9 100644 --- a/net/dsa/tag.c +++ b/net/dsa/tag.c @@ -105,8 +105,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, p = netdev_priv(skb->dev); - if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { - nskb = dsa_untag_bridge_pvid(skb); + if (unlikely(cpu_dp->ds->untag_bridge_pvid || + cpu_dp->ds->untag_vlan_aware_bridge_pvid)) { + nskb = dsa_software_vlan_untag(skb); if (!nskb) { kfree_skb(skb); return 0; diff --git a/net/dsa/tag.h b/net/dsa/tag.h index f6b9c73718df..d5707870906b 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -44,46 +44,81 @@ static inline struct net_device *dsa_conduit_find_user(struct net_device *dev, return NULL; } -/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged - * frames as untagged, since the bridge will not untag them. +/** + * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge can process tagged packets. Software like STP/PTP may not. The + * bridge can also process untagged packets, to the same effect as if they were + * tagged with the PVID of the ingress port. So packets tagged with the PVID of + * the bridge port must be software-untagged, to support both use cases. */ -static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) +static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) { - struct dsa_port *dp = dsa_user_to_port(skb->dev); - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct net_device *dev = skb->dev; - struct net_device *upper_dev; - u16 vid, pvid, proto; + u16 pvid, proto; int err; - if (!br || br_vlan_enabled(br)) - return skb; - err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { - skb = skb_vlan_untag(skb); - if (!skb) - return NULL; - } + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; - if (!skb_vlan_tag_present(skb)) - return skb; + if (vid == pvid && skb->vlan_proto == htons(proto)) + __vlan_hwaccel_clear_tag(skb); +} - vid = skb_vlan_tag_get_id(skb); +/** + * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run + * on the plain port, or on a VLAN upper interface). Maybe packets are coming + * to software as tagged with a driver-defined VID which is NOT equal to the + * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration + * should NOT be committed to hardware). DSA needs a method for this private + * VID to be communicated by software to it, and if packets are tagged with it, + * software-untag them. Note: the private VID may be different per bridge, to + * support the FDB isolation use case. + * + * FIXME: this is currently implemented based on the broken assumption that + * the "private VID" used by the driver in VLAN-unaware mode is equal to the + * bridge PVID. It should not be, except for a coincidence; the bridge PVID is + * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that + * this function removes is wrong. + * + * All users of ds->untag_bridge_pvid should fix their drivers, if necessary, + * to make the two independent. Only then, if there still remains a need to + * strip the private VID from packets, then a new ds->ops->get_private_vid() + * API shall be introduced to communicate to DSA what this VID is, which needs + * to be stripped here. + */ +static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) +{ + struct net_device *upper_dev; + u16 pvid, proto; + int err; - /* We already run under an RCU read-side critical section since - * we are called from netif_receive_skb_list_internal(). - */ - err = br_vlan_get_pvid_rcu(dev, &pvid); + err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - if (vid != pvid) - return skb; + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; + + if (vid != pvid || skb->vlan_proto != htons(proto)) + return; /* The sad part about attempting to untag from DSA is that we * don't know, unless we check, if the skb will end up in @@ -95,10 +130,50 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) * definitely keep the tag, to make sure it keeps working. */ upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); - if (upper_dev) + if (!upper_dev) + __vlan_hwaccel_clear_tag(skb); +} + +/** + * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path + * @skb: Pointer to socket buffer (packet) + * + * Receive path method for switches which cannot avoid tagging all packets + * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or + * ds->untag_vlan_aware_bridge_pvid is set to true. + * + * As a side effect of this method, any VLAN tag from the skb head is moved + * to hwaccel. + */ +static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_user_to_port(skb->dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + u16 vid; + + /* software untagging for standalone ports not yet necessary */ + if (!br) return skb; - __vlan_hwaccel_clear_tag(skb); + /* Move VLAN tag from data to hwaccel */ + if (!skb_vlan_tag_present(skb)) { + skb = skb_vlan_untag(skb); + if (!skb) + return NULL; + } + + if (!skb_vlan_tag_present(skb)) + return skb; + + vid = skb_vlan_tag_get_id(skb); + + if (br_vlan_enabled(br)) { + if (dp->ds->untag_vlan_aware_bridge_pvid) + dsa_software_untag_vlan_aware_bridge(skb, br, vid); + } else { + if (dp->ds->untag_bridge_pvid) + dsa_software_untag_vlan_unaware_bridge(skb, br, vid); + } return skb; } -- cgit v1.2.3 From 36dd1141be70b5966906919714dc504a24c65ddf Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:07 +0300 Subject: net: mscc: ocelot: treat 802.1ad tagged traffic as 802.1Q-untagged I was revisiting the topic of 802.1ad treatment in the Ocelot switch [0] and realized that not only is its basic VLAN classification pipeline improper for offloading vlan_protocol 802.1ad bridges, but also improper for offloading regular 802.1Q bridges already. Namely, 802.1ad-tagged traffic should be treated as VLAN-untagged by bridged ports, but this switch treats it as if it was 802.1Q-tagged with the same VID as in the 802.1ad header. This is markedly different to what the Linux bridge expects; see the "other_tpid()" function in tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh. An idea came to me that the VCAP IS1 TCAM is more powerful than I'm giving it credit for, and that it actually overwrites the classified VID before the VLAN Table lookup takes place. In other words, it can be used even to save a packet from being dropped on ingress due to VLAN membership. Add a sophisticated TCAM rule hardcoded into the driver to force the switch to behave like a Linux bridge with vlan_filtering 1 vlan_protocol 802.1Q. Regarding the lifetime of the filter: eventually the bridge will disappear, and vlan_filtering on the port will be restored to 0 for standalone mode. Then the filter will be deleted. [0]: https://lore.kernel.org/netdev/20201009122947.nvhye4hvcha3tljh@skbuf/ Fixes: 7142529f1688 ("net: mscc: ocelot: add VLAN filtering") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 188 ++++++++++++++++++++++++++++++-- drivers/net/ethernet/mscc/ocelot_vcap.c | 1 + include/soc/mscc/ocelot_vcap.h | 2 + 3 files changed, 180 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index f4e027a6fe95..3d72aa7b1305 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -453,9 +453,158 @@ static u16 ocelot_vlan_unaware_pvid(struct ocelot *ocelot, return VLAN_N_VID - bridge_num - 1; } +/** + * ocelot_update_vlan_reclassify_rule() - Make switch aware only to bridge VLAN TPID + * + * @ocelot: Switch private data structure + * @port: Index of ingress port + * + * IEEE 802.1Q-2018 clauses "5.5 C-VLAN component conformance" and "5.6 S-VLAN + * component conformance" suggest that a C-VLAN component should only recognize + * and filter on C-Tags, and an S-VLAN component should only recognize and + * process based on C-Tags. + * + * In Linux, as per commit 1a0b20b25732 ("Merge branch 'bridge-next'"), C-VLAN + * components are largely represented by a bridge with vlan_protocol 802.1Q, + * and S-VLAN components by a bridge with vlan_protocol 802.1ad. + * + * Currently the driver only offloads vlan_protocol 802.1Q, but the hardware + * design is non-conformant, because the switch assigns each frame to a VLAN + * based on an entirely different question, as detailed in figure "Basic VLAN + * Classification Flow" from its manual and reproduced below. + * + * Set TAG_TYPE, PCP, DEI, VID to port-default values in VLAN_CFG register + * if VLAN_AWARE_ENA[port] and frame has outer tag then: + * if VLAN_INNER_TAG_ENA[port] and frame has inner tag then: + * TAG_TYPE = (Frame.InnerTPID <> 0x8100) + * Set PCP, DEI, VID to values from inner VLAN header + * else: + * TAG_TYPE = (Frame.OuterTPID <> 0x8100) + * Set PCP, DEI, VID to values from outer VLAN header + * if VID == 0 then: + * VID = VLAN_CFG.VLAN_VID + * + * Summarized, the switch will recognize both 802.1Q and 802.1ad TPIDs as VLAN + * "with equal rights", and just set the TAG_TYPE bit to 0 (if 802.1Q) or to 1 + * (if 802.1ad). It will classify based on whichever of the tags is "outer", no + * matter what TPID that may have (or "inner", if VLAN_INNER_TAG_ENA[port]). + * + * In the VLAN Table, the TAG_TYPE information is not accessible - just the + * classified VID is - so it is as if each VLAN Table entry is for 2 VLANs: + * C-VLAN X, and S-VLAN X. + * + * Whereas the Linux bridge behavior is to only filter on frames with a TPID + * equal to the vlan_protocol, and treat everything else as VLAN-untagged. + * + * Consider an ingress packet tagged with 802.1ad VID=3 and 802.1Q VID=5, + * received on a bridge vlan_filtering=1 vlan_protocol=802.1Q port. This frame + * should be treated as 802.1Q-untagged, and classified to the PVID of that + * bridge port. Not to VID=3, and not to VID=5. + * + * The VCAP IS1 TCAM has everything we need to overwrite the choices made in + * the basic VLAN classification pipeline: it can match on TAG_TYPE in the key, + * and it can modify the classified VID in the action. Thus, for each port + * under a vlan_filtering bridge, we can insert a rule in VCAP IS1 lookup 0 to + * match on 802.1ad tagged frames and modify their classified VID to the 802.1Q + * PVID of the port. This effectively makes it appear to the outside world as + * if those packets were processed as VLAN-untagged. + * + * The rule needs to be updated each time the bridge PVID changes, and needs + * to be deleted if the bridge PVID is deleted, or if the port becomes + * VLAN-unaware. + */ +static int ocelot_update_vlan_reclassify_rule(struct ocelot *ocelot, int port) +{ + unsigned long cookie = OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port); + struct ocelot_vcap_block *block_vcap_is1 = &ocelot->block[VCAP_IS1]; + struct ocelot_port *ocelot_port = ocelot->ports[port]; + const struct ocelot_bridge_vlan *pvid_vlan; + struct ocelot_vcap_filter *filter; + int err, val, pcp, dei; + bool vid_replace_ena; + u16 vid; + + pvid_vlan = ocelot_port->pvid_vlan; + vid_replace_ena = ocelot_port->vlan_aware && pvid_vlan; + + filter = ocelot_vcap_block_find_filter_by_id(block_vcap_is1, cookie, + false); + if (!vid_replace_ena) { + /* If the reclassification filter doesn't need to exist, delete + * it if it was previously installed, and exit doing nothing + * otherwise. + */ + if (filter) + return ocelot_vcap_filter_del(ocelot, filter); + + return 0; + } + + /* The reclassification rule must apply. See if it already exists + * or if it must be created. + */ + + /* Treating as VLAN-untagged means using as classified VID equal to + * the bridge PVID, and PCP/DEI set to the port default QoS values. + */ + vid = pvid_vlan->vid; + val = ocelot_read_gix(ocelot, ANA_PORT_QOS_CFG, port); + pcp = ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL_X(val); + dei = !!(val & ANA_PORT_QOS_CFG_DP_DEFAULT_VAL); + + if (filter) { + bool changed = false; + + /* Filter exists, just update it */ + if (filter->action.vid != vid) { + filter->action.vid = vid; + changed = true; + } + if (filter->action.pcp != pcp) { + filter->action.pcp = pcp; + changed = true; + } + if (filter->action.dei != dei) { + filter->action.dei = dei; + changed = true; + } + + if (!changed) + return 0; + + return ocelot_vcap_filter_replace(ocelot, filter); + } + + /* Filter doesn't exist, create it */ + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->ingress_port_mask = BIT(port); + filter->vlan.tpid = OCELOT_VCAP_BIT_1; + filter->prio = 1; + filter->id.cookie = cookie; + filter->id.tc_offload = false; + filter->block_id = VCAP_IS1; + filter->type = OCELOT_VCAP_FILTER_OFFLOAD; + filter->lookup = 0; + filter->action.vid_replace_ena = true; + filter->action.pcp_dei_ena = true; + filter->action.vid = vid; + filter->action.pcp = pcp; + filter->action.dei = dei; + + err = ocelot_vcap_filter_add(ocelot, filter, NULL); + if (err) + kfree(filter); + + return err; +} + /* Default vlan to clasify for untagged frames (may be zero) */ -static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, - const struct ocelot_bridge_vlan *pvid_vlan) +static int ocelot_port_set_pvid(struct ocelot *ocelot, int port, + const struct ocelot_bridge_vlan *pvid_vlan) { struct ocelot_port *ocelot_port = ocelot->ports[port]; u16 pvid = ocelot_vlan_unaware_pvid(ocelot, ocelot_port->bridge); @@ -475,15 +624,23 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, * happens automatically), but also 802.1p traffic which gets * classified to VLAN 0, but that is always in our RX filter, so it * would get accepted were it not for this setting. + * + * Also, we only support the bridge 802.1Q VLAN protocol, so + * 802.1ad-tagged frames (carrying S-Tags) should be considered + * 802.1Q-untagged, and also dropped. */ if (!pvid_vlan && ocelot_port->vlan_aware) val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA; ocelot_rmw_gix(ocelot, val, ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA, + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA, ANA_PORT_DROP_CFG, port); + + return ocelot_update_vlan_reclassify_rule(ocelot, port); } static struct ocelot_bridge_vlan *ocelot_bridge_vlan_find(struct ocelot *ocelot, @@ -631,7 +788,10 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M, ANA_PORT_VLAN_CFG, port); - ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + err = ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + if (err) + return err; + ocelot_port_manage_port_tag(ocelot, port); return 0; @@ -684,9 +844,12 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, return err; /* Default ingress vlan classification */ - if (pvid) - ocelot_port_set_pvid(ocelot, port, - ocelot_bridge_vlan_find(ocelot, vid)); + if (pvid) { + err = ocelot_port_set_pvid(ocelot, port, + ocelot_bridge_vlan_find(ocelot, vid)); + if (err) + return err; + } /* Untagged egress vlan clasification */ ocelot_port_manage_port_tag(ocelot, port); @@ -712,8 +875,11 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) return err; /* Ingress */ - if (del_pvid) - ocelot_port_set_pvid(ocelot, port, NULL); + if (del_pvid) { + err = ocelot_port_set_pvid(ocelot, port, NULL); + if (err) + return err; + } /* Egress */ ocelot_port_manage_port_tag(ocelot, port); @@ -2607,7 +2773,7 @@ int ocelot_port_set_default_prio(struct ocelot *ocelot, int port, u8 prio) ANA_PORT_QOS_CFG, port); - return 0; + return ocelot_update_vlan_reclassify_rule(ocelot, port); } EXPORT_SYMBOL_GPL(ocelot_port_set_default_prio); diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 73cdec5ca6a3..5734b86aed5b 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -695,6 +695,7 @@ static void is1_entry_set(struct ocelot *ocelot, int ix, vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_MC, filter->dmac_mc); vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_BC, filter->dmac_bc); vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_VLAN_TAGGED, tag->tagged); + vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TPID, tag->tpid); vcap_key_set(vcap, &data, VCAP_IS1_HK_VID, tag->vid.value, tag->vid.mask); vcap_key_set(vcap, &data, VCAP_IS1_HK_PCP, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index c601a4598b0d..eb19668a06db 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -13,6 +13,7 @@ */ #define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port)) #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port) ((ocelot)->num_phys_ports + (port)) #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port)) #define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2) @@ -499,6 +500,7 @@ struct ocelot_vcap_key_vlan { struct ocelot_vcap_u8 pcp; /* PCP (3 bit) */ enum ocelot_vcap_bit dei; /* DEI */ enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */ + enum ocelot_vcap_bit tpid; }; struct ocelot_vcap_key_etype { -- cgit v1.2.3 From 6e6f58a170ea98e44075b761f2da42a5aec47dfb Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 13 Aug 2024 16:29:11 +0200 Subject: thermal: gov_bang_bang: Use governor_data to reduce overhead MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After running once, the for_each_trip_desc() loop in bang_bang_manage() is pure needless overhead because it is not going to make any changes unless a new cooling device has been bound to one of the trips in the thermal zone or the system is resuming from sleep. For this reason, make bang_bang_manage() set governor_data for the thermal zone and check it upfront to decide whether or not it needs to do anything. However, governor_data needs to be reset in some cases to let bang_bang_manage() know that it should walk the trips again, so add an .update_tz() callback to the governor and make the core additionally invoke it during system resume. To avoid affecting the other users of that callback unnecessarily, add a special notification reason for system resume, THERMAL_TZ_RESUME, and also pass it to __thermal_zone_device_update() called during system resume for consistency. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Kästle Reviewed-by: Zhang Rui Cc: 6.10+ # 6.10+ Link: https://patch.msgid.link/2285575.iZASKD2KPV@rjwysocki.net --- drivers/thermal/gov_bang_bang.c | 18 ++++++++++++++++++ drivers/thermal/thermal_core.c | 3 ++- include/linux/thermal.h | 1 + 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index bc55e0698bfa..daed67d19efb 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -86,6 +86,10 @@ static void bang_bang_manage(struct thermal_zone_device *tz) const struct thermal_trip_desc *td; struct thermal_instance *instance; + /* If the code below has run already, nothing needs to be done. */ + if (tz->governor_data) + return; + for_each_trip_desc(tz, td) { const struct thermal_trip *trip = &td->trip; @@ -107,11 +111,25 @@ static void bang_bang_manage(struct thermal_zone_device *tz) bang_bang_set_instance_target(instance, 0); } } + + tz->governor_data = (void *)true; +} + +static void bang_bang_update_tz(struct thermal_zone_device *tz, + enum thermal_notify_event reason) +{ + /* + * Let bang_bang_manage() know that it needs to walk trips after binding + * a new cdev and after system resume. + */ + if (reason == THERMAL_TZ_BIND_CDEV || reason == THERMAL_TZ_RESUME) + tz->governor_data = NULL; } static struct thermal_governor thermal_gov_bang_bang = { .name = "bang_bang", .trip_crossed = bang_bang_control, .manage = bang_bang_manage, + .update_tz = bang_bang_update_tz, }; THERMAL_GOVERNOR_DECLARE(thermal_gov_bang_bang); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 95c399f94744..e6669aeda1ff 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1728,7 +1728,8 @@ static void thermal_zone_device_resume(struct work_struct *work) thermal_debug_tz_resume(tz); thermal_zone_device_init(tz); - __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED); + thermal_governor_update_tz(tz, THERMAL_TZ_RESUME); + __thermal_zone_device_update(tz, THERMAL_TZ_RESUME); complete(&tz->resume); tz->resuming = false; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 25fbf960b474..b86ddca46b9e 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -55,6 +55,7 @@ enum thermal_notify_event { THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */ THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */ THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */ + THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */ }; /** -- cgit v1.2.3 From 1fc2ac428ef7d2ab9e8e19efe7ec3e58aea51bf3 Mon Sep 17 00:00:00 2001 From: Caleb Sander Mateos Date: Fri, 16 Aug 2024 12:15:23 -0600 Subject: io_uring: fix user_data field name in comment io_uring_cqe's user_data field refers to `sqe->data`, but io_uring_sqe does not have a data field. Fix the comment to say `sqe->user_data`. Signed-off-by: Caleb Sander Mateos Link: https://github.com/axboe/liburing/pull/1206 Link: https://lore.kernel.org/r/20240816181526.3642732-1-csander@purestorage.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 2aaf7ee256ac..adc2524fd8e3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -421,7 +421,7 @@ enum io_uring_msg_ring_flags { * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { - __u64 user_data; /* sqe->data submission passed back */ + __u64 user_data; /* sqe->user_data value passed back */ __s32 res; /* result code for this event */ __u32 flags; -- cgit v1.2.3 From f03e94f23b04c2b71c0044c1534921b3975ef10c Mon Sep 17 00:00:00 2001 From: Chaotian Jing Date: Tue, 13 Aug 2024 13:34:10 +0800 Subject: scsi: core: Fix the return value of scsi_logical_block_count() scsi_logical_block_count() should return the block count of a given SCSI command. The original implementation ended up shifting twice, leading to an incorrect count being returned. Fix the conversion between bytes and logical blocks. Cc: stable@vger.kernel.org Fixes: 6a20e21ae1e2 ("scsi: core: Add helper to return number of logical blocks in a request") Signed-off-by: Chaotian Jing Link: https://lore.kernel.org/r/20240813053534.7720-1-chaotian.jing@mediatek.com Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 45c40d200154..8ecfb94049db 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -234,7 +234,7 @@ static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd) static inline unsigned int scsi_logical_block_count(struct scsi_cmnd *scmd) { - unsigned int shift = ilog2(scmd->device->sector_size) - SECTOR_SHIFT; + unsigned int shift = ilog2(scmd->device->sector_size); return blk_rq_bytes(scsi_cmd_to_rq(scmd)) >> shift; } -- cgit v1.2.3 From cd06b713a6880997ca5aecac8e33d5f9c541749e Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 16 Aug 2024 11:55:10 +0530 Subject: scsi: ufs: core: Add a quirk for handling broken LSDBS field in controller capabilities register 'Legacy Queue & Single Doorbell Support (LSDBS)' field in the controller capabilities register is supposed to report whether the legacy single doorbell mode is supported in the controller or not. But some controllers report '1' in this field which corresponds to 'LSDB not supported', but they indeed support LSDB. So let's add a quirk to handle those controllers. If the quirk is enabled by the controller driver, then LSDBS register field will be ignored and legacy single doorbell mode is assumed to be enabled always. Tested-by: Amit Pundir Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20240816-ufs-bug-fix-v3-1-e6fe0e18e2a3@linaro.org Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 6 +++++- include/ufs/ufshcd.h | 8 ++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 0b3d0c8e0dda..a6f818cdef0e 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2426,7 +2426,11 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba) * 0h: legacy single doorbell support is available * 1h: indicate that legacy single doorbell support has been removed */ - hba->lsdb_sup = !FIELD_GET(MASK_LSDB_SUPPORT, hba->capabilities); + if (!(hba->quirks & UFSHCD_QUIRK_BROKEN_LSDBS_CAP)) + hba->lsdb_sup = !FIELD_GET(MASK_LSDB_SUPPORT, hba->capabilities); + else + hba->lsdb_sup = true; + if (!hba->mcq_sup) return 0; diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index cac0cdb9a916..0fd2aebac728 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -676,6 +676,14 @@ enum ufshcd_quirks { * the standard best practice for managing keys). */ UFSHCD_QUIRK_KEYS_IN_PRDT = 1 << 24, + + /* + * This quirk indicates that the controller reports the value 1 (not + * supported) in the Legacy Single DoorBell Support (LSDBS) bit of the + * Controller Capabilities register although it supports the legacy + * single doorbell mode. + */ + UFSHCD_QUIRK_BROKEN_LSDBS_CAP = 1 << 25, }; enum ufshcd_caps { -- cgit v1.2.3 From cd8e468efb4fb2742e06328a75b282c35c1abf8d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 14 Aug 2024 21:01:57 +0200 Subject: ACPI: video: Add Dell UART backlight controller detection Dell All In One (AIO) models released after 2017 use a backlight controller board connected to an UART. In DSDT this uart port will be defined as: Name (_HID, "DELL0501") Name (_CID, EisaId ("PNP0501") Commit 484bae9e4d6a ("platform/x86: Add new Dell UART backlight driver") has added support for this, but I neglected to tie this into acpi_video_get_backlight_type(). Now the first AIO has turned up which has not only the DSDT bits for this, but also an actual controller attached to the UART, yet it is not using this controller for backlight control. Add support to acpi_video_get_backlight_type() for a new dell_uart backlight type. So that the existing infra to override the backlight control method on the commandline or with DMI quirks can be used. Fixes: 484bae9e4d6a ("platform/x86: Add new Dell UART backlight driver") Cc: All applicable Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Link: https://patch.msgid.link/20240814190159.15650-2-hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/video_detect.c | 7 +++++++ include/acpi/video.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index c11cbe5b6eaa..e509dcbf3090 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -54,6 +54,8 @@ static void acpi_video_parse_cmdline(void) acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec; if (!strcmp("apple_gmux", acpi_video_backlight_string)) acpi_backlight_cmdline = acpi_backlight_apple_gmux; + if (!strcmp("dell_uart", acpi_video_backlight_string)) + acpi_backlight_cmdline = acpi_backlight_dell_uart; if (!strcmp("none", acpi_video_backlight_string)) acpi_backlight_cmdline = acpi_backlight_none; } @@ -918,6 +920,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto static DEFINE_MUTEX(init_mutex); static bool nvidia_wmi_ec_present; static bool apple_gmux_present; + static bool dell_uart_present; static bool native_available; static bool init_done; static long video_caps; @@ -932,6 +935,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto &video_caps, NULL); nvidia_wmi_ec_present = nvidia_wmi_ec_supported(); apple_gmux_present = apple_gmux_detect(NULL, NULL); + dell_uart_present = acpi_dev_present("DELL0501", NULL, -1); init_done = true; } if (native) @@ -962,6 +966,9 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto if (apple_gmux_present) return acpi_backlight_apple_gmux; + if (dell_uart_present) + return acpi_backlight_dell_uart; + /* Use ACPI video if available, except when native should be preferred. */ if ((video_caps & ACPI_VIDEO_BACKLIGHT) && !(native_available && prefer_native_over_acpi_video())) diff --git a/include/acpi/video.h b/include/acpi/video.h index 3d538d4178ab..044c463138df 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -50,6 +50,7 @@ enum acpi_backlight_type { acpi_backlight_native, acpi_backlight_nvidia_wmi_ec, acpi_backlight_apple_gmux, + acpi_backlight_dell_uart, }; #if IS_ENABLED(CONFIG_ACPI_VIDEO) -- cgit v1.2.3 From ad614a706b1ac83b95b333f44b8f5e70bcb37dc5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 29 Jul 2024 11:26:34 +0200 Subject: drm/xe/oa/uapi: Make bit masks unsigned MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When building with gcc-5: In function ‘decode_oa_format.isra.26’, inlined from ‘xe_oa_set_prop_oa_format’ at drivers/gpu/drm/xe/xe_oa.c:1664:6: ././include/linux/compiler_types.h:510:38: error: call to ‘__compiletime_assert_1336’ declared with attribute error: FIELD_GET: mask is not constant [...] ./include/linux/bitfield.h:155:3: note: in expansion of macro ‘__BF_FIELD_CHECK’ __BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \ ^ drivers/gpu/drm/xe/xe_oa.c:1573:18: note: in expansion of macro ‘FIELD_GET’ u32 bc_report = FIELD_GET(DRM_XE_OA_FORMAT_MASK_BC_REPORT, fmt); ^ Fixes: b6fd51c62119 ("drm/xe/oa/uapi: Define and parse OA stream properties") Signed-off-by: Geert Uytterhoeven Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240729092634.2227611-1-geert+renesas@glider.be Signed-off-by: Lucas De Marchi (cherry picked from commit f2881dfdaaa9ec873dbd383ef5512fc31e576cbb) Signed-off-by: Rodrigo Vivi --- include/uapi/drm/xe_drm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 19619d4952a8..db232a25189e 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -1590,10 +1590,10 @@ enum drm_xe_oa_property_id { * b. Counter select c. Counter size and d. BC report. Also refer to the * oa_formats array in drivers/gpu/drm/xe/xe_oa.c. */ -#define DRM_XE_OA_FORMAT_MASK_FMT_TYPE (0xff << 0) -#define DRM_XE_OA_FORMAT_MASK_COUNTER_SEL (0xff << 8) -#define DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE (0xff << 16) -#define DRM_XE_OA_FORMAT_MASK_BC_REPORT (0xff << 24) +#define DRM_XE_OA_FORMAT_MASK_FMT_TYPE (0xffu << 0) +#define DRM_XE_OA_FORMAT_MASK_COUNTER_SEL (0xffu << 8) +#define DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE (0xffu << 16) +#define DRM_XE_OA_FORMAT_MASK_BC_REPORT (0xffu << 24) /** * @DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT: Requests periodic OA unit -- cgit v1.2.3 From 81475beb1b5996505a39cd1d9316ce1e668932a2 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 15 Aug 2024 16:32:28 +0000 Subject: block: Drop NULL check in bdev_write_zeroes_sectors() Function bdev_get_queue() must not return NULL, so drop the check in bdev_write_zeroes_sectors(). Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Reviewed-by: Martin K. Petersen Reviewed-by: Nitesh Shetty Link: https://lore.kernel.org/r/20240815163228.216051-3-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e85ec73a07d5..b7664d593486 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1296,12 +1296,7 @@ bdev_max_secure_erase_sectors(struct block_device *bdev) static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return bdev_get_queue(bdev)->limits.max_write_zeroes_sectors; } static inline bool bdev_nonrot(struct block_device *bdev) -- cgit v1.2.3 From dc0112e6d8b42b39f9d283bab489a757e9d284f0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 12 Aug 2024 11:47:59 -0400 Subject: rpcrdma: Trace connection registration and unregistration These new trace points record xarray indices and the time of endpoint registration and unregistration, to co-ordinate with device removal events. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 36 ++++++++++++++++++++++++++++++++++++ net/sunrpc/xprtrdma/ib_client.c | 2 ++ 2 files changed, 38 insertions(+) (limited to 'include') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index ba2d6a0e41cc..a96a985c49b3 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -2277,6 +2277,42 @@ DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one); DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_wait_on); DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one_done); +DECLARE_EVENT_CLASS(rpcrdma_client_register_class, + TP_PROTO( + const struct ib_device *device, + const struct rpcrdma_notification *rn + ), + + TP_ARGS(device, rn), + + TP_STRUCT__entry( + __string(name, device->name) + __field(void *, callback) + __field(u32, index) + ), + + TP_fast_assign( + __assign_str(name); + __entry->callback = rn->rn_done; + __entry->index = rn->rn_index; + ), + + TP_printk("device=%s index=%u done callback=%pS\n", + __get_str(name), __entry->index, __entry->callback + ) +); + +#define DEFINE_CLIENT_REGISTER_EVENT(name) \ + DEFINE_EVENT(rpcrdma_client_register_class, name, \ + TP_PROTO( \ + const struct ib_device *device, \ + const struct rpcrdma_notification *rn \ + ), \ + TP_ARGS(device, rn)) + +DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_register); +DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_unregister); + #endif /* _TRACE_RPCRDMA_H */ #include diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c index 7913d7bad23d..8507cd4d8921 100644 --- a/net/sunrpc/xprtrdma/ib_client.c +++ b/net/sunrpc/xprtrdma/ib_client.c @@ -66,6 +66,7 @@ int rpcrdma_rn_register(struct ib_device *device, return -ENOMEM; kref_get(&rd->rd_kref); rn->rn_done = done; + trace_rpcrdma_client_register(device, rn); return 0; } @@ -91,6 +92,7 @@ void rpcrdma_rn_unregister(struct ib_device *device, if (!rd) return; + trace_rpcrdma_client_unregister(device, rn); xa_erase(&rd->rd_xa, rn->rn_index); kref_put(&rd->rd_kref, rpcrdma_rn_release); } -- cgit v1.2.3 From 807067bf014d4a3ae2cc55bd3de16f22a01eb580 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 15 Aug 2024 15:04:37 -0700 Subject: kcm: Serialise kcm_sendmsg() for the same socket. syzkaller reported UAF in kcm_release(). [0] The scenario is 1. Thread A builds a skb with MSG_MORE and sets kcm->seq_skb. 2. Thread A resumes building skb from kcm->seq_skb but is blocked by sk_stream_wait_memory() 3. Thread B calls sendmsg() concurrently, finishes building kcm->seq_skb and puts the skb to the write queue 4. Thread A faces an error and finally frees skb that is already in the write queue 5. kcm_release() does double-free the skb in the write queue When a thread is building a MSG_MORE skb, another thread must not touch it. Let's add a per-sk mutex and serialise kcm_sendmsg(). [0]: BUG: KASAN: slab-use-after-free in __skb_unlink include/linux/skbuff.h:2366 [inline] BUG: KASAN: slab-use-after-free in __skb_dequeue include/linux/skbuff.h:2385 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge include/linux/skbuff.h:3181 [inline] BUG: KASAN: slab-use-after-free in kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 Read of size 8 at addr ffff0000ced0fc80 by task syz-executor329/6167 CPU: 1 PID: 6167 Comm: syz-executor329 Tainted: G B 6.8.0-rc5-syzkaller-g9abbc24128bc #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 Call trace: dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:291 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:298 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:377 [inline] print_report+0x178/0x518 mm/kasan/report.c:488 kasan_report+0xd8/0x138 mm/kasan/report.c:601 __asan_report_load8_noabort+0x20/0x2c mm/kasan/report_generic.c:381 __skb_unlink include/linux/skbuff.h:2366 [inline] __skb_dequeue include/linux/skbuff.h:2385 [inline] __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] __skb_queue_purge include/linux/skbuff.h:3181 [inline] kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Allocated by task 6166: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_alloc_info+0x70/0x84 mm/kasan/generic.c:626 unpoison_slab_object mm/kasan/common.c:314 [inline] __kasan_slab_alloc+0x74/0x8c mm/kasan/common.c:340 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slub.c:3813 [inline] slab_alloc_node mm/slub.c:3860 [inline] kmem_cache_alloc_node+0x204/0x4c0 mm/slub.c:3903 __alloc_skb+0x19c/0x3d8 net/core/skbuff.c:641 alloc_skb include/linux/skbuff.h:1296 [inline] kcm_sendmsg+0x1d3c/0x2124 net/kcm/kcmsock.c:783 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg net/socket.c:745 [inline] sock_sendmsg+0x220/0x2c0 net/socket.c:768 splice_to_socket+0x7cc/0xd58 fs/splice.c:889 do_splice_from fs/splice.c:941 [inline] direct_splice_actor+0xec/0x1d8 fs/splice.c:1164 splice_direct_to_actor+0x438/0xa0c fs/splice.c:1108 do_splice_direct_actor fs/splice.c:1207 [inline] do_splice_direct+0x1e4/0x304 fs/splice.c:1233 do_sendfile+0x460/0xb3c fs/read_write.c:1295 __do_sys_sendfile64 fs/read_write.c:1362 [inline] __se_sys_sendfile64 fs/read_write.c:1348 [inline] __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1348 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Freed by task 6167: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_free_info+0x5c/0x74 mm/kasan/generic.c:640 poison_slab_object+0x124/0x18c mm/kasan/common.c:241 __kasan_slab_free+0x3c/0x78 mm/kasan/common.c:257 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2121 [inline] slab_free mm/slub.c:4299 [inline] kmem_cache_free+0x15c/0x3d4 mm/slub.c:4363 kfree_skbmem+0x10c/0x19c __kfree_skb net/core/skbuff.c:1109 [inline] kfree_skb_reason+0x240/0x6f4 net/core/skbuff.c:1144 kfree_skb include/linux/skbuff.h:1244 [inline] kcm_release+0x104/0x4c8 net/kcm/kcmsock.c:1685 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The buggy address belongs to the object at ffff0000ced0fc80 which belongs to the cache skbuff_head_cache of size 240 The buggy address is located 0 bytes inside of freed 240-byte region [ffff0000ced0fc80, ffff0000ced0fd70) The buggy address belongs to the physical page: page:00000000d35f4ae4 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10ed0f flags: 0x5ffc00000000800(slab|node=0|zone=2|lastcpupid=0x7ff) page_type: 0xffffffff() raw: 05ffc00000000800 ffff0000c1cbf640 fffffdffc3423100 dead000000000004 raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff0000ced0fb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff0000ced0fc00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff0000ced0fc80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff0000ced0fd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc ffff0000ced0fd80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-by: syzbot+b72d86aa5df17ce74c60@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b72d86aa5df17ce74c60 Tested-by: syzbot+b72d86aa5df17ce74c60@syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240815220437.69511-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/kcm.h | 1 + net/kcm/kcmsock.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/kcm.h b/include/net/kcm.h index 90279e5e09a5..441e993be634 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 2f191e50d4fc..d4118c796290 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -926,6 +927,7 @@ partial_message: KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -951,6 +953,7 @@ out_error: sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); -- cgit v1.2.3 From ea72ce5da22806d5713f3ffb39a6d5ae73841f93 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 14 Aug 2024 00:29:36 +0200 Subject: x86/kaslr: Expose and use the end of the physical memory address space iounmap() on x86 occasionally fails to unmap because the provided valid ioremap address is not below high_memory. It turned out that this happens due to KASLR. KASLR uses the full address space between PAGE_OFFSET and vaddr_end to randomize the starting points of the direct map, vmalloc and vmemmap regions. It thereby limits the size of the direct map by using the installed memory size plus an extra configurable margin for hot-plug memory. This limitation is done to gain more randomization space because otherwise only the holes between the direct map, vmalloc, vmemmap and vaddr_end would be usable for randomizing. The limited direct map size is not exposed to the rest of the kernel, so the memory hot-plug and resource management related code paths still operate under the assumption that the available address space can be determined with MAX_PHYSMEM_BITS. request_free_mem_region() allocates from (1 << MAX_PHYSMEM_BITS) - 1 downwards. That means the first allocation happens past the end of the direct map and if unlucky this address is in the vmalloc space, which causes high_memory to become greater than VMALLOC_START and consequently causes iounmap() to fail for valid ioremap addresses. MAX_PHYSMEM_BITS cannot be changed for that because the randomization does not align with address bit boundaries and there are other places which actually require to know the maximum number of address bits. All remaining usage sites of MAX_PHYSMEM_BITS have been analyzed and found to be correct. Cure this by exposing the end of the direct map via PHYSMEM_END and use that for the memory hot-plug and resource management related places instead of relying on MAX_PHYSMEM_BITS. In the KASLR case PHYSMEM_END maps to a variable which is initialized by the KASLR initialization and otherwise it is based on MAX_PHYSMEM_BITS as before. To prevent future hickups add a check into add_pages() to catch callers trying to add memory above PHYSMEM_END. Fixes: 0483e1fa6e09 ("x86/mm: Implement ASLR for kernel memory regions") Reported-by: Max Ramanouski Reported-by: Alistair Popple Signed-off-by: Thomas Gleixner Tested-By: Max Ramanouski Tested-by: Alistair Popple Reviewed-by: Dan Williams Reviewed-by: Alistair Popple Reviewed-by: Kees Cook Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/87ed6soy3z.ffs@tglx --- arch/x86/include/asm/page_64.h | 1 + arch/x86/include/asm/pgtable_64_types.h | 4 ++++ arch/x86/mm/init_64.c | 4 ++++ arch/x86/mm/kaslr.c | 32 ++++++++++++++++++++++++++------ include/linux/mm.h | 4 ++++ kernel/resource.c | 6 ++---- mm/memory_hotplug.c | 2 +- mm/sparse.c | 2 +- 8 files changed, 43 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index af4302d79b59..f3d257c45225 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -17,6 +17,7 @@ extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; +extern unsigned long physmem_end; static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 9053dfe9fa03..a98e53491a4e 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -140,6 +140,10 @@ extern unsigned int ptrs_per_p4d; # define VMEMMAP_START __VMEMMAP_BASE_L4 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ +#ifdef CONFIG_RANDOMIZE_MEMORY +# define PHYSMEM_END physmem_end +#endif + /* * End of the region for which vmalloc page tables are pre-allocated. * For non-KMSAN builds, this is the same as VMALLOC_END. diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index d8dbeac8b206..ff253648706f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -958,8 +958,12 @@ static void update_end_of_memory_vars(u64 start, u64 size) int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params) { + unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1; int ret; + if (WARN_ON_ONCE(end > PHYSMEM_END)) + return -ERANGE; + ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 37db264866b6..230f1dee4f09 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE; */ static __initdata struct kaslr_memory_region { unsigned long *base; + unsigned long *end; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 0 }, - { &vmalloc_base, 0 }, - { &vmemmap_base, 0 }, + { + .base = &page_offset_base, + .end = &physmem_end, + }, + { + .base = &vmalloc_base, + }, + { + .base = &vmemmap_base, + }, }; +/* The end of the possible address space for physical memory */ +unsigned long physmem_end __ro_after_init; + /* Get size in bytes used by the memory region */ static inline unsigned long get_padding(struct kaslr_memory_region *region) { @@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void) BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE); BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); + /* Preset the end of the possible address space for physical memory */ + physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1); if (!kaslr_memory_enabled()) return; @@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void) vaddr += entropy; *kaslr_regions[i].base = vaddr; + /* Calculate the end of the region */ + vaddr += get_padding(&kaslr_regions[i]); /* - * Jump the region and add a minimum padding based on - * randomization alignment. + * KASLR trims the maximum possible size of the + * direct-map. Update the physmem_end boundary. + * No rounding required as the region starts + * PUD aligned and size is in units of TB. */ - vaddr += get_padding(&kaslr_regions[i]); + if (kaslr_regions[i].end) + *kaslr_regions[i].end = __pa_nodebug(vaddr - 1); + + /* Add a minimum padding based on randomization alignment. */ vaddr = round_up(vaddr + 1, PUD_SIZE); remain_entropy -= entropy; } diff --git a/include/linux/mm.h b/include/linux/mm.h index c4b238a20b76..b3864156eaa4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -97,6 +97,10 @@ extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif +#ifndef PHYSMEM_END +# define PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) +#endif + #include #include diff --git a/kernel/resource.c b/kernel/resource.c index 14777afb0a99..a83040fde236 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1826,8 +1826,7 @@ static resource_size_t gfr_start(struct resource *base, resource_size_t size, if (flags & GFR_DESCENDING) { resource_size_t end; - end = min_t(resource_size_t, base->end, - (1ULL << MAX_PHYSMEM_BITS) - 1); + end = min_t(resource_size_t, base->end, PHYSMEM_END); return end - size + 1; } @@ -1844,8 +1843,7 @@ static bool gfr_continue(struct resource *base, resource_size_t addr, * @size did not wrap 0. */ return addr > addr - size && - addr <= min_t(resource_size_t, base->end, - (1ULL << MAX_PHYSMEM_BITS) - 1); + addr <= min_t(resource_size_t, base->end, PHYSMEM_END); } static resource_size_t gfr_next(resource_size_t addr, resource_size_t size, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 66267c26ca1b..951878ab627a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1681,7 +1681,7 @@ struct range __weak arch_get_mappable_range(void) struct range mhp_get_pluggable_range(bool need_mapping) { - const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1; + const u64 max_phys = PHYSMEM_END; struct range mhp_range; if (need_mapping) { diff --git a/mm/sparse.c b/mm/sparse.c index e4b830091d13..0c3bff882033 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -129,7 +129,7 @@ static inline int sparse_early_nid(struct mem_section *section) static void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn) { - unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT); + unsigned long max_sparsemem_pfn = (PHYSMEM_END + 1) >> PAGE_SHIFT; /* * Sanity checks - do not allow an architecture to pass -- cgit v1.2.3 From 3568affcddd68743e25aa3ec1647d9b82797757b Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 20 Aug 2024 13:29:30 -0700 Subject: soc: qcom: pmic_glink: Fix race during initialization As pointed out by Stephen Boyd it is possible that during initialization of the pmic_glink child drivers, the protection-domain notifiers fires, and the associated work is scheduled, before the client registration returns and as a result the local "client" pointer has been initialized. The outcome of this is a NULL pointer dereference as the "client" pointer is blindly dereferenced. Timeline provided by Stephen: CPU0 CPU1 ---- ---- ucsi->client = NULL; devm_pmic_glink_register_client() client->pdr_notify(client->priv, pg->client_state) pmic_glink_ucsi_pdr_notify() schedule_work(&ucsi->register_work) pmic_glink_ucsi_register() ucsi_register() pmic_glink_ucsi_read_version() pmic_glink_ucsi_read() pmic_glink_ucsi_read() pmic_glink_send(ucsi->client) ucsi->client = client // Too late! This code is identical across the altmode, battery manager and usci child drivers. Resolve this by splitting the allocation of the "client" object and the registration thereof into two operations. This only happens if the protection domain registry is populated at the time of registration, which by the introduction of commit '1ebcde047c54 ("soc: qcom: add pd-mapper implementation")' became much more likely. Reported-by: Amit Pundir Closes: https://lore.kernel.org/all/CAMi1Hd2_a7TjA7J9ShrAbNOd_CoZ3D87twmO5t+nZxC9sX18tA@mail.gmail.com/ Reported-by: Johan Hovold Closes: https://lore.kernel.org/all/ZqiyLvP0gkBnuekL@hovoldconsulting.com/ Reported-by: Stephen Boyd Closes: https://lore.kernel.org/all/CAE-0n52JgfCBWiFQyQWPji8cq_rCsviBpW-m72YitgNfdaEhQg@mail.gmail.com/ Fixes: 58ef4ece1e41 ("soc: qcom: pmic_glink: Introduce base PMIC GLINK driver") Cc: stable@vger.kernel.org Reviewed-by: Heikki Krogerus Reviewed-by: Neil Armstrong Tested-by: Amit Pundir Reviewed-by: Johan Hovold Acked-by: Sebastian Reichel Tested-by: Johan Hovold Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20240820-pmic-glink-v6-11-races-v3-1-eec53c750a04@quicinc.com Signed-off-by: Bjorn Andersson --- drivers/power/supply/qcom_battmgr.c | 16 ++++++++++------ drivers/soc/qcom/pmic_glink.c | 28 ++++++++++++++++++---------- drivers/soc/qcom/pmic_glink_altmode.c | 17 +++++++++++------ drivers/usb/typec/ucsi/ucsi_glink.c | 16 ++++++++++------ include/linux/soc/qcom/pmic_glink.h | 11 ++++++----- 5 files changed, 55 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index 46f36dcb185c..7cf19a39d986 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -1385,12 +1385,16 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev, "failed to register wireless charing power supply\n"); } - battmgr->client = devm_pmic_glink_register_client(dev, - PMIC_GLINK_OWNER_BATTMGR, - qcom_battmgr_callback, - qcom_battmgr_pdr_notify, - battmgr); - return PTR_ERR_OR_ZERO(battmgr->client); + battmgr->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_BATTMGR, + qcom_battmgr_callback, + qcom_battmgr_pdr_notify, + battmgr); + if (IS_ERR(battmgr->client)) + return PTR_ERR(battmgr->client); + + pmic_glink_client_register(battmgr->client); + + return 0; } static const struct auxiliary_device_id qcom_battmgr_id_table[] = { diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c index 9ebc0ba35947..53b176d04fbd 100644 --- a/drivers/soc/qcom/pmic_glink.c +++ b/drivers/soc/qcom/pmic_glink.c @@ -66,15 +66,14 @@ static void _devm_pmic_glink_release_client(struct device *dev, void *res) spin_unlock_irqrestore(&pg->client_lock, flags); } -struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, - unsigned int id, - void (*cb)(const void *, size_t, void *), - void (*pdr)(void *, int), - void *priv) +struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv) { struct pmic_glink_client *client; struct pmic_glink *pg = dev_get_drvdata(dev->parent); - unsigned long flags; client = devres_alloc(_devm_pmic_glink_release_client, sizeof(*client), GFP_KERNEL); if (!client) @@ -85,6 +84,18 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, client->cb = cb; client->pdr_notify = pdr; client->priv = priv; + INIT_LIST_HEAD(&client->node); + + devres_add(dev, client); + + return client; +} +EXPORT_SYMBOL_GPL(devm_pmic_glink_client_alloc); + +void pmic_glink_client_register(struct pmic_glink_client *client) +{ + struct pmic_glink *pg = client->pg; + unsigned long flags; mutex_lock(&pg->state_lock); spin_lock_irqsave(&pg->client_lock, flags); @@ -95,11 +106,8 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, spin_unlock_irqrestore(&pg->client_lock, flags); mutex_unlock(&pg->state_lock); - devres_add(dev, client); - - return client; } -EXPORT_SYMBOL_GPL(devm_pmic_glink_register_client); +EXPORT_SYMBOL_GPL(pmic_glink_client_register); int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len) { diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c index 1e0808b3cb93..463b1c528831 100644 --- a/drivers/soc/qcom/pmic_glink_altmode.c +++ b/drivers/soc/qcom/pmic_glink_altmode.c @@ -520,12 +520,17 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, return ret; } - altmode->client = devm_pmic_glink_register_client(dev, - altmode->owner_id, - pmic_glink_altmode_callback, - pmic_glink_altmode_pdr_notify, - altmode); - return PTR_ERR_OR_ZERO(altmode->client); + altmode->client = devm_pmic_glink_client_alloc(dev, + altmode->owner_id, + pmic_glink_altmode_callback, + pmic_glink_altmode_pdr_notify, + altmode); + if (IS_ERR(altmode->client)) + return PTR_ERR(altmode->client); + + pmic_glink_client_register(altmode->client); + + return 0; } static const struct auxiliary_device_id pmic_glink_altmode_id_table[] = { diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index 16c328497e0b..f6f4fae40399 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -367,12 +367,16 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev, ucsi->port_orientation[port] = desc; } - ucsi->client = devm_pmic_glink_register_client(dev, - PMIC_GLINK_OWNER_USBC, - pmic_glink_ucsi_callback, - pmic_glink_ucsi_pdr_notify, - ucsi); - return PTR_ERR_OR_ZERO(ucsi->client); + ucsi->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_USBC, + pmic_glink_ucsi_callback, + pmic_glink_ucsi_pdr_notify, + ucsi); + if (IS_ERR(ucsi->client)) + return PTR_ERR(ucsi->client); + + pmic_glink_client_register(ucsi->client); + + return 0; } static void pmic_glink_ucsi_remove(struct auxiliary_device *adev) diff --git a/include/linux/soc/qcom/pmic_glink.h b/include/linux/soc/qcom/pmic_glink.h index fd124aa18c81..7cddf1027752 100644 --- a/include/linux/soc/qcom/pmic_glink.h +++ b/include/linux/soc/qcom/pmic_glink.h @@ -23,10 +23,11 @@ struct pmic_glink_hdr { int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len); -struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev, - unsigned int id, - void (*cb)(const void *, size_t, void *), - void (*pdr)(void *, int), - void *priv); +struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev, + unsigned int id, + void (*cb)(const void *, size_t, void *), + void (*pdr)(void *, int), + void *priv); +void pmic_glink_client_register(struct pmic_glink_client *client); #endif -- cgit v1.2.3 From b58b133e680b20d219940e0fdb6f6132c2b60f38 Mon Sep 17 00:00:00 2001 From: Pranjal Shrivastava Date: Fri, 16 Aug 2024 10:49:06 +0000 Subject: iommu: Handle iommu faults for a bad iopf setup The iommu_report_device_fault function was updated to return void while assuming that drivers only need to call iommu_report_device_fault() for reporting an iopf. This implementation causes following problems: 1. The drivers rely on the core code to call it's page_reponse, however, when a fault is received and no fault capable domain is attached / iopf_param is NULL, the ops->page_response is NOT called causing the device to stall in case the fault type was PAGE_REQ. 2. The arm_smmu_v3 driver relies on the returned value to log errors returning void from iommu_report_device_fault causes these events to be missed while logging. Modify the iommu_report_device_fault function to return -EINVAL for cases where no fault capable domain is attached or iopf_param was NULL and calls back to the driver (ops->page_response) in case the fault type was IOMMU_FAULT_PAGE_REQ. The returned value can be used by the drivers to log the fault/event as needed. Reported-by: Kunkun Jiang Closes: https://lore.kernel.org/all/6147caf0-b9a0-30ca-795e-a1aa502a5c51@huawei.com/ Fixes: 3dfa64aecbaf ("iommu: Make iommu_report_device_fault() return void") Signed-off-by: Jason Gunthorpe Signed-off-by: Pranjal Shrivastava Reviewed-by: Jason Gunthorpe Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20240816104906.1010626-1-praan@google.com Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- drivers/iommu/io-pgfault.c | 121 +++++++++++++++++++--------- include/linux/iommu.h | 5 +- 3 files changed, 87 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index a31460f9f3d4..ed2b106e02dd 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1777,7 +1777,7 @@ static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt) goto out_unlock; } - iommu_report_device_fault(master->dev, &fault_evt); + ret = iommu_report_device_fault(master->dev, &fault_evt); out_unlock: mutex_unlock(&smmu->streams_mutex); return ret; diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 81e9cc6e3164..4674e618797c 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -115,6 +115,59 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param, return group; } +static struct iommu_attach_handle *find_fault_handler(struct device *dev, + struct iopf_fault *evt) +{ + struct iommu_fault *fault = &evt->fault; + struct iommu_attach_handle *attach_handle; + + if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) { + attach_handle = iommu_attach_handle_get(dev->iommu_group, + fault->prm.pasid, 0); + if (IS_ERR(attach_handle)) { + const struct iommu_ops *ops = dev_iommu_ops(dev); + + if (!ops->user_pasid_table) + return NULL; + /* + * The iommu driver for this device supports user- + * managed PASID table. Therefore page faults for + * any PASID should go through the NESTING domain + * attached to the device RID. + */ + attach_handle = iommu_attach_handle_get( + dev->iommu_group, IOMMU_NO_PASID, + IOMMU_DOMAIN_NESTED); + if (IS_ERR(attach_handle)) + return NULL; + } + } else { + attach_handle = iommu_attach_handle_get(dev->iommu_group, + IOMMU_NO_PASID, 0); + + if (IS_ERR(attach_handle)) + return NULL; + } + + if (!attach_handle->domain->iopf_handler) + return NULL; + + return attach_handle; +} + +static void iopf_error_response(struct device *dev, struct iopf_fault *evt) +{ + const struct iommu_ops *ops = dev_iommu_ops(dev); + struct iommu_fault *fault = &evt->fault; + struct iommu_page_response resp = { + .pasid = fault->prm.pasid, + .grpid = fault->prm.grpid, + .code = IOMMU_PAGE_RESP_INVALID + }; + + ops->page_response(dev, evt, &resp); +} + /** * iommu_report_device_fault() - Report fault event to device driver * @dev: the device @@ -153,24 +206,39 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param, * handling framework should guarantee that the iommu domain could only be * freed after the device has stopped generating page faults (or the iommu * hardware has been set to block the page faults) and the pending page faults - * have been flushed. + * have been flushed. In case no page fault handler is attached or no iopf params + * are setup, then the ops->page_response() is called to complete the evt. + * + * Returns 0 on success, or an error in case of a bad/failed iopf setup. */ -void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) +int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) { + struct iommu_attach_handle *attach_handle; struct iommu_fault *fault = &evt->fault; struct iommu_fault_param *iopf_param; struct iopf_group abort_group = {}; struct iopf_group *group; + attach_handle = find_fault_handler(dev, evt); + if (!attach_handle) + goto err_bad_iopf; + + /* + * Something has gone wrong if a fault capable domain is attached but no + * iopf_param is setup + */ iopf_param = iopf_get_dev_fault_param(dev); if (WARN_ON(!iopf_param)) - return; + goto err_bad_iopf; if (!(fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) { - report_partial_fault(iopf_param, fault); + int ret; + + ret = report_partial_fault(iopf_param, fault); iopf_put_dev_fault_param(iopf_param); /* A request that is not the last does not need to be ack'd */ - return; + + return ret; } /* @@ -185,38 +253,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) if (group == &abort_group) goto err_abort; - if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) { - group->attach_handle = iommu_attach_handle_get(dev->iommu_group, - fault->prm.pasid, - 0); - if (IS_ERR(group->attach_handle)) { - const struct iommu_ops *ops = dev_iommu_ops(dev); - - if (!ops->user_pasid_table) - goto err_abort; - - /* - * The iommu driver for this device supports user- - * managed PASID table. Therefore page faults for - * any PASID should go through the NESTING domain - * attached to the device RID. - */ - group->attach_handle = - iommu_attach_handle_get(dev->iommu_group, - IOMMU_NO_PASID, - IOMMU_DOMAIN_NESTED); - if (IS_ERR(group->attach_handle)) - goto err_abort; - } - } else { - group->attach_handle = - iommu_attach_handle_get(dev->iommu_group, IOMMU_NO_PASID, 0); - if (IS_ERR(group->attach_handle)) - goto err_abort; - } - - if (!group->attach_handle->domain->iopf_handler) - goto err_abort; + group->attach_handle = attach_handle; /* * On success iopf_handler must call iopf_group_response() and @@ -225,7 +262,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) if (group->attach_handle->domain->iopf_handler(group)) goto err_abort; - return; + return 0; err_abort: dev_warn_ratelimited(dev, "iopf with pasid %d aborted\n", @@ -235,6 +272,14 @@ err_abort: __iopf_free_group(group); else iopf_free_group(group); + + return 0; + +err_bad_iopf: + if (fault->type == IOMMU_FAULT_PAGE_REQ) + iopf_error_response(dev, evt); + + return -EINVAL; } EXPORT_SYMBOL_GPL(iommu_report_device_fault); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 04cbdae0052e..bd722f473635 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1563,7 +1563,7 @@ struct iopf_queue *iopf_queue_alloc(const char *name); void iopf_queue_free(struct iopf_queue *queue); int iopf_queue_discard_partial(struct iopf_queue *queue); void iopf_free_group(struct iopf_group *group); -void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); +int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); void iopf_group_response(struct iopf_group *group, enum iommu_page_response_code status); #else @@ -1601,9 +1601,10 @@ static inline void iopf_free_group(struct iopf_group *group) { } -static inline void +static inline int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt) { + return -ENODEV; } static inline void iopf_group_response(struct iopf_group *group, -- cgit v1.2.3 From c358a809cb58af944d496944391a240e02f5837a Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 20 Aug 2024 09:46:00 -0400 Subject: Revert "drm/ttm: increase ttm pre-fault value to PMD size" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 0ddd2ae586d28e521d37393364d989ce118802e0. This patch causes sluggishness and stuttering in graphical apps. Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3564 Link: https://www.spinics.net/lists/dri-devel/msg457005.html Signed-off-by: Alex Deucher Cc: Zhu Lingshan Cc: Christian König Reviewed-by: Christian König Signed-off-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20240820134600.1909370-1-alexander.deucher@amd.com --- include/drm/ttm/ttm_bo.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo.h b/include/drm/ttm/ttm_bo.h index ef0f52f56ebc..6ccf96c91f3a 100644 --- a/include/drm/ttm/ttm_bo.h +++ b/include/drm/ttm/ttm_bo.h @@ -39,11 +39,7 @@ #include "ttm_device.h" /* Default number of pre-faulted pages in the TTM fault handler */ -#if CONFIG_PGTABLE_LEVELS > 2 -#define TTM_BO_VM_NUM_PREFAULT (1 << (PMD_SHIFT - PAGE_SHIFT)) -#else #define TTM_BO_VM_NUM_PREFAULT 16 -#endif struct iosys_map; -- cgit v1.2.3 From 5fd0628918977a0afdc2e6bc562d8751b5d3b8c5 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 26 Aug 2024 12:45:22 +0200 Subject: netfilter: nf_tables: restore IP sanity checks for netdev/egress Subtract network offset to skb->len before performing IPv4 header sanity checks, then adjust transport offset from offset from mac header. Jorge Ortiz says: When small UDP packets (< 4 bytes payload) are sent from eth0, `meta l4proto udp` condition is not met because `NFT_PKTINFO_L4PROTO` is not set. This happens because there is a comparison that checks if the transport header offset exceeds the total length. This comparison does not take into account the fact that the skb network offset might be non-zero in egress mode (e.g., 14 bytes for Ethernet header). Fixes: 0ae8e4cca787 ("netfilter: nf_tables: set transport offset from mac header for netdev/egress") Reported-by: Jorge Ortiz Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_ipv4.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 60a7d0ce3080..fcf967286e37 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -19,7 +19,7 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt) static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) { struct iphdr *iph, _iph; - u32 len, thoff; + u32 len, thoff, skb_len; iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), sizeof(*iph), &_iph); @@ -30,8 +30,10 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) return -1; len = iph_totlen(pkt->skb, iph); - thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4); - if (pkt->skb->len < len) + thoff = iph->ihl * 4; + skb_len = pkt->skb->len - skb_network_offset(pkt->skb); + + if (skb_len < len) return -1; else if (len < thoff) return -1; @@ -40,7 +42,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = iph->protocol; - pkt->thoff = thoff; + pkt->thoff = skb_network_offset(pkt->skb) + thoff; pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; -- cgit v1.2.3 From f2c6dbd220170c2396fb019ead67fbada1e23ebd Mon Sep 17 00:00:00 2001 From: David Gow Date: Fri, 16 Aug 2024 12:51:22 +0800 Subject: kunit: Device wrappers should also manage driver name kunit_driver_create() accepts a name for the driver, but does not copy it, so if that name is either on the stack, or otherwise freed, we end up with a use-after-free when the driver is cleaned up. Instead, strdup() the name, and manage it as another KUnit allocation. As there was no existing kunit_kstrdup(), we add one. Further, add a kunit_ variant of strdup_const() and kfree_const(), so we don't need to allocate and manage the string in the majority of cases where it's a constant. However, these are inline functions, and is_kernel_rodata() only works for built-in code. This causes problems in two cases: - If kunit is built as a module, __{start,end}_rodata is not defined. - If a kunit test using these functions is built as a module, it will suffer the same fate. This fixes a KASAN splat with overflow.overflow_allocation_test, when built as a module. Restrict the is_kernel_rodata() case to when KUnit is built as a module, which fixes the first case, at the cost of losing the optimisation. Also, make kunit_{kstrdup,kfree}_const non-inline, so that other modules using them will not accidentally depend on is_kernel_rodata(). If KUnit is built-in, they'll benefit from the optimisation, if KUnit is not, they won't, but the string will be properly duplicated. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Reported-by: Nico Pache Closes: https://groups.google.com/g/kunit-dev/c/81V9b9QYON0 Reviewed-by: Kees Cook Reviewed-by: Maxime Ripard Reviewed-by: Rae Moar Signed-off-by: David Gow Tested-by: Rae Moar Signed-off-by: Shuah Khan --- include/kunit/test.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ lib/kunit/device.c | 7 +++++-- lib/kunit/test.c | 19 +++++++++++++++++++ 3 files changed, 72 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index e2a1f0928e8b..5ac237c949a0 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -28,6 +28,7 @@ #include #include +#include /* Static key: true if any KUnit tests are currently running */ DECLARE_STATIC_KEY_FALSE(kunit_running); @@ -480,6 +481,53 @@ static inline void *kunit_kcalloc(struct kunit *test, size_t n, size_t size, gfp return kunit_kmalloc_array(test, n, size, gfp | __GFP_ZERO); } + +/** + * kunit_kfree_const() - conditionally free test managed memory + * @x: pointer to the memory + * + * Calls kunit_kfree() only if @x is not in .rodata section. + * See kunit_kstrdup_const() for more information. + */ +void kunit_kfree_const(struct kunit *test, const void *x); + +/** + * kunit_kstrdup() - Duplicates a string into a test managed allocation. + * + * @test: The test context object. + * @str: The NULL-terminated string to duplicate. + * @gfp: flags passed to underlying kmalloc(). + * + * See kstrdup() and kunit_kmalloc_array() for more information. + */ +static inline char *kunit_kstrdup(struct kunit *test, const char *str, gfp_t gfp) +{ + size_t len; + char *buf; + + if (!str) + return NULL; + + len = strlen(str) + 1; + buf = kunit_kmalloc(test, len, gfp); + if (buf) + memcpy(buf, str, len); + return buf; +} + +/** + * kunit_kstrdup_const() - Conditionally duplicates a string into a test managed allocation. + * + * @test: The test context object. + * @str: The NULL-terminated string to duplicate. + * @gfp: flags passed to underlying kmalloc(). + * + * Calls kunit_kstrdup() only if @str is not in the rodata section. Must be freed with + * kunit_kfree_const() -- not kunit_kfree(). + * See kstrdup_const() and kunit_kmalloc_array() for more information. + */ +const char *kunit_kstrdup_const(struct kunit *test, const char *str, gfp_t gfp); + /** * kunit_vm_mmap() - Allocate KUnit-tracked vm_mmap() area * @test: The test context object. diff --git a/lib/kunit/device.c b/lib/kunit/device.c index 25c81ed465fb..520c1fccee8a 100644 --- a/lib/kunit/device.c +++ b/lib/kunit/device.c @@ -89,7 +89,7 @@ struct device_driver *kunit_driver_create(struct kunit *test, const char *name) if (!driver) return ERR_PTR(err); - driver->name = name; + driver->name = kunit_kstrdup_const(test, name, GFP_KERNEL); driver->bus = &kunit_bus_type; driver->owner = THIS_MODULE; @@ -192,8 +192,11 @@ void kunit_device_unregister(struct kunit *test, struct device *dev) const struct device_driver *driver = to_kunit_device(dev)->driver; kunit_release_action(test, device_unregister_wrapper, dev); - if (driver) + if (driver) { + const char *driver_name = driver->name; kunit_release_action(test, driver_unregister_wrapper, (void *)driver); + kunit_kfree_const(test, driver_name); + } } EXPORT_SYMBOL_GPL(kunit_device_unregister); diff --git a/lib/kunit/test.c b/lib/kunit/test.c index e8b1b52a19ab..089c832e3cdb 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -874,6 +874,25 @@ void kunit_kfree(struct kunit *test, const void *ptr) } EXPORT_SYMBOL_GPL(kunit_kfree); +void kunit_kfree_const(struct kunit *test, const void *x) +{ +#if !IS_MODULE(CONFIG_KUNIT) + if (!is_kernel_rodata((unsigned long)x)) +#endif + kunit_kfree(test, x); +} +EXPORT_SYMBOL_GPL(kunit_kfree_const); + +const char *kunit_kstrdup_const(struct kunit *test, const char *str, gfp_t gfp) +{ +#if !IS_MODULE(CONFIG_KUNIT) + if (is_kernel_rodata((unsigned long)str)) + return str; +#endif + return kunit_kstrdup(test, str, gfp); +} +EXPORT_SYMBOL_GPL(kunit_kstrdup_const); + void kunit_cleanup(struct kunit *test) { struct kunit_resource *res; -- cgit v1.2.3 From 22652022c7eef3c4ad6ab5f13a6dfc7f25f853d4 Mon Sep 17 00:00:00 2001 From: Laurentiu Mihalcea Date: Mon, 26 Aug 2024 14:24:42 -0400 Subject: ASoC: SOF: ipc: replace "enum sof_comp_type" field with "uint32_t" Normally, the type of enums is "unsigned int" or "int". GCC has the "-fshort-enums" option, which instructs the compiler to use the smallest data type that can hold all the values in the enum (i.e: char, short, int or their unsigned variants). According to the GCC documentation, "-fshort-enums" may be default on some targets. This seems to be the case for SOF when built for a certain 32-bit ARM platform. On Linux, this is not the case (tested with "aarch64-linux-gnu-gcc") which means enums such as "enum sof_comp_type" will end up having different sizes on Linux and SOF. Since "enum sof_comp_type" is used in IPC-related structures such as "struct sof_ipc_comp", this means the fields of the structures will end up being placed at different offsets. This, in turn, leads to SOF not being able to properly interpret data passed from Linux. With this in mind, replace "enum sof_comp_type" from "struct sof_ipc_comp" with "uint32_t". Signed-off-by: Laurentiu Mihalcea Reviewed-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Daniel Baluta Link: https://patch.msgid.link/20240826182442.6191-1-laurentiumihalcea111@gmail.com Signed-off-by: Mark Brown --- include/sound/sof/topology.h | 2 +- include/uapi/sound/sof/abi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h index 3ba086f61983..449e93c25184 100644 --- a/include/sound/sof/topology.h +++ b/include/sound/sof/topology.h @@ -54,7 +54,7 @@ enum sof_comp_type { struct sof_ipc_comp { struct sof_ipc_cmd_hdr hdr; uint32_t id; - enum sof_comp_type type; + uint32_t type; uint32_t pipeline_id; uint32_t core; diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h index 937ed9408c23..c1b158ec5dab 100644 --- a/include/uapi/sound/sof/abi.h +++ b/include/uapi/sound/sof/abi.h @@ -29,7 +29,7 @@ /* SOF ABI version major, minor and patch numbers */ #define SOF_ABI_MAJOR 3 #define SOF_ABI_MINOR 23 -#define SOF_ABI_PATCH 0 +#define SOF_ABI_PATCH 1 /* SOF ABI version number. Format within 32bit word is MMmmmppp */ #define SOF_ABI_MAJOR_SHIFT 24 -- cgit v1.2.3 From 7e8ae8486e4471513e2111aba6ac29f2357bed2a Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 26 Aug 2024 10:32:34 -0400 Subject: fs/nfsd: fix update of inode attrs in CB_GETATTR Currently, we copy the mtime and ctime to the in-core inode and then mark the inode dirty. This is fine for certain types of filesystems, but not all. Some require a real setattr to properly change these values (e.g. ceph or reexported NFS). Fix this code to call notify_change() instead, which is the proper way to effect a setattr. There is one problem though: In this case, the client is holding a write delegation and has sent us attributes to update our cache. We don't want to break the delegation for this since that would defeat the purpose. Add a new ATTR_DELEG flag that makes notify_change bypass the try_break_deleg call. Fixes: c5967721e106 ("NFSD: handle GETATTR conflict with write delegation") Reviewed-by: Christian Brauner Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/attr.c | 14 +++++++++++--- fs/nfsd/nfs4state.c | 18 +++++++++++++----- fs/nfsd/nfs4xdr.c | 2 +- fs/nfsd/state.h | 2 +- include/linux/fs.h | 1 + 5 files changed, 27 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/fs/attr.c b/fs/attr.c index 960a310581eb..0dbf43b6555c 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -489,9 +489,17 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, error = security_inode_setattr(idmap, dentry, attr); if (error) return error; - error = try_break_deleg(inode, delegated_inode); - if (error) - return error; + + /* + * If ATTR_DELEG is set, then these attributes are being set on + * behalf of the holder of a write delegation. We want to avoid + * breaking the delegation in this case. + */ + if (!(ia_valid & ATTR_DELEG)) { + error = try_break_deleg(inode, delegated_inode); + if (error) + return error; + } if (inode->i_op->setattr) error = inode->i_op->setattr(idmap, dentry, attr); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 02d43f95146e..07f2496850c4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -8815,7 +8815,7 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, /** * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict * @rqstp: RPC transaction context - * @inode: file to be checked for a conflict + * @dentry: dentry of inode to be checked for a conflict * @modified: return true if file was modified * @size: new size of file if modified is true * @@ -8830,7 +8830,7 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, * code is returned. */ __be32 -nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode, +nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, bool *modified, u64 *size) { __be32 status; @@ -8839,6 +8839,7 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode, struct file_lease *fl; struct iattr attrs; struct nfs4_cb_fattr *ncf; + struct inode *inode = d_inode(dentry); *modified = false; ctx = locks_inode_context(inode); @@ -8890,15 +8891,22 @@ break_lease: ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) ncf->ncf_file_modified = true; if (ncf->ncf_file_modified) { + int err; + /* * Per section 10.4.3 of RFC 8881, the server would * not update the file's metadata with the client's * modified size */ attrs.ia_mtime = attrs.ia_ctime = current_time(inode); - attrs.ia_valid = ATTR_MTIME | ATTR_CTIME; - setattr_copy(&nop_mnt_idmap, inode, &attrs); - mark_inode_dirty(inode); + attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG; + inode_lock(inode); + err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); + inode_unlock(inode); + if (err) { + nfs4_put_stid(&dp->dl_stid); + return nfserrno(err); + } ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; *size = ncf->ncf_cur_fsize; *modified = true; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 43ccf6119cf1..97f583777972 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3565,7 +3565,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, } args.size = 0; if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { - status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry), + status = nfsd4_deleg_getattr_conflict(rqstp, dentry, &file_modified, &size); if (status) goto out; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index ffc217099d19..ec4559ecd193 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -781,5 +781,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp) } extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, - struct inode *inode, bool *file_modified, u64 *size); + struct dentry *dentry, bool *file_modified, u64 *size); #endif /* NFSD4_STATE_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 0283cf366c2a..bafc1d134b94 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -208,6 +208,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) +#define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ /* * Whiteout is represented by a char device. The following constants define the -- cgit v1.2.3 From b49420d6a1aeb399e5b107fc6eb8584d0860fbd7 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 21 Aug 2024 15:11:35 -0400 Subject: video/aperture: optionally match the device in sysfb_disable() In aperture_remove_conflicting_pci_devices(), we currently only call sysfb_disable() on vga class devices. This leads to the following problem when the pimary device is not VGA compatible: 1. A PCI device with a non-VGA class is the boot display 2. That device is probed first and it is not a VGA device so sysfb_disable() is not called, but the device resources are freed by aperture_detach_platform_device() 3. Non-primary GPU has a VGA class and it ends up calling sysfb_disable() 4. NULL pointer dereference via sysfb_disable() since the resources have already been freed by aperture_detach_platform_device() when it was called by the other device. Fix this by passing a device pointer to sysfb_disable() and checking the device to determine if we should execute it or not. v2: Fix build when CONFIG_SCREEN_INFO is not set v3: Move device check into the mutex Drop primary variable in aperture_remove_conflicting_pci_devices() Drop __init on pci sysfb_pci_dev_is_enabled() Fixes: 5ae3716cfdcd ("video/aperture: Only remove sysfb on the default vga pci device") Cc: Javier Martinez Canillas Cc: Thomas Zimmermann Cc: Helge Deller Cc: Sam Ravnborg Cc: Daniel Vetter Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Reviewed-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Signed-off-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20240821191135.829765-1-alexander.deucher@amd.com --- drivers/firmware/sysfb.c | 19 +++++++++++++------ drivers/of/platform.c | 2 +- drivers/video/aperture.c | 11 +++-------- include/linux/sysfb.h | 4 ++-- 4 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 921f61507ae8..02a07d3d0d40 100644 --- a/drivers/firmware/sysfb.c +++ b/drivers/firmware/sysfb.c @@ -39,6 +39,8 @@ static struct platform_device *pd; static DEFINE_MUTEX(disable_lock); static bool disabled; +static struct device *sysfb_parent_dev(const struct screen_info *si); + static bool sysfb_unregister(void) { if (IS_ERR_OR_NULL(pd)) @@ -52,6 +54,7 @@ static bool sysfb_unregister(void) /** * sysfb_disable() - disable the Generic System Framebuffers support + * @dev: the device to check if non-NULL * * This disables the registration of system framebuffer devices that match the * generic drivers that make use of the system framebuffer set up by firmware. @@ -61,17 +64,21 @@ static bool sysfb_unregister(void) * Context: The function can sleep. A @disable_lock mutex is acquired to serialize * against sysfb_init(), that registers a system framebuffer device. */ -void sysfb_disable(void) +void sysfb_disable(struct device *dev) { + struct screen_info *si = &screen_info; + mutex_lock(&disable_lock); - sysfb_unregister(); - disabled = true; + if (!dev || dev == sysfb_parent_dev(si)) { + sysfb_unregister(); + disabled = true; + } mutex_unlock(&disable_lock); } EXPORT_SYMBOL_GPL(sysfb_disable); #if defined(CONFIG_PCI) -static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) +static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) { /* * TODO: Try to integrate this code into the PCI subsystem @@ -87,13 +94,13 @@ static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) return true; } #else -static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) +static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev) { return false; } #endif -static __init struct device *sysfb_parent_dev(const struct screen_info *si) +static struct device *sysfb_parent_dev(const struct screen_info *si) { struct pci_dev *pdev; diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 389d4ea6bfc1..ef622d41eb5b 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -592,7 +592,7 @@ static int __init of_platform_default_populate_init(void) * This can happen for example on DT systems that do EFI * booting and may provide a GOP handle to the EFI stub. */ - sysfb_disable(); + sysfb_disable(NULL); of_platform_device_create(node, NULL, NULL); of_node_put(node); } diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c index 561be8feca96..2b5a1e666e9b 100644 --- a/drivers/video/aperture.c +++ b/drivers/video/aperture.c @@ -293,7 +293,7 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si * ask for this, so let's assume that a real driver for the display * was already probed and prevent sysfb to register devices later. */ - sysfb_disable(); + sysfb_disable(NULL); aperture_detach_devices(base, size); @@ -346,15 +346,10 @@ EXPORT_SYMBOL(__aperture_remove_legacy_vga_devices); */ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name) { - bool primary = false; resource_size_t base, size; int bar, ret = 0; - if (pdev == vga_default_device()) - primary = true; - - if (primary) - sysfb_disable(); + sysfb_disable(&pdev->dev); for (bar = 0; bar < PCI_STD_NUM_BARS; ++bar) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) @@ -370,7 +365,7 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na * that consumes the VGA framebuffer I/O range. Remove this * device as well. */ - if (primary) + if (pdev == vga_default_device()) ret = __aperture_remove_legacy_vga_devices(pdev); return ret; diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index c9cb657dad08..bef5f06a91de 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -58,11 +58,11 @@ struct efifb_dmi_info { #ifdef CONFIG_SYSFB -void sysfb_disable(void); +void sysfb_disable(struct device *dev); #else /* CONFIG_SYSFB */ -static inline void sysfb_disable(void) +static inline void sysfb_disable(struct device *dev) { } -- cgit v1.2.3 From 2955ae8186c8a6f029e429f7890e0c7e5f6e215e Mon Sep 17 00:00:00 2001 From: John Harrison Date: Thu, 1 Aug 2024 20:10:51 -0700 Subject: drm/i915: ARL requires a newer GSC firmware ARL and MTL share a single GSC firmware blob. However, ARL requires a newer version of it. So add differentiate of the PCI ids for ARL from MTL and create ARL as a sub-platform of MTL. That way, all the existing workarounds and such still treat ARL as MTL exactly as before. However, now the GSC code can check for ARL and do an extra version check on the firmware before committing to it. Also, the version extraction code has various ways of failing but the return code was being ignore and so the firmware load would attempt to continue anyway. Fix that by propagating the return code to the next level out. Signed-off-by: John Harrison Fixes: 213c43676beb ("drm/i915/mtl: Remove the 'force_probe' requirement for Meteor Lake") Reviewed-by: Daniele Ceraolo Spurio Acked-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20240802031051.3816392-1-John.C.Harrison@Intel.com Signed-off-by: Rodrigo Vivi (cherry picked from commit 67733d7a71503fd3e32eeada371f8aa2516c5c95) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c | 31 +++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c | 10 ++++++++-- drivers/gpu/drm/i915/i915_drv.h | 2 ++ drivers/gpu/drm/i915/intel_device_info.c | 7 +++++++ drivers/gpu/drm/i915/intel_device_info.h | 3 +++ include/drm/intel/i915_pciids.h | 11 +++++++---- 6 files changed, 58 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c index 3b69bc6616bd..551b0d7974ff 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c @@ -212,6 +212,37 @@ int intel_gsc_fw_get_binary_info(struct intel_uc_fw *gsc_fw, const void *data, s } } + if (IS_ARROWLAKE(gt->i915)) { + bool too_old = false; + + /* + * ARL requires a newer firmware than MTL did (102.0.10.1878) but the + * firmware is actually common. So, need to do an explicit version check + * here rather than using a separate table entry. And if the older + * MTL-only version is found, then just don't use GSC rather than aborting + * the driver load. + */ + if (gsc->release.major < 102) { + too_old = true; + } else if (gsc->release.major == 102) { + if (gsc->release.minor == 0) { + if (gsc->release.patch < 10) { + too_old = true; + } else if (gsc->release.patch == 10) { + if (gsc->release.build < 1878) + too_old = true; + } + } + } + + if (too_old) { + gt_info(gt, "GSC firmware too old for ARL, got %d.%d.%d.%d but need at least 102.0.10.1878", + gsc->release.major, gsc->release.minor, + gsc->release.patch, gsc->release.build); + return -EINVAL; + } + } + return 0; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index d80278eb45d7..ec33ad942115 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -698,12 +698,18 @@ static int check_gsc_manifest(struct intel_gt *gt, const struct firmware *fw, struct intel_uc_fw *uc_fw) { + int ret; + switch (uc_fw->type) { case INTEL_UC_FW_TYPE_HUC: - intel_huc_fw_get_binary_info(uc_fw, fw->data, fw->size); + ret = intel_huc_fw_get_binary_info(uc_fw, fw->data, fw->size); + if (ret) + return ret; break; case INTEL_UC_FW_TYPE_GSC: - intel_gsc_fw_get_binary_info(uc_fw, fw->data, fw->size); + ret = intel_gsc_fw_get_binary_info(uc_fw, fw->data, fw->size); + if (ret) + return ret; break; default: MISSING_CASE(uc_fw->type); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index d7723dd11c80..110340e02a02 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -546,6 +546,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_LUNARLAKE(i915) (0 && i915) #define IS_BATTLEMAGE(i915) (0 && i915) +#define IS_ARROWLAKE(i915) \ + IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL) #define IS_DG2_G10(i915) \ IS_SUBPLATFORM(i915, INTEL_DG2, INTEL_SUBPLATFORM_G10) #define IS_DG2_G11(i915) \ diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index d26de37719a7..eede5417cb3f 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -203,6 +203,10 @@ static const u16 subplatform_g12_ids[] = { INTEL_DG2_G12_IDS(ID), }; +static const u16 subplatform_arl_ids[] = { + INTEL_ARL_IDS(ID), +}; + static bool find_devid(u16 id, const u16 *p, unsigned int num) { for (; num; num--, p++) { @@ -260,6 +264,9 @@ static void intel_device_info_subplatform_init(struct drm_i915_private *i915) } else if (find_devid(devid, subplatform_g12_ids, ARRAY_SIZE(subplatform_g12_ids))) { mask = BIT(INTEL_SUBPLATFORM_G12); + } else if (find_devid(devid, subplatform_arl_ids, + ARRAY_SIZE(subplatform_arl_ids))) { + mask = BIT(INTEL_SUBPLATFORM_ARL); } GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_MASK); diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index d1a2abc7e513..df73ef94615d 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -127,6 +127,9 @@ enum intel_platform { #define INTEL_SUBPLATFORM_N 1 #define INTEL_SUBPLATFORM_RPLU 2 +/* MTL */ +#define INTEL_SUBPLATFORM_ARL 0 + enum intel_ppgtt_type { INTEL_PPGTT_NONE = I915_GEM_PPGTT_NONE, INTEL_PPGTT_ALIASING = I915_GEM_PPGTT_ALIASING, diff --git a/include/drm/intel/i915_pciids.h b/include/drm/intel/i915_pciids.h index b21374f76df2..2bf03ebfcf73 100644 --- a/include/drm/intel/i915_pciids.h +++ b/include/drm/intel/i915_pciids.h @@ -772,15 +772,18 @@ INTEL_ATS_M75_IDS(MACRO__, ## __VA_ARGS__) /* MTL */ +#define INTEL_ARL_IDS(MACRO__, ...) \ + MACRO__(0x7D41, ## __VA_ARGS__), \ + MACRO__(0x7D51, ## __VA_ARGS__), \ + MACRO__(0x7D67, ## __VA_ARGS__), \ + MACRO__(0x7DD1, ## __VA_ARGS__) + #define INTEL_MTL_IDS(MACRO__, ...) \ + INTEL_ARL_IDS(MACRO__, ## __VA_ARGS__), \ MACRO__(0x7D40, ## __VA_ARGS__), \ - MACRO__(0x7D41, ## __VA_ARGS__), \ MACRO__(0x7D45, ## __VA_ARGS__), \ - MACRO__(0x7D51, ## __VA_ARGS__), \ MACRO__(0x7D55, ## __VA_ARGS__), \ MACRO__(0x7D60, ## __VA_ARGS__), \ - MACRO__(0x7D67, ## __VA_ARGS__), \ - MACRO__(0x7DD1, ## __VA_ARGS__), \ MACRO__(0x7DD5, ## __VA_ARGS__) /* LNL */ -- cgit v1.2.3 From 70c261d500951cf3ea0fcf32651aab9a65a91471 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 26 Aug 2024 15:03:23 +0200 Subject: netfilter: nf_tables_ipv6: consider network offset in netdev/egress validation From netdev/egress, skb->len can include the ethernet header, therefore, subtract network offset from skb->len when validating IPv6 packet length. Fixes: 42df6e1d221d ("netfilter: Introduce egress hook") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_ipv6.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 467d59b9e533..a0633eeaec97 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -31,8 +31,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) struct ipv6hdr *ip6h, _ip6h; unsigned int thoff = 0; unsigned short frag_off; + u32 pkt_len, skb_len; int protohdr; - u32 pkt_len; ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), sizeof(*ip6h), &_ip6h); @@ -43,7 +43,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) return -1; pkt_len = ntohs(ip6h->payload_len); - if (pkt_len + sizeof(*ip6h) > pkt->skb->len) + skb_len = pkt->skb->len - skb_network_offset(pkt->skb); + if (pkt_len + sizeof(*ip6h) > skb_len) return -1; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); -- cgit v1.2.3 From 2aeeef906d5a526dc60cf4af92eda69836c39b1f Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Fri, 23 Aug 2024 06:10:56 +0300 Subject: bonding: change ipsec_lock from spin lock to mutex In the cited commit, bond->ipsec_lock is added to protect ipsec_list, hence xdo_dev_state_add and xdo_dev_state_delete are called inside this lock. As ipsec_lock is a spin lock and such xfrmdev ops may sleep, "scheduling while atomic" will be triggered when changing bond's active slave. [ 101.055189] BUG: scheduling while atomic: bash/902/0x00000200 [ 101.055726] Modules linked in: [ 101.058211] CPU: 3 PID: 902 Comm: bash Not tainted 6.9.0-rc4+ #1 [ 101.058760] Hardware name: [ 101.059434] Call Trace: [ 101.059436] [ 101.060873] dump_stack_lvl+0x51/0x60 [ 101.061275] __schedule_bug+0x4e/0x60 [ 101.061682] __schedule+0x612/0x7c0 [ 101.062078] ? __mod_timer+0x25c/0x370 [ 101.062486] schedule+0x25/0xd0 [ 101.062845] schedule_timeout+0x77/0xf0 [ 101.063265] ? asm_common_interrupt+0x22/0x40 [ 101.063724] ? __bpf_trace_itimer_state+0x10/0x10 [ 101.064215] __wait_for_common+0x87/0x190 [ 101.064648] ? usleep_range_state+0x90/0x90 [ 101.065091] cmd_exec+0x437/0xb20 [mlx5_core] [ 101.065569] mlx5_cmd_do+0x1e/0x40 [mlx5_core] [ 101.066051] mlx5_cmd_exec+0x18/0x30 [mlx5_core] [ 101.066552] mlx5_crypto_create_dek_key+0xea/0x120 [mlx5_core] [ 101.067163] ? bonding_sysfs_store_option+0x4d/0x80 [bonding] [ 101.067738] ? kmalloc_trace+0x4d/0x350 [ 101.068156] mlx5_ipsec_create_sa_ctx+0x33/0x100 [mlx5_core] [ 101.068747] mlx5e_xfrm_add_state+0x47b/0xaa0 [mlx5_core] [ 101.069312] bond_change_active_slave+0x392/0x900 [bonding] [ 101.069868] bond_option_active_slave_set+0x1c2/0x240 [bonding] [ 101.070454] __bond_opt_set+0xa6/0x430 [bonding] [ 101.070935] __bond_opt_set_notify+0x2f/0x90 [bonding] [ 101.071453] bond_opt_tryset_rtnl+0x72/0xb0 [bonding] [ 101.071965] bonding_sysfs_store_option+0x4d/0x80 [bonding] [ 101.072567] kernfs_fop_write_iter+0x10c/0x1a0 [ 101.073033] vfs_write+0x2d8/0x400 [ 101.073416] ? alloc_fd+0x48/0x180 [ 101.073798] ksys_write+0x5f/0xe0 [ 101.074175] do_syscall_64+0x52/0x110 [ 101.074576] entry_SYSCALL_64_after_hwframe+0x4b/0x53 As bond_ipsec_add_sa_all and bond_ipsec_del_sa_all are only called from bond_change_active_slave, which requires holding the RTNL lock. And bond_ipsec_add_sa and bond_ipsec_del_sa are xfrm state xdo_dev_state_add and xdo_dev_state_delete APIs, which are in user context. So ipsec_lock doesn't have to be spin lock, change it to mutex, and thus the above issue can be resolved. Fixes: 9a5605505d9c ("bonding: Add struct bond_ipesc to manage SA") Signed-off-by: Jianbo Liu Signed-off-by: Tariq Toukan Reviewed-by: Hangbin Liu Acked-by: Jay Vosburgh Link: https://patch.msgid.link/20240823031056.110999-4-jianbol@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 79 ++++++++++++++++++++++------------------- include/net/bonding.h | 2 +- 2 files changed, 44 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index f98491748420..bb9c3d6ef435 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -428,6 +428,7 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs, { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; + netdevice_tracker tracker; struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; @@ -439,24 +440,26 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs, rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); - if (!slave) { - rcu_read_unlock(); - return -ENODEV; + real_dev = slave ? slave->dev : NULL; + netdev_hold(real_dev, &tracker, GFP_ATOMIC); + rcu_read_unlock(); + if (!real_dev) { + err = -ENODEV; + goto out; } - real_dev = slave->dev; if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(real_dev)) { NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload"); - rcu_read_unlock(); - return -EINVAL; + err = -EINVAL; + goto out; } - ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC); + ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL); if (!ipsec) { - rcu_read_unlock(); - return -ENOMEM; + err = -ENOMEM; + goto out; } xs->xso.real_dev = real_dev; @@ -464,13 +467,14 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs, if (!err) { ipsec->xs = xs; INIT_LIST_HEAD(&ipsec->list); - spin_lock_bh(&bond->ipsec_lock); + mutex_lock(&bond->ipsec_lock); list_add(&ipsec->list, &bond->ipsec_list); - spin_unlock_bh(&bond->ipsec_lock); + mutex_unlock(&bond->ipsec_lock); } else { kfree(ipsec); } - rcu_read_unlock(); +out: + netdev_put(real_dev, &tracker); return err; } @@ -481,35 +485,35 @@ static void bond_ipsec_add_sa_all(struct bonding *bond) struct bond_ipsec *ipsec; struct slave *slave; - rcu_read_lock(); - slave = rcu_dereference(bond->curr_active_slave); - if (!slave) - goto out; + slave = rtnl_dereference(bond->curr_active_slave); + real_dev = slave ? slave->dev : NULL; + if (!real_dev) + return; - real_dev = slave->dev; + mutex_lock(&bond->ipsec_lock); if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_state_add || netif_is_bond_master(real_dev)) { - spin_lock_bh(&bond->ipsec_lock); if (!list_empty(&bond->ipsec_list)) slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_add\n", __func__); - spin_unlock_bh(&bond->ipsec_lock); goto out; } - spin_lock_bh(&bond->ipsec_lock); list_for_each_entry(ipsec, &bond->ipsec_list, list) { + /* If new state is added before ipsec_lock acquired */ + if (ipsec->xs->xso.real_dev == real_dev) + continue; + ipsec->xs->xso.real_dev = real_dev; if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) { slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__); ipsec->xs->xso.real_dev = NULL; } } - spin_unlock_bh(&bond->ipsec_lock); out: - rcu_read_unlock(); + mutex_unlock(&bond->ipsec_lock); } /** @@ -520,6 +524,7 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) { struct net_device *bond_dev = xs->xso.dev; struct net_device *real_dev; + netdevice_tracker tracker; struct bond_ipsec *ipsec; struct bonding *bond; struct slave *slave; @@ -530,6 +535,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) rcu_read_lock(); bond = netdev_priv(bond_dev); slave = rcu_dereference(bond->curr_active_slave); + real_dev = slave ? slave->dev : NULL; + netdev_hold(real_dev, &tracker, GFP_ATOMIC); + rcu_read_unlock(); if (!slave) goto out; @@ -537,7 +545,6 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) if (!xs->xso.real_dev) goto out; - real_dev = slave->dev; WARN_ON(xs->xso.real_dev != real_dev); if (!real_dev->xfrmdev_ops || @@ -549,7 +556,8 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs) real_dev->xfrmdev_ops->xdo_dev_state_delete(xs); out: - spin_lock_bh(&bond->ipsec_lock); + netdev_put(real_dev, &tracker); + mutex_lock(&bond->ipsec_lock); list_for_each_entry(ipsec, &bond->ipsec_list, list) { if (ipsec->xs == xs) { list_del(&ipsec->list); @@ -557,8 +565,7 @@ out: break; } } - spin_unlock_bh(&bond->ipsec_lock); - rcu_read_unlock(); + mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_del_sa_all(struct bonding *bond) @@ -568,15 +575,12 @@ static void bond_ipsec_del_sa_all(struct bonding *bond) struct bond_ipsec *ipsec; struct slave *slave; - rcu_read_lock(); - slave = rcu_dereference(bond->curr_active_slave); - if (!slave) { - rcu_read_unlock(); + slave = rtnl_dereference(bond->curr_active_slave); + real_dev = slave ? slave->dev : NULL; + if (!real_dev) return; - } - real_dev = slave->dev; - spin_lock_bh(&bond->ipsec_lock); + mutex_lock(&bond->ipsec_lock); list_for_each_entry(ipsec, &bond->ipsec_list, list) { if (!ipsec->xs->xso.real_dev) continue; @@ -593,8 +597,7 @@ static void bond_ipsec_del_sa_all(struct bonding *bond) real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs); } } - spin_unlock_bh(&bond->ipsec_lock); - rcu_read_unlock(); + mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_free_sa(struct xfrm_state *xs) @@ -5921,7 +5924,7 @@ void bond_setup(struct net_device *bond_dev) /* set up xfrm device ops (only supported in active-backup right now) */ bond_dev->xfrmdev_ops = &bond_xfrmdev_ops; INIT_LIST_HEAD(&bond->ipsec_list); - spin_lock_init(&bond->ipsec_lock); + mutex_init(&bond->ipsec_lock); #endif /* CONFIG_XFRM_OFFLOAD */ /* don't acquire bond device's netif_tx_lock when transmitting */ @@ -5970,6 +5973,10 @@ static void bond_uninit(struct net_device *bond_dev) __bond_release_one(bond_dev, slave->dev, true, true); netdev_info(bond_dev, "Released all slaves\n"); +#ifdef CONFIG_XFRM_OFFLOAD + mutex_destroy(&bond->ipsec_lock); +#endif /* CONFIG_XFRM_OFFLOAD */ + bond_set_slave_arr(bond, NULL, NULL); list_del_rcu(&bond->bond_list); diff --git a/include/net/bonding.h b/include/net/bonding.h index b61fb1aa3a56..8bb5f016969f 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -260,7 +260,7 @@ struct bonding { #ifdef CONFIG_XFRM_OFFLOAD struct list_head ipsec_list; /* protecting ipsec_list */ - spinlock_t ipsec_lock; + struct mutex ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ struct bpf_prog *xdp_prog; }; -- cgit v1.2.3 From a547a5880cba6f287179135381f1b484b251be31 Mon Sep 17 00:00:00 2001 From: Peter Newman Date: Thu, 22 Aug 2024 12:02:11 -0700 Subject: x86/resctrl: Fix arch_mbm_* array overrun on SNC When using resctrl on systems with Sub-NUMA Clustering enabled, monitoring groups may be allocated RMID values which would overrun the arch_mbm_{local,total} arrays. This is due to inconsistencies in whether the SNC-adjusted num_rmid value or the unadjusted value in resctrl_arch_system_num_rmid_idx() is used. The num_rmid value for the L3 resource is currently: resctrl_arch_system_num_rmid_idx() / snc_nodes_per_l3_cache As a simple fix, make resctrl_arch_system_num_rmid_idx() return the SNC-adjusted, L3 num_rmid value on x86. Fixes: e13db55b5a0d ("x86/resctrl: Introduce snc_nodes_per_l3_cache") Signed-off-by: Peter Newman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Reinette Chatre Link: https://lore.kernel.org/r/20240822190212.1848788-1-peternewman@google.com --- arch/x86/include/asm/resctrl.h | 6 ------ arch/x86/kernel/cpu/resctrl/core.c | 8 ++++++++ include/linux/resctrl.h | 1 + 3 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 12dbd2588ca7..8b1b6ce1e51b 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -156,12 +156,6 @@ static inline void resctrl_sched_in(struct task_struct *tsk) __resctrl_sched_in(tsk); } -static inline u32 resctrl_arch_system_num_rmid_idx(void) -{ - /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ - return boot_cpu_data.x86_cache_max_rmid + 1; -} - static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid) { *rmid = idx; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 1930fce9dfe9..8591d53c144b 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -119,6 +119,14 @@ struct rdt_hw_resource rdt_resources_all[] = { }, }; +u32 resctrl_arch_system_num_rmid_idx(void) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + + /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ + return r->num_rmid; +} + /* * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs * as they do not have CPUID enumeration support for Cache allocation. diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index b0875b99e811..d94abba1c716 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -248,6 +248,7 @@ struct resctrl_schema { /* The number of closid supported by this resource regardless of CDP */ u32 resctrl_arch_get_num_closid(struct rdt_resource *r); +u32 resctrl_arch_system_num_rmid_idx(void); int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); /* -- cgit v1.2.3 From 1da29f2c39b67b846b74205c81bf0ccd96d34727 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 22 Aug 2024 23:06:49 +0100 Subject: netfs, cifs: Fix handling of short DIO read Short DIO reads, particularly in relation to cifs, are not being handled correctly by cifs and netfslib. This can be tested by doing a DIO read of a file where the size of read is larger than the size of the file. When it crosses the EOF, it gets a short read and this gets retried, and in the case of cifs, the retry read fails, with the failure being translated to ENODATA. Fix this by the following means: (1) Add a flag, NETFS_SREQ_HIT_EOF, for the filesystem to set when it detects that the read did hit the EOF. (2) Make the netfslib read assessment stop processing subrequests when it encounters one with that flag set. (3) Return rreq->transferred, the accumulated contiguous amount read to that point, to userspace for a DIO read. (4) Make cifs set the flag and clear the error if the read RPC returned ENODATA. (5) Make cifs set the flag and clear the error if a short read occurred without error and the read-to file position is now at the remote inode size. Fixes: 69c3c023af25 ("cifs: Implement netfslib hooks") Signed-off-by: David Howells cc: Steve French cc: Paulo Alcantara cc: Jeff Layton cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French --- fs/netfs/io.c | 17 +++++++++++------ fs/smb/client/smb2pdu.c | 13 +++++++++---- include/linux/netfs.h | 1 + 3 files changed, 21 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/fs/netfs/io.c b/fs/netfs/io.c index 3303b515b536..943128507af5 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -368,7 +368,8 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) if (subreq->error || subreq->transferred == 0) break; transferred += subreq->transferred; - if (subreq->transferred < subreq->len) + if (subreq->transferred < subreq->len || + test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) break; } @@ -503,7 +504,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, subreq->error = 0; subreq->transferred += transferred_or_error; - if (subreq->transferred < subreq->len) + if (subreq->transferred < subreq->len && + !test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags)) goto incomplete; complete: @@ -782,10 +784,13 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) TASK_UNINTERRUPTIBLE); ret = rreq->error; - if (ret == 0 && rreq->submitted < rreq->len && - rreq->origin != NETFS_DIO_READ) { - trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); - ret = -EIO; + if (ret == 0) { + if (rreq->origin == NETFS_DIO_READ) { + ret = rreq->transferred; + } else if (rreq->submitted < rreq->len) { + trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read); + ret = -EIO; + } } } else { /* If we decrement nr_outstanding to 0, the ref belongs to us. */ diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index be7a1a9c691d..88dc49d67037 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4507,6 +4507,7 @@ static void smb2_readv_callback(struct mid_q_entry *mid) { struct cifs_io_subrequest *rdata = mid->callback_data; + struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode); struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct TCP_Server_Info *server = rdata->server; struct smb2_hdr *shdr = @@ -4599,11 +4600,15 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->got_bytes); if (rdata->result == -ENODATA) { - /* We may have got an EOF error because fallocate - * failed to enlarge the file. - */ - if (rdata->subreq.start < rdata->subreq.rreq->i_size) + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + rdata->result = 0; + } else { + if (rdata->got_bytes < rdata->actual_len && + rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes == + ictx->remote_i_size) { + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + } } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, server->credits, server->in_flight, diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 983816608f15..c47443e7a97e 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -198,6 +198,7 @@ struct netfs_io_subrequest { #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ #define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ #define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ +#define NETFS_SREQ_HIT_EOF 12 /* Set if we hit the EOF */ }; enum netfs_io_origin { -- cgit v1.2.3 From 0870b0d8b393dde53106678a1e2cec9dfa52f9b7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Aug 2024 11:49:16 +0000 Subject: net: busy-poll: use ktime_get_ns() instead of local_clock() Typically, busy-polling durations are below 100 usec. When/if the busy-poller thread migrates to another cpu, local_clock() can be off by +/-2msec or more for small values of HZ, depending on the platform. Use ktimer_get_ns() to ensure deterministic behavior, which is the whole point of busy-polling. Fixes: 060212928670 ("net: add low latency socket poll") Fixes: 9a3c71aa8024 ("net: convert low latency sockets to sched_clock()") Fixes: 37089834528b ("sched, net: Fixup busy_loop_us_clock()") Signed-off-by: Eric Dumazet Cc: Mina Almasry Cc: Willem de Bruijn Reviewed-by: Joe Damato Link: https://patch.msgid.link/20240827114916.223377-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/busy_poll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 9b09acac538e..522f1da8b747 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -68,7 +68,7 @@ static inline bool sk_can_busy_loop(struct sock *sk) static inline unsigned long busy_loop_current_time(void) { #ifdef CONFIG_NET_RX_BUSY_POLL - return (unsigned long)(local_clock() >> 10); + return (unsigned long)(ktime_get_ns() >> 10); #else return 0; #endif -- cgit v1.2.3 From 1a5caec7f80ca2e659c03f45378ee26915f4eda2 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 30 Aug 2024 07:35:12 -0700 Subject: regulator: core: Stub devm_regulator_bulk_get_const() if !CONFIG_REGULATOR When adding devm_regulator_bulk_get_const() I missed adding a stub for when CONFIG_REGULATOR is not enabled. Under certain conditions (like randconfig testing) this can cause the compiler to reports errors like: error: implicit declaration of function 'devm_regulator_bulk_get_const'; did you mean 'devm_regulator_bulk_get_enable'? Add the stub. Fixes: 1de452a0edda ("regulator: core: Allow drivers to define their init data as const") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202408301813.TesFuSbh-lkp@intel.com/ Cc: Neil Armstrong Signed-off-by: Douglas Anderson Link: https://patch.msgid.link/20240830073511.1.Ib733229a8a19fad8179213c05e1af01b51e42328@changeid Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index d986ec13092e..b9ce521910a0 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -452,6 +452,14 @@ static inline int of_regulator_bulk_get_all(struct device *dev, struct device_no return 0; } +static inline int devm_regulator_bulk_get_const( + struct device *dev, int num_consumers, + const struct regulator_bulk_data *in_consumers, + struct regulator_bulk_data **out_consumers) +{ + return 0; +} + static inline int regulator_bulk_enable(int num_consumers, struct regulator_bulk_data *consumers) { -- cgit v1.2.3 From c898f6d7b093bd71e66569cd6797c87d4056f44b Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 26 Aug 2024 15:47:30 -0400 Subject: Bluetooth: hci_sync: Introduce hci_cmd_sync_run/hci_cmd_sync_run_once This introduces hci_cmd_sync_run/hci_cmd_sync_run_once which acts like hci_cmd_sync_queue/hci_cmd_sync_queue_once but runs immediately when already on hdev->cmd_sync_work context. Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_sync.h | 4 ++++ net/bluetooth/hci_sync.c | 42 ++++++++++++++++++++++++++++++++++++++-- 2 files changed, 44 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 75e052909b5f..f3052cb252ef 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -73,6 +73,10 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); struct hci_cmd_sync_work_entry * hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index e79cd40bd079..5533e6f561b3 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -112,7 +112,7 @@ static void hci_cmd_sync_add(struct hci_request *req, u16 opcode, u32 plen, skb_queue_tail(&req->cmd_q, skb); } -static int hci_cmd_sync_run(struct hci_request *req) +static int hci_req_sync_run(struct hci_request *req) { struct hci_dev *hdev = req->hdev; struct sk_buff *skb; @@ -169,7 +169,7 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, hdev->req_status = HCI_REQ_PEND; - err = hci_cmd_sync_run(&req); + err = hci_req_sync_run(&req); if (err < 0) return ERR_PTR(err); @@ -782,6 +782,44 @@ int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, } EXPORT_SYMBOL(hci_cmd_sync_queue_once); +/* Run HCI command: + * + * - hdev must be running + * - if on cmd_sync_work then run immediately otherwise queue + */ +int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + /* Only queue command if hdev is running which means it had been opened + * and is either on init phase or is already up. + */ + if (!test_bit(HCI_RUNNING, &hdev->flags)) + return -ENETDOWN; + + /* If on cmd_sync_work then run immediately otherwise queue */ + if (current_work() == &hdev->cmd_sync_work) + return func(hdev, data); + + return hci_cmd_sync_submit(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_run); + +/* Run HCI command entry once: + * + * - Lookup if an entry already exist and only if it doesn't creates a new entry + * and run it. + * - if on cmd_sync_work then run immediately otherwise queue + */ +int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy)) + return 0; + + return hci_cmd_sync_run(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_run_once); + /* Lookup HCI command entry: * * - Return first entry that matches by function callback or data or -- cgit v1.2.3 From 532f8bcd1c2c4e8112f62e1922fd1703bc0ffce0 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Tue, 27 Aug 2024 14:37:22 -0400 Subject: Revert "Bluetooth: MGMT/SMP: Fix address type when using SMP over BREDR/LE" This reverts commit 59b047bc98084f8af2c41483e4d68a5adf2fa7f7 which breaks compatibility with commands like: bluetoothd[46328]: @ MGMT Command: Load.. (0x0013) plen 74 {0x0001} [hci0] Keys: 2 BR/EDR Address: C0:DC:DA:A5:E5:47 (Samsung Electronics Co.,Ltd) Key type: Authenticated key from P-256 (0x03) Central: 0x00 Encryption size: 16 Diversifier[2]: 0000 Randomizer[8]: 0000000000000000 Key[16]: 6ed96089bd9765be2f2c971b0b95f624 LE Address: D7:2A:DE:1E:73:A2 (Static) Key type: Unauthenticated key from P-256 (0x02) Central: 0x00 Encryption size: 16 Diversifier[2]: 0000 Randomizer[8]: 0000000000000000 Key[16]: 87dd2546ededda380ffcdc0a8faa4597 @ MGMT Event: Command Status (0x0002) plen 3 {0x0001} [hci0] Load Long Term Keys (0x0013) Status: Invalid Parameters (0x0d) Cc: stable@vger.kernel.org Link: https://github.com/bluez/bluez/issues/875 Fixes: 59b047bc9808 ("Bluetooth: MGMT/SMP: Fix address type when using SMP over BREDR/LE") Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 5 ----- net/bluetooth/mgmt.c | 25 +++++++------------------ net/bluetooth/smp.c | 7 ------- 3 files changed, 7 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index e449dba698f3..1a32e602630e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -186,7 +186,6 @@ struct blocked_key { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; - u8 link_type; u8 type; u8 val[16]; }; @@ -196,7 +195,6 @@ struct smp_ltk { struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; - u8 link_type; u8 authenticated; u8 type; u8 enc_size; @@ -211,7 +209,6 @@ struct smp_irk { bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; - u8 link_type; u8 val[16]; }; @@ -219,8 +216,6 @@ struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; - u8 bdaddr_type; - u8 link_type; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 4c20dbf92c71..240dd8cf7c7d 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2833,8 +2833,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; - /* Considering SMP over BREDR/LE, there is no need to check addr_type */ - if (key->type > 0x08) + if (key->addr.type != BDADDR_BREDR || key->type > 0x08) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); @@ -7089,7 +7088,6 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, for (i = 0; i < irk_count; i++) { struct mgmt_irk_info *irk = &cp->irks[i]; - u8 addr_type = le_addr_type(irk->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, @@ -7099,12 +7097,8 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, continue; } - /* When using SMP over BR/EDR, the addr type should be set to BREDR */ - if (irk->addr.type == BDADDR_BREDR) - addr_type = BDADDR_BREDR; - hci_add_irk(hdev, &irk->addr.bdaddr, - addr_type, irk->val, + le_addr_type(irk->addr.type), irk->val, BDADDR_ANY); } @@ -7185,7 +7179,6 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, for (i = 0; i < key_count; i++) { struct mgmt_ltk_info *key = &cp->keys[i]; u8 type, authenticated; - u8 addr_type = le_addr_type(key->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, @@ -7220,12 +7213,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, continue; } - /* When using SMP over BR/EDR, the addr type should be set to BREDR */ - if (key->addr.type == BDADDR_BREDR) - addr_type = BDADDR_BREDR; - hci_add_ltk(hdev, &key->addr.bdaddr, - addr_type, type, authenticated, + le_addr_type(key->addr.type), type, authenticated, key->val, key->enc_size, key->ediv, key->rand); } @@ -9519,7 +9508,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); + ev.key.addr.type = BDADDR_BREDR; ev.key.type = key->type; memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE); ev.key.pin_len = key->pin_len; @@ -9570,7 +9559,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); ev.key.type = mgmt_ltk_type(key); ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; @@ -9599,7 +9588,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent) bacpy(&ev.rpa, &irk->rpa); bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr); - ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type); + ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type); memcpy(ev.irk.val, irk->val, sizeof(irk->val)); mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL); @@ -9628,7 +9617,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr); - ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type); ev.key.type = csrk->type; memcpy(ev.key.val, csrk->val, sizeof(csrk->val)); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 4f9fdf400584..8b9724fd752a 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1060,7 +1060,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->remote_irk) { - smp->remote_irk->link_type = hcon->type; mgmt_new_irk(hdev, smp->remote_irk, persistent); /* Now that user space can be considered to know the @@ -1080,28 +1079,24 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->csrk) { - smp->csrk->link_type = hcon->type; smp->csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->csrk, persistent); } if (smp->responder_csrk) { - smp->responder_csrk->link_type = hcon->type; smp->responder_csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->responder_csrk, persistent); } if (smp->ltk) { - smp->ltk->link_type = hcon->type; smp->ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->ltk, persistent); } if (smp->responder_ltk) { - smp->responder_ltk->link_type = hcon->type; smp->responder_ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->responder_ltk, persistent); @@ -1121,8 +1116,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst, smp->link_key, type, 0, &persistent); if (key) { - key->link_type = hcon->type; - key->bdaddr_type = hcon->dst_type; mgmt_new_link_key(hdev, key, persistent); /* Don't keep debug keys around if the relevant -- cgit v1.2.3 From 33f339a1ba54e56bba57ee9a77c71e385ab4825c Mon Sep 17 00:00:00 2001 From: Tze-nan Wu Date: Fri, 30 Aug 2024 16:25:17 +0800 Subject: bpf, net: Fix a potential race in do_sock_getsockopt() There's a potential race when `cgroup_bpf_enabled(CGROUP_GETSOCKOPT)` is false during the execution of `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN`, but becomes true when `BPF_CGROUP_RUN_PROG_GETSOCKOPT` is called. This inconsistency can lead to `BPF_CGROUP_RUN_PROG_GETSOCKOPT` receiving an "-EFAULT" from `__cgroup_bpf_run_filter_getsockopt(max_optlen=0)`. Scenario shown as below: `process A` `process B` ----------- ------------ BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN enable CGROUP_GETSOCKOPT BPF_CGROUP_RUN_PROG_GETSOCKOPT (-EFAULT) To resolve this, remove the `BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN` macro and directly uses `copy_from_sockptr` to ensure that `max_optlen` is always set before `BPF_CGROUP_RUN_PROG_GETSOCKOPT` is invoked. Fixes: 0d01da6afc54 ("bpf: implement getsockopt and setsockopt hooks") Co-developed-by: Yanghui Li Signed-off-by: Yanghui Li Co-developed-by: Cheng-Jui Wang Signed-off-by: Cheng-Jui Wang Signed-off-by: Tze-nan Wu Acked-by: Stanislav Fomichev Acked-by: Alexei Starovoitov Link: https://patch.msgid.link/20240830082518.23243-1-Tze-nan.Wu@mediatek.com Signed-off-by: Jakub Kicinski --- include/linux/bpf-cgroup.h | 9 --------- net/socket.c | 4 ++-- 2 files changed, 2 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index fb3c3e7181e6..ce91d9b2acb9 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -390,14 +390,6 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, __ret; \ }) -#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ -({ \ - int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ - copy_from_sockptr(&__ret, optlen, sizeof(int)); \ - __ret; \ -}) - #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ max_optlen, retval) \ ({ \ @@ -518,7 +510,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) -#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ diff --git a/net/socket.c b/net/socket.c index fcbdd5bc47ac..0a2bd22ec105 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2362,7 +2362,7 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen) { - int max_optlen __maybe_unused; + int max_optlen __maybe_unused = 0; const struct proto_ops *ops; int err; @@ -2371,7 +2371,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level, return err; if (!compat) - max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + copy_from_sockptr(&max_optlen, optlen, sizeof(int)); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) { -- cgit v1.2.3 From 8f62819aaace77dd85037ae766eb767f8c4417ce Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 23 Aug 2024 11:33:23 +0200 Subject: PCI/pwrctl: Rescan bus on a separate thread If we trigger the bus rescan from sysfs, we'll try to lock the PCI rescan mutex recursively and deadlock - the platform device will be populated and probed on the same thread that handles the sysfs write. Add a workqueue to the pwrctl code on which we schedule the rescan for controlled PCI devices. While at it: add a new interface for initializing the pwrctl context where we'd now assign the parent device address and initialize the workqueue. Link: https://lore.kernel.org/r/20240823093323.33450-3-brgl@bgdev.pl Fixes: 4565d2652a37 ("PCI/pwrctl: Add PCI power control core code") Reported-by: Konrad Dybcio Signed-off-by: Bartosz Golaszewski Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam --- drivers/pci/pwrctl/core.c | 26 +++++++++++++++++++++++--- drivers/pci/pwrctl/pci-pwrctl-pwrseq.c | 2 +- include/linux/pci-pwrctl.h | 3 +++ 3 files changed, 27 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/pci/pwrctl/core.c b/drivers/pci/pwrctl/core.c index feca26ad2f6a..01d913b60316 100644 --- a/drivers/pci/pwrctl/core.c +++ b/drivers/pci/pwrctl/core.c @@ -48,6 +48,28 @@ static int pci_pwrctl_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_DONE; } +static void rescan_work_func(struct work_struct *work) +{ + struct pci_pwrctl *pwrctl = container_of(work, struct pci_pwrctl, work); + + pci_lock_rescan_remove(); + pci_rescan_bus(to_pci_dev(pwrctl->dev->parent)->bus); + pci_unlock_rescan_remove(); +} + +/** + * pci_pwrctl_init() - Initialize the PCI power control context struct + * + * @pwrctl: PCI power control data + * @dev: Parent device + */ +void pci_pwrctl_init(struct pci_pwrctl *pwrctl, struct device *dev) +{ + pwrctl->dev = dev; + INIT_WORK(&pwrctl->work, rescan_work_func); +} +EXPORT_SYMBOL_GPL(pci_pwrctl_init); + /** * pci_pwrctl_device_set_ready() - Notify the pwrctl subsystem that the PCI * device is powered-up and ready to be detected. @@ -74,9 +96,7 @@ int pci_pwrctl_device_set_ready(struct pci_pwrctl *pwrctl) if (ret) return ret; - pci_lock_rescan_remove(); - pci_rescan_bus(to_pci_dev(pwrctl->dev->parent)->bus); - pci_unlock_rescan_remove(); + schedule_work(&pwrctl->work); return 0; } diff --git a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c b/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c index c7a113a76c0c..f07758c9edad 100644 --- a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c +++ b/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c @@ -50,7 +50,7 @@ static int pci_pwrctl_pwrseq_probe(struct platform_device *pdev) if (ret) return ret; - data->ctx.dev = dev; + pci_pwrctl_init(&data->ctx, dev); ret = devm_pci_pwrctl_device_set_ready(dev, &data->ctx); if (ret) diff --git a/include/linux/pci-pwrctl.h b/include/linux/pci-pwrctl.h index 45e9cfe740e4..0d23dddf59ec 100644 --- a/include/linux/pci-pwrctl.h +++ b/include/linux/pci-pwrctl.h @@ -7,6 +7,7 @@ #define __PCI_PWRCTL_H__ #include +#include struct device; struct device_link; @@ -41,8 +42,10 @@ struct pci_pwrctl { /* Private: don't use. */ struct notifier_block nb; struct device_link *link; + struct work_struct work; }; +void pci_pwrctl_init(struct pci_pwrctl *pwrctl, struct device *dev); int pci_pwrctl_device_set_ready(struct pci_pwrctl *pwrctl); void pci_pwrctl_device_unset_ready(struct pci_pwrctl *pwrctl); int devm_pci_pwrctl_device_set_ready(struct device *dev, -- cgit v1.2.3 From b6ecc662037694488bfff7c9fd21c405df8411f2 Mon Sep 17 00:00:00 2001 From: Souradeep Chakrabarti Date: Mon, 2 Sep 2024 05:43:47 -0700 Subject: net: mana: Fix error handling in mana_create_txq/rxq's NAPI cleanup Currently napi_disable() gets called during rxq and txq cleanup, even before napi is enabled and hrtimer is initialized. It causes kernel panic. ? page_fault_oops+0x136/0x2b0 ? page_counter_cancel+0x2e/0x80 ? do_user_addr_fault+0x2f2/0x640 ? refill_obj_stock+0xc4/0x110 ? exc_page_fault+0x71/0x160 ? asm_exc_page_fault+0x27/0x30 ? __mmdrop+0x10/0x180 ? __mmdrop+0xec/0x180 ? hrtimer_active+0xd/0x50 hrtimer_try_to_cancel+0x2c/0xf0 hrtimer_cancel+0x15/0x30 napi_disable+0x65/0x90 mana_destroy_rxq+0x4c/0x2f0 mana_create_rxq.isra.0+0x56c/0x6d0 ? mana_uncfg_vport+0x50/0x50 mana_alloc_queues+0x21b/0x320 ? skb_dequeue+0x5f/0x80 Cc: stable@vger.kernel.org Fixes: e1b5683ff62e ("net: mana: Move NAPI from EQ to CQ") Signed-off-by: Souradeep Chakrabarti Reviewed-by: Haiyang Zhang Reviewed-by: Shradha Gupta Signed-off-by: David S. Miller --- drivers/net/ethernet/microsoft/mana/mana_en.c | 22 +++++++++++++--------- include/net/mana/mana.h | 2 ++ 2 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 39f56973746d..3d151700f658 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1872,10 +1872,12 @@ static void mana_destroy_txq(struct mana_port_context *apc) for (i = 0; i < apc->num_queues; i++) { napi = &apc->tx_qp[i].tx_cq.napi; - napi_synchronize(napi); - napi_disable(napi); - netif_napi_del(napi); - + if (apc->tx_qp[i].txq.napi_initialized) { + napi_synchronize(napi); + napi_disable(napi); + netif_napi_del(napi); + apc->tx_qp[i].txq.napi_initialized = false; + } mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object); mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq); @@ -1931,6 +1933,7 @@ static int mana_create_txq(struct mana_port_context *apc, txq->ndev = net; txq->net_txq = netdev_get_tx_queue(net, i); txq->vp_offset = apc->tx_vp_offset; + txq->napi_initialized = false; skb_queue_head_init(&txq->pending_skbs); memset(&spec, 0, sizeof(spec)); @@ -1997,6 +2000,7 @@ static int mana_create_txq(struct mana_port_context *apc, netif_napi_add_tx(net, &cq->napi, mana_poll); napi_enable(&cq->napi); + txq->napi_initialized = true; mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); } @@ -2008,7 +2012,7 @@ out: } static void mana_destroy_rxq(struct mana_port_context *apc, - struct mana_rxq *rxq, bool validate_state) + struct mana_rxq *rxq, bool napi_initialized) { struct gdma_context *gc = apc->ac->gdma_dev->gdma_context; @@ -2023,15 +2027,15 @@ static void mana_destroy_rxq(struct mana_port_context *apc, napi = &rxq->rx_cq.napi; - if (validate_state) + if (napi_initialized) { napi_synchronize(napi); - napi_disable(napi); + napi_disable(napi); + netif_napi_del(napi); + } xdp_rxq_info_unreg(&rxq->xdp_rxq); - netif_napi_del(napi); - mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj); mana_deinit_cq(apc, &rxq->rx_cq); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 7caa334f4888..b8a6c7504ee1 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -98,6 +98,8 @@ struct mana_txq { atomic_t pending_sends; + bool napi_initialized; + struct mana_stats_tx stats; }; -- cgit v1.2.3 From 593377036e50de89132bc1222800174fde0780ec Mon Sep 17 00:00:00 2001 From: Leonardo Bras Date: Fri, 10 May 2024 23:05:56 -0300 Subject: kvm: Note an RCU quiescent state on guest exit As of today, KVM notes a quiescent state only in guest entry, which is good as it avoids the guest being interrupted for current RCU operations. While the guest vcpu runs, it can be interrupted by a timer IRQ that will check for any RCU operations waiting for this CPU. In case there are any of such, it invokes rcu_core() in order to sched-out the current thread and note a quiescent state. This occasional schedule work will introduce tens of microsseconds of latency, which is really bad for vcpus running latency-sensitive applications, such as real-time workloads. So, note a quiescent state in guest exit, so the interrupted guests is able to deal with any pending RCU operations before being required to invoke rcu_core(), and thus avoid the overhead of related scheduler work. Signed-off-by: Leonardo Bras Acked-by: Paul E. McKenney Acked-by: Sean Christopherson Message-ID: <20240511020557.1198200-1-leobras@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/context_tracking.h | 6 ++++-- include/linux/kvm_host.h | 10 +++++++++- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 6e76b9dba00e..8a78fabeafc3 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -80,10 +80,12 @@ static __always_inline bool context_tracking_guest_enter(void) return context_tracking_enabled_this_cpu(); } -static __always_inline void context_tracking_guest_exit(void) +static __always_inline bool context_tracking_guest_exit(void) { if (context_tracking_enabled()) __ct_user_exit(CONTEXT_GUEST); + + return context_tracking_enabled_this_cpu(); } #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) @@ -98,7 +100,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } -static __always_inline void context_tracking_guest_exit(void) { } +static __always_inline bool context_tracking_guest_exit(void) { return false; } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b23c6d48392f..0d5125a3e31a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -485,7 +485,15 @@ static __always_inline void guest_state_enter_irqoff(void) */ static __always_inline void guest_context_exit_irqoff(void) { - context_tracking_guest_exit(); + /* + * Guest mode is treated as a quiescent state, see + * guest_context_enter_irqoff() for more details. + */ + if (!context_tracking_guest_exit()) { + instrumentation_begin(); + rcu_virt_note_context_switch(); + instrumentation_end(); + } } /* -- cgit v1.2.3 From 5f7762042f8a5377bd8a32844db353c0311a7369 Mon Sep 17 00:00:00 2001 From: Mary Guillemard Date: Tue, 3 Sep 2024 16:49:55 +0200 Subject: drm/panthor: Restrict high priorities on group_create We were allowing any users to create a high priority group without any permission checks. As a result, this was allowing possible denial of service. We now only allow the DRM master or users with the CAP_SYS_NICE capability to set higher priorities than PANTHOR_GROUP_PRIORITY_MEDIUM. As the sole user of that uAPI lives in Mesa and hardcode a value of MEDIUM [1], this should be safe to do. Additionally, as those checks are performed at the ioctl level, panthor_group_create now only check for priority level validity. [1]https://gitlab.freedesktop.org/mesa/mesa/-/blob/f390835074bdf162a63deb0311d1a6de527f9f89/src/gallium/drivers/panfrost/pan_csf.c#L1038 Signed-off-by: Mary Guillemard Fixes: de8548813824 ("drm/panthor: Add the scheduler logical block") Cc: stable@vger.kernel.org Reviewed-by: Boris Brezillon Signed-off-by: Boris Brezillon Link: https://patchwork.freedesktop.org/patch/msgid/20240903144955.144278-2-mary.guillemard@collabora.com --- drivers/gpu/drm/panthor/panthor_drv.c | 23 +++++++++++++++++++++++ drivers/gpu/drm/panthor/panthor_sched.c | 2 +- include/uapi/drm/panthor_drm.h | 6 +++++- 3 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index b5e7b919f241..34182f67136c 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -996,6 +997,24 @@ static int panthor_ioctl_group_destroy(struct drm_device *ddev, void *data, return panthor_group_destroy(pfile, args->group_handle); } +static int group_priority_permit(struct drm_file *file, + u8 priority) +{ + /* Ensure that priority is valid */ + if (priority > PANTHOR_GROUP_PRIORITY_HIGH) + return -EINVAL; + + /* Medium priority and below are always allowed */ + if (priority <= PANTHOR_GROUP_PRIORITY_MEDIUM) + return 0; + + /* Higher priorities require CAP_SYS_NICE or DRM_MASTER */ + if (capable(CAP_SYS_NICE) || drm_is_current_master(file)) + return 0; + + return -EACCES; +} + static int panthor_ioctl_group_create(struct drm_device *ddev, void *data, struct drm_file *file) { @@ -1011,6 +1030,10 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data, if (ret) return ret; + ret = group_priority_permit(file, args->priority); + if (ret) + return ret; + ret = panthor_group_create(pfile, args, queue_args); if (ret >= 0) { args->group_handle = ret; diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index 463bcd3cf00f..12b272a912f8 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -3092,7 +3092,7 @@ int panthor_group_create(struct panthor_file *pfile, if (group_args->pad) return -EINVAL; - if (group_args->priority > PANTHOR_CSG_PRIORITY_HIGH) + if (group_args->priority >= PANTHOR_CSG_PRIORITY_COUNT) return -EINVAL; if ((group_args->compute_core_mask & ~ptdev->gpu_info.shader_present) || diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index 926b1deb1116..e23a7f9b0eac 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -692,7 +692,11 @@ enum drm_panthor_group_priority { /** @PANTHOR_GROUP_PRIORITY_MEDIUM: Medium priority group. */ PANTHOR_GROUP_PRIORITY_MEDIUM, - /** @PANTHOR_GROUP_PRIORITY_HIGH: High priority group. */ + /** + * @PANTHOR_GROUP_PRIORITY_HIGH: High priority group. + * + * Requires CAP_SYS_NICE or DRM_MASTER. + */ PANTHOR_GROUP_PRIORITY_HIGH, }; -- cgit v1.2.3 From 12cb32a52eb607dc4d0e45fe6f4cf946d08da0fd Mon Sep 17 00:00:00 2001 From: David Gow Date: Thu, 5 Sep 2024 10:47:55 +0800 Subject: kunit: Fix missing kerneldoc comment Add a missing kerneldoc comment for the 'test' test context parameter, fixing the following warning: include/kunit/test.h:492: warning: Function parameter or struct member 'test' not described in 'kunit_kfree_const' Reported-by: Stephen Rothwell Closes: https://lore.kernel.org/lkml/20240827160631.67e121ed@canb.auug.org.au/ Fixes: f2c6dbd22017 ("kunit: Device wrappers should also manage driver name") Signed-off-by: David Gow Reviewed-by: Kees Cook Signed-off-by: Shuah Khan --- include/kunit/test.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 5ac237c949a0..34b71e42fb10 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -484,6 +484,7 @@ static inline void *kunit_kcalloc(struct kunit *test, size_t n, size_t size, gfp /** * kunit_kfree_const() - conditionally free test managed memory + * @test: The test context object. * @x: pointer to the memory * * Calls kunit_kfree() only if @x is not in .rodata section. -- cgit v1.2.3