From: Parav Pandit parav@nvidia.com

[ Upstream commit 43bb40c5b92659966bdf4bfe584fde0a3575a049 ]

When a virtio pci device undergo surprise removal (aka async removal in PCIe spec), mark the device as broken so that any upper layer drivers can abort any outstanding operation.

When a virtio net pci device undergo surprise removal which is used by a NetworkManager, a below call trace was observed.

kernel:watchdog: BUG: soft lockup - CPU#1 stuck for 26s! [kworker/1:1:27059] watchdog: BUG: soft lockup - CPU#1 stuck for 52s! [kworker/1:1:27059] CPU: 1 PID: 27059 Comm: kworker/1:1 Tainted: G S W I L 5.13.0-hotplug+ #8 Hardware name: Dell Inc. PowerEdge R640/0H28RR, BIOS 2.9.4 11/06/2020 Workqueue: events linkwatch_event RIP: 0010:virtnet_send_command+0xfc/0x150 [virtio_net] Call Trace: virtnet_set_rx_mode+0xcf/0x2a7 [virtio_net] ? __hw_addr_create_ex+0x85/0xc0 __dev_mc_add+0x72/0x80 igmp6_group_added+0xa7/0xd0 ipv6_mc_up+0x3c/0x60 ipv6_find_idev+0x36/0x80 addrconf_add_dev+0x1e/0xa0 addrconf_dev_config+0x71/0x130 addrconf_notify+0x1f5/0xb40 ? rtnl_is_locked+0x11/0x20 ? __switch_to_asm+0x42/0x70 ? finish_task_switch+0xaf/0x2c0 ? raw_notifier_call_chain+0x3e/0x50 raw_notifier_call_chain+0x3e/0x50 netdev_state_change+0x67/0x90 linkwatch_do_dev+0x3c/0x50 __linkwatch_run_queue+0xd2/0x220 linkwatch_event+0x21/0x30 process_one_work+0x1c8/0x370 worker_thread+0x30/0x380 ? process_one_work+0x370/0x370 kthread+0x118/0x140 ? set_kthread_struct+0x40/0x40 ret_from_fork+0x1f/0x30

Hence, add the ability to abort the command on surprise removal which prevents infinite loop and system lockup.

Signed-off-by: Parav Pandit parav@nvidia.com Link: https://lore.kernel.org/r/20210721142648.1525924-5-parav@nvidia.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/virtio/virtio_pci_common.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 45b04bc91f24..b7cc63f556ee 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -579,6 +579,13 @@ static void virtio_pci_remove(struct pci_dev *pci_dev) struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct device *dev = get_device(&vp_dev->vdev.dev);

+ /* + * Device is marked broken on surprise removal so that virtio upper + * layers can abort any ongoing operation. + */ + if (!pci_device_is_present(pci_dev)) + virtio_break_device(&vp_dev->vdev); + pci_disable_sriov(pci_dev);

unregister_virtio_device(&vp_dev->vdev);

From: Shai Malin smalin@marvell.com

[ Upstream commit 37110237f31105d679fc0aa7b11cdec867750ea7 ]

Avoiding qed ll2 race condition and NULL pointer dereference as part of the remove and recovery flows.

Changes form V1: - Change (!p_rx->set_prod_addr). - qed_ll2.c checkpatch fixes.

Change from V2: - Revert "qed_ll2.c checkpatch fixes".

Signed-off-by: Ariel Elior aelior@marvell.com Signed-off-by: Shai Malin smalin@marvell.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 2847509a183d..cb3569ac85f7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -354,6 +354,9 @@ static int qed_ll2_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie) unsigned long flags; int rc = -EINVAL;

+ if (!p_ll2_conn) + return rc; + spin_lock_irqsave(&p_tx->lock, flags); if (p_tx->b_completing_packet) { rc = -EBUSY; @@ -527,7 +530,16 @@ static int qed_ll2_rxq_completion(struct qed_hwfn *p_hwfn, void *cookie) unsigned long flags = 0; int rc = 0;

+ if (!p_ll2_conn) + return rc; + spin_lock_irqsave(&p_rx->lock, flags); + + if (!QED_LL2_RX_REGISTERED(p_ll2_conn)) { + spin_unlock_irqrestore(&p_rx->lock, flags); + return 0; + } + cq_new_idx = le16_to_cpu(*p_rx->p_fw_cons); cq_old_idx = qed_chain_get_cons_idx(&p_rx->rcq_chain);

@@ -848,6 +860,9 @@ static int qed_ll2_lb_rxq_completion(struct qed_hwfn *p_hwfn, void *p_cookie) struct qed_ll2_info *p_ll2_conn = (struct qed_ll2_info *)p_cookie; int rc;

+ if (!p_ll2_conn) + return 0; + if (!QED_LL2_RX_REGISTERED(p_ll2_conn)) return 0;

@@ -871,6 +886,9 @@ static int qed_ll2_lb_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie) u16 new_idx = 0, num_bds = 0; int rc;

+ if (!p_ll2_conn) + return 0; + if (!QED_LL2_TX_REGISTERED(p_ll2_conn)) return 0;

@@ -1628,6 +1646,8 @@ int qed_ll2_post_rx_buffer(void *cxt, if (!p_ll2_conn) return -EINVAL; p_rx = &p_ll2_conn->rx_queue; + if (!p_rx->set_prod_addr) + return -EIO;

spin_lock_irqsave(&p_rx->lock, flags); if (!list_empty(&p_rx->free_descq))

From: Mark Yacoub markyacoub@google.com

[ Upstream commit fa0b1ef5f7a694f48e00804a391245f3471aa155 ]

[Why] Userspace should get back a copy of drm_wait_vblank that's been modified even when drm_wait_vblank_ioctl returns a failure.

Rationale: drm_wait_vblank_ioctl modifies the request and expects the user to read it back. When the type is RELATIVE, it modifies it to ABSOLUTE and updates the sequence to become current_vblank_count + sequence (which was RELATIVE), but now it became ABSOLUTE. drmWaitVBlank (in libdrm) expects this to be the case as it modifies the request to be Absolute so it expects the sequence to would have been updated.

The change is in compat_drm_wait_vblank, which is called by drm_compat_ioctl. This change of copying the data back regardless of the return number makes it en par with drm_ioctl, which always copies the data before returning.

[How] Return from the function after everything has been copied to user.

Fixes IGT:kms_flip::modeset-vs-vblank-race-interruptible Tested on ChromeOS Trogdor(msm)

Reviewed-by: Michel Dänzer mdaenzer@redhat.com Signed-off-by: Mark Yacoub markyacoub@chromium.org Signed-off-by: Sean Paul seanpaul@chromium.org Link: https://patchwork.freedesktop.org/patch/msgid/20210812194917.1703356-1-marky... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/drm_ioc32.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c index ab8847c7dd96..87e13bcd7a67 100644 --- a/drivers/gpu/drm/drm_ioc32.c +++ b/drivers/gpu/drm/drm_ioc32.c @@ -855,8 +855,6 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd, req.request.sequence = req32.request.sequence; req.request.signal = req32.request.signal; err = drm_ioctl_kernel(file, drm_wait_vblank_ioctl, &req, DRM_UNLOCKED); - if (err) - return err;

req32.reply.type = req.reply.type; req32.reply.sequence = req.reply.sequence; @@ -865,7 +863,7 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd, if (copy_to_user(argp, &req32, sizeof(req32))) return -EFAULT;

- return 0; + return err; }

#if defined(CONFIG_X86)

From: Ben Skeggs bskeggs@redhat.com

[ Upstream commit 148a8653789c01f159764ffcc3f370008966b42f ]

Long ago, there had been plans for making use of a bunch of these APIs from userspace and there's various checks in place to stop misbehaving.

Countless other projects have occurred in the meantime, and the pieces didn't finish falling into place for that to happen.

They will (hopefully) in the not-too-distant future, but it won't look quite as insane. The super checks are causing problems right now, and are going to be removed.

Signed-off-by: Ben Skeggs bskeggs@redhat.com Reviewed-by: Lyude Paul lyude@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/nouveau/include/nvif/cl0080.h | 3 +- drivers/gpu/drm/nouveau/nouveau_drm.c | 1 + drivers/gpu/drm/nouveau/nouveau_usif.c | 57 ++++++++++++++----- .../gpu/drm/nouveau/nvkm/engine/device/user.c | 2 +- 4 files changed, 48 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h index 4f5233107f5f..82daa2bf8415 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h +++ b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h @@ -4,7 +4,8 @@

struct nv_device_v0 { __u8 version; - __u8 pad01[7]; + __u8 priv; + __u8 pad02[6]; __u64 device; /* device identifier, ~0 for client default */ };

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 81999bed1e4a..f4f0a1772774 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -237,6 +237,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, ret = nvif_device_init(&cli->base.object, 0, NV_DEVICE, &(struct nv_device_v0) { .device = ~0, + .priv = true, }, sizeof(struct nv_device_v0), &cli->device); if (ret) { diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c index 9dc10b17ad34..5da1f4d223d7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_usif.c +++ b/drivers/gpu/drm/nouveau/nouveau_usif.c @@ -32,6 +32,9 @@ #include <nvif/event.h> #include <nvif/ioctl.h>

+#include <nvif/class.h> +#include <nvif/cl0080.h> + struct usif_notify_p { struct drm_pending_event base; struct { @@ -261,7 +264,7 @@ usif_object_dtor(struct usif_object *object) }

static int -usif_object_new(struct drm_file *f, void *data, u32 size, void *argv, u32 argc) +usif_object_new(struct drm_file *f, void *data, u32 size, void *argv, u32 argc, bool parent_abi16) { struct nouveau_cli *cli = nouveau_cli(f); struct nvif_client *client = &cli->base; @@ -271,23 +274,48 @@ usif_object_new(struct drm_file *f, void *data, u32 size, void *argv, u32 argc) struct usif_object *object; int ret = -ENOSYS;

+ if ((ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, true))) + return ret; + + switch (args->v0.oclass) { + case NV_DMA_FROM_MEMORY: + case NV_DMA_TO_MEMORY: + case NV_DMA_IN_MEMORY: + return -EINVAL; + case NV_DEVICE: { + union { + struct nv_device_v0 v0; + } *args = data; + + if ((ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, false))) + return ret; + + args->v0.priv = false; + break; + } + default: + if (!parent_abi16) + return -EINVAL; + break; + } + if (!(object = kmalloc(sizeof(*object), GFP_KERNEL))) return -ENOMEM; list_add(&object->head, &cli->objects);

- if (!(ret = nvif_unpack(ret, &data, &size, args->v0, 0, 0, true))) { - object->route = args->v0.route; - object->token = args->v0.token; - args->v0.route = NVDRM_OBJECT_USIF; - args->v0.token = (unsigned long)(void *)object; - ret = nvif_client_ioctl(client, argv, argc); - args->v0.token = object->token; - args->v0.route = object->route; + object->route = args->v0.route; + object->token = args->v0.token; + args->v0.route = NVDRM_OBJECT_USIF; + args->v0.token = (unsigned long)(void *)object; + ret = nvif_client_ioctl(client, argv, argc); + if (ret) { + usif_object_dtor(object); + return ret; }

- if (ret) - usif_object_dtor(object); - return ret; + args->v0.token = object->token; + args->v0.route = object->route; + return 0; }

int @@ -301,6 +329,7 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc) struct nvif_ioctl_v0 v0; } *argv = data; struct usif_object *object; + bool abi16 = false; u8 owner; int ret;

@@ -331,11 +360,13 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc) mutex_unlock(&cli->mutex); goto done; } + + abi16 = true; }

switch (argv->v0.type) { case NVIF_IOCTL_V0_NEW: - ret = usif_object_new(filp, data, size, argv, argc); + ret = usif_object_new(filp, data, size, argv, argc, abi16); break; case NVIF_IOCTL_V0_NTFY_NEW: ret = usif_notify_new(filp, data, size, argv, argc); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c index dde6bbafa709..f8658894e753 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c @@ -426,7 +426,7 @@ nvkm_udevice_new(const struct nvkm_oclass *oclass, void *data, u32 size, return ret;

/* give priviledged clients register access */ - if (client->super) + if (args->v0.priv) func = &nvkm_udevice_super; else func = &nvkm_udevice;