kernel/git/stable/linux-stable.git/drivers/vdpa, branch linux-6.10.y

vdpa/mlx5: Fix invalid mr resource destroy

2024-10-04T14:33:19+00:00

[ Upstream commit dc12502905b7a3de9097ea6b98870470c2921e09 ] Certain error paths from mlx5_vdpa_dev_add() can end up releasing mr resources which never got initialized in the first place. This patch adds the missing check in mlx5_vdpa_destroy_mr_resources() to block releasing non-initialized mr resources. Reference trace: mlx5_core 0000:08:00.2: mlx5_vdpa_dev_add:3274:(pid 2700) warning: No mac address provisioned? BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 140216067 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 8 PID: 2700 Comm: vdpa Kdump: loaded Not tainted 5.14.0-496.el9.x86_64 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:vhost_iotlb_del_range+0xf/0xe0 [vhost_iotlb] Code: [...] RSP: 0018:ff1c823ac23077f0 EFLAGS: 00010246 RAX: ffffffffc1a21a60 RBX: ffffffff899567a0 RCX: 0000000000000000 RDX: ffffffffffffffff RSI: 0000000000000000 RDI: 0000000000000000 RBP: ff1bda1f7c21e800 R08: 0000000000000000 R09: ff1c823ac2307670 R10: ff1c823ac2307668 R11: ffffffff8a9e7b68 R12: 0000000000000000 R13: 0000000000000000 R14: ff1bda1f43e341a0 R15: 00000000ffffffea FS: 00007f56eba7c740(0000) GS:ff1bda269f800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000104d90001 CR4: 0000000000771ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: ? show_trace_log_lvl+0x1c4/0x2df ? show_trace_log_lvl+0x1c4/0x2df ? mlx5_vdpa_free+0x3d/0x150 [mlx5_vdpa] ? __die_body.cold+0x8/0xd ? page_fault_oops+0x134/0x170 ? __irq_work_queue_local+0x2b/0xc0 ? irq_work_queue+0x2c/0x50 ? exc_page_fault+0x62/0x150 ? asm_exc_page_fault+0x22/0x30 ? __pfx_mlx5_vdpa_free+0x10/0x10 [mlx5_vdpa] ? vhost_iotlb_del_range+0xf/0xe0 [vhost_iotlb] mlx5_vdpa_free+0x3d/0x150 [mlx5_vdpa] vdpa_release_dev+0x1e/0x50 [vdpa] device_release+0x31/0x90 kobject_cleanup+0x37/0x130 mlx5_vdpa_dev_add+0x2d2/0x7a0 [mlx5_vdpa] vdpa_nl_cmd_dev_add_set_doit+0x277/0x4c0 [vdpa] genl_family_rcv_msg_doit+0xd9/0x130 genl_family_rcv_msg+0x14d/0x220 ? __pfx_vdpa_nl_cmd_dev_add_set_doit+0x10/0x10 [vdpa] ? _copy_to_user+0x1a/0x30 ? move_addr_to_user+0x4b/0xe0 genl_rcv_msg+0x47/0xa0 ? __import_iovec+0x46/0x150 ? __pfx_genl_rcv_msg+0x10/0x10 netlink_rcv_skb+0x54/0x100 genl_rcv+0x24/0x40 netlink_unicast+0x245/0x370 netlink_sendmsg+0x206/0x440 __sys_sendto+0x1dc/0x1f0 ? do_read_fault+0x10c/0x1d0 ? do_pte_missing+0x10d/0x190 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x5c/0xf0 ? __count_memcg_events+0x4f/0xb0 ? mm_account_fault+0x6c/0x100 ? handle_mm_fault+0x116/0x270 ? do_user_addr_fault+0x1d6/0x6a0 ? do_syscall_64+0x6b/0xf0 ? clear_bhb_loop+0x25/0x80 ? clear_bhb_loop+0x25/0x80 ? clear_bhb_loop+0x25/0x80 ? clear_bhb_loop+0x25/0x80 ? clear_bhb_loop+0x25/0x80 entry_SYSCALL_64_after_hwframe+0x78/0x80 Fixes: 512c0cdd80c1 ("vdpa/mlx5: Decouple cvq iotlb handling from hw mapping code") Signed-off-by: Dragos Tatulea Reviewed-by: Cosmin Ratiu Message-Id: <20240827160808.2448017-2-dtatulea@nvidia.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Si-Wei Liu Acked-by: Jason Wang Reviewed-by: Shannon Nelson Signed-off-by: Sasha Levin

Merge tag 'stable/vduse-virtio-net' into vhost

2024-05-22T12:32:48+00:00

This adds support for virtio-net to vduse. Signed-off-by: Michael S. Tsirkin

vp_vdpa: don't allocate unused msix vectors

2024-05-22T12:31:18+00:00

When there is a ctlq and it doesn't require interrupt callbacks,the original method of calculating vectors wastes hardware msi or msix resources as well as system IRQ resources. When conducting performance testing using testpmd in the guest os, it was found that the performance was lower compared to directly using vfio-pci to passthrough the device In scenarios where the virtio device in the guest os does not utilize interrupts, the vdpa driver still configures the hardware's msix vector. Therefore, the hardware still sends interrupts to the host os. Because of this unnecessary action by the hardware, hardware performance decreases, and it also affects the performance of the host os. Before modification:(interrupt mode) 32: 0 0 0 0 PCI-MSI 32768-edge vp-vdpa[0000:00:02.0]-0 33: 0 0 0 0 PCI-MSI 32769-edge vp-vdpa[0000:00:02.0]-1 34: 0 0 0 0 PCI-MSI 32770-edge vp-vdpa[0000:00:02.0]-2 35: 0 0 0 0 PCI-MSI 32771-edge vp-vdpa[0000:00:02.0]-config After modification:(interrupt mode) 32: 0 0 1 7 PCI-MSI 32768-edge vp-vdpa[0000:00:02.0]-0 33: 36 0 3 0 PCI-MSI 32769-edge vp-vdpa[0000:00:02.0]-1 34: 0 0 0 0 PCI-MSI 32770-edge vp-vdpa[0000:00:02.0]-config Before modification:(virtio pmd mode for guest os) 32: 0 0 0 0 PCI-MSI 32768-edge vp-vdpa[0000:00:02.0]-0 33: 0 0 0 0 PCI-MSI 32769-edge vp-vdpa[0000:00:02.0]-1 34: 0 0 0 0 PCI-MSI 32770-edge vp-vdpa[0000:00:02.0]-2 35: 0 0 0 0 PCI-MSI 32771-edge vp-vdpa[0000:00:02.0]-config After modification:(virtio pmd mode for guest os) 32: 0 0 0 0 PCI-MSI 32768-edge vp-vdpa[0000:00:02.0]-config To verify the use of the virtio PMD mode in the guest operating system, the following patch needs to be applied to QEMU: https://lore.kernel.org/all/20240408073311.2049-1-yuxue.liu@jaguarmicro.com Signed-off-by: Yuxue Liu Acked-by: Jason Wang Reviewed-by: Heng Qi Message-Id: <20240410033020.1310-1-yuxue.liu@jaguarmicro.com> Signed-off-by: Michael S. Tsirkin

vdpa: Convert sprintf/snprintf to sysfs_emit

2024-05-22T12:31:15+00:00

Per filesystems/sysfs.rst, show() should only use sysfs_emit() or sysfs_emit_at() when formatting the value to be returned to user space. coccinelle complains that there are still a couple of functions that use snprintf(). Convert them to sysfs_emit(). sprintf() will be converted as weel if they have. Generally, this patch is generated by make coccicheck M= MODE=patch \ COCCI=scripts/coccinelle/api/device_attr_show.cocci No functional change intended CC: "Michael S. Tsirkin" CC: Jason Wang CC: Xuan Zhuo CC: virtualization@lists.linux.dev Signed-off-by: Li Zhijian Message-Id: <20240314095853.1326111-1-lizhijian@fujitsu.com> Signed-off-by: Michael S. Tsirkin

vp_vdpa: Fix return value check vp_vdpa_request_irq

2024-05-22T12:31:15+00:00

In the vp_vdpa_set_status function, when setting the device status to VIRTIO_CONFIG_S_DRIVER_OK, the vp_vdpa_request_irq function may fail. In such cases, the device status should not be set to DRIVER_OK. Add exception printing to remind the user. Signed-off-by: Yuxue Liu Message-Id: <20240325105448.235-1-gavin.liu@jaguarmicro.com> Signed-off-by: Michael S. Tsirkin

vDPA: code clean for vhost_vdpa uapi

2024-04-22T21:07:13+00:00

This commit cleans up the uapi for vhost_vdpa by better naming some of the enums which report blk information to user space, and they are not in any official releases yet. Fixes: 1ac61ddfee93 ("vDPA: report virtio-blk flush info to user space") Fixes: ae1374b7f72c ("vDPA: report virtio-block read-only info to user space") Fixes: 330b8aea6924 ("vDPA: report virtio-block max segment size to user space") Signed-off-by: Zhu Lingshan Message-Id: <20240415111047.1047774-1-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin

vduse: enable Virtio-net device type

2024-03-19T12:19:15+00:00

This patch adds Virtio-net device type to the supported devices types. Initialization fails if the device does not support VIRTIO_F_VERSION_1 feature, in order to guarantee the configuration space is read-only. It also fails with -EPERM if the CAP_NET_ADMIN is missing. Acked-by: Jason Wang Reviewed-by: Eugenio Pérez Signed-off-by: Maxime Coquelin Message-Id: <20240109111025.1320976-4-maxime.coquelin@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xie Yongji

vduse: Temporarily fail if control queue feature requested

2024-03-19T12:19:14+00:00

Virtio-net driver control queue implementation is not safe when used with VDUSE. If the VDUSE application does not reply to control queue messages, it currently ends up hanging the kernel thread sending this command. Some work is on-going to make the control queue implementation robust with VDUSE. Until it is completed, let's fail features check if control-queue feature is requested. Signed-off-by: Maxime Coquelin Message-Id: <20240109111025.1320976-3-maxime.coquelin@redhat.com> Signed-off-by: Michael S. Tsirkin Acked-by: Eugenio Pérez Reviewed-by: Xie Yongji Acked-by: Jason Wang

vduse: validate block features only with block devices

2024-03-19T12:18:35+00:00

This patch is preliminary work to enable network device type support to VDUSE. As VIRTIO_BLK_F_CONFIG_WCE shares the same value as VIRTIO_NET_F_HOST_TSO4, we need to restrict its check to Virtio-blk device type. Acked-by: Jason Wang Reviewed-by: Xie Yongji Reviewed-by: Eugenio Pérez Signed-off-by: Maxime Coquelin Message-Id: <20240109111025.1320976-2-maxime.coquelin@redhat.com> Signed-off-by: Michael S. Tsirkin

vDPA: report virtio-blk flush info to user space

2024-03-19T06:45:51+00:00

This commit reports whether a virtio-blk device support cache flush command to user space Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-11-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin