From 95bfec41bd3d39b7659cba65b72080420bf5691e Mon Sep 17 00:00:00 2001 From: Dmitry Fomichev Date: Sat, 15 Oct 2022 23:41:27 -0400 Subject: virtio-blk: add support for zoned block devices This patch adds support for Zoned Block Devices (ZBDs) to the kernel virtio-blk driver. The patch accompanies the virtio-blk ZBD support draft that is now being proposed for standardization. The latest version of the draft is linked at https://github.com/oasis-tcs/virtio-spec/issues/143 . The QEMU zoned device code that implements these protocol extensions has been developed by Sam Li and it is currently in review at the QEMU mailing list. A number of virtblk request structure changes has been introduced to accommodate the functionality that is specific to zoned block devices and, most importantly, make room for carrying the Zoned Append sector value from the device back to the driver along with the request status. The zone-specific code in the patch is heavily influenced by NVMe ZNS code in drivers/nvme/host/zns.c, but it is simpler because the proposed virtio ZBD draft only covers the zoned device features that are relevant to the zoned functionality provided by Linux block layer. includes the following fixup: virtio-blk: fix probe without CONFIG_BLK_DEV_ZONED When building without CONFIG_BLK_DEV_ZONED, VIRTIO_BLK_F_ZONED is excluded from array of driver features. As a result virtio_has_feature panics in virtio_check_driver_offered_feature since that by design verifies that a feature we are checking for is listed in the feature array. To fix, replace the call to virtio_has_feature with a stub. Message-Id: <20221016034127.330942-3-dmitry.fomichev@wdc.com> Co-developed-by: Stefan Hajnoczi Signed-off-by: Stefan Hajnoczi Signed-off-by: Dmitry Fomichev Message-Id: <20221220112340.518841-1-mst@redhat.com> Reported-by: Linux Kernel Functional Testing Tested-by: Linux Kernel Functional Testing Reported-by: Xuan Zhuo Debugged-by: Xuan Zhuo Tested-by: Anders Roxell Tested-by: Marek Szyprowski Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/uapi/linux/virtio_blk.h | 105 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 105 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 58e70b24b504..3744e4da1b2a 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -41,6 +41,7 @@ #define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */ #define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */ #define VIRTIO_BLK_F_SECURE_ERASE 16 /* Secure Erase is supported */ +#define VIRTIO_BLK_F_ZONED 17 /* Zoned block device */ /* Legacy feature bits */ #ifndef VIRTIO_BLK_NO_LEGACY @@ -137,6 +138,16 @@ struct virtio_blk_config { /* Secure erase commands must be aligned to this number of sectors. */ __virtio32 secure_erase_sector_alignment; + /* Zoned block device characteristics (if VIRTIO_BLK_F_ZONED) */ + struct virtio_blk_zoned_characteristics { + __virtio32 zone_sectors; + __virtio32 max_open_zones; + __virtio32 max_active_zones; + __virtio32 max_append_sectors; + __virtio32 write_granularity; + __u8 model; + __u8 unused2[3]; + } zoned; } __attribute__((packed)); /* @@ -174,6 +185,27 @@ struct virtio_blk_config { /* Secure erase command */ #define VIRTIO_BLK_T_SECURE_ERASE 14 +/* Zone append command */ +#define VIRTIO_BLK_T_ZONE_APPEND 15 + +/* Report zones command */ +#define VIRTIO_BLK_T_ZONE_REPORT 16 + +/* Open zone command */ +#define VIRTIO_BLK_T_ZONE_OPEN 18 + +/* Close zone command */ +#define VIRTIO_BLK_T_ZONE_CLOSE 20 + +/* Finish zone command */ +#define VIRTIO_BLK_T_ZONE_FINISH 22 + +/* Reset zone command */ +#define VIRTIO_BLK_T_ZONE_RESET 24 + +/* Reset All zones command */ +#define VIRTIO_BLK_T_ZONE_RESET_ALL 26 + #ifndef VIRTIO_BLK_NO_LEGACY /* Barrier before this op. */ #define VIRTIO_BLK_T_BARRIER 0x80000000 @@ -193,6 +225,72 @@ struct virtio_blk_outhdr { __virtio64 sector; }; +/* + * Supported zoned device models. + */ + +/* Regular block device */ +#define VIRTIO_BLK_Z_NONE 0 +/* Host-managed zoned device */ +#define VIRTIO_BLK_Z_HM 1 +/* Host-aware zoned device */ +#define VIRTIO_BLK_Z_HA 2 + +/* + * Zone descriptor. A part of VIRTIO_BLK_T_ZONE_REPORT command reply. + */ +struct virtio_blk_zone_descriptor { + /* Zone capacity */ + __virtio64 z_cap; + /* The starting sector of the zone */ + __virtio64 z_start; + /* Zone write pointer position in sectors */ + __virtio64 z_wp; + /* Zone type */ + __u8 z_type; + /* Zone state */ + __u8 z_state; + __u8 reserved[38]; +}; + +struct virtio_blk_zone_report { + __virtio64 nr_zones; + __u8 reserved[56]; + struct virtio_blk_zone_descriptor zones[]; +}; + +/* + * Supported zone types. + */ + +/* Conventional zone */ +#define VIRTIO_BLK_ZT_CONV 1 +/* Sequential Write Required zone */ +#define VIRTIO_BLK_ZT_SWR 2 +/* Sequential Write Preferred zone */ +#define VIRTIO_BLK_ZT_SWP 3 + +/* + * Zone states that are available for zones of all types. + */ + +/* Not a write pointer (conventional zones only) */ +#define VIRTIO_BLK_ZS_NOT_WP 0 +/* Empty */ +#define VIRTIO_BLK_ZS_EMPTY 1 +/* Implicitly Open */ +#define VIRTIO_BLK_ZS_IOPEN 2 +/* Explicitly Open */ +#define VIRTIO_BLK_ZS_EOPEN 3 +/* Closed */ +#define VIRTIO_BLK_ZS_CLOSED 4 +/* Read-Only */ +#define VIRTIO_BLK_ZS_RDONLY 13 +/* Full */ +#define VIRTIO_BLK_ZS_FULL 14 +/* Offline */ +#define VIRTIO_BLK_ZS_OFFLINE 15 + /* Unmap this range (only valid for write zeroes command) */ #define VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP 0x00000001 @@ -219,4 +317,11 @@ struct virtio_scsi_inhdr { #define VIRTIO_BLK_S_OK 0 #define VIRTIO_BLK_S_IOERR 1 #define VIRTIO_BLK_S_UNSUPP 2 + +/* Error codes that are specific to zoned block devices */ +#define VIRTIO_BLK_S_ZONE_INVALID_CMD 3 +#define VIRTIO_BLK_S_ZONE_UNALIGNED_WP 4 +#define VIRTIO_BLK_S_ZONE_OPEN_RESOURCE 5 +#define VIRTIO_BLK_S_ZONE_ACTIVE_RESOURCE 6 + #endif /* _LINUX_VIRTIO_BLK_H */ -- cgit v1.2.3 From b16a1756c716235891e298beabd68f3cd6bb5952 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 22 Dec 2022 14:30:13 -0500 Subject: virtio_blk: mark all zone fields LE zone is a virtio 1.x feature so all fields are LE, they are handled as such, but have mistakenly been labeled __virtioXX in the header. This results in a bunch of sparse warnings. Use the __leXX tags to make sparse happy. Message-Id: <20221222193214.55146-1-mst@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_blk.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 3744e4da1b2a..5af2a0300bb9 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -140,11 +140,11 @@ struct virtio_blk_config { /* Zoned block device characteristics (if VIRTIO_BLK_F_ZONED) */ struct virtio_blk_zoned_characteristics { - __virtio32 zone_sectors; - __virtio32 max_open_zones; - __virtio32 max_active_zones; - __virtio32 max_append_sectors; - __virtio32 write_granularity; + __le32 zone_sectors; + __le32 max_open_zones; + __le32 max_active_zones; + __le32 max_append_sectors; + __le32 write_granularity; __u8 model; __u8 unused2[3]; } zoned; @@ -241,11 +241,11 @@ struct virtio_blk_outhdr { */ struct virtio_blk_zone_descriptor { /* Zone capacity */ - __virtio64 z_cap; + __le64 z_cap; /* The starting sector of the zone */ - __virtio64 z_start; + __le64 z_start; /* Zone write pointer position in sectors */ - __virtio64 z_wp; + __le64 z_wp; /* Zone type */ __u8 z_type; /* Zone state */ @@ -254,7 +254,7 @@ struct virtio_blk_zone_descriptor { }; struct virtio_blk_zone_report { - __virtio64 nr_zones; + __le64 nr_zones; __u8 reserved[56]; struct virtio_blk_zone_descriptor zones[]; }; -- cgit v1.2.3 From 69106b6fb3d73bd4252daa48ae96e600c9701147 Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Tue, 3 Jan 2023 11:51:06 +0100 Subject: vhost-vdpa: Introduce RESUME backend feature bit Userspace knows if the device can be resumed or not by checking this feature bit. It's only exposed if the vdpa driver backend implements the resume() operation callback. Userspace trying to negotiate this feature when it hasn't been exposed will result in an error. Acked-by: Jason Wang Signed-off-by: Sebastien Boeuf Message-Id: Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella --- include/uapi/linux/vhost_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 53601ce2c20a..c5690a8992d8 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -163,5 +163,7 @@ struct vhost_vdpa_iova_range { #define VHOST_BACKEND_F_IOTLB_ASID 0x3 /* Device can be suspended */ #define VHOST_BACKEND_F_SUSPEND 0x4 +/* Device can be resumed */ +#define VHOST_BACKEND_F_RESUME 0x5 #endif -- cgit v1.2.3 From 3b688d7a086d0438649ea37990c6e811954fc780 Mon Sep 17 00:00:00 2001 From: Sebastien Boeuf Date: Tue, 3 Jan 2023 11:51:07 +0100 Subject: vhost-vdpa: uAPI to resume the device This new ioctl adds support for resuming the device from userspace. This is required when trying to restore the device in a functioning state after it's been suspended. It is already possible to reset a suspended device, but that means the device must be reconfigured and all the IOMMU/IOTLB mappings must be recreated. This new operation allows the device to be resumed without going through a full reset. This is particularly useful when trying to perform offline migration of a virtual machine (also known as snapshot/restore) as it allows the VMM to resume the virtual machine back to a running state after the snapshot is performed. Acked-by: Jason Wang Signed-off-by: Sebastien Boeuf Message-Id: <73b75fb87d25cff59768b4955a81fe7ffe5b4770.1672742878.git.sebastien.boeuf@intel.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella --- include/uapi/linux/vhost.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index f9f115a7c75b..92e1b700b51c 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -180,4 +180,12 @@ */ #define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) +/* Resume a device so it can resume processing virtqueue requests + * + * After the return of this ioctl the device will have restored all the + * necessary states and it is fully operational to continue processing the + * virtqueue descriptors. + */ +#define VHOST_VDPA_RESUME _IO(VHOST_VIRTIO, 0x7E) + #endif -- cgit v1.2.3