From a8a24f3f6e38103b77cf399c38eb54e1219d00d6 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:47 +0530 Subject: vfio: UAPI for migration interface for device state - Defined MIGRATION region type and sub-type. - Defined vfio_device_migration_info structure which will be placed at the 0th offset of migration region to get/set VFIO device related information. Defined members of structure and usage on read/write access. - Defined device states and state transition details. - Defined sequence to be followed while saving and resuming VFIO device. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Cornelia Huck Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 228 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 228 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 015516bcfaa3..ad9bb5af3463 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -305,6 +305,7 @@ struct vfio_region_info_cap_type { #define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff) #define VFIO_REGION_TYPE_GFX (1) #define VFIO_REGION_TYPE_CCW (2) +#define VFIO_REGION_TYPE_MIGRATION (3) /* sub-types for VFIO_REGION_TYPE_PCI_* */ @@ -379,6 +380,233 @@ struct vfio_region_gfx_edid { /* sub-types for VFIO_REGION_TYPE_CCW */ #define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD (1) +/* sub-types for VFIO_REGION_TYPE_MIGRATION */ +#define VFIO_REGION_SUBTYPE_MIGRATION (1) + +/* + * The structure vfio_device_migration_info is placed at the 0th offset of + * the VFIO_REGION_SUBTYPE_MIGRATION region to get and set VFIO device related + * migration information. Field accesses from this structure are only supported + * at their native width and alignment. Otherwise, the result is undefined and + * vendor drivers should return an error. + * + * device_state: (read/write) + * - The user application writes to this field to inform the vendor driver + * about the device state to be transitioned to. + * - The vendor driver should take the necessary actions to change the + * device state. After successful transition to a given state, the + * vendor driver should return success on write(device_state, state) + * system call. If the device state transition fails, the vendor driver + * should return an appropriate -errno for the fault condition. + * - On the user application side, if the device state transition fails, + * that is, if write(device_state, state) returns an error, read + * device_state again to determine the current state of the device from + * the vendor driver. + * - The vendor driver should return previous state of the device unless + * the vendor driver has encountered an internal error, in which case + * the vendor driver may report the device_state VFIO_DEVICE_STATE_ERROR. + * - The user application must use the device reset ioctl to recover the + * device from VFIO_DEVICE_STATE_ERROR state. If the device is + * indicated to be in a valid device state by reading device_state, the + * user application may attempt to transition the device to any valid + * state reachable from the current state or terminate itself. + * + * device_state consists of 3 bits: + * - If bit 0 is set, it indicates the _RUNNING state. If bit 0 is clear, + * it indicates the _STOP state. When the device state is changed to + * _STOP, driver should stop the device before write() returns. + * - If bit 1 is set, it indicates the _SAVING state, which means that the + * driver should start gathering device state information that will be + * provided to the VFIO user application to save the device's state. + * - If bit 2 is set, it indicates the _RESUMING state, which means that + * the driver should prepare to resume the device. Data provided through + * the migration region should be used to resume the device. + * Bits 3 - 31 are reserved for future use. To preserve them, the user + * application should perform a read-modify-write operation on this + * field when modifying the specified bits. + * + * +------- _RESUMING + * |+------ _SAVING + * ||+----- _RUNNING + * ||| + * 000b => Device Stopped, not saving or resuming + * 001b => Device running, which is the default state + * 010b => Stop the device & save the device state, stop-and-copy state + * 011b => Device running and save the device state, pre-copy state + * 100b => Device stopped and the device state is resuming + * 101b => Invalid state + * 110b => Error state + * 111b => Invalid state + * + * State transitions: + * + * _RESUMING _RUNNING Pre-copy Stop-and-copy _STOP + * (100b) (001b) (011b) (010b) (000b) + * 0. Running or default state + * | + * + * 1. Normal Shutdown (optional) + * |------------------------------------->| + * + * 2. Save the state or suspend + * |------------------------->|---------->| + * + * 3. Save the state during live migration + * |----------->|------------>|---------->| + * + * 4. Resuming + * |<---------| + * + * 5. Resumed + * |--------->| + * + * 0. Default state of VFIO device is _RUNNNG when the user application starts. + * 1. During normal shutdown of the user application, the user application may + * optionally change the VFIO device state from _RUNNING to _STOP. This + * transition is optional. The vendor driver must support this transition but + * must not require it. + * 2. When the user application saves state or suspends the application, the + * device state transitions from _RUNNING to stop-and-copy and then to _STOP. + * On state transition from _RUNNING to stop-and-copy, driver must stop the + * device, save the device state and send it to the application through the + * migration region. The sequence to be followed for such transition is given + * below. + * 3. In live migration of user application, the state transitions from _RUNNING + * to pre-copy, to stop-and-copy, and to _STOP. + * On state transition from _RUNNING to pre-copy, the driver should start + * gathering the device state while the application is still running and send + * the device state data to application through the migration region. + * On state transition from pre-copy to stop-and-copy, the driver must stop + * the device, save the device state and send it to the user application + * through the migration region. + * Vendor drivers must support the pre-copy state even for implementations + * where no data is provided to the user before the stop-and-copy state. The + * user must not be required to consume all migration data before the device + * transitions to a new state, including the stop-and-copy state. + * The sequence to be followed for above two transitions is given below. + * 4. To start the resuming phase, the device state should be transitioned from + * the _RUNNING to the _RESUMING state. + * In the _RESUMING state, the driver should use the device state data + * received through the migration region to resume the device. + * 5. After providing saved device data to the driver, the application should + * change the state from _RESUMING to _RUNNING. + * + * reserved: + * Reads on this field return zero and writes are ignored. + * + * pending_bytes: (read only) + * The number of pending bytes still to be migrated from the vendor driver. + * + * data_offset: (read only) + * The user application should read data_offset field from the migration + * region. The user application should read the device data from this + * offset within the migration region during the _SAVING state or write + * the device data during the _RESUMING state. See below for details of + * sequence to be followed. + * + * data_size: (read/write) + * The user application should read data_size to get the size in bytes of + * the data copied in the migration region during the _SAVING state and + * write the size in bytes of the data copied in the migration region + * during the _RESUMING state. + * + * The format of the migration region is as follows: + * ------------------------------------------------------------------ + * |vfio_device_migration_info| data section | + * | | /////////////////////////////// | + * ------------------------------------------------------------------ + * ^ ^ + * offset 0-trapped part data_offset + * + * The structure vfio_device_migration_info is always followed by the data + * section in the region, so data_offset will always be nonzero. The offset + * from where the data is copied is decided by the kernel driver. The data + * section can be trapped, mmapped, or partitioned, depending on how the kernel + * driver defines the data section. The data section partition can be defined + * as mapped by the sparse mmap capability. If mmapped, data_offset must be + * page aligned, whereas initial section which contains the + * vfio_device_migration_info structure, might not end at the offset, which is + * page aligned. The user is not required to access through mmap regardless + * of the capabilities of the region mmap. + * The vendor driver should determine whether and how to partition the data + * section. The vendor driver should return data_offset accordingly. + * + * The sequence to be followed while in pre-copy state and stop-and-copy state + * is as follows: + * a. Read pending_bytes, indicating the start of a new iteration to get device + * data. Repeated read on pending_bytes at this stage should have no side + * effects. + * If pending_bytes == 0, the user application should not iterate to get data + * for that device. + * If pending_bytes > 0, perform the following steps. + * b. Read data_offset, indicating that the vendor driver should make data + * available through the data section. The vendor driver should return this + * read operation only after data is available from (region + data_offset) + * to (region + data_offset + data_size). + * c. Read data_size, which is the amount of data in bytes available through + * the migration region. + * Read on data_offset and data_size should return the offset and size of + * the current buffer if the user application reads data_offset and + * data_size more than once here. + * d. Read data_size bytes of data from (region + data_offset) from the + * migration region. + * e. Process the data. + * f. Read pending_bytes, which indicates that the data from the previous + * iteration has been read. If pending_bytes > 0, go to step b. + * + * The user application can transition from the _SAVING|_RUNNING + * (pre-copy state) to the _SAVING (stop-and-copy) state regardless of the + * number of pending bytes. The user application should iterate in _SAVING + * (stop-and-copy) until pending_bytes is 0. + * + * The sequence to be followed while _RESUMING device state is as follows: + * While data for this device is available, repeat the following steps: + * a. Read data_offset from where the user application should write data. + * b. Write migration data starting at the migration region + data_offset for + * the length determined by data_size from the migration source. + * c. Write data_size, which indicates to the vendor driver that data is + * written in the migration region. Vendor driver must return this write + * operations on consuming data. Vendor driver should apply the + * user-provided migration region data to the device resume state. + * + * If an error occurs during the above sequences, the vendor driver can return + * an error code for next read() or write() operation, which will terminate the + * loop. The user application should then take the next necessary action, for + * example, failing migration or terminating the user application. + * + * For the user application, data is opaque. The user application should write + * data in the same order as the data is received and the data should be of + * same transaction size at the source. + */ + +struct vfio_device_migration_info { + __u32 device_state; /* VFIO device state */ +#define VFIO_DEVICE_STATE_STOP (0) +#define VFIO_DEVICE_STATE_RUNNING (1 << 0) +#define VFIO_DEVICE_STATE_SAVING (1 << 1) +#define VFIO_DEVICE_STATE_RESUMING (1 << 2) +#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \ + VFIO_DEVICE_STATE_SAVING | \ + VFIO_DEVICE_STATE_RESUMING) + +#define VFIO_DEVICE_STATE_VALID(state) \ + (state & VFIO_DEVICE_STATE_RESUMING ? \ + (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1) + +#define VFIO_DEVICE_STATE_IS_ERROR(state) \ + ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \ + VFIO_DEVICE_STATE_RESUMING)) + +#define VFIO_DEVICE_STATE_SET_ERROR(state) \ + ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \ + VFIO_DEVICE_STATE_RESUMING) + + __u32 reserved; + __u64 pending_bytes; + __u64 data_offset; + __u64 data_size; +}; + /* * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped * which allows direct access to non-MSIX registers which happened to be within -- cgit v1.2.3 From b704fd14a06f678f080e44db28061f1bcb1f595c Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:50 +0530 Subject: vfio iommu: Add ioctl definition for dirty pages tracking IOMMU container maintains a list of all pages pinned by vfio_pin_pages API. All pages pinned by vendor driver through this API should be considered as dirty during migration. When container consists of IOMMU capable device and all pages are pinned and mapped, then all pages are marked dirty. Added support to start/stop dirtied pages tracking and to get bitmap of all dirtied pages for requested IO virtual address range. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Cornelia Huck Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 57 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index ad9bb5af3463..009a8c80079d 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1033,6 +1033,12 @@ struct vfio_iommu_type1_dma_map { #define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13) +struct vfio_bitmap { + __u64 pgsize; /* page size for bitmap in bytes */ + __u64 size; /* in bytes */ + __u64 __user *data; /* one bit per page */ +}; + /** * VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14, * struct vfio_dma_unmap) @@ -1059,6 +1065,57 @@ struct vfio_iommu_type1_dma_unmap { #define VFIO_IOMMU_ENABLE _IO(VFIO_TYPE, VFIO_BASE + 15) #define VFIO_IOMMU_DISABLE _IO(VFIO_TYPE, VFIO_BASE + 16) +/** + * VFIO_IOMMU_DIRTY_PAGES - _IOWR(VFIO_TYPE, VFIO_BASE + 17, + * struct vfio_iommu_type1_dirty_bitmap) + * IOCTL is used for dirty pages logging. + * Caller should set flag depending on which operation to perform, details as + * below: + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_START flag set, instructs + * the IOMMU driver to log pages that are dirtied or potentially dirtied by + * the device; designed to be used when a migration is in progress. Dirty pages + * are logged until logging is disabled by user application by calling the IOCTL + * with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag. + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP flag set, instructs + * the IOMMU driver to stop logging dirtied pages. + * + * Calling the IOCTL with VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP flag set + * returns the dirty pages bitmap for IOMMU container for a given IOVA range. + * The user must specify the IOVA range and the pgsize through the structure + * vfio_iommu_type1_dirty_bitmap_get in the data[] portion. This interface + * supports getting a bitmap of the smallest supported pgsize only and can be + * modified in future to get a bitmap of any specified supported pgsize. The + * user must provide a zeroed memory area for the bitmap memory and specify its + * size in bitmap.size. One bit is used to represent one page consecutively + * starting from iova offset. The user should provide page size in bitmap.pgsize + * field. A bit set in the bitmap indicates that the page at that offset from + * iova is dirty. The caller must set argsz to a value including the size of + * structure vfio_iommu_type1_dirty_bitmap_get, but excluding the size of the + * actual bitmap. If dirty pages logging is not enabled, an error will be + * returned. + * + * Only one of the flags _START, _STOP and _GET may be specified at a time. + * + */ +struct vfio_iommu_type1_dirty_bitmap { + __u32 argsz; + __u32 flags; +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_START (1 << 0) +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP (1 << 1) +#define VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP (1 << 2) + __u8 data[]; +}; + +struct vfio_iommu_type1_dirty_bitmap_get { + __u64 iova; /* IO virtual address */ + __u64 size; /* Size of iova range */ + struct vfio_bitmap bitmap; +}; + +#define VFIO_IOMMU_DIRTY_PAGES _IO(VFIO_TYPE, VFIO_BASE + 17) + /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */ /* -- cgit v1.2.3 From 331e33d2960c8292bad8b02578fcfac18f721517 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:52 +0530 Subject: vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap DMA mapped pages, including those pinned by mdev vendor drivers, might get unpinned and unmapped while migration is active and device is still running. For example, in pre-copy phase while guest driver could access those pages, host device or vendor driver can dirty these mapped pages. Such pages should be marked dirty so as to maintain memory consistency for a user making use of dirty page tracking. To get bitmap during unmap, user should allocate memory for bitmap, set it all zeros, set size of allocated memory, set page size to be considered for bitmap and set flag VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Cornelia Huck Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 61 +++++++++++++++++++++++++++++++++-------- include/uapi/linux/vfio.h | 11 ++++++++ 2 files changed, 61 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index be6fc0d88633..e31fcc23e81a 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1049,23 +1049,25 @@ static int verify_bitmap_size(uint64_t npages, uint64_t bitmap_size) } static int vfio_dma_do_unmap(struct vfio_iommu *iommu, - struct vfio_iommu_type1_dma_unmap *unmap) + struct vfio_iommu_type1_dma_unmap *unmap, + struct vfio_bitmap *bitmap) { - uint64_t mask; struct vfio_dma *dma, *dma_last = NULL; - size_t unmapped = 0; + size_t unmapped = 0, pgsize; int ret = 0, retries = 0; + unsigned long pgshift; mutex_lock(&iommu->lock); - mask = ((uint64_t)1 << __ffs(iommu->pgsize_bitmap)) - 1; + pgshift = __ffs(iommu->pgsize_bitmap); + pgsize = (size_t)1 << pgshift; - if (unmap->iova & mask) { + if (unmap->iova & (pgsize - 1)) { ret = -EINVAL; goto unlock; } - if (!unmap->size || unmap->size & mask) { + if (!unmap->size || unmap->size & (pgsize - 1)) { ret = -EINVAL; goto unlock; } @@ -1076,9 +1078,15 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu, goto unlock; } - WARN_ON(mask & PAGE_MASK); -again: + /* When dirty tracking is enabled, allow only min supported pgsize */ + if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) && + (!iommu->dirty_page_tracking || (bitmap->pgsize != pgsize))) { + ret = -EINVAL; + goto unlock; + } + WARN_ON((pgsize - 1) & PAGE_MASK); +again: /* * vfio-iommu-type1 (v1) - User mappings were coalesced together to * avoid tracking individual mappings. This means that the granularity @@ -1159,6 +1167,14 @@ again: mutex_lock(&iommu->lock); goto again; } + + if (unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) { + ret = update_user_bitmap(bitmap->data, dma, + unmap->iova, pgsize); + if (ret) + break; + } + unmapped += dma->size; vfio_remove_dma(iommu, dma); } @@ -2497,17 +2513,40 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, } else if (cmd == VFIO_IOMMU_UNMAP_DMA) { struct vfio_iommu_type1_dma_unmap unmap; - long ret; + struct vfio_bitmap bitmap = { 0 }; + int ret; minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size); if (copy_from_user(&unmap, (void __user *)arg, minsz)) return -EFAULT; - if (unmap.argsz < minsz || unmap.flags) + if (unmap.argsz < minsz || + unmap.flags & ~VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) return -EINVAL; - ret = vfio_dma_do_unmap(iommu, &unmap); + if (unmap.flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) { + unsigned long pgshift; + + if (unmap.argsz < (minsz + sizeof(bitmap))) + return -EINVAL; + + if (copy_from_user(&bitmap, + (void __user *)(arg + minsz), + sizeof(bitmap))) + return -EFAULT; + + if (!access_ok((void __user *)bitmap.data, bitmap.size)) + return -EINVAL; + + pgshift = __ffs(bitmap.pgsize); + ret = verify_bitmap_size(unmap.size >> pgshift, + bitmap.size); + if (ret) + return ret; + } + + ret = vfio_dma_do_unmap(iommu, &unmap, &bitmap); if (ret) return ret; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 009a8c80079d..ff4b6706f7df 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1048,12 +1048,23 @@ struct vfio_bitmap { * field. No guarantee is made to the user that arbitrary unmaps of iova * or size different from those used in the original mapping call will * succeed. + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get the dirty bitmap + * before unmapping IO virtual addresses. When this flag is set, the user must + * provide a struct vfio_bitmap in data[]. User must provide zero-allocated + * memory via vfio_bitmap.data and its size in the vfio_bitmap.size field. + * A bit in the bitmap represents one page, of user provided page size in + * vfio_bitmap.pgsize field, consecutively starting from iova offset. Bit set + * indicates that the page at that offset from iova is dirty. A Bitmap of the + * pages in the range of unmapped size is returned in the user-provided + * vfio_bitmap.data. */ struct vfio_iommu_type1_dma_unmap { __u32 argsz; __u32 flags; +#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0) __u64 iova; /* IO virtual address */ __u64 size; /* Size of mapping (bytes) */ + __u8 data[]; }; #define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14) -- cgit v1.2.3 From ad721705d09c62f0d108a6b4f59867ebfd592c90 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:53 +0530 Subject: vfio iommu: Add migration capability to report supported features Added migration capability in IOMMU info chain. User application should check IOMMU info chain for migration capability to use dirty page tracking feature provided by kernel module. User application must check page sizes supported and maximum dirty bitmap size returned by this capability structure for ioctls used to get dirty bitmap. Signed-off-by: Kirti Wankhede Reviewed-by: Cornelia Huck Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 23 ++++++++++++++++++++++- include/uapi/linux/vfio.h | 23 +++++++++++++++++++++++ 2 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index e31fcc23e81a..f5c6ca46f165 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -2423,6 +2423,22 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu, return ret; } +static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu, + struct vfio_info_cap *caps) +{ + struct vfio_iommu_type1_info_cap_migration cap_mig; + + cap_mig.header.id = VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION; + cap_mig.header.version = 1; + + cap_mig.flags = 0; + /* support minimum pgsize */ + cap_mig.pgsize_bitmap = (size_t)1 << __ffs(iommu->pgsize_bitmap); + cap_mig.max_dirty_bitmap_size = DIRTY_BITMAP_SIZE_MAX; + + return vfio_info_add_capability(caps, &cap_mig.header, sizeof(cap_mig)); +} + static long vfio_iommu_type1_ioctl(void *iommu_data, unsigned int cmd, unsigned long arg) { @@ -2469,8 +2485,13 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, info.iova_pgsizes = iommu->pgsize_bitmap; - ret = vfio_iommu_iova_build_caps(iommu, &caps); + ret = vfio_iommu_migration_build_caps(iommu, &caps); + + if (!ret) + ret = vfio_iommu_iova_build_caps(iommu, &caps); + mutex_unlock(&iommu->lock); + if (ret) return ret; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index ff4b6706f7df..fde4692a6989 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1013,6 +1013,29 @@ struct vfio_iommu_type1_info_cap_iova_range { struct vfio_iova_range iova_ranges[]; }; +/* + * The migration capability allows to report supported features for migration. + * + * The structures below define version 1 of this capability. + * + * The existence of this capability indicates that IOMMU kernel driver supports + * dirty page logging. + * + * pgsize_bitmap: Kernel driver returns bitmap of supported page sizes for dirty + * page logging. + * max_dirty_bitmap_size: Kernel driver returns maximum supported dirty bitmap + * size in bytes that can be used by user applications when getting the dirty + * bitmap. + */ +#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 1 + +struct vfio_iommu_type1_info_cap_migration { + struct vfio_info_cap_header header; + __u32 flags; + __u64 pgsize_bitmap; + __u64 max_dirty_bitmap_size; /* in bytes */ +}; + #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) /** -- cgit v1.2.3 From 95fc87b44104d9a524ff3e975bbfbd7c1f1a2dd5 Mon Sep 17 00:00:00 2001 From: Kirti Wankhede Date: Fri, 29 May 2020 02:00:54 +0530 Subject: vfio: Selective dirty page tracking if IOMMU backed device pins pages Added a check such that only singleton IOMMU groups can pin pages. >From the point when vendor driver pins any pages, consider IOMMU group dirty page scope to be limited to pinned pages. To optimize to avoid walking list often, added flag pinned_page_dirty_scope to indicate if all of the vfio_groups for each vfio_domain in the domain_list dirty page scope is limited to pinned pages. This flag is updated on first pinned pages request for that IOMMU group and on attaching/detaching group. Signed-off-by: Kirti Wankhede Reviewed-by: Neo Jia Reviewed-by: Yan Zhao Signed-off-by: Alex Williamson --- drivers/vfio/vfio.c | 13 +++-- drivers/vfio/vfio_iommu_type1.c | 103 +++++++++++++++++++++++++++++++++++++--- include/linux/vfio.h | 4 +- 3 files changed, 109 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 765e0e5d83ed..580099afeaff 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -85,6 +85,7 @@ struct vfio_group { atomic_t opened; wait_queue_head_t container_q; bool noiommu; + unsigned int dev_counter; struct kvm *kvm; struct blocking_notifier_head notifier; }; @@ -555,6 +556,7 @@ struct vfio_device *vfio_group_create_device(struct vfio_group *group, mutex_lock(&group->device_lock); list_add(&device->group_next, &group->device_list); + group->dev_counter++; mutex_unlock(&group->device_lock); return device; @@ -567,6 +569,7 @@ static void vfio_device_release(struct kref *kref) struct vfio_group *group = device->group; list_del(&device->group_next); + group->dev_counter--; mutex_unlock(&group->device_lock); dev_set_drvdata(device->dev, NULL); @@ -1945,6 +1948,9 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage, if (!group) return -ENODEV; + if (group->dev_counter > 1) + return -EINVAL; + ret = vfio_group_add_container_user(group); if (ret) goto err_pin_pages; @@ -1952,7 +1958,8 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage, container = group->container; driver = container->iommu_driver; if (likely(driver && driver->ops->pin_pages)) - ret = driver->ops->pin_pages(container->iommu_data, user_pfn, + ret = driver->ops->pin_pages(container->iommu_data, + group->iommu_group, user_pfn, npage, prot, phys_pfn); else ret = -ENOTTY; @@ -2050,8 +2057,8 @@ int vfio_group_pin_pages(struct vfio_group *group, driver = container->iommu_driver; if (likely(driver && driver->ops->pin_pages)) ret = driver->ops->pin_pages(container->iommu_data, - user_iova_pfn, npage, - prot, phys_pfn); + group->iommu_group, user_iova_pfn, + npage, prot, phys_pfn); else ret = -ENOTTY; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index f5c6ca46f165..a6d632d44c82 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -73,6 +73,7 @@ struct vfio_iommu { bool v2; bool nesting; bool dirty_page_tracking; + bool pinned_page_dirty_scope; }; struct vfio_domain { @@ -100,6 +101,7 @@ struct vfio_group { struct iommu_group *iommu_group; struct list_head next; bool mdev_group; /* An mdev group */ + bool pinned_page_dirty_scope; }; struct vfio_iova { @@ -143,6 +145,10 @@ struct vfio_regions { static int put_pfn(unsigned long pfn, int prot); +static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu, + struct iommu_group *iommu_group); + +static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu); /* * This code handles mapping and unmapping of user data buffers * into DMA'ble space using the IOMMU @@ -622,11 +628,13 @@ static int vfio_unpin_page_external(struct vfio_dma *dma, dma_addr_t iova, } static int vfio_iommu_type1_pin_pages(void *iommu_data, + struct iommu_group *iommu_group, unsigned long *user_pfn, int npage, int prot, unsigned long *phys_pfn) { struct vfio_iommu *iommu = iommu_data; + struct vfio_group *group; int i, j, ret; unsigned long remote_vaddr; struct vfio_dma *dma; @@ -699,8 +707,14 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, (iova - dma->iova) >> pgshift, 1); } } - ret = i; + + group = vfio_iommu_find_iommu_group(iommu, iommu_group); + if (!group->pinned_page_dirty_scope) { + group->pinned_page_dirty_scope = true; + update_pinned_page_dirty_scope(iommu); + } + goto pin_done; pin_unwind: @@ -960,8 +974,9 @@ static void vfio_update_pgsize_bitmap(struct vfio_iommu *iommu) } } -static int update_user_bitmap(u64 __user *bitmap, struct vfio_dma *dma, - dma_addr_t base_iova, size_t pgsize) +static int update_user_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu, + struct vfio_dma *dma, dma_addr_t base_iova, + size_t pgsize) { unsigned long pgshift = __ffs(pgsize); unsigned long nbits = dma->size >> pgshift; @@ -970,8 +985,11 @@ static int update_user_bitmap(u64 __user *bitmap, struct vfio_dma *dma, unsigned long shift = bit_offset % BITS_PER_LONG; unsigned long leftover; - /* mark all pages dirty if all pages are pinned and mapped. */ - if (dma->iommu_mapped) + /* + * mark all pages dirty if any IOMMU capable device is not able + * to report dirty pages and all pages are pinned and mapped. + */ + if (!iommu->pinned_page_dirty_scope && dma->iommu_mapped) bitmap_set(dma->bitmap, 0, nbits); if (shift) { @@ -1024,7 +1042,7 @@ static int vfio_iova_dirty_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu, if (dma->iova > iova + size - 1) break; - ret = update_user_bitmap(bitmap, dma, iova, pgsize); + ret = update_user_bitmap(bitmap, iommu, dma, iova, pgsize); if (ret) return ret; @@ -1169,7 +1187,7 @@ again: } if (unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) { - ret = update_user_bitmap(bitmap->data, dma, + ret = update_user_bitmap(bitmap->data, iommu, dma, unmap->iova, pgsize); if (ret) break; @@ -1521,6 +1539,51 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain, return NULL; } +static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu, + struct iommu_group *iommu_group) +{ + struct vfio_domain *domain; + struct vfio_group *group = NULL; + + list_for_each_entry(domain, &iommu->domain_list, next) { + group = find_iommu_group(domain, iommu_group); + if (group) + return group; + } + + if (iommu->external_domain) + group = find_iommu_group(iommu->external_domain, iommu_group); + + return group; +} + +static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu) +{ + struct vfio_domain *domain; + struct vfio_group *group; + + list_for_each_entry(domain, &iommu->domain_list, next) { + list_for_each_entry(group, &domain->group_list, next) { + if (!group->pinned_page_dirty_scope) { + iommu->pinned_page_dirty_scope = false; + return; + } + } + } + + if (iommu->external_domain) { + domain = iommu->external_domain; + list_for_each_entry(group, &domain->group_list, next) { + if (!group->pinned_page_dirty_scope) { + iommu->pinned_page_dirty_scope = false; + return; + } + } + } + + iommu->pinned_page_dirty_scope = true; +} + static bool vfio_iommu_has_sw_msi(struct list_head *group_resv_regions, phys_addr_t *base) { @@ -1928,6 +1991,16 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, list_add(&group->next, &iommu->external_domain->group_list); + /* + * Non-iommu backed group cannot dirty memory directly, + * it can only use interfaces that provide dirty + * tracking. + * The iommu scope can only be promoted with the + * addition of a dirty tracking group. + */ + group->pinned_page_dirty_scope = true; + if (!iommu->pinned_page_dirty_scope) + update_pinned_page_dirty_scope(iommu); mutex_unlock(&iommu->lock); return 0; @@ -2051,6 +2124,13 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, done: /* Delete the old one and insert new iova list */ vfio_iommu_iova_insert_copy(iommu, &iova_copy); + + /* + * An iommu backed group can dirty memory directly and therefore + * demotes the iommu scope until it declares itself dirty tracking + * capable via the page pinning interface. + */ + iommu->pinned_page_dirty_scope = false; mutex_unlock(&iommu->lock); vfio_iommu_resv_free(&group_resv_regions); @@ -2203,6 +2283,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data, struct vfio_iommu *iommu = iommu_data; struct vfio_domain *domain; struct vfio_group *group; + bool update_dirty_scope = false; LIST_HEAD(iova_copy); mutex_lock(&iommu->lock); @@ -2210,6 +2291,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data, if (iommu->external_domain) { group = find_iommu_group(iommu->external_domain, iommu_group); if (group) { + update_dirty_scope = !group->pinned_page_dirty_scope; list_del(&group->next); kfree(group); @@ -2239,6 +2321,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data, continue; vfio_iommu_detach_group(domain, group); + update_dirty_scope = !group->pinned_page_dirty_scope; list_del(&group->next); kfree(group); /* @@ -2270,6 +2353,12 @@ static void vfio_iommu_type1_detach_group(void *iommu_data, vfio_iommu_iova_free(&iova_copy); detach_group_done: + /* + * Removal of a group without dirty tracking may allow the iommu scope + * to be promoted. + */ + if (update_dirty_scope) + update_pinned_page_dirty_scope(iommu); mutex_unlock(&iommu->lock); } diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 5d92ee15d098..38d3c6a8dc7e 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -76,7 +76,9 @@ struct vfio_iommu_driver_ops { struct iommu_group *group); void (*detach_group)(void *iommu_data, struct iommu_group *group); - int (*pin_pages)(void *iommu_data, unsigned long *user_pfn, + int (*pin_pages)(void *iommu_data, + struct iommu_group *group, + unsigned long *user_pfn, int npage, int prot, unsigned long *phys_pfn); int (*unpin_pages)(void *iommu_data, -- cgit v1.2.3