Add UAPIs to support migration for VFIO devices
Subsystems (2)
v24 cover Add UAPIs to support migration for VFIO devices
Hi,
This patch set adds:
* IOCTL VFIO_IOMMU_DIRTY_PAGES to get dirty pages bitmap with respect to IOMMU container rather than per device. All pages pinned by vendor driver through vfio_pin_pages external API has to be marked as dirty during migration. When IOMMU capable device is present in the container and all pages are pinned and mapped, then all pages are marked dirty.
When there are CPU writes, CPU dirty page tracking can identify dirtied pages, but any page pinned by vendor driver can also be written by device. As of now there is no device which has hardware support for dirty page tracking. So all pages which are pinned should be considered as dirty.
This ioctl is also used to start/stop dirty pages tracking for pinned and unpinned pages while migration is active.
* Updated IOCTL VFIO_IOMMU_UNMAP_DMA to get dirty pages bitmap before unmapping IO virtual address range.
With vIOMMU, during pre-copy phase of migration, while CPUs are still running, IO virtual address unmap can happen while device still keeping reference of guest pfns. Those pages should be reported as dirty before unmap, so that VFIO user space application can copy content of those pages from source to destination.
* Patch 8 detect if IOMMU capable device driver is smart to report pages to be marked dirty by pinning pages using vfio_pin_pages() API.
Yet TODO:
Since there is no device which has hardware support for system memmory dirty bitmap tracking, right now there is no other API from vendor driver to VFIO IOMMU module to report dirty pages. In future, when such hardware support will be implemented, an API will be required such that vendor driver could report dirty pages to VFIO module during migration phases.
v23 -> v24
- Fixed nit picks by Cornelia
- Fixed warning reported by test robot.
v22 -> v23
- Fixed issue reported by Yan
https://lore.kernel.org/kvm/[email protected]/
- Fixed nit picks suggested by Cornelia
v21 -> v22
- Fixed issue raised by Alex :
https://lore.kernel.org/kvm/[email protected]/
v20 -> v21
- Added checkin for GET_BITMAP ioctl for vfio_dma boundaries.
- Updated unmap ioctl function - as suggested by Alex.
- Updated comments in DIRTY_TRACKING ioctl definition - as suggested by Cornelia.
v19 -> v20
- Fixed ioctl to get dirty bitmap to get bitmap of multiple vfio_dmas
- Fixed unmap ioctl to get dirty bitmap of multiple vfio_dmas.
- Removed flag definition from migration capability.
v18 -> v19
- Updated migration capability with supported page sizes bitmap for dirty page tracking and maximum bitmap size supported by kernel module.
- Added patch to calculate and cache pgsize_bitmap when iommu->domain_list is updated.
- Removed extra buffers added in previous version for bitmap manipulation and optimised the code.
v17 -> v18
- Add migration capability to the capability chain for VFIO_IOMMU_GET_INFO ioctl
- Updated UMAP_DMA ioctl to return bitmap of multiple vfio_dma
v16 -> v17
- Fixed errors reported by kbuild test robot <[email protected]> on i386
v15 -> v16
- Minor edits and nit picks (Auger Eric)
- On copying bitmap to user, re-populated bitmap only for pinned pages, excluding unmapped pages and CPU dirtied pages.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255
v14 -> v15
- Minor edits and nit picks.
- In the verification of user allocated bitmap memory, added check of maximum size.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255
v13 -> v14
- Added struct vfio_bitmap to kabi. updated structure vfio_iommu_type1_dirty_bitmap_get and vfio_iommu_type1_dma_unmap.
- All small changes suggested by Alex.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255
v12 -> v13
- Changed bitmap allocation in vfio_iommu_type1 to per vfio_dma
- Changed VFIO_IOMMU_DIRTY_PAGES ioctl behaviour to be per vfio_dma range.
- Changed vfio_iommu_type1_dirty_bitmap structure to have separate data field.
v11 -> v12
- Changed bitmap allocation in vfio_iommu_type1.
- Remove atomicity of ref_count.
- Updated comments for migration device state structure about error reporting.
- Nit picks from v11 reviews
v10 -> v11
- Fix pin pages API to free vpfn if it is marked as unpinned tracking page.
- Added proposal to detect if IOMMU capable device calls external pin pages API to mark pages dirty.
- Nit picks from v10 reviews
v9 -> v10:
- Updated existing VFIO_IOMMU_UNMAP_DMA ioctl to get dirty pages bitmap during unmap while migration is active
- Added flag in VFIO_IOMMU_GET_INFO to indicate driver support dirty page tracking.
- If iommu_mapped, mark all pages dirty.
- Added unpinned pages tracking while migration is active.
- Updated comments for migration device state structure with bit combination table and state transition details.
v8 -> v9:
- Split patch set in 2 sets, Kernel and QEMU.
- Dirty pages bitmap is queried from IOMMU container rather than from vendor driver for per device. Added 2 ioctls to achieve this.
v7 -> v8:
- Updated comments for KABI
- Added BAR address validation check during PCI device's config space load as suggested by Dr. David Alan Gilbert.
- Changed vfio_migration_set_state() to set or clear device state flags.
- Some nit fixes.
v6 -> v7:
- Fix build failures.
v5 -> v6:
- Fix build failure.
v4 -> v5:
- Added decriptive comment about the sequence of access of members of structure vfio_device_migration_info to be followed based on Alex's suggestion
- Updated get dirty pages sequence.
- As per Cornelia Huck's suggestion, added callbacks to VFIODeviceOps to get_object, save_config and load_config.
- Fixed multiple nit picks.
- Tested live migration with multiple vfio device assigned to a VM.
v3 -> v4:
- Added one more bit for _RESUMING flag to be set explicitly.
- data_offset field is read-only for user space application.
- data_size is read for every iteration before reading data from migration, that is removed assumption that data will be till end of migration region.
- If vendor driver supports mappable sparsed region, map those region during setup state of save/load, similarly unmap those from cleanup routines.
- Handles race condition that causes data corruption in migration region during save device state by adding mutex and serialiaing save_buffer and get_dirty_pages routines.
- Skip called get_dirty_pages routine for mapped MMIO region of device.
- Added trace events.
- Split into multiple functional patches.
v2 -> v3:
- Removed enum of VFIO device states. Defined VFIO device state with 2 bits.
- Re-structured vfio_device_migration_info to keep it minimal and defined action on read and write access on its members.
v1 -> v2:
- Defined MIGRATION region type and sub-type which should be used with region type capability.
- Re-structured vfio_device_migration_info. This structure will be placed at 0th offset of migration region.
- Replaced ioctl with read/write for trapped part of migration region.
- Added both type of access support, trapped or mmapped, for data section of the region.
- Moved PCI device functions to pci file.
- Added iteration to get dirty page bitmap until bitmap for all requested pages are copied.
Thanks,
Kirti
Kirti Wankhede (8):
vfio: UAPI for migration interface for device state
vfio iommu: Remove atomicity of ref_count of pinned pages vfio iommu: Cache pgsize_bitmap in struct vfio_iommu
vfio iommu: Add ioctl definition for dirty pages tracking vfio iommu: Implementation of ioctl for dirty pages tracking vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap vfio iommu: Add migration capability to report supported features
vfio: Selective dirty page tracking if IOMMU backed device pins pages
drivers/vfio/vfio.c | 13 +- drivers/vfio/vfio_iommu_type1.c | 572 ++++++++++++++++++++++++++++++++++++---- include/linux/vfio.h | 4 +- include/uapi/linux/vfio.h | 319 ++++++++++++++++++++++ 4 files changed, 849 insertions(+), 59 deletions(-)
Signature · 1 line
2.7.0
PATCH v24 1/8 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.
--- include/uapi/linux/vfio.h | 228 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 228 insertions(+)
include/uapi/linux/vfio.h +228 -0
@@ -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
Signature · 1 line
2.7.0
Re: [PATCH Kernel v24 1/8] vfio: UAPI for migration interface for device state
Quoted 7 lines · Kirti Wankhede
+ * The sequence to be followed while in pre-copy state and stop-and-copy state
+ * is as follows:
+ * a. Readpending_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.
What if the device doesn't have any data yet but might have some later? This seems to say that if pending_bytes reads 0 the first time then this device doesn't support pre-copy at all.
PATCH v24 2/8 vfio iommu: Remove atomicity of ref_count of pinned pages
In reply to Kirti Wankhedevfio_pfn.ref_count is always updated while holding iommu->lock, using atomic variable is overkill.
--- drivers/vfio/vfio_iommu_type1.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/vfio/vfio_iommu_type1.c +5 -4
@@ -112,7 +112,7 @@ struct vfio_pfn {struct rb_node node;dma_addr_t iova;/* Device address */ unsigned long pfn;/* Host pfn */ -atomic_t ref_count; +unsigned int ref_count; };struct vfio_regions {
@@ -233,7 +233,7 @@ static int vfio_add_to_pfn_list(struct vfio_dma *dma, dma_addr_t iova, vpfn->iova = iova; vpfn->pfn = pfn; -atomic_set (&vpfn->ref_count,1 ); + vpfn->ref_count =1 ;vfio_link_pfn (dma, vpfn);return 0 ; }
@@ -251,7 +251,7 @@ static struct vfio_pfn *vfio_iova_get_vfio_pfn(struct vfio_dma *dma,struct vfio_pfn *vpfn =vfio_find_vpfn (dma, iova);if (vpfn) -atomic_inc (&vpfn->ref_count); + vpfn->ref_count++;return vpfn; }
@@ -259,7 +259,8 @@ static int vfio_iova_put_vfio_pfn(struct vfio_dma *dma, struct vfio_pfn *vpfn) {int ret =0 ; -if (atomic_dec_and_test (&vpfn->ref_count)) { + vpfn->ref_count--; +if (!vpfn->ref_count) { ret =put_pfn (vpfn->pfn, dma->prot);vfio_remove_from_pfn_list (dma, vpfn); }
Signature · 1 line
2.7.0
PATCH v24 3/8 vfio iommu: Cache pgsize_bitmap in struct vfio_iommu
In reply to Kirti WankhedeCalculate and cache pgsize_bitmap when iommu->domain_list is updated and iommu->external_domain is set for mdev device.
Add iommu->lock protection when cached pgsize_bitmap is accessed.
--- drivers/vfio/vfio_iommu_type1.c | 88 +++++++++++++++++++++++------------------ 1 file changed, 49 insertions(+), 39 deletions(-)
drivers/vfio/vfio_iommu_type1.c +49 -39
@@ -69,6 +69,7 @@ struct vfio_iommu {struct rb_root dma_list;struct blocking_notifier_head notifier;unsigned int dma_avail; +uint64_t pgsize_bitmap;bool v2;bool nesting; };
@@ -835,15 +836,14 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma) iommu->dma_avail++; } -static unsigned long vfio_pgsize_bitmap (struct vfio_iommu *iommu) +static void vfio_update_pgsize_bitmap (struct vfio_iommu *iommu) {struct vfio_domain *domain; -unsigned long bitmap =ULONG_MAX ; -mutex_lock (&iommu->lock); + iommu->pgsize_bitmap =ULONG_MAX ; +list_for_each_entry (domain, &iommu->domain_list, next) - bitmap &= domain->domain->pgsize_bitmap; -mutex_unlock (&iommu->lock); + iommu->pgsize_bitmap &= domain->domain->pgsize_bitmap;/* * In case the IOMMU supports page sizes smaller than PAGE_SIZE
@@ -853,12 +853,10 @@ static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)* granularity while iommu driver can use the sub-PAGE_SIZE size * to map the buffer. */ -if (bitmap & ~PAGE_MASK ) { - bitmap &=PAGE_MASK ; - bitmap |=PAGE_SIZE ; +if (iommu->pgsize_bitmap & ~PAGE_MASK ) { + iommu->pgsize_bitmap &=PAGE_MASK ; + iommu->pgsize_bitmap |=PAGE_SIZE ; } - -return bitmap; } static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
@@ -869,19 +867,28 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,size_t unmapped =0 ;int ret =0 , retries =0 ; - mask = ((uint64_t )1 <<__ffs (vfio_pgsize_bitmap (iommu))) -1 ; +mutex_lock (&iommu->lock); + + mask = ((uint64_t )1 <<__ffs (iommu->pgsize_bitmap)) -1 ; + +if (unmap->iova & mask) { + ret = -EINVAL ; + goto unlock; + } + +if (!unmap->size || unmap->size & mask) { + ret = -EINVAL ; + goto unlock; + } -if (unmap->iova & mask) -return -EINVAL ; -if (!unmap->size || unmap->size & mask) -return -EINVAL ;if (unmap->iova + unmap->size -1 < unmap->iova || - unmap->size >SIZE_MAX ) -return -EINVAL ; + unmap->size >SIZE_MAX ) { + ret = -EINVAL ; + goto unlock; + }WARN_ON (mask &PAGE_MASK ); again: -mutex_lock (&iommu->lock);/* * vfio-iommu-type1 (v1) - User mappings were coalesced together to
@@ -960,6 +967,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,blocking_notifier_call_chain (&iommu->notifier,VFIO_IOMMU_NOTIFY_DMA_UNMAP , &nb_unmap); +mutex_lock (&iommu->lock); goto again; } unmapped += dma->size;
@@ -1075,24 +1083,28 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,if (map->size != size || map->vaddr != vaddr || map->iova != iova)return -EINVAL ; - mask = ((uint64_t )1 <<__ffs (vfio_pgsize_bitmap (iommu))) -1 ; - -WARN_ON (mask &PAGE_MASK ); -/* READ/WRITE from device perspective */ if (map->flags &VFIO_DMA_MAP_FLAG_WRITE ) prot |=IOMMU_WRITE ;if (map->flags &VFIO_DMA_MAP_FLAG_READ ) prot |=IOMMU_READ ; -if (!prot || !size || (size | iova | vaddr) & mask) -return -EINVAL ; +mutex_lock (&iommu->lock); -/* Don't allow IOVA or virtual address wrap */ -if (iova + size -1 < iova || vaddr + size -1 < vaddr) -return -EINVAL ; + mask = ((uint64_t )1 <<__ffs (iommu->pgsize_bitmap)) -1 ; -mutex_lock (&iommu->lock); +WARN_ON (mask &PAGE_MASK ); + +if (!prot || !size || (size | iova | vaddr) & mask) { + ret = -EINVAL ; + goto out_unlock; + } + +/* Don't allow IOVA or virtual address wrap */ +if (iova + size -1 < iova || vaddr + size -1 < vaddr) { + ret = -EINVAL ; + goto out_unlock; + }if (vfio_find_dma (iommu, iova, size)) { ret = -EEXIST ;
@@ -1698,6 +1710,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,if (!iommu->external_domain) {INIT_LIST_HEAD (&domain->group_list); iommu->external_domain = domain; +vfio_update_pgsize_bitmap (iommu); }else {kfree (domain); }
@@ -1823,6 +1836,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, }list_add (&domain->next, &iommu->domain_list); +vfio_update_pgsize_bitmap (iommu); done:/* Delete the old one and insert new iova list */ vfio_iommu_iova_insert_copy (iommu, &iova_copy);
@@ -2034,6 +2048,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,list_del (&domain->next);kfree (domain);vfio_iommu_aper_expand (iommu, &iova_copy); +vfio_update_pgsize_bitmap (iommu); }break ; }
@@ -2166,8 +2181,6 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu,size_t size;int iovas =0 , i =0 , ret; -mutex_lock (&iommu->lock); -list_for_each_entry (iova, &iommu->iova_list, list) iovas++;
@@ -2176,17 +2189,14 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu,* Return 0 as a container with a single mdev device * will have an empty list */ - ret =0 ; - goto out_unlock; +return 0 ; } size =sizeof (*cap_iovas) + (iovas *sizeof (*cap_iovas->iova_ranges)); cap_iovas =kzalloc (size,GFP_KERNEL ); -if (!cap_iovas) { - ret = -ENOMEM ; - goto out_unlock; - } +if (!cap_iovas) +return -ENOMEM ; cap_iovas->nr_iovas = iovas;
@@ -2199,8 +2209,6 @@ static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu, ret =vfio_iommu_iova_add_cap (caps, cap_iovas, size);kfree (cap_iovas); -out_unlock: -mutex_unlock (&iommu->lock);return ret; }
@@ -2245,11 +2253,13 @@ static long vfio_iommu_type1_ioctl(void *iommu_data, info.cap_offset =0 ;/* output, no-recopy necessary */ } +mutex_lock (&iommu->lock); info.flags =VFIO_IOMMU_INFO_PGSIZES ; - info.iova_pgsizes =vfio_pgsize_bitmap (iommu); + info.iova_pgsizes = iommu->pgsize_bitmap; ret =vfio_iommu_iova_build_caps (iommu, &caps); +mutex_unlock (&iommu->lock);if (ret)return ret;
Signature · 1 line
2.7.0
PATCH v24 4/8 vfio iommu: Add ioctl definition for dirty pages tracking
In reply to Kirti WankhedeIOMMU 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.
--- include/uapi/linux/vfio.h | 57 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+)
include/uapi/linux/vfio.h +57 -0
@@ -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 -------- */ /*
Signature · 1 line
2.7.0
Re: [PATCH Kernel v24 4/8] vfio iommu: Add ioctl definition for dirty pages tracking
Quoted 8 lines · Kirti Wankhede
+ * Calling the IOCTL with
VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAPflag 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_getin 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
Does "user must provide a zeroed memory area" actually means "the vendor driver sets bits for pages that are dirty and leaves bits unchanged for pages that were not dirtied"? That is more flexible and different from requiring userspace to zero memory.
For example, if userspace doesn't actually have to zero memory then it can accumulate dirty pages from multiple devices by passing the same bitmap buffers to multiple VFIO devices.
If that's the intention, then the documentation shouldn't say "must" zero memory, because applications will need to violate that :). Instead the documentation should describe the behavior (setting dirty bits, leaving clean bits unmodified).
include/uapi/linux/vfio.h struct vfio_iommu_type1_dma_unmap { · line 1115
Quoted 5 lines
include/uapi/linux/vfio.h +5
-0+struct vfio_iommu_type1_dirty_bitmap_get { +__u64 iova;/* IO virtual address */ +__u64 size;/* Size of iova range */ +struct vfio_bitmap bitmap; +};
Can the user application efficiently seek to the next dirty bit or does this API force it to scan the entire iova space each time?
PATCH v24 5/8 vfio iommu: Implementation of ioctl for dirty pages tracking
In reply to Kirti WankhedeVFIO_IOMMU_DIRTY_PAGES ioctl performs three operations:
- Start dirty pages tracking while migration is active
- Stop dirty pages tracking.
- Get dirty pages bitmap. Its user space application's responsibility to copy content of dirty pages from source to destination during migration.
To prevent DoS attack, memory for bitmap is allocated per vfio_dma structure. Bitmap size is calculated considering smallest supported page size. Bitmap is allocated for all vfio_dmas when dirty logging is enabled
Bitmap is populated for already pinned pages when bitmap is allocated for a vfio_dma with the smallest supported page size. Update bitmap from pinning functions when tracking is enabled. When user application queries bitmap, check if requested page size is same as page size used to populated bitmap. If it is equal, copy bitmap, but if not equal, return error.
Fixed error reported by build bot by changing pgsize type from uint64_t to size_t.
--- drivers/vfio/vfio_iommu_type1.c | 314 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 308 insertions(+), 6 deletions(-)
drivers/vfio/vfio_iommu_type1.c +308 -6
@@ -72,6 +72,7 @@ struct vfio_iommu {uint64_t pgsize_bitmap;bool v2;bool nesting; +bool dirty_page_tracking; };struct vfio_domain {
@@ -92,6 +93,7 @@ struct vfio_dma {bool lock_cap;/* capable(CAP_IPC_LOCK) */ struct task_struct *task;struct rb_root pfn_list;/* Ex-user pinned pfn list */ +unsigned long *bitmap; };struct vfio_group {
@@ -126,6 +128,19 @@ struct vfio_regions {#define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER (iommu) \ (!list_empty(&iommu->domain_list)) +#define DIRTY_BITMAP_BYTES (n) (ALIGN(n, BITS_PER_TYPE(u64)) / BITS_PER_BYTE) + +/* +* Input argument of number of bits to bitmap_set() is unsigned integer, which +* further casts to signed integer for unaligned multi-bit operation, +* __bitmap_set(). +* Then maximum bitmap size supported is 2^31 bits divided by 2^3 bits/byte, +* that is 2^28 (256 MB) which maps to 2^31 * 2^12 = 2^43 (8TB) on 4K page +* system. +*/ +#define DIRTY_BITMAP_PAGES_MAX ((u64)INT_MAX) +#define DIRTY_BITMAP_SIZE_MAX DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX) +static int put_pfn (unsigned long pfn,int prot);/*
@@ -176,6 +191,80 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old)rb_erase (&old->node, &iommu->dma_list); } + +static int vfio_dma_bitmap_alloc (struct vfio_dma *dma,size_t pgsize) +{ +uint64_t npages = dma->size / pgsize; + +if (npages >DIRTY_BITMAP_PAGES_MAX ) +return -EINVAL ; + +/* +* Allocate extra 64 bits that are used to calculate shift required for +* bitmap_shift_left() to manipulate and club unaligned number of pages +* in adjacent vfio_dma ranges. +*/ + dma->bitmap =kvzalloc (DIRTY_BITMAP_BYTES (npages) +sizeof (u64), +GFP_KERNEL ); +if (!dma->bitmap) +return -ENOMEM ; + +return 0 ; +} + +static void vfio_dma_bitmap_free (struct vfio_dma *dma) +{ +kfree (dma->bitmap); + dma->bitmap =NULL ; +} + +static void vfio_dma_populate_bitmap (struct vfio_dma *dma,size_t pgsize) +{ +struct rb_node *p; + +for (p =rb_first (&dma->pfn_list); p; p =rb_next (p)) { + struct vfio_pfn *vpfn = rb_entry(p, struct vfio_pfn, node); + +bitmap_set (dma->bitmap, (vpfn->iova - dma->iova) / pgsize,1 ); + } +} + +static int vfio_dma_bitmap_alloc_all (struct vfio_iommu *iommu,size_t pgsize) +{ +struct rb_node *n; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); +int ret; + + ret =vfio_dma_bitmap_alloc (dma, pgsize); +if (ret) { +struct rb_node *p; + +for (p =rb_prev (n); p; p =rb_prev (p)) { +struct vfio_dma *dma =rb_entry (n, + struct vfio_dma, node); + +vfio_dma_bitmap_free (dma); + } +return ret; + } +vfio_dma_populate_bitmap (dma, pgsize); + } +return 0 ; +} + +static void vfio_dma_bitmap_free_all (struct vfio_iommu *iommu) +{ +struct rb_node *n; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + +vfio_dma_bitmap_free (dma); + } +} +/* * Helper Functions for host iova-pfn list */
@@ -598,6 +687,17 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,vfio_unpin_page_external (dma, iova, do_accounting); goto pin_unwind; } + +if (iommu->dirty_page_tracking) { +unsigned long pgshift =__ffs (iommu->pgsize_bitmap); + +/* +* Bitmap populated with the smallest supported page +* size +*/ +bitmap_set (dma->bitmap, + (iova - dma->iova) >> pgshift,1 ); + } } ret = i;
@@ -832,6 +932,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)vfio_unmap_unpin (iommu, dma, true);vfio_unlink_dma (iommu, dma);put_task_struct (dma->task); +vfio_dma_bitmap_free (dma);kfree (dma); iommu->dma_avail++; }
@@ -859,6 +960,94 @@ 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) +{ +unsigned long pgshift =__ffs (pgsize); +unsigned long nbits = dma->size >> pgshift; +unsigned long bit_offset = (dma->iova - base_iova) >> pgshift; +unsigned long copy_offset = bit_offset /BITS_PER_LONG ; +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) +bitmap_set (dma->bitmap,0 , nbits); + +if (shift) { +bitmap_shift_left (dma->bitmap, dma->bitmap, shift, + nbits + shift); + +if (copy_from_user (&leftover, + (const void *)(bitmap + copy_offset), +sizeof (leftover))) +return -EFAULT ; + +bitmap_or (dma->bitmap, dma->bitmap, &leftover, shift); + } + +if (copy_to_user ((void *)(bitmap + copy_offset), dma->bitmap, +DIRTY_BITMAP_BYTES (nbits + shift))) +return -EFAULT ; + +return 0 ; +} + +static int vfio_iova_dirty_bitmap (u64 __user *bitmap,struct vfio_iommu *iommu, +dma_addr_t iova,size_t size,size_t pgsize) +{ +struct vfio_dma *dma; +struct rb_node *n; +unsigned long pgshift =__ffs (pgsize); +int ret; + +/* +* GET_BITMAP request must fully cover vfio_dma mappings. Multiple +* vfio_dma mappings may be clubbed by specifying large ranges, but +* there must not be any previous mappings bisected by the range. +* An error will be returned if these conditions are not met. +*/ + dma =vfio_find_dma (iommu, iova,1 ); +if (dma && dma->iova != iova) +return -EINVAL ; + + dma =vfio_find_dma (iommu, iova + size -1 ,0 ); +if (dma && dma->iova + dma->size != iova + size) +return -EINVAL ; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + +if (dma->iova < iova) +continue ; + +if (dma->iova > iova + size -1 ) +break ; + + ret =update_user_bitmap (bitmap, dma, iova, pgsize); +if (ret) +return ret; + +/* +* Re-populate bitmap to include all pinned pages which are +* considered as dirty but exclude pages which are unpinned and +* pages which are marked dirty by vfio_dma_rw() +*/ +bitmap_clear (dma->bitmap,0 , dma->size >> pgshift); +vfio_dma_populate_bitmap (dma, pgsize); + } +return 0 ; +} + +static int verify_bitmap_size (uint64_t npages,uint64_t bitmap_size) +{ +if (!npages || !bitmap_size || (bitmap_size >DIRTY_BITMAP_SIZE_MAX ) || + (bitmap_size <DIRTY_BITMAP_BYTES (npages))) +return -EINVAL ; + +return 0 ; +} +static int vfio_dma_do_unmap (struct vfio_iommu *iommu,struct vfio_iommu_type1_dma_unmap *unmap) {
@@ -1076,7 +1265,7 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,unsigned long vaddr = map->vaddr;size_t size = map->size;int ret =0 , prot =0 ; -uint64_t mask; +size_t pgsize;struct vfio_dma *dma;/* Verify that none of our __u64 fields overflow */
@@ -1091,11 +1280,11 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,mutex_lock (&iommu->lock); - mask = ((uint64_t )1 <<__ffs (iommu->pgsize_bitmap)) -1 ; + pgsize = (size_t )1 <<__ffs (iommu->pgsize_bitmap); -WARN_ON (mask &PAGE_MASK ); +WARN_ON ((pgsize -1 ) &PAGE_MASK ); -if (!prot || !size || (size | iova | vaddr) & mask) { +if (!prot || !size || (size | iova | vaddr) & (pgsize -1 )) { ret = -EINVAL ; goto out_unlock; }
@@ -1172,6 +1361,12 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,else ret =vfio_pin_map_dma (iommu, dma, size); +if (!ret && iommu->dirty_page_tracking) { + ret =vfio_dma_bitmap_alloc (dma, pgsize); +if (ret) +vfio_remove_dma (iommu, dma); + } + out_unlock:mutex_unlock (&iommu->lock);return ret;
@@ -2318,6 +2513,104 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,return copy_to_user ((void __user *)arg, &unmap, minsz) ? -EFAULT :0 ; + }else if (cmd ==VFIO_IOMMU_DIRTY_PAGES ) { +struct vfio_iommu_type1_dirty_bitmap dirty; +uint32_t mask =VFIO_IOMMU_DIRTY_PAGES_FLAG_START | +VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP | +VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP ; +int ret =0 ; + +if (!iommu->v2) +return -EACCES ; + + minsz = offsetofend(struct vfio_iommu_type1_dirty_bitmap, + flags); + +if (copy_from_user (&dirty, (void __user *)arg, minsz)) +return -EFAULT ; + +if (dirty.argsz < minsz || dirty.flags & ~mask) +return -EINVAL ; + +/* only one flag should be set at a time */ +if (__ffs (dirty.flags) !=__fls (dirty.flags)) +return -EINVAL ; + +if (dirty.flags &VFIO_IOMMU_DIRTY_PAGES_FLAG_START ) { +size_t pgsize; + +mutex_lock (&iommu->lock); + pgsize =1 <<__ffs (iommu->pgsize_bitmap); +if (!iommu->dirty_page_tracking) { + ret =vfio_dma_bitmap_alloc_all (iommu, pgsize); +if (!ret) + iommu->dirty_page_tracking = true; + } +mutex_unlock (&iommu->lock); +return ret; + }else if (dirty.flags &VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP ) { +mutex_lock (&iommu->lock); +if (iommu->dirty_page_tracking) { + iommu->dirty_page_tracking = false; +vfio_dma_bitmap_free_all (iommu); + } +mutex_unlock (&iommu->lock); +return 0 ; + }else if (dirty.flags & +VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP ) { +struct vfio_iommu_type1_dirty_bitmap_get range; +unsigned long pgshift; +size_t data_size = dirty.argsz - minsz; +size_t iommu_pgsize; + +if (!data_size || data_size <sizeof (range)) +return -EINVAL ; + +if (copy_from_user (&range, (void __user *)(arg + minsz), +sizeof (range))) +return -EFAULT ; + +if (range.iova + range.size < range.iova) +return -EINVAL ; +if (!access_ok ((void __user *)range.bitmap.data, + range.bitmap.size)) +return -EINVAL ; + + pgshift =__ffs (range.bitmap.pgsize); + ret =verify_bitmap_size (range.size >> pgshift, + range.bitmap.size); +if (ret) +return ret; + +mutex_lock (&iommu->lock); + + iommu_pgsize = (size_t )1 <<__ffs (iommu->pgsize_bitmap); + +/* allow only smallest supported pgsize */ +if (range.bitmap.pgsize != iommu_pgsize) { + ret = -EINVAL ; + goto out_unlock; + } +if (range.iova & (iommu_pgsize -1 )) { + ret = -EINVAL ; + goto out_unlock; + } +if (!range.size || range.size & (iommu_pgsize -1 )) { + ret = -EINVAL ; + goto out_unlock; + } + +if (iommu->dirty_page_tracking) + ret =vfio_iova_dirty_bitmap (range.bitmap.data, + iommu, range.iova, range.size, + range.bitmap.pgsize); +else + ret = -EINVAL ; +out_unlock: +mutex_unlock (&iommu->lock); + +return ret; + } }return -ENOTTY ;
@@ -2385,10 +2678,19 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu, vaddr = dma->vaddr + offset; -if (write) +if (write) { *copied =copy_to_user ((void __user *)vaddr, data, count) ?0 : count; -else +if (*copied && iommu->dirty_page_tracking) { +unsigned long pgshift =__ffs (iommu->pgsize_bitmap); +/* +* Bitmap populated with the smallest supported page +* size +*/ +bitmap_set (dma->bitmap, offset >> pgshift, + *copied >> pgshift); + } + }else *copied =copy_from_user (data, (void __user *)vaddr, count) ?0 : count;if (kthread)
Signature · 1 line
2.7.0
kbuild test robot
build botRe: [PATCH Kernel v24 5/8] vfio iommu: Implementation of ioctl for dirty pages tracking
I love your patch! Perhaps something to improve:
Hi Kirti,
I love your patch! Perhaps something to improve:
[auto build test WARNING on v5.7-rc7]
[also build test WARNING on next-20200529]
[cannot apply to vfio/next]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system. BTW, we also suggest to use '--base' option to specify the base tree in git format-patch, please see https://stackoverflow.com/a/37406982]
url: https://github.com/0day-ci/linux/commits/Kirti-Wankhede/Add-UAPIs-to-support-migration-for-VFIO-devices/20200531-020103 base: 9cb1fd0efd195590b828b9b865421ad345a4a145 config: i386-randconfig-s031-20200531 (attached as .config) compiler: gcc-9 (Debian 9.3.0-13) 9.3.0 reproduce: # apt-get install sparse # sparse version: v0.6.1-243-gc100a7ab-dirty # save the attached .config to linux build tree make W=1 C=1 ARCH=i386 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__'
If you fix the issue, kindly add following tag as appropriate
sparse warnings: (new ones prefixed by >>)
drivers/vfio/vfio_iommu_type1.c:952:37: sparse: sparse: cast removes address space '<asn:1>' of expression
>> drivers/vfio/vfio_iommu_type1.c:952:37: sparse: sparse: incorrect type in argument 2 (different address spaces) @@ expected void const [noderef] <asn:1> *from @@ got void const * @@ drivers/vfio/vfio_iommu_type1.c:952:37: sparse: expected void const [noderef] <asn:1> *from >> drivers/vfio/vfio_iommu_type1.c:952:37: sparse: got void const * drivers/vfio/vfio_iommu_type1.c:959:27: sparse: sparse: cast removes address space '<asn:1>' of expression >> drivers/vfio/vfio_iommu_type1.c:959:27: sparse: sparse: incorrect type in argument 1 (different address spaces) @@ expected void [noderef] <asn:1> *to @@ got void * @@ drivers/vfio/vfio_iommu_type1.c:959:27: sparse: expected void [noderef] <asn:1> *to >> drivers/vfio/vfio_iommu_type1.c:959:27: sparse: got void *
vim +952 drivers/vfio/vfio_iommu_type1.c
932
933 static int update_user_bitmap(u64 __user *bitmap, struct vfio_dma *dma,
934 dma_addr_t base_iova, size_t pgsize)
935 {
936 unsigned long pgshift = __ffs(pgsize);
937 unsigned long nbits = dma->size >> pgshift;
938 unsigned long bit_offset = (dma->iova - base_iova) >> pgshift;
939 unsigned long copy_offset = bit_offset / BITS_PER_LONG;
940 unsigned long shift = bit_offset % BITS_PER_LONG;
941 unsigned long leftover;
942
943 /* mark all pages dirty if all pages are pinned and mapped. */
944 if (dma->iommu_mapped)
945 bitmap_set(dma->bitmap, 0, nbits);
946
947 if (shift) {
948 bitmap_shift_left(dma->bitmap, dma->bitmap, shift,
949 nbits + shift);
950
951 if (copy_from_user(&leftover,
> 952 (const void *)(bitmap + copy_offset), 953 sizeof(leftover))) 954 return -EFAULT; 955 956 bitmap_or(dma->bitmap, dma->bitmap, &leftover, shift); 957 } 958 > 959 if (copy_to_user((void *)(bitmap + copy_offset), dma->bitmap,
960 DIRTY_BITMAP_BYTES(nbits + shift)))
961 return -EFAULT;
962
963 return 0;
964 }
965
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org
kbuild test robot
build botRe: [PATCH Kernel v24 5/8] vfio iommu: Implementation of ioctl for dirty pages tracking
In reply to Kirti WankhedeI love your patch! Yet something to improve:
Hi Kirti,
I love your patch! Yet something to improve:
[auto build test ERROR on v5.7-rc7]
[also build test ERROR on next-20200529]
[cannot apply to vfio/next]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system. BTW, we also suggest to use '--base' option to specify the base tree in git format-patch, please see https://stackoverflow.com/a/37406982]
url: https://github.com/0day-ci/linux/commits/Kirti-Wankhede/Add-UAPIs-to-support-migration-for-VFIO-devices/20200531-020103 base: 9cb1fd0efd195590b828b9b865421ad345a4a145 config: i386-randconfig-s031-20200531 (attached as .config) compiler: gcc-9 (Debian 9.3.0-13) 9.3.0 reproduce: # apt-get install sparse # sparse version: v0.6.1-243-gc100a7ab-dirty # save the attached .config to linux build tree make W=1 C=1 ARCH=i386 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__'
If you fix the issue, kindly add following tag as appropriate
All errors (new ones prefixed by >>, old ones prefixed by <<):
ld: drivers/vfio/vfio_iommu_type1.o: in function `vfio_dma_populate_bitmap':
>> vfio_iommu_type1.c:(.text+0x666): undefined reference to `__udivdi3'
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org
PATCH v24 5/8 vfio iommu: Implementation of ioctl for dirty pages tracking
In reply to Kirti WankhedeVFIO_IOMMU_DIRTY_PAGES ioctl performs three operations:
- Start dirty pages tracking while migration is active
- Stop dirty pages tracking.
- Get dirty pages bitmap. Its user space application's responsibility to copy content of dirty pages from source to destination during migration.
To prevent DoS attack, memory for bitmap is allocated per vfio_dma structure. Bitmap size is calculated considering smallest supported page size. Bitmap is allocated for all vfio_dmas when dirty logging is enabled
Bitmap is populated for already pinned pages when bitmap is allocated for a vfio_dma with the smallest supported page size. Update bitmap from pinning functions when tracking is enabled. When user application queries bitmap, check if requested page size is same as page size used to populated bitmap. If it is equal, copy bitmap, but if not equal, return error.
Fixed error reported by build bot by changing pgsize type from uint64_t to size_t.
---
Fixed errors and sparse warnings reported by kbuild test robot
ld: drivers/vfio/vfio_iommu_type1.o: in function `vfio_dma_populate_bitmap':
Quoted 1 line
Quoted 1 line
vfio_iommu_type1.c:(.text+0x666): undefined reference to `__udivdi3'
drivers/vfio/vfio_iommu_type1.c | 315 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 309 insertions(+), 6 deletions(-)
drivers/vfio/vfio_iommu_type1.c +309 -6
@@ -72,6 +72,7 @@ struct vfio_iommu {uint64_t pgsize_bitmap;bool v2;bool nesting; +bool dirty_page_tracking; };struct vfio_domain {
@@ -92,6 +93,7 @@ struct vfio_dma {bool lock_cap;/* capable(CAP_IPC_LOCK) */ struct task_struct *task;struct rb_root pfn_list;/* Ex-user pinned pfn list */ +unsigned long *bitmap; };struct vfio_group {
@@ -126,6 +128,19 @@ struct vfio_regions {#define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER (iommu) \ (!list_empty(&iommu->domain_list)) +#define DIRTY_BITMAP_BYTES (n) (ALIGN(n, BITS_PER_TYPE(u64)) / BITS_PER_BYTE) + +/* +* Input argument of number of bits to bitmap_set() is unsigned integer, which +* further casts to signed integer for unaligned multi-bit operation, +* __bitmap_set(). +* Then maximum bitmap size supported is 2^31 bits divided by 2^3 bits/byte, +* that is 2^28 (256 MB) which maps to 2^31 * 2^12 = 2^43 (8TB) on 4K page +* system. +*/ +#define DIRTY_BITMAP_PAGES_MAX ((u64)INT_MAX) +#define DIRTY_BITMAP_SIZE_MAX DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX) +static int put_pfn (unsigned long pfn,int prot);/*
@@ -176,6 +191,81 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old)rb_erase (&old->node, &iommu->dma_list); } + +static int vfio_dma_bitmap_alloc (struct vfio_dma *dma,size_t pgsize) +{ +uint64_t npages = dma->size / pgsize; + +if (npages >DIRTY_BITMAP_PAGES_MAX ) +return -EINVAL ; + +/* +* Allocate extra 64 bits that are used to calculate shift required for +* bitmap_shift_left() to manipulate and club unaligned number of pages +* in adjacent vfio_dma ranges. +*/ + dma->bitmap =kvzalloc (DIRTY_BITMAP_BYTES (npages) +sizeof (u64), +GFP_KERNEL ); +if (!dma->bitmap) +return -ENOMEM ; + +return 0 ; +} + +static void vfio_dma_bitmap_free (struct vfio_dma *dma) +{ +kfree (dma->bitmap); + dma->bitmap =NULL ; +} + +static void vfio_dma_populate_bitmap (struct vfio_dma *dma,size_t pgsize) +{ +struct rb_node *p; +unsigned long pgshift =__ffs (pgsize); + +for (p =rb_first (&dma->pfn_list); p; p =rb_next (p)) { + struct vfio_pfn *vpfn = rb_entry(p, struct vfio_pfn, node); + +bitmap_set (dma->bitmap, (vpfn->iova - dma->iova) >> pgshift,1 ); + } +} + +static int vfio_dma_bitmap_alloc_all (struct vfio_iommu *iommu,size_t pgsize) +{ +struct rb_node *n; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); +int ret; + + ret =vfio_dma_bitmap_alloc (dma, pgsize); +if (ret) { +struct rb_node *p; + +for (p =rb_prev (n); p; p =rb_prev (p)) { +struct vfio_dma *dma =rb_entry (n, + struct vfio_dma, node); + +vfio_dma_bitmap_free (dma); + } +return ret; + } +vfio_dma_populate_bitmap (dma, pgsize); + } +return 0 ; +} + +static void vfio_dma_bitmap_free_all (struct vfio_iommu *iommu) +{ +struct rb_node *n; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + +vfio_dma_bitmap_free (dma); + } +} +/* * Helper Functions for host iova-pfn list */
@@ -598,6 +688,17 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,vfio_unpin_page_external (dma, iova, do_accounting); goto pin_unwind; } + +if (iommu->dirty_page_tracking) { +unsigned long pgshift =__ffs (iommu->pgsize_bitmap); + +/* +* Bitmap populated with the smallest supported page +* size +*/ +bitmap_set (dma->bitmap, + (iova - dma->iova) >> pgshift,1 ); + } } ret = i;
@@ -832,6 +933,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)vfio_unmap_unpin (iommu, dma, true);vfio_unlink_dma (iommu, dma);put_task_struct (dma->task); +vfio_dma_bitmap_free (dma);kfree (dma); iommu->dma_avail++; }
@@ -859,6 +961,94 @@ 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) +{ +unsigned long pgshift =__ffs (pgsize); +unsigned long nbits = dma->size >> pgshift; +unsigned long bit_offset = (dma->iova - base_iova) >> pgshift; +unsigned long copy_offset = bit_offset /BITS_PER_LONG ; +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) +bitmap_set (dma->bitmap,0 , nbits); + +if (shift) { +bitmap_shift_left (dma->bitmap, dma->bitmap, shift, + nbits + shift); + +if (copy_from_user (&leftover, + (void __user *)(bitmap + copy_offset), +sizeof (leftover))) +return -EFAULT ; + +bitmap_or (dma->bitmap, dma->bitmap, &leftover, shift); + } + +if (copy_to_user ((void __user *)(bitmap + copy_offset), dma->bitmap, +DIRTY_BITMAP_BYTES (nbits + shift))) +return -EFAULT ; + +return 0 ; +} + +static int vfio_iova_dirty_bitmap (u64 __user *bitmap,struct vfio_iommu *iommu, +dma_addr_t iova,size_t size,size_t pgsize) +{ +struct vfio_dma *dma; +struct rb_node *n; +unsigned long pgshift =__ffs (pgsize); +int ret; + +/* +* GET_BITMAP request must fully cover vfio_dma mappings. Multiple +* vfio_dma mappings may be clubbed by specifying large ranges, but +* there must not be any previous mappings bisected by the range. +* An error will be returned if these conditions are not met. +*/ + dma =vfio_find_dma (iommu, iova,1 ); +if (dma && dma->iova != iova) +return -EINVAL ; + + dma =vfio_find_dma (iommu, iova + size -1 ,0 ); +if (dma && dma->iova + dma->size != iova + size) +return -EINVAL ; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + +if (dma->iova < iova) +continue ; + +if (dma->iova > iova + size -1 ) +break ; + + ret =update_user_bitmap (bitmap, dma, iova, pgsize); +if (ret) +return ret; + +/* +* Re-populate bitmap to include all pinned pages which are +* considered as dirty but exclude pages which are unpinned and +* pages which are marked dirty by vfio_dma_rw() +*/ +bitmap_clear (dma->bitmap,0 , dma->size >> pgshift); +vfio_dma_populate_bitmap (dma, pgsize); + } +return 0 ; +} + +static int verify_bitmap_size (uint64_t npages,uint64_t bitmap_size) +{ +if (!npages || !bitmap_size || (bitmap_size >DIRTY_BITMAP_SIZE_MAX ) || + (bitmap_size <DIRTY_BITMAP_BYTES (npages))) +return -EINVAL ; + +return 0 ; +} +static int vfio_dma_do_unmap (struct vfio_iommu *iommu,struct vfio_iommu_type1_dma_unmap *unmap) {
@@ -1076,7 +1266,7 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,unsigned long vaddr = map->vaddr;size_t size = map->size;int ret =0 , prot =0 ; -uint64_t mask; +size_t pgsize;struct vfio_dma *dma;/* Verify that none of our __u64 fields overflow */
@@ -1091,11 +1281,11 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,mutex_lock (&iommu->lock); - mask = ((uint64_t )1 <<__ffs (iommu->pgsize_bitmap)) -1 ; + pgsize = (size_t )1 <<__ffs (iommu->pgsize_bitmap); -WARN_ON (mask &PAGE_MASK ); +WARN_ON ((pgsize -1 ) &PAGE_MASK ); -if (!prot || !size || (size | iova | vaddr) & mask) { +if (!prot || !size || (size | iova | vaddr) & (pgsize -1 )) { ret = -EINVAL ; goto out_unlock; }
@@ -1172,6 +1362,12 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,else ret =vfio_pin_map_dma (iommu, dma, size); +if (!ret && iommu->dirty_page_tracking) { + ret =vfio_dma_bitmap_alloc (dma, pgsize); +if (ret) +vfio_remove_dma (iommu, dma); + } + out_unlock:mutex_unlock (&iommu->lock);return ret;
@@ -2318,6 +2514,104 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,return copy_to_user ((void __user *)arg, &unmap, minsz) ? -EFAULT :0 ; + }else if (cmd ==VFIO_IOMMU_DIRTY_PAGES ) { +struct vfio_iommu_type1_dirty_bitmap dirty; +uint32_t mask =VFIO_IOMMU_DIRTY_PAGES_FLAG_START | +VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP | +VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP ; +int ret =0 ; + +if (!iommu->v2) +return -EACCES ; + + minsz = offsetofend(struct vfio_iommu_type1_dirty_bitmap, + flags); + +if (copy_from_user (&dirty, (void __user *)arg, minsz)) +return -EFAULT ; + +if (dirty.argsz < minsz || dirty.flags & ~mask) +return -EINVAL ; + +/* only one flag should be set at a time */ +if (__ffs (dirty.flags) !=__fls (dirty.flags)) +return -EINVAL ; + +if (dirty.flags &VFIO_IOMMU_DIRTY_PAGES_FLAG_START ) { +size_t pgsize; + +mutex_lock (&iommu->lock); + pgsize =1 <<__ffs (iommu->pgsize_bitmap); +if (!iommu->dirty_page_tracking) { + ret =vfio_dma_bitmap_alloc_all (iommu, pgsize); +if (!ret) + iommu->dirty_page_tracking = true; + } +mutex_unlock (&iommu->lock); +return ret; + }else if (dirty.flags &VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP ) { +mutex_lock (&iommu->lock); +if (iommu->dirty_page_tracking) { + iommu->dirty_page_tracking = false; +vfio_dma_bitmap_free_all (iommu); + } +mutex_unlock (&iommu->lock); +return 0 ; + }else if (dirty.flags & +VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP ) { +struct vfio_iommu_type1_dirty_bitmap_get range; +unsigned long pgshift; +size_t data_size = dirty.argsz - minsz; +size_t iommu_pgsize; + +if (!data_size || data_size <sizeof (range)) +return -EINVAL ; + +if (copy_from_user (&range, (void __user *)(arg + minsz), +sizeof (range))) +return -EFAULT ; + +if (range.iova + range.size < range.iova) +return -EINVAL ; +if (!access_ok ((void __user *)range.bitmap.data, + range.bitmap.size)) +return -EINVAL ; + + pgshift =__ffs (range.bitmap.pgsize); + ret =verify_bitmap_size (range.size >> pgshift, + range.bitmap.size); +if (ret) +return ret; + +mutex_lock (&iommu->lock); + + iommu_pgsize = (size_t )1 <<__ffs (iommu->pgsize_bitmap); + +/* allow only smallest supported pgsize */ +if (range.bitmap.pgsize != iommu_pgsize) { + ret = -EINVAL ; + goto out_unlock; + } +if (range.iova & (iommu_pgsize -1 )) { + ret = -EINVAL ; + goto out_unlock; + } +if (!range.size || range.size & (iommu_pgsize -1 )) { + ret = -EINVAL ; + goto out_unlock; + } + +if (iommu->dirty_page_tracking) + ret =vfio_iova_dirty_bitmap (range.bitmap.data, + iommu, range.iova, range.size, + range.bitmap.pgsize); +else + ret = -EINVAL ; +out_unlock: +mutex_unlock (&iommu->lock); + +return ret; + } }return -ENOTTY ;
@@ -2385,10 +2679,19 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu, vaddr = dma->vaddr + offset; -if (write) +if (write) { *copied =copy_to_user ((void __user *)vaddr, data, count) ?0 : count; -else +if (*copied && iommu->dirty_page_tracking) { +unsigned long pgshift =__ffs (iommu->pgsize_bitmap); +/* +* Bitmap populated with the smallest supported page +* size +*/ +bitmap_set (dma->bitmap, offset >> pgshift, + *copied >> pgshift); + } + }else *copied =copy_from_user (data, (void __user *)vaddr, count) ?0 : count;if (kthread)
Signature · 1 line
2.7.0
Re: [PATCH Kernel v24 5/8] vfio iommu: Implementation of ioctl for dirty pages tracking
Quoted 23 lines · On Tue, 2 Jun 2020 21:21:30 +0530 Kirti Wankhede <[email protected]> wrote:
VFIO_IOMMU_DIRTY_PAGESioctl performs three operations:
- Start dirty pages tracking while migration is active
- Stop dirty pages tracking.
- Get dirty pages bitmap. Its user space application's responsibility to copy content of dirty pages from source to destination during migration.To prevent DoS attack, memory for bitmap is allocated per
vfio_dmastructure. Bitmap size is calculated considering smallest supported page size. Bitmap is allocated for allvfio_dmaswhen dirty logging is enabledBitmap is populated for already pinned pages when bitmap is allocated for a
vfio_dmawith the smallest supported page size. Update bitmap from pinning functions when tracking is enabled. When user application queries bitmap, check if requested page size is same as page size used to populated bitmap. If it is equal, copy bitmap, but if not equal, return error.Signed-off-by Kirti Wankhede <[email protected]>Reviewed-by Neo Jia <[email protected]>Reviewed-by Yan Zhao <[email protected]>Fixed error reported by build bot by changing pgsize type from
uint64_ttosize_t.
Quoted 8 lines
Reported-by kbuild test robot <[email protected]>---
Fixed errors and sparse warnings reported by kbuild test robot
Reported-by kbuild test robot <[email protected]>ld:
drivers/vfio/vfio_iommu_type1.o: in function `vfio_dma_populate_bitmap':Quoted 1 line
Quoted 1 line
vfio_iommu_type1.c:(.text+0x666): undefined reference to `__udivdi3'
Hi Kirti,
This is already in linux-next, could you please send just the incremental fix with a Fixes: tag? Thanks,
Alex
Quoted 410 lines
drivers/vfio/vfio_iommu_type1.c | 315 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 309 insertions(+), 6 deletions(-)drivers/vfio/vfio_iommu_type1.c +309
-6@@ -72,6 +72,7 @@ struct vfio_iommu {uint64_t pgsize_bitmap;bool v2;bool nesting; +bool dirty_page_tracking; };struct vfio_domain {@@ -92,6 +93,7 @@ struct vfio_dma {bool lock_cap;/* capable(CAP_IPC_LOCK) */ struct task_struct *task;struct rb_root pfn_list;/* Ex-user pinned pfn list */ +unsigned long *bitmap; };struct vfio_group {@@ -126,6 +128,19 @@ struct vfio_regions {#define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER (iommu) \ (!list_empty(&iommu->domain_list)) +#define DIRTY_BITMAP_BYTES (n) (ALIGN(n, BITS_PER_TYPE(u64)) / BITS_PER_BYTE) + +/* +* Input argument of number of bits to bitmap_set() is unsigned integer, which +* further casts to signed integer for unaligned multi-bit operation, +* __bitmap_set(). +* Then maximum bitmap size supported is 2^31 bits divided by 2^3 bits/byte, +* that is 2^28 (256 MB) which maps to 2^31 * 2^12 = 2^43 (8TB) on 4K page +* system. +*/ +#define DIRTY_BITMAP_PAGES_MAX ((u64)INT_MAX) +#define DIRTY_BITMAP_SIZE_MAX DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX) +static int put_pfn (unsigned long pfn,int prot);/* @@ -176,6 +191,81 @@ static void vfio_unlink_dma(struct vfio_iommu *iommu, struct vfio_dma *old)rb_erase (&old->node, &iommu->dma_list); } + +static int vfio_dma_bitmap_alloc (struct vfio_dma *dma,size_t pgsize) +{ +uint64_t npages = dma->size / pgsize; + +if (npages >DIRTY_BITMAP_PAGES_MAX ) +return -EINVAL ; + +/* +* Allocate extra 64 bits that are used to calculate shift required for +* bitmap_shift_left() to manipulate and club unaligned number of pages +* in adjacent vfio_dma ranges. +*/ + dma->bitmap =kvzalloc (DIRTY_BITMAP_BYTES (npages) +sizeof (u64), +GFP_KERNEL ); +if (!dma->bitmap) +return -ENOMEM ; + +return 0 ; +} + +static void vfio_dma_bitmap_free (struct vfio_dma *dma) +{ +kfree (dma->bitmap); + dma->bitmap =NULL ; +} + +static void vfio_dma_populate_bitmap (struct vfio_dma *dma,size_t pgsize) +{ +struct rb_node *p; +unsigned long pgshift =__ffs (pgsize); + +for (p =rb_first (&dma->pfn_list); p; p =rb_next (p)) { + struct vfio_pfn *vpfn = rb_entry(p, struct vfio_pfn, node); + +bitmap_set (dma->bitmap, (vpfn->iova - dma->iova) >> pgshift,1 ); + } +} + +static int vfio_dma_bitmap_alloc_all (struct vfio_iommu *iommu,size_t pgsize) +{ +struct rb_node *n; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); +int ret; + + ret =vfio_dma_bitmap_alloc (dma, pgsize); +if (ret) { +struct rb_node *p; + +for (p =rb_prev (n); p; p =rb_prev (p)) { +struct vfio_dma *dma =rb_entry (n, + struct vfio_dma, node); + +vfio_dma_bitmap_free (dma); + } +return ret; + } +vfio_dma_populate_bitmap (dma, pgsize); + } +return 0 ; +} + +static void vfio_dma_bitmap_free_all (struct vfio_iommu *iommu) +{ +struct rb_node *n; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + +vfio_dma_bitmap_free (dma); + } +} +/* * Helper Functions for host iova-pfn list */ @@ -598,6 +688,17 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,vfio_unpin_page_external (dma, iova, do_accounting); goto pin_unwind; } + +if (iommu->dirty_page_tracking) { +unsigned long pgshift =__ffs (iommu->pgsize_bitmap); + +/* +* Bitmap populated with the smallest supported page +* size +*/ +bitmap_set (dma->bitmap, + (iova - dma->iova) >> pgshift,1 ); + } } ret = i;@@ -832,6 +933,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)vfio_unmap_unpin (iommu, dma, true);vfio_unlink_dma (iommu, dma);put_task_struct (dma->task); +vfio_dma_bitmap_free (dma);kfree (dma); iommu->dma_avail++; }@@ -859,6 +961,94 @@ 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) +{ +unsigned long pgshift =__ffs (pgsize); +unsigned long nbits = dma->size >> pgshift; +unsigned long bit_offset = (dma->iova - base_iova) >> pgshift; +unsigned long copy_offset = bit_offset /BITS_PER_LONG ; +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) +bitmap_set (dma->bitmap,0 , nbits); + +if (shift) { +bitmap_shift_left (dma->bitmap, dma->bitmap, shift, + nbits + shift); + +if (copy_from_user (&leftover, + (void __user *)(bitmap + copy_offset), +sizeof (leftover))) +return -EFAULT ; + +bitmap_or (dma->bitmap, dma->bitmap, &leftover, shift); + } + +if (copy_to_user ((void __user *)(bitmap + copy_offset), dma->bitmap, +DIRTY_BITMAP_BYTES (nbits + shift))) +return -EFAULT ; + +return 0 ; +} + +static int vfio_iova_dirty_bitmap (u64 __user *bitmap,struct vfio_iommu *iommu, +dma_addr_t iova,size_t size,size_t pgsize) +{ +struct vfio_dma *dma; +struct rb_node *n; +unsigned long pgshift =__ffs (pgsize); +int ret; + +/* +* GET_BITMAP request must fully cover vfio_dma mappings. Multiple +* vfio_dma mappings may be clubbed by specifying large ranges, but +* there must not be any previous mappings bisected by the range. +* An error will be returned if these conditions are not met. +*/ + dma =vfio_find_dma (iommu, iova,1 ); +if (dma && dma->iova != iova) +return -EINVAL ; + + dma =vfio_find_dma (iommu, iova + size -1 ,0 ); +if (dma && dma->iova + dma->size != iova + size) +return -EINVAL ; + +for (n =rb_first (&iommu->dma_list); n; n =rb_next (n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + +if (dma->iova < iova) +continue ; + +if (dma->iova > iova + size -1 ) +break ; + + ret =update_user_bitmap (bitmap, dma, iova, pgsize); +if (ret) +return ret; + +/* +* Re-populate bitmap to include all pinned pages which are +* considered as dirty but exclude pages which are unpinned and +* pages which are marked dirty by vfio_dma_rw() +*/ +bitmap_clear (dma->bitmap,0 , dma->size >> pgshift); +vfio_dma_populate_bitmap (dma, pgsize); + } +return 0 ; +} + +static int verify_bitmap_size (uint64_t npages,uint64_t bitmap_size) +{ +if (!npages || !bitmap_size || (bitmap_size >DIRTY_BITMAP_SIZE_MAX ) || + (bitmap_size <DIRTY_BITMAP_BYTES (npages))) +return -EINVAL ; + +return 0 ; +} +static int vfio_dma_do_unmap (struct vfio_iommu *iommu,struct vfio_iommu_type1_dma_unmap *unmap) {@@ -1076,7 +1266,7 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,unsigned long vaddr = map->vaddr;size_t size = map->size;int ret =0 , prot =0 ; -uint64_t mask; +size_t pgsize;struct vfio_dma *dma;/* Verify that none of our __u64 fields overflow */ @@ -1091,11 +1281,11 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,mutex_lock (&iommu->lock); - mask = ((uint64_t )1 <<__ffs (iommu->pgsize_bitmap)) -1 ; + pgsize = (size_t )1 <<__ffs (iommu->pgsize_bitmap); -WARN_ON (mask &PAGE_MASK ); +WARN_ON ((pgsize -1 ) &PAGE_MASK ); -if (!prot || !size || (size | iova | vaddr) & mask) { +if (!prot || !size || (size | iova | vaddr) & (pgsize -1 )) { ret = -EINVAL ; goto out_unlock; }@@ -1172,6 +1362,12 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,else ret =vfio_pin_map_dma (iommu, dma, size); +if (!ret && iommu->dirty_page_tracking) { + ret =vfio_dma_bitmap_alloc (dma, pgsize); +if (ret) +vfio_remove_dma (iommu, dma); + } + out_unlock:mutex_unlock (&iommu->lock);return ret;@@ -2318,6 +2514,104 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,return copy_to_user ((void __user *)arg, &unmap, minsz) ? -EFAULT :0 ; + }else if (cmd ==VFIO_IOMMU_DIRTY_PAGES ) { +struct vfio_iommu_type1_dirty_bitmap dirty; +uint32_t mask =VFIO_IOMMU_DIRTY_PAGES_FLAG_START | +VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP | +VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP ; +int ret =0 ; + +if (!iommu->v2) +return -EACCES ; + + minsz = offsetofend(struct vfio_iommu_type1_dirty_bitmap, + flags); + +if (copy_from_user (&dirty, (void __user *)arg, minsz)) +return -EFAULT ; + +if (dirty.argsz < minsz || dirty.flags & ~mask) +return -EINVAL ; + +/* only one flag should be set at a time */ +if (__ffs (dirty.flags) !=__fls (dirty.flags)) +return -EINVAL ; + +if (dirty.flags &VFIO_IOMMU_DIRTY_PAGES_FLAG_START ) { +size_t pgsize; + +mutex_lock (&iommu->lock); + pgsize =1 <<__ffs (iommu->pgsize_bitmap); +if (!iommu->dirty_page_tracking) { + ret =vfio_dma_bitmap_alloc_all (iommu, pgsize); +if (!ret) + iommu->dirty_page_tracking = true; + } +mutex_unlock (&iommu->lock); +return ret; + }else if (dirty.flags &VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP ) { +mutex_lock (&iommu->lock); +if (iommu->dirty_page_tracking) { + iommu->dirty_page_tracking = false; +vfio_dma_bitmap_free_all (iommu); + } +mutex_unlock (&iommu->lock); +return 0 ; + }else if (dirty.flags & +VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP ) { +struct vfio_iommu_type1_dirty_bitmap_get range; +unsigned long pgshift; +size_t data_size = dirty.argsz - minsz; +size_t iommu_pgsize; + +if (!data_size || data_size <sizeof (range)) +return -EINVAL ; + +if (copy_from_user (&range, (void __user *)(arg + minsz), +sizeof (range))) +return -EFAULT ; + +if (range.iova + range.size < range.iova) +return -EINVAL ; +if (!access_ok ((void __user *)range.bitmap.data, + range.bitmap.size)) +return -EINVAL ; + + pgshift =__ffs (range.bitmap.pgsize); + ret =verify_bitmap_size (range.size >> pgshift, + range.bitmap.size); +if (ret) +return ret; + +mutex_lock (&iommu->lock); + + iommu_pgsize = (size_t )1 <<__ffs (iommu->pgsize_bitmap); + +/* allow only smallest supported pgsize */ +if (range.bitmap.pgsize != iommu_pgsize) { + ret = -EINVAL ; + goto out_unlock; + } +if (range.iova & (iommu_pgsize -1 )) { + ret = -EINVAL ; + goto out_unlock; + } +if (!range.size || range.size & (iommu_pgsize -1 )) { + ret = -EINVAL ; + goto out_unlock; + } + +if (iommu->dirty_page_tracking) + ret =vfio_iova_dirty_bitmap (range.bitmap.data, + iommu, range.iova, range.size, + range.bitmap.pgsize); +else + ret = -EINVAL ; +out_unlock: +mutex_unlock (&iommu->lock); + +return ret; + } }return -ENOTTY ;@@ -2385,10 +2679,19 @@ static int vfio_iommu_type1_dma_rw_chunk(struct vfio_iommu *iommu, vaddr = dma->vaddr + offset; -if (write) +if (write) { *copied =copy_to_user ((void __user *)vaddr, data, count) ?0 : count; -else +if (*copied && iommu->dirty_page_tracking) { +unsigned long pgshift =__ffs (iommu->pgsize_bitmap); +/* +* Bitmap populated with the smallest supported page +* size +*/ +bitmap_set (dma->bitmap, offset >> pgshift, + *copied >> pgshift); + } + }else *copied =copy_from_user (data, (void __user *)vaddr, count) ?0 : count;if (kthread)
PATCH v24 6/8 vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap
In reply to Kirti WankhedeDMA 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.
--- drivers/vfio/vfio_iommu_type1.c | 61 +++++++++++++++++++++++++++++++++-------- include/uapi/linux/vfio.h | 11 ++++++++ 2 files changed, 61 insertions(+), 11 deletions(-)
drivers/vfio/vfio_iommu_type1.c +50 -11
@@ -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 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,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;
include/uapi/linux/vfio.h +11 -0
@@ -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)
Signature · 1 line
2.7.0
PATCH v24 7/8 vfio iommu: Add migration capability to report supported features
In reply to Kirti WankhedeAdded 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.
--- drivers/vfio/vfio_iommu_type1.c | 23 ++++++++++++++++++++++- include/uapi/linux/vfio.h | 23 +++++++++++++++++++++++ 2 files changed, 45 insertions(+), 1 deletion(-)
drivers/vfio/vfio_iommu_type1.c +22 -1
@@ -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;
include/uapi/linux/vfio.h +23 -0
@@ -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)/**
Signature · 1 line
2.7.0
PATCH v24 8/8 vfio: Selective dirty page tracking if IOMMU backed device pins pages
In reply to Kirti WankhedeAdded 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.
--- drivers/vfio/vfio.c | 13 +++-- drivers/vfio/vfio_iommu_type1.c | 103 +++++++++++++++++++++++++++++++++++++--- include/linux/vfio.h | 4 +- 3 files changed, 109 insertions(+), 11 deletions(-)
drivers/vfio/vfio.c +10 -3
@@ -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 ;
drivers/vfio/vfio_iommu_type1.c +96 -7
205 lines not on this page · raw message
include/linux/vfio.h +3 -1
@@ -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,
Signature · 1 line
2.7.0
Alex Williamson
AppliedQuoted 36 lines · On Fri, 29 May 2020 02:00:46 +0530 Kirti Wankhede <[email protected]> wrote:
Hi,
This patch set adds:
* IOCTLVFIO_IOMMU_DIRTY_PAGESto get dirty pages bitmap with respect to IOMMU container rather than per device. All pages pinned by vendor driver throughvfio_pin_pagesexternal API has to be marked as dirty during migration. When IOMMU capable device is present in the container and all pages are pinned and mapped, then all pages are marked dirty.
When there are CPU writes, CPU dirty page tracking can identify dirtied pages, but any page pinned by vendor driver can also be written by device. As of now there is no device which has hardware support for dirty page tracking. So all pages which are pinned should be considered as dirty.
This ioctl is also used to start/stop dirty pages tracking for pinned and unpinned pages while migration is active.* Updated IOCTL
VFIO_IOMMU_UNMAP_DMAto get dirty pages bitmap before unmapping IO virtual address range.
With vIOMMU, during pre-copy phase of migration, while CPUs are still running, IO virtual address unmap can happen while device still keeping reference of guest pfns. Those pages should be reported as dirty before unmap, so that VFIO user space application can copy content of those pages from source to destination.* Patch 8 detect if IOMMU capable device driver is smart to report pages to be marked dirty by pinning pages using
vfio_pin_pages()API.Yet TODO:
Since there is no device which has hardware support for system memmory dirty bitmap tracking, right now there is no other API from vendor driver to VFIO IOMMU module to report dirty pages. In future, when such hardware support will be implemented, an API will be required such that vendor driver could report dirty pages to VFIO module during migration phases.
Quoted 3 lines
v23 -> v24
- Fixed nit picks by Cornelia
- Fixed warning reported by test robot.
Applied to my next branch for v5.8. Thanks for your persistence and for everyone's participation! Thanks,
Alex
Quoted 169 lines
v22 -> v23
- Fixed issue reported by Yan
https://lore.kernel.org/kvm/[email protected]/
- Fixed nit picks suggested by Corneliav21 -> v22
- Fixed issue raised by Alex :
https://lore.kernel.org/kvm/[email protected]/v20 -> v21
- Added checkin forGET_BITMAPioctl forvfio_dmaboundaries.
- Updated unmap ioctl function - as suggested by Alex.
- Updated comments inDIRTY_TRACKINGioctl definition - as suggested by Cornelia.v19 -> v20
- Fixed ioctl to get dirty bitmap to get bitmap of multiplevfio_dmas
- Fixed unmap ioctl to get dirty bitmap of multiplevfio_dmas.
- Removed flag definition from migration capability.v18 -> v19
- Updated migration capability with supported page sizes bitmap for dirty page tracking and maximum bitmap size supported by kernel module.
- Added patch to calculate and cachepgsize_bitmapwheniommu->domain_listis updated.
- Removed extra buffers added in previous version for bitmap manipulation and optimised the code.v17 -> v18
- Add migration capability to the capability chain forVFIO_IOMMU_GET_INFOioctl
- UpdatedUMAP_DMAioctl to return bitmap of multiplevfio_dmav16 -> v17
- Fixed errors reported by kbuild test robot <[email protected]> on i386v15 -> v16
- Minor edits and nit picks (Auger Eric)
- On copying bitmap to user, re-populated bitmap only for pinned pages, excluding unmapped pages and CPU dirtied pages.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255v14 -> v15
- Minor edits and nit picks.
- In the verification of user allocated bitmap memory, added check of maximum size.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255v13 -> v14
- Added structvfio_bitmapto kabi. updated structurevfio_iommu_type1_dirty_bitmap_getandvfio_iommu_type1_dma_unmap.
- All small changes suggested by Alex.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255v12 -> v13
- Changed bitmap allocation invfio_iommu_type1to pervfio_dma
- ChangedVFIO_IOMMU_DIRTY_PAGESioctl behaviour to be pervfio_dmarange.
- Changedvfio_iommu_type1_dirty_bitmapstructure to have separate data field.v11 -> v12
- Changed bitmap allocation invfio_iommu_type1.
- Remove atomicity ofref_count.
- Updated comments for migration device state structure about error reporting.
- Nit picks from v11 reviewsv10 -> v11
- Fix pin pages API to free vpfn if it is marked as unpinned tracking page.
- Added proposal to detect if IOMMU capable device calls external pin pages API to mark pages dirty.
- Nit picks from v10 reviewsv9 -> v10:
- Updated existingVFIO_IOMMU_UNMAP_DMAioctl to get dirty pages bitmap during unmap while migration is active
- Added flag inVFIO_IOMMU_GET_INFOto indicate driver support dirty page tracking.
- Ifiommu_mapped, mark all pages dirty.
- Added unpinned pages tracking while migration is active.
- Updated comments for migration device state structure with bit combination table and state transition details.v8 -> v9:
- Split patch set in 2 sets, Kernel and QEMU.
- Dirty pages bitmap is queried from IOMMU container rather than from vendor driver for per device. Added 2 ioctls to achieve this.v7 -> v8:
- Updated comments for KABI
- Added BAR address validation check during PCI device's config space load as suggested by Dr. David Alan Gilbert.
- Changedvfio_migration_set_state()to set or clear device state flags.
- Some nit fixes.v6 -> v7:
- Fix build failures.v5 -> v6:
- Fix build failure.v4 -> v5:
- Added decriptive comment about the sequence of access of members of structurevfio_device_migration_infoto be followed based on Alex's suggestion
- Updated get dirty pages sequence.
- As per Cornelia Huck's suggestion, added callbacks to VFIODeviceOps toget_object,save_configandload_config.
- Fixed multiple nit picks.
- Tested live migration with multiple vfio device assigned to a VM.v3 -> v4:
- Added one more bit for_RESUMINGflag to be set explicitly.
-data_offsetfield is read-only for user space application.
-data_sizeis read for every iteration before reading data from migration, that is removed assumption that data will be till end of migration region.
- If vendor driver supports mappable sparsed region, map those region during setup state of save/load, similarly unmap those from cleanup routines.
- Handles race condition that causes data corruption in migration region during save device state by adding mutex and serialiaingsave_bufferandget_dirty_pagesroutines.
- Skip calledget_dirty_pagesroutine for mapped MMIO region of device.
- Added trace events.
- Split into multiple functional patches.v2 -> v3:
- Removed enum of VFIO device states. Defined VFIO device state with 2 bits.
- Re-structuredvfio_device_migration_infoto keep it minimal and defined action on read and write access on its members.v1 -> v2:
- Defined MIGRATION region type and sub-type which should be used with region type capability.
- Re-structuredvfio_device_migration_info. This structure will be placed at 0th offset of migration region.
- Replaced ioctl with read/write for trapped part of migration region.
- Added both type of access support, trapped or mmapped, for data section of the region.
- Moved PCI device functions to pci file.
- Added iteration to get dirty page bitmap until bitmap for all requested pages are copied.Thanks,
KirtiKirti Wankhede (8):
vfio: UAPI for migration interface for device state
vfio iommu: Remove atomicity ofref_countof pinned pages vfio iommu: Cachepgsize_bitmapin structvfio_iommu
vfio iommu: Add ioctl definition for dirty pages tracking vfio iommu: Implementation of ioctl for dirty pages tracking vfio iommu: UpdateUNMAP_DMAioctl to get dirty bitmap before unmap vfio iommu: Add migration capability to report supported features
vfio: Selective dirty page tracking if IOMMU backed device pins pagesdrivers/vfio/vfio.c | 13 +- drivers/vfio/vfio_iommu_type1.c | 572 ++++++++++++++++++++++++++++++++++++---- include/linux/vfio.h | 4 +- include/uapi/linux/vfio.h | 319 ++++++++++++++++++++++ 4 files changed, 849 insertions(+), 59 deletions(-)
Hi Kirti,
Sorry to disturb you since this patch set has been merged, and I cannot receive the qemu-side emails about this patch set.
We are going to support migration for VFIO devices which support dirty pages tracking.
And we also plan to leverage SMMU HTTU feature to do the dirty pages tracking for the devices which don't support dirty pages tracking.
For the above two cases, which side determines to choose IOMMU driver or vendor driver to do dirty bitmap tracking, Qemu or VFIO?
In brief, if both IOMMU and VFIO devices support dirty pages tracking, we can check the capability and prefer to track dirty pages on device vendor driver which is more efficient.
The qusetion is which side to do the check and selection? In my opinion, Qemu/userspace seems more suitable.
Quoted 209 lines · Kirti Wankhede
Hi,
This patch set adds:
* IOCTLVFIO_IOMMU_DIRTY_PAGESto get dirty pages bitmap with respect to IOMMU container rather than per device. All pages pinned by vendor driver throughvfio_pin_pagesexternal API has to be marked as dirty during migration. When IOMMU capable device is present in the container and all pages are pinned and mapped, then all pages are marked dirty.
When there are CPU writes, CPU dirty page tracking can identify dirtied pages, but any page pinned by vendor driver can also be written by device. As of now there is no device which has hardware support for dirty page tracking. So all pages which are pinned should be considered as dirty.
This ioctl is also used to start/stop dirty pages tracking for pinned and unpinned pages while migration is active.* Updated IOCTL
VFIO_IOMMU_UNMAP_DMAto get dirty pages bitmap before unmapping IO virtual address range.
With vIOMMU, during pre-copy phase of migration, while CPUs are still running, IO virtual address unmap can happen while device still keeping reference of guest pfns. Those pages should be reported as dirty before unmap, so that VFIO user space application can copy content of those pages from source to destination.* Patch 8 detect if IOMMU capable device driver is smart to report pages to be marked dirty by pinning pages using
vfio_pin_pages()API.Yet TODO:
Since there is no device which has hardware support for system memmory dirty bitmap tracking, right now there is no other API from vendor driver to VFIO IOMMU module to report dirty pages. In future, when such hardware support will be implemented, an API will be required such that vendor driver could report dirty pages to VFIO module during migration phases.v23 -> v24
- Fixed nit picks by Cornelia
- Fixed warning reported by test robot.v22 -> v23
- Fixed issue reported by Yan
https://lore.kernel.org/kvm/[email protected]/
- Fixed nit picks suggested by Corneliav21 -> v22
- Fixed issue raised by Alex :
https://lore.kernel.org/kvm/[email protected]/v20 -> v21
- Added checkin forGET_BITMAPioctl forvfio_dmaboundaries.
- Updated unmap ioctl function - as suggested by Alex.
- Updated comments inDIRTY_TRACKINGioctl definition - as suggested by Cornelia.v19 -> v20
- Fixed ioctl to get dirty bitmap to get bitmap of multiplevfio_dmas
- Fixed unmap ioctl to get dirty bitmap of multiplevfio_dmas.
- Removed flag definition from migration capability.v18 -> v19
- Updated migration capability with supported page sizes bitmap for dirty page tracking and maximum bitmap size supported by kernel module.
- Added patch to calculate and cachepgsize_bitmapwheniommu->domain_listis updated.
- Removed extra buffers added in previous version for bitmap manipulation and optimised the code.v17 -> v18
- Add migration capability to the capability chain forVFIO_IOMMU_GET_INFOioctl
- UpdatedUMAP_DMAioctl to return bitmap of multiplevfio_dmav16 -> v17
- Fixed errors reported by kbuild test robot <[email protected]> on i386v15 -> v16
- Minor edits and nit picks (Auger Eric)
- On copying bitmap to user, re-populated bitmap only for pinned pages, excluding unmapped pages and CPU dirtied pages.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255v14 -> v15
- Minor edits and nit picks.
- In the verification of user allocated bitmap memory, added check of maximum size.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255v13 -> v14
- Added structvfio_bitmapto kabi. updated structurevfio_iommu_type1_dirty_bitmap_getandvfio_iommu_type1_dma_unmap.
- All small changes suggested by Alex.
- Patches are on tag: next-20200318 and 1-3 patches from Yan's series
https://lkml.org/lkml/2020/3/12/1255v12 -> v13
- Changed bitmap allocation invfio_iommu_type1to pervfio_dma
- ChangedVFIO_IOMMU_DIRTY_PAGESioctl behaviour to be pervfio_dmarange.
- Changedvfio_iommu_type1_dirty_bitmapstructure to have separate data field.v11 -> v12
- Changed bitmap allocation invfio_iommu_type1.
- Remove atomicity ofref_count.
- Updated comments for migration device state structure about error reporting.
- Nit picks from v11 reviewsv10 -> v11
- Fix pin pages API to free vpfn if it is marked as unpinned tracking page.
- Added proposal to detect if IOMMU capable device calls external pin pages API to mark pages dirty.
- Nit picks from v10 reviewsv9 -> v10:
- Updated existingVFIO_IOMMU_UNMAP_DMAioctl to get dirty pages bitmap during unmap while migration is active
- Added flag inVFIO_IOMMU_GET_INFOto indicate driver support dirty page tracking.
- Ifiommu_mapped, mark all pages dirty.
- Added unpinned pages tracking while migration is active.
- Updated comments for migration device state structure with bit combination table and state transition details.v8 -> v9:
- Split patch set in 2 sets, Kernel and QEMU.
- Dirty pages bitmap is queried from IOMMU container rather than from vendor driver for per device. Added 2 ioctls to achieve this.v7 -> v8:
- Updated comments for KABI
- Added BAR address validation check during PCI device's config space load as suggested by Dr. David Alan Gilbert.
- Changedvfio_migration_set_state()to set or clear device state flags.
- Some nit fixes.v6 -> v7:
- Fix build failures.v5 -> v6:
- Fix build failure.v4 -> v5:
- Added decriptive comment about the sequence of access of members of structurevfio_device_migration_infoto be followed based on Alex's suggestion
- Updated get dirty pages sequence.
- As per Cornelia Huck's suggestion, added callbacks to VFIODeviceOps toget_object,save_configandload_config.
- Fixed multiple nit picks.
- Tested live migration with multiple vfio device assigned to a VM.v3 -> v4:
- Added one more bit for_RESUMINGflag to be set explicitly.
-data_offsetfield is read-only for user space application.
-data_sizeis read for every iteration before reading data from migration, that is removed assumption that data will be till end of migration region.
- If vendor driver supports mappable sparsed region, map those region during setup state of save/load, similarly unmap those from cleanup routines.
- Handles race condition that causes data corruption in migration region during save device state by adding mutex and serialiaingsave_bufferandget_dirty_pagesroutines.
- Skip calledget_dirty_pagesroutine for mapped MMIO region of device.
- Added trace events.
- Split into multiple functional patches.v2 -> v3:
- Removed enum of VFIO device states. Defined VFIO device state with 2 bits.
- Re-structuredvfio_device_migration_infoto keep it minimal and defined action on read and write access on its members.v1 -> v2:
- Defined MIGRATION region type and sub-type which should be used with region type capability.
- Re-structuredvfio_device_migration_info. This structure will be placed at 0th offset of migration region.
- Replaced ioctl with read/write for trapped part of migration region.
- Added both type of access support, trapped or mmapped, for data section of the region.
- Moved PCI device functions to pci file.
- Added iteration to get dirty page bitmap until bitmap for all requested pages are copied.Thanks,
KirtiKirti Wankhede (8):
vfio: UAPI for migration interface for device state
vfio iommu: Remove atomicity ofref_countof pinned pages vfio iommu: Cachepgsize_bitmapin structvfio_iommu
vfio iommu: Add ioctl definition for dirty pages tracking vfio iommu: Implementation of ioctl for dirty pages tracking vfio iommu: UpdateUNMAP_DMAioctl to get dirty bitmap before unmap vfio iommu: Add migration capability to report supported features
vfio: Selective dirty page tracking if IOMMU backed device pins pagesdrivers/vfio/vfio.c | 13 +- drivers/vfio/vfio_iommu_type1.c | 572 ++++++++++++++++++++++++++++++++++++---- include/linux/vfio.h | 4 +- include/uapi/linux/vfio.h | 319 ++++++++++++++++++++++ 4 files changed, 849 insertions(+), 59 deletions(-)
Signature · 2 lines
Thanks, Xiang
Quoted 14 lines · On Tue, 21 Jul 2020 10:43:21 +0800 Xiang Zheng <[email protected]> wrote:
Hi Kirti,
Sorry to disturb you since this patch set has been merged, and I cannot receive the qemu-side emails about this patch set.
We are going to support migration for VFIO devices which support dirty pages tracking.
And we also plan to leverage SMMU HTTU feature to do the dirty pages tracking for the devices which don't support dirty pages tracking.
For the above two cases, which side determines to choose IOMMU driver or vendor driver to do dirty bitmap tracking, Qemu or VFIO?
Quoted 6 lines
In brief, if both IOMMU and VFIO devices support dirty pages tracking, we can check the capability and prefer to track dirty pages on device vendor driver which is more efficient.
The qusetion is which side to do the check and selection? In my opinion, Qemu/userspace seems more suitable.
Dirty page tracking is consolidated at the vfio container level. Userspace has no basis for determining or interface for selecting a dirty bitmap provider, so I would disagree that QEMU should play any role here. The container dirty bitmap tries to provide the finest granularity available based on the support of all the devices/groups managed by the container. If there are groups attached to the container that have not participated in page pinning, then we consider all DMA mappings within the container as persistently dirty. Once all of the participants subscribe to page pinning, the dirty scope is reduced to the pinned pages. IOMMU support for dirty page logging would introduce finer granularity yet, which we would probably prefer over page pinning, but interfaces for this have not been devised.
Ideally userspace should be unaware of any of this, the benefit would be seen transparently by having a more sparsely filled dirty bitmap, which more accurately reflects how memory is actually being dirtied. Thanks,
Alex
Hi Alex,
Thank you for your suggestion.
Quoted 24 lines · Alex Williamson
Quoted 14 lines · On Tue, 21 Jul 2020 10:43:21 +0800 Xiang Zheng <[email protected]> wrote:
Hi Kirti,
Sorry to disturb you since this patch set has been merged, and I cannot receive the qemu-side emails about this patch set.
We are going to support migration for VFIO devices which support dirty pages tracking.
And we also plan to leverage SMMU HTTU feature to do the dirty pages tracking for the devices which don't support dirty pages tracking.
For the above two cases, which side determines to choose IOMMU driver or vendor driver to do dirty bitmap tracking, Qemu or VFIO?
Quoted 6 lines
In brief, if both IOMMU and VFIO devices support dirty pages tracking, we can check the capability and prefer to track dirty pages on device vendor driver which is more efficient.
The qusetion is which side to do the check and selection? In my opinion, Qemu/userspace seems more suitable.
Quoted 12 lines
Dirty page tracking is consolidated at the vfio container level. Userspace has no basis for determining or interface for selecting a dirty bitmap provider, so I would disagree that QEMU should play any role here. The container dirty bitmap tries to provide the finest granularity available based on the support of all the devices/groups managed by the container. If there are groups attached to the container that have not participated in page pinning, then we consider all DMA mappings within the container as persistently dirty. Once all of the participants subscribe to page pinning, the dirty scope is reduced to the pinned pages. IOMMU support for dirty page logging would introduce finer granularity yet, which we would probably prefer over page pinning, but interfaces for this have not been devised.
Kevin and his colleagues may add these APIs in the future.
We also plan to support these interfaces on SMMU driver and afterwards we can have a further discussion.
Quoted 4 lines
Ideally userspace should be unaware of any of this, the benefit would be seen transparently by having a more sparsely filled dirty bitmap, which more accurately reflects how memory is actually being dirtied.
Yes, indeed.
Signature · 2 lines
Thanks, Xiang
Quoted 46 lines
From: Xiang Zheng
Sent: Wednesday, July 22, 2020 10:56 AMHi Alex,
Thank you for your suggestion.
Quoted 8 lines · Alex Williamson
Quoted 5 lines · On Tue, 21 Jul 2020 10:43:21 +0800 Xiang Zheng <[email protected]> wrote:
Hi Kirti,
Sorry to disturb you since this patch set has been merged, and I cannot receive the qemu-side emails about this patch set.
Quoted 7 lines
Quoted 7 lines
We are going to support migration for VFIO devices which support dirty pages tracking.
And we also plan to leverage SMMU HTTU feature to do the dirty pages tracking for the devices which don't support dirty pages tracking.
For the above two cases, which side determines to choose IOMMU driver
or
Quoted 9 lines
Quoted 8 lines
vendor driver to do dirty bitmap tracking, Qemu or VFIO?
In brief, if both IOMMU and VFIO devices support dirty pages tracking, we can check the capability and prefer to track dirty pages on device vendor driver which is more efficient.
The qusetion is which side to do the check and selection? In my opinion, Qemu/userspace seems more suitable.
Quoted 12 lines
Dirty page tracking is consolidated at the vfio container level. Userspace has no basis for determining or interface for selecting a dirty bitmap provider, so I would disagree that QEMU should play any role here. The container dirty bitmap tries to provide the finest granularity available based on the support of all the devices/groups managed by the container. If there are groups attached to the container that have not participated in page pinning, then we consider all DMA mappings within the container as persistently dirty. Once all of the participants subscribe to page pinning, the dirty scope is reduced to the pinned pages. IOMMU support for dirty page logging would introduce finer granularity yet, which we would probably prefer over page pinning, but interfaces for this have not been devised.
Quoted 3 lines
Kevin and his colleagues may add these APIs in the future.
We also plan to support these interfaces on SMMU driver and afterwards we can have a further discussion.
Yes, we are working on that part. Generally speaking I agree with Alex that the kernel should decide dirty bitmap provider and IOMMU dirty logging is likely preferred over page pinning. Page pinning either provides only coarse-grained dirty info (e.g. 100's MB pinned pages observed in vGPU case) or when reaching finer granularity it may affect fast-path performance (e.g. driver may have to intercept fast-path operations to track dirtied pages closely). IOMMU provides an architectural and lighter approach for tracking dirty pages.
Thanks
Kevin
Quoted 11 lines
Quoted 5 lines
Ideally userspace should be unaware of any of this, the benefit would be seen transparently by having a more sparsely filled dirty bitmap, which more accurately reflects how memory is actually being dirtied.
Yes, indeed.
--
Thanks,
Xiang
Quoted 6 lines · Kirti Wankhede
* IOCTL
VFIO_IOMMU_DIRTY_PAGESto get dirty pages bitmap with respect to IOMMU container rather than per device. All pages pinned by vendor driver throughvfio_pin_pagesexternal API has to be marked as dirty during migration. When IOMMU capable device is present in the container and all pages are pinned and mapped, then all pages are marked dirty.
From what I can tell only the iommu participates in dirty page tracking. This places the responsibility for dirty page tracking on IOMMUs. My understanding is that support for dirty page tracking is currently not available in IOMMUs.
Can a PCI device implement its own DMA dirty log and let an mdev driver implement the dirty page tracking using this mechanism? That way we don't need to treat all pinned pages as dirty all the time.
Stefan
Quoted 8 lines · On Tue, 29 Sep 2020 09:27:02 +0100 Stefan Hajnoczi <[email protected]> wrote:
Quoted 6 lines · Kirti Wankhede
* IOCTL
VFIO_IOMMU_DIRTY_PAGESto get dirty pages bitmap with respect to IOMMU container rather than per device. All pages pinned by vendor driver throughvfio_pin_pagesexternal API has to be marked as dirty during migration. When IOMMU capable device is present in the container and all pages are pinned and mapped, then all pages are marked dirty.
Quoted 8 lines
From what I can tell only the iommu participates in dirty page tracking. This places the responsibility for dirty page tracking on IOMMUs. My understanding is that support for dirty page tracking is currently not available in IOMMUs.
Can a PCI device implement its own DMA dirty log and let an mdev driver implement the dirty page tracking using this mechanism? That way we don't need to treat all pinned pages as dirty all the time.
Look at the last patch in this series, there we define a mechanism whereby the act of a vendor driver pinning pages both marks those pages dirty and indicates a mode in the vfio type1 container where the scope of dirty pages is limited to those pages pinned by the driver. The vfio_dma_rw() interface does the same. We could clearly implement a more lightweight interface for this as well, one without pinning or memory access, but there are no proposed users for such an interface currently. Thanks,
Alex