QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Kirti Wankhede <kwankhede@nvidia.com>
To: Alex Williamson <alex.williamson@redhat.com>
Cc: Zhengxiao.zx@Alibaba-inc.com, kevin.tian@intel.com,
	yi.l.liu@intel.com, cjia@nvidia.com, kvm@vger.kernel.org,
	eskultet@redhat.com, ziye.yang@intel.com, qemu-devel@nongnu.org,
	cohuck@redhat.com, shuangtai.tst@alibaba-inc.com,
	dgilbert@redhat.com, zhi.a.wang@intel.com, mlevitsk@redhat.com,
	pasic@linux.ibm.com, aik@ozlabs.ru, eauger@redhat.com,
	felipe@nutanix.com, jonathan.davies@nutanix.com,
	yan.y.zhao@intel.com, changpeng.liu@intel.com, Ken.Xue@amd.com
Subject: Re: [PATCH v16 Kernel 4/7] vfio iommu: Implementation of ioctl for dirty pages tracking.
Date: Wed, 25 Mar 2020 03:18:24 +0530
Message-ID: <983b1069-672d-765e-af55-bad42040fe61@nvidia.com> (raw)
In-Reply-To: <20200324144507.5e11a50d@w520.home>



On 3/25/2020 2:15 AM, Alex Williamson wrote:
> On Tue, 24 Mar 2020 14:37:16 -0600
> Alex Williamson <alex.williamson@redhat.com> wrote:
> 
>> On Wed, 25 Mar 2020 01:02:36 +0530
>> Kirti Wankhede <kwankhede@nvidia.com> wrote:
>>
>>> VFIO_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.
>>>
>>> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
>>> Reviewed-by: Neo Jia <cjia@nvidia.com>
>>> ---
>>>   drivers/vfio/vfio_iommu_type1.c | 265 +++++++++++++++++++++++++++++++++++++++-
>>>   1 file changed, 259 insertions(+), 6 deletions(-)
>>>
>>> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
>>> index 70aeab921d0f..27ed069c5053 100644
>>> --- a/drivers/vfio/vfio_iommu_type1.c
>>> +++ b/drivers/vfio/vfio_iommu_type1.c
>>> @@ -71,6 +71,7 @@ struct vfio_iommu {
>>>   	unsigned int		dma_avail;
>>>   	bool			v2;
>>>   	bool			nesting;
>>> +	bool			dirty_page_tracking;
>>>   };
>>>   
>>>   struct vfio_domain {
>>> @@ -91,6 +92,7 @@ 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 {
>>> @@ -125,7 +127,21 @@ 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	(uint64_t)(INT_MAX - 1)
>>> +#define DIRTY_BITMAP_SIZE_MAX	 DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX)
>>> +
>>>   static int put_pfn(unsigned long pfn, int prot);
>>> +static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu);
>>>   
>>>   /*
>>>    * This code handles mapping and unmapping of user data buffers
>>> @@ -175,6 +191,77 @@ 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, uint64_t pgsize)
>>> +{
>>> +	uint64_t npages = dma->size / pgsize;
>>> +
>>> +	if (npages > DIRTY_BITMAP_PAGES_MAX)
>>> +		return -EINVAL;
>>> +
>>> +	dma->bitmap = kvzalloc(DIRTY_BITMAP_BYTES(npages), 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, uint64_t pgsize)
>>> +{
>>> +	struct rb_node *p;
>>> +
>>> +	if (RB_EMPTY_ROOT(&dma->pfn_list))
>>> +		return;
>>> +
>>> +	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, uint64_t pgsize)
>>> +{
>>> +	struct rb_node *n = rb_first(&iommu->dma_list);
>>> +
>>> +	for (; 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 = rb_prev(n);
>>> +
>>> +			for (; 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 = rb_first(&iommu->dma_list);
>>> +
>>> +	for (; 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
>>>    */
>>> @@ -567,6 +654,18 @@ 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(vfio_pgsize_bitmap(iommu));
>>> +
>>> +			/*
>>> +			 * Bitmap populated with the smallest supported page
>>> +			 * size
>>> +			 */
>>> +			bitmap_set(dma->bitmap,
>>> +				   (vpfn->iova - dma->iova) >> pgshift, 1);
>>> +		}
>>>   	}
>>>   
>>>   	ret = i;
>>> @@ -801,6 +900,7 @@ 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++;
>>>   }
>>> @@ -831,6 +931,56 @@ static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
>>>   	return bitmap;
>>>   }
>>>   
>>> +static int vfio_iova_dirty_bitmap(struct vfio_iommu *iommu, dma_addr_t iova,
>>> +				  size_t size, uint64_t pgsize,
>>> +				  u64 __user *bitmap)
>>> +{
>>> +	struct vfio_dma *dma;
>>> +	unsigned long pgshift = __ffs(pgsize);
>>> +	unsigned int npages, bitmap_size;
>>> +
>>> +	dma = vfio_find_dma(iommu, iova, 1);
>>> +
>>> +	if (!dma)
>>> +		return -EINVAL;
>>> +
>>> +	if (dma->iova != iova || dma->size != size)
>>> +		return -EINVAL;
>>> +
>>> +	npages = dma->size >> pgshift;
>>> +	bitmap_size = DIRTY_BITMAP_BYTES(npages);
>>> +
>>> +	/* mark all pages dirty if all pages are pinned and mapped. */
>>> +	if (dma->iommu_mapped)
>>> +		bitmap_set(dma->bitmap, 0, npages);
>>> +
>>> +	if (copy_to_user((void __user *)bitmap, dma->bitmap, bitmap_size))
>>> +		return -EFAULT;
>>> +
>>> +	/*
>>> +	 * 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()
>>> +	 */
>>> +	vfio_dma_populate_bitmap(dma, pgsize);
>>
>> vfio_dma_populate_bitmap() only sets bits, it doesn't clear them.
>> Shouldn't we do a memset() zero before calling this?  Thanks,
> 
> Or a bitmap_clear() would be better given we use bitmap_set() above.
> Thanks,
> 

Oh, I missed clearing bitmap. Resending only this patch again.

Thanks,
Kirti


  reply index

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-24 19:32 [PATCH v16 Kernel 0/7] KABIs to support migration for VFIO devices Kirti Wankhede
2020-03-24 19:32 ` [PATCH v16 Kernel 1/7] vfio: KABI for migration interface for device state Kirti Wankhede
2020-03-26 10:41   ` Cornelia Huck
2020-03-26 21:39     ` Kirti Wankhede
2020-03-24 19:32 ` [PATCH v16 Kernel 2/7] vfio iommu: Remove atomicity of ref_count of pinned pages Kirti Wankhede
2020-03-26 10:49   ` Cornelia Huck
2020-03-26 21:45     ` Kirti Wankhede
2020-03-24 19:32 ` [PATCH v16 Kernel 3/7] vfio iommu: Add ioctl definition for dirty pages tracking Kirti Wankhede
2020-03-24 19:32 ` [PATCH v16 Kernel 4/7] vfio iommu: Implementation of ioctl " Kirti Wankhede
2020-03-24 20:37   ` Alex Williamson
2020-03-24 20:45     ` Alex Williamson
2020-03-24 21:48       ` Kirti Wankhede [this message]
2020-03-24 19:32 ` [PATCH v16 Kernel 5/7] vfio iommu: Update UNMAP_DMA ioctl to get dirty bitmap before unmap Kirti Wankhede
2020-03-25  2:18   ` Yan Zhao
2020-03-26 21:39     ` Kirti Wankhede
2020-03-27  0:04       ` Yan Zhao
2020-03-27  4:42         ` Kirti Wankhede
2020-03-30  2:15           ` Yan Zhao
2020-04-01 18:04             ` Kirti Wankhede
2020-03-24 19:32 ` [PATCH v16 Kernel 6/7] vfio iommu: Adds flag to indicate dirty pages tracking capability support Kirti Wankhede
2020-03-24 19:32 ` [PATCH v16 Kernel 7/7] vfio: Selective dirty page tracking if IOMMU backed device pins pages Kirti Wankhede
2020-03-24 21:18 [PATCH v16 Kernel 4/7] vfio iommu: Implementation of ioctl for dirty pages tracking Kirti Wankhede
2020-03-25  2:11 ` Yan Zhao
2020-03-26 21:39   ` Kirti Wankhede
2020-03-27  0:30     ` Yan Zhao
2020-03-27  5:07       ` Kirti Wankhede
2020-03-30  2:07         ` Yan Zhao
2020-03-30 20:47           ` Alex Williamson
2020-03-30 23:49             ` Yan Zhao
2020-03-27  5:28       ` Kirti Wankhede
2020-03-30  3:24         ` Yan Zhao
2020-03-30 13:49           ` Kirti Wankhede
2020-03-30 23:51             ` Yan Zhao
2020-03-31  0:53               ` Alex Williamson
2020-03-31  0:50                 ` Yan Zhao
2020-03-31  1:12                   ` Alex Williamson
2020-03-31  1:16                     ` Yan Zhao
2020-03-31  2:38                       ` Alex Williamson
2020-03-31  2:40                         ` Zhao, Yan Y
2020-03-27 11:57 ` Dr. David Alan Gilbert
2020-03-27 13:57   ` Alex Williamson
2020-03-27 14:09     ` Dr. David Alan Gilbert

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=983b1069-672d-765e-af55-bad42040fe61@nvidia.com \
    --to=kwankhede@nvidia.com \
    --cc=Ken.Xue@amd.com \
    --cc=Zhengxiao.zx@Alibaba-inc.com \
    --cc=aik@ozlabs.ru \
    --cc=alex.williamson@redhat.com \
    --cc=changpeng.liu@intel.com \
    --cc=cjia@nvidia.com \
    --cc=cohuck@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=eauger@redhat.com \
    --cc=eskultet@redhat.com \
    --cc=felipe@nutanix.com \
    --cc=jonathan.davies@nutanix.com \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=mlevitsk@redhat.com \
    --cc=pasic@linux.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --cc=shuangtai.tst@alibaba-inc.com \
    --cc=yan.y.zhao@intel.com \
    --cc=yi.l.liu@intel.com \
    --cc=zhi.a.wang@intel.com \
    --cc=ziye.yang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git