Re: [PATCH v14 09/22] vfio iommu type1: Add task structure to vfio_dma

[Alexey Kardashevskiy]

On 17/11/16 07:46, Kirti Wankhede wrote:
> Add task structure to vfio_dma structure. Task structure is used for:
> - During DMA_UNMAP, same task who mapped it or other task who shares same
> address space is allowed to unmap, otherwise unmap fails.
> QEMU maps few iova ranges initially, then fork threads and from the child
> thread calls DMA_UNMAP on previously mapped iova. Since child shares same
> address space, DMA_UNMAP is successful.
> - Avoid accessing struct mm while process is exiting by acquiring
> reference of task's mm during page accounting.
> - It is also used to get task mlock capability and rlimit for mlock.
> 
> Signed-off-by: Kirti Wankhede <kwankhede@xxxxxxxxxx>
> Signed-off-by: Neo Jia <cjia@xxxxxxxxxx>
> Reviewed-by: Dong Jia Shi <bjsdjshi@xxxxxxxxxxxxxxxxxx>


I keep whinging that @mm should be referenced, not @current but you keep
referencing @current even if you only need @mm and you are not telling why
- and I am wondering what I am missing here? Something else will be used
from @task later, besides just @mm?


> 
> Change-Id: I7600f1bea6b384fd589fa72421ccf031bcfd9ac5
> ---
>  drivers/vfio/vfio_iommu_type1.c | 137 +++++++++++++++++++++++++---------------
>  1 file changed, 86 insertions(+), 51 deletions(-)
> 
> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
> index ffe2026f1341..a0a7484cec64 100644
> --- a/drivers/vfio/vfio_iommu_type1.c
> +++ b/drivers/vfio/vfio_iommu_type1.c
> @@ -36,6 +36,7 @@
>  #include <linux/uaccess.h>
>  #include <linux/vfio.h>
>  #include <linux/workqueue.h>
> +#include <linux/pid_namespace.h>
>  
>  #define DRIVER_VERSION  "0.2"
>  #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@xxxxxxxxxx>"
> @@ -75,6 +76,7 @@ struct vfio_dma {
>  	unsigned long		vaddr;		/* Process virtual addr */
>  	size_t			size;		/* Map size (bytes) */
>  	int			prot;		/* IOMMU_READ/WRITE */
> +	struct task_struct	*task;
>  };
>  
>  struct vfio_group {
> @@ -277,41 +279,47 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
>   * the iommu can only map chunks of consecutive pfns anyway, so get the
>   * first page and all consecutive pages with the same locking.
>   */
> -static long vfio_pin_pages_remote(unsigned long vaddr, long npage,
> -				  int prot, unsigned long *pfn_base)
> +static long vfio_pin_pages_remote(struct vfio_dma *dma, unsigned long vaddr,
> +				  long npage, int prot, unsigned long *pfn_base)
>  {
> -	unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
> -	bool lock_cap = capable(CAP_IPC_LOCK);
> +	unsigned long limit;
> +	bool lock_cap = ns_capable(task_active_pid_ns(dma->task)->user_ns,
> +				   CAP_IPC_LOCK);
> +	struct mm_struct *mm;
>  	long ret, i;
>  	bool rsvd;
>  
> -	if (!current->mm)
> +	mm = get_task_mm(dma->task);
> +	if (!mm)
>  		return -ENODEV;
>  
> -	ret = vaddr_get_pfn(current->mm, vaddr, prot, pfn_base);
> +	ret = vaddr_get_pfn(mm, vaddr, prot, pfn_base);
>  	if (ret)
> -		return ret;
> +		goto pin_pg_remote_exit;
>  
>  	rsvd = is_invalid_reserved_pfn(*pfn_base);
> +	limit = task_rlimit(dma->task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
>  
> -	if (!rsvd && !lock_cap && current->mm->locked_vm + 1 > limit) {
> +	if (!rsvd && !lock_cap && mm->locked_vm + 1 > limit) {
>  		put_pfn(*pfn_base, prot);
>  		pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
>  			limit << PAGE_SHIFT);
> -		return -ENOMEM;
> +		ret = -ENOMEM;
> +		goto pin_pg_remote_exit;
>  	}
>  
>  	if (unlikely(disable_hugepages)) {
>  		if (!rsvd)
> -			vfio_lock_acct(current, 1);
> -		return 1;
> +			vfio_lock_acct(dma->task, 1);
> +		ret = 1;
> +		goto pin_pg_remote_exit;
>  	}
>  
>  	/* Lock all the consecutive pages from pfn_base */
>  	for (i = 1, vaddr += PAGE_SIZE; i < npage; i++, vaddr += PAGE_SIZE) {
>  		unsigned long pfn = 0;
>  
> -		ret = vaddr_get_pfn(current->mm, vaddr, prot, &pfn);
> +		ret = vaddr_get_pfn(mm, vaddr, prot, &pfn);
>  		if (ret)
>  			break;
>  
> @@ -321,8 +329,7 @@ static long vfio_pin_pages_remote(unsigned long vaddr, long npage,
>  			break;
>  		}
>  
> -		if (!rsvd && !lock_cap &&
> -		    current->mm->locked_vm + i + 1 > limit) {
> +		if (!rsvd && !lock_cap && mm->locked_vm + i + 1 > limit) {
>  			put_pfn(pfn, prot);
>  			pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
>  				__func__, limit << PAGE_SHIFT);
> @@ -331,13 +338,16 @@ static long vfio_pin_pages_remote(unsigned long vaddr, long npage,
>  	}
>  
>  	if (!rsvd)
> -		vfio_lock_acct(current, i);
> +		vfio_lock_acct(dma->task, i);
> +	ret = i;
>  
> -	return i;
> +pin_pg_remote_exit:
> +	mmput(mm);
> +	return ret;
>  }
>  
> -static long vfio_unpin_pages_remote(unsigned long pfn, long npage,
> -				    int prot, bool do_accounting)
> +static long vfio_unpin_pages_remote(struct vfio_dma *dma, unsigned long pfn,
> +				    long npage, int prot, bool do_accounting)
>  {
>  	unsigned long unlocked = 0;
>  	long i;
> @@ -346,7 +356,7 @@ static long vfio_unpin_pages_remote(unsigned long pfn, long npage,
>  		unlocked += put_pfn(pfn++, prot);
>  
>  	if (do_accounting)
> -		vfio_lock_acct(current, -unlocked);
> +		vfio_lock_acct(dma->task, -unlocked);
>  
>  	return unlocked;
>  }
> @@ -400,7 +410,7 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma)
>  		if (WARN_ON(!unmapped))
>  			break;
>  
> -		unlocked += vfio_unpin_pages_remote(phys >> PAGE_SHIFT,
> +		unlocked += vfio_unpin_pages_remote(dma, phys >> PAGE_SHIFT,
>  						    unmapped >> PAGE_SHIFT,
>  						    dma->prot, false);
>  		iova += unmapped;
> @@ -408,13 +418,14 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma)
>  		cond_resched();
>  	}
>  
> -	vfio_lock_acct(current, -unlocked);
> +	vfio_lock_acct(dma->task, -unlocked);
>  }
>  
>  static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
>  {
>  	vfio_unmap_unpin(iommu, dma);
>  	vfio_unlink_dma(iommu, dma);
> +	put_task_struct(dma->task);
>  	kfree(dma);
>  }
>  
> @@ -510,6 +521,12 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
>  	while ((dma = vfio_find_dma(iommu, unmap->iova, unmap->size))) {
>  		if (!iommu->v2 && unmap->iova > dma->iova)
>  			break;
> +		/*
> +		 * Task with same address space who mapped this iova range is
> +		 * allowed to unmap the iova range.
> +		 */
> +		if (dma->task->mm != current->mm)
> +			break;
>  		unmapped += dma->size;
>  		vfio_remove_dma(iommu, dma);
>  	}
> @@ -576,17 +593,55 @@ unwind:
>  	return ret;
>  }
>  
> +static int vfio_pin_map_dma(struct vfio_iommu *iommu, struct vfio_dma *dma,
> +			    size_t map_size)
> +{
> +	dma_addr_t iova = dma->iova;
> +	unsigned long vaddr = dma->vaddr;
> +	size_t size = map_size;
> +	long npage;
> +	unsigned long pfn;
> +	int ret = 0;
> +
> +	while (size) {
> +		/* Pin a contiguous chunk of memory */
> +		npage = vfio_pin_pages_remote(dma, vaddr + dma->size,
> +					      size >> PAGE_SHIFT, dma->prot,
> +					      &pfn);
> +		if (npage <= 0) {
> +			WARN_ON(!npage);
> +			ret = (int)npage;
> +			break;
> +		}
> +
> +		/* Map it! */
> +		ret = vfio_iommu_map(iommu, iova + dma->size, pfn, npage,
> +				     dma->prot);
> +		if (ret) {
> +			vfio_unpin_pages_remote(dma, pfn, npage,
> +						 dma->prot, true);
> +			break;
> +		}
> +
> +		size -= npage << PAGE_SHIFT;
> +		dma->size += npage << PAGE_SHIFT;
> +	}
> +
> +	if (ret)
> +		vfio_remove_dma(iommu, dma);
> +
> +	return ret;
> +}
> +
>  static int vfio_dma_do_map(struct vfio_iommu *iommu,
>  			   struct vfio_iommu_type1_dma_map *map)
>  {
>  	dma_addr_t iova = map->iova;
>  	unsigned long vaddr = map->vaddr;
>  	size_t size = map->size;
> -	long npage;
>  	int ret = 0, prot = 0;
>  	uint64_t mask;
>  	struct vfio_dma *dma;
> -	unsigned long pfn;
>  
>  	/* Verify that none of our __u64 fields overflow */
>  	if (map->size != size || map->vaddr != vaddr || map->iova != iova)
> @@ -612,47 +667,27 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
>  	mutex_lock(&iommu->lock);
>  
>  	if (vfio_find_dma(iommu, iova, size)) {
> -		mutex_unlock(&iommu->lock);
> -		return -EEXIST;
> +		ret = -EEXIST;
> +		goto out_unlock;
>  	}
>  
>  	dma = kzalloc(sizeof(*dma), GFP_KERNEL);
>  	if (!dma) {
> -		mutex_unlock(&iommu->lock);
> -		return -ENOMEM;
> +		ret = -ENOMEM;
> +		goto out_unlock;
>  	}
>  
>  	dma->iova = iova;
>  	dma->vaddr = vaddr;
>  	dma->prot = prot;
> +	get_task_struct(current);
> +	dma->task = current;
>  
>  	/* Insert zero-sized and grow as we map chunks of it */
>  	vfio_link_dma(iommu, dma);
>  
> -	while (size) {
> -		/* Pin a contiguous chunk of memory */
> -		npage = vfio_pin_pages_remote(vaddr + dma->size,
> -					      size >> PAGE_SHIFT, prot, &pfn);
> -		if (npage <= 0) {
> -			WARN_ON(!npage);
> -			ret = (int)npage;
> -			break;
> -		}
> -
> -		/* Map it! */
> -		ret = vfio_iommu_map(iommu, iova + dma->size, pfn, npage, prot);
> -		if (ret) {
> -			vfio_unpin_pages_remote(pfn, npage, prot, true);
> -			break;
> -		}
> -
> -		size -= npage << PAGE_SHIFT;
> -		dma->size += npage << PAGE_SHIFT;
> -	}
> -
> -	if (ret)
> -		vfio_remove_dma(iommu, dma);
> -
> +	ret = vfio_pin_map_dma(iommu, dma, size);
> +out_unlock:
>  	mutex_unlock(&iommu->lock);
>  	return ret;
>  }
> 


-- 
Alexey