[PATCH] iommu/amd: flush IOTLB for specific domains only (v3)

[Deucher, Alexander]

> -----Original Message-----
> From: Arindam Nath [mailto:anath.amd at gmail.com] On Behalf Of
> arindam.nath at amd.com
> Sent: Monday, May 22, 2017 3:48 AM
> To: iommu at lists.linux-foundation.org
> Cc: amd-gfx at lists.freedesktop.org; Joerg Roedel; Deucher, Alexander;
> Bridgman, John; drake at endlessm.com; Suthikulpanit, Suravee;
> linux at endlessm.com; Craig Stein; michel at daenzer.net; Kuehling, Felix;
> stable at vger.kernel.org; Nath, Arindam
> Subject: [PATCH] iommu/amd: flush IOTLB for specific domains only (v3)
> 
> From: Arindam Nath <arindam.nath at amd.com>
> 
> Change History
> --------------
> 
> v3:
> - add Fixes and CC tags
> - add link to Bugzilla
> 
> v2: changes suggested by Joerg
> - add flush flag to improve efficiency of flush operation
> 
> v1:
> - The idea behind flush queues is to defer the IOTLB flushing
>   for domains for which the mappings are no longer valid. We
>   add such domains in queue_add(), and when the queue size
>   reaches FLUSH_QUEUE_SIZE, we perform __queue_flush().
> 
>   Since we have already taken lock before __queue_flush()
>   is called, we need to make sure the IOTLB flushing is
>   performed as quickly as possible.
> 
>   In the current implementation, we perform IOTLB flushing
>   for all domains irrespective of which ones were actually
>   added in the flush queue initially. This can be quite
>   expensive especially for domains for which unmapping is
>   not required at this point of time.
> 
>   This patch makes use of domain information in
>   'struct flush_queue_entry' to make sure we only flush
>   IOTLBs for domains who need it, skipping others.
> 
> Bugzilla: https://bugs.freedesktop.org/101029
> Fixes: b1516a14657a ("iommu/amd: Implement flush queue")
> Cc: stable at vger.kernel.org
> Suggested-by: Joerg Roedel <joro at 8bytes.org>
> Signed-off-by: Arindam Nath <arindam.nath at amd.com>

Acked-by: Alex Deucher <alexander.deucher at amd.com>

> ---
>  drivers/iommu/amd_iommu.c       | 27 ++++++++++++++++++++-------
>  drivers/iommu/amd_iommu_types.h |  2 ++
>  2 files changed, 22 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
> index 63cacf5..1edeebec 100644
> --- a/drivers/iommu/amd_iommu.c
> +++ b/drivers/iommu/amd_iommu.c
> @@ -2227,15 +2227,26 @@ static struct iommu_group
> *amd_iommu_device_group(struct device *dev)
> 
>  static void __queue_flush(struct flush_queue *queue)
>  {
> -	struct protection_domain *domain;
> -	unsigned long flags;
>  	int idx;
> 
> -	/* First flush TLB of all known domains */
> -	spin_lock_irqsave(&amd_iommu_pd_lock, flags);
> -	list_for_each_entry(domain, &amd_iommu_pd_list, list)
> -		domain_flush_tlb(domain);
> -	spin_unlock_irqrestore(&amd_iommu_pd_lock, flags);
> +	/* First flush TLB of all domains which were added to flush queue */
> +	for (idx = 0; idx < queue->next; ++idx) {
> +		struct flush_queue_entry *entry;
> +
> +		entry = queue->entries + idx;
> +
> +		/*
> +		 * There might be cases where multiple IOVA entries for the
> +		 * same domain are queued in the flush queue. To avoid
> +		 * flushing the same domain again, we check whether the
> +		 * flag is set or not. This improves the efficiency of
> +		 * flush operation.
> +		 */
> +		if (!entry->dma_dom->domain.already_flushed) {
> +			entry->dma_dom->domain.already_flushed = true;
> +			domain_flush_tlb(&entry->dma_dom->domain);
> +		}
> +	}
> 
>  	/* Wait until flushes have completed */
>  	domain_flush_complete(NULL);
> @@ -2289,6 +2300,8 @@ static void queue_add(struct dma_ops_domain
> *dma_dom,
>  	pages     = __roundup_pow_of_two(pages);
>  	address >>= PAGE_SHIFT;
> 
> +	dma_dom->domain.already_flushed = false;
> +
>  	queue = get_cpu_ptr(&flush_queue);
>  	spin_lock_irqsave(&queue->lock, flags);
> 
> diff --git a/drivers/iommu/amd_iommu_types.h
> b/drivers/iommu/amd_iommu_types.h
> index 4de8f41..4f5519d 100644
> --- a/drivers/iommu/amd_iommu_types.h
> +++ b/drivers/iommu/amd_iommu_types.h
> @@ -454,6 +454,8 @@ struct protection_domain {
>  	bool updated;		/* complete domain flush required */
>  	unsigned dev_cnt;	/* devices assigned to this domain */
>  	unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference
> count */
> +	bool already_flushed;	/* flag to avoid flushing the same domain
> again
> +				   in a single invocation of __queue_flush() */
>  };
> 
>  /*
> --
> 2.7.4