Re: [RFC PATCH v2 2/2] iommu/amd: Add support for fast IOTLB flushing

[Suravee Suthikulpanit]

Hi Joerg,

Do you have any feedback regarding this patch for AMD IOMMU? I'm re-sending the patch 1/2
separately per Alex's suggestion.

Thanks,
Suravee

On 12/27/17 4:20 PM, Suravee Suthikulpanit wrote:
> Implement the newly added IOTLB flushing interface for AMD IOMMU.
>
> Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
> ---
>   drivers/iommu/amd_iommu.c       | 73 ++++++++++++++++++++++++++++++++++++++++-
>   drivers/iommu/amd_iommu_init.c  |  7 ++++
>   drivers/iommu/amd_iommu_types.h |  7 ++++
>   3 files changed, 86 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
> index 7d5eb00..42fe365 100644
> --- a/drivers/iommu/amd_iommu.c
> +++ b/drivers/iommu/amd_iommu.c
> @@ -129,6 +129,12 @@ struct dma_ops_domain {
>   static struct iova_domain reserved_iova_ranges;
>   static struct lock_class_key reserved_rbtree_key;
>   
> +struct amd_iommu_flush_entries {
> +	struct list_head list;
> +	unsigned long iova;
> +	size_t size;
> +};
> +
>   /****************************************************************************
>    *
>    * Helper functions
> @@ -3043,7 +3049,6 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
>   	unmap_size = iommu_unmap_page(domain, iova, page_size);
>   	mutex_unlock(&domain->api_lock);
>   
> -	domain_flush_tlb_pde(domain);
>   	domain_flush_complete(domain);
>   
>   	return unmap_size;
> @@ -3163,6 +3168,69 @@ static bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
>   	return dev_data->defer_attach;
>   }
>   
> +static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
> +{
> +	struct protection_domain *dom = to_pdomain(domain);
> +
> +	domain_flush_tlb_pde(dom);
> +}
> +
> +static void amd_iommu_iotlb_range_add(struct iommu_domain *domain,
> +				      unsigned long iova, size_t size)
> +{
> +	struct amd_iommu_flush_entries *entry, *p;
> +	unsigned long flags;
> +	bool found = false;
> +
> +	spin_lock_irqsave(&amd_iommu_flush_list_lock, flags);
> +	list_for_each_entry(p, &amd_iommu_flush_list, list) {
> +		if (iova != p->iova)
> +			continue;
> +
> +		if (size > p->size) {
> +			p->size = size;
> +			pr_debug("%s: update range: iova=%#lx, size = %#lx\n",
> +				 __func__, p->iova, p->size);
> +		}
> +		found = true;
> +		break;
> +	}
> +
> +	if (!found) {
> +		entry = kzalloc(sizeof(struct amd_iommu_flush_entries),
> +				GFP_KERNEL);
> +		if (entry) {
> +			pr_debug("%s: new range: iova=%lx, size=%#lx\n",
> +				 __func__, iova, size);
> +
> +			entry->iova = iova;
> +			entry->size = size;
> +			list_add(&entry->list, &amd_iommu_flush_list);
> +		}
> +	}
> +	spin_unlock_irqrestore(&amd_iommu_flush_list_lock, flags);
> +}
> +
> +static void amd_iommu_iotlb_sync(struct iommu_domain *domain)
> +{
> +	struct protection_domain *pdom = to_pdomain(domain);
> +	struct amd_iommu_flush_entries *entry, *next;
> +	unsigned long flags;
> +
> +	/* Note:
> +	 * Currently, IOMMU driver just flushes the whole IO/TLB for
> +	 * a given domain. So, just remove entries from the list here.
> +	 */
> +	spin_lock_irqsave(&amd_iommu_flush_list_lock, flags);
> +	list_for_each_entry_safe(entry, next, &amd_iommu_flush_list, list) {
> +		list_del(&entry->list);
> +		kfree(entry);
> +	}
> +	spin_unlock_irqrestore(&amd_iommu_flush_list_lock, flags);
> +
> +	domain_flush_tlb_pde(pdom);
> +}
> +
>   const struct iommu_ops amd_iommu_ops = {
>   	.capable = amd_iommu_capable,
>   	.domain_alloc = amd_iommu_domain_alloc,
> @@ -3181,6 +3249,9 @@ static bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
>   	.apply_resv_region = amd_iommu_apply_resv_region,
>   	.is_attach_deferred = amd_iommu_is_attach_deferred,
>   	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
> +	.flush_iotlb_all = amd_iommu_flush_iotlb_all,
> +	.iotlb_range_add = amd_iommu_iotlb_range_add,
> +	.iotlb_sync = amd_iommu_iotlb_sync,
>   };
>   
>   /*****************************************************************************
> diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
> index 6fe2d03..e8f8cee 100644
> --- a/drivers/iommu/amd_iommu_init.c
> +++ b/drivers/iommu/amd_iommu_init.c
> @@ -185,6 +185,12 @@ struct ivmd_header {
>   bool amd_iommu_force_isolation __read_mostly;
>   
>   /*
> + * IOTLB flush list
> + */
> +LIST_HEAD(amd_iommu_flush_list);
> +spinlock_t amd_iommu_flush_list_lock;
> +
> +/*
>    * List of protection domains - used during resume
>    */
>   LIST_HEAD(amd_iommu_pd_list);
> @@ -2490,6 +2496,7 @@ static int __init early_amd_iommu_init(void)
>   	__set_bit(0, amd_iommu_pd_alloc_bitmap);
>   
>   	spin_lock_init(&amd_iommu_pd_lock);
> +	spin_lock_init(&amd_iommu_flush_list_lock);
>   
>   	/*
>   	 * now the data structures are allocated and basically initialized
> diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
> index f6b24c7..c3f4a7e 100644
> --- a/drivers/iommu/amd_iommu_types.h
> +++ b/drivers/iommu/amd_iommu_types.h
> @@ -668,6 +668,13 @@ struct iommu_dev_data {
>   extern struct list_head amd_iommu_pd_list;
>   
>   /*
> + * Declarations for the global flush list to support
> + * iotlb_range_add() and iotlb_sync.
> + */
> +extern spinlock_t amd_iommu_flush_list_lock;
> +extern struct list_head amd_iommu_flush_list;
> +
> +/*
>    * Structure defining one entry in the device table
>    */
>   struct dev_table_entry {