iommu/amd: Remove unnecessary locking from AMD iommu driver

With or without locking it doesn't make sense for two writers to be
writing to the same IOVA range at the same time. Even with locking we
still have a race condition, whoever gets the lock first, so we still
can't be sure what the result will be. With locking the result will be
more sane, it will be correct for the last writer, but still useless
because we can't be sure which writer will get the lock last. It's a
fundamentally broken design to have two writers writing to the same
IOVA range at the same time.

So we can remove the locking and work on the assumption that no two
writers will be writing to the same IOVA range at the same time.

The only exception is when we have to allocate a middle page in the page
tables, the middle page can cover more than just the IOVA range a writer
has been allocated. However this isn't an issue in the AMD driver
because it can atomically allocate middle pages using "cmpxchg64()".

Signed-off-by: Tom Murphy <murphyt7@tcd.ie>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/amd_iommu.c

@@ -2934,7 +2934,6 @@ static void protection_domain_free(struct protection_domain *domain)
 static int protection_domain_init(struct protection_domain *domain)
 {
 	spin_lock_init(&domain->lock);
-	mutex_init(&domain->api_lock);
 	domain->id = domain_id_alloc();
 	if (!domain->id)
 		return -ENOMEM;
@@ -3121,9 +3120,7 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= IOMMU_PROT_IW;
 
-	mutex_lock(&domain->api_lock);
 	ret = iommu_map_page(domain, iova, paddr, page_size, prot, GFP_KERNEL);
-	mutex_unlock(&domain->api_lock);
 
 	domain_flush_np_cache(domain, iova, page_size);
 
@@ -3135,16 +3132,11 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 			      struct iommu_iotlb_gather *gather)
 {
 	struct protection_domain *domain = to_pdomain(dom);
-	size_t unmap_size;
 
 	if (domain->mode == PAGE_MODE_NONE)
 		return 0;
 
-	mutex_lock(&domain->api_lock);
-	unmap_size = iommu_unmap_page(domain, iova, page_size);
-	mutex_unlock(&domain->api_lock);
-
-	return unmap_size;
+	return iommu_unmap_page(domain, iova, page_size);
 }
 
 static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,

drivers/iommu/amd_iommu_types.h

@@ -468,7 +468,6 @@ struct protection_domain {
 	struct iommu_domain domain; /* generic domain handle used by
 				       iommu core code */
 	spinlock_t lock;	/* mostly used to lock the page table*/
-	struct mutex api_lock;	/* protect page tables in the iommu-api path */
 	u16 id;			/* the domain id written to the device table */
 	int mode;		/* paging mode (0-6 levels) */
 	u64 *pt_root;		/* page table root pointer */