--- v2
+++ v12
@@ -1,121 +1,155 @@
-There moves locked pages accounting to helpers.
-Later they will be reused for Dynamic DMA windows (DDW).
+This is a pretty mechanical patch to make next patches simpler.
 
-While we are here, update the comment explaining why RLIMIT_MEMLOCK
-might be required to be bigger than the guest RAM.
+New tce_iommu_unuse_page() helper does put_page() now but it might skip
+that after the memory registering patch applied.
+
+As we are here, this removes unnecessary checks for a value returned
+by pfn_to_page() as it cannot possibly return NULL.
+
+This moves tce_iommu_disable() later to let tce_iommu_clear() know if
+the container has been enabled because if it has not been, then
+put_page() must not be called on TCEs from the TCE table. This situation
+is not yet possible but it will after KVM acceleration patchset is
+applied.
+
+This changes code to work with physical addresses rather than linear
+mapping addresses for better code readability. Following patches will
+add an xchg() callback for an IOMMU table which will accept/return
+physical addresses (unlike current tce_build()) which will eliminate
+redundant conversions.
 
 Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
+[aw: for the vfio related changes]
+Acked-by: Alex Williamson <alex.williamson@redhat.com>
+Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
+Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
 ---
- drivers/vfio/vfio_iommu_spapr_tce.c | 71 +++++++++++++++++++++++++++----------
- 1 file changed, 53 insertions(+), 18 deletions(-)
+Changes:
+v9:
+* changed helpers to work with physical addresses rather than linear
+(for simplicity - later ::xchg() will receive physical and avoid
+additional convertions)
+
+v6:
+* tce_get_hva() returns hva via a pointer
+---
+ drivers/vfio/vfio_iommu_spapr_tce.c | 61 +++++++++++++++++++++++++------------
+ 1 file changed, 41 insertions(+), 20 deletions(-)
 
 diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
-index 1c1a9c4..c9fac97 100644
+index 5bbdf37..cf5d4a1 100644
 --- a/drivers/vfio/vfio_iommu_spapr_tce.c
 +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
-@@ -29,6 +29,46 @@
- static void tce_iommu_detach_group(void *iommu_data,
- 		struct iommu_group *iommu_group);
+@@ -191,69 +191,90 @@ static void tce_iommu_release(void *iommu_data)
+ 	struct tce_container *container = iommu_data;
  
-+static long try_increment_locked_vm(struct iommu_table *tbl)
+ 	WARN_ON(container->tbl && !container->tbl->it_group);
+-	tce_iommu_disable(container);
+ 
+ 	if (container->tbl && container->tbl->it_group)
+ 		tce_iommu_detach_group(iommu_data, container->tbl->it_group);
+ 
++	tce_iommu_disable(container);
+ 	mutex_destroy(&container->lock);
+ 
+ 	kfree(container);
+ }
+ 
++static void tce_iommu_unuse_page(struct tce_container *container,
++		unsigned long oldtce)
 +{
-+	long ret = 0, locked, lock_limit, npages;
++	struct page *page;
 +
-+	if (!current || !current->mm)
-+		return -ESRCH; /* process exited */
++	if (!(oldtce & (TCE_PCI_READ | TCE_PCI_WRITE)))
++		return;
 +
-+	npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
++	page = pfn_to_page(oldtce >> PAGE_SHIFT);
 +
-+	down_write(&current->mm->mmap_sem);
-+	locked = current->mm->locked_vm + npages;
-+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-+	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
-+		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
-+				rlimit(RLIMIT_MEMLOCK));
-+		ret = -ENOMEM;
-+	} else {
-+		current->mm->locked_vm += npages;
-+	}
-+	up_write(&current->mm->mmap_sem);
++	if (oldtce & TCE_PCI_WRITE)
++		SetPageDirty(page);
 +
-+	return ret;
++	put_page(page);
 +}
 +
-+static void decrement_locked_vm(struct iommu_table *tbl)
+ static int tce_iommu_clear(struct tce_container *container,
+ 		struct iommu_table *tbl,
+ 		unsigned long entry, unsigned long pages)
+ {
+ 	unsigned long oldtce;
+-	struct page *page;
+ 
+ 	for ( ; pages; --pages, ++entry) {
+ 		oldtce = iommu_clear_tce(tbl, entry);
+ 		if (!oldtce)
+ 			continue;
+ 
+-		page = pfn_to_page(oldtce >> PAGE_SHIFT);
+-		WARN_ON(!page);
+-		if (page) {
+-			if (oldtce & TCE_PCI_WRITE)
+-				SetPageDirty(page);
+-			put_page(page);
+-		}
++		tce_iommu_unuse_page(container, oldtce);
+ 	}
+ 
+ 	return 0;
+ }
+ 
++static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
 +{
-+	long npages;
++	struct page *page = NULL;
++	enum dma_data_direction direction = iommu_tce_direction(tce);
 +
-+	if (!current || !current->mm)
-+		return; /* process exited */
++	if (get_user_pages_fast(tce & PAGE_MASK, 1,
++			direction != DMA_TO_DEVICE, &page) != 1)
++		return -EFAULT;
 +
-+	npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
++	*hpa = __pa((unsigned long) page_address(page));
 +
-+	down_write(&current->mm->mmap_sem);
-+	if (npages > current->mm->locked_vm)
-+		npages = current->mm->locked_vm;
-+	current->mm->locked_vm -= npages;
-+	up_write(&current->mm->mmap_sem);
++	return 0;
 +}
 +
- /*
-  * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
-  *
-@@ -86,7 +126,6 @@ static void tce_iommu_take_ownership_notify(struct spapr_tce_iommu_group *data,
- static int tce_iommu_enable(struct tce_container *container)
+ static long tce_iommu_build(struct tce_container *container,
+ 		struct iommu_table *tbl,
+ 		unsigned long entry, unsigned long tce, unsigned long pages)
  {
- 	int ret = 0;
--	unsigned long locked, lock_limit, npages;
- 	struct iommu_table *tbl;
- 	struct spapr_tce_iommu_group *data;
+ 	long i, ret = 0;
+-	struct page *page = NULL;
+-	unsigned long hva;
++	struct page *page;
++	unsigned long hpa;
+ 	enum dma_data_direction direction = iommu_tce_direction(tce);
  
-@@ -120,24 +159,23 @@ static int tce_iommu_enable(struct tce_container *container)
- 	 * Also we don't have a nice way to fail on H_PUT_TCE due to ulimits,
- 	 * that would effectively kill the guest at random points, much better
- 	 * enforcing the limit based on the max that the guest can map.
-+	 *
-+	 * Unfortunately at the moment it counts whole tables, no matter how
-+	 * much memory the guest has. I.e. for 4GB guest and 4 IOMMU groups
-+	 * each with 2GB DMA window, 8GB will be counted here. The reason for
-+	 * this is that we cannot tell here the amount of RAM used by the guest
-+	 * as this information is only available from KVM and VFIO is
-+	 * KVM agnostic.
- 	 */
- 	tbl = data->ops->get_table(data, 0);
- 	if (!tbl)
- 		return -ENXIO;
+ 	for (i = 0; i < pages; ++i) {
+ 		unsigned long offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
  
--	down_write(&current->mm->mmap_sem);
--	npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
--	locked = current->mm->locked_vm + npages;
--	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
--	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
--		pr_warn("RLIMIT_MEMLOCK (%ld) exceeded\n",
--				rlimit(RLIMIT_MEMLOCK));
--		ret = -ENOMEM;
--	} else {
--		current->mm->locked_vm += npages;
--		container->enabled = true;
--	}
--	up_write(&current->mm->mmap_sem);
-+	ret = try_increment_locked_vm(tbl);
-+	if (ret)
-+		return ret;
-+
-+	container->enabled = true;
+-		ret = get_user_pages_fast(tce & PAGE_MASK, 1,
+-				direction != DMA_TO_DEVICE, &page);
+-		if (unlikely(ret != 1)) {
+-			ret = -EFAULT;
++		ret = tce_iommu_use_page(tce, &hpa);
++		if (ret)
+ 			break;
+-		}
  
- 	return ret;
- }
-@@ -163,10 +201,7 @@ static void tce_iommu_disable(struct tce_container *container)
- 	if (!tbl)
- 		return;
++		page = pfn_to_page(hpa >> PAGE_SHIFT);
+ 		if (!tce_page_is_contained(page, tbl->it_page_shift)) {
+ 			ret = -EPERM;
+ 			break;
+ 		}
  
--	down_write(&current->mm->mmap_sem);
--	current->mm->locked_vm -= (tbl->it_size <<
--			IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
--	up_write(&current->mm->mmap_sem);
-+	decrement_locked_vm(tbl);
- }
- 
- static void *tce_iommu_open(unsigned long arg)
+-		hva = (unsigned long) page_address(page) + offset;
+-
+-		ret = iommu_tce_build(tbl, entry + i, hva, direction);
++		hpa |= offset;
++		ret = iommu_tce_build(tbl, entry + i, (unsigned long) __va(hpa),
++				direction);
+ 		if (ret) {
+-			put_page(page);
++			tce_iommu_unuse_page(container, hpa);
+ 			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
+ 					__func__, entry << tbl->it_page_shift,
+ 					tce, ret);
 -- 
-2.0.0
+2.4.0.rc3.8.gfb3e7d5