Merge remote-tracking branch 'iommu/next'

14 files changed, 180 insertions, 133 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d4fac09095f8..04f3f7d18fdb 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -26,7 +26,7 @@
  *
  */
 
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 #include <linux/reservation.h>
 #include <linux/sync_file.h>
 #include <linux/uaccess.h>
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 132e978227fb..c051088154c6 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -46,7 +46,7 @@
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_rect.h>
 #include <drm/drm_atomic_uapi.h>
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 #include <linux/reservation.h>
 
 /* Primary plane formats for gen <= 3 */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index b9c078860a7c..5788ef6687dc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -34,7 +34,7 @@
 #include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_module.h>
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 
 #define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices"
 #define VMWGFX_CHIP_SVGAII 0
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 1167ff0416cf..71797b3d67e5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1317,6 +1317,101 @@ static void domain_flush_devices(struct protection_domain *domain)
  *
  ****************************************************************************/
 
+static void free_page_list(struct page *freelist)
+{
+	while (freelist != NULL) {
+		unsigned long p = (unsigned long)page_address(freelist);
+		freelist = freelist->freelist;
+		free_page(p);
+	}
+}
+
+static struct page *free_pt_page(unsigned long pt, struct page *freelist)
+{
+	struct page *p = virt_to_page((void *)pt);
+
+	p->freelist = freelist;
+
+	return p;
+}
+
+#define DEFINE_FREE_PT_FN(LVL, FN)						\
+static struct page *free_pt_##LVL (unsigned long __pt, struct page *freelist)	\
+{										\
+	unsigned long p;							\
+	u64 *pt;								\
+	int i;									\
+										\
+	pt = (u64 *)__pt;							\
+										\
+	for (i = 0; i < 512; ++i) {						\
+		/* PTE present? */						\
+		if (!IOMMU_PTE_PRESENT(pt[i]))					\
+			continue;						\
+										\
+		/* Large PTE? */						\
+		if (PM_PTE_LEVEL(pt[i]) == 0 ||					\
+		    PM_PTE_LEVEL(pt[i]) == 7)					\
+			continue;						\
+										\
+		p = (unsigned long)IOMMU_PTE_PAGE(pt[i]);			\
+		freelist = FN(p, freelist);					\
+	}									\
+										\
+	return free_pt_page((unsigned long)pt, freelist);			\
+}
+
+DEFINE_FREE_PT_FN(l2, free_pt_page)
+DEFINE_FREE_PT_FN(l3, free_pt_l2)
+DEFINE_FREE_PT_FN(l4, free_pt_l3)
+DEFINE_FREE_PT_FN(l5, free_pt_l4)
+DEFINE_FREE_PT_FN(l6, free_pt_l5)
+
+static struct page *free_sub_pt(unsigned long root, int mode,
+				struct page *freelist)
+{
+	switch (mode) {
+	case PAGE_MODE_NONE:
+	case PAGE_MODE_7_LEVEL:
+		break;
+	case PAGE_MODE_1_LEVEL:
+		freelist = free_pt_page(root, freelist);
+		break;
+	case PAGE_MODE_2_LEVEL:
+		freelist = free_pt_l2(root, freelist);
+		break;
+	case PAGE_MODE_3_LEVEL:
+		freelist = free_pt_l3(root, freelist);
+		break;
+	case PAGE_MODE_4_LEVEL:
+		freelist = free_pt_l4(root, freelist);
+		break;
+	case PAGE_MODE_5_LEVEL:
+		freelist = free_pt_l5(root, freelist);
+		break;
+	case PAGE_MODE_6_LEVEL:
+		freelist = free_pt_l6(root, freelist);
+		break;
+	default:
+		BUG();
+	}
+
+	return freelist;
+}
+
+static void free_pagetable(struct protection_domain *domain)
+{
+	unsigned long root = (unsigned long)domain->pt_root;
+	struct page *freelist = NULL;
+
+	BUG_ON(domain->mode < PAGE_MODE_NONE ||
+	       domain->mode > PAGE_MODE_6_LEVEL);
+
+	free_sub_pt(root, domain->mode, freelist);
+
+	free_page_list(freelist);
+}
+
 /*
  * This function is used to add another level to an IO page table. Adding
  * another level increases the size of the address space by 9 bits to a size up
@@ -1365,10 +1460,13 @@ static u64 *alloc_pte(struct protection_domain *domain,
 
 	while (level > end_lvl) {
 		u64 __pte, __npte;
+		int pte_level;
 
-		__pte = *pte;
+		__pte     = *pte;
+		pte_level = PM_PTE_LEVEL(__pte);
 
-		if (!IOMMU_PTE_PRESENT(__pte)) {
+		if (!IOMMU_PTE_PRESENT(__pte) ||
+		    pte_level == PAGE_MODE_7_LEVEL) {
 			page = (u64 *)get_zeroed_page(gfp);
 			if (!page)
 				return NULL;
@@ -1376,19 +1474,21 @@ static u64 *alloc_pte(struct protection_domain *domain,
 			__npte = PM_LEVEL_PDE(level, iommu_virt_to_phys(page));
 
 			/* pte could have been changed somewhere. */
-			if (cmpxchg64(pte, __pte, __npte) != __pte) {
+			if (cmpxchg64(pte, __pte, __npte) != __pte)
 				free_page((unsigned long)page);
-				continue;
-			}
+			else if (pte_level == PAGE_MODE_7_LEVEL)
+				domain->updated = true;
+
+			continue;
 		}
 
 		/* No level skipping support yet */
-		if (PM_PTE_LEVEL(*pte) != level)
+		if (pte_level != level)
 			return NULL;
 
 		level -= 1;
 
-		pte = IOMMU_PTE_PAGE(*pte);
+		pte = IOMMU_PTE_PAGE(__pte);
 
 		if (pte_page && level == end_lvl)
 			*pte_page = pte;
@@ -1457,6 +1557,25 @@ static u64 *fetch_pte(struct protection_domain *domain,
 	return pte;
 }
 
+static struct page *free_clear_pte(u64 *pte, u64 pteval, struct page *freelist)
+{
+	unsigned long pt;
+	int mode;
+
+	while (cmpxchg64(pte, pteval, 0) != pteval) {
+		pr_warn("AMD-Vi: IOMMU pte changed since we read it\n");
+		pteval = *pte;
+	}
+
+	if (!IOMMU_PTE_PRESENT(pteval))
+		return freelist;
+
+	pt   = (unsigned long)IOMMU_PTE_PAGE(pteval);
+	mode = IOMMU_PTE_MODE(pteval);
+
+	return free_sub_pt(pt, mode, freelist);
+}
+
 /*
  * Generic mapping functions. It maps a physical address into a DMA
  * address space. It allocates the page table pages if necessary.
@@ -1471,6 +1590,7 @@ static int iommu_map_page(struct protection_domain *dom,
 			  int prot,
 			  gfp_t gfp)
 {
+	struct page *freelist = NULL;
 	u64 __pte, *pte;
 	int i, count;
 
@@ -1487,8 +1607,10 @@ static int iommu_map_page(struct protection_domain *dom,
 		return -ENOMEM;
 
 	for (i = 0; i < count; ++i)
-		if (IOMMU_PTE_PRESENT(pte[i]))
-			return -EBUSY;
+		freelist = free_clear_pte(&pte[i], pte[i], freelist);
+
+	if (freelist != NULL)
+		dom->updated = true;
 
 	if (count > 1) {
 		__pte = PAGE_SIZE_PTE(__sme_set(phys_addr), page_size);
@@ -1506,6 +1628,9 @@ static int iommu_map_page(struct protection_domain *dom,
 
 	update_domain(dom);
 
+	/* Everything flushed out, free pages now */
+	free_page_list(freelist);
+
 	return 0;
 }
 
@@ -1638,67 +1763,6 @@ static void domain_id_free(int id)
 	spin_unlock(&pd_bitmap_lock);
 }
 
-#define DEFINE_FREE_PT_FN(LVL, FN)				\
-static void free_pt_##LVL (unsigned long __pt)			\
-{								\
-	unsigned long p;					\
-	u64 *pt;						\
-	int i;							\
-								\
-	pt = (u64 *)__pt;					\
-								\
-	for (i = 0; i < 512; ++i) {				\
-		/* PTE present? */				\
-		if (!IOMMU_PTE_PRESENT(pt[i]))			\
-			continue;				\
-								\
-		/* Large PTE? */				\
-		if (PM_PTE_LEVEL(pt[i]) == 0 ||			\
-		    PM_PTE_LEVEL(pt[i]) == 7)			\
-			continue;				\
-								\
-		p = (unsigned long)IOMMU_PTE_PAGE(pt[i]);	\
-		FN(p);						\
-	}							\
-	free_page((unsigned long)pt);				\
-}
-
-DEFINE_FREE_PT_FN(l2, free_page)
-DEFINE_FREE_PT_FN(l3, free_pt_l2)
-DEFINE_FREE_PT_FN(l4, free_pt_l3)
-DEFINE_FREE_PT_FN(l5, free_pt_l4)
-DEFINE_FREE_PT_FN(l6, free_pt_l5)
-
-static void free_pagetable(struct protection_domain *domain)
-{
-	unsigned long root = (unsigned long)domain->pt_root;
-
-	switch (domain->mode) {
-	case PAGE_MODE_NONE:
-		break;
-	case PAGE_MODE_1_LEVEL:
-		free_page(root);
-		break;
-	case PAGE_MODE_2_LEVEL:
-		free_pt_l2(root);
-		break;
-	case PAGE_MODE_3_LEVEL:
-		free_pt_l3(root);
-		break;
-	case PAGE_MODE_4_LEVEL:
-		free_pt_l4(root);
-		break;
-	case PAGE_MODE_5_LEVEL:
-		free_pt_l5(root);
-		break;
-	case PAGE_MODE_6_LEVEL:
-		free_pt_l6(root);
-		break;
-	default:
-		BUG();
-	}
-}
-
 static void free_gcr3_tbl_level1(u64 *tbl)
 {
 	u64 *ptr;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index bb2cd29e1658..d8f7000a466a 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -797,7 +797,8 @@ static int iommu_init_ga_log(struct amd_iommu *iommu)
 	entry = iommu_virt_to_phys(iommu->ga_log) | GA_LOG_SIZE_512;
 	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_BASE_OFFSET,
 		    &entry, sizeof(entry));
-	entry = (iommu_virt_to_phys(iommu->ga_log) & 0xFFFFFFFFFFFFFULL) & ~7ULL;
+	entry = (iommu_virt_to_phys(iommu->ga_log_tail) &
+		 (BIT_ULL(52)-1)) & ~7ULL;
 	memcpy_toio(iommu->mmio_base + MMIO_GA_LOG_TAIL_OFFSET,
 		    &entry, sizeof(entry));
 	writel(0x00, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index e2b342e65a7b..eae0741f72dc 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -269,6 +269,7 @@
 #define PAGE_MODE_4_LEVEL 0x04
 #define PAGE_MODE_5_LEVEL 0x05
 #define PAGE_MODE_6_LEVEL 0x06
+#define PAGE_MODE_7_LEVEL 0x07
 
 #define PM_LEVEL_SHIFT(x)	(12 + ((x) * 9))
 #define PM_LEVEL_SIZE(x)	(((x) < 6) ? \
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index db301efe126d..887150907526 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -595,7 +595,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			pr_err("%s: Page request without PASID: %08llx %08llx\n",
 			       iommu->name, ((unsigned long long *)req)[0],
 			       ((unsigned long long *)req)[1]);
-			goto bad_req;
+			goto no_pasid;
 		}
 
 		if (!svm || svm->pasid != req->pasid) {
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index edbdf5d6962c..f8ec49e0f6c6 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1712,33 +1712,32 @@ EXPORT_SYMBOL_GPL(iommu_unmap_fast);
 size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 		    struct scatterlist *sg, unsigned int nents, int prot)
 {
-	struct scatterlist *s;
-	size_t mapped = 0;
-	unsigned int i, min_pagesz;
+	size_t len = 0, mapped = 0;
+	phys_addr_t start;
+	unsigned int i = 0;
 	int ret;
 
-	if (unlikely(domain->pgsize_bitmap == 0UL))
-		return 0;
-
-	min_pagesz = 1 << __ffs(domain->pgsize_bitmap);
+	while (i <= nents) {
+		phys_addr_t s_phys = sg_phys(sg);
 
-	for_each_sg(sg, s, nents, i) {
-		phys_addr_t phys = page_to_phys(sg_page(s)) + s->offset;
+		if (len && s_phys != start + len) {
+			ret = iommu_map(domain, iova + mapped, start, len, prot);
+			if (ret)
+				goto out_err;
 
-		/*
-		 * We are mapping on IOMMU page boundaries, so offset within
-		 * the page must be 0. However, the IOMMU may support pages
-		 * smaller than PAGE_SIZE, so s->offset may still represent
-		 * an offset of that boundary within the CPU page.
-		 */
-		if (!IS_ALIGNED(s->offset, min_pagesz))
-			goto out_err;
+			mapped += len;
+			len = 0;
+		}
 
-		ret = iommu_map(domain, iova + mapped, phys, s->length, prot);
-		if (ret)
-			goto out_err;
+		if (len) {
+			len += sg->length;
+		} else {
+			len = sg->length;
+			start = s_phys;
+		}
 
-		mapped += s->length;
+		if (++i < nents)
+			sg = sg_next(sg);
 	}
 
 	return mapped;
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index b98a03189580..9e2655f1c1bf 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -498,6 +498,9 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 
 static void ipmmu_domain_destroy_context(struct ipmmu_vmsa_domain *domain)
 {
+	if (!domain->mmu)
+		return;
+
 	/*
 	 * Disable the context. Flush the TLB as required when modifying the
 	 * context registers.
@@ -758,10 +761,12 @@ static bool ipmmu_slave_whitelist(struct device *dev)
 }
 
 static const struct soc_device_attribute soc_rcar_gen3[] = {
+	{ .soc_id = "r8a774a1", },
 	{ .soc_id = "r8a7795", },
 	{ .soc_id = "r8a7796", },
 	{ .soc_id = "r8a77965", },
 	{ .soc_id = "r8a77970", },
+	{ .soc_id = "r8a77990", },
 	{ .soc_id = "r8a77995", },
 	{ /* sentinel */ }
 };
@@ -938,6 +943,9 @@ static const struct of_device_id ipmmu_of_ids[] = {
 		.compatible = "renesas,ipmmu-vmsa",
 		.data = &ipmmu_features_default,
 	}, {
+		.compatible = "renesas,ipmmu-r8a774a1",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
 		.compatible = "renesas,ipmmu-r8a7795",
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
@@ -950,6 +958,9 @@ static const struct of_device_id ipmmu_of_ids[] = {
 		.compatible = "renesas,ipmmu-r8a77970",
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
+		.compatible = "renesas,ipmmu-r8a77990",
+		.data = &ipmmu_features_rcar_gen3,
+	}, {
 		.compatible = "renesas,ipmmu-r8a77995",
 		.data = &ipmmu_features_rcar_gen3,
 	}, {
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 44bd5b9166bb..d69a9ffa58a4 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -113,7 +113,7 @@ struct mtk_iommu_domain {
 	struct iommu_domain		domain;
 };
 
-static struct iommu_ops mtk_iommu_ops;
+static const struct iommu_ops mtk_iommu_ops;
 
 static LIST_HEAD(m4ulist);	/* List all the M4U HWs */
 
@@ -488,7 +488,7 @@ static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	return iommu_fwspec_add_ids(dev, args->args, 1);
 }
 
-static struct iommu_ops mtk_iommu_ops = {
+static const struct iommu_ops mtk_iommu_ops = {
 	.domain_alloc	= mtk_iommu_domain_alloc,
 	.domain_free	= mtk_iommu_domain_free,
 	.attach_dev	= mtk_iommu_attach_device,
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index 0e780848f59b..27867b862d7a 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -362,7 +362,7 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 	return pa;
 }
 
-static struct iommu_ops mtk_iommu_ops;
+static const struct iommu_ops mtk_iommu_ops;
 
 /*
  * MTK generation one iommu HW only support one iommu domain, and all the client
@@ -524,7 +524,7 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 	return 0;
 }
 
-static struct iommu_ops mtk_iommu_ops = {
+static const struct iommu_ops mtk_iommu_ops = {
 	.domain_alloc	= mtk_iommu_domain_alloc,
 	.domain_free	= mtk_iommu_domain_free,
 	.attach_dev	= mtk_iommu_attach_device,
diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c
index c824329f7012..b441f6b0c743 100644
--- a/drivers/misc/mic/scif/scif_rma.c
+++ b/drivers/misc/mic/scif/scif_rma.c
@@ -15,7 +15,7 @@
  * Intel SCIF driver.
  *
  */
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 #include <linux/pagemap.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
diff --git a/drivers/misc/mic/scif/scif_rma.h b/drivers/misc/mic/scif/scif_rma.h
index fa6722279196..d90a06d4e93b 100644
--- a/drivers/misc/mic/scif/scif_rma.h
+++ b/drivers/misc/mic/scif/scif_rma.h
@@ -53,7 +53,7 @@
 #ifndef SCIF_RMA_H
 #define SCIF_RMA_H
 
-#include <linux/dma_remapping.h>
+#include <linux/intel-iommu.h>
 #include <linux/mmu_notifier.h>
 
 #include "../bus/scif_bus.h"
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index d9fd3188615d..7651cfb14836 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -978,32 +978,6 @@ unlock:
 	return ret;
 }
 
-/*
- * Turns out AMD IOMMU has a page table bug where it won't map large pages
- * to a region that previously mapped smaller pages.  This should be fixed
- * soon, so this is just a temporary workaround to break mappings down into
- * PAGE_SIZE.  Better to map smaller pages than nothing.
- */
-static int map_try_harder(struct vfio_domain *domain, dma_addr_t iova,
-			  unsigned long pfn, long npage, int prot)
-{
-	long i;
-	int ret = 0;
-
-	for (i = 0; i < npage; i++, pfn++, iova += PAGE_SIZE) {
-		ret = iommu_map(domain->domain, iova,
-				(phys_addr_t)pfn << PAGE_SHIFT,
-				PAGE_SIZE, prot | domain->prot);
-		if (ret)
-			break;
-	}
-
-	for (; i < npage && i > 0; i--, iova -= PAGE_SIZE)
-		iommu_unmap(domain->domain, iova, PAGE_SIZE);
-
-	return ret;
-}
-
 static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
 			  unsigned long pfn, long npage, int prot)
 {
@@ -1013,11 +987,8 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT,
 				npage << PAGE_SHIFT, prot | d->prot);
-		if (ret) {
-			if (ret != -EBUSY ||
-			    map_try_harder(d, iova, pfn, npage, prot))
-				goto unwind;
-		}
+		if (ret)
+			goto unwind;
 
 		cond_resched();
 	}