4 files changed, 228 insertions, 101 deletions

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 5219d7ddfdaa..a698a2e7ce2a 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -555,6 +555,7 @@ struct gcr3_tbl_info {
 };
 
 struct amd_io_pgtable {
+	seqcount_t		seqcount;	/* Protects root/mode update */
 	struct io_pgtable	pgtbl;
 	int			mode;
 	u64			*root;
@@ -791,6 +792,11 @@ struct amd_iommu {
 	u32 flags;
 	volatile u64 *cmd_sem;
 	atomic64_t cmd_sem_val;
+	/*
+	 * Track physical address to directly use it in build_completion_wait()
+	 * and avoid adding any special checks and handling for kdump.
+	 */
+	u64 cmd_sem_paddr;
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 	/* DebugFS Info */
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 8de689b2c5ed..f2991c11867c 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -406,6 +406,9 @@ static void iommu_set_device_table(struct amd_iommu *iommu)
 
 	BUG_ON(iommu->mmio_base == NULL);
 
+	if (is_kdump_kernel())
+		return;
+
 	entry = iommu_virt_to_phys(dev_table);
 	entry |= (dev_table_size >> 12) - 1;
 	memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET,
@@ -646,7 +649,10 @@ static inline int __init alloc_dev_table(struct amd_iommu_pci_seg *pci_seg)
 
 static inline void free_dev_table(struct amd_iommu_pci_seg *pci_seg)
 {
-	iommu_free_pages(pci_seg->dev_table);
+	if (is_kdump_kernel())
+		memunmap((void *)pci_seg->dev_table);
+	else
+		iommu_free_pages(pci_seg->dev_table);
 	pci_seg->dev_table = NULL;
 }
 
@@ -710,6 +716,26 @@ static void __init free_alias_table(struct amd_iommu_pci_seg *pci_seg)
 	pci_seg->alias_table = NULL;
 }
 
+static inline void *iommu_memremap(unsigned long paddr, size_t size)
+{
+	phys_addr_t phys;
+
+	if (!paddr)
+		return NULL;
+
+	/*
+	 * Obtain true physical address in kdump kernel when SME is enabled.
+	 * Currently, previous kernel with SME enabled and kdump kernel
+	 * with SME support disabled is not supported.
+	 */
+	phys = __sme_clr(paddr);
+
+	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		return (__force void *)ioremap_encrypted(phys, size);
+	else
+		return memremap(phys, size, MEMREMAP_WB);
+}
+
 /*
  * Allocates the command buffer. This buffer is per AMD IOMMU. We can
  * write commands to that buffer later and the IOMMU will execute them
@@ -795,11 +821,16 @@ static void iommu_enable_command_buffer(struct amd_iommu *iommu)
 
 	BUG_ON(iommu->cmd_buf == NULL);
 
-	entry = iommu_virt_to_phys(iommu->cmd_buf);
-	entry |= MMIO_CMD_SIZE_512;
-
-	memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
-		    &entry, sizeof(entry));
+	if (!is_kdump_kernel()) {
+		/*
+		 * Command buffer is re-used for kdump kernel and setting
+		 * of MMIO register is not required.
+		 */
+		entry = iommu_virt_to_phys(iommu->cmd_buf);
+		entry |= MMIO_CMD_SIZE_512;
+		memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
+			    &entry, sizeof(entry));
+	}
 
 	amd_iommu_reset_cmd_buffer(iommu);
 }
@@ -850,10 +881,15 @@ static void iommu_enable_event_buffer(struct amd_iommu *iommu)
 
 	BUG_ON(iommu->evt_buf == NULL);
 
-	entry = iommu_virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
-
-	memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
-		    &entry, sizeof(entry));
+	if (!is_kdump_kernel()) {
+		/*
+		 * Event buffer is re-used for kdump kernel and setting
+		 * of MMIO register is not required.
+		 */
+		entry = iommu_virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;
+		memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
+			    &entry, sizeof(entry));
+	}
 
 	/* set head and tail to zero manually */
 	writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
@@ -942,8 +978,91 @@ err_out:
 static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
 {
 	iommu->cmd_sem = iommu_alloc_4k_pages(iommu, GFP_KERNEL, 1);
+	if (!iommu->cmd_sem)
+		return -ENOMEM;
+	iommu->cmd_sem_paddr = iommu_virt_to_phys((void *)iommu->cmd_sem);
+	return 0;
+}
+
+static int __init remap_event_buffer(struct amd_iommu *iommu)
+{
+	u64 paddr;
+
+	pr_info_once("Re-using event buffer from the previous kernel\n");
+	paddr = readq(iommu->mmio_base + MMIO_EVT_BUF_OFFSET) & PM_ADDR_MASK;
+	iommu->evt_buf = iommu_memremap(paddr, EVT_BUFFER_SIZE);
+
+	return iommu->evt_buf ? 0 : -ENOMEM;
+}
+
+static int __init remap_command_buffer(struct amd_iommu *iommu)
+{
+	u64 paddr;
+
+	pr_info_once("Re-using command buffer from the previous kernel\n");
+	paddr = readq(iommu->mmio_base + MMIO_CMD_BUF_OFFSET) & PM_ADDR_MASK;
+	iommu->cmd_buf = iommu_memremap(paddr, CMD_BUFFER_SIZE);
+
+	return iommu->cmd_buf ? 0 : -ENOMEM;
+}
+
+static int __init remap_or_alloc_cwwb_sem(struct amd_iommu *iommu)
+{
+	u64 paddr;
+
+	if (check_feature(FEATURE_SNP)) {
+		/*
+		 * When SNP is enabled, the exclusion base register is used for the
+		 * completion wait buffer (CWB) address. Read and re-use it.
+		 */
+		pr_info_once("Re-using CWB buffers from the previous kernel\n");
+		paddr = readq(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET) & PM_ADDR_MASK;
+		iommu->cmd_sem = iommu_memremap(paddr, PAGE_SIZE);
+		if (!iommu->cmd_sem)
+			return -ENOMEM;
+		iommu->cmd_sem_paddr = paddr;
+	} else {
+		return alloc_cwwb_sem(iommu);
+	}
 
-	return iommu->cmd_sem ? 0 : -ENOMEM;
+	return 0;
+}
+
+static int __init alloc_iommu_buffers(struct amd_iommu *iommu)
+{
+	int ret;
+
+	/*
+	 * Reuse/Remap the previous kernel's allocated completion wait
+	 * command and event buffers for kdump boot.
+	 */
+	if (is_kdump_kernel()) {
+		ret = remap_or_alloc_cwwb_sem(iommu);
+		if (ret)
+			return ret;
+
+		ret = remap_command_buffer(iommu);
+		if (ret)
+			return ret;
+
+		ret = remap_event_buffer(iommu);
+		if (ret)
+			return ret;
+	} else {
+		ret = alloc_cwwb_sem(iommu);
+		if (ret)
+			return ret;
+
+		ret = alloc_command_buffer(iommu);
+		if (ret)
+			return ret;
+
+		ret = alloc_event_buffer(iommu);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static void __init free_cwwb_sem(struct amd_iommu *iommu)
@@ -951,6 +1070,38 @@ static void __init free_cwwb_sem(struct amd_iommu *iommu)
 	if (iommu->cmd_sem)
 		iommu_free_pages((void *)iommu->cmd_sem);
 }
+static void __init unmap_cwwb_sem(struct amd_iommu *iommu)
+{
+	if (iommu->cmd_sem) {
+		if (check_feature(FEATURE_SNP))
+			memunmap((void *)iommu->cmd_sem);
+		else
+			iommu_free_pages((void *)iommu->cmd_sem);
+	}
+}
+
+static void __init unmap_command_buffer(struct amd_iommu *iommu)
+{
+	memunmap((void *)iommu->cmd_buf);
+}
+
+static void __init unmap_event_buffer(struct amd_iommu *iommu)
+{
+	memunmap(iommu->evt_buf);
+}
+
+static void __init free_iommu_buffers(struct amd_iommu *iommu)
+{
+	if (is_kdump_kernel()) {
+		unmap_cwwb_sem(iommu);
+		unmap_command_buffer(iommu);
+		unmap_event_buffer(iommu);
+	} else {
+		free_cwwb_sem(iommu);
+		free_command_buffer(iommu);
+		free_event_buffer(iommu);
+	}
+}
 
 static void iommu_enable_xt(struct amd_iommu *iommu)
 {
@@ -982,15 +1133,12 @@ static void set_dte_bit(struct dev_table_entry *dte, u8 bit)
 	dte->data[i] |= (1UL << _bit);
 }
 
-static bool __copy_device_table(struct amd_iommu *iommu)
+static bool __reuse_device_table(struct amd_iommu *iommu)
 {
-	u64 int_ctl, int_tab_len, entry = 0;
 	struct amd_iommu_pci_seg *pci_seg = iommu->pci_seg;
-	struct dev_table_entry *old_devtb = NULL;
-	u32 lo, hi, devid, old_devtb_size;
+	u32 lo, hi, old_devtb_size;
 	phys_addr_t old_devtb_phys;
-	u16 dom_id, dte_v, irq_v;
-	u64 tmp;
+	u64 entry;
 
 	/* Each IOMMU use separate device table with the same size */
 	lo = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET);
@@ -1015,66 +1163,20 @@ static bool __copy_device_table(struct amd_iommu *iommu)
 		pr_err("The address of old device table is above 4G, not trustworthy!\n");
 		return false;
 	}
-	old_devtb = (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT) && is_kdump_kernel())
-		    ? (__force void *)ioremap_encrypted(old_devtb_phys,
-							pci_seg->dev_table_size)
-		    : memremap(old_devtb_phys, pci_seg->dev_table_size, MEMREMAP_WB);
 
-	if (!old_devtb)
-		return false;
-
-	pci_seg->old_dev_tbl_cpy = iommu_alloc_pages_sz(
-		GFP_KERNEL | GFP_DMA32, pci_seg->dev_table_size);
+	/*
+	 * Re-use the previous kernel's device table for kdump.
+	 */
+	pci_seg->old_dev_tbl_cpy = iommu_memremap(old_devtb_phys, pci_seg->dev_table_size);
 	if (pci_seg->old_dev_tbl_cpy == NULL) {
-		pr_err("Failed to allocate memory for copying old device table!\n");
-		memunmap(old_devtb);
+		pr_err("Failed to remap memory for reusing old device table!\n");
 		return false;
 	}
 
-	for (devid = 0; devid <= pci_seg->last_bdf; ++devid) {
-		pci_seg->old_dev_tbl_cpy[devid] = old_devtb[devid];
-		dom_id = old_devtb[devid].data[1] & DEV_DOMID_MASK;
-		dte_v = old_devtb[devid].data[0] & DTE_FLAG_V;
-
-		if (dte_v && dom_id) {
-			pci_seg->old_dev_tbl_cpy[devid].data[0] = old_devtb[devid].data[0];
-			pci_seg->old_dev_tbl_cpy[devid].data[1] = old_devtb[devid].data[1];
-			/* Reserve the Domain IDs used by previous kernel */
-			if (ida_alloc_range(&pdom_ids, dom_id, dom_id, GFP_ATOMIC) != dom_id) {
-				pr_err("Failed to reserve domain ID 0x%x\n", dom_id);
-				memunmap(old_devtb);
-				return false;
-			}
-			/* If gcr3 table existed, mask it out */
-			if (old_devtb[devid].data[0] & DTE_FLAG_GV) {
-				tmp = (DTE_GCR3_30_15 | DTE_GCR3_51_31);
-				pci_seg->old_dev_tbl_cpy[devid].data[1] &= ~tmp;
-				tmp = (DTE_GCR3_14_12 | DTE_FLAG_GV);
-				pci_seg->old_dev_tbl_cpy[devid].data[0] &= ~tmp;
-			}
-		}
-
-		irq_v = old_devtb[devid].data[2] & DTE_IRQ_REMAP_ENABLE;
-		int_ctl = old_devtb[devid].data[2] & DTE_IRQ_REMAP_INTCTL_MASK;
-		int_tab_len = old_devtb[devid].data[2] & DTE_INTTABLEN_MASK;
-		if (irq_v && (int_ctl || int_tab_len)) {
-			if ((int_ctl != DTE_IRQ_REMAP_INTCTL) ||
-			    (int_tab_len != DTE_INTTABLEN_512 &&
-			     int_tab_len != DTE_INTTABLEN_2K)) {
-				pr_err("Wrong old irq remapping flag: %#x\n", devid);
-				memunmap(old_devtb);
-				return false;
-			}
-
-			pci_seg->old_dev_tbl_cpy[devid].data[2] = old_devtb[devid].data[2];
-		}
-	}
-	memunmap(old_devtb);
-
 	return true;
 }
 
-static bool copy_device_table(void)
+static bool reuse_device_table(void)
 {
 	struct amd_iommu *iommu;
 	struct amd_iommu_pci_seg *pci_seg;
@@ -1082,17 +1184,17 @@ static bool copy_device_table(void)
 	if (!amd_iommu_pre_enabled)
 		return false;
 
-	pr_warn("Translation is already enabled - trying to copy translation structures\n");
+	pr_warn("Translation is already enabled - trying to reuse translation structures\n");
 
 	/*
 	 * All IOMMUs within PCI segment shares common device table.
-	 * Hence copy device table only once per PCI segment.
+	 * Hence reuse device table only once per PCI segment.
 	 */
 	for_each_pci_segment(pci_seg) {
 		for_each_iommu(iommu) {
 			if (pci_seg->id != iommu->pci_seg->id)
 				continue;
-			if (!__copy_device_table(iommu))
+			if (!__reuse_device_table(iommu))
 				return false;
 			break;
 		}
@@ -1455,12 +1557,12 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 				    PCI_FUNC(e->devid));
 
 			devid = e->devid;
-			for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
-				if (alias)
+			if (alias) {
+				for (dev_i = devid_start; dev_i <= devid; ++dev_i)
 					pci_seg->alias_table[dev_i] = devid_to;
+				set_dev_entry_from_acpi(iommu, devid_to, flags, ext_flags);
 			}
 			set_dev_entry_from_acpi_range(iommu, devid_start, devid, flags, ext_flags);
-			set_dev_entry_from_acpi(iommu, devid_to, flags, ext_flags);
 			break;
 		case IVHD_DEV_SPECIAL: {
 			u8 handle, type;
@@ -1655,9 +1757,7 @@ static void __init free_sysfs(struct amd_iommu *iommu)
 static void __init free_iommu_one(struct amd_iommu *iommu)
 {
 	free_sysfs(iommu);
-	free_cwwb_sem(iommu);
-	free_command_buffer(iommu);
-	free_event_buffer(iommu);
+	free_iommu_buffers(iommu);
 	amd_iommu_free_ppr_log(iommu);
 	free_ga_log(iommu);
 	iommu_unmap_mmio_space(iommu);
@@ -1821,14 +1921,9 @@ static int __init init_iommu_one_late(struct amd_iommu *iommu)
 {
 	int ret;
 
-	if (alloc_cwwb_sem(iommu))
-		return -ENOMEM;
-
-	if (alloc_command_buffer(iommu))
-		return -ENOMEM;
-
-	if (alloc_event_buffer(iommu))
-		return -ENOMEM;
+	ret = alloc_iommu_buffers(iommu);
+	if (ret)
+		return ret;
 
 	iommu->int_enabled = false;
 
@@ -2778,8 +2873,8 @@ static void early_enable_iommu(struct amd_iommu *iommu)
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized.
  *
- * Or if in kdump kernel and IOMMUs are all pre-enabled, try to copy
- * the old content of device table entries. Not this case or copy failed,
+ * Or if in kdump kernel and IOMMUs are all pre-enabled, try to reuse
+ * the old content of device table entries. Not this case or reuse failed,
  * just continue as normal kernel does.
  */
 static void early_enable_iommus(void)
@@ -2787,18 +2882,25 @@ static void early_enable_iommus(void)
 	struct amd_iommu *iommu;
 	struct amd_iommu_pci_seg *pci_seg;
 
-	if (!copy_device_table()) {
+	if (!reuse_device_table()) {
 		/*
-		 * If come here because of failure in copying device table from old
+		 * If come here because of failure in reusing device table from old
 		 * kernel with all IOMMUs enabled, print error message and try to
 		 * free allocated old_dev_tbl_cpy.
 		 */
-		if (amd_iommu_pre_enabled)
-			pr_err("Failed to copy DEV table from previous kernel.\n");
+		if (amd_iommu_pre_enabled) {
+			pr_err("Failed to reuse DEV table from previous kernel.\n");
+			/*
+			 * Bail out early if unable to remap/reuse DEV table from
+			 * previous kernel if SNP enabled as IOMMU commands will
+			 * time out without DEV table and cause kdump boot panic.
+			 */
+			BUG_ON(check_feature(FEATURE_SNP));
+		}
 
 		for_each_pci_segment(pci_seg) {
 			if (pci_seg->old_dev_tbl_cpy != NULL) {
-				iommu_free_pages(pci_seg->old_dev_tbl_cpy);
+				memunmap((void *)pci_seg->old_dev_tbl_cpy);
 				pci_seg->old_dev_tbl_cpy = NULL;
 			}
 		}
@@ -2808,7 +2910,7 @@ static void early_enable_iommus(void)
 			early_enable_iommu(iommu);
 		}
 	} else {
-		pr_info("Copied DEV table from previous kernel.\n");
+		pr_info("Reused DEV table from previous kernel.\n");
 
 		for_each_pci_segment(pci_seg) {
 			iommu_free_pages(pci_seg->dev_table);
@@ -3067,7 +3169,8 @@ static int __init early_amd_iommu_init(void)
 
 	if (!boot_cpu_has(X86_FEATURE_CX16)) {
 		pr_err("Failed to initialize. The CMPXCHG16B feature is required.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	/*
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index a91e71f981ef..70c2f5b1631b 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
+#include <linux/seqlock.h>
 
 #include <asm/barrier.h>
 
@@ -130,8 +131,11 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable,
 
 	*pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root));
 
+	write_seqcount_begin(&pgtable->seqcount);
 	pgtable->root  = pte;
 	pgtable->mode += 1;
+	write_seqcount_end(&pgtable->seqcount);
+
 	amd_iommu_update_and_flush_device_table(domain);
 
 	pte = NULL;
@@ -153,6 +157,7 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable,
 {
 	unsigned long last_addr = address + (page_size - 1);
 	struct io_pgtable_cfg *cfg = &pgtable->pgtbl.cfg;
+	unsigned int seqcount;
 	int level, end_lvl;
 	u64 *pte, *page;
 
@@ -170,8 +175,14 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable,
 	}
 
 
-	level   = pgtable->mode - 1;
-	pte     = &pgtable->root[PM_LEVEL_INDEX(level, address)];
+	do {
+		seqcount = read_seqcount_begin(&pgtable->seqcount);
+
+		level   = pgtable->mode - 1;
+		pte     = &pgtable->root[PM_LEVEL_INDEX(level, address)];
+	} while (read_seqcount_retry(&pgtable->seqcount, seqcount));
+
+
 	address = PAGE_SIZE_ALIGN(address, page_size);
 	end_lvl = PAGE_SIZE_LEVEL(page_size);
 
@@ -249,6 +260,7 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable,
 		      unsigned long *page_size)
 {
 	int level;
+	unsigned int seqcount;
 	u64 *pte;
 
 	*page_size = 0;
@@ -256,8 +268,12 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable,
 	if (address > PM_LEVEL_SIZE(pgtable->mode))
 		return NULL;
 
-	level	   =  pgtable->mode - 1;
-	pte	   = &pgtable->root[PM_LEVEL_INDEX(level, address)];
+	do {
+		seqcount = read_seqcount_begin(&pgtable->seqcount);
+		level	   =  pgtable->mode - 1;
+		pte	   = &pgtable->root[PM_LEVEL_INDEX(level, address)];
+	} while (read_seqcount_retry(&pgtable->seqcount, seqcount));
+
 	*page_size =  PTE_LEVEL_PAGE_SIZE(level);
 
 	while (level > 0) {
@@ -541,6 +557,7 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo
 	if (!pgtable->root)
 		return NULL;
 	pgtable->mode = PAGE_MODE_3_LEVEL;
+	seqcount_init(&pgtable->seqcount);
 
 	cfg->pgsize_bitmap  = amd_iommu_pgsize_bitmap;
 	cfg->ias            = IOMMU_IN_ADDR_BIT_SIZE;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index eb348c63a8d0..2e1865daa1ce 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -14,6 +14,7 @@
 #include <linux/pci-ats.h>
 #include <linux/bitmap.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-map-ops.h>
@@ -265,7 +266,7 @@ static inline int get_acpihid_device_id(struct device *dev,
 		return -EINVAL;
 	if (fw_bug)
 		dev_err_once(dev, FW_BUG "No ACPI device matched UID, but %d device%s matched HID.\n",
-			     hid_count, hid_count > 1 ? "s" : "");
+			     hid_count, str_plural(hid_count));
 	if (hid_count > 1)
 		return -EINVAL;
 	if (entry)
@@ -1195,7 +1196,7 @@ static void build_completion_wait(struct iommu_cmd *cmd,
 				  struct amd_iommu *iommu,
 				  u64 data)
 {
-	u64 paddr = iommu_virt_to_phys((void *)iommu->cmd_sem);
+	u64 paddr = iommu->cmd_sem_paddr;
 
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;