Add host kdump support for SNP

index 5219d7ddfdaa..8a863cae99db 100644
@@ -791,6 +791,11 @@ 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 */

183 lines not on this page · raw message

index eb348c63a8d0..05a9ab3da1a3 100644
@@ -1195,7 +1195,7 @@ 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;

index 5b8e9d6befa5..dac6282675da 100644
@@ -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;
 }
 

@@ -1117,15 +1123,12 @@ 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);

@@ -1150,66 +1153,20 @@ 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;

@@ -1217,17 +1174,17 @@ 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;
 		}

@@ -2906,8 +2863,8 @@ 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)

@@ -2915,18 +2872,25 @@ 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;
 			}
 		}

@@ -2936,7 +2900,7 @@ 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);

index 4f000dc2e639..b701908c0bdc 100644
@@ -28,6 +28,7 @@
 #include <linux/fs_struct.h>
 #include <linux/psp.h>
 #include <linux/amd-iommu.h>
+#include <linux/crash_dump.h>
 
 #include <asm/smp.h>
 #include <asm/cacheflush.h>

@@ -1374,6 +1375,15 @@ static int __sev_platform_init_locked(int *error)
 	if (!psp_master || !psp_master->sev_data)
 		return -ENODEV;
 
+	/*
+	 * Skip SNP/SEV initialization under a kdump kernel as SEV/SNP
+	 * may already be initialized in the previous kernel. Since no
+	 * SNP/SEV guests are run under a kdump kernel, there is no
+	 * need to initialize SNP or SEV during kdump boot.
+	 */
+	if (is_kdump_kernel())
+		return 0;
+
 	sev = psp_master->sev_data;
 
 	if (sev->sev_plat_status.state == SEV_STATE_INIT)

index dac6282675da..d179344ad598 100644
@@ -821,11 +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);
 }

@@ -876,10 +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);