[PATCH v8 06/10] iommu/vt-d: datatypes and functions used for kdump

[Li, Zhen-Hua]

Populate it with support functions to copy iommu translation tables from
from the panicked kernel into the kdump kernel in the event of a crash.

Functions:
    malloc new context table and copy old context table to the new one.
    malloc new page table and copy old page table to the new one.

Bill Sumner:
    Original version, the creation of the data types and functions.

Li, Zhenhua:
    Minor change:
    Update the usage of context_get_* and context_put*, use context_*
    and context_set_* for replacement.
    Update the name of the function that copies root entry table.
    Use new function to copy old context entry tables and page tables.
    Use "unsigned long" for physical address.
    Change incorrect aw_shift[4] and a few comments in copy_context_entry().

Signed-off-by: Bill Sumner <billsumnerlinux@xxxxxxxxx>
Signed-off-by: Li, Zhen-Hua <zhen-hual@xxxxxx>
---
 drivers/iommu/intel-iommu.c | 547 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 547 insertions(+)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 5f11f43..277b294 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -399,6 +399,62 @@ struct iommu_remapped_entry {
 static LIST_HEAD(__iommu_remapped_mem);
 static DEFINE_MUTEX(__iommu_mem_list_lock);
 
+/* ========================================================================
+ * Copy iommu translation tables from old kernel into new  kernel.
+ * Entry to this set of functions is: intel_iommu_load_translation_tables()
+ * ------------------------------------------------------------------------
+ */
+
+/*
+ * Lists of domain_values_entry to hold domain values found during the copy.
+ * One list for each iommu in g_number_of_iommus.
+ */
+static struct list_head *domain_values_list;
+
+
+#define RET_BADCOPY -1	/* Return-code: Cannot copy translate tables */
+
+/*
+ * Struct copy_page_addr_parms is used to allow copy_page_addr()
+ * to accumulate values across multiple calls and returns.
+ */
+struct copy_page_addr_parms {
+	u32 first;	/* flag: first-time  */
+	u32 last;	/* flag: last-time */
+	u32 bus;	/* last bus number we saw */
+	u32 devfn;	/* last devfn we saw */
+	u32 shift;	/* last shift we saw */
+	u64 pte;	/* Page Table Entry */
+	u64 next_addr;	/* next-expected page_addr */
+
+	u64 page_addr;	/* page_addr accumulating size */
+	u64 page_size;	/* page_size accumulated */
+
+	struct domain_values_entry *dve;	/* to accumulate iova ranges */
+};
+
+enum returns_from_copy_context_entry {
+RET_CCE_NOT_PRESENT = 1,
+RET_CCE_NEW_PAGE_TABLES,
+RET_CCE_PASS_THROUGH_1,
+RET_CCE_PASS_THROUGH_2,
+RET_CCE_RESERVED_VALUE,
+RET_CCE_PREVIOUS_DID
+};
+
+static int copy_context_entry(struct intel_iommu *iommu, u32 bus, u32 devfn,
+			      void *ppap, struct context_entry *ce);
+
+static int copy_context_entry_table(struct intel_iommu *iommu,
+				    u32 bus, void *ppap,
+				    unsigned long *context_new_p,
+				    unsigned long context_old_phys);
+
+static int copy_root_entry_table(struct intel_iommu *iommu, void *ppap);
+
+static int intel_iommu_load_translation_tables(struct dmar_drhd_unit *drhd,
+		int g_num_of_iommus);
+
 #endif /* CONFIG_CRASH_DUMP */
 
 /*
@@ -5039,4 +5095,495 @@ static void __iommu_update_old_root_entry(struct intel_iommu *iommu, int index)
 	__iommu_flush_cache(iommu, to + start, size);
 }
 
+/*
+ * constant for initializing instances of copy_page_addr_parms properly.
+ */
+static struct copy_page_addr_parms copy_page_addr_parms_init = {1, 0};
+
+
+
+/*
+ * Lowest-level function in the 'Copy Page Tables' set
+ * Called once for each page_addr present in an iommu page-address table.
+ *
+ * Because of the depth-first traversal of the page-tables by the
+ * higher-level functions that call 'copy_page_addr', all pages
+ * of a domain will be presented in ascending order of IO Virtual Address.
+ *
+ * This function accumulates each contiguous range of these IOVAs and
+ * reserves it within the proper domain in the crashdump kernel when a
+ * non-contiguous range is detected, as determined by any of the following:
+ * 1. a change in the bus or device owning the presented page
+ * 2. a change in the page-size of the presented page (parameter shift)
+ * 3. a change in the page-table entry of the presented page
+ * 4. a presented IOVA that does not match the expected next-page address
+ * 5. the 'last' flag is set, indicating that all IOVAs have been seen.
+ */
+static int copy_page_addr(u64 page_addr, u32 shift, u32 bus, u32 devfn,
+				u64 pte, struct domain_values_entry *dve,
+				void *parms)
+{
+	struct copy_page_addr_parms *ppap = parms;
+
+	u64 page_size = ((u64)1 << shift);	/* page_size */
+	u64 pfn_lo;				/* For reserving IOVA range */
+	u64 pfn_hi;				/* For reserving IOVA range */
+	struct iova *iova_p;			/* For reserving IOVA range */
+
+	if (!ppap) {
+		pr_err("ERROR: ppap is NULL: 0x%3.3x(%3.3d) DevFn: 0x%3.3x(%3.3d) Page: 0x%16.16llx Size: 0x%16.16llx(%lld)\n",
+			bus, bus, devfn, devfn,  page_addr,
+			page_size, page_size);
+		return 0;
+	}
+
+	/* If (only extending current addr range) */
+	if (ppap->first     == 0      &&
+	    ppap->last      == 0      &&
+	    ppap->bus       == bus    &&
+	    ppap->devfn     == devfn  &&
+	    ppap->shift     == shift  &&
+	    (ppap->pte & ~VTD_PAGE_MASK) == (pte & ~VTD_PAGE_MASK) &&
+	    ppap->next_addr == page_addr) {
+
+		/* Update page size and next-expected address */
+		ppap->next_addr += page_size;
+		ppap->page_size += page_size;
+		return 0;
+	}
+
+	if (!ppap->first) {
+		/* Close-out the accumulated IOVA address range */
+
+		if (!ppap->dve) {
+			pr_err("%s ERROR: ppap->dve is NULL -- needed to reserve range for B:D:F=%2.2x:%2.2x:%1.1x\n",
+				__func__,
+				ppap->bus, ppap->devfn >> 3, ppap->devfn & 0x7);
+			return RET_BADCOPY;
+		}
+		pfn_lo = IOVA_PFN(ppap->page_addr);
+		pfn_hi = IOVA_PFN(ppap->page_addr + ppap->page_size);
+		iova_p = reserve_iova(&ppap->dve->iovad, pfn_lo, pfn_hi);
+	}
+
+	/* Prepare for a new IOVA address range */
+	ppap->first     = 0;		/* Not first-time anymore */
+	ppap->bus       = bus;
+	ppap->devfn     = devfn;
+	ppap->shift     = shift;
+	ppap->pte       = pte;
+	ppap->next_addr = page_addr + page_size; /* Next-expected page_addr */
+
+	ppap->page_addr = page_addr;	/* Addr(new page) */
+	ppap->page_size = page_size;	/* Size(new page) */
+
+	ppap->dve	= dve;	/* adr(device_values_entry for new range) */
+
+	return 0;
+}
+
+/*
+ * Recursive function to copy the tree of page tables (max 6 recursions)
+ * Parameter 'shift' controls the recursion
+ */
+static int copy_page_table(unsigned long *dma_pte_new_p,
+			   unsigned long dma_pte_phys,
+			   u32 shift, u64 page_addr,
+			   struct intel_iommu *iommu,
+			   u32 bus, u32 devfn,
+			   struct domain_values_entry *dve, void *ppap)
+{
+	int ret;			/* Integer return code */
+	struct dma_pte *p;		/* Virtual adr(each entry) iterator */
+	struct dma_pte *pgt_new_virt;	/* Adr(dma_pte in new kernel) */
+	unsigned long dma_pte_next;	/* Adr(next table down)  */
+	u64 u;				/* index(each entry in page_table) */
+
+
+	/* If (already done all levels -- problem) */
+	if (shift < 12) {
+		pr_err("ERROR %s shift < 12 %lx\n", __func__, dma_pte_phys);
+		pr_err("shift %d, page_addr %16.16llu bus %3.3u devfn %3.3u\n",
+			shift, page_addr, bus, devfn);
+		return RET_BADCOPY;
+	}
+
+	/* allocate a page table in the new kernel
+	 * copy contents from old kernel
+	 * then update each entry in the table in the new kernel
+	 */
+
+	pgt_new_virt = (struct dma_pte *)alloc_pgtable_page(iommu->node);
+	if (!pgt_new_virt)
+		return -ENOMEM;
+
+	ret = __iommu_load_from_oldmem(pgt_new_virt,
+					dma_pte_phys,
+					VTD_PAGE_SIZE);
+
+	if (ret <= 0)
+		return ret;
+
+	for (u = 0, p = pgt_new_virt; u < 512; u++, p++) {
+
+		if (((p->val & DMA_PTE_READ) == 0) &&
+		    ((p->val & DMA_PTE_WRITE) == 0))
+			continue;
+
+		if (dma_pte_superpage(p) || (shift == 12)) {
+
+			ret = copy_page_addr(page_addr | (u << shift),
+				shift, bus, devfn, p->val, dve, ppap);
+			if (ret)
+				return ret;
+			continue;
+		}
+
+		ret = copy_page_table(&dma_pte_next,
+				(p->val & VTD_PAGE_MASK),
+				shift-9, page_addr | (u << shift),
+				iommu, bus, devfn, dve, ppap);
+
+		__iommu_flush_cache(iommu, phys_to_virt(dma_pte_next),
+				VTD_PAGE_SIZE);
+
+		if (ret)
+			return ret;
+
+		p->val &= ~VTD_PAGE_MASK;	/* Clear old and set new pgd */
+		p->val |= ((u64)dma_pte_next & VTD_PAGE_MASK);
+	}
+
+	*dma_pte_new_p = virt_to_phys(pgt_new_virt);
+
+	return 0;
+}
+
+
+/*
+ * Called once for each context_entry found in a copied context_entry_table
+ * Each context_entry represents one PCIe device handled by the IOMMU.
+ *
+ * The 'domain_values_list' contains one 'domain_values_entry' for each
+ * unique domain-id found while copying the context entries for each iommu.
+ *
+ * The Intel-iommu spec. requires that every context_entry that contains
+ * the same domain-id point to the same set of page translation tables.
+ * The hardware uses this to improve the use of its translation cache.
+ * In order to insure that the copied translate tables abide by this
+ * requirement, this function keeps a list of domain-ids (dids) that
+ * have already been seen for this iommu. This function checks each entry
+ * already on the list for a domain-id that matches the domain-id in this
+ * context_entry.  If found, this function places the address of the previous
+ * context's tree of page translation tables into this context_entry.
+ * If a matching previous entry is not found, a new 'domain_values_entry'
+ * structure is created for the domain-id in this context_entry and
+ * copy_page_table is called to duplicate its tree of page tables.
+ */
+static int copy_context_entry(struct intel_iommu *iommu, u32 bus, u32 devfn,
+			      void *ppap, struct context_entry *ce)
+{
+	int ret = 0;			/* Integer Return Code */
+	u32 shift = 0;			/* bits to shift page_addr  */
+	u64 page_addr = 0;		/* Address of translated page */
+	unsigned long pgt_old_phys;	/* Adr(page_table in the old kernel) */
+	unsigned long pgt_new_phys;	/* Adr(page_table in the new kernel) */
+	u8  t;				/* Translation-type from context */
+	u8  aw;				/* Address-width from context */
+	u32 aw_shift[8] = {
+		12+9+9,		/* [000b] 30-bit AGAW (2-level page table) */
+		12+9+9+9,	/* [001b] 39-bit AGAW (3-level page table) */
+		12+9+9+9+9,	/* [010b] 48-bit AGAW (4-level page table) */
+		12+9+9+9+9+9,	/* [011b] 57-bit AGAW (5-level page table) */
+		12+9+9+9+9+9+7,	/* [100b] 64-bit AGAW (6-level page table) */
+		0,		/* [101b] Reserved */
+		0,		/* [110b] Reserved */
+		0,		/* [111b] Reserved */
+	};
+
+	struct domain_values_entry *dve = NULL;
+
+	if (!context_present(ce)) {	/* If (context not present) */
+		ret = RET_CCE_NOT_PRESENT;		/* Skip it */
+		goto exit;
+	}
+
+	t = context_translation_type(ce);
+	/* If we have seen this domain-id before on this iommu,
+	 * give this context the same page-tables and we are done.
+	 */
+	list_for_each_entry(dve, &domain_values_list[iommu->seq_id], link) {
+		if (dve->did == (int) context_domain_id(ce)) {
+			switch (t) {
+			case 0:	/* page tables */
+			case 1:	/* page tables */
+				context_set_address_root(ce,
+						virt_to_phys(dve->pgd));
+				ret = RET_CCE_PREVIOUS_DID;
+				break;
+
+			case 2:	/* Pass through */
+				if (dve->pgd == NULL)
+					ret =  RET_CCE_PASS_THROUGH_2;
+				else
+					ret = RET_BADCOPY;
+				break;
+
+			default: /* Bad value of 't'*/
+				ret = RET_BADCOPY;
+				break;
+			}
+			goto exit;
+		}
+	}
+
+	/* Since we now know that this is a new domain-id for this iommu,
+	 * create a new entry, add it to the list, and handle its
+	 * page tables.
+	 */
+
+	dve = kcalloc(1, sizeof(struct domain_values_entry), GFP_KERNEL);
+	if (!dve) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	dve->did = (int) context_domain_id(ce);
+	dve->gaw = (int) agaw_to_width(context_address_width(ce));
+	dve->pgd = NULL;
+	init_iova_domain(&dve->iovad, DMA_32BIT_PFN);
+
+	list_add(&dve->link, &domain_values_list[iommu->seq_id]);
+
+
+	if (t == 0 || t == 1) {		/* If (context has page tables) */
+		aw = context_address_width(ce);
+		shift = aw_shift[aw];
+
+		pgt_old_phys = context_address_root(ce) << VTD_PAGE_SHIFT;
+
+		ret = copy_page_table(&pgt_new_phys, pgt_old_phys,
+			shift-9, page_addr, iommu, bus, devfn, dve, ppap);
+
+		__iommu_flush_cache(iommu, phys_to_virt(pgt_new_phys),
+				VTD_PAGE_SIZE);
+
+		if (ret)		/* if (problem) bail out */
+			goto exit;
+
+		context_set_address_root(ce, pgt_new_phys);
+		dve->pgd = phys_to_virt(pgt_new_phys);
+		ret = RET_CCE_NEW_PAGE_TABLES;
+		goto exit;
+	}
+
+	if (t == 2) {		/* If (Identity mapped pass-through) */
+		ret = RET_CCE_PASS_THROUGH_1;	/* REVISIT: Skip for now */
+		goto exit;
+	}
+
+	ret = RET_CCE_RESERVED_VALUE;	/* Else ce->t is a Reserved value */
+	/* Note fall-through */
+
+exit:	/* all returns come through here to insure good clean-up */
+	return ret;
+}
+
+
+/*
+ * Called once for each context_entry_table found in the root_entry_table
+ */
+static int copy_context_entry_table(struct intel_iommu *iommu,
+				    u32 bus, void *ppap,
+				    unsigned long *context_new_p,
+				    unsigned long context_old_phys)
+{
+	int ret = 0;				/* Integer return code */
+	struct context_entry *ce;		/* Iterator */
+	unsigned long context_new_phys;		/* adr(table in new kernel) */
+	struct context_entry *context_new_virt;	/* adr(table in new kernel) */
+	u32 devfn = 0;				/* PCI Device & function */
+
+	/* allocate a context-entry table in the new kernel
+	 * copy contents from old kernel
+	 * then update each entry in the table in the new kernel
+	 */
+	context_new_virt =
+		(struct context_entry *)alloc_pgtable_page(iommu->node);
+	if (!context_new_virt)
+		return -ENOMEM;
+
+	context_new_phys = virt_to_phys(context_new_virt);
+
+	__iommu_load_from_oldmem(context_new_virt,
+					context_old_phys,
+					VTD_PAGE_SIZE);
+
+	for (devfn = 0, ce = context_new_virt; devfn < 256; devfn++, ce++) {
+
+		if (!context_present(ce))	/* If (context not present) */
+			continue;		/* Skip it */
+
+		ret = copy_context_entry(iommu, bus, devfn, ppap, ce);
+		if (ret < 0)		/* if (problem) */
+			return RET_BADCOPY;
+
+		switch (ret) {
+		case RET_CCE_NOT_PRESENT:
+			continue;
+		case RET_CCE_NEW_PAGE_TABLES:
+			continue;
+		case RET_CCE_PASS_THROUGH_1:
+			continue;
+		case RET_CCE_PASS_THROUGH_2:
+			continue;
+		case RET_CCE_RESERVED_VALUE:
+			return RET_BADCOPY;
+		case RET_CCE_PREVIOUS_DID:
+			continue;
+		default:
+			return RET_BADCOPY;
+		};
+	}
+
+	*context_new_p = context_new_phys;
+	return 0;
+}
+
+
+/*
+ * Highest-level function in the 'copy translation tables' set of functions
+ */
+static int copy_root_entry_table(struct intel_iommu *iommu, void *ppap)
+{
+	int ret = 0;				/* Integer return code */
+	u32 bus;				/* Index: root-entry-table */
+	struct root_entry  *re;			/* Virt(iterator: new table) */
+	unsigned long context_old_phys;	/* Phys(context table entry) */
+	unsigned long context_new_phys;	/* Phys(new context_entry) */
+
+	/*
+	 * allocate a root-entry table in the new kernel
+	 * copy contents from old kernel
+	 * then update each entry in the table in the new kernel
+	 */
+
+	if (!iommu->root_entry_old_phys)
+		return -ENOMEM;
+
+	for (bus = 0, re = iommu->root_entry; bus < 256; bus += 1, re += 1) {
+		if (!root_present(re))
+			continue;
+
+		context_old_phys = get_context_phys_from_root(re);
+
+		if (!context_old_phys)
+			continue;
+
+		context_new_phys = 0;
+		ret = copy_context_entry_table(iommu, bus, ppap,
+						&context_new_phys,
+						context_old_phys);
+		__iommu_flush_cache(iommu,
+				phys_to_virt(context_new_phys),
+				VTD_PAGE_SIZE);
+
+		if (ret)
+			return ret;
+
+		set_root_value(re, context_new_phys);
+	}
+
+	return 0;
+}
+/*
+ * Interface to the "copy translation tables" set of functions
+ * from mainline code.
+ */
+static int intel_iommu_load_translation_tables(struct dmar_drhd_unit *drhd,
+		int g_num_of_iommus)
+{
+	struct intel_iommu *iommu;	/* Virt(iommu hardware registers) */
+	unsigned long long q;		/* quadword scratch */
+	int ret = 0;			/* Integer return code */
+	int i = 0;			/* Loop index */
+	unsigned long flags;
+
+	/* Structure so copy_page_addr() can accumulate things
+	 * over multiple calls and returns
+	 */
+	struct copy_page_addr_parms ppa_parms = copy_page_addr_parms_init;
+	struct copy_page_addr_parms *ppap = &ppa_parms;
+
+
+	iommu = drhd->iommu;
+	q = dmar_readq(iommu->reg + DMAR_RTADDR_REG);
+	if (!q)
+		return -1;
+
+	/* If (list needs initializing) do it here */
+	if (!domain_values_list) {
+		domain_values_list =
+			 kcalloc(g_num_of_iommus, sizeof(struct list_head),
+					GFP_KERNEL);
+
+		if (!domain_values_list) {
+			pr_err("Allocation failed for domain_values_list array\n");
+			return -ENOMEM;
+		}
+		for (i = 0; i < g_num_of_iommus; i++)
+			INIT_LIST_HEAD(&domain_values_list[i]);
+	}
+
+	spin_lock_irqsave(&iommu->lock, flags);
+
+	/* Load the root-entry table from the old kernel
+	 * foreach context_entry_table in root_entry
+	 *    foreach context_entry in context_entry_table
+	 *       foreach level-1 page_table_entry in context_entry
+	 *          foreach level-2 page_table_entry in level 1 page_table_entry
+	 *             Above pattern continues up to 6 levels of page tables
+	 *                Sanity-check the entry
+	 *                Process the bus, devfn, page_address, page_size
+	 */
+	if (!iommu->root_entry) {
+		iommu->root_entry =
+			(struct root_entry *)alloc_pgtable_page(iommu->node);
+		if (!iommu->root_entry) {
+			spin_unlock_irqrestore(&iommu->lock, flags);
+			return -ENOMEM;
+		}
+	}
+
+	iommu->root_entry_old_phys = q & VTD_PAGE_MASK;
+	if (!iommu->root_entry_old_phys) {
+		pr_err("Could not read old root entry address.");
+		return -1;
+	}
+
+	iommu->root_entry_old_virt = ioremap_cache(iommu->root_entry_old_phys,
+						VTD_PAGE_SIZE);
+	if (!iommu->root_entry_old_virt) {
+		pr_err("Could not map the old root entry.");
+		return -ENOMEM;
+	}
+
+	__iommu_load_old_root_entry(iommu);
+	ret = copy_root_entry_table(iommu, ppap);
+	__iommu_flush_cache(iommu, iommu->root_entry, PAGE_SIZE);
+	__iommu_update_old_root_entry(iommu, -1);
+
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	__iommu_free_mapped_mem();
+
+	if (ret)
+		return ret;
+
+	ppa_parms.last = 1;
+	copy_page_addr(0, 0, 0, 0, 0, NULL, ppap);
+
+	return 0;
+}
+
 #endif /* CONFIG_CRASH_DUMP */
-- 
2.0.0-rc0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/