[PATCH RFC v1 6/6] xen-swiotlb: enable 64-bit xen-swiotlb

[Dongli Zhang <dongli.zhang@oracle.com>]

This patch is to enable the 64-bit xen-swiotlb buffer.

For Xen PVM DMA address, the 64-bit device will be able to allocate from
64-bit swiotlb buffer.

Cc: Joe Jin <joe.jin@oracle.com>
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
---
 drivers/xen/swiotlb-xen.c | 117 ++++++++++++++++++++++++--------------
 1 file changed, 74 insertions(+), 43 deletions(-)

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index e18cae693cdc..c9ab07809e32 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -108,27 +108,36 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
 	unsigned long bfn = XEN_PFN_DOWN(dma_to_phys(dev, dma_addr));
 	unsigned long xen_pfn = bfn_to_local_pfn(bfn);
 	phys_addr_t paddr = (phys_addr_t)xen_pfn << XEN_PAGE_SHIFT;
+	int i;
 
 	/* If the address is outside our domain, it CAN
 	 * have the same virtual address as another address
 	 * in our domain. Therefore _only_ check address within our domain.
 	 */
-	if (pfn_valid(PFN_DOWN(paddr))) {
-		return paddr >= virt_to_phys(xen_io_tlb_start[SWIOTLB_LO]) &&
-		       paddr < virt_to_phys(xen_io_tlb_end[SWIOTLB_LO]);
-	}
+	if (!pfn_valid(PFN_DOWN(paddr)))
+		return 0;
+
+	for (i = 0; i < swiotlb_nr; i++)
+		if (paddr >= virt_to_phys(xen_io_tlb_start[i]) &&
+		    paddr < virt_to_phys(xen_io_tlb_end[i]))
+			return 1;
+
 	return 0;
 }
 
 static int
-xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
+xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs,
+		  enum swiotlb_t type)
 {
 	int i, rc;
 	int dma_bits;
 	dma_addr_t dma_handle;
 	phys_addr_t p = virt_to_phys(buf);
 
-	dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
+	if (type == SWIOTLB_HI)
+		dma_bits = max_dma_bits[SWIOTLB_HI];
+	else
+		dma_bits = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT) + PAGE_SHIFT;
 
 	i = 0;
 	do {
@@ -139,7 +148,7 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 				p + (i << IO_TLB_SHIFT),
 				get_order(slabs << IO_TLB_SHIFT),
 				dma_bits, &dma_handle);
-		} while (rc && dma_bits++ < max_dma_bits[SWIOTLB_LO]);
+		} while (rc && dma_bits++ < max_dma_bits[type]);
 		if (rc)
 			return rc;
 
@@ -147,16 +156,17 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 	} while (i < nslabs);
 	return 0;
 }
-static unsigned long xen_set_nslabs(unsigned long nr_tbl)
+
+static unsigned long xen_set_nslabs(unsigned long nr_tbl, enum swiotlb_t type)
 {
 	if (!nr_tbl) {
-		xen_io_tlb_nslabs[SWIOTLB_LO] = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
-		xen_io_tlb_nslabs[SWIOTLB_LO] = ALIGN(xen_io_tlb_nslabs[SWIOTLB_LO],
+		xen_io_tlb_nslabs[type] = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
+		xen_io_tlb_nslabs[type] = ALIGN(xen_io_tlb_nslabs[type],
 						      IO_TLB_SEGSIZE);
 	} else
-		xen_io_tlb_nslabs[SWIOTLB_LO] = nr_tbl;
+		xen_io_tlb_nslabs[type] = nr_tbl;
 
-	return xen_io_tlb_nslabs[SWIOTLB_LO] << IO_TLB_SHIFT;
+	return xen_io_tlb_nslabs[type] << IO_TLB_SHIFT;
 }
 
 enum xen_swiotlb_err {
@@ -180,23 +190,24 @@ static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
 	}
 	return "";
 }
-int __ref xen_swiotlb_init(int verbose, bool early)
+
+static int xen_swiotlb_init_type(int verbose, bool early, enum swiotlb_t type)
 {
 	unsigned long bytes, order;
 	int rc = -ENOMEM;
 	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
 	unsigned int repeat = 3;
 
-	xen_io_tlb_nslabs[SWIOTLB_LO] = swiotlb_nr_tbl(SWIOTLB_LO);
+	xen_io_tlb_nslabs[type] = swiotlb_nr_tbl(type);
 retry:
-	bytes = xen_set_nslabs(xen_io_tlb_nslabs[SWIOTLB_LO]);
-	order = get_order(xen_io_tlb_nslabs[SWIOTLB_LO] << IO_TLB_SHIFT);
+	bytes = xen_set_nslabs(xen_io_tlb_nslabs[type], type);
+	order = get_order(xen_io_tlb_nslabs[type] << IO_TLB_SHIFT);
 
 	/*
 	 * IO TLB memory already allocated. Just use it.
 	 */
-	if (io_tlb_start[SWIOTLB_LO] != 0) {
-		xen_io_tlb_start[SWIOTLB_LO] = phys_to_virt(io_tlb_start[SWIOTLB_LO]);
+	if (io_tlb_start[type] != 0) {
+		xen_io_tlb_start[type] = phys_to_virt(io_tlb_start[type]);
 		goto end;
 	}
 
@@ -204,81 +215,95 @@ int __ref xen_swiotlb_init(int verbose, bool early)
 	 * Get IO TLB memory from any location.
 	 */
 	if (early) {
-		xen_io_tlb_start[SWIOTLB_LO] = memblock_alloc(PAGE_ALIGN(bytes),
+		xen_io_tlb_start[type] = memblock_alloc(PAGE_ALIGN(bytes),
 						  PAGE_SIZE);
-		if (!xen_io_tlb_start[SWIOTLB_LO])
+		if (!xen_io_tlb_start[type])
 			panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
 			      __func__, PAGE_ALIGN(bytes), PAGE_SIZE);
 	} else {
 #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
 #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
 		while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-			xen_io_tlb_start[SWIOTLB_LO] = (void *)xen_get_swiotlb_free_pages(order);
-			if (xen_io_tlb_start[SWIOTLB_LO])
+			xen_io_tlb_start[type] = (void *)xen_get_swiotlb_free_pages(order);
+			if (xen_io_tlb_start[type])
 				break;
 			order--;
 		}
 		if (order != get_order(bytes)) {
 			pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
 				(PAGE_SIZE << order) >> 20);
-			xen_io_tlb_nslabs[SWIOTLB_LO] = SLABS_PER_PAGE << order;
-			bytes = xen_io_tlb_nslabs[SWIOTLB_LO] << IO_TLB_SHIFT;
+			xen_io_tlb_nslabs[type] = SLABS_PER_PAGE << order;
+			bytes = xen_io_tlb_nslabs[type] << IO_TLB_SHIFT;
 		}
 	}
-	if (!xen_io_tlb_start[SWIOTLB_LO]) {
+	if (!xen_io_tlb_start[type]) {
 		m_ret = XEN_SWIOTLB_ENOMEM;
 		goto error;
 	}
 	/*
 	 * And replace that memory with pages under 4GB.
 	 */
-	rc = xen_swiotlb_fixup(xen_io_tlb_start[SWIOTLB_LO],
+	rc = xen_swiotlb_fixup(xen_io_tlb_start[type],
 			       bytes,
-			       xen_io_tlb_nslabs[SWIOTLB_LO]);
+			       xen_io_tlb_nslabs[type],
+			       type);
 	if (rc) {
 		if (early)
-			memblock_free(__pa(xen_io_tlb_start[SWIOTLB_LO]),
+			memblock_free(__pa(xen_io_tlb_start[type]),
 				      PAGE_ALIGN(bytes));
 		else {
-			free_pages((unsigned long)xen_io_tlb_start[SWIOTLB_LO], order);
-			xen_io_tlb_start[SWIOTLB_LO] = NULL;
+			free_pages((unsigned long)xen_io_tlb_start[type], order);
+			xen_io_tlb_start[type] = NULL;
 		}
 		m_ret = XEN_SWIOTLB_EFIXUP;
 		goto error;
 	}
 	if (early) {
-		if (swiotlb_init_with_tbl(xen_io_tlb_start[SWIOTLB_LO],
-					  xen_io_tlb_nslabs[SWIOTLB_LO],
-					  SWIOTLB_LO, verbose))
+		if (swiotlb_init_with_tbl(xen_io_tlb_start[type],
+					  xen_io_tlb_nslabs[type],
+					  type, verbose))
 			panic("Cannot allocate SWIOTLB buffer");
 		rc = 0;
 	} else
-		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start[SWIOTLB_LO],
-						xen_io_tlb_nslabs[SWIOTLB_LO],
-						SWIOTLB_LO);
+		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start[type],
+						xen_io_tlb_nslabs[type],
+						type);
 
 end:
-	xen_io_tlb_end[SWIOTLB_LO] = xen_io_tlb_start[SWIOTLB_LO] + bytes;
+	xen_io_tlb_end[type] = xen_io_tlb_start[type] + bytes;
 	if (!rc)
-		swiotlb_set_max_segment(PAGE_SIZE, SWIOTLB_LO);
+		swiotlb_set_max_segment(PAGE_SIZE, type);
 
 	return rc;
 error:
 	if (repeat--) {
-		xen_io_tlb_nslabs[SWIOTLB_LO] = max(1024UL, /* Min is 2MB */
-					(xen_io_tlb_nslabs[SWIOTLB_LO] >> 1));
+		xen_io_tlb_nslabs[type] = max(1024UL, /* Min is 2MB */
+					(xen_io_tlb_nslabs[type] >> 1));
 		pr_info("Lowering to %luMB\n",
-			(xen_io_tlb_nslabs[SWIOTLB_LO] << IO_TLB_SHIFT) >> 20);
+			(xen_io_tlb_nslabs[type] << IO_TLB_SHIFT) >> 20);
 		goto retry;
 	}
 	pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc);
 	if (early)
 		panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
 	else
-		free_pages((unsigned long)xen_io_tlb_start[SWIOTLB_LO], order);
+		free_pages((unsigned long)xen_io_tlb_start[type], order);
 	return rc;
 }
 
+int __ref xen_swiotlb_init(int verbose, bool early)
+{
+	int i, rc;
+
+	for (i = 0; i < swiotlb_nr; i++) {
+		rc = xen_swiotlb_init_type(verbose, early, i);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,
@@ -566,7 +591,13 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
 static int
 xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-	return xen_virt_to_bus(hwdev, xen_io_tlb_end[SWIOTLB_LO] - 1) <= mask;
+	int i;
+
+	for (i = 0; i < swiotlb_nr; i++)
+		if (xen_virt_to_bus(hwdev, xen_io_tlb_end[i] - 1) <= mask)
+			return true;
+
+	return false;
 }
 
 const struct dma_map_ops xen_swiotlb_dma_ops = {
-- 
2.17.1