Nouveau - Feb 2021 - [PATCH RFC v1 5/6] xen-swiotlb: convert variables to arrays

This patch converts several xen-swiotlb related variables to arrays, in
order to maintain stat/status for different swiotlb buffers. Here are
variables involved:

- xen_io_tlb_start and xen_io_tlb_end
- xen_io_tlb_nslabs
- MAX_DMA_BITS

There is no functional change and this is to prepare to enable 64-bit
xen-swiotlb.

Cc: Joe Jin <joe.jin at oracle.com>
Signed-off-by: Dongli Zhang <dongli.zhang at oracle.com>
---
 drivers/xen/swiotlb-xen.c | 75 +++++++++++++++++++++------------------
 1 file changed, 40 insertions(+), 35 deletions(-)

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 662638093542..e18cae693cdc 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -39,15 +39,17 @@
 #include <asm/xen/page-coherent.h>
 
 #include <trace/events/swiotlb.h>
-#define MAX_DMA_BITS 32
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
  * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by
this
  * API.
  */
 
-static char *xen_io_tlb_start, *xen_io_tlb_end;
-static unsigned long xen_io_tlb_nslabs;
+static char *xen_io_tlb_start[SWIOTLB_MAX], *xen_io_tlb_end[SWIOTLB_MAX];
+static unsigned long xen_io_tlb_nslabs[SWIOTLB_MAX];
+
+static int max_dma_bits[] = {32, 64};
+
 /*
  * Quick lookup value of the bus address of the IOTLB.
  */
@@ -112,8 +114,8 @@ static int is_xen_swiotlb_buffer(struct device *dev,
dma_addr_t dma_addr)
 	 * 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) &&
-		       paddr < virt_to_phys(xen_io_tlb_end);
+		return paddr >= virt_to_phys(xen_io_tlb_start[SWIOTLB_LO]) &&
+		       paddr < virt_to_phys(xen_io_tlb_end[SWIOTLB_LO]);
 	}
 	return 0;
 }
@@ -137,7 +139,7 @@ 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);
+		} while (rc && dma_bits++ < max_dma_bits[SWIOTLB_LO]);
 		if (rc)
 			return rc;
 
@@ -148,12 +150,13 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long
nslabs)
 static unsigned long xen_set_nslabs(unsigned long nr_tbl)
 {
 	if (!nr_tbl) {
-		xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
-		xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
+		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],
+						      IO_TLB_SEGSIZE);
 	} else
-		xen_io_tlb_nslabs = nr_tbl;
+		xen_io_tlb_nslabs[SWIOTLB_LO] = nr_tbl;
 
-	return xen_io_tlb_nslabs << IO_TLB_SHIFT;
+	return xen_io_tlb_nslabs[SWIOTLB_LO] << IO_TLB_SHIFT;
 }
 
 enum xen_swiotlb_err {
@@ -184,16 +187,16 @@ int __ref xen_swiotlb_init(int verbose, bool early)
 	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
 	unsigned int repeat = 3;
 
-	xen_io_tlb_nslabs = swiotlb_nr_tbl(SWIOTLB_LO);
+	xen_io_tlb_nslabs[SWIOTLB_LO] = swiotlb_nr_tbl(SWIOTLB_LO);
 retry:
-	bytes = xen_set_nslabs(xen_io_tlb_nslabs);
-	order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
+	bytes = xen_set_nslabs(xen_io_tlb_nslabs[SWIOTLB_LO]);
+	order = get_order(xen_io_tlb_nslabs[SWIOTLB_LO] << IO_TLB_SHIFT);
 
 	/*
 	 * IO TLB memory already allocated. Just use it.
 	 */
 	if (io_tlb_start[SWIOTLB_LO] != 0) {
-		xen_io_tlb_start = phys_to_virt(io_tlb_start[SWIOTLB_LO]);
+		xen_io_tlb_start[SWIOTLB_LO] = phys_to_virt(io_tlb_start[SWIOTLB_LO]);
 		goto end;
 	}
 
@@ -201,76 +204,78 @@ int __ref xen_swiotlb_init(int verbose, bool early)
 	 * Get IO TLB memory from any location.
 	 */
 	if (early) {
-		xen_io_tlb_start = memblock_alloc(PAGE_ALIGN(bytes),
+		xen_io_tlb_start[SWIOTLB_LO] = memblock_alloc(PAGE_ALIGN(bytes),
 						  PAGE_SIZE);
-		if (!xen_io_tlb_start)
+		if (!xen_io_tlb_start[SWIOTLB_LO])
 			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 = (void *)xen_get_swiotlb_free_pages(order);
-			if (xen_io_tlb_start)
+			xen_io_tlb_start[SWIOTLB_LO] = (void *)xen_get_swiotlb_free_pages(order);
+			if (xen_io_tlb_start[SWIOTLB_LO])
 				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 = SLABS_PER_PAGE << order;
-			bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+			xen_io_tlb_nslabs[SWIOTLB_LO] = SLABS_PER_PAGE << order;
+			bytes = xen_io_tlb_nslabs[SWIOTLB_LO] << IO_TLB_SHIFT;
 		}
 	}
-	if (!xen_io_tlb_start) {
+	if (!xen_io_tlb_start[SWIOTLB_LO]) {
 		m_ret = XEN_SWIOTLB_ENOMEM;
 		goto error;
 	}
 	/*
 	 * And replace that memory with pages under 4GB.
 	 */
-	rc = xen_swiotlb_fixup(xen_io_tlb_start,
+	rc = xen_swiotlb_fixup(xen_io_tlb_start[SWIOTLB_LO],
 			       bytes,
-			       xen_io_tlb_nslabs);
+			       xen_io_tlb_nslabs[SWIOTLB_LO]);
 	if (rc) {
 		if (early)
-			memblock_free(__pa(xen_io_tlb_start),
+			memblock_free(__pa(xen_io_tlb_start[SWIOTLB_LO]),
 				      PAGE_ALIGN(bytes));
 		else {
-			free_pages((unsigned long)xen_io_tlb_start, order);
-			xen_io_tlb_start = NULL;
+			free_pages((unsigned long)xen_io_tlb_start[SWIOTLB_LO], order);
+			xen_io_tlb_start[SWIOTLB_LO] = NULL;
 		}
 		m_ret = XEN_SWIOTLB_EFIXUP;
 		goto error;
 	}
 	if (early) {
-		if (swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs,
+		if (swiotlb_init_with_tbl(xen_io_tlb_start[SWIOTLB_LO],
+					  xen_io_tlb_nslabs[SWIOTLB_LO],
 					  SWIOTLB_LO, verbose))
 			panic("Cannot allocate SWIOTLB buffer");
 		rc = 0;
 	} else
-		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start,
-						xen_io_tlb_nslabs, SWIOTLB_LO);
+		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start[SWIOTLB_LO],
+						xen_io_tlb_nslabs[SWIOTLB_LO],
+						SWIOTLB_LO);
 
 end:
-	xen_io_tlb_end = xen_io_tlb_start + bytes;
+	xen_io_tlb_end[SWIOTLB_LO] = xen_io_tlb_start[SWIOTLB_LO] + bytes;
 	if (!rc)
 		swiotlb_set_max_segment(PAGE_SIZE, SWIOTLB_LO);
 
 	return rc;
 error:
 	if (repeat--) {
-		xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
-					(xen_io_tlb_nslabs >> 1));
+		xen_io_tlb_nslabs[SWIOTLB_LO] = max(1024UL, /* Min is 2MB */
+					(xen_io_tlb_nslabs[SWIOTLB_LO] >> 1));
 		pr_info("Lowering to %luMB\n",
-			(xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
+			(xen_io_tlb_nslabs[SWIOTLB_LO] << 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, order);
+		free_pages((unsigned long)xen_io_tlb_start[SWIOTLB_LO], order);
 	return rc;
 }
 
@@ -561,7 +566,7 @@ 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 - 1) <= mask;
+	return xen_virt_to_bus(hwdev, xen_io_tlb_end[SWIOTLB_LO] - 1) <= mask;
 }
 
 const struct dma_map_ops xen_swiotlb_dma_ops = {
-- 
2.17.1

So one thing that has been on my mind for a while:  I'd really like
to kill the separate dma ops in Xen swiotlb.  If we compare xen-swiotlb
to swiotlb the main difference seems to be:

 - additional reasons to bounce I/O vs the plain DMA capable
 - the possibility to do a hypercall on arm/arm64
 - an extra translation layer before doing the phys_to_dma and vice
   versa
 - an special memory allocator

I wonder if inbetween a few jump labels or other no overhead enablement
options and possibly better use of the dma_range_map we could kill
off most of swiotlb-xen instead of maintaining all this code duplication?