Merge branch 'stable/late-swiotlb.v3.3' into stable/for-linus-3.7

* stable/late-swiotlb.v3.3:
  xen/swiotlb: Fix compile warnings when using plain integer instead of NULL pointer.
  xen/swiotlb: Remove functions not needed anymore.
  xen/pcifront: Use Xen-SWIOTLB when initting if required.
  xen/swiotlb: For early initialization, return zero on success.
  xen/swiotlb: Use the swiotlb_late_init_with_tbl to init Xen-SWIOTLB late when PV PCI is used.
  xen/swiotlb: Move the error strings to its own function.
  xen/swiotlb: Move the nr_tbl determination in its own function.
  swiotlb: add the late swiotlb initialization function with iotlb memory
  xen/swiotlb: With more than 4GB on 64-bit, disable the native SWIOTLB.
  xen/swiotlb: Simplify the logic.

Conflicts:
	arch/x86/xen/pci-swiotlb-xen.c

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

1 files changed, 75 insertions, 26 deletions

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 2e74dba6a04d..58db6df866ef 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -144,31 +144,72 @@ 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)
+{
+	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);
+	} else
+		xen_io_tlb_nslabs = nr_tbl;
+
+	return xen_io_tlb_nslabs << IO_TLB_SHIFT;
+}
+
+enum xen_swiotlb_err {
+	XEN_SWIOTLB_UNKNOWN = 0,
+	XEN_SWIOTLB_ENOMEM,
+	XEN_SWIOTLB_EFIXUP
+};
 
-void __init xen_swiotlb_init(int verbose)
+static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
 {
-	unsigned long bytes;
+	switch (err) {
+	case XEN_SWIOTLB_ENOMEM:
+		return "Cannot allocate Xen-SWIOTLB buffer\n";
+	case XEN_SWIOTLB_EFIXUP:
+		return "Failed to get contiguous memory for DMA from Xen!\n"\
+		    "You either: don't have the permissions, do not have"\
+		    " enough free memory under 4GB, or the hypervisor memory"\
+		    " is too fragmented!";
+	default:
+		break;
+	}
+	return "";
+}
+int __ref xen_swiotlb_init(int verbose, bool early)
+{
+	unsigned long bytes, order;
 	int rc = -ENOMEM;
-	unsigned long nr_tbl;
-	char *m = NULL;
+	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
 	unsigned int repeat = 3;
 
-	nr_tbl = swiotlb_nr_tbl();
-	if (nr_tbl)
-		xen_io_tlb_nslabs = nr_tbl;
-	else {
-		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_nr_tbl();
 retry:
-	bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
-
+	bytes = xen_set_nslabs(xen_io_tlb_nslabs);
+	order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
 	/*
 	 * Get IO TLB memory from any location.
 	 */
-	xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	if (early)
+		xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	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 *)__get_free_pages(__GFP_NOWARN, order);
+			if (xen_io_tlb_start)
+				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;
+		}
+	}
 	if (!xen_io_tlb_start) {
-		m = "Cannot allocate Xen-SWIOTLB buffer!\n";
+		m_ret = XEN_SWIOTLB_ENOMEM;
 		goto error;
 	}
 	xen_io_tlb_end = xen_io_tlb_start + bytes;
@@ -179,17 +220,22 @@ retry:
 			       bytes,
 			       xen_io_tlb_nslabs);
 	if (rc) {
-		free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
-		m = "Failed to get contiguous memory for DMA from Xen!\n"\
-		    "You either: don't have the permissions, do not have"\
-		    " enough free memory under 4GB, or the hypervisor memory"\
-		    "is too fragmented!";
+		if (early)
+			free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
+		else {
+			free_pages((unsigned long)xen_io_tlb_start, order);
+			xen_io_tlb_start = NULL;
+		}
+		m_ret = XEN_SWIOTLB_EFIXUP;
 		goto error;
 	}
 	start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
-	swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
-
-	return;
+	if (early) {
+		swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+		rc = 0;
+	} else
+		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
+	return rc;
 error:
 	if (repeat--) {
 		xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
@@ -198,10 +244,13 @@ error:
 		      (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
 		goto retry;
 	}
-	xen_raw_printk("%s (rc:%d)", m, rc);
-	panic("%s (rc:%d)", m, rc);
+	pr_err("%s (rc:%d)", 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);
+	return rc;
 }
-
 void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,