Merge remote-tracking branch 'stefano/swiotlb-xen-9.1' into stable/for-linus-3.13

* stefano/swiotlb-xen-9.1:
  swiotlb-xen: fix error code returned by xen_swiotlb_map_sg_attrs
  swiotlb-xen: static inline xen_phys_to_bus, xen_bus_to_phys, xen_virt_to_bus and range_straddles_page_boundary
  grant-table: call set_phys_to_machine after mapping grant refs
  arm,arm64: do not always merge biovec if we are running on Xen
  swiotlb: print a warning when the swiotlb is full
  swiotlb-xen: use xen_dma_map/unmap_page, xen_dma_sync_single_for_cpu/device
  xen: introduce xen_dma_map/unmap_page and xen_dma_sync_single_for_cpu/device
  swiotlb-xen: use xen_alloc/free_coherent_pages
  xen: introduce xen_alloc/free_coherent_pages
  arm64/xen: get_dma_ops: return xen_dma_ops if we are running as xen_initial_domain
  arm/xen: get_dma_ops: return xen_dma_ops if we are running as xen_initial_domain
  swiotlb-xen: introduce xen_swiotlb_set_dma_mask
  xen/arm,arm64: enable SWIOTLB_XEN
  xen: make xen_create_contiguous_region return the dma address
  xen/x86: allow __set_phys_to_machine for autotranslate guests
  arm/xen,arm64/xen: introduce p2m
  arm64: define DMA_ERROR_CODE
  arm: make SWIOTLB available

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

Conflicts:
	arch/arm/include/asm/dma-mapping.h
	drivers/xen/swiotlb-xen.c

[Conflicts arose b/c "arm: make SWIOTLB available" v8 was in Stefano's
branch, while I had v9 + Ack from Russel. I also fixed up white-space
issues]

3 files changed, 106 insertions, 29 deletions

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 23eae5cb69c2..c794ea182140 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -140,7 +140,6 @@ config XEN_GRANT_DEV_ALLOC
 
 config SWIOTLB_XEN
         def_bool y
-        depends on PCI && X86
         select SWIOTLB
 
 config XEN_TMEM
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index c4d2298893b1..62ccf5424ba8 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -49,6 +49,7 @@
 #include <xen/grant_table.h>
 #include <xen/interface/memory.h>
 #include <xen/hvc-console.h>
+#include <xen/swiotlb-xen.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -898,8 +899,16 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
                         gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
                                                 &map_ops[i].status, __func__);
 
-        if (xen_feature(XENFEAT_auto_translated_physmap))
+        /* this is basically a nop on x86 */
+        if (xen_feature(XENFEAT_auto_translated_physmap)) {
+                for (i = 0; i < count; i++) {
+                        if (map_ops[i].status)
+                                continue;
+                        set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT,
+                                        map_ops[i].dev_bus_addr >> PAGE_SHIFT);
+                }
                 return ret;
+        }
 
         if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
                 arch_enter_lazy_mmu_mode();
@@ -942,8 +951,14 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
         if (ret)
                 return ret;
 
-        if (xen_feature(XENFEAT_auto_translated_physmap))
+        /* this is basically a nop on x86 */
+        if (xen_feature(XENFEAT_auto_translated_physmap)) {
+                for (i = 0; i < count; i++) {
+                        set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT,
+                                        INVALID_P2M_ENTRY);
+                }
                 return ret;
+        }
 
         if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
                 arch_enter_lazy_mmu_mode();
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 44af9d8577de..a224bc74b6b9 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -43,6 +43,9 @@
 #include <xen/xen-ops.h>
 #include <xen/hvc-console.h>
 
+#include <asm/dma-mapping.h>
+#include <asm/xen/page-coherent.h>
+
 #include <trace/events/swiotlb.h>
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
@@ -50,6 +53,20 @@
  * API.
  */
 
+#ifndef CONFIG_X86
+static unsigned long dma_alloc_coherent_mask(struct device *dev,
+                                            gfp_t gfp)
+{
+        unsigned long dma_mask = 0;
+
+        dma_mask = dev->coherent_dma_mask;
+        if (!dma_mask)
+                dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32);
+
+        return dma_mask;
+}
+#endif
+
 static char *xen_io_tlb_start, *xen_io_tlb_end;
 static unsigned long xen_io_tlb_nslabs;
 /*
@@ -58,17 +75,17 @@ static unsigned long xen_io_tlb_nslabs;
 
 static u64 start_dma_addr;
 
-static dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
+static inline dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
 {
         return phys_to_machine(XPADDR(paddr)).maddr;
 }
 
-static phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
+static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
 {
         return machine_to_phys(XMADDR(baddr)).paddr;
 }
 
-static dma_addr_t xen_virt_to_bus(void *address)
+static inline dma_addr_t xen_virt_to_bus(void *address)
 {
         return xen_phys_to_bus(virt_to_phys(address));
 }
@@ -91,7 +108,7 @@ static int check_pages_physically_contiguous(unsigned long pfn,
         return 1;
 }
 
-static int range_straddles_page_boundary(phys_addr_t p, size_t size)
+static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
 {
         unsigned long pfn = PFN_DOWN(p);
         unsigned int offset = p & ~PAGE_MASK;
@@ -128,6 +145,8 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 {
         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;
 
@@ -137,9 +156,9 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs)
 
                 do {
                         rc = xen_create_contiguous_region(
-                                (unsigned long)buf + (i << IO_TLB_SHIFT),
+                                p + (i << IO_TLB_SHIFT),
                                 get_order(slabs << IO_TLB_SHIFT),
-                                dma_bits);
+                                dma_bits, &dma_handle);
                 } while (rc && dma_bits++ < max_dma_bits);
                 if (rc)
                         return rc;
@@ -265,7 +284,6 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         void *ret;
         int order = get_order(size);
         u64 dma_mask = DMA_BIT_MASK(32);
-        unsigned long vstart;
         phys_addr_t phys;
         dma_addr_t dev_addr;
 
@@ -280,8 +298,12 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
                 return ret;
 
-        vstart = __get_free_pages(flags, order);
-        ret = (void *)vstart;
+        /* On ARM this function returns an ioremap'ped virtual address for
+         * which virt_to_phys doesn't return the corresponding physical
+         * address. In fact on ARM virt_to_phys only works for kernel direct
+         * mapped RAM memory. Also see comment below.
+         */
+        ret = xen_alloc_coherent_pages(hwdev, size, dma_handle, flags, attrs);
 
         if (!ret)
                 return ret;
@@ -289,18 +311,21 @@ xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         if (hwdev && hwdev->coherent_dma_mask)
                 dma_mask = dma_alloc_coherent_mask(hwdev, flags);
 
-        phys = virt_to_phys(ret);
+        /* At this point dma_handle is the physical address, next we are
+         * going to set it to the machine address.
+         * Do not use virt_to_phys(ret) because on ARM it doesn't correspond
+         * to *dma_handle. */
+        phys = *dma_handle;
         dev_addr = xen_phys_to_bus(phys);
         if (((dev_addr + size - 1 <= dma_mask)) &&
             !range_straddles_page_boundary(phys, size))
                 *dma_handle = dev_addr;
         else {
-                if (xen_create_contiguous_region(vstart, order,
-                                                 fls64(dma_mask)) != 0) {
-                        free_pages(vstart, order);
+                if (xen_create_contiguous_region(phys, order,
+                                                 fls64(dma_mask), dma_handle) != 0) {
+                        xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
                         return NULL;
                 }
-                *dma_handle = virt_to_machine(ret).maddr;
         }
         memset(ret, 0, size);
         return ret;
@@ -321,13 +346,15 @@ xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
         if (hwdev && hwdev->coherent_dma_mask)
                 dma_mask = hwdev->coherent_dma_mask;
 
-        phys = virt_to_phys(vaddr);
+        /* do not use virt_to_phys because on ARM it doesn't return you the
+         * physical address */
+        phys = xen_bus_to_phys(dev_addr);
 
         if (((dev_addr + size - 1 > dma_mask)) ||
             range_straddles_page_boundary(phys, size))
-                xen_destroy_contiguous_region((unsigned long)vaddr, order);
+                xen_destroy_contiguous_region(phys, order);
 
-        free_pages((unsigned long)vaddr, order);
+        xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
 
@@ -354,8 +381,13 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
          * buffering it.
          */
         if (dma_capable(dev, dev_addr, size) &&
-            !range_straddles_page_boundary(phys, size) && !swiotlb_force)
+            !range_straddles_page_boundary(phys, size) && !swiotlb_force) {
+                /* we are not interested in the dma_addr returned by
+                 * xen_dma_map_page, only in the potential cache flushes executed
+                 * by the function. */
+                xen_dma_map_page(dev, page, offset, size, dir, attrs);
                 return dev_addr;
+        }
 
         /*
          * Oh well, have to allocate and map a bounce buffer.
@@ -366,6 +398,8 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
         if (map == SWIOTLB_MAP_ERROR)
                 return DMA_ERROR_CODE;
 
+        xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
+                                        map & ~PAGE_MASK, size, dir, attrs);
         dev_addr = xen_phys_to_bus(map);
 
         /*
@@ -388,12 +422,15 @@ EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
  * whatever the device wrote there.
  */
 static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
-                             size_t size, enum dma_data_direction dir)
+                             size_t size, enum dma_data_direction dir,
+                                 struct dma_attrs *attrs)
 {
         phys_addr_t paddr = xen_bus_to_phys(dev_addr);
 
         BUG_ON(dir == DMA_NONE);
 
+        xen_dma_unmap_page(hwdev, paddr, size, dir, attrs);
+
         /* NOTE: We use dev_addr here, not paddr! */
         if (is_xen_swiotlb_buffer(dev_addr)) {
                 swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
@@ -416,7 +453,7 @@ void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
                             size_t size, enum dma_data_direction dir,
                             struct dma_attrs *attrs)
 {
-        xen_unmap_single(hwdev, dev_addr, size, dir);
+        xen_unmap_single(hwdev, dev_addr, size, dir, attrs);
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);
 
@@ -439,11 +476,15 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 
         BUG_ON(dir == DMA_NONE);
 
+        if (target == SYNC_FOR_CPU)
+                xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
+
         /* NOTE: We use dev_addr here, not paddr! */
-        if (is_xen_swiotlb_buffer(dev_addr)) {
+        if (is_xen_swiotlb_buffer(dev_addr))
                 swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
-                return;
-        }
+
+        if (target == SYNC_FOR_DEVICE)
+                xen_dma_sync_single_for_cpu(hwdev, paddr, size, dir);
 
         if (dir != DMA_FROM_DEVICE)
                 return;
@@ -506,16 +547,26 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
                                                                  sg->length,
                                                                  dir);
                         if (map == SWIOTLB_MAP_ERROR) {
+                                dev_warn(hwdev, "swiotlb buffer is full\n");
                                 /* Don't panic here, we expect map_sg users
                                    to do proper error handling. */
                                 xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
                                                            attrs);
                                 sg_dma_len(sgl) = 0;
-                                return DMA_ERROR_CODE;
+                                return 0;
                         }
                         sg->dma_address = xen_phys_to_bus(map);
-                } else
+                } else {
+                        /* we are not interested in the dma_addr returned by
+                         * xen_dma_map_page, only in the potential cache flushes executed
+                         * by the function. */
+                        xen_dma_map_page(hwdev, pfn_to_page(paddr >> PAGE_SHIFT),
+                                                paddr & ~PAGE_MASK,
+                                                sg->length,
+                                                dir,
+                                                attrs);
                         sg->dma_address = dev_addr;
+                }
                 sg_dma_len(sg) = sg->length;
         }
         return nelems;
@@ -537,7 +588,7 @@ xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
         BUG_ON(dir == DMA_NONE);
 
         for_each_sg(sgl, sg, nelems, i)
-                xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir);
+                xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs);
 
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
@@ -597,3 +648,15 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
         return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_dma_supported);
+
+int
+xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
+{
+        if (!dev->dma_mask || !xen_swiotlb_dma_supported(dev, dma_mask))
+                return -EIO;
+
+        *dev->dma_mask = dma_mask;
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);