OpenCloudOS-Kernel/drivers/xen/swiotlb-xen.c

689 lines
19 KiB
C
Raw Normal View History

/*
* Copyright 2010
* by Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
*
* This code provides a IOMMU for Xen PV guests with PCI passthrough.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License v2.0 as published by
* the Free Software Foundation
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* PV guests under Xen are running in an non-contiguous memory architecture.
*
* When PCI pass-through is utilized, this necessitates an IOMMU for
* translating bus (DMA) to virtual and vice-versa and also providing a
* mechanism to have contiguous pages for device drivers operations (say DMA
* operations).
*
* Specifically, under Xen the Linux idea of pages is an illusion. It
* assumes that pages start at zero and go up to the available memory. To
* help with that, the Linux Xen MMU provides a lookup mechanism to
* translate the page frame numbers (PFN) to machine frame numbers (MFN)
* and vice-versa. The MFN are the "real" frame numbers. Furthermore
* memory is not contiguous. Xen hypervisor stitches memory for guests
* from different pools, which means there is no guarantee that PFN==MFN
* and PFN+1==MFN+1. Lastly with Xen 4.0, pages (in debug mode) are
* allocated in descending order (high to low), meaning the guest might
* never get any MFN's under the 4GB mark.
*
*/
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
#include <linux/bootmem.h>
#include <linux/dma-mapping.h>
#include <linux/export.h>
#include <xen/swiotlb-xen.h>
#include <xen/page.h>
#include <xen/xen-ops.h>
#include <xen/hvc-console.h>
xen/arm,arm64: enable SWIOTLB_XEN Xen on arm and arm64 needs SWIOTLB_XEN: when running on Xen we need to program the hardware with mfns rather than pfns for dma addresses. Remove SWIOTLB_XEN dependency on X86 and PCI and make XEN select SWIOTLB_XEN on arm and arm64. At the moment always rely on swiotlb-xen, but when Xen starts supporting hardware IOMMUs we'll be able to avoid it conditionally on the presence of an IOMMU on the platform. Implement xen_create_contiguous_region on arm and arm64: for the moment we assume that dom0 has been mapped 1:1 (physical addresses == machine addresses) therefore we don't need to call XENMEM_exchange. Simply return the physical address as dma address. Initialize the xen-swiotlb from xen_early_init (before the native dma_ops are initialized), set xen_dma_ops to &xen_swiotlb_dma_ops. Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Changes in v8: - assume dom0 is mapped 1:1, no need to call XENMEM_exchange. Changes in v7: - call __set_phys_to_machine_multi from xen_create_contiguous_region and xen_destroy_contiguous_region to update the P2M; - don't call XENMEM_unpin, it has been removed; - call XENMEM_exchange instead of XENMEM_exchange_and_pin; - set nr_exchanged to 0 before calling the hypercall. Changes in v6: - introduce and export xen_dma_ops; - call xen_mm_init from as arch_initcall. Changes in v4: - remove redefinition of DMA_ERROR_CODE; - update the code to use XENMEM_exchange_and_pin and XENMEM_unpin; - add a note about hardware IOMMU in the commit message. Changes in v3: - code style changes; - warn on XENMEM_put_dma_buf failures.
2013-10-10 21:40:44 +08:00
#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
* swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
* API.
*/
xen/arm,arm64: enable SWIOTLB_XEN Xen on arm and arm64 needs SWIOTLB_XEN: when running on Xen we need to program the hardware with mfns rather than pfns for dma addresses. Remove SWIOTLB_XEN dependency on X86 and PCI and make XEN select SWIOTLB_XEN on arm and arm64. At the moment always rely on swiotlb-xen, but when Xen starts supporting hardware IOMMUs we'll be able to avoid it conditionally on the presence of an IOMMU on the platform. Implement xen_create_contiguous_region on arm and arm64: for the moment we assume that dom0 has been mapped 1:1 (physical addresses == machine addresses) therefore we don't need to call XENMEM_exchange. Simply return the physical address as dma address. Initialize the xen-swiotlb from xen_early_init (before the native dma_ops are initialized), set xen_dma_ops to &xen_swiotlb_dma_ops. Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Changes in v8: - assume dom0 is mapped 1:1, no need to call XENMEM_exchange. Changes in v7: - call __set_phys_to_machine_multi from xen_create_contiguous_region and xen_destroy_contiguous_region to update the P2M; - don't call XENMEM_unpin, it has been removed; - call XENMEM_exchange instead of XENMEM_exchange_and_pin; - set nr_exchanged to 0 before calling the hypercall. Changes in v6: - introduce and export xen_dma_ops; - call xen_mm_init from as arch_initcall. Changes in v4: - remove redefinition of DMA_ERROR_CODE; - update the code to use XENMEM_exchange_and_pin and XENMEM_unpin; - add a note about hardware IOMMU in the commit message. Changes in v3: - code style changes; - warn on XENMEM_put_dma_buf failures.
2013-10-10 21:40:44 +08:00
#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;
/*
* Quick lookup value of the bus address of the IOTLB.
*/
static u64 start_dma_addr;
/*
* Both of these functions should avoid PFN_PHYS because phys_addr_t
* can be 32bit when dma_addr_t is 64bit leading to a loss in
* information if the shift is done before casting to 64bit.
*/
static inline dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
{
unsigned long mfn = pfn_to_mfn(PFN_DOWN(paddr));
dma_addr_t dma = (dma_addr_t)mfn << PAGE_SHIFT;
dma |= paddr & ~PAGE_MASK;
return dma;
}
static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
{
unsigned long pfn = mfn_to_pfn(PFN_DOWN(baddr));
dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT;
phys_addr_t paddr = dma;
paddr |= baddr & ~PAGE_MASK;
return paddr;
}
static inline dma_addr_t xen_virt_to_bus(void *address)
{
return xen_phys_to_bus(virt_to_phys(address));
}
static int check_pages_physically_contiguous(unsigned long pfn,
unsigned int offset,
size_t length)
{
unsigned long next_mfn;
int i;
int nr_pages;
next_mfn = pfn_to_mfn(pfn);
nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT;
for (i = 1; i < nr_pages; i++) {
if (pfn_to_mfn(++pfn) != ++next_mfn)
return 0;
}
return 1;
}
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;
if (offset + size <= PAGE_SIZE)
return 0;
if (check_pages_physically_contiguous(pfn, offset, size))
return 0;
return 1;
}
static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
{
unsigned long mfn = PFN_DOWN(dma_addr);
unsigned long pfn = mfn_to_local_pfn(mfn);
phys_addr_t paddr;
/* 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)) {
paddr = PFN_PHYS(pfn);
return paddr >= virt_to_phys(xen_io_tlb_start) &&
paddr < virt_to_phys(xen_io_tlb_end);
}
return 0;
}
static int max_dma_bits = 32;
static int
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;
i = 0;
do {
int slabs = min(nslabs - i, (unsigned long)IO_TLB_SEGSIZE);
do {
rc = xen_create_contiguous_region(
p + (i << IO_TLB_SHIFT),
get_order(slabs << IO_TLB_SHIFT),
dma_bits, &dma_handle);
} while (rc && dma_bits++ < max_dma_bits);
if (rc)
return rc;
i += slabs;
} 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
};
static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
{
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;
enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
unsigned int repeat = 3;
xen_io_tlb_nslabs = swiotlb_nr_tbl();
retry:
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.
*/
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 *)xen_get_swiotlb_free_pages(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_ret = XEN_SWIOTLB_ENOMEM;
goto error;
}
xen_io_tlb_end = xen_io_tlb_start + bytes;
/*
* And replace that memory with pages under 4GB.
*/
rc = xen_swiotlb_fixup(xen_io_tlb_start,
bytes,
xen_io_tlb_nslabs);
if (rc) {
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);
if (early) {
x86: Don't panic if can not alloc buffer for swiotlb Normal boot path on system with iommu support: swiotlb buffer will be allocated early at first and then try to initialize iommu, if iommu for intel or AMD could setup properly, swiotlb buffer will be freed. The early allocating is with bootmem, and could panic when we try to use kdump with buffer above 4G only, or with memmap to limit mem under 4G. for example: memmap=4095M$1M to remove memory under 4G. According to Eric, add _nopanic version and no_iotlb_memory to fail map single later if swiotlb is still needed. -v2: don't pass nopanic, and use -ENOMEM return value according to Eric. panic early instead of using swiotlb_full to panic...according to Eric/Konrad. -v3: make swiotlb_init to be notpanic, but will affect: arm64, ia64, powerpc, tile, unicore32, x86. -v4: cleanup swiotlb_init by removing swiotlb_init_with_default_size. Suggested-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-36-git-send-email-yinghai@kernel.org Reviewed-and-tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Joerg Roedel <joro@8bytes.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Andrzej Pietrasiewicz <andrzej.p@samsung.com> Cc: linux-mips@linux-mips.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: Shuah Khan <shuahkhan@gmail.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 04:20:16 +08:00
if (swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs,
verbose))
panic("Cannot allocate SWIOTLB buffer");
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 */
(xen_io_tlb_nslabs >> 1));
pr_info("Lowering to %luMB\n",
(xen_io_tlb_nslabs << 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);
return rc;
}
void *
xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags,
struct dma_attrs *attrs)
{
void *ret;
int order = get_order(size);
u64 dma_mask = DMA_BIT_MASK(32);
phys_addr_t phys;
dma_addr_t dev_addr;
/*
* Ignore region specifiers - the kernel's ideas of
* pseudo-phys memory layout has nothing to do with the
* machine physical layout. We can't allocate highmem
* because we can't return a pointer to it.
*/
flags &= ~(__GFP_DMA | __GFP_HIGHMEM);
if (dma_alloc_from_coherent(hwdev, size, dma_handle, &ret))
return ret;
/* 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;
if (hwdev && hwdev->coherent_dma_mask)
xen: Use correct masking in xen_swiotlb_alloc_coherent. When running 32-bit pvops-dom0 and a driver tries to allocate a coherent DMA-memory the xen swiotlb-implementation returned memory beyond 4GB. The underlaying reason is that if the supplied driver passes in a DMA_BIT_MASK(64) ( hwdev->coherent_dma_mask is set to 0xffffffffffffffff) our dma_mask will be u64 set to 0xffffffffffffffff even if we set it to DMA_BIT_MASK(32) previously. Meaning we do not reset the upper bits. By using the dma_alloc_coherent_mask function - it does the proper casting and we get 0xfffffffff. This caused not working sound on a system with 4 GB and a 64-bit compatible sound-card with sets the DMA-mask to 64bit. On bare-metal and the forward-ported xen-dom0 patches from OpenSuse a coherent DMA-memory is always allocated inside the 32-bit address-range by calling dma_alloc_coherent_mask. This patch adds the same functionality to xen swiotlb and is a rebase of the original patch from Ronny Hegewald which never got upstream b/c the underlaying reason was not understood until now. The original email with the original patch is in: http://old-list-archives.xen.org/archives/html/xen-devel/2010-02/msg00038.html the original thread from where the discussion started is in: http://old-list-archives.xen.org/archives/html/xen-devel/2010-01/msg00928.html Signed-off-by: Ronny Hegewald <ronny.hegewald@online.de> Signed-off-by: Stefano Panella <stefano.panella@citrix.com> Acked-By: David Vrabel <david.vrabel@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> CC: stable@vger.kernel.org
2012-08-31 17:57:52 +08:00
dma_mask = dma_alloc_coherent_mask(hwdev, flags);
/* 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(phys, order,
fls64(dma_mask), dma_handle) != 0) {
xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
return NULL;
}
}
memset(ret, 0, size);
return ret;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_alloc_coherent);
void
xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
dma_addr_t dev_addr, struct dma_attrs *attrs)
{
int order = get_order(size);
phys_addr_t phys;
u64 dma_mask = DMA_BIT_MASK(32);
if (dma_release_from_coherent(hwdev, order, vaddr))
return;
if (hwdev && hwdev->coherent_dma_mask)
dma_mask = hwdev->coherent_dma_mask;
/* 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(phys, order);
xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_free_coherent);
/*
* Map a single buffer of the indicated size for DMA in streaming mode. The
* physical address to use is returned.
*
* Once the device is given the dma address, the device owns this memory until
* either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
*/
dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
unsigned long offset, size_t size,
enum dma_data_direction dir,
struct dma_attrs *attrs)
{
phys_addr_t map, phys = page_to_phys(page) + offset;
dma_addr_t dev_addr = xen_phys_to_bus(phys);
BUG_ON(dir == DMA_NONE);
/*
* If the address happens to be in the device's DMA window,
* we can safely return the device addr and not worry about bounce
* buffering it.
*/
if (dma_capable(dev, dev_addr, size) &&
!range_straddles_page_boundary(phys, size) &&
!xen_arch_need_swiotlb(dev, PFN_DOWN(phys), PFN_DOWN(dev_addr)) &&
!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, dev_addr, offset, size, dir, attrs);
return dev_addr;
}
/*
* Oh well, have to allocate and map a bounce buffer.
*/
trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
if (map == SWIOTLB_MAP_ERROR)
return DMA_ERROR_CODE;
xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
dev_addr, map & ~PAGE_MASK, size, dir, attrs);
dev_addr = xen_phys_to_bus(map);
/*
* Ensure that the address returned is DMA'ble
*/
if (!dma_capable(dev, dev_addr, size)) {
swiotlb_tbl_unmap_single(dev, map, size, dir);
dev_addr = 0;
}
return dev_addr;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
/*
* Unmap a single streaming mode DMA translation. The dma_addr and size must
* match what was provided for in a previous xen_swiotlb_map_page call. All
* other usages are undefined.
*
* After this call, reads by the cpu to the buffer are guaranteed to see
* 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,
struct dma_attrs *attrs)
{
phys_addr_t paddr = xen_bus_to_phys(dev_addr);
BUG_ON(dir == DMA_NONE);
xen_dma_unmap_page(hwdev, dev_addr, 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);
return;
}
if (dir != DMA_FROM_DEVICE)
return;
/*
* phys_to_virt doesn't work with hihgmem page but we could
* call dma_mark_clean() with hihgmem page here. However, we
* are fine since dma_mark_clean() is null on POWERPC. We can
* make dma_mark_clean() take a physical address if necessary.
*/
dma_mark_clean(phys_to_virt(paddr), size);
}
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, attrs);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_page);
/*
* Make physical memory consistent for a single streaming mode DMA translation
* after a transfer.
*
* If you perform a xen_swiotlb_map_page() but wish to interrogate the buffer
* using the cpu, yet do not wish to teardown the dma mapping, you must
* call this function before doing so. At the next point you give the dma
* address back to the card, you must first perform a
* xen_swiotlb_dma_sync_for_device, and then the device again owns the buffer
*/
static void
xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
size_t size, enum dma_data_direction dir,
enum dma_sync_target target)
{
phys_addr_t paddr = xen_bus_to_phys(dev_addr);
BUG_ON(dir == DMA_NONE);
if (target == SYNC_FOR_CPU)
xen_dma_sync_single_for_cpu(hwdev, dev_addr, size, dir);
/* NOTE: We use dev_addr here, not paddr! */
if (is_xen_swiotlb_buffer(dev_addr))
swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
if (target == SYNC_FOR_DEVICE)
xen_dma_sync_single_for_device(hwdev, dev_addr, size, dir);
if (dir != DMA_FROM_DEVICE)
return;
dma_mark_clean(phys_to_virt(paddr), size);
}
void
xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
size_t size, enum dma_data_direction dir)
{
xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_cpu);
void
xen_swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
size_t size, enum dma_data_direction dir)
{
xen_swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_sync_single_for_device);
/*
* Map a set of buffers described by scatterlist in streaming mode for DMA.
* This is the scatter-gather version of the above xen_swiotlb_map_page
* interface. Here the scatter gather list elements are each tagged with the
* appropriate dma address and length. They are obtained via
* sg_dma_{address,length}(SG).
*
* NOTE: An implementation may be able to use a smaller number of
* DMA address/length pairs than there are SG table elements.
* (for example via virtual mapping capabilities)
* The routine returns the number of addr/length pairs actually
* used, at most nents.
*
* Device ownership issues as mentioned above for xen_swiotlb_map_page are the
* same here.
*/
int
xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
int nelems, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
struct scatterlist *sg;
int i;
BUG_ON(dir == DMA_NONE);
for_each_sg(sgl, sg, nelems, i) {
phys_addr_t paddr = sg_phys(sg);
dma_addr_t dev_addr = xen_phys_to_bus(paddr);
if (swiotlb_force ||
xen_arch_need_swiotlb(hwdev, PFN_DOWN(paddr), PFN_DOWN(dev_addr)) ||
!dma_capable(hwdev, dev_addr, sg->length) ||
range_straddles_page_boundary(paddr, sg->length)) {
phys_addr_t map = swiotlb_tbl_map_single(hwdev,
start_dma_addr,
sg_phys(sg),
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 0;
}
xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT),
dev_addr,
map & ~PAGE_MASK,
sg->length,
dir,
attrs);
sg->dma_address = xen_phys_to_bus(map);
} 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),
dev_addr,
paddr & ~PAGE_MASK,
sg->length,
dir,
attrs);
sg->dma_address = dev_addr;
}
sg_dma_len(sg) = sg->length;
}
return nelems;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_map_sg_attrs);
/*
* Unmap a set of streaming mode DMA translations. Again, cpu read rules
* concerning calls here are the same as for swiotlb_unmap_page() above.
*/
void
xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
int nelems, enum dma_data_direction dir,
struct dma_attrs *attrs)
{
struct scatterlist *sg;
int i;
BUG_ON(dir == DMA_NONE);
for_each_sg(sgl, sg, nelems, i)
xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_unmap_sg_attrs);
/*
* Make physical memory consistent for a set of streaming mode DMA translations
* after a transfer.
*
* The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
* and usage.
*/
static void
xen_swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
int nelems, enum dma_data_direction dir,
enum dma_sync_target target)
{
struct scatterlist *sg;
int i;
for_each_sg(sgl, sg, nelems, i)
xen_swiotlb_sync_single(hwdev, sg->dma_address,
sg_dma_len(sg), dir, target);
}
void
xen_swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
int nelems, enum dma_data_direction dir)
{
xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_cpu);
void
xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
int nelems, enum dma_data_direction dir)
{
xen_swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
}
EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);
int
xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
{
return !dma_addr;
}
EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mapping_error);
/*
* Return whether the given device DMA address mask can be supported
* properly. For example, if your device can only drive the low 24-bits
* during bus mastering, then you would pass 0x00ffffff as the mask to
* this function.
*/
int
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);