Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-23 04:31:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

arm64/xen: fix xen-swiotlb cache flushing

Browse Source 
Xen-swiotlb hooks into the arm/arm64 arch code through a copy of the DMA
DMA mapping operations stored in the struct device arch data.

Switching arm64 to use the direct calls for the merged DMA direct /
swiotlb code broke this scheme.  Replace the indirect calls with
direct-calls in xen-swiotlb as well to fix this problem.

Fixes: 356da6d0cd ("dma-mapping: bypass indirect calls for dma-direct")
Reported-by: Julien Grall <julien.grall@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
This commit is contained in:
Christoph Hellwig 2019-01-16 19:01:48 +01:00
parent 333478a7eb
commit 60d8cd572f
6 changed files with 176 additions and 102 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

94
arch/arm/include/asm/xen/page-coherent.h
View File

@ -1 +1,95 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
#define _ASM_ARM_XEN_PAGE_COHERENT_H
#include <linux/dma-mapping.h>
#include <asm/page.h>
#include <xen/arm/page-coherent.h>
static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
{
if (dev && dev->archdata.dev_dma_ops)
return dev->archdata.dev_dma_ops;
return get_arch_dma_ops(NULL);
}
static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
{
return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
}
static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
{
xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
}
static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
dma_addr_t dev_addr, unsigned long offset, size_t size,
enum dma_data_direction dir, unsigned long attrs)
{
unsigned long page_pfn = page_to_xen_pfn(page);
unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
unsigned long compound_pages =
(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
bool local = (page_pfn <= dev_pfn) &&
(dev_pfn - page_pfn < compound_pages);
/*
* Dom0 is mapped 1:1, while the Linux page can span across
* multiple Xen pages, it's not possible for it to contain a
* mix of local and foreign Xen pages. So if the first xen_pfn
* == mfn the page is local otherwise it's a foreign page
* grant-mapped in dom0. If the page is local we can safely
* call the native dma_ops function, otherwise we call the xen
* specific function.
*/
if (local)
xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
else
__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
}
static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
unsigned long pfn = PFN_DOWN(handle);
/*
* Dom0 is mapped 1:1, while the Linux page can be spanned accross
* multiple Xen page, it's not possible to have a mix of local and
* foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
* foreign mfn will always return false. If the page is local we can
* safely call the native dma_ops function, otherwise we call the xen
* specific function.
*/
if (pfn_valid(pfn)) {
if (xen_get_dma_ops(hwdev)->unmap_page)
xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
} else
__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
}
static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
unsigned long pfn = PFN_DOWN(handle);
if (pfn_valid(pfn)) {
if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
} else
__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
}
static inline void xen_dma_sync_single_for_device(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
unsigned long pfn = PFN_DOWN(handle);
if (pfn_valid(pfn)) {
if (xen_get_dma_ops(hwdev)->sync_single_for_device)
xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
} else
__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
}
#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */

3
arch/arm64/include/asm/device.h
View File

@ -20,9 +20,6 @@ struct dev_archdata {
#ifdef CONFIG_IOMMU_API
void *iommu; /* private IOMMU data */
#endif
#ifdef CONFIG_XEN
const struct dma_map_ops *dev_dma_ops;
#endif
};
struct pdev_archdata {

76
arch/arm64/include/asm/xen/page-coherent.h
View File

@ -1 +1,77 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H
#define _ASM_ARM64_XEN_PAGE_COHERENT_H
#include <linux/dma-mapping.h>
#include <asm/page.h>
#include <xen/arm/page-coherent.h>
static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
{
return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
}
static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
{
dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
}
static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
unsigned long pfn = PFN_DOWN(handle);
if (pfn_valid(pfn))
dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
else
__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
}
static inline void xen_dma_sync_single_for_device(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
unsigned long pfn = PFN_DOWN(handle);
if (pfn_valid(pfn))
dma_direct_sync_single_for_device(hwdev, handle, size, dir);
else
__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
}
static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
dma_addr_t dev_addr, unsigned long offset, size_t size,
enum dma_data_direction dir, unsigned long attrs)
{
unsigned long page_pfn = page_to_xen_pfn(page);
unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
unsigned long compound_pages =
(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
bool local = (page_pfn <= dev_pfn) &&
(dev_pfn - page_pfn < compound_pages);
if (local)
dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
else
__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
}
static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
unsigned long pfn = PFN_DOWN(handle);
/*
* Dom0 is mapped 1:1, while the Linux page can be spanned accross
* multiple Xen page, it's not possible to have a mix of local and
* foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
* foreign mfn will always return false. If the page is local we can
* safely call the native dma_ops function, otherwise we call the xen
* specific function.
*/
if (pfn_valid(pfn))
dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
else
__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
}
#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */

4
arch/arm64/mm/dma-mapping.c
View File

@ -466,9 +466,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
__iommu_setup_dma_ops(dev, dma_base, size, iommu);
#ifdef CONFIG_XEN
if (xen_initial_domain()) {
dev->archdata.dev_dma_ops = dev->dma_ops;
if (xen_initial_domain())
dev->dma_ops = xen_dma_ops;
}
#endif
}

4
drivers/xen/swiotlb-xen.c
View File

@ -645,7 +645,7 @@ xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size,
unsigned long attrs)
{
#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
#ifdef CONFIG_ARM
if (xen_get_dma_ops(dev)->mmap)
return xen_get_dma_ops(dev)->mmap(dev, vma, cpu_addr,
dma_addr, size, attrs);
@ -662,7 +662,7 @@ xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t handle, size_t size,
unsigned long attrs)
{
#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
#ifdef CONFIG_ARM
if (xen_get_dma_ops(dev)->get_sgtable) {
#if 0
/*

97
include/xen/arm/page-coherent.h
View File

@ -1,17 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
#define _ASM_ARM_XEN_PAGE_COHERENT_H
#include <asm/page.h>
#include <asm/dma-mapping.h>
#include <linux/dma-mapping.h>
static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
{
if (dev && dev->archdata.dev_dma_ops)
return dev->archdata.dev_dma_ops;
return get_arch_dma_ops(NULL);
}
#ifndef _XEN_ARM_PAGE_COHERENT_H
#define _XEN_ARM_PAGE_COHERENT_H
void __xen_dma_map_page(struct device *hwdev, struct page *page,
dma_addr_t dev_addr, unsigned long offset, size_t size,
@ -21,87 +10,7 @@ void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
unsigned long attrs);
void __xen_dma_sync_single_for_cpu(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir);
void __xen_dma_sync_single_for_device(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir);
static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
{
return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
}
static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
{
xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
}
static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
dma_addr_t dev_addr, unsigned long offset, size_t size,
enum dma_data_direction dir, unsigned long attrs)
{
unsigned long page_pfn = page_to_xen_pfn(page);
unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
unsigned long compound_pages =
(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
bool local = (page_pfn <= dev_pfn) &&
(dev_pfn - page_pfn < compound_pages);
/*
* Dom0 is mapped 1:1, while the Linux page can span across
* multiple Xen pages, it's not possible for it to contain a
* mix of local and foreign Xen pages. So if the first xen_pfn
* == mfn the page is local otherwise it's a foreign page
* grant-mapped in dom0. If the page is local we can safely
* call the native dma_ops function, otherwise we call the xen
* specific function.
*/
if (local)
xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
else
__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
}
static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
unsigned long pfn = PFN_DOWN(handle);
/*
* Dom0 is mapped 1:1, while the Linux page can be spanned accross
* multiple Xen page, it's not possible to have a mix of local and
* foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
* foreign mfn will always return false. If the page is local we can
* safely call the native dma_ops function, otherwise we call the xen
* specific function.
*/
if (pfn_valid(pfn)) {
if (xen_get_dma_ops(hwdev)->unmap_page)
xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
} else
__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
}
static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
unsigned long pfn = PFN_DOWN(handle);
if (pfn_valid(pfn)) {
if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
} else
__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
}
static inline void xen_dma_sync_single_for_device(struct device *hwdev,
dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
unsigned long pfn = PFN_DOWN(handle);
if (pfn_valid(pfn)) {
if (xen_get_dma_ops(hwdev)->sync_single_for_device)
xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
} else
__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
}
#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */
#endif /* _XEN_ARM_PAGE_COHERENT_H */