leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

swiotlb-xen: fix DMA_ATTR_NO_KERNEL_MAPPING on arm

Browse Source 
swiotlb-xen uses very different ways to allocate coherent memory on x86
vs arm.  On the former it allocates memory from the page allocator, while
on the later it reuses the dma-direct allocator the handles the
complexities of non-coherent DMA on arm platforms.

Unfortunately the complexities of trying to deal with the two cases in
the swiotlb-xen.c code lead to a bug in the handling of
DMA_ATTR_NO_KERNEL_MAPPING on arm.  With the DMA_ATTR_NO_KERNEL_MAPPING
flag the coherent memory allocator does not actually allocate coherent
memory, but just a DMA handle for some memory that is DMA addressable
by the device, but which does not have to have a kernel mapping.  Thus
dereferencing the return value will lead to kernel crashed and memory
corruption.

Fix this by using the dma-direct allocator directly for arm, which works
perfectly fine because on arm swiotlb-xen is only used when the domain is
1:1 mapped, and then simplifying the remaining code to only cater for the
x86 case with DMA coherent device.

Reported-by: Rahul Singh <Rahul.Singh@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Rahul Singh <rahul.singh@arm.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Tested-by: Rahul Singh <rahul.singh@arm.com>
This commit is contained in:
Christoph Hellwig 2022-04-22 06:37:57 +02:00
parent 3cb4503a33
commit 566fb90e05
10 changed files with 40 additions and 139 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
arch/arm/include/asm/xen/page-coherent.h
View File

@ -1,2 +0,0 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <xen/arm/page-coherent.h>

14
arch/arm/xen/mm.c
View File

@ -116,20 +116,6 @@ bool xen_arch_need_swiotlb(struct device *dev,
!dev_is_dma_coherent(dev));
}
int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
unsigned int address_bits,
dma_addr_t *dma_handle)
{
/* the domain is 1:1 mapped to use swiotlb-xen */
*dma_handle = pstart;
return 0;
}
void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
{
return;
}
static int __init xen_mm_init(void)
{
struct gnttab_cache_flush cflush;

2
arch/arm64/include/asm/xen/page-coherent.h
View File

@ -1,2 +0,0 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <xen/arm/page-coherent.h>

24
arch/x86/include/asm/xen/page-coherent.h
View File

@ -1,24 +0,0 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_XEN_PAGE_COHERENT_H
#define _ASM_X86_XEN_PAGE_COHERENT_H
#include <asm/page.h>
#include <linux/dma-mapping.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)
{
void *vstart = (void*)__get_free_pages(flags, get_order(size));
*dma_handle = virt_to_phys(vstart);
return vstart;
}
static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
void *cpu_addr, dma_addr_t dma_handle,
unsigned long attrs)
{
free_pages((unsigned long) cpu_addr, get_order(size));
}
#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */

6
arch/x86/include/asm/xen/swiotlb-xen.h
View File

@ -8,4 +8,10 @@ extern int pci_xen_swiotlb_init_late(void);
static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
#endif
int xen_swiotlb_fixup(void *buf, unsigned long nslabs);
int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
unsigned int address_bits,
dma_addr_t *dma_handle);
void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order);
#endif /* _ASM_X86_SWIOTLB_XEN_H */

1
arch/x86/xen/mmu_pv.c
View File

@ -80,6 +80,7 @@
#include <xen/interface/version.h>
#include <xen/interface/memory.h>
#include <xen/hvc-console.h>
#include <xen/swiotlb-xen.h>
#include "multicalls.h"
#include "mmu.h"

97
drivers/xen/swiotlb-xen.c
View File

@ -36,7 +36,6 @@
#include <xen/hvc-console.h>
#include <asm/dma-mapping.h>
#include <asm/xen/page-coherent.h>
#include <trace/events/swiotlb.h>
#define MAX_DMA_BITS 32
@ -104,6 +103,7 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
return 0;
}
#ifdef CONFIG_X86
int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
{
int rc;
@ -131,94 +131,58 @@ int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
}
static void *
xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags,
unsigned long attrs)
xen_swiotlb_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
{
void *ret;
u64 dma_mask = dev->coherent_dma_mask;
int order = get_order(size);
u64 dma_mask = DMA_BIT_MASK(32);
phys_addr_t phys;
dma_addr_t dev_addr;
void *ret;
/*
* 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);
/* Convert the size to actually allocated. */
/* Align the allocation to the Xen page size */
size = 1UL << (order + XEN_PAGE_SHIFT);
/* 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);
ret = (void *)__get_free_pages(flags, get_order(size));
if (!ret)
return ret;
phys = virt_to_phys(ret);
if (hwdev && hwdev->coherent_dma_mask)
dma_mask = hwdev->coherent_dma_mask;
/* At this point dma_handle is the dma 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_to_phys(hwdev, *dma_handle);
dev_addr = xen_phys_to_dma(hwdev, 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;
}
*dma_handle = phys_to_dma(hwdev, *dma_handle);
*dma_handle = xen_phys_to_dma(dev, phys);
if (*dma_handle + size - 1 > dma_mask ||
range_straddles_page_boundary(phys, size)) {
if (xen_create_contiguous_region(phys, order, fls64(dma_mask),
dma_handle) != 0)
goto out_free_pages;
SetPageXenRemapped(virt_to_page(ret));
}
memset(ret, 0, size);
return ret;
out_free_pages:
free_pages((unsigned long)ret, get_order(size));
return NULL;
}
static void
xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
dma_addr_t dev_addr, unsigned long attrs)
xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
phys_addr_t phys = virt_to_phys(vaddr);
int order = get_order(size);
phys_addr_t phys;
u64 dma_mask = DMA_BIT_MASK(32);
struct page *page;
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_dma_to_phys(hwdev, dev_addr);
/* Convert the size to actually allocated. */
size = 1UL << (order + XEN_PAGE_SHIFT);
if (is_vmalloc_addr(vaddr))
page = vmalloc_to_page(vaddr);
else
page = virt_to_page(vaddr);
if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) ||
WARN_ON_ONCE(range_straddles_page_boundary(phys, size)))
return;
if (!WARN_ON((dev_addr + size - 1 > dma_mask) ||
range_straddles_page_boundary(phys, size)) &&
TestClearPageXenRemapped(page))
if (TestClearPageXenRemapped(virt_to_page(vaddr)))
xen_destroy_contiguous_region(phys, order);
xen_free_coherent_pages(hwdev, size, vaddr, phys_to_dma(hwdev, phys),
attrs);
free_pages((unsigned long)vaddr, get_order(size));
}
#endif /* CONFIG_X86 */
/*
* Map a single buffer of the indicated size for DMA in streaming mode. The
@ -421,8 +385,13 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
}
const struct dma_map_ops xen_swiotlb_dma_ops = {
#ifdef CONFIG_X86
.alloc = xen_swiotlb_alloc_coherent,
.free = xen_swiotlb_free_coherent,
#else
.alloc = dma_direct_alloc,
.free = dma_direct_free,
#endif
.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
.sync_single_for_device = xen_swiotlb_sync_single_for_device,
.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,

20
include/xen/arm/page-coherent.h
View File

@ -1,20 +0,0 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _XEN_ARM_PAGE_COHERENT_H
#define _XEN_ARM_PAGE_COHERENT_H
#include <linux/dma-mapping.h>
#include <asm/page.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);
}
#endif /* _XEN_ARM_PAGE_COHERENT_H */

6
include/xen/swiotlb-xen.h
View File

@ -10,12 +10,6 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
size_t size, enum dma_data_direction dir);
#ifdef CONFIG_SWIOTLB_XEN
int xen_swiotlb_fixup(void *buf, unsigned long nslabs);
#else
#define xen_swiotlb_fixup NULL
#endif
extern const struct dma_map_ops xen_swiotlb_dma_ops;
#endif /* __LINUX_SWIOTLB_XEN_H */

7
include/xen/xen-ops.h
View File

@ -42,13 +42,6 @@ int xen_setup_shutdown_event(void);
extern unsigned long *xen_contiguous_bitmap;
#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64)
int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
unsigned int address_bits,
dma_addr_t *dma_handle);
void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order);
#endif
#if defined(CONFIG_XEN_PV)
int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,