linux/kernel/dma/mapping.c

330 lines
7.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* arch-independent dma-mapping routines
*
* Copyright (c) 2006 SUSE Linux Products GmbH
* Copyright (c) 2006 Tejun Heo <teheo@suse.de>
*/
#include <linux/acpi.h>
#include <linux/dma-mapping.h>
#include <linux/export.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/of_device.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
/*
* Managed DMA API
*/
struct dma_devres {
size_t size;
void *vaddr;
dma_addr_t dma_handle;
unsigned long attrs;
};
static void dmam_release(struct device *dev, void *res)
{
struct dma_devres *this = res;
dma_free_attrs(dev, this->size, this->vaddr, this->dma_handle,
this->attrs);
}
static int dmam_match(struct device *dev, void *res, void *match_data)
{
struct dma_devres *this = res, *match = match_data;
if (this->vaddr == match->vaddr) {
WARN_ON(this->size != match->size ||
this->dma_handle != match->dma_handle);
return 1;
}
return 0;
}
/**
* dmam_alloc_coherent - Managed dma_alloc_coherent()
* @dev: Device to allocate coherent memory for
* @size: Size of allocation
* @dma_handle: Out argument for allocated DMA handle
* @gfp: Allocation flags
*
* Managed dma_alloc_coherent(). Memory allocated using this function
* will be automatically released on driver detach.
*
* RETURNS:
* Pointer to allocated memory on success, NULL on failure.
*/
void *dmam_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp)
{
struct dma_devres *dr;
void *vaddr;
dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
if (!dr)
return NULL;
vaddr = dma_alloc_coherent(dev, size, dma_handle, gfp);
if (!vaddr) {
devres_free(dr);
return NULL;
}
dr->vaddr = vaddr;
dr->dma_handle = *dma_handle;
dr->size = size;
devres_add(dev, dr);
return vaddr;
}
EXPORT_SYMBOL(dmam_alloc_coherent);
/**
* dmam_free_coherent - Managed dma_free_coherent()
* @dev: Device to free coherent memory for
* @size: Size of allocation
* @vaddr: Virtual address of the memory to free
* @dma_handle: DMA handle of the memory to free
*
* Managed dma_free_coherent().
*/
void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle)
{
struct dma_devres match_data = { size, vaddr, dma_handle };
dma_free_coherent(dev, size, vaddr, dma_handle);
WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data));
}
EXPORT_SYMBOL(dmam_free_coherent);
/**
* dmam_alloc_attrs - Managed dma_alloc_attrs()
* @dev: Device to allocate non_coherent memory for
* @size: Size of allocation
* @dma_handle: Out argument for allocated DMA handle
* @gfp: Allocation flags
* @attrs: Flags in the DMA_ATTR_* namespace.
*
* Managed dma_alloc_attrs(). Memory allocated using this function will be
* automatically released on driver detach.
*
* RETURNS:
* Pointer to allocated memory on success, NULL on failure.
*/
void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t gfp, unsigned long attrs)
{
struct dma_devres *dr;
void *vaddr;
dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
if (!dr)
return NULL;
vaddr = dma_alloc_attrs(dev, size, dma_handle, gfp, attrs);
if (!vaddr) {
devres_free(dr);
return NULL;
}
dr->vaddr = vaddr;
dr->dma_handle = *dma_handle;
dr->size = size;
dr->attrs = attrs;
devres_add(dev, dr);
return vaddr;
}
EXPORT_SYMBOL(dmam_alloc_attrs);
#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
static void dmam_coherent_decl_release(struct device *dev, void *res)
{
dma_release_declared_memory(dev);
}
/**
* dmam_declare_coherent_memory - Managed dma_declare_coherent_memory()
* @dev: Device to declare coherent memory for
* @phys_addr: Physical address of coherent memory to be declared
* @device_addr: Device address of coherent memory to be declared
* @size: Size of coherent memory to be declared
* @flags: Flags
*
* Managed dma_declare_coherent_memory().
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
dma_addr_t device_addr, size_t size, int flags)
{
void *res;
int rc;
res = devres_alloc(dmam_coherent_decl_release, 0, GFP_KERNEL);
if (!res)
return -ENOMEM;
rc = dma_declare_coherent_memory(dev, phys_addr, device_addr, size,
flags);
if (!rc)
devres_add(dev, res);
else
devres_free(res);
return rc;
}
EXPORT_SYMBOL(dmam_declare_coherent_memory);
/**
* dmam_release_declared_memory - Managed dma_release_declared_memory().
* @dev: Device to release declared coherent memory for
*
* Managed dmam_release_declared_memory().
*/
void dmam_release_declared_memory(struct device *dev)
{
WARN_ON(devres_destroy(dev, dmam_coherent_decl_release, NULL, NULL));
}
EXPORT_SYMBOL(dmam_release_declared_memory);
#endif
/*
* Create scatter-list for the already allocated DMA buffer.
*/
int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t handle, size_t size)
{
struct page *page = virt_to_page(cpu_addr);
int ret;
ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
if (unlikely(ret))
return ret;
sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
return 0;
}
EXPORT_SYMBOL(dma_common_get_sgtable);
/*
* Create userspace mapping for the DMA-coherent memory.
*/
int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size)
{
int ret = -ENXIO;
#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
if (off < count && user_count <= (count - off))
ret = remap_pfn_range(vma, vma->vm_start,
page_to_pfn(virt_to_page(cpu_addr)) + off,
user_count << PAGE_SHIFT,
vma->vm_page_prot);
#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
return ret;
}
EXPORT_SYMBOL(dma_common_mmap);
#ifdef CONFIG_MMU
static struct vm_struct *__dma_common_pages_remap(struct page **pages,
size_t size, unsigned long vm_flags, pgprot_t prot,
const void *caller)
{
struct vm_struct *area;
area = get_vm_area_caller(size, vm_flags, caller);
if (!area)
return NULL;
if (map_vm_area(area, prot, pages)) {
vunmap(area->addr);
return NULL;
}
return area;
}
/*
* remaps an array of PAGE_SIZE pages into another vm_area
* Cannot be used in non-sleeping contexts
*/
void *dma_common_pages_remap(struct page **pages, size_t size,
unsigned long vm_flags, pgprot_t prot,
const void *caller)
{
struct vm_struct *area;
area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
if (!area)
return NULL;
area->pages = pages;
return area->addr;
}
/*
* remaps an allocated contiguous region into another vm_area.
* Cannot be used in non-sleeping contexts
*/
void *dma_common_contiguous_remap(struct page *page, size_t size,
unsigned long vm_flags,
pgprot_t prot, const void *caller)
{
int i;
struct page **pages;
struct vm_struct *area;
pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
if (!pages)
return NULL;
for (i = 0; i < (size >> PAGE_SHIFT); i++)
pages[i] = nth_page(page, i);
area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
kfree(pages);
if (!area)
return NULL;
return area->addr;
}
/*
* unmaps a range previously mapped by dma_common_*_remap
*/
void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
{
struct vm_struct *area = find_vm_area(cpu_addr);
if (!area || (area->flags & vm_flags) != vm_flags) {
WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
return;
}
drivers: base: dma-mapping: page align the size when unmap_kernel_range When dma_common_free_remap, the input parameter 'size' may not be page aligned. And, met kernel warning when doing iommu dma for usb on i.MX8 platform: " WARNING: CPU: 0 PID: 869 at mm/vmalloc.c:70 vunmap_page_range+0x1cc/0x1d0() Modules linked in: CPU: 0 PID: 869 Comm: kworker/u8:2 Not tainted 4.1.12-00444-gc5f9d1d-dirty #147 Hardware name: Freescale i.MX8DV Sabreauto (DT) Workqueue: ci_otg ci_otg_work Call trace: [<ffffffc000089920>] dump_backtrace+0x0/0x124 [<ffffffc000089a54>] show_stack+0x10/0x1c [<ffffffc0006d1e6c>] dump_stack+0x84/0xc8 [<ffffffc0000b4568>] warn_slowpath_common+0x98/0xd0 [<ffffffc0000b4664>] warn_slowpath_null+0x14/0x20 [<ffffffc000170348>] vunmap_page_range+0x1c8/0x1d0 [<ffffffc000170388>] unmap_kernel_range+0x20/0x88 [<ffffffc000460ad0>] dma_common_free_remap+0x74/0x84 [<ffffffc0000940d8>] __iommu_free_attrs+0x9c/0x178 [<ffffffc0005032bc>] ehci_mem_cleanup+0x140/0x194 [<ffffffc000503548>] ehci_stop+0x8c/0xdc [<ffffffc0004e8258>] usb_remove_hcd+0xf0/0x1cc [<ffffffc000516bc0>] host_stop+0x1c/0x58 [<ffffffc000514240>] ci_otg_work+0xdc/0x120 [<ffffffc0000c9c34>] process_one_work+0x134/0x33c [<ffffffc0000c9f78>] worker_thread+0x13c/0x47c [<ffffffc0000cf43c>] kthread+0xd8/0xf0 " For dma_common_pages_remap: dma_common_pages_remap |->get_vm_area_caller |->__get_vm_area_node |->size = PAGE_ALIGN(size); Round up to page aligned So, in dma_common_free_remap, we also need a page aligned size, pass 'PAGE_ALIGN(size)' to unmap_kernel_range. Signed-off-by: Peng Fan <van.freenix@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: <stable@vger.kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-07-21 16:04:21 +08:00
unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
vunmap(cpu_addr);
}
#endif