linux/drivers/base/dma-coherent.c

395 lines
10 KiB
C
Raw Normal View History

/*
* Coherent per-device memory handling.
* Borrowed from i386
*/
#include <linux/io.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/slab.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/dma-mapping.h>
struct dma_coherent_mem {
void *virt_base;
dma_addr_t device_base;
unsigned long pfn_base;
int size;
int flags;
unsigned long *bitmap;
spinlock_t spinlock;
bool use_dev_dma_pfn_offset;
};
static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev)
{
if (dev && dev->dma_mem)
return dev->dma_mem;
return dma_coherent_default_memory;
}
static inline dma_addr_t dma_get_device_base(struct device *dev,
struct dma_coherent_mem * mem)
{
if (mem->use_dev_dma_pfn_offset)
return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
else
return mem->device_base;
}
static bool dma_init_coherent_memory(
phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags,
struct dma_coherent_mem **mem)
{
struct dma_coherent_mem *dma_mem = NULL;
void __iomem *mem_base = NULL;
int pages = size >> PAGE_SHIFT;
int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
goto out;
if (!size)
goto out;
if (flags & DMA_MEMORY_MAP)
mem_base = memremap(phys_addr, size, MEMREMAP_WC);
else
mem_base = ioremap(phys_addr, size);
if (!mem_base)
goto out;
dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
if (!dma_mem)
goto out;
dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
if (!dma_mem->bitmap)
goto out;
dma_mem->virt_base = mem_base;
dma_mem->device_base = device_addr;
dma_mem->pfn_base = PFN_DOWN(phys_addr);
dma_mem->size = pages;
dma_mem->flags = flags;
spin_lock_init(&dma_mem->spinlock);
*mem = dma_mem;
return true;
out:
kfree(dma_mem);
if (mem_base) {
if (flags & DMA_MEMORY_MAP)
memunmap(mem_base);
else
iounmap(mem_base);
}
return false;
}
static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
{
if (!mem)
return;
if (mem->flags & DMA_MEMORY_MAP)
memunmap(mem->virt_base);
else
iounmap(mem->virt_base);
kfree(mem->bitmap);
kfree(mem);
}
static int dma_assign_coherent_memory(struct device *dev,
struct dma_coherent_mem *mem)
{
if (!dev)
return -ENODEV;
if (dev->dma_mem)
return -EBUSY;
dev->dma_mem = mem;
/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
return 0;
}
int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
dma_addr_t device_addr, size_t size, int flags)
{
struct dma_coherent_mem *mem;
if (!dma_init_coherent_memory(phys_addr, device_addr, size, flags,
&mem))
return 0;
if (dma_assign_coherent_memory(dev, mem) == 0)
return flags & DMA_MEMORY_MAP ? DMA_MEMORY_MAP : DMA_MEMORY_IO;
dma_release_coherent_memory(mem);
return 0;
}
EXPORT_SYMBOL(dma_declare_coherent_memory);
void dma_release_declared_memory(struct device *dev)
{
struct dma_coherent_mem *mem = dev->dma_mem;
if (!mem)
return;
dma_release_coherent_memory(mem);
dev->dma_mem = NULL;
}
EXPORT_SYMBOL(dma_release_declared_memory);
void *dma_mark_declared_memory_occupied(struct device *dev,
dma_addr_t device_addr, size_t size)
{
struct dma_coherent_mem *mem = dev->dma_mem;
unsigned long flags;
int pos, err;
size += device_addr & ~PAGE_MASK;
if (!mem)
return ERR_PTR(-EINVAL);
spin_lock_irqsave(&mem->spinlock, flags);
pos = PFN_DOWN(device_addr - dma_get_device_base(dev, mem));
err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
spin_unlock_irqrestore(&mem->spinlock, flags);
if (err != 0)
return ERR_PTR(err);
return mem->virt_base + (pos << PAGE_SHIFT);
}
EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
/**
* dma_alloc_from_coherent() - try to allocate memory from the per-device coherent area
*
* @dev: device from which we allocate memory
* @size: size of requested memory area
* @dma_handle: This will be filled with the correct dma handle
* @ret: This pointer will be filled with the virtual address
* to allocated area.
*
* This function should be only called from per-arch dma_alloc_coherent()
* to support allocation from per-device coherent memory pools.
*
* Returns 0 if dma_alloc_coherent should continue with allocating from
* generic memory areas, or !0 if dma_alloc_coherent should return @ret.
*/
int dma_alloc_from_coherent(struct device *dev, ssize_t size,
dma_addr_t *dma_handle, void **ret)
{
struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
int order = get_order(size);
unsigned long flags;
int pageno;
int dma_memory_map;
if (!mem)
return 0;
*ret = NULL;
spin_lock_irqsave(&mem->spinlock, flags);
if (unlikely(size > (mem->size << PAGE_SHIFT)))
goto err;
pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
if (unlikely(pageno < 0))
goto err;
/*
* Memory was found in the per-device area.
*/
*dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT);
*ret = mem->virt_base + (pageno << PAGE_SHIFT);
dma_memory_map = (mem->flags & DMA_MEMORY_MAP);
spin_unlock_irqrestore(&mem->spinlock, flags);
if (dma_memory_map)
drivers: dma-coherent: use memset_io for DMA_MEMORY_IO mappings Use memset_io() for DMA_MEMORY_IO mappings which are mapped as I/O memory, and regular memset() for DMA_MEMORY_MAP mappings. This fixes the below alignment fault on arm64 for DMA_MEMORY_IO mappings, where memset() uses the DC ZVA instruction which is invalid on device memory. Unhandled fault: alignment fault (0x96000061) at 0xffffff8000380000 Internal error: : 96000061 [#1] PREEMPT SMP Modules linked in: hdlcd(+) clk_scpi CPU: 4 PID: 1355 Comm: systemd-udevd Not tainted 4.4.0-rc1+ #5 Hardware name: ARM Juno development board (r0) (DT) task: ffffffc9763eee00 ti: ffffffc9758c4000 task.ti: ffffffc9758c4000 PC is at __efistub_memset+0x1ac/0x200 LR is at dma_alloc_from_coherent+0xb0/0x120 pc : [<ffffffc00030ff2c>] lr : [<ffffffc00042a918>] pstate: 400001c5 sp : ffffffc9758c79a0 x29: ffffffc9758c79a0 x28: ffffffc000635cd0 x27: 0000000000000124 x26: ffffffc000119ef4 x25: 0000000000010000 x24: 0000000000000140 x23: ffffffc07e9ac3a8 x22: ffffffc9758c7a58 x21: ffffffc9758c7a68 x20: 0000000000000004 x19: ffffffc07e9ac380 x18: 0000000000000001 x17: 0000007fae1bbba8 x16: ffffffc0001b2d1c x15: ffffffffffffffff x14: 0ffffffffffffffe x13: 0000000000000010 x12: ffffff800837ffff x11: ffffff800837ffff x10: 0000000040000000 x9 : 0000000000000000 x8 : ffffff8000380000 x7 : 0000000000000000 x6 : 000000000000003f x5 : 0000000000000040 x4 : 0000000000000000 x3 : 0000000000000004 x2 : 000000000000ffc0 x1 : 0000000000000000 x0 : ffffff8000380000 Signed-off-by: Brian Starkey <brian.starkey@arm.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-23 05:28:06 +08:00
memset(*ret, 0, size);
else
memset_io(*ret, 0, size);
return 1;
err:
spin_unlock_irqrestore(&mem->spinlock, flags);
/*
* In the case where the allocation can not be satisfied from the
* per-device area, try to fall back to generic memory if the
* constraints allow it.
*/
return mem->flags & DMA_MEMORY_EXCLUSIVE;
}
EXPORT_SYMBOL(dma_alloc_from_coherent);
/**
* dma_release_from_coherent() - try to free the memory allocated from per-device coherent memory pool
* @dev: device from which the memory was allocated
* @order: the order of pages allocated
* @vaddr: virtual address of allocated pages
*
* This checks whether the memory was allocated from the per-device
* coherent memory pool and if so, releases that memory.
*
* Returns 1 if we correctly released the memory, or 0 if
* dma_release_coherent() should proceed with releasing memory from
* generic pools.
*/
int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
{
struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
if (mem && vaddr >= mem->virt_base && vaddr <
(mem->virt_base + (mem->size << PAGE_SHIFT))) {
int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
unsigned long flags;
spin_lock_irqsave(&mem->spinlock, flags);
bitmap_release_region(mem->bitmap, page, order);
spin_unlock_irqrestore(&mem->spinlock, flags);
return 1;
}
return 0;
}
EXPORT_SYMBOL(dma_release_from_coherent);
/**
* dma_mmap_from_coherent() - try to mmap the memory allocated from
* per-device coherent memory pool to userspace
* @dev: device from which the memory was allocated
* @vma: vm_area for the userspace memory
* @vaddr: cpu address returned by dma_alloc_from_coherent
* @size: size of the memory buffer allocated by dma_alloc_from_coherent
* @ret: result from remap_pfn_range()
*
* This checks whether the memory was allocated from the per-device
* coherent memory pool and if so, maps that memory to the provided vma.
*
* Returns 1 if we correctly mapped the memory, or 0 if the caller should
* proceed with mapping memory from generic pools.
*/
int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
void *vaddr, size_t size, int *ret)
{
struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
if (mem && vaddr >= mem->virt_base && vaddr + size <=
(mem->virt_base + (mem->size << PAGE_SHIFT))) {
unsigned long off = vma->vm_pgoff;
int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
int user_count = vma_pages(vma);
int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
*ret = -ENXIO;
if (off < count && user_count <= count - off) {
unsigned long pfn = mem->pfn_base + start + off;
*ret = remap_pfn_range(vma, vma->vm_start, pfn,
user_count << PAGE_SHIFT,
vma->vm_page_prot);
}
return 1;
}
return 0;
}
EXPORT_SYMBOL(dma_mmap_from_coherent);
/*
* Support for reserved memory regions defined in device tree
*/
#ifdef CONFIG_OF_RESERVED_MEM
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/of_reserved_mem.h>
static struct reserved_mem *dma_reserved_default_memory __initdata;
static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
{
struct dma_coherent_mem *mem = rmem->priv;
if (!mem &&
!dma_init_coherent_memory(rmem->base, rmem->base, rmem->size,
DMA_MEMORY_MAP | DMA_MEMORY_EXCLUSIVE,
&mem)) {
pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
&rmem->base, (unsigned long)rmem->size / SZ_1M);
return -ENODEV;
}
mem->use_dev_dma_pfn_offset = true;
rmem->priv = mem;
dma_assign_coherent_memory(dev, mem);
return 0;
}
static void rmem_dma_device_release(struct reserved_mem *rmem,
struct device *dev)
{
if (dev)
dev->dma_mem = NULL;
}
static const struct reserved_mem_ops rmem_dma_ops = {
.device_init = rmem_dma_device_init,
.device_release = rmem_dma_device_release,
};
static int __init rmem_dma_setup(struct reserved_mem *rmem)
{
unsigned long node = rmem->fdt_node;
if (of_get_flat_dt_prop(node, "reusable", NULL))
return -EINVAL;
#ifdef CONFIG_ARM
if (!of_get_flat_dt_prop(node, "no-map", NULL)) {
pr_err("Reserved memory: regions without no-map are not yet supported\n");
return -EINVAL;
}
if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) {
WARN(dma_reserved_default_memory,
"Reserved memory: region for default DMA coherent area is redefined\n");
dma_reserved_default_memory = rmem;
}
#endif
rmem->ops = &rmem_dma_ops;
pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n",
&rmem->base, (unsigned long)rmem->size / SZ_1M);
return 0;
}
static int __init dma_init_reserved_memory(void)
{
const struct reserved_mem_ops *ops;
int ret;
if (!dma_reserved_default_memory)
return -ENOMEM;
ops = dma_reserved_default_memory->ops;
/*
* We rely on rmem_dma_device_init() does not propagate error of
* dma_assign_coherent_memory() for "NULL" device.
*/
ret = ops->device_init(dma_reserved_default_memory, NULL);
if (!ret) {
dma_coherent_default_memory = dma_reserved_default_memory->priv;
pr_info("DMA: default coherent area is set\n");
}
return ret;
}
core_initcall(dma_init_reserved_memory);
RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
#endif