forked from Minki/linux
20d7a35bc8
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>
337 lines
8.8 KiB
C
337 lines
8.8 KiB
C
/*
|
|
* Coherent per-device memory handling.
|
|
* Borrowed from i386
|
|
*/
|
|
#include <linux/io.h>
|
|
#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;
|
|
};
|
|
|
|
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->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 = (device_addr - mem->device_base) >> PAGE_SHIFT;
|
|
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;
|
|
int order = get_order(size);
|
|
unsigned long flags;
|
|
int pageno;
|
|
|
|
if (!dev)
|
|
return 0;
|
|
mem = dev->dma_mem;
|
|
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 = mem->device_base + (pageno << PAGE_SHIFT);
|
|
*ret = mem->virt_base + (pageno << PAGE_SHIFT);
|
|
if (mem->flags & DMA_MEMORY_MAP)
|
|
memset(*ret, 0, size);
|
|
else
|
|
memset_io(*ret, 0, size);
|
|
spin_unlock_irqrestore(&mem->spinlock, flags);
|
|
|
|
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 ? dev->dma_mem : NULL;
|
|
|
|
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 ? dev->dma_mem : NULL;
|
|
|
|
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->vm_end - vma->vm_start) >> PAGE_SHIFT;
|
|
int count = 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 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;
|
|
}
|
|
rmem->priv = mem;
|
|
dma_assign_coherent_memory(dev, mem);
|
|
return 0;
|
|
}
|
|
|
|
static void rmem_dma_device_release(struct reserved_mem *rmem,
|
|
struct device *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;
|
|
}
|
|
#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;
|
|
}
|
|
RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
|
|
#endif
|