mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
1c51c429f3
R/M classes of cpus can have memory covered by MPU which in turn might configure RAM as Normal i.e. bufferable and cacheable. It breaks dma_alloc_coherent() and friends, since data can stuck in caches now or be buffered. This patch factors out DMA support for NOMMU configuration into separate entity which provides dedicated dma_ops. We have to handle there several cases: - configurations with MMU/MPU setup - configurations without MMU/MPU setup - special case for M-class, since caches and MPU there are optional In general we rely on default DMA area for coherent allocations or/and per-device memory reserves suitable for coherent DMA, so if such regions are set coherent allocations go from there. In case MMU/MPU was not setup we fallback to normal page allocator for DMA memory allocation. In case we run M-class cpus, for configuration without cache support (like Cortex-M3/M4) dma operations are forced to be coherent and wired with dma-noop (such decision is made based on cacheid global variable); however, if caches are detected there and no DMA coherent region is given (either default or per-device), dma is disallowed even MPU is not set - it is because M-class implement system memory map which defines part of address space as Normal memory. Reported-by: Alexandre Torgue <alexandre.torgue@st.com> Reported-by: Andras Szemzo <sza@esh.hu> Tested-by: Benjamin Gaignard <benjamin.gaignard@linaro.org> Tested-by: Andras Szemzo <sza@esh.hu> Tested-by: Alexandre TORGUE <alexandre.torgue@st.com> Reviewed-by: Robin Murphy <robin.murphy@arm.com> Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Russell King <rmk+kernel@armlinux.org.uk> [hch: removed the dma_supported() implementation that isn't required anymore] Signed-off-by: Christoph Hellwig <hch@lst.de>
257 lines
7.6 KiB
C
257 lines
7.6 KiB
C
#ifndef ASMARM_DMA_MAPPING_H
|
|
#define ASMARM_DMA_MAPPING_H
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#include <linux/mm_types.h>
|
|
#include <linux/scatterlist.h>
|
|
#include <linux/dma-debug.h>
|
|
|
|
#include <asm/memory.h>
|
|
|
|
#include <xen/xen.h>
|
|
#include <asm/xen/hypervisor.h>
|
|
|
|
extern const struct dma_map_ops arm_dma_ops;
|
|
extern const struct dma_map_ops arm_coherent_dma_ops;
|
|
|
|
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
|
|
{
|
|
return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_noop_ops;
|
|
}
|
|
|
|
#ifdef __arch_page_to_dma
|
|
#error Please update to __arch_pfn_to_dma
|
|
#endif
|
|
|
|
/*
|
|
* dma_to_pfn/pfn_to_dma/dma_to_virt/virt_to_dma are architecture private
|
|
* functions used internally by the DMA-mapping API to provide DMA
|
|
* addresses. They must not be used by drivers.
|
|
*/
|
|
#ifndef __arch_pfn_to_dma
|
|
static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
|
|
{
|
|
if (dev)
|
|
pfn -= dev->dma_pfn_offset;
|
|
return (dma_addr_t)__pfn_to_bus(pfn);
|
|
}
|
|
|
|
static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
|
|
{
|
|
unsigned long pfn = __bus_to_pfn(addr);
|
|
|
|
if (dev)
|
|
pfn += dev->dma_pfn_offset;
|
|
|
|
return pfn;
|
|
}
|
|
|
|
static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
|
|
{
|
|
if (dev) {
|
|
unsigned long pfn = dma_to_pfn(dev, addr);
|
|
|
|
return phys_to_virt(__pfn_to_phys(pfn));
|
|
}
|
|
|
|
return (void *)__bus_to_virt((unsigned long)addr);
|
|
}
|
|
|
|
static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
|
|
{
|
|
if (dev)
|
|
return pfn_to_dma(dev, virt_to_pfn(addr));
|
|
|
|
return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
|
|
}
|
|
|
|
#else
|
|
static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
|
|
{
|
|
return __arch_pfn_to_dma(dev, pfn);
|
|
}
|
|
|
|
static inline unsigned long dma_to_pfn(struct device *dev, dma_addr_t addr)
|
|
{
|
|
return __arch_dma_to_pfn(dev, addr);
|
|
}
|
|
|
|
static inline void *dma_to_virt(struct device *dev, dma_addr_t addr)
|
|
{
|
|
return __arch_dma_to_virt(dev, addr);
|
|
}
|
|
|
|
static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
|
|
{
|
|
return __arch_virt_to_dma(dev, addr);
|
|
}
|
|
#endif
|
|
|
|
/* The ARM override for dma_max_pfn() */
|
|
static inline unsigned long dma_max_pfn(struct device *dev)
|
|
{
|
|
return dma_to_pfn(dev, *dev->dma_mask);
|
|
}
|
|
#define dma_max_pfn(dev) dma_max_pfn(dev)
|
|
|
|
#define arch_setup_dma_ops arch_setup_dma_ops
|
|
extern void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
|
|
const struct iommu_ops *iommu, bool coherent);
|
|
|
|
#define arch_teardown_dma_ops arch_teardown_dma_ops
|
|
extern void arch_teardown_dma_ops(struct device *dev);
|
|
|
|
/* do not use this function in a driver */
|
|
static inline bool is_device_dma_coherent(struct device *dev)
|
|
{
|
|
return dev->archdata.dma_coherent;
|
|
}
|
|
|
|
static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
|
|
{
|
|
unsigned int offset = paddr & ~PAGE_MASK;
|
|
return pfn_to_dma(dev, __phys_to_pfn(paddr)) + offset;
|
|
}
|
|
|
|
static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr)
|
|
{
|
|
unsigned int offset = dev_addr & ~PAGE_MASK;
|
|
return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset;
|
|
}
|
|
|
|
static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
|
|
{
|
|
u64 limit, mask;
|
|
|
|
if (!dev->dma_mask)
|
|
return 0;
|
|
|
|
mask = *dev->dma_mask;
|
|
|
|
limit = (mask + 1) & ~mask;
|
|
if (limit && size > limit)
|
|
return 0;
|
|
|
|
if ((addr | (addr + size - 1)) & ~mask)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static inline void dma_mark_clean(void *addr, size_t size) { }
|
|
|
|
/**
|
|
* arm_dma_alloc - allocate consistent memory for DMA
|
|
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
|
|
* @size: required memory size
|
|
* @handle: bus-specific DMA address
|
|
* @attrs: optinal attributes that specific mapping properties
|
|
*
|
|
* Allocate some memory for a device for performing DMA. This function
|
|
* allocates pages, and will return the CPU-viewed address, and sets @handle
|
|
* to be the device-viewed address.
|
|
*/
|
|
extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
|
|
gfp_t gfp, unsigned long attrs);
|
|
|
|
/**
|
|
* arm_dma_free - free memory allocated by arm_dma_alloc
|
|
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
|
|
* @size: size of memory originally requested in dma_alloc_coherent
|
|
* @cpu_addr: CPU-view address returned from dma_alloc_coherent
|
|
* @handle: device-view address returned from dma_alloc_coherent
|
|
* @attrs: optinal attributes that specific mapping properties
|
|
*
|
|
* Free (and unmap) a DMA buffer previously allocated by
|
|
* arm_dma_alloc().
|
|
*
|
|
* References to memory and mappings associated with cpu_addr/handle
|
|
* during and after this call executing are illegal.
|
|
*/
|
|
extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
|
|
dma_addr_t handle, unsigned long attrs);
|
|
|
|
/**
|
|
* arm_dma_mmap - map a coherent DMA allocation into user space
|
|
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
|
|
* @vma: vm_area_struct describing requested user mapping
|
|
* @cpu_addr: kernel CPU-view address returned from dma_alloc_coherent
|
|
* @handle: device-view address returned from dma_alloc_coherent
|
|
* @size: size of memory originally requested in dma_alloc_coherent
|
|
* @attrs: optinal attributes that specific mapping properties
|
|
*
|
|
* Map a coherent DMA buffer previously allocated by dma_alloc_coherent
|
|
* into user space. The coherent DMA buffer must not be freed by the
|
|
* driver until the user space mapping has been released.
|
|
*/
|
|
extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
|
|
void *cpu_addr, dma_addr_t dma_addr, size_t size,
|
|
unsigned long attrs);
|
|
|
|
/*
|
|
* This can be called during early boot to increase the size of the atomic
|
|
* coherent DMA pool above the default value of 256KiB. It must be called
|
|
* before postcore_initcall.
|
|
*/
|
|
extern void __init init_dma_coherent_pool_size(unsigned long size);
|
|
|
|
/*
|
|
* For SA-1111, IXP425, and ADI systems the dma-mapping functions are "magic"
|
|
* and utilize bounce buffers as needed to work around limited DMA windows.
|
|
*
|
|
* On the SA-1111, a bug limits DMA to only certain regions of RAM.
|
|
* On the IXP425, the PCI inbound window is 64MB (256MB total RAM)
|
|
* On some ADI engineering systems, PCI inbound window is 32MB (12MB total RAM)
|
|
*
|
|
* The following are helper functions used by the dmabounce subystem
|
|
*
|
|
*/
|
|
|
|
/**
|
|
* dmabounce_register_dev
|
|
*
|
|
* @dev: valid struct device pointer
|
|
* @small_buf_size: size of buffers to use with small buffer pool
|
|
* @large_buf_size: size of buffers to use with large buffer pool (can be 0)
|
|
* @needs_bounce_fn: called to determine whether buffer needs bouncing
|
|
*
|
|
* This function should be called by low-level platform code to register
|
|
* a device as requireing DMA buffer bouncing. The function will allocate
|
|
* appropriate DMA pools for the device.
|
|
*/
|
|
extern int dmabounce_register_dev(struct device *, unsigned long,
|
|
unsigned long, int (*)(struct device *, dma_addr_t, size_t));
|
|
|
|
/**
|
|
* dmabounce_unregister_dev
|
|
*
|
|
* @dev: valid struct device pointer
|
|
*
|
|
* This function should be called by low-level platform code when device
|
|
* that was previously registered with dmabounce_register_dev is removed
|
|
* from the system.
|
|
*
|
|
*/
|
|
extern void dmabounce_unregister_dev(struct device *);
|
|
|
|
|
|
|
|
/*
|
|
* The scatter list versions of the above methods.
|
|
*/
|
|
extern int arm_dma_map_sg(struct device *, struct scatterlist *, int,
|
|
enum dma_data_direction, unsigned long attrs);
|
|
extern void arm_dma_unmap_sg(struct device *, struct scatterlist *, int,
|
|
enum dma_data_direction, unsigned long attrs);
|
|
extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
|
|
enum dma_data_direction);
|
|
extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
|
|
enum dma_data_direction);
|
|
extern int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
|
|
void *cpu_addr, dma_addr_t dma_addr, size_t size,
|
|
unsigned long attrs);
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif
|