diff options
| -rw-r--r-- | arch/arm64/include/asm/io.h | 132 | ||||
| -rw-r--r-- | arch/arm64/kernel/io.c | 42 |
2 files changed, 174 insertions, 0 deletions
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 8d825522c55c84..4ff0ae3f6d6690 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -140,6 +140,138 @@ extern void __memset_io(volatile void __iomem *, int, size_t); #define memcpy_toio(c,a,l) __memcpy_toio((c),(a),(l)) /* + * The ARM64 iowrite implementation is intended to support drivers that want to + * use write combining. For instance PCI drivers using write combining with a 64 + * byte __iowrite64_copy() expect to get a 64 byte MemWr TLP on the PCIe bus. + * + * Newer ARM core have sensitive write combining buffers, it is important that + * the stores be contiguous blocks of store instructions. Normal memcpy + * approaches have a very low chance to generate write combining. + * + * Since this is the only API on ARM64 that should be used with write combining + * it also integrates the DGH hint which is supposed to lower the latency to + * emit the large TLP from the CPU. + */ + +static inline void __const_memcpy_toio_aligned32(volatile u32 __iomem *to, + const u32 *from, size_t count) +{ + switch (count) { + case 8: + asm volatile("str %w0, [%8, #4 * 0]\n" + "str %w1, [%8, #4 * 1]\n" + "str %w2, [%8, #4 * 2]\n" + "str %w3, [%8, #4 * 3]\n" + "str %w4, [%8, #4 * 4]\n" + "str %w5, [%8, #4 * 5]\n" + "str %w6, [%8, #4 * 6]\n" + "str %w7, [%8, #4 * 7]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]), + "rZ"(from[3]), "rZ"(from[4]), "rZ"(from[5]), + "rZ"(from[6]), "rZ"(from[7]), "r"(to)); + break; + case 4: + asm volatile("str %w0, [%4, #4 * 0]\n" + "str %w1, [%4, #4 * 1]\n" + "str %w2, [%4, #4 * 2]\n" + "str %w3, [%4, #4 * 3]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]), + "rZ"(from[3]), "r"(to)); + break; + case 2: + asm volatile("str %w0, [%2, #4 * 0]\n" + "str %w1, [%2, #4 * 1]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "r"(to)); + break; + case 1: + __raw_writel(*from, to); + break; + default: + BUILD_BUG(); + } +} + +void __iowrite32_copy_full(void __iomem *to, const void *from, size_t count); + +static inline void __const_iowrite32_copy(void __iomem *to, const void *from, + size_t count) +{ + if (count == 8 || count == 4 || count == 2 || count == 1) { + __const_memcpy_toio_aligned32(to, from, count); + dgh(); + } else { + __iowrite32_copy_full(to, from, count); + } +} + +#define __iowrite32_copy(to, from, count) \ + (__builtin_constant_p(count) ? \ + __const_iowrite32_copy(to, from, count) : \ + __iowrite32_copy_full(to, from, count)) + +static inline void __const_memcpy_toio_aligned64(volatile u64 __iomem *to, + const u64 *from, size_t count) +{ + switch (count) { + case 8: + asm volatile("str %x0, [%8, #8 * 0]\n" + "str %x1, [%8, #8 * 1]\n" + "str %x2, [%8, #8 * 2]\n" + "str %x3, [%8, #8 * 3]\n" + "str %x4, [%8, #8 * 4]\n" + "str %x5, [%8, #8 * 5]\n" + "str %x6, [%8, #8 * 6]\n" + "str %x7, [%8, #8 * 7]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]), + "rZ"(from[3]), "rZ"(from[4]), "rZ"(from[5]), + "rZ"(from[6]), "rZ"(from[7]), "r"(to)); + break; + case 4: + asm volatile("str %x0, [%4, #8 * 0]\n" + "str %x1, [%4, #8 * 1]\n" + "str %x2, [%4, #8 * 2]\n" + "str %x3, [%4, #8 * 3]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "rZ"(from[2]), + "rZ"(from[3]), "r"(to)); + break; + case 2: + asm volatile("str %x0, [%2, #8 * 0]\n" + "str %x1, [%2, #8 * 1]\n" + : + : "rZ"(from[0]), "rZ"(from[1]), "r"(to)); + break; + case 1: + __raw_writeq(*from, to); + break; + default: + BUILD_BUG(); + } +} + +void __iowrite64_copy_full(void __iomem *to, const void *from, size_t count); + +static inline void __const_iowrite64_copy(void __iomem *to, const void *from, + size_t count) +{ + if (count == 8 || count == 4 || count == 2 || count == 1) { + __const_memcpy_toio_aligned64(to, from, count); + dgh(); + } else { + __iowrite64_copy_full(to, from, count); + } +} + +#define __iowrite64_copy(to, from, count) \ + (__builtin_constant_p(count) ? \ + __const_iowrite64_copy(to, from, count) : \ + __iowrite64_copy_full(to, from, count)) + +/* * I/O memory mapping functions. */ diff --git a/arch/arm64/kernel/io.c b/arch/arm64/kernel/io.c index aa7a4ec6a3ae6f..ef48089fbfe1a4 100644 --- a/arch/arm64/kernel/io.c +++ b/arch/arm64/kernel/io.c @@ -38,6 +38,48 @@ void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count) EXPORT_SYMBOL(__memcpy_fromio); /* + * This generates a memcpy that works on a from/to address which is aligned to + * bits. Count is in terms of the number of bits sized quantities to copy. It + * optimizes to use the STR groupings when possible so that it is WC friendly. + */ +#define memcpy_toio_aligned(to, from, count, bits) \ + ({ \ + volatile u##bits __iomem *_to = to; \ + const u##bits *_from = from; \ + size_t _count = count; \ + const u##bits *_end_from = _from + ALIGN_DOWN(_count, 8); \ + \ + for (; _from < _end_from; _from += 8, _to += 8) \ + __const_memcpy_toio_aligned##bits(_to, _from, 8); \ + if ((_count % 8) >= 4) { \ + __const_memcpy_toio_aligned##bits(_to, _from, 4); \ + _from += 4; \ + _to += 4; \ + } \ + if ((_count % 4) >= 2) { \ + __const_memcpy_toio_aligned##bits(_to, _from, 2); \ + _from += 2; \ + _to += 2; \ + } \ + if (_count % 2) \ + __const_memcpy_toio_aligned##bits(_to, _from, 1); \ + }) + +void __iowrite64_copy_full(void __iomem *to, const void *from, size_t count) +{ + memcpy_toio_aligned(to, from, count, 64); + dgh(); +} +EXPORT_SYMBOL(__iowrite64_copy_full); + +void __iowrite32_copy_full(void __iomem *to, const void *from, size_t count) +{ + memcpy_toio_aligned(to, from, count, 32); + dgh(); +} +EXPORT_SYMBOL(__iowrite32_copy_full); + +/* * Copy data from "real" memory space to IO memory space. */ void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count) |