diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-18 13:04:15 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-18 13:04:15 -0700 |
commit | 25f4874662fb0d43fc1d934dd7802b740ed2ab5f (patch) | |
tree | 03922245c2f078c36789ecbc15fe9e4497ec96b2 /arch/arm64/include/asm | |
parent | 56172ac1024d2cb9194ea42fe76d05c0748863f4 (diff) | |
parent | 9c0731832d3b7420cbadba6a7f334363bc8dfb15 (diff) | |
download | linux-stable-25f4874662fb0d43fc1d934dd7802b740ed2ab5f.tar.gz linux-stable-25f4874662fb0d43fc1d934dd7802b740ed2ab5f.tar.bz2 linux-stable-25f4874662fb0d43fc1d934dd7802b740ed2ab5f.zip |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull rdma updates from Jason Gunthorpe:
"Aside from the usual things this has an arch update for
__iowrite64_copy() used by the RDMA drivers.
This API was intended to generate large 64 byte MemWr TLPs on PCI.
These days most processors had done this by just repeating writel() in
a loop. S390 and some new ARM64 designs require a special helper to
get this to generate.
- Small improvements and fixes for erdma, efa, hfi1, bnxt_re
- Fix a UAF crash after module unload on leaking restrack entry
- Continue adding full RDMA support in mana with support for EQs,
GID's and CQs
- Improvements to the mkey cache in mlx5
- DSCP traffic class support in hns and several bug fixes
- Cap the maximum number of MADs in the receive queue to avoid OOM
- Another batch of rxe bug fixes from large scale testing
- __iowrite64_copy() optimizations for write combining MMIO memory
- Remove NULL checks before dev_put/hold()
- EFA support for receive with immediate
- Fix a recent memleaking regression in a cma error path"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (70 commits)
RDMA/cma: Fix kmemleak in rdma_core observed during blktests nvme/rdma use siw
RDMA/IPoIB: Fix format truncation compilation errors
bnxt_re: avoid shift undefined behavior in bnxt_qplib_alloc_init_hwq
RDMA/efa: Support QP with unsolicited write w/ imm. receive
IB/hfi1: Remove generic .ndo_get_stats64
IB/hfi1: Do not use custom stat allocator
RDMA/hfi1: Use RMW accessors for changing LNKCTL2
RDMA/mana_ib: implement uapi for creation of rnic cq
RDMA/mana_ib: boundary check before installing cq callbacks
RDMA/mana_ib: introduce a helper to remove cq callbacks
RDMA/mana_ib: create and destroy RNIC cqs
RDMA/mana_ib: create EQs for RNIC CQs
RDMA/core: Remove NULL check before dev_{put, hold}
RDMA/ipoib: Remove NULL check before dev_{put, hold}
RDMA/mlx5: Remove NULL check before dev_{put, hold}
RDMA/mlx5: Track DCT, DCI and REG_UMR QPs as diver_detail resources.
RDMA/core: Add an option to display driver-specific QPs in the rdmatool
RDMA/efa: Add shutdown notifier
RDMA/mana_ib: Fix missing ret value
IB/mlx5: Use __iowrite64_copy() for write combining stores
...
Diffstat (limited to 'arch/arm64/include/asm')
-rw-r--r-- | arch/arm64/include/asm/io.h | 132 |
1 files changed, 132 insertions, 0 deletions
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 8d825522c55c..4ff0ae3f6d66 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. */ |