The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable@xxxxxxxxxxxxxxx>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 4eb2eb1b4c0eb07793c240744843498564a67b83 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable@xxxxxxxxxxxxxxx>' --in-reply-to '2023081242-take-crabgrass-6e98@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: 4eb2eb1b4c0e ("riscv,mmio: Fix readX()-to-delay() ordering") 0c3ac28931d5 ("riscv: separate MMIO functions into their own header file") b012980d1c6e ("riscv/mmiowb: Hook up mmwiob() implementation to asm-generic code") 3d8dfe75ef69 ("Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 4eb2eb1b4c0eb07793c240744843498564a67b83 Mon Sep 17 00:00:00 2001 From: Andrea Parri <parri.andrea@xxxxxxxxx> Date: Thu, 3 Aug 2023 06:27:38 +0200 Subject: [PATCH] riscv,mmio: Fix readX()-to-delay() ordering Section 2.1 of the Platform Specification [1] states: Unless otherwise specified by a given I/O device, I/O devices are on ordering channel 0 (i.e., they are point-to-point strongly ordered). which is not sufficient to guarantee that a readX() by a hart completes before a subsequent delay() on the same hart (cf. memory-barriers.txt, "Kernel I/O barrier effects"). Set the I(nput) bit in __io_ar() to restore the ordering, align inline comments. [1] https://github.com/riscv/riscv-platform-specs Signed-off-by: Andrea Parri <parri.andrea@xxxxxxxxx> Link: https://lore.kernel.org/r/20230803042738.5937-1-parri.andrea@xxxxxxxxx Fixes: fab957c11efe ("RISC-V: Atomic and Locking Code") Cc: stable@xxxxxxxxxxxxxxx Signed-off-by: Palmer Dabbelt <palmer@xxxxxxxxxxxx> diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index aff6c33ab0c0..4c58ee7f95ec 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -101,9 +101,9 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * Relaxed I/O memory access primitives. These follow the Device memory * ordering rules but do not guarantee any ordering relative to Normal memory * accesses. These are defined to order the indicated access (either a read or - * write) with all other I/O memory accesses. Since the platform specification - * defines that all I/O regions are strongly ordered on channel 2, no explicit - * fences are required to enforce this ordering. + * write) with all other I/O memory accesses to the same peripheral. Since the + * platform specification defines that all I/O regions are strongly ordered on + * channel 0, no explicit fences are required to enforce this ordering. */ /* FIXME: These are now the same as asm-generic */ #define __io_rbr() do {} while (0) @@ -125,14 +125,14 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* - * I/O memory access primitives. Reads are ordered relative to any - * following Normal memory access. Writes are ordered relative to any prior - * Normal memory access. The memory barriers here are necessary as RISC-V + * I/O memory access primitives. Reads are ordered relative to any following + * Normal memory read and delay() loop. Writes are ordered relative to any + * prior Normal memory write. The memory barriers here are necessary as RISC-V * doesn't define any ordering between the memory space and the I/O space. */ #define __io_br() do {} while (0) -#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory") -#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory") +#define __io_ar(v) ({ __asm__ __volatile__ ("fence i,ir" : : : "memory"); }) +#define __io_bw() ({ __asm__ __volatile__ ("fence w,o" : : : "memory"); }) #define __io_aw() mmiowb_set_pending() #define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })
