Merge patch series "riscv: enable EFFICIENT_UNALIGNED_ACCESS and DCACHE_WORD_ACCESS"

Jisheng Zhang <jszhang@kernel.org> says:

Some riscv implementations such as T-HEAD's C906, C908, C910 and C920
support efficient unaligned access, for performance reason we want
to enable HAVE_EFFICIENT_UNALIGNED_ACCESS on these platforms. To
avoid performance regressions on non efficient unaligned access
platforms, HAVE_EFFICIENT_UNALIGNED_ACCESS can't be globally selected.

To solve this problem, runtime code patching based on the detected
speed is a good solution. But that's not easy, it involves lots of
work to modify vairous subsystems such as net, mm, lib and so on.
This can be done step by step.

So let's take an easier solution: add support to efficient unaligned
access and hide the support under NONPORTABLE.

patch1 introduces RISCV_EFFICIENT_UNALIGNED_ACCESS which depends on
NONPORTABLE, if users know during config time that the kernel will be
only run on those efficient unaligned access hw platforms, they can
enable it. Obviously, generic unified kernel Image shouldn't enable it.

patch2 adds support DCACHE_WORD_ACCESS when MMU and
RISCV_EFFICIENT_UNALIGNED_ACCESS.

Below test program and step shows how much performance can be improved:

 $ cat tt.c
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>

 #define ITERATIONS 1000000

 #define PATH "123456781234567812345678123456781"

 int main(void)
 {
         unsigned long i;
         struct stat buf;

         for (i = 0; i < ITERATIONS; i++)
                 stat(PATH, &buf);

         return 0;
 }

 $ gcc -O2 tt.c
 $ touch 123456781234567812345678123456781
 $ time ./a.out

Per my test on T-HEAD C910 platforms, the above test performance is
improved by about 7.5%.

* b4-shazam-merge:
  riscv: select DCACHE_WORD_ACCESS for efficient unaligned access HW
  riscv: introduce RISCV_EFFICIENT_UNALIGNED_ACCESS

Link: https://lore.kernel.org/r/20231225044207.3821-1-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

2 files changed, 42 insertions, 0 deletions

diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h
index 00a96e7a9664..0c8bfd54fc4e 100644
--- a/arch/riscv/include/asm/asm-extable.h
+++ b/arch/riscv/include/asm/asm-extable.h
@@ -6,6 +6,7 @@
 #define EX_TYPE_FIXUP			1
 #define EX_TYPE_BPF			2
 #define EX_TYPE_UACCESS_ERR_ZERO	3
+#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD	4
 
 #ifdef CONFIG_MMU
 
@@ -47,6 +48,11 @@
 #define EX_DATA_REG_ZERO_SHIFT	5
 #define EX_DATA_REG_ZERO	GENMASK(9, 5)
 
+#define EX_DATA_REG_DATA_SHIFT	0
+#define EX_DATA_REG_DATA	GENMASK(4, 0)
+#define EX_DATA_REG_ADDR_SHIFT	5
+#define EX_DATA_REG_ADDR	GENMASK(9, 5)
+
 #define EX_DATA_REG(reg, gpr)						\
 	"((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")"
 
@@ -62,6 +68,15 @@
 #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)			\
 	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
 
+#define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr)		\
+	__DEFINE_ASM_GPR_NUMS							\
+	__ASM_EXTABLE_RAW(#insn, #fixup,					\
+			  __stringify(EX_TYPE_LOAD_UNALIGNED_ZEROPAD),		\
+			  "("							\
+			    EX_DATA_REG(DATA, data) " | "			\
+			    EX_DATA_REG(ADDR, addr)				\
+			  ")")
+
 #endif /* __ASSEMBLY__ */
 
 #else /* CONFIG_MMU */
diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h
index 7c086ac6ecd4..f3f031e34191 100644
--- a/arch/riscv/include/asm/word-at-a-time.h
+++ b/arch/riscv/include/asm/word-at-a-time.h
@@ -9,6 +9,7 @@
 #define _ASM_RISCV_WORD_AT_A_TIME_H
 
 
+#include <asm/asm-extable.h>
 #include <linux/kernel.h>
 
 struct word_at_a_time {
@@ -45,4 +46,30 @@ static inline unsigned long find_zero(unsigned long mask)
 /* The mask we created is directly usable as a bytemask */
 #define zero_bytemask(mask) (mask)
 
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret;
+
+	/* Load word from unaligned pointer addr */
+	asm(
+	"1:	" REG_L " %0, %2\n"
+	"2:\n"
+	_ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1)
+	: "=&r" (ret)
+	: "r" (addr), "m" (*(unsigned long *)addr));
+
+	return ret;
+}
+
+#endif	/* CONFIG_DCACHE_WORD_ACCESS */
+
 #endif /* _ASM_RISCV_WORD_AT_A_TIME_H */