@@ -654,6 +654,7 @@ config RISCV_MISALIGNED
config RISCV_EFFICIENT_UNALIGNED_ACCESS
bool "Assume the CPU supports fast unaligned memory accesses"
depends on NONPORTABLE
+ select DCACHE_WORD_ACCESS if MMU
select HAVE_EFFICIENT_UNALIGNED_ACCESS
help
Say Y here if you want the kernel to assume that the CPU supports
@@ -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 */
@@ -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 */
@@ -27,6 +27,14 @@ static bool ex_handler_fixup(const struct exception_table_entry *ex,
return true;
}
+static inline unsigned long regs_get_gpr(struct pt_regs *regs, unsigned int offset)
+{
+ if (unlikely(!offset || offset > MAX_REG_OFFSET))
+ return 0;
+
+ return *(unsigned long *)((unsigned long)regs + offset);
+}
+
static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
unsigned long val)
{
@@ -50,6 +58,27 @@ static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
return true;
}
+static bool
+ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
+ struct pt_regs *regs)
+{
+ int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data);
+ int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
+ unsigned long data, addr, offset;
+
+ addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long));
+
+ offset = addr & 0x7UL;
+ addr &= ~0x7UL;
+
+ data = *(unsigned long *)addr >> (offset * 8);
+
+ regs_set_gpr(regs, reg_data * sizeof(unsigned long), data);
+
+ regs->epc = get_ex_fixup(ex);
+ return true;
+}
+
bool fixup_exception(struct pt_regs *regs)
{
const struct exception_table_entry *ex;
@@ -65,6 +94,8 @@ bool fixup_exception(struct pt_regs *regs)
return ex_handler_bpf(ex, regs);
case EX_TYPE_UACCESS_ERR_ZERO:
return ex_handler_uaccess_err_zero(ex, regs);
+ case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
+ return ex_handler_load_unaligned_zeropad(ex, regs);
}
BUG();
DCACHE_WORD_ACCESS uses the word-at-a-time API for optimised string comparisons in the vfs layer. This patch implements support for load_unaligned_zeropad in much the same way as has been done for arm64. Here is the test program and step: $ 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%. Signed-off-by: Jisheng Zhang <jszhang@kernel.org> --- arch/riscv/Kconfig | 1 + arch/riscv/include/asm/asm-extable.h | 15 ++++++++++++ arch/riscv/include/asm/word-at-a-time.h | 27 +++++++++++++++++++++ arch/riscv/mm/extable.c | 31 +++++++++++++++++++++++++ 4 files changed, 74 insertions(+)