From: Dave Jiang
quoted hunk
Sent: 24 September 2020 00:11
The MOVDIR64B instruction can be used by other wrapper instructions. Move
the asm code to special_insns.h and have iosubmit_cmds512() call the
asm function.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
---
arch/x86/include/asm/io.h | 17 +++--------------
arch/x86/include/asm/special_insns.h | 19 +++++++++++++++++++
2 files changed, 22 insertions(+), 14 deletions(-)
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index e1aa17a468a8..d726459d08e5 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
...
quoted hunk
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 59a3e13204c3..2a5abd27bb86 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -234,6 +234,25 @@ static inline void clwb(volatile void *__p)
#define nop() asm volatile ("nop")
+/* The dst parameter must be 64-bytes aligned */
+static inline void movdir64b(void *dst, const void *src)
+{
+ /*
+ * Note that this isn't an "on-stack copy", just definition of "dst"
+ * as a pointer to 64-bytes of stuff that is going to be overwritten.
+ * In the MOVDIR64B case that may be needed as you can use the
+ * MOVDIR64B instruction to copy arbitrary memory around. This trick
+ * lets the compiler know how much gets clobbered.
+ */
+ volatile struct { char _[64]; } *__dst = dst;
+
+ /* MOVDIR64B [rdx], rax */
+ asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02"
+ :
+ : "m" (*(struct { char _[64];} **)src), "a" (__dst)
+ : "memory");
+}
+
#endif /* __KERNEL__ */
You've lost the "d" (src).
You don't need the 'memory' clobber, just:
static inline void movdir64b(void *dst, const void *src)
{
/*
* 64 bytes from dst are marked as modified for completeness.
* Since the writes bypass the cache later reads may return
* old data anyway.
*/
/* MOVDIR64B [rdx], rax */
asm volatile (".byte 0x66, 0x0f, 0x38, 0xf8, 0x02"
: "=m" ((struct { char _[64];} *)dst),
: "m" ((struct { char _[64];} *)src), "d" (src), "a" (dst));
}
I've checked that the "m" constraint on src does force (at least one
version of) gcc to actually write to the supplied buffer.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)