[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[PATCH v5 2/6] x86: re-work memset()


  • To: "xen-devel@xxxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxxx>
  • From: Jan Beulich <jbeulich@xxxxxxxx>
  • Date: Thu, 5 Jun 2025 12:25:17 +0200
  • Autocrypt: addr=jbeulich@xxxxxxxx; keydata= xsDiBFk3nEQRBADAEaSw6zC/EJkiwGPXbWtPxl2xCdSoeepS07jW8UgcHNurfHvUzogEq5xk hu507c3BarVjyWCJOylMNR98Yd8VqD9UfmX0Hb8/BrA+Hl6/DB/eqGptrf4BSRwcZQM32aZK 7Pj2XbGWIUrZrd70x1eAP9QE3P79Y2oLrsCgbZJfEwCgvz9JjGmQqQkRiTVzlZVCJYcyGGsD /0tbFCzD2h20ahe8rC1gbb3K3qk+LpBtvjBu1RY9drYk0NymiGbJWZgab6t1jM7sk2vuf0Py O9Hf9XBmK0uE9IgMaiCpc32XV9oASz6UJebwkX+zF2jG5I1BfnO9g7KlotcA/v5ClMjgo6Gl MDY4HxoSRu3i1cqqSDtVlt+AOVBJBACrZcnHAUSuCXBPy0jOlBhxPqRWv6ND4c9PH1xjQ3NP nxJuMBS8rnNg22uyfAgmBKNLpLgAGVRMZGaGoJObGf72s6TeIqKJo/LtggAS9qAUiuKVnygo 3wjfkS9A3DRO+SpU7JqWdsveeIQyeyEJ/8PTowmSQLakF+3fote9ybzd880fSmFuIEJldWxp Y2ggPGpiZXVsaWNoQHN1c2UuY29tPsJgBBMRAgAgBQJZN5xEAhsDBgsJCAcDAgQVAggDBBYC AwECHgECF4AACgkQoDSui/t3IH4J+wCfQ5jHdEjCRHj23O/5ttg9r9OIruwAn3103WUITZee e7Sbg12UgcQ5lv7SzsFNBFk3nEQQCACCuTjCjFOUdi5Nm244F+78kLghRcin/awv+IrTcIWF hUpSs1Y91iQQ7KItirz5uwCPlwejSJDQJLIS+QtJHaXDXeV6NI0Uef1hP20+y8qydDiVkv6l IreXjTb7DvksRgJNvCkWtYnlS3mYvQ9NzS9PhyALWbXnH6sIJd2O9lKS1Mrfq+y0IXCP10eS FFGg+Av3IQeFatkJAyju0PPthyTqxSI4lZYuJVPknzgaeuJv/2NccrPvmeDg6Coe7ZIeQ8Yj t0ARxu2xytAkkLCel1Lz1WLmwLstV30g80nkgZf/wr+/BXJW/oIvRlonUkxv+IbBM3dX2OV8 AmRv1ySWPTP7AAMFB/9PQK/VtlNUJvg8GXj9ootzrteGfVZVVT4XBJkfwBcpC/XcPzldjv+3 HYudvpdNK3lLujXeA5fLOH+Z/G9WBc5pFVSMocI71I8bT8lIAzreg0WvkWg5V2WZsUMlnDL9 mpwIGFhlbM3gfDMs7MPMu8YQRFVdUvtSpaAs8OFfGQ0ia3LGZcjA6Ik2+xcqscEJzNH+qh8V m5jjp28yZgaqTaRbg3M/+MTbMpicpZuqF4rnB0AQD12/3BNWDR6bmh+EkYSMcEIpQmBM51qM EKYTQGybRCjpnKHGOxG0rfFY1085mBDZCH5Kx0cl0HVJuQKC+dV2ZY5AqjcKwAxpE75MLFkr wkkEGBECAAkFAlk3nEQCGwwACgkQoDSui/t3IH7nnwCfcJWUDUFKdCsBH/E5d+0ZnMQi+G0A nAuWpQkjM1ASeQwSHEeAWPgskBQL
  • Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>, Roger Pau Monné <roger.pau@xxxxxxxxxx>
  • Delivery-date: Thu, 05 Jun 2025 10:25:28 +0000
  • List-id: Xen developer discussion <xen-devel.lists.xenproject.org>

Move the function to its own assembly file. Having it in C just for the
entire body to be an asm() isn't really helpful. Then have two flavors:
A "basic" version using qword steps for the bulk of the operation, and an
ERMS version for modern hardware, to be substituted in via alternatives
patching.

For RET to be usable in an alternative's replacement code, extend the
CALL/JMP patching to cover the case of "JMP __x86_return_thunk" coming
last in replacement code.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
We may want to consider branching over the REP STOSQ as well, if the
number of qwords turns out to be zero.
We may also want to consider using non-REP STOS{L,W,B} for the tail.
---
v5: Re-base.
v4: Use %r8 instead of %rsi in a few places.
v3: Re-base.

--- a/xen/arch/x86/Makefile
+++ b/xen/arch/x86/Makefile
@@ -47,6 +47,7 @@ obj-$(CONFIG_RETURN_THUNK) += indirect-t
 obj-$(CONFIG_PV) += ioport_emulate.o
 obj-y += irq.o
 obj-$(CONFIG_KEXEC) += machine_kexec.o
+obj-y += memset.o
 obj-y += mm.o x86_64/mm.o
 obj-$(CONFIG_VM_EVENT) += monitor.o
 obj-y += mpparse.o
--- a/xen/arch/x86/alternative.c
+++ b/xen/arch/x86/alternative.c
@@ -346,6 +346,12 @@ static int init_or_livepatch _apply_alte
         /* 0xe8/0xe9 are relative branches; fix the offset. */
         if ( a->repl_len >= 5 && (*buf & 0xfe) == 0xe8 )
             *(int32_t *)(buf + 1) += repl - orig;
+        else if ( IS_ENABLED(CONFIG_RETURN_THUNK) &&
+                  a->repl_len > 5 && buf[a->repl_len - 5] == 0xe9 &&
+                  ((long)repl + a->repl_len +
+                   *(int32_t *)(buf + a->repl_len - 4) ==
+                   (long)__x86_return_thunk) )
+            *(int32_t *)(buf + a->repl_len - 4) += repl - orig;
 
         a->priv = 1;
 
--- /dev/null
+++ b/xen/arch/x86/memset.S
@@ -0,0 +1,30 @@
+#include <asm/asm_defns.h>
+
+.macro memset
+        and     $7, %edx
+        shr     $3, %rcx
+        movzbl  %sil, %esi
+        mov     $0x0101010101010101, %rax
+        imul    %rsi, %rax
+        mov     %rdi, %r8
+        rep stosq
+        or      %edx, %ecx
+        jz      0f
+        rep stosb
+0:
+        mov     %r8, %rax
+        RET
+.endm
+
+.macro memset_erms
+        mov     %esi, %eax
+        mov     %rdi, %r8
+        rep stosb
+        mov     %r8, %rax
+        RET
+.endm
+
+FUNC(memset)
+        mov     %rdx, %rcx
+        ALTERNATIVE memset, memset_erms, X86_FEATURE_ERMS
+END(memset)
--- a/xen/arch/x86/string.c
+++ b/xen/arch/x86/string.c
@@ -22,19 +22,6 @@ void *(memcpy)(void *dest, const void *s
     return dest;
 }
 
-void *(memset)(void *s, int c, size_t n)
-{
-    long d0, d1;
-
-    asm volatile (
-        "rep stosb"
-        : "=&c" (d0), "=&D" (d1)
-        : "a" (c), "1" (s), "0" (n)
-        : "memory");
-
-    return s;
-}
-
 void *(memmove)(void *dest, const void *src, size_t n)
 {
     long d0, d1, d2;




 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.