Re: [PATCH] x86/xsave: Robustify and merge macros

From: Borislav Petkov <bp@alien8.de>
To: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: X86 ML <x86@kernel.org>, LKML <linux-kernel@vger.kernel.org>,
	"H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Oleg Nesterov <oleg@redhat.com>,
	Andy Lutomirski <luto@amacapital.net>
Subject: Re: [PATCH] x86/xsave: Robustify and merge macros
Date: Sat, 4 Apr 2015 11:25:36 +0200	[thread overview]
Message-ID: <20150404092536.GB21152@pd.tnic> (raw)
In-Reply-To: <20150404083611.GA5922@chrystal.uk.oracle.com>

On Sat, Apr 04, 2015 at 10:36:11AM +0200, Quentin Casasnovas wrote:
> Since all of these are compile time constants, could we not use the safe
> variant on that same page?  Not that I'm too worried about the signed right
> shift but heh that would be portable and should not impact performance
> anyway, so no added value in using the optimized version is there?

Seems to work with the experimental diff below. I need to do

	-(-(x < y))

with the last term though as we're working with s32s.

---

diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 44a1fc5439d3..2cb6da2716bf 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -53,14 +53,14 @@
  * Shamelessly stolen and adapted from:
  * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
  */
-#define alt_max_short(a,b)	(((a) - (((a) - (b)) & (((a) - (b)) >> 15))) & 0xffff)
+#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
 
 .macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
 140:
 	\oldinstr
 141:
-	.skip -((alt_max_short(new_len1, new_len2) - old_len) > 0) * \
-		(alt_max_short(new_len1, new_len2) - old_len),0x90
+	.skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
+		(alt_max_short(new_len1, new_len2) - (old_len)),0x90
 142:
 
 	.pushsection .altinstructions,"a"
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 93118fb23976..453b6a05a07e 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -29,6 +29,14 @@ ENTRY(__memset)
 	ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memset_erms", X86_FEATURE_ERMS
 
+	ALTERNATIVE_2 \
+		".byte 0xc3, 0xc3, 0xc3", \
+		".byte 0x66, 0x66, 0x66, 0x90", \
+		X86_FEATURE_ALWAYS, \
+		".byte 0x66, 0x66, 0x66, 0x66, 0xcc", \
+		X86_FEATURE_ALWAYS
+
+
 	movq %rdi,%r9
 	movq %rdx,%rcx
 	andl $7,%edx

> On the bonus side, you're getting rid of the double 'alt_end_marker' label
> in case of an alternative_2()!
> 
> Looks good to me and I find it much easier to understand here :)

Cool. Please give it more critical staring as we're under time pressure
here.

Thanks!

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.
--
