[ALPHA] Fix unaligned stxncpy again
diff mbox series

Message ID 20040409103244.GA1904@gondor.apana.org.au
State New, archived
Headers show
Series
  • [ALPHA] Fix unaligned stxncpy again
Related show

Commit Message

Herbert Xu April 9, 2004, 10:32 a.m. UTC
Hi:

The current stxncpy on alpha is still broken when it comes to single
word, unaligned, src misalignment > dest misalignment copies.

I've attached a program which demonstrates this problem.

It looks like the code in glibc is correct and does not suffer from
the last problem that Richard fixed where the destination got
partially cleared.

So here is the patch to revert the unaligned case to use the same code
as glibc.

Cheers,

Comments

Ivan Kokshaysky April 9, 2004, 7:35 p.m. UTC | #1
On Fri, Apr 09, 2004 at 08:32:44PM +1000, Herbert Xu wrote:
> The current stxncpy on alpha is still broken when it comes to single
> word, unaligned, src misalignment > dest misalignment copies.
> 
> I've attached a program which demonstrates this problem.

Ugh, indeed. It fails when there is a zero byte before the data.
Thanks.

> So here is the patch to revert the unaligned case to use the same code
> as glibc.

Here is simpler equivalent of that and ev6 fix.

Ivan.

--- linux.orig/arch/alpha/lib/ev6-stxncpy.S	Sun Apr  4 07:37:42 2004
+++ linux/arch/alpha/lib/ev6-stxncpy.S	Fri Apr  9 22:13:40 2004
@@ -365,7 +365,7 @@ $unaligned:
 	andnot	t2, t6, t12	# E : dest mask for a single word copy
 	or	t8, t10, t5	# E : test for end-of-count too
 
-	cmpbge	zero, t2, t3	# E :
+	cmpbge	zero, t12, t3	# E :
 	cmoveq	a2, t5, t8	# E : Latency=2, extra map slot
 	nop			# E : keep with cmoveq
 	andnot	t8, t3, t8	# E : (stall)
--- linux.orig/arch/alpha/lib/stxncpy.S	Sun Apr  4 07:38:22 2004
+++ linux/arch/alpha/lib/stxncpy.S	Fri Apr  9 22:14:24 2004
@@ -317,7 +317,7 @@ $unaligned:
 	cmpbge	zero, t1, t8	# .. e1 : is there a zero?
 	andnot	t2, t6, t12	# e0    : dest mask for a single word copy
 	or	t8, t10, t5	# .. e1 : test for end-of-count too
-	cmpbge	zero, t2, t3	# e0    :
+	cmpbge	zero, t12, t3	# e0    :
 	cmoveq	a2, t5, t8	# .. e1 :
 	andnot	t8, t3, t8	# e0    :
 	beq	t8, $u_head	# .. e1 (zdb)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
Herbert Xu April 9, 2004, 11:50 p.m. UTC | #2
On Fri, Apr 09, 2004 at 11:35:11PM +0400, Ivan Kokshaysky wrote:
> 
> Here is simpler equivalent of that and ev6 fix.

Thanks.  But is there any reason why we need to have code that
is different from glibc?
Ivan Kokshaysky April 10, 2004, 5:46 p.m. UTC | #3
On Sat, Apr 10, 2004 at 09:50:40AM +1000, Herbert Xu wrote:
> Thanks.  But is there any reason why we need to have code that
> is different from glibc?

The code is different anyway because the glibc routine clobbers
t7 register which must not be touched in the kernel.
Apparently the whole mess started with a typo in the register
renaming patch...
Yes, ideally glibc and kernel stxncpy code can be exactly the same,
but this assumes that the glibc variant is updated to not use the t7.

Ivan.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Patch
diff mbox series

Index: arch/alpha/lib/stxncpy.S
===================================================================
RCS file: /home/gondolin/herbert/src/CVS/debian/kernel-source-2.4/arch/alpha/lib/stxncpy.S,v
retrieving revision 1.4
diff -u -r1.4 stxncpy.S
--- a/arch/alpha/lib/stxncpy.S	3 Sep 2003 10:26:49 -0000	1.4
+++ b/arch/alpha/lib/stxncpy.S	9 Apr 2004 10:23:30 -0000
@@ -313,9 +313,9 @@ 
 	lda	t2, -1		# e0    : for creating masks later
 	beq	t12, $u_head	# .. e1 :
 
-	extql	t2, a1, t2	# e0    :
+	mskqh	t2, t5, t2	# e0	: begin src validity mask
 	cmpbge	zero, t1, t8	# .. e1 : is there a zero?
-	andnot	t2, t6, t12	# e0    : dest mask for a single word copy
+	extql	t2, a1, t2	# e0    :
 	or	t8, t10, t5	# .. e1 : test for end-of-count too
 	cmpbge	zero, t2, t3	# e0    :
 	cmoveq	a2, t5, t8	# .. e1 :
@@ -330,14 +330,14 @@ 
 	ldq_u	t0, 0(a0)	# e0    :
 	negq	t8, t6		# .. e1 : build bitmask of bytes <= zero
 	mskqh	t1, t4, t1	# e0    :
-	and	t6, t8, t2	# .. e1 :
-	subq	t2, 1, t6	# e0    :
-	or	t6, t2, t8	# e1    :
+	and	t6, t8, t12	# .. e1 :
+	subq	t12, 1, t6	# e0    :
+	or	t6, t12, t8	# e1    :
 
-	zapnot	t12, t8, t12	# e0    : prepare source word; mirror changes
+	zapnot	t2, t8, t2	# e0    : prepare source word; mirror changes
 	zapnot	t1, t8, t1	# .. e1 : to source validity mask
 
-	andnot	t0, t12, t0	# e0    : zero place for source to reside
+	andnot	t0, t2, t0	# e0    : zero place for source to reside
 	or	t0, t1, t0	# e1    : and put it there
 	stq_u	t0, 0(a0)	# e0    :
 	ret	(t9)		# .. e1 :