[kernel/f18] Power: Fix VMX fix for memcpy case (rhbz 862420)

Tue Oct 2 20:39:56 UTC 2012

commit b48142ecf2278a715b23f8b9e8c8d855dd0b8215
Author: Justin M. Forbes <jforbes at redhat.com>
Date:   Tue Oct 2 15:36:46 2012 -0500

    Power: Fix VMX fix for memcpy case (rhbz 862420)

 kernel.spec                               |    9 +++
 powerpc-fix-VMX-fix-for-memcpy-case.patch |   97 +++++++++++++++++++++++++++++
 2 files changed, 106 insertions(+), 0 deletions(-)
---

diff --git a/kernel.spec b/kernel.spec
index db1dabf..5431117 100644
--- a/kernel.spec
+++ b/kernel.spec
@@ -759,6 +759,9 @@ Patch22066: virtio-scsi-Initialize-scatterlist-structure.patch
 #rhbz 846037
 Patch22067: selinux-Fix-sel_netnode_insert-suspicious-rcu-dereference.patch
 
+#rhbz 862420
+Patch22068: powerpc-fix-VMX-fix-for-memcpy-case.patch
+
 # END OF PATCH DEFINITIONS
 
 %endif
@@ -1468,6 +1471,9 @@ ApplyPatch virtio-scsi-Initialize-scatterlist-structure.patch
 #rhbz 846037
 ApplyPatch selinux-Fix-sel_netnode_insert-suspicious-rcu-dereference.patch
 
+#rhbz 862420
+ApplyPatch powerpc-fix-VMX-fix-for-memcpy-case.patch
+
 # END OF PATCH APPLICATIONS
 
 %endif
@@ -2320,6 +2326,9 @@ fi
 #                 ||----w |
 #                 ||     ||
 %changelog
+* Tue Oct 02 2012 Justin M. Forbes <jforbes at redhat.com> - 3.6.0-2
+- Power: Fix VMX fix for memcpy case (rhbz 862420)
+
 * Tue Oct 02 2012 Josh Boyer <jwboyer at redhat.com>
 - Patch from David Howells to fix overflow on 32-bit X.509 certs (rhbz 861322)
 
diff --git a/powerpc-fix-VMX-fix-for-memcpy-case.patch b/powerpc-fix-VMX-fix-for-memcpy-case.patch
new file mode 100644
index 0000000..78a0a70
--- /dev/null
+++ b/powerpc-fix-VMX-fix-for-memcpy-case.patch
@@ -0,0 +1,97 @@
+From patchwork Tue Oct  2 00:59:13 2012
+Content-Type: text/plain; charset="utf-8"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Subject: powerpc: fix VMX fix for memcpy case
+Date: Mon, 01 Oct 2012 14:59:13 -0000
+From: Nishanth Aravamudan <nacc at linux.vnet.ibm.com>
+X-Patchwork-Id: 188371
+Message-Id: <20121002005912.GA27768 at linux.vnet.ibm.com>
+To: Anton Blanchard <anton at samba.org>
+Cc: paulus at samba.org, linuxppc-dev at lists.ozlabs.org
+
+[urgh, sorry Anton, Ben & Paul, inadvertently hit send before adding
+linuxppc-dev to the cc!]
+
+Hi Anton,
+
+In 2fae7cdb60240e2e2d9b378afbf6d9fcce8a3890 ("powerpc: Fix VMX in
+interrupt check in POWER7 copy loops"), I think you inadvertently
+introduced a regression for memcpy on POWER7 machines. copyuer and
+memcpy diverge slightly in their use of cr1 (copyuser doesn't use it,
+but memcpy does) and you end up clobbering that register with your fix.
+That results in (taken from an FC18 kernel):
+
+[   18.824604] Unrecoverable VMX/Altivec Unavailable Exception f20 at c000000000052f40
+[   18.824618] Oops: Unrecoverable VMX/Altivec Unavailable Exception, sig: 6 [#1]
+[   18.824623] SMP NR_CPUS=1024 NUMA pSeries
+[   18.824633] Modules linked in: tg3(+) be2net(+) cxgb4(+) ipr(+) sunrpc xts lrw gf128mul dm_crypt dm_round_robin dm_multipath linear raid10 raid456 async_raid6_recov async_memcpy async_pq raid6_pq async_xor xor async_tx raid1 raid0 scsi_dh_rdac scsi_dh_hp_sw scsi_dh_emc scsi_dh_alua squashfs cramfs
+[   18.824705] NIP: c000000000052f40 LR: c00000000020b874 CTR: 0000000000000512
+[   18.824709] REGS: c000001f1fef7790 TRAP: 0f20   Not tainted  (3.6.0-0.rc6.git0.2.fc18.ppc64)
+[   18.824713] MSR: 8000000000009032 <SF,EE,ME,IR,DR,RI>  CR: 4802802e  XER: 20000010
+[   18.824726] SOFTE: 0
+[   18.824728] CFAR: 0000000000000f20
+[   18.824731] TASK = c000000fa7128400[0] 'swapper/24' THREAD: c000000fa7480000 CPU: 24
+GPR00: 00000000ffffffc0 c000001f1fef7a10 c00000000164edc0 c000000f9b9a8120
+GPR04: c000000f9b9a8124 0000000000001438 0000000000000060 03ffffff064657ee
+GPR08: 0000000080000000 0000000000000010 0000000000000020 0000000000000030
+GPR12: 0000000028028022 c00000000ff25400 0000000000000001 0000000000000000
+GPR16: 0000000000000000 7fffffffffffffff c0000000016b2180 c00000000156a500
+GPR20: c000000f968c7a90 c0000000131c31d8 c000001f1fef4000 c000000001561d00
+GPR24: 000000000000000a 0000000000000000 0000000000000001 0000000000000012
+GPR28: c000000fa5c04f80 00000000000008bc c0000000015c0a28 000000000000022e
+[   18.824792] NIP [c000000000052f40] .memcpy_power7+0x5a0/0x7c4
+[   18.824797] LR [c00000000020b874] .pcpu_free_area+0x174/0x2d0
+[   18.824800] Call Trace:
+[   18.824803] [c000001f1fef7a10] [c000000000052c14] .memcpy_power7+0x274/0x7c4 (unreliable)
+[   18.824809] [c000001f1fef7b10] [c00000000020b874] .pcpu_free_area+0x174/0x2d0
+[   18.824813] [c000001f1fef7bb0] [c00000000020ba88] .free_percpu+0xb8/0x1b0
+[   18.824819] [c000001f1fef7c50] [c00000000043d144] .throtl_pd_exit+0x94/0xd0
+[   18.824824] [c000001f1fef7cf0] [c00000000043acf8] .blkg_free+0x88/0xe0
+[   18.824829] [c000001f1fef7d90] [c00000000018c048] .rcu_process_callbacks+0x2e8/0x8a0
+[   18.824835] [c000001f1fef7e90] [c0000000000a8ce8] .__do_softirq+0x158/0x4d0
+[   18.824840] [c000001f1fef7f90] [c000000000025ecc] .call_do_softirq+0x14/0x24
+[   18.824845] [c000000fa7483650] [c000000000010e80] .do_softirq+0x160/0x1a0
+[   18.824850] [c000000fa74836f0] [c0000000000a94a4] .irq_exit+0xf4/0x120
+[   18.824854] [c000000fa7483780] [c000000000020c44] .timer_interrupt+0x154/0x4d0
+[   18.824859] [c000000fa7483830] [c000000000003be0] decrementer_common+0x160/0x180
+[   18.824866] --- Exception: 901 at .plpar_hcall_norets+0x84/0xd4
+[   18.824866]     LR = .check_and_cede_processor+0x48/0x80
+[   18.824871] [c000000fa7483b20] [c00000000007f018] .check_and_cede_processor+0x18/0x80 (unreliable)
+[   18.824877] [c000000fa7483b90] [c00000000007f104] .dedicated_cede_loop+0x84/0x150
+[   18.824883] [c000000fa7483c50] [c0000000006bc030] .cpuidle_enter+0x30/0x50
+[   18.824887] [c000000fa7483cc0] [c0000000006bc9f4] .cpuidle_idle_call+0x104/0x720
+[   18.824892] [c000000fa7483d80] [c000000000070af8] .pSeries_idle+0x18/0x40
+[   18.824897] [c000000fa7483df0] [c000000000019084] .cpu_idle+0x1a4/0x380
+[   18.824902] [c000000fa7483ec0] [c0000000008a4c18] .start_secondary+0x520/0x528
+[   18.824907] [c000000fa7483f90] [c0000000000093f0] .start_secondary_prolog+0x10/0x14
+[   18.824911] Instruction dump:
+[   18.824914] 38840008 90030000 90e30004 38630008 7ca62850 7cc300d0 78c7e102 7cf01120
+[   18.824923] 78c60660 39200010 39400020 39600030 <7e00200c> 7c0020ce 38840010 409f001c
+[   18.824935] ---[ end trace 0bb95124affaaa45 ]---
+[   18.825046] Unrecoverable VMX/Altivec Unavailable Exception f20 at c000000000052d08
+
+I believe the right fix is to make memcpy match usercopy and not use
+cr1.
+
+Signed-off-by: Nishanth Aravamudan <nacc at us.ibm.com>
+
+---
+I've not tested this fix yet, but I think it's logically correct.
+Probably needs to go to 3.6-stable as well.
+
+diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
+index 7ba6c96..0663630 100644
+--- a/arch/powerpc/lib/memcpy_power7.S
++++ b/arch/powerpc/lib/memcpy_power7.S
+@@ -239,8 +239,8 @@ _GLOBAL(memcpy_power7)
+ 	ori	r9,r9,1		/* stream=1 */
+ 
+ 	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
+-	cmpldi	cr1,r7,0x3FF
+-	ble	cr1,1f
++	cmpldi	r7,0x3FF
++	ble	1f
+ 	li	r7,0x3FF
+ 1:	lis	r0,0x0E00	/* depth=7 */
+ 	sldi	r7,r7,7
