Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS updates from Ralf Baechle:
 "This is the main pull request for MIPS for Linux 4.1.  Most
  noteworthy:

   - Add more Octeon-optimized crypto functions
   - Octeon crypto preemption and locking fixes
   - Little endian support for Octeon
   - Use correct CSR to soft reset Octeons
   - Support LEDs on the Octeon-based DSR-1000N
   - Fix PCI interrupt mapping for the Octeon-based DSR-1000N
   - Mark prom_free_prom_memory() as __init for a number of systems
   - Support for Imagination's Pistachio SOC.  This includes arch and
     CLK bits.  I'd like to merge pinctrl bits later
   - Improve parallelism of csum_partial for certain pipelines
   - Organize DTB files in subdirs like other architectures
   - Implement read_sched_clock for all MIPS platforms other than
     Octeon
   - Massive series of 38 fixes and cleanups for the FPU emulator /
     kernel
   - Further FPU remulator work to support new features.  This sits on a
     separate branch which also has been pulled into the 4.1 KVM branch
   - Clean up and fixes for the SEAD3 eval board; remove unused file
   - Various updates for Netlogic platforms
   - A number of small updates for Loongson 3 platforms
   - Increase the memory limit for ATH79 platforms to 256MB
   - A fair number of fixes and updates for BCM47xx platforms
   - Finish the implementation of XPA support
   - MIPS FDC support.  No, not floppy controller but Fast Debug Channel :)
   - Detect the R16000 used in SGI legacy platforms
   - Fix Kconfig dependencies for the SSB bus support"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (265 commits)
  MIPS: Makefile: Fix MIPS ASE detection code
  MIPS: asm: elf: Set O32 default FPU flags
  MIPS: BCM47XX: Fix detecting Microsoft MN-700 & Asus WL500G
  MIPS: Kconfig: Disable SMP/CPS for 64-bit
  MIPS: Hibernate: flush TLB entries earlier
  MIPS: smp-cps: cpu_set FPU mask if FPU present
  MIPS: lose_fpu(): Disable FPU when MSA enabled
  MIPS: ralink: add missing symbol for RALINK_ILL_ACC
  MIPS: ralink: Fix bad config symbol in PCI makefile.
  SSB: fix Kconfig dependencies
  MIPS: Malta: Detect and fix bad memsize values
  Revert "MIPS: Avoid pipeline stalls on some MIPS32R2 cores."
  MIPS: Octeon: Delete override of cpu_has_mips_r2_exec_hazard.
  MIPS: Fix cpu_has_mips_r2_exec_hazard.
  MIPS: kernel: entry.S: Set correct ISA level for mips_ihb
  MIPS: asm: spinlock: Fix addiu instruction for R10000_LLSC_WAR case
  MIPS: r4kcache: Use correct base register for MIPS R6 cache flushes
  MIPS: Kconfig: Fix typo for the r2-to-r6 emulator kernel parameter
  MIPS: unaligned: Fix regular load/store instruction emulation for EVA
  MIPS: unaligned: Surround load/store macros in do {} while statements
  ...

1 files changed, 19 insertions, 19 deletions

diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 4c721e247ac9..ed88647b57e2 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -76,10 +76,10 @@
         LOAD    _t1, (offset + UNIT(1))(src);                   \
         LOAD    _t2, (offset + UNIT(2))(src);                   \
         LOAD    _t3, (offset + UNIT(3))(src);                   \
+        ADDC(_t0, _t1);                                         \
+        ADDC(_t2, _t3);                                         \
         ADDC(sum, _t0);                                         \
-        ADDC(sum, _t1);                                         \
-        ADDC(sum, _t2);                                         \
-        ADDC(sum, _t3)
+        ADDC(sum, _t2)
 
 #ifdef USE_DOUBLE
 #define CSUM_BIGCHUNK(src, offset, sum, _t0, _t1, _t2, _t3)     \
@@ -504,21 +504,21 @@ LEAF(csum_partial)
         SUB     len, len, 8*NBYTES
         ADD     src, src, 8*NBYTES
         STORE(t0, UNIT(0)(dst), .Ls_exc\@)
-        ADDC(sum, t0)
+        ADDC(t0, t1)
         STORE(t1, UNIT(1)(dst), .Ls_exc\@)
-        ADDC(sum, t1)
+        ADDC(sum, t0)
         STORE(t2, UNIT(2)(dst), .Ls_exc\@)
-        ADDC(sum, t2)
+        ADDC(t2, t3)
         STORE(t3, UNIT(3)(dst), .Ls_exc\@)
-        ADDC(sum, t3)
+        ADDC(sum, t2)
         STORE(t4, UNIT(4)(dst), .Ls_exc\@)
-        ADDC(sum, t4)
+        ADDC(t4, t5)
         STORE(t5, UNIT(5)(dst), .Ls_exc\@)
-        ADDC(sum, t5)
+        ADDC(sum, t4)
         STORE(t6, UNIT(6)(dst), .Ls_exc\@)
-        ADDC(sum, t6)
+        ADDC(t6, t7)
         STORE(t7, UNIT(7)(dst), .Ls_exc\@)
-        ADDC(sum, t7)
+        ADDC(sum, t6)
         .set    reorder                         /* DADDI_WAR */
         ADD     dst, dst, 8*NBYTES
         bgez    len, 1b
@@ -544,13 +544,13 @@ LEAF(csum_partial)
         SUB     len, len, 4*NBYTES
         ADD     src, src, 4*NBYTES
         STORE(t0, UNIT(0)(dst), .Ls_exc\@)
-        ADDC(sum, t0)
+        ADDC(t0, t1)
         STORE(t1, UNIT(1)(dst), .Ls_exc\@)
-        ADDC(sum, t1)
+        ADDC(sum, t0)
         STORE(t2, UNIT(2)(dst), .Ls_exc\@)
-        ADDC(sum, t2)
+        ADDC(t2, t3)
         STORE(t3, UNIT(3)(dst), .Ls_exc\@)
-        ADDC(sum, t3)
+        ADDC(sum, t2)
         .set    reorder                         /* DADDI_WAR */
         ADD     dst, dst, 4*NBYTES
         beqz    len, .Ldone\@
@@ -649,13 +649,13 @@ LEAF(csum_partial)
         nop                             # improves slotting
 #endif
         STORE(t0, UNIT(0)(dst), .Ls_exc\@)
-        ADDC(sum, t0)
+        ADDC(t0, t1)
         STORE(t1, UNIT(1)(dst), .Ls_exc\@)
-        ADDC(sum, t1)
+        ADDC(sum, t0)
         STORE(t2, UNIT(2)(dst), .Ls_exc\@)
-        ADDC(sum, t2)
+        ADDC(t2, t3)
         STORE(t3, UNIT(3)(dst), .Ls_exc\@)
-        ADDC(sum, t3)
+        ADDC(sum, t2)
         .set    reorder                         /* DADDI_WAR */
         ADD     dst, dst, 4*NBYTES
         bne     len, rem, 1b