Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel...

[~andy/linux] / arch / mips / kernel / r4k_fpu.S

diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 55ffe149dae90582bd2be2ec1d828639eae79b8d..73b0ddf910d41b08dd1bacd97f862e97f94f4c95 100644 (file)
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -35,7 +35,15 @@
 LEAF(_save_fp_context)
        cfc1    t1, fcr31
 
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+       .set    push
+#ifdef CONFIG_CPU_MIPS32_R2
+       .set    mips64r2
+       mfc0    t0, CP0_STATUS
+       sll     t0, t0, 5
+       bgez    t0, 1f                  # skip storing odd if FR=0
+        nop
+#endif
        /* Store the 16 odd double precision registers */
        EX      sdc1 $f1, SC_FPREGS+8(a0)
        EX      sdc1 $f3, SC_FPREGS+24(a0)
@@ -53,6 +61,7 @@ LEAF(_save_fp_context)
        EX      sdc1 $f27, SC_FPREGS+216(a0)
        EX      sdc1 $f29, SC_FPREGS+232(a0)
        EX      sdc1 $f31, SC_FPREGS+248(a0)
+1:     .set    pop
 #endif
 
        /* Store the 16 even double precision registers */
@@ -82,7 +91,31 @@ LEAF(_save_fp_context)
 LEAF(_save_fp_context32)
        cfc1    t1, fcr31
 
-       EX      sdc1 $f0, SC32_FPREGS+0(a0)
+       mfc0    t0, CP0_STATUS
+       sll     t0, t0, 5
+       bgez    t0, 1f                  # skip storing odd if FR=0
+        nop
+
+       /* Store the 16 odd double precision registers */
+       EX      sdc1 $f1, SC32_FPREGS+8(a0)
+       EX      sdc1 $f3, SC32_FPREGS+24(a0)
+       EX      sdc1 $f5, SC32_FPREGS+40(a0)
+       EX      sdc1 $f7, SC32_FPREGS+56(a0)
+       EX      sdc1 $f9, SC32_FPREGS+72(a0)
+       EX      sdc1 $f11, SC32_FPREGS+88(a0)
+       EX      sdc1 $f13, SC32_FPREGS+104(a0)
+       EX      sdc1 $f15, SC32_FPREGS+120(a0)
+       EX      sdc1 $f17, SC32_FPREGS+136(a0)
+       EX      sdc1 $f19, SC32_FPREGS+152(a0)
+       EX      sdc1 $f21, SC32_FPREGS+168(a0)
+       EX      sdc1 $f23, SC32_FPREGS+184(a0)
+       EX      sdc1 $f25, SC32_FPREGS+200(a0)
+       EX      sdc1 $f27, SC32_FPREGS+216(a0)
+       EX      sdc1 $f29, SC32_FPREGS+232(a0)
+       EX      sdc1 $f31, SC32_FPREGS+248(a0)
+
+       /* Store the 16 even double precision registers */
+1:     EX      sdc1 $f0, SC32_FPREGS+0(a0)
        EX      sdc1 $f2, SC32_FPREGS+16(a0)
        EX      sdc1 $f4, SC32_FPREGS+32(a0)
        EX      sdc1 $f6, SC32_FPREGS+48(a0)
@@ -113,8 +146,17 @@ LEAF(_save_fp_context32)
  *  - cp1 status/control register
  */
 LEAF(_restore_fp_context)
-       EX      lw t0, SC_FPC_CSR(a0)
-#ifdef CONFIG_64BIT
+       EX      lw t1, SC_FPC_CSR(a0)
+
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
+       .set    push
+#ifdef CONFIG_CPU_MIPS32_R2
+       .set    mips64r2
+       mfc0    t0, CP0_STATUS
+       sll     t0, t0, 5
+       bgez    t0, 1f                  # skip loading odd if FR=0
+        nop
+#endif
        EX      ldc1 $f1, SC_FPREGS+8(a0)
        EX      ldc1 $f3, SC_FPREGS+24(a0)
        EX      ldc1 $f5, SC_FPREGS+40(a0)
@@ -131,6 +173,7 @@ LEAF(_restore_fp_context)
        EX      ldc1 $f27, SC_FPREGS+216(a0)
        EX      ldc1 $f29, SC_FPREGS+232(a0)
        EX      ldc1 $f31, SC_FPREGS+248(a0)
+1:     .set pop
 #endif
        EX      ldc1 $f0, SC_FPREGS+0(a0)
        EX      ldc1 $f2, SC_FPREGS+16(a0)
@@ -148,7 +191,7 @@ LEAF(_restore_fp_context)
        EX      ldc1 $f26, SC_FPREGS+208(a0)
        EX      ldc1 $f28, SC_FPREGS+224(a0)
        EX      ldc1 $f30, SC_FPREGS+240(a0)
-       ctc1    t0, fcr31
+       ctc1    t1, fcr31
        jr      ra
         li     v0, 0                                   # success
        END(_restore_fp_context)
@@ -156,8 +199,31 @@ LEAF(_restore_fp_context)
 #ifdef CONFIG_MIPS32_COMPAT
 LEAF(_restore_fp_context32)
        /* Restore an o32 sigcontext.  */
-       EX      lw t0, SC32_FPC_CSR(a0)
-       EX      ldc1 $f0, SC32_FPREGS+0(a0)
+       EX      lw t1, SC32_FPC_CSR(a0)
+
+       mfc0    t0, CP0_STATUS
+       sll     t0, t0, 5
+       bgez    t0, 1f                  # skip loading odd if FR=0
+        nop
+
+       EX      ldc1 $f1, SC32_FPREGS+8(a0)
+       EX      ldc1 $f3, SC32_FPREGS+24(a0)
+       EX      ldc1 $f5, SC32_FPREGS+40(a0)
+       EX      ldc1 $f7, SC32_FPREGS+56(a0)
+       EX      ldc1 $f9, SC32_FPREGS+72(a0)
+       EX      ldc1 $f11, SC32_FPREGS+88(a0)
+       EX      ldc1 $f13, SC32_FPREGS+104(a0)
+       EX      ldc1 $f15, SC32_FPREGS+120(a0)
+       EX      ldc1 $f17, SC32_FPREGS+136(a0)
+       EX      ldc1 $f19, SC32_FPREGS+152(a0)
+       EX      ldc1 $f21, SC32_FPREGS+168(a0)
+       EX      ldc1 $f23, SC32_FPREGS+184(a0)
+       EX      ldc1 $f25, SC32_FPREGS+200(a0)
+       EX      ldc1 $f27, SC32_FPREGS+216(a0)
+       EX      ldc1 $f29, SC32_FPREGS+232(a0)
+       EX      ldc1 $f31, SC32_FPREGS+248(a0)
+
+1:     EX      ldc1 $f0, SC32_FPREGS+0(a0)
        EX      ldc1 $f2, SC32_FPREGS+16(a0)
        EX      ldc1 $f4, SC32_FPREGS+32(a0)
        EX      ldc1 $f6, SC32_FPREGS+48(a0)
@@ -173,7 +239,7 @@ LEAF(_restore_fp_context32)
        EX      ldc1 $f26, SC32_FPREGS+208(a0)
        EX      ldc1 $f28, SC32_FPREGS+224(a0)
        EX      ldc1 $f30, SC32_FPREGS+240(a0)
-       ctc1    t0, fcr31
+       ctc1    t1, fcr31
        jr      ra
         li     v0, 0                                   # success
        END(_restore_fp_context32)