powerpc: Save CFAR before branching in interrupt entry paths

Some of the interrupt vectors on 64-bit POWER server processors are
only 32 bytes long, which is not enough for the full first-level
interrupt handler.  For these we currently just have a branch to an
out-of-line handler.  However, this means that we corrupt the CFAR
(come-from address register) on POWER7 and later processors.

To fix this, we split the EXCEPTION_PROLOG_1 macro into two pieces:
EXCEPTION_PROLOG_0 contains the part up to the point where the CFAR
is saved in the PACA, and EXCEPTION_PROLOG_1 contains the rest.  We
then put EXCEPTION_PROLOG_0 in the short interrupt vectors before
we branch to the out-of-line handler, which contains the rest of the
first-level interrupt handler.  To facilitate this, we define new
_OOL (out of line) variants of STD_EXCEPTION_PSERIES, etc.

In order to get EXCEPTION_PROLOG_0 to be short enough, i.e., no more
than 6 instructions, it was necessary to move the stores that move
the PPR and CFAR values into the PACA into __EXCEPTION_PROLOG_1 and
to get rid of one of the two HMT_MEDIUM instructions.  Previously
there was a HMT_MEDIUM_PPR_DISCARD before the prolog, which was
nop'd out on processors with the PPR (POWER7 and later), and then
another HMT_MEDIUM inside the HMT_MEDIUM_PPR_SAVE macro call inside
__EXCEPTION_PROLOG_1, which was nop'd out on processors without PPR.
Now the HMT_MEDIUM inside EXCEPTION_PROLOG_0 is there unconditionally
and the HMT_MEDIUM_PPR_DISCARD is not strictly necessary, although
this leaves it in for the interrupt vectors where there is room for
it.

Previously we had a handler for hypervisor maintenance interrupts at
0xe50, which doesn't leave enough room for the vector for hypervisor
emulation assist interrupts at 0xe40, since we need 8 instructions.
The 0xe50 vector was only used on POWER6, as the HMI vector was moved
to 0xe60 on POWER7.  Since we don't support running in hypervisor mode
on POWER6, we just remove the handler at 0xe50.

This also changes denorm_exception_hv to use EXCEPTION_PROLOG_0
instead of open-coding it, and removes the HMT_MEDIUM_PPR_DISCARD
from the relocation-on vectors (since any CPU that supports
relocation-on interrupts also has the PPR).

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

2 files changed, 133 insertions, 46 deletions

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 370298a0bca3..4dfc51588be5 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -50,7 +50,7 @@
 #define EX_PPR          88      /* SMT thread status register (priority) */
 
 #ifdef CONFIG_RELOCATABLE
-#define EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)                      \
+#define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)                    \
         ld      r12,PACAKBASE(r13);     /* get high part of &label */   \
         mfspr   r11,SPRN_##h##SRR0;     /* save SRR0 */                 \
         LOAD_HANDLER(r12,label);                                        \
@@ -61,13 +61,15 @@
         blr;
 #else
 /* If not relocatable, we can jump directly -- and save messing with LR */
-#define EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)                      \
+#define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)                    \
         mfspr   r11,SPRN_##h##SRR0;     /* save SRR0 */                 \
         mfspr   r12,SPRN_##h##SRR1;     /* and SRR1 */                  \
         li      r10,MSR_RI;                                             \
         mtmsrd  r10,1;                  /* Set RI (EE=0) */             \
         b       label;
 #endif
+#define EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)                      \
+        __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)                    \
 
 /*
  * As EXCEPTION_PROLOG_PSERIES(), except we've already got relocation on
@@ -75,6 +77,7 @@
  * case EXCEPTION_RELON_PROLOG_PSERIES_1 will be using lr.
  */
 #define EXCEPTION_RELON_PROLOG_PSERIES(area, label, h, extra, vec)      \
+        EXCEPTION_PROLOG_0(area);                                       \
         EXCEPTION_PROLOG_1(area, extra, vec);                           \
         EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)
 
@@ -135,25 +138,32 @@ BEGIN_FTR_SECTION_NESTED(942)						\
 END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,0,942)  /*non P7*/               
 
 /*
- * Save PPR in paca whenever some register is available to use.
- * Then increase the priority.
+ * Get an SPR into a register if the CPU has the given feature
  */
-#define HMT_MEDIUM_PPR_SAVE(area, ra)                                   \
+#define OPT_GET_SPR(ra, spr, ftr)                                       \
 BEGIN_FTR_SECTION_NESTED(943)                                           \
-        mfspr   ra,SPRN_PPR;                                            \
-        std     ra,area+EX_PPR(r13);                                    \
-        HMT_MEDIUM;                                                     \
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,943) 
+        mfspr   ra,spr;                                                 \
+END_FTR_SECTION_NESTED(ftr,ftr,943)
 
-#define __EXCEPTION_PROLOG_1(area, extra, vec)                          \
+/*
+ * Save a register to the PACA if the CPU has the given feature
+ */
+#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr)                           \
+BEGIN_FTR_SECTION_NESTED(943)                                           \
+        std     ra,offset(r13);                                         \
+END_FTR_SECTION_NESTED(ftr,ftr,943)
+
+#define EXCEPTION_PROLOG_0(area)                                        \
         GET_PACA(r13);                                                  \
         std     r9,area+EX_R9(r13);     /* save r9 */                   \
-        HMT_MEDIUM_PPR_SAVE(area, r9);                                  \
+        OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR);                     \
+        HMT_MEDIUM;                                                     \
         std     r10,area+EX_R10(r13);   /* save r10 - r12 */            \
-        BEGIN_FTR_SECTION_NESTED(66);                                   \
-        mfspr   r10,SPRN_CFAR;                                          \
-        std     r10,area+EX_CFAR(r13);                                  \
-        END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66);         \
+        OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
+
+#define __EXCEPTION_PROLOG_1(area, extra, vec)                          \
+        OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR);         \
+        OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR);          \
         SAVE_LR(r10, area);                                             \
         mfcr    r9;                                                     \
         extra(vec);                                                     \
@@ -178,6 +188,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,943)
         __EXCEPTION_PROLOG_PSERIES_1(label, h)
 
 #define EXCEPTION_PROLOG_PSERIES(area, label, h, extra, vec)            \
+        EXCEPTION_PROLOG_0(area);                                       \
         EXCEPTION_PROLOG_1(area, extra, vec);                           \
         EXCEPTION_PROLOG_PSERIES_1(label, h);
 
@@ -312,6 +323,13 @@ label##_pSeries:					\
         EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common,    \
                                  EXC_STD, KVMTEST_PR, vec)
 
+/* Version of above for when we have to branch out-of-line */
+#define STD_EXCEPTION_PSERIES_OOL(vec, label)                   \
+        .globl label##_pSeries;                                 \
+label##_pSeries:                                                \
+        EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec);        \
+        EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_STD)
+
 #define STD_EXCEPTION_HV(loc, vec, label)               \
         . = loc;                                        \
         .globl label##_hv;                              \
@@ -321,6 +339,13 @@ label##_hv:						\
         EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common,    \
                                  EXC_HV, KVMTEST, vec)
 
+/* Version of above for when we have to branch out-of-line */
+#define STD_EXCEPTION_HV_OOL(vec, label)                \
+        .globl label##_hv;                              \
+label##_hv:                                             \
+        EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec);   \
+        EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_HV)
+
 #define STD_RELON_EXCEPTION_PSERIES(loc, vec, label)    \
         . = loc;                                        \
         .globl label##_relon_pSeries;                   \
@@ -331,6 +356,12 @@ label##_relon_pSeries:					\
         EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
                                        EXC_STD, KVMTEST_PR, vec)
 
+#define STD_RELON_EXCEPTION_PSERIES_OOL(vec, label)             \
+        .globl label##_relon_pSeries;                           \
+label##_relon_pSeries:                                          \
+        EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec);        \
+        EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_STD)
+
 #define STD_RELON_EXCEPTION_HV(loc, vec, label)         \
         . = loc;                                        \
         .globl label##_relon_hv;                        \
@@ -341,6 +372,12 @@ label##_relon_hv:					\
         EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
                                        EXC_HV, KVMTEST, vec)
 
+#define STD_RELON_EXCEPTION_HV_OOL(vec, label)                  \
+        .globl label##_relon_hv;                                \
+label##_relon_hv:                                               \
+        EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec);           \