Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Benjamin Herrenschmidt:
 "So from the depth of frozen Minnesota, here's the powerpc pull request
  for 3.9.  It has a few interesting highlights, in addition to the
  usual bunch of bug fixes, minor updates, embedded device tree updates
  and new boards:

   - Hand tuned asm implementation of SHA1 (by Paulus & Michael
     Ellerman)

   - Support for Doorbell interrupts on Power8 (kind of fast
     thread-thread IPIs) by Ian Munsie

   - Long overdue cleanup of the way we handle relocation of our open
     firmware trampoline (prom_init.c) on 64-bit by Anton Blanchard

   - Support for saving/restoring & context switching the PPR (Processor
     Priority Register) on server processors that support it.  This
     allows the kernel to preserve thread priorities established by
     userspace.  By Haren Myneni.

   - DAWR (new watchpoint facility) support on Power8 by Michael Neuling

   - Ability to change the DSCR (Data Stream Control Register) which
     controls cache prefetching on a running process via ptrace by
     Alexey Kardashevskiy

   - Support for context switching the TAR register on Power8 (new
     branch target register meant to be used by some new specific
     userspace perf event interrupt facility which is yet to be enabled)
     by Ian Munsie.

   - Improve preservation of the CFAR register (which captures the
     origin of a branch) on various exception conditions by Paulus.

   - Move the Bestcomm DMA driver from arch powerpc to drivers/dma where
     it belongs by Philippe De Muyter

   - Support for Transactional Memory on Power8 by Michael Neuling
     (based on original work by Matt Evans).  For those curious about
     the feature, the patch contains a pretty good description."

(See commit db8ff907027b: "powerpc: Documentation for transactional
memory on powerpc" for the mentioned description added to the file
Documentation/powerpc/transactional_memory.txt)

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (140 commits)
  powerpc/kexec: Disable hard IRQ before kexec
  powerpc/85xx: l2sram - Add compatible string for BSC9131 platform
  powerpc/85xx: bsc9131 - Correct typo in SDHC device node
  powerpc/e500/qemu-e500: enable coreint
  powerpc/mpic: allow coreint to be determined by MPIC version
  powerpc/fsl_pci: Store the pci ctlr device ptr in the pci ctlr struct
  powerpc/85xx: Board support for ppa8548
  powerpc/fsl: remove extraneous DIU platform functions
  arch/powerpc/platforms/85xx/p1022_ds.c: adjust duplicate test
  powerpc: Documentation for transactional memory on powerpc
  powerpc: Add transactional memory to pseries and ppc64 defconfigs
  powerpc: Add config option for transactional memory
  powerpc: Add transactional memory to POWER8 cpu features
  powerpc: Add new transactional memory state to the signal context
  powerpc: Hook in new transactional memory code
  powerpc: Routines for FP/VSX/VMX unavailable during a transaction
  powerpc: Add transactional memory unavaliable execption handler
  powerpc: Add reclaim and recheckpoint functions for context switching transactional memory processes
  powerpc: Add FP/VSX and VMX register load functions for transactional memory
  powerpc: Add helper functions for transactional memory context switching
  ...

1 files changed, 108 insertions, 2 deletions

diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 2d0e1f5d8339..cea8496091ff 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -30,7 +30,6 @@
 #define ACCOUNT_STOLEN_TIME
 #else
 #define ACCOUNT_CPU_USER_ENTRY(ra, rb)                                  \
-        beq     2f;                     /* if from kernel mode */       \
         MFTB(ra);                       /* get timebase */              \
         ld      rb,PACA_STARTTIME_USER(r13);                            \
         std     ra,PACA_STARTTIME(r13);                                 \
@@ -38,7 +37,6 @@
         ld      ra,PACA_USER_TIME(r13);                                 \
         add     ra,ra,rb;               /* add on to user time */       \
         std     ra,PACA_USER_TIME(r13);                                 \
-2:
 
 #define ACCOUNT_CPU_USER_EXIT(ra, rb)                                   \
         MFTB(ra);                       /* get timebase */              \
@@ -125,6 +123,89 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define REST_16VRS(n,b,base)    REST_8VRS(n,b,base); REST_8VRS(n+8,b,base)
 #define REST_32VRS(n,b,base)    REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
 
+/* Save/restore FPRs, VRs and VSRs from their checkpointed backups in
+ * thread_struct:
+ */
+#define SAVE_FPR_TRANSACT(n, base)      stfd n,THREAD_TRANSACT_FPR0+    \
+                                        8*TS_FPRWIDTH*(n)(base)
+#define SAVE_2FPRS_TRANSACT(n, base)    SAVE_FPR_TRANSACT(n, base);     \
+                                        SAVE_FPR_TRANSACT(n+1, base)
+#define SAVE_4FPRS_TRANSACT(n, base)    SAVE_2FPRS_TRANSACT(n, base);   \
+                                        SAVE_2FPRS_TRANSACT(n+2, base)
+#define SAVE_8FPRS_TRANSACT(n, base)    SAVE_4FPRS_TRANSACT(n, base);   \
+                                        SAVE_4FPRS_TRANSACT(n+4, base)
+#define SAVE_16FPRS_TRANSACT(n, base)   SAVE_8FPRS_TRANSACT(n, base);   \
+                                        SAVE_8FPRS_TRANSACT(n+8, base)
+#define SAVE_32FPRS_TRANSACT(n, base)   SAVE_16FPRS_TRANSACT(n, base);  \
+                                        SAVE_16FPRS_TRANSACT(n+16, base)
+
+#define REST_FPR_TRANSACT(n, base)      lfd     n,THREAD_TRANSACT_FPR0+ \
+                                        8*TS_FPRWIDTH*(n)(base)
+#define REST_2FPRS_TRANSACT(n, base)    REST_FPR_TRANSACT(n, base);     \
+                                        REST_FPR_TRANSACT(n+1, base)
+#define REST_4FPRS_TRANSACT(n, base)    REST_2FPRS_TRANSACT(n, base);   \
+                                        REST_2FPRS_TRANSACT(n+2, base)
+#define REST_8FPRS_TRANSACT(n, base)    REST_4FPRS_TRANSACT(n, base);   \
+                                        REST_4FPRS_TRANSACT(n+4, base)
+#define REST_16FPRS_TRANSACT(n, base)   REST_8FPRS_TRANSACT(n, base);   \
+                                        REST_8FPRS_TRANSACT(n+8, base)
+#define REST_32FPRS_TRANSACT(n, base)   REST_16FPRS_TRANSACT(n, base);  \
+                                        REST_16FPRS_TRANSACT(n+16, base)
+
+
+#define SAVE_VR_TRANSACT(n,b,base)      li b,THREAD_TRANSACT_VR0+(16*(n)); \
+                                        stvx n,b,base
+#define SAVE_2VRS_TRANSACT(n,b,base)    SAVE_VR_TRANSACT(n,b,base);     \
+                                        SAVE_VR_TRANSACT(n+1,b,base)
+#define SAVE_4VRS_TRANSACT(n,b,base)    SAVE_2VRS_TRANSACT(n,b,base);   \
+                                        SAVE_2VRS_TRANSACT(n+2,b,base)
+#define SAVE_8VRS_TRANSACT(n,b,base)    SAVE_4VRS_TRANSACT(n,b,base);   \
+                                        SAVE_4VRS_TRANSACT(n+4,b,base)
+#define SAVE_16VRS_TRANSACT(n,b,base)   SAVE_8VRS_TRANSACT(n,b,base);   \
+                                        SAVE_8VRS_TRANSACT(n+8,b,base)
+#define SAVE_32VRS_TRANSACT(n,b,base)   SAVE_16VRS_TRANSACT(n,b,base);  \
+                                        SAVE_16VRS_TRANSACT(n+16,b,base)
+
+#define REST_VR_TRANSACT(n,b,base)      li b,THREAD_TRANSACT_VR0+(16*(n)); \
+                                        lvx n,b,base
+#define REST_2VRS_TRANSACT(n,b,base)    REST_VR_TRANSACT(n,b,base);     \
+                                        REST_VR_TRANSACT(n+1,b,base)
+#define REST_4VRS_TRANSACT(n,b,base)    REST_2VRS_TRANSACT(n,b,base);   \
+                                        REST_2VRS_TRANSACT(n+2,b,base)
+#define REST_8VRS_TRANSACT(n,b,base)    REST_4VRS_TRANSACT(n,b,base);   \
+                                        REST_4VRS_TRANSACT(n+4,b,base)
+#define REST_16VRS_TRANSACT(n,b,base)   REST_8VRS_TRANSACT(n,b,base);   \
+                                        REST_8VRS_TRANSACT(n+8,b,base)
+#define REST_32VRS_TRANSACT(n,b,base)   REST_16VRS_TRANSACT(n,b,base);  \
+                                        REST_16VRS_TRANSACT(n+16,b,base)
+
+
+#define SAVE_VSR_TRANSACT(n,b,base)     li b,THREAD_TRANSACT_VSR0+(16*(n)); \
+                                        STXVD2X(n,R##base,R##b)
+#define SAVE_2VSRS_TRANSACT(n,b,base)   SAVE_VSR_TRANSACT(n,b,base);    \
+                                        SAVE_VSR_TRANSACT(n+1,b,base)
+#define SAVE_4VSRS_TRANSACT(n,b,base)   SAVE_2VSRS_TRANSACT(n,b,base);  \
+                                        SAVE_2VSRS_TRANSACT(n+2,b,base)
+#define SAVE_8VSRS_TRANSACT(n,b,base)   SAVE_4VSRS_TRANSACT(n,b,base);  \
+                                        SAVE_4VSRS_TRANSACT(n+4,b,base)
+#define SAVE_16VSRS_TRANSACT(n,b,base)  SAVE_8VSRS_TRANSACT(n,b,base);  \
+                                        SAVE_8VSRS_TRANSACT(n+8,b,base)
+#define SAVE_32VSRS_TRANSACT(n,b,base)  SAVE_16VSRS_TRANSACT(n,b,base); \
+                                        SAVE_16VSRS_TRANSACT(n+16,b,base)
+
+#define REST_VSR_TRANSACT(n,b,base)     li b,THREAD_TRANSACT_VSR0+(16*(n)); \
+                                        LXVD2X(n,R##base,R##b)
+#define REST_2VSRS_TRANSACT(n,b,base)   REST_VSR_TRANSACT(n,b,base);    \
+                                        REST_VSR_TRANSACT(n+1,b,base)
+#define REST_4VSRS_TRANSACT(n,b,base)   REST_2VSRS_TRANSACT(n,b,base);  \
+                                        REST_2VSRS_TRANSACT(n+2,b,base)
+#define REST_8VSRS_TRANSACT(n,b,base)   REST_4VSRS_TRANSACT(n,b,base);  \
+                                        REST_4VSRS_TRANSACT(n+4,b,base)
+#define REST_16VSRS_TRANSACT(n,b,base)  REST_8VSRS_TRANSACT(n,b,base);  \
+                                        REST_8VSRS_TRANSACT(n+8,b,base)
+#define REST_32VSRS_TRANSACT(n,b,base)  REST_16VSRS_TRANSACT(n,b,base); \
+                                        REST_16VSRS_TRANSACT(n+16,b,base)
+
 /* Save the lower 32 VSRs in the thread VSR region */
 #define SAVE_VSR(n,b,base)      li b,THREAD_VSR0+(16*(n));  STXVD2X(n,R##base,R##b)
 #define SAVE_2VSRS(n,b,base)    SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
@@ -391,6 +472,31 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
         FTR_SECTION_ELSE_NESTED(848);   \
         mtocrf (FXM), RS;               \
         ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_NOEXECUTE, 848)
+
+/*
+ * PPR restore macros used in entry_64.S
+ * Used for P7 or later processors
+ */
+#define HMT_MEDIUM_LOW_HAS_PPR                                          \
+BEGIN_FTR_SECTION_NESTED(944)                                           \
+        HMT_MEDIUM_LOW;                                                 \
+END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,944)
+
+#define SET_DEFAULT_THREAD_PPR(ra, rb)                                  \
+BEGIN_FTR_SECTION_NESTED(945)                                           \
+        lis     ra,INIT_PPR@highest;    /* default ppr=3 */             \
+        ld      rb,PACACURRENT(r13);                                    \
+        sldi    ra,ra,32;       /* 11- 13 bits are used for ppr */      \
+        std     ra,TASKTHREADPPR(rb);                                   \
+END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,945)
+
+#define RESTORE_PPR(ra, rb)                                             \
+BEGIN_FTR_SECTION_NESTED(946)                                           \
+        ld      ra,PACACURRENT(r13);                                    \
+        ld      rb,TASKTHREADPPR(ra);                                   \
+        mtspr   SPRN_PPR,rb;    /* Restore PPR */                       \
+END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946)
+
 #endif
 
 /*