powerpc: New macros for transactional memory support

This adds new macros for saving and restoring checkpointed architected state
from and to the thread_struct.

It also adds some debugging macros for when your brain explodes trying to debug
your transactional memory enabled kernel.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/include/asm/ppc_asm.h

@@ -123,6 +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)

arch/powerpc/include/asm/processor.h

@@ -152,6 +152,7 @@ typedef struct {
 #define TS_FPROFFSET 0
 #define TS_VSRLOWOFFSET 1
 #define TS_FPR(i) fpr[i][TS_FPROFFSET]
+#define TS_TRANS_FPR(i) transact_fpr[i][TS_FPROFFSET]
 
 struct thread_struct {
 	unsigned long	ksp;		/* Kernel stack pointer */

arch/powerpc/kernel/asm-offsets.c

@@ -125,6 +125,29 @@ int main(void)
 #ifdef CONFIG_PPC_BOOK3S_64
 	DEFINE(THREAD_TAR, offsetof(struct thread_struct, tar));
 #endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
+	DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
+	DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
+	DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
+	DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
+					 transact_vr[0]));
+	DEFINE(THREAD_TRANSACT_VSCR, offsetof(struct thread_struct,
+					  transact_vscr));
+	DEFINE(THREAD_TRANSACT_VRSAVE, offsetof(struct thread_struct,
+					    transact_vrsave));
+	DEFINE(THREAD_TRANSACT_FPR0, offsetof(struct thread_struct,
+					  transact_fpr[0]));
+	DEFINE(THREAD_TRANSACT_FPSCR, offsetof(struct thread_struct,
+					   transact_fpscr));
+#ifdef CONFIG_VSX
+	DEFINE(THREAD_TRANSACT_VSR0, offsetof(struct thread_struct,
+					  transact_fpr[0]));
+#endif
+	/* Local pt_regs on stack for Transactional Memory funcs. */
+	DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD +
+	       sizeof(struct pt_regs) + 16);
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));

arch/powerpc/kernel/fpu.S

@@ -35,6 +35,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 2:	REST_32VSRS(n,c,base);						\
 3:
 
+#define __REST_32FPVSRS_TRANSACT(n,c,base)				\
+BEGIN_FTR_SECTION							\
+	b	2f;							\
+END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
+	REST_32FPRS_TRANSACT(n,base);					\
+	b	3f;							\
+2:	REST_32VSRS_TRANSACT(n,c,base);					\
+3:
+
 #define __SAVE_32FPVSRS(n,c,base)					\
 BEGIN_FTR_SECTION							\
 	b	2f;							\
@@ -45,9 +54,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 3:
 #else
 #define __REST_32FPVSRS(n,b,base)	REST_32FPRS(n, base)
+#define __REST_32FPVSRS_TRANSACT(n,b,base)	REST_32FPRS(n, base)
 #define __SAVE_32FPVSRS(n,b,base)	SAVE_32FPRS(n, base)
 #endif
 #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
+#define REST_32FPVSRS_TRANSACT(n,c,base) \
+	__REST_32FPVSRS_TRANSACT(n,__REG_##c,__REG_##base)
 #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
 
 /*

arch/powerpc/kernel/process.c

@@ -57,6 +57,13 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
+/* Transactional Memory debug */
+#ifdef TM_DEBUG_SW
+#define TM_DEBUG(x...) printk(KERN_INFO x)
+#else
+#define TM_DEBUG(x...) do { } while(0)
+#endif
+
 extern unsigned long _get_SP(void);
 
 #ifndef CONFIG_SMP

arch/powerpc/kernel/traps.c

@@ -78,6 +78,13 @@ EXPORT_SYMBOL(__debugger_break_match);
 EXPORT_SYMBOL(__debugger_fault_handler);
 #endif
 
+/* Transactional Memory trap debug */
+#ifdef TM_DEBUG_SW
+#define TM_DEBUG(x...) printk(KERN_INFO x)
+#else
+#define TM_DEBUG(x...) do { } while(0)
+#endif
+
 /*
  * Trap & Exception support
  */
@@ -350,6 +357,7 @@ static inline int check_io_access(struct pt_regs *regs)
    exception is in the MSR. */
 #define get_reason(regs)	((regs)->msr)
 #define get_mc_reason(regs)	((regs)->msr)
+#define REASON_TM		0x200000
 #define REASON_FP		0x100000
 #define REASON_ILLEGAL		0x80000
 #define REASON_PRIVILEGED	0x40000