powerpc: Add VSX context save/restore, ptrace and signal support

This patch extends the floating point save and restore code to use the
VSX load/stores when VSX is available.  This will make FP context
save/restore marginally slower on FP only code, when VSX is available,
as it has to load/store 128bits rather than just 64bits.

Mixing FP, VMX and VSX code will get constant architected state.

The signals interface is extended to enable access to VSR 0-31
doubleword 1 after discussions with tool chain maintainers.  Backward
compatibility is maintained.

The ptrace interface is also extended to allow access to VSR 0-31 full
registers.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>

5 files changed, 63 insertions, 3 deletions

diff --git a/include/asm-powerpc/elf.h b/include/asm-powerpc/elf.h
index d1e3bda..746e53d 100644
--- a/include/asm-powerpc/elf.h
+++ b/include/asm-powerpc/elf.h
@@ -109,6 +109,7 @@ typedef elf_gregset_t32 compat_elf_gregset_t;
 #ifdef __powerpc64__
 # define ELF_NVRREG32	33	/* includes vscr & vrsave stuffed together */
 # define ELF_NVRREG	34	/* includes vscr & vrsave in split vectors */
+# define ELF_NVSRHALFREG 32	/* Half the vsx registers */
 # define ELF_GREG_TYPE	elf_greg_t64
 #else
 # define ELF_NEVRREG	34	/* includes acc (as 2) */
@@ -158,6 +159,7 @@ typedef __vector128 elf_vrreg_t;
 typedef elf_vrreg_t elf_vrregset_t[ELF_NVRREG];
 #ifdef __powerpc64__
 typedef elf_vrreg_t elf_vrregset_t32[ELF_NVRREG32];
+typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG];
 #endif
 
 #ifdef __KERNEL__
@@ -219,8 +221,8 @@ extern int dump_task_fpu(struct task_struct *, elf_fpregset_t *);
 typedef elf_vrregset_t elf_fpxregset_t;
 
 #ifdef CONFIG_ALTIVEC
-extern int dump_task_altivec(struct task_struct *, elf_vrregset_t *vrregs);
-#define ELF_CORE_COPY_XFPREGS(tsk, regs) dump_task_altivec(tsk, regs)
+extern int dump_task_vector(struct task_struct *, elf_vrregset_t *vrregs);
+#define ELF_CORE_COPY_XFPREGS(tsk, regs) dump_task_vector(tsk, regs)
 #define ELF_CORE_XFPREG_TYPE NT_PPC_VMX
 #endif
 
diff --git a/include/asm-powerpc/ptrace.h b/include/asm-powerpc/ptrace.h
index 38d87e5..3d6e310 100644
--- a/include/asm-powerpc/ptrace.h
+++ b/include/asm-powerpc/ptrace.h
@@ -224,6 +224,14 @@ extern void user_disable_single_step(struct task_struct *);
 #define PT_VRSAVE_32 (PT_VR0 + 33*4)
 #endif
 
+/*
+ * Only store first 32 VSRs here. The second 32 VSRs in VR0-31
+ */
+#define PT_VSR0 150	/* each VSR reg occupies 2 slots in 64-bit */
+#define PT_VSR31 (PT_VSR0 + 2*31)
+#ifdef __KERNEL__
+#define PT_VSR0_32 300 	/* each VSR reg occupies 4 slots in 32-bit */
+#endif
 #endif /* __powerpc64__ */
 
 /*
@@ -246,6 +254,10 @@ extern void user_disable_single_step(struct task_struct *);
 #define PTRACE_GETEVRREGS	20
 #define PTRACE_SETEVRREGS	21
 
+/* Get the first 32 128bit VSX registers */
+#define PTRACE_GETVSRREGS	27
+#define PTRACE_SETVSRREGS	28
+
 /*
  * Get or set a debug register. The first 16 are DABR registers and the
  * second 16 are IABR registers.
diff --git a/include/asm-powerpc/reg.h b/include/asm-powerpc/reg.h
index 7256efb..bbccadf 100644
--- a/include/asm-powerpc/reg.h
+++ b/include/asm-powerpc/reg.h
@@ -30,6 +30,7 @@
 #define MSR_ISF_LG	61              /* Interrupt 64b mode valid on 630 */
 #define MSR_HV_LG 	60              /* Hypervisor state */
 #define MSR_VEC_LG	25	        /* Enable AltiVec */
+#define MSR_VSX_LG	23		/* Enable VSX */
 #define MSR_POW_LG	18		/* Enable Power Management */
 #define MSR_WE_LG	18		/* Wait State Enable */
 #define MSR_TGPR_LG	17		/* TLB Update registers in use */
@@ -71,6 +72,7 @@
 #endif
 
 #define MSR_VEC		__MASK(MSR_VEC_LG)	/* Enable AltiVec */
+#define MSR_VSX		__MASK(MSR_VSX_LG)	/* Enable VSX */
 #define MSR_POW		__MASK(MSR_POW_LG)	/* Enable Power Management */
 #define MSR_WE		__MASK(MSR_WE_LG)	/* Wait State Enable */
 #define MSR_TGPR	__MASK(MSR_TGPR_LG)	/* TLB Update registers in use */
diff --git a/include/asm-powerpc/sigcontext.h b/include/asm-powerpc/sigcontext.h
index 165d630..9c1f24f 100644
--- a/include/asm-powerpc/sigcontext.h
+++ b/include/asm-powerpc/sigcontext.h
@@ -43,9 +43,44 @@ struct sigcontext {
  * it must be copied via a vector register to/from storage) or as a word.
  * The entry with index 33 contains the vrsave as the first word (offset 0)
  * within the quadword.
+ *
+ * Part of the VSX data is stored here also by extending vmx_restore
+ * by an additional 32 double words.  Architecturally the layout of
+ * the VSR registers and how they overlap on top of the legacy FPR and
+ * VR registers is shown below:
+ *
+ *                    VSR doubleword 0               VSR doubleword 1
+ *           ----------------------------------------------------------------
+ *   VSR[0]  |             FPR[0]            |                              |
+ *           ----------------------------------------------------------------
+ *   VSR[1]  |             FPR[1]            |                              |
+ *           ----------------------------------------------------------------
+ *           |              ...              |                              |
+ *           |              ...              |                              |
+ *           ----------------------------------------------------------------
+ *   VSR[30] |             FPR[30]           |                              |
+ *           ----------------------------------------------------------------
+ *   VSR[31] |             FPR[31]           |                              |
+ *           ----------------------------------------------------------------
+ *   VSR[32] |                             VR[0]                            |
+ *           ----------------------------------------------------------------
+ *   VSR[33] |                             VR[1]                            |
+ *           ----------------------------------------------------------------
+ *           |                              ...                             |
+ *           |                              ...                             |
+ *           ----------------------------------------------------------------
+ *   VSR[62] |                             VR[30]                           |
+ *           ----------------------------------------------------------------
+ *   VSR[63] |                             VR[31]                           |
+ *           ----------------------------------------------------------------
+ *
+ * FPR/VSR 0-31 doubleword 0 is stored in fp_regs, and VMX/VSR 32-63
+ * is stored at the start of vmx_reserve.  vmx_reserve is extended for
+ * backwards compatility to store VSR 0-31 doubleword 1 after the VMX
+ * registers and vscr/vrsave.
  */
 	elf_vrreg_t	__user *v_regs;
-	long		vmx_reserve[ELF_NVRREG+ELF_NVRREG+1];
+	long		vmx_reserve[ELF_NVRREG+ELF_NVRREG+32+1];
 #endif
 };
 
diff --git a/include/asm-powerpc/system.h b/include/asm-powerpc/system.h
index 2642a92..0c12c66 100644
--- a/include/asm-powerpc/system.h
+++ b/include/asm-powerpc/system.h
@@ -139,6 +139,7 @@ extern void enable_kernel_altivec(void);
 extern void giveup_altivec(struct task_struct *);
 extern void load_up_altivec(struct task_struct *);
 extern int emulate_altivec(struct pt_regs *);
+extern void giveup_vsx(struct task_struct *);
 extern void enable_kernel_spe(void);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
@@ -162,6 +163,14 @@ static inline void flush_altivec_to_thread(struct task_struct *t)
 }
 #endif
 
+#ifdef CONFIG_VSX
+extern void flush_vsx_to_thread(struct task_struct *);
+#else
+static inline void flush_vsx_to_thread(struct task_struct *t)
+{
+}
+#endif
+
 #ifdef CONFIG_SPE
 extern void flush_spe_to_thread(struct task_struct *);
 #else