From: Nicholas Piggin <npiggin@gmail.com>
To: linuxppc-dev@lists.ozlabs.org
Cc: Nicholas Piggin <npiggin@gmail.com>
Subject: [RFC PATCH 1/8] powerpc/64s: stop using r14 register
Date: Thu, 21 Dec 2017 00:51:59 +1000 [thread overview]
Message-ID: <20171220145206.12234-2-npiggin@gmail.com> (raw)
In-Reply-To: <20171220145206.12234-1-npiggin@gmail.com>
---
arch/powerpc/Makefile | 1 +
arch/powerpc/crypto/md5-asm.S | 40 +++----
arch/powerpc/crypto/sha1-powerpc-asm.S | 10 +-
arch/powerpc/include/asm/kvm_book3s_asm.h | 2 +-
arch/powerpc/include/asm/ppc_asm.h | 21 +++-
arch/powerpc/kernel/asm-offsets.c | 4 +-
arch/powerpc/kernel/entry_32.S | 4 +-
arch/powerpc/kernel/entry_64.S | 45 ++++----
arch/powerpc/kernel/exceptions-64s.S | 3 +-
arch/powerpc/kernel/head_64.S | 8 +-
arch/powerpc/kernel/idle_book3s.S | 79 +++++++------
arch/powerpc/kernel/kgdb.c | 8 +-
arch/powerpc/kernel/process.c | 4 +-
arch/powerpc/kernel/tm.S | 40 ++++---
arch/powerpc/kernel/trace/ftrace_64_mprofile.S | 10 +-
arch/powerpc/kvm/book3s_hv_interrupts.S | 5 +-
arch/powerpc/kvm/book3s_interrupts.S | 93 +++++++++++----
arch/powerpc/kvm/book3s_pr.c | 6 +
arch/powerpc/lib/checksum_64.S | 66 +++++------
arch/powerpc/lib/copypage_power7.S | 32 +++---
arch/powerpc/lib/copyuser_power7.S | 152 ++++++++++++-------------
arch/powerpc/lib/crtsavres.S | 3 +
arch/powerpc/lib/memcpy_power7.S | 80 ++++++-------
23 files changed, 396 insertions(+), 320 deletions(-)
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 1381693a4a51..8dd38facc5f2 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -140,6 +140,7 @@ AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1)
endif
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions)
+CFLAGS-$(CONFIG_PPC64) += -ffixed-r13 -ffixed-r14
CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 $(MULTIPLEWORD)
ifeq ($(CONFIG_PPC_BOOK3S_64),y)
diff --git a/arch/powerpc/crypto/md5-asm.S b/arch/powerpc/crypto/md5-asm.S
index 10cdf5bceebb..99e41af88e19 100644
--- a/arch/powerpc/crypto/md5-asm.S
+++ b/arch/powerpc/crypto/md5-asm.S
@@ -25,31 +25,31 @@
#define rW02 r10
#define rW03 r11
#define rW04 r12
-#define rW05 r14
-#define rW06 r15
-#define rW07 r16
-#define rW08 r17
-#define rW09 r18
-#define rW10 r19
-#define rW11 r20
-#define rW12 r21
-#define rW13 r22
-#define rW14 r23
-#define rW15 r24
-
-#define rT0 r25
-#define rT1 r26
+#define rW05 r15
+#define rW06 r16
+#define rW07 r17
+#define rW08 r18
+#define rW09 r19
+#define rW10 r20
+#define rW11 r21
+#define rW12 r22
+#define rW13 r23
+#define rW14 r24
+#define rW15 r25
+
+#define rT0 r26
+#define rT1 r27
#define INITIALIZE \
PPC_STLU r1,-INT_FRAME_SIZE(r1); \
- SAVE_8GPRS(14, r1); /* push registers onto stack */ \
- SAVE_4GPRS(22, r1); \
- SAVE_GPR(26, r1)
+ SAVE_8GPRS(15, r1); /* push registers onto stack */ \
+ SAVE_4GPRS(23, r1); \
+ SAVE_GPR(27, r1)
#define FINALIZE \
- REST_8GPRS(14, r1); /* pop registers from stack */ \
- REST_4GPRS(22, r1); \
- REST_GPR(26, r1); \
+ REST_8GPRS(15, r1); /* pop registers from stack */ \
+ REST_4GPRS(23, r1); \
+ REST_GPR(27, r1); \
addi r1,r1,INT_FRAME_SIZE;
#ifdef __BIG_ENDIAN__
diff --git a/arch/powerpc/crypto/sha1-powerpc-asm.S b/arch/powerpc/crypto/sha1-powerpc-asm.S
index c8951ce0dcc4..6c38de214c11 100644
--- a/arch/powerpc/crypto/sha1-powerpc-asm.S
+++ b/arch/powerpc/crypto/sha1-powerpc-asm.S
@@ -42,10 +42,10 @@
or r6,r6,r0; \
add r0,RE(t),r15; \
add RT(t),RT(t),r6; \
- add r14,r0,W(t); \
+ add r6,r0,W(t); \
LWZ(W((t)+4),((t)+4)*4,r4); \
rotlwi RB(t),RB(t),30; \
- add RT(t),RT(t),r14
+ add RT(t),RT(t),r6
#define STEPD0_UPDATE(t) \
and r6,RB(t),RC(t); \
@@ -124,8 +124,7 @@
_GLOBAL(powerpc_sha_transform)
PPC_STLU r1,-INT_FRAME_SIZE(r1)
- SAVE_8GPRS(14, r1)
- SAVE_10GPRS(22, r1)
+ SAVE_NVGPRS(r1)
/* Load up A - E */
lwz RA(0),0(r3) /* A */
@@ -183,7 +182,6 @@ _GLOBAL(powerpc_sha_transform)
stw RD(0),12(r3)
stw RE(0),16(r3)
- REST_8GPRS(14, r1)
- REST_10GPRS(22, r1)
+ REST_NVGPRS(r1)
addi r1,r1,INT_FRAME_SIZE
blr
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index ab386af2904f..fbbd2ca18866 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -143,7 +143,7 @@ struct kvmppc_host_state {
struct kvmppc_book3s_shadow_vcpu {
bool in_use;
- ulong gpr[14];
+ ulong gpr[15];
u32 cr;
ulong xer;
ulong ctr;
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index ae94b3626b6c..109f4dce8a79 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -10,6 +10,16 @@
#include <asm/ppc-opcode.h>
#include <asm/firmware.h>
+#ifdef __powerpc64__
+#ifdef CONFIG_PPC_BOOK3S
+#define FIRST_NVGPR 15
+#else
+#define FIRST_NVGPR 14
+#endif
+#else
+#define FIRST_NVGPR 13
+#endif
+
#ifdef __ASSEMBLY__
#define SZL (BITS_PER_LONG/8)
@@ -75,16 +85,21 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
#ifdef __powerpc64__
#define SAVE_GPR(n, base) std n,GPR0+8*(n)(base)
#define REST_GPR(n, base) ld n,GPR0+8*(n)(base)
+#ifdef CONFIG_PPC_BOOK3S
+#define SAVE_NVGPRS(base) SAVE_GPR(15, base); SAVE_2GPRS(16, base); SAVE_4GPRS(18, base); SAVE_10GPRS(22, base)
+#define REST_NVGPRS(base) REST_GPR(15, base); REST_2GPRS(16, base); REST_4GPRS(18, base); REST_10GPRS(22, base)
+#else /* CONFIG_PPC_BOOK3S */
#define SAVE_NVGPRS(base) SAVE_8GPRS(14, base); SAVE_10GPRS(22, base)
#define REST_NVGPRS(base) REST_8GPRS(14, base); REST_10GPRS(22, base)
-#else
+#endif /* CONFIG_PPC_BOOK3S */
+#else /* __powerpc64__ */
#define SAVE_GPR(n, base) stw n,GPR0+4*(n)(base)
#define REST_GPR(n, base) lwz n,GPR0+4*(n)(base)
#define SAVE_NVGPRS(base) SAVE_GPR(13, base); SAVE_8GPRS(14, base); \
SAVE_10GPRS(22, base)
#define REST_NVGPRS(base) REST_GPR(13, base); REST_8GPRS(14, base); \
REST_10GPRS(22, base)
-#endif
+#endif /* __powerpc64__ */
#define SAVE_2GPRS(n, base) SAVE_GPR(n, base); SAVE_GPR(n+1, base)
#define SAVE_4GPRS(n, base) SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base)
@@ -184,7 +199,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
#ifdef CONFIG_PPC64
#define STACKFRAMESIZE 256
-#define __STK_REG(i) (112 + ((i)-14)*8)
+#define __STK_REG(i) (112 + ((i)-15)*8)
#define STK_REG(i) __STK_REG(__REG_##i)
#ifdef PPC64_ELF_ABI_v2
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 397681f43eed..db8407483c9e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -283,9 +283,9 @@ int main(void)
STACK_PT_REGS_OFFSET(GPR11, gpr[11]);
STACK_PT_REGS_OFFSET(GPR12, gpr[12]);
STACK_PT_REGS_OFFSET(GPR13, gpr[13]);
-#ifndef CONFIG_PPC64
+#ifndef CONFIG_PPC_BOOK3E_64
STACK_PT_REGS_OFFSET(GPR14, gpr[14]);
-#endif /* CONFIG_PPC64 */
+#endif
/*
* Note: these symbols include _ because they overlap with special
* register names
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e780e1fbf6c2..4b3cf4dc7d05 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -458,8 +458,8 @@ ret_from_fork:
ret_from_kernel_thread:
REST_NVGPRS(r1)
bl schedule_tail
- mtlr r14
- mr r3,r15
+ mtlr FIRST_NVGPR
+ mr r3,FIRST_NVGPR+1
PPC440EP_ERR42
blrl
li r3,0
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index f2ffb9aa7ff4..b9bf44635b10 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -419,7 +419,7 @@ _ASM_NOKPROBE_SYMBOL(save_nvgprs);
* The sigsuspend and rt_sigsuspend system calls can call do_signal
* and thus put the process into the stopped state where we might
* want to examine its user state with ptrace. Therefore we need
- * to save all the nonvolatile registers (r14 - r31) before calling
+ * to save all the nonvolatile registers (r15 - r31) before calling
* the C code. Similarly, fork, vfork and clone need the full
* register state on the stack so that it can be copied to the child.
*/
@@ -463,10 +463,10 @@ _GLOBAL(ret_from_fork)
_GLOBAL(ret_from_kernel_thread)
bl schedule_tail
REST_NVGPRS(r1)
- mtlr r14
- mr r3,r15
+ mtlr FIRST_NVGPR
+ mr r3,FIRST_NVGPR+1
#ifdef PPC64_ELF_ABI_v2
- mr r12,r14
+ mr r12,FIRST_NVGPR
#endif
blrl
li r3,0
@@ -495,9 +495,7 @@ _GLOBAL(_switch)
mflr r0
std r0,16(r1)
stdu r1,-SWITCH_FRAME_SIZE(r1)
- /* r3-r13 are caller saved -- Cort */
- SAVE_8GPRS(14, r1)
- SAVE_10GPRS(22, r1)
+ SAVE_NVGPRS(r1)
std r0,_NIP(r1) /* Return to switch caller */
mfcr r23
std r23,_CCR(r1)
@@ -609,9 +607,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
ld r6,_CCR(r1)
mtcrf 0xFF,r6
- /* r3-r13 are destroyed -- Cort */
- REST_8GPRS(14, r1)
- REST_10GPRS(22, r1)
+ /* Volatile regs are destroyed */
+ REST_NVGPRS(r1)
/* convert old thread to its task_struct for return value */
addi r3,r3,-THREAD
@@ -1011,12 +1008,14 @@ _GLOBAL(enter_rtas)
/* Because RTAS is running in 32b mode, it clobbers the high order half
* of all registers that it saves. We therefore save those registers
- * RTAS might touch to the stack. (r0, r3-r13 are caller saved)
+ * RTAS might touch to the stack. (r0, r3-r12 are caller saved)
*/
SAVE_GPR(2, r1) /* Save the TOC */
SAVE_GPR(13, r1) /* Save paca */
- SAVE_8GPRS(14, r1) /* Save the non-volatiles */
- SAVE_10GPRS(22, r1) /* ditto */
+#ifdef CONFIG_PPC_BOOK3S
+ SAVE_GPR(14, r1) /* Save r14 */
+#endif
+ SAVE_NVGPRS(r1) /* Save the non-volatiles */
mfcr r4
std r4,_CCR(r1)
@@ -1118,8 +1117,10 @@ rtas_restore_regs:
/* relocation is on at this point */
REST_GPR(2, r1) /* Restore the TOC */
REST_GPR(13, r1) /* Restore paca */
- REST_8GPRS(14, r1) /* Restore the non-volatiles */
- REST_10GPRS(22, r1) /* ditto */
+#ifdef CONFIG_PPC_BOOK3S
+ REST_GPR(14, r1) /* Restore r14 */
+#endif
+ REST_NVGPRS(r1) /* Restore the non-volatiles */
GET_PACA(r13)
@@ -1149,12 +1150,14 @@ _GLOBAL(enter_prom)
/* Because PROM is running in 32b mode, it clobbers the high order half
* of all registers that it saves. We therefore save those registers
- * PROM might touch to the stack. (r0, r3-r13 are caller saved)
+ * PROM might touch to the stack. (r0, r3-r14 are caller saved)
*/
SAVE_GPR(2, r1)
SAVE_GPR(13, r1)
- SAVE_8GPRS(14, r1)
- SAVE_10GPRS(22, r1)
+#ifdef CONFIG_PPC_BOOK3S
+ SAVE_GPR(14, r1)
+#endif
+ SAVE_NVGPRS(r1)
mfcr r10
mfmsr r11
std r10,_CCR(r1)
@@ -1198,8 +1201,10 @@ _GLOBAL(enter_prom)
/* Restore other registers */
REST_GPR(2, r1)
REST_GPR(13, r1)
- REST_8GPRS(14, r1)
- REST_10GPRS(22, r1)
+#ifdef CONFIG_PPC_BOOK3S
+ REST_GPR(14, r1)
+#endif
+ REST_NVGPRS(r1)
ld r4,_CCR(r1)
mtcr r4
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 60d9c68ef414..189c456450e2 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1656,8 +1656,7 @@ BEGIN_FTR_SECTION
ld r10,EX_CFAR(r3)
std r10,ORIG_GPR3(r1)
END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
- SAVE_8GPRS(14,r1)
- SAVE_10GPRS(22,r1)
+ SAVE_NVGPRS(r1)
lhz r12,PACA_TRAP_SAVE(r13)
std r12,_TRAP(r1)
addi r11,r1,INT_FRAME_SIZE
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 56f9e112b98d..87b2c2264118 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -802,9 +802,9 @@ __secondary_start:
/* Initialize the kernel stack */
LOAD_REG_ADDR(r3, current_set)
sldi r28,r24,3 /* get current_set[cpu#] */
- ldx r14,r3,r28
- addi r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD
- std r14,PACAKSAVE(r13)
+ ldx r15,r3,r28
+ addi r15,r15,THREAD_SIZE-STACK_FRAME_OVERHEAD
+ std r15,PACAKSAVE(r13)
/* Do early setup for that CPU (SLB and hash table pointer) */
bl early_setup_secondary
@@ -813,7 +813,7 @@ __secondary_start:
* setup the new stack pointer, but *don't* use this until
* translation is on.
*/
- mr r1, r14
+ mr r1, r15
/* Clear backchain so we get nice backtraces */
li r7,0
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 01e1c1997893..5065c4cb5f12 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -150,19 +150,19 @@ power9_restore_additional_sprs:
/*
* Used by threads when the lock bit of core_idle_state is set.
* Threads will spin in HMT_LOW until the lock bit is cleared.
- * r14 - pointer to core_idle_state
- * r15 - used to load contents of core_idle_state
+ * r15 - pointer to core_idle_state
+ * r16 - used to load contents of core_idle_state
* r9 - used as a temporary variable
*/
core_idle_lock_held:
HMT_LOW
-3: lwz r15,0(r14)
- andis. r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
+3: lwz r16,0(r15)
+ andis. r16,r16,PNV_CORE_IDLE_LOCK_BIT@h
bne 3b
HMT_MEDIUM
- lwarx r15,0,r14
- andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ lwarx r16,0,r15
+ andis. r9,r16,PNV_CORE_IDLE_LOCK_BIT@h
bne- core_idle_lock_held
blr
@@ -263,21 +263,21 @@ pnv_enter_arch207_idle_mode:
2:
/* Sleep or winkle */
lbz r7,PACA_THREAD_MASK(r13)
- ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
+ ld r15,PACA_CORE_IDLE_STATE_PTR(r13)
li r5,0
beq cr3,3f
lis r5,PNV_CORE_IDLE_WINKLE_COUNT@h
3:
lwarx_loop1:
- lwarx r15,0,r14
+ lwarx r16,0,r15
- andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ andis. r9,r16,PNV_CORE_IDLE_LOCK_BIT@h
bnel- core_idle_lock_held
- add r15,r15,r5 /* Add if winkle */
- andc r15,r15,r7 /* Clear thread bit */
+ add r16,r16,r5 /* Add if winkle */
+ andc r16,r16,r7 /* Clear thread bit */
- andi. r9,r15,PNV_CORE_IDLE_THREAD_BITS
+ andi. r9,r16,PNV_CORE_IDLE_THREAD_BITS
/*
* If cr0 = 0, then current thread is the last thread of the core entering
@@ -291,7 +291,7 @@ lwarx_loop1:
pnv_fastsleep_workaround_at_entry:
beq fastsleep_workaround_at_entry
- stwcx. r15,0,r14
+ stwcx. r16,0,r15
bne- lwarx_loop1
isync
@@ -300,8 +300,8 @@ common_enter: /* common code for all the threads entering sleep or winkle */
IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
fastsleep_workaround_at_entry:
- oris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
- stwcx. r15,0,r14
+ oris r16,r16,PNV_CORE_IDLE_LOCK_BIT@h
+ stwcx. r16,0,r15
bne- lwarx_loop1
isync
@@ -311,9 +311,9 @@ fastsleep_workaround_at_entry:
bl opal_config_cpu_idle_state
/* Unlock */
- xoris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ xoris r16,r16,PNV_CORE_IDLE_LOCK_BIT@h
lwsync
- stw r15,0(r14)
+ stw r16,0(r15)
b common_enter
enter_winkle:
@@ -381,15 +381,15 @@ END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
* stack and enter stop
*/
lbz r7,PACA_THREAD_MASK(r13)
- ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
+ ld r15,PACA_CORE_IDLE_STATE_PTR(r13)
lwarx_loop_stop:
- lwarx r15,0,r14
- andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ lwarx r16,0,r15
+ andis. r9,r16,PNV_CORE_IDLE_LOCK_BIT@h
bnel- core_idle_lock_held
- andc r15,r15,r7 /* Clear thread bit */
+ andc r16,r16,r7 /* Clear thread bit */
- stwcx. r15,0,r14
+ stwcx. r16,0,r15
bne- lwarx_loop_stop
isync
@@ -643,8 +643,7 @@ pnv_wakeup_tb_loss:
stb r0,PACA_NAPSTATELOST(r13)
/*
- *
- * Save SRR1 and LR in NVGPRs as they might be clobbered in
+ * Save SRR1 (r12) and LR in NVGPRs as they might be clobbered in
* opal_call() (called in CHECK_HMI_INTERRUPT). SRR1 is required
* to determine the wakeup reason if we branch to kvm_start_guest. LR
* is required to return back to reset vector after hypervisor state
@@ -657,7 +656,7 @@ BEGIN_FTR_SECTION
CHECK_HMI_INTERRUPT
END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
- ld r14,PACA_CORE_IDLE_STATE_PTR(r13)
+ ld r15,PACA_CORE_IDLE_STATE_PTR(r13)
lbz r7,PACA_THREAD_MASK(r13)
/*
@@ -671,15 +670,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
* In either case loop until the lock bit is cleared.
*/
1:
- lwarx r15,0,r14
- andis. r9,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ lwarx r16,0,r15
+ andis. r9,r16,PNV_CORE_IDLE_LOCK_BIT@h
bnel- core_idle_lock_held
- oris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
- stwcx. r15,0,r14
+ oris r16,r16,PNV_CORE_IDLE_LOCK_BIT@h
+ stwcx. r16,0,r15
bne- 1b
isync
- andi. r9,r15,PNV_CORE_IDLE_THREAD_BITS
+ andi. r9,r16,PNV_CORE_IDLE_THREAD_BITS
cmpwi cr2,r9,0
/*
@@ -745,27 +744,27 @@ BEGIN_FTR_SECTION
*/
cmpwi r18,PNV_THREAD_WINKLE
bne 2f
- andis. r9,r15,PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT@h
- subis r15,r15,PNV_CORE_IDLE_WINKLE_COUNT@h
+ andis. r9,r16,PNV_CORE_IDLE_WINKLE_COUNT_ALL_BIT@h
+ subis r16,r16,PNV_CORE_IDLE_WINKLE_COUNT@h
beq 2f
- ori r15,r15,PNV_CORE_IDLE_THREAD_WINKLE_BITS /* all were winkle */
+ ori r16,r16,PNV_CORE_IDLE_THREAD_WINKLE_BITS /* all were winkle */
2:
/* Shift thread bit to winkle mask, then test if this thread is set,
* and remove it from the winkle bits */
slwi r8,r7,8
- and r8,r8,r15
- andc r15,r15,r8
+ and r8,r8,r16
+ andc r16,r16,r8
cmpwi cr4,r8,1 /* cr4 will be gt if our bit is set, lt if not */
lbz r4,PACA_SUBCORE_SIBLING_MASK(r13)
- and r4,r4,r15
+ and r4,r4,r16
cmpwi r4,0 /* Check if first in subcore */
- or r15,r15,r7 /* Set thread bit */
+ or r16,r16,r7 /* Set thread bit */
beq first_thread_in_subcore
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
- or r15,r15,r7 /* Set thread bit */
+ or r16,r16,r7 /* Set thread bit */
beq cr2,first_thread_in_core
/* Not first thread in core or subcore to wake up */
@@ -842,9 +841,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
mtspr SPRN_WORC,r4
clear_lock:
- xoris r15,r15,PNV_CORE_IDLE_LOCK_BIT@h
+ xoris r16,r16,PNV_CORE_IDLE_LOCK_BIT@h
lwsync
- stw r15,0(r14)
+ stw r16,0(r15)
common_exit:
/*
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 35e240a0a408..d593e381f34d 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -230,11 +230,11 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
for (reg = 0; reg < 3; reg++)
PACK64(ptr, regs->gpr[reg]);
- /* Regs GPR3-13 are caller saved, not in regs->gpr[] */
- ptr += 11;
+ /* Regs GPR3-13/14 are caller saved, not in regs->gpr[] */
+ ptr += FIRST_NVGPR - 2;
- /* Regs GPR14-31 */
- for (reg = 14; reg < 32; reg++)
+ /* Regs GPR14/15-31 */
+ for (reg = FIRST_NVGPR; reg < 32; reg++)
PACK64(ptr, regs->gpr[reg]);
#ifdef CONFIG_FSL_BOOKE
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 2a63cc78257d..f56e42f06f24 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1672,12 +1672,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
childregs->gpr[1] = sp + sizeof(struct pt_regs);
/* function */
if (usp)
- childregs->gpr[14] = ppc_function_entry((void *)usp);
+ childregs->gpr[FIRST_NVGPR] = ppc_function_entry((void *)usp);
#ifdef CONFIG_PPC64
clear_tsk_thread_flag(p, TIF_32BIT);
childregs->softe = IRQ_SOFT_MASK_NONE;
#endif
- childregs->gpr[15] = kthread_arg;
+ childregs->gpr[FIRST_NVGPR + 1] = kthread_arg;
p->thread.regs = NULL; /* no user register state */
ti->flags |= _TIF_RESTOREALL;
f = ret_from_kernel_thread;
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index b92ac8e711db..3f62b8157aea 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -106,27 +106,28 @@ _GLOBAL(tm_reclaim)
/* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */
std r3, STK_PARAM(R3)(r1)
+ SAVE_GPR(14, r1)
SAVE_NVGPRS(r1)
/* We need to setup MSR for VSX register save instructions. */
- mfmsr r14
- mr r15, r14
- ori r15, r15, MSR_FP
- li r16, 0
- ori r16, r16, MSR_EE /* IRQs hard off */
- andc r15, r15, r16
- oris r15, r15, MSR_VEC@h
+ mfmsr r15
+ mr r16, r15
+ ori r16, r16, MSR_FP
+ li r17, 0
+ ori r17, r17, MSR_EE /* IRQs hard off */
+ andc r16, r16, r17
+ oris r16, r16, MSR_VEC@h
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
- oris r15,r15, MSR_VSX@h
+ oris r16,r16, MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
- mtmsrd r15
- std r14, TM_FRAME_L0(r1)
+ mtmsrd r16
+ std r15, TM_FRAME_L0(r1)
/* Do sanity check on MSR to make sure we are suspended */
li r7, (MSR_TS_S)@higher
- srdi r6, r14, 32
+ srdi r6, r15, 32
and r6, r6, r7
1: tdeqi r6, 0
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
@@ -205,7 +206,8 @@ _GLOBAL(tm_reclaim)
std r6, GPR12(r7)
std r8, GPR13(r7)
- SAVE_NVGPRS(r7) /* user r14-r31 */
+ SAVE_GPR(14, r7) /* user r14 */
+ SAVE_NVGPRS(r7) /* user r15-r31 */
/* ******************** NIP ******************** */
mfspr r3, SPRN_TFHAR
@@ -278,12 +280,13 @@ _GLOBAL(tm_reclaim)
/* AMR is checkpointed too, but is unsupported by Linux. */
/* Restore original MSR/IRQ state & clear TM mode */
- ld r14, TM_FRAME_L0(r1) /* Orig MSR */
+ ld r15, TM_FRAME_L0(r1) /* Orig MSR */
- li r15, 0
- rldimi r14, r15, MSR_TS_LG, (63-MSR_TS_LG)-1
- mtmsrd r14
+ li r16, 0
+ rldimi r15, r16, MSR_TS_LG, (63-MSR_TS_LG)-1
+ mtmsrd r15
+ REST_GPR(14, r1)
REST_NVGPRS(r1)
addi r1, r1, TM_FRAME_SIZE
@@ -319,6 +322,7 @@ _GLOBAL(__tm_recheckpoint)
/* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD].
* This is used for backing up the NVGPRs:
*/
+ SAVE_GPR(14, r1)
SAVE_NVGPRS(r1)
/* Load complete register state from ts_ckpt* registers */
@@ -391,8 +395,9 @@ restore_gprs:
REST_GPR(4, r7) /* GPR4 */
REST_4GPRS(8, r7) /* GPR8-11 */
REST_2GPRS(12, r7) /* GPR12-13 */
+ REST_GPR(14, r7) /* GPR14 */
- REST_NVGPRS(r7) /* GPR14-31 */
+ REST_NVGPRS(r7) /* GPR15-31 */
/* Load up PPR and DSCR here so we don't run with user values for long
*/
@@ -471,6 +476,7 @@ restore_gprs:
li r4, MSR_RI
mtmsrd r4, 1
+ REST_GPR(14, r1)
REST_NVGPRS(r1)
addi r1, r1, TM_FRAME_SIZE
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 3f3e81852422..a0f62ff3442f 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -76,7 +76,7 @@ _GLOBAL(ftrace_caller)
ld r5,0(r3)
#ifdef CONFIG_LIVEPATCH
- mr r14,r7 /* remember old NIP */
+ mr r15,r7 /* remember old NIP */
#endif
/* Calculate ip from nip-4 into r3 for call below */
subi r3, r7, MCOUNT_INSN_SIZE
@@ -100,10 +100,10 @@ ftrace_call:
nop
/* Load the possibly modified NIP */
- ld r15, _NIP(r1)
+ ld r16, _NIP(r1)
#ifdef CONFIG_LIVEPATCH
- cmpd r14, r15 /* has NIP been altered? */
+ cmpd r15, r16 /* has NIP been altered? */
#endif
#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
@@ -111,7 +111,7 @@ ftrace_call:
beq 1f
/* Check if there is an active jprobe on us */
- subi r3, r14, 4
+ subi r3, r15, 4
bl __is_active_jprobe
nop
@@ -130,7 +130,7 @@ ftrace_call:
#endif
/* Load CTR with the possibly modified NIP */
- mtctr r15
+ mtctr r16
/* Restore gprs */
REST_GPR(0,r1)
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index dc54373c8780..ef1c0c1e57ff 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -46,7 +46,7 @@ _GLOBAL(__kvmppc_vcore_entry)
/* Save host state to the stack */
stdu r1, -SWITCH_FRAME_SIZE(r1)
- /* Save non-volatile registers (r14 - r31) and CR */
+ /* Save non-volatile registers (r15 - r31) and CR */
SAVE_NVGPRS(r1)
mfcr r3
std r3, _CCR(r1)
@@ -149,9 +149,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
* R3 = trap number on this thread
* R12 = exit handler id
* R13 = PACA
+ * R14 = ? XXX
*/
- /* Restore non-volatile host registers (r14 - r31) and CR */
+ /* Restore non-volatile host registers (r15 - r31) and CR */
REST_NVGPRS(r1)
ld r4, _CCR(r1)
mtcr r4
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 901e6fe00c39..b275a544129e 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -38,6 +38,45 @@
#endif /* CONFIG_PPC_BOOK3S_XX */
+#if defined(CONFIG_PPC_BOOK3S_64)
+#define VCPU_LOAD_NVGPRS(vcpu) \
+ PPC_LL r15, VCPU_GPR(R15)(vcpu); \
+ PPC_LL r16, VCPU_GPR(R16)(vcpu); \
+ PPC_LL r17, VCPU_GPR(R17)(vcpu); \
+ PPC_LL r18, VCPU_GPR(R18)(vcpu); \
+ PPC_LL r19, VCPU_GPR(R19)(vcpu); \
+ PPC_LL r20, VCPU_GPR(R20)(vcpu); \
+ PPC_LL r21, VCPU_GPR(R21)(vcpu); \
+ PPC_LL r22, VCPU_GPR(R22)(vcpu); \
+ PPC_LL r23, VCPU_GPR(R23)(vcpu); \
+ PPC_LL r24, VCPU_GPR(R24)(vcpu); \
+ PPC_LL r25, VCPU_GPR(R25)(vcpu); \
+ PPC_LL r26, VCPU_GPR(R26)(vcpu); \
+ PPC_LL r27, VCPU_GPR(R27)(vcpu); \
+ PPC_LL r28, VCPU_GPR(R28)(vcpu); \
+ PPC_LL r29, VCPU_GPR(R29)(vcpu); \
+ PPC_LL r30, VCPU_GPR(R30)(vcpu); \
+ PPC_LL r31, VCPU_GPR(R31)(vcpu);
+
+#define VCPU_STORE_NVGPRS(vcpu) \
+ PPC_STL r15, VCPU_GPR(R15)(vcpu); \
+ PPC_STL r16, VCPU_GPR(R16)(vcpu); \
+ PPC_STL r17, VCPU_GPR(R17)(vcpu); \
+ PPC_STL r18, VCPU_GPR(R18)(vcpu); \
+ PPC_STL r19, VCPU_GPR(R19)(vcpu); \
+ PPC_STL r20, VCPU_GPR(R20)(vcpu); \
+ PPC_STL r21, VCPU_GPR(R21)(vcpu); \
+ PPC_STL r22, VCPU_GPR(R22)(vcpu); \
+ PPC_STL r23, VCPU_GPR(R23)(vcpu); \
+ PPC_STL r24, VCPU_GPR(R24)(vcpu); \
+ PPC_STL r25, VCPU_GPR(R25)(vcpu); \
+ PPC_STL r26, VCPU_GPR(R26)(vcpu); \
+ PPC_STL r27, VCPU_GPR(R27)(vcpu); \
+ PPC_STL r28, VCPU_GPR(R28)(vcpu); \
+ PPC_STL r29, VCPU_GPR(R29)(vcpu); \
+ PPC_STL r30, VCPU_GPR(R30)(vcpu); \
+ PPC_STL r31, VCPU_GPR(R31)(vcpu);
+#else
#define VCPU_LOAD_NVGPRS(vcpu) \
PPC_LL r14, VCPU_GPR(R14)(vcpu); \
PPC_LL r15, VCPU_GPR(R15)(vcpu); \
@@ -56,7 +95,28 @@
PPC_LL r28, VCPU_GPR(R28)(vcpu); \
PPC_LL r29, VCPU_GPR(R29)(vcpu); \
PPC_LL r30, VCPU_GPR(R30)(vcpu); \
- PPC_LL r31, VCPU_GPR(R31)(vcpu); \
+ PPC_LL r31, VCPU_GPR(R31)(vcpu);
+
+#define VCPU_STORE_NVGPRS(vcpu) \
+ PPC_STL r14, VCPU_GPR(R14)(vcpu); \
+ PPC_STL r15, VCPU_GPR(R15)(vcpu); \
+ PPC_STL r16, VCPU_GPR(R16)(vcpu); \
+ PPC_STL r17, VCPU_GPR(R17)(vcpu); \
+ PPC_STL r18, VCPU_GPR(R18)(vcpu); \
+ PPC_STL r19, VCPU_GPR(R19)(vcpu); \
+ PPC_STL r20, VCPU_GPR(R20)(vcpu); \
+ PPC_STL r21, VCPU_GPR(R21)(vcpu); \
+ PPC_STL r22, VCPU_GPR(R22)(vcpu); \
+ PPC_STL r23, VCPU_GPR(R23)(vcpu); \
+ PPC_STL r24, VCPU_GPR(R24)(vcpu); \
+ PPC_STL r25, VCPU_GPR(R25)(vcpu); \
+ PPC_STL r26, VCPU_GPR(R26)(vcpu); \
+ PPC_STL r27, VCPU_GPR(R27)(vcpu); \
+ PPC_STL r28, VCPU_GPR(R28)(vcpu); \
+ PPC_STL r29, VCPU_GPR(R29)(vcpu); \
+ PPC_STL r30, VCPU_GPR(R30)(vcpu); \
+ PPC_STL r31, VCPU_GPR(R31)(vcpu);
+#endif
/*****************************************************************************
* *
@@ -81,12 +141,12 @@ kvm_start_entry:
/* Save r3 (kvm_run) and r4 (vcpu) */
SAVE_2GPRS(3, r1)
- /* Save non-volatile registers (r14 - r31) */
+ /* Save non-volatile registers (r14/r15 - r31) */
SAVE_NVGPRS(r1)
/* Save CR */
- mfcr r14
- stw r14, _CCR(r1)
+ mfcr r15
+ stw r15, _CCR(r1)
/* Save LR */
PPC_STL r0, _LINK(r1)
@@ -183,24 +243,7 @@ after_sprg3_load:
/* R7 = vcpu */
PPC_LL r7, GPR4(r1)
- PPC_STL r14, VCPU_GPR(R14)(r7)
- PPC_STL r15, VCPU_GPR(R15)(r7)
- PPC_STL r16, VCPU_GPR(R16)(r7)
- PPC_STL r17, VCPU_GPR(R17)(r7)
- PPC_STL r18, VCPU_GPR(R18)(r7)
- PPC_STL r19, VCPU_GPR(R19)(r7)
- PPC_STL r20, VCPU_GPR(R20)(r7)
- PPC_STL r21, VCPU_GPR(R21)(r7)
- PPC_STL r22, VCPU_GPR(R22)(r7)
- PPC_STL r23, VCPU_GPR(R23)(r7)
- PPC_STL r24, VCPU_GPR(R24)(r7)
- PPC_STL r25, VCPU_GPR(R25)(r7)
- PPC_STL r26, VCPU_GPR(R26)(r7)
- PPC_STL r27, VCPU_GPR(R27)(r7)
- PPC_STL r28, VCPU_GPR(R28)(r7)
- PPC_STL r29, VCPU_GPR(R29)(r7)
- PPC_STL r30, VCPU_GPR(R30)(r7)
- PPC_STL r31, VCPU_GPR(R31)(r7)
+ VCPU_STORE_NVGPRS(r7)
/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
lwz r5, VCPU_TRAP(r7)
@@ -221,10 +264,10 @@ kvm_exit_loop:
PPC_LL r4, _LINK(r1)
mtlr r4
- lwz r14, _CCR(r1)
- mtcr r14
+ lwz r15, _CCR(r1)
+ mtcr r15
- /* Restore non-volatile host registers (r14 - r31) */
+ /* Restore non-volatile host registers (r14/r15 - r31) */
REST_NVGPRS(r1)
addi r1, r1, SWITCH_FRAME_SIZE
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index d0dc8624198f..b149d4fa4a45 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -159,6 +159,9 @@ void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
svcpu->gpr[11] = vcpu->arch.gpr[11];
svcpu->gpr[12] = vcpu->arch.gpr[12];
svcpu->gpr[13] = vcpu->arch.gpr[13];
+#ifdef CONFIG_PPC_BOOK3S_64
+ svcpu->gpr[14] = vcpu->arch.gpr[14];
+#endif
svcpu->cr = vcpu->arch.cr;
svcpu->xer = vcpu->arch.xer;
svcpu->ctr = vcpu->arch.ctr;
@@ -209,6 +212,9 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
vcpu->arch.gpr[11] = svcpu->gpr[11];
vcpu->arch.gpr[12] = svcpu->gpr[12];
vcpu->arch.gpr[13] = svcpu->gpr[13];
+#ifdef CONFIG_PPC_BOOK3S_64
+ vcpu->arch.gpr[14] = svcpu->gpr[14];
+#endif
vcpu->arch.cr = svcpu->cr;
vcpu->arch.xer = svcpu->xer;
vcpu->arch.ctr = svcpu->ctr;
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index d7f1a966136e..19b0fd549b24 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -64,9 +64,9 @@ _GLOBAL(__csum_partial)
mtctr r6
stdu r1,-STACKFRAMESIZE(r1)
- std r14,STK_REG(R14)(r1)
std r15,STK_REG(R15)(r1)
std r16,STK_REG(R16)(r1)
+ std r17,STK_REG(R17)(r1)
ld r6,0(r3)
ld r9,8(r3)
@@ -84,11 +84,11 @@ _GLOBAL(__csum_partial)
2:
adde r0,r0,r6
ld r12,32(r3)
- ld r14,40(r3)
+ ld r15,40(r3)
adde r0,r0,r9
- ld r15,48(r3)
- ld r16,56(r3)
+ ld r16,48(r3)
+ ld r17,56(r3)
addi r3,r3,64
adde r0,r0,r10
@@ -97,13 +97,13 @@ _GLOBAL(__csum_partial)
adde r0,r0,r12
- adde r0,r0,r14
-
adde r0,r0,r15
+
+ adde r0,r0,r16
ld r6,0(r3)
ld r9,8(r3)
- adde r0,r0,r16
+ adde r0,r0,r17
ld r10,16(r3)
ld r11,24(r3)
bdnz 2b
@@ -111,23 +111,23 @@ _GLOBAL(__csum_partial)
adde r0,r0,r6
ld r12,32(r3)
- ld r14,40(r3)
+ ld r15,40(r3)
adde r0,r0,r9
- ld r15,48(r3)
- ld r16,56(r3)
+ ld r16,48(r3)
+ ld r17,56(r3)
addi r3,r3,64
adde r0,r0,r10
adde r0,r0,r11
adde r0,r0,r12
- adde r0,r0,r14
adde r0,r0,r15
adde r0,r0,r16
+ adde r0,r0,r17
- ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
addi r1,r1,STACKFRAMESIZE
andi. r4,r4,63
@@ -258,9 +258,9 @@ dstnr; sth r6,0(r4)
mtctr r6
stdu r1,-STACKFRAMESIZE(r1)
- std r14,STK_REG(R14)(r1)
std r15,STK_REG(R15)(r1)
std r16,STK_REG(R16)(r1)
+ std r17,STK_REG(R17)(r1)
source; ld r6,0(r3)
source; ld r9,8(r3)
@@ -278,11 +278,11 @@ source; ld r11,24(r3)
2:
adde r0,r0,r6
source; ld r12,32(r3)
-source; ld r14,40(r3)
+source; ld r15,40(r3)
adde r0,r0,r9
-source; ld r15,48(r3)
-source; ld r16,56(r3)
+source; ld r16,48(r3)
+source; ld r17,56(r3)
addi r3,r3,64
adde r0,r0,r10
@@ -295,18 +295,18 @@ dest; std r11,24(r4)
adde r0,r0,r12
dest; std r12,32(r4)
-dest; std r14,40(r4)
+dest; std r15,40(r4)
- adde r0,r0,r14
-dest; std r15,48(r4)
-dest; std r16,56(r4)
+ adde r0,r0,r15
+dest; std r16,48(r4)
+dest; std r17,56(r4)
addi r4,r4,64
- adde r0,r0,r15
+ adde r0,r0,r16
source; ld r6,0(r3)
source; ld r9,8(r3)
- adde r0,r0,r16
+ adde r0,r0,r17
source; ld r10,16(r3)
source; ld r11,24(r3)
bdnz 2b
@@ -314,11 +314,11 @@ source; ld r11,24(r3)
adde r0,r0,r6
source; ld r12,32(r3)
-source; ld r14,40(r3)
+source; ld r15,40(r3)
adde r0,r0,r9
-source; ld r15,48(r3)
-source; ld r16,56(r3)
+source; ld r16,48(r3)
+source; ld r17,56(r3)
addi r3,r3,64
adde r0,r0,r10
@@ -331,19 +331,19 @@ dest; std r11,24(r4)
adde r0,r0,r12
dest; std r12,32(r4)
-dest; std r14,40(r4)
+dest; std r15,40(r4)
- adde r0,r0,r14
-dest; std r15,48(r4)
-dest; std r16,56(r4)
+ adde r0,r0,r15
+dest; std r16,48(r4)
+dest; std r17,56(r4)
addi r4,r4,64
- adde r0,r0,r15
adde r0,r0,r16
+ adde r0,r0,r17
- ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
addi r1,r1,STACKFRAMESIZE
andi. r5,r5,63
@@ -406,9 +406,9 @@ dstnr; stb r6,0(r4)
blr
.Lsrc_error:
- ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
addi r1,r1,STACKFRAMESIZE
.Lsrc_error_nr:
cmpdi 0,r7,0
@@ -418,9 +418,9 @@ dstnr; stb r6,0(r4)
blr
.Ldest_error:
- ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
addi r1,r1,STACKFRAMESIZE
.Ldest_error_nr:
cmpdi 0,r8,0
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index ca5fc8fa7efc..c65fc4a412f2 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -113,13 +113,13 @@ _GLOBAL(copypage_power7)
#endif
.Lnonvmx_copy:
- std r14,STK_REG(R14)(r1)
std r15,STK_REG(R15)(r1)
std r16,STK_REG(R16)(r1)
std r17,STK_REG(R17)(r1)
std r18,STK_REG(R18)(r1)
std r19,STK_REG(R19)(r1)
std r20,STK_REG(R20)(r1)
+ std r21,STK_REG(R21)(r1)
1: ld r0,0(r4)
ld r5,8(r4)
@@ -130,13 +130,13 @@ _GLOBAL(copypage_power7)
ld r10,48(r4)
ld r11,56(r4)
ld r12,64(r4)
- ld r14,72(r4)
- ld r15,80(r4)
- ld r16,88(r4)
- ld r17,96(r4)
- ld r18,104(r4)
- ld r19,112(r4)
- ld r20,120(r4)
+ ld r15,72(r4)
+ ld r16,80(r4)
+ ld r17,88(r4)
+ ld r18,96(r4)
+ ld r19,104(r4)
+ ld r20,112(r4)
+ ld r21,120(r4)
addi r4,r4,128
std r0,0(r3)
std r5,8(r3)
@@ -147,22 +147,22 @@ _GLOBAL(copypage_power7)
std r10,48(r3)
std r11,56(r3)
std r12,64(r3)
- std r14,72(r3)
- std r15,80(r3)
- std r16,88(r3)
- std r17,96(r3)
- std r18,104(r3)
- std r19,112(r3)
- std r20,120(r3)
+ std r15,72(r3)
+ std r16,80(r3)
+ std r17,88(r3)
+ std r18,96(r3)
+ std r19,104(r3)
+ std r20,112(r3)
+ std r21,120(r3)
addi r3,r3,128
bdnz 1b
- ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
ld r17,STK_REG(R17)(r1)
ld r18,STK_REG(R18)(r1)
ld r19,STK_REG(R19)(r1)
ld r20,STK_REG(R20)(r1)
+ ld r21,STK_REG(R21)(r1)
addi r1,r1,STACKFRAMESIZE
blr
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index d416a4a66578..9c137451149b 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -50,9 +50,9 @@
.Ldo_err4:
- ld r16,STK_REG(R16)(r1)
- ld r15,STK_REG(R15)(r1)
- ld r14,STK_REG(R14)(r1)
+ ld r17,STK_REG(R16)(r1)
+ ld r16,STK_REG(R15)(r1)
+ ld r15,STK_REG(R14)(r1)
.Ldo_err3:
bl exit_vmx_usercopy
ld r0,STACKFRAMESIZE+16(r1)
@@ -61,15 +61,15 @@
#endif /* CONFIG_ALTIVEC */
.Ldo_err2:
- ld r22,STK_REG(R22)(r1)
- ld r21,STK_REG(R21)(r1)
- ld r20,STK_REG(R20)(r1)
- ld r19,STK_REG(R19)(r1)
- ld r18,STK_REG(R18)(r1)
- ld r17,STK_REG(R17)(r1)
- ld r16,STK_REG(R16)(r1)
- ld r15,STK_REG(R15)(r1)
- ld r14,STK_REG(R14)(r1)
+ ld r23,STK_REG(R22)(r1)
+ ld r22,STK_REG(R21)(r1)
+ ld r21,STK_REG(R20)(r1)
+ ld r20,STK_REG(R19)(r1)
+ ld r19,STK_REG(R18)(r1)
+ ld r18,STK_REG(R17)(r1)
+ ld r17,STK_REG(R16)(r1)
+ ld r16,STK_REG(R15)(r1)
+ ld r15,STK_REG(R14)(r1)
.Lexit:
addi r1,r1,STACKFRAMESIZE
.Ldo_err1:
@@ -130,15 +130,15 @@ err1; stw r0,0(r3)
mflr r0
stdu r1,-STACKFRAMESIZE(r1)
- std r14,STK_REG(R14)(r1)
- std r15,STK_REG(R15)(r1)
- std r16,STK_REG(R16)(r1)
- std r17,STK_REG(R17)(r1)
- std r18,STK_REG(R18)(r1)
- std r19,STK_REG(R19)(r1)
- std r20,STK_REG(R20)(r1)
- std r21,STK_REG(R21)(r1)
- std r22,STK_REG(R22)(r1)
+ std r15,STK_REG(R14)(r1)
+ std r16,STK_REG(R15)(r1)
+ std r17,STK_REG(R16)(r1)
+ std r18,STK_REG(R17)(r1)
+ std r19,STK_REG(R18)(r1)
+ std r20,STK_REG(R19)(r1)
+ std r21,STK_REG(R20)(r1)
+ std r22,STK_REG(R21)(r1)
+ std r23,STK_REG(R22)(r1)
std r0,STACKFRAMESIZE+16(r1)
srdi r6,r5,7
@@ -155,14 +155,14 @@ err2; ld r9,32(r4)
err2; ld r10,40(r4)
err2; ld r11,48(r4)
err2; ld r12,56(r4)
-err2; ld r14,64(r4)
-err2; ld r15,72(r4)
-err2; ld r16,80(r4)
-err2; ld r17,88(r4)
-err2; ld r18,96(r4)
-err2; ld r19,104(r4)
-err2; ld r20,112(r4)
-err2; ld r21,120(r4)
+err2; ld r15,64(r4)
+err2; ld r16,72(r4)
+err2; ld r17,80(r4)
+err2; ld r18,88(r4)
+err2; ld r19,96(r4)
+err2; ld r20,104(r4)
+err2; ld r21,112(r4)
+err2; ld r22,120(r4)
addi r4,r4,128
err2; std r0,0(r3)
err2; std r6,8(r3)
@@ -172,28 +172,28 @@ err2; std r9,32(r3)
err2; std r10,40(r3)
err2; std r11,48(r3)
err2; std r12,56(r3)
-err2; std r14,64(r3)
-err2; std r15,72(r3)
-err2; std r16,80(r3)
-err2; std r17,88(r3)
-err2; std r18,96(r3)
-err2; std r19,104(r3)
-err2; std r20,112(r3)
-err2; std r21,120(r3)
+err2; std r15,64(r3)
+err2; std r16,72(r3)
+err2; std r17,80(r3)
+err2; std r18,88(r3)
+err2; std r19,96(r3)
+err2; std r20,104(r3)
+err2; std r21,112(r3)
+err2; std r22,120(r3)
addi r3,r3,128
bdnz 4b
clrldi r5,r5,(64-7)
- ld r14,STK_REG(R14)(r1)
- ld r15,STK_REG(R15)(r1)
- ld r16,STK_REG(R16)(r1)
- ld r17,STK_REG(R17)(r1)
- ld r18,STK_REG(R18)(r1)
- ld r19,STK_REG(R19)(r1)
- ld r20,STK_REG(R20)(r1)
- ld r21,STK_REG(R21)(r1)
- ld r22,STK_REG(R22)(r1)
+ ld r15,STK_REG(R14)(r1)
+ ld r16,STK_REG(R15)(r1)
+ ld r17,STK_REG(R16)(r1)
+ ld r18,STK_REG(R17)(r1)
+ ld r19,STK_REG(R18)(r1)
+ ld r20,STK_REG(R19)(r1)
+ ld r21,STK_REG(R20)(r1)
+ ld r22,STK_REG(R21)(r1)
+ ld r23,STK_REG(R22)(r1)
addi r1,r1,STACKFRAMESIZE
/* Up to 127B to go */
@@ -404,14 +404,14 @@ err3; stvx v0,r3,r11
7: sub r5,r5,r6
srdi r6,r5,7
- std r14,STK_REG(R14)(r1)
- std r15,STK_REG(R15)(r1)
- std r16,STK_REG(R16)(r1)
+ std r15,STK_REG(R14)(r1)
+ std r16,STK_REG(R15)(r1)
+ std r17,STK_REG(R16)(r1)
li r12,64
- li r14,80
- li r15,96
- li r16,112
+ li r15,80
+ li r16,96
+ li r17,112
mtctr r6
@@ -426,24 +426,24 @@ err4; lvx v6,r4,r9
err4; lvx v5,r4,r10
err4; lvx v4,r4,r11
err4; lvx v3,r4,r12
-err4; lvx v2,r4,r14
-err4; lvx v1,r4,r15
-err4; lvx v0,r4,r16
+err4; lvx v2,r4,r15
+err4; lvx v1,r4,r16
+err4; lvx v0,r4,r17
addi r4,r4,128
err4; stvx v7,0,r3
err4; stvx v6,r3,r9
err4; stvx v5,r3,r10
err4; stvx v4,r3,r11
err4; stvx v3,r3,r12
-err4; stvx v2,r3,r14
-err4; stvx v1,r3,r15
-err4; stvx v0,r3,r16
+err4; stvx v2,r3,r15
+err4; stvx v1,r3,r16
+err4; stvx v0,r3,r17
addi r3,r3,128
bdnz 8b
- ld r14,STK_REG(R14)(r1)
- ld r15,STK_REG(R15)(r1)
- ld r16,STK_REG(R16)(r1)
+ ld r15,STK_REG(R14)(r1)
+ ld r16,STK_REG(R15)(r1)
+ ld r17,STK_REG(R16)(r1)
/* Up to 127B to go */
clrldi r5,r5,(64-7)
@@ -589,14 +589,14 @@ err3; stvx v11,r3,r11
7: sub r5,r5,r6
srdi r6,r5,7
- std r14,STK_REG(R14)(r1)
- std r15,STK_REG(R15)(r1)
- std r16,STK_REG(R16)(r1)
+ std r15,STK_REG(R14)(r1)
+ std r16,STK_REG(R15)(r1)
+ std r17,STK_REG(R16)(r1)
li r12,64
- li r14,80
- li r15,96
- li r16,112
+ li r15,80
+ li r16,96
+ li r17,112
mtctr r6
@@ -616,11 +616,11 @@ err4; lvx v4,r4,r11
VPERM(v11,v5,v4,v16)
err4; lvx v3,r4,r12
VPERM(v12,v4,v3,v16)
-err4; lvx v2,r4,r14
+err4; lvx v2,r4,r15
VPERM(v13,v3,v2,v16)
-err4; lvx v1,r4,r15
+err4; lvx v1,r4,r16
VPERM(v14,v2,v1,v16)
-err4; lvx v0,r4,r16
+err4; lvx v0,r4,r17
VPERM(v15,v1,v0,v16)
addi r4,r4,128
err4; stvx v8,0,r3
@@ -628,15 +628,15 @@ err4; stvx v9,r3,r9
err4; stvx v10,r3,r10
err4; stvx v11,r3,r11
err4; stvx v12,r3,r12
-err4; stvx v13,r3,r14
-err4; stvx v14,r3,r15
-err4; stvx v15,r3,r16
+err4; stvx v13,r3,r15
+err4; stvx v14,r3,r16
+err4; stvx v15,r3,r17
addi r3,r3,128
bdnz 8b
- ld r14,STK_REG(R14)(r1)
- ld r15,STK_REG(R15)(r1)
- ld r16,STK_REG(R16)(r1)
+ ld r15,STK_REG(R14)(r1)
+ ld r16,STK_REG(R15)(r1)
+ ld r17,STK_REG(R16)(r1)
/* Up to 127B to go */
clrldi r5,r5,(64-7)
diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
index 7e5e1c28e56a..c46ad2f0a718 100644
--- a/arch/powerpc/lib/crtsavres.S
+++ b/arch/powerpc/lib/crtsavres.S
@@ -314,9 +314,12 @@ _GLOBAL(_restvr_31)
#else /* CONFIG_PPC64 */
+/* 64-bit has -ffixed-r13, Book3S also has -ffixed-r14 */
+#ifdef CONFIG_PPC_BOOK3E
.globl _savegpr0_14
_savegpr0_14:
std r14,-144(r1)
+#endif
.globl _savegpr0_15
_savegpr0_15:
std r15,-136(r1)
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 193909abd18b..dd679a0fa650 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -75,7 +75,6 @@ _GLOBAL(memcpy_power7)
mflr r0
stdu r1,-STACKFRAMESIZE(r1)
- std r14,STK_REG(R14)(r1)
std r15,STK_REG(R15)(r1)
std r16,STK_REG(R16)(r1)
std r17,STK_REG(R17)(r1)
@@ -84,6 +83,7 @@ _GLOBAL(memcpy_power7)
std r20,STK_REG(R20)(r1)
std r21,STK_REG(R21)(r1)
std r22,STK_REG(R22)(r1)
+ std r23,STK_REG(R23)(r1)
std r0,STACKFRAMESIZE+16(r1)
srdi r6,r5,7
@@ -100,14 +100,14 @@ _GLOBAL(memcpy_power7)
ld r10,40(r4)
ld r11,48(r4)
ld r12,56(r4)
- ld r14,64(r4)
- ld r15,72(r4)
- ld r16,80(r4)
- ld r17,88(r4)
- ld r18,96(r4)
- ld r19,104(r4)
- ld r20,112(r4)
- ld r21,120(r4)
+ ld r15,64(r4)
+ ld r16,72(r4)
+ ld r17,80(r4)
+ ld r18,88(r4)
+ ld r19,96(r4)
+ ld r20,104(r4)
+ ld r21,112(r4)
+ ld r22,120(r4)
addi r4,r4,128
std r0,0(r3)
std r6,8(r3)
@@ -117,20 +117,19 @@ _GLOBAL(memcpy_power7)
std r10,40(r3)
std r11,48(r3)
std r12,56(r3)
- std r14,64(r3)
- std r15,72(r3)
- std r16,80(r3)
- std r17,88(r3)
- std r18,96(r3)
- std r19,104(r3)
- std r20,112(r3)
- std r21,120(r3)
+ std r15,64(r3)
+ std r16,72(r3)
+ std r17,80(r3)
+ std r18,88(r3)
+ std r19,96(r3)
+ std r20,104(r3)
+ std r21,112(r3)
+ std r22,120(r3)
addi r3,r3,128
bdnz 4b
clrldi r5,r5,(64-7)
- ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
ld r17,STK_REG(R17)(r1)
@@ -139,6 +138,7 @@ _GLOBAL(memcpy_power7)
ld r20,STK_REG(R20)(r1)
ld r21,STK_REG(R21)(r1)
ld r22,STK_REG(R22)(r1)
+ ld r23,STK_REG(R23)(r1)
addi r1,r1,STACKFRAMESIZE
/* Up to 127B to go */
@@ -349,14 +349,14 @@ _GLOBAL(memcpy_power7)
7: sub r5,r5,r6
srdi r6,r5,7
- std r14,STK_REG(R14)(r1)
std r15,STK_REG(R15)(r1)
std r16,STK_REG(R16)(r1)
+ std r17,STK_REG(R17)(r1)
li r12,64
- li r14,80
- li r15,96
- li r16,112
+ li r15,80
+ li r16,96
+ li r17,112
mtctr r6
@@ -371,24 +371,24 @@ _GLOBAL(memcpy_power7)
lvx v5,r4,r10
lvx v4,r4,r11
lvx v3,r4,r12
- lvx v2,r4,r14
- lvx v1,r4,r15
- lvx v0,r4,r16
+ lvx v2,r4,r15
+ lvx v1,r4,r16
+ lvx v0,r4,r17
addi r4,r4,128
stvx v7,0,r3
stvx v6,r3,r9
stvx v5,r3,r10
stvx v4,r3,r11
stvx v3,r3,r12
- stvx v2,r3,r14
- stvx v1,r3,r15
- stvx v0,r3,r16
+ stvx v2,r3,r15
+ stvx v1,r3,r16
+ stvx v0,r3,r17
addi r3,r3,128
bdnz 8b
- ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
/* Up to 127B to go */
clrldi r5,r5,(64-7)
@@ -535,14 +535,14 @@ _GLOBAL(memcpy_power7)
7: sub r5,r5,r6
srdi r6,r5,7
- std r14,STK_REG(R14)(r1)
std r15,STK_REG(R15)(r1)
std r16,STK_REG(R16)(r1)
+ std r17,STK_REG(R17)(r1)
li r12,64
- li r14,80
- li r15,96
- li r16,112
+ li r15,80
+ li r16,96
+ li r17,112
mtctr r6
@@ -562,11 +562,11 @@ _GLOBAL(memcpy_power7)
VPERM(v11,v5,v4,v16)
lvx v3,r4,r12
VPERM(v12,v4,v3,v16)
- lvx v2,r4,r14
+ lvx v2,r4,r15
VPERM(v13,v3,v2,v16)
- lvx v1,r4,r15
+ lvx v1,r4,r16
VPERM(v14,v2,v1,v16)
- lvx v0,r4,r16
+ lvx v0,r4,r17
VPERM(v15,v1,v0,v16)
addi r4,r4,128
stvx v8,0,r3
@@ -574,15 +574,15 @@ _GLOBAL(memcpy_power7)
stvx v10,r3,r10
stvx v11,r3,r11
stvx v12,r3,r12
- stvx v13,r3,r14
- stvx v14,r3,r15
- stvx v15,r3,r16
+ stvx v13,r3,r15
+ stvx v14,r3,r16
+ stvx v15,r3,r17
addi r3,r3,128
bdnz 8b
- ld r14,STK_REG(R14)(r1)
ld r15,STK_REG(R15)(r1)
ld r16,STK_REG(R16)(r1)
+ ld r17,STK_REG(R17)(r1)
/* Up to 127B to go */
clrldi r5,r5,(64-7)
--
2.15.0
next prev parent reply other threads:[~2017-12-20 14:52 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-20 14:51 [RFC PATCH 0/8] use r14 for a per-cpu kernel register Nicholas Piggin
2017-12-20 14:51 ` Nicholas Piggin [this message]
2017-12-20 14:52 ` [RFC PATCH 2/8] powerpc/64s: poison r14 register while in kernel Nicholas Piggin
2017-12-20 14:52 ` [RFC PATCH 3/8] powerpc/64s: put the per-cpu data_offset in r14 Nicholas Piggin
2017-12-20 17:53 ` Gabriel Paubert
2017-12-22 13:50 ` Nicholas Piggin
2017-12-20 14:52 ` [RFC PATCH 4/8] powerpc/64s: put io_sync bit into r14 Nicholas Piggin
2017-12-22 15:08 ` Thiago Jung Bauermann
2017-12-20 14:52 ` [RFC PATCH 5/8] powerpc/64s: put work_pending " Nicholas Piggin
2017-12-20 14:52 ` [RFC PATCH 6/8] powerpc/64s: put irq_soft_mask bits " Nicholas Piggin
2017-12-20 14:52 ` [RFC PATCH 7/8] powerpc/64s: put irq_soft_mask and irq_happened " Nicholas Piggin
2017-12-20 14:52 ` [RFC PATCH 8/8] powerpc/64s: inline local_irq_enable/restore Nicholas Piggin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20171220145206.12234-2-npiggin@gmail.com \
--to=npiggin@gmail.com \
--cc=linuxppc-dev@lists.ozlabs.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.