UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/arch/powerpc/platforms/pseries/hvCall.S

339 lines
6.4 KiB
ArmAsm
Raw Normal View History

Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/*
* This file contains the generic code to perform a call to the
* pSeries LPAR hypervisor.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <asm/hvcall.h>
#include <asm/processor.h>
#include <asm/ppc_asm.h>
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
#include <asm/asm-offsets.h>
powerpc: Remove second definition of STACK_FRAME_OVERHEAD Since STACK_FRAME_OVERHEAD is defined in asm/ptrace.h and that is ASSEMBER safe, we can just include that instead of going via asm-offsets.h. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-11-18 23:06:17 +08:00
#include <asm/ptrace.h>
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
#include <asm/jump_label.h>
.section ".text"
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
#ifdef CONFIG_TRACEPOINTS
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
#ifndef CONFIG_JUMP_LABEL
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
.section ".toc","aw"
.globl hcall_tracepoint_refcount
hcall_tracepoint_refcount:
.llong 0
.section ".text"
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
#endif
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
/*
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
* precall must preserve all registers. use unused STK_PARAM()
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
* areas to save snapshots and opcode.
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
*/
powerpc: tracing: Give hypervisor call tracepoints access to arguments While most users of the hcall tracepoints will only want the opcode and return code, some will want all the arguments. To avoid the complexity of using varargs we pass a pointer to the register save area, which contains all the arguments. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:51:09 +08:00
#define HCALL_INST_PRECALL(FIRST_REG) \
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
mflr r0; \
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
std r3,STK_PARAM(R3)(r1); \
std r4,STK_PARAM(R4)(r1); \
std r5,STK_PARAM(R5)(r1); \
std r6,STK_PARAM(R6)(r1); \
std r7,STK_PARAM(R7)(r1); \
std r8,STK_PARAM(R8)(r1); \
std r9,STK_PARAM(R9)(r1); \
std r10,STK_PARAM(R10)(r1); \
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
std r0,16(r1); \
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
addi r4,r1,STK_PARAM(FIRST_REG); \
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
stdu r1,-STACK_FRAME_OVERHEAD(r1); \
powerpc: No need to use dot symbols when branching to a function binutils is smart enough to know that a branch to a function descriptor is actually a branch to the functions text address. Alan tells me that binutils has been doing this for 9 years. Signed-off-by: Anton Blanchard <anton@samba.org>
2014-02-04 13:04:35 +08:00
bl __trace_hcall_entry; \
powerpc/pseries: Optimise hcall tracepoints Now that we execute the hcall tracepoint entry and exit code out of line, we can use the same stack across both functions. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:56 +08:00
ld r3,STACK_FRAME_OVERHEAD+STK_PARAM(R3)(r1); \
ld r4,STACK_FRAME_OVERHEAD+STK_PARAM(R4)(r1); \
ld r5,STACK_FRAME_OVERHEAD+STK_PARAM(R5)(r1); \
ld r6,STACK_FRAME_OVERHEAD+STK_PARAM(R6)(r1); \
ld r7,STACK_FRAME_OVERHEAD+STK_PARAM(R7)(r1); \
ld r8,STACK_FRAME_OVERHEAD+STK_PARAM(R8)(r1); \
ld r9,STACK_FRAME_OVERHEAD+STK_PARAM(R9)(r1); \
ld r10,STACK_FRAME_OVERHEAD+STK_PARAM(R10)(r1)
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
/*
* postcall is performed immediately before function return which
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
* allows liberal use of volatile registers.
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
*/
powerpc: tracing: Give hypervisor call tracepoints access to arguments While most users of the hcall tracepoints will only want the opcode and return code, some will want all the arguments. To avoid the complexity of using varargs we pass a pointer to the register save area, which contains all the arguments. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:51:09 +08:00
#define __HCALL_INST_POSTCALL \
powerpc/pseries: Optimise hcall tracepoints Now that we execute the hcall tracepoint entry and exit code out of line, we can use the same stack across both functions. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:56 +08:00
ld r0,STACK_FRAME_OVERHEAD+STK_PARAM(R3)(r1); \
std r3,STACK_FRAME_OVERHEAD+STK_PARAM(R3)(r1); \
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
mr r4,r3; \
powerpc/pseries: Optimise hcall tracepoints Now that we execute the hcall tracepoint entry and exit code out of line, we can use the same stack across both functions. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:56 +08:00
mr r3,r0; \
powerpc: No need to use dot symbols when branching to a function binutils is smart enough to know that a branch to a function descriptor is actually a branch to the functions text address. Alan tells me that binutils has been doing this for 9 years. Signed-off-by: Anton Blanchard <anton@samba.org>
2014-02-04 13:04:35 +08:00
bl __trace_hcall_exit; \
powerpc/pseries: Optimise hcall tracepoints Now that we execute the hcall tracepoint entry and exit code out of line, we can use the same stack across both functions. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:56 +08:00
ld r0,STACK_FRAME_OVERHEAD+16(r1); \
powerpc: tracing: Add hypervisor call tracepoints Add hcall_entry and hcall_exit tracepoints. This replaces the inline assembly HCALL_STATS code and converts it to use the new tracepoints. To keep the disabled case as quick as possible, we embed a status word in the TOC so we can get at it with a single load. By doing so we keep the overhead at a minimum. Time taken for a null hcall: No tracepoint code: 135.79 cycles Disabled tracepoints: 137.95 cycles For reference, before this patch enabling HCALL_STATS resulted in a null hcall of 201.44 cycles! Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:50:29 +08:00
addi r1,r1,STACK_FRAME_OVERHEAD; \
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
ld r3,STK_PARAM(R3)(r1); \
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
mtlr r0
powerpc: tracing: Give hypervisor call tracepoints access to arguments While most users of the hcall tracepoints will only want the opcode and return code, some will want all the arguments. To avoid the complexity of using varargs we pass a pointer to the register save area, which contains all the arguments. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:51:09 +08:00
#define HCALL_INST_POSTCALL_NORETS \
li r5,0; \
__HCALL_INST_POSTCALL
#define HCALL_INST_POSTCALL(BUFREG) \
mr r5,BUFREG; \
__HCALL_INST_POSTCALL
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
#ifdef CONFIG_JUMP_LABEL
#define HCALL_BRANCH(LABEL) \
ARCH_STATIC_BRANCH(LABEL, hcall_tracepoint_key)
#else
/*
* We branch around this in early init (eg when populating the MMU
* hashtable) by using an unconditional cpu feature.
*/
#define HCALL_BRANCH(LABEL) \
BEGIN_FTR_SECTION; \
b 1f; \
END_FTR_SECTION(0, 1); \
ld r12,hcall_tracepoint_refcount@toc(r2); \
std r12,32(r1); \
cmpdi r12,0; \
bne- LABEL; \
1:
#endif
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
#else
powerpc: tracing: Give hypervisor call tracepoints access to arguments While most users of the hcall tracepoints will only want the opcode and return code, some will want all the arguments. To avoid the complexity of using varargs we pass a pointer to the register save area, which contains all the arguments. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:51:09 +08:00
#define HCALL_INST_PRECALL(FIRST_ARG)
#define HCALL_INST_POSTCALL_NORETS
#define HCALL_INST_POSTCALL(BUFREG)
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
#define HCALL_BRANCH(LABEL)
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
#endif
powerpc/pseries: hcall functions are exported to modules, need _GLOBAL_TOC() The hcall macros may call out to c code for tracing, so we need to set up a valid r2. This fixes an oops found when testing ibmvscsi as a module. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-05-13 18:48:57 +08:00
_GLOBAL_TOC(plpar_hcall_norets)
[PATCH] ppc64: enforce medium thread priority in hypervisor calls Calls into the hypervisor do not raise the thread priority. Ensure we are running at medium priority upon entry to the hypervisor. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 23:58:46 +08:00
HMT_MEDIUM
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
mfcr r0
stw r0,8(r1)
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
HCALL_BRANCH(plpar_hcall_norets_trace)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
HVSC /* invoke the hypervisor */
lwz r0,8(r1)
mtcrf 0xff,r0
blr /* return r3 = status */
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
#ifdef CONFIG_TRACEPOINTS
plpar_hcall_norets_trace:
HCALL_INST_PRECALL(R4)
HVSC
HCALL_INST_POSTCALL_NORETS
lwz r0,8(r1)
mtcrf 0xff,r0
blr
#endif
powerpc/pseries: hcall functions are exported to modules, need _GLOBAL_TOC() The hcall macros may call out to c code for tracing, so we need to set up a valid r2. This fixes an oops found when testing ibmvscsi as a module. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-05-13 18:48:57 +08:00
_GLOBAL_TOC(plpar_hcall)
[PATCH] ppc64: enforce medium thread priority in hypervisor calls Calls into the hypervisor do not raise the thread priority. Ensure we are running at medium priority upon entry to the hypervisor. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 23:58:46 +08:00
HMT_MEDIUM
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
mfcr r0
stw r0,8(r1)
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
HCALL_BRANCH(plpar_hcall_trace)
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
std r4,STK_PARAM(R4)(r1) /* Save ret buffer */
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[POWERPC] clean up pseries hcall interfaces Our pseries hcall interfaces are out of control: plpar_hcall_norets plpar_hcall plpar_hcall_8arg_2ret plpar_hcall_4out plpar_hcall_7arg_7ret plpar_hcall_9arg_9ret Create 3 interfaces to cover all cases: plpar_hcall_norets: 7 arguments no returns plpar_hcall: 6 arguments 4 returns plpar_hcall9: 9 arguments 9 returns There are only 2 cases in the kernel that need plpar_hcall9, hopefully we can keep it that way. Pass in a buffer to stash return parameters so we avoid the &dummy1, &dummy2 madness. Signed-off-by: Anton Blanchard <anton@samba.org> -- Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-07-19 06:01:28 +08:00
mr r4,r5
mr r5,r6
mr r6,r7
mr r7,r8
mr r8,r9
mr r9,r10
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
HVSC /* invoke the hypervisor */
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
ld r12,STK_PARAM(R4)(r1)
[POWERPC] clean up pseries hcall interfaces Our pseries hcall interfaces are out of control: plpar_hcall_norets plpar_hcall plpar_hcall_8arg_2ret plpar_hcall_4out plpar_hcall_7arg_7ret plpar_hcall_9arg_9ret Create 3 interfaces to cover all cases: plpar_hcall_norets: 7 arguments no returns plpar_hcall: 6 arguments 4 returns plpar_hcall9: 9 arguments 9 returns There are only 2 cases in the kernel that need plpar_hcall9, hopefully we can keep it that way. Pass in a buffer to stash return parameters so we avoid the &dummy1, &dummy2 madness. Signed-off-by: Anton Blanchard <anton@samba.org> -- Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-07-19 06:01:28 +08:00
std r4, 0(r12)
std r5, 8(r12)
std r6, 16(r12)
std r7, 24(r12)
[PATCH] powerpc: Extends HCALL interface for InfiniBand usage This extends the HCALL interface for InfiniBand usage. I've made the patch against the linux-2.6 git tree and Segher's patch: [PATCH] Change H_StudlyCaps to H_SHOUTING_CAPS We moved this into the common powerpc code based on comments we got after posting the first eHCA InfiniBand device driver patch. Signed-off-by: Heiko j Schick <schickhj@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-03-31 04:47:14 +08:00
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
lwz r0,8(r1)
mtcrf 0xff,r0
blr /* return r3 = status */
#ifdef CONFIG_TRACEPOINTS
plpar_hcall_trace:
HCALL_INST_PRECALL(R5)
std r4,STK_PARAM(R4)(r1)
mr r0,r4
mr r4,r5
mr r5,r6
mr r6,r7
mr r7,r8
mr r8,r9
mr r9,r10
HVSC
ld r12,STK_PARAM(R4)(r1)
std r4,0(r12)
std r5,8(r12)
std r6,16(r12)
std r7,24(r12)
powerpc: tracing: Give hypervisor call tracepoints access to arguments While most users of the hcall tracepoints will only want the opcode and return code, some will want all the arguments. To avoid the complexity of using varargs we pass a pointer to the register save area, which contains all the arguments. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:51:09 +08:00
HCALL_INST_POSTCALL(r12)
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
[PATCH] powerpc: Extends HCALL interface for InfiniBand usage This extends the HCALL interface for InfiniBand usage. I've made the patch against the linux-2.6 git tree and Segher's patch: [PATCH] Change H_StudlyCaps to H_SHOUTING_CAPS We moved this into the common powerpc code based on comments we got after posting the first eHCA InfiniBand device driver patch. Signed-off-by: Heiko j Schick <schickhj@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-03-31 04:47:14 +08:00
lwz r0,8(r1)
mtcrf 0xff,r0
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
blr
#endif
[PATCH] powerpc: Extends HCALL interface for InfiniBand usage This extends the HCALL interface for InfiniBand usage. I've made the patch against the linux-2.6 git tree and Segher's patch: [PATCH] Change H_StudlyCaps to H_SHOUTING_CAPS We moved this into the common powerpc code based on comments we got after posting the first eHCA InfiniBand device driver patch. Signed-off-by: Heiko j Schick <schickhj@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-03-31 04:47:14 +08:00
[POWERPC] Avoid hypervisor statistics calculation in real mode kexec invokes plpar_hcall hypervisor call in real mode. plpar_hcall refers to per cpu variables for accounting hypervisor statistics. These variables may not be in the RMO region, so accesses to them in real mode may result in a data storage exception. This fixes this problem by using a new plpar_hcall_raw function which does not update the hypervisor call statistics. Thanks to Anton for suggesting this idea. Signed-off-by: Mohan Kumar M <mohan@in.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-03-21 13:51:32 +08:00
/*
* plpar_hcall_raw can be called in real mode. kexec/kdump need some
* hypervisor calls to be executed in real mode. So plpar_hcall_raw
* does not access the per cpu hypervisor call statistics variables,
* since these variables may not be present in the RMO region.
*/
_GLOBAL(plpar_hcall_raw)
HMT_MEDIUM
mfcr r0
stw r0,8(r1)
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
std r4,STK_PARAM(R4)(r1) /* Save ret buffer */
[POWERPC] Avoid hypervisor statistics calculation in real mode kexec invokes plpar_hcall hypervisor call in real mode. plpar_hcall refers to per cpu variables for accounting hypervisor statistics. These variables may not be in the RMO region, so accesses to them in real mode may result in a data storage exception. This fixes this problem by using a new plpar_hcall_raw function which does not update the hypervisor call statistics. Thanks to Anton for suggesting this idea. Signed-off-by: Mohan Kumar M <mohan@in.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-03-21 13:51:32 +08:00
mr r4,r5
mr r5,r6
mr r6,r7
mr r7,r8
mr r8,r9
mr r9,r10
HVSC /* invoke the hypervisor */
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
ld r12,STK_PARAM(R4)(r1)
[POWERPC] Avoid hypervisor statistics calculation in real mode kexec invokes plpar_hcall hypervisor call in real mode. plpar_hcall refers to per cpu variables for accounting hypervisor statistics. These variables may not be in the RMO region, so accesses to them in real mode may result in a data storage exception. This fixes this problem by using a new plpar_hcall_raw function which does not update the hypervisor call statistics. Thanks to Anton for suggesting this idea. Signed-off-by: Mohan Kumar M <mohan@in.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-03-21 13:51:32 +08:00
std r4, 0(r12)
std r5, 8(r12)
std r6, 16(r12)
std r7, 24(r12)
lwz r0,8(r1)
mtcrf 0xff,r0
blr /* return r3 = status */
powerpc/pseries: hcall functions are exported to modules, need _GLOBAL_TOC() The hcall macros may call out to c code for tracing, so we need to set up a valid r2. This fixes an oops found when testing ibmvscsi as a module. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-05-13 18:48:57 +08:00
_GLOBAL_TOC(plpar_hcall9)
[PATCH] powerpc: Extends HCALL interface for InfiniBand usage This extends the HCALL interface for InfiniBand usage. I've made the patch against the linux-2.6 git tree and Segher's patch: [PATCH] Change H_StudlyCaps to H_SHOUTING_CAPS We moved this into the common powerpc code based on comments we got after posting the first eHCA InfiniBand device driver patch. Signed-off-by: Heiko j Schick <schickhj@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-03-31 04:47:14 +08:00
HMT_MEDIUM
mfcr r0
stw r0,8(r1)
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
HCALL_BRANCH(plpar_hcall9_trace)
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
std r4,STK_PARAM(R4)(r1) /* Save ret buffer */
[POWERPC] clean up pseries hcall interfaces Our pseries hcall interfaces are out of control: plpar_hcall_norets plpar_hcall plpar_hcall_8arg_2ret plpar_hcall_4out plpar_hcall_7arg_7ret plpar_hcall_9arg_9ret Create 3 interfaces to cover all cases: plpar_hcall_norets: 7 arguments no returns plpar_hcall: 6 arguments 4 returns plpar_hcall9: 9 arguments 9 returns There are only 2 cases in the kernel that need plpar_hcall9, hopefully we can keep it that way. Pass in a buffer to stash return parameters so we avoid the &dummy1, &dummy2 madness. Signed-off-by: Anton Blanchard <anton@samba.org> -- Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-07-19 06:01:28 +08:00
mr r4,r5
mr r5,r6
mr r6,r7
mr r7,r8
mr r8,r9
mr r9,r10
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
ld r10,STK_PARAM(R11)(r1) /* put arg7 in R10 */
ld r11,STK_PARAM(R12)(r1) /* put arg8 in R11 */
ld r12,STK_PARAM(R13)(r1) /* put arg9 in R12 */
[PATCH] powerpc: Extends HCALL interface for InfiniBand usage This extends the HCALL interface for InfiniBand usage. I've made the patch against the linux-2.6 git tree and Segher's patch: [PATCH] Change H_StudlyCaps to H_SHOUTING_CAPS We moved this into the common powerpc code based on comments we got after posting the first eHCA InfiniBand device driver patch. Signed-off-by: Heiko j Schick <schickhj@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-03-31 04:47:14 +08:00
HVSC /* invoke the hypervisor */
[POWERPC] Fix corruption in hcall9 It looks to me like we are corrupting r12 in the hcall9 function. Although we have r0 free we cant use offsets against it, so save away r12 in there instead. r12 holds the ninth return value from the hypervisor call, so without this fix, the caller will see the wrong value for the ninth element in the array that gets the return values. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-01-08 23:37:16 +08:00
mr r0,r12
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
ld r12,STK_PARAM(R4)(r1)
[POWERPC] clean up pseries hcall interfaces Our pseries hcall interfaces are out of control: plpar_hcall_norets plpar_hcall plpar_hcall_8arg_2ret plpar_hcall_4out plpar_hcall_7arg_7ret plpar_hcall_9arg_9ret Create 3 interfaces to cover all cases: plpar_hcall_norets: 7 arguments no returns plpar_hcall: 6 arguments 4 returns plpar_hcall9: 9 arguments 9 returns There are only 2 cases in the kernel that need plpar_hcall9, hopefully we can keep it that way. Pass in a buffer to stash return parameters so we avoid the &dummy1, &dummy2 madness. Signed-off-by: Anton Blanchard <anton@samba.org> -- Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-07-19 06:01:28 +08:00
std r4, 0(r12)
std r5, 8(r12)
std r6, 16(r12)
std r7, 24(r12)
std r8, 32(r12)
std r9, 40(r12)
std r10,48(r12)
std r11,56(r12)
[POWERPC] Fix corruption in hcall9 It looks to me like we are corrupting r12 in the hcall9 function. Although we have r0 free we cant use offsets against it, so save away r12 in there instead. r12 holds the ninth return value from the hypervisor call, so without this fix, the caller will see the wrong value for the ninth element in the array that gets the return values. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2007-01-08 23:37:16 +08:00
std r0, 64(r12)
[PATCH] powerpc: Extends HCALL interface for InfiniBand usage This extends the HCALL interface for InfiniBand usage. I've made the patch against the linux-2.6 git tree and Segher's patch: [PATCH] Change H_StudlyCaps to H_SHOUTING_CAPS We moved this into the common powerpc code based on comments we got after posting the first eHCA InfiniBand device driver patch. Signed-off-by: Heiko j Schick <schickhj@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-03-31 04:47:14 +08:00
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
lwz r0,8(r1)
mtcrf 0xff,r0
blr /* return r3 = status */
#ifdef CONFIG_TRACEPOINTS
plpar_hcall9_trace:
HCALL_INST_PRECALL(R5)
std r4,STK_PARAM(R4)(r1)
mr r0,r4
mr r4,r5
mr r5,r6
mr r6,r7
mr r7,r8
mr r8,r9
mr r9,r10
powerpc/pseries: Optimise hcall tracepoints Now that we execute the hcall tracepoint entry and exit code out of line, we can use the same stack across both functions. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:56 +08:00
ld r10,STACK_FRAME_OVERHEAD+STK_PARAM(R11)(r1)
ld r11,STACK_FRAME_OVERHEAD+STK_PARAM(R12)(r1)
ld r12,STACK_FRAME_OVERHEAD+STK_PARAM(R13)(r1)
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
HVSC
mr r0,r12
powerpc/pseries: Optimise hcall tracepoints Now that we execute the hcall tracepoint entry and exit code out of line, we can use the same stack across both functions. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:56 +08:00
ld r12,STACK_FRAME_OVERHEAD+STK_PARAM(R4)(r1)
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
std r4,0(r12)
std r5,8(r12)
std r6,16(r12)
std r7,24(r12)
std r8,32(r12)
std r9,40(r12)
std r10,48(r12)
std r11,56(r12)
std r0,64(r12)
powerpc: tracing: Give hypervisor call tracepoints access to arguments While most users of the hcall tracepoints will only want the opcode and return code, some will want all the arguments. To avoid the complexity of using varargs we pass a pointer to the register save area, which contains all the arguments. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-10-27 02:51:09 +08:00
HCALL_INST_POSTCALL(r12)
[POWERPC] powerpc: Instrument Hypervisor Calls Add instrumentation for hypervisor calls on pseries. Call statistics include number of calls, wall time and cpu cycles (if available) and are made available via debugfs. Instrumentation code is behind the HCALL_STATS config option and has no impact if not enabled. Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-09-07 07:23:12 +08:00
[PATCH] powerpc: Extends HCALL interface for InfiniBand usage This extends the HCALL interface for InfiniBand usage. I've made the patch against the linux-2.6 git tree and Segher's patch: [PATCH] Change H_StudlyCaps to H_SHOUTING_CAPS We moved this into the common powerpc code based on comments we got after posting the first eHCA InfiniBand device driver patch. Signed-off-by: Heiko j Schick <schickhj@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-03-31 04:47:14 +08:00
lwz r0,8(r1)
mtcrf 0xff,r0
powerpc/pseries: Use jump labels for hcall tracepoints hcall tracepoints add quite a few instructions to our hcall path: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) b 164 <---- start ld r12,0(r2) std r12,32(r1) cmpdi r12,0 beq 164 <---- end ... We have an unconditional branch that gets noped out during boot and a load/compare/branch. We also store the tracepoint value to the stack for the hcall_exit path to use. By using jump labels we can simplify this to just a single nop that gets replaced with a branch when the tracepoint is enabled: plpar_hcall: mr r2,r2 mfcr r0 stw r0,8(r1) nop <---- ... If jump labels are not enabled, we fall back to the old method. Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2014-07-03 13:52:03 +08:00
blr
#endif
powerpc/pseries: Add hcall to read 4 ptes at a time in real mode This adds plpar_pte_read_4_raw() which can be used read 4 PTEs from PHYP at a time, while in real mode. It also creates a new hcall9 which can be used in real mode. It's the same as plpar_hcall9 but minus the tracing hcall statistics which may require variables outside the RMO. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-05-11 04:28:26 +08:00
/* See plpar_hcall_raw to see why this is needed */
_GLOBAL(plpar_hcall9_raw)
HMT_MEDIUM
mfcr r0
stw r0,8(r1)
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
std r4,STK_PARAM(R4)(r1) /* Save ret buffer */
powerpc/pseries: Add hcall to read 4 ptes at a time in real mode This adds plpar_pte_read_4_raw() which can be used read 4 PTEs from PHYP at a time, while in real mode. It also creates a new hcall9 which can be used in real mode. It's the same as plpar_hcall9 but minus the tracing hcall statistics which may require variables outside the RMO. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-05-11 04:28:26 +08:00
mr r4,r5
mr r5,r6
mr r6,r7
mr r7,r8
mr r8,r9
mr r9,r10
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
ld r10,STK_PARAM(R11)(r1) /* put arg7 in R10 */
ld r11,STK_PARAM(R12)(r1) /* put arg8 in R11 */
ld r12,STK_PARAM(R13)(r1) /* put arg9 in R12 */
powerpc/pseries: Add hcall to read 4 ptes at a time in real mode This adds plpar_pte_read_4_raw() which can be used read 4 PTEs from PHYP at a time, while in real mode. It also creates a new hcall9 which can be used in real mode. It's the same as plpar_hcall9 but minus the tracing hcall statistics which may require variables outside the RMO. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-05-11 04:28:26 +08:00
HVSC /* invoke the hypervisor */
mr r0,r12
powerpc: Merge STK_REG/PARAM/FRAMESIZE Merge the defines of STACKFRAMESIZE, STK_REG, STK_PARAM from different places. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2012-06-25 21:33:14 +08:00
ld r12,STK_PARAM(R4)(r1)
powerpc/pseries: Add hcall to read 4 ptes at a time in real mode This adds plpar_pte_read_4_raw() which can be used read 4 PTEs from PHYP at a time, while in real mode. It also creates a new hcall9 which can be used in real mode. It's the same as plpar_hcall9 but minus the tracing hcall statistics which may require variables outside the RMO. Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2010-05-11 04:28:26 +08:00
std r4, 0(r12)
std r5, 8(r12)
std r6, 16(r12)
std r7, 24(r12)
std r8, 32(r12)
std r9, 40(r12)
std r10,48(r12)
std r11,56(r12)
std r0, 64(r12)
lwz r0,8(r1)
mtcrf 0xff,r0
blr /* return r3 = status */