mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/herbert/cryptodev-2.6.git
synced 2026-04-18 03:23:53 -04:00
eec37961a5
Function profile sequence on powerpc includes two instructions at the beginning of each function: mflr r0 bl ftrace_caller The call to ftrace_caller() gets nop'ed out during kernel boot and is patched in when ftrace is enabled. Given the sequence, we cannot return from ftrace_caller with 'blr' as we need to keep LR and r0 intact. This results in link stack (return address predictor) imbalance when ftrace is enabled. To address that, we would like to use a three instruction sequence: mflr r0 bl ftrace_caller mtlr r0 Further more, to support DYNAMIC_FTRACE_WITH_CALL_OPS, we need to reserve two instruction slots before the function. This results in a total of five instruction slots to be reserved for ftrace use on each function that is traced. Move the function profile sequence out-of-line to minimize its impact. To do this, we reserve a single nop at function entry using -fpatchable-function-entry=1 and add a pass on vmlinux.o to determine the total number of functions that can be traced. This is then used to generate a .S file reserving the appropriate amount of space for use as ftrace stubs, which is built and linked into vmlinux. On bootup, the stub space is split into separate stubs per function and populated with the proper instruction sequence. A pointer to the associated stub is maintained in dyn_arch_ftrace. For modules, space for ftrace stubs is reserved from the generic module stub space. This is restricted to and enabled by default only on 64-bit powerpc, though there are some changes to accommodate 32-bit powerpc. This is done so that 32-bit powerpc could choose to opt into this based on further tests and benchmarks. As an example, after this patch, kernel functions will have a single nop at function entry: <kernel_clone>: addis r2,r12,467 addi r2,r2,-16028 nop mfocrf r11,8 ... When ftrace is enabled, the nop is converted to an unconditional branch to the stub associated with that function: <kernel_clone>: addis r2,r12,467 addi r2,r2,-16028 b ftrace_ool_stub_text_end+0x11b28 mfocrf r11,8 ... The associated stub: <ftrace_ool_stub_text_end+0x11b28>: mflr r0 bl ftrace_caller mtlr r0 b kernel_clone+0xc ... This change showed an improvement of ~10% in null_syscall benchmark on a Power 10 system with ftrace enabled. Signed-off-by: Naveen N Rao <naveen@kernel.org> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://patch.msgid.link/20241030070850.1361304-13-hbathini@linux.ibm.com
388 lines
8.7 KiB
ArmAsm
388 lines
8.7 KiB
ArmAsm
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/*
|
|
* Split from ftrace_64.S
|
|
*/
|
|
|
|
#include <linux/export.h>
|
|
#include <linux/magic.h>
|
|
#include <asm/ppc_asm.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/ftrace.h>
|
|
#include <asm/ppc-opcode.h>
|
|
#include <asm/thread_info.h>
|
|
#include <asm/bug.h>
|
|
#include <asm/ptrace.h>
|
|
|
|
/*
|
|
*
|
|
* ftrace_caller()/ftrace_regs_caller() is the function that replaces _mcount()
|
|
* when ftrace is active.
|
|
*
|
|
* We arrive here after a function A calls function B, and we are the trace
|
|
* function for B. When we enter r1 points to A's stack frame, B has not yet
|
|
* had a chance to allocate one yet.
|
|
*
|
|
* Additionally r2 may point either to the TOC for A, or B, depending on
|
|
* whether B did a TOC setup sequence before calling us.
|
|
*
|
|
* On entry the LR points back to the _mcount() call site, and r0 holds the
|
|
* saved LR as it was on entry to B, ie. the original return address at the
|
|
* call site in A.
|
|
*
|
|
* Our job is to save the register state into a struct pt_regs (on the stack)
|
|
* and then arrange for the ftrace function to be called.
|
|
*/
|
|
.macro ftrace_regs_entry allregs
|
|
/* Save the original return address in A's stack frame */
|
|
PPC_STL r0, LRSAVE(r1)
|
|
/* Create a minimal stack frame for representing B */
|
|
PPC_STLU r1, -STACK_FRAME_MIN_SIZE(r1)
|
|
|
|
/* Create our stack frame + pt_regs */
|
|
PPC_STLU r1,-SWITCH_FRAME_SIZE(r1)
|
|
|
|
/* Save all gprs to pt_regs */
|
|
SAVE_GPR(0, r1)
|
|
SAVE_GPRS(3, 10, r1)
|
|
|
|
#ifdef CONFIG_PPC64
|
|
/* Ok to continue? */
|
|
lbz r3, PACA_FTRACE_ENABLED(r13)
|
|
cmpdi r3, 0
|
|
beq ftrace_no_trace
|
|
#endif
|
|
|
|
.if \allregs == 1
|
|
SAVE_GPR(2, r1)
|
|
SAVE_GPRS(11, 31, r1)
|
|
.else
|
|
#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
|
|
SAVE_GPR(14, r1)
|
|
#endif
|
|
.endif
|
|
|
|
/* Save previous stack pointer (r1) */
|
|
addi r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
|
|
PPC_STL r8, GPR1(r1)
|
|
|
|
.if \allregs == 1
|
|
/* Load special regs for save below */
|
|
mfmsr r8
|
|
mfctr r9
|
|
mfxer r10
|
|
mfcr r11
|
|
.else
|
|
/* Clear MSR to flag as ftrace_caller versus frace_regs_caller */
|
|
li r8, 0
|
|
.endif
|
|
|
|
/* Get the _mcount() call site out of LR */
|
|
mflr r7
|
|
/* Save the read LR in pt_regs->link */
|
|
PPC_STL r0, _LINK(r1)
|
|
|
|
#ifdef CONFIG_PPC64
|
|
/* Save callee's TOC in the ABI compliant location */
|
|
std r2, STK_GOT(r1)
|
|
LOAD_PACA_TOC() /* get kernel TOC in r2 */
|
|
LOAD_REG_ADDR(r3, function_trace_op)
|
|
ld r5,0(r3)
|
|
#else
|
|
lis r3,function_trace_op@ha
|
|
lwz r5,function_trace_op@l(r3)
|
|
#endif
|
|
|
|
/* Save special regs */
|
|
PPC_STL r8, _MSR(r1)
|
|
.if \allregs == 1
|
|
PPC_STL r9, _CTR(r1)
|
|
PPC_STL r10, _XER(r1)
|
|
PPC_STL r11, _CCR(r1)
|
|
.endif
|
|
|
|
#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
|
|
/* Save our real return address in nvr for return */
|
|
.if \allregs == 0
|
|
SAVE_GPR(15, r1)
|
|
.endif
|
|
mr r15, r7
|
|
/*
|
|
* We want the ftrace location in the function, but our lr (in r7)
|
|
* points at the 'mtlr r0' instruction in the out of line stub. To
|
|
* recover the ftrace location, we read the branch instruction in the
|
|
* stub, and adjust our lr by the branch offset.
|
|
*
|
|
* See ftrace_init_ool_stub() for the profile sequence.
|
|
*/
|
|
lwz r8, MCOUNT_INSN_SIZE(r7)
|
|
slwi r8, r8, 6
|
|
srawi r8, r8, 6
|
|
add r3, r7, r8
|
|
/*
|
|
* Override our nip to point past the branch in the original function.
|
|
* This allows reliable stack trace and the ftrace stack tracer to work as-is.
|
|
*/
|
|
addi r7, r3, MCOUNT_INSN_SIZE
|
|
#else
|
|
/* Calculate ip from nip-4 into r3 for call below */
|
|
subi r3, r7, MCOUNT_INSN_SIZE
|
|
#endif
|
|
|
|
/* Save NIP as pt_regs->nip */
|
|
PPC_STL r7, _NIP(r1)
|
|
/* Also save it in B's stackframe header for proper unwind */
|
|
PPC_STL r7, LRSAVE+SWITCH_FRAME_SIZE(r1)
|
|
#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
|
|
mr r14, r7 /* remember old NIP */
|
|
#endif
|
|
|
|
/* Put the original return address in r4 as parent_ip */
|
|
mr r4, r0
|
|
|
|
/* Load &pt_regs in r6 for call below */
|
|
addi r6, r1, STACK_INT_FRAME_REGS
|
|
.endm
|
|
|
|
.macro ftrace_regs_exit allregs
|
|
#ifndef CONFIG_PPC_FTRACE_OUT_OF_LINE
|
|
/* Load ctr with the possibly modified NIP */
|
|
PPC_LL r3, _NIP(r1)
|
|
mtctr r3
|
|
|
|
#ifdef CONFIG_LIVEPATCH_64
|
|
cmpd r14, r3 /* has NIP been altered? */
|
|
#endif
|
|
#else /* !CONFIG_PPC_FTRACE_OUT_OF_LINE */
|
|
/* Load LR with the possibly modified NIP */
|
|
PPC_LL r3, _NIP(r1)
|
|
cmpd r14, r3 /* has NIP been altered? */
|
|
bne- 1f
|
|
|
|
mr r3, r15
|
|
.if \allregs == 0
|
|
REST_GPR(15, r1)
|
|
.endif
|
|
1: mtlr r3
|
|
#endif
|
|
|
|
/* Restore gprs */
|
|
.if \allregs == 1
|
|
REST_GPRS(2, 31, r1)
|
|
.else
|
|
REST_GPRS(3, 10, r1)
|
|
#if defined(CONFIG_LIVEPATCH_64) || defined(CONFIG_PPC_FTRACE_OUT_OF_LINE)
|
|
REST_GPR(14, r1)
|
|
#endif
|
|
.endif
|
|
|
|
/* Restore possibly modified LR */
|
|
PPC_LL r0, _LINK(r1)
|
|
#ifndef CONFIG_PPC_FTRACE_OUT_OF_LINE
|
|
mtlr r0
|
|
#endif
|
|
|
|
#ifdef CONFIG_PPC64
|
|
/* Restore callee's TOC */
|
|
ld r2, STK_GOT(r1)
|
|
#endif
|
|
|
|
/* Pop our stack frame */
|
|
addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
|
|
|
|
#ifdef CONFIG_LIVEPATCH_64
|
|
/* Based on the cmpd above, if the NIP was altered handle livepatch */
|
|
bne- livepatch_handler
|
|
#endif
|
|
/* jump after _mcount site */
|
|
#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
|
|
/*
|
|
* Return with blr to keep the link stack balanced. The function profiling sequence
|
|
* uses 'mtlr r0' to restore LR.
|
|
*/
|
|
blr
|
|
#else
|
|
bctr
|
|
#endif
|
|
.endm
|
|
|
|
_GLOBAL(ftrace_regs_caller)
|
|
ftrace_regs_entry 1
|
|
/* ftrace_call(r3, r4, r5, r6) */
|
|
.globl ftrace_regs_call
|
|
ftrace_regs_call:
|
|
bl ftrace_stub
|
|
ftrace_regs_exit 1
|
|
|
|
_GLOBAL(ftrace_caller)
|
|
ftrace_regs_entry 0
|
|
/* ftrace_call(r3, r4, r5, r6) */
|
|
.globl ftrace_call
|
|
ftrace_call:
|
|
bl ftrace_stub
|
|
ftrace_regs_exit 0
|
|
|
|
_GLOBAL(ftrace_stub)
|
|
blr
|
|
|
|
#ifdef CONFIG_PPC64
|
|
ftrace_no_trace:
|
|
#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
|
|
REST_GPR(3, r1)
|
|
addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
|
|
blr
|
|
#else
|
|
mflr r3
|
|
mtctr r3
|
|
REST_GPR(3, r1)
|
|
addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE
|
|
mtlr r0
|
|
bctr
|
|
#endif
|
|
#endif
|
|
|
|
#ifdef CONFIG_LIVEPATCH_64
|
|
/*
|
|
* This function runs in the mcount context, between two functions. As
|
|
* such it can only clobber registers which are volatile and used in
|
|
* function linkage.
|
|
*
|
|
* We get here when a function A, calls another function B, but B has
|
|
* been live patched with a new function C.
|
|
*
|
|
* On entry, we have no stack frame and can not allocate one.
|
|
*
|
|
* With PPC_FTRACE_OUT_OF_LINE=n, on entry:
|
|
* - LR points back to the original caller (in A)
|
|
* - CTR holds the new NIP in C
|
|
* - r0, r11 & r12 are free
|
|
*
|
|
* With PPC_FTRACE_OUT_OF_LINE=y, on entry:
|
|
* - r0 points back to the original caller (in A)
|
|
* - LR holds the new NIP in C
|
|
* - r11 & r12 are free
|
|
*/
|
|
livepatch_handler:
|
|
ld r12, PACA_THREAD_INFO(r13)
|
|
|
|
/* Allocate 3 x 8 bytes */
|
|
ld r11, TI_livepatch_sp(r12)
|
|
addi r11, r11, 24
|
|
std r11, TI_livepatch_sp(r12)
|
|
|
|
/* Store stack end marker */
|
|
lis r12, STACK_END_MAGIC@h
|
|
ori r12, r12, STACK_END_MAGIC@l
|
|
std r12, -8(r11)
|
|
|
|
/* Save toc & real LR on livepatch stack */
|
|
std r2, -24(r11)
|
|
#ifndef CONFIG_PPC_FTRACE_OUT_OF_LINE
|
|
mflr r12
|
|
std r12, -16(r11)
|
|
mfctr r12
|
|
#else
|
|
std r0, -16(r11)
|
|
mflr r12
|
|
/* Put ctr in r12 for global entry and branch there */
|
|
mtctr r12
|
|
#endif
|
|
bctrl
|
|
|
|
/*
|
|
* Now we are returning from the patched function to the original
|
|
* caller A. We are free to use r11, r12 and we can use r2 until we
|
|
* restore it.
|
|
*/
|
|
|
|
ld r12, PACA_THREAD_INFO(r13)
|
|
|
|
ld r11, TI_livepatch_sp(r12)
|
|
|
|
/* Check stack marker hasn't been trashed */
|
|
lis r2, STACK_END_MAGIC@h
|
|
ori r2, r2, STACK_END_MAGIC@l
|
|
ld r12, -8(r11)
|
|
1: tdne r12, r2
|
|
EMIT_BUG_ENTRY 1b, __FILE__, __LINE__ - 1, 0
|
|
|
|
/* Restore LR & toc from livepatch stack */
|
|
ld r12, -16(r11)
|
|
mtlr r12
|
|
ld r2, -24(r11)
|
|
|
|
/* Pop livepatch stack frame */
|
|
ld r12, PACA_THREAD_INFO(r13)
|
|
subi r11, r11, 24
|
|
std r11, TI_livepatch_sp(r12)
|
|
|
|
/* Return to original caller of live patched function */
|
|
blr
|
|
#endif /* CONFIG_LIVEPATCH */
|
|
|
|
#ifndef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
|
|
_GLOBAL(mcount)
|
|
_GLOBAL(_mcount)
|
|
EXPORT_SYMBOL(_mcount)
|
|
mflr r12
|
|
mtctr r12
|
|
mtlr r0
|
|
bctr
|
|
#endif
|
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
_GLOBAL(return_to_handler)
|
|
/* need to save return values */
|
|
#ifdef CONFIG_PPC64
|
|
std r4, -32(r1)
|
|
std r3, -24(r1)
|
|
/* save TOC */
|
|
std r2, -16(r1)
|
|
std r31, -8(r1)
|
|
mr r31, r1
|
|
stdu r1, -112(r1)
|
|
|
|
/*
|
|
* We might be called from a module.
|
|
* Switch to our TOC to run inside the core kernel.
|
|
*/
|
|
LOAD_PACA_TOC()
|
|
#else
|
|
stwu r1, -16(r1)
|
|
stw r3, 8(r1)
|
|
stw r4, 12(r1)
|
|
#endif
|
|
|
|
bl ftrace_return_to_handler
|
|
nop
|
|
|
|
/* return value has real return address */
|
|
mtlr r3
|
|
|
|
#ifdef CONFIG_PPC64
|
|
ld r1, 0(r1)
|
|
ld r4, -32(r1)
|
|
ld r3, -24(r1)
|
|
ld r2, -16(r1)
|
|
ld r31, -8(r1)
|
|
#else
|
|
lwz r3, 8(r1)
|
|
lwz r4, 12(r1)
|
|
addi r1, r1, 16
|
|
#endif
|
|
|
|
/* Jump back to real return address */
|
|
blr
|
|
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
|
|
|
|
.pushsection ".tramp.ftrace.text","aw",@progbits;
|
|
.globl ftrace_tramp_text
|
|
ftrace_tramp_text:
|
|
.space 32
|
|
.popsection
|
|
|
|
.pushsection ".tramp.ftrace.init","aw",@progbits;
|
|
.globl ftrace_tramp_init
|
|
ftrace_tramp_init:
|
|
.space 32
|
|
.popsection
|