linux-stable/arch/powerpc/kernel/entry_64.S
Christophe Leroy 1e688dd2a3 powerpc/bug: Provide better flexibility to WARN_ON/__WARN_FLAGS() with asm goto
Using asm goto in __WARN_FLAGS() and WARN_ON() allows more
flexibility to GCC.

For that add an entry to the exception table so that
program_check_exception() knowns where to resume execution
after a WARNING.

Here are two exemples. The first one is done on PPC32 (which
benefits from the previous patch), the second is on PPC64.

	unsigned long test(struct pt_regs *regs)
	{
		int ret;

		WARN_ON(regs->msr & MSR_PR);

		return regs->gpr[3];
	}

	unsigned long test9w(unsigned long a, unsigned long b)
	{
		if (WARN_ON(!b))
			return 0;
		return a / b;
	}

Before the patch:

	000003a8 <test>:
	 3a8:	81 23 00 84 	lwz     r9,132(r3)
	 3ac:	71 29 40 00 	andi.   r9,r9,16384
	 3b0:	40 82 00 0c 	bne     3bc <test+0x14>
	 3b4:	80 63 00 0c 	lwz     r3,12(r3)
	 3b8:	4e 80 00 20 	blr

	 3bc:	0f e0 00 00 	twui    r0,0
	 3c0:	80 63 00 0c 	lwz     r3,12(r3)
	 3c4:	4e 80 00 20 	blr

	0000000000000bf0 <.test9w>:
	 bf0:	7c 89 00 74 	cntlzd  r9,r4
	 bf4:	79 29 d1 82 	rldicl  r9,r9,58,6
	 bf8:	0b 09 00 00 	tdnei   r9,0
	 bfc:	2c 24 00 00 	cmpdi   r4,0
	 c00:	41 82 00 0c 	beq     c0c <.test9w+0x1c>
	 c04:	7c 63 23 92 	divdu   r3,r3,r4
	 c08:	4e 80 00 20 	blr

	 c0c:	38 60 00 00 	li      r3,0
	 c10:	4e 80 00 20 	blr

After the patch:

	000003a8 <test>:
	 3a8:	81 23 00 84 	lwz     r9,132(r3)
	 3ac:	71 29 40 00 	andi.   r9,r9,16384
	 3b0:	40 82 00 0c 	bne     3bc <test+0x14>
	 3b4:	80 63 00 0c 	lwz     r3,12(r3)
	 3b8:	4e 80 00 20 	blr

	 3bc:	0f e0 00 00 	twui    r0,0

	0000000000000c50 <.test9w>:
	 c50:	7c 89 00 74 	cntlzd  r9,r4
	 c54:	79 29 d1 82 	rldicl  r9,r9,58,6
	 c58:	0b 09 00 00 	tdnei   r9,0
	 c5c:	7c 63 23 92 	divdu   r3,r3,r4
	 c60:	4e 80 00 20 	blr

	 c70:	38 60 00 00 	li      r3,0
	 c74:	4e 80 00 20 	blr

In the first exemple, we see GCC doesn't need to duplicate what
happens after the trap.

In the second exemple, we see that GCC doesn't need to emit a test
and a branch in the likely path in addition to the trap.

We've got some WARN_ON() in .softirqentry.text section so it needs
to be added in the OTHER_TEXT_SECTIONS in modpost.c

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/389962b1b702e3c78d169e59bcfac56282889173.1618331882.git.christophe.leroy@csgroup.eu
2021-08-15 13:49:24 +10:00

479 lines
12 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
* Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
* Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
* Adapted for Power Macintosh by Paul Mackerras.
* Low-level exception handlers and MMU support
* rewritten by Paul Mackerras.
* Copyright (C) 1996 Paul Mackerras.
* MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
*
* This file contains the system call entry code, context switch
* code, and exception/interrupt return code for PowerPC.
*/
#include <linux/errno.h>
#include <linux/err.h>
#include <asm/cache.h>
#include <asm/unistd.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/thread_info.h>
#include <asm/code-patching-asm.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/cputable.h>
#include <asm/firmware.h>
#include <asm/bug.h>
#include <asm/ptrace.h>
#include <asm/irqflags.h>
#include <asm/hw_irq.h>
#include <asm/context_tracking.h>
#include <asm/ppc-opcode.h>
#include <asm/barrier.h>
#include <asm/export.h>
#include <asm/asm-compat.h>
#ifdef CONFIG_PPC_BOOK3S
#include <asm/exception-64s.h>
#else
#include <asm/exception-64e.h>
#endif
#include <asm/feature-fixups.h>
#include <asm/kup.h>
/*
* System calls.
*/
.section ".text"
#ifdef CONFIG_PPC_BOOK3S_64
#define FLUSH_COUNT_CACHE \
1: nop; \
patch_site 1b, patch__call_flush_branch_caches1; \
1: nop; \
patch_site 1b, patch__call_flush_branch_caches2; \
1: nop; \
patch_site 1b, patch__call_flush_branch_caches3
.macro nops number
.rept \number
nop
.endr
.endm
.balign 32
.global flush_branch_caches
flush_branch_caches:
/* Save LR into r9 */
mflr r9
// Flush the link stack
.rept 64
bl .+4
.endr
b 1f
nops 6
.balign 32
/* Restore LR */
1: mtlr r9
// If we're just flushing the link stack, return here
3: nop
patch_site 3b patch__flush_link_stack_return
li r9,0x7fff
mtctr r9
PPC_BCCTR_FLUSH
2: nop
patch_site 2b patch__flush_count_cache_return
nops 3
.rept 278
.balign 32
PPC_BCCTR_FLUSH
nops 7
.endr
blr
#else
#define FLUSH_COUNT_CACHE
#endif /* CONFIG_PPC_BOOK3S_64 */
/*
* This routine switches between two different tasks. The process
* state of one is saved on its kernel stack. Then the state
* of the other is restored from its kernel stack. The memory
* management hardware is updated to the second process's state.
* Finally, we can return to the second process, via interrupt_return.
* On entry, r3 points to the THREAD for the current task, r4
* points to the THREAD for the new task.
*
* Note: there are two ways to get to the "going out" portion
* of this code; either by coming in via the entry (_switch)
* or via "fork" which must set up an environment equivalent
* to the "_switch" path. If you change this you'll have to change
* the fork code also.
*
* The code which creates the new task context is in 'copy_thread'
* in arch/powerpc/kernel/process.c
*/
.align 7
_GLOBAL(_switch)
mflr r0
std r0,16(r1)
stdu r1,-SWITCH_FRAME_SIZE(r1)
/* r3-r13 are caller saved -- Cort */
SAVE_NVGPRS(r1)
std r0,_NIP(r1) /* Return to switch caller */
mfcr r23
std r23,_CCR(r1)
std r1,KSP(r3) /* Set old stack pointer */
kuap_check_amr r9, r10
FLUSH_COUNT_CACHE /* Clobbers r9, ctr */
/*
* On SMP kernels, care must be taken because a task may be
* scheduled off CPUx and on to CPUy. Memory ordering must be
* considered.
*
* Cacheable stores on CPUx will be visible when the task is
* scheduled on CPUy by virtue of the core scheduler barriers
* (see "Notes on Program-Order guarantees on SMP systems." in
* kernel/sched/core.c).
*
* Uncacheable stores in the case of involuntary preemption must
* be taken care of. The smp_mb__after_spinlock() in __schedule()
* is implemented as hwsync on powerpc, which orders MMIO too. So
* long as there is an hwsync in the context switch path, it will
* be executed on the source CPU after the task has performed
* all MMIO ops on that CPU, and on the destination CPU before the
* task performs any MMIO ops there.
*/
/*
* The kernel context switch path must contain a spin_lock,
* which contains larx/stcx, which will clear any reservation
* of the task being switched.
*/
#ifdef CONFIG_PPC_BOOK3S
/* Cancel all explict user streams as they will have no use after context
* switch and will stop the HW from creating streams itself
*/
DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r6)
#endif
addi r6,r4,-THREAD /* Convert THREAD to 'current' */
std r6,PACACURRENT(r13) /* Set new 'current' */
#if defined(CONFIG_STACKPROTECTOR)
ld r6, TASK_CANARY(r6)
std r6, PACA_CANARY(r13)
#endif
ld r8,KSP(r4) /* new stack pointer */
#ifdef CONFIG_PPC_BOOK3S_64
BEGIN_MMU_FTR_SECTION
b 2f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
BEGIN_FTR_SECTION
clrrdi r6,r8,28 /* get its ESID */
clrrdi r9,r1,28 /* get current sp ESID */
FTR_SECTION_ELSE
clrrdi r6,r8,40 /* get its 1T ESID */
clrrdi r9,r1,40 /* get current sp 1T ESID */
ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_1T_SEGMENT)
clrldi. r0,r6,2 /* is new ESID c00000000? */
cmpd cr1,r6,r9 /* or is new ESID the same as current ESID? */
cror eq,4*cr1+eq,eq
beq 2f /* if yes, don't slbie it */
/* Bolt in the new stack SLB entry */
ld r7,KSP_VSID(r4) /* Get new stack's VSID */
oris r0,r6,(SLB_ESID_V)@h
ori r0,r0,(SLB_NUM_BOLTED-1)@l
BEGIN_FTR_SECTION
li r9,MMU_SEGSIZE_1T /* insert B field */
oris r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h
rldimi r7,r9,SLB_VSID_SSIZE_SHIFT,0
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
/* Update the last bolted SLB. No write barriers are needed
* here, provided we only update the current CPU's SLB shadow
* buffer.
*/
ld r9,PACA_SLBSHADOWPTR(r13)
li r12,0
std r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */
li r12,SLBSHADOW_STACKVSID
STDX_BE r7,r12,r9 /* Save VSID */
li r12,SLBSHADOW_STACKESID
STDX_BE r0,r12,r9 /* Save ESID */
/* No need to check for MMU_FTR_NO_SLBIE_B here, since when
* we have 1TB segments, the only CPUs known to have the errata
* only support less than 1TB of system memory and we'll never
* actually hit this code path.
*/
isync
slbie r6
BEGIN_FTR_SECTION
slbie r6 /* Workaround POWER5 < DD2.1 issue */
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
slbmte r7,r0
isync
2:
#endif /* CONFIG_PPC_BOOK3S_64 */
clrrdi r7, r8, THREAD_SHIFT /* base of new stack */
/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
because we don't need to leave the 288-byte ABI gap at the
top of the kernel stack. */
addi r7,r7,THREAD_SIZE-SWITCH_FRAME_SIZE
/*
* PMU interrupts in radix may come in here. They will use r1, not
* PACAKSAVE, so this stack switch will not cause a problem. They
* will store to the process stack, which may then be migrated to
* another CPU. However the rq lock release on this CPU paired with
* the rq lock acquire on the new CPU before the stack becomes
* active on the new CPU, will order those stores.
*/
mr r1,r8 /* start using new stack pointer */
std r7,PACAKSAVE(r13)
ld r6,_CCR(r1)
mtcrf 0xFF,r6
/* r3-r13 are destroyed -- Cort */
REST_NVGPRS(r1)
/* convert old thread to its task_struct for return value */
addi r3,r3,-THREAD
ld r7,_NIP(r1) /* Return to _switch caller in new task */
mtlr r7
addi r1,r1,SWITCH_FRAME_SIZE
blr
#ifdef CONFIG_PPC_RTAS
/*
* On CHRP, the Run-Time Abstraction Services (RTAS) have to be
* called with the MMU off.
*
* In addition, we need to be in 32b mode, at least for now.
*
* Note: r3 is an input parameter to rtas, so don't trash it...
*/
_GLOBAL(enter_rtas)
mflr r0
std r0,16(r1)
stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space. */
/* 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)
*/
SAVE_GPR(2, r1) /* Save the TOC */
SAVE_GPR(13, r1) /* Save paca */
SAVE_NVGPRS(r1) /* Save the non-volatiles */
mfcr r4
std r4,_CCR(r1)
mfctr r5
std r5,_CTR(r1)
mfspr r6,SPRN_XER
std r6,_XER(r1)
mfdar r7
std r7,_DAR(r1)
mfdsisr r8
std r8,_DSISR(r1)
/* Temporary workaround to clear CR until RTAS can be modified to
* ignore all bits.
*/
li r0,0
mtcr r0
#ifdef CONFIG_BUG
/* There is no way it is acceptable to get here with interrupts enabled,
* check it with the asm equivalent of WARN_ON
*/
lbz r0,PACAIRQSOFTMASK(r13)
1: tdeqi r0,IRQS_ENABLED
EMIT_WARN_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
#endif
/* Hard-disable interrupts */
mfmsr r6
rldicl r7,r6,48,1
rotldi r7,r7,16
mtmsrd r7,1
/* Unfortunately, the stack pointer and the MSR are also clobbered,
* so they are saved in the PACA which allows us to restore
* our original state after RTAS returns.
*/
std r1,PACAR1(r13)
std r6,PACASAVEDMSR(r13)
/* Setup our real return addr */
LOAD_REG_ADDR(r4,rtas_return_loc)
clrldi r4,r4,2 /* convert to realmode address */
mtlr r4
li r0,0
ori r0,r0,MSR_EE|MSR_SE|MSR_BE|MSR_RI
andc r0,r6,r0
li r9,1
rldicr r9,r9,MSR_SF_LG,(63-MSR_SF_LG)
ori r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI|MSR_LE
andc r6,r0,r9
__enter_rtas:
sync /* disable interrupts so SRR0/1 */
mtmsrd r0 /* don't get trashed */
LOAD_REG_ADDR(r4, rtas)
ld r5,RTASENTRY(r4) /* get the rtas->entry value */
ld r4,RTASBASE(r4) /* get the rtas->base value */
mtspr SPRN_SRR0,r5
mtspr SPRN_SRR1,r6
RFI_TO_KERNEL
b . /* prevent speculative execution */
rtas_return_loc:
FIXUP_ENDIAN
/*
* Clear RI and set SF before anything.
*/
mfmsr r6
li r0,MSR_RI
andc r6,r6,r0
sldi r0,r0,(MSR_SF_LG - MSR_RI_LG)
or r6,r6,r0
sync
mtmsrd r6
/* relocation is off at this point */
GET_PACA(r4)
clrldi r4,r4,2 /* convert to realmode address */
bcl 20,31,$+4
0: mflr r3
ld r3,(1f-0b)(r3) /* get &rtas_restore_regs */
ld r1,PACAR1(r4) /* Restore our SP */
ld r4,PACASAVEDMSR(r4) /* Restore our MSR */
mtspr SPRN_SRR0,r3
mtspr SPRN_SRR1,r4
RFI_TO_KERNEL
b . /* prevent speculative execution */
_ASM_NOKPROBE_SYMBOL(__enter_rtas)
_ASM_NOKPROBE_SYMBOL(rtas_return_loc)
.align 3
1: .8byte rtas_restore_regs
rtas_restore_regs:
/* relocation is on at this point */
REST_GPR(2, r1) /* Restore the TOC */
REST_GPR(13, r1) /* Restore paca */
REST_NVGPRS(r1) /* Restore the non-volatiles */
GET_PACA(r13)
ld r4,_CCR(r1)
mtcr r4
ld r5,_CTR(r1)
mtctr r5
ld r6,_XER(r1)
mtspr SPRN_XER,r6
ld r7,_DAR(r1)
mtdar r7
ld r8,_DSISR(r1)
mtdsisr r8
addi r1,r1,SWITCH_FRAME_SIZE /* Unstack our frame */
ld r0,16(r1) /* get return address */
mtlr r0
blr /* return to caller */
#endif /* CONFIG_PPC_RTAS */
_GLOBAL(enter_prom)
mflr r0
std r0,16(r1)
stdu r1,-SWITCH_FRAME_SIZE(r1) /* Save SP and create stack space */
/* Because PROM is running in 32b mode, it clobbers the high order half
* of all registers that it saves. We therefore save those registers
* PROM might touch to the stack. (r0, r3-r13 are caller saved)
*/
SAVE_GPR(2, r1)
SAVE_GPR(13, r1)
SAVE_NVGPRS(r1)
mfcr r10
mfmsr r11
std r10,_CCR(r1)
std r11,_MSR(r1)
/* Put PROM address in SRR0 */
mtsrr0 r4
/* Setup our trampoline return addr in LR */
bcl 20,31,$+4
0: mflr r4
addi r4,r4,(1f - 0b)
mtlr r4
/* Prepare a 32-bit mode big endian MSR
*/
#ifdef CONFIG_PPC_BOOK3E
rlwinm r11,r11,0,1,31
mtsrr1 r11
rfi
#else /* CONFIG_PPC_BOOK3E */
LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_LE)
andc r11,r11,r12
mtsrr1 r11
RFI_TO_KERNEL
#endif /* CONFIG_PPC_BOOK3E */
1: /* Return from OF */
FIXUP_ENDIAN
/* Just make sure that r1 top 32 bits didn't get
* corrupt by OF
*/
rldicl r1,r1,0,32
/* Restore the MSR (back to 64 bits) */
ld r0,_MSR(r1)
MTMSRD(r0)
isync
/* Restore other registers */
REST_GPR(2, r1)
REST_GPR(13, r1)
REST_NVGPRS(r1)
ld r4,_CCR(r1)
mtcr r4
addi r1,r1,SWITCH_FRAME_SIZE
ld r0,16(r1)
mtlr r0
blr