linux-stable/arch/powerpc/kernel/idle_book3s.S
Michael Ellerman 496c5fe25c powerpc/idle: Don't corrupt back chain when going idle
In isa206_idle_insn_mayloss() we store various registers into the stack
red zone, which is allowed.

However inside the IDLE_STATE_ENTER_SEQ_NORET macro we save r2 again,
to 0(r1), which corrupts the stack back chain.

We used to do the same in isa206_idle_insn_mayloss() itself, but we
fixed that in 73287caa92 ("powerpc64/idle: Fix SP offsets when saving
GPRs"), however we missed that the macro also corrupts the back chain.

Corrupting the back chain is bad for debuggability but doesn't
necessarily cause a bug.

However we recently changed the stack handling in some KVM code, and it
now relies on the stack back chain being valid when it returns. The
corruption causes that code to return with r1 pointing somewhere in
kernel data, at some point LR is restored from the stack and we branch
to NULL or somewhere else invalid.

Only affects Power8 hosts running KVM guests, with dynamic_mt_modes
enabled (which it is by default).

The fixes tag below points to the commit that changed the KVM stack
handling, exposing this bug. The actual corruption of the back chain has
always existed since 948cf67c47 ("powerpc: Add NAP mode support on
Power7 in HV mode").

Fixes: 9b4416c509 ("KVM: PPC: Book3S HV: Fix stack handling in idle_kvm_start_guest()")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211020094826.3222052-1-mpe@ellerman.id.au
2021-10-20 21:37:58 +11:00

218 lines
5.6 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Copyright 2018, IBM Corporation.
*
* This file contains general idle entry/exit functions to save
* and restore stack and NVGPRs which allows C code to call idle
* states that lose GPRs, and it will return transparently with
* SRR1 wakeup reason return value.
*
* The platform / CPU caller must ensure SPRs and any other non-GPR
* state is saved and restored correctly, handle KVM, interrupts, etc.
*/
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/ppc-opcode.h>
#include <asm/cpuidle.h>
#include <asm/thread_info.h> /* TLF_NAPPING */
#ifdef CONFIG_PPC_P7_NAP
/*
* Desired PSSCR in r3
*
* No state will be lost regardless of wakeup mechanism (interrupt or NIA).
*
* An EC=0 type wakeup will return with a value of 0. SRESET wakeup (which can
* happen with xscom SRESET and possibly MCE) may clobber volatiles except LR,
* and must blr, to return to caller with r3 set according to caller's expected
* return code (for Book3S/64 that is SRR1).
*/
_GLOBAL(isa300_idle_stop_noloss)
mtspr SPRN_PSSCR,r3
PPC_STOP
li r3,0
blr
/*
* Desired PSSCR in r3
*
* GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
* The SRESET wakeup returns to this function's caller by calling
* idle_return_gpr_loss with r3 set to desired return value.
*
* A wakeup without GPR loss may alteratively be handled as in
* isa300_idle_stop_noloss and blr directly, as an optimisation.
*
* The caller is responsible for saving/restoring SPRs, MSR, timebase,
* etc.
*/
_GLOBAL(isa300_idle_stop_mayloss)
mtspr SPRN_PSSCR,r3
std r1,PACAR1(r13)
mflr r4
mfcr r5
/*
* Use the stack red zone rather than a new frame for saving regs since
* in the case of no GPR loss the wakeup code branches directly back to
* the caller without deallocating the stack frame first.
*/
std r2,-8*1(r1)
std r14,-8*2(r1)
std r15,-8*3(r1)
std r16,-8*4(r1)
std r17,-8*5(r1)
std r18,-8*6(r1)
std r19,-8*7(r1)
std r20,-8*8(r1)
std r21,-8*9(r1)
std r22,-8*10(r1)
std r23,-8*11(r1)
std r24,-8*12(r1)
std r25,-8*13(r1)
std r26,-8*14(r1)
std r27,-8*15(r1)
std r28,-8*16(r1)
std r29,-8*17(r1)
std r30,-8*18(r1)
std r31,-8*19(r1)
std r4,-8*20(r1)
std r5,-8*21(r1)
/* 168 bytes */
PPC_STOP
b . /* catch bugs */
/*
* Desired return value in r3
*
* The idle wakeup SRESET interrupt can call this after calling
* to return to the idle sleep function caller with r3 as the return code.
*
* This must not be used if idle was entered via a _noloss function (use
* a simple blr instead).
*/
_GLOBAL(idle_return_gpr_loss)
ld r1,PACAR1(r13)
ld r4,-8*20(r1)
ld r5,-8*21(r1)
mtlr r4
mtcr r5
/*
* KVM nap requires r2 to be saved, rather than just restoring it
* from PACATOC. This could be avoided for that less common case
* if KVM saved its r2.
*/
ld r2,-8*1(r1)
ld r14,-8*2(r1)
ld r15,-8*3(r1)
ld r16,-8*4(r1)
ld r17,-8*5(r1)
ld r18,-8*6(r1)
ld r19,-8*7(r1)
ld r20,-8*8(r1)
ld r21,-8*9(r1)
ld r22,-8*10(r1)
ld r23,-8*11(r1)
ld r24,-8*12(r1)
ld r25,-8*13(r1)
ld r26,-8*14(r1)
ld r27,-8*15(r1)
ld r28,-8*16(r1)
ld r29,-8*17(r1)
ld r30,-8*18(r1)
ld r31,-8*19(r1)
blr
/*
* This is the sequence required to execute idle instructions, as
* specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
* We have to store a GPR somewhere, ptesync, then reload it, and create
* a false dependency on the result of the load. It doesn't matter which
* GPR we store, or where we store it. We have already stored r2 to the
* stack at -8(r1) in isa206_idle_insn_mayloss, so use that.
*/
#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \
/* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
std r2,-8(r1); \
ptesync; \
ld r2,-8(r1); \
236: cmpd cr0,r2,r2; \
bne 236b; \
IDLE_INST; \
b . /* catch bugs */
/*
* Desired instruction type in r3
*
* GPRs may be lost, so they are saved here. Wakeup is by interrupt only.
* The SRESET wakeup returns to this function's caller by calling
* idle_return_gpr_loss with r3 set to desired return value.
*
* A wakeup without GPR loss may alteratively be handled as in
* isa300_idle_stop_noloss and blr directly, as an optimisation.
*
* The caller is responsible for saving/restoring SPRs, MSR, timebase,
* etc.
*
* This must be called in real-mode (MSR_IDLE).
*/
_GLOBAL(isa206_idle_insn_mayloss)
std r1,PACAR1(r13)
mflr r4
mfcr r5
/*
* Use the stack red zone rather than a new frame for saving regs since
* in the case of no GPR loss the wakeup code branches directly back to
* the caller without deallocating the stack frame first.
*/
std r2,-8*1(r1)
std r14,-8*2(r1)
std r15,-8*3(r1)
std r16,-8*4(r1)
std r17,-8*5(r1)
std r18,-8*6(r1)
std r19,-8*7(r1)
std r20,-8*8(r1)
std r21,-8*9(r1)
std r22,-8*10(r1)
std r23,-8*11(r1)
std r24,-8*12(r1)
std r25,-8*13(r1)
std r26,-8*14(r1)
std r27,-8*15(r1)
std r28,-8*16(r1)
std r29,-8*17(r1)
std r30,-8*18(r1)
std r31,-8*19(r1)
std r4,-8*20(r1)
std r5,-8*21(r1)
cmpwi r3,PNV_THREAD_NAP
bne 1f
IDLE_STATE_ENTER_SEQ_NORET(PPC_NAP)
1: cmpwi r3,PNV_THREAD_SLEEP
bne 2f
IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
2: IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
#endif
#ifdef CONFIG_PPC_970_NAP
_GLOBAL(power4_idle_nap)
LOAD_REG_IMMEDIATE(r7, MSR_KERNEL|MSR_EE|MSR_POW)
ld r9,PACA_THREAD_INFO(r13)
ld r8,TI_LOCAL_FLAGS(r9)
ori r8,r8,_TLF_NAPPING
std r8,TI_LOCAL_FLAGS(r9)
/*
* NAPPING bit is set, from this point onward power4_fixup_nap
* will cause exceptions to return to power4_idle_nap_return.
*/
1: sync
isync
mtmsrd r7
isync
b 1b
.globl power4_idle_nap_return
power4_idle_nap_return:
blr
#endif