leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
master
linux/arch/powerpc/kernel/tm.S
Nicholas Piggin 9d71165d39 powerpc/tm: Fix more userspace r13 corruption 
Commit cf13435b73 ("powerpc/tm: Fix userspace r13 corruption") fixes a
problem in treclaim where a SLB miss can occur on the
thread_struct->ckpt_regs while SCRATCH0 is live with the saved user r13
value, clobbering it with the kernel r13 and ultimately resulting in
kernel r13 being stored in ckpt_regs.

There is an equivalent problem in trechkpt where the user r13 value is
loaded into r13 from chkpt_regs to be recheckpointed, but a SLB miss
could occur on ckpt_regs accesses after that, which will result in r13
being clobbered with a kernel value and that will get recheckpointed and
then restored to user registers.

The same memory page is accessed right before this critical window where
a SLB miss could cause corruption, so hitting the bug requires the SLB
entry be removed within a small window of instructions, which is
possible if a SLB related MCE hits there. PAPR also permits the
hypervisor to discard this SLB entry (because slb_shadow->persistent is
only set to SLB_NUM_BOLTED) although it's not known whether any
implementations would do this (KVM does not). So this is an extremely
unlikely bug, only found by inspection.

Fix this by also storing user r13 in a temporary location on the kernel
stack and don't change the r13 register from kernel r13 until the RI=0
critical section that does not fault.

The SCRATCH0 change is not strictly part of the fix, it's only used in
the RI=0 section so it does not have the same problem as the previous
SCRATCH0 bug.

Fixes: 98ae22e15b ("powerpc: Add helper functions for transactional memory context switching")
Cc: stable@vger.kernel.org # v3.9+
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220311024733.48926-1-npiggin@gmail.com
2022-03-16 11:59:24 +11:00

555 lines
13 KiB
ArmAsm
Raw Permalink Blame History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Transactional memory support routines to reclaim and recheckpoint
* transactional process state.
*
* Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation.
*/
#include <asm/asm-offsets.h>
#include <asm/ppc_asm.h>
#include <asm/ppc-opcode.h>
#include <asm/ptrace.h>
#include <asm/reg.h>
#include <asm/bug.h>
#include <asm/export.h>
#include <asm/feature-fixups.h>
#ifdef CONFIG_VSX
/* See fpu.S, this is borrowed from there */
#define __SAVE_32FPRS_VSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
SAVE_32FPRS(n,base); \
b 3f; \
2: SAVE_32VSRS(n,c,base); \
3:
#define __REST_32FPRS_VSRS(n,c,base) \
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
REST_32FPRS(n,base); \
b 3f; \
2: REST_32VSRS(n,c,base); \
3:
#else
#define __SAVE_32FPRS_VSRS(n,c,base) SAVE_32FPRS(n, base)
#define __REST_32FPRS_VSRS(n,c,base) REST_32FPRS(n, base)
#endif
#define SAVE_32FPRS_VSRS(n,c,base) \
__SAVE_32FPRS_VSRS(n,__REG_##c,__REG_##base)
#define REST_32FPRS_VSRS(n,c,base) \
__REST_32FPRS_VSRS(n,__REG_##c,__REG_##base)
/* Stack frame offsets for local variables. */
#define TM_FRAME_L0 TM_FRAME_SIZE-16
#define TM_FRAME_L1 TM_FRAME_SIZE-8
/* In order to access the TM SPRs, TM must be enabled. So, do so: */
_GLOBAL(tm_enable)
mfmsr r4
li r3, MSR_TM >> 32
sldi r3, r3, 32
and. r0, r4, r3
bne 1f
or r4, r4, r3
mtmsrd r4
1: blr
EXPORT_SYMBOL_GPL(tm_enable);
_GLOBAL(tm_disable)
mfmsr r4
li r3, MSR_TM >> 32
sldi r3, r3, 32
andc r4, r4, r3
mtmsrd r4
blr
EXPORT_SYMBOL_GPL(tm_disable);
_GLOBAL(tm_save_sprs)
mfspr r0, SPRN_TFHAR
std r0, THREAD_TM_TFHAR(r3)
mfspr r0, SPRN_TEXASR
std r0, THREAD_TM_TEXASR(r3)
mfspr r0, SPRN_TFIAR
std r0, THREAD_TM_TFIAR(r3)
blr
_GLOBAL(tm_restore_sprs)
ld r0, THREAD_TM_TFHAR(r3)
mtspr SPRN_TFHAR, r0
ld r0, THREAD_TM_TEXASR(r3)
mtspr SPRN_TEXASR, r0
ld r0, THREAD_TM_TFIAR(r3)
mtspr SPRN_TFIAR, r0
blr
/* Passed an 8-bit failure cause as first argument. */
_GLOBAL(tm_abort)
TABORT(R3)
blr
EXPORT_SYMBOL_GPL(tm_abort);
/*
* void tm_reclaim(struct thread_struct *thread,
* uint8_t cause)
*
* - Performs a full reclaim. This destroys outstanding
* transactions and updates thread.ckpt_regs, thread.ckfp_state and
* thread.ckvr_state with the original checkpointed state. Note that
* thread->regs is unchanged.
*
* Purpose is to both abort transactions of, and preserve the state of,
* a transactions at a context switch. We preserve/restore both sets of process
* state to restore them when the thread's scheduled again. We continue in
* userland as though nothing happened, but when the transaction is resumed
* they will abort back to the checkpointed state we save out here.
*
* Call with IRQs off, stacks get all out of sync for some periods in here!
*/
_GLOBAL(tm_reclaim)
mfcr r5
mflr r0
stw r5, 8(r1)
std r0, 16(r1)
std r2, STK_GOT(r1)
stdu r1, -TM_FRAME_SIZE(r1)
/* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */
std r3, STK_PARAM(R3)(r1)
SAVE_NVGPRS(r1)
/*
* Save kernel live AMR since it will be clobbered by treclaim
* but can be used elsewhere later in kernel space.
*/
mfspr r3, SPRN_AMR
std r3, TM_FRAME_L1(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
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
oris r15,r15, MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
mtmsrd r15
std r14, 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
and r6, r6, r7
1: tdeqi r6, 0
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
/* Stash the stack pointer away for use after reclaim */
std r1, PACAR1(r13)
/* Clear MSR RI since we are about to use SCRATCH0, EE is already off */
li r5, 0
mtmsrd r5, 1
/*
* BE CAREFUL HERE:
* At this point we can't take an SLB miss since we have MSR_RI
* off. Load only to/from the stack/paca which are in SLB bolted regions
* until we turn MSR RI back on.
*
* The moment we treclaim, ALL of our GPRs will switch
* to user register state. (FPRs, CCR etc. also!)
* Use an sprg and a tm_scratch in the PACA to shuffle.
*/
TRECLAIM(R4) /* Cause in r4 */
/*
* ******************** GPRs ********************
* Stash the checkpointed r13 in the scratch SPR and get the real paca.
*/
SET_SCRATCH0(r13)
GET_PACA(r13)
/*
* Stash the checkpointed r1 away in paca->tm_scratch and get the real
* stack pointer back into r1.
*/
std r1, PACATMSCRATCH(r13)
ld r1, PACAR1(r13)
std r11, GPR11(r1) /* Temporary stash */
/*
* Move the saved user r1 to the kernel stack in case PACATMSCRATCH is
* clobbered by an exception once we turn on MSR_RI below.
*/
ld r11, PACATMSCRATCH(r13)
std r11, GPR1(r1)
/*
* Store r13 away so we can free up the scratch SPR for the SLB fault
* handler (needed once we start accessing the thread_struct).
*/
GET_SCRATCH0(r11)
std r11, GPR13(r1)
/* Reset MSR RI so we can take SLB faults again */
li r11, MSR_RI
mtmsrd r11, 1
/* Store the PPR in r11 and reset to decent value */
mfspr r11, SPRN_PPR
HMT_MEDIUM
/* Now get some more GPRS free */
std r7, GPR7(r1) /* Temporary stash */
std r12, GPR12(r1) /* '' '' '' */
ld r12, STK_PARAM(R3)(r1) /* Param 0, thread_struct * */
std r11, THREAD_TM_PPR(r12) /* Store PPR and free r11 */
addi r7, r12, PT_CKPT_REGS /* Thread's ckpt_regs */
/*
* Make r7 look like an exception frame so that we can use the neat
* GPRx(n) macros. r7 is NOT a pt_regs ptr!
*/
subi r7, r7, STACK_FRAME_OVERHEAD
/* Sync the userland GPRs 2-12, 14-31 to thread->regs: */
SAVE_GPR(0, r7) /* user r0 */
SAVE_GPRS(2, 6, r7) /* user r2-r6 */
SAVE_GPRS(8, 10, r7) /* user r8-r10 */
ld r3, GPR1(r1) /* user r1 */
ld r4, GPR7(r1) /* user r7 */
ld r5, GPR11(r1) /* user r11 */
ld r6, GPR12(r1) /* user r12 */
ld r8, GPR13(r1) /* user r13 */
std r3, GPR1(r7)
std r4, GPR7(r7)
std r5, GPR11(r7)
std r6, GPR12(r7)
std r8, GPR13(r7)
SAVE_NVGPRS(r7) /* user r14-r31 */
/* ******************** NIP ******************** */
mfspr r3, SPRN_TFHAR
std r3, _NIP(r7) /* Returns to failhandler */
/*
* The checkpointed NIP is ignored when rescheduling/rechkpting,
* but is used in signal return to 'wind back' to the abort handler.
*/
/* ***************** CTR, LR, CR, XER ********** */
mfctr r3
mflr r4
mfcr r5
mfxer r6
std r3, _CTR(r7)
std r4, _LINK(r7)
std r5, _CCR(r7)
std r6, _XER(r7)
/* ******************** TAR, DSCR ********** */
mfspr r3, SPRN_TAR
mfspr r4, SPRN_DSCR
std r3, THREAD_TM_TAR(r12)
std r4, THREAD_TM_DSCR(r12)
/* ******************** AMR **************** */
mfspr r3, SPRN_AMR
std r3, THREAD_TM_AMR(r12)
/*
* MSR and flags: We don't change CRs, and we don't need to alter MSR.
*/
/*
* ******************** FPR/VR/VSRs ************
* After reclaiming, capture the checkpointed FPRs/VRs.
*
* We enabled VEC/FP/VSX in the msr above, so we can execute these
* instructions!
*/
mr r3, r12
/* Altivec (VEC/VMX/VR)*/
addi r7, r3, THREAD_CKVRSTATE
SAVE_32VRS(0, r6, r7) /* r6 scratch, r7 ckvr_state */
mfvscr v0
li r6, VRSTATE_VSCR
stvx v0, r7, r6
/* VRSAVE */
mfspr r0, SPRN_VRSAVE
std r0, THREAD_CKVRSAVE(r3)
/* Floating Point (FP) */
addi r7, r3, THREAD_CKFPSTATE
SAVE_32FPRS_VSRS(0, R6, R7) /* r6 scratch, r7 ckfp_state */
mffs fr0
stfd fr0,FPSTATE_FPSCR(r7)
/*
* TM regs, incl TEXASR -- these live in thread_struct. Note they've
* been updated by the treclaim, to explain to userland the failure
* cause (aborted).
*/
mfspr r0, SPRN_TEXASR
mfspr r3, SPRN_TFHAR
mfspr r4, SPRN_TFIAR
std r0, THREAD_TM_TEXASR(r12)
std r3, THREAD_TM_TFHAR(r12)
std r4, THREAD_TM_TFIAR(r12)
/* Restore kernel live AMR */
ld r8, TM_FRAME_L1(r1)
mtspr SPRN_AMR, r8
/* Restore original MSR/IRQ state & clear TM mode */
ld r14, TM_FRAME_L0(r1) /* Orig MSR */
li r15, 0
rldimi r14, r15, MSR_TS_LG, (63-MSR_TS_LG)-1
mtmsrd r14
REST_NVGPRS(r1)
addi r1, r1, TM_FRAME_SIZE
lwz r4, 8(r1)
ld r0, 16(r1)
mtcr r4
mtlr r0
ld r2, STK_GOT(r1)
/* Load CPU's default DSCR */
ld r0, PACA_DSCR_DEFAULT(r13)
mtspr SPRN_DSCR, r0
blr
/*
* void __tm_recheckpoint(struct thread_struct *thread)
* - Restore the checkpointed register state saved by tm_reclaim
* when we switch_to a process.
*
* Call with IRQs off, stacks get all out of sync for
* some periods in here!
*/
_GLOBAL(__tm_recheckpoint)
mfcr r5
mflr r0
stw r5, 8(r1)
std r0, 16(r1)
std r2, STK_GOT(r1)
stdu r1, -TM_FRAME_SIZE(r1)
/*
* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD].
* This is used for backing up the NVGPRs:
*/
SAVE_NVGPRS(r1)
/*
* Save kernel live AMR since it will be clobbered for trechkpt
* but can be used elsewhere later in kernel space.
*/
mfspr r8, SPRN_AMR
std r8, TM_FRAME_L0(r1)
/* Load complete register state from ts_ckpt* registers */
addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */
/*
* Make r7 look like an exception frame so that we can use the neat
* GPRx(n) macros. r7 is now NOT a pt_regs ptr!
*/
subi r7, r7, STACK_FRAME_OVERHEAD
/* We need to setup MSR for FP/VMX/VSX register save instructions. */
mfmsr r6
mr r5, r6
ori r5, r5, MSR_FP
#ifdef CONFIG_ALTIVEC
oris r5, r5, MSR_VEC@h
#endif
#ifdef CONFIG_VSX
BEGIN_FTR_SECTION
oris r5,r5, MSR_VSX@h
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
mtmsrd r5
#ifdef CONFIG_ALTIVEC
/*
* FP and VEC registers: These are recheckpointed from
* thread.ckfp_state and thread.ckvr_state respectively. The
* thread.fp_state[] version holds the 'live' (transactional)
* and will be loaded subsequently by any FPUnavailable trap.
*/
addi r8, r3, THREAD_CKVRSTATE
li r5, VRSTATE_VSCR
lvx v0, r8, r5
mtvscr v0
REST_32VRS(0, r5, r8) /* r5 scratch, r8 ptr */
ld r5, THREAD_CKVRSAVE(r3)
mtspr SPRN_VRSAVE, r5
#endif
addi r8, r3, THREAD_CKFPSTATE
lfd fr0, FPSTATE_FPSCR(r8)
MTFSF_L(fr0)
REST_32FPRS_VSRS(0, R4, R8)
mtmsr r6 /* FP/Vec off again! */
restore_gprs:
/* ****************** CTR, LR, XER ************* */
ld r4, _CTR(r7)
ld r5, _LINK(r7)
ld r8, _XER(r7)
mtctr r4
mtlr r5
mtxer r8
/* ******************** TAR ******************** */
ld r4, THREAD_TM_TAR(r3)
mtspr SPRN_TAR, r4
/* ******************** AMR ******************** */
ld r4, THREAD_TM_AMR(r3)
mtspr SPRN_AMR, r4
/* Load up the PPR and DSCR in GPRs only at this stage */
ld r5, THREAD_TM_DSCR(r3)
ld r6, THREAD_TM_PPR(r3)
REST_GPR(0, r7) /* GPR0 */
REST_GPRS(2, 4, r7) /* GPR2-4 */
REST_GPRS(8, 12, r7) /* GPR8-12 */
REST_GPRS(14, 31, r7) /* GPR14-31 */
/* Load up PPR and DSCR here so we don't run with user values for long */
mtspr SPRN_DSCR, r5
mtspr SPRN_PPR, r6
/*
* Do final sanity check on TEXASR to make sure FS is set. Do this
* here before we load up the userspace r1 so any bugs we hit will get
* a call chain.
*/
mfspr r5, SPRN_TEXASR
srdi r5, r5, 16
li r6, (TEXASR_FS)@h
and r6, r6, r5
1: tdeqi r6, 0
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
/*
* Do final sanity check on MSR to make sure we are not transactional
* or suspended.
*/
mfmsr r6
li r5, (MSR_TS_MASK)@higher
srdi r6, r6, 32
and r6, r6, r5
1: tdnei r6, 0
EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
/* Restore CR */
ld r6, _CCR(r7)
mtcr r6
REST_GPR(6, r7)
/*
* Store user r1 and r5 and r13 on the stack (in the unused save
* areas / compiler reserved areas), so that we can access them after
* we clear MSR RI.
*/
REST_GPR(5, r7)
std r5, -8(r1)
ld r5, GPR13(r7)
std r5, -16(r1)
ld r5, GPR1(r7)
std r5, -24(r1)
REST_GPR(7, r7)
/* Stash the stack pointer away for use after recheckpoint */
std r1, PACAR1(r13)
/* Clear MSR RI since we are about to clobber r13. EE is already off */
li r5, 0
mtmsrd r5, 1
/*
* BE CAREFUL HERE:
* At this point we can't take an SLB miss since we have MSR_RI
* off. Load only to/from the stack/paca which are in SLB bolted regions
* until we turn MSR RI back on.
*/
ld r5, -8(r1)
ld r13, -16(r1)
ld r1, -24(r1)
/* Commit register state as checkpointed state: */
TRECHKPT
HMT_MEDIUM
/*
* Our transactional state has now changed.
*
* Now just get out of here. Transactional (current) state will be
* updated once restore is called on the return path in the _switch-ed
* -to process.
*/
GET_PACA(r13)
ld r1, PACAR1(r13)
/* R13, R1 is restored, so we are recoverable again. EE is still off */
li r4, MSR_RI
mtmsrd r4, 1
/* Restore kernel live AMR */
ld r8, TM_FRAME_L0(r1)
mtspr SPRN_AMR, r8
REST_NVGPRS(r1)
addi r1, r1, TM_FRAME_SIZE
lwz r4, 8(r1)
ld r0, 16(r1)
mtcr r4
mtlr r0
ld r2, STK_GOT(r1)
/* Load CPU's default DSCR */
ld r0, PACA_DSCR_DEFAULT(r13)
mtspr SPRN_DSCR, r0
blr
/* ****************************************************************** */
Reference in New Issue View Git Blame Copy Permalink