Hello,
On Wed, 04 Jul 2018 23:28:21 +0530
"Mahesh J Salgaonkar" <mah...@linux.vnet.ibm.com> wrote:
> From: Mahesh Salgaonkar <mah...@linux.vnet.ibm.com>
>
> On pseries, as of today system crashes if we get a machine check
> exceptions due to SLB errors. These are soft errors and can be fixed
> by flushing the SLBs so the kernel can continue to function instead of
> system crash. We do this in real mode before turning on MMU. Otherwise
> we would run into nested machine checks. This patch now fetches the
> rtas error log in real mode and flushes the SLBs on SLB errors.
>
> Signed-off-by: Mahesh Salgaonkar <mah...@linux.vnet.ibm.com>
> ---
> arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1
> arch/powerpc/include/asm/machdep.h | 1
> arch/powerpc/kernel/exceptions-64s.S | 42
> +++++++++++++++++++++ arch/powerpc/kernel/mce.c
> | 16 +++++++- arch/powerpc/mm/slb.c | 6
> +++ arch/powerpc/platforms/pseries/pseries.h | 1
> arch/powerpc/platforms/pseries/ras.c | 51
> +++++++++++++++++++++++++
> arch/powerpc/platforms/pseries/setup.c | 1 8 files changed,
> 116 insertions(+), 3 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
> b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index
> 50ed64fba4ae..cc00a7088cf3 100644 ---
> a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++
> b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -487,6 +487,7 @@
> extern void hpte_init_native(void);
> extern void slb_initialize(void);
> extern void slb_flush_and_rebolt(void);
> +extern void slb_flush_and_rebolt_realmode(void);
>
> extern void slb_vmalloc_update(void);
> extern void slb_set_size(u16 size);
> diff --git a/arch/powerpc/include/asm/machdep.h
> b/arch/powerpc/include/asm/machdep.h index ffe7c71e1132..fe447e0d4140
> 100644 --- a/arch/powerpc/include/asm/machdep.h
> +++ b/arch/powerpc/include/asm/machdep.h
> @@ -108,6 +108,7 @@ struct machdep_calls {
>
> /* Early exception handlers called in realmode */
> int (*hmi_exception_early)(struct pt_regs
> *regs);
> + int (*machine_check_early)(struct pt_regs
> *regs);
> /* Called during machine check exception to retrive fixup
> address. */ bool (*mce_check_early_recovery)(struct
> pt_regs *regs); diff --git a/arch/powerpc/kernel/exceptions-64s.S
> b/arch/powerpc/kernel/exceptions-64s.S index
> f283958129f2..0038596b7906 100644 ---
> a/arch/powerpc/kernel/exceptions-64s.S +++
> b/arch/powerpc/kernel/exceptions-64s.S @@ -332,6 +332,9 @@
> TRAMP_REAL_BEGIN(machine_check_pSeries) machine_check_fwnmi:
> SET_SCRATCH0(r13) /* save r13 */
> EXCEPTION_PROLOG_0(PACA_EXMC)
> +BEGIN_FTR_SECTION
> + b machine_check_pSeries_early
> +END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
> machine_check_pSeries_0:
> EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST_PR, 0x200)
> /*
> @@ -343,6 +346,45 @@ machine_check_pSeries_0:
>
> TRAMP_KVM_SKIP(PACA_EXMC, 0x200)
>
> +TRAMP_REAL_BEGIN(machine_check_pSeries_early)
> +BEGIN_FTR_SECTION
> + EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
> + mr r10,r1 /* Save r1 */
> + ld r1,PACAMCEMERGSP(r13) /* Use MC emergency
> stack */
> + subi r1,r1,INT_FRAME_SIZE /* alloc stack
> frame */
> + mfspr r11,SPRN_SRR0 /* Save SRR0 */
> + mfspr r12,SPRN_SRR1 /* Save SRR1 */
> + EXCEPTION_PROLOG_COMMON_1()
> + EXCEPTION_PROLOG_COMMON_2(PACA_EXMC)
> + EXCEPTION_PROLOG_COMMON_3(0x200)
> + addi r3,r1,STACK_FRAME_OVERHEAD
> + BRANCH_LINK_TO_FAR(machine_check_early) /* Function call ABI
> */ +
> + /* Move original SRR0 and SRR1 into the respective regs */
> + ld r9,_MSR(r1)
> + mtspr SPRN_SRR1,r9
> + ld r3,_NIP(r1)
> + mtspr SPRN_SRR0,r3
> + ld r9,_CTR(r1)
> + mtctr r9
> + ld r9,_XER(r1)
> + mtxer r9
> + ld r9,_LINK(r1)
> + mtlr r9
> + REST_GPR(0, r1)
> + REST_8GPRS(2, r1)
> + REST_GPR(10, r1)
> + ld r11,_CCR(r1)
> + mtcr r11
> + REST_GPR(11, r1)
> + REST_2GPRS(12, r1)
> + /* restore original r1. */
> + ld r1,GPR1(r1)
> + SET_SCRATCH0(r13) /* save r13 */
> + EXCEPTION_PROLOG_0(PACA_EXMC)
> + b machine_check_pSeries_0
> +END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
> +
> EXC_COMMON_BEGIN(machine_check_common)
> /*
> * Machine check is different because we use a different
> diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
> index efdd16a79075..221271c96a57 100644
> --- a/arch/powerpc/kernel/mce.c
> +++ b/arch/powerpc/kernel/mce.c
> @@ -488,9 +488,21 @@ long machine_check_early(struct pt_regs *regs)
> {
> long handled = 0;
>
> - __this_cpu_inc(irq_stat.mce_exceptions);
> + /*
> + * For pSeries we count mce when we go into virtual mode
> machine
> + * check handler. Hence skip it. Also, We can't access per
> cpu
> + * variables in real mode for LPAR.
> + */
> + if (early_cpu_has_feature(CPU_FTR_HVMODE))
> + __this_cpu_inc(irq_stat.mce_exceptions);
Maybe we could simplify the condition
if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !cpu_has_feature(CPU_FTR_HVMODE))
in machine_check instead?
Thanks
Michal
