Excerpts from Sachin Sant's message of June 29, 2021 12:37 am:
>
>> On 28-Jun-2021, at 1:19 PM, Nicholas Piggin <npig...@gmail.com> wrote:
>>
>> Similar to 2b48e96be2f9f ("powerpc/64: fix irq replay pt_regs->softe
>> value"), enable MSR_EE in pt_regs->msr, which makes the regs look a
>> bit more normal and allows the extra debug checks to be added to
>> interrupt handler entry.
>>
>> Signed-off-by: Nicholas Piggin <npig...@gmail.com>
>> ---
>> arch/powerpc/include/asm/interrupt.h | 4 ++++
>> arch/powerpc/kernel/irq.c | 1 +
>> 2 files changed, 5 insertions(+)
>>
>> diff --git a/arch/powerpc/include/asm/interrupt.h
>> b/arch/powerpc/include/asm/interrupt.h
>> index 789311d1e283..d4bdf7d274ac 100644
>> --- a/arch/powerpc/include/asm/interrupt.h
>> +++ b/arch/powerpc/include/asm/interrupt.h
>> @@ -173,6 +173,8 @@ static inline void interrupt_enter_prepare(struct
>> pt_regs *regs, struct interrup
>> BUG_ON(search_kernel_restart_table(regs->nip));
>> #endif
>> }
>> + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
>> + BUG_ON(!arch_irq_disabled_regs(regs) && !(regs->msr & MSR_EE));
>> #endif
>
> I think this BUG_ON was triggered while running selftests
> (powerpc/mm/pkey_exec_prot)
>
> [ 9741.254969] ------------[ cut here ]------------
> [ 9741.254978] kernel BUG at arch/powerpc/include/asm/interrupt.h:177!
> [ 9741.254985] Oops: Exception in kernel mode, sig: 5 [#1]
> [ 9741.254990] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
> [ 9741.254995] Modules linked in: rpadlpar_io rpaphp uinput sha512_generic
> vmac n_gsm pps_ldisc pps_core ppp_synctty ppp_async ppp_generic slcan slip
> slhc snd_hrtimer snd_seq snd_seq_device snd_timer snd soundcore authenc
> pcrypt crypto_user n_hdlc dummy veth nfsv3 nfs_acl nfs lockd grace fscache
> netfs tun brd overlay vfat fat btrfs blake2b_generic xor zstd_compress
> raid6_pq xfs loop sctp ip6_udp_tunnel udp_tunnel dm_mod bonding nft_ct
> nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set rfkill nf_tables libcrc32c
> nfnetlink sunrpc pseries_rng xts vmx_crypto uio_pdrv_genirq uio sch_fq_codel
> ip_tables ext4 mbcache jbd2 sr_mod sd_mod cdrom t10_pi sg ibmvscsi ibmveth
> scsi_transport_srp fuse [last unloaded: test_cpuidle_latency]
> [ 9741.255097] CPU: 17 PID: 3278920 Comm: pkey_exec_prot Tainted: G W
> OE 5.13.0-rc7-next-20210625-dirty #4
> [ 9741.255106] NIP: c0000000000300d8 LR: c000000000009604 CTR:
> c000000000009330
> [ 9741.255111] REGS: c0000000347536f0 TRAP: 0700 Tainted: G W OE
> (5.13.0-rc7-next-20210625-dirty)
> [ 9741.255117] MSR: 8000000000021033 <SF,ME,IR,DR,RI,LE> CR: 22004282 XER:
> 20040000
> [ 9741.255130] CFAR: c00000000003007c IRQMASK: 3
> [ 9741.255130] GPR00: c000000000093cd0 c000000034753990 c0000000029bbe00
> c000000034753a30
> [ 9741.255130] GPR04: 00007fff9ebb0000 0000000000200000 000000000000000a
> 000000000000002d
> [ 9741.255130] GPR08: 0000000000000000 0000000000000001 0000000000000000
> 7265677368657265
> [ 9741.255130] GPR12: 8000000000021033 c00000001ec27280 0000000000000000
> 0000000000000000
> [ 9741.255130] GPR16: 0000000000000000 0000000000000000 0000000000000000
> 0000000000000000
> [ 9741.255130] GPR20: 0000000000000000 0000000000000000 0000000000000000
> 0000000010003c40
> [ 9741.255130] GPR24: 0000000000000000 0000000000000000 0000000000200000
> c00000005e89d200
> [ 9741.255130] GPR28: 0000000000000300 00007fff9ebb0000 c000000034753e80
> c000000034753a30
> [ 9741.255191] NIP [c0000000000300d8] program_check_exception+0xe8/0x1c0
> [ 9741.255202] LR [c000000000009604] program_check_common_virt+0x2d4/0x320
> [ 9741.255209] Call Trace:
> [ 9741.255212] [c000000034753990] [0000000000000008] 0x8 (unreliable)
> [ 9741.255219] [c0000000347539c0] [c000000034753a80] 0xc000000034753a80
> [ 9741.255225] --- interrupt: 700 at arch_local_irq_restore+0x1d0/0x200
> [ 9741.255231] NIP: c000000000016790 LR: c000000000093388 CTR:
> c000000000008780
> [ 9741.255236] REGS: c000000034753a30 TRAP: 0700 Tainted: G W OE
> (5.13.0-rc7-next-20210625-dirty)
> [ 9741.255242] MSR: 8000000000021033 <SF,ME,IR,DR,RI,LE> CR: 24004288 XER:
> 20040000
> [ 9741.255253] CFAR: c0000000000165ec IRQMASK: 0
> [ 9741.255253] GPR00: c000000000093cd0 c000000034753cd0 c0000000029bbe00
> 0000000000000000
> [ 9741.255253] GPR04: 00007fff9ebb0000 0000000000200000 000000000000000a
> 000000000000002d
> [ 9741.255253] GPR08: 0000000000000000 0000000000000000 c0000000bd77d400
> 7265677368657265
> [ 9741.255253] GPR12: 0000000044000282 c00000001ec27280 0000000000000000
> 0000000000000000
> [ 9741.255253] GPR16: 0000000000000000 0000000000000000 0000000000000000
> 0000000000000000
> [ 9741.255253] GPR20: 0000000000000000 0000000000000000 0000000000000000
> 0000000010003c40
> [ 9741.255253] GPR24: 0000000000000000 0000000000000000 0000000000200000
> c00000005e89d200
> [ 9741.255253] GPR28: 0000000000000300 00007fff9ebb0000 c000000034753e80
> 0000000000000001
> [ 9741.255313] NIP [c000000000016790] arch_local_irq_restore+0x1d0/0x200
> [ 9741.255319] LR [c000000000093388] ___do_page_fault+0x438/0xb80
> [ 9741.255325] --- interrupt: 700
> [ 9741.255328] [c000000034753cd0] [c00000000009be74] hash_page_mm+0x5e4/0x800
> (unreliable)
> [ 9741.255335] [c000000034753d00] [000000000000002d] 0x2d
> [ 9741.255340] [c000000034753db0] [c000000000093cd0]
> hash__do_page_fault+0x30/0x70
> [ 9741.255348] [c000000034753de0] [c00000000009c438] do_hash_fault+0x78/0xb0
This looks like it's probably running un-reconciled due to the first
call to hash__do_page_fault not calling a real interrupt handler.
Without this patch, the test must be causing a warning due to the same
thing probably (the bug triggered in the program check interrupt handler).
I think this patch is probably the right fix for it.
Thanks,
Nick
---
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c
b/arch/powerpc/mm/book3s64/hash_utils.c
index 96d9aa164007..ac5720371c0d 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1522,8 +1522,8 @@ int hash_page(unsigned long ea, unsigned long access,
unsigned long trap,
}
EXPORT_SYMBOL_GPL(hash_page);
-DECLARE_INTERRUPT_HANDLER_RET(__do_hash_fault);
-DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
+DECLARE_INTERRUPT_HANDLER(__do_hash_fault);
+DEFINE_INTERRUPT_HANDLER(__do_hash_fault)
{
unsigned long ea = regs->dar;
unsigned long dsisr = regs->dsisr;
@@ -1533,6 +1533,11 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
unsigned int region_id;
long err;
+ if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT))) {
+ hash__do_page_fault(regs);
+ return;
+ }
+
region_id = get_region_id(ea);
if ((region_id == VMALLOC_REGION_ID) || (region_id == IO_REGION_ID))
mm = &init_mm;
@@ -1571,9 +1576,10 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
bad_page_fault(regs, SIGBUS);
}
err = 0;
- }
- return err;
+ } else if (err) {
+ hash__do_page_fault(regs);
+ }
}
/*
@@ -1582,13 +1588,6 @@ DEFINE_INTERRUPT_HANDLER_RET(__do_hash_fault)
*/
DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
{
- unsigned long dsisr = regs->dsisr;
-
- if (unlikely(dsisr & (DSISR_BAD_FAULT_64S | DSISR_KEYFAULT))) {
- hash__do_page_fault(regs);
- return 0;
- }
-
/*
* If we are in an "NMI" (e.g., an interrupt when soft-disabled), then
* don't call hash_page, just fail the fault. This is required to
@@ -1607,8 +1606,7 @@ DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
return 0;
}
- if (__do_hash_fault(regs))
- hash__do_page_fault(regs);
+ __do_hash_fault(regs);
return 0;
}
