| Message ID | 20180326150946.23555-1-npiggin@gmail.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | [RFC] powerpc/xmon: Use OPAL_DEBUG to debug srest in OPAL | expand |
On 03/26/2018 08:39 PM, Nicholas Piggin wrote: > xmon can be entered via sreset NMI (from a management sreset, or an > NMI IPI), which can interrupt OPAL. Add checks to xmon to see if pc > or sp are within OPAL memory, and if so, then use OPAL_DEBUG to > print the opal stack and return the Linux stack, which can then be > dumped by xmon Nick, OPAL uses FSP/cronus interface for many of debug interface (like OPAL assert, getting opal console, triggering FSP R/R etc). May be in future we may add new debug capability. Once secureboot is enabled none of these interface work and we have limited debug capability. Here you are using very generic API name (OPAL_DEBUG). May be we should have generic interface (exported via debugfs?) here rather than SRESET specific one. -Vasant > > The OPAL side of this, with sample xmon output is here: > > https://lists.ozlabs.org/pipermail/skiboot/2018-March/010856.html > > This could be plumed into the oops printing code as well. > > Thanks, > Nick > --- > arch/powerpc/include/asm/opal.h | 4 ++++ > arch/powerpc/platforms/powernv/opal-wrappers.S | 1 + > arch/powerpc/platforms/powernv/opal.c | 5 +++++ > arch/powerpc/xmon/xmon.c | 27 ++++++++++++++++++++++++++ > 4 files changed, 37 insertions(+) > > diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h > index 12e70fb58700..afcc0c5ed5b0 100644 > --- a/arch/powerpc/include/asm/opal.h > +++ b/arch/powerpc/include/asm/opal.h > @@ -27,6 +27,8 @@ extern struct kobject *opal_kobj; > /* /ibm,opal */ > extern struct device_node *opal_node; > > +bool in_opal_text_heap_stack(u64 address); > + > /* API functions */ > int64_t opal_invalid_call(void); > int64_t opal_npu_destroy_context(uint64_t phb_id, uint64_t pid, uint64_t bdf); > @@ -289,6 +291,8 @@ int opal_sensor_group_clear(u32 group_hndl, int token); > > s64 opal_signal_system_reset(s32 cpu); > > +s64 opal_debug(u32 debug_type, u64 r1); > + > /* Internal functions */ > extern int early_init_dt_scan_opal(unsigned long node, const char *uname, > int depth, void *data); > diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S > index 1b2936ba6040..78b9ae003553 100644 > --- a/arch/powerpc/platforms/powernv/opal-wrappers.S > +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S > @@ -323,3 +323,4 @@ OPAL_CALL(opal_sensor_group_clear, OPAL_SENSOR_GROUP_CLEAR); > OPAL_CALL(opal_npu_spa_setup, OPAL_NPU_SPA_SETUP); > OPAL_CALL(opal_npu_spa_clear_cache, OPAL_NPU_SPA_CLEAR_CACHE); > OPAL_CALL(opal_npu_tl_set, OPAL_NPU_TL_SET); > +OPAL_CALL(opal_debug, 167); > diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c > index c15182765ff5..0b7ff5fb18f8 100644 > --- a/arch/powerpc/platforms/powernv/opal.c > +++ b/arch/powerpc/platforms/powernv/opal.c > @@ -64,6 +64,11 @@ static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX]; > static uint32_t opal_heartbeat; > static struct task_struct *kopald_tsk; > > +bool in_opal_text_heap_stack(u64 address) > +{ > + return (address >= opal.base && address < opal.base + opal.size); > +} > + > void opal_configure_cores(void) > { > u64 reinit_flags = 0; > diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c > index 82e1a3ee6e0f..ade1adcc1ab8 100644 > --- a/arch/powerpc/xmon/xmon.c > +++ b/arch/powerpc/xmon/xmon.c > @@ -452,6 +452,15 @@ static inline int unrecoverable_excp(struct pt_regs *regs) > #endif > } > > +static bool in_opal(unsigned long addr) > +{ > + if (firmware_has_feature(FW_FEATURE_OPAL)) > + if (in_opal_text_heap_stack(addr)) > + return true; > + > + return false; > +} > + > static int xmon_core(struct pt_regs *regs, int fromipi) > { > int cmd = 0; > @@ -510,6 +519,9 @@ static int xmon_core(struct pt_regs *regs, int fromipi) > > xmon_fault_jmp[cpu] = recurse_jmp; > > + if (in_opal(regs->nip)) > + printf("xmon: cpu 0x%x stopped in OPAL!\n", cpu); > + > bp = NULL; > if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT)) > bp = at_breakpoint(regs->nip); > @@ -1484,8 +1496,23 @@ static void xmon_show_stack(unsigned long sp, unsigned long lr, > unsigned long marker; > struct pt_regs regs; > > + if (in_opal(sp)) { > + struct debug_struct { > + unsigned long nip; > + unsigned long r1; > + unsigned long r1_caller; > + } db; > + printf("SP is in OPAL, calling OPAL to dump stack\n"); > + db.nip = cpu_to_be64(pc); > + db.r1 = cpu_to_be64(sp); > + opal_debug(1, (unsigned long)&db); > + sp = be64_to_cpu(db.r1_caller); > + } > + > while (max_to_print--) { > if (!is_kernel_addr(sp)) { > + if (in_opal(pc) && in_opal(sp)) > + printf("SP (%lx) is in OPAL\n", sp); > if (sp != 0) > printf("SP (%lx) is in userspace\n", sp); > break; >
On Tue, 27 Mar 2018 12:42:32 +0530 Vasant Hegde <hegdevasant@linux.vnet.ibm.com> wrote: > On 03/26/2018 08:39 PM, Nicholas Piggin wrote: > > xmon can be entered via sreset NMI (from a management sreset, or an > > NMI IPI), which can interrupt OPAL. Add checks to xmon to see if pc > > or sp are within OPAL memory, and if so, then use OPAL_DEBUG to > > print the opal stack and return the Linux stack, which can then be > > dumped by xmon > > Nick, > > > OPAL uses FSP/cronus interface for many of debug interface (like OPAL assert, > getting opal console, triggering FSP R/R etc). May be in future we may add new > debug capability. It would be good to ensure an API could accommodate them, or at least not get in the way. > Once secureboot is enabled none of these interface work and we have limited debug > capability. > > Here you are using very generic API name (OPAL_DEBUG). May be we should have generic > interface (exported via debugfs?) here rather than SRESET specific one. OPAL_DEBUG here actually uses the sub-function OPAL_DEBUG_DUMP_STACK (1), but I didn't bring that constant across from skiboot which I should have. But I don't think this is SRESET specific. If Linux has any way to get an r1 for a CPU in OPAL, then it can use this function. If it does not, then it simply can't use it. I haven't really followed what's happening with secure boot, but presumably we can still get NMIs (at least machine check, even if all system reset sources are suppressed). > > > > The OPAL side of this, with sample xmon output is here: > > > > https://lists.ozlabs.org/pipermail/skiboot/2018-March/010856.html > > > > This could be plumed into the oops printing code as well. Thanks, Nick
On 03/27/2018 12:58 PM, Nicholas Piggin wrote: > On Tue, 27 Mar 2018 12:42:32 +0530 > Vasant Hegde <hegdevasant@linux.vnet.ibm.com> wrote: > >> On 03/26/2018 08:39 PM, Nicholas Piggin wrote: >>> xmon can be entered via sreset NMI (from a management sreset, or an >>> NMI IPI), which can interrupt OPAL. Add checks to xmon to see if pc >>> or sp are within OPAL memory, and if so, then use OPAL_DEBUG to >>> print the opal stack and return the Linux stack, which can then be >>> dumped by xmon >> >> Nick, >> >> >> OPAL uses FSP/cronus interface for many of debug interface (like OPAL assert, >> getting opal console, triggering FSP R/R etc). May be in future we may add new >> debug capability. > > It would be good to ensure an API could accommodate them, or at least > not get in the way. Agree. > >> Once secureboot is enabled none of these interface work and we have limited debug >> capability. >> >> Here you are using very generic API name (OPAL_DEBUG). May be we should have generic >> interface (exported via debugfs?) here rather than SRESET specific one. > > OPAL_DEBUG here actually uses the sub-function OPAL_DEBUG_DUMP_STACK (1), > but I didn't bring that constant across from skiboot which I should have. Nick, May be we should define sub-function usage. Also current API limits number of arguments and its type. may be we should have argument 2 as "void *" ? something like : s64 opal_debug(u32 debug_type, void *data, u64 dsize); That way individual sub-function can parse/use based on its need. > > But I don't think this is SRESET specific. If Linux has any way to get > an r1 for a CPU in OPAL, then it can use this function. If it does not, > then it simply can't use it. > > I haven't really followed what's happening with secure boot, but presumably > we can still get NMIs (at least machine check, even if all system reset > sources are suppressed). AFAIK secureboot won't block us here. It mostly blocks external entity (like FSP/cronus) from accessing host memory. (like they can't directly read, write to host memory, SCOM operations are restricted etc). -Vasant
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 12e70fb58700..afcc0c5ed5b0 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -27,6 +27,8 @@ extern struct kobject *opal_kobj; /* /ibm,opal */ extern struct device_node *opal_node; +bool in_opal_text_heap_stack(u64 address); + /* API functions */ int64_t opal_invalid_call(void); int64_t opal_npu_destroy_context(uint64_t phb_id, uint64_t pid, uint64_t bdf); @@ -289,6 +291,8 @@ int opal_sensor_group_clear(u32 group_hndl, int token); s64 opal_signal_system_reset(s32 cpu); +s64 opal_debug(u32 debug_type, u64 r1); + /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 1b2936ba6040..78b9ae003553 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -323,3 +323,4 @@ OPAL_CALL(opal_sensor_group_clear, OPAL_SENSOR_GROUP_CLEAR); OPAL_CALL(opal_npu_spa_setup, OPAL_NPU_SPA_SETUP); OPAL_CALL(opal_npu_spa_clear_cache, OPAL_NPU_SPA_CLEAR_CACHE); OPAL_CALL(opal_npu_tl_set, OPAL_NPU_TL_SET); +OPAL_CALL(opal_debug, 167); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index c15182765ff5..0b7ff5fb18f8 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -64,6 +64,11 @@ static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX]; static uint32_t opal_heartbeat; static struct task_struct *kopald_tsk; +bool in_opal_text_heap_stack(u64 address) +{ + return (address >= opal.base && address < opal.base + opal.size); +} + void opal_configure_cores(void) { u64 reinit_flags = 0; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 82e1a3ee6e0f..ade1adcc1ab8 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -452,6 +452,15 @@ static inline int unrecoverable_excp(struct pt_regs *regs) #endif } +static bool in_opal(unsigned long addr) +{ + if (firmware_has_feature(FW_FEATURE_OPAL)) + if (in_opal_text_heap_stack(addr)) + return true; + + return false; +} + static int xmon_core(struct pt_regs *regs, int fromipi) { int cmd = 0; @@ -510,6 +519,9 @@ static int xmon_core(struct pt_regs *regs, int fromipi) xmon_fault_jmp[cpu] = recurse_jmp; + if (in_opal(regs->nip)) + printf("xmon: cpu 0x%x stopped in OPAL!\n", cpu); + bp = NULL; if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT)) bp = at_breakpoint(regs->nip); @@ -1484,8 +1496,23 @@ static void xmon_show_stack(unsigned long sp, unsigned long lr, unsigned long marker; struct pt_regs regs; + if (in_opal(sp)) { + struct debug_struct { + unsigned long nip; + unsigned long r1; + unsigned long r1_caller; + } db; + printf("SP is in OPAL, calling OPAL to dump stack\n"); + db.nip = cpu_to_be64(pc); + db.r1 = cpu_to_be64(sp); + opal_debug(1, (unsigned long)&db); + sp = be64_to_cpu(db.r1_caller); + } + while (max_to_print--) { if (!is_kernel_addr(sp)) { + if (in_opal(pc) && in_opal(sp)) + printf("SP (%lx) is in OPAL\n", sp); if (sp != 0) printf("SP (%lx) is in userspace\n", sp); break;