From 5aa04b3eb6fca63d2e9827be656dcadc26d54e11 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Thu, 30 Nov 2017 14:03:22 +0530 Subject: [PATCH 1/4] powerpc/perf: Fix oops when grouping different pmu events When user tries to group imc (In-Memory Collections) event with normal event, (sometime) kernel crashes with following log: Faulting instruction address: 0x00000000 [link register ] c00000000010ce88 power_check_constraints+0x128/0x980 ... c00000000010e238 power_pmu_event_init+0x268/0x6f0 c0000000002dc60c perf_try_init_event+0xdc/0x1a0 c0000000002dce88 perf_event_alloc+0x7b8/0xac0 c0000000002e92e0 SyS_perf_event_open+0x530/0xda0 c00000000000b004 system_call+0x38/0xe0 'event_base' field of 'struct hw_perf_event' is used as flags for normal hw events and used as memory address for imc events. While grouping these two types of events, collect_events() tries to interpret imc 'event_base' as a flag, which causes a corruption resulting in a crash. Consider only those events which belongs to 'perf_hw_context' in collect_events(). Signed-off-by: Ravi Bangoria Reviewed-By: Madhavan Srinivasan Signed-off-by: Michael Ellerman --- arch/powerpc/perf/core-book3s.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 9e3da168d54c..153812966365 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1415,7 +1415,7 @@ static int collect_events(struct perf_event *group, int max_count, int n = 0; struct perf_event *event; - if (!is_software_event(group)) { + if (group->pmu->task_ctx_nr == perf_hw_context) { if (n >= max_count) return -1; ctrs[n] = group; @@ -1423,7 +1423,7 @@ static int collect_events(struct perf_event *group, int max_count, events[n++] = group->hw.config; } list_for_each_entry(event, &group->sibling_list, group_entry) { - if (!is_software_event(event) && + if (event->pmu->task_ctx_nr == perf_hw_context && event->state != PERF_EVENT_STATE_OFF) { if (n >= max_count) return -1; From ab9dbf771ff9b6b7e814e759213ed01d7f0de320 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Mon, 4 Dec 2017 16:27:25 +1100 Subject: [PATCH 2/4] Revert "powerpc: Do not call ppc_md.panic in fadump panic notifier" This reverts commit a3b2cb30f252b21a6f962e0dd107c8b897ca65e4. That commit tried to fix problems with panic on powerpc in certain circumstances, where some output from the generic panic code was being dropped. Unfortunately, it breaks things worse in other circumstances. In particular when running a PAPR guest, it will now attempt to reboot instead of informing the hypervisor (KVM or PowerVM) that the guest has crashed. The crash notification is important to some virtualization management layers. Revert it for now until we can come up with a better solution. Fixes: a3b2cb30f252 ("powerpc: Do not call ppc_md.panic in fadump panic notifier") Cc: stable@vger.kernel.org # v4.14+ Signed-off-by: David Gibson [mpe: Tweak change log a bit] Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/machdep.h | 1 + arch/powerpc/include/asm/setup.h | 1 + arch/powerpc/kernel/fadump.c | 22 --------------------- arch/powerpc/kernel/setup-common.c | 27 ++++++++++++++++++++++++++ arch/powerpc/platforms/ps3/setup.c | 15 ++++++++++++++ arch/powerpc/platforms/pseries/setup.c | 1 + 6 files changed, 45 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 73b92017b6d7..cd2fc1cc1cc7 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -76,6 +76,7 @@ struct machdep_calls { void __noreturn (*restart)(char *cmd); void __noreturn (*halt)(void); + void (*panic)(char *str); void (*cpu_die)(void); long (*time_init)(void); /* Optional, may be NULL */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 257d23dbf55d..cf00ec26303a 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -24,6 +24,7 @@ extern void reloc_got2(unsigned long); void check_for_initrd(void); void initmem_init(void); +void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 04ea5c04fd24..3c2c2688918f 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1462,25 +1462,6 @@ static void fadump_init_files(void) return; } -static int fadump_panic_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - /* - * If firmware-assisted dump has been registered then trigger - * firmware-assisted dump and let firmware handle everything - * else. If this returns, then fadump was not registered, so - * go through the rest of the panic path. - */ - crash_fadump(NULL, ptr); - - return NOTIFY_DONE; -} - -static struct notifier_block fadump_panic_block = { - .notifier_call = fadump_panic_event, - .priority = INT_MIN /* may not return; must be done last */ -}; - /* * Prepare for firmware-assisted dump. */ @@ -1513,9 +1494,6 @@ int __init setup_fadump(void) init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start); fadump_init_files(); - atomic_notifier_chain_register(&panic_notifier_list, - &fadump_panic_block); - return 1; } subsys_initcall(setup_fadump); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 2075322cd225..9d213542a48b 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -704,6 +704,30 @@ int check_legacy_ioport(unsigned long base_port) } EXPORT_SYMBOL(check_legacy_ioport); +static int ppc_panic_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + /* + * If firmware-assisted dump has been registered then trigger + * firmware-assisted dump and let firmware handle everything else. + */ + crash_fadump(NULL, ptr); + ppc_md.panic(ptr); /* May not return */ + return NOTIFY_DONE; +} + +static struct notifier_block ppc_panic_block = { + .notifier_call = ppc_panic_event, + .priority = INT_MIN /* may not return; must be done last */ +}; + +void __init setup_panic(void) +{ + if (!ppc_md.panic) + return; + atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); +} + #ifdef CONFIG_CHECK_CACHE_COHERENCY /* * For platforms that have configurable cache-coherency. This function @@ -848,6 +872,9 @@ void __init setup_arch(char **cmdline_p) /* Probe the machine type, establish ppc_md. */ probe_machine(); + /* Setup panic notifier if requested by the platform. */ + setup_panic(); + /* * Configure ppc_md.power_save (ppc32 only, 64-bit machines do * it from their respective probe() function. diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 9dabea6e1443..6244bc849469 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -104,6 +104,20 @@ static void __noreturn ps3_halt(void) ps3_sys_manager_halt(); /* never returns */ } +static void ps3_panic(char *str) +{ + DBG("%s:%d %s\n", __func__, __LINE__, str); + + smp_send_stop(); + printk("\n"); + printk(" System does not reboot automatically.\n"); + printk(" Please press POWER button.\n"); + printk("\n"); + + while(1) + lv1_pause(1); +} + #if defined(CONFIG_FB_PS3) || defined(CONFIG_FB_PS3_MODULE) || \ defined(CONFIG_PS3_FLASH) || defined(CONFIG_PS3_FLASH_MODULE) static void __init prealloc(struct ps3_prealloc *p) @@ -255,6 +269,7 @@ define_machine(ps3) { .probe = ps3_probe, .setup_arch = ps3_setup_arch, .init_IRQ = ps3_init_IRQ, + .panic = ps3_panic, .get_boot_time = ps3_get_boot_time, .set_dabr = ps3_set_dabr, .calibrate_decr = ps3_calibrate_decr, diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 5f1beb8367ac..a8531e012658 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -726,6 +726,7 @@ define_machine(pseries) { .pcibios_fixup = pSeries_final_fixup, .restart = rtas_restart, .halt = rtas_halt, + .panic = rtas_os_term, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, .set_rtc_time = rtas_set_rtc_time, From 371b80447ff33ddac392c189cf884a5a3e18faeb Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 6 Dec 2017 18:21:14 +1000 Subject: [PATCH 3/4] powerpc/64s: Initialize ISAv3 MMU registers before setting partition table kexec can leave MMU registers set when booting into a new kernel, the PIDR (Process Identification Register) in particular. The boot sequence does not zero PIDR, so it only gets set when CPUs first switch to a userspace processes (until then it's running a kernel thread with effective PID = 0). This leaves a window where a process table entry and page tables are set up due to user processes running on other CPUs, that happen to match with a stale PID. The CPU with that PID may cause speculative accesses that address quadrant 0 (aka userspace addresses), which will result in cached translations and PWC (Page Walk Cache) for that process, on a CPU which is not in the mm_cpumask and so they will not be invalidated properly. The most common result is the kernel hanging in infinite page fault loops soon after kexec (usually in schedule_tail, which is usually the first non-speculative quadrant 0 access to a new PID) due to a stale PWC. However being a stale translation error, it could result in anything up to security and data corruption problems. Fix this by zeroing out PIDR at boot and kexec. Fixes: 7e381c0ff618 ("powerpc/mm/radix: Add mmu context handling callback for radix") Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/cpu_setup_power.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index 610955fe8b81..679bbe714e85 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -102,6 +102,7 @@ _GLOBAL(__setup_cpu_power9) li r0,0 mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 + mtspr SPRN_PID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC) or r3, r3, r4 @@ -126,6 +127,7 @@ _GLOBAL(__restore_cpu_power9) li r0,0 mtspr SPRN_PSSCR,r0 mtspr SPRN_LPID,r0 + mtspr SPRN_PID,r0 mfspr r3,SPRN_LPCR LOAD_REG_IMMEDIATE(r4, LPCR_PECEDH | LPCR_PECE_HVEE | LPCR_HVICE | LPCR_HEIC) or r3, r3, r4 From d8104182087319fd753d6d8e0afcd95d84c2aa2f Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 6 Dec 2017 23:23:28 +1100 Subject: [PATCH 4/4] powerpc/xmon: Don't print hashed pointers in xmon Since commit ad67b74d2469 ("printk: hash addresses printed with %p") pointers printed with %p are hashed, ie. you don't see the actual pointer value but rather a cryptographic hash of its value. In xmon we want to see the actual pointer values, because xmon is a debugger, so replace %p with %px which prints the actual pointer value. We justify doing this in xmon because 1) xmon is a kernel crash debugger, it's only accessible via the console 2) xmon doesn't print to dmesg, so the pointers it prints are not able to be leaked that way. Signed-off-by: Michael Ellerman --- arch/powerpc/xmon/xmon.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 1b2d8cb49abb..cab24f549e7c 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1590,7 +1590,7 @@ static void print_bug_trap(struct pt_regs *regs) printf("kernel BUG at %s:%u!\n", bug->file, bug->line); #else - printf("kernel BUG at %p!\n", (void *)bug->bug_addr); + printf("kernel BUG at %px!\n", (void *)bug->bug_addr); #endif #endif /* CONFIG_BUG */ } @@ -2329,7 +2329,7 @@ static void dump_one_paca(int cpu) p = &paca[cpu]; - printf("paca for cpu 0x%x @ %p:\n", cpu, p); + printf("paca for cpu 0x%x @ %px:\n", cpu, p); printf(" %-*s = %s\n", 20, "possible", cpu_possible(cpu) ? "yes" : "no"); printf(" %-*s = %s\n", 20, "present", cpu_present(cpu) ? "yes" : "no"); @@ -2945,7 +2945,7 @@ static void show_task(struct task_struct *tsk) (tsk->exit_state & EXIT_DEAD) ? 'E' : (tsk->state & TASK_INTERRUPTIBLE) ? 'S' : '?'; - printf("%p %016lx %6d %6d %c %2d %s\n", tsk, + printf("%px %016lx %6d %6d %c %2d %s\n", tsk, tsk->thread.ksp, tsk->pid, tsk->parent->pid, state, task_thread_info(tsk)->cpu, @@ -2988,7 +2988,7 @@ static void show_pte(unsigned long addr) if (setjmp(bus_error_jmp) != 0) { catch_memory_errors = 0; - printf("*** Error dumping pte for task %p\n", tsk); + printf("*** Error dumping pte for task %px\n", tsk); return; } @@ -3074,7 +3074,7 @@ static void show_tasks(void) if (setjmp(bus_error_jmp) != 0) { catch_memory_errors = 0; - printf("*** Error dumping task %p\n", tsk); + printf("*** Error dumping task %px\n", tsk); return; }