From 749a0278c2177b2d16da5d8b135ba7f940bb4199 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 13 Jun 2018 23:23:56 +1000 Subject: powerpc/64s: Fix DT CPU features Power9 DD2.1 logic In the device tree CPU features quirk code we want to set CPU_FTR_POWER9_DD2_1 on all Power9s that aren't DD2.0 or earlier. But we got the logic wrong and instead set it on all CPUs that aren't Power9 DD2.0 or earlier, ie. including Power8. Fix it by making sure we're on a Power9. This isn't a bug in practice because the only code that checks the feature is Power9 only to begin with. But we'll backport it anyway to avoid confusion. Fixes: 9e9626ed3a4a ("powerpc/64s: Fix POWER9 DD2.2 and above in DT CPU features") Cc: stable@vger.kernel.org # v4.17+ Reported-by: Paul Mackerras Signed-off-by: Michael Ellerman Acked-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/dt_cpu_ftrs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 4be1c0de9406..96dd3d871986 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -711,7 +711,8 @@ static __init void cpufeatures_cpu_quirks(void) cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST; cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG; cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; - } else /* DD2.1 and up have DD2_1 */ + } else if ((version & 0xffff0000) == 0x004e0000) + /* DD2.1 and up have DD2_1 */ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; if ((version & 0xffff0000) == 0x004e0000) { -- cgit v1.2.3 From 8c1aef6a682f87a059f10ab606cc1e2cdd663d5a Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 19 May 2018 14:35:52 +1000 Subject: powerpc/64: hard disable irqs in panic_smp_self_stop Similarly to commit 855bfe0de1 ("powerpc: hard disable irqs in smp_send_stop loop"), irqs should be hard disabled by panic_smp_self_stop. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/setup_64.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 7a7ce8ad455e..225bc5f91049 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -387,6 +387,14 @@ void early_setup_secondary(void) #endif /* CONFIG_SMP */ +void panic_smp_self_stop(void) +{ + hard_irq_disable(); + spin_begin(); + while (1) + spin_cpu_relax(); +} + #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) static bool use_spinloop(void) { -- cgit v1.2.3 From de6e5d38417e6cdb005843db420a2974993d36ff Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 19 May 2018 14:35:53 +1000 Subject: powerpc: smp_send_stop do not offline stopped CPUs Marking CPUs stopped by smp_send_stop as offline can cause warnings due to cross-CPU wakeups. This trace was noticed on a busy system running a sysrq+c crash test, after the injected crash: WARNING: CPU: 51 PID: 1546 at kernel/sched/core.c:1179 set_task_cpu+0x22c/0x240 CPU: 51 PID: 1546 Comm: kworker/u352:1 Tainted: G D Workqueue: mlx5e mlx5e_update_stats_work [mlx5_core] [...] NIP [c00000000017c21c] set_task_cpu+0x22c/0x240 LR [c00000000017d580] try_to_wake_up+0x230/0x720 Call Trace: [c000000001017700] runqueues+0x0/0xb00 (unreliable) [c00000000017d580] try_to_wake_up+0x230/0x720 [c00000000015a214] insert_work+0x104/0x140 [c00000000015adb0] __queue_work+0x230/0x690 [c000003fc5007910] [c00000000015b26c] queue_work_on+0x5c/0x90 [c0080000135fc8f8] mlx5_cmd_exec+0x538/0xcb0 [mlx5_core] [c008000013608fd0] mlx5_core_access_reg+0x140/0x1d0 [mlx5_core] [c00800001362777c] mlx5e_update_pport_counters.constprop.59+0x6c/0x90 [mlx5_core] [c008000013628868] mlx5e_update_ndo_stats+0x28/0x90 [mlx5_core] [c008000013625558] mlx5e_update_stats_work+0x68/0xb0 [mlx5_core] [c00000000015bcec] process_one_work+0x1bc/0x5f0 [c00000000015ecac] worker_thread+0xac/0x6b0 [c000000000168338] kthread+0x168/0x1b0 [c00000000000b628] ret_from_kernel_thread+0x5c/0xb4 This happens because firstly the CPU is not really offline in the usual sense, processes and interrupts have not been migrated away. Secondly smp_send_stop does not happen atomically on all CPUs, so one CPU can have marked itself offline, while another CPU is still running processes or interrupts which can affect the first CPU. Fix this by just not marking the CPU as offline. It's more like frozen in time, so offline does not really reflect its state properly anyway. There should be nothing in the crash/panic path that walks online CPUs and synchronously waits for them, so this change should not introduce new hangs. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/smp.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5eadfffabe35..4794d6b4f4d2 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -600,9 +600,6 @@ static void nmi_stop_this_cpu(struct pt_regs *regs) nmi_ipi_busy_count--; nmi_ipi_unlock(); - /* Remove this CPU */ - set_cpu_online(smp_processor_id(), false); - spin_begin(); while (1) spin_cpu_relax(); @@ -617,9 +614,6 @@ void smp_send_stop(void) static void stop_this_cpu(void *dummy) { - /* Remove this CPU */ - set_cpu_online(smp_processor_id(), false); - hard_irq_disable(); spin_begin(); while (1) -- cgit v1.2.3 From 855b6232dda2b6941ecd22979893e8a1d25642db Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 19 May 2018 14:35:54 +1000 Subject: powerpc/64: hard disable irqs on the panic()ing CPU Similar to previous patches, hard disable interrupts when a CPU is in panic. This reduces the chance the watchdog has to interfere with the panic, and avoids any other type of masked interrupt being executed when crashing which minimises the length of the crash path. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/setup-common.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 62b1a40d8957..40b44bb53a4e 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -700,12 +700,19 @@ EXPORT_SYMBOL(check_legacy_ioport); static int ppc_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { + /* + * panic does a local_irq_disable, but we really + * want interrupts to be hard disabled. + */ + hard_irq_disable(); + /* * 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 */ + if (ppc_md.panic) + ppc_md.panic(ptr); /* May not return */ return NOTIFY_DONE; } @@ -716,7 +723,8 @@ static struct notifier_block ppc_panic_block = { void __init setup_panic(void) { - if (!ppc_md.panic) + /* PPC64 always does a hard irq disable in its panic handler */ + if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic) return; atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); } -- cgit v1.2.3 From e08ecba17b72aeb01859601bc242a5bc48620109 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 19 Jun 2018 21:51:55 +1000 Subject: powerpc/64s: Fix build failures with CONFIG_NMI_IPI=n I broke the build when CONFIG_NMI_IPI=n with my recent commit to add arch_trigger_cpumask_backtrace(), eg: stacktrace.c:(.text+0x1b0): undefined reference to `.smp_send_safe_nmi_ipi' We should rework the CONFIG symbols here in future to avoid these double barrelled ifdefs but for now they fix the build. Fixes: 5cc05910f26e ("powerpc/64s: Wire up arch_trigger_cpumask_backtrace()") Reported-by: Christophe LEROY Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/nmi.h | 2 +- arch/powerpc/kernel/stacktrace.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index 0f571e0ebca1..bd9ba8defd72 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -8,7 +8,7 @@ extern void arch_touch_nmi_watchdog(void); static inline void arch_touch_nmi_watchdog(void) {} #endif -#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_STACKTRACE) +#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE) extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 07e97f289c52..e2c50b55138f 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -196,7 +196,7 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable); #endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */ -#ifdef CONFIG_PPC_BOOK3S_64 +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) static void handle_backtrace_ipi(struct pt_regs *regs) { nmi_cpu_backtrace(regs); @@ -242,4 +242,4 @@ void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); } -#endif /* CONFIG_PPC64 */ +#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */ -- cgit v1.2.3 From 784e0300fe9fe4aa81bd7df9d59e138f56bb605b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 22 Jun 2018 11:45:07 +0100 Subject: rseq: Avoid infinite recursion when delivering SIGSEGV When delivering a signal to a task that is using rseq, we call into __rseq_handle_notify_resume() so that the registers pushed in the sigframe are updated to reflect the state of the restartable sequence (for example, ensuring that the signal returns to the abort handler if necessary). However, if the rseq management fails due to an unrecoverable fault when accessing userspace or certain combinations of RSEQ_CS_* flags, then we will attempt to deliver a SIGSEGV. This has the potential for infinite recursion if the rseq code continuously fails on signal delivery. Avoid this problem by using force_sigsegv() instead of force_sig(), which is explicitly designed to reset the SEGV handler to SIG_DFL in the case of a recursive fault. In doing so, remove rseq_signal_deliver() from the internal rseq API and have an optional struct ksignal * parameter to rseq_handle_notify_resume() instead. Signed-off-by: Will Deacon Signed-off-by: Thomas Gleixner Acked-by: Mathieu Desnoyers Cc: peterz@infradead.org Cc: paulmck@linux.vnet.ibm.com Cc: boqun.feng@gmail.com Link: https://lkml.kernel.org/r/1529664307-983-1-git-send-email-will.deacon@arm.com --- arch/arm/kernel/signal.c | 4 ++-- arch/powerpc/kernel/signal.c | 4 ++-- arch/x86/entry/common.c | 2 +- arch/x86/kernel/signal.c | 2 +- include/linux/sched.h | 18 +++++++++++------- kernel/rseq.c | 7 ++++--- 6 files changed, 21 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index f09e9d66d605..dec130e7078c 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -544,7 +544,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) * Increment event counter and perform fixup for the pre-signal * frame. */ - rseq_signal_deliver(regs); + rseq_signal_deliver(ksig, regs); /* * Set up the stack frame @@ -666,7 +666,7 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) } else { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } } local_irq_disable(); diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 17fe4339ba59..b3e8db376ecd 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -134,7 +134,7 @@ static void do_signal(struct task_struct *tsk) /* Re-enable the breakpoints for the signal stack */ thread_change_pc(tsk, tsk->thread.regs); - rseq_signal_deliver(tsk->thread.regs); + rseq_signal_deliver(&ksig, tsk->thread.regs); if (is32) { if (ksig.ka.sa.sa_flags & SA_SIGINFO) @@ -170,7 +170,7 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } user_enter(); diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 92190879b228..3b2490b81918 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -164,7 +164,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) if (cached_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(NULL, regs); } if (cached_flags & _TIF_USER_RETURN_NOTIFY) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 445ca11ff863..92a3b312a53c 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -692,7 +692,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) * Increment event counter and perform fixup for the pre-signal * frame. */ - rseq_signal_deliver(regs); + rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ if (is_ia32_frame(ksig)) { diff --git a/include/linux/sched.h b/include/linux/sched.h index c1882643d455..9256118bd40c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1799,20 +1799,22 @@ static inline void rseq_set_notify_resume(struct task_struct *t) set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } -void __rseq_handle_notify_resume(struct pt_regs *regs); +void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); -static inline void rseq_handle_notify_resume(struct pt_regs *regs) +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) { if (current->rseq) - __rseq_handle_notify_resume(regs); + __rseq_handle_notify_resume(ksig, regs); } -static inline void rseq_signal_deliver(struct pt_regs *regs) +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) { preempt_disable(); __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); preempt_enable(); - rseq_handle_notify_resume(regs); + rseq_handle_notify_resume(ksig, regs); } /* rseq_preempt() requires preemption to be disabled. */ @@ -1861,10 +1863,12 @@ static inline void rseq_execve(struct task_struct *t) static inline void rseq_set_notify_resume(struct task_struct *t) { } -static inline void rseq_handle_notify_resume(struct pt_regs *regs) +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) { } -static inline void rseq_signal_deliver(struct pt_regs *regs) +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) { } static inline void rseq_preempt(struct task_struct *t) diff --git a/kernel/rseq.c b/kernel/rseq.c index ae306f90c514..22b6acf1ad63 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -251,10 +251,10 @@ static int rseq_ip_fixup(struct pt_regs *regs) * respect to other threads scheduled on the same CPU, and with respect * to signal handlers. */ -void __rseq_handle_notify_resume(struct pt_regs *regs) +void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { struct task_struct *t = current; - int ret; + int ret, sig; if (unlikely(t->flags & PF_EXITING)) return; @@ -268,7 +268,8 @@ void __rseq_handle_notify_resume(struct pt_regs *regs) return; error: - force_sig(SIGSEGV, t); + sig = ksig ? ksig->sig : 0; + force_sigsegv(sig, t); } #ifdef CONFIG_DEBUG_RSEQ -- cgit v1.2.3 From ac8517440344dbe598f7c1c23e686c800b563061 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Tue, 19 Jun 2018 13:14:58 -0700 Subject: powerpc: Remove -Wattribute-alias pragmas With SYSCALL_DEFINEx() disabling -Wattribute-alias generically, there's no need to duplicate that for PowerPC syscalls. This reverts commit 415520373975 ("powerpc: fix build failure by disabling attribute-alias warning in pci_32") and commit 2479bfc9bc60 ("powerpc: Fix build by disabling attribute-alias warning for SYSCALL_DEFINEx"). Signed-off-by: Paul Burton Acked-by: Christophe Leroy Acked-by: Michael Ellerman Signed-off-by: Masahiro Yamada --- arch/powerpc/kernel/pci_32.c | 4 ---- arch/powerpc/kernel/pci_64.c | 4 ---- arch/powerpc/kernel/rtas.c | 4 ---- arch/powerpc/kernel/signal_32.c | 8 -------- arch/powerpc/kernel/signal_64.c | 4 ---- arch/powerpc/kernel/syscalls.c | 4 ---- arch/powerpc/mm/subpage-prot.c | 4 ---- 7 files changed, 32 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 4f861055a852..d63b488d34d7 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -285,9 +285,6 @@ pci_bus_to_hose(int bus) * Note that the returned IO or memory base is a physical address */ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpragmas" -#pragma GCC diagnostic ignored "-Wattribute-alias" SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, bus, unsigned long, devfn) { @@ -313,4 +310,3 @@ SYSCALL_DEFINE3(pciconfig_iobase, long, which, return result; } -#pragma GCC diagnostic pop diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 812171c09f42..dff28f903512 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -203,9 +203,6 @@ void pcibios_setup_phb_io_space(struct pci_controller *hose) #define IOBASE_ISA_IO 3 #define IOBASE_ISA_MEM 4 -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpragmas" -#pragma GCC diagnostic ignored "-Wattribute-alias" SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus, unsigned long, in_devfn) { @@ -259,7 +256,6 @@ SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, in_bus, return -EOPNOTSUPP; } -#pragma GCC diagnostic pop #ifdef CONFIG_NUMA int pcibus_to_node(struct pci_bus *bus) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 7fb9f83dcde8..8afd146bc9c7 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1051,9 +1051,6 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, } /* We assume to be passed big endian arguments */ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpragmas" -#pragma GCC diagnostic ignored "-Wattribute-alias" SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) { struct rtas_args args; @@ -1140,7 +1137,6 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) return 0; } -#pragma GCC diagnostic pop /* * Call early during boot, before mem init, to retrieve the RTAS diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 5eedbb282d42..e6474a45cef5 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1038,9 +1038,6 @@ static int do_setcontext_tm(struct ucontext __user *ucp, } #endif -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpragmas" -#pragma GCC diagnostic ignored "-Wattribute-alias" #ifdef CONFIG_PPC64 COMPAT_SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, struct ucontext __user *, new_ctx, int, ctx_size) @@ -1134,7 +1131,6 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, set_thread_flag(TIF_RESTOREALL); return 0; } -#pragma GCC diagnostic pop #ifdef CONFIG_PPC64 COMPAT_SYSCALL_DEFINE0(rt_sigreturn) @@ -1231,9 +1227,6 @@ SYSCALL_DEFINE0(rt_sigreturn) return 0; } -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpragmas" -#pragma GCC diagnostic ignored "-Wattribute-alias" #ifdef CONFIG_PPC32 SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx, int, ndbg, struct sig_dbg_op __user *, dbg) @@ -1337,7 +1330,6 @@ SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx, return 0; } #endif -#pragma GCC diagnostic pop /* * OK, we're invoking a handler diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index d42b60020389..83d51bf586c7 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -625,9 +625,6 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp) /* * Handle {get,set,swap}_context operations */ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpragmas" -#pragma GCC diagnostic ignored "-Wattribute-alias" SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, struct ucontext __user *, new_ctx, long, ctx_size) { @@ -693,7 +690,6 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, set_thread_flag(TIF_RESTOREALL); return 0; } -#pragma GCC diagnostic pop /* diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 083fa06962fd..466216506eb2 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -62,9 +62,6 @@ out: return ret; } -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpragmas" -#pragma GCC diagnostic ignored "-Wattribute-alias" SYSCALL_DEFINE6(mmap2, unsigned long, addr, size_t, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) @@ -78,7 +75,6 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, { return do_mmap2(addr, len, prot, flags, fd, offset, PAGE_SHIFT); } -#pragma GCC diagnostic pop #ifdef CONFIG_PPC32 /* diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index 75cb646a79c3..9d16ee251fc0 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -186,9 +186,6 @@ static void subpage_mark_vma_nohuge(struct mm_struct *mm, unsigned long addr, * in a 2-bit field won't allow writes to a page that is otherwise * write-protected. */ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wpragmas" -#pragma GCC diagnostic ignored "-Wattribute-alias" SYSCALL_DEFINE3(subpage_prot, unsigned long, addr, unsigned long, len, u32 __user *, map) { @@ -272,4 +269,3 @@ SYSCALL_DEFINE3(subpage_prot, unsigned long, addr, up_write(&mm->mmap_sem); return err; } -#pragma GCC diagnostic pop -- cgit v1.2.3 From b03897cf318dfc47de33a7ecbc7655584266f034 Mon Sep 17 00:00:00 2001 From: "Gautham R. Shenoy" Date: Wed, 18 Jul 2018 14:03:16 +0530 Subject: powerpc/powernv: Fix save/restore of SPRG3 on entry/exit from stop (idle) On 64-bit servers, SPRN_SPRG3 and its userspace read-only mirror SPRN_USPRG3 are used as userspace VDSO write and read registers respectively. SPRN_SPRG3 is lost when we enter stop4 and above, and is currently not restored. As a result, any read from SPRN_USPRG3 returns zero on an exit from stop4 (Power9 only) and above. Thus in this situation, on POWER9, any call from sched_getcpu() always returns zero, as on powerpc, we call __kernel_getcpu() which relies upon SPRN_USPRG3 to report the CPU and NUMA node information. Fix this by restoring SPRN_SPRG3 on wake up from a deep stop state with the sprg_vdso value that is cached in PACA. Fixes: e1c1cfed5432 ("powerpc/powernv: Save/Restore additional SPRs for stop4 cpuidle") Cc: stable@vger.kernel.org # v4.14+ Reported-by: Florian Weimer Signed-off-by: Gautham R. Shenoy Reviewed-by: Michael Ellerman Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/idle_book3s.S | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index e734f6e45abc..689306118b48 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -144,7 +144,9 @@ power9_restore_additional_sprs: mtspr SPRN_MMCR1, r4 ld r3, STOP_MMCR2(r13) + ld r4, PACA_SPRG_VDSO(r13) mtspr SPRN_MMCR2, r3 + mtspr SPRN_SPRG3, r4 blr /* -- cgit v1.2.3 From 44bda4b7d26e9fffed6d7152d98a2e9edaeb2a76 Mon Sep 17 00:00:00 2001 From: Hari Vyas Date: Tue, 3 Jul 2018 14:35:41 +0530 Subject: PCI: Fix is_added/is_busmaster race condition When a PCI device is detected, pdev->is_added is set to 1 and proc and sysfs entries are created. When the device is removed, pdev->is_added is checked for one and then device is detached with clearing of proc and sys entries and at end, pdev->is_added is set to 0. is_added and is_busmaster are bit fields in pci_dev structure sharing same memory location. A strange issue was observed with multiple removal and rescan of a PCIe NVMe device using sysfs commands where is_added flag was observed as zero instead of one while removing device and proc,sys entries are not cleared. This causes issue in later device addition with warning message "proc_dir_entry" already registered. Debugging revealed a race condition between the PCI core setting the is_added bit in pci_bus_add_device() and the NVMe driver reset work-queue setting the is_busmaster bit in pci_set_master(). As these fields are not handled atomically, that clears the is_added bit. Move the is_added bit to a separate private flag variable and use atomic functions to set and retrieve the device addition state. This avoids the race because is_added no longer shares a memory location with is_busmaster. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200283 Signed-off-by: Hari Vyas Signed-off-by: Bjorn Helgaas Reviewed-by: Lukas Wunner Acked-by: Michael Ellerman --- arch/powerpc/kernel/pci-common.c | 4 +++- arch/powerpc/platforms/powernv/pci-ioda.c | 3 ++- arch/powerpc/platforms/pseries/setup.c | 3 ++- drivers/pci/bus.c | 6 +++--- drivers/pci/hotplug/acpiphp_glue.c | 2 +- drivers/pci/pci.h | 11 +++++++++++ drivers/pci/probe.c | 4 ++-- drivers/pci/remove.c | 5 +++-- include/linux/pci.h | 1 - 9 files changed, 27 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index fe9733ffffaa..471aac313b89 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -42,6 +42,8 @@ #include #include +#include "../../../drivers/pci/pci.h" + /* hose_spinlock protects accesses to the the phb_bitmap. */ static DEFINE_SPINLOCK(hose_spinlock); LIST_HEAD(hose_list); @@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) /* Cardbus can call us to add new devices to a bus, so ignore * those who are already fully discovered */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pcibios_setup_device(dev); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 5bd0eb6681bc..70b2e1e0f23c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -46,6 +46,7 @@ #include "powernv.h" #include "pci.h" +#include "../../../../drivers/pci/pci.h" #define PNV_IODA1_M64_NUM 16 /* Number of M64 BARs */ #define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */ @@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) struct pci_dn *pdn; int mul, total_vfs; - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; pdn = pci_get_pdn(pdev); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 139f0af6c3d9..8a4868a3964b 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -71,6 +71,7 @@ #include #include "pseries.h" +#include "../../../../drivers/pci/pci.h" int CMO_PrPSP = -1; int CMO_SecPSP = -1; @@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev) const int *indexes; struct device_node *dn = pci_device_to_OF_node(pdev); - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; /*Firmware must support open sriov otherwise dont configure*/ indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL); diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 35b7fc87eac5..5cb40b2518f9 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -330,7 +330,7 @@ void pci_bus_add_device(struct pci_dev *dev) return; } - dev->is_added = 1; + pci_dev_assign_added(dev, true); } EXPORT_SYMBOL_GPL(pci_bus_add_device); @@ -347,14 +347,14 @@ void pci_bus_add_devices(const struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip already-added devices */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pci_bus_add_device(dev); } list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip if device attach failed */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) continue; child = dev->subordinate; if (child) diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 3a17b290df5d..ef0b1b6ba86f 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -509,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot) list_for_each_entry(dev, &bus->devices, bus_list) { /* Assume that newly added devices are powered on already. */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) dev->current_state = PCI_D0; } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 882f1f9596df..08817253c8a2 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -288,6 +288,7 @@ struct pci_sriov { /* pci_dev priv_flags */ #define PCI_DEV_DISCONNECTED 0 +#define PCI_DEV_ADDED 1 static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) { @@ -300,6 +301,16 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags); } +static inline void pci_dev_assign_added(struct pci_dev *dev, bool added) +{ + assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added); +} + +static inline bool pci_dev_is_added(const struct pci_dev *dev) +{ + return test_bit(PCI_DEV_ADDED, &dev->priv_flags); +} + #ifdef CONFIG_PCI_ATS void pci_restore_ats_state(struct pci_dev *dev); #else diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ac876e32de4b..611adcd9c169 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2433,13 +2433,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) dev = pci_scan_single_device(bus, devfn); if (!dev) return 0; - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; dev->multifunction = 1; } diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 6f072eae4f7a..5e3d0dced2b8 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -19,11 +19,12 @@ static void pci_stop_dev(struct pci_dev *dev) { pci_pme_active(dev, false); - if (dev->is_added) { + if (pci_dev_is_added(dev)) { device_release_driver(&dev->dev); pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); - dev->is_added = 0; + + pci_dev_assign_added(dev, false); } if (dev->bus->self) diff --git a/include/linux/pci.h b/include/linux/pci.h index abd5d5e17aee..c133ccfa002e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -368,7 +368,6 @@ struct pci_dev { unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int multifunction:1; /* Multi-function device */ - unsigned int is_added:1; unsigned int is_busmaster:1; /* Is busmaster */ unsigned int no_msi:1; /* May not use MSI */ unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ -- cgit v1.2.3