From 4562c986f0d694124de20815adf7e1aad8a94668 Mon Sep 17 00:00:00 2001 From: Matthew McClintock Date: Fri, 27 Aug 2010 11:58:21 +0000 Subject: powerpc/kexec: Adds correct calling convention for kexec purgatory Call kexec purgatory code correctly. We were getting lucky before. If you examine the powerpc 32bit kexec "purgatory" code you will see it expects the following: >From kexec-tools: purgatory/arch/ppc/v2wrap_32.S -> calling convention: -> r3 = physical number of this cpu (all cpus) -> r4 = address of this chunk (master only) As such, we need to set r3 to the current core, r4 happens to be unused by purgatory at the moment but we go ahead and set it here as well Signed-off-by: Matthew McClintock Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/misc_32.S | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 6bbd7a604d24..a7a570dcdd57 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -810,6 +810,9 @@ relocate_new_kernel: isync sync + mfspr r3, SPRN_PIR /* current core we are running on */ + mr r4, r5 /* load physical address of chunk called */ + /* jump to the entry point, usually the setup routine */ mtlr r5 blrl -- cgit v1.2.3 From b0d278b7d3ae9115939ddcea93f516308cc367e2 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Tue, 10 Aug 2010 20:38:23 +0000 Subject: powerpc/perf_event: Reduce latency of calling perf_event_do_pending Commit 0fe1ac48 ("powerpc/perf_event: Fix oops due to perf_event_do_pending call") moved the call to perf_event_do_pending in timer_interrupt() down so that it was after the irq_enter() call. Unfortunately this moved it after the code that checks whether it is time for the next decrementer clock event. The result is that the call to perf_event_do_pending() won't happen until the next decrementer clock event is due. This was pointed out by Milton Miller. This fixes it by moving the check for whether it's time for the next decrementer clock event down to the point where we're about to call the event handler, after we've called perf_event_do_pending. This has the side effect that on old pre-Core99 Powermacs where we use the ppc_n_lost_interrupts mechanism to replay interrupts, a replayed interrupt will incur a little more latency since it will now do the code from the irq_enter down to the irq_exit, that it used to skip. However, these machines are now old and rare enough that this doesn't matter. To make it clear that ppc_n_lost_interrupts is only used on Powermacs, and to speed up the code slightly on non-Powermac ppc32 machines, the code that tests ppc_n_lost_interrupts is now conditional on CONFIG_PMAC as well as CONFIG_PPC32. Signed-off-by: Paul Mackerras Cc: stable@kernel.org Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/time.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index ce53dfa7130d..8533b3b83f5d 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -577,20 +577,11 @@ void timer_interrupt(struct pt_regs * regs) * some CPUs will continuue to take decrementer exceptions */ set_dec(DECREMENTER_MAX); -#ifdef CONFIG_PPC32 +#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) do_IRQ(regs); #endif - now = get_tb_or_rtc(); - if (now < decrementer->next_tb) { - /* not time for this event yet */ - now = decrementer->next_tb - now; - if (now <= DECREMENTER_MAX) - set_dec((int)now); - trace_timer_interrupt_exit(regs); - return; - } old_regs = set_irq_regs(regs); irq_enter(); @@ -606,8 +597,16 @@ void timer_interrupt(struct pt_regs * regs) get_lppaca()->int_dword.fields.decr_int = 0; #endif - if (evt->event_handler) - evt->event_handler(evt); + now = get_tb_or_rtc(); + if (now >= decrementer->next_tb) { + decrementer->next_tb = ~(u64)0; + if (evt->event_handler) + evt->event_handler(evt); + } else { + now = decrementer->next_tb - now; + if (now <= DECREMENTER_MAX) + set_dec((int)now); + } #ifdef CONFIG_PPC_ISERIES if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending()) -- cgit v1.2.3 From 54a834043314c257210db2a9d59f8cc605571639 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 25 Aug 2010 21:04:25 +0000 Subject: powerpc: Don't use kernel stack with translation off In f761622e59433130bc33ad086ce219feee9eb961 we changed early_setup_secondary so it's called using the proper kernel stack rather than the emergency one. Unfortunately, this stack pointer can't be used when translation is off on PHYP as this stack pointer might be outside the RMO. This results in the following on all non zero cpus: cpu 0x1: Vector: 300 (Data Access) at [c00000001639fd10] pc: 000000000001c50c lr: 000000000000821c sp: c00000001639ff90 msr: 8000000000001000 dar: c00000001639ffa0 dsisr: 42000000 current = 0xc000000016393540 paca = 0xc000000006e00200 pid = 0, comm = swapper The original patch was only tested on bare metal system, so it never caught this problem. This changes __secondary_start so that we calculate the new stack pointer but only start using it after we've called early_setup_secondary. With this patch, the above problem goes away. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/head_64.S | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4d6681dce816..c571cd3c1453 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -575,13 +575,19 @@ __secondary_start: /* Initialize the kernel stack. Just a repeat for iSeries. */ LOAD_REG_ADDR(r3, current_set) sldi r28,r24,3 /* get current_set[cpu#] */ - ldx r1,r3,r28 - addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD - std r1,PACAKSAVE(r13) + ldx r14,r3,r28 + addi r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD + std r14,PACAKSAVE(r13) /* Do early setup for that CPU (stab, slb, hash table pointer) */ bl .early_setup_secondary + /* + * setup the new stack pointer, but *don't* use this until + * translation is on. + */ + mr r1, r14 + /* Clear backchain so we get nice backtraces */ li r7,0 mtlr r7 -- cgit v1.2.3 From 9a81c16b527528ad307843be5571111aa8d35a80 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 20 Sep 2010 21:48:57 +0100 Subject: powerpc: fix double syscall restarts Make sigreturn zero regs->trap, make do_signal() do the same on all paths. As it is, signal interrupting e.g. read() from fd 512 (== ERESTARTSYS) with another signal getting unblocked when the first handler finishes will lead to restart one insn earlier than it ought to. Same for multiple signals with in-kernel handlers interrupting that sucker at the same time. Same for multiple signals of any kind interrupting that sucker on 64bit... Signed-off-by: Al Viro Acked-by: Paul Mackerras Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/signal.c | 2 ++ arch/powerpc/kernel/signal_32.c | 3 +-- arch/powerpc/kernel/signal_64.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 7109f5b1baa8..2300426e531a 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -138,6 +138,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs) ti->local_flags &= ~_TLF_RESTORE_SIGMASK; sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } + regs->trap = 0; return 0; /* no signals delivered */ } @@ -164,6 +165,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs) ret = handle_rt_signal64(signr, &ka, &info, oldset, regs); } + regs->trap = 0; if (ret) { spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked, ¤t->blocked, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 266610119f66..b96a3a010c26 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -511,6 +511,7 @@ static long restore_user_regs(struct pt_regs *regs, if (!sig) save_r2 = (unsigned int)regs->gpr[2]; err = restore_general_regs(regs, sr); + regs->trap = 0; err |= __get_user(msr, &sr->mc_gregs[PT_MSR]); if (!sig) regs->gpr[2] = (unsigned long) save_r2; @@ -884,7 +885,6 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, regs->nip = (unsigned long) ka->sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; - regs->trap = 0; return 1; badframe: @@ -1228,7 +1228,6 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, regs->nip = (unsigned long) ka->sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; - regs->trap = 0; return 1; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2fe6fc64b614..27c4a4584f80 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -178,7 +178,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, err |= __get_user(regs->xer, &sc->gp_regs[PT_XER]); err |= __get_user(regs->ccr, &sc->gp_regs[PT_CCR]); /* skip SOFTE */ - err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]); + regs->trap = 0; err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]); err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]); err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]); -- cgit v1.2.3 From 5336377d6225959624146629ce3fc88ee8ecda3d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 5 Oct 2010 11:29:27 -0700 Subject: modules: Fix module_bug_list list corruption race With all the recent module loading cleanups, we've minimized the code that sits under module_mutex, fixing various deadlocks and making it possible to do most of the module loading in parallel. However, that whole conversion totally missed the rather obscure code that adds a new module to the list for BUG() handling. That code was doubly obscure because (a) the code itself lives in lib/bugs.c (for dubious reasons) and (b) it gets called from the architecture-specific "module_finalize()" rather than from generic code. Calling it from arch-specific code makes no sense what-so-ever to begin with, and is now actively wrong since that code isn't protected by the module loading lock any more. So this commit moves the "module_bug_{finalize,cleanup}()" calls away from the arch-specific code, and into the generic code - and in the process protects it with the module_mutex so that the list operations are now safe. Future fixups: - move the module list handling code into kernel/module.c where it belongs. - get rid of 'module_bug_list' and just use the regular list of modules (called 'modules' - imagine that) that we already create and maintain for other reasons. Reported-and-tested-by: Thomas Gleixner Cc: Rusty Russell Cc: Adrian Bunk Cc: Andrew Morton Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- arch/avr32/kernel/module.c | 3 +-- arch/h8300/kernel/module.c | 3 +-- arch/mn10300/kernel/module.c | 3 +-- arch/parisc/kernel/module.c | 3 +-- arch/powerpc/kernel/module.c | 5 ----- arch/s390/kernel/module.c | 3 +-- arch/sh/kernel/module.c | 2 -- arch/x86/kernel/module.c | 3 +-- include/linux/module.h | 5 ++--- kernel/module.c | 4 ++++ lib/bug.c | 6 ++---- 11 files changed, 14 insertions(+), 26 deletions(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 98f94d041d9c..a727f54d64d6 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -314,10 +314,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, vfree(module->arch.syminfo); module->arch.syminfo = NULL; - return module_bug_finalize(hdr, sechdrs, module); + return 0; } void module_arch_cleanup(struct module *module) { - module_bug_cleanup(module); } diff --git a/arch/h8300/kernel/module.c b/arch/h8300/kernel/module.c index 0865e291c20d..db4953dc4e1b 100644 --- a/arch/h8300/kernel/module.c +++ b/arch/h8300/kernel/module.c @@ -112,10 +112,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/mn10300/kernel/module.c b/arch/mn10300/kernel/module.c index 6aea7fd76993..196a111e2e29 100644 --- a/arch/mn10300/kernel/module.c +++ b/arch/mn10300/kernel/module.c @@ -206,7 +206,7 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { - return module_bug_finalize(hdr, sechdrs, me); + return 0; } /* @@ -214,5 +214,4 @@ int module_finalize(const Elf_Ehdr *hdr, */ void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 159a2b81e90c..6e81bb596e5b 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -941,11 +941,10 @@ int module_finalize(const Elf_Ehdr *hdr, nsyms = newptr - (Elf_Sym *)symhdr->sh_addr; DEBUGP("NEW num_symtab %lu\n", nsyms); symhdr->sh_size = nsyms * sizeof(Elf_Sym); - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { deregister_unwind_table(mod); - module_bug_cleanup(mod); } diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 477c663e0140..4ef93ae2235f 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -65,10 +65,6 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sect; int err; - err = module_bug_finalize(hdr, sechdrs, me); - if (err) - return err; - /* Apply feature fixups */ sect = find_section(hdr, sechdrs, "__ftr_fixup"); if (sect != NULL) @@ -101,5 +97,4 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 22cfd634c355..f7167ee4604c 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -407,10 +407,9 @@ int module_finalize(const Elf_Ehdr *hdr, { vfree(me->arch.syminfo); me->arch.syminfo = NULL; - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/sh/kernel/module.c b/arch/sh/kernel/module.c index 43adddfe4c04..ae0be697a89e 100644 --- a/arch/sh/kernel/module.c +++ b/arch/sh/kernel/module.c @@ -149,13 +149,11 @@ int module_finalize(const Elf_Ehdr *hdr, int ret = 0; ret |= module_dwarf_finalize(hdr, sechdrs, me); - ret |= module_bug_finalize(hdr, sechdrs, me); return ret; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); module_dwarf_cleanup(mod); } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index e0bc186d7501..1c355c550960 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -239,11 +239,10 @@ int module_finalize(const Elf_Ehdr *hdr, apply_paravirt(pseg, pseg + para->sh_size); } - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { alternatives_smp_module_del(mod); - module_bug_cleanup(mod); } diff --git a/include/linux/module.h b/include/linux/module.h index 8a6b9fdc7ffa..aace066bad8f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -686,17 +686,16 @@ extern int module_sysfs_initialized; #ifdef CONFIG_GENERIC_BUG -int module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, +void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, struct module *); void module_bug_cleanup(struct module *); #else /* !CONFIG_GENERIC_BUG */ -static inline int module_bug_finalize(const Elf_Ehdr *hdr, +static inline void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { - return 0; } static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ diff --git a/kernel/module.c b/kernel/module.c index d0b5f8db11b4..ccd641991842 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1537,6 +1537,7 @@ static int __unlink_module(void *_mod) { struct module *mod = _mod; list_del(&mod->list); + module_bug_cleanup(mod); return 0; } @@ -2625,6 +2626,7 @@ static struct module *load_module(void __user *umod, if (err < 0) goto ddebug; + module_bug_finalize(info.hdr, info.sechdrs, mod); list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); @@ -2650,6 +2652,8 @@ static struct module *load_module(void __user *umod, mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); + module_bug_cleanup(mod); + ddebug: if (!mod->taints) dynamic_debug_remove(info.debug); diff --git a/lib/bug.c b/lib/bug.c index 7cdfad88128f..19552096d16b 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -72,8 +72,8 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr) return NULL; } -int module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, - struct module *mod) +void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, + struct module *mod) { char *secstrings; unsigned int i; @@ -97,8 +97,6 @@ int module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, * could potentially lead to deadlock and thus be counter-productive. */ list_add(&mod->bug_list, &module_bug_list); - - return 0; } void module_bug_cleanup(struct module *mod) -- cgit v1.2.3 From 7c6d45e665d5322401e4439060bbf758b08422d4 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 6 Oct 2010 11:06:44 +1100 Subject: powerpc: remove unused variable Since powerpc uses -Werror on arch powerpc, the build was broken like this: cc1: warnings being treated as errors arch/powerpc/kernel/module.c: In function 'module_finalize': arch/powerpc/kernel/module.c:66: error: unused variable 'err' Signed-off-by: Stephen Rothwell Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/module.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/kernel') diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 4ef93ae2235f..49cee9df225b 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -63,7 +63,6 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { const Elf_Shdr *sect; - int err; /* Apply feature fixups */ sect = find_section(hdr, sechdrs, "__ftr_fixup"); -- cgit v1.2.3