diff --git a/arch/ia64/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S index 687e5fdc9683..99b665e2b1d5 100644 --- a/arch/ia64/ia32/ia32_entry.S +++ b/arch/ia64/ia32/ia32_entry.S @@ -52,43 +52,6 @@ ENTRY(ia32_clone) br.ret.sptk.many rp END(ia32_clone) -ENTRY(sys32_rt_sigsuspend) - .prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(8) - alloc loc1=ar.pfs,8,2,3,0 // preserve all eight input regs - mov loc0=rp - mov out0=in0 // mask - mov out1=in1 // sigsetsize - mov out2=sp // out2 = &sigscratch - .fframe 16 - adds sp=-16,sp // allocate dummy "sigscratch" - ;; - .body - br.call.sptk.many rp=ia32_rt_sigsuspend -1: .restore sp - adds sp=16,sp - mov rp=loc0 - mov ar.pfs=loc1 - br.ret.sptk.many rp -END(sys32_rt_sigsuspend) - -ENTRY(sys32_sigsuspend) - .prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(8) - alloc loc1=ar.pfs,8,2,3,0 // preserve all eight input regs - mov loc0=rp - mov out0=in2 // mask (first two args are ignored) - ;; - mov out1=sp // out1 = &sigscratch - .fframe 16 - adds sp=-16,sp // allocate dummy "sigscratch" - .body - br.call.sptk.many rp=ia32_sigsuspend -1: .restore sp - adds sp=16,sp - mov rp=loc0 - mov ar.pfs=loc1 - br.ret.sptk.many rp -END(sys32_sigsuspend) - GLOBAL_ENTRY(ia32_ret_from_clone) PT_REGS_UNWIND_INFO(0) { /* @@ -389,7 +352,7 @@ ia32_syscall_table: data8 sys_rt_sigpending data8 compat_sys_rt_sigtimedwait data8 sys32_rt_sigqueueinfo - data8 sys32_rt_sigsuspend + data8 compat_sys_rt_sigsuspend data8 sys32_pread /* 180 */ data8 sys32_pwrite data8 sys_chown /* 16-bit version */ diff --git a/arch/ia64/ia32/ia32_signal.c b/arch/ia64/ia32/ia32_signal.c index 10510e585204..85e82f32e480 100644 --- a/arch/ia64/ia32/ia32_signal.c +++ b/arch/ia64/ia32/ia32_signal.c @@ -451,59 +451,20 @@ sigact_set_handler (struct k_sigaction *sa, unsigned int handler, unsigned int r sa->sa.sa_handler = (__sighandler_t) (((unsigned long) restorer << 32) | handler); } -long -__ia32_rt_sigsuspend (compat_sigset_t *sset, unsigned int sigsetsize, struct sigscratch *scr) +asmlinkage long +sys32_sigsuspend (int history0, int history1, old_sigset_t mask) { - extern long ia64_do_signal (sigset_t *oldset, struct sigscratch *scr, long in_syscall); - sigset_t oldset, set; - - scr->scratch_unat = 0; /* avoid leaking kernel bits to user level */ - memset(&set, 0, sizeof(set)); - - memcpy(&set.sig, &sset->sig, sigsetsize); - - sigdelsetmask(&set, ~_BLOCKABLE); - + mask &= _BLOCKABLE; spin_lock_irq(¤t->sighand->siglock); - { - oldset = current->blocked; - current->blocked = set; - recalc_sigpending(); - } + current->saved_sigmask = current->blocked; + siginitset(¤t->blocked, mask); + recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - /* - * The return below usually returns to the signal handler. We need to pre-set the - * correct error code here to ensure that the right values get saved in sigcontext - * by ia64_do_signal. - */ - scr->pt.r8 = -EINTR; - while (1) { - current->state = TASK_INTERRUPTIBLE; - schedule(); - if (ia64_do_signal(&oldset, scr, 1)) - return -EINTR; - } -} - -asmlinkage long -ia32_rt_sigsuspend (compat_sigset_t __user *uset, unsigned int sigsetsize, struct sigscratch *scr) -{ - compat_sigset_t set; - - if (sigsetsize > sizeof(compat_sigset_t)) - return -EINVAL; - - if (copy_from_user(&set.sig, &uset->sig, sigsetsize)) - return -EFAULT; - - return __ia32_rt_sigsuspend(&set, sigsetsize, scr); -} - -asmlinkage long -ia32_sigsuspend (unsigned int mask, struct sigscratch *scr) -{ - return __ia32_rt_sigsuspend((compat_sigset_t *) &mask, sizeof(mask), scr); + current->state = TASK_INTERRUPTIBLE; + schedule(); + set_thread_flag(TIF_RESTORE_SIGMASK); + return -ERESTARTNOHAND; } asmlinkage long @@ -810,7 +771,11 @@ get_sigframe (struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) } /* Legacy stack switching not supported */ - return (void __user *)((esp - frame_size) & -8ul); + esp -= frame_size; + /* Align the stack pointer according to the i386 ABI, + * i.e. so that on function entry ((sp + 4) & 15) == 0. */ + esp = ((esp + 4) & -16ul) - 4; + return (void __user *) esp; } static int diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index 55fd2d5471e1..b50bf208678e 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1199,32 +1199,6 @@ ENTRY(notify_resume_user) br.ret.sptk.many rp END(notify_resume_user) -GLOBAL_ENTRY(sys_rt_sigsuspend) - .prologue ASM_UNW_PRLG_RP|ASM_UNW_PRLG_PFS, ASM_UNW_PRLG_GRSAVE(8) - alloc loc1=ar.pfs,8,2,3,0 // preserve all eight input regs in case of syscall restart! - mov r9=ar.unat - mov loc0=rp // save return address - mov out0=in0 // mask - mov out1=in1 // sigsetsize - adds out2=8,sp // out2=&sigscratch->ar_pfs - ;; - .fframe 16 - .spillsp ar.unat, 16 - st8 [sp]=r9,-16 // allocate space for ar.unat and save it - st8 [out2]=loc1,-8 // save ar.pfs, out2=&sigscratch - .body - br.call.sptk.many rp=ia64_rt_sigsuspend -.ret17: .restore sp - adds sp=16,sp // pop scratch stack space - ;; - ld8 r9=[sp] // load new unat from sw->caller_unat - mov rp=loc0 - ;; - mov ar.unat=r9 - mov ar.pfs=loc1 - br.ret.sptk.many rp -END(sys_rt_sigsuspend) - ENTRY(sys_rt_sigreturn) PT_REGS_UNWIND_INFO(0) /* @@ -1598,8 +1572,8 @@ sys_call_table: data8 sys_readlinkat data8 sys_fchmodat data8 sys_faccessat - data8 sys_ni_syscall // reserved for pselect - data8 sys_ni_syscall // 1295 reserved for ppoll + data8 sys_pselect6 + data8 sys_ppoll data8 sys_unshare data8 sys_splice data8 sys_set_robust_list diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index 93d9ab14ba24..37f46527d233 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -1012,7 +1012,7 @@ iosapic_register_platform_intr (u32 int_type, unsigned int gsi, /* * ACPI calls this when it finds an entry for a legacy ISA IRQ override. */ -void __init +void __devinit iosapic_override_isa_irq (unsigned int isa_irq, unsigned int gsi, unsigned long polarity, unsigned long trigger) diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index 1c5044a80958..dce5341303de 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -38,6 +38,7 @@ #include #include #include +#include #ifdef CONFIG_PERFMON # include @@ -126,8 +127,10 @@ void destroy_irq(unsigned int irq) #ifdef CONFIG_SMP # define IS_RESCHEDULE(vec) (vec == IA64_IPI_RESCHEDULE) +# define IS_LOCAL_TLB_FLUSH(vec) (vec == IA64_IPI_LOCAL_TLB_FLUSH) #else # define IS_RESCHEDULE(vec) (0) +# define IS_LOCAL_TLB_FLUSH(vec) (0) #endif /* * That's where the IVT branches when we get an external @@ -179,8 +182,11 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs) saved_tpr = ia64_getreg(_IA64_REG_CR_TPR); ia64_srlz_d(); while (vector != IA64_SPURIOUS_INT_VECTOR) { - if (unlikely(IS_RESCHEDULE(vector))) - kstat_this_cpu.irqs[vector]++; + if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) { + smp_local_flush_tlb(); + kstat_this_cpu.irqs[vector]++; + } else if (unlikely(IS_RESCHEDULE(vector))) + kstat_this_cpu.irqs[vector]++; else { ia64_setreg(_IA64_REG_CR_TPR, vector); ia64_srlz_d(); @@ -226,8 +232,11 @@ void ia64_process_pending_intr(void) * Perform normal interrupt style processing */ while (vector != IA64_SPURIOUS_INT_VECTOR) { - if (unlikely(IS_RESCHEDULE(vector))) - kstat_this_cpu.irqs[vector]++; + if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) { + smp_local_flush_tlb(); + kstat_this_cpu.irqs[vector]++; + } else if (unlikely(IS_RESCHEDULE(vector))) + kstat_this_cpu.irqs[vector]++; else { struct pt_regs *old_regs = set_irq_regs(NULL); @@ -259,12 +268,12 @@ void ia64_process_pending_intr(void) #ifdef CONFIG_SMP -extern irqreturn_t handle_IPI (int irq, void *dev_id); static irqreturn_t dummy_handler (int irq, void *dev_id) { BUG(); } +extern irqreturn_t handle_IPI (int irq, void *dev_id); static struct irqaction ipi_irqaction = { .handler = handle_IPI, @@ -277,6 +286,13 @@ static struct irqaction resched_irqaction = { .flags = IRQF_DISABLED, .name = "resched" }; + +static struct irqaction tlb_irqaction = { + .handler = dummy_handler, + .flags = SA_INTERRUPT, + .name = "tlb_flush" +}; + #endif void @@ -302,6 +318,7 @@ init_IRQ (void) #ifdef CONFIG_SMP register_percpu_irq(IA64_IPI_VECTOR, &ipi_irqaction); register_percpu_irq(IA64_IPI_RESCHEDULE, &resched_irqaction); + register_percpu_irq(IA64_IPI_LOCAL_TLB_FLUSH, &tlb_irqaction); #endif #ifdef CONFIG_PERFMON pfm_init_percpu(); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 8bb571a8a738..d1c3ed9943e5 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -155,7 +155,7 @@ show_regs (struct pt_regs *regs) } void -do_notify_resume_user (sigset_t *oldset, struct sigscratch *scr, long in_syscall) +do_notify_resume_user (sigset_t *unused, struct sigscratch *scr, long in_syscall) { if (fsys_mode(current, &scr->pt)) { /* defer signal-handling etc. until we return to privilege-level 0. */ @@ -170,8 +170,8 @@ do_notify_resume_user (sigset_t *oldset, struct sigscratch *scr, long in_syscall #endif /* deal with pending signal delivery */ - if (test_thread_flag(TIF_SIGPENDING)) - ia64_do_signal(oldset, scr, in_syscall); + if (test_thread_flag(TIF_SIGPENDING)||test_thread_flag(TIF_RESTORE_SIGMASK)) + ia64_do_signal(scr, in_syscall); } static int pal_halt = 1; @@ -236,6 +236,7 @@ void cpu_idle_wait(void) { unsigned int cpu, this_cpu = get_cpu(); cpumask_t map; + cpumask_t tmp = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); put_cpu(); @@ -257,6 +258,7 @@ void cpu_idle_wait(void) } cpus_and(map, map, cpu_online_map); } while (!cpus_empty(map)); + set_cpus_allowed(current, tmp); } EXPORT_SYMBOL_GPL(cpu_idle_wait); diff --git a/arch/ia64/kernel/relocate_kernel.S b/arch/ia64/kernel/relocate_kernel.S index ae473e3f2a0d..903babd22d62 100644 --- a/arch/ia64/kernel/relocate_kernel.S +++ b/arch/ia64/kernel/relocate_kernel.S @@ -94,7 +94,7 @@ GLOBAL_ENTRY(relocate_new_kernel) 4: srlz.i ;; - //purge TR entry for kernel text and data + // purge TR entry for kernel text and data movl r16=KERNEL_START mov r18=KERNEL_TR_PAGE_SHIFT<<2 ;; @@ -104,15 +104,6 @@ GLOBAL_ENTRY(relocate_new_kernel) srlz.i ;; - // purge TR entry for percpu data - movl r16=PERCPU_ADDR - mov r18=PERCPU_PAGE_SHIFT<<2 - ;; - ptr.d r16,r18 - ;; - srlz.d - ;; - // purge TR entry for pal code mov r16=in3 mov r18=IA64_GRANULE_SHIFT<<2 diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 6e19da122ae3..9df1efe7487d 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -786,7 +786,7 @@ identify_cpu (struct cpuinfo_ia64 *c) c->unimpl_pa_mask = ~((1L<<63) | ((1L << phys_addr_size) - 1)); } -void +void __init setup_per_cpu_areas (void) { /* start_kernel() requires this... */ diff --git a/arch/ia64/kernel/sigframe.h b/arch/ia64/kernel/sigframe.h index 37b986cb86e0..9fd9a1933b3d 100644 --- a/arch/ia64/kernel/sigframe.h +++ b/arch/ia64/kernel/sigframe.h @@ -22,4 +22,4 @@ struct sigframe { struct sigcontext sc; }; -extern long ia64_do_signal (sigset_t *, struct sigscratch *, long); +extern void ia64_do_signal (struct sigscratch *, long); diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index 0dcd56da6001..aeec8184e862 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -40,47 +40,6 @@ # define GET_SIGSET(k,u) __get_user((k)->sig[0], &(u)->sig[0]) #endif -long -ia64_rt_sigsuspend (sigset_t __user *uset, size_t sigsetsize, struct sigscratch *scr) -{ - sigset_t oldset, set; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - - if (!access_ok(VERIFY_READ, uset, sigsetsize)) - return -EFAULT; - - if (GET_SIGSET(&set, uset)) - return -EFAULT; - - sigdelsetmask(&set, ~_BLOCKABLE); - - spin_lock_irq(¤t->sighand->siglock); - { - oldset = current->blocked; - current->blocked = set; - recalc_sigpending(); - } - spin_unlock_irq(¤t->sighand->siglock); - - /* - * The return below usually returns to the signal handler. We need to - * pre-set the correct error code here to ensure that the right values - * get saved in sigcontext by ia64_do_signal. - */ - scr->pt.r8 = EINTR; - scr->pt.r10 = -1; - - while (1) { - current->state = TASK_INTERRUPTIBLE; - schedule(); - if (ia64_do_signal(&oldset, scr, 1)) - return -EINTR; - } -} - asmlinkage long sys_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, long arg2, long arg3, long arg4, long arg5, long arg6, long arg7, @@ -477,10 +436,11 @@ handle_signal (unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigse * Note that `init' is a special process: it doesn't get signals it doesn't want to * handle. Thus you cannot kill init even with a SIGKILL even by mistake. */ -long -ia64_do_signal (sigset_t *oldset, struct sigscratch *scr, long in_syscall) +void +ia64_do_signal (struct sigscratch *scr, long in_syscall) { struct k_sigaction ka; + sigset_t *oldset; siginfo_t info; long restart = in_syscall; long errno = scr->pt.r8; @@ -492,9 +452,11 @@ ia64_do_signal (sigset_t *oldset, struct sigscratch *scr, long in_syscall) * doing anything if so. */ if (!user_mode(&scr->pt)) - return 0; + return; - if (!oldset) + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + oldset = ¤t->saved_sigmask; + else oldset = ¤t->blocked; /* @@ -557,8 +519,15 @@ ia64_do_signal (sigset_t *oldset, struct sigscratch *scr, long in_syscall) * Whee! Actually deliver the signal. If the delivery failed, we need to * continue to iterate in this loop so we can deliver the SIGSEGV... */ - if (handle_signal(signr, &ka, &info, oldset, scr)) - return 1; + if (handle_signal(signr, &ka, &info, oldset, scr)) { + /* a signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TIF_RESTORE_SIGMASK flag */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + clear_thread_flag(TIF_RESTORE_SIGMASK); + return; + } } /* Did we come from a system call? */ @@ -584,5 +553,11 @@ ia64_do_signal (sigset_t *oldset, struct sigscratch *scr, long in_syscall) } } } - return 0; + + /* if there's no signal to deliver, we just put the saved sigmask + * back */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) { + clear_thread_flag(TIF_RESTORE_SIGMASK); + sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + } } diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c index 55ddd809b02d..221de3804560 100644 --- a/arch/ia64/kernel/smp.c +++ b/arch/ia64/kernel/smp.c @@ -49,6 +49,18 @@ #include #include +/* + * Note: alignment of 4 entries/cacheline was empirically determined + * to be a good tradeoff between hot cachelines & spreading the array + * across too many cacheline. + */ +static struct local_tlb_flush_counts { + unsigned int count; +} __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS]; + +static DEFINE_PER_CPU(unsigned int, shadow_flush_counts[NR_CPUS]) ____cacheline_aligned; + + /* * Structure and data for smp_call_function(). This is designed to minimise static memory * requirements. It also looks cleaner. @@ -248,6 +260,62 @@ smp_send_reschedule (int cpu) platform_send_ipi(cpu, IA64_IPI_RESCHEDULE, IA64_IPI_DM_INT, 0); } +/* + * Called with preeemption disabled. + */ +static void +smp_send_local_flush_tlb (int cpu) +{ + platform_send_ipi(cpu, IA64_IPI_LOCAL_TLB_FLUSH, IA64_IPI_DM_INT, 0); +} + +void +smp_local_flush_tlb(void) +{ + /* + * Use atomic ops. Otherwise, the load/increment/store sequence from + * a "++" operation can have the line stolen between the load & store. + * The overhead of the atomic op in negligible in this case & offers + * significant benefit for the brief periods where lots of cpus + * are simultaneously flushing TLBs. + */ + ia64_fetchadd(1, &local_tlb_flush_counts[smp_processor_id()].count, acq); + local_flush_tlb_all(); +} + +#define FLUSH_DELAY 5 /* Usec backoff to eliminate excessive cacheline bouncing */ + +void +smp_flush_tlb_cpumask(cpumask_t xcpumask) +{ + unsigned int *counts = __ia64_per_cpu_var(shadow_flush_counts); + cpumask_t cpumask = xcpumask; + int mycpu, cpu, flush_mycpu = 0; + + preempt_disable(); + mycpu = smp_processor_id(); + + for_each_cpu_mask(cpu, cpumask) + counts[cpu] = local_tlb_flush_counts[cpu].count; + + mb(); + for_each_cpu_mask(cpu, cpumask) { + if (cpu == mycpu) + flush_mycpu = 1; + else + smp_send_local_flush_tlb(cpu); + } + + if (flush_mycpu) + smp_local_flush_tlb(); + + for_each_cpu_mask(cpu, cpumask) + while(counts[cpu] == local_tlb_flush_counts[cpu].count) + udelay(FLUSH_DELAY); + + preempt_enable(); +} + void smp_flush_tlb_all (void) { diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index 5bfb8be02b70..b8e0d70bf989 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -43,9 +43,9 @@ die (const char *str, struct pt_regs *regs, long err) u32 lock_owner; int lock_owner_depth; } die = { - .lock = SPIN_LOCK_UNLOCKED, - .lock_owner = -1, - .lock_owner_depth = 0 + .lock = __SPIN_LOCK_UNLOCKED(die.lock), + .lock_owner = -1, + .lock_owner_depth = 0 }; static int die_counter; int cpu = get_cpu(); diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index 93d5a3b41f69..fe1426266b9b 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -60,6 +60,7 @@ # define UNW_DEBUG_ON(n) unw_debug_level >= n /* Do not code a printk level, not all debug lines end in newline */ # define UNW_DPRINT(n, ...) if (UNW_DEBUG_ON(n)) printk(__VA_ARGS__) +# undef inline # define inline #else /* !UNW_DEBUG */ # define UNW_DEBUG_ON(n) 0 @@ -145,7 +146,7 @@ static struct { # endif } unw = { .tables = &unw.kernel_table, - .lock = SPIN_LOCK_UNLOCKED, + .lock = __SPIN_LOCK_UNLOCKED(unw.lock), .save_order = { UNW_REG_RP, UNW_REG_PFS, UNW_REG_PSP, UNW_REG_PR, UNW_REG_UNAT, UNW_REG_LC, UNW_REG_FPSR, UNW_REG_PRI_UNAT_GR @@ -1943,9 +1944,9 @@ EXPORT_SYMBOL(unw_unwind); int unw_unwind_to_user (struct unw_frame_info *info) { - unsigned long ip, sp, pr = 0; + unsigned long ip, sp, pr = info->pr; - while (unw_unwind(info) >= 0) { + do { unw_get_sp(info, &sp); if ((long)((unsigned long)info->task + IA64_STK_OFFSET - sp) < IA64_PT_REGS_SIZE) { @@ -1963,7 +1964,7 @@ unw_unwind_to_user (struct unw_frame_info *info) __FUNCTION__, ip); return -1; } - } + } while (unw_unwind(info) >= 0); unw_get_ip(info, &ip); UNW_DPRINT(0, "unwind.%s: failed to unwind to user-level (ip=0x%lx)\n", __FUNCTION__, ip); diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index ffad7624436c..fa4e6d4810f3 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -32,9 +32,9 @@ static struct { } purge; struct ia64_ctx ia64_ctx = { - .lock = SPIN_LOCK_UNLOCKED, - .next = 1, - .max_ctx = ~0U + .lock = __SPIN_LOCK_UNLOCKED(ia64_ctx.lock), + .next = 1, + .max_ctx = ~0U }; DEFINE_PER_CPU(u8, ia64_need_tlb_flush); diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c index 8d2a1bfbfe7c..7f6d2360a262 100644 --- a/arch/ia64/sn/kernel/irq.c +++ b/arch/ia64/sn/kernel/irq.c @@ -59,6 +59,22 @@ void sn_intr_free(nasid_t local_nasid, int local_widget, (u64) sn_irq_info->irq_cookie, 0, 0); } +u64 sn_intr_redirect(nasid_t local_nasid, int local_widget, + struct sn_irq_info *sn_irq_info, + nasid_t req_nasid, int req_slice) +{ + struct ia64_sal_retval ret_stuff; + ret_stuff.status = 0; + ret_stuff.v0 = 0; + + SAL_CALL_NOLOCK(ret_stuff, (u64) SN_SAL_IOIF_INTERRUPT, + (u64) SAL_INTR_REDIRECT, (u64) local_nasid, + (u64) local_widget, __pa(sn_irq_info), + (u64) req_nasid, (u64) req_slice, 0); + + return ret_stuff.status; +} + static unsigned int sn_startup_irq(unsigned int irq) { return 0; @@ -127,15 +143,8 @@ struct sn_irq_info *sn_retarget_vector(struct sn_irq_info *sn_irq_info, struct sn_irq_info *new_irq_info; struct sn_pcibus_provider *pci_provider; - new_irq_info = kmalloc(sizeof(struct sn_irq_info), GFP_ATOMIC); - if (new_irq_info == NULL) - return NULL; - - memcpy(new_irq_info, sn_irq_info, sizeof(struct sn_irq_info)); - - bridge = (u64) new_irq_info->irq_bridge; + bridge = (u64) sn_irq_info->irq_bridge; if (!bridge) { - kfree(new_irq_info); return NULL; /* irq is not a device interrupt */ } @@ -145,8 +154,25 @@ struct sn_irq_info *sn_retarget_vector(struct sn_irq_info *sn_irq_info, local_widget = TIO_SWIN_WIDGETNUM(bridge); else local_widget = SWIN_WIDGETNUM(bridge); - vector = sn_irq_info->irq_irq; + + /* Make use of SAL_INTR_REDIRECT if PROM supports it */ + status = sn_intr_redirect(local_nasid, local_widget, sn_irq_info, nasid, slice); + if (!status) { + new_irq_info = sn_irq_info; + goto finish_up; + } + + /* + * PROM does not support SAL_INTR_REDIRECT, or it failed. + * Revert to old method. + */ + new_irq_info = kmalloc(sizeof(struct sn_irq_info), GFP_ATOMIC); + if (new_irq_info == NULL) + return NULL; + + memcpy(new_irq_info, sn_irq_info, sizeof(struct sn_irq_info)); + /* Free the old PROM new_irq_info structure */ sn_intr_free(local_nasid, local_widget, new_irq_info); unregister_intr_pda(new_irq_info); @@ -162,11 +188,18 @@ struct sn_irq_info *sn_retarget_vector(struct sn_irq_info *sn_irq_info, return NULL; } + register_intr_pda(new_irq_info); + spin_lock(&sn_irq_info_lock); + list_replace_rcu(&sn_irq_info->list, &new_irq_info->list); + spin_unlock(&sn_irq_info_lock); + call_rcu(&sn_irq_info->rcu, sn_irq_info_free); + + +finish_up: /* Update kernels new_irq_info with new target info */ cpuid = nasid_slice_to_cpuid(new_irq_info->irq_nasid, new_irq_info->irq_slice); new_irq_info->irq_cpuid = cpuid; - register_intr_pda(new_irq_info); pci_provider = sn_pci_provider[new_irq_info->irq_bridge_type]; @@ -178,11 +211,6 @@ struct sn_irq_info *sn_retarget_vector(struct sn_irq_info *sn_irq_info, pci_provider && pci_provider->target_interrupt) (pci_provider->target_interrupt)(new_irq_info); - spin_lock(&sn_irq_info_lock); - list_replace_rcu(&sn_irq_info->list, &new_irq_info->list); - spin_unlock(&sn_irq_info_lock); - call_rcu(&sn_irq_info->rcu, sn_irq_info_free); - #ifdef CONFIG_SMP cpuphys = cpu_physical_id(cpuid); set_irq_affinity_info((vector & 0xff), cpuphys, 0); diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c index 601747b1e22a..5d318b579fb1 100644 --- a/arch/ia64/sn/kernel/sn2/sn2_smp.c +++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c @@ -46,6 +46,9 @@ DECLARE_PER_CPU(struct ptc_stats, ptcstats); static __cacheline_aligned DEFINE_SPINLOCK(sn2_global_ptc_lock); +/* 0 = old algorithm (no IPI flushes), 1 = ipi deadlock flush, 2 = ipi instead of SHUB ptc, >2 = always ipi */ +static int sn2_flush_opt = 0; + extern unsigned long sn2_ptc_deadlock_recovery_core(volatile unsigned long *, unsigned long, volatile unsigned long *, unsigned long, @@ -76,6 +79,8 @@ struct ptc_stats { unsigned long shub_itc_clocks; unsigned long shub_itc_clocks_max; unsigned long shub_ptc_flushes_not_my_mm; + unsigned long shub_ipi_flushes; + unsigned long shub_ipi_flushes_itc_clocks; }; #define sn2_ptctest 0 @@ -121,6 +126,18 @@ void sn_tlb_migrate_finish(struct mm_struct *mm) flush_tlb_mm(mm); } +static void +sn2_ipi_flush_all_tlb(struct mm_struct *mm) +{ + unsigned long itc; + + itc = ia64_get_itc(); + smp_flush_tlb_cpumask(mm->cpu_vm_mask); + itc = ia64_get_itc() - itc; + __get_cpu_var(ptcstats).shub_ipi_flushes_itc_clocks += itc; + __get_cpu_var(ptcstats).shub_ipi_flushes++; +} + /** * sn2_global_tlb_purge - globally purge translation cache of virtual address range * @mm: mm_struct containing virtual address range @@ -154,7 +171,12 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start, unsigned long itc, itc2, flags, data0 = 0, data1 = 0, rr_value, old_rr = 0; short nasids[MAX_NUMNODES], nix; nodemask_t nodes_flushed; - int active, max_active, deadlock; + int active, max_active, deadlock, flush_opt = sn2_flush_opt; + + if (flush_opt > 2) { + sn2_ipi_flush_all_tlb(mm); + return; + } nodes_clear(nodes_flushed); i = 0; @@ -189,6 +211,12 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start, return; } + if (flush_opt == 2) { + sn2_ipi_flush_all_tlb(mm); + preempt_enable(); + return; + } + itc = ia64_get_itc(); nix = 0; for_each_node_mask(cnode, nodes_flushed) @@ -256,6 +284,8 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start, } if (active >= max_active || i == (nix - 1)) { if ((deadlock = wait_piowc())) { + if (flush_opt == 1) + goto done; sn2_ptc_deadlock_recovery(nasids, ibegin, i, mynasid, ptc0, data0, ptc1, data1); if (reset_max_active_on_deadlock()) max_active = 1; @@ -267,6 +297,7 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start, start += (1UL << nbits); } while (start < end); +done: itc2 = ia64_get_itc() - itc2; __get_cpu_var(ptcstats).shub_itc_clocks += itc2; if (itc2 > __get_cpu_var(ptcstats).shub_itc_clocks_max) @@ -279,6 +310,11 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start, spin_unlock_irqrestore(PTC_LOCK(shub1), flags); + if (flush_opt == 1 && deadlock) { + __get_cpu_var(ptcstats).deadlocks++; + sn2_ipi_flush_all_tlb(mm); + } + preempt_enable(); } @@ -425,24 +461,42 @@ static int sn2_ptc_seq_show(struct seq_file *file, void *data) if (!cpu) { seq_printf(file, - "# cpu ptc_l newrid ptc_flushes nodes_flushed deadlocks lock_nsec shub_nsec shub_nsec_max not_my_mm deadlock2\n"); - seq_printf(file, "# ptctest %d\n", sn2_ptctest); + "# cpu ptc_l newrid ptc_flushes nodes_flushed deadlocks lock_nsec shub_nsec shub_nsec_max not_my_mm deadlock2 ipi_fluches ipi_nsec\n"); + seq_printf(file, "# ptctest %d, flushopt %d\n", sn2_ptctest, sn2_flush_opt); } if (cpu < NR_CPUS && cpu_online(cpu)) { stat = &per_cpu(ptcstats, cpu); - seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", cpu, stat->ptc_l, + seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", cpu, stat->ptc_l, stat->change_rid, stat->shub_ptc_flushes, stat->nodes_flushed, stat->deadlocks, 1000 * stat->lock_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec, 1000 * stat->shub_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec, 1000 * stat->shub_itc_clocks_max / per_cpu(cpu_info, cpu).cyc_per_usec, stat->shub_ptc_flushes_not_my_mm, - stat->deadlocks2); + stat->deadlocks2, + stat->shub_ipi_flushes, + 1000 * stat->shub_ipi_flushes_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec); } return 0; } +static ssize_t sn2_ptc_proc_write(struct file *file, const char __user *user, size_t count, loff_t *data) +{ + int cpu; + char optstr[64]; + + if (copy_from_user(optstr, user, count)) + return -EFAULT; + optstr[count - 1] = '\0'; + sn2_flush_opt = simple_strtoul(optstr, NULL, 0); + + for_each_online_cpu(cpu) + memset(&per_cpu(ptcstats, cpu), 0, sizeof(struct ptc_stats)); + + return count; +} + static struct seq_operations sn2_ptc_seq_ops = { .start = sn2_ptc_seq_start, .next = sn2_ptc_seq_next, @@ -458,6 +512,7 @@ static int sn2_ptc_proc_open(struct inode *inode, struct file *file) static const struct file_operations proc_sn2_ptc_operations = { .open = sn2_ptc_proc_open, .read = seq_read, + .write = sn2_ptc_proc_write, .llseek = seq_lseek, .release = seq_release, }; diff --git a/drivers/char/mmtimer.c b/drivers/char/mmtimer.c index c09160383a53..6e55cfb9c65a 100644 --- a/drivers/char/mmtimer.c +++ b/drivers/char/mmtimer.c @@ -705,15 +705,13 @@ static int __init mmtimer_init(void) maxn++; /* Allocate list of node ptrs to mmtimer_t's */ - timers = kmalloc(sizeof(mmtimer_t *)*maxn, GFP_KERNEL); + timers = kzalloc(sizeof(mmtimer_t *)*maxn, GFP_KERNEL); if (timers == NULL) { printk(KERN_ERR "%s: failed to allocate memory for device\n", MMTIMER_NAME); goto out3; } - memset(timers,0,(sizeof(mmtimer_t *)*maxn)); - /* Allocate mmtimer_t's for each online node */ for_each_online_node(node) { timers[node] = kmalloc_node(sizeof(mmtimer_t)*NUM_COMPARATORS, GFP_KERNEL, node); diff --git a/include/asm-ia64/hw_irq.h b/include/asm-ia64/hw_irq.h index 27f9df6b9145..c054d7a9aaa7 100644 --- a/include/asm-ia64/hw_irq.h +++ b/include/asm-ia64/hw_irq.h @@ -66,6 +66,7 @@ extern int ia64_last_device_vector; #define IA64_PERFMON_VECTOR 0xee /* performanc monitor interrupt vector */ #define IA64_TIMER_VECTOR 0xef /* use highest-prio group 15 interrupt for timer */ #define IA64_MCA_WAKEUP_VECTOR 0xf0 /* MCA wakeup (must be >MCA_RENDEZ_VECTOR) */ +#define IA64_IPI_LOCAL_TLB_FLUSH 0xfc /* SMP flush local TLB */ #define IA64_IPI_RESCHEDULE 0xfd /* SMP reschedule */ #define IA64_IPI_VECTOR 0xfe /* inter-processor interrupt vector */ diff --git a/include/asm-ia64/iosapic.h b/include/asm-ia64/iosapic.h index 20f98f1751a1..421cb6b62a7c 100644 --- a/include/asm-ia64/iosapic.h +++ b/include/asm-ia64/iosapic.h @@ -83,7 +83,7 @@ extern int gsi_to_irq (unsigned int gsi); extern int iosapic_register_intr (unsigned int gsi, unsigned long polarity, unsigned long trigger); extern void iosapic_unregister_intr (unsigned int irq); -extern void __init iosapic_override_isa_irq (unsigned int isa_irq, unsigned int gsi, +extern void __devinit iosapic_override_isa_irq (unsigned int isa_irq, unsigned int gsi, unsigned long polarity, unsigned long trigger); extern int __init iosapic_register_platform_intr (u32 int_type, diff --git a/include/asm-ia64/sn/sn_sal.h b/include/asm-ia64/sn/sn_sal.h index 2c4004eb5a68..291e8ceed6e6 100644 --- a/include/asm-ia64/sn/sn_sal.h +++ b/include/asm-ia64/sn/sn_sal.h @@ -106,6 +106,7 @@ /* interrupt handling */ #define SAL_INTR_ALLOC 1 #define SAL_INTR_FREE 2 +#define SAL_INTR_REDIRECT 3 /* * operations available on the generic SN_SAL_SYSCTL_OP diff --git a/include/asm-ia64/thread_info.h b/include/asm-ia64/thread_info.h index d28147506585..7d0241db622b 100644 --- a/include/asm-ia64/thread_info.h +++ b/include/asm-ia64/thread_info.h @@ -85,6 +85,7 @@ struct thread_info { #define TIF_SYSCALL_TRACE 3 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 4 /* syscall auditing active */ #define TIF_SINGLESTEP 5 /* restore singlestep on return to user mode */ +#define TIF_RESTORE_SIGMASK 6 /* restore signal mask in do_signal() */ #define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_MEMDIE 17 #define TIF_MCA_INIT 18 /* this task is processing MCA or INIT */ @@ -96,6 +97,7 @@ struct thread_info { #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SYSCALL_TRACEAUDIT (_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) +#define _TIF_RESTORE_SIGMASK (1 << TIF_RESTORE_SIGMASK) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) @@ -104,7 +106,7 @@ struct thread_info { #define _TIF_FREEZE (1 << TIF_FREEZE) /* "work to do on user-return" bits */ -#define TIF_ALLWORK_MASK (_TIF_NOTIFY_RESUME|_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT) +#define TIF_ALLWORK_MASK (_TIF_NOTIFY_RESUME|_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_RESTORE_SIGMASK) /* like TIF_ALLWORK_BITS but sans TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT */ #define TIF_WORK_MASK (TIF_ALLWORK_MASK&~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT)) diff --git a/include/asm-ia64/tlbflush.h b/include/asm-ia64/tlbflush.h index cf9acb9bb1fb..e37f9fbf33af 100644 --- a/include/asm-ia64/tlbflush.h +++ b/include/asm-ia64/tlbflush.h @@ -27,9 +27,11 @@ extern void local_flush_tlb_all (void); #ifdef CONFIG_SMP extern void smp_flush_tlb_all (void); extern void smp_flush_tlb_mm (struct mm_struct *mm); + extern void smp_flush_tlb_cpumask (cpumask_t xcpumask); # define flush_tlb_all() smp_flush_tlb_all() #else # define flush_tlb_all() local_flush_tlb_all() +# define smp_flush_tlb_cpumask(m) local_flush_tlb_all() #endif static inline void @@ -94,6 +96,15 @@ flush_tlb_pgtables (struct mm_struct *mm, unsigned long start, unsigned long end */ } +/* + * Flush the local TLB. Invoked from another cpu using an IPI. + */ +#ifdef CONFIG_SMP +void smp_local_flush_tlb(void); +#else +#define smp_local_flush_tlb() +#endif + #define flush_tlb_kernel_range(start, end) flush_tlb_all() /* XXX fix me */ #endif /* _ASM_IA64_TLBFLUSH_H */ diff --git a/include/asm-ia64/unistd.h b/include/asm-ia64/unistd.h index a9e1fa4cac4d..861c8ec87b09 100644 --- a/include/asm-ia64/unistd.h +++ b/include/asm-ia64/unistd.h @@ -283,7 +283,8 @@ #define __NR_readlinkat 1291 #define __NR_fchmodat 1292 #define __NR_faccessat 1293 -/* 1294, 1295 reserved for pselect/ppoll */ +#define __NR_pselect6 1294 +#define __NR_ppoll 1295 #define __NR_unshare 1296 #define __NR_splice 1297 #define __NR_set_robust_list 1298 @@ -300,6 +301,7 @@ #define NR_syscalls 281 /* length of syscall table */ #define __ARCH_WANT_SYS_RT_SIGACTION +#define __ARCH_WANT_SYS_RT_SIGSUSPEND #ifdef CONFIG_IA32_SUPPORT # define __ARCH_WANT_SYS_FADVISE64 @@ -310,6 +312,7 @@ # define __ARCH_WANT_SYS_OLDUMOUNT # define __ARCH_WANT_SYS_SIGPENDING # define __ARCH_WANT_SYS_SIGPROCMASK +# define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND # define __ARCH_WANT_COMPAT_SYS_TIME #endif